diff --git a/.gitattributes b/.gitattributes
index 4dad65ab84b63900ed6c1615183430c6f9d4cc55..6c0e6da2e0f08602e345e9061404f6b6e07fc72f 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -42,3 +42,4 @@ cpt_qwen_14B/checkpoints/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge
 cpt_qwen_14B/checkpoints/checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 cpt_qwen_14B/checkpoints/checkpoint-656/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 cpt_qwen_14B/wandb/offline-run-20251223_125436-g6vlcw0j/run-g6vlcw0j.wandb filter=lfs diff=lfs merge=lfs -text
+sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/run-ldjr67u6.wandb filter=lfs diff=lfs merge=lfs -text
diff --git a/sft_qwen_14B/best_adapter/README.md b/sft_qwen_14B/best_adapter/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..779b6406e547b32301fef1d181301a873befe542
--- /dev/null
+++ b/sft_qwen_14B/best_adapter/README.md
@@ -0,0 +1,207 @@
+---
+base_model: runs/cpt_run_14b/merged_14b_cpt_lora
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:runs/cpt_run_14b/merged_14b_cpt_lora
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0
\ No newline at end of file
diff --git a/sft_qwen_14B/best_adapter/adapter_config.json b/sft_qwen_14B/best_adapter/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8ea271115c141fb10c6d899b06f46f21800e1ad6
--- /dev/null
+++ b/sft_qwen_14B/best_adapter/adapter_config.json
@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "runs/cpt_run_14b/merged_14b_cpt_lora",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/sft_qwen_14B/best_adapter/adapter_model.safetensors b/sft_qwen_14B/best_adapter/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b2ec2989386a7dc70e84257fe7c09f5b18e7ee8c
--- /dev/null
+++ b/sft_qwen_14B/best_adapter/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3726a3859050973f5670196544ebe752cfffa4253f1767f5b0af266df2ace6b
+size 100715016
diff --git a/sft_qwen_14B/best_adapter/training_args.bin b/sft_qwen_14B/best_adapter/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b023888140f1fb107e8d5ebbfbcb9d9558b09d43
--- /dev/null
+++ b/sft_qwen_14B/best_adapter/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4200830b23d19bc86049c280236c4a6b18c26d7061b5a57cc024888ec760920f
+size 5201
diff --git a/sft_qwen_14B/checkpoints/checkpoint-1000/README.md b/sft_qwen_14B/checkpoints/checkpoint-1000/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..779b6406e547b32301fef1d181301a873befe542
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-1000/README.md
@@ -0,0 +1,207 @@
+---
+base_model: runs/cpt_run_14b/merged_14b_cpt_lora
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:runs/cpt_run_14b/merged_14b_cpt_lora
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0
\ No newline at end of file
diff --git a/sft_qwen_14B/checkpoints/checkpoint-1000/adapter_config.json b/sft_qwen_14B/checkpoints/checkpoint-1000/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8ea271115c141fb10c6d899b06f46f21800e1ad6
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-1000/adapter_config.json
@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "runs/cpt_run_14b/merged_14b_cpt_lora",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/sft_qwen_14B/checkpoints/checkpoint-1000/adapter_model.safetensors b/sft_qwen_14B/checkpoints/checkpoint-1000/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..969eefe9ee247628cffd6acb9fd8cfd2018cfcb7
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-1000/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dee36ed11c4fd0959b1919f775473a19f346b153e63c34bcf79a533556e19e4
+size 100715016
diff --git a/sft_qwen_14B/checkpoints/checkpoint-1000/optimizer.pt b/sft_qwen_14B/checkpoints/checkpoint-1000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bc9367f0ea19443b7e2a5b03a3ef41cc6b1bd81c
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-1000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a70e161c960aa70fcafcc1f927ed2d20fab7a428206158a303bd7dde1ca82e78
+size 201650659
diff --git a/sft_qwen_14B/checkpoints/checkpoint-1000/rng_state.pth b/sft_qwen_14B/checkpoints/checkpoint-1000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..13e452bba9961730240e796c0f3963c89476a99c
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-1000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0268028a2ba7d054993db8c39cdcda05f1f60e5f99a796fc9a68ac3c248a51f
+size 14645
diff --git a/sft_qwen_14B/checkpoints/checkpoint-1000/scheduler.pt b/sft_qwen_14B/checkpoints/checkpoint-1000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b71605cea7abaeac4953eabdfca233455ad9dd46
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-1000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71bca8257f6a48d8c00a2797d198b1ab37d03a410f59b9bb8e7d7f293ee8880b
+size 1465
diff --git a/sft_qwen_14B/checkpoints/checkpoint-1000/trainer_state.json b/sft_qwen_14B/checkpoints/checkpoint-1000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..be25f1858be68f493e1403d863ba18fcfd80ea63
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-1000/trainer_state.json
@@ -0,0 +1,3623 @@
+{
+  "best_global_step": 1000,
+  "best_metric": 0.9606748819351196,
+  "best_model_checkpoint": "runs/instruct_run_14b_v1/checkpoints/checkpoint-1000",
+  "epoch": 0.43149946062567424,
+  "eval_steps": 100,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008629989212513484,
+      "grad_norm": 0.36567428708076477,
+      "learning_rate": 1.7969451931716084e-07,
+      "loss": 1.6794371604919434,
+      "step": 2
+    },
+    {
+      "epoch": 0.001725997842502697,
+      "grad_norm": 0.4024646580219269,
+      "learning_rate": 5.390835579514825e-07,
+      "loss": 1.6853073835372925,
+      "step": 4
+    },
+    {
+      "epoch": 0.0025889967637540453,
+      "grad_norm": 0.40199393033981323,
+      "learning_rate": 8.984725965858042e-07,
+      "loss": 1.7621158361434937,
+      "step": 6
+    },
+    {
+      "epoch": 0.003451995685005394,
+      "grad_norm": 0.35409677028656006,
+      "learning_rate": 1.257861635220126e-06,
+      "loss": 1.633257269859314,
+      "step": 8
+    },
+    {
+      "epoch": 0.004314994606256742,
+      "grad_norm": 0.39087551832199097,
+      "learning_rate": 1.6172506738544475e-06,
+      "loss": 1.7374768257141113,
+      "step": 10
+    },
+    {
+      "epoch": 0.005177993527508091,
+      "grad_norm": 0.3586857318878174,
+      "learning_rate": 1.9766397124887693e-06,
+      "loss": 1.6955714225769043,
+      "step": 12
+    },
+    {
+      "epoch": 0.006040992448759439,
+      "grad_norm": 0.32755669951438904,
+      "learning_rate": 2.3360287511230908e-06,
+      "loss": 1.720664381980896,
+      "step": 14
+    },
+    {
+      "epoch": 0.006903991370010788,
+      "grad_norm": 0.4054872691631317,
+      "learning_rate": 2.6954177897574127e-06,
+      "loss": 1.6957035064697266,
+      "step": 16
+    },
+    {
+      "epoch": 0.007766990291262136,
+      "grad_norm": 0.37593814730644226,
+      "learning_rate": 3.0548068283917343e-06,
+      "loss": 1.7286947965621948,
+      "step": 18
+    },
+    {
+      "epoch": 0.008629989212513484,
+      "grad_norm": 0.3344813287258148,
+      "learning_rate": 3.414195867026056e-06,
+      "loss": 1.727295994758606,
+      "step": 20
+    },
+    {
+      "epoch": 0.009492988133764833,
+      "grad_norm": 0.357474148273468,
+      "learning_rate": 3.7735849056603773e-06,
+      "loss": 1.6727914810180664,
+      "step": 22
+    },
+    {
+      "epoch": 0.010355987055016181,
+      "grad_norm": 0.39115726947784424,
+      "learning_rate": 4.132973944294699e-06,
+      "loss": 1.6518884897232056,
+      "step": 24
+    },
+    {
+      "epoch": 0.01121898597626753,
+      "grad_norm": 0.4711727201938629,
+      "learning_rate": 4.492362982929021e-06,
+      "loss": 1.7868088483810425,
+      "step": 26
+    },
+    {
+      "epoch": 0.012081984897518877,
+      "grad_norm": 0.34112176299095154,
+      "learning_rate": 4.851752021563342e-06,
+      "loss": 1.6127634048461914,
+      "step": 28
+    },
+    {
+      "epoch": 0.012944983818770227,
+      "grad_norm": 0.5071991682052612,
+      "learning_rate": 5.211141060197664e-06,
+      "loss": 1.7858378887176514,
+      "step": 30
+    },
+    {
+      "epoch": 0.013807982740021575,
+      "grad_norm": 0.42048847675323486,
+      "learning_rate": 5.570530098831986e-06,
+      "loss": 1.7123326063156128,
+      "step": 32
+    },
+    {
+      "epoch": 0.014670981661272923,
+      "grad_norm": 0.48883870244026184,
+      "learning_rate": 5.929919137466308e-06,
+      "loss": 1.737749695777893,
+      "step": 34
+    },
+    {
+      "epoch": 0.015533980582524271,
+      "grad_norm": 0.3311465084552765,
+      "learning_rate": 6.289308176100629e-06,
+      "loss": 1.5578981637954712,
+      "step": 36
+    },
+    {
+      "epoch": 0.01639697950377562,
+      "grad_norm": 0.5178973078727722,
+      "learning_rate": 6.64869721473495e-06,
+      "loss": 1.719806432723999,
+      "step": 38
+    },
+    {
+      "epoch": 0.017259978425026967,
+      "grad_norm": 0.47097742557525635,
+      "learning_rate": 7.008086253369272e-06,
+      "loss": 1.728212833404541,
+      "step": 40
+    },
+    {
+      "epoch": 0.018122977346278317,
+      "grad_norm": 0.5051584243774414,
+      "learning_rate": 7.367475292003594e-06,
+      "loss": 1.6542466878890991,
+      "step": 42
+    },
+    {
+      "epoch": 0.018985976267529667,
+      "grad_norm": 0.4645111560821533,
+      "learning_rate": 7.726864330637915e-06,
+      "loss": 1.7087690830230713,
+      "step": 44
+    },
+    {
+      "epoch": 0.019848975188781013,
+      "grad_norm": 0.5184999704360962,
+      "learning_rate": 8.086253369272237e-06,
+      "loss": 1.7018946409225464,
+      "step": 46
+    },
+    {
+      "epoch": 0.020711974110032363,
+      "grad_norm": 0.4543815851211548,
+      "learning_rate": 8.44564240790656e-06,
+      "loss": 1.6818269491195679,
+      "step": 48
+    },
+    {
+      "epoch": 0.021574973031283712,
+      "grad_norm": 0.44411996006965637,
+      "learning_rate": 8.80503144654088e-06,
+      "loss": 1.5772877931594849,
+      "step": 50
+    },
+    {
+      "epoch": 0.02243797195253506,
+      "grad_norm": 0.3409404158592224,
+      "learning_rate": 9.164420485175203e-06,
+      "loss": 1.498152732849121,
+      "step": 52
+    },
+    {
+      "epoch": 0.02330097087378641,
+      "grad_norm": 0.42104434967041016,
+      "learning_rate": 9.523809523809523e-06,
+      "loss": 1.6189048290252686,
+      "step": 54
+    },
+    {
+      "epoch": 0.024163969795037755,
+      "grad_norm": 0.3756246268749237,
+      "learning_rate": 9.883198562443846e-06,
+      "loss": 1.4596441984176636,
+      "step": 56
+    },
+    {
+      "epoch": 0.025026968716289105,
+      "grad_norm": 0.36214128136634827,
+      "learning_rate": 1.0242587601078168e-05,
+      "loss": 1.503880500793457,
+      "step": 58
+    },
+    {
+      "epoch": 0.025889967637540454,
+      "grad_norm": 0.40893009305000305,
+      "learning_rate": 1.060197663971249e-05,
+      "loss": 1.5912823677062988,
+      "step": 60
+    },
+    {
+      "epoch": 0.0267529665587918,
+      "grad_norm": 0.28710272908210754,
+      "learning_rate": 1.0961365678346811e-05,
+      "loss": 1.2956721782684326,
+      "step": 62
+    },
+    {
+      "epoch": 0.02761596548004315,
+      "grad_norm": 0.304573118686676,
+      "learning_rate": 1.1320754716981132e-05,
+      "loss": 1.4648056030273438,
+      "step": 64
+    },
+    {
+      "epoch": 0.0284789644012945,
+      "grad_norm": 0.36523914337158203,
+      "learning_rate": 1.1680143755615454e-05,
+      "loss": 1.6078968048095703,
+      "step": 66
+    },
+    {
+      "epoch": 0.029341963322545846,
+      "grad_norm": 0.37929031252861023,
+      "learning_rate": 1.2039532794249775e-05,
+      "loss": 1.5969421863555908,
+      "step": 68
+    },
+    {
+      "epoch": 0.030204962243797196,
+      "grad_norm": 0.3053947389125824,
+      "learning_rate": 1.2398921832884097e-05,
+      "loss": 1.4312325716018677,
+      "step": 70
+    },
+    {
+      "epoch": 0.031067961165048542,
+      "grad_norm": 0.3028779923915863,
+      "learning_rate": 1.275831087151842e-05,
+      "loss": 1.4101300239562988,
+      "step": 72
+    },
+    {
+      "epoch": 0.03193096008629989,
+      "grad_norm": 0.29649803042411804,
+      "learning_rate": 1.3117699910152742e-05,
+      "loss": 1.4553817510604858,
+      "step": 74
+    },
+    {
+      "epoch": 0.03279395900755124,
+      "grad_norm": 0.26032644510269165,
+      "learning_rate": 1.3477088948787062e-05,
+      "loss": 1.4623000621795654,
+      "step": 76
+    },
+    {
+      "epoch": 0.03365695792880259,
+      "grad_norm": 0.33558446168899536,
+      "learning_rate": 1.3836477987421385e-05,
+      "loss": 1.5181745290756226,
+      "step": 78
+    },
+    {
+      "epoch": 0.034519956850053934,
+      "grad_norm": 0.28307804465293884,
+      "learning_rate": 1.4195867026055706e-05,
+      "loss": 1.4397861957550049,
+      "step": 80
+    },
+    {
+      "epoch": 0.035382955771305284,
+      "grad_norm": 0.3451690673828125,
+      "learning_rate": 1.455525606469003e-05,
+      "loss": 1.463841199874878,
+      "step": 82
+    },
+    {
+      "epoch": 0.036245954692556634,
+      "grad_norm": 0.3248669505119324,
+      "learning_rate": 1.4914645103324348e-05,
+      "loss": 1.3554227352142334,
+      "step": 84
+    },
+    {
+      "epoch": 0.037108953613807984,
+      "grad_norm": 0.2855011224746704,
+      "learning_rate": 1.527403414195867e-05,
+      "loss": 1.2810425758361816,
+      "step": 86
+    },
+    {
+      "epoch": 0.03797195253505933,
+      "grad_norm": 0.33365535736083984,
+      "learning_rate": 1.5633423180592992e-05,
+      "loss": 1.428163766860962,
+      "step": 88
+    },
+    {
+      "epoch": 0.038834951456310676,
+      "grad_norm": 0.34099438786506653,
+      "learning_rate": 1.5992812219227316e-05,
+      "loss": 1.3487578630447388,
+      "step": 90
+    },
+    {
+      "epoch": 0.039697950377562026,
+      "grad_norm": 0.39247506856918335,
+      "learning_rate": 1.6352201257861635e-05,
+      "loss": 1.30057954788208,
+      "step": 92
+    },
+    {
+      "epoch": 0.040560949298813376,
+      "grad_norm": 0.32692041993141174,
+      "learning_rate": 1.671159029649596e-05,
+      "loss": 1.2923580408096313,
+      "step": 94
+    },
+    {
+      "epoch": 0.041423948220064725,
+      "grad_norm": 0.43452519178390503,
+      "learning_rate": 1.707097933513028e-05,
+      "loss": 1.5002273321151733,
+      "step": 96
+    },
+    {
+      "epoch": 0.042286947141316075,
+      "grad_norm": 0.3251534402370453,
+      "learning_rate": 1.7430368373764602e-05,
+      "loss": 1.330254077911377,
+      "step": 98
+    },
+    {
+      "epoch": 0.043149946062567425,
+      "grad_norm": 0.3198273479938507,
+      "learning_rate": 1.778975741239892e-05,
+      "loss": 1.3054943084716797,
+      "step": 100
+    },
+    {
+      "epoch": 0.043149946062567425,
+      "eval_loss": 1.366738200187683,
+      "eval_runtime": 651.8198,
+      "eval_samples_per_second": 3.16,
+      "eval_steps_per_second": 3.16,
+      "step": 100
+    },
+    {
+      "epoch": 0.04401294498381877,
+      "grad_norm": 0.37364065647125244,
+      "learning_rate": 1.8149146451033245e-05,
+      "loss": 1.314281940460205,
+      "step": 102
+    },
+    {
+      "epoch": 0.04487594390507012,
+      "grad_norm": 0.39384758472442627,
+      "learning_rate": 1.8508535489667568e-05,
+      "loss": 1.2737246751785278,
+      "step": 104
+    },
+    {
+      "epoch": 0.04573894282632147,
+      "grad_norm": 0.3521905541419983,
+      "learning_rate": 1.8867924528301888e-05,
+      "loss": 1.3113226890563965,
+      "step": 106
+    },
+    {
+      "epoch": 0.04660194174757282,
+      "grad_norm": 0.33531463146209717,
+      "learning_rate": 1.9227313566936208e-05,
+      "loss": 1.3253653049468994,
+      "step": 108
+    },
+    {
+      "epoch": 0.04746494066882417,
+      "grad_norm": 0.35596340894699097,
+      "learning_rate": 1.958670260557053e-05,
+      "loss": 1.3236849308013916,
+      "step": 110
+    },
+    {
+      "epoch": 0.04832793959007551,
+      "grad_norm": 0.36028242111206055,
+      "learning_rate": 1.9946091644204854e-05,
+      "loss": 1.183128833770752,
+      "step": 112
+    },
+    {
+      "epoch": 0.04919093851132686,
+      "grad_norm": 0.42109814286231995,
+      "learning_rate": 2.0305480682839174e-05,
+      "loss": 1.2741888761520386,
+      "step": 114
+    },
+    {
+      "epoch": 0.05005393743257821,
+      "grad_norm": 0.39675939083099365,
+      "learning_rate": 2.0664869721473494e-05,
+      "loss": 1.3050109148025513,
+      "step": 116
+    },
+    {
+      "epoch": 0.05091693635382956,
+      "grad_norm": 0.4414141774177551,
+      "learning_rate": 2.1024258760107817e-05,
+      "loss": 1.2472094297409058,
+      "step": 118
+    },
+    {
+      "epoch": 0.05177993527508091,
+      "grad_norm": 0.42872729897499084,
+      "learning_rate": 2.138364779874214e-05,
+      "loss": 1.3338921070098877,
+      "step": 120
+    },
+    {
+      "epoch": 0.05264293419633225,
+      "grad_norm": 0.38336244225502014,
+      "learning_rate": 2.174303683737646e-05,
+      "loss": 1.322908878326416,
+      "step": 122
+    },
+    {
+      "epoch": 0.0535059331175836,
+      "grad_norm": 0.41046878695487976,
+      "learning_rate": 2.2102425876010783e-05,
+      "loss": 1.2169240713119507,
+      "step": 124
+    },
+    {
+      "epoch": 0.05436893203883495,
+      "grad_norm": 0.39460113644599915,
+      "learning_rate": 2.2461814914645103e-05,
+      "loss": 1.2085309028625488,
+      "step": 126
+    },
+    {
+      "epoch": 0.0552319309600863,
+      "grad_norm": 0.42829909920692444,
+      "learning_rate": 2.2821203953279426e-05,
+      "loss": 1.2969133853912354,
+      "step": 128
+    },
+    {
+      "epoch": 0.05609492988133765,
+      "grad_norm": 0.3940851390361786,
+      "learning_rate": 2.3180592991913746e-05,
+      "loss": 1.1892330646514893,
+      "step": 130
+    },
+    {
+      "epoch": 0.056957928802589,
+      "grad_norm": 0.45011839270591736,
+      "learning_rate": 2.353998203054807e-05,
+      "loss": 1.2082979679107666,
+      "step": 132
+    },
+    {
+      "epoch": 0.05782092772384034,
+      "grad_norm": 0.46059420704841614,
+      "learning_rate": 2.3899371069182393e-05,
+      "loss": 1.2388817071914673,
+      "step": 134
+    },
+    {
+      "epoch": 0.05868392664509169,
+      "grad_norm": 0.41085872054100037,
+      "learning_rate": 2.4258760107816713e-05,
+      "loss": 1.193917155265808,
+      "step": 136
+    },
+    {
+      "epoch": 0.05954692556634304,
+      "grad_norm": 0.4024205207824707,
+      "learning_rate": 2.4618149146451032e-05,
+      "loss": 1.1514034271240234,
+      "step": 138
+    },
+    {
+      "epoch": 0.06040992448759439,
+      "grad_norm": 0.3893793523311615,
+      "learning_rate": 2.4977538185085356e-05,
+      "loss": 1.1626157760620117,
+      "step": 140
+    },
+    {
+      "epoch": 0.06127292340884574,
+      "grad_norm": 0.4456317126750946,
+      "learning_rate": 2.5336927223719675e-05,
+      "loss": 1.1627076864242554,
+      "step": 142
+    },
+    {
+      "epoch": 0.062135922330097085,
+      "grad_norm": 0.5050215125083923,
+      "learning_rate": 2.5696316262354e-05,
+      "loss": 1.3038755655288696,
+      "step": 144
+    },
+    {
+      "epoch": 0.06299892125134844,
+      "grad_norm": 0.4071207642555237,
+      "learning_rate": 2.605570530098832e-05,
+      "loss": 1.1708844900131226,
+      "step": 146
+    },
+    {
+      "epoch": 0.06386192017259978,
+      "grad_norm": 0.4363228678703308,
+      "learning_rate": 2.641509433962264e-05,
+      "loss": 1.2149070501327515,
+      "step": 148
+    },
+    {
+      "epoch": 0.06472491909385113,
+      "grad_norm": 0.4436556398868561,
+      "learning_rate": 2.6774483378256965e-05,
+      "loss": 1.1942368745803833,
+      "step": 150
+    },
+    {
+      "epoch": 0.06558791801510248,
+      "grad_norm": 0.4068629741668701,
+      "learning_rate": 2.7133872416891288e-05,
+      "loss": 1.1799161434173584,
+      "step": 152
+    },
+    {
+      "epoch": 0.06645091693635383,
+      "grad_norm": 0.5291106700897217,
+      "learning_rate": 2.7493261455525608e-05,
+      "loss": 1.1832845211029053,
+      "step": 154
+    },
+    {
+      "epoch": 0.06731391585760518,
+      "grad_norm": 0.4410109221935272,
+      "learning_rate": 2.785265049415993e-05,
+      "loss": 1.1696993112564087,
+      "step": 156
+    },
+    {
+      "epoch": 0.06817691477885653,
+      "grad_norm": 0.4858371913433075,
+      "learning_rate": 2.8212039532794248e-05,
+      "loss": 1.2036973237991333,
+      "step": 158
+    },
+    {
+      "epoch": 0.06903991370010787,
+      "grad_norm": 0.45373693108558655,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 1.1145079135894775,
+      "step": 160
+    },
+    {
+      "epoch": 0.06990291262135923,
+      "grad_norm": 0.4881038963794708,
+      "learning_rate": 2.8930817610062894e-05,
+      "loss": 1.173502802848816,
+      "step": 162
+    },
+    {
+      "epoch": 0.07076591154261057,
+      "grad_norm": 0.576934814453125,
+      "learning_rate": 2.9290206648697217e-05,
+      "loss": 1.250414490699768,
+      "step": 164
+    },
+    {
+      "epoch": 0.07162891046386193,
+      "grad_norm": 0.4900001287460327,
+      "learning_rate": 2.9649595687331537e-05,
+      "loss": 1.0721495151519775,
+      "step": 166
+    },
+    {
+      "epoch": 0.07249190938511327,
+      "grad_norm": 0.4440019726753235,
+      "learning_rate": 3.000898472596586e-05,
+      "loss": 1.0689374208450317,
+      "step": 168
+    },
+    {
+      "epoch": 0.07335490830636461,
+      "grad_norm": 0.4267268180847168,
+      "learning_rate": 3.0368373764600184e-05,
+      "loss": 1.2095128297805786,
+      "step": 170
+    },
+    {
+      "epoch": 0.07421790722761597,
+      "grad_norm": 0.6062787771224976,
+      "learning_rate": 3.0727762803234503e-05,
+      "loss": 1.077776551246643,
+      "step": 172
+    },
+    {
+      "epoch": 0.07508090614886731,
+      "grad_norm": 0.49510180950164795,
+      "learning_rate": 3.108715184186882e-05,
+      "loss": 1.144006371498108,
+      "step": 174
+    },
+    {
+      "epoch": 0.07594390507011867,
+      "grad_norm": 0.4670701026916504,
+      "learning_rate": 3.144654088050314e-05,
+      "loss": 1.1663392782211304,
+      "step": 176
+    },
+    {
+      "epoch": 0.07680690399137001,
+      "grad_norm": 0.5615383386611938,
+      "learning_rate": 3.1805929919137466e-05,
+      "loss": 1.1665973663330078,
+      "step": 178
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "grad_norm": 0.47305551171302795,
+      "learning_rate": 3.216531895777179e-05,
+      "loss": 1.1337063312530518,
+      "step": 180
+    },
+    {
+      "epoch": 0.07853290183387271,
+      "grad_norm": 0.5127068758010864,
+      "learning_rate": 3.252470799640611e-05,
+      "loss": 1.072874903678894,
+      "step": 182
+    },
+    {
+      "epoch": 0.07939590075512405,
+      "grad_norm": 0.632448136806488,
+      "learning_rate": 3.2884097035040436e-05,
+      "loss": 1.1577240228652954,
+      "step": 184
+    },
+    {
+      "epoch": 0.08025889967637541,
+      "grad_norm": 0.4041025638580322,
+      "learning_rate": 3.324348607367476e-05,
+      "loss": 1.1186822652816772,
+      "step": 186
+    },
+    {
+      "epoch": 0.08112189859762675,
+      "grad_norm": 0.5239102244377136,
+      "learning_rate": 3.3602875112309076e-05,
+      "loss": 1.1468429565429688,
+      "step": 188
+    },
+    {
+      "epoch": 0.08198489751887811,
+      "grad_norm": 0.4486575424671173,
+      "learning_rate": 3.39622641509434e-05,
+      "loss": 1.0017019510269165,
+      "step": 190
+    },
+    {
+      "epoch": 0.08284789644012945,
+      "grad_norm": 0.4994317293167114,
+      "learning_rate": 3.4321653189577715e-05,
+      "loss": 1.1901532411575317,
+      "step": 192
+    },
+    {
+      "epoch": 0.0837108953613808,
+      "grad_norm": 0.5023699998855591,
+      "learning_rate": 3.468104222821204e-05,
+      "loss": 1.1398564577102661,
+      "step": 194
+    },
+    {
+      "epoch": 0.08457389428263215,
+      "grad_norm": 0.5077701807022095,
+      "learning_rate": 3.504043126684636e-05,
+      "loss": 1.1390413045883179,
+      "step": 196
+    },
+    {
+      "epoch": 0.0854368932038835,
+      "grad_norm": 0.5527892112731934,
+      "learning_rate": 3.5399820305480685e-05,
+      "loss": 1.1411432027816772,
+      "step": 198
+    },
+    {
+      "epoch": 0.08629989212513485,
+      "grad_norm": 0.5572488903999329,
+      "learning_rate": 3.575920934411501e-05,
+      "loss": 1.071260690689087,
+      "step": 200
+    },
+    {
+      "epoch": 0.08629989212513485,
+      "eval_loss": 1.1519012451171875,
+      "eval_runtime": 654.6055,
+      "eval_samples_per_second": 3.147,
+      "eval_steps_per_second": 3.147,
+      "step": 200
+    },
+    {
+      "epoch": 0.08716289104638619,
+      "grad_norm": 0.5134095549583435,
+      "learning_rate": 3.611859838274933e-05,
+      "loss": 1.138135552406311,
+      "step": 202
+    },
+    {
+      "epoch": 0.08802588996763754,
+      "grad_norm": 0.5166040658950806,
+      "learning_rate": 3.647798742138365e-05,
+      "loss": 1.111999273300171,
+      "step": 204
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.5336993336677551,
+      "learning_rate": 3.683737646001797e-05,
+      "loss": 1.1031352281570435,
+      "step": 206
+    },
+    {
+      "epoch": 0.08975188781014024,
+      "grad_norm": 0.8289600014686584,
+      "learning_rate": 3.7196765498652294e-05,
+      "loss": 1.0388667583465576,
+      "step": 208
+    },
+    {
+      "epoch": 0.09061488673139159,
+      "grad_norm": 0.47992637753486633,
+      "learning_rate": 3.755615453728661e-05,
+      "loss": 1.0950241088867188,
+      "step": 210
+    },
+    {
+      "epoch": 0.09147788565264293,
+      "grad_norm": 0.5629691481590271,
+      "learning_rate": 3.7915543575920934e-05,
+      "loss": 1.0361733436584473,
+      "step": 212
+    },
+    {
+      "epoch": 0.09234088457389428,
+      "grad_norm": 0.5515111684799194,
+      "learning_rate": 3.827493261455526e-05,
+      "loss": 1.0922447443008423,
+      "step": 214
+    },
+    {
+      "epoch": 0.09320388349514563,
+      "grad_norm": 0.5078643560409546,
+      "learning_rate": 3.863432165318958e-05,
+      "loss": 1.0866856575012207,
+      "step": 216
+    },
+    {
+      "epoch": 0.09406688241639698,
+      "grad_norm": 0.6046127676963806,
+      "learning_rate": 3.8993710691823904e-05,
+      "loss": 1.1231595277786255,
+      "step": 218
+    },
+    {
+      "epoch": 0.09492988133764833,
+      "grad_norm": 0.6255762577056885,
+      "learning_rate": 3.935309973045822e-05,
+      "loss": 1.099171757698059,
+      "step": 220
+    },
+    {
+      "epoch": 0.09579288025889968,
+      "grad_norm": 0.6036638021469116,
+      "learning_rate": 3.971248876909254e-05,
+      "loss": 1.0557761192321777,
+      "step": 222
+    },
+    {
+      "epoch": 0.09665587918015102,
+      "grad_norm": 0.5520529747009277,
+      "learning_rate": 4.0071877807726867e-05,
+      "loss": 1.0467877388000488,
+      "step": 224
+    },
+    {
+      "epoch": 0.09751887810140238,
+      "grad_norm": 0.5958684682846069,
+      "learning_rate": 4.043126684636119e-05,
+      "loss": 1.17941153049469,
+      "step": 226
+    },
+    {
+      "epoch": 0.09838187702265372,
+      "grad_norm": 0.5283281803131104,
+      "learning_rate": 4.079065588499551e-05,
+      "loss": 1.104217767715454,
+      "step": 228
+    },
+    {
+      "epoch": 0.09924487594390508,
+      "grad_norm": 0.5608792901039124,
+      "learning_rate": 4.115004492362983e-05,
+      "loss": 1.0900640487670898,
+      "step": 230
+    },
+    {
+      "epoch": 0.10010787486515642,
+      "grad_norm": 0.555964469909668,
+      "learning_rate": 4.150943396226415e-05,
+      "loss": 0.9887422323226929,
+      "step": 232
+    },
+    {
+      "epoch": 0.10097087378640776,
+      "grad_norm": 0.5875785946846008,
+      "learning_rate": 4.1868823000898476e-05,
+      "loss": 1.1298567056655884,
+      "step": 234
+    },
+    {
+      "epoch": 0.10183387270765912,
+      "grad_norm": 0.4544795751571655,
+      "learning_rate": 4.222821203953279e-05,
+      "loss": 1.0957067012786865,
+      "step": 236
+    },
+    {
+      "epoch": 0.10269687162891046,
+      "grad_norm": 0.564145565032959,
+      "learning_rate": 4.2587601078167116e-05,
+      "loss": 1.0328738689422607,
+      "step": 238
+    },
+    {
+      "epoch": 0.10355987055016182,
+      "grad_norm": 0.6285979747772217,
+      "learning_rate": 4.294699011680144e-05,
+      "loss": 1.1085515022277832,
+      "step": 240
+    },
+    {
+      "epoch": 0.10442286947141316,
+      "grad_norm": 0.6442288756370544,
+      "learning_rate": 4.330637915543576e-05,
+      "loss": 1.1291271448135376,
+      "step": 242
+    },
+    {
+      "epoch": 0.1052858683926645,
+      "grad_norm": 0.6137154698371887,
+      "learning_rate": 4.3665768194070085e-05,
+      "loss": 1.1759567260742188,
+      "step": 244
+    },
+    {
+      "epoch": 0.10614886731391586,
+      "grad_norm": 0.5906805992126465,
+      "learning_rate": 4.402515723270441e-05,
+      "loss": 1.148414969444275,
+      "step": 246
+    },
+    {
+      "epoch": 0.1070118662351672,
+      "grad_norm": 0.5382888913154602,
+      "learning_rate": 4.438454627133873e-05,
+      "loss": 1.0749616622924805,
+      "step": 248
+    },
+    {
+      "epoch": 0.10787486515641856,
+      "grad_norm": 0.6185492873191833,
+      "learning_rate": 4.474393530997305e-05,
+      "loss": 1.2235801219940186,
+      "step": 250
+    },
+    {
+      "epoch": 0.1087378640776699,
+      "grad_norm": 0.5981597900390625,
+      "learning_rate": 4.5103324348607365e-05,
+      "loss": 1.1390639543533325,
+      "step": 252
+    },
+    {
+      "epoch": 0.10960086299892124,
+      "grad_norm": 0.5664694905281067,
+      "learning_rate": 4.546271338724169e-05,
+      "loss": 1.171774983406067,
+      "step": 254
+    },
+    {
+      "epoch": 0.1104638619201726,
+      "grad_norm": 0.7071851491928101,
+      "learning_rate": 4.582210242587601e-05,
+      "loss": 1.1704237461090088,
+      "step": 256
+    },
+    {
+      "epoch": 0.11132686084142394,
+      "grad_norm": 0.5815614461898804,
+      "learning_rate": 4.6181491464510334e-05,
+      "loss": 1.0619677305221558,
+      "step": 258
+    },
+    {
+      "epoch": 0.1121898597626753,
+      "grad_norm": 0.6481915712356567,
+      "learning_rate": 4.654088050314466e-05,
+      "loss": 1.0824390649795532,
+      "step": 260
+    },
+    {
+      "epoch": 0.11305285868392664,
+      "grad_norm": 0.5988591313362122,
+      "learning_rate": 4.690026954177898e-05,
+      "loss": 1.087929606437683,
+      "step": 262
+    },
+    {
+      "epoch": 0.113915857605178,
+      "grad_norm": 0.6545296311378479,
+      "learning_rate": 4.7259658580413304e-05,
+      "loss": 1.0936195850372314,
+      "step": 264
+    },
+    {
+      "epoch": 0.11477885652642934,
+      "grad_norm": 0.5826204419136047,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 1.0433681011199951,
+      "step": 266
+    },
+    {
+      "epoch": 0.11564185544768069,
+      "grad_norm": 0.5907514095306396,
+      "learning_rate": 4.7978436657681944e-05,
+      "loss": 1.0719536542892456,
+      "step": 268
+    },
+    {
+      "epoch": 0.11650485436893204,
+      "grad_norm": 0.524394154548645,
+      "learning_rate": 4.833782569631627e-05,
+      "loss": 1.0231504440307617,
+      "step": 270
+    },
+    {
+      "epoch": 0.11736785329018339,
+      "grad_norm": 0.5472846031188965,
+      "learning_rate": 4.869721473495058e-05,
+      "loss": 0.9905915260314941,
+      "step": 272
+    },
+    {
+      "epoch": 0.11823085221143474,
+      "grad_norm": 0.727922260761261,
+      "learning_rate": 4.9056603773584906e-05,
+      "loss": 1.213677167892456,
+      "step": 274
+    },
+    {
+      "epoch": 0.11909385113268608,
+      "grad_norm": 0.6009684801101685,
+      "learning_rate": 4.941599281221923e-05,
+      "loss": 1.0052144527435303,
+      "step": 276
+    },
+    {
+      "epoch": 0.11995685005393743,
+      "grad_norm": 0.6564669013023376,
+      "learning_rate": 4.977538185085355e-05,
+      "loss": 1.108136773109436,
+      "step": 278
+    },
+    {
+      "epoch": 0.12081984897518878,
+      "grad_norm": 0.650074303150177,
+      "learning_rate": 5.013477088948787e-05,
+      "loss": 0.9700815677642822,
+      "step": 280
+    },
+    {
+      "epoch": 0.12168284789644013,
+      "grad_norm": 0.5772947072982788,
+      "learning_rate": 5.04941599281222e-05,
+      "loss": 1.038031816482544,
+      "step": 282
+    },
+    {
+      "epoch": 0.12254584681769148,
+      "grad_norm": 0.7293002009391785,
+      "learning_rate": 5.0853548966756516e-05,
+      "loss": 1.1063730716705322,
+      "step": 284
+    },
+    {
+      "epoch": 0.12340884573894283,
+      "grad_norm": 0.7937333583831787,
+      "learning_rate": 5.1212938005390846e-05,
+      "loss": 1.128495693206787,
+      "step": 286
+    },
+    {
+      "epoch": 0.12427184466019417,
+      "grad_norm": 0.48499324917793274,
+      "learning_rate": 5.157232704402516e-05,
+      "loss": 0.9438712000846863,
+      "step": 288
+    },
+    {
+      "epoch": 0.12513484358144553,
+      "grad_norm": 0.6010656952857971,
+      "learning_rate": 5.193171608265948e-05,
+      "loss": 1.0872881412506104,
+      "step": 290
+    },
+    {
+      "epoch": 0.12599784250269688,
+      "grad_norm": 0.6240811944007874,
+      "learning_rate": 5.22911051212938e-05,
+      "loss": 1.110992193222046,
+      "step": 292
+    },
+    {
+      "epoch": 0.1268608414239482,
+      "grad_norm": 0.7172768712043762,
+      "learning_rate": 5.265049415992812e-05,
+      "loss": 1.1109752655029297,
+      "step": 294
+    },
+    {
+      "epoch": 0.12772384034519957,
+      "grad_norm": 0.6442400217056274,
+      "learning_rate": 5.300988319856245e-05,
+      "loss": 1.05553138256073,
+      "step": 296
+    },
+    {
+      "epoch": 0.12858683926645093,
+      "grad_norm": 0.7074702382087708,
+      "learning_rate": 5.3369272237196765e-05,
+      "loss": 1.0717648267745972,
+      "step": 298
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "grad_norm": 0.5277591347694397,
+      "learning_rate": 5.3728661275831095e-05,
+      "loss": 0.9777541756629944,
+      "step": 300
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "eval_loss": 1.0977506637573242,
+      "eval_runtime": 662.1728,
+      "eval_samples_per_second": 3.111,
+      "eval_steps_per_second": 3.111,
+      "step": 300
+    },
+    {
+      "epoch": 0.1303128371089536,
+      "grad_norm": 0.7252246737480164,
+      "learning_rate": 5.408805031446541e-05,
+      "loss": 1.075905203819275,
+      "step": 302
+    },
+    {
+      "epoch": 0.13117583603020497,
+      "grad_norm": 0.7003294229507446,
+      "learning_rate": 5.444743935309974e-05,
+      "loss": 1.1117515563964844,
+      "step": 304
+    },
+    {
+      "epoch": 0.13203883495145632,
+      "grad_norm": 0.5878211259841919,
+      "learning_rate": 5.480682839173406e-05,
+      "loss": 1.0289191007614136,
+      "step": 306
+    },
+    {
+      "epoch": 0.13290183387270765,
+      "grad_norm": 0.7133644223213196,
+      "learning_rate": 5.5166217430368374e-05,
+      "loss": 1.0199183225631714,
+      "step": 308
+    },
+    {
+      "epoch": 0.133764832793959,
+      "grad_norm": 0.6098423600196838,
+      "learning_rate": 5.55256064690027e-05,
+      "loss": 1.0132375955581665,
+      "step": 310
+    },
+    {
+      "epoch": 0.13462783171521037,
+      "grad_norm": 0.6386916041374207,
+      "learning_rate": 5.5884995507637014e-05,
+      "loss": 1.1595754623413086,
+      "step": 312
+    },
+    {
+      "epoch": 0.1354908306364617,
+      "grad_norm": 0.6563469767570496,
+      "learning_rate": 5.6244384546271344e-05,
+      "loss": 1.0921307802200317,
+      "step": 314
+    },
+    {
+      "epoch": 0.13635382955771305,
+      "grad_norm": 0.6388015747070312,
+      "learning_rate": 5.660377358490566e-05,
+      "loss": 1.0200815200805664,
+      "step": 316
+    },
+    {
+      "epoch": 0.1372168284789644,
+      "grad_norm": 0.6026274561882019,
+      "learning_rate": 5.696316262353999e-05,
+      "loss": 0.9339485764503479,
+      "step": 318
+    },
+    {
+      "epoch": 0.13807982740021574,
+      "grad_norm": 0.619800865650177,
+      "learning_rate": 5.732255166217431e-05,
+      "loss": 1.0268478393554688,
+      "step": 320
+    },
+    {
+      "epoch": 0.1389428263214671,
+      "grad_norm": 0.5924715399742126,
+      "learning_rate": 5.768194070080862e-05,
+      "loss": 1.1394236087799072,
+      "step": 322
+    },
+    {
+      "epoch": 0.13980582524271845,
+      "grad_norm": 0.6829012036323547,
+      "learning_rate": 5.804132973944295e-05,
+      "loss": 1.002437949180603,
+      "step": 324
+    },
+    {
+      "epoch": 0.1406688241639698,
+      "grad_norm": 0.7012544274330139,
+      "learning_rate": 5.840071877807727e-05,
+      "loss": 1.132503628730774,
+      "step": 326
+    },
+    {
+      "epoch": 0.14153182308522114,
+      "grad_norm": 0.7921599745750427,
+      "learning_rate": 5.876010781671159e-05,
+      "loss": 1.1859129667282104,
+      "step": 328
+    },
+    {
+      "epoch": 0.1423948220064725,
+      "grad_norm": 0.6373353004455566,
+      "learning_rate": 5.9119496855345916e-05,
+      "loss": 1.0896776914596558,
+      "step": 330
+    },
+    {
+      "epoch": 0.14325782092772385,
+      "grad_norm": 0.6174030900001526,
+      "learning_rate": 5.947888589398024e-05,
+      "loss": 1.0691723823547363,
+      "step": 332
+    },
+    {
+      "epoch": 0.14412081984897518,
+      "grad_norm": 0.5110617280006409,
+      "learning_rate": 5.9838274932614556e-05,
+      "loss": 1.0144777297973633,
+      "step": 334
+    },
+    {
+      "epoch": 0.14498381877022654,
+      "grad_norm": 0.5580511093139648,
+      "learning_rate": 6.019766397124887e-05,
+      "loss": 0.9955101609230042,
+      "step": 336
+    },
+    {
+      "epoch": 0.1458468176914779,
+      "grad_norm": 0.6427345275878906,
+      "learning_rate": 6.05570530098832e-05,
+      "loss": 0.9863013625144958,
+      "step": 338
+    },
+    {
+      "epoch": 0.14670981661272922,
+      "grad_norm": 0.7464537024497986,
+      "learning_rate": 6.091644204851752e-05,
+      "loss": 1.0682255029678345,
+      "step": 340
+    },
+    {
+      "epoch": 0.14757281553398058,
+      "grad_norm": 0.599926769733429,
+      "learning_rate": 6.127583108715184e-05,
+      "loss": 1.034083366394043,
+      "step": 342
+    },
+    {
+      "epoch": 0.14843581445523193,
+      "grad_norm": 0.6320257186889648,
+      "learning_rate": 6.163522012578616e-05,
+      "loss": 1.0776089429855347,
+      "step": 344
+    },
+    {
+      "epoch": 0.1492988133764833,
+      "grad_norm": 0.6565091013908386,
+      "learning_rate": 6.199460916442049e-05,
+      "loss": 1.0493087768554688,
+      "step": 346
+    },
+    {
+      "epoch": 0.15016181229773462,
+      "grad_norm": 0.6512171626091003,
+      "learning_rate": 6.23539982030548e-05,
+      "loss": 1.0469218492507935,
+      "step": 348
+    },
+    {
+      "epoch": 0.15102481121898598,
+      "grad_norm": 0.8487282991409302,
+      "learning_rate": 6.271338724168913e-05,
+      "loss": 1.0985081195831299,
+      "step": 350
+    },
+    {
+      "epoch": 0.15188781014023733,
+      "grad_norm": 0.6718961596488953,
+      "learning_rate": 6.307277628032345e-05,
+      "loss": 1.0714176893234253,
+      "step": 352
+    },
+    {
+      "epoch": 0.15275080906148866,
+      "grad_norm": 0.8175088167190552,
+      "learning_rate": 6.343216531895777e-05,
+      "loss": 1.0599322319030762,
+      "step": 354
+    },
+    {
+      "epoch": 0.15361380798274002,
+      "grad_norm": 0.6359215378761292,
+      "learning_rate": 6.37915543575921e-05,
+      "loss": 0.9268131256103516,
+      "step": 356
+    },
+    {
+      "epoch": 0.15447680690399138,
+      "grad_norm": 0.6423866748809814,
+      "learning_rate": 6.415094339622641e-05,
+      "loss": 0.9838354587554932,
+      "step": 358
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "grad_norm": 0.6496716737747192,
+      "learning_rate": 6.451033243486074e-05,
+      "loss": 1.048566460609436,
+      "step": 360
+    },
+    {
+      "epoch": 0.15620280474649406,
+      "grad_norm": 0.6536920666694641,
+      "learning_rate": 6.486972147349506e-05,
+      "loss": 1.0910537242889404,
+      "step": 362
+    },
+    {
+      "epoch": 0.15706580366774542,
+      "grad_norm": 0.5832068920135498,
+      "learning_rate": 6.522911051212939e-05,
+      "loss": 0.9971448183059692,
+      "step": 364
+    },
+    {
+      "epoch": 0.15792880258899678,
+      "grad_norm": 0.6647719144821167,
+      "learning_rate": 6.558849955076371e-05,
+      "loss": 1.0496708154678345,
+      "step": 366
+    },
+    {
+      "epoch": 0.1587918015102481,
+      "grad_norm": 0.623252809047699,
+      "learning_rate": 6.594788858939802e-05,
+      "loss": 0.955894410610199,
+      "step": 368
+    },
+    {
+      "epoch": 0.15965480043149946,
+      "grad_norm": 0.6311860084533691,
+      "learning_rate": 6.630727762803235e-05,
+      "loss": 1.1304032802581787,
+      "step": 370
+    },
+    {
+      "epoch": 0.16051779935275082,
+      "grad_norm": 0.5306481122970581,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.8746405243873596,
+      "step": 372
+    },
+    {
+      "epoch": 0.16138079827400215,
+      "grad_norm": 0.6249631643295288,
+      "learning_rate": 6.7026055705301e-05,
+      "loss": 0.9104986786842346,
+      "step": 374
+    },
+    {
+      "epoch": 0.1622437971952535,
+      "grad_norm": 0.6243219971656799,
+      "learning_rate": 6.738544474393532e-05,
+      "loss": 1.043666124343872,
+      "step": 376
+    },
+    {
+      "epoch": 0.16310679611650486,
+      "grad_norm": 0.6833282113075256,
+      "learning_rate": 6.774483378256963e-05,
+      "loss": 1.0504906177520752,
+      "step": 378
+    },
+    {
+      "epoch": 0.16396979503775622,
+      "grad_norm": 0.7124452590942383,
+      "learning_rate": 6.810422282120395e-05,
+      "loss": 1.0608166456222534,
+      "step": 380
+    },
+    {
+      "epoch": 0.16483279395900755,
+      "grad_norm": 0.7520908117294312,
+      "learning_rate": 6.846361185983828e-05,
+      "loss": 1.1653732061386108,
+      "step": 382
+    },
+    {
+      "epoch": 0.1656957928802589,
+      "grad_norm": 0.7121814489364624,
+      "learning_rate": 6.88230008984726e-05,
+      "loss": 1.0626367330551147,
+      "step": 384
+    },
+    {
+      "epoch": 0.16655879180151026,
+      "grad_norm": 0.6825008988380432,
+      "learning_rate": 6.918238993710691e-05,
+      "loss": 1.012121319770813,
+      "step": 386
+    },
+    {
+      "epoch": 0.1674217907227616,
+      "grad_norm": 0.4922940135002136,
+      "learning_rate": 6.954177897574124e-05,
+      "loss": 1.0576211214065552,
+      "step": 388
+    },
+    {
+      "epoch": 0.16828478964401294,
+      "grad_norm": 0.6122089624404907,
+      "learning_rate": 6.990116801437556e-05,
+      "loss": 1.03916597366333,
+      "step": 390
+    },
+    {
+      "epoch": 0.1691477885652643,
+      "grad_norm": 0.6348981261253357,
+      "learning_rate": 7.026055705300989e-05,
+      "loss": 1.17647123336792,
+      "step": 392
+    },
+    {
+      "epoch": 0.17001078748651563,
+      "grad_norm": 0.6205878257751465,
+      "learning_rate": 7.06199460916442e-05,
+      "loss": 0.9095983505249023,
+      "step": 394
+    },
+    {
+      "epoch": 0.170873786407767,
+      "grad_norm": 0.61506187915802,
+      "learning_rate": 7.097933513027853e-05,
+      "loss": 1.082506775856018,
+      "step": 396
+    },
+    {
+      "epoch": 0.17173678532901834,
+      "grad_norm": 0.6481751799583435,
+      "learning_rate": 7.133872416891285e-05,
+      "loss": 1.0716280937194824,
+      "step": 398
+    },
+    {
+      "epoch": 0.1725997842502697,
+      "grad_norm": 0.4871014952659607,
+      "learning_rate": 7.169811320754717e-05,
+      "loss": 0.9616814851760864,
+      "step": 400
+    },
+    {
+      "epoch": 0.1725997842502697,
+      "eval_loss": 1.0649415254592896,
+      "eval_runtime": 668.6025,
+      "eval_samples_per_second": 3.081,
+      "eval_steps_per_second": 3.081,
+      "step": 400
+    },
+    {
+      "epoch": 0.17346278317152103,
+      "grad_norm": 0.5680040121078491,
+      "learning_rate": 7.20575022461815e-05,
+      "loss": 1.0475050210952759,
+      "step": 402
+    },
+    {
+      "epoch": 0.17432578209277239,
+      "grad_norm": 0.6417813897132874,
+      "learning_rate": 7.241689128481581e-05,
+      "loss": 0.9851161241531372,
+      "step": 404
+    },
+    {
+      "epoch": 0.17518878101402374,
+      "grad_norm": 0.6600468158721924,
+      "learning_rate": 7.277628032345014e-05,
+      "loss": 1.013339638710022,
+      "step": 406
+    },
+    {
+      "epoch": 0.17605177993527507,
+      "grad_norm": 0.6733932495117188,
+      "learning_rate": 7.313566936208446e-05,
+      "loss": 0.9346804022789001,
+      "step": 408
+    },
+    {
+      "epoch": 0.17691477885652643,
+      "grad_norm": 0.6812151074409485,
+      "learning_rate": 7.349505840071879e-05,
+      "loss": 0.9890368580818176,
+      "step": 410
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.6380394697189331,
+      "learning_rate": 7.385444743935311e-05,
+      "loss": 0.8787848949432373,
+      "step": 412
+    },
+    {
+      "epoch": 0.1786407766990291,
+      "grad_norm": 0.6004905700683594,
+      "learning_rate": 7.421383647798742e-05,
+      "loss": 1.0235728025436401,
+      "step": 414
+    },
+    {
+      "epoch": 0.17950377562028047,
+      "grad_norm": 0.6569193005561829,
+      "learning_rate": 7.457322551662175e-05,
+      "loss": 0.9972385168075562,
+      "step": 416
+    },
+    {
+      "epoch": 0.18036677454153183,
+      "grad_norm": 0.6761631369590759,
+      "learning_rate": 7.493261455525607e-05,
+      "loss": 0.9593698382377625,
+      "step": 418
+    },
+    {
+      "epoch": 0.18122977346278318,
+      "grad_norm": 0.7328561544418335,
+      "learning_rate": 7.529200359389039e-05,
+      "loss": 1.0426853895187378,
+      "step": 420
+    },
+    {
+      "epoch": 0.1820927723840345,
+      "grad_norm": 0.6256070137023926,
+      "learning_rate": 7.56513926325247e-05,
+      "loss": 0.9608182311058044,
+      "step": 422
+    },
+    {
+      "epoch": 0.18295577130528587,
+      "grad_norm": 1.2549844980239868,
+      "learning_rate": 7.601078167115903e-05,
+      "loss": 1.0162668228149414,
+      "step": 424
+    },
+    {
+      "epoch": 0.18381877022653723,
+      "grad_norm": 0.6751510500907898,
+      "learning_rate": 7.637017070979335e-05,
+      "loss": 1.130725383758545,
+      "step": 426
+    },
+    {
+      "epoch": 0.18468176914778855,
+      "grad_norm": 0.7029808163642883,
+      "learning_rate": 7.672955974842768e-05,
+      "loss": 1.0384817123413086,
+      "step": 428
+    },
+    {
+      "epoch": 0.1855447680690399,
+      "grad_norm": 0.644353449344635,
+      "learning_rate": 7.7088948787062e-05,
+      "loss": 1.017020344734192,
+      "step": 430
+    },
+    {
+      "epoch": 0.18640776699029127,
+      "grad_norm": 0.6784916520118713,
+      "learning_rate": 7.744833782569631e-05,
+      "loss": 1.005354404449463,
+      "step": 432
+    },
+    {
+      "epoch": 0.1872707659115426,
+      "grad_norm": 0.5989449620246887,
+      "learning_rate": 7.780772686433064e-05,
+      "loss": 1.026848316192627,
+      "step": 434
+    },
+    {
+      "epoch": 0.18813376483279395,
+      "grad_norm": 0.6502639651298523,
+      "learning_rate": 7.816711590296496e-05,
+      "loss": 0.9891080856323242,
+      "step": 436
+    },
+    {
+      "epoch": 0.1889967637540453,
+      "grad_norm": 0.6176205277442932,
+      "learning_rate": 7.852650494159929e-05,
+      "loss": 0.966316819190979,
+      "step": 438
+    },
+    {
+      "epoch": 0.18985976267529667,
+      "grad_norm": 0.6801626086235046,
+      "learning_rate": 7.88858939802336e-05,
+      "loss": 1.123063087463379,
+      "step": 440
+    },
+    {
+      "epoch": 0.190722761596548,
+      "grad_norm": 0.6718618273735046,
+      "learning_rate": 7.924528301886794e-05,
+      "loss": 1.0467073917388916,
+      "step": 442
+    },
+    {
+      "epoch": 0.19158576051779935,
+      "grad_norm": 0.6761009097099304,
+      "learning_rate": 7.960467205750225e-05,
+      "loss": 1.0952889919281006,
+      "step": 444
+    },
+    {
+      "epoch": 0.1924487594390507,
+      "grad_norm": 0.6356327533721924,
+      "learning_rate": 7.996406109613657e-05,
+      "loss": 0.954807698726654,
+      "step": 446
+    },
+    {
+      "epoch": 0.19331175836030204,
+      "grad_norm": 0.6798669695854187,
+      "learning_rate": 8.03234501347709e-05,
+      "loss": 0.9941422343254089,
+      "step": 448
+    },
+    {
+      "epoch": 0.1941747572815534,
+      "grad_norm": 0.6511302590370178,
+      "learning_rate": 8.068283917340521e-05,
+      "loss": 1.0351495742797852,
+      "step": 450
+    },
+    {
+      "epoch": 0.19503775620280475,
+      "grad_norm": 0.6061258912086487,
+      "learning_rate": 8.104222821203954e-05,
+      "loss": 1.00546133518219,
+      "step": 452
+    },
+    {
+      "epoch": 0.1959007551240561,
+      "grad_norm": 0.6278533935546875,
+      "learning_rate": 8.140161725067386e-05,
+      "loss": 1.0778460502624512,
+      "step": 454
+    },
+    {
+      "epoch": 0.19676375404530744,
+      "grad_norm": 0.6866298317909241,
+      "learning_rate": 8.176100628930818e-05,
+      "loss": 1.0344486236572266,
+      "step": 456
+    },
+    {
+      "epoch": 0.1976267529665588,
+      "grad_norm": 0.7338075041770935,
+      "learning_rate": 8.212039532794251e-05,
+      "loss": 1.0663033723831177,
+      "step": 458
+    },
+    {
+      "epoch": 0.19848975188781015,
+      "grad_norm": 0.6811459064483643,
+      "learning_rate": 8.247978436657682e-05,
+      "loss": 0.9665339589118958,
+      "step": 460
+    },
+    {
+      "epoch": 0.19935275080906148,
+      "grad_norm": 0.6779627799987793,
+      "learning_rate": 8.283917340521114e-05,
+      "loss": 1.024712324142456,
+      "step": 462
+    },
+    {
+      "epoch": 0.20021574973031284,
+      "grad_norm": 0.6486892700195312,
+      "learning_rate": 8.319856244384546e-05,
+      "loss": 0.9699305295944214,
+      "step": 464
+    },
+    {
+      "epoch": 0.2010787486515642,
+      "grad_norm": 0.7022278308868408,
+      "learning_rate": 8.355795148247979e-05,
+      "loss": 0.9540432095527649,
+      "step": 466
+    },
+    {
+      "epoch": 0.20194174757281552,
+      "grad_norm": 0.5922990441322327,
+      "learning_rate": 8.39173405211141e-05,
+      "loss": 0.9253339767456055,
+      "step": 468
+    },
+    {
+      "epoch": 0.20280474649406688,
+      "grad_norm": 0.7076792120933533,
+      "learning_rate": 8.427672955974843e-05,
+      "loss": 0.9987741112709045,
+      "step": 470
+    },
+    {
+      "epoch": 0.20366774541531824,
+      "grad_norm": 0.6491380333900452,
+      "learning_rate": 8.463611859838275e-05,
+      "loss": 1.0249329805374146,
+      "step": 472
+    },
+    {
+      "epoch": 0.2045307443365696,
+      "grad_norm": 0.6784211993217468,
+      "learning_rate": 8.499550763701708e-05,
+      "loss": 1.0577133893966675,
+      "step": 474
+    },
+    {
+      "epoch": 0.20539374325782092,
+      "grad_norm": 0.6453303694725037,
+      "learning_rate": 8.53548966756514e-05,
+      "loss": 1.1312458515167236,
+      "step": 476
+    },
+    {
+      "epoch": 0.20625674217907228,
+      "grad_norm": 0.7431377172470093,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 1.0592451095581055,
+      "step": 478
+    },
+    {
+      "epoch": 0.20711974110032363,
+      "grad_norm": 0.6097649931907654,
+      "learning_rate": 8.607367475292004e-05,
+      "loss": 0.9337235689163208,
+      "step": 480
+    },
+    {
+      "epoch": 0.20798274002157496,
+      "grad_norm": 0.5693124532699585,
+      "learning_rate": 8.643306379155436e-05,
+      "loss": 0.9088928699493408,
+      "step": 482
+    },
+    {
+      "epoch": 0.20884573894282632,
+      "grad_norm": 0.7377229332923889,
+      "learning_rate": 8.679245283018869e-05,
+      "loss": 1.0729358196258545,
+      "step": 484
+    },
+    {
+      "epoch": 0.20970873786407768,
+      "grad_norm": 0.7399470210075378,
+      "learning_rate": 8.7151841868823e-05,
+      "loss": 1.0428457260131836,
+      "step": 486
+    },
+    {
+      "epoch": 0.210571736785329,
+      "grad_norm": 0.677052915096283,
+      "learning_rate": 8.751123090745734e-05,
+      "loss": 0.9940266013145447,
+      "step": 488
+    },
+    {
+      "epoch": 0.21143473570658036,
+      "grad_norm": 0.7126721739768982,
+      "learning_rate": 8.787061994609165e-05,
+      "loss": 1.011808156967163,
+      "step": 490
+    },
+    {
+      "epoch": 0.21229773462783172,
+      "grad_norm": 0.6663792729377747,
+      "learning_rate": 8.823000898472597e-05,
+      "loss": 1.0054185390472412,
+      "step": 492
+    },
+    {
+      "epoch": 0.21316073354908308,
+      "grad_norm": 0.6661092042922974,
+      "learning_rate": 8.85893980233603e-05,
+      "loss": 1.0167138576507568,
+      "step": 494
+    },
+    {
+      "epoch": 0.2140237324703344,
+      "grad_norm": 0.6975740194320679,
+      "learning_rate": 8.894878706199461e-05,
+      "loss": 1.1470818519592285,
+      "step": 496
+    },
+    {
+      "epoch": 0.21488673139158576,
+      "grad_norm": 0.6594390869140625,
+      "learning_rate": 8.930817610062893e-05,
+      "loss": 0.9619631171226501,
+      "step": 498
+    },
+    {
+      "epoch": 0.21574973031283712,
+      "grad_norm": 0.7216679453849792,
+      "learning_rate": 8.966756513926325e-05,
+      "loss": 0.9971368312835693,
+      "step": 500
+    },
+    {
+      "epoch": 0.21574973031283712,
+      "eval_loss": 1.0417571067810059,
+      "eval_runtime": 659.3112,
+      "eval_samples_per_second": 3.124,
+      "eval_steps_per_second": 3.124,
+      "step": 500
+    },
+    {
+      "epoch": 0.21661272923408845,
+      "grad_norm": 0.6188210844993591,
+      "learning_rate": 9.002695417789758e-05,
+      "loss": 1.0307213068008423,
+      "step": 502
+    },
+    {
+      "epoch": 0.2174757281553398,
+      "grad_norm": 0.6716445088386536,
+      "learning_rate": 9.03863432165319e-05,
+      "loss": 1.0188794136047363,
+      "step": 504
+    },
+    {
+      "epoch": 0.21833872707659116,
+      "grad_norm": 0.6790863275527954,
+      "learning_rate": 9.074573225516622e-05,
+      "loss": 0.9764845967292786,
+      "step": 506
+    },
+    {
+      "epoch": 0.2192017259978425,
+      "grad_norm": 0.6764960289001465,
+      "learning_rate": 9.110512129380054e-05,
+      "loss": 0.948829174041748,
+      "step": 508
+    },
+    {
+      "epoch": 0.22006472491909385,
+      "grad_norm": 0.6210965514183044,
+      "learning_rate": 9.146451033243486e-05,
+      "loss": 1.008013129234314,
+      "step": 510
+    },
+    {
+      "epoch": 0.2209277238403452,
+      "grad_norm": 0.7739297747612,
+      "learning_rate": 9.182389937106919e-05,
+      "loss": 1.1662557125091553,
+      "step": 512
+    },
+    {
+      "epoch": 0.22179072276159656,
+      "grad_norm": 0.7055562138557434,
+      "learning_rate": 9.21832884097035e-05,
+      "loss": 1.0325161218643188,
+      "step": 514
+    },
+    {
+      "epoch": 0.2226537216828479,
+      "grad_norm": 0.6079210042953491,
+      "learning_rate": 9.254267744833783e-05,
+      "loss": 1.00056791305542,
+      "step": 516
+    },
+    {
+      "epoch": 0.22351672060409924,
+      "grad_norm": 0.5974318981170654,
+      "learning_rate": 9.290206648697215e-05,
+      "loss": 0.9422364234924316,
+      "step": 518
+    },
+    {
+      "epoch": 0.2243797195253506,
+      "grad_norm": 0.5963430404663086,
+      "learning_rate": 9.326145552560648e-05,
+      "loss": 0.936336100101471,
+      "step": 520
+    },
+    {
+      "epoch": 0.22524271844660193,
+      "grad_norm": 0.6823658347129822,
+      "learning_rate": 9.36208445642408e-05,
+      "loss": 1.0538607835769653,
+      "step": 522
+    },
+    {
+      "epoch": 0.2261057173678533,
+      "grad_norm": 0.6409855484962463,
+      "learning_rate": 9.398023360287511e-05,
+      "loss": 1.0483653545379639,
+      "step": 524
+    },
+    {
+      "epoch": 0.22696871628910464,
+      "grad_norm": 0.6867254376411438,
+      "learning_rate": 9.433962264150944e-05,
+      "loss": 0.9668049812316895,
+      "step": 526
+    },
+    {
+      "epoch": 0.227831715210356,
+      "grad_norm": 0.5690792798995972,
+      "learning_rate": 9.469901168014376e-05,
+      "loss": 1.008763313293457,
+      "step": 528
+    },
+    {
+      "epoch": 0.22869471413160733,
+      "grad_norm": 0.5964897274971008,
+      "learning_rate": 9.505840071877809e-05,
+      "loss": 1.0816441774368286,
+      "step": 530
+    },
+    {
+      "epoch": 0.2295577130528587,
+      "grad_norm": 0.627419114112854,
+      "learning_rate": 9.54177897574124e-05,
+      "loss": 0.9265700578689575,
+      "step": 532
+    },
+    {
+      "epoch": 0.23042071197411004,
+      "grad_norm": 0.5862151980400085,
+      "learning_rate": 9.577717879604674e-05,
+      "loss": 0.9804646372795105,
+      "step": 534
+    },
+    {
+      "epoch": 0.23128371089536137,
+      "grad_norm": 0.5573718547821045,
+      "learning_rate": 9.613656783468105e-05,
+      "loss": 0.9627988934516907,
+      "step": 536
+    },
+    {
+      "epoch": 0.23214670981661273,
+      "grad_norm": 0.6705166101455688,
+      "learning_rate": 9.649595687331537e-05,
+      "loss": 1.0012824535369873,
+      "step": 538
+    },
+    {
+      "epoch": 0.23300970873786409,
+      "grad_norm": 0.6251236796379089,
+      "learning_rate": 9.685534591194969e-05,
+      "loss": 0.9568162560462952,
+      "step": 540
+    },
+    {
+      "epoch": 0.23387270765911541,
+      "grad_norm": 0.6466493010520935,
+      "learning_rate": 9.7214734950584e-05,
+      "loss": 1.031549334526062,
+      "step": 542
+    },
+    {
+      "epoch": 0.23473570658036677,
+      "grad_norm": 0.5183866024017334,
+      "learning_rate": 9.757412398921833e-05,
+      "loss": 0.8603643774986267,
+      "step": 544
+    },
+    {
+      "epoch": 0.23559870550161813,
+      "grad_norm": 0.6725775599479675,
+      "learning_rate": 9.793351302785265e-05,
+      "loss": 1.0365077257156372,
+      "step": 546
+    },
+    {
+      "epoch": 0.23646170442286948,
+      "grad_norm": 0.5972357988357544,
+      "learning_rate": 9.829290206648698e-05,
+      "loss": 0.9304701089859009,
+      "step": 548
+    },
+    {
+      "epoch": 0.2373247033441208,
+      "grad_norm": 0.5319957733154297,
+      "learning_rate": 9.86522911051213e-05,
+      "loss": 0.9575805068016052,
+      "step": 550
+    },
+    {
+      "epoch": 0.23818770226537217,
+      "grad_norm": 0.6502835750579834,
+      "learning_rate": 9.901168014375562e-05,
+      "loss": 1.0307214260101318,
+      "step": 552
+    },
+    {
+      "epoch": 0.23905070118662353,
+      "grad_norm": 0.6734047532081604,
+      "learning_rate": 9.937106918238994e-05,
+      "loss": 1.05185067653656,
+      "step": 554
+    },
+    {
+      "epoch": 0.23991370010787486,
+      "grad_norm": 0.5667978525161743,
+      "learning_rate": 9.973045822102426e-05,
+      "loss": 1.0190176963806152,
+      "step": 556
+    },
+    {
+      "epoch": 0.2407766990291262,
+      "grad_norm": 0.6370418667793274,
+      "learning_rate": 0.00010008984725965857,
+      "loss": 1.076182246208191,
+      "step": 558
+    },
+    {
+      "epoch": 0.24163969795037757,
+      "grad_norm": 0.689719021320343,
+      "learning_rate": 0.0001004492362982929,
+      "loss": 1.0408724546432495,
+      "step": 560
+    },
+    {
+      "epoch": 0.2425026968716289,
+      "grad_norm": 0.6304254531860352,
+      "learning_rate": 0.00010080862533692723,
+      "loss": 0.9869902729988098,
+      "step": 562
+    },
+    {
+      "epoch": 0.24336569579288025,
+      "grad_norm": 0.6797420382499695,
+      "learning_rate": 0.00010116801437556156,
+      "loss": 1.0198370218276978,
+      "step": 564
+    },
+    {
+      "epoch": 0.2442286947141316,
+      "grad_norm": 0.5993657112121582,
+      "learning_rate": 0.00010152740341419587,
+      "loss": 0.9947441816329956,
+      "step": 566
+    },
+    {
+      "epoch": 0.24509169363538297,
+      "grad_norm": 0.6369836330413818,
+      "learning_rate": 0.0001018867924528302,
+      "loss": 0.9722896814346313,
+      "step": 568
+    },
+    {
+      "epoch": 0.2459546925566343,
+      "grad_norm": 0.6942457556724548,
+      "learning_rate": 0.00010224618149146453,
+      "loss": 0.9716570973396301,
+      "step": 570
+    },
+    {
+      "epoch": 0.24681769147788565,
+      "grad_norm": 0.5403370261192322,
+      "learning_rate": 0.00010260557053009883,
+      "loss": 0.9797524213790894,
+      "step": 572
+    },
+    {
+      "epoch": 0.247680690399137,
+      "grad_norm": 0.5207529067993164,
+      "learning_rate": 0.00010296495956873316,
+      "loss": 0.985367476940155,
+      "step": 574
+    },
+    {
+      "epoch": 0.24854368932038834,
+      "grad_norm": 0.6751103401184082,
+      "learning_rate": 0.00010332434860736748,
+      "loss": 1.075042724609375,
+      "step": 576
+    },
+    {
+      "epoch": 0.2494066882416397,
+      "grad_norm": 0.565331220626831,
+      "learning_rate": 0.0001036837376460018,
+      "loss": 0.9273878335952759,
+      "step": 578
+    },
+    {
+      "epoch": 0.25026968716289105,
+      "grad_norm": 0.6858948469161987,
+      "learning_rate": 0.00010404312668463612,
+      "loss": 0.9872279763221741,
+      "step": 580
+    },
+    {
+      "epoch": 0.2511326860841424,
+      "grad_norm": 0.7091426253318787,
+      "learning_rate": 0.00010440251572327044,
+      "loss": 1.0038671493530273,
+      "step": 582
+    },
+    {
+      "epoch": 0.25199568500539377,
+      "grad_norm": 0.6493771076202393,
+      "learning_rate": 0.00010476190476190477,
+      "loss": 1.0109868049621582,
+      "step": 584
+    },
+    {
+      "epoch": 0.25285868392664507,
+      "grad_norm": 0.6107586622238159,
+      "learning_rate": 0.00010512129380053907,
+      "loss": 1.0020402669906616,
+      "step": 586
+    },
+    {
+      "epoch": 0.2537216828478964,
+      "grad_norm": 0.6878048181533813,
+      "learning_rate": 0.0001054806828391734,
+      "loss": 0.961039662361145,
+      "step": 588
+    },
+    {
+      "epoch": 0.2545846817691478,
+      "grad_norm": 0.664034903049469,
+      "learning_rate": 0.00010584007187780773,
+      "loss": 0.9725209474563599,
+      "step": 590
+    },
+    {
+      "epoch": 0.25544768069039914,
+      "grad_norm": 0.6399680376052856,
+      "learning_rate": 0.00010619946091644206,
+      "loss": 0.9907437562942505,
+      "step": 592
+    },
+    {
+      "epoch": 0.2563106796116505,
+      "grad_norm": 0.6163286566734314,
+      "learning_rate": 0.00010655884995507636,
+      "loss": 0.9650095701217651,
+      "step": 594
+    },
+    {
+      "epoch": 0.25717367853290185,
+      "grad_norm": 0.6008322238922119,
+      "learning_rate": 0.0001069182389937107,
+      "loss": 1.0102758407592773,
+      "step": 596
+    },
+    {
+      "epoch": 0.2580366774541532,
+      "grad_norm": 0.6752071380615234,
+      "learning_rate": 0.00010727762803234502,
+      "loss": 0.9101885557174683,
+      "step": 598
+    },
+    {
+      "epoch": 0.2588996763754045,
+      "grad_norm": 0.6789175868034363,
+      "learning_rate": 0.00010763701707097935,
+      "loss": 1.0461398363113403,
+      "step": 600
+    },
+    {
+      "epoch": 0.2588996763754045,
+      "eval_loss": 1.021111011505127,
+      "eval_runtime": 648.1611,
+      "eval_samples_per_second": 3.178,
+      "eval_steps_per_second": 3.178,
+      "step": 600
+    },
+    {
+      "epoch": 0.25976267529665586,
+      "grad_norm": 0.5660730600357056,
+      "learning_rate": 0.00010799640610961366,
+      "loss": 0.9582418203353882,
+      "step": 602
+    },
+    {
+      "epoch": 0.2606256742179072,
+      "grad_norm": 0.6726544499397278,
+      "learning_rate": 0.00010835579514824799,
+      "loss": 1.0763746500015259,
+      "step": 604
+    },
+    {
+      "epoch": 0.2614886731391586,
+      "grad_norm": 0.6068508625030518,
+      "learning_rate": 0.00010871518418688232,
+      "loss": 1.0432032346725464,
+      "step": 606
+    },
+    {
+      "epoch": 0.26235167206040994,
+      "grad_norm": 0.5731637477874756,
+      "learning_rate": 0.00010907457322551662,
+      "loss": 0.9830516576766968,
+      "step": 608
+    },
+    {
+      "epoch": 0.2632146709816613,
+      "grad_norm": 0.6777567267417908,
+      "learning_rate": 0.00010943396226415095,
+      "loss": 1.0442042350769043,
+      "step": 610
+    },
+    {
+      "epoch": 0.26407766990291265,
+      "grad_norm": 0.6372506618499756,
+      "learning_rate": 0.00010979335130278528,
+      "loss": 1.0001944303512573,
+      "step": 612
+    },
+    {
+      "epoch": 0.26494066882416395,
+      "grad_norm": 0.6606221795082092,
+      "learning_rate": 0.0001101527403414196,
+      "loss": 1.035884141921997,
+      "step": 614
+    },
+    {
+      "epoch": 0.2658036677454153,
+      "grad_norm": 0.6083229780197144,
+      "learning_rate": 0.00011051212938005391,
+      "loss": 0.9403397440910339,
+      "step": 616
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.6318517923355103,
+      "learning_rate": 0.00011087151841868823,
+      "loss": 0.9274454116821289,
+      "step": 618
+    },
+    {
+      "epoch": 0.267529665587918,
+      "grad_norm": 0.628190279006958,
+      "learning_rate": 0.00011123090745732256,
+      "loss": 0.9883754253387451,
+      "step": 620
+    },
+    {
+      "epoch": 0.2683926645091694,
+      "grad_norm": 0.5961961150169373,
+      "learning_rate": 0.00011159029649595688,
+      "loss": 1.0317535400390625,
+      "step": 622
+    },
+    {
+      "epoch": 0.26925566343042073,
+      "grad_norm": 0.5995341539382935,
+      "learning_rate": 0.00011194968553459119,
+      "loss": 0.9776126742362976,
+      "step": 624
+    },
+    {
+      "epoch": 0.27011866235167203,
+      "grad_norm": 0.6639334559440613,
+      "learning_rate": 0.00011230907457322552,
+      "loss": 1.0112378597259521,
+      "step": 626
+    },
+    {
+      "epoch": 0.2709816612729234,
+      "grad_norm": 0.6348621249198914,
+      "learning_rate": 0.00011266846361185985,
+      "loss": 1.0553804636001587,
+      "step": 628
+    },
+    {
+      "epoch": 0.27184466019417475,
+      "grad_norm": 0.5929805040359497,
+      "learning_rate": 0.00011302785265049416,
+      "loss": 1.025888442993164,
+      "step": 630
+    },
+    {
+      "epoch": 0.2727076591154261,
+      "grad_norm": 0.6052366495132446,
+      "learning_rate": 0.00011338724168912849,
+      "loss": 1.02956223487854,
+      "step": 632
+    },
+    {
+      "epoch": 0.27357065803667746,
+      "grad_norm": 0.6494882106781006,
+      "learning_rate": 0.00011374663072776282,
+      "loss": 0.989752471446991,
+      "step": 634
+    },
+    {
+      "epoch": 0.2744336569579288,
+      "grad_norm": 0.6005767583847046,
+      "learning_rate": 0.00011410601976639712,
+      "loss": 1.0030683279037476,
+      "step": 636
+    },
+    {
+      "epoch": 0.2752966558791802,
+      "grad_norm": 0.6478356122970581,
+      "learning_rate": 0.00011446540880503145,
+      "loss": 1.002000093460083,
+      "step": 638
+    },
+    {
+      "epoch": 0.2761596548004315,
+      "grad_norm": 0.5804725289344788,
+      "learning_rate": 0.00011482479784366578,
+      "loss": 0.9807654023170471,
+      "step": 640
+    },
+    {
+      "epoch": 0.27702265372168283,
+      "grad_norm": 0.632530689239502,
+      "learning_rate": 0.00011518418688230011,
+      "loss": 0.9841892123222351,
+      "step": 642
+    },
+    {
+      "epoch": 0.2778856526429342,
+      "grad_norm": 0.5340113639831543,
+      "learning_rate": 0.00011554357592093441,
+      "loss": 0.8902478814125061,
+      "step": 644
+    },
+    {
+      "epoch": 0.27874865156418555,
+      "grad_norm": 0.5901665091514587,
+      "learning_rate": 0.00011590296495956874,
+      "loss": 0.9019404649734497,
+      "step": 646
+    },
+    {
+      "epoch": 0.2796116504854369,
+      "grad_norm": 0.666589617729187,
+      "learning_rate": 0.00011626235399820307,
+      "loss": 0.9384423494338989,
+      "step": 648
+    },
+    {
+      "epoch": 0.28047464940668826,
+      "grad_norm": 0.7000334858894348,
+      "learning_rate": 0.00011662174303683737,
+      "loss": 1.0666629076004028,
+      "step": 650
+    },
+    {
+      "epoch": 0.2813376483279396,
+      "grad_norm": 0.663663923740387,
+      "learning_rate": 0.0001169811320754717,
+      "loss": 1.000019907951355,
+      "step": 652
+    },
+    {
+      "epoch": 0.2822006472491909,
+      "grad_norm": 0.6097694039344788,
+      "learning_rate": 0.00011734052111410603,
+      "loss": 0.9450293183326721,
+      "step": 654
+    },
+    {
+      "epoch": 0.2830636461704423,
+      "grad_norm": 0.6130967140197754,
+      "learning_rate": 0.00011769991015274035,
+      "loss": 0.9480894207954407,
+      "step": 656
+    },
+    {
+      "epoch": 0.28392664509169363,
+      "grad_norm": 0.7091249227523804,
+      "learning_rate": 0.00011805929919137467,
+      "loss": 1.1377143859863281,
+      "step": 658
+    },
+    {
+      "epoch": 0.284789644012945,
+      "grad_norm": 0.6556766629219055,
+      "learning_rate": 0.00011841868823000898,
+      "loss": 0.9421243667602539,
+      "step": 660
+    },
+    {
+      "epoch": 0.28565264293419634,
+      "grad_norm": 0.6682968735694885,
+      "learning_rate": 0.00011877807726864331,
+      "loss": 0.9726828336715698,
+      "step": 662
+    },
+    {
+      "epoch": 0.2865156418554477,
+      "grad_norm": 0.5224708914756775,
+      "learning_rate": 0.00011913746630727762,
+      "loss": 0.8996511697769165,
+      "step": 664
+    },
+    {
+      "epoch": 0.287378640776699,
+      "grad_norm": 0.5914195775985718,
+      "learning_rate": 0.00011949685534591195,
+      "loss": 0.9679517149925232,
+      "step": 666
+    },
+    {
+      "epoch": 0.28824163969795036,
+      "grad_norm": 0.6175519824028015,
+      "learning_rate": 0.00011985624438454628,
+      "loss": 0.8743209838867188,
+      "step": 668
+    },
+    {
+      "epoch": 0.2891046386192017,
+      "grad_norm": 0.6019226312637329,
+      "learning_rate": 0.0001202156334231806,
+      "loss": 0.9741992354393005,
+      "step": 670
+    },
+    {
+      "epoch": 0.28996763754045307,
+      "grad_norm": 0.6080542206764221,
+      "learning_rate": 0.00012057502246181491,
+      "loss": 0.9516472816467285,
+      "step": 672
+    },
+    {
+      "epoch": 0.29083063646170443,
+      "grad_norm": 0.5885615944862366,
+      "learning_rate": 0.00012093441150044924,
+      "loss": 1.122761607170105,
+      "step": 674
+    },
+    {
+      "epoch": 0.2916936353829558,
+      "grad_norm": 0.6635209918022156,
+      "learning_rate": 0.00012129380053908357,
+      "loss": 1.0105189085006714,
+      "step": 676
+    },
+    {
+      "epoch": 0.29255663430420714,
+      "grad_norm": 0.5805009007453918,
+      "learning_rate": 0.0001216531895777179,
+      "loss": 0.906292200088501,
+      "step": 678
+    },
+    {
+      "epoch": 0.29341963322545844,
+      "grad_norm": 0.5980029702186584,
+      "learning_rate": 0.0001220125786163522,
+      "loss": 1.009568691253662,
+      "step": 680
+    },
+    {
+      "epoch": 0.2942826321467098,
+      "grad_norm": 0.6797705292701721,
+      "learning_rate": 0.00012237196765498652,
+      "loss": 1.0373667478561401,
+      "step": 682
+    },
+    {
+      "epoch": 0.29514563106796116,
+      "grad_norm": 0.6280547976493835,
+      "learning_rate": 0.00012273135669362085,
+      "loss": 0.9758188724517822,
+      "step": 684
+    },
+    {
+      "epoch": 0.2960086299892125,
+      "grad_norm": 0.511608898639679,
+      "learning_rate": 0.00012309074573225515,
+      "loss": 0.9111692905426025,
+      "step": 686
+    },
+    {
+      "epoch": 0.29687162891046387,
+      "grad_norm": 0.5781835317611694,
+      "learning_rate": 0.00012345013477088948,
+      "loss": 0.8865921497344971,
+      "step": 688
+    },
+    {
+      "epoch": 0.2977346278317152,
+      "grad_norm": 0.6514166593551636,
+      "learning_rate": 0.0001238095238095238,
+      "loss": 0.9768189191818237,
+      "step": 690
+    },
+    {
+      "epoch": 0.2985976267529666,
+      "grad_norm": 0.6109189987182617,
+      "learning_rate": 0.00012416891284815814,
+      "loss": 0.9991607069969177,
+      "step": 692
+    },
+    {
+      "epoch": 0.2994606256742179,
+      "grad_norm": 0.6598902344703674,
+      "learning_rate": 0.00012452830188679244,
+      "loss": 0.9548360705375671,
+      "step": 694
+    },
+    {
+      "epoch": 0.30032362459546924,
+      "grad_norm": 0.5633156895637512,
+      "learning_rate": 0.00012488769092542677,
+      "loss": 0.992988109588623,
+      "step": 696
+    },
+    {
+      "epoch": 0.3011866235167206,
+      "grad_norm": 0.6098802089691162,
+      "learning_rate": 0.0001252470799640611,
+      "loss": 0.9709890484809875,
+      "step": 698
+    },
+    {
+      "epoch": 0.30204962243797195,
+      "grad_norm": 0.6197102665901184,
+      "learning_rate": 0.0001256064690026954,
+      "loss": 1.018282175064087,
+      "step": 700
+    },
+    {
+      "epoch": 0.30204962243797195,
+      "eval_loss": 1.0030721426010132,
+      "eval_runtime": 655.4533,
+      "eval_samples_per_second": 3.143,
+      "eval_steps_per_second": 3.143,
+      "step": 700
+    },
+    {
+      "epoch": 0.3029126213592233,
+      "grad_norm": 0.5817480683326721,
+      "learning_rate": 0.00012596585804132974,
+      "loss": 0.9147283434867859,
+      "step": 702
+    },
+    {
+      "epoch": 0.30377562028047467,
+      "grad_norm": 0.5976696014404297,
+      "learning_rate": 0.00012632524707996407,
+      "loss": 0.9318362474441528,
+      "step": 704
+    },
+    {
+      "epoch": 0.304638619201726,
+      "grad_norm": 0.6389723420143127,
+      "learning_rate": 0.0001266846361185984,
+      "loss": 0.9500927925109863,
+      "step": 706
+    },
+    {
+      "epoch": 0.3055016181229773,
+      "grad_norm": 0.6485719084739685,
+      "learning_rate": 0.0001270440251572327,
+      "loss": 1.0271424055099487,
+      "step": 708
+    },
+    {
+      "epoch": 0.3063646170442287,
+      "grad_norm": 0.5802455544471741,
+      "learning_rate": 0.00012740341419586703,
+      "loss": 0.9781906008720398,
+      "step": 710
+    },
+    {
+      "epoch": 0.30722761596548004,
+      "grad_norm": 0.6359356641769409,
+      "learning_rate": 0.00012776280323450136,
+      "loss": 1.0195324420928955,
+      "step": 712
+    },
+    {
+      "epoch": 0.3080906148867314,
+      "grad_norm": 0.5975426435470581,
+      "learning_rate": 0.00012812219227313566,
+      "loss": 0.9250738024711609,
+      "step": 714
+    },
+    {
+      "epoch": 0.30895361380798275,
+      "grad_norm": 0.643110454082489,
+      "learning_rate": 0.00012848158131177,
+      "loss": 0.9888015985488892,
+      "step": 716
+    },
+    {
+      "epoch": 0.3098166127292341,
+      "grad_norm": 0.6043205261230469,
+      "learning_rate": 0.00012884097035040432,
+      "loss": 0.9709514379501343,
+      "step": 718
+    },
+    {
+      "epoch": 0.3106796116504854,
+      "grad_norm": 0.5687094926834106,
+      "learning_rate": 0.00012920035938903865,
+      "loss": 1.0272964239120483,
+      "step": 720
+    },
+    {
+      "epoch": 0.31154261057173677,
+      "grad_norm": 0.5688400864601135,
+      "learning_rate": 0.00012955974842767296,
+      "loss": 0.9370370507240295,
+      "step": 722
+    },
+    {
+      "epoch": 0.3124056094929881,
+      "grad_norm": 0.5610610246658325,
+      "learning_rate": 0.00012991913746630729,
+      "loss": 0.9535608291625977,
+      "step": 724
+    },
+    {
+      "epoch": 0.3132686084142395,
+      "grad_norm": 0.6338257193565369,
+      "learning_rate": 0.00013027852650494162,
+      "loss": 1.0188907384872437,
+      "step": 726
+    },
+    {
+      "epoch": 0.31413160733549084,
+      "grad_norm": 0.5365633368492126,
+      "learning_rate": 0.00013063791554357592,
+      "loss": 0.9253716468811035,
+      "step": 728
+    },
+    {
+      "epoch": 0.3149946062567422,
+      "grad_norm": 0.5599163174629211,
+      "learning_rate": 0.00013099730458221025,
+      "loss": 0.8941492438316345,
+      "step": 730
+    },
+    {
+      "epoch": 0.31585760517799355,
+      "grad_norm": 0.6059780716896057,
+      "learning_rate": 0.00013135669362084458,
+      "loss": 0.9831459522247314,
+      "step": 732
+    },
+    {
+      "epoch": 0.31672060409924485,
+      "grad_norm": 0.5596494078636169,
+      "learning_rate": 0.0001317160826594789,
+      "loss": 0.9332310557365417,
+      "step": 734
+    },
+    {
+      "epoch": 0.3175836030204962,
+      "grad_norm": 0.5618010759353638,
+      "learning_rate": 0.0001320754716981132,
+      "loss": 0.9082580208778381,
+      "step": 736
+    },
+    {
+      "epoch": 0.31844660194174756,
+      "grad_norm": 0.6412109732627869,
+      "learning_rate": 0.00013243486073674754,
+      "loss": 1.008690357208252,
+      "step": 738
+    },
+    {
+      "epoch": 0.3193096008629989,
+      "grad_norm": 0.5742355585098267,
+      "learning_rate": 0.00013279424977538187,
+      "loss": 0.9597798585891724,
+      "step": 740
+    },
+    {
+      "epoch": 0.3201725997842503,
+      "grad_norm": 0.6470226645469666,
+      "learning_rate": 0.00013315363881401617,
+      "loss": 0.989331841468811,
+      "step": 742
+    },
+    {
+      "epoch": 0.32103559870550163,
+      "grad_norm": 0.5598039031028748,
+      "learning_rate": 0.0001335130278526505,
+      "loss": 0.8677343130111694,
+      "step": 744
+    },
+    {
+      "epoch": 0.321898597626753,
+      "grad_norm": 0.5441372990608215,
+      "learning_rate": 0.00013387241689128483,
+      "loss": 0.9462730288505554,
+      "step": 746
+    },
+    {
+      "epoch": 0.3227615965480043,
+      "grad_norm": 0.5858626365661621,
+      "learning_rate": 0.00013423180592991916,
+      "loss": 0.994694173336029,
+      "step": 748
+    },
+    {
+      "epoch": 0.32362459546925565,
+      "grad_norm": 0.511372447013855,
+      "learning_rate": 0.00013459119496855347,
+      "loss": 0.9387269616127014,
+      "step": 750
+    },
+    {
+      "epoch": 0.324487594390507,
+      "grad_norm": 0.47798457741737366,
+      "learning_rate": 0.0001349505840071878,
+      "loss": 0.9473881721496582,
+      "step": 752
+    },
+    {
+      "epoch": 0.32535059331175836,
+      "grad_norm": 0.5907022953033447,
+      "learning_rate": 0.0001353099730458221,
+      "loss": 0.9375183582305908,
+      "step": 754
+    },
+    {
+      "epoch": 0.3262135922330097,
+      "grad_norm": 0.618733286857605,
+      "learning_rate": 0.00013566936208445643,
+      "loss": 1.028738260269165,
+      "step": 756
+    },
+    {
+      "epoch": 0.3270765911542611,
+      "grad_norm": 0.5234512090682983,
+      "learning_rate": 0.00013602875112309076,
+      "loss": 0.9420192241668701,
+      "step": 758
+    },
+    {
+      "epoch": 0.32793959007551243,
+      "grad_norm": 0.7036319971084595,
+      "learning_rate": 0.00013638814016172506,
+      "loss": 1.0252270698547363,
+      "step": 760
+    },
+    {
+      "epoch": 0.32880258899676373,
+      "grad_norm": 0.5543172359466553,
+      "learning_rate": 0.0001367475292003594,
+      "loss": 0.8453778028488159,
+      "step": 762
+    },
+    {
+      "epoch": 0.3296655879180151,
+      "grad_norm": 0.5438711643218994,
+      "learning_rate": 0.0001371069182389937,
+      "loss": 0.8659937977790833,
+      "step": 764
+    },
+    {
+      "epoch": 0.33052858683926645,
+      "grad_norm": 0.6390914916992188,
+      "learning_rate": 0.00013746630727762803,
+      "loss": 1.038142442703247,
+      "step": 766
+    },
+    {
+      "epoch": 0.3313915857605178,
+      "grad_norm": 0.50070720911026,
+      "learning_rate": 0.00013782569631626236,
+      "loss": 0.899932861328125,
+      "step": 768
+    },
+    {
+      "epoch": 0.33225458468176916,
+      "grad_norm": 0.5982286334037781,
+      "learning_rate": 0.00013818508535489669,
+      "loss": 0.9712884426116943,
+      "step": 770
+    },
+    {
+      "epoch": 0.3331175836030205,
+      "grad_norm": 0.6588822603225708,
+      "learning_rate": 0.000138544474393531,
+      "loss": 0.9427542686462402,
+      "step": 772
+    },
+    {
+      "epoch": 0.3339805825242718,
+      "grad_norm": 0.6022042632102966,
+      "learning_rate": 0.00013890386343216532,
+      "loss": 0.8961561918258667,
+      "step": 774
+    },
+    {
+      "epoch": 0.3348435814455232,
+      "grad_norm": 0.6595642566680908,
+      "learning_rate": 0.00013926325247079965,
+      "loss": 0.9525937438011169,
+      "step": 776
+    },
+    {
+      "epoch": 0.33570658036677453,
+      "grad_norm": 0.5210421681404114,
+      "learning_rate": 0.00013962264150943395,
+      "loss": 0.9218845367431641,
+      "step": 778
+    },
+    {
+      "epoch": 0.3365695792880259,
+      "grad_norm": 0.549669623374939,
+      "learning_rate": 0.00013998203054806828,
+      "loss": 0.877951443195343,
+      "step": 780
+    },
+    {
+      "epoch": 0.33743257820927725,
+      "grad_norm": 0.5360157489776611,
+      "learning_rate": 0.0001403414195867026,
+      "loss": 0.8670064210891724,
+      "step": 782
+    },
+    {
+      "epoch": 0.3382955771305286,
+      "grad_norm": 0.614734947681427,
+      "learning_rate": 0.00014070080862533694,
+      "loss": 0.9561367630958557,
+      "step": 784
+    },
+    {
+      "epoch": 0.33915857605177996,
+      "grad_norm": 0.5798251628875732,
+      "learning_rate": 0.00014106019766397124,
+      "loss": 0.9132505059242249,
+      "step": 786
+    },
+    {
+      "epoch": 0.34002157497303126,
+      "grad_norm": 0.6267077326774597,
+      "learning_rate": 0.00014141958670260557,
+      "loss": 0.9297707080841064,
+      "step": 788
+    },
+    {
+      "epoch": 0.3408845738942826,
+      "grad_norm": 0.6045349836349487,
+      "learning_rate": 0.0001417789757412399,
+      "loss": 0.9382412433624268,
+      "step": 790
+    },
+    {
+      "epoch": 0.341747572815534,
+      "grad_norm": 0.6125404834747314,
+      "learning_rate": 0.0001421383647798742,
+      "loss": 0.9078555107116699,
+      "step": 792
+    },
+    {
+      "epoch": 0.34261057173678533,
+      "grad_norm": 0.5927051901817322,
+      "learning_rate": 0.00014249775381850854,
+      "loss": 0.899101197719574,
+      "step": 794
+    },
+    {
+      "epoch": 0.3434735706580367,
+      "grad_norm": 0.6315743923187256,
+      "learning_rate": 0.00014285714285714287,
+      "loss": 1.028346300125122,
+      "step": 796
+    },
+    {
+      "epoch": 0.34433656957928804,
+      "grad_norm": 0.549271285533905,
+      "learning_rate": 0.0001432165318957772,
+      "loss": 0.8988189697265625,
+      "step": 798
+    },
+    {
+      "epoch": 0.3451995685005394,
+      "grad_norm": 0.6344245672225952,
+      "learning_rate": 0.0001435759209344115,
+      "loss": 1.0489003658294678,
+      "step": 800
+    },
+    {
+      "epoch": 0.3451995685005394,
+      "eval_loss": 0.9864639639854431,
+      "eval_runtime": 667.3516,
+      "eval_samples_per_second": 3.087,
+      "eval_steps_per_second": 3.087,
+      "step": 800
+    },
+    {
+      "epoch": 0.3460625674217907,
+      "grad_norm": 0.5625309348106384,
+      "learning_rate": 0.00014393530997304583,
+      "loss": 0.8773928284645081,
+      "step": 802
+    },
+    {
+      "epoch": 0.34692556634304206,
+      "grad_norm": 0.5931969285011292,
+      "learning_rate": 0.00014429469901168016,
+      "loss": 0.9116050004959106,
+      "step": 804
+    },
+    {
+      "epoch": 0.3477885652642934,
+      "grad_norm": 0.5189821720123291,
+      "learning_rate": 0.00014465408805031446,
+      "loss": 0.9124425649642944,
+      "step": 806
+    },
+    {
+      "epoch": 0.34865156418554477,
+      "grad_norm": 0.5392254590988159,
+      "learning_rate": 0.0001450134770889488,
+      "loss": 0.9517888426780701,
+      "step": 808
+    },
+    {
+      "epoch": 0.34951456310679613,
+      "grad_norm": 0.5584444999694824,
+      "learning_rate": 0.00014537286612758312,
+      "loss": 0.9947572350502014,
+      "step": 810
+    },
+    {
+      "epoch": 0.3503775620280475,
+      "grad_norm": 0.5188854932785034,
+      "learning_rate": 0.00014573225516621745,
+      "loss": 0.9314022660255432,
+      "step": 812
+    },
+    {
+      "epoch": 0.3512405609492988,
+      "grad_norm": 0.5783659815788269,
+      "learning_rate": 0.00014609164420485176,
+      "loss": 0.9135628938674927,
+      "step": 814
+    },
+    {
+      "epoch": 0.35210355987055014,
+      "grad_norm": 0.550959050655365,
+      "learning_rate": 0.0001464510332434861,
+      "loss": 0.9665075540542603,
+      "step": 816
+    },
+    {
+      "epoch": 0.3529665587918015,
+      "grad_norm": 0.6013346314430237,
+      "learning_rate": 0.00014681042228212042,
+      "loss": 0.9836555123329163,
+      "step": 818
+    },
+    {
+      "epoch": 0.35382955771305286,
+      "grad_norm": 0.49219194054603577,
+      "learning_rate": 0.00014716981132075472,
+      "loss": 0.8900108337402344,
+      "step": 820
+    },
+    {
+      "epoch": 0.3546925566343042,
+      "grad_norm": 0.5517411828041077,
+      "learning_rate": 0.00014752920035938905,
+      "loss": 0.8769304156303406,
+      "step": 822
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.6062695980072021,
+      "learning_rate": 0.00014788858939802338,
+      "loss": 0.9744759202003479,
+      "step": 824
+    },
+    {
+      "epoch": 0.3564185544768069,
+      "grad_norm": 0.5132041573524475,
+      "learning_rate": 0.0001482479784366577,
+      "loss": 0.8875447511672974,
+      "step": 826
+    },
+    {
+      "epoch": 0.3572815533980582,
+      "grad_norm": 0.551799476146698,
+      "learning_rate": 0.000148607367475292,
+      "loss": 0.962710440158844,
+      "step": 828
+    },
+    {
+      "epoch": 0.3581445523193096,
+      "grad_norm": 0.6046625971794128,
+      "learning_rate": 0.00014896675651392634,
+      "loss": 0.8997528553009033,
+      "step": 830
+    },
+    {
+      "epoch": 0.35900755124056094,
+      "grad_norm": 0.560025691986084,
+      "learning_rate": 0.00014932614555256067,
+      "loss": 0.9541417360305786,
+      "step": 832
+    },
+    {
+      "epoch": 0.3598705501618123,
+      "grad_norm": 0.6441047787666321,
+      "learning_rate": 0.00014968553459119498,
+      "loss": 0.907791018486023,
+      "step": 834
+    },
+    {
+      "epoch": 0.36073354908306365,
+      "grad_norm": 0.5636281967163086,
+      "learning_rate": 0.0001500449236298293,
+      "loss": 1.0295937061309814,
+      "step": 836
+    },
+    {
+      "epoch": 0.361596548004315,
+      "grad_norm": 0.5528303384780884,
+      "learning_rate": 0.0001504043126684636,
+      "loss": 0.8875265717506409,
+      "step": 838
+    },
+    {
+      "epoch": 0.36245954692556637,
+      "grad_norm": 0.5345163345336914,
+      "learning_rate": 0.00015076370170709794,
+      "loss": 0.9678915739059448,
+      "step": 840
+    },
+    {
+      "epoch": 0.36332254584681767,
+      "grad_norm": 0.5551225543022156,
+      "learning_rate": 0.00015112309074573224,
+      "loss": 0.9235162734985352,
+      "step": 842
+    },
+    {
+      "epoch": 0.364185544768069,
+      "grad_norm": 0.5131904482841492,
+      "learning_rate": 0.00015148247978436657,
+      "loss": 0.8624292016029358,
+      "step": 844
+    },
+    {
+      "epoch": 0.3650485436893204,
+      "grad_norm": 0.6811004281044006,
+      "learning_rate": 0.0001518418688230009,
+      "loss": 1.0360193252563477,
+      "step": 846
+    },
+    {
+      "epoch": 0.36591154261057174,
+      "grad_norm": 0.6409741640090942,
+      "learning_rate": 0.00015220125786163523,
+      "loss": 0.9254010915756226,
+      "step": 848
+    },
+    {
+      "epoch": 0.3667745415318231,
+      "grad_norm": 0.5534068942070007,
+      "learning_rate": 0.00015256064690026953,
+      "loss": 0.8900630474090576,
+      "step": 850
+    },
+    {
+      "epoch": 0.36763754045307445,
+      "grad_norm": 0.4999487102031708,
+      "learning_rate": 0.00015292003593890386,
+      "loss": 0.88521409034729,
+      "step": 852
+    },
+    {
+      "epoch": 0.3685005393743258,
+      "grad_norm": 0.5805923938751221,
+      "learning_rate": 0.0001532794249775382,
+      "loss": 0.9563921093940735,
+      "step": 854
+    },
+    {
+      "epoch": 0.3693635382955771,
+      "grad_norm": 0.5485470294952393,
+      "learning_rate": 0.0001536388140161725,
+      "loss": 0.8909372687339783,
+      "step": 856
+    },
+    {
+      "epoch": 0.37022653721682847,
+      "grad_norm": 0.5317923426628113,
+      "learning_rate": 0.00015399820305480683,
+      "loss": 0.9145731925964355,
+      "step": 858
+    },
+    {
+      "epoch": 0.3710895361380798,
+      "grad_norm": 0.6073495745658875,
+      "learning_rate": 0.00015435759209344116,
+      "loss": 1.01466965675354,
+      "step": 860
+    },
+    {
+      "epoch": 0.3719525350593312,
+      "grad_norm": 0.566655158996582,
+      "learning_rate": 0.0001547169811320755,
+      "loss": 0.9941825270652771,
+      "step": 862
+    },
+    {
+      "epoch": 0.37281553398058254,
+      "grad_norm": 0.5262459516525269,
+      "learning_rate": 0.0001550763701707098,
+      "loss": 1.0059782266616821,
+      "step": 864
+    },
+    {
+      "epoch": 0.3736785329018339,
+      "grad_norm": 0.6264083981513977,
+      "learning_rate": 0.00015543575920934412,
+      "loss": 1.0332856178283691,
+      "step": 866
+    },
+    {
+      "epoch": 0.3745415318230852,
+      "grad_norm": 0.6575480699539185,
+      "learning_rate": 0.00015579514824797845,
+      "loss": 1.022459626197815,
+      "step": 868
+    },
+    {
+      "epoch": 0.37540453074433655,
+      "grad_norm": 0.6291940212249756,
+      "learning_rate": 0.00015615453728661275,
+      "loss": 0.9550372362136841,
+      "step": 870
+    },
+    {
+      "epoch": 0.3762675296655879,
+      "grad_norm": 0.6710562109947205,
+      "learning_rate": 0.00015651392632524708,
+      "loss": 0.9861716628074646,
+      "step": 872
+    },
+    {
+      "epoch": 0.37713052858683926,
+      "grad_norm": 0.5505748987197876,
+      "learning_rate": 0.0001568733153638814,
+      "loss": 0.9719111919403076,
+      "step": 874
+    },
+    {
+      "epoch": 0.3779935275080906,
+      "grad_norm": 0.5055180788040161,
+      "learning_rate": 0.00015723270440251574,
+      "loss": 0.8698170185089111,
+      "step": 876
+    },
+    {
+      "epoch": 0.378856526429342,
+      "grad_norm": 0.5935947895050049,
+      "learning_rate": 0.00015759209344115005,
+      "loss": 1.029494285583496,
+      "step": 878
+    },
+    {
+      "epoch": 0.37971952535059333,
+      "grad_norm": 0.538325846195221,
+      "learning_rate": 0.00015795148247978438,
+      "loss": 0.923010528087616,
+      "step": 880
+    },
+    {
+      "epoch": 0.38058252427184464,
+      "grad_norm": 0.587297797203064,
+      "learning_rate": 0.0001583108715184187,
+      "loss": 0.9394056797027588,
+      "step": 882
+    },
+    {
+      "epoch": 0.381445523193096,
+      "grad_norm": 0.5910462737083435,
+      "learning_rate": 0.000158670260557053,
+      "loss": 0.9472483992576599,
+      "step": 884
+    },
+    {
+      "epoch": 0.38230852211434735,
+      "grad_norm": 0.629048764705658,
+      "learning_rate": 0.00015902964959568734,
+      "loss": 0.9028263688087463,
+      "step": 886
+    },
+    {
+      "epoch": 0.3831715210355987,
+      "grad_norm": 0.5028086304664612,
+      "learning_rate": 0.00015938903863432167,
+      "loss": 0.9579087495803833,
+      "step": 888
+    },
+    {
+      "epoch": 0.38403451995685006,
+      "grad_norm": 0.5372384190559387,
+      "learning_rate": 0.000159748427672956,
+      "loss": 0.8318673372268677,
+      "step": 890
+    },
+    {
+      "epoch": 0.3848975188781014,
+      "grad_norm": 0.6314184665679932,
+      "learning_rate": 0.0001601078167115903,
+      "loss": 0.9804943203926086,
+      "step": 892
+    },
+    {
+      "epoch": 0.3857605177993528,
+      "grad_norm": 0.5545229911804199,
+      "learning_rate": 0.00016046720575022463,
+      "loss": 1.0078438520431519,
+      "step": 894
+    },
+    {
+      "epoch": 0.3866235167206041,
+      "grad_norm": 0.4674014151096344,
+      "learning_rate": 0.00016082659478885896,
+      "loss": 0.9269036650657654,
+      "step": 896
+    },
+    {
+      "epoch": 0.38748651564185543,
+      "grad_norm": 1.5887153148651123,
+      "learning_rate": 0.00016118598382749326,
+      "loss": 0.8927953243255615,
+      "step": 898
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "grad_norm": 0.5217035412788391,
+      "learning_rate": 0.0001615453728661276,
+      "loss": 0.908074140548706,
+      "step": 900
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "eval_loss": 0.9741895794868469,
+      "eval_runtime": 667.2236,
+      "eval_samples_per_second": 3.087,
+      "eval_steps_per_second": 3.087,
+      "step": 900
+    },
+    {
+      "epoch": 0.38921251348435815,
+      "grad_norm": 0.470498651266098,
+      "learning_rate": 0.00016190476190476192,
+      "loss": 0.9660369157791138,
+      "step": 902
+    },
+    {
+      "epoch": 0.3900755124056095,
+      "grad_norm": 0.5111004114151001,
+      "learning_rate": 0.00016226415094339625,
+      "loss": 0.9236379265785217,
+      "step": 904
+    },
+    {
+      "epoch": 0.39093851132686086,
+      "grad_norm": 0.5872815251350403,
+      "learning_rate": 0.00016262353998203056,
+      "loss": 1.0061595439910889,
+      "step": 906
+    },
+    {
+      "epoch": 0.3918015102481122,
+      "grad_norm": 0.5150740742683411,
+      "learning_rate": 0.0001629829290206649,
+      "loss": 0.8347328901290894,
+      "step": 908
+    },
+    {
+      "epoch": 0.3926645091693635,
+      "grad_norm": 0.46554985642433167,
+      "learning_rate": 0.00016334231805929922,
+      "loss": 0.9091183543205261,
+      "step": 910
+    },
+    {
+      "epoch": 0.3935275080906149,
+      "grad_norm": 0.5292875170707703,
+      "learning_rate": 0.00016370170709793352,
+      "loss": 0.9299798011779785,
+      "step": 912
+    },
+    {
+      "epoch": 0.39439050701186623,
+      "grad_norm": 0.5177125930786133,
+      "learning_rate": 0.00016406109613656785,
+      "loss": 0.942286491394043,
+      "step": 914
+    },
+    {
+      "epoch": 0.3952535059331176,
+      "grad_norm": 0.5564161539077759,
+      "learning_rate": 0.00016442048517520215,
+      "loss": 0.825290858745575,
+      "step": 916
+    },
+    {
+      "epoch": 0.39611650485436894,
+      "grad_norm": 0.5572530031204224,
+      "learning_rate": 0.00016477987421383648,
+      "loss": 0.876898467540741,
+      "step": 918
+    },
+    {
+      "epoch": 0.3969795037756203,
+      "grad_norm": 0.7294673323631287,
+      "learning_rate": 0.0001651392632524708,
+      "loss": 0.8949798941612244,
+      "step": 920
+    },
+    {
+      "epoch": 0.3978425026968716,
+      "grad_norm": 0.5234251022338867,
+      "learning_rate": 0.00016549865229110512,
+      "loss": 0.8457819223403931,
+      "step": 922
+    },
+    {
+      "epoch": 0.39870550161812296,
+      "grad_norm": 0.5273709893226624,
+      "learning_rate": 0.00016585804132973945,
+      "loss": 0.9080174565315247,
+      "step": 924
+    },
+    {
+      "epoch": 0.3995685005393743,
+      "grad_norm": 0.5795063376426697,
+      "learning_rate": 0.00016621743036837378,
+      "loss": 1.0304023027420044,
+      "step": 926
+    },
+    {
+      "epoch": 0.4004314994606257,
+      "grad_norm": 0.6153313517570496,
+      "learning_rate": 0.00016657681940700808,
+      "loss": 0.8900477886199951,
+      "step": 928
+    },
+    {
+      "epoch": 0.40129449838187703,
+      "grad_norm": 0.6293173432350159,
+      "learning_rate": 0.0001669362084456424,
+      "loss": 1.0130009651184082,
+      "step": 930
+    },
+    {
+      "epoch": 0.4021574973031284,
+      "grad_norm": 0.5455223321914673,
+      "learning_rate": 0.00016729559748427674,
+      "loss": 0.9339282512664795,
+      "step": 932
+    },
+    {
+      "epoch": 0.40302049622437974,
+      "grad_norm": 0.5349094271659851,
+      "learning_rate": 0.00016765498652291104,
+      "loss": 0.9628980755805969,
+      "step": 934
+    },
+    {
+      "epoch": 0.40388349514563104,
+      "grad_norm": 0.491227924823761,
+      "learning_rate": 0.00016801437556154537,
+      "loss": 0.8922860026359558,
+      "step": 936
+    },
+    {
+      "epoch": 0.4047464940668824,
+      "grad_norm": 0.6331246495246887,
+      "learning_rate": 0.0001683737646001797,
+      "loss": 1.0470497608184814,
+      "step": 938
+    },
+    {
+      "epoch": 0.40560949298813376,
+      "grad_norm": 0.6079246401786804,
+      "learning_rate": 0.00016873315363881403,
+      "loss": 0.8868283629417419,
+      "step": 940
+    },
+    {
+      "epoch": 0.4064724919093851,
+      "grad_norm": 0.5326972603797913,
+      "learning_rate": 0.00016909254267744833,
+      "loss": 0.9938711524009705,
+      "step": 942
+    },
+    {
+      "epoch": 0.40733549083063647,
+      "grad_norm": 0.47754305601119995,
+      "learning_rate": 0.00016945193171608266,
+      "loss": 0.8280484676361084,
+      "step": 944
+    },
+    {
+      "epoch": 0.4081984897518878,
+      "grad_norm": 0.6683310270309448,
+      "learning_rate": 0.000169811320754717,
+      "loss": 1.089701533317566,
+      "step": 946
+    },
+    {
+      "epoch": 0.4090614886731392,
+      "grad_norm": 0.42798754572868347,
+      "learning_rate": 0.0001701707097933513,
+      "loss": 0.8535542488098145,
+      "step": 948
+    },
+    {
+      "epoch": 0.4099244875943905,
+      "grad_norm": 0.5999574065208435,
+      "learning_rate": 0.00017053009883198563,
+      "loss": 0.9039298295974731,
+      "step": 950
+    },
+    {
+      "epoch": 0.41078748651564184,
+      "grad_norm": 0.5752781629562378,
+      "learning_rate": 0.00017088948787061996,
+      "loss": 0.8786448240280151,
+      "step": 952
+    },
+    {
+      "epoch": 0.4116504854368932,
+      "grad_norm": 0.5121532678604126,
+      "learning_rate": 0.0001712488769092543,
+      "loss": 0.9206072688102722,
+      "step": 954
+    },
+    {
+      "epoch": 0.41251348435814456,
+      "grad_norm": 0.611078143119812,
+      "learning_rate": 0.0001716082659478886,
+      "loss": 0.9246986508369446,
+      "step": 956
+    },
+    {
+      "epoch": 0.4133764832793959,
+      "grad_norm": 0.5101020336151123,
+      "learning_rate": 0.00017196765498652292,
+      "loss": 0.9221894145011902,
+      "step": 958
+    },
+    {
+      "epoch": 0.41423948220064727,
+      "grad_norm": 0.5681450963020325,
+      "learning_rate": 0.00017232704402515725,
+      "loss": 0.9072799682617188,
+      "step": 960
+    },
+    {
+      "epoch": 0.41510248112189857,
+      "grad_norm": 0.47865498065948486,
+      "learning_rate": 0.00017268643306379155,
+      "loss": 0.9460896849632263,
+      "step": 962
+    },
+    {
+      "epoch": 0.4159654800431499,
+      "grad_norm": 0.49861401319503784,
+      "learning_rate": 0.00017304582210242588,
+      "loss": 0.9121519923210144,
+      "step": 964
+    },
+    {
+      "epoch": 0.4168284789644013,
+      "grad_norm": 0.43025892972946167,
+      "learning_rate": 0.0001734052111410602,
+      "loss": 0.8826848864555359,
+      "step": 966
+    },
+    {
+      "epoch": 0.41769147788565264,
+      "grad_norm": 0.4600491225719452,
+      "learning_rate": 0.00017376460017969454,
+      "loss": 0.8756251335144043,
+      "step": 968
+    },
+    {
+      "epoch": 0.418554476806904,
+      "grad_norm": 0.5297656059265137,
+      "learning_rate": 0.00017412398921832885,
+      "loss": 0.9171333312988281,
+      "step": 970
+    },
+    {
+      "epoch": 0.41941747572815535,
+      "grad_norm": 0.4906919002532959,
+      "learning_rate": 0.00017448337825696318,
+      "loss": 0.8887524008750916,
+      "step": 972
+    },
+    {
+      "epoch": 0.4202804746494067,
+      "grad_norm": 0.49263402819633484,
+      "learning_rate": 0.0001748427672955975,
+      "loss": 0.8345810174942017,
+      "step": 974
+    },
+    {
+      "epoch": 0.421143473570658,
+      "grad_norm": 0.5706565380096436,
+      "learning_rate": 0.0001752021563342318,
+      "loss": 0.968651294708252,
+      "step": 976
+    },
+    {
+      "epoch": 0.42200647249190937,
+      "grad_norm": 0.5269908308982849,
+      "learning_rate": 0.00017556154537286614,
+      "loss": 0.9729376435279846,
+      "step": 978
+    },
+    {
+      "epoch": 0.4228694714131607,
+      "grad_norm": 0.47058001160621643,
+      "learning_rate": 0.00017592093441150047,
+      "loss": 0.963884711265564,
+      "step": 980
+    },
+    {
+      "epoch": 0.4237324703344121,
+      "grad_norm": 0.5322962999343872,
+      "learning_rate": 0.0001762803234501348,
+      "loss": 0.8952447175979614,
+      "step": 982
+    },
+    {
+      "epoch": 0.42459546925566344,
+      "grad_norm": 0.5750975012779236,
+      "learning_rate": 0.0001766397124887691,
+      "loss": 0.8932783603668213,
+      "step": 984
+    },
+    {
+      "epoch": 0.4254584681769148,
+      "grad_norm": 0.5539655685424805,
+      "learning_rate": 0.00017699910152740343,
+      "loss": 0.916595458984375,
+      "step": 986
+    },
+    {
+      "epoch": 0.42632146709816615,
+      "grad_norm": 0.568000853061676,
+      "learning_rate": 0.00017735849056603776,
+      "loss": 0.9669626355171204,
+      "step": 988
+    },
+    {
+      "epoch": 0.42718446601941745,
+      "grad_norm": 0.6010684370994568,
+      "learning_rate": 0.00017771787960467206,
+      "loss": 1.0089105367660522,
+      "step": 990
+    },
+    {
+      "epoch": 0.4280474649406688,
+      "grad_norm": 0.6083462238311768,
+      "learning_rate": 0.0001780772686433064,
+      "loss": 0.9810921549797058,
+      "step": 992
+    },
+    {
+      "epoch": 0.42891046386192017,
+      "grad_norm": 0.5076655149459839,
+      "learning_rate": 0.0001784366576819407,
+      "loss": 0.9524372816085815,
+      "step": 994
+    },
+    {
+      "epoch": 0.4297734627831715,
+      "grad_norm": 0.5260922312736511,
+      "learning_rate": 0.00017879604672057503,
+      "loss": 0.881294846534729,
+      "step": 996
+    },
+    {
+      "epoch": 0.4306364617044229,
+      "grad_norm": 0.6130498051643372,
+      "learning_rate": 0.00017915543575920936,
+      "loss": 0.9138327836990356,
+      "step": 998
+    },
+    {
+      "epoch": 0.43149946062567424,
+      "grad_norm": 0.5346242785453796,
+      "learning_rate": 0.00017951482479784366,
+      "loss": 0.8861367106437683,
+      "step": 1000
+    },
+    {
+      "epoch": 0.43149946062567424,
+      "eval_loss": 0.9606748819351196,
+      "eval_runtime": 655.4358,
+      "eval_samples_per_second": 3.143,
+      "eval_steps_per_second": 3.143,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 13908,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.001
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.98992434435586e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/sft_qwen_14B/checkpoints/checkpoint-1000/training_args.bin b/sft_qwen_14B/checkpoints/checkpoint-1000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b023888140f1fb107e8d5ebbfbcb9d9558b09d43
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-1000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4200830b23d19bc86049c280236c4a6b18c26d7061b5a57cc024888ec760920f
+size 5201
diff --git a/sft_qwen_14B/checkpoints/checkpoint-1500/README.md b/sft_qwen_14B/checkpoints/checkpoint-1500/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..779b6406e547b32301fef1d181301a873befe542
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-1500/README.md
@@ -0,0 +1,207 @@
+---
+base_model: runs/cpt_run_14b/merged_14b_cpt_lora
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:runs/cpt_run_14b/merged_14b_cpt_lora
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0
\ No newline at end of file
diff --git a/sft_qwen_14B/checkpoints/checkpoint-1500/adapter_config.json b/sft_qwen_14B/checkpoints/checkpoint-1500/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8ea271115c141fb10c6d899b06f46f21800e1ad6
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-1500/adapter_config.json
@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "runs/cpt_run_14b/merged_14b_cpt_lora",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/sft_qwen_14B/checkpoints/checkpoint-1500/adapter_model.safetensors b/sft_qwen_14B/checkpoints/checkpoint-1500/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..09e3b94469360c1a73bb3858f14c5b5d99c0dc14
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-1500/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d30694443628488e12d237aa3f10dc7201eb3cad1bd3f9502c86c23d3e61559d
+size 100715016
diff --git a/sft_qwen_14B/checkpoints/checkpoint-1500/optimizer.pt b/sft_qwen_14B/checkpoints/checkpoint-1500/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0d380147b570493c3974c5a30bbc14038378b5fb
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-1500/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79236304328b73630e2b46bd5fd41cf80bc8c4ba971c80892b4ca8a2dd60ed90
+size 201650659
diff --git a/sft_qwen_14B/checkpoints/checkpoint-1500/rng_state.pth b/sft_qwen_14B/checkpoints/checkpoint-1500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9dc33f59ebee604673e31bc7bfd6343ec381dbe9
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-1500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:062ed3c2bd7316800413ed3478ac76458e28f1148909e6811779e93c087c1f41
+size 14645
diff --git a/sft_qwen_14B/checkpoints/checkpoint-1500/scheduler.pt b/sft_qwen_14B/checkpoints/checkpoint-1500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..dad542c8b424258f16ce06707e376f05f05078bd
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-1500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a4170f3d34ca4a6959c04cb0d7d28946b661dbf270b5e56d1e31191350e1e65
+size 1465
diff --git a/sft_qwen_14B/checkpoints/checkpoint-1500/trainer_state.json b/sft_qwen_14B/checkpoints/checkpoint-1500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..71f69d60359fedf505b3f38cf821def9e7694851
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-1500/trainer_state.json
@@ -0,0 +1,5413 @@
+{
+  "best_global_step": 1500,
+  "best_metric": 0.8972997665405273,
+  "best_model_checkpoint": "runs/instruct_run_14b_v1/checkpoints/checkpoint-1500",
+  "epoch": 0.6472491909385113,
+  "eval_steps": 100,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008629989212513484,
+      "grad_norm": 0.36567428708076477,
+      "learning_rate": 1.7969451931716084e-07,
+      "loss": 1.6794371604919434,
+      "step": 2
+    },
+    {
+      "epoch": 0.001725997842502697,
+      "grad_norm": 0.4024646580219269,
+      "learning_rate": 5.390835579514825e-07,
+      "loss": 1.6853073835372925,
+      "step": 4
+    },
+    {
+      "epoch": 0.0025889967637540453,
+      "grad_norm": 0.40199393033981323,
+      "learning_rate": 8.984725965858042e-07,
+      "loss": 1.7621158361434937,
+      "step": 6
+    },
+    {
+      "epoch": 0.003451995685005394,
+      "grad_norm": 0.35409677028656006,
+      "learning_rate": 1.257861635220126e-06,
+      "loss": 1.633257269859314,
+      "step": 8
+    },
+    {
+      "epoch": 0.004314994606256742,
+      "grad_norm": 0.39087551832199097,
+      "learning_rate": 1.6172506738544475e-06,
+      "loss": 1.7374768257141113,
+      "step": 10
+    },
+    {
+      "epoch": 0.005177993527508091,
+      "grad_norm": 0.3586857318878174,
+      "learning_rate": 1.9766397124887693e-06,
+      "loss": 1.6955714225769043,
+      "step": 12
+    },
+    {
+      "epoch": 0.006040992448759439,
+      "grad_norm": 0.32755669951438904,
+      "learning_rate": 2.3360287511230908e-06,
+      "loss": 1.720664381980896,
+      "step": 14
+    },
+    {
+      "epoch": 0.006903991370010788,
+      "grad_norm": 0.4054872691631317,
+      "learning_rate": 2.6954177897574127e-06,
+      "loss": 1.6957035064697266,
+      "step": 16
+    },
+    {
+      "epoch": 0.007766990291262136,
+      "grad_norm": 0.37593814730644226,
+      "learning_rate": 3.0548068283917343e-06,
+      "loss": 1.7286947965621948,
+      "step": 18
+    },
+    {
+      "epoch": 0.008629989212513484,
+      "grad_norm": 0.3344813287258148,
+      "learning_rate": 3.414195867026056e-06,
+      "loss": 1.727295994758606,
+      "step": 20
+    },
+    {
+      "epoch": 0.009492988133764833,
+      "grad_norm": 0.357474148273468,
+      "learning_rate": 3.7735849056603773e-06,
+      "loss": 1.6727914810180664,
+      "step": 22
+    },
+    {
+      "epoch": 0.010355987055016181,
+      "grad_norm": 0.39115726947784424,
+      "learning_rate": 4.132973944294699e-06,
+      "loss": 1.6518884897232056,
+      "step": 24
+    },
+    {
+      "epoch": 0.01121898597626753,
+      "grad_norm": 0.4711727201938629,
+      "learning_rate": 4.492362982929021e-06,
+      "loss": 1.7868088483810425,
+      "step": 26
+    },
+    {
+      "epoch": 0.012081984897518877,
+      "grad_norm": 0.34112176299095154,
+      "learning_rate": 4.851752021563342e-06,
+      "loss": 1.6127634048461914,
+      "step": 28
+    },
+    {
+      "epoch": 0.012944983818770227,
+      "grad_norm": 0.5071991682052612,
+      "learning_rate": 5.211141060197664e-06,
+      "loss": 1.7858378887176514,
+      "step": 30
+    },
+    {
+      "epoch": 0.013807982740021575,
+      "grad_norm": 0.42048847675323486,
+      "learning_rate": 5.570530098831986e-06,
+      "loss": 1.7123326063156128,
+      "step": 32
+    },
+    {
+      "epoch": 0.014670981661272923,
+      "grad_norm": 0.48883870244026184,
+      "learning_rate": 5.929919137466308e-06,
+      "loss": 1.737749695777893,
+      "step": 34
+    },
+    {
+      "epoch": 0.015533980582524271,
+      "grad_norm": 0.3311465084552765,
+      "learning_rate": 6.289308176100629e-06,
+      "loss": 1.5578981637954712,
+      "step": 36
+    },
+    {
+      "epoch": 0.01639697950377562,
+      "grad_norm": 0.5178973078727722,
+      "learning_rate": 6.64869721473495e-06,
+      "loss": 1.719806432723999,
+      "step": 38
+    },
+    {
+      "epoch": 0.017259978425026967,
+      "grad_norm": 0.47097742557525635,
+      "learning_rate": 7.008086253369272e-06,
+      "loss": 1.728212833404541,
+      "step": 40
+    },
+    {
+      "epoch": 0.018122977346278317,
+      "grad_norm": 0.5051584243774414,
+      "learning_rate": 7.367475292003594e-06,
+      "loss": 1.6542466878890991,
+      "step": 42
+    },
+    {
+      "epoch": 0.018985976267529667,
+      "grad_norm": 0.4645111560821533,
+      "learning_rate": 7.726864330637915e-06,
+      "loss": 1.7087690830230713,
+      "step": 44
+    },
+    {
+      "epoch": 0.019848975188781013,
+      "grad_norm": 0.5184999704360962,
+      "learning_rate": 8.086253369272237e-06,
+      "loss": 1.7018946409225464,
+      "step": 46
+    },
+    {
+      "epoch": 0.020711974110032363,
+      "grad_norm": 0.4543815851211548,
+      "learning_rate": 8.44564240790656e-06,
+      "loss": 1.6818269491195679,
+      "step": 48
+    },
+    {
+      "epoch": 0.021574973031283712,
+      "grad_norm": 0.44411996006965637,
+      "learning_rate": 8.80503144654088e-06,
+      "loss": 1.5772877931594849,
+      "step": 50
+    },
+    {
+      "epoch": 0.02243797195253506,
+      "grad_norm": 0.3409404158592224,
+      "learning_rate": 9.164420485175203e-06,
+      "loss": 1.498152732849121,
+      "step": 52
+    },
+    {
+      "epoch": 0.02330097087378641,
+      "grad_norm": 0.42104434967041016,
+      "learning_rate": 9.523809523809523e-06,
+      "loss": 1.6189048290252686,
+      "step": 54
+    },
+    {
+      "epoch": 0.024163969795037755,
+      "grad_norm": 0.3756246268749237,
+      "learning_rate": 9.883198562443846e-06,
+      "loss": 1.4596441984176636,
+      "step": 56
+    },
+    {
+      "epoch": 0.025026968716289105,
+      "grad_norm": 0.36214128136634827,
+      "learning_rate": 1.0242587601078168e-05,
+      "loss": 1.503880500793457,
+      "step": 58
+    },
+    {
+      "epoch": 0.025889967637540454,
+      "grad_norm": 0.40893009305000305,
+      "learning_rate": 1.060197663971249e-05,
+      "loss": 1.5912823677062988,
+      "step": 60
+    },
+    {
+      "epoch": 0.0267529665587918,
+      "grad_norm": 0.28710272908210754,
+      "learning_rate": 1.0961365678346811e-05,
+      "loss": 1.2956721782684326,
+      "step": 62
+    },
+    {
+      "epoch": 0.02761596548004315,
+      "grad_norm": 0.304573118686676,
+      "learning_rate": 1.1320754716981132e-05,
+      "loss": 1.4648056030273438,
+      "step": 64
+    },
+    {
+      "epoch": 0.0284789644012945,
+      "grad_norm": 0.36523914337158203,
+      "learning_rate": 1.1680143755615454e-05,
+      "loss": 1.6078968048095703,
+      "step": 66
+    },
+    {
+      "epoch": 0.029341963322545846,
+      "grad_norm": 0.37929031252861023,
+      "learning_rate": 1.2039532794249775e-05,
+      "loss": 1.5969421863555908,
+      "step": 68
+    },
+    {
+      "epoch": 0.030204962243797196,
+      "grad_norm": 0.3053947389125824,
+      "learning_rate": 1.2398921832884097e-05,
+      "loss": 1.4312325716018677,
+      "step": 70
+    },
+    {
+      "epoch": 0.031067961165048542,
+      "grad_norm": 0.3028779923915863,
+      "learning_rate": 1.275831087151842e-05,
+      "loss": 1.4101300239562988,
+      "step": 72
+    },
+    {
+      "epoch": 0.03193096008629989,
+      "grad_norm": 0.29649803042411804,
+      "learning_rate": 1.3117699910152742e-05,
+      "loss": 1.4553817510604858,
+      "step": 74
+    },
+    {
+      "epoch": 0.03279395900755124,
+      "grad_norm": 0.26032644510269165,
+      "learning_rate": 1.3477088948787062e-05,
+      "loss": 1.4623000621795654,
+      "step": 76
+    },
+    {
+      "epoch": 0.03365695792880259,
+      "grad_norm": 0.33558446168899536,
+      "learning_rate": 1.3836477987421385e-05,
+      "loss": 1.5181745290756226,
+      "step": 78
+    },
+    {
+      "epoch": 0.034519956850053934,
+      "grad_norm": 0.28307804465293884,
+      "learning_rate": 1.4195867026055706e-05,
+      "loss": 1.4397861957550049,
+      "step": 80
+    },
+    {
+      "epoch": 0.035382955771305284,
+      "grad_norm": 0.3451690673828125,
+      "learning_rate": 1.455525606469003e-05,
+      "loss": 1.463841199874878,
+      "step": 82
+    },
+    {
+      "epoch": 0.036245954692556634,
+      "grad_norm": 0.3248669505119324,
+      "learning_rate": 1.4914645103324348e-05,
+      "loss": 1.3554227352142334,
+      "step": 84
+    },
+    {
+      "epoch": 0.037108953613807984,
+      "grad_norm": 0.2855011224746704,
+      "learning_rate": 1.527403414195867e-05,
+      "loss": 1.2810425758361816,
+      "step": 86
+    },
+    {
+      "epoch": 0.03797195253505933,
+      "grad_norm": 0.33365535736083984,
+      "learning_rate": 1.5633423180592992e-05,
+      "loss": 1.428163766860962,
+      "step": 88
+    },
+    {
+      "epoch": 0.038834951456310676,
+      "grad_norm": 0.34099438786506653,
+      "learning_rate": 1.5992812219227316e-05,
+      "loss": 1.3487578630447388,
+      "step": 90
+    },
+    {
+      "epoch": 0.039697950377562026,
+      "grad_norm": 0.39247506856918335,
+      "learning_rate": 1.6352201257861635e-05,
+      "loss": 1.30057954788208,
+      "step": 92
+    },
+    {
+      "epoch": 0.040560949298813376,
+      "grad_norm": 0.32692041993141174,
+      "learning_rate": 1.671159029649596e-05,
+      "loss": 1.2923580408096313,
+      "step": 94
+    },
+    {
+      "epoch": 0.041423948220064725,
+      "grad_norm": 0.43452519178390503,
+      "learning_rate": 1.707097933513028e-05,
+      "loss": 1.5002273321151733,
+      "step": 96
+    },
+    {
+      "epoch": 0.042286947141316075,
+      "grad_norm": 0.3251534402370453,
+      "learning_rate": 1.7430368373764602e-05,
+      "loss": 1.330254077911377,
+      "step": 98
+    },
+    {
+      "epoch": 0.043149946062567425,
+      "grad_norm": 0.3198273479938507,
+      "learning_rate": 1.778975741239892e-05,
+      "loss": 1.3054943084716797,
+      "step": 100
+    },
+    {
+      "epoch": 0.043149946062567425,
+      "eval_loss": 1.366738200187683,
+      "eval_runtime": 651.8198,
+      "eval_samples_per_second": 3.16,
+      "eval_steps_per_second": 3.16,
+      "step": 100
+    },
+    {
+      "epoch": 0.04401294498381877,
+      "grad_norm": 0.37364065647125244,
+      "learning_rate": 1.8149146451033245e-05,
+      "loss": 1.314281940460205,
+      "step": 102
+    },
+    {
+      "epoch": 0.04487594390507012,
+      "grad_norm": 0.39384758472442627,
+      "learning_rate": 1.8508535489667568e-05,
+      "loss": 1.2737246751785278,
+      "step": 104
+    },
+    {
+      "epoch": 0.04573894282632147,
+      "grad_norm": 0.3521905541419983,
+      "learning_rate": 1.8867924528301888e-05,
+      "loss": 1.3113226890563965,
+      "step": 106
+    },
+    {
+      "epoch": 0.04660194174757282,
+      "grad_norm": 0.33531463146209717,
+      "learning_rate": 1.9227313566936208e-05,
+      "loss": 1.3253653049468994,
+      "step": 108
+    },
+    {
+      "epoch": 0.04746494066882417,
+      "grad_norm": 0.35596340894699097,
+      "learning_rate": 1.958670260557053e-05,
+      "loss": 1.3236849308013916,
+      "step": 110
+    },
+    {
+      "epoch": 0.04832793959007551,
+      "grad_norm": 0.36028242111206055,
+      "learning_rate": 1.9946091644204854e-05,
+      "loss": 1.183128833770752,
+      "step": 112
+    },
+    {
+      "epoch": 0.04919093851132686,
+      "grad_norm": 0.42109814286231995,
+      "learning_rate": 2.0305480682839174e-05,
+      "loss": 1.2741888761520386,
+      "step": 114
+    },
+    {
+      "epoch": 0.05005393743257821,
+      "grad_norm": 0.39675939083099365,
+      "learning_rate": 2.0664869721473494e-05,
+      "loss": 1.3050109148025513,
+      "step": 116
+    },
+    {
+      "epoch": 0.05091693635382956,
+      "grad_norm": 0.4414141774177551,
+      "learning_rate": 2.1024258760107817e-05,
+      "loss": 1.2472094297409058,
+      "step": 118
+    },
+    {
+      "epoch": 0.05177993527508091,
+      "grad_norm": 0.42872729897499084,
+      "learning_rate": 2.138364779874214e-05,
+      "loss": 1.3338921070098877,
+      "step": 120
+    },
+    {
+      "epoch": 0.05264293419633225,
+      "grad_norm": 0.38336244225502014,
+      "learning_rate": 2.174303683737646e-05,
+      "loss": 1.322908878326416,
+      "step": 122
+    },
+    {
+      "epoch": 0.0535059331175836,
+      "grad_norm": 0.41046878695487976,
+      "learning_rate": 2.2102425876010783e-05,
+      "loss": 1.2169240713119507,
+      "step": 124
+    },
+    {
+      "epoch": 0.05436893203883495,
+      "grad_norm": 0.39460113644599915,
+      "learning_rate": 2.2461814914645103e-05,
+      "loss": 1.2085309028625488,
+      "step": 126
+    },
+    {
+      "epoch": 0.0552319309600863,
+      "grad_norm": 0.42829909920692444,
+      "learning_rate": 2.2821203953279426e-05,
+      "loss": 1.2969133853912354,
+      "step": 128
+    },
+    {
+      "epoch": 0.05609492988133765,
+      "grad_norm": 0.3940851390361786,
+      "learning_rate": 2.3180592991913746e-05,
+      "loss": 1.1892330646514893,
+      "step": 130
+    },
+    {
+      "epoch": 0.056957928802589,
+      "grad_norm": 0.45011839270591736,
+      "learning_rate": 2.353998203054807e-05,
+      "loss": 1.2082979679107666,
+      "step": 132
+    },
+    {
+      "epoch": 0.05782092772384034,
+      "grad_norm": 0.46059420704841614,
+      "learning_rate": 2.3899371069182393e-05,
+      "loss": 1.2388817071914673,
+      "step": 134
+    },
+    {
+      "epoch": 0.05868392664509169,
+      "grad_norm": 0.41085872054100037,
+      "learning_rate": 2.4258760107816713e-05,
+      "loss": 1.193917155265808,
+      "step": 136
+    },
+    {
+      "epoch": 0.05954692556634304,
+      "grad_norm": 0.4024205207824707,
+      "learning_rate": 2.4618149146451032e-05,
+      "loss": 1.1514034271240234,
+      "step": 138
+    },
+    {
+      "epoch": 0.06040992448759439,
+      "grad_norm": 0.3893793523311615,
+      "learning_rate": 2.4977538185085356e-05,
+      "loss": 1.1626157760620117,
+      "step": 140
+    },
+    {
+      "epoch": 0.06127292340884574,
+      "grad_norm": 0.4456317126750946,
+      "learning_rate": 2.5336927223719675e-05,
+      "loss": 1.1627076864242554,
+      "step": 142
+    },
+    {
+      "epoch": 0.062135922330097085,
+      "grad_norm": 0.5050215125083923,
+      "learning_rate": 2.5696316262354e-05,
+      "loss": 1.3038755655288696,
+      "step": 144
+    },
+    {
+      "epoch": 0.06299892125134844,
+      "grad_norm": 0.4071207642555237,
+      "learning_rate": 2.605570530098832e-05,
+      "loss": 1.1708844900131226,
+      "step": 146
+    },
+    {
+      "epoch": 0.06386192017259978,
+      "grad_norm": 0.4363228678703308,
+      "learning_rate": 2.641509433962264e-05,
+      "loss": 1.2149070501327515,
+      "step": 148
+    },
+    {
+      "epoch": 0.06472491909385113,
+      "grad_norm": 0.4436556398868561,
+      "learning_rate": 2.6774483378256965e-05,
+      "loss": 1.1942368745803833,
+      "step": 150
+    },
+    {
+      "epoch": 0.06558791801510248,
+      "grad_norm": 0.4068629741668701,
+      "learning_rate": 2.7133872416891288e-05,
+      "loss": 1.1799161434173584,
+      "step": 152
+    },
+    {
+      "epoch": 0.06645091693635383,
+      "grad_norm": 0.5291106700897217,
+      "learning_rate": 2.7493261455525608e-05,
+      "loss": 1.1832845211029053,
+      "step": 154
+    },
+    {
+      "epoch": 0.06731391585760518,
+      "grad_norm": 0.4410109221935272,
+      "learning_rate": 2.785265049415993e-05,
+      "loss": 1.1696993112564087,
+      "step": 156
+    },
+    {
+      "epoch": 0.06817691477885653,
+      "grad_norm": 0.4858371913433075,
+      "learning_rate": 2.8212039532794248e-05,
+      "loss": 1.2036973237991333,
+      "step": 158
+    },
+    {
+      "epoch": 0.06903991370010787,
+      "grad_norm": 0.45373693108558655,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 1.1145079135894775,
+      "step": 160
+    },
+    {
+      "epoch": 0.06990291262135923,
+      "grad_norm": 0.4881038963794708,
+      "learning_rate": 2.8930817610062894e-05,
+      "loss": 1.173502802848816,
+      "step": 162
+    },
+    {
+      "epoch": 0.07076591154261057,
+      "grad_norm": 0.576934814453125,
+      "learning_rate": 2.9290206648697217e-05,
+      "loss": 1.250414490699768,
+      "step": 164
+    },
+    {
+      "epoch": 0.07162891046386193,
+      "grad_norm": 0.4900001287460327,
+      "learning_rate": 2.9649595687331537e-05,
+      "loss": 1.0721495151519775,
+      "step": 166
+    },
+    {
+      "epoch": 0.07249190938511327,
+      "grad_norm": 0.4440019726753235,
+      "learning_rate": 3.000898472596586e-05,
+      "loss": 1.0689374208450317,
+      "step": 168
+    },
+    {
+      "epoch": 0.07335490830636461,
+      "grad_norm": 0.4267268180847168,
+      "learning_rate": 3.0368373764600184e-05,
+      "loss": 1.2095128297805786,
+      "step": 170
+    },
+    {
+      "epoch": 0.07421790722761597,
+      "grad_norm": 0.6062787771224976,
+      "learning_rate": 3.0727762803234503e-05,
+      "loss": 1.077776551246643,
+      "step": 172
+    },
+    {
+      "epoch": 0.07508090614886731,
+      "grad_norm": 0.49510180950164795,
+      "learning_rate": 3.108715184186882e-05,
+      "loss": 1.144006371498108,
+      "step": 174
+    },
+    {
+      "epoch": 0.07594390507011867,
+      "grad_norm": 0.4670701026916504,
+      "learning_rate": 3.144654088050314e-05,
+      "loss": 1.1663392782211304,
+      "step": 176
+    },
+    {
+      "epoch": 0.07680690399137001,
+      "grad_norm": 0.5615383386611938,
+      "learning_rate": 3.1805929919137466e-05,
+      "loss": 1.1665973663330078,
+      "step": 178
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "grad_norm": 0.47305551171302795,
+      "learning_rate": 3.216531895777179e-05,
+      "loss": 1.1337063312530518,
+      "step": 180
+    },
+    {
+      "epoch": 0.07853290183387271,
+      "grad_norm": 0.5127068758010864,
+      "learning_rate": 3.252470799640611e-05,
+      "loss": 1.072874903678894,
+      "step": 182
+    },
+    {
+      "epoch": 0.07939590075512405,
+      "grad_norm": 0.632448136806488,
+      "learning_rate": 3.2884097035040436e-05,
+      "loss": 1.1577240228652954,
+      "step": 184
+    },
+    {
+      "epoch": 0.08025889967637541,
+      "grad_norm": 0.4041025638580322,
+      "learning_rate": 3.324348607367476e-05,
+      "loss": 1.1186822652816772,
+      "step": 186
+    },
+    {
+      "epoch": 0.08112189859762675,
+      "grad_norm": 0.5239102244377136,
+      "learning_rate": 3.3602875112309076e-05,
+      "loss": 1.1468429565429688,
+      "step": 188
+    },
+    {
+      "epoch": 0.08198489751887811,
+      "grad_norm": 0.4486575424671173,
+      "learning_rate": 3.39622641509434e-05,
+      "loss": 1.0017019510269165,
+      "step": 190
+    },
+    {
+      "epoch": 0.08284789644012945,
+      "grad_norm": 0.4994317293167114,
+      "learning_rate": 3.4321653189577715e-05,
+      "loss": 1.1901532411575317,
+      "step": 192
+    },
+    {
+      "epoch": 0.0837108953613808,
+      "grad_norm": 0.5023699998855591,
+      "learning_rate": 3.468104222821204e-05,
+      "loss": 1.1398564577102661,
+      "step": 194
+    },
+    {
+      "epoch": 0.08457389428263215,
+      "grad_norm": 0.5077701807022095,
+      "learning_rate": 3.504043126684636e-05,
+      "loss": 1.1390413045883179,
+      "step": 196
+    },
+    {
+      "epoch": 0.0854368932038835,
+      "grad_norm": 0.5527892112731934,
+      "learning_rate": 3.5399820305480685e-05,
+      "loss": 1.1411432027816772,
+      "step": 198
+    },
+    {
+      "epoch": 0.08629989212513485,
+      "grad_norm": 0.5572488903999329,
+      "learning_rate": 3.575920934411501e-05,
+      "loss": 1.071260690689087,
+      "step": 200
+    },
+    {
+      "epoch": 0.08629989212513485,
+      "eval_loss": 1.1519012451171875,
+      "eval_runtime": 654.6055,
+      "eval_samples_per_second": 3.147,
+      "eval_steps_per_second": 3.147,
+      "step": 200
+    },
+    {
+      "epoch": 0.08716289104638619,
+      "grad_norm": 0.5134095549583435,
+      "learning_rate": 3.611859838274933e-05,
+      "loss": 1.138135552406311,
+      "step": 202
+    },
+    {
+      "epoch": 0.08802588996763754,
+      "grad_norm": 0.5166040658950806,
+      "learning_rate": 3.647798742138365e-05,
+      "loss": 1.111999273300171,
+      "step": 204
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.5336993336677551,
+      "learning_rate": 3.683737646001797e-05,
+      "loss": 1.1031352281570435,
+      "step": 206
+    },
+    {
+      "epoch": 0.08975188781014024,
+      "grad_norm": 0.8289600014686584,
+      "learning_rate": 3.7196765498652294e-05,
+      "loss": 1.0388667583465576,
+      "step": 208
+    },
+    {
+      "epoch": 0.09061488673139159,
+      "grad_norm": 0.47992637753486633,
+      "learning_rate": 3.755615453728661e-05,
+      "loss": 1.0950241088867188,
+      "step": 210
+    },
+    {
+      "epoch": 0.09147788565264293,
+      "grad_norm": 0.5629691481590271,
+      "learning_rate": 3.7915543575920934e-05,
+      "loss": 1.0361733436584473,
+      "step": 212
+    },
+    {
+      "epoch": 0.09234088457389428,
+      "grad_norm": 0.5515111684799194,
+      "learning_rate": 3.827493261455526e-05,
+      "loss": 1.0922447443008423,
+      "step": 214
+    },
+    {
+      "epoch": 0.09320388349514563,
+      "grad_norm": 0.5078643560409546,
+      "learning_rate": 3.863432165318958e-05,
+      "loss": 1.0866856575012207,
+      "step": 216
+    },
+    {
+      "epoch": 0.09406688241639698,
+      "grad_norm": 0.6046127676963806,
+      "learning_rate": 3.8993710691823904e-05,
+      "loss": 1.1231595277786255,
+      "step": 218
+    },
+    {
+      "epoch": 0.09492988133764833,
+      "grad_norm": 0.6255762577056885,
+      "learning_rate": 3.935309973045822e-05,
+      "loss": 1.099171757698059,
+      "step": 220
+    },
+    {
+      "epoch": 0.09579288025889968,
+      "grad_norm": 0.6036638021469116,
+      "learning_rate": 3.971248876909254e-05,
+      "loss": 1.0557761192321777,
+      "step": 222
+    },
+    {
+      "epoch": 0.09665587918015102,
+      "grad_norm": 0.5520529747009277,
+      "learning_rate": 4.0071877807726867e-05,
+      "loss": 1.0467877388000488,
+      "step": 224
+    },
+    {
+      "epoch": 0.09751887810140238,
+      "grad_norm": 0.5958684682846069,
+      "learning_rate": 4.043126684636119e-05,
+      "loss": 1.17941153049469,
+      "step": 226
+    },
+    {
+      "epoch": 0.09838187702265372,
+      "grad_norm": 0.5283281803131104,
+      "learning_rate": 4.079065588499551e-05,
+      "loss": 1.104217767715454,
+      "step": 228
+    },
+    {
+      "epoch": 0.09924487594390508,
+      "grad_norm": 0.5608792901039124,
+      "learning_rate": 4.115004492362983e-05,
+      "loss": 1.0900640487670898,
+      "step": 230
+    },
+    {
+      "epoch": 0.10010787486515642,
+      "grad_norm": 0.555964469909668,
+      "learning_rate": 4.150943396226415e-05,
+      "loss": 0.9887422323226929,
+      "step": 232
+    },
+    {
+      "epoch": 0.10097087378640776,
+      "grad_norm": 0.5875785946846008,
+      "learning_rate": 4.1868823000898476e-05,
+      "loss": 1.1298567056655884,
+      "step": 234
+    },
+    {
+      "epoch": 0.10183387270765912,
+      "grad_norm": 0.4544795751571655,
+      "learning_rate": 4.222821203953279e-05,
+      "loss": 1.0957067012786865,
+      "step": 236
+    },
+    {
+      "epoch": 0.10269687162891046,
+      "grad_norm": 0.564145565032959,
+      "learning_rate": 4.2587601078167116e-05,
+      "loss": 1.0328738689422607,
+      "step": 238
+    },
+    {
+      "epoch": 0.10355987055016182,
+      "grad_norm": 0.6285979747772217,
+      "learning_rate": 4.294699011680144e-05,
+      "loss": 1.1085515022277832,
+      "step": 240
+    },
+    {
+      "epoch": 0.10442286947141316,
+      "grad_norm": 0.6442288756370544,
+      "learning_rate": 4.330637915543576e-05,
+      "loss": 1.1291271448135376,
+      "step": 242
+    },
+    {
+      "epoch": 0.1052858683926645,
+      "grad_norm": 0.6137154698371887,
+      "learning_rate": 4.3665768194070085e-05,
+      "loss": 1.1759567260742188,
+      "step": 244
+    },
+    {
+      "epoch": 0.10614886731391586,
+      "grad_norm": 0.5906805992126465,
+      "learning_rate": 4.402515723270441e-05,
+      "loss": 1.148414969444275,
+      "step": 246
+    },
+    {
+      "epoch": 0.1070118662351672,
+      "grad_norm": 0.5382888913154602,
+      "learning_rate": 4.438454627133873e-05,
+      "loss": 1.0749616622924805,
+      "step": 248
+    },
+    {
+      "epoch": 0.10787486515641856,
+      "grad_norm": 0.6185492873191833,
+      "learning_rate": 4.474393530997305e-05,
+      "loss": 1.2235801219940186,
+      "step": 250
+    },
+    {
+      "epoch": 0.1087378640776699,
+      "grad_norm": 0.5981597900390625,
+      "learning_rate": 4.5103324348607365e-05,
+      "loss": 1.1390639543533325,
+      "step": 252
+    },
+    {
+      "epoch": 0.10960086299892124,
+      "grad_norm": 0.5664694905281067,
+      "learning_rate": 4.546271338724169e-05,
+      "loss": 1.171774983406067,
+      "step": 254
+    },
+    {
+      "epoch": 0.1104638619201726,
+      "grad_norm": 0.7071851491928101,
+      "learning_rate": 4.582210242587601e-05,
+      "loss": 1.1704237461090088,
+      "step": 256
+    },
+    {
+      "epoch": 0.11132686084142394,
+      "grad_norm": 0.5815614461898804,
+      "learning_rate": 4.6181491464510334e-05,
+      "loss": 1.0619677305221558,
+      "step": 258
+    },
+    {
+      "epoch": 0.1121898597626753,
+      "grad_norm": 0.6481915712356567,
+      "learning_rate": 4.654088050314466e-05,
+      "loss": 1.0824390649795532,
+      "step": 260
+    },
+    {
+      "epoch": 0.11305285868392664,
+      "grad_norm": 0.5988591313362122,
+      "learning_rate": 4.690026954177898e-05,
+      "loss": 1.087929606437683,
+      "step": 262
+    },
+    {
+      "epoch": 0.113915857605178,
+      "grad_norm": 0.6545296311378479,
+      "learning_rate": 4.7259658580413304e-05,
+      "loss": 1.0936195850372314,
+      "step": 264
+    },
+    {
+      "epoch": 0.11477885652642934,
+      "grad_norm": 0.5826204419136047,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 1.0433681011199951,
+      "step": 266
+    },
+    {
+      "epoch": 0.11564185544768069,
+      "grad_norm": 0.5907514095306396,
+      "learning_rate": 4.7978436657681944e-05,
+      "loss": 1.0719536542892456,
+      "step": 268
+    },
+    {
+      "epoch": 0.11650485436893204,
+      "grad_norm": 0.524394154548645,
+      "learning_rate": 4.833782569631627e-05,
+      "loss": 1.0231504440307617,
+      "step": 270
+    },
+    {
+      "epoch": 0.11736785329018339,
+      "grad_norm": 0.5472846031188965,
+      "learning_rate": 4.869721473495058e-05,
+      "loss": 0.9905915260314941,
+      "step": 272
+    },
+    {
+      "epoch": 0.11823085221143474,
+      "grad_norm": 0.727922260761261,
+      "learning_rate": 4.9056603773584906e-05,
+      "loss": 1.213677167892456,
+      "step": 274
+    },
+    {
+      "epoch": 0.11909385113268608,
+      "grad_norm": 0.6009684801101685,
+      "learning_rate": 4.941599281221923e-05,
+      "loss": 1.0052144527435303,
+      "step": 276
+    },
+    {
+      "epoch": 0.11995685005393743,
+      "grad_norm": 0.6564669013023376,
+      "learning_rate": 4.977538185085355e-05,
+      "loss": 1.108136773109436,
+      "step": 278
+    },
+    {
+      "epoch": 0.12081984897518878,
+      "grad_norm": 0.650074303150177,
+      "learning_rate": 5.013477088948787e-05,
+      "loss": 0.9700815677642822,
+      "step": 280
+    },
+    {
+      "epoch": 0.12168284789644013,
+      "grad_norm": 0.5772947072982788,
+      "learning_rate": 5.04941599281222e-05,
+      "loss": 1.038031816482544,
+      "step": 282
+    },
+    {
+      "epoch": 0.12254584681769148,
+      "grad_norm": 0.7293002009391785,
+      "learning_rate": 5.0853548966756516e-05,
+      "loss": 1.1063730716705322,
+      "step": 284
+    },
+    {
+      "epoch": 0.12340884573894283,
+      "grad_norm": 0.7937333583831787,
+      "learning_rate": 5.1212938005390846e-05,
+      "loss": 1.128495693206787,
+      "step": 286
+    },
+    {
+      "epoch": 0.12427184466019417,
+      "grad_norm": 0.48499324917793274,
+      "learning_rate": 5.157232704402516e-05,
+      "loss": 0.9438712000846863,
+      "step": 288
+    },
+    {
+      "epoch": 0.12513484358144553,
+      "grad_norm": 0.6010656952857971,
+      "learning_rate": 5.193171608265948e-05,
+      "loss": 1.0872881412506104,
+      "step": 290
+    },
+    {
+      "epoch": 0.12599784250269688,
+      "grad_norm": 0.6240811944007874,
+      "learning_rate": 5.22911051212938e-05,
+      "loss": 1.110992193222046,
+      "step": 292
+    },
+    {
+      "epoch": 0.1268608414239482,
+      "grad_norm": 0.7172768712043762,
+      "learning_rate": 5.265049415992812e-05,
+      "loss": 1.1109752655029297,
+      "step": 294
+    },
+    {
+      "epoch": 0.12772384034519957,
+      "grad_norm": 0.6442400217056274,
+      "learning_rate": 5.300988319856245e-05,
+      "loss": 1.05553138256073,
+      "step": 296
+    },
+    {
+      "epoch": 0.12858683926645093,
+      "grad_norm": 0.7074702382087708,
+      "learning_rate": 5.3369272237196765e-05,
+      "loss": 1.0717648267745972,
+      "step": 298
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "grad_norm": 0.5277591347694397,
+      "learning_rate": 5.3728661275831095e-05,
+      "loss": 0.9777541756629944,
+      "step": 300
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "eval_loss": 1.0977506637573242,
+      "eval_runtime": 662.1728,
+      "eval_samples_per_second": 3.111,
+      "eval_steps_per_second": 3.111,
+      "step": 300
+    },
+    {
+      "epoch": 0.1303128371089536,
+      "grad_norm": 0.7252246737480164,
+      "learning_rate": 5.408805031446541e-05,
+      "loss": 1.075905203819275,
+      "step": 302
+    },
+    {
+      "epoch": 0.13117583603020497,
+      "grad_norm": 0.7003294229507446,
+      "learning_rate": 5.444743935309974e-05,
+      "loss": 1.1117515563964844,
+      "step": 304
+    },
+    {
+      "epoch": 0.13203883495145632,
+      "grad_norm": 0.5878211259841919,
+      "learning_rate": 5.480682839173406e-05,
+      "loss": 1.0289191007614136,
+      "step": 306
+    },
+    {
+      "epoch": 0.13290183387270765,
+      "grad_norm": 0.7133644223213196,
+      "learning_rate": 5.5166217430368374e-05,
+      "loss": 1.0199183225631714,
+      "step": 308
+    },
+    {
+      "epoch": 0.133764832793959,
+      "grad_norm": 0.6098423600196838,
+      "learning_rate": 5.55256064690027e-05,
+      "loss": 1.0132375955581665,
+      "step": 310
+    },
+    {
+      "epoch": 0.13462783171521037,
+      "grad_norm": 0.6386916041374207,
+      "learning_rate": 5.5884995507637014e-05,
+      "loss": 1.1595754623413086,
+      "step": 312
+    },
+    {
+      "epoch": 0.1354908306364617,
+      "grad_norm": 0.6563469767570496,
+      "learning_rate": 5.6244384546271344e-05,
+      "loss": 1.0921307802200317,
+      "step": 314
+    },
+    {
+      "epoch": 0.13635382955771305,
+      "grad_norm": 0.6388015747070312,
+      "learning_rate": 5.660377358490566e-05,
+      "loss": 1.0200815200805664,
+      "step": 316
+    },
+    {
+      "epoch": 0.1372168284789644,
+      "grad_norm": 0.6026274561882019,
+      "learning_rate": 5.696316262353999e-05,
+      "loss": 0.9339485764503479,
+      "step": 318
+    },
+    {
+      "epoch": 0.13807982740021574,
+      "grad_norm": 0.619800865650177,
+      "learning_rate": 5.732255166217431e-05,
+      "loss": 1.0268478393554688,
+      "step": 320
+    },
+    {
+      "epoch": 0.1389428263214671,
+      "grad_norm": 0.5924715399742126,
+      "learning_rate": 5.768194070080862e-05,
+      "loss": 1.1394236087799072,
+      "step": 322
+    },
+    {
+      "epoch": 0.13980582524271845,
+      "grad_norm": 0.6829012036323547,
+      "learning_rate": 5.804132973944295e-05,
+      "loss": 1.002437949180603,
+      "step": 324
+    },
+    {
+      "epoch": 0.1406688241639698,
+      "grad_norm": 0.7012544274330139,
+      "learning_rate": 5.840071877807727e-05,
+      "loss": 1.132503628730774,
+      "step": 326
+    },
+    {
+      "epoch": 0.14153182308522114,
+      "grad_norm": 0.7921599745750427,
+      "learning_rate": 5.876010781671159e-05,
+      "loss": 1.1859129667282104,
+      "step": 328
+    },
+    {
+      "epoch": 0.1423948220064725,
+      "grad_norm": 0.6373353004455566,
+      "learning_rate": 5.9119496855345916e-05,
+      "loss": 1.0896776914596558,
+      "step": 330
+    },
+    {
+      "epoch": 0.14325782092772385,
+      "grad_norm": 0.6174030900001526,
+      "learning_rate": 5.947888589398024e-05,
+      "loss": 1.0691723823547363,
+      "step": 332
+    },
+    {
+      "epoch": 0.14412081984897518,
+      "grad_norm": 0.5110617280006409,
+      "learning_rate": 5.9838274932614556e-05,
+      "loss": 1.0144777297973633,
+      "step": 334
+    },
+    {
+      "epoch": 0.14498381877022654,
+      "grad_norm": 0.5580511093139648,
+      "learning_rate": 6.019766397124887e-05,
+      "loss": 0.9955101609230042,
+      "step": 336
+    },
+    {
+      "epoch": 0.1458468176914779,
+      "grad_norm": 0.6427345275878906,
+      "learning_rate": 6.05570530098832e-05,
+      "loss": 0.9863013625144958,
+      "step": 338
+    },
+    {
+      "epoch": 0.14670981661272922,
+      "grad_norm": 0.7464537024497986,
+      "learning_rate": 6.091644204851752e-05,
+      "loss": 1.0682255029678345,
+      "step": 340
+    },
+    {
+      "epoch": 0.14757281553398058,
+      "grad_norm": 0.599926769733429,
+      "learning_rate": 6.127583108715184e-05,
+      "loss": 1.034083366394043,
+      "step": 342
+    },
+    {
+      "epoch": 0.14843581445523193,
+      "grad_norm": 0.6320257186889648,
+      "learning_rate": 6.163522012578616e-05,
+      "loss": 1.0776089429855347,
+      "step": 344
+    },
+    {
+      "epoch": 0.1492988133764833,
+      "grad_norm": 0.6565091013908386,
+      "learning_rate": 6.199460916442049e-05,
+      "loss": 1.0493087768554688,
+      "step": 346
+    },
+    {
+      "epoch": 0.15016181229773462,
+      "grad_norm": 0.6512171626091003,
+      "learning_rate": 6.23539982030548e-05,
+      "loss": 1.0469218492507935,
+      "step": 348
+    },
+    {
+      "epoch": 0.15102481121898598,
+      "grad_norm": 0.8487282991409302,
+      "learning_rate": 6.271338724168913e-05,
+      "loss": 1.0985081195831299,
+      "step": 350
+    },
+    {
+      "epoch": 0.15188781014023733,
+      "grad_norm": 0.6718961596488953,
+      "learning_rate": 6.307277628032345e-05,
+      "loss": 1.0714176893234253,
+      "step": 352
+    },
+    {
+      "epoch": 0.15275080906148866,
+      "grad_norm": 0.8175088167190552,
+      "learning_rate": 6.343216531895777e-05,
+      "loss": 1.0599322319030762,
+      "step": 354
+    },
+    {
+      "epoch": 0.15361380798274002,
+      "grad_norm": 0.6359215378761292,
+      "learning_rate": 6.37915543575921e-05,
+      "loss": 0.9268131256103516,
+      "step": 356
+    },
+    {
+      "epoch": 0.15447680690399138,
+      "grad_norm": 0.6423866748809814,
+      "learning_rate": 6.415094339622641e-05,
+      "loss": 0.9838354587554932,
+      "step": 358
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "grad_norm": 0.6496716737747192,
+      "learning_rate": 6.451033243486074e-05,
+      "loss": 1.048566460609436,
+      "step": 360
+    },
+    {
+      "epoch": 0.15620280474649406,
+      "grad_norm": 0.6536920666694641,
+      "learning_rate": 6.486972147349506e-05,
+      "loss": 1.0910537242889404,
+      "step": 362
+    },
+    {
+      "epoch": 0.15706580366774542,
+      "grad_norm": 0.5832068920135498,
+      "learning_rate": 6.522911051212939e-05,
+      "loss": 0.9971448183059692,
+      "step": 364
+    },
+    {
+      "epoch": 0.15792880258899678,
+      "grad_norm": 0.6647719144821167,
+      "learning_rate": 6.558849955076371e-05,
+      "loss": 1.0496708154678345,
+      "step": 366
+    },
+    {
+      "epoch": 0.1587918015102481,
+      "grad_norm": 0.623252809047699,
+      "learning_rate": 6.594788858939802e-05,
+      "loss": 0.955894410610199,
+      "step": 368
+    },
+    {
+      "epoch": 0.15965480043149946,
+      "grad_norm": 0.6311860084533691,
+      "learning_rate": 6.630727762803235e-05,
+      "loss": 1.1304032802581787,
+      "step": 370
+    },
+    {
+      "epoch": 0.16051779935275082,
+      "grad_norm": 0.5306481122970581,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.8746405243873596,
+      "step": 372
+    },
+    {
+      "epoch": 0.16138079827400215,
+      "grad_norm": 0.6249631643295288,
+      "learning_rate": 6.7026055705301e-05,
+      "loss": 0.9104986786842346,
+      "step": 374
+    },
+    {
+      "epoch": 0.1622437971952535,
+      "grad_norm": 0.6243219971656799,
+      "learning_rate": 6.738544474393532e-05,
+      "loss": 1.043666124343872,
+      "step": 376
+    },
+    {
+      "epoch": 0.16310679611650486,
+      "grad_norm": 0.6833282113075256,
+      "learning_rate": 6.774483378256963e-05,
+      "loss": 1.0504906177520752,
+      "step": 378
+    },
+    {
+      "epoch": 0.16396979503775622,
+      "grad_norm": 0.7124452590942383,
+      "learning_rate": 6.810422282120395e-05,
+      "loss": 1.0608166456222534,
+      "step": 380
+    },
+    {
+      "epoch": 0.16483279395900755,
+      "grad_norm": 0.7520908117294312,
+      "learning_rate": 6.846361185983828e-05,
+      "loss": 1.1653732061386108,
+      "step": 382
+    },
+    {
+      "epoch": 0.1656957928802589,
+      "grad_norm": 0.7121814489364624,
+      "learning_rate": 6.88230008984726e-05,
+      "loss": 1.0626367330551147,
+      "step": 384
+    },
+    {
+      "epoch": 0.16655879180151026,
+      "grad_norm": 0.6825008988380432,
+      "learning_rate": 6.918238993710691e-05,
+      "loss": 1.012121319770813,
+      "step": 386
+    },
+    {
+      "epoch": 0.1674217907227616,
+      "grad_norm": 0.4922940135002136,
+      "learning_rate": 6.954177897574124e-05,
+      "loss": 1.0576211214065552,
+      "step": 388
+    },
+    {
+      "epoch": 0.16828478964401294,
+      "grad_norm": 0.6122089624404907,
+      "learning_rate": 6.990116801437556e-05,
+      "loss": 1.03916597366333,
+      "step": 390
+    },
+    {
+      "epoch": 0.1691477885652643,
+      "grad_norm": 0.6348981261253357,
+      "learning_rate": 7.026055705300989e-05,
+      "loss": 1.17647123336792,
+      "step": 392
+    },
+    {
+      "epoch": 0.17001078748651563,
+      "grad_norm": 0.6205878257751465,
+      "learning_rate": 7.06199460916442e-05,
+      "loss": 0.9095983505249023,
+      "step": 394
+    },
+    {
+      "epoch": 0.170873786407767,
+      "grad_norm": 0.61506187915802,
+      "learning_rate": 7.097933513027853e-05,
+      "loss": 1.082506775856018,
+      "step": 396
+    },
+    {
+      "epoch": 0.17173678532901834,
+      "grad_norm": 0.6481751799583435,
+      "learning_rate": 7.133872416891285e-05,
+      "loss": 1.0716280937194824,
+      "step": 398
+    },
+    {
+      "epoch": 0.1725997842502697,
+      "grad_norm": 0.4871014952659607,
+      "learning_rate": 7.169811320754717e-05,
+      "loss": 0.9616814851760864,
+      "step": 400
+    },
+    {
+      "epoch": 0.1725997842502697,
+      "eval_loss": 1.0649415254592896,
+      "eval_runtime": 668.6025,
+      "eval_samples_per_second": 3.081,
+      "eval_steps_per_second": 3.081,
+      "step": 400
+    },
+    {
+      "epoch": 0.17346278317152103,
+      "grad_norm": 0.5680040121078491,
+      "learning_rate": 7.20575022461815e-05,
+      "loss": 1.0475050210952759,
+      "step": 402
+    },
+    {
+      "epoch": 0.17432578209277239,
+      "grad_norm": 0.6417813897132874,
+      "learning_rate": 7.241689128481581e-05,
+      "loss": 0.9851161241531372,
+      "step": 404
+    },
+    {
+      "epoch": 0.17518878101402374,
+      "grad_norm": 0.6600468158721924,
+      "learning_rate": 7.277628032345014e-05,
+      "loss": 1.013339638710022,
+      "step": 406
+    },
+    {
+      "epoch": 0.17605177993527507,
+      "grad_norm": 0.6733932495117188,
+      "learning_rate": 7.313566936208446e-05,
+      "loss": 0.9346804022789001,
+      "step": 408
+    },
+    {
+      "epoch": 0.17691477885652643,
+      "grad_norm": 0.6812151074409485,
+      "learning_rate": 7.349505840071879e-05,
+      "loss": 0.9890368580818176,
+      "step": 410
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.6380394697189331,
+      "learning_rate": 7.385444743935311e-05,
+      "loss": 0.8787848949432373,
+      "step": 412
+    },
+    {
+      "epoch": 0.1786407766990291,
+      "grad_norm": 0.6004905700683594,
+      "learning_rate": 7.421383647798742e-05,
+      "loss": 1.0235728025436401,
+      "step": 414
+    },
+    {
+      "epoch": 0.17950377562028047,
+      "grad_norm": 0.6569193005561829,
+      "learning_rate": 7.457322551662175e-05,
+      "loss": 0.9972385168075562,
+      "step": 416
+    },
+    {
+      "epoch": 0.18036677454153183,
+      "grad_norm": 0.6761631369590759,
+      "learning_rate": 7.493261455525607e-05,
+      "loss": 0.9593698382377625,
+      "step": 418
+    },
+    {
+      "epoch": 0.18122977346278318,
+      "grad_norm": 0.7328561544418335,
+      "learning_rate": 7.529200359389039e-05,
+      "loss": 1.0426853895187378,
+      "step": 420
+    },
+    {
+      "epoch": 0.1820927723840345,
+      "grad_norm": 0.6256070137023926,
+      "learning_rate": 7.56513926325247e-05,
+      "loss": 0.9608182311058044,
+      "step": 422
+    },
+    {
+      "epoch": 0.18295577130528587,
+      "grad_norm": 1.2549844980239868,
+      "learning_rate": 7.601078167115903e-05,
+      "loss": 1.0162668228149414,
+      "step": 424
+    },
+    {
+      "epoch": 0.18381877022653723,
+      "grad_norm": 0.6751510500907898,
+      "learning_rate": 7.637017070979335e-05,
+      "loss": 1.130725383758545,
+      "step": 426
+    },
+    {
+      "epoch": 0.18468176914778855,
+      "grad_norm": 0.7029808163642883,
+      "learning_rate": 7.672955974842768e-05,
+      "loss": 1.0384817123413086,
+      "step": 428
+    },
+    {
+      "epoch": 0.1855447680690399,
+      "grad_norm": 0.644353449344635,
+      "learning_rate": 7.7088948787062e-05,
+      "loss": 1.017020344734192,
+      "step": 430
+    },
+    {
+      "epoch": 0.18640776699029127,
+      "grad_norm": 0.6784916520118713,
+      "learning_rate": 7.744833782569631e-05,
+      "loss": 1.005354404449463,
+      "step": 432
+    },
+    {
+      "epoch": 0.1872707659115426,
+      "grad_norm": 0.5989449620246887,
+      "learning_rate": 7.780772686433064e-05,
+      "loss": 1.026848316192627,
+      "step": 434
+    },
+    {
+      "epoch": 0.18813376483279395,
+      "grad_norm": 0.6502639651298523,
+      "learning_rate": 7.816711590296496e-05,
+      "loss": 0.9891080856323242,
+      "step": 436
+    },
+    {
+      "epoch": 0.1889967637540453,
+      "grad_norm": 0.6176205277442932,
+      "learning_rate": 7.852650494159929e-05,
+      "loss": 0.966316819190979,
+      "step": 438
+    },
+    {
+      "epoch": 0.18985976267529667,
+      "grad_norm": 0.6801626086235046,
+      "learning_rate": 7.88858939802336e-05,
+      "loss": 1.123063087463379,
+      "step": 440
+    },
+    {
+      "epoch": 0.190722761596548,
+      "grad_norm": 0.6718618273735046,
+      "learning_rate": 7.924528301886794e-05,
+      "loss": 1.0467073917388916,
+      "step": 442
+    },
+    {
+      "epoch": 0.19158576051779935,
+      "grad_norm": 0.6761009097099304,
+      "learning_rate": 7.960467205750225e-05,
+      "loss": 1.0952889919281006,
+      "step": 444
+    },
+    {
+      "epoch": 0.1924487594390507,
+      "grad_norm": 0.6356327533721924,
+      "learning_rate": 7.996406109613657e-05,
+      "loss": 0.954807698726654,
+      "step": 446
+    },
+    {
+      "epoch": 0.19331175836030204,
+      "grad_norm": 0.6798669695854187,
+      "learning_rate": 8.03234501347709e-05,
+      "loss": 0.9941422343254089,
+      "step": 448
+    },
+    {
+      "epoch": 0.1941747572815534,
+      "grad_norm": 0.6511302590370178,
+      "learning_rate": 8.068283917340521e-05,
+      "loss": 1.0351495742797852,
+      "step": 450
+    },
+    {
+      "epoch": 0.19503775620280475,
+      "grad_norm": 0.6061258912086487,
+      "learning_rate": 8.104222821203954e-05,
+      "loss": 1.00546133518219,
+      "step": 452
+    },
+    {
+      "epoch": 0.1959007551240561,
+      "grad_norm": 0.6278533935546875,
+      "learning_rate": 8.140161725067386e-05,
+      "loss": 1.0778460502624512,
+      "step": 454
+    },
+    {
+      "epoch": 0.19676375404530744,
+      "grad_norm": 0.6866298317909241,
+      "learning_rate": 8.176100628930818e-05,
+      "loss": 1.0344486236572266,
+      "step": 456
+    },
+    {
+      "epoch": 0.1976267529665588,
+      "grad_norm": 0.7338075041770935,
+      "learning_rate": 8.212039532794251e-05,
+      "loss": 1.0663033723831177,
+      "step": 458
+    },
+    {
+      "epoch": 0.19848975188781015,
+      "grad_norm": 0.6811459064483643,
+      "learning_rate": 8.247978436657682e-05,
+      "loss": 0.9665339589118958,
+      "step": 460
+    },
+    {
+      "epoch": 0.19935275080906148,
+      "grad_norm": 0.6779627799987793,
+      "learning_rate": 8.283917340521114e-05,
+      "loss": 1.024712324142456,
+      "step": 462
+    },
+    {
+      "epoch": 0.20021574973031284,
+      "grad_norm": 0.6486892700195312,
+      "learning_rate": 8.319856244384546e-05,
+      "loss": 0.9699305295944214,
+      "step": 464
+    },
+    {
+      "epoch": 0.2010787486515642,
+      "grad_norm": 0.7022278308868408,
+      "learning_rate": 8.355795148247979e-05,
+      "loss": 0.9540432095527649,
+      "step": 466
+    },
+    {
+      "epoch": 0.20194174757281552,
+      "grad_norm": 0.5922990441322327,
+      "learning_rate": 8.39173405211141e-05,
+      "loss": 0.9253339767456055,
+      "step": 468
+    },
+    {
+      "epoch": 0.20280474649406688,
+      "grad_norm": 0.7076792120933533,
+      "learning_rate": 8.427672955974843e-05,
+      "loss": 0.9987741112709045,
+      "step": 470
+    },
+    {
+      "epoch": 0.20366774541531824,
+      "grad_norm": 0.6491380333900452,
+      "learning_rate": 8.463611859838275e-05,
+      "loss": 1.0249329805374146,
+      "step": 472
+    },
+    {
+      "epoch": 0.2045307443365696,
+      "grad_norm": 0.6784211993217468,
+      "learning_rate": 8.499550763701708e-05,
+      "loss": 1.0577133893966675,
+      "step": 474
+    },
+    {
+      "epoch": 0.20539374325782092,
+      "grad_norm": 0.6453303694725037,
+      "learning_rate": 8.53548966756514e-05,
+      "loss": 1.1312458515167236,
+      "step": 476
+    },
+    {
+      "epoch": 0.20625674217907228,
+      "grad_norm": 0.7431377172470093,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 1.0592451095581055,
+      "step": 478
+    },
+    {
+      "epoch": 0.20711974110032363,
+      "grad_norm": 0.6097649931907654,
+      "learning_rate": 8.607367475292004e-05,
+      "loss": 0.9337235689163208,
+      "step": 480
+    },
+    {
+      "epoch": 0.20798274002157496,
+      "grad_norm": 0.5693124532699585,
+      "learning_rate": 8.643306379155436e-05,
+      "loss": 0.9088928699493408,
+      "step": 482
+    },
+    {
+      "epoch": 0.20884573894282632,
+      "grad_norm": 0.7377229332923889,
+      "learning_rate": 8.679245283018869e-05,
+      "loss": 1.0729358196258545,
+      "step": 484
+    },
+    {
+      "epoch": 0.20970873786407768,
+      "grad_norm": 0.7399470210075378,
+      "learning_rate": 8.7151841868823e-05,
+      "loss": 1.0428457260131836,
+      "step": 486
+    },
+    {
+      "epoch": 0.210571736785329,
+      "grad_norm": 0.677052915096283,
+      "learning_rate": 8.751123090745734e-05,
+      "loss": 0.9940266013145447,
+      "step": 488
+    },
+    {
+      "epoch": 0.21143473570658036,
+      "grad_norm": 0.7126721739768982,
+      "learning_rate": 8.787061994609165e-05,
+      "loss": 1.011808156967163,
+      "step": 490
+    },
+    {
+      "epoch": 0.21229773462783172,
+      "grad_norm": 0.6663792729377747,
+      "learning_rate": 8.823000898472597e-05,
+      "loss": 1.0054185390472412,
+      "step": 492
+    },
+    {
+      "epoch": 0.21316073354908308,
+      "grad_norm": 0.6661092042922974,
+      "learning_rate": 8.85893980233603e-05,
+      "loss": 1.0167138576507568,
+      "step": 494
+    },
+    {
+      "epoch": 0.2140237324703344,
+      "grad_norm": 0.6975740194320679,
+      "learning_rate": 8.894878706199461e-05,
+      "loss": 1.1470818519592285,
+      "step": 496
+    },
+    {
+      "epoch": 0.21488673139158576,
+      "grad_norm": 0.6594390869140625,
+      "learning_rate": 8.930817610062893e-05,
+      "loss": 0.9619631171226501,
+      "step": 498
+    },
+    {
+      "epoch": 0.21574973031283712,
+      "grad_norm": 0.7216679453849792,
+      "learning_rate": 8.966756513926325e-05,
+      "loss": 0.9971368312835693,
+      "step": 500
+    },
+    {
+      "epoch": 0.21574973031283712,
+      "eval_loss": 1.0417571067810059,
+      "eval_runtime": 659.3112,
+      "eval_samples_per_second": 3.124,
+      "eval_steps_per_second": 3.124,
+      "step": 500
+    },
+    {
+      "epoch": 0.21661272923408845,
+      "grad_norm": 0.6188210844993591,
+      "learning_rate": 9.002695417789758e-05,
+      "loss": 1.0307213068008423,
+      "step": 502
+    },
+    {
+      "epoch": 0.2174757281553398,
+      "grad_norm": 0.6716445088386536,
+      "learning_rate": 9.03863432165319e-05,
+      "loss": 1.0188794136047363,
+      "step": 504
+    },
+    {
+      "epoch": 0.21833872707659116,
+      "grad_norm": 0.6790863275527954,
+      "learning_rate": 9.074573225516622e-05,
+      "loss": 0.9764845967292786,
+      "step": 506
+    },
+    {
+      "epoch": 0.2192017259978425,
+      "grad_norm": 0.6764960289001465,
+      "learning_rate": 9.110512129380054e-05,
+      "loss": 0.948829174041748,
+      "step": 508
+    },
+    {
+      "epoch": 0.22006472491909385,
+      "grad_norm": 0.6210965514183044,
+      "learning_rate": 9.146451033243486e-05,
+      "loss": 1.008013129234314,
+      "step": 510
+    },
+    {
+      "epoch": 0.2209277238403452,
+      "grad_norm": 0.7739297747612,
+      "learning_rate": 9.182389937106919e-05,
+      "loss": 1.1662557125091553,
+      "step": 512
+    },
+    {
+      "epoch": 0.22179072276159656,
+      "grad_norm": 0.7055562138557434,
+      "learning_rate": 9.21832884097035e-05,
+      "loss": 1.0325161218643188,
+      "step": 514
+    },
+    {
+      "epoch": 0.2226537216828479,
+      "grad_norm": 0.6079210042953491,
+      "learning_rate": 9.254267744833783e-05,
+      "loss": 1.00056791305542,
+      "step": 516
+    },
+    {
+      "epoch": 0.22351672060409924,
+      "grad_norm": 0.5974318981170654,
+      "learning_rate": 9.290206648697215e-05,
+      "loss": 0.9422364234924316,
+      "step": 518
+    },
+    {
+      "epoch": 0.2243797195253506,
+      "grad_norm": 0.5963430404663086,
+      "learning_rate": 9.326145552560648e-05,
+      "loss": 0.936336100101471,
+      "step": 520
+    },
+    {
+      "epoch": 0.22524271844660193,
+      "grad_norm": 0.6823658347129822,
+      "learning_rate": 9.36208445642408e-05,
+      "loss": 1.0538607835769653,
+      "step": 522
+    },
+    {
+      "epoch": 0.2261057173678533,
+      "grad_norm": 0.6409855484962463,
+      "learning_rate": 9.398023360287511e-05,
+      "loss": 1.0483653545379639,
+      "step": 524
+    },
+    {
+      "epoch": 0.22696871628910464,
+      "grad_norm": 0.6867254376411438,
+      "learning_rate": 9.433962264150944e-05,
+      "loss": 0.9668049812316895,
+      "step": 526
+    },
+    {
+      "epoch": 0.227831715210356,
+      "grad_norm": 0.5690792798995972,
+      "learning_rate": 9.469901168014376e-05,
+      "loss": 1.008763313293457,
+      "step": 528
+    },
+    {
+      "epoch": 0.22869471413160733,
+      "grad_norm": 0.5964897274971008,
+      "learning_rate": 9.505840071877809e-05,
+      "loss": 1.0816441774368286,
+      "step": 530
+    },
+    {
+      "epoch": 0.2295577130528587,
+      "grad_norm": 0.627419114112854,
+      "learning_rate": 9.54177897574124e-05,
+      "loss": 0.9265700578689575,
+      "step": 532
+    },
+    {
+      "epoch": 0.23042071197411004,
+      "grad_norm": 0.5862151980400085,
+      "learning_rate": 9.577717879604674e-05,
+      "loss": 0.9804646372795105,
+      "step": 534
+    },
+    {
+      "epoch": 0.23128371089536137,
+      "grad_norm": 0.5573718547821045,
+      "learning_rate": 9.613656783468105e-05,
+      "loss": 0.9627988934516907,
+      "step": 536
+    },
+    {
+      "epoch": 0.23214670981661273,
+      "grad_norm": 0.6705166101455688,
+      "learning_rate": 9.649595687331537e-05,
+      "loss": 1.0012824535369873,
+      "step": 538
+    },
+    {
+      "epoch": 0.23300970873786409,
+      "grad_norm": 0.6251236796379089,
+      "learning_rate": 9.685534591194969e-05,
+      "loss": 0.9568162560462952,
+      "step": 540
+    },
+    {
+      "epoch": 0.23387270765911541,
+      "grad_norm": 0.6466493010520935,
+      "learning_rate": 9.7214734950584e-05,
+      "loss": 1.031549334526062,
+      "step": 542
+    },
+    {
+      "epoch": 0.23473570658036677,
+      "grad_norm": 0.5183866024017334,
+      "learning_rate": 9.757412398921833e-05,
+      "loss": 0.8603643774986267,
+      "step": 544
+    },
+    {
+      "epoch": 0.23559870550161813,
+      "grad_norm": 0.6725775599479675,
+      "learning_rate": 9.793351302785265e-05,
+      "loss": 1.0365077257156372,
+      "step": 546
+    },
+    {
+      "epoch": 0.23646170442286948,
+      "grad_norm": 0.5972357988357544,
+      "learning_rate": 9.829290206648698e-05,
+      "loss": 0.9304701089859009,
+      "step": 548
+    },
+    {
+      "epoch": 0.2373247033441208,
+      "grad_norm": 0.5319957733154297,
+      "learning_rate": 9.86522911051213e-05,
+      "loss": 0.9575805068016052,
+      "step": 550
+    },
+    {
+      "epoch": 0.23818770226537217,
+      "grad_norm": 0.6502835750579834,
+      "learning_rate": 9.901168014375562e-05,
+      "loss": 1.0307214260101318,
+      "step": 552
+    },
+    {
+      "epoch": 0.23905070118662353,
+      "grad_norm": 0.6734047532081604,
+      "learning_rate": 9.937106918238994e-05,
+      "loss": 1.05185067653656,
+      "step": 554
+    },
+    {
+      "epoch": 0.23991370010787486,
+      "grad_norm": 0.5667978525161743,
+      "learning_rate": 9.973045822102426e-05,
+      "loss": 1.0190176963806152,
+      "step": 556
+    },
+    {
+      "epoch": 0.2407766990291262,
+      "grad_norm": 0.6370418667793274,
+      "learning_rate": 0.00010008984725965857,
+      "loss": 1.076182246208191,
+      "step": 558
+    },
+    {
+      "epoch": 0.24163969795037757,
+      "grad_norm": 0.689719021320343,
+      "learning_rate": 0.0001004492362982929,
+      "loss": 1.0408724546432495,
+      "step": 560
+    },
+    {
+      "epoch": 0.2425026968716289,
+      "grad_norm": 0.6304254531860352,
+      "learning_rate": 0.00010080862533692723,
+      "loss": 0.9869902729988098,
+      "step": 562
+    },
+    {
+      "epoch": 0.24336569579288025,
+      "grad_norm": 0.6797420382499695,
+      "learning_rate": 0.00010116801437556156,
+      "loss": 1.0198370218276978,
+      "step": 564
+    },
+    {
+      "epoch": 0.2442286947141316,
+      "grad_norm": 0.5993657112121582,
+      "learning_rate": 0.00010152740341419587,
+      "loss": 0.9947441816329956,
+      "step": 566
+    },
+    {
+      "epoch": 0.24509169363538297,
+      "grad_norm": 0.6369836330413818,
+      "learning_rate": 0.0001018867924528302,
+      "loss": 0.9722896814346313,
+      "step": 568
+    },
+    {
+      "epoch": 0.2459546925566343,
+      "grad_norm": 0.6942457556724548,
+      "learning_rate": 0.00010224618149146453,
+      "loss": 0.9716570973396301,
+      "step": 570
+    },
+    {
+      "epoch": 0.24681769147788565,
+      "grad_norm": 0.5403370261192322,
+      "learning_rate": 0.00010260557053009883,
+      "loss": 0.9797524213790894,
+      "step": 572
+    },
+    {
+      "epoch": 0.247680690399137,
+      "grad_norm": 0.5207529067993164,
+      "learning_rate": 0.00010296495956873316,
+      "loss": 0.985367476940155,
+      "step": 574
+    },
+    {
+      "epoch": 0.24854368932038834,
+      "grad_norm": 0.6751103401184082,
+      "learning_rate": 0.00010332434860736748,
+      "loss": 1.075042724609375,
+      "step": 576
+    },
+    {
+      "epoch": 0.2494066882416397,
+      "grad_norm": 0.565331220626831,
+      "learning_rate": 0.0001036837376460018,
+      "loss": 0.9273878335952759,
+      "step": 578
+    },
+    {
+      "epoch": 0.25026968716289105,
+      "grad_norm": 0.6858948469161987,
+      "learning_rate": 0.00010404312668463612,
+      "loss": 0.9872279763221741,
+      "step": 580
+    },
+    {
+      "epoch": 0.2511326860841424,
+      "grad_norm": 0.7091426253318787,
+      "learning_rate": 0.00010440251572327044,
+      "loss": 1.0038671493530273,
+      "step": 582
+    },
+    {
+      "epoch": 0.25199568500539377,
+      "grad_norm": 0.6493771076202393,
+      "learning_rate": 0.00010476190476190477,
+      "loss": 1.0109868049621582,
+      "step": 584
+    },
+    {
+      "epoch": 0.25285868392664507,
+      "grad_norm": 0.6107586622238159,
+      "learning_rate": 0.00010512129380053907,
+      "loss": 1.0020402669906616,
+      "step": 586
+    },
+    {
+      "epoch": 0.2537216828478964,
+      "grad_norm": 0.6878048181533813,
+      "learning_rate": 0.0001054806828391734,
+      "loss": 0.961039662361145,
+      "step": 588
+    },
+    {
+      "epoch": 0.2545846817691478,
+      "grad_norm": 0.664034903049469,
+      "learning_rate": 0.00010584007187780773,
+      "loss": 0.9725209474563599,
+      "step": 590
+    },
+    {
+      "epoch": 0.25544768069039914,
+      "grad_norm": 0.6399680376052856,
+      "learning_rate": 0.00010619946091644206,
+      "loss": 0.9907437562942505,
+      "step": 592
+    },
+    {
+      "epoch": 0.2563106796116505,
+      "grad_norm": 0.6163286566734314,
+      "learning_rate": 0.00010655884995507636,
+      "loss": 0.9650095701217651,
+      "step": 594
+    },
+    {
+      "epoch": 0.25717367853290185,
+      "grad_norm": 0.6008322238922119,
+      "learning_rate": 0.0001069182389937107,
+      "loss": 1.0102758407592773,
+      "step": 596
+    },
+    {
+      "epoch": 0.2580366774541532,
+      "grad_norm": 0.6752071380615234,
+      "learning_rate": 0.00010727762803234502,
+      "loss": 0.9101885557174683,
+      "step": 598
+    },
+    {
+      "epoch": 0.2588996763754045,
+      "grad_norm": 0.6789175868034363,
+      "learning_rate": 0.00010763701707097935,
+      "loss": 1.0461398363113403,
+      "step": 600
+    },
+    {
+      "epoch": 0.2588996763754045,
+      "eval_loss": 1.021111011505127,
+      "eval_runtime": 648.1611,
+      "eval_samples_per_second": 3.178,
+      "eval_steps_per_second": 3.178,
+      "step": 600
+    },
+    {
+      "epoch": 0.25976267529665586,
+      "grad_norm": 0.5660730600357056,
+      "learning_rate": 0.00010799640610961366,
+      "loss": 0.9582418203353882,
+      "step": 602
+    },
+    {
+      "epoch": 0.2606256742179072,
+      "grad_norm": 0.6726544499397278,
+      "learning_rate": 0.00010835579514824799,
+      "loss": 1.0763746500015259,
+      "step": 604
+    },
+    {
+      "epoch": 0.2614886731391586,
+      "grad_norm": 0.6068508625030518,
+      "learning_rate": 0.00010871518418688232,
+      "loss": 1.0432032346725464,
+      "step": 606
+    },
+    {
+      "epoch": 0.26235167206040994,
+      "grad_norm": 0.5731637477874756,
+      "learning_rate": 0.00010907457322551662,
+      "loss": 0.9830516576766968,
+      "step": 608
+    },
+    {
+      "epoch": 0.2632146709816613,
+      "grad_norm": 0.6777567267417908,
+      "learning_rate": 0.00010943396226415095,
+      "loss": 1.0442042350769043,
+      "step": 610
+    },
+    {
+      "epoch": 0.26407766990291265,
+      "grad_norm": 0.6372506618499756,
+      "learning_rate": 0.00010979335130278528,
+      "loss": 1.0001944303512573,
+      "step": 612
+    },
+    {
+      "epoch": 0.26494066882416395,
+      "grad_norm": 0.6606221795082092,
+      "learning_rate": 0.0001101527403414196,
+      "loss": 1.035884141921997,
+      "step": 614
+    },
+    {
+      "epoch": 0.2658036677454153,
+      "grad_norm": 0.6083229780197144,
+      "learning_rate": 0.00011051212938005391,
+      "loss": 0.9403397440910339,
+      "step": 616
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.6318517923355103,
+      "learning_rate": 0.00011087151841868823,
+      "loss": 0.9274454116821289,
+      "step": 618
+    },
+    {
+      "epoch": 0.267529665587918,
+      "grad_norm": 0.628190279006958,
+      "learning_rate": 0.00011123090745732256,
+      "loss": 0.9883754253387451,
+      "step": 620
+    },
+    {
+      "epoch": 0.2683926645091694,
+      "grad_norm": 0.5961961150169373,
+      "learning_rate": 0.00011159029649595688,
+      "loss": 1.0317535400390625,
+      "step": 622
+    },
+    {
+      "epoch": 0.26925566343042073,
+      "grad_norm": 0.5995341539382935,
+      "learning_rate": 0.00011194968553459119,
+      "loss": 0.9776126742362976,
+      "step": 624
+    },
+    {
+      "epoch": 0.27011866235167203,
+      "grad_norm": 0.6639334559440613,
+      "learning_rate": 0.00011230907457322552,
+      "loss": 1.0112378597259521,
+      "step": 626
+    },
+    {
+      "epoch": 0.2709816612729234,
+      "grad_norm": 0.6348621249198914,
+      "learning_rate": 0.00011266846361185985,
+      "loss": 1.0553804636001587,
+      "step": 628
+    },
+    {
+      "epoch": 0.27184466019417475,
+      "grad_norm": 0.5929805040359497,
+      "learning_rate": 0.00011302785265049416,
+      "loss": 1.025888442993164,
+      "step": 630
+    },
+    {
+      "epoch": 0.2727076591154261,
+      "grad_norm": 0.6052366495132446,
+      "learning_rate": 0.00011338724168912849,
+      "loss": 1.02956223487854,
+      "step": 632
+    },
+    {
+      "epoch": 0.27357065803667746,
+      "grad_norm": 0.6494882106781006,
+      "learning_rate": 0.00011374663072776282,
+      "loss": 0.989752471446991,
+      "step": 634
+    },
+    {
+      "epoch": 0.2744336569579288,
+      "grad_norm": 0.6005767583847046,
+      "learning_rate": 0.00011410601976639712,
+      "loss": 1.0030683279037476,
+      "step": 636
+    },
+    {
+      "epoch": 0.2752966558791802,
+      "grad_norm": 0.6478356122970581,
+      "learning_rate": 0.00011446540880503145,
+      "loss": 1.002000093460083,
+      "step": 638
+    },
+    {
+      "epoch": 0.2761596548004315,
+      "grad_norm": 0.5804725289344788,
+      "learning_rate": 0.00011482479784366578,
+      "loss": 0.9807654023170471,
+      "step": 640
+    },
+    {
+      "epoch": 0.27702265372168283,
+      "grad_norm": 0.632530689239502,
+      "learning_rate": 0.00011518418688230011,
+      "loss": 0.9841892123222351,
+      "step": 642
+    },
+    {
+      "epoch": 0.2778856526429342,
+      "grad_norm": 0.5340113639831543,
+      "learning_rate": 0.00011554357592093441,
+      "loss": 0.8902478814125061,
+      "step": 644
+    },
+    {
+      "epoch": 0.27874865156418555,
+      "grad_norm": 0.5901665091514587,
+      "learning_rate": 0.00011590296495956874,
+      "loss": 0.9019404649734497,
+      "step": 646
+    },
+    {
+      "epoch": 0.2796116504854369,
+      "grad_norm": 0.666589617729187,
+      "learning_rate": 0.00011626235399820307,
+      "loss": 0.9384423494338989,
+      "step": 648
+    },
+    {
+      "epoch": 0.28047464940668826,
+      "grad_norm": 0.7000334858894348,
+      "learning_rate": 0.00011662174303683737,
+      "loss": 1.0666629076004028,
+      "step": 650
+    },
+    {
+      "epoch": 0.2813376483279396,
+      "grad_norm": 0.663663923740387,
+      "learning_rate": 0.0001169811320754717,
+      "loss": 1.000019907951355,
+      "step": 652
+    },
+    {
+      "epoch": 0.2822006472491909,
+      "grad_norm": 0.6097694039344788,
+      "learning_rate": 0.00011734052111410603,
+      "loss": 0.9450293183326721,
+      "step": 654
+    },
+    {
+      "epoch": 0.2830636461704423,
+      "grad_norm": 0.6130967140197754,
+      "learning_rate": 0.00011769991015274035,
+      "loss": 0.9480894207954407,
+      "step": 656
+    },
+    {
+      "epoch": 0.28392664509169363,
+      "grad_norm": 0.7091249227523804,
+      "learning_rate": 0.00011805929919137467,
+      "loss": 1.1377143859863281,
+      "step": 658
+    },
+    {
+      "epoch": 0.284789644012945,
+      "grad_norm": 0.6556766629219055,
+      "learning_rate": 0.00011841868823000898,
+      "loss": 0.9421243667602539,
+      "step": 660
+    },
+    {
+      "epoch": 0.28565264293419634,
+      "grad_norm": 0.6682968735694885,
+      "learning_rate": 0.00011877807726864331,
+      "loss": 0.9726828336715698,
+      "step": 662
+    },
+    {
+      "epoch": 0.2865156418554477,
+      "grad_norm": 0.5224708914756775,
+      "learning_rate": 0.00011913746630727762,
+      "loss": 0.8996511697769165,
+      "step": 664
+    },
+    {
+      "epoch": 0.287378640776699,
+      "grad_norm": 0.5914195775985718,
+      "learning_rate": 0.00011949685534591195,
+      "loss": 0.9679517149925232,
+      "step": 666
+    },
+    {
+      "epoch": 0.28824163969795036,
+      "grad_norm": 0.6175519824028015,
+      "learning_rate": 0.00011985624438454628,
+      "loss": 0.8743209838867188,
+      "step": 668
+    },
+    {
+      "epoch": 0.2891046386192017,
+      "grad_norm": 0.6019226312637329,
+      "learning_rate": 0.0001202156334231806,
+      "loss": 0.9741992354393005,
+      "step": 670
+    },
+    {
+      "epoch": 0.28996763754045307,
+      "grad_norm": 0.6080542206764221,
+      "learning_rate": 0.00012057502246181491,
+      "loss": 0.9516472816467285,
+      "step": 672
+    },
+    {
+      "epoch": 0.29083063646170443,
+      "grad_norm": 0.5885615944862366,
+      "learning_rate": 0.00012093441150044924,
+      "loss": 1.122761607170105,
+      "step": 674
+    },
+    {
+      "epoch": 0.2916936353829558,
+      "grad_norm": 0.6635209918022156,
+      "learning_rate": 0.00012129380053908357,
+      "loss": 1.0105189085006714,
+      "step": 676
+    },
+    {
+      "epoch": 0.29255663430420714,
+      "grad_norm": 0.5805009007453918,
+      "learning_rate": 0.0001216531895777179,
+      "loss": 0.906292200088501,
+      "step": 678
+    },
+    {
+      "epoch": 0.29341963322545844,
+      "grad_norm": 0.5980029702186584,
+      "learning_rate": 0.0001220125786163522,
+      "loss": 1.009568691253662,
+      "step": 680
+    },
+    {
+      "epoch": 0.2942826321467098,
+      "grad_norm": 0.6797705292701721,
+      "learning_rate": 0.00012237196765498652,
+      "loss": 1.0373667478561401,
+      "step": 682
+    },
+    {
+      "epoch": 0.29514563106796116,
+      "grad_norm": 0.6280547976493835,
+      "learning_rate": 0.00012273135669362085,
+      "loss": 0.9758188724517822,
+      "step": 684
+    },
+    {
+      "epoch": 0.2960086299892125,
+      "grad_norm": 0.511608898639679,
+      "learning_rate": 0.00012309074573225515,
+      "loss": 0.9111692905426025,
+      "step": 686
+    },
+    {
+      "epoch": 0.29687162891046387,
+      "grad_norm": 0.5781835317611694,
+      "learning_rate": 0.00012345013477088948,
+      "loss": 0.8865921497344971,
+      "step": 688
+    },
+    {
+      "epoch": 0.2977346278317152,
+      "grad_norm": 0.6514166593551636,
+      "learning_rate": 0.0001238095238095238,
+      "loss": 0.9768189191818237,
+      "step": 690
+    },
+    {
+      "epoch": 0.2985976267529666,
+      "grad_norm": 0.6109189987182617,
+      "learning_rate": 0.00012416891284815814,
+      "loss": 0.9991607069969177,
+      "step": 692
+    },
+    {
+      "epoch": 0.2994606256742179,
+      "grad_norm": 0.6598902344703674,
+      "learning_rate": 0.00012452830188679244,
+      "loss": 0.9548360705375671,
+      "step": 694
+    },
+    {
+      "epoch": 0.30032362459546924,
+      "grad_norm": 0.5633156895637512,
+      "learning_rate": 0.00012488769092542677,
+      "loss": 0.992988109588623,
+      "step": 696
+    },
+    {
+      "epoch": 0.3011866235167206,
+      "grad_norm": 0.6098802089691162,
+      "learning_rate": 0.0001252470799640611,
+      "loss": 0.9709890484809875,
+      "step": 698
+    },
+    {
+      "epoch": 0.30204962243797195,
+      "grad_norm": 0.6197102665901184,
+      "learning_rate": 0.0001256064690026954,
+      "loss": 1.018282175064087,
+      "step": 700
+    },
+    {
+      "epoch": 0.30204962243797195,
+      "eval_loss": 1.0030721426010132,
+      "eval_runtime": 655.4533,
+      "eval_samples_per_second": 3.143,
+      "eval_steps_per_second": 3.143,
+      "step": 700
+    },
+    {
+      "epoch": 0.3029126213592233,
+      "grad_norm": 0.5817480683326721,
+      "learning_rate": 0.00012596585804132974,
+      "loss": 0.9147283434867859,
+      "step": 702
+    },
+    {
+      "epoch": 0.30377562028047467,
+      "grad_norm": 0.5976696014404297,
+      "learning_rate": 0.00012632524707996407,
+      "loss": 0.9318362474441528,
+      "step": 704
+    },
+    {
+      "epoch": 0.304638619201726,
+      "grad_norm": 0.6389723420143127,
+      "learning_rate": 0.0001266846361185984,
+      "loss": 0.9500927925109863,
+      "step": 706
+    },
+    {
+      "epoch": 0.3055016181229773,
+      "grad_norm": 0.6485719084739685,
+      "learning_rate": 0.0001270440251572327,
+      "loss": 1.0271424055099487,
+      "step": 708
+    },
+    {
+      "epoch": 0.3063646170442287,
+      "grad_norm": 0.5802455544471741,
+      "learning_rate": 0.00012740341419586703,
+      "loss": 0.9781906008720398,
+      "step": 710
+    },
+    {
+      "epoch": 0.30722761596548004,
+      "grad_norm": 0.6359356641769409,
+      "learning_rate": 0.00012776280323450136,
+      "loss": 1.0195324420928955,
+      "step": 712
+    },
+    {
+      "epoch": 0.3080906148867314,
+      "grad_norm": 0.5975426435470581,
+      "learning_rate": 0.00012812219227313566,
+      "loss": 0.9250738024711609,
+      "step": 714
+    },
+    {
+      "epoch": 0.30895361380798275,
+      "grad_norm": 0.643110454082489,
+      "learning_rate": 0.00012848158131177,
+      "loss": 0.9888015985488892,
+      "step": 716
+    },
+    {
+      "epoch": 0.3098166127292341,
+      "grad_norm": 0.6043205261230469,
+      "learning_rate": 0.00012884097035040432,
+      "loss": 0.9709514379501343,
+      "step": 718
+    },
+    {
+      "epoch": 0.3106796116504854,
+      "grad_norm": 0.5687094926834106,
+      "learning_rate": 0.00012920035938903865,
+      "loss": 1.0272964239120483,
+      "step": 720
+    },
+    {
+      "epoch": 0.31154261057173677,
+      "grad_norm": 0.5688400864601135,
+      "learning_rate": 0.00012955974842767296,
+      "loss": 0.9370370507240295,
+      "step": 722
+    },
+    {
+      "epoch": 0.3124056094929881,
+      "grad_norm": 0.5610610246658325,
+      "learning_rate": 0.00012991913746630729,
+      "loss": 0.9535608291625977,
+      "step": 724
+    },
+    {
+      "epoch": 0.3132686084142395,
+      "grad_norm": 0.6338257193565369,
+      "learning_rate": 0.00013027852650494162,
+      "loss": 1.0188907384872437,
+      "step": 726
+    },
+    {
+      "epoch": 0.31413160733549084,
+      "grad_norm": 0.5365633368492126,
+      "learning_rate": 0.00013063791554357592,
+      "loss": 0.9253716468811035,
+      "step": 728
+    },
+    {
+      "epoch": 0.3149946062567422,
+      "grad_norm": 0.5599163174629211,
+      "learning_rate": 0.00013099730458221025,
+      "loss": 0.8941492438316345,
+      "step": 730
+    },
+    {
+      "epoch": 0.31585760517799355,
+      "grad_norm": 0.6059780716896057,
+      "learning_rate": 0.00013135669362084458,
+      "loss": 0.9831459522247314,
+      "step": 732
+    },
+    {
+      "epoch": 0.31672060409924485,
+      "grad_norm": 0.5596494078636169,
+      "learning_rate": 0.0001317160826594789,
+      "loss": 0.9332310557365417,
+      "step": 734
+    },
+    {
+      "epoch": 0.3175836030204962,
+      "grad_norm": 0.5618010759353638,
+      "learning_rate": 0.0001320754716981132,
+      "loss": 0.9082580208778381,
+      "step": 736
+    },
+    {
+      "epoch": 0.31844660194174756,
+      "grad_norm": 0.6412109732627869,
+      "learning_rate": 0.00013243486073674754,
+      "loss": 1.008690357208252,
+      "step": 738
+    },
+    {
+      "epoch": 0.3193096008629989,
+      "grad_norm": 0.5742355585098267,
+      "learning_rate": 0.00013279424977538187,
+      "loss": 0.9597798585891724,
+      "step": 740
+    },
+    {
+      "epoch": 0.3201725997842503,
+      "grad_norm": 0.6470226645469666,
+      "learning_rate": 0.00013315363881401617,
+      "loss": 0.989331841468811,
+      "step": 742
+    },
+    {
+      "epoch": 0.32103559870550163,
+      "grad_norm": 0.5598039031028748,
+      "learning_rate": 0.0001335130278526505,
+      "loss": 0.8677343130111694,
+      "step": 744
+    },
+    {
+      "epoch": 0.321898597626753,
+      "grad_norm": 0.5441372990608215,
+      "learning_rate": 0.00013387241689128483,
+      "loss": 0.9462730288505554,
+      "step": 746
+    },
+    {
+      "epoch": 0.3227615965480043,
+      "grad_norm": 0.5858626365661621,
+      "learning_rate": 0.00013423180592991916,
+      "loss": 0.994694173336029,
+      "step": 748
+    },
+    {
+      "epoch": 0.32362459546925565,
+      "grad_norm": 0.511372447013855,
+      "learning_rate": 0.00013459119496855347,
+      "loss": 0.9387269616127014,
+      "step": 750
+    },
+    {
+      "epoch": 0.324487594390507,
+      "grad_norm": 0.47798457741737366,
+      "learning_rate": 0.0001349505840071878,
+      "loss": 0.9473881721496582,
+      "step": 752
+    },
+    {
+      "epoch": 0.32535059331175836,
+      "grad_norm": 0.5907022953033447,
+      "learning_rate": 0.0001353099730458221,
+      "loss": 0.9375183582305908,
+      "step": 754
+    },
+    {
+      "epoch": 0.3262135922330097,
+      "grad_norm": 0.618733286857605,
+      "learning_rate": 0.00013566936208445643,
+      "loss": 1.028738260269165,
+      "step": 756
+    },
+    {
+      "epoch": 0.3270765911542611,
+      "grad_norm": 0.5234512090682983,
+      "learning_rate": 0.00013602875112309076,
+      "loss": 0.9420192241668701,
+      "step": 758
+    },
+    {
+      "epoch": 0.32793959007551243,
+      "grad_norm": 0.7036319971084595,
+      "learning_rate": 0.00013638814016172506,
+      "loss": 1.0252270698547363,
+      "step": 760
+    },
+    {
+      "epoch": 0.32880258899676373,
+      "grad_norm": 0.5543172359466553,
+      "learning_rate": 0.0001367475292003594,
+      "loss": 0.8453778028488159,
+      "step": 762
+    },
+    {
+      "epoch": 0.3296655879180151,
+      "grad_norm": 0.5438711643218994,
+      "learning_rate": 0.0001371069182389937,
+      "loss": 0.8659937977790833,
+      "step": 764
+    },
+    {
+      "epoch": 0.33052858683926645,
+      "grad_norm": 0.6390914916992188,
+      "learning_rate": 0.00013746630727762803,
+      "loss": 1.038142442703247,
+      "step": 766
+    },
+    {
+      "epoch": 0.3313915857605178,
+      "grad_norm": 0.50070720911026,
+      "learning_rate": 0.00013782569631626236,
+      "loss": 0.899932861328125,
+      "step": 768
+    },
+    {
+      "epoch": 0.33225458468176916,
+      "grad_norm": 0.5982286334037781,
+      "learning_rate": 0.00013818508535489669,
+      "loss": 0.9712884426116943,
+      "step": 770
+    },
+    {
+      "epoch": 0.3331175836030205,
+      "grad_norm": 0.6588822603225708,
+      "learning_rate": 0.000138544474393531,
+      "loss": 0.9427542686462402,
+      "step": 772
+    },
+    {
+      "epoch": 0.3339805825242718,
+      "grad_norm": 0.6022042632102966,
+      "learning_rate": 0.00013890386343216532,
+      "loss": 0.8961561918258667,
+      "step": 774
+    },
+    {
+      "epoch": 0.3348435814455232,
+      "grad_norm": 0.6595642566680908,
+      "learning_rate": 0.00013926325247079965,
+      "loss": 0.9525937438011169,
+      "step": 776
+    },
+    {
+      "epoch": 0.33570658036677453,
+      "grad_norm": 0.5210421681404114,
+      "learning_rate": 0.00013962264150943395,
+      "loss": 0.9218845367431641,
+      "step": 778
+    },
+    {
+      "epoch": 0.3365695792880259,
+      "grad_norm": 0.549669623374939,
+      "learning_rate": 0.00013998203054806828,
+      "loss": 0.877951443195343,
+      "step": 780
+    },
+    {
+      "epoch": 0.33743257820927725,
+      "grad_norm": 0.5360157489776611,
+      "learning_rate": 0.0001403414195867026,
+      "loss": 0.8670064210891724,
+      "step": 782
+    },
+    {
+      "epoch": 0.3382955771305286,
+      "grad_norm": 0.614734947681427,
+      "learning_rate": 0.00014070080862533694,
+      "loss": 0.9561367630958557,
+      "step": 784
+    },
+    {
+      "epoch": 0.33915857605177996,
+      "grad_norm": 0.5798251628875732,
+      "learning_rate": 0.00014106019766397124,
+      "loss": 0.9132505059242249,
+      "step": 786
+    },
+    {
+      "epoch": 0.34002157497303126,
+      "grad_norm": 0.6267077326774597,
+      "learning_rate": 0.00014141958670260557,
+      "loss": 0.9297707080841064,
+      "step": 788
+    },
+    {
+      "epoch": 0.3408845738942826,
+      "grad_norm": 0.6045349836349487,
+      "learning_rate": 0.0001417789757412399,
+      "loss": 0.9382412433624268,
+      "step": 790
+    },
+    {
+      "epoch": 0.341747572815534,
+      "grad_norm": 0.6125404834747314,
+      "learning_rate": 0.0001421383647798742,
+      "loss": 0.9078555107116699,
+      "step": 792
+    },
+    {
+      "epoch": 0.34261057173678533,
+      "grad_norm": 0.5927051901817322,
+      "learning_rate": 0.00014249775381850854,
+      "loss": 0.899101197719574,
+      "step": 794
+    },
+    {
+      "epoch": 0.3434735706580367,
+      "grad_norm": 0.6315743923187256,
+      "learning_rate": 0.00014285714285714287,
+      "loss": 1.028346300125122,
+      "step": 796
+    },
+    {
+      "epoch": 0.34433656957928804,
+      "grad_norm": 0.549271285533905,
+      "learning_rate": 0.0001432165318957772,
+      "loss": 0.8988189697265625,
+      "step": 798
+    },
+    {
+      "epoch": 0.3451995685005394,
+      "grad_norm": 0.6344245672225952,
+      "learning_rate": 0.0001435759209344115,
+      "loss": 1.0489003658294678,
+      "step": 800
+    },
+    {
+      "epoch": 0.3451995685005394,
+      "eval_loss": 0.9864639639854431,
+      "eval_runtime": 667.3516,
+      "eval_samples_per_second": 3.087,
+      "eval_steps_per_second": 3.087,
+      "step": 800
+    },
+    {
+      "epoch": 0.3460625674217907,
+      "grad_norm": 0.5625309348106384,
+      "learning_rate": 0.00014393530997304583,
+      "loss": 0.8773928284645081,
+      "step": 802
+    },
+    {
+      "epoch": 0.34692556634304206,
+      "grad_norm": 0.5931969285011292,
+      "learning_rate": 0.00014429469901168016,
+      "loss": 0.9116050004959106,
+      "step": 804
+    },
+    {
+      "epoch": 0.3477885652642934,
+      "grad_norm": 0.5189821720123291,
+      "learning_rate": 0.00014465408805031446,
+      "loss": 0.9124425649642944,
+      "step": 806
+    },
+    {
+      "epoch": 0.34865156418554477,
+      "grad_norm": 0.5392254590988159,
+      "learning_rate": 0.0001450134770889488,
+      "loss": 0.9517888426780701,
+      "step": 808
+    },
+    {
+      "epoch": 0.34951456310679613,
+      "grad_norm": 0.5584444999694824,
+      "learning_rate": 0.00014537286612758312,
+      "loss": 0.9947572350502014,
+      "step": 810
+    },
+    {
+      "epoch": 0.3503775620280475,
+      "grad_norm": 0.5188854932785034,
+      "learning_rate": 0.00014573225516621745,
+      "loss": 0.9314022660255432,
+      "step": 812
+    },
+    {
+      "epoch": 0.3512405609492988,
+      "grad_norm": 0.5783659815788269,
+      "learning_rate": 0.00014609164420485176,
+      "loss": 0.9135628938674927,
+      "step": 814
+    },
+    {
+      "epoch": 0.35210355987055014,
+      "grad_norm": 0.550959050655365,
+      "learning_rate": 0.0001464510332434861,
+      "loss": 0.9665075540542603,
+      "step": 816
+    },
+    {
+      "epoch": 0.3529665587918015,
+      "grad_norm": 0.6013346314430237,
+      "learning_rate": 0.00014681042228212042,
+      "loss": 0.9836555123329163,
+      "step": 818
+    },
+    {
+      "epoch": 0.35382955771305286,
+      "grad_norm": 0.49219194054603577,
+      "learning_rate": 0.00014716981132075472,
+      "loss": 0.8900108337402344,
+      "step": 820
+    },
+    {
+      "epoch": 0.3546925566343042,
+      "grad_norm": 0.5517411828041077,
+      "learning_rate": 0.00014752920035938905,
+      "loss": 0.8769304156303406,
+      "step": 822
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.6062695980072021,
+      "learning_rate": 0.00014788858939802338,
+      "loss": 0.9744759202003479,
+      "step": 824
+    },
+    {
+      "epoch": 0.3564185544768069,
+      "grad_norm": 0.5132041573524475,
+      "learning_rate": 0.0001482479784366577,
+      "loss": 0.8875447511672974,
+      "step": 826
+    },
+    {
+      "epoch": 0.3572815533980582,
+      "grad_norm": 0.551799476146698,
+      "learning_rate": 0.000148607367475292,
+      "loss": 0.962710440158844,
+      "step": 828
+    },
+    {
+      "epoch": 0.3581445523193096,
+      "grad_norm": 0.6046625971794128,
+      "learning_rate": 0.00014896675651392634,
+      "loss": 0.8997528553009033,
+      "step": 830
+    },
+    {
+      "epoch": 0.35900755124056094,
+      "grad_norm": 0.560025691986084,
+      "learning_rate": 0.00014932614555256067,
+      "loss": 0.9541417360305786,
+      "step": 832
+    },
+    {
+      "epoch": 0.3598705501618123,
+      "grad_norm": 0.6441047787666321,
+      "learning_rate": 0.00014968553459119498,
+      "loss": 0.907791018486023,
+      "step": 834
+    },
+    {
+      "epoch": 0.36073354908306365,
+      "grad_norm": 0.5636281967163086,
+      "learning_rate": 0.0001500449236298293,
+      "loss": 1.0295937061309814,
+      "step": 836
+    },
+    {
+      "epoch": 0.361596548004315,
+      "grad_norm": 0.5528303384780884,
+      "learning_rate": 0.0001504043126684636,
+      "loss": 0.8875265717506409,
+      "step": 838
+    },
+    {
+      "epoch": 0.36245954692556637,
+      "grad_norm": 0.5345163345336914,
+      "learning_rate": 0.00015076370170709794,
+      "loss": 0.9678915739059448,
+      "step": 840
+    },
+    {
+      "epoch": 0.36332254584681767,
+      "grad_norm": 0.5551225543022156,
+      "learning_rate": 0.00015112309074573224,
+      "loss": 0.9235162734985352,
+      "step": 842
+    },
+    {
+      "epoch": 0.364185544768069,
+      "grad_norm": 0.5131904482841492,
+      "learning_rate": 0.00015148247978436657,
+      "loss": 0.8624292016029358,
+      "step": 844
+    },
+    {
+      "epoch": 0.3650485436893204,
+      "grad_norm": 0.6811004281044006,
+      "learning_rate": 0.0001518418688230009,
+      "loss": 1.0360193252563477,
+      "step": 846
+    },
+    {
+      "epoch": 0.36591154261057174,
+      "grad_norm": 0.6409741640090942,
+      "learning_rate": 0.00015220125786163523,
+      "loss": 0.9254010915756226,
+      "step": 848
+    },
+    {
+      "epoch": 0.3667745415318231,
+      "grad_norm": 0.5534068942070007,
+      "learning_rate": 0.00015256064690026953,
+      "loss": 0.8900630474090576,
+      "step": 850
+    },
+    {
+      "epoch": 0.36763754045307445,
+      "grad_norm": 0.4999487102031708,
+      "learning_rate": 0.00015292003593890386,
+      "loss": 0.88521409034729,
+      "step": 852
+    },
+    {
+      "epoch": 0.3685005393743258,
+      "grad_norm": 0.5805923938751221,
+      "learning_rate": 0.0001532794249775382,
+      "loss": 0.9563921093940735,
+      "step": 854
+    },
+    {
+      "epoch": 0.3693635382955771,
+      "grad_norm": 0.5485470294952393,
+      "learning_rate": 0.0001536388140161725,
+      "loss": 0.8909372687339783,
+      "step": 856
+    },
+    {
+      "epoch": 0.37022653721682847,
+      "grad_norm": 0.5317923426628113,
+      "learning_rate": 0.00015399820305480683,
+      "loss": 0.9145731925964355,
+      "step": 858
+    },
+    {
+      "epoch": 0.3710895361380798,
+      "grad_norm": 0.6073495745658875,
+      "learning_rate": 0.00015435759209344116,
+      "loss": 1.01466965675354,
+      "step": 860
+    },
+    {
+      "epoch": 0.3719525350593312,
+      "grad_norm": 0.566655158996582,
+      "learning_rate": 0.0001547169811320755,
+      "loss": 0.9941825270652771,
+      "step": 862
+    },
+    {
+      "epoch": 0.37281553398058254,
+      "grad_norm": 0.5262459516525269,
+      "learning_rate": 0.0001550763701707098,
+      "loss": 1.0059782266616821,
+      "step": 864
+    },
+    {
+      "epoch": 0.3736785329018339,
+      "grad_norm": 0.6264083981513977,
+      "learning_rate": 0.00015543575920934412,
+      "loss": 1.0332856178283691,
+      "step": 866
+    },
+    {
+      "epoch": 0.3745415318230852,
+      "grad_norm": 0.6575480699539185,
+      "learning_rate": 0.00015579514824797845,
+      "loss": 1.022459626197815,
+      "step": 868
+    },
+    {
+      "epoch": 0.37540453074433655,
+      "grad_norm": 0.6291940212249756,
+      "learning_rate": 0.00015615453728661275,
+      "loss": 0.9550372362136841,
+      "step": 870
+    },
+    {
+      "epoch": 0.3762675296655879,
+      "grad_norm": 0.6710562109947205,
+      "learning_rate": 0.00015651392632524708,
+      "loss": 0.9861716628074646,
+      "step": 872
+    },
+    {
+      "epoch": 0.37713052858683926,
+      "grad_norm": 0.5505748987197876,
+      "learning_rate": 0.0001568733153638814,
+      "loss": 0.9719111919403076,
+      "step": 874
+    },
+    {
+      "epoch": 0.3779935275080906,
+      "grad_norm": 0.5055180788040161,
+      "learning_rate": 0.00015723270440251574,
+      "loss": 0.8698170185089111,
+      "step": 876
+    },
+    {
+      "epoch": 0.378856526429342,
+      "grad_norm": 0.5935947895050049,
+      "learning_rate": 0.00015759209344115005,
+      "loss": 1.029494285583496,
+      "step": 878
+    },
+    {
+      "epoch": 0.37971952535059333,
+      "grad_norm": 0.538325846195221,
+      "learning_rate": 0.00015795148247978438,
+      "loss": 0.923010528087616,
+      "step": 880
+    },
+    {
+      "epoch": 0.38058252427184464,
+      "grad_norm": 0.587297797203064,
+      "learning_rate": 0.0001583108715184187,
+      "loss": 0.9394056797027588,
+      "step": 882
+    },
+    {
+      "epoch": 0.381445523193096,
+      "grad_norm": 0.5910462737083435,
+      "learning_rate": 0.000158670260557053,
+      "loss": 0.9472483992576599,
+      "step": 884
+    },
+    {
+      "epoch": 0.38230852211434735,
+      "grad_norm": 0.629048764705658,
+      "learning_rate": 0.00015902964959568734,
+      "loss": 0.9028263688087463,
+      "step": 886
+    },
+    {
+      "epoch": 0.3831715210355987,
+      "grad_norm": 0.5028086304664612,
+      "learning_rate": 0.00015938903863432167,
+      "loss": 0.9579087495803833,
+      "step": 888
+    },
+    {
+      "epoch": 0.38403451995685006,
+      "grad_norm": 0.5372384190559387,
+      "learning_rate": 0.000159748427672956,
+      "loss": 0.8318673372268677,
+      "step": 890
+    },
+    {
+      "epoch": 0.3848975188781014,
+      "grad_norm": 0.6314184665679932,
+      "learning_rate": 0.0001601078167115903,
+      "loss": 0.9804943203926086,
+      "step": 892
+    },
+    {
+      "epoch": 0.3857605177993528,
+      "grad_norm": 0.5545229911804199,
+      "learning_rate": 0.00016046720575022463,
+      "loss": 1.0078438520431519,
+      "step": 894
+    },
+    {
+      "epoch": 0.3866235167206041,
+      "grad_norm": 0.4674014151096344,
+      "learning_rate": 0.00016082659478885896,
+      "loss": 0.9269036650657654,
+      "step": 896
+    },
+    {
+      "epoch": 0.38748651564185543,
+      "grad_norm": 1.5887153148651123,
+      "learning_rate": 0.00016118598382749326,
+      "loss": 0.8927953243255615,
+      "step": 898
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "grad_norm": 0.5217035412788391,
+      "learning_rate": 0.0001615453728661276,
+      "loss": 0.908074140548706,
+      "step": 900
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "eval_loss": 0.9741895794868469,
+      "eval_runtime": 667.2236,
+      "eval_samples_per_second": 3.087,
+      "eval_steps_per_second": 3.087,
+      "step": 900
+    },
+    {
+      "epoch": 0.38921251348435815,
+      "grad_norm": 0.470498651266098,
+      "learning_rate": 0.00016190476190476192,
+      "loss": 0.9660369157791138,
+      "step": 902
+    },
+    {
+      "epoch": 0.3900755124056095,
+      "grad_norm": 0.5111004114151001,
+      "learning_rate": 0.00016226415094339625,
+      "loss": 0.9236379265785217,
+      "step": 904
+    },
+    {
+      "epoch": 0.39093851132686086,
+      "grad_norm": 0.5872815251350403,
+      "learning_rate": 0.00016262353998203056,
+      "loss": 1.0061595439910889,
+      "step": 906
+    },
+    {
+      "epoch": 0.3918015102481122,
+      "grad_norm": 0.5150740742683411,
+      "learning_rate": 0.0001629829290206649,
+      "loss": 0.8347328901290894,
+      "step": 908
+    },
+    {
+      "epoch": 0.3926645091693635,
+      "grad_norm": 0.46554985642433167,
+      "learning_rate": 0.00016334231805929922,
+      "loss": 0.9091183543205261,
+      "step": 910
+    },
+    {
+      "epoch": 0.3935275080906149,
+      "grad_norm": 0.5292875170707703,
+      "learning_rate": 0.00016370170709793352,
+      "loss": 0.9299798011779785,
+      "step": 912
+    },
+    {
+      "epoch": 0.39439050701186623,
+      "grad_norm": 0.5177125930786133,
+      "learning_rate": 0.00016406109613656785,
+      "loss": 0.942286491394043,
+      "step": 914
+    },
+    {
+      "epoch": 0.3952535059331176,
+      "grad_norm": 0.5564161539077759,
+      "learning_rate": 0.00016442048517520215,
+      "loss": 0.825290858745575,
+      "step": 916
+    },
+    {
+      "epoch": 0.39611650485436894,
+      "grad_norm": 0.5572530031204224,
+      "learning_rate": 0.00016477987421383648,
+      "loss": 0.876898467540741,
+      "step": 918
+    },
+    {
+      "epoch": 0.3969795037756203,
+      "grad_norm": 0.7294673323631287,
+      "learning_rate": 0.0001651392632524708,
+      "loss": 0.8949798941612244,
+      "step": 920
+    },
+    {
+      "epoch": 0.3978425026968716,
+      "grad_norm": 0.5234251022338867,
+      "learning_rate": 0.00016549865229110512,
+      "loss": 0.8457819223403931,
+      "step": 922
+    },
+    {
+      "epoch": 0.39870550161812296,
+      "grad_norm": 0.5273709893226624,
+      "learning_rate": 0.00016585804132973945,
+      "loss": 0.9080174565315247,
+      "step": 924
+    },
+    {
+      "epoch": 0.3995685005393743,
+      "grad_norm": 0.5795063376426697,
+      "learning_rate": 0.00016621743036837378,
+      "loss": 1.0304023027420044,
+      "step": 926
+    },
+    {
+      "epoch": 0.4004314994606257,
+      "grad_norm": 0.6153313517570496,
+      "learning_rate": 0.00016657681940700808,
+      "loss": 0.8900477886199951,
+      "step": 928
+    },
+    {
+      "epoch": 0.40129449838187703,
+      "grad_norm": 0.6293173432350159,
+      "learning_rate": 0.0001669362084456424,
+      "loss": 1.0130009651184082,
+      "step": 930
+    },
+    {
+      "epoch": 0.4021574973031284,
+      "grad_norm": 0.5455223321914673,
+      "learning_rate": 0.00016729559748427674,
+      "loss": 0.9339282512664795,
+      "step": 932
+    },
+    {
+      "epoch": 0.40302049622437974,
+      "grad_norm": 0.5349094271659851,
+      "learning_rate": 0.00016765498652291104,
+      "loss": 0.9628980755805969,
+      "step": 934
+    },
+    {
+      "epoch": 0.40388349514563104,
+      "grad_norm": 0.491227924823761,
+      "learning_rate": 0.00016801437556154537,
+      "loss": 0.8922860026359558,
+      "step": 936
+    },
+    {
+      "epoch": 0.4047464940668824,
+      "grad_norm": 0.6331246495246887,
+      "learning_rate": 0.0001683737646001797,
+      "loss": 1.0470497608184814,
+      "step": 938
+    },
+    {
+      "epoch": 0.40560949298813376,
+      "grad_norm": 0.6079246401786804,
+      "learning_rate": 0.00016873315363881403,
+      "loss": 0.8868283629417419,
+      "step": 940
+    },
+    {
+      "epoch": 0.4064724919093851,
+      "grad_norm": 0.5326972603797913,
+      "learning_rate": 0.00016909254267744833,
+      "loss": 0.9938711524009705,
+      "step": 942
+    },
+    {
+      "epoch": 0.40733549083063647,
+      "grad_norm": 0.47754305601119995,
+      "learning_rate": 0.00016945193171608266,
+      "loss": 0.8280484676361084,
+      "step": 944
+    },
+    {
+      "epoch": 0.4081984897518878,
+      "grad_norm": 0.6683310270309448,
+      "learning_rate": 0.000169811320754717,
+      "loss": 1.089701533317566,
+      "step": 946
+    },
+    {
+      "epoch": 0.4090614886731392,
+      "grad_norm": 0.42798754572868347,
+      "learning_rate": 0.0001701707097933513,
+      "loss": 0.8535542488098145,
+      "step": 948
+    },
+    {
+      "epoch": 0.4099244875943905,
+      "grad_norm": 0.5999574065208435,
+      "learning_rate": 0.00017053009883198563,
+      "loss": 0.9039298295974731,
+      "step": 950
+    },
+    {
+      "epoch": 0.41078748651564184,
+      "grad_norm": 0.5752781629562378,
+      "learning_rate": 0.00017088948787061996,
+      "loss": 0.8786448240280151,
+      "step": 952
+    },
+    {
+      "epoch": 0.4116504854368932,
+      "grad_norm": 0.5121532678604126,
+      "learning_rate": 0.0001712488769092543,
+      "loss": 0.9206072688102722,
+      "step": 954
+    },
+    {
+      "epoch": 0.41251348435814456,
+      "grad_norm": 0.611078143119812,
+      "learning_rate": 0.0001716082659478886,
+      "loss": 0.9246986508369446,
+      "step": 956
+    },
+    {
+      "epoch": 0.4133764832793959,
+      "grad_norm": 0.5101020336151123,
+      "learning_rate": 0.00017196765498652292,
+      "loss": 0.9221894145011902,
+      "step": 958
+    },
+    {
+      "epoch": 0.41423948220064727,
+      "grad_norm": 0.5681450963020325,
+      "learning_rate": 0.00017232704402515725,
+      "loss": 0.9072799682617188,
+      "step": 960
+    },
+    {
+      "epoch": 0.41510248112189857,
+      "grad_norm": 0.47865498065948486,
+      "learning_rate": 0.00017268643306379155,
+      "loss": 0.9460896849632263,
+      "step": 962
+    },
+    {
+      "epoch": 0.4159654800431499,
+      "grad_norm": 0.49861401319503784,
+      "learning_rate": 0.00017304582210242588,
+      "loss": 0.9121519923210144,
+      "step": 964
+    },
+    {
+      "epoch": 0.4168284789644013,
+      "grad_norm": 0.43025892972946167,
+      "learning_rate": 0.0001734052111410602,
+      "loss": 0.8826848864555359,
+      "step": 966
+    },
+    {
+      "epoch": 0.41769147788565264,
+      "grad_norm": 0.4600491225719452,
+      "learning_rate": 0.00017376460017969454,
+      "loss": 0.8756251335144043,
+      "step": 968
+    },
+    {
+      "epoch": 0.418554476806904,
+      "grad_norm": 0.5297656059265137,
+      "learning_rate": 0.00017412398921832885,
+      "loss": 0.9171333312988281,
+      "step": 970
+    },
+    {
+      "epoch": 0.41941747572815535,
+      "grad_norm": 0.4906919002532959,
+      "learning_rate": 0.00017448337825696318,
+      "loss": 0.8887524008750916,
+      "step": 972
+    },
+    {
+      "epoch": 0.4202804746494067,
+      "grad_norm": 0.49263402819633484,
+      "learning_rate": 0.0001748427672955975,
+      "loss": 0.8345810174942017,
+      "step": 974
+    },
+    {
+      "epoch": 0.421143473570658,
+      "grad_norm": 0.5706565380096436,
+      "learning_rate": 0.0001752021563342318,
+      "loss": 0.968651294708252,
+      "step": 976
+    },
+    {
+      "epoch": 0.42200647249190937,
+      "grad_norm": 0.5269908308982849,
+      "learning_rate": 0.00017556154537286614,
+      "loss": 0.9729376435279846,
+      "step": 978
+    },
+    {
+      "epoch": 0.4228694714131607,
+      "grad_norm": 0.47058001160621643,
+      "learning_rate": 0.00017592093441150047,
+      "loss": 0.963884711265564,
+      "step": 980
+    },
+    {
+      "epoch": 0.4237324703344121,
+      "grad_norm": 0.5322962999343872,
+      "learning_rate": 0.0001762803234501348,
+      "loss": 0.8952447175979614,
+      "step": 982
+    },
+    {
+      "epoch": 0.42459546925566344,
+      "grad_norm": 0.5750975012779236,
+      "learning_rate": 0.0001766397124887691,
+      "loss": 0.8932783603668213,
+      "step": 984
+    },
+    {
+      "epoch": 0.4254584681769148,
+      "grad_norm": 0.5539655685424805,
+      "learning_rate": 0.00017699910152740343,
+      "loss": 0.916595458984375,
+      "step": 986
+    },
+    {
+      "epoch": 0.42632146709816615,
+      "grad_norm": 0.568000853061676,
+      "learning_rate": 0.00017735849056603776,
+      "loss": 0.9669626355171204,
+      "step": 988
+    },
+    {
+      "epoch": 0.42718446601941745,
+      "grad_norm": 0.6010684370994568,
+      "learning_rate": 0.00017771787960467206,
+      "loss": 1.0089105367660522,
+      "step": 990
+    },
+    {
+      "epoch": 0.4280474649406688,
+      "grad_norm": 0.6083462238311768,
+      "learning_rate": 0.0001780772686433064,
+      "loss": 0.9810921549797058,
+      "step": 992
+    },
+    {
+      "epoch": 0.42891046386192017,
+      "grad_norm": 0.5076655149459839,
+      "learning_rate": 0.0001784366576819407,
+      "loss": 0.9524372816085815,
+      "step": 994
+    },
+    {
+      "epoch": 0.4297734627831715,
+      "grad_norm": 0.5260922312736511,
+      "learning_rate": 0.00017879604672057503,
+      "loss": 0.881294846534729,
+      "step": 996
+    },
+    {
+      "epoch": 0.4306364617044229,
+      "grad_norm": 0.6130498051643372,
+      "learning_rate": 0.00017915543575920936,
+      "loss": 0.9138327836990356,
+      "step": 998
+    },
+    {
+      "epoch": 0.43149946062567424,
+      "grad_norm": 0.5346242785453796,
+      "learning_rate": 0.00017951482479784366,
+      "loss": 0.8861367106437683,
+      "step": 1000
+    },
+    {
+      "epoch": 0.43149946062567424,
+      "eval_loss": 0.9606748819351196,
+      "eval_runtime": 655.4358,
+      "eval_samples_per_second": 3.143,
+      "eval_steps_per_second": 3.143,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4323624595469256,
+      "grad_norm": 0.5977228879928589,
+      "learning_rate": 0.000179874213836478,
+      "loss": 0.8711628913879395,
+      "step": 1002
+    },
+    {
+      "epoch": 0.4332254584681769,
+      "grad_norm": 0.5547866821289062,
+      "learning_rate": 0.00018023360287511232,
+      "loss": 0.9393253326416016,
+      "step": 1004
+    },
+    {
+      "epoch": 0.43408845738942825,
+      "grad_norm": 0.536856472492218,
+      "learning_rate": 0.00018059299191374662,
+      "loss": 0.9486003518104553,
+      "step": 1006
+    },
+    {
+      "epoch": 0.4349514563106796,
+      "grad_norm": 0.4769814610481262,
+      "learning_rate": 0.00018095238095238095,
+      "loss": 0.9042052030563354,
+      "step": 1008
+    },
+    {
+      "epoch": 0.43581445523193096,
+      "grad_norm": 0.5554604530334473,
+      "learning_rate": 0.00018131176999101528,
+      "loss": 0.978546142578125,
+      "step": 1010
+    },
+    {
+      "epoch": 0.4366774541531823,
+      "grad_norm": 0.5112947225570679,
+      "learning_rate": 0.00018167115902964959,
+      "loss": 0.8382073640823364,
+      "step": 1012
+    },
+    {
+      "epoch": 0.4375404530744337,
+      "grad_norm": 0.45194941759109497,
+      "learning_rate": 0.00018203054806828392,
+      "loss": 0.8577026724815369,
+      "step": 1014
+    },
+    {
+      "epoch": 0.438403451995685,
+      "grad_norm": 0.5115043520927429,
+      "learning_rate": 0.00018238993710691825,
+      "loss": 0.8517863154411316,
+      "step": 1016
+    },
+    {
+      "epoch": 0.43926645091693634,
+      "grad_norm": 0.5485050082206726,
+      "learning_rate": 0.00018274932614555258,
+      "loss": 0.9597266912460327,
+      "step": 1018
+    },
+    {
+      "epoch": 0.4401294498381877,
+      "grad_norm": 0.5742959976196289,
+      "learning_rate": 0.00018310871518418688,
+      "loss": 1.0407187938690186,
+      "step": 1020
+    },
+    {
+      "epoch": 0.44099244875943905,
+      "grad_norm": 0.44870051741600037,
+      "learning_rate": 0.0001834681042228212,
+      "loss": 0.8696310520172119,
+      "step": 1022
+    },
+    {
+      "epoch": 0.4418554476806904,
+      "grad_norm": 0.5179623961448669,
+      "learning_rate": 0.00018382749326145554,
+      "loss": 0.9673634767532349,
+      "step": 1024
+    },
+    {
+      "epoch": 0.44271844660194176,
+      "grad_norm": 0.5404779314994812,
+      "learning_rate": 0.00018418688230008984,
+      "loss": 0.9596615433692932,
+      "step": 1026
+    },
+    {
+      "epoch": 0.4435814455231931,
+      "grad_norm": 0.47766315937042236,
+      "learning_rate": 0.00018454627133872417,
+      "loss": 0.8483878970146179,
+      "step": 1028
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.503380537033081,
+      "learning_rate": 0.0001849056603773585,
+      "loss": 0.9330979585647583,
+      "step": 1030
+    },
+    {
+      "epoch": 0.4453074433656958,
+      "grad_norm": 0.6129396557807922,
+      "learning_rate": 0.00018526504941599283,
+      "loss": 0.9341012239456177,
+      "step": 1032
+    },
+    {
+      "epoch": 0.44617044228694713,
+      "grad_norm": 0.4497876465320587,
+      "learning_rate": 0.00018562443845462713,
+      "loss": 0.9139068126678467,
+      "step": 1034
+    },
+    {
+      "epoch": 0.4470334412081985,
+      "grad_norm": 0.5369747281074524,
+      "learning_rate": 0.00018598382749326146,
+      "loss": 0.8874827027320862,
+      "step": 1036
+    },
+    {
+      "epoch": 0.44789644012944985,
+      "grad_norm": 0.5947322845458984,
+      "learning_rate": 0.0001863432165318958,
+      "loss": 0.9653725028038025,
+      "step": 1038
+    },
+    {
+      "epoch": 0.4487594390507012,
+      "grad_norm": 0.6649987101554871,
+      "learning_rate": 0.0001867026055705301,
+      "loss": 0.9553119540214539,
+      "step": 1040
+    },
+    {
+      "epoch": 0.44962243797195256,
+      "grad_norm": 0.5369387269020081,
+      "learning_rate": 0.00018706199460916443,
+      "loss": 0.904233992099762,
+      "step": 1042
+    },
+    {
+      "epoch": 0.45048543689320386,
+      "grad_norm": 0.4956842362880707,
+      "learning_rate": 0.00018742138364779876,
+      "loss": 0.8837952017784119,
+      "step": 1044
+    },
+    {
+      "epoch": 0.4513484358144552,
+      "grad_norm": 0.48045051097869873,
+      "learning_rate": 0.0001877807726864331,
+      "loss": 0.8964687585830688,
+      "step": 1046
+    },
+    {
+      "epoch": 0.4522114347357066,
+      "grad_norm": 0.4925530254840851,
+      "learning_rate": 0.0001881401617250674,
+      "loss": 0.9105878472328186,
+      "step": 1048
+    },
+    {
+      "epoch": 0.45307443365695793,
+      "grad_norm": 0.5131362080574036,
+      "learning_rate": 0.00018849955076370172,
+      "loss": 0.96272873878479,
+      "step": 1050
+    },
+    {
+      "epoch": 0.4539374325782093,
+      "grad_norm": 0.435739129781723,
+      "learning_rate": 0.00018885893980233605,
+      "loss": 0.8796783685684204,
+      "step": 1052
+    },
+    {
+      "epoch": 0.45480043149946064,
+      "grad_norm": 0.500938892364502,
+      "learning_rate": 0.00018921832884097035,
+      "loss": 0.9463814496994019,
+      "step": 1054
+    },
+    {
+      "epoch": 0.455663430420712,
+      "grad_norm": 0.4769900143146515,
+      "learning_rate": 0.00018957771787960468,
+      "loss": 0.9030335545539856,
+      "step": 1056
+    },
+    {
+      "epoch": 0.4565264293419633,
+      "grad_norm": 0.49585285782814026,
+      "learning_rate": 0.00018993710691823901,
+      "loss": 0.986995279788971,
+      "step": 1058
+    },
+    {
+      "epoch": 0.45738942826321466,
+      "grad_norm": 0.5875195264816284,
+      "learning_rate": 0.00019029649595687334,
+      "loss": 0.9297246932983398,
+      "step": 1060
+    },
+    {
+      "epoch": 0.458252427184466,
+      "grad_norm": 0.5552583932876587,
+      "learning_rate": 0.00019065588499550765,
+      "loss": 1.005869746208191,
+      "step": 1062
+    },
+    {
+      "epoch": 0.4591154261057174,
+      "grad_norm": 0.49282076954841614,
+      "learning_rate": 0.00019101527403414198,
+      "loss": 0.8949927091598511,
+      "step": 1064
+    },
+    {
+      "epoch": 0.45997842502696873,
+      "grad_norm": 0.4951777160167694,
+      "learning_rate": 0.0001913746630727763,
+      "loss": 0.9997886419296265,
+      "step": 1066
+    },
+    {
+      "epoch": 0.4608414239482201,
+      "grad_norm": 0.5154827237129211,
+      "learning_rate": 0.0001917340521114106,
+      "loss": 0.9532123804092407,
+      "step": 1068
+    },
+    {
+      "epoch": 0.4617044228694714,
+      "grad_norm": 0.5547500252723694,
+      "learning_rate": 0.00019209344115004494,
+      "loss": 0.8959843516349792,
+      "step": 1070
+    },
+    {
+      "epoch": 0.46256742179072274,
+      "grad_norm": 0.500188946723938,
+      "learning_rate": 0.00019245283018867927,
+      "loss": 0.8201484680175781,
+      "step": 1072
+    },
+    {
+      "epoch": 0.4634304207119741,
+      "grad_norm": 0.4181794822216034,
+      "learning_rate": 0.00019281221922731357,
+      "loss": 0.8255136609077454,
+      "step": 1074
+    },
+    {
+      "epoch": 0.46429341963322546,
+      "grad_norm": 0.5613874197006226,
+      "learning_rate": 0.0001931716082659479,
+      "loss": 0.896024763584137,
+      "step": 1076
+    },
+    {
+      "epoch": 0.4651564185544768,
+      "grad_norm": 0.5000972151756287,
+      "learning_rate": 0.0001935309973045822,
+      "loss": 0.8831873536109924,
+      "step": 1078
+    },
+    {
+      "epoch": 0.46601941747572817,
+      "grad_norm": 0.6321820616722107,
+      "learning_rate": 0.00019389038634321654,
+      "loss": 0.9787988662719727,
+      "step": 1080
+    },
+    {
+      "epoch": 0.4668824163969795,
+      "grad_norm": 0.4843652546405792,
+      "learning_rate": 0.00019424977538185087,
+      "loss": 0.933361828327179,
+      "step": 1082
+    },
+    {
+      "epoch": 0.46774541531823083,
+      "grad_norm": 0.537330150604248,
+      "learning_rate": 0.00019460916442048517,
+      "loss": 0.9046981334686279,
+      "step": 1084
+    },
+    {
+      "epoch": 0.4686084142394822,
+      "grad_norm": 0.5761371850967407,
+      "learning_rate": 0.0001949685534591195,
+      "loss": 0.9625781178474426,
+      "step": 1086
+    },
+    {
+      "epoch": 0.46947141316073354,
+      "grad_norm": 0.5209522843360901,
+      "learning_rate": 0.00019532794249775383,
+      "loss": 0.9280619025230408,
+      "step": 1088
+    },
+    {
+      "epoch": 0.4703344120819849,
+      "grad_norm": 0.5383933186531067,
+      "learning_rate": 0.00019568733153638813,
+      "loss": 0.8236247301101685,
+      "step": 1090
+    },
+    {
+      "epoch": 0.47119741100323626,
+      "grad_norm": 0.4994274377822876,
+      "learning_rate": 0.00019604672057502246,
+      "loss": 0.9404071569442749,
+      "step": 1092
+    },
+    {
+      "epoch": 0.4720604099244876,
+      "grad_norm": 0.5177807211875916,
+      "learning_rate": 0.0001964061096136568,
+      "loss": 0.8517536520957947,
+      "step": 1094
+    },
+    {
+      "epoch": 0.47292340884573897,
+      "grad_norm": 0.5374870896339417,
+      "learning_rate": 0.00019676549865229112,
+      "loss": 0.8214367032051086,
+      "step": 1096
+    },
+    {
+      "epoch": 0.47378640776699027,
+      "grad_norm": 0.5544074177742004,
+      "learning_rate": 0.00019712488769092542,
+      "loss": 1.016176700592041,
+      "step": 1098
+    },
+    {
+      "epoch": 0.4746494066882416,
+      "grad_norm": 0.5125867128372192,
+      "learning_rate": 0.00019748427672955975,
+      "loss": 0.8425421118736267,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4746494066882416,
+      "eval_loss": 0.944629430770874,
+      "eval_runtime": 649.9107,
+      "eval_samples_per_second": 3.17,
+      "eval_steps_per_second": 3.17,
+      "step": 1100
+    },
+    {
+      "epoch": 0.475512405609493,
+      "grad_norm": 0.5204418897628784,
+      "learning_rate": 0.00019784366576819408,
+      "loss": 0.9444556832313538,
+      "step": 1102
+    },
+    {
+      "epoch": 0.47637540453074434,
+      "grad_norm": 0.46085885167121887,
+      "learning_rate": 0.0001982030548068284,
+      "loss": 0.877082109451294,
+      "step": 1104
+    },
+    {
+      "epoch": 0.4772384034519957,
+      "grad_norm": 0.5269598960876465,
+      "learning_rate": 0.00019856244384546272,
+      "loss": 0.9214640259742737,
+      "step": 1106
+    },
+    {
+      "epoch": 0.47810140237324705,
+      "grad_norm": 0.4894753694534302,
+      "learning_rate": 0.00019892183288409705,
+      "loss": 0.8867175579071045,
+      "step": 1108
+    },
+    {
+      "epoch": 0.47896440129449835,
+      "grad_norm": 0.5204115509986877,
+      "learning_rate": 0.00019928122192273138,
+      "loss": 0.9641162753105164,
+      "step": 1110
+    },
+    {
+      "epoch": 0.4798274002157497,
+      "grad_norm": 0.6399031281471252,
+      "learning_rate": 0.00019964061096136568,
+      "loss": 1.0219199657440186,
+      "step": 1112
+    },
+    {
+      "epoch": 0.48069039913700107,
+      "grad_norm": 0.3979159891605377,
+      "learning_rate": 0.0002,
+      "loss": 0.8189998269081116,
+      "step": 1114
+    },
+    {
+      "epoch": 0.4815533980582524,
+      "grad_norm": 0.4782681465148926,
+      "learning_rate": 0.0001999999879427254,
+      "loss": 0.83241868019104,
+      "step": 1116
+    },
+    {
+      "epoch": 0.4824163969795038,
+      "grad_norm": 0.5235620141029358,
+      "learning_rate": 0.00019999995177090454,
+      "loss": 0.9371466636657715,
+      "step": 1118
+    },
+    {
+      "epoch": 0.48327939590075514,
+      "grad_norm": 0.4543023407459259,
+      "learning_rate": 0.00019999989148454606,
+      "loss": 0.7767758369445801,
+      "step": 1120
+    },
+    {
+      "epoch": 0.4841423948220065,
+      "grad_norm": 0.6191229820251465,
+      "learning_rate": 0.00019999980708366457,
+      "loss": 1.0103063583374023,
+      "step": 1122
+    },
+    {
+      "epoch": 0.4850053937432578,
+      "grad_norm": 0.45392486453056335,
+      "learning_rate": 0.00019999969856828042,
+      "loss": 0.8720875382423401,
+      "step": 1124
+    },
+    {
+      "epoch": 0.48586839266450915,
+      "grad_norm": 0.42748701572418213,
+      "learning_rate": 0.00019999956593841974,
+      "loss": 0.7859150171279907,
+      "step": 1126
+    },
+    {
+      "epoch": 0.4867313915857605,
+      "grad_norm": 0.4952569603919983,
+      "learning_rate": 0.00019999940919411454,
+      "loss": 0.9154419898986816,
+      "step": 1128
+    },
+    {
+      "epoch": 0.48759439050701187,
+      "grad_norm": 0.5522173047065735,
+      "learning_rate": 0.00019999922833540264,
+      "loss": 0.9076330065727234,
+      "step": 1130
+    },
+    {
+      "epoch": 0.4884573894282632,
+      "grad_norm": 0.5355855226516724,
+      "learning_rate": 0.00019999902336232758,
+      "loss": 0.8933543562889099,
+      "step": 1132
+    },
+    {
+      "epoch": 0.4893203883495146,
+      "grad_norm": 0.4613489508628845,
+      "learning_rate": 0.00019999879427493885,
+      "loss": 0.9160735607147217,
+      "step": 1134
+    },
+    {
+      "epoch": 0.49018338727076594,
+      "grad_norm": 0.4758962094783783,
+      "learning_rate": 0.0001999985410732917,
+      "loss": 0.8552446961402893,
+      "step": 1136
+    },
+    {
+      "epoch": 0.49104638619201724,
+      "grad_norm": 0.4549376964569092,
+      "learning_rate": 0.00019999826375744715,
+      "loss": 0.9979530572891235,
+      "step": 1138
+    },
+    {
+      "epoch": 0.4919093851132686,
+      "grad_norm": 0.4363284409046173,
+      "learning_rate": 0.0001999979623274721,
+      "loss": 0.9295380115509033,
+      "step": 1140
+    },
+    {
+      "epoch": 0.49277238403451995,
+      "grad_norm": 0.5090877413749695,
+      "learning_rate": 0.0001999976367834392,
+      "loss": 0.8737252950668335,
+      "step": 1142
+    },
+    {
+      "epoch": 0.4936353829557713,
+      "grad_norm": 0.45340779423713684,
+      "learning_rate": 0.000199997287125427,
+      "loss": 0.8312779068946838,
+      "step": 1144
+    },
+    {
+      "epoch": 0.49449838187702266,
+      "grad_norm": 0.4771472215652466,
+      "learning_rate": 0.0001999969133535198,
+      "loss": 0.9105207324028015,
+      "step": 1146
+    },
+    {
+      "epoch": 0.495361380798274,
+      "grad_norm": 0.5251384377479553,
+      "learning_rate": 0.00019999651546780773,
+      "loss": 0.8578172922134399,
+      "step": 1148
+    },
+    {
+      "epoch": 0.4962243797195254,
+      "grad_norm": 0.49128198623657227,
+      "learning_rate": 0.00019999609346838676,
+      "loss": 0.9193941950798035,
+      "step": 1150
+    },
+    {
+      "epoch": 0.4970873786407767,
+      "grad_norm": 0.5558596849441528,
+      "learning_rate": 0.0001999956473553586,
+      "loss": 0.9141314625740051,
+      "step": 1152
+    },
+    {
+      "epoch": 0.49795037756202803,
+      "grad_norm": 0.45872750878334045,
+      "learning_rate": 0.00019999517712883087,
+      "loss": 0.9058388471603394,
+      "step": 1154
+    },
+    {
+      "epoch": 0.4988133764832794,
+      "grad_norm": 0.4710173010826111,
+      "learning_rate": 0.00019999468278891698,
+      "loss": 0.8462487459182739,
+      "step": 1156
+    },
+    {
+      "epoch": 0.49967637540453075,
+      "grad_norm": 0.4805637001991272,
+      "learning_rate": 0.0001999941643357361,
+      "loss": 0.8960906863212585,
+      "step": 1158
+    },
+    {
+      "epoch": 0.5005393743257821,
+      "grad_norm": 0.5108052492141724,
+      "learning_rate": 0.00019999362176941325,
+      "loss": 0.9074980020523071,
+      "step": 1160
+    },
+    {
+      "epoch": 0.5014023732470334,
+      "grad_norm": 0.49572333693504333,
+      "learning_rate": 0.00019999305509007932,
+      "loss": 0.9710080623626709,
+      "step": 1162
+    },
+    {
+      "epoch": 0.5022653721682848,
+      "grad_norm": 0.5304561257362366,
+      "learning_rate": 0.0001999924642978709,
+      "loss": 0.8877825140953064,
+      "step": 1164
+    },
+    {
+      "epoch": 0.5031283710895361,
+      "grad_norm": 0.5007328391075134,
+      "learning_rate": 0.0001999918493929305,
+      "loss": 0.8955381512641907,
+      "step": 1166
+    },
+    {
+      "epoch": 0.5039913700107875,
+      "grad_norm": 0.569549024105072,
+      "learning_rate": 0.0001999912103754064,
+      "loss": 0.9478562474250793,
+      "step": 1168
+    },
+    {
+      "epoch": 0.5048543689320388,
+      "grad_norm": 0.5354957580566406,
+      "learning_rate": 0.00019999054724545264,
+      "loss": 0.9685383439064026,
+      "step": 1170
+    },
+    {
+      "epoch": 0.5057173678532901,
+      "grad_norm": 0.547788143157959,
+      "learning_rate": 0.00019998986000322917,
+      "loss": 0.9221975207328796,
+      "step": 1172
+    },
+    {
+      "epoch": 0.5065803667745415,
+      "grad_norm": 0.4919529855251312,
+      "learning_rate": 0.00019998914864890175,
+      "loss": 0.9104788303375244,
+      "step": 1174
+    },
+    {
+      "epoch": 0.5074433656957928,
+      "grad_norm": 0.5274141430854797,
+      "learning_rate": 0.00019998841318264187,
+      "loss": 0.9176050424575806,
+      "step": 1176
+    },
+    {
+      "epoch": 0.5083063646170443,
+      "grad_norm": 0.4257420301437378,
+      "learning_rate": 0.00019998765360462688,
+      "loss": 0.8389710187911987,
+      "step": 1178
+    },
+    {
+      "epoch": 0.5091693635382956,
+      "grad_norm": 0.4947778880596161,
+      "learning_rate": 0.00019998686991504002,
+      "loss": 1.0164397954940796,
+      "step": 1180
+    },
+    {
+      "epoch": 0.510032362459547,
+      "grad_norm": 0.5540821552276611,
+      "learning_rate": 0.00019998606211407016,
+      "loss": 0.9900994300842285,
+      "step": 1182
+    },
+    {
+      "epoch": 0.5108953613807983,
+      "grad_norm": 0.4793289601802826,
+      "learning_rate": 0.0001999852302019122,
+      "loss": 0.8797636032104492,
+      "step": 1184
+    },
+    {
+      "epoch": 0.5117583603020496,
+      "grad_norm": 0.47429659962654114,
+      "learning_rate": 0.00019998437417876672,
+      "loss": 0.96225905418396,
+      "step": 1186
+    },
+    {
+      "epoch": 0.512621359223301,
+      "grad_norm": 0.44918450713157654,
+      "learning_rate": 0.00019998349404484013,
+      "loss": 0.8604235649108887,
+      "step": 1188
+    },
+    {
+      "epoch": 0.5134843581445523,
+      "grad_norm": 0.566977858543396,
+      "learning_rate": 0.00019998258980034468,
+      "loss": 1.0325366258621216,
+      "step": 1190
+    },
+    {
+      "epoch": 0.5143473570658037,
+      "grad_norm": 0.4671999514102936,
+      "learning_rate": 0.00019998166144549843,
+      "loss": 0.7658900022506714,
+      "step": 1192
+    },
+    {
+      "epoch": 0.515210355987055,
+      "grad_norm": 0.42312702536582947,
+      "learning_rate": 0.00019998070898052521,
+      "loss": 0.9365432858467102,
+      "step": 1194
+    },
+    {
+      "epoch": 0.5160733549083064,
+      "grad_norm": 0.4652721881866455,
+      "learning_rate": 0.00019997973240565476,
+      "loss": 0.771016538143158,
+      "step": 1196
+    },
+    {
+      "epoch": 0.5169363538295577,
+      "grad_norm": 0.5048499703407288,
+      "learning_rate": 0.00019997873172112254,
+      "loss": 0.9123705625534058,
+      "step": 1198
+    },
+    {
+      "epoch": 0.517799352750809,
+      "grad_norm": 0.5446439981460571,
+      "learning_rate": 0.0001999777069271699,
+      "loss": 0.8975751399993896,
+      "step": 1200
+    },
+    {
+      "epoch": 0.517799352750809,
+      "eval_loss": 0.9344067573547363,
+      "eval_runtime": 658.6934,
+      "eval_samples_per_second": 3.127,
+      "eval_steps_per_second": 3.127,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5186623516720604,
+      "grad_norm": 0.5044088959693909,
+      "learning_rate": 0.0001999766580240439,
+      "loss": 0.89097660779953,
+      "step": 1202
+    },
+    {
+      "epoch": 0.5195253505933117,
+      "grad_norm": 0.4672294855117798,
+      "learning_rate": 0.00019997558501199753,
+      "loss": 0.9138525128364563,
+      "step": 1204
+    },
+    {
+      "epoch": 0.5203883495145631,
+      "grad_norm": 0.45749008655548096,
+      "learning_rate": 0.00019997448789128952,
+      "loss": 0.8946340680122375,
+      "step": 1206
+    },
+    {
+      "epoch": 0.5212513484358144,
+      "grad_norm": 0.4828707277774811,
+      "learning_rate": 0.00019997336666218447,
+      "loss": 0.8661436438560486,
+      "step": 1208
+    },
+    {
+      "epoch": 0.5221143473570659,
+      "grad_norm": 0.3975147008895874,
+      "learning_rate": 0.0001999722213249527,
+      "loss": 0.7684835195541382,
+      "step": 1210
+    },
+    {
+      "epoch": 0.5229773462783172,
+      "grad_norm": 0.5642077326774597,
+      "learning_rate": 0.00019997105187987045,
+      "loss": 0.9667536616325378,
+      "step": 1212
+    },
+    {
+      "epoch": 0.5238403451995685,
+      "grad_norm": 0.4907105565071106,
+      "learning_rate": 0.00019996985832721972,
+      "loss": 0.8679366707801819,
+      "step": 1214
+    },
+    {
+      "epoch": 0.5247033441208199,
+      "grad_norm": 0.46214789152145386,
+      "learning_rate": 0.0001999686406672883,
+      "loss": 0.8802784085273743,
+      "step": 1216
+    },
+    {
+      "epoch": 0.5255663430420712,
+      "grad_norm": 0.4355131685733795,
+      "learning_rate": 0.00019996739890036985,
+      "loss": 0.8493598103523254,
+      "step": 1218
+    },
+    {
+      "epoch": 0.5264293419633226,
+      "grad_norm": 0.4293915331363678,
+      "learning_rate": 0.0001999661330267638,
+      "loss": 0.8949980735778809,
+      "step": 1220
+    },
+    {
+      "epoch": 0.5272923408845739,
+      "grad_norm": 0.5452485680580139,
+      "learning_rate": 0.00019996484304677544,
+      "loss": 0.9497376680374146,
+      "step": 1222
+    },
+    {
+      "epoch": 0.5281553398058253,
+      "grad_norm": 0.45874500274658203,
+      "learning_rate": 0.00019996352896071583,
+      "loss": 0.9170818328857422,
+      "step": 1224
+    },
+    {
+      "epoch": 0.5290183387270766,
+      "grad_norm": 0.4414025843143463,
+      "learning_rate": 0.00019996219076890182,
+      "loss": 0.7557252645492554,
+      "step": 1226
+    },
+    {
+      "epoch": 0.5298813376483279,
+      "grad_norm": 0.4891829192638397,
+      "learning_rate": 0.0001999608284716562,
+      "loss": 0.848960816860199,
+      "step": 1228
+    },
+    {
+      "epoch": 0.5307443365695793,
+      "grad_norm": 0.5048345327377319,
+      "learning_rate": 0.00019995944206930734,
+      "loss": 0.9555954933166504,
+      "step": 1230
+    },
+    {
+      "epoch": 0.5316073354908306,
+      "grad_norm": 0.5006756782531738,
+      "learning_rate": 0.00019995803156218968,
+      "loss": 0.8080939054489136,
+      "step": 1232
+    },
+    {
+      "epoch": 0.532470334412082,
+      "grad_norm": 0.5422173738479614,
+      "learning_rate": 0.00019995659695064332,
+      "loss": 0.8638371825218201,
+      "step": 1234
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.4535163640975952,
+      "learning_rate": 0.0001999551382350142,
+      "loss": 0.889068067073822,
+      "step": 1236
+    },
+    {
+      "epoch": 0.5341963322545846,
+      "grad_norm": 0.4588642418384552,
+      "learning_rate": 0.00019995365541565412,
+      "loss": 0.8803121447563171,
+      "step": 1238
+    },
+    {
+      "epoch": 0.535059331175836,
+      "grad_norm": 0.49366191029548645,
+      "learning_rate": 0.00019995214849292064,
+      "loss": 0.9694926738739014,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5359223300970873,
+      "grad_norm": 0.41988301277160645,
+      "learning_rate": 0.0001999506174671771,
+      "loss": 0.8367960453033447,
+      "step": 1242
+    },
+    {
+      "epoch": 0.5367853290183388,
+      "grad_norm": 0.5242130160331726,
+      "learning_rate": 0.00019994906233879273,
+      "loss": 0.942340612411499,
+      "step": 1244
+    },
+    {
+      "epoch": 0.53764832793959,
+      "grad_norm": 0.4899834096431732,
+      "learning_rate": 0.00019994748310814256,
+      "loss": 0.8926790356636047,
+      "step": 1246
+    },
+    {
+      "epoch": 0.5385113268608415,
+      "grad_norm": 0.5496823787689209,
+      "learning_rate": 0.00019994587977560744,
+      "loss": 0.99891597032547,
+      "step": 1248
+    },
+    {
+      "epoch": 0.5393743257820928,
+      "grad_norm": 0.4497414231300354,
+      "learning_rate": 0.00019994425234157396,
+      "loss": 0.8873116970062256,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5402373247033441,
+      "grad_norm": 0.4256928563117981,
+      "learning_rate": 0.00019994260080643454,
+      "loss": 0.9041396975517273,
+      "step": 1252
+    },
+    {
+      "epoch": 0.5411003236245955,
+      "grad_norm": 0.36910608410835266,
+      "learning_rate": 0.00019994092517058753,
+      "loss": 0.7647561430931091,
+      "step": 1254
+    },
+    {
+      "epoch": 0.5419633225458468,
+      "grad_norm": 0.537584125995636,
+      "learning_rate": 0.0001999392254344369,
+      "loss": 0.8892287015914917,
+      "step": 1256
+    },
+    {
+      "epoch": 0.5428263214670982,
+      "grad_norm": 0.49463894963264465,
+      "learning_rate": 0.00019993750159839264,
+      "loss": 0.8638571500778198,
+      "step": 1258
+    },
+    {
+      "epoch": 0.5436893203883495,
+      "grad_norm": 0.5052056908607483,
+      "learning_rate": 0.00019993575366287036,
+      "loss": 0.8165372014045715,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5445523193096009,
+      "grad_norm": 0.47367510199546814,
+      "learning_rate": 0.0001999339816282916,
+      "loss": 0.9099977016448975,
+      "step": 1262
+    },
+    {
+      "epoch": 0.5454153182308522,
+      "grad_norm": 0.4600350558757782,
+      "learning_rate": 0.00019993218549508364,
+      "loss": 0.8557311296463013,
+      "step": 1264
+    },
+    {
+      "epoch": 0.5462783171521035,
+      "grad_norm": 0.5684534311294556,
+      "learning_rate": 0.0001999303652636797,
+      "loss": 0.9136497974395752,
+      "step": 1266
+    },
+    {
+      "epoch": 0.5471413160733549,
+      "grad_norm": 0.5151359438896179,
+      "learning_rate": 0.00019992852093451865,
+      "loss": 0.7906932830810547,
+      "step": 1268
+    },
+    {
+      "epoch": 0.5480043149946062,
+      "grad_norm": 0.48577409982681274,
+      "learning_rate": 0.00019992665250804525,
+      "loss": 0.9326766133308411,
+      "step": 1270
+    },
+    {
+      "epoch": 0.5488673139158576,
+      "grad_norm": 0.490531325340271,
+      "learning_rate": 0.00019992475998471004,
+      "loss": 0.9734495878219604,
+      "step": 1272
+    },
+    {
+      "epoch": 0.5497303128371089,
+      "grad_norm": 0.5092435479164124,
+      "learning_rate": 0.00019992284336496947,
+      "loss": 0.8728410005569458,
+      "step": 1274
+    },
+    {
+      "epoch": 0.5505933117583603,
+      "grad_norm": 0.3843296766281128,
+      "learning_rate": 0.00019992090264928566,
+      "loss": 0.7572637796401978,
+      "step": 1276
+    },
+    {
+      "epoch": 0.5514563106796116,
+      "grad_norm": 0.534304678440094,
+      "learning_rate": 0.00019991893783812662,
+      "loss": 0.8895323872566223,
+      "step": 1278
+    },
+    {
+      "epoch": 0.552319309600863,
+      "grad_norm": 0.4567227363586426,
+      "learning_rate": 0.00019991694893196614,
+      "loss": 0.9318088293075562,
+      "step": 1280
+    },
+    {
+      "epoch": 0.5531823085221144,
+      "grad_norm": 0.48464900255203247,
+      "learning_rate": 0.0001999149359312839,
+      "loss": 0.8541979789733887,
+      "step": 1282
+    },
+    {
+      "epoch": 0.5540453074433657,
+      "grad_norm": 0.5569567084312439,
+      "learning_rate": 0.00019991289883656524,
+      "loss": 0.977894127368927,
+      "step": 1284
+    },
+    {
+      "epoch": 0.5549083063646171,
+      "grad_norm": 0.4637227952480316,
+      "learning_rate": 0.00019991083764830145,
+      "loss": 0.8860608339309692,
+      "step": 1286
+    },
+    {
+      "epoch": 0.5557713052858684,
+      "grad_norm": 0.4096687436103821,
+      "learning_rate": 0.00019990875236698956,
+      "loss": 0.8429648876190186,
+      "step": 1288
+    },
+    {
+      "epoch": 0.5566343042071198,
+      "grad_norm": 0.5221695303916931,
+      "learning_rate": 0.00019990664299313242,
+      "loss": 0.8510909080505371,
+      "step": 1290
+    },
+    {
+      "epoch": 0.5574973031283711,
+      "grad_norm": 0.5155899524688721,
+      "learning_rate": 0.00019990450952723872,
+      "loss": 0.8971074223518372,
+      "step": 1292
+    },
+    {
+      "epoch": 0.5583603020496224,
+      "grad_norm": 0.5064809322357178,
+      "learning_rate": 0.0001999023519698229,
+      "loss": 0.9030373096466064,
+      "step": 1294
+    },
+    {
+      "epoch": 0.5592233009708738,
+      "grad_norm": 0.40551698207855225,
+      "learning_rate": 0.00019990017032140526,
+      "loss": 0.7866057753562927,
+      "step": 1296
+    },
+    {
+      "epoch": 0.5600862998921251,
+      "grad_norm": 0.5009430050849915,
+      "learning_rate": 0.00019989796458251194,
+      "loss": 0.9477730989456177,
+      "step": 1298
+    },
+    {
+      "epoch": 0.5609492988133765,
+      "grad_norm": 0.5192028880119324,
+      "learning_rate": 0.00019989573475367477,
+      "loss": 0.9206778407096863,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5609492988133765,
+      "eval_loss": 0.9177446365356445,
+      "eval_runtime": 665.3245,
+      "eval_samples_per_second": 3.096,
+      "eval_steps_per_second": 3.096,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5618122977346278,
+      "grad_norm": 0.5580230951309204,
+      "learning_rate": 0.00019989348083543148,
+      "loss": 0.9516512155532837,
+      "step": 1302
+    },
+    {
+      "epoch": 0.5626752966558792,
+      "grad_norm": 0.4151005744934082,
+      "learning_rate": 0.00019989120282832564,
+      "loss": 0.7725991606712341,
+      "step": 1304
+    },
+    {
+      "epoch": 0.5635382955771305,
+      "grad_norm": 0.56330406665802,
+      "learning_rate": 0.00019988890073290656,
+      "loss": 0.9241501688957214,
+      "step": 1306
+    },
+    {
+      "epoch": 0.5644012944983818,
+      "grad_norm": 0.44836440682411194,
+      "learning_rate": 0.00019988657454972936,
+      "loss": 0.8351686000823975,
+      "step": 1308
+    },
+    {
+      "epoch": 0.5652642934196332,
+      "grad_norm": 0.5414754152297974,
+      "learning_rate": 0.00019988422427935496,
+      "loss": 0.9033217430114746,
+      "step": 1310
+    },
+    {
+      "epoch": 0.5661272923408845,
+      "grad_norm": 0.5283750891685486,
+      "learning_rate": 0.0001998818499223502,
+      "loss": 0.8885331153869629,
+      "step": 1312
+    },
+    {
+      "epoch": 0.566990291262136,
+      "grad_norm": 0.45846256613731384,
+      "learning_rate": 0.00019987945147928758,
+      "loss": 0.8359912037849426,
+      "step": 1314
+    },
+    {
+      "epoch": 0.5678532901833873,
+      "grad_norm": 0.44439879059791565,
+      "learning_rate": 0.0001998770289507455,
+      "loss": 0.8327895402908325,
+      "step": 1316
+    },
+    {
+      "epoch": 0.5687162891046387,
+      "grad_norm": 0.5491341948509216,
+      "learning_rate": 0.00019987458233730813,
+      "loss": 0.9354757070541382,
+      "step": 1318
+    },
+    {
+      "epoch": 0.56957928802589,
+      "grad_norm": 0.5502263307571411,
+      "learning_rate": 0.00019987211163956548,
+      "loss": 0.944054901599884,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5704422869471413,
+      "grad_norm": 0.47165682911872864,
+      "learning_rate": 0.00019986961685811334,
+      "loss": 0.9515072107315063,
+      "step": 1322
+    },
+    {
+      "epoch": 0.5713052858683927,
+      "grad_norm": 0.5136987566947937,
+      "learning_rate": 0.0001998670979935533,
+      "loss": 0.9455493688583374,
+      "step": 1324
+    },
+    {
+      "epoch": 0.572168284789644,
+      "grad_norm": 0.4822693169116974,
+      "learning_rate": 0.00019986455504649277,
+      "loss": 0.8626728057861328,
+      "step": 1326
+    },
+    {
+      "epoch": 0.5730312837108954,
+      "grad_norm": 0.4639468193054199,
+      "learning_rate": 0.000199861988017545,
+      "loss": 0.8857194781303406,
+      "step": 1328
+    },
+    {
+      "epoch": 0.5738942826321467,
+      "grad_norm": 0.5224950313568115,
+      "learning_rate": 0.00019985939690732898,
+      "loss": 0.9198446273803711,
+      "step": 1330
+    },
+    {
+      "epoch": 0.574757281553398,
+      "grad_norm": 0.47504499554634094,
+      "learning_rate": 0.00019985678171646954,
+      "loss": 0.8785439133644104,
+      "step": 1332
+    },
+    {
+      "epoch": 0.5756202804746494,
+      "grad_norm": 0.5022051930427551,
+      "learning_rate": 0.0001998541424455974,
+      "loss": 0.9593754410743713,
+      "step": 1334
+    },
+    {
+      "epoch": 0.5764832793959007,
+      "grad_norm": 0.4572875201702118,
+      "learning_rate": 0.00019985147909534897,
+      "loss": 0.986197292804718,
+      "step": 1336
+    },
+    {
+      "epoch": 0.5773462783171521,
+      "grad_norm": 0.5153827667236328,
+      "learning_rate": 0.00019984879166636644,
+      "loss": 0.9163863658905029,
+      "step": 1338
+    },
+    {
+      "epoch": 0.5782092772384034,
+      "grad_norm": 0.4813650846481323,
+      "learning_rate": 0.00019984608015929792,
+      "loss": 0.8815995454788208,
+      "step": 1340
+    },
+    {
+      "epoch": 0.5790722761596548,
+      "grad_norm": 0.4319819211959839,
+      "learning_rate": 0.0001998433445747973,
+      "loss": 0.857044517993927,
+      "step": 1342
+    },
+    {
+      "epoch": 0.5799352750809061,
+      "grad_norm": 0.5128870010375977,
+      "learning_rate": 0.00019984058491352423,
+      "loss": 0.8939256072044373,
+      "step": 1344
+    },
+    {
+      "epoch": 0.5807982740021574,
+      "grad_norm": 0.41450315713882446,
+      "learning_rate": 0.0001998378011761442,
+      "loss": 0.9267327785491943,
+      "step": 1346
+    },
+    {
+      "epoch": 0.5816612729234089,
+      "grad_norm": 0.42916348576545715,
+      "learning_rate": 0.00019983499336332844,
+      "loss": 0.8494639992713928,
+      "step": 1348
+    },
+    {
+      "epoch": 0.5825242718446602,
+      "grad_norm": 0.43995746970176697,
+      "learning_rate": 0.00019983216147575412,
+      "loss": 0.9720427989959717,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5833872707659116,
+      "grad_norm": 0.5063773989677429,
+      "learning_rate": 0.00019982930551410411,
+      "loss": 0.9400854706764221,
+      "step": 1352
+    },
+    {
+      "epoch": 0.5842502696871629,
+      "grad_norm": 0.5029586553573608,
+      "learning_rate": 0.0001998264254790671,
+      "loss": 0.8657845258712769,
+      "step": 1354
+    },
+    {
+      "epoch": 0.5851132686084143,
+      "grad_norm": 0.45519232749938965,
+      "learning_rate": 0.00019982352137133764,
+      "loss": 0.8593506813049316,
+      "step": 1356
+    },
+    {
+      "epoch": 0.5859762675296656,
+      "grad_norm": 0.49116215109825134,
+      "learning_rate": 0.000199820593191616,
+      "loss": 0.8658114671707153,
+      "step": 1358
+    },
+    {
+      "epoch": 0.5868392664509169,
+      "grad_norm": 0.45347318053245544,
+      "learning_rate": 0.00019981764094060826,
+      "loss": 0.8044605255126953,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5877022653721683,
+      "grad_norm": 0.5191754698753357,
+      "learning_rate": 0.00019981466461902643,
+      "loss": 0.9176861047744751,
+      "step": 1362
+    },
+    {
+      "epoch": 0.5885652642934196,
+      "grad_norm": 0.4791528284549713,
+      "learning_rate": 0.00019981166422758818,
+      "loss": 0.8453370928764343,
+      "step": 1364
+    },
+    {
+      "epoch": 0.589428263214671,
+      "grad_norm": 0.5105116367340088,
+      "learning_rate": 0.00019980863976701705,
+      "loss": 0.9343777298927307,
+      "step": 1366
+    },
+    {
+      "epoch": 0.5902912621359223,
+      "grad_norm": 0.44593656063079834,
+      "learning_rate": 0.00019980559123804236,
+      "loss": 0.8950760960578918,
+      "step": 1368
+    },
+    {
+      "epoch": 0.5911542610571737,
+      "grad_norm": 0.4375658631324768,
+      "learning_rate": 0.0001998025186413993,
+      "loss": 0.8613521456718445,
+      "step": 1370
+    },
+    {
+      "epoch": 0.592017259978425,
+      "grad_norm": 0.5138815641403198,
+      "learning_rate": 0.00019979942197782878,
+      "loss": 0.8982083201408386,
+      "step": 1372
+    },
+    {
+      "epoch": 0.5928802588996763,
+      "grad_norm": 0.45473602414131165,
+      "learning_rate": 0.00019979630124807753,
+      "loss": 0.9372450709342957,
+      "step": 1374
+    },
+    {
+      "epoch": 0.5937432578209277,
+      "grad_norm": 0.4961191713809967,
+      "learning_rate": 0.00019979315645289814,
+      "loss": 0.8758652806282043,
+      "step": 1376
+    },
+    {
+      "epoch": 0.594606256742179,
+      "grad_norm": 0.5672827363014221,
+      "learning_rate": 0.00019978998759304895,
+      "loss": 0.9852207899093628,
+      "step": 1378
+    },
+    {
+      "epoch": 0.5954692556634305,
+      "grad_norm": 0.44907906651496887,
+      "learning_rate": 0.00019978679466929407,
+      "loss": 0.8451287746429443,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5963322545846818,
+      "grad_norm": 0.4759652316570282,
+      "learning_rate": 0.00019978357768240352,
+      "loss": 0.8381558656692505,
+      "step": 1382
+    },
+    {
+      "epoch": 0.5971952535059332,
+      "grad_norm": 0.4936048686504364,
+      "learning_rate": 0.00019978033663315304,
+      "loss": 0.8820816874504089,
+      "step": 1384
+    },
+    {
+      "epoch": 0.5980582524271845,
+      "grad_norm": 0.44983741641044617,
+      "learning_rate": 0.00019977707152232416,
+      "loss": 0.9156787991523743,
+      "step": 1386
+    },
+    {
+      "epoch": 0.5989212513484358,
+      "grad_norm": 0.45198705792427063,
+      "learning_rate": 0.0001997737823507043,
+      "loss": 0.8285194039344788,
+      "step": 1388
+    },
+    {
+      "epoch": 0.5997842502696872,
+      "grad_norm": 0.45788463950157166,
+      "learning_rate": 0.00019977046911908664,
+      "loss": 0.8109505772590637,
+      "step": 1390
+    },
+    {
+      "epoch": 0.6006472491909385,
+      "grad_norm": 0.4795142412185669,
+      "learning_rate": 0.0001997671318282701,
+      "loss": 0.8285947442054749,
+      "step": 1392
+    },
+    {
+      "epoch": 0.6015102481121899,
+      "grad_norm": 0.5026728510856628,
+      "learning_rate": 0.00019976377047905945,
+      "loss": 0.9497535228729248,
+      "step": 1394
+    },
+    {
+      "epoch": 0.6023732470334412,
+      "grad_norm": 0.4994853734970093,
+      "learning_rate": 0.0001997603850722653,
+      "loss": 0.9171916246414185,
+      "step": 1396
+    },
+    {
+      "epoch": 0.6032362459546926,
+      "grad_norm": 0.4789866507053375,
+      "learning_rate": 0.00019975697560870403,
+      "loss": 0.7894434928894043,
+      "step": 1398
+    },
+    {
+      "epoch": 0.6040992448759439,
+      "grad_norm": 0.42282742261886597,
+      "learning_rate": 0.0001997535420891978,
+      "loss": 0.8942429423332214,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6040992448759439,
+      "eval_loss": 0.9080492854118347,
+      "eval_runtime": 661.4597,
+      "eval_samples_per_second": 3.114,
+      "eval_steps_per_second": 3.114,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6049622437971952,
+      "grad_norm": 0.5789905190467834,
+      "learning_rate": 0.00019975008451457454,
+      "loss": 0.8938372731208801,
+      "step": 1402
+    },
+    {
+      "epoch": 0.6058252427184466,
+      "grad_norm": 0.46121683716773987,
+      "learning_rate": 0.00019974660288566814,
+      "loss": 0.8746235370635986,
+      "step": 1404
+    },
+    {
+      "epoch": 0.6066882416396979,
+      "grad_norm": 0.5195551514625549,
+      "learning_rate": 0.00019974309720331807,
+      "loss": 0.8650617003440857,
+      "step": 1406
+    },
+    {
+      "epoch": 0.6075512405609493,
+      "grad_norm": 0.46930259466171265,
+      "learning_rate": 0.00019973956746836976,
+      "loss": 0.8853039145469666,
+      "step": 1408
+    },
+    {
+      "epoch": 0.6084142394822006,
+      "grad_norm": 0.40869632363319397,
+      "learning_rate": 0.0001997360136816744,
+      "loss": 0.7865594029426575,
+      "step": 1410
+    },
+    {
+      "epoch": 0.609277238403452,
+      "grad_norm": 0.5398361086845398,
+      "learning_rate": 0.00019973243584408895,
+      "loss": 0.907535970211029,
+      "step": 1412
+    },
+    {
+      "epoch": 0.6101402373247033,
+      "grad_norm": 0.5110154747962952,
+      "learning_rate": 0.00019972883395647615,
+      "loss": 0.8682730197906494,
+      "step": 1414
+    },
+    {
+      "epoch": 0.6110032362459547,
+      "grad_norm": 0.44484639167785645,
+      "learning_rate": 0.00019972520801970467,
+      "loss": 0.8786011338233948,
+      "step": 1416
+    },
+    {
+      "epoch": 0.6118662351672061,
+      "grad_norm": 0.4768071472644806,
+      "learning_rate": 0.0001997215580346488,
+      "loss": 0.9021878242492676,
+      "step": 1418
+    },
+    {
+      "epoch": 0.6127292340884574,
+      "grad_norm": 0.43265241384506226,
+      "learning_rate": 0.0001997178840021888,
+      "loss": 0.7737482786178589,
+      "step": 1420
+    },
+    {
+      "epoch": 0.6135922330097088,
+      "grad_norm": 0.525692343711853,
+      "learning_rate": 0.0001997141859232106,
+      "loss": 0.876280665397644,
+      "step": 1422
+    },
+    {
+      "epoch": 0.6144552319309601,
+      "grad_norm": 0.48206865787506104,
+      "learning_rate": 0.00019971046379860594,
+      "loss": 0.8503577709197998,
+      "step": 1424
+    },
+    {
+      "epoch": 0.6153182308522115,
+      "grad_norm": 0.6032769680023193,
+      "learning_rate": 0.00019970671762927246,
+      "loss": 0.9459730982780457,
+      "step": 1426
+    },
+    {
+      "epoch": 0.6161812297734628,
+      "grad_norm": 0.4491981863975525,
+      "learning_rate": 0.0001997029474161135,
+      "loss": 0.8836647868156433,
+      "step": 1428
+    },
+    {
+      "epoch": 0.6170442286947141,
+      "grad_norm": 0.47503358125686646,
+      "learning_rate": 0.00019969915316003824,
+      "loss": 0.8614388108253479,
+      "step": 1430
+    },
+    {
+      "epoch": 0.6179072276159655,
+      "grad_norm": 0.44801047444343567,
+      "learning_rate": 0.00019969533486196162,
+      "loss": 0.8420360684394836,
+      "step": 1432
+    },
+    {
+      "epoch": 0.6187702265372168,
+      "grad_norm": 0.45057111978530884,
+      "learning_rate": 0.00019969149252280446,
+      "loss": 0.8256269693374634,
+      "step": 1434
+    },
+    {
+      "epoch": 0.6196332254584682,
+      "grad_norm": 0.4589645266532898,
+      "learning_rate": 0.00019968762614349327,
+      "loss": 0.9130199551582336,
+      "step": 1436
+    },
+    {
+      "epoch": 0.6204962243797195,
+      "grad_norm": 0.48914027214050293,
+      "learning_rate": 0.00019968373572496045,
+      "loss": 0.74083012342453,
+      "step": 1438
+    },
+    {
+      "epoch": 0.6213592233009708,
+      "grad_norm": 0.4582098424434662,
+      "learning_rate": 0.00019967982126814412,
+      "loss": 0.8538379669189453,
+      "step": 1440
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.48722779750823975,
+      "learning_rate": 0.00019967588277398823,
+      "loss": 0.8780114054679871,
+      "step": 1442
+    },
+    {
+      "epoch": 0.6230852211434735,
+      "grad_norm": 0.4291327893733978,
+      "learning_rate": 0.00019967192024344254,
+      "loss": 0.8341028690338135,
+      "step": 1444
+    },
+    {
+      "epoch": 0.623948220064725,
+      "grad_norm": 0.4773139953613281,
+      "learning_rate": 0.00019966793367746265,
+      "loss": 0.8651667237281799,
+      "step": 1446
+    },
+    {
+      "epoch": 0.6248112189859762,
+      "grad_norm": 0.45556166768074036,
+      "learning_rate": 0.00019966392307700986,
+      "loss": 0.8339929580688477,
+      "step": 1448
+    },
+    {
+      "epoch": 0.6256742179072277,
+      "grad_norm": 0.5126671195030212,
+      "learning_rate": 0.00019965988844305129,
+      "loss": 0.9129340052604675,
+      "step": 1450
+    },
+    {
+      "epoch": 0.626537216828479,
+      "grad_norm": 0.6067109704017639,
+      "learning_rate": 0.00019965582977655988,
+      "loss": 0.9057610034942627,
+      "step": 1452
+    },
+    {
+      "epoch": 0.6274002157497303,
+      "grad_norm": 0.46425968408584595,
+      "learning_rate": 0.00019965174707851438,
+      "loss": 0.874100387096405,
+      "step": 1454
+    },
+    {
+      "epoch": 0.6282632146709817,
+      "grad_norm": 0.481077641248703,
+      "learning_rate": 0.0001996476403498993,
+      "loss": 0.915635347366333,
+      "step": 1456
+    },
+    {
+      "epoch": 0.629126213592233,
+      "grad_norm": 0.47299909591674805,
+      "learning_rate": 0.000199643509591705,
+      "loss": 0.9059650301933289,
+      "step": 1458
+    },
+    {
+      "epoch": 0.6299892125134844,
+      "grad_norm": 0.48924630880355835,
+      "learning_rate": 0.00019963935480492753,
+      "loss": 0.9775188565254211,
+      "step": 1460
+    },
+    {
+      "epoch": 0.6308522114347357,
+      "grad_norm": 0.4407665431499481,
+      "learning_rate": 0.0001996351759905688,
+      "loss": 0.8950685858726501,
+      "step": 1462
+    },
+    {
+      "epoch": 0.6317152103559871,
+      "grad_norm": 0.5018318295478821,
+      "learning_rate": 0.00019963097314963657,
+      "loss": 0.8532119989395142,
+      "step": 1464
+    },
+    {
+      "epoch": 0.6325782092772384,
+      "grad_norm": 0.43245720863342285,
+      "learning_rate": 0.0001996267462831443,
+      "loss": 0.7775963544845581,
+      "step": 1466
+    },
+    {
+      "epoch": 0.6334412081984897,
+      "grad_norm": 0.5028865337371826,
+      "learning_rate": 0.00019962249539211125,
+      "loss": 0.8315839767456055,
+      "step": 1468
+    },
+    {
+      "epoch": 0.6343042071197411,
+      "grad_norm": 0.4697185754776001,
+      "learning_rate": 0.0001996182204775626,
+      "loss": 0.849076509475708,
+      "step": 1470
+    },
+    {
+      "epoch": 0.6351672060409924,
+      "grad_norm": 0.46725034713745117,
+      "learning_rate": 0.00019961392154052912,
+      "loss": 0.8828577995300293,
+      "step": 1472
+    },
+    {
+      "epoch": 0.6360302049622438,
+      "grad_norm": 0.4301203489303589,
+      "learning_rate": 0.00019960959858204754,
+      "loss": 0.850115954875946,
+      "step": 1474
+    },
+    {
+      "epoch": 0.6368932038834951,
+      "grad_norm": 0.46635881066322327,
+      "learning_rate": 0.0001996052516031603,
+      "loss": 0.7912618517875671,
+      "step": 1476
+    },
+    {
+      "epoch": 0.6377562028047465,
+      "grad_norm": 0.44143620133399963,
+      "learning_rate": 0.00019960088060491565,
+      "loss": 0.9072504639625549,
+      "step": 1478
+    },
+    {
+      "epoch": 0.6386192017259978,
+      "grad_norm": 0.47458893060684204,
+      "learning_rate": 0.00019959648558836763,
+      "loss": 0.8976638317108154,
+      "step": 1480
+    },
+    {
+      "epoch": 0.6394822006472491,
+      "grad_norm": 0.4596816897392273,
+      "learning_rate": 0.00019959206655457612,
+      "loss": 0.8142043352127075,
+      "step": 1482
+    },
+    {
+      "epoch": 0.6403451995685006,
+      "grad_norm": 0.4839977025985718,
+      "learning_rate": 0.0001995876235046067,
+      "loss": 0.860643744468689,
+      "step": 1484
+    },
+    {
+      "epoch": 0.6412081984897519,
+      "grad_norm": 0.3542814552783966,
+      "learning_rate": 0.00019958315643953085,
+      "loss": 0.7586524486541748,
+      "step": 1486
+    },
+    {
+      "epoch": 0.6420711974110033,
+      "grad_norm": 0.5423269271850586,
+      "learning_rate": 0.00019957866536042572,
+      "loss": 0.9353570342063904,
+      "step": 1488
+    },
+    {
+      "epoch": 0.6429341963322546,
+      "grad_norm": 0.4580909013748169,
+      "learning_rate": 0.00019957415026837437,
+      "loss": 0.9919291138648987,
+      "step": 1490
+    },
+    {
+      "epoch": 0.643797195253506,
+      "grad_norm": 0.4211732745170593,
+      "learning_rate": 0.00019956961116446555,
+      "loss": 0.8720914125442505,
+      "step": 1492
+    },
+    {
+      "epoch": 0.6446601941747573,
+      "grad_norm": 0.4583161175251007,
+      "learning_rate": 0.00019956504804979384,
+      "loss": 0.8661212921142578,
+      "step": 1494
+    },
+    {
+      "epoch": 0.6455231930960086,
+      "grad_norm": 0.4359884262084961,
+      "learning_rate": 0.00019956046092545966,
+      "loss": 0.8170996308326721,
+      "step": 1496
+    },
+    {
+      "epoch": 0.64638619201726,
+      "grad_norm": 0.4642556607723236,
+      "learning_rate": 0.00019955584979256913,
+      "loss": 0.8607422113418579,
+      "step": 1498
+    },
+    {
+      "epoch": 0.6472491909385113,
+      "grad_norm": 0.4496007561683655,
+      "learning_rate": 0.00019955121465223426,
+      "loss": 0.837529182434082,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6472491909385113,
+      "eval_loss": 0.8972997665405273,
+      "eval_runtime": 649.796,
+      "eval_samples_per_second": 3.17,
+      "eval_steps_per_second": 3.17,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 13908,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.001
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.99747667572269e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/sft_qwen_14B/checkpoints/checkpoint-1500/training_args.bin b/sft_qwen_14B/checkpoints/checkpoint-1500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b023888140f1fb107e8d5ebbfbcb9d9558b09d43
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-1500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4200830b23d19bc86049c280236c4a6b18c26d7061b5a57cc024888ec760920f
+size 5201
diff --git a/sft_qwen_14B/checkpoints/checkpoint-2000/README.md b/sft_qwen_14B/checkpoints/checkpoint-2000/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..779b6406e547b32301fef1d181301a873befe542
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-2000/README.md
@@ -0,0 +1,207 @@
+---
+base_model: runs/cpt_run_14b/merged_14b_cpt_lora
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:runs/cpt_run_14b/merged_14b_cpt_lora
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0
\ No newline at end of file
diff --git a/sft_qwen_14B/checkpoints/checkpoint-2000/adapter_config.json b/sft_qwen_14B/checkpoints/checkpoint-2000/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8ea271115c141fb10c6d899b06f46f21800e1ad6
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-2000/adapter_config.json
@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "runs/cpt_run_14b/merged_14b_cpt_lora",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/sft_qwen_14B/checkpoints/checkpoint-2000/adapter_model.safetensors b/sft_qwen_14B/checkpoints/checkpoint-2000/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d990ec5607df5cc8851209454bf3603f346e9ec9
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-2000/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac4fd06ae0a5072195431c638f9fa0553bde7cbdef4450af22ee4920688ac7c1
+size 100715016
diff --git a/sft_qwen_14B/checkpoints/checkpoint-2000/optimizer.pt b/sft_qwen_14B/checkpoints/checkpoint-2000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bb9d8cb87edd73175a1d9cdf0666db50b8a0a47a
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-2000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1169f222c822dab1e5ce598a86b466b0ac52e8232e29a6e897e87612c208a024
+size 201650659
diff --git a/sft_qwen_14B/checkpoints/checkpoint-2000/rng_state.pth b/sft_qwen_14B/checkpoints/checkpoint-2000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..55b3880f66665986ce2c81375bd08272b7c26801
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-2000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceabeff68a5532e9645fa847866094307abb118a32832ab82c4e32244ed9ef1a
+size 14645
diff --git a/sft_qwen_14B/checkpoints/checkpoint-2000/scheduler.pt b/sft_qwen_14B/checkpoints/checkpoint-2000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d498b54350967a0950de21941a212808c70eeaca
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-2000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37edb23690c4b97b9dc4a4a7b4f3bb29738198651fbb5fb02cf420e84396a51b
+size 1465
diff --git a/sft_qwen_14B/checkpoints/checkpoint-2000/trainer_state.json b/sft_qwen_14B/checkpoints/checkpoint-2000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..34ffd6900dd6a53bb4aff080dabaebe5d36e97ca
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-2000/trainer_state.json
@@ -0,0 +1,7203 @@
+{
+  "best_global_step": 2000,
+  "best_metric": 0.8567262887954712,
+  "best_model_checkpoint": "runs/instruct_run_14b_v1/checkpoints/checkpoint-2000",
+  "epoch": 0.8629989212513485,
+  "eval_steps": 100,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008629989212513484,
+      "grad_norm": 0.36567428708076477,
+      "learning_rate": 1.7969451931716084e-07,
+      "loss": 1.6794371604919434,
+      "step": 2
+    },
+    {
+      "epoch": 0.001725997842502697,
+      "grad_norm": 0.4024646580219269,
+      "learning_rate": 5.390835579514825e-07,
+      "loss": 1.6853073835372925,
+      "step": 4
+    },
+    {
+      "epoch": 0.0025889967637540453,
+      "grad_norm": 0.40199393033981323,
+      "learning_rate": 8.984725965858042e-07,
+      "loss": 1.7621158361434937,
+      "step": 6
+    },
+    {
+      "epoch": 0.003451995685005394,
+      "grad_norm": 0.35409677028656006,
+      "learning_rate": 1.257861635220126e-06,
+      "loss": 1.633257269859314,
+      "step": 8
+    },
+    {
+      "epoch": 0.004314994606256742,
+      "grad_norm": 0.39087551832199097,
+      "learning_rate": 1.6172506738544475e-06,
+      "loss": 1.7374768257141113,
+      "step": 10
+    },
+    {
+      "epoch": 0.005177993527508091,
+      "grad_norm": 0.3586857318878174,
+      "learning_rate": 1.9766397124887693e-06,
+      "loss": 1.6955714225769043,
+      "step": 12
+    },
+    {
+      "epoch": 0.006040992448759439,
+      "grad_norm": 0.32755669951438904,
+      "learning_rate": 2.3360287511230908e-06,
+      "loss": 1.720664381980896,
+      "step": 14
+    },
+    {
+      "epoch": 0.006903991370010788,
+      "grad_norm": 0.4054872691631317,
+      "learning_rate": 2.6954177897574127e-06,
+      "loss": 1.6957035064697266,
+      "step": 16
+    },
+    {
+      "epoch": 0.007766990291262136,
+      "grad_norm": 0.37593814730644226,
+      "learning_rate": 3.0548068283917343e-06,
+      "loss": 1.7286947965621948,
+      "step": 18
+    },
+    {
+      "epoch": 0.008629989212513484,
+      "grad_norm": 0.3344813287258148,
+      "learning_rate": 3.414195867026056e-06,
+      "loss": 1.727295994758606,
+      "step": 20
+    },
+    {
+      "epoch": 0.009492988133764833,
+      "grad_norm": 0.357474148273468,
+      "learning_rate": 3.7735849056603773e-06,
+      "loss": 1.6727914810180664,
+      "step": 22
+    },
+    {
+      "epoch": 0.010355987055016181,
+      "grad_norm": 0.39115726947784424,
+      "learning_rate": 4.132973944294699e-06,
+      "loss": 1.6518884897232056,
+      "step": 24
+    },
+    {
+      "epoch": 0.01121898597626753,
+      "grad_norm": 0.4711727201938629,
+      "learning_rate": 4.492362982929021e-06,
+      "loss": 1.7868088483810425,
+      "step": 26
+    },
+    {
+      "epoch": 0.012081984897518877,
+      "grad_norm": 0.34112176299095154,
+      "learning_rate": 4.851752021563342e-06,
+      "loss": 1.6127634048461914,
+      "step": 28
+    },
+    {
+      "epoch": 0.012944983818770227,
+      "grad_norm": 0.5071991682052612,
+      "learning_rate": 5.211141060197664e-06,
+      "loss": 1.7858378887176514,
+      "step": 30
+    },
+    {
+      "epoch": 0.013807982740021575,
+      "grad_norm": 0.42048847675323486,
+      "learning_rate": 5.570530098831986e-06,
+      "loss": 1.7123326063156128,
+      "step": 32
+    },
+    {
+      "epoch": 0.014670981661272923,
+      "grad_norm": 0.48883870244026184,
+      "learning_rate": 5.929919137466308e-06,
+      "loss": 1.737749695777893,
+      "step": 34
+    },
+    {
+      "epoch": 0.015533980582524271,
+      "grad_norm": 0.3311465084552765,
+      "learning_rate": 6.289308176100629e-06,
+      "loss": 1.5578981637954712,
+      "step": 36
+    },
+    {
+      "epoch": 0.01639697950377562,
+      "grad_norm": 0.5178973078727722,
+      "learning_rate": 6.64869721473495e-06,
+      "loss": 1.719806432723999,
+      "step": 38
+    },
+    {
+      "epoch": 0.017259978425026967,
+      "grad_norm": 0.47097742557525635,
+      "learning_rate": 7.008086253369272e-06,
+      "loss": 1.728212833404541,
+      "step": 40
+    },
+    {
+      "epoch": 0.018122977346278317,
+      "grad_norm": 0.5051584243774414,
+      "learning_rate": 7.367475292003594e-06,
+      "loss": 1.6542466878890991,
+      "step": 42
+    },
+    {
+      "epoch": 0.018985976267529667,
+      "grad_norm": 0.4645111560821533,
+      "learning_rate": 7.726864330637915e-06,
+      "loss": 1.7087690830230713,
+      "step": 44
+    },
+    {
+      "epoch": 0.019848975188781013,
+      "grad_norm": 0.5184999704360962,
+      "learning_rate": 8.086253369272237e-06,
+      "loss": 1.7018946409225464,
+      "step": 46
+    },
+    {
+      "epoch": 0.020711974110032363,
+      "grad_norm": 0.4543815851211548,
+      "learning_rate": 8.44564240790656e-06,
+      "loss": 1.6818269491195679,
+      "step": 48
+    },
+    {
+      "epoch": 0.021574973031283712,
+      "grad_norm": 0.44411996006965637,
+      "learning_rate": 8.80503144654088e-06,
+      "loss": 1.5772877931594849,
+      "step": 50
+    },
+    {
+      "epoch": 0.02243797195253506,
+      "grad_norm": 0.3409404158592224,
+      "learning_rate": 9.164420485175203e-06,
+      "loss": 1.498152732849121,
+      "step": 52
+    },
+    {
+      "epoch": 0.02330097087378641,
+      "grad_norm": 0.42104434967041016,
+      "learning_rate": 9.523809523809523e-06,
+      "loss": 1.6189048290252686,
+      "step": 54
+    },
+    {
+      "epoch": 0.024163969795037755,
+      "grad_norm": 0.3756246268749237,
+      "learning_rate": 9.883198562443846e-06,
+      "loss": 1.4596441984176636,
+      "step": 56
+    },
+    {
+      "epoch": 0.025026968716289105,
+      "grad_norm": 0.36214128136634827,
+      "learning_rate": 1.0242587601078168e-05,
+      "loss": 1.503880500793457,
+      "step": 58
+    },
+    {
+      "epoch": 0.025889967637540454,
+      "grad_norm": 0.40893009305000305,
+      "learning_rate": 1.060197663971249e-05,
+      "loss": 1.5912823677062988,
+      "step": 60
+    },
+    {
+      "epoch": 0.0267529665587918,
+      "grad_norm": 0.28710272908210754,
+      "learning_rate": 1.0961365678346811e-05,
+      "loss": 1.2956721782684326,
+      "step": 62
+    },
+    {
+      "epoch": 0.02761596548004315,
+      "grad_norm": 0.304573118686676,
+      "learning_rate": 1.1320754716981132e-05,
+      "loss": 1.4648056030273438,
+      "step": 64
+    },
+    {
+      "epoch": 0.0284789644012945,
+      "grad_norm": 0.36523914337158203,
+      "learning_rate": 1.1680143755615454e-05,
+      "loss": 1.6078968048095703,
+      "step": 66
+    },
+    {
+      "epoch": 0.029341963322545846,
+      "grad_norm": 0.37929031252861023,
+      "learning_rate": 1.2039532794249775e-05,
+      "loss": 1.5969421863555908,
+      "step": 68
+    },
+    {
+      "epoch": 0.030204962243797196,
+      "grad_norm": 0.3053947389125824,
+      "learning_rate": 1.2398921832884097e-05,
+      "loss": 1.4312325716018677,
+      "step": 70
+    },
+    {
+      "epoch": 0.031067961165048542,
+      "grad_norm": 0.3028779923915863,
+      "learning_rate": 1.275831087151842e-05,
+      "loss": 1.4101300239562988,
+      "step": 72
+    },
+    {
+      "epoch": 0.03193096008629989,
+      "grad_norm": 0.29649803042411804,
+      "learning_rate": 1.3117699910152742e-05,
+      "loss": 1.4553817510604858,
+      "step": 74
+    },
+    {
+      "epoch": 0.03279395900755124,
+      "grad_norm": 0.26032644510269165,
+      "learning_rate": 1.3477088948787062e-05,
+      "loss": 1.4623000621795654,
+      "step": 76
+    },
+    {
+      "epoch": 0.03365695792880259,
+      "grad_norm": 0.33558446168899536,
+      "learning_rate": 1.3836477987421385e-05,
+      "loss": 1.5181745290756226,
+      "step": 78
+    },
+    {
+      "epoch": 0.034519956850053934,
+      "grad_norm": 0.28307804465293884,
+      "learning_rate": 1.4195867026055706e-05,
+      "loss": 1.4397861957550049,
+      "step": 80
+    },
+    {
+      "epoch": 0.035382955771305284,
+      "grad_norm": 0.3451690673828125,
+      "learning_rate": 1.455525606469003e-05,
+      "loss": 1.463841199874878,
+      "step": 82
+    },
+    {
+      "epoch": 0.036245954692556634,
+      "grad_norm": 0.3248669505119324,
+      "learning_rate": 1.4914645103324348e-05,
+      "loss": 1.3554227352142334,
+      "step": 84
+    },
+    {
+      "epoch": 0.037108953613807984,
+      "grad_norm": 0.2855011224746704,
+      "learning_rate": 1.527403414195867e-05,
+      "loss": 1.2810425758361816,
+      "step": 86
+    },
+    {
+      "epoch": 0.03797195253505933,
+      "grad_norm": 0.33365535736083984,
+      "learning_rate": 1.5633423180592992e-05,
+      "loss": 1.428163766860962,
+      "step": 88
+    },
+    {
+      "epoch": 0.038834951456310676,
+      "grad_norm": 0.34099438786506653,
+      "learning_rate": 1.5992812219227316e-05,
+      "loss": 1.3487578630447388,
+      "step": 90
+    },
+    {
+      "epoch": 0.039697950377562026,
+      "grad_norm": 0.39247506856918335,
+      "learning_rate": 1.6352201257861635e-05,
+      "loss": 1.30057954788208,
+      "step": 92
+    },
+    {
+      "epoch": 0.040560949298813376,
+      "grad_norm": 0.32692041993141174,
+      "learning_rate": 1.671159029649596e-05,
+      "loss": 1.2923580408096313,
+      "step": 94
+    },
+    {
+      "epoch": 0.041423948220064725,
+      "grad_norm": 0.43452519178390503,
+      "learning_rate": 1.707097933513028e-05,
+      "loss": 1.5002273321151733,
+      "step": 96
+    },
+    {
+      "epoch": 0.042286947141316075,
+      "grad_norm": 0.3251534402370453,
+      "learning_rate": 1.7430368373764602e-05,
+      "loss": 1.330254077911377,
+      "step": 98
+    },
+    {
+      "epoch": 0.043149946062567425,
+      "grad_norm": 0.3198273479938507,
+      "learning_rate": 1.778975741239892e-05,
+      "loss": 1.3054943084716797,
+      "step": 100
+    },
+    {
+      "epoch": 0.043149946062567425,
+      "eval_loss": 1.366738200187683,
+      "eval_runtime": 651.8198,
+      "eval_samples_per_second": 3.16,
+      "eval_steps_per_second": 3.16,
+      "step": 100
+    },
+    {
+      "epoch": 0.04401294498381877,
+      "grad_norm": 0.37364065647125244,
+      "learning_rate": 1.8149146451033245e-05,
+      "loss": 1.314281940460205,
+      "step": 102
+    },
+    {
+      "epoch": 0.04487594390507012,
+      "grad_norm": 0.39384758472442627,
+      "learning_rate": 1.8508535489667568e-05,
+      "loss": 1.2737246751785278,
+      "step": 104
+    },
+    {
+      "epoch": 0.04573894282632147,
+      "grad_norm": 0.3521905541419983,
+      "learning_rate": 1.8867924528301888e-05,
+      "loss": 1.3113226890563965,
+      "step": 106
+    },
+    {
+      "epoch": 0.04660194174757282,
+      "grad_norm": 0.33531463146209717,
+      "learning_rate": 1.9227313566936208e-05,
+      "loss": 1.3253653049468994,
+      "step": 108
+    },
+    {
+      "epoch": 0.04746494066882417,
+      "grad_norm": 0.35596340894699097,
+      "learning_rate": 1.958670260557053e-05,
+      "loss": 1.3236849308013916,
+      "step": 110
+    },
+    {
+      "epoch": 0.04832793959007551,
+      "grad_norm": 0.36028242111206055,
+      "learning_rate": 1.9946091644204854e-05,
+      "loss": 1.183128833770752,
+      "step": 112
+    },
+    {
+      "epoch": 0.04919093851132686,
+      "grad_norm": 0.42109814286231995,
+      "learning_rate": 2.0305480682839174e-05,
+      "loss": 1.2741888761520386,
+      "step": 114
+    },
+    {
+      "epoch": 0.05005393743257821,
+      "grad_norm": 0.39675939083099365,
+      "learning_rate": 2.0664869721473494e-05,
+      "loss": 1.3050109148025513,
+      "step": 116
+    },
+    {
+      "epoch": 0.05091693635382956,
+      "grad_norm": 0.4414141774177551,
+      "learning_rate": 2.1024258760107817e-05,
+      "loss": 1.2472094297409058,
+      "step": 118
+    },
+    {
+      "epoch": 0.05177993527508091,
+      "grad_norm": 0.42872729897499084,
+      "learning_rate": 2.138364779874214e-05,
+      "loss": 1.3338921070098877,
+      "step": 120
+    },
+    {
+      "epoch": 0.05264293419633225,
+      "grad_norm": 0.38336244225502014,
+      "learning_rate": 2.174303683737646e-05,
+      "loss": 1.322908878326416,
+      "step": 122
+    },
+    {
+      "epoch": 0.0535059331175836,
+      "grad_norm": 0.41046878695487976,
+      "learning_rate": 2.2102425876010783e-05,
+      "loss": 1.2169240713119507,
+      "step": 124
+    },
+    {
+      "epoch": 0.05436893203883495,
+      "grad_norm": 0.39460113644599915,
+      "learning_rate": 2.2461814914645103e-05,
+      "loss": 1.2085309028625488,
+      "step": 126
+    },
+    {
+      "epoch": 0.0552319309600863,
+      "grad_norm": 0.42829909920692444,
+      "learning_rate": 2.2821203953279426e-05,
+      "loss": 1.2969133853912354,
+      "step": 128
+    },
+    {
+      "epoch": 0.05609492988133765,
+      "grad_norm": 0.3940851390361786,
+      "learning_rate": 2.3180592991913746e-05,
+      "loss": 1.1892330646514893,
+      "step": 130
+    },
+    {
+      "epoch": 0.056957928802589,
+      "grad_norm": 0.45011839270591736,
+      "learning_rate": 2.353998203054807e-05,
+      "loss": 1.2082979679107666,
+      "step": 132
+    },
+    {
+      "epoch": 0.05782092772384034,
+      "grad_norm": 0.46059420704841614,
+      "learning_rate": 2.3899371069182393e-05,
+      "loss": 1.2388817071914673,
+      "step": 134
+    },
+    {
+      "epoch": 0.05868392664509169,
+      "grad_norm": 0.41085872054100037,
+      "learning_rate": 2.4258760107816713e-05,
+      "loss": 1.193917155265808,
+      "step": 136
+    },
+    {
+      "epoch": 0.05954692556634304,
+      "grad_norm": 0.4024205207824707,
+      "learning_rate": 2.4618149146451032e-05,
+      "loss": 1.1514034271240234,
+      "step": 138
+    },
+    {
+      "epoch": 0.06040992448759439,
+      "grad_norm": 0.3893793523311615,
+      "learning_rate": 2.4977538185085356e-05,
+      "loss": 1.1626157760620117,
+      "step": 140
+    },
+    {
+      "epoch": 0.06127292340884574,
+      "grad_norm": 0.4456317126750946,
+      "learning_rate": 2.5336927223719675e-05,
+      "loss": 1.1627076864242554,
+      "step": 142
+    },
+    {
+      "epoch": 0.062135922330097085,
+      "grad_norm": 0.5050215125083923,
+      "learning_rate": 2.5696316262354e-05,
+      "loss": 1.3038755655288696,
+      "step": 144
+    },
+    {
+      "epoch": 0.06299892125134844,
+      "grad_norm": 0.4071207642555237,
+      "learning_rate": 2.605570530098832e-05,
+      "loss": 1.1708844900131226,
+      "step": 146
+    },
+    {
+      "epoch": 0.06386192017259978,
+      "grad_norm": 0.4363228678703308,
+      "learning_rate": 2.641509433962264e-05,
+      "loss": 1.2149070501327515,
+      "step": 148
+    },
+    {
+      "epoch": 0.06472491909385113,
+      "grad_norm": 0.4436556398868561,
+      "learning_rate": 2.6774483378256965e-05,
+      "loss": 1.1942368745803833,
+      "step": 150
+    },
+    {
+      "epoch": 0.06558791801510248,
+      "grad_norm": 0.4068629741668701,
+      "learning_rate": 2.7133872416891288e-05,
+      "loss": 1.1799161434173584,
+      "step": 152
+    },
+    {
+      "epoch": 0.06645091693635383,
+      "grad_norm": 0.5291106700897217,
+      "learning_rate": 2.7493261455525608e-05,
+      "loss": 1.1832845211029053,
+      "step": 154
+    },
+    {
+      "epoch": 0.06731391585760518,
+      "grad_norm": 0.4410109221935272,
+      "learning_rate": 2.785265049415993e-05,
+      "loss": 1.1696993112564087,
+      "step": 156
+    },
+    {
+      "epoch": 0.06817691477885653,
+      "grad_norm": 0.4858371913433075,
+      "learning_rate": 2.8212039532794248e-05,
+      "loss": 1.2036973237991333,
+      "step": 158
+    },
+    {
+      "epoch": 0.06903991370010787,
+      "grad_norm": 0.45373693108558655,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 1.1145079135894775,
+      "step": 160
+    },
+    {
+      "epoch": 0.06990291262135923,
+      "grad_norm": 0.4881038963794708,
+      "learning_rate": 2.8930817610062894e-05,
+      "loss": 1.173502802848816,
+      "step": 162
+    },
+    {
+      "epoch": 0.07076591154261057,
+      "grad_norm": 0.576934814453125,
+      "learning_rate": 2.9290206648697217e-05,
+      "loss": 1.250414490699768,
+      "step": 164
+    },
+    {
+      "epoch": 0.07162891046386193,
+      "grad_norm": 0.4900001287460327,
+      "learning_rate": 2.9649595687331537e-05,
+      "loss": 1.0721495151519775,
+      "step": 166
+    },
+    {
+      "epoch": 0.07249190938511327,
+      "grad_norm": 0.4440019726753235,
+      "learning_rate": 3.000898472596586e-05,
+      "loss": 1.0689374208450317,
+      "step": 168
+    },
+    {
+      "epoch": 0.07335490830636461,
+      "grad_norm": 0.4267268180847168,
+      "learning_rate": 3.0368373764600184e-05,
+      "loss": 1.2095128297805786,
+      "step": 170
+    },
+    {
+      "epoch": 0.07421790722761597,
+      "grad_norm": 0.6062787771224976,
+      "learning_rate": 3.0727762803234503e-05,
+      "loss": 1.077776551246643,
+      "step": 172
+    },
+    {
+      "epoch": 0.07508090614886731,
+      "grad_norm": 0.49510180950164795,
+      "learning_rate": 3.108715184186882e-05,
+      "loss": 1.144006371498108,
+      "step": 174
+    },
+    {
+      "epoch": 0.07594390507011867,
+      "grad_norm": 0.4670701026916504,
+      "learning_rate": 3.144654088050314e-05,
+      "loss": 1.1663392782211304,
+      "step": 176
+    },
+    {
+      "epoch": 0.07680690399137001,
+      "grad_norm": 0.5615383386611938,
+      "learning_rate": 3.1805929919137466e-05,
+      "loss": 1.1665973663330078,
+      "step": 178
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "grad_norm": 0.47305551171302795,
+      "learning_rate": 3.216531895777179e-05,
+      "loss": 1.1337063312530518,
+      "step": 180
+    },
+    {
+      "epoch": 0.07853290183387271,
+      "grad_norm": 0.5127068758010864,
+      "learning_rate": 3.252470799640611e-05,
+      "loss": 1.072874903678894,
+      "step": 182
+    },
+    {
+      "epoch": 0.07939590075512405,
+      "grad_norm": 0.632448136806488,
+      "learning_rate": 3.2884097035040436e-05,
+      "loss": 1.1577240228652954,
+      "step": 184
+    },
+    {
+      "epoch": 0.08025889967637541,
+      "grad_norm": 0.4041025638580322,
+      "learning_rate": 3.324348607367476e-05,
+      "loss": 1.1186822652816772,
+      "step": 186
+    },
+    {
+      "epoch": 0.08112189859762675,
+      "grad_norm": 0.5239102244377136,
+      "learning_rate": 3.3602875112309076e-05,
+      "loss": 1.1468429565429688,
+      "step": 188
+    },
+    {
+      "epoch": 0.08198489751887811,
+      "grad_norm": 0.4486575424671173,
+      "learning_rate": 3.39622641509434e-05,
+      "loss": 1.0017019510269165,
+      "step": 190
+    },
+    {
+      "epoch": 0.08284789644012945,
+      "grad_norm": 0.4994317293167114,
+      "learning_rate": 3.4321653189577715e-05,
+      "loss": 1.1901532411575317,
+      "step": 192
+    },
+    {
+      "epoch": 0.0837108953613808,
+      "grad_norm": 0.5023699998855591,
+      "learning_rate": 3.468104222821204e-05,
+      "loss": 1.1398564577102661,
+      "step": 194
+    },
+    {
+      "epoch": 0.08457389428263215,
+      "grad_norm": 0.5077701807022095,
+      "learning_rate": 3.504043126684636e-05,
+      "loss": 1.1390413045883179,
+      "step": 196
+    },
+    {
+      "epoch": 0.0854368932038835,
+      "grad_norm": 0.5527892112731934,
+      "learning_rate": 3.5399820305480685e-05,
+      "loss": 1.1411432027816772,
+      "step": 198
+    },
+    {
+      "epoch": 0.08629989212513485,
+      "grad_norm": 0.5572488903999329,
+      "learning_rate": 3.575920934411501e-05,
+      "loss": 1.071260690689087,
+      "step": 200
+    },
+    {
+      "epoch": 0.08629989212513485,
+      "eval_loss": 1.1519012451171875,
+      "eval_runtime": 654.6055,
+      "eval_samples_per_second": 3.147,
+      "eval_steps_per_second": 3.147,
+      "step": 200
+    },
+    {
+      "epoch": 0.08716289104638619,
+      "grad_norm": 0.5134095549583435,
+      "learning_rate": 3.611859838274933e-05,
+      "loss": 1.138135552406311,
+      "step": 202
+    },
+    {
+      "epoch": 0.08802588996763754,
+      "grad_norm": 0.5166040658950806,
+      "learning_rate": 3.647798742138365e-05,
+      "loss": 1.111999273300171,
+      "step": 204
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.5336993336677551,
+      "learning_rate": 3.683737646001797e-05,
+      "loss": 1.1031352281570435,
+      "step": 206
+    },
+    {
+      "epoch": 0.08975188781014024,
+      "grad_norm": 0.8289600014686584,
+      "learning_rate": 3.7196765498652294e-05,
+      "loss": 1.0388667583465576,
+      "step": 208
+    },
+    {
+      "epoch": 0.09061488673139159,
+      "grad_norm": 0.47992637753486633,
+      "learning_rate": 3.755615453728661e-05,
+      "loss": 1.0950241088867188,
+      "step": 210
+    },
+    {
+      "epoch": 0.09147788565264293,
+      "grad_norm": 0.5629691481590271,
+      "learning_rate": 3.7915543575920934e-05,
+      "loss": 1.0361733436584473,
+      "step": 212
+    },
+    {
+      "epoch": 0.09234088457389428,
+      "grad_norm": 0.5515111684799194,
+      "learning_rate": 3.827493261455526e-05,
+      "loss": 1.0922447443008423,
+      "step": 214
+    },
+    {
+      "epoch": 0.09320388349514563,
+      "grad_norm": 0.5078643560409546,
+      "learning_rate": 3.863432165318958e-05,
+      "loss": 1.0866856575012207,
+      "step": 216
+    },
+    {
+      "epoch": 0.09406688241639698,
+      "grad_norm": 0.6046127676963806,
+      "learning_rate": 3.8993710691823904e-05,
+      "loss": 1.1231595277786255,
+      "step": 218
+    },
+    {
+      "epoch": 0.09492988133764833,
+      "grad_norm": 0.6255762577056885,
+      "learning_rate": 3.935309973045822e-05,
+      "loss": 1.099171757698059,
+      "step": 220
+    },
+    {
+      "epoch": 0.09579288025889968,
+      "grad_norm": 0.6036638021469116,
+      "learning_rate": 3.971248876909254e-05,
+      "loss": 1.0557761192321777,
+      "step": 222
+    },
+    {
+      "epoch": 0.09665587918015102,
+      "grad_norm": 0.5520529747009277,
+      "learning_rate": 4.0071877807726867e-05,
+      "loss": 1.0467877388000488,
+      "step": 224
+    },
+    {
+      "epoch": 0.09751887810140238,
+      "grad_norm": 0.5958684682846069,
+      "learning_rate": 4.043126684636119e-05,
+      "loss": 1.17941153049469,
+      "step": 226
+    },
+    {
+      "epoch": 0.09838187702265372,
+      "grad_norm": 0.5283281803131104,
+      "learning_rate": 4.079065588499551e-05,
+      "loss": 1.104217767715454,
+      "step": 228
+    },
+    {
+      "epoch": 0.09924487594390508,
+      "grad_norm": 0.5608792901039124,
+      "learning_rate": 4.115004492362983e-05,
+      "loss": 1.0900640487670898,
+      "step": 230
+    },
+    {
+      "epoch": 0.10010787486515642,
+      "grad_norm": 0.555964469909668,
+      "learning_rate": 4.150943396226415e-05,
+      "loss": 0.9887422323226929,
+      "step": 232
+    },
+    {
+      "epoch": 0.10097087378640776,
+      "grad_norm": 0.5875785946846008,
+      "learning_rate": 4.1868823000898476e-05,
+      "loss": 1.1298567056655884,
+      "step": 234
+    },
+    {
+      "epoch": 0.10183387270765912,
+      "grad_norm": 0.4544795751571655,
+      "learning_rate": 4.222821203953279e-05,
+      "loss": 1.0957067012786865,
+      "step": 236
+    },
+    {
+      "epoch": 0.10269687162891046,
+      "grad_norm": 0.564145565032959,
+      "learning_rate": 4.2587601078167116e-05,
+      "loss": 1.0328738689422607,
+      "step": 238
+    },
+    {
+      "epoch": 0.10355987055016182,
+      "grad_norm": 0.6285979747772217,
+      "learning_rate": 4.294699011680144e-05,
+      "loss": 1.1085515022277832,
+      "step": 240
+    },
+    {
+      "epoch": 0.10442286947141316,
+      "grad_norm": 0.6442288756370544,
+      "learning_rate": 4.330637915543576e-05,
+      "loss": 1.1291271448135376,
+      "step": 242
+    },
+    {
+      "epoch": 0.1052858683926645,
+      "grad_norm": 0.6137154698371887,
+      "learning_rate": 4.3665768194070085e-05,
+      "loss": 1.1759567260742188,
+      "step": 244
+    },
+    {
+      "epoch": 0.10614886731391586,
+      "grad_norm": 0.5906805992126465,
+      "learning_rate": 4.402515723270441e-05,
+      "loss": 1.148414969444275,
+      "step": 246
+    },
+    {
+      "epoch": 0.1070118662351672,
+      "grad_norm": 0.5382888913154602,
+      "learning_rate": 4.438454627133873e-05,
+      "loss": 1.0749616622924805,
+      "step": 248
+    },
+    {
+      "epoch": 0.10787486515641856,
+      "grad_norm": 0.6185492873191833,
+      "learning_rate": 4.474393530997305e-05,
+      "loss": 1.2235801219940186,
+      "step": 250
+    },
+    {
+      "epoch": 0.1087378640776699,
+      "grad_norm": 0.5981597900390625,
+      "learning_rate": 4.5103324348607365e-05,
+      "loss": 1.1390639543533325,
+      "step": 252
+    },
+    {
+      "epoch": 0.10960086299892124,
+      "grad_norm": 0.5664694905281067,
+      "learning_rate": 4.546271338724169e-05,
+      "loss": 1.171774983406067,
+      "step": 254
+    },
+    {
+      "epoch": 0.1104638619201726,
+      "grad_norm": 0.7071851491928101,
+      "learning_rate": 4.582210242587601e-05,
+      "loss": 1.1704237461090088,
+      "step": 256
+    },
+    {
+      "epoch": 0.11132686084142394,
+      "grad_norm": 0.5815614461898804,
+      "learning_rate": 4.6181491464510334e-05,
+      "loss": 1.0619677305221558,
+      "step": 258
+    },
+    {
+      "epoch": 0.1121898597626753,
+      "grad_norm": 0.6481915712356567,
+      "learning_rate": 4.654088050314466e-05,
+      "loss": 1.0824390649795532,
+      "step": 260
+    },
+    {
+      "epoch": 0.11305285868392664,
+      "grad_norm": 0.5988591313362122,
+      "learning_rate": 4.690026954177898e-05,
+      "loss": 1.087929606437683,
+      "step": 262
+    },
+    {
+      "epoch": 0.113915857605178,
+      "grad_norm": 0.6545296311378479,
+      "learning_rate": 4.7259658580413304e-05,
+      "loss": 1.0936195850372314,
+      "step": 264
+    },
+    {
+      "epoch": 0.11477885652642934,
+      "grad_norm": 0.5826204419136047,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 1.0433681011199951,
+      "step": 266
+    },
+    {
+      "epoch": 0.11564185544768069,
+      "grad_norm": 0.5907514095306396,
+      "learning_rate": 4.7978436657681944e-05,
+      "loss": 1.0719536542892456,
+      "step": 268
+    },
+    {
+      "epoch": 0.11650485436893204,
+      "grad_norm": 0.524394154548645,
+      "learning_rate": 4.833782569631627e-05,
+      "loss": 1.0231504440307617,
+      "step": 270
+    },
+    {
+      "epoch": 0.11736785329018339,
+      "grad_norm": 0.5472846031188965,
+      "learning_rate": 4.869721473495058e-05,
+      "loss": 0.9905915260314941,
+      "step": 272
+    },
+    {
+      "epoch": 0.11823085221143474,
+      "grad_norm": 0.727922260761261,
+      "learning_rate": 4.9056603773584906e-05,
+      "loss": 1.213677167892456,
+      "step": 274
+    },
+    {
+      "epoch": 0.11909385113268608,
+      "grad_norm": 0.6009684801101685,
+      "learning_rate": 4.941599281221923e-05,
+      "loss": 1.0052144527435303,
+      "step": 276
+    },
+    {
+      "epoch": 0.11995685005393743,
+      "grad_norm": 0.6564669013023376,
+      "learning_rate": 4.977538185085355e-05,
+      "loss": 1.108136773109436,
+      "step": 278
+    },
+    {
+      "epoch": 0.12081984897518878,
+      "grad_norm": 0.650074303150177,
+      "learning_rate": 5.013477088948787e-05,
+      "loss": 0.9700815677642822,
+      "step": 280
+    },
+    {
+      "epoch": 0.12168284789644013,
+      "grad_norm": 0.5772947072982788,
+      "learning_rate": 5.04941599281222e-05,
+      "loss": 1.038031816482544,
+      "step": 282
+    },
+    {
+      "epoch": 0.12254584681769148,
+      "grad_norm": 0.7293002009391785,
+      "learning_rate": 5.0853548966756516e-05,
+      "loss": 1.1063730716705322,
+      "step": 284
+    },
+    {
+      "epoch": 0.12340884573894283,
+      "grad_norm": 0.7937333583831787,
+      "learning_rate": 5.1212938005390846e-05,
+      "loss": 1.128495693206787,
+      "step": 286
+    },
+    {
+      "epoch": 0.12427184466019417,
+      "grad_norm": 0.48499324917793274,
+      "learning_rate": 5.157232704402516e-05,
+      "loss": 0.9438712000846863,
+      "step": 288
+    },
+    {
+      "epoch": 0.12513484358144553,
+      "grad_norm": 0.6010656952857971,
+      "learning_rate": 5.193171608265948e-05,
+      "loss": 1.0872881412506104,
+      "step": 290
+    },
+    {
+      "epoch": 0.12599784250269688,
+      "grad_norm": 0.6240811944007874,
+      "learning_rate": 5.22911051212938e-05,
+      "loss": 1.110992193222046,
+      "step": 292
+    },
+    {
+      "epoch": 0.1268608414239482,
+      "grad_norm": 0.7172768712043762,
+      "learning_rate": 5.265049415992812e-05,
+      "loss": 1.1109752655029297,
+      "step": 294
+    },
+    {
+      "epoch": 0.12772384034519957,
+      "grad_norm": 0.6442400217056274,
+      "learning_rate": 5.300988319856245e-05,
+      "loss": 1.05553138256073,
+      "step": 296
+    },
+    {
+      "epoch": 0.12858683926645093,
+      "grad_norm": 0.7074702382087708,
+      "learning_rate": 5.3369272237196765e-05,
+      "loss": 1.0717648267745972,
+      "step": 298
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "grad_norm": 0.5277591347694397,
+      "learning_rate": 5.3728661275831095e-05,
+      "loss": 0.9777541756629944,
+      "step": 300
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "eval_loss": 1.0977506637573242,
+      "eval_runtime": 662.1728,
+      "eval_samples_per_second": 3.111,
+      "eval_steps_per_second": 3.111,
+      "step": 300
+    },
+    {
+      "epoch": 0.1303128371089536,
+      "grad_norm": 0.7252246737480164,
+      "learning_rate": 5.408805031446541e-05,
+      "loss": 1.075905203819275,
+      "step": 302
+    },
+    {
+      "epoch": 0.13117583603020497,
+      "grad_norm": 0.7003294229507446,
+      "learning_rate": 5.444743935309974e-05,
+      "loss": 1.1117515563964844,
+      "step": 304
+    },
+    {
+      "epoch": 0.13203883495145632,
+      "grad_norm": 0.5878211259841919,
+      "learning_rate": 5.480682839173406e-05,
+      "loss": 1.0289191007614136,
+      "step": 306
+    },
+    {
+      "epoch": 0.13290183387270765,
+      "grad_norm": 0.7133644223213196,
+      "learning_rate": 5.5166217430368374e-05,
+      "loss": 1.0199183225631714,
+      "step": 308
+    },
+    {
+      "epoch": 0.133764832793959,
+      "grad_norm": 0.6098423600196838,
+      "learning_rate": 5.55256064690027e-05,
+      "loss": 1.0132375955581665,
+      "step": 310
+    },
+    {
+      "epoch": 0.13462783171521037,
+      "grad_norm": 0.6386916041374207,
+      "learning_rate": 5.5884995507637014e-05,
+      "loss": 1.1595754623413086,
+      "step": 312
+    },
+    {
+      "epoch": 0.1354908306364617,
+      "grad_norm": 0.6563469767570496,
+      "learning_rate": 5.6244384546271344e-05,
+      "loss": 1.0921307802200317,
+      "step": 314
+    },
+    {
+      "epoch": 0.13635382955771305,
+      "grad_norm": 0.6388015747070312,
+      "learning_rate": 5.660377358490566e-05,
+      "loss": 1.0200815200805664,
+      "step": 316
+    },
+    {
+      "epoch": 0.1372168284789644,
+      "grad_norm": 0.6026274561882019,
+      "learning_rate": 5.696316262353999e-05,
+      "loss": 0.9339485764503479,
+      "step": 318
+    },
+    {
+      "epoch": 0.13807982740021574,
+      "grad_norm": 0.619800865650177,
+      "learning_rate": 5.732255166217431e-05,
+      "loss": 1.0268478393554688,
+      "step": 320
+    },
+    {
+      "epoch": 0.1389428263214671,
+      "grad_norm": 0.5924715399742126,
+      "learning_rate": 5.768194070080862e-05,
+      "loss": 1.1394236087799072,
+      "step": 322
+    },
+    {
+      "epoch": 0.13980582524271845,
+      "grad_norm": 0.6829012036323547,
+      "learning_rate": 5.804132973944295e-05,
+      "loss": 1.002437949180603,
+      "step": 324
+    },
+    {
+      "epoch": 0.1406688241639698,
+      "grad_norm": 0.7012544274330139,
+      "learning_rate": 5.840071877807727e-05,
+      "loss": 1.132503628730774,
+      "step": 326
+    },
+    {
+      "epoch": 0.14153182308522114,
+      "grad_norm": 0.7921599745750427,
+      "learning_rate": 5.876010781671159e-05,
+      "loss": 1.1859129667282104,
+      "step": 328
+    },
+    {
+      "epoch": 0.1423948220064725,
+      "grad_norm": 0.6373353004455566,
+      "learning_rate": 5.9119496855345916e-05,
+      "loss": 1.0896776914596558,
+      "step": 330
+    },
+    {
+      "epoch": 0.14325782092772385,
+      "grad_norm": 0.6174030900001526,
+      "learning_rate": 5.947888589398024e-05,
+      "loss": 1.0691723823547363,
+      "step": 332
+    },
+    {
+      "epoch": 0.14412081984897518,
+      "grad_norm": 0.5110617280006409,
+      "learning_rate": 5.9838274932614556e-05,
+      "loss": 1.0144777297973633,
+      "step": 334
+    },
+    {
+      "epoch": 0.14498381877022654,
+      "grad_norm": 0.5580511093139648,
+      "learning_rate": 6.019766397124887e-05,
+      "loss": 0.9955101609230042,
+      "step": 336
+    },
+    {
+      "epoch": 0.1458468176914779,
+      "grad_norm": 0.6427345275878906,
+      "learning_rate": 6.05570530098832e-05,
+      "loss": 0.9863013625144958,
+      "step": 338
+    },
+    {
+      "epoch": 0.14670981661272922,
+      "grad_norm": 0.7464537024497986,
+      "learning_rate": 6.091644204851752e-05,
+      "loss": 1.0682255029678345,
+      "step": 340
+    },
+    {
+      "epoch": 0.14757281553398058,
+      "grad_norm": 0.599926769733429,
+      "learning_rate": 6.127583108715184e-05,
+      "loss": 1.034083366394043,
+      "step": 342
+    },
+    {
+      "epoch": 0.14843581445523193,
+      "grad_norm": 0.6320257186889648,
+      "learning_rate": 6.163522012578616e-05,
+      "loss": 1.0776089429855347,
+      "step": 344
+    },
+    {
+      "epoch": 0.1492988133764833,
+      "grad_norm": 0.6565091013908386,
+      "learning_rate": 6.199460916442049e-05,
+      "loss": 1.0493087768554688,
+      "step": 346
+    },
+    {
+      "epoch": 0.15016181229773462,
+      "grad_norm": 0.6512171626091003,
+      "learning_rate": 6.23539982030548e-05,
+      "loss": 1.0469218492507935,
+      "step": 348
+    },
+    {
+      "epoch": 0.15102481121898598,
+      "grad_norm": 0.8487282991409302,
+      "learning_rate": 6.271338724168913e-05,
+      "loss": 1.0985081195831299,
+      "step": 350
+    },
+    {
+      "epoch": 0.15188781014023733,
+      "grad_norm": 0.6718961596488953,
+      "learning_rate": 6.307277628032345e-05,
+      "loss": 1.0714176893234253,
+      "step": 352
+    },
+    {
+      "epoch": 0.15275080906148866,
+      "grad_norm": 0.8175088167190552,
+      "learning_rate": 6.343216531895777e-05,
+      "loss": 1.0599322319030762,
+      "step": 354
+    },
+    {
+      "epoch": 0.15361380798274002,
+      "grad_norm": 0.6359215378761292,
+      "learning_rate": 6.37915543575921e-05,
+      "loss": 0.9268131256103516,
+      "step": 356
+    },
+    {
+      "epoch": 0.15447680690399138,
+      "grad_norm": 0.6423866748809814,
+      "learning_rate": 6.415094339622641e-05,
+      "loss": 0.9838354587554932,
+      "step": 358
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "grad_norm": 0.6496716737747192,
+      "learning_rate": 6.451033243486074e-05,
+      "loss": 1.048566460609436,
+      "step": 360
+    },
+    {
+      "epoch": 0.15620280474649406,
+      "grad_norm": 0.6536920666694641,
+      "learning_rate": 6.486972147349506e-05,
+      "loss": 1.0910537242889404,
+      "step": 362
+    },
+    {
+      "epoch": 0.15706580366774542,
+      "grad_norm": 0.5832068920135498,
+      "learning_rate": 6.522911051212939e-05,
+      "loss": 0.9971448183059692,
+      "step": 364
+    },
+    {
+      "epoch": 0.15792880258899678,
+      "grad_norm": 0.6647719144821167,
+      "learning_rate": 6.558849955076371e-05,
+      "loss": 1.0496708154678345,
+      "step": 366
+    },
+    {
+      "epoch": 0.1587918015102481,
+      "grad_norm": 0.623252809047699,
+      "learning_rate": 6.594788858939802e-05,
+      "loss": 0.955894410610199,
+      "step": 368
+    },
+    {
+      "epoch": 0.15965480043149946,
+      "grad_norm": 0.6311860084533691,
+      "learning_rate": 6.630727762803235e-05,
+      "loss": 1.1304032802581787,
+      "step": 370
+    },
+    {
+      "epoch": 0.16051779935275082,
+      "grad_norm": 0.5306481122970581,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.8746405243873596,
+      "step": 372
+    },
+    {
+      "epoch": 0.16138079827400215,
+      "grad_norm": 0.6249631643295288,
+      "learning_rate": 6.7026055705301e-05,
+      "loss": 0.9104986786842346,
+      "step": 374
+    },
+    {
+      "epoch": 0.1622437971952535,
+      "grad_norm": 0.6243219971656799,
+      "learning_rate": 6.738544474393532e-05,
+      "loss": 1.043666124343872,
+      "step": 376
+    },
+    {
+      "epoch": 0.16310679611650486,
+      "grad_norm": 0.6833282113075256,
+      "learning_rate": 6.774483378256963e-05,
+      "loss": 1.0504906177520752,
+      "step": 378
+    },
+    {
+      "epoch": 0.16396979503775622,
+      "grad_norm": 0.7124452590942383,
+      "learning_rate": 6.810422282120395e-05,
+      "loss": 1.0608166456222534,
+      "step": 380
+    },
+    {
+      "epoch": 0.16483279395900755,
+      "grad_norm": 0.7520908117294312,
+      "learning_rate": 6.846361185983828e-05,
+      "loss": 1.1653732061386108,
+      "step": 382
+    },
+    {
+      "epoch": 0.1656957928802589,
+      "grad_norm": 0.7121814489364624,
+      "learning_rate": 6.88230008984726e-05,
+      "loss": 1.0626367330551147,
+      "step": 384
+    },
+    {
+      "epoch": 0.16655879180151026,
+      "grad_norm": 0.6825008988380432,
+      "learning_rate": 6.918238993710691e-05,
+      "loss": 1.012121319770813,
+      "step": 386
+    },
+    {
+      "epoch": 0.1674217907227616,
+      "grad_norm": 0.4922940135002136,
+      "learning_rate": 6.954177897574124e-05,
+      "loss": 1.0576211214065552,
+      "step": 388
+    },
+    {
+      "epoch": 0.16828478964401294,
+      "grad_norm": 0.6122089624404907,
+      "learning_rate": 6.990116801437556e-05,
+      "loss": 1.03916597366333,
+      "step": 390
+    },
+    {
+      "epoch": 0.1691477885652643,
+      "grad_norm": 0.6348981261253357,
+      "learning_rate": 7.026055705300989e-05,
+      "loss": 1.17647123336792,
+      "step": 392
+    },
+    {
+      "epoch": 0.17001078748651563,
+      "grad_norm": 0.6205878257751465,
+      "learning_rate": 7.06199460916442e-05,
+      "loss": 0.9095983505249023,
+      "step": 394
+    },
+    {
+      "epoch": 0.170873786407767,
+      "grad_norm": 0.61506187915802,
+      "learning_rate": 7.097933513027853e-05,
+      "loss": 1.082506775856018,
+      "step": 396
+    },
+    {
+      "epoch": 0.17173678532901834,
+      "grad_norm": 0.6481751799583435,
+      "learning_rate": 7.133872416891285e-05,
+      "loss": 1.0716280937194824,
+      "step": 398
+    },
+    {
+      "epoch": 0.1725997842502697,
+      "grad_norm": 0.4871014952659607,
+      "learning_rate": 7.169811320754717e-05,
+      "loss": 0.9616814851760864,
+      "step": 400
+    },
+    {
+      "epoch": 0.1725997842502697,
+      "eval_loss": 1.0649415254592896,
+      "eval_runtime": 668.6025,
+      "eval_samples_per_second": 3.081,
+      "eval_steps_per_second": 3.081,
+      "step": 400
+    },
+    {
+      "epoch": 0.17346278317152103,
+      "grad_norm": 0.5680040121078491,
+      "learning_rate": 7.20575022461815e-05,
+      "loss": 1.0475050210952759,
+      "step": 402
+    },
+    {
+      "epoch": 0.17432578209277239,
+      "grad_norm": 0.6417813897132874,
+      "learning_rate": 7.241689128481581e-05,
+      "loss": 0.9851161241531372,
+      "step": 404
+    },
+    {
+      "epoch": 0.17518878101402374,
+      "grad_norm": 0.6600468158721924,
+      "learning_rate": 7.277628032345014e-05,
+      "loss": 1.013339638710022,
+      "step": 406
+    },
+    {
+      "epoch": 0.17605177993527507,
+      "grad_norm": 0.6733932495117188,
+      "learning_rate": 7.313566936208446e-05,
+      "loss": 0.9346804022789001,
+      "step": 408
+    },
+    {
+      "epoch": 0.17691477885652643,
+      "grad_norm": 0.6812151074409485,
+      "learning_rate": 7.349505840071879e-05,
+      "loss": 0.9890368580818176,
+      "step": 410
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.6380394697189331,
+      "learning_rate": 7.385444743935311e-05,
+      "loss": 0.8787848949432373,
+      "step": 412
+    },
+    {
+      "epoch": 0.1786407766990291,
+      "grad_norm": 0.6004905700683594,
+      "learning_rate": 7.421383647798742e-05,
+      "loss": 1.0235728025436401,
+      "step": 414
+    },
+    {
+      "epoch": 0.17950377562028047,
+      "grad_norm": 0.6569193005561829,
+      "learning_rate": 7.457322551662175e-05,
+      "loss": 0.9972385168075562,
+      "step": 416
+    },
+    {
+      "epoch": 0.18036677454153183,
+      "grad_norm": 0.6761631369590759,
+      "learning_rate": 7.493261455525607e-05,
+      "loss": 0.9593698382377625,
+      "step": 418
+    },
+    {
+      "epoch": 0.18122977346278318,
+      "grad_norm": 0.7328561544418335,
+      "learning_rate": 7.529200359389039e-05,
+      "loss": 1.0426853895187378,
+      "step": 420
+    },
+    {
+      "epoch": 0.1820927723840345,
+      "grad_norm": 0.6256070137023926,
+      "learning_rate": 7.56513926325247e-05,
+      "loss": 0.9608182311058044,
+      "step": 422
+    },
+    {
+      "epoch": 0.18295577130528587,
+      "grad_norm": 1.2549844980239868,
+      "learning_rate": 7.601078167115903e-05,
+      "loss": 1.0162668228149414,
+      "step": 424
+    },
+    {
+      "epoch": 0.18381877022653723,
+      "grad_norm": 0.6751510500907898,
+      "learning_rate": 7.637017070979335e-05,
+      "loss": 1.130725383758545,
+      "step": 426
+    },
+    {
+      "epoch": 0.18468176914778855,
+      "grad_norm": 0.7029808163642883,
+      "learning_rate": 7.672955974842768e-05,
+      "loss": 1.0384817123413086,
+      "step": 428
+    },
+    {
+      "epoch": 0.1855447680690399,
+      "grad_norm": 0.644353449344635,
+      "learning_rate": 7.7088948787062e-05,
+      "loss": 1.017020344734192,
+      "step": 430
+    },
+    {
+      "epoch": 0.18640776699029127,
+      "grad_norm": 0.6784916520118713,
+      "learning_rate": 7.744833782569631e-05,
+      "loss": 1.005354404449463,
+      "step": 432
+    },
+    {
+      "epoch": 0.1872707659115426,
+      "grad_norm": 0.5989449620246887,
+      "learning_rate": 7.780772686433064e-05,
+      "loss": 1.026848316192627,
+      "step": 434
+    },
+    {
+      "epoch": 0.18813376483279395,
+      "grad_norm": 0.6502639651298523,
+      "learning_rate": 7.816711590296496e-05,
+      "loss": 0.9891080856323242,
+      "step": 436
+    },
+    {
+      "epoch": 0.1889967637540453,
+      "grad_norm": 0.6176205277442932,
+      "learning_rate": 7.852650494159929e-05,
+      "loss": 0.966316819190979,
+      "step": 438
+    },
+    {
+      "epoch": 0.18985976267529667,
+      "grad_norm": 0.6801626086235046,
+      "learning_rate": 7.88858939802336e-05,
+      "loss": 1.123063087463379,
+      "step": 440
+    },
+    {
+      "epoch": 0.190722761596548,
+      "grad_norm": 0.6718618273735046,
+      "learning_rate": 7.924528301886794e-05,
+      "loss": 1.0467073917388916,
+      "step": 442
+    },
+    {
+      "epoch": 0.19158576051779935,
+      "grad_norm": 0.6761009097099304,
+      "learning_rate": 7.960467205750225e-05,
+      "loss": 1.0952889919281006,
+      "step": 444
+    },
+    {
+      "epoch": 0.1924487594390507,
+      "grad_norm": 0.6356327533721924,
+      "learning_rate": 7.996406109613657e-05,
+      "loss": 0.954807698726654,
+      "step": 446
+    },
+    {
+      "epoch": 0.19331175836030204,
+      "grad_norm": 0.6798669695854187,
+      "learning_rate": 8.03234501347709e-05,
+      "loss": 0.9941422343254089,
+      "step": 448
+    },
+    {
+      "epoch": 0.1941747572815534,
+      "grad_norm": 0.6511302590370178,
+      "learning_rate": 8.068283917340521e-05,
+      "loss": 1.0351495742797852,
+      "step": 450
+    },
+    {
+      "epoch": 0.19503775620280475,
+      "grad_norm": 0.6061258912086487,
+      "learning_rate": 8.104222821203954e-05,
+      "loss": 1.00546133518219,
+      "step": 452
+    },
+    {
+      "epoch": 0.1959007551240561,
+      "grad_norm": 0.6278533935546875,
+      "learning_rate": 8.140161725067386e-05,
+      "loss": 1.0778460502624512,
+      "step": 454
+    },
+    {
+      "epoch": 0.19676375404530744,
+      "grad_norm": 0.6866298317909241,
+      "learning_rate": 8.176100628930818e-05,
+      "loss": 1.0344486236572266,
+      "step": 456
+    },
+    {
+      "epoch": 0.1976267529665588,
+      "grad_norm": 0.7338075041770935,
+      "learning_rate": 8.212039532794251e-05,
+      "loss": 1.0663033723831177,
+      "step": 458
+    },
+    {
+      "epoch": 0.19848975188781015,
+      "grad_norm": 0.6811459064483643,
+      "learning_rate": 8.247978436657682e-05,
+      "loss": 0.9665339589118958,
+      "step": 460
+    },
+    {
+      "epoch": 0.19935275080906148,
+      "grad_norm": 0.6779627799987793,
+      "learning_rate": 8.283917340521114e-05,
+      "loss": 1.024712324142456,
+      "step": 462
+    },
+    {
+      "epoch": 0.20021574973031284,
+      "grad_norm": 0.6486892700195312,
+      "learning_rate": 8.319856244384546e-05,
+      "loss": 0.9699305295944214,
+      "step": 464
+    },
+    {
+      "epoch": 0.2010787486515642,
+      "grad_norm": 0.7022278308868408,
+      "learning_rate": 8.355795148247979e-05,
+      "loss": 0.9540432095527649,
+      "step": 466
+    },
+    {
+      "epoch": 0.20194174757281552,
+      "grad_norm": 0.5922990441322327,
+      "learning_rate": 8.39173405211141e-05,
+      "loss": 0.9253339767456055,
+      "step": 468
+    },
+    {
+      "epoch": 0.20280474649406688,
+      "grad_norm": 0.7076792120933533,
+      "learning_rate": 8.427672955974843e-05,
+      "loss": 0.9987741112709045,
+      "step": 470
+    },
+    {
+      "epoch": 0.20366774541531824,
+      "grad_norm": 0.6491380333900452,
+      "learning_rate": 8.463611859838275e-05,
+      "loss": 1.0249329805374146,
+      "step": 472
+    },
+    {
+      "epoch": 0.2045307443365696,
+      "grad_norm": 0.6784211993217468,
+      "learning_rate": 8.499550763701708e-05,
+      "loss": 1.0577133893966675,
+      "step": 474
+    },
+    {
+      "epoch": 0.20539374325782092,
+      "grad_norm": 0.6453303694725037,
+      "learning_rate": 8.53548966756514e-05,
+      "loss": 1.1312458515167236,
+      "step": 476
+    },
+    {
+      "epoch": 0.20625674217907228,
+      "grad_norm": 0.7431377172470093,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 1.0592451095581055,
+      "step": 478
+    },
+    {
+      "epoch": 0.20711974110032363,
+      "grad_norm": 0.6097649931907654,
+      "learning_rate": 8.607367475292004e-05,
+      "loss": 0.9337235689163208,
+      "step": 480
+    },
+    {
+      "epoch": 0.20798274002157496,
+      "grad_norm": 0.5693124532699585,
+      "learning_rate": 8.643306379155436e-05,
+      "loss": 0.9088928699493408,
+      "step": 482
+    },
+    {
+      "epoch": 0.20884573894282632,
+      "grad_norm": 0.7377229332923889,
+      "learning_rate": 8.679245283018869e-05,
+      "loss": 1.0729358196258545,
+      "step": 484
+    },
+    {
+      "epoch": 0.20970873786407768,
+      "grad_norm": 0.7399470210075378,
+      "learning_rate": 8.7151841868823e-05,
+      "loss": 1.0428457260131836,
+      "step": 486
+    },
+    {
+      "epoch": 0.210571736785329,
+      "grad_norm": 0.677052915096283,
+      "learning_rate": 8.751123090745734e-05,
+      "loss": 0.9940266013145447,
+      "step": 488
+    },
+    {
+      "epoch": 0.21143473570658036,
+      "grad_norm": 0.7126721739768982,
+      "learning_rate": 8.787061994609165e-05,
+      "loss": 1.011808156967163,
+      "step": 490
+    },
+    {
+      "epoch": 0.21229773462783172,
+      "grad_norm": 0.6663792729377747,
+      "learning_rate": 8.823000898472597e-05,
+      "loss": 1.0054185390472412,
+      "step": 492
+    },
+    {
+      "epoch": 0.21316073354908308,
+      "grad_norm": 0.6661092042922974,
+      "learning_rate": 8.85893980233603e-05,
+      "loss": 1.0167138576507568,
+      "step": 494
+    },
+    {
+      "epoch": 0.2140237324703344,
+      "grad_norm": 0.6975740194320679,
+      "learning_rate": 8.894878706199461e-05,
+      "loss": 1.1470818519592285,
+      "step": 496
+    },
+    {
+      "epoch": 0.21488673139158576,
+      "grad_norm": 0.6594390869140625,
+      "learning_rate": 8.930817610062893e-05,
+      "loss": 0.9619631171226501,
+      "step": 498
+    },
+    {
+      "epoch": 0.21574973031283712,
+      "grad_norm": 0.7216679453849792,
+      "learning_rate": 8.966756513926325e-05,
+      "loss": 0.9971368312835693,
+      "step": 500
+    },
+    {
+      "epoch": 0.21574973031283712,
+      "eval_loss": 1.0417571067810059,
+      "eval_runtime": 659.3112,
+      "eval_samples_per_second": 3.124,
+      "eval_steps_per_second": 3.124,
+      "step": 500
+    },
+    {
+      "epoch": 0.21661272923408845,
+      "grad_norm": 0.6188210844993591,
+      "learning_rate": 9.002695417789758e-05,
+      "loss": 1.0307213068008423,
+      "step": 502
+    },
+    {
+      "epoch": 0.2174757281553398,
+      "grad_norm": 0.6716445088386536,
+      "learning_rate": 9.03863432165319e-05,
+      "loss": 1.0188794136047363,
+      "step": 504
+    },
+    {
+      "epoch": 0.21833872707659116,
+      "grad_norm": 0.6790863275527954,
+      "learning_rate": 9.074573225516622e-05,
+      "loss": 0.9764845967292786,
+      "step": 506
+    },
+    {
+      "epoch": 0.2192017259978425,
+      "grad_norm": 0.6764960289001465,
+      "learning_rate": 9.110512129380054e-05,
+      "loss": 0.948829174041748,
+      "step": 508
+    },
+    {
+      "epoch": 0.22006472491909385,
+      "grad_norm": 0.6210965514183044,
+      "learning_rate": 9.146451033243486e-05,
+      "loss": 1.008013129234314,
+      "step": 510
+    },
+    {
+      "epoch": 0.2209277238403452,
+      "grad_norm": 0.7739297747612,
+      "learning_rate": 9.182389937106919e-05,
+      "loss": 1.1662557125091553,
+      "step": 512
+    },
+    {
+      "epoch": 0.22179072276159656,
+      "grad_norm": 0.7055562138557434,
+      "learning_rate": 9.21832884097035e-05,
+      "loss": 1.0325161218643188,
+      "step": 514
+    },
+    {
+      "epoch": 0.2226537216828479,
+      "grad_norm": 0.6079210042953491,
+      "learning_rate": 9.254267744833783e-05,
+      "loss": 1.00056791305542,
+      "step": 516
+    },
+    {
+      "epoch": 0.22351672060409924,
+      "grad_norm": 0.5974318981170654,
+      "learning_rate": 9.290206648697215e-05,
+      "loss": 0.9422364234924316,
+      "step": 518
+    },
+    {
+      "epoch": 0.2243797195253506,
+      "grad_norm": 0.5963430404663086,
+      "learning_rate": 9.326145552560648e-05,
+      "loss": 0.936336100101471,
+      "step": 520
+    },
+    {
+      "epoch": 0.22524271844660193,
+      "grad_norm": 0.6823658347129822,
+      "learning_rate": 9.36208445642408e-05,
+      "loss": 1.0538607835769653,
+      "step": 522
+    },
+    {
+      "epoch": 0.2261057173678533,
+      "grad_norm": 0.6409855484962463,
+      "learning_rate": 9.398023360287511e-05,
+      "loss": 1.0483653545379639,
+      "step": 524
+    },
+    {
+      "epoch": 0.22696871628910464,
+      "grad_norm": 0.6867254376411438,
+      "learning_rate": 9.433962264150944e-05,
+      "loss": 0.9668049812316895,
+      "step": 526
+    },
+    {
+      "epoch": 0.227831715210356,
+      "grad_norm": 0.5690792798995972,
+      "learning_rate": 9.469901168014376e-05,
+      "loss": 1.008763313293457,
+      "step": 528
+    },
+    {
+      "epoch": 0.22869471413160733,
+      "grad_norm": 0.5964897274971008,
+      "learning_rate": 9.505840071877809e-05,
+      "loss": 1.0816441774368286,
+      "step": 530
+    },
+    {
+      "epoch": 0.2295577130528587,
+      "grad_norm": 0.627419114112854,
+      "learning_rate": 9.54177897574124e-05,
+      "loss": 0.9265700578689575,
+      "step": 532
+    },
+    {
+      "epoch": 0.23042071197411004,
+      "grad_norm": 0.5862151980400085,
+      "learning_rate": 9.577717879604674e-05,
+      "loss": 0.9804646372795105,
+      "step": 534
+    },
+    {
+      "epoch": 0.23128371089536137,
+      "grad_norm": 0.5573718547821045,
+      "learning_rate": 9.613656783468105e-05,
+      "loss": 0.9627988934516907,
+      "step": 536
+    },
+    {
+      "epoch": 0.23214670981661273,
+      "grad_norm": 0.6705166101455688,
+      "learning_rate": 9.649595687331537e-05,
+      "loss": 1.0012824535369873,
+      "step": 538
+    },
+    {
+      "epoch": 0.23300970873786409,
+      "grad_norm": 0.6251236796379089,
+      "learning_rate": 9.685534591194969e-05,
+      "loss": 0.9568162560462952,
+      "step": 540
+    },
+    {
+      "epoch": 0.23387270765911541,
+      "grad_norm": 0.6466493010520935,
+      "learning_rate": 9.7214734950584e-05,
+      "loss": 1.031549334526062,
+      "step": 542
+    },
+    {
+      "epoch": 0.23473570658036677,
+      "grad_norm": 0.5183866024017334,
+      "learning_rate": 9.757412398921833e-05,
+      "loss": 0.8603643774986267,
+      "step": 544
+    },
+    {
+      "epoch": 0.23559870550161813,
+      "grad_norm": 0.6725775599479675,
+      "learning_rate": 9.793351302785265e-05,
+      "loss": 1.0365077257156372,
+      "step": 546
+    },
+    {
+      "epoch": 0.23646170442286948,
+      "grad_norm": 0.5972357988357544,
+      "learning_rate": 9.829290206648698e-05,
+      "loss": 0.9304701089859009,
+      "step": 548
+    },
+    {
+      "epoch": 0.2373247033441208,
+      "grad_norm": 0.5319957733154297,
+      "learning_rate": 9.86522911051213e-05,
+      "loss": 0.9575805068016052,
+      "step": 550
+    },
+    {
+      "epoch": 0.23818770226537217,
+      "grad_norm": 0.6502835750579834,
+      "learning_rate": 9.901168014375562e-05,
+      "loss": 1.0307214260101318,
+      "step": 552
+    },
+    {
+      "epoch": 0.23905070118662353,
+      "grad_norm": 0.6734047532081604,
+      "learning_rate": 9.937106918238994e-05,
+      "loss": 1.05185067653656,
+      "step": 554
+    },
+    {
+      "epoch": 0.23991370010787486,
+      "grad_norm": 0.5667978525161743,
+      "learning_rate": 9.973045822102426e-05,
+      "loss": 1.0190176963806152,
+      "step": 556
+    },
+    {
+      "epoch": 0.2407766990291262,
+      "grad_norm": 0.6370418667793274,
+      "learning_rate": 0.00010008984725965857,
+      "loss": 1.076182246208191,
+      "step": 558
+    },
+    {
+      "epoch": 0.24163969795037757,
+      "grad_norm": 0.689719021320343,
+      "learning_rate": 0.0001004492362982929,
+      "loss": 1.0408724546432495,
+      "step": 560
+    },
+    {
+      "epoch": 0.2425026968716289,
+      "grad_norm": 0.6304254531860352,
+      "learning_rate": 0.00010080862533692723,
+      "loss": 0.9869902729988098,
+      "step": 562
+    },
+    {
+      "epoch": 0.24336569579288025,
+      "grad_norm": 0.6797420382499695,
+      "learning_rate": 0.00010116801437556156,
+      "loss": 1.0198370218276978,
+      "step": 564
+    },
+    {
+      "epoch": 0.2442286947141316,
+      "grad_norm": 0.5993657112121582,
+      "learning_rate": 0.00010152740341419587,
+      "loss": 0.9947441816329956,
+      "step": 566
+    },
+    {
+      "epoch": 0.24509169363538297,
+      "grad_norm": 0.6369836330413818,
+      "learning_rate": 0.0001018867924528302,
+      "loss": 0.9722896814346313,
+      "step": 568
+    },
+    {
+      "epoch": 0.2459546925566343,
+      "grad_norm": 0.6942457556724548,
+      "learning_rate": 0.00010224618149146453,
+      "loss": 0.9716570973396301,
+      "step": 570
+    },
+    {
+      "epoch": 0.24681769147788565,
+      "grad_norm": 0.5403370261192322,
+      "learning_rate": 0.00010260557053009883,
+      "loss": 0.9797524213790894,
+      "step": 572
+    },
+    {
+      "epoch": 0.247680690399137,
+      "grad_norm": 0.5207529067993164,
+      "learning_rate": 0.00010296495956873316,
+      "loss": 0.985367476940155,
+      "step": 574
+    },
+    {
+      "epoch": 0.24854368932038834,
+      "grad_norm": 0.6751103401184082,
+      "learning_rate": 0.00010332434860736748,
+      "loss": 1.075042724609375,
+      "step": 576
+    },
+    {
+      "epoch": 0.2494066882416397,
+      "grad_norm": 0.565331220626831,
+      "learning_rate": 0.0001036837376460018,
+      "loss": 0.9273878335952759,
+      "step": 578
+    },
+    {
+      "epoch": 0.25026968716289105,
+      "grad_norm": 0.6858948469161987,
+      "learning_rate": 0.00010404312668463612,
+      "loss": 0.9872279763221741,
+      "step": 580
+    },
+    {
+      "epoch": 0.2511326860841424,
+      "grad_norm": 0.7091426253318787,
+      "learning_rate": 0.00010440251572327044,
+      "loss": 1.0038671493530273,
+      "step": 582
+    },
+    {
+      "epoch": 0.25199568500539377,
+      "grad_norm": 0.6493771076202393,
+      "learning_rate": 0.00010476190476190477,
+      "loss": 1.0109868049621582,
+      "step": 584
+    },
+    {
+      "epoch": 0.25285868392664507,
+      "grad_norm": 0.6107586622238159,
+      "learning_rate": 0.00010512129380053907,
+      "loss": 1.0020402669906616,
+      "step": 586
+    },
+    {
+      "epoch": 0.2537216828478964,
+      "grad_norm": 0.6878048181533813,
+      "learning_rate": 0.0001054806828391734,
+      "loss": 0.961039662361145,
+      "step": 588
+    },
+    {
+      "epoch": 0.2545846817691478,
+      "grad_norm": 0.664034903049469,
+      "learning_rate": 0.00010584007187780773,
+      "loss": 0.9725209474563599,
+      "step": 590
+    },
+    {
+      "epoch": 0.25544768069039914,
+      "grad_norm": 0.6399680376052856,
+      "learning_rate": 0.00010619946091644206,
+      "loss": 0.9907437562942505,
+      "step": 592
+    },
+    {
+      "epoch": 0.2563106796116505,
+      "grad_norm": 0.6163286566734314,
+      "learning_rate": 0.00010655884995507636,
+      "loss": 0.9650095701217651,
+      "step": 594
+    },
+    {
+      "epoch": 0.25717367853290185,
+      "grad_norm": 0.6008322238922119,
+      "learning_rate": 0.0001069182389937107,
+      "loss": 1.0102758407592773,
+      "step": 596
+    },
+    {
+      "epoch": 0.2580366774541532,
+      "grad_norm": 0.6752071380615234,
+      "learning_rate": 0.00010727762803234502,
+      "loss": 0.9101885557174683,
+      "step": 598
+    },
+    {
+      "epoch": 0.2588996763754045,
+      "grad_norm": 0.6789175868034363,
+      "learning_rate": 0.00010763701707097935,
+      "loss": 1.0461398363113403,
+      "step": 600
+    },
+    {
+      "epoch": 0.2588996763754045,
+      "eval_loss": 1.021111011505127,
+      "eval_runtime": 648.1611,
+      "eval_samples_per_second": 3.178,
+      "eval_steps_per_second": 3.178,
+      "step": 600
+    },
+    {
+      "epoch": 0.25976267529665586,
+      "grad_norm": 0.5660730600357056,
+      "learning_rate": 0.00010799640610961366,
+      "loss": 0.9582418203353882,
+      "step": 602
+    },
+    {
+      "epoch": 0.2606256742179072,
+      "grad_norm": 0.6726544499397278,
+      "learning_rate": 0.00010835579514824799,
+      "loss": 1.0763746500015259,
+      "step": 604
+    },
+    {
+      "epoch": 0.2614886731391586,
+      "grad_norm": 0.6068508625030518,
+      "learning_rate": 0.00010871518418688232,
+      "loss": 1.0432032346725464,
+      "step": 606
+    },
+    {
+      "epoch": 0.26235167206040994,
+      "grad_norm": 0.5731637477874756,
+      "learning_rate": 0.00010907457322551662,
+      "loss": 0.9830516576766968,
+      "step": 608
+    },
+    {
+      "epoch": 0.2632146709816613,
+      "grad_norm": 0.6777567267417908,
+      "learning_rate": 0.00010943396226415095,
+      "loss": 1.0442042350769043,
+      "step": 610
+    },
+    {
+      "epoch": 0.26407766990291265,
+      "grad_norm": 0.6372506618499756,
+      "learning_rate": 0.00010979335130278528,
+      "loss": 1.0001944303512573,
+      "step": 612
+    },
+    {
+      "epoch": 0.26494066882416395,
+      "grad_norm": 0.6606221795082092,
+      "learning_rate": 0.0001101527403414196,
+      "loss": 1.035884141921997,
+      "step": 614
+    },
+    {
+      "epoch": 0.2658036677454153,
+      "grad_norm": 0.6083229780197144,
+      "learning_rate": 0.00011051212938005391,
+      "loss": 0.9403397440910339,
+      "step": 616
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.6318517923355103,
+      "learning_rate": 0.00011087151841868823,
+      "loss": 0.9274454116821289,
+      "step": 618
+    },
+    {
+      "epoch": 0.267529665587918,
+      "grad_norm": 0.628190279006958,
+      "learning_rate": 0.00011123090745732256,
+      "loss": 0.9883754253387451,
+      "step": 620
+    },
+    {
+      "epoch": 0.2683926645091694,
+      "grad_norm": 0.5961961150169373,
+      "learning_rate": 0.00011159029649595688,
+      "loss": 1.0317535400390625,
+      "step": 622
+    },
+    {
+      "epoch": 0.26925566343042073,
+      "grad_norm": 0.5995341539382935,
+      "learning_rate": 0.00011194968553459119,
+      "loss": 0.9776126742362976,
+      "step": 624
+    },
+    {
+      "epoch": 0.27011866235167203,
+      "grad_norm": 0.6639334559440613,
+      "learning_rate": 0.00011230907457322552,
+      "loss": 1.0112378597259521,
+      "step": 626
+    },
+    {
+      "epoch": 0.2709816612729234,
+      "grad_norm": 0.6348621249198914,
+      "learning_rate": 0.00011266846361185985,
+      "loss": 1.0553804636001587,
+      "step": 628
+    },
+    {
+      "epoch": 0.27184466019417475,
+      "grad_norm": 0.5929805040359497,
+      "learning_rate": 0.00011302785265049416,
+      "loss": 1.025888442993164,
+      "step": 630
+    },
+    {
+      "epoch": 0.2727076591154261,
+      "grad_norm": 0.6052366495132446,
+      "learning_rate": 0.00011338724168912849,
+      "loss": 1.02956223487854,
+      "step": 632
+    },
+    {
+      "epoch": 0.27357065803667746,
+      "grad_norm": 0.6494882106781006,
+      "learning_rate": 0.00011374663072776282,
+      "loss": 0.989752471446991,
+      "step": 634
+    },
+    {
+      "epoch": 0.2744336569579288,
+      "grad_norm": 0.6005767583847046,
+      "learning_rate": 0.00011410601976639712,
+      "loss": 1.0030683279037476,
+      "step": 636
+    },
+    {
+      "epoch": 0.2752966558791802,
+      "grad_norm": 0.6478356122970581,
+      "learning_rate": 0.00011446540880503145,
+      "loss": 1.002000093460083,
+      "step": 638
+    },
+    {
+      "epoch": 0.2761596548004315,
+      "grad_norm": 0.5804725289344788,
+      "learning_rate": 0.00011482479784366578,
+      "loss": 0.9807654023170471,
+      "step": 640
+    },
+    {
+      "epoch": 0.27702265372168283,
+      "grad_norm": 0.632530689239502,
+      "learning_rate": 0.00011518418688230011,
+      "loss": 0.9841892123222351,
+      "step": 642
+    },
+    {
+      "epoch": 0.2778856526429342,
+      "grad_norm": 0.5340113639831543,
+      "learning_rate": 0.00011554357592093441,
+      "loss": 0.8902478814125061,
+      "step": 644
+    },
+    {
+      "epoch": 0.27874865156418555,
+      "grad_norm": 0.5901665091514587,
+      "learning_rate": 0.00011590296495956874,
+      "loss": 0.9019404649734497,
+      "step": 646
+    },
+    {
+      "epoch": 0.2796116504854369,
+      "grad_norm": 0.666589617729187,
+      "learning_rate": 0.00011626235399820307,
+      "loss": 0.9384423494338989,
+      "step": 648
+    },
+    {
+      "epoch": 0.28047464940668826,
+      "grad_norm": 0.7000334858894348,
+      "learning_rate": 0.00011662174303683737,
+      "loss": 1.0666629076004028,
+      "step": 650
+    },
+    {
+      "epoch": 0.2813376483279396,
+      "grad_norm": 0.663663923740387,
+      "learning_rate": 0.0001169811320754717,
+      "loss": 1.000019907951355,
+      "step": 652
+    },
+    {
+      "epoch": 0.2822006472491909,
+      "grad_norm": 0.6097694039344788,
+      "learning_rate": 0.00011734052111410603,
+      "loss": 0.9450293183326721,
+      "step": 654
+    },
+    {
+      "epoch": 0.2830636461704423,
+      "grad_norm": 0.6130967140197754,
+      "learning_rate": 0.00011769991015274035,
+      "loss": 0.9480894207954407,
+      "step": 656
+    },
+    {
+      "epoch": 0.28392664509169363,
+      "grad_norm": 0.7091249227523804,
+      "learning_rate": 0.00011805929919137467,
+      "loss": 1.1377143859863281,
+      "step": 658
+    },
+    {
+      "epoch": 0.284789644012945,
+      "grad_norm": 0.6556766629219055,
+      "learning_rate": 0.00011841868823000898,
+      "loss": 0.9421243667602539,
+      "step": 660
+    },
+    {
+      "epoch": 0.28565264293419634,
+      "grad_norm": 0.6682968735694885,
+      "learning_rate": 0.00011877807726864331,
+      "loss": 0.9726828336715698,
+      "step": 662
+    },
+    {
+      "epoch": 0.2865156418554477,
+      "grad_norm": 0.5224708914756775,
+      "learning_rate": 0.00011913746630727762,
+      "loss": 0.8996511697769165,
+      "step": 664
+    },
+    {
+      "epoch": 0.287378640776699,
+      "grad_norm": 0.5914195775985718,
+      "learning_rate": 0.00011949685534591195,
+      "loss": 0.9679517149925232,
+      "step": 666
+    },
+    {
+      "epoch": 0.28824163969795036,
+      "grad_norm": 0.6175519824028015,
+      "learning_rate": 0.00011985624438454628,
+      "loss": 0.8743209838867188,
+      "step": 668
+    },
+    {
+      "epoch": 0.2891046386192017,
+      "grad_norm": 0.6019226312637329,
+      "learning_rate": 0.0001202156334231806,
+      "loss": 0.9741992354393005,
+      "step": 670
+    },
+    {
+      "epoch": 0.28996763754045307,
+      "grad_norm": 0.6080542206764221,
+      "learning_rate": 0.00012057502246181491,
+      "loss": 0.9516472816467285,
+      "step": 672
+    },
+    {
+      "epoch": 0.29083063646170443,
+      "grad_norm": 0.5885615944862366,
+      "learning_rate": 0.00012093441150044924,
+      "loss": 1.122761607170105,
+      "step": 674
+    },
+    {
+      "epoch": 0.2916936353829558,
+      "grad_norm": 0.6635209918022156,
+      "learning_rate": 0.00012129380053908357,
+      "loss": 1.0105189085006714,
+      "step": 676
+    },
+    {
+      "epoch": 0.29255663430420714,
+      "grad_norm": 0.5805009007453918,
+      "learning_rate": 0.0001216531895777179,
+      "loss": 0.906292200088501,
+      "step": 678
+    },
+    {
+      "epoch": 0.29341963322545844,
+      "grad_norm": 0.5980029702186584,
+      "learning_rate": 0.0001220125786163522,
+      "loss": 1.009568691253662,
+      "step": 680
+    },
+    {
+      "epoch": 0.2942826321467098,
+      "grad_norm": 0.6797705292701721,
+      "learning_rate": 0.00012237196765498652,
+      "loss": 1.0373667478561401,
+      "step": 682
+    },
+    {
+      "epoch": 0.29514563106796116,
+      "grad_norm": 0.6280547976493835,
+      "learning_rate": 0.00012273135669362085,
+      "loss": 0.9758188724517822,
+      "step": 684
+    },
+    {
+      "epoch": 0.2960086299892125,
+      "grad_norm": 0.511608898639679,
+      "learning_rate": 0.00012309074573225515,
+      "loss": 0.9111692905426025,
+      "step": 686
+    },
+    {
+      "epoch": 0.29687162891046387,
+      "grad_norm": 0.5781835317611694,
+      "learning_rate": 0.00012345013477088948,
+      "loss": 0.8865921497344971,
+      "step": 688
+    },
+    {
+      "epoch": 0.2977346278317152,
+      "grad_norm": 0.6514166593551636,
+      "learning_rate": 0.0001238095238095238,
+      "loss": 0.9768189191818237,
+      "step": 690
+    },
+    {
+      "epoch": 0.2985976267529666,
+      "grad_norm": 0.6109189987182617,
+      "learning_rate": 0.00012416891284815814,
+      "loss": 0.9991607069969177,
+      "step": 692
+    },
+    {
+      "epoch": 0.2994606256742179,
+      "grad_norm": 0.6598902344703674,
+      "learning_rate": 0.00012452830188679244,
+      "loss": 0.9548360705375671,
+      "step": 694
+    },
+    {
+      "epoch": 0.30032362459546924,
+      "grad_norm": 0.5633156895637512,
+      "learning_rate": 0.00012488769092542677,
+      "loss": 0.992988109588623,
+      "step": 696
+    },
+    {
+      "epoch": 0.3011866235167206,
+      "grad_norm": 0.6098802089691162,
+      "learning_rate": 0.0001252470799640611,
+      "loss": 0.9709890484809875,
+      "step": 698
+    },
+    {
+      "epoch": 0.30204962243797195,
+      "grad_norm": 0.6197102665901184,
+      "learning_rate": 0.0001256064690026954,
+      "loss": 1.018282175064087,
+      "step": 700
+    },
+    {
+      "epoch": 0.30204962243797195,
+      "eval_loss": 1.0030721426010132,
+      "eval_runtime": 655.4533,
+      "eval_samples_per_second": 3.143,
+      "eval_steps_per_second": 3.143,
+      "step": 700
+    },
+    {
+      "epoch": 0.3029126213592233,
+      "grad_norm": 0.5817480683326721,
+      "learning_rate": 0.00012596585804132974,
+      "loss": 0.9147283434867859,
+      "step": 702
+    },
+    {
+      "epoch": 0.30377562028047467,
+      "grad_norm": 0.5976696014404297,
+      "learning_rate": 0.00012632524707996407,
+      "loss": 0.9318362474441528,
+      "step": 704
+    },
+    {
+      "epoch": 0.304638619201726,
+      "grad_norm": 0.6389723420143127,
+      "learning_rate": 0.0001266846361185984,
+      "loss": 0.9500927925109863,
+      "step": 706
+    },
+    {
+      "epoch": 0.3055016181229773,
+      "grad_norm": 0.6485719084739685,
+      "learning_rate": 0.0001270440251572327,
+      "loss": 1.0271424055099487,
+      "step": 708
+    },
+    {
+      "epoch": 0.3063646170442287,
+      "grad_norm": 0.5802455544471741,
+      "learning_rate": 0.00012740341419586703,
+      "loss": 0.9781906008720398,
+      "step": 710
+    },
+    {
+      "epoch": 0.30722761596548004,
+      "grad_norm": 0.6359356641769409,
+      "learning_rate": 0.00012776280323450136,
+      "loss": 1.0195324420928955,
+      "step": 712
+    },
+    {
+      "epoch": 0.3080906148867314,
+      "grad_norm": 0.5975426435470581,
+      "learning_rate": 0.00012812219227313566,
+      "loss": 0.9250738024711609,
+      "step": 714
+    },
+    {
+      "epoch": 0.30895361380798275,
+      "grad_norm": 0.643110454082489,
+      "learning_rate": 0.00012848158131177,
+      "loss": 0.9888015985488892,
+      "step": 716
+    },
+    {
+      "epoch": 0.3098166127292341,
+      "grad_norm": 0.6043205261230469,
+      "learning_rate": 0.00012884097035040432,
+      "loss": 0.9709514379501343,
+      "step": 718
+    },
+    {
+      "epoch": 0.3106796116504854,
+      "grad_norm": 0.5687094926834106,
+      "learning_rate": 0.00012920035938903865,
+      "loss": 1.0272964239120483,
+      "step": 720
+    },
+    {
+      "epoch": 0.31154261057173677,
+      "grad_norm": 0.5688400864601135,
+      "learning_rate": 0.00012955974842767296,
+      "loss": 0.9370370507240295,
+      "step": 722
+    },
+    {
+      "epoch": 0.3124056094929881,
+      "grad_norm": 0.5610610246658325,
+      "learning_rate": 0.00012991913746630729,
+      "loss": 0.9535608291625977,
+      "step": 724
+    },
+    {
+      "epoch": 0.3132686084142395,
+      "grad_norm": 0.6338257193565369,
+      "learning_rate": 0.00013027852650494162,
+      "loss": 1.0188907384872437,
+      "step": 726
+    },
+    {
+      "epoch": 0.31413160733549084,
+      "grad_norm": 0.5365633368492126,
+      "learning_rate": 0.00013063791554357592,
+      "loss": 0.9253716468811035,
+      "step": 728
+    },
+    {
+      "epoch": 0.3149946062567422,
+      "grad_norm": 0.5599163174629211,
+      "learning_rate": 0.00013099730458221025,
+      "loss": 0.8941492438316345,
+      "step": 730
+    },
+    {
+      "epoch": 0.31585760517799355,
+      "grad_norm": 0.6059780716896057,
+      "learning_rate": 0.00013135669362084458,
+      "loss": 0.9831459522247314,
+      "step": 732
+    },
+    {
+      "epoch": 0.31672060409924485,
+      "grad_norm": 0.5596494078636169,
+      "learning_rate": 0.0001317160826594789,
+      "loss": 0.9332310557365417,
+      "step": 734
+    },
+    {
+      "epoch": 0.3175836030204962,
+      "grad_norm": 0.5618010759353638,
+      "learning_rate": 0.0001320754716981132,
+      "loss": 0.9082580208778381,
+      "step": 736
+    },
+    {
+      "epoch": 0.31844660194174756,
+      "grad_norm": 0.6412109732627869,
+      "learning_rate": 0.00013243486073674754,
+      "loss": 1.008690357208252,
+      "step": 738
+    },
+    {
+      "epoch": 0.3193096008629989,
+      "grad_norm": 0.5742355585098267,
+      "learning_rate": 0.00013279424977538187,
+      "loss": 0.9597798585891724,
+      "step": 740
+    },
+    {
+      "epoch": 0.3201725997842503,
+      "grad_norm": 0.6470226645469666,
+      "learning_rate": 0.00013315363881401617,
+      "loss": 0.989331841468811,
+      "step": 742
+    },
+    {
+      "epoch": 0.32103559870550163,
+      "grad_norm": 0.5598039031028748,
+      "learning_rate": 0.0001335130278526505,
+      "loss": 0.8677343130111694,
+      "step": 744
+    },
+    {
+      "epoch": 0.321898597626753,
+      "grad_norm": 0.5441372990608215,
+      "learning_rate": 0.00013387241689128483,
+      "loss": 0.9462730288505554,
+      "step": 746
+    },
+    {
+      "epoch": 0.3227615965480043,
+      "grad_norm": 0.5858626365661621,
+      "learning_rate": 0.00013423180592991916,
+      "loss": 0.994694173336029,
+      "step": 748
+    },
+    {
+      "epoch": 0.32362459546925565,
+      "grad_norm": 0.511372447013855,
+      "learning_rate": 0.00013459119496855347,
+      "loss": 0.9387269616127014,
+      "step": 750
+    },
+    {
+      "epoch": 0.324487594390507,
+      "grad_norm": 0.47798457741737366,
+      "learning_rate": 0.0001349505840071878,
+      "loss": 0.9473881721496582,
+      "step": 752
+    },
+    {
+      "epoch": 0.32535059331175836,
+      "grad_norm": 0.5907022953033447,
+      "learning_rate": 0.0001353099730458221,
+      "loss": 0.9375183582305908,
+      "step": 754
+    },
+    {
+      "epoch": 0.3262135922330097,
+      "grad_norm": 0.618733286857605,
+      "learning_rate": 0.00013566936208445643,
+      "loss": 1.028738260269165,
+      "step": 756
+    },
+    {
+      "epoch": 0.3270765911542611,
+      "grad_norm": 0.5234512090682983,
+      "learning_rate": 0.00013602875112309076,
+      "loss": 0.9420192241668701,
+      "step": 758
+    },
+    {
+      "epoch": 0.32793959007551243,
+      "grad_norm": 0.7036319971084595,
+      "learning_rate": 0.00013638814016172506,
+      "loss": 1.0252270698547363,
+      "step": 760
+    },
+    {
+      "epoch": 0.32880258899676373,
+      "grad_norm": 0.5543172359466553,
+      "learning_rate": 0.0001367475292003594,
+      "loss": 0.8453778028488159,
+      "step": 762
+    },
+    {
+      "epoch": 0.3296655879180151,
+      "grad_norm": 0.5438711643218994,
+      "learning_rate": 0.0001371069182389937,
+      "loss": 0.8659937977790833,
+      "step": 764
+    },
+    {
+      "epoch": 0.33052858683926645,
+      "grad_norm": 0.6390914916992188,
+      "learning_rate": 0.00013746630727762803,
+      "loss": 1.038142442703247,
+      "step": 766
+    },
+    {
+      "epoch": 0.3313915857605178,
+      "grad_norm": 0.50070720911026,
+      "learning_rate": 0.00013782569631626236,
+      "loss": 0.899932861328125,
+      "step": 768
+    },
+    {
+      "epoch": 0.33225458468176916,
+      "grad_norm": 0.5982286334037781,
+      "learning_rate": 0.00013818508535489669,
+      "loss": 0.9712884426116943,
+      "step": 770
+    },
+    {
+      "epoch": 0.3331175836030205,
+      "grad_norm": 0.6588822603225708,
+      "learning_rate": 0.000138544474393531,
+      "loss": 0.9427542686462402,
+      "step": 772
+    },
+    {
+      "epoch": 0.3339805825242718,
+      "grad_norm": 0.6022042632102966,
+      "learning_rate": 0.00013890386343216532,
+      "loss": 0.8961561918258667,
+      "step": 774
+    },
+    {
+      "epoch": 0.3348435814455232,
+      "grad_norm": 0.6595642566680908,
+      "learning_rate": 0.00013926325247079965,
+      "loss": 0.9525937438011169,
+      "step": 776
+    },
+    {
+      "epoch": 0.33570658036677453,
+      "grad_norm": 0.5210421681404114,
+      "learning_rate": 0.00013962264150943395,
+      "loss": 0.9218845367431641,
+      "step": 778
+    },
+    {
+      "epoch": 0.3365695792880259,
+      "grad_norm": 0.549669623374939,
+      "learning_rate": 0.00013998203054806828,
+      "loss": 0.877951443195343,
+      "step": 780
+    },
+    {
+      "epoch": 0.33743257820927725,
+      "grad_norm": 0.5360157489776611,
+      "learning_rate": 0.0001403414195867026,
+      "loss": 0.8670064210891724,
+      "step": 782
+    },
+    {
+      "epoch": 0.3382955771305286,
+      "grad_norm": 0.614734947681427,
+      "learning_rate": 0.00014070080862533694,
+      "loss": 0.9561367630958557,
+      "step": 784
+    },
+    {
+      "epoch": 0.33915857605177996,
+      "grad_norm": 0.5798251628875732,
+      "learning_rate": 0.00014106019766397124,
+      "loss": 0.9132505059242249,
+      "step": 786
+    },
+    {
+      "epoch": 0.34002157497303126,
+      "grad_norm": 0.6267077326774597,
+      "learning_rate": 0.00014141958670260557,
+      "loss": 0.9297707080841064,
+      "step": 788
+    },
+    {
+      "epoch": 0.3408845738942826,
+      "grad_norm": 0.6045349836349487,
+      "learning_rate": 0.0001417789757412399,
+      "loss": 0.9382412433624268,
+      "step": 790
+    },
+    {
+      "epoch": 0.341747572815534,
+      "grad_norm": 0.6125404834747314,
+      "learning_rate": 0.0001421383647798742,
+      "loss": 0.9078555107116699,
+      "step": 792
+    },
+    {
+      "epoch": 0.34261057173678533,
+      "grad_norm": 0.5927051901817322,
+      "learning_rate": 0.00014249775381850854,
+      "loss": 0.899101197719574,
+      "step": 794
+    },
+    {
+      "epoch": 0.3434735706580367,
+      "grad_norm": 0.6315743923187256,
+      "learning_rate": 0.00014285714285714287,
+      "loss": 1.028346300125122,
+      "step": 796
+    },
+    {
+      "epoch": 0.34433656957928804,
+      "grad_norm": 0.549271285533905,
+      "learning_rate": 0.0001432165318957772,
+      "loss": 0.8988189697265625,
+      "step": 798
+    },
+    {
+      "epoch": 0.3451995685005394,
+      "grad_norm": 0.6344245672225952,
+      "learning_rate": 0.0001435759209344115,
+      "loss": 1.0489003658294678,
+      "step": 800
+    },
+    {
+      "epoch": 0.3451995685005394,
+      "eval_loss": 0.9864639639854431,
+      "eval_runtime": 667.3516,
+      "eval_samples_per_second": 3.087,
+      "eval_steps_per_second": 3.087,
+      "step": 800
+    },
+    {
+      "epoch": 0.3460625674217907,
+      "grad_norm": 0.5625309348106384,
+      "learning_rate": 0.00014393530997304583,
+      "loss": 0.8773928284645081,
+      "step": 802
+    },
+    {
+      "epoch": 0.34692556634304206,
+      "grad_norm": 0.5931969285011292,
+      "learning_rate": 0.00014429469901168016,
+      "loss": 0.9116050004959106,
+      "step": 804
+    },
+    {
+      "epoch": 0.3477885652642934,
+      "grad_norm": 0.5189821720123291,
+      "learning_rate": 0.00014465408805031446,
+      "loss": 0.9124425649642944,
+      "step": 806
+    },
+    {
+      "epoch": 0.34865156418554477,
+      "grad_norm": 0.5392254590988159,
+      "learning_rate": 0.0001450134770889488,
+      "loss": 0.9517888426780701,
+      "step": 808
+    },
+    {
+      "epoch": 0.34951456310679613,
+      "grad_norm": 0.5584444999694824,
+      "learning_rate": 0.00014537286612758312,
+      "loss": 0.9947572350502014,
+      "step": 810
+    },
+    {
+      "epoch": 0.3503775620280475,
+      "grad_norm": 0.5188854932785034,
+      "learning_rate": 0.00014573225516621745,
+      "loss": 0.9314022660255432,
+      "step": 812
+    },
+    {
+      "epoch": 0.3512405609492988,
+      "grad_norm": 0.5783659815788269,
+      "learning_rate": 0.00014609164420485176,
+      "loss": 0.9135628938674927,
+      "step": 814
+    },
+    {
+      "epoch": 0.35210355987055014,
+      "grad_norm": 0.550959050655365,
+      "learning_rate": 0.0001464510332434861,
+      "loss": 0.9665075540542603,
+      "step": 816
+    },
+    {
+      "epoch": 0.3529665587918015,
+      "grad_norm": 0.6013346314430237,
+      "learning_rate": 0.00014681042228212042,
+      "loss": 0.9836555123329163,
+      "step": 818
+    },
+    {
+      "epoch": 0.35382955771305286,
+      "grad_norm": 0.49219194054603577,
+      "learning_rate": 0.00014716981132075472,
+      "loss": 0.8900108337402344,
+      "step": 820
+    },
+    {
+      "epoch": 0.3546925566343042,
+      "grad_norm": 0.5517411828041077,
+      "learning_rate": 0.00014752920035938905,
+      "loss": 0.8769304156303406,
+      "step": 822
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.6062695980072021,
+      "learning_rate": 0.00014788858939802338,
+      "loss": 0.9744759202003479,
+      "step": 824
+    },
+    {
+      "epoch": 0.3564185544768069,
+      "grad_norm": 0.5132041573524475,
+      "learning_rate": 0.0001482479784366577,
+      "loss": 0.8875447511672974,
+      "step": 826
+    },
+    {
+      "epoch": 0.3572815533980582,
+      "grad_norm": 0.551799476146698,
+      "learning_rate": 0.000148607367475292,
+      "loss": 0.962710440158844,
+      "step": 828
+    },
+    {
+      "epoch": 0.3581445523193096,
+      "grad_norm": 0.6046625971794128,
+      "learning_rate": 0.00014896675651392634,
+      "loss": 0.8997528553009033,
+      "step": 830
+    },
+    {
+      "epoch": 0.35900755124056094,
+      "grad_norm": 0.560025691986084,
+      "learning_rate": 0.00014932614555256067,
+      "loss": 0.9541417360305786,
+      "step": 832
+    },
+    {
+      "epoch": 0.3598705501618123,
+      "grad_norm": 0.6441047787666321,
+      "learning_rate": 0.00014968553459119498,
+      "loss": 0.907791018486023,
+      "step": 834
+    },
+    {
+      "epoch": 0.36073354908306365,
+      "grad_norm": 0.5636281967163086,
+      "learning_rate": 0.0001500449236298293,
+      "loss": 1.0295937061309814,
+      "step": 836
+    },
+    {
+      "epoch": 0.361596548004315,
+      "grad_norm": 0.5528303384780884,
+      "learning_rate": 0.0001504043126684636,
+      "loss": 0.8875265717506409,
+      "step": 838
+    },
+    {
+      "epoch": 0.36245954692556637,
+      "grad_norm": 0.5345163345336914,
+      "learning_rate": 0.00015076370170709794,
+      "loss": 0.9678915739059448,
+      "step": 840
+    },
+    {
+      "epoch": 0.36332254584681767,
+      "grad_norm": 0.5551225543022156,
+      "learning_rate": 0.00015112309074573224,
+      "loss": 0.9235162734985352,
+      "step": 842
+    },
+    {
+      "epoch": 0.364185544768069,
+      "grad_norm": 0.5131904482841492,
+      "learning_rate": 0.00015148247978436657,
+      "loss": 0.8624292016029358,
+      "step": 844
+    },
+    {
+      "epoch": 0.3650485436893204,
+      "grad_norm": 0.6811004281044006,
+      "learning_rate": 0.0001518418688230009,
+      "loss": 1.0360193252563477,
+      "step": 846
+    },
+    {
+      "epoch": 0.36591154261057174,
+      "grad_norm": 0.6409741640090942,
+      "learning_rate": 0.00015220125786163523,
+      "loss": 0.9254010915756226,
+      "step": 848
+    },
+    {
+      "epoch": 0.3667745415318231,
+      "grad_norm": 0.5534068942070007,
+      "learning_rate": 0.00015256064690026953,
+      "loss": 0.8900630474090576,
+      "step": 850
+    },
+    {
+      "epoch": 0.36763754045307445,
+      "grad_norm": 0.4999487102031708,
+      "learning_rate": 0.00015292003593890386,
+      "loss": 0.88521409034729,
+      "step": 852
+    },
+    {
+      "epoch": 0.3685005393743258,
+      "grad_norm": 0.5805923938751221,
+      "learning_rate": 0.0001532794249775382,
+      "loss": 0.9563921093940735,
+      "step": 854
+    },
+    {
+      "epoch": 0.3693635382955771,
+      "grad_norm": 0.5485470294952393,
+      "learning_rate": 0.0001536388140161725,
+      "loss": 0.8909372687339783,
+      "step": 856
+    },
+    {
+      "epoch": 0.37022653721682847,
+      "grad_norm": 0.5317923426628113,
+      "learning_rate": 0.00015399820305480683,
+      "loss": 0.9145731925964355,
+      "step": 858
+    },
+    {
+      "epoch": 0.3710895361380798,
+      "grad_norm": 0.6073495745658875,
+      "learning_rate": 0.00015435759209344116,
+      "loss": 1.01466965675354,
+      "step": 860
+    },
+    {
+      "epoch": 0.3719525350593312,
+      "grad_norm": 0.566655158996582,
+      "learning_rate": 0.0001547169811320755,
+      "loss": 0.9941825270652771,
+      "step": 862
+    },
+    {
+      "epoch": 0.37281553398058254,
+      "grad_norm": 0.5262459516525269,
+      "learning_rate": 0.0001550763701707098,
+      "loss": 1.0059782266616821,
+      "step": 864
+    },
+    {
+      "epoch": 0.3736785329018339,
+      "grad_norm": 0.6264083981513977,
+      "learning_rate": 0.00015543575920934412,
+      "loss": 1.0332856178283691,
+      "step": 866
+    },
+    {
+      "epoch": 0.3745415318230852,
+      "grad_norm": 0.6575480699539185,
+      "learning_rate": 0.00015579514824797845,
+      "loss": 1.022459626197815,
+      "step": 868
+    },
+    {
+      "epoch": 0.37540453074433655,
+      "grad_norm": 0.6291940212249756,
+      "learning_rate": 0.00015615453728661275,
+      "loss": 0.9550372362136841,
+      "step": 870
+    },
+    {
+      "epoch": 0.3762675296655879,
+      "grad_norm": 0.6710562109947205,
+      "learning_rate": 0.00015651392632524708,
+      "loss": 0.9861716628074646,
+      "step": 872
+    },
+    {
+      "epoch": 0.37713052858683926,
+      "grad_norm": 0.5505748987197876,
+      "learning_rate": 0.0001568733153638814,
+      "loss": 0.9719111919403076,
+      "step": 874
+    },
+    {
+      "epoch": 0.3779935275080906,
+      "grad_norm": 0.5055180788040161,
+      "learning_rate": 0.00015723270440251574,
+      "loss": 0.8698170185089111,
+      "step": 876
+    },
+    {
+      "epoch": 0.378856526429342,
+      "grad_norm": 0.5935947895050049,
+      "learning_rate": 0.00015759209344115005,
+      "loss": 1.029494285583496,
+      "step": 878
+    },
+    {
+      "epoch": 0.37971952535059333,
+      "grad_norm": 0.538325846195221,
+      "learning_rate": 0.00015795148247978438,
+      "loss": 0.923010528087616,
+      "step": 880
+    },
+    {
+      "epoch": 0.38058252427184464,
+      "grad_norm": 0.587297797203064,
+      "learning_rate": 0.0001583108715184187,
+      "loss": 0.9394056797027588,
+      "step": 882
+    },
+    {
+      "epoch": 0.381445523193096,
+      "grad_norm": 0.5910462737083435,
+      "learning_rate": 0.000158670260557053,
+      "loss": 0.9472483992576599,
+      "step": 884
+    },
+    {
+      "epoch": 0.38230852211434735,
+      "grad_norm": 0.629048764705658,
+      "learning_rate": 0.00015902964959568734,
+      "loss": 0.9028263688087463,
+      "step": 886
+    },
+    {
+      "epoch": 0.3831715210355987,
+      "grad_norm": 0.5028086304664612,
+      "learning_rate": 0.00015938903863432167,
+      "loss": 0.9579087495803833,
+      "step": 888
+    },
+    {
+      "epoch": 0.38403451995685006,
+      "grad_norm": 0.5372384190559387,
+      "learning_rate": 0.000159748427672956,
+      "loss": 0.8318673372268677,
+      "step": 890
+    },
+    {
+      "epoch": 0.3848975188781014,
+      "grad_norm": 0.6314184665679932,
+      "learning_rate": 0.0001601078167115903,
+      "loss": 0.9804943203926086,
+      "step": 892
+    },
+    {
+      "epoch": 0.3857605177993528,
+      "grad_norm": 0.5545229911804199,
+      "learning_rate": 0.00016046720575022463,
+      "loss": 1.0078438520431519,
+      "step": 894
+    },
+    {
+      "epoch": 0.3866235167206041,
+      "grad_norm": 0.4674014151096344,
+      "learning_rate": 0.00016082659478885896,
+      "loss": 0.9269036650657654,
+      "step": 896
+    },
+    {
+      "epoch": 0.38748651564185543,
+      "grad_norm": 1.5887153148651123,
+      "learning_rate": 0.00016118598382749326,
+      "loss": 0.8927953243255615,
+      "step": 898
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "grad_norm": 0.5217035412788391,
+      "learning_rate": 0.0001615453728661276,
+      "loss": 0.908074140548706,
+      "step": 900
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "eval_loss": 0.9741895794868469,
+      "eval_runtime": 667.2236,
+      "eval_samples_per_second": 3.087,
+      "eval_steps_per_second": 3.087,
+      "step": 900
+    },
+    {
+      "epoch": 0.38921251348435815,
+      "grad_norm": 0.470498651266098,
+      "learning_rate": 0.00016190476190476192,
+      "loss": 0.9660369157791138,
+      "step": 902
+    },
+    {
+      "epoch": 0.3900755124056095,
+      "grad_norm": 0.5111004114151001,
+      "learning_rate": 0.00016226415094339625,
+      "loss": 0.9236379265785217,
+      "step": 904
+    },
+    {
+      "epoch": 0.39093851132686086,
+      "grad_norm": 0.5872815251350403,
+      "learning_rate": 0.00016262353998203056,
+      "loss": 1.0061595439910889,
+      "step": 906
+    },
+    {
+      "epoch": 0.3918015102481122,
+      "grad_norm": 0.5150740742683411,
+      "learning_rate": 0.0001629829290206649,
+      "loss": 0.8347328901290894,
+      "step": 908
+    },
+    {
+      "epoch": 0.3926645091693635,
+      "grad_norm": 0.46554985642433167,
+      "learning_rate": 0.00016334231805929922,
+      "loss": 0.9091183543205261,
+      "step": 910
+    },
+    {
+      "epoch": 0.3935275080906149,
+      "grad_norm": 0.5292875170707703,
+      "learning_rate": 0.00016370170709793352,
+      "loss": 0.9299798011779785,
+      "step": 912
+    },
+    {
+      "epoch": 0.39439050701186623,
+      "grad_norm": 0.5177125930786133,
+      "learning_rate": 0.00016406109613656785,
+      "loss": 0.942286491394043,
+      "step": 914
+    },
+    {
+      "epoch": 0.3952535059331176,
+      "grad_norm": 0.5564161539077759,
+      "learning_rate": 0.00016442048517520215,
+      "loss": 0.825290858745575,
+      "step": 916
+    },
+    {
+      "epoch": 0.39611650485436894,
+      "grad_norm": 0.5572530031204224,
+      "learning_rate": 0.00016477987421383648,
+      "loss": 0.876898467540741,
+      "step": 918
+    },
+    {
+      "epoch": 0.3969795037756203,
+      "grad_norm": 0.7294673323631287,
+      "learning_rate": 0.0001651392632524708,
+      "loss": 0.8949798941612244,
+      "step": 920
+    },
+    {
+      "epoch": 0.3978425026968716,
+      "grad_norm": 0.5234251022338867,
+      "learning_rate": 0.00016549865229110512,
+      "loss": 0.8457819223403931,
+      "step": 922
+    },
+    {
+      "epoch": 0.39870550161812296,
+      "grad_norm": 0.5273709893226624,
+      "learning_rate": 0.00016585804132973945,
+      "loss": 0.9080174565315247,
+      "step": 924
+    },
+    {
+      "epoch": 0.3995685005393743,
+      "grad_norm": 0.5795063376426697,
+      "learning_rate": 0.00016621743036837378,
+      "loss": 1.0304023027420044,
+      "step": 926
+    },
+    {
+      "epoch": 0.4004314994606257,
+      "grad_norm": 0.6153313517570496,
+      "learning_rate": 0.00016657681940700808,
+      "loss": 0.8900477886199951,
+      "step": 928
+    },
+    {
+      "epoch": 0.40129449838187703,
+      "grad_norm": 0.6293173432350159,
+      "learning_rate": 0.0001669362084456424,
+      "loss": 1.0130009651184082,
+      "step": 930
+    },
+    {
+      "epoch": 0.4021574973031284,
+      "grad_norm": 0.5455223321914673,
+      "learning_rate": 0.00016729559748427674,
+      "loss": 0.9339282512664795,
+      "step": 932
+    },
+    {
+      "epoch": 0.40302049622437974,
+      "grad_norm": 0.5349094271659851,
+      "learning_rate": 0.00016765498652291104,
+      "loss": 0.9628980755805969,
+      "step": 934
+    },
+    {
+      "epoch": 0.40388349514563104,
+      "grad_norm": 0.491227924823761,
+      "learning_rate": 0.00016801437556154537,
+      "loss": 0.8922860026359558,
+      "step": 936
+    },
+    {
+      "epoch": 0.4047464940668824,
+      "grad_norm": 0.6331246495246887,
+      "learning_rate": 0.0001683737646001797,
+      "loss": 1.0470497608184814,
+      "step": 938
+    },
+    {
+      "epoch": 0.40560949298813376,
+      "grad_norm": 0.6079246401786804,
+      "learning_rate": 0.00016873315363881403,
+      "loss": 0.8868283629417419,
+      "step": 940
+    },
+    {
+      "epoch": 0.4064724919093851,
+      "grad_norm": 0.5326972603797913,
+      "learning_rate": 0.00016909254267744833,
+      "loss": 0.9938711524009705,
+      "step": 942
+    },
+    {
+      "epoch": 0.40733549083063647,
+      "grad_norm": 0.47754305601119995,
+      "learning_rate": 0.00016945193171608266,
+      "loss": 0.8280484676361084,
+      "step": 944
+    },
+    {
+      "epoch": 0.4081984897518878,
+      "grad_norm": 0.6683310270309448,
+      "learning_rate": 0.000169811320754717,
+      "loss": 1.089701533317566,
+      "step": 946
+    },
+    {
+      "epoch": 0.4090614886731392,
+      "grad_norm": 0.42798754572868347,
+      "learning_rate": 0.0001701707097933513,
+      "loss": 0.8535542488098145,
+      "step": 948
+    },
+    {
+      "epoch": 0.4099244875943905,
+      "grad_norm": 0.5999574065208435,
+      "learning_rate": 0.00017053009883198563,
+      "loss": 0.9039298295974731,
+      "step": 950
+    },
+    {
+      "epoch": 0.41078748651564184,
+      "grad_norm": 0.5752781629562378,
+      "learning_rate": 0.00017088948787061996,
+      "loss": 0.8786448240280151,
+      "step": 952
+    },
+    {
+      "epoch": 0.4116504854368932,
+      "grad_norm": 0.5121532678604126,
+      "learning_rate": 0.0001712488769092543,
+      "loss": 0.9206072688102722,
+      "step": 954
+    },
+    {
+      "epoch": 0.41251348435814456,
+      "grad_norm": 0.611078143119812,
+      "learning_rate": 0.0001716082659478886,
+      "loss": 0.9246986508369446,
+      "step": 956
+    },
+    {
+      "epoch": 0.4133764832793959,
+      "grad_norm": 0.5101020336151123,
+      "learning_rate": 0.00017196765498652292,
+      "loss": 0.9221894145011902,
+      "step": 958
+    },
+    {
+      "epoch": 0.41423948220064727,
+      "grad_norm": 0.5681450963020325,
+      "learning_rate": 0.00017232704402515725,
+      "loss": 0.9072799682617188,
+      "step": 960
+    },
+    {
+      "epoch": 0.41510248112189857,
+      "grad_norm": 0.47865498065948486,
+      "learning_rate": 0.00017268643306379155,
+      "loss": 0.9460896849632263,
+      "step": 962
+    },
+    {
+      "epoch": 0.4159654800431499,
+      "grad_norm": 0.49861401319503784,
+      "learning_rate": 0.00017304582210242588,
+      "loss": 0.9121519923210144,
+      "step": 964
+    },
+    {
+      "epoch": 0.4168284789644013,
+      "grad_norm": 0.43025892972946167,
+      "learning_rate": 0.0001734052111410602,
+      "loss": 0.8826848864555359,
+      "step": 966
+    },
+    {
+      "epoch": 0.41769147788565264,
+      "grad_norm": 0.4600491225719452,
+      "learning_rate": 0.00017376460017969454,
+      "loss": 0.8756251335144043,
+      "step": 968
+    },
+    {
+      "epoch": 0.418554476806904,
+      "grad_norm": 0.5297656059265137,
+      "learning_rate": 0.00017412398921832885,
+      "loss": 0.9171333312988281,
+      "step": 970
+    },
+    {
+      "epoch": 0.41941747572815535,
+      "grad_norm": 0.4906919002532959,
+      "learning_rate": 0.00017448337825696318,
+      "loss": 0.8887524008750916,
+      "step": 972
+    },
+    {
+      "epoch": 0.4202804746494067,
+      "grad_norm": 0.49263402819633484,
+      "learning_rate": 0.0001748427672955975,
+      "loss": 0.8345810174942017,
+      "step": 974
+    },
+    {
+      "epoch": 0.421143473570658,
+      "grad_norm": 0.5706565380096436,
+      "learning_rate": 0.0001752021563342318,
+      "loss": 0.968651294708252,
+      "step": 976
+    },
+    {
+      "epoch": 0.42200647249190937,
+      "grad_norm": 0.5269908308982849,
+      "learning_rate": 0.00017556154537286614,
+      "loss": 0.9729376435279846,
+      "step": 978
+    },
+    {
+      "epoch": 0.4228694714131607,
+      "grad_norm": 0.47058001160621643,
+      "learning_rate": 0.00017592093441150047,
+      "loss": 0.963884711265564,
+      "step": 980
+    },
+    {
+      "epoch": 0.4237324703344121,
+      "grad_norm": 0.5322962999343872,
+      "learning_rate": 0.0001762803234501348,
+      "loss": 0.8952447175979614,
+      "step": 982
+    },
+    {
+      "epoch": 0.42459546925566344,
+      "grad_norm": 0.5750975012779236,
+      "learning_rate": 0.0001766397124887691,
+      "loss": 0.8932783603668213,
+      "step": 984
+    },
+    {
+      "epoch": 0.4254584681769148,
+      "grad_norm": 0.5539655685424805,
+      "learning_rate": 0.00017699910152740343,
+      "loss": 0.916595458984375,
+      "step": 986
+    },
+    {
+      "epoch": 0.42632146709816615,
+      "grad_norm": 0.568000853061676,
+      "learning_rate": 0.00017735849056603776,
+      "loss": 0.9669626355171204,
+      "step": 988
+    },
+    {
+      "epoch": 0.42718446601941745,
+      "grad_norm": 0.6010684370994568,
+      "learning_rate": 0.00017771787960467206,
+      "loss": 1.0089105367660522,
+      "step": 990
+    },
+    {
+      "epoch": 0.4280474649406688,
+      "grad_norm": 0.6083462238311768,
+      "learning_rate": 0.0001780772686433064,
+      "loss": 0.9810921549797058,
+      "step": 992
+    },
+    {
+      "epoch": 0.42891046386192017,
+      "grad_norm": 0.5076655149459839,
+      "learning_rate": 0.0001784366576819407,
+      "loss": 0.9524372816085815,
+      "step": 994
+    },
+    {
+      "epoch": 0.4297734627831715,
+      "grad_norm": 0.5260922312736511,
+      "learning_rate": 0.00017879604672057503,
+      "loss": 0.881294846534729,
+      "step": 996
+    },
+    {
+      "epoch": 0.4306364617044229,
+      "grad_norm": 0.6130498051643372,
+      "learning_rate": 0.00017915543575920936,
+      "loss": 0.9138327836990356,
+      "step": 998
+    },
+    {
+      "epoch": 0.43149946062567424,
+      "grad_norm": 0.5346242785453796,
+      "learning_rate": 0.00017951482479784366,
+      "loss": 0.8861367106437683,
+      "step": 1000
+    },
+    {
+      "epoch": 0.43149946062567424,
+      "eval_loss": 0.9606748819351196,
+      "eval_runtime": 655.4358,
+      "eval_samples_per_second": 3.143,
+      "eval_steps_per_second": 3.143,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4323624595469256,
+      "grad_norm": 0.5977228879928589,
+      "learning_rate": 0.000179874213836478,
+      "loss": 0.8711628913879395,
+      "step": 1002
+    },
+    {
+      "epoch": 0.4332254584681769,
+      "grad_norm": 0.5547866821289062,
+      "learning_rate": 0.00018023360287511232,
+      "loss": 0.9393253326416016,
+      "step": 1004
+    },
+    {
+      "epoch": 0.43408845738942825,
+      "grad_norm": 0.536856472492218,
+      "learning_rate": 0.00018059299191374662,
+      "loss": 0.9486003518104553,
+      "step": 1006
+    },
+    {
+      "epoch": 0.4349514563106796,
+      "grad_norm": 0.4769814610481262,
+      "learning_rate": 0.00018095238095238095,
+      "loss": 0.9042052030563354,
+      "step": 1008
+    },
+    {
+      "epoch": 0.43581445523193096,
+      "grad_norm": 0.5554604530334473,
+      "learning_rate": 0.00018131176999101528,
+      "loss": 0.978546142578125,
+      "step": 1010
+    },
+    {
+      "epoch": 0.4366774541531823,
+      "grad_norm": 0.5112947225570679,
+      "learning_rate": 0.00018167115902964959,
+      "loss": 0.8382073640823364,
+      "step": 1012
+    },
+    {
+      "epoch": 0.4375404530744337,
+      "grad_norm": 0.45194941759109497,
+      "learning_rate": 0.00018203054806828392,
+      "loss": 0.8577026724815369,
+      "step": 1014
+    },
+    {
+      "epoch": 0.438403451995685,
+      "grad_norm": 0.5115043520927429,
+      "learning_rate": 0.00018238993710691825,
+      "loss": 0.8517863154411316,
+      "step": 1016
+    },
+    {
+      "epoch": 0.43926645091693634,
+      "grad_norm": 0.5485050082206726,
+      "learning_rate": 0.00018274932614555258,
+      "loss": 0.9597266912460327,
+      "step": 1018
+    },
+    {
+      "epoch": 0.4401294498381877,
+      "grad_norm": 0.5742959976196289,
+      "learning_rate": 0.00018310871518418688,
+      "loss": 1.0407187938690186,
+      "step": 1020
+    },
+    {
+      "epoch": 0.44099244875943905,
+      "grad_norm": 0.44870051741600037,
+      "learning_rate": 0.0001834681042228212,
+      "loss": 0.8696310520172119,
+      "step": 1022
+    },
+    {
+      "epoch": 0.4418554476806904,
+      "grad_norm": 0.5179623961448669,
+      "learning_rate": 0.00018382749326145554,
+      "loss": 0.9673634767532349,
+      "step": 1024
+    },
+    {
+      "epoch": 0.44271844660194176,
+      "grad_norm": 0.5404779314994812,
+      "learning_rate": 0.00018418688230008984,
+      "loss": 0.9596615433692932,
+      "step": 1026
+    },
+    {
+      "epoch": 0.4435814455231931,
+      "grad_norm": 0.47766315937042236,
+      "learning_rate": 0.00018454627133872417,
+      "loss": 0.8483878970146179,
+      "step": 1028
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.503380537033081,
+      "learning_rate": 0.0001849056603773585,
+      "loss": 0.9330979585647583,
+      "step": 1030
+    },
+    {
+      "epoch": 0.4453074433656958,
+      "grad_norm": 0.6129396557807922,
+      "learning_rate": 0.00018526504941599283,
+      "loss": 0.9341012239456177,
+      "step": 1032
+    },
+    {
+      "epoch": 0.44617044228694713,
+      "grad_norm": 0.4497876465320587,
+      "learning_rate": 0.00018562443845462713,
+      "loss": 0.9139068126678467,
+      "step": 1034
+    },
+    {
+      "epoch": 0.4470334412081985,
+      "grad_norm": 0.5369747281074524,
+      "learning_rate": 0.00018598382749326146,
+      "loss": 0.8874827027320862,
+      "step": 1036
+    },
+    {
+      "epoch": 0.44789644012944985,
+      "grad_norm": 0.5947322845458984,
+      "learning_rate": 0.0001863432165318958,
+      "loss": 0.9653725028038025,
+      "step": 1038
+    },
+    {
+      "epoch": 0.4487594390507012,
+      "grad_norm": 0.6649987101554871,
+      "learning_rate": 0.0001867026055705301,
+      "loss": 0.9553119540214539,
+      "step": 1040
+    },
+    {
+      "epoch": 0.44962243797195256,
+      "grad_norm": 0.5369387269020081,
+      "learning_rate": 0.00018706199460916443,
+      "loss": 0.904233992099762,
+      "step": 1042
+    },
+    {
+      "epoch": 0.45048543689320386,
+      "grad_norm": 0.4956842362880707,
+      "learning_rate": 0.00018742138364779876,
+      "loss": 0.8837952017784119,
+      "step": 1044
+    },
+    {
+      "epoch": 0.4513484358144552,
+      "grad_norm": 0.48045051097869873,
+      "learning_rate": 0.0001877807726864331,
+      "loss": 0.8964687585830688,
+      "step": 1046
+    },
+    {
+      "epoch": 0.4522114347357066,
+      "grad_norm": 0.4925530254840851,
+      "learning_rate": 0.0001881401617250674,
+      "loss": 0.9105878472328186,
+      "step": 1048
+    },
+    {
+      "epoch": 0.45307443365695793,
+      "grad_norm": 0.5131362080574036,
+      "learning_rate": 0.00018849955076370172,
+      "loss": 0.96272873878479,
+      "step": 1050
+    },
+    {
+      "epoch": 0.4539374325782093,
+      "grad_norm": 0.435739129781723,
+      "learning_rate": 0.00018885893980233605,
+      "loss": 0.8796783685684204,
+      "step": 1052
+    },
+    {
+      "epoch": 0.45480043149946064,
+      "grad_norm": 0.500938892364502,
+      "learning_rate": 0.00018921832884097035,
+      "loss": 0.9463814496994019,
+      "step": 1054
+    },
+    {
+      "epoch": 0.455663430420712,
+      "grad_norm": 0.4769900143146515,
+      "learning_rate": 0.00018957771787960468,
+      "loss": 0.9030335545539856,
+      "step": 1056
+    },
+    {
+      "epoch": 0.4565264293419633,
+      "grad_norm": 0.49585285782814026,
+      "learning_rate": 0.00018993710691823901,
+      "loss": 0.986995279788971,
+      "step": 1058
+    },
+    {
+      "epoch": 0.45738942826321466,
+      "grad_norm": 0.5875195264816284,
+      "learning_rate": 0.00019029649595687334,
+      "loss": 0.9297246932983398,
+      "step": 1060
+    },
+    {
+      "epoch": 0.458252427184466,
+      "grad_norm": 0.5552583932876587,
+      "learning_rate": 0.00019065588499550765,
+      "loss": 1.005869746208191,
+      "step": 1062
+    },
+    {
+      "epoch": 0.4591154261057174,
+      "grad_norm": 0.49282076954841614,
+      "learning_rate": 0.00019101527403414198,
+      "loss": 0.8949927091598511,
+      "step": 1064
+    },
+    {
+      "epoch": 0.45997842502696873,
+      "grad_norm": 0.4951777160167694,
+      "learning_rate": 0.0001913746630727763,
+      "loss": 0.9997886419296265,
+      "step": 1066
+    },
+    {
+      "epoch": 0.4608414239482201,
+      "grad_norm": 0.5154827237129211,
+      "learning_rate": 0.0001917340521114106,
+      "loss": 0.9532123804092407,
+      "step": 1068
+    },
+    {
+      "epoch": 0.4617044228694714,
+      "grad_norm": 0.5547500252723694,
+      "learning_rate": 0.00019209344115004494,
+      "loss": 0.8959843516349792,
+      "step": 1070
+    },
+    {
+      "epoch": 0.46256742179072274,
+      "grad_norm": 0.500188946723938,
+      "learning_rate": 0.00019245283018867927,
+      "loss": 0.8201484680175781,
+      "step": 1072
+    },
+    {
+      "epoch": 0.4634304207119741,
+      "grad_norm": 0.4181794822216034,
+      "learning_rate": 0.00019281221922731357,
+      "loss": 0.8255136609077454,
+      "step": 1074
+    },
+    {
+      "epoch": 0.46429341963322546,
+      "grad_norm": 0.5613874197006226,
+      "learning_rate": 0.0001931716082659479,
+      "loss": 0.896024763584137,
+      "step": 1076
+    },
+    {
+      "epoch": 0.4651564185544768,
+      "grad_norm": 0.5000972151756287,
+      "learning_rate": 0.0001935309973045822,
+      "loss": 0.8831873536109924,
+      "step": 1078
+    },
+    {
+      "epoch": 0.46601941747572817,
+      "grad_norm": 0.6321820616722107,
+      "learning_rate": 0.00019389038634321654,
+      "loss": 0.9787988662719727,
+      "step": 1080
+    },
+    {
+      "epoch": 0.4668824163969795,
+      "grad_norm": 0.4843652546405792,
+      "learning_rate": 0.00019424977538185087,
+      "loss": 0.933361828327179,
+      "step": 1082
+    },
+    {
+      "epoch": 0.46774541531823083,
+      "grad_norm": 0.537330150604248,
+      "learning_rate": 0.00019460916442048517,
+      "loss": 0.9046981334686279,
+      "step": 1084
+    },
+    {
+      "epoch": 0.4686084142394822,
+      "grad_norm": 0.5761371850967407,
+      "learning_rate": 0.0001949685534591195,
+      "loss": 0.9625781178474426,
+      "step": 1086
+    },
+    {
+      "epoch": 0.46947141316073354,
+      "grad_norm": 0.5209522843360901,
+      "learning_rate": 0.00019532794249775383,
+      "loss": 0.9280619025230408,
+      "step": 1088
+    },
+    {
+      "epoch": 0.4703344120819849,
+      "grad_norm": 0.5383933186531067,
+      "learning_rate": 0.00019568733153638813,
+      "loss": 0.8236247301101685,
+      "step": 1090
+    },
+    {
+      "epoch": 0.47119741100323626,
+      "grad_norm": 0.4994274377822876,
+      "learning_rate": 0.00019604672057502246,
+      "loss": 0.9404071569442749,
+      "step": 1092
+    },
+    {
+      "epoch": 0.4720604099244876,
+      "grad_norm": 0.5177807211875916,
+      "learning_rate": 0.0001964061096136568,
+      "loss": 0.8517536520957947,
+      "step": 1094
+    },
+    {
+      "epoch": 0.47292340884573897,
+      "grad_norm": 0.5374870896339417,
+      "learning_rate": 0.00019676549865229112,
+      "loss": 0.8214367032051086,
+      "step": 1096
+    },
+    {
+      "epoch": 0.47378640776699027,
+      "grad_norm": 0.5544074177742004,
+      "learning_rate": 0.00019712488769092542,
+      "loss": 1.016176700592041,
+      "step": 1098
+    },
+    {
+      "epoch": 0.4746494066882416,
+      "grad_norm": 0.5125867128372192,
+      "learning_rate": 0.00019748427672955975,
+      "loss": 0.8425421118736267,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4746494066882416,
+      "eval_loss": 0.944629430770874,
+      "eval_runtime": 649.9107,
+      "eval_samples_per_second": 3.17,
+      "eval_steps_per_second": 3.17,
+      "step": 1100
+    },
+    {
+      "epoch": 0.475512405609493,
+      "grad_norm": 0.5204418897628784,
+      "learning_rate": 0.00019784366576819408,
+      "loss": 0.9444556832313538,
+      "step": 1102
+    },
+    {
+      "epoch": 0.47637540453074434,
+      "grad_norm": 0.46085885167121887,
+      "learning_rate": 0.0001982030548068284,
+      "loss": 0.877082109451294,
+      "step": 1104
+    },
+    {
+      "epoch": 0.4772384034519957,
+      "grad_norm": 0.5269598960876465,
+      "learning_rate": 0.00019856244384546272,
+      "loss": 0.9214640259742737,
+      "step": 1106
+    },
+    {
+      "epoch": 0.47810140237324705,
+      "grad_norm": 0.4894753694534302,
+      "learning_rate": 0.00019892183288409705,
+      "loss": 0.8867175579071045,
+      "step": 1108
+    },
+    {
+      "epoch": 0.47896440129449835,
+      "grad_norm": 0.5204115509986877,
+      "learning_rate": 0.00019928122192273138,
+      "loss": 0.9641162753105164,
+      "step": 1110
+    },
+    {
+      "epoch": 0.4798274002157497,
+      "grad_norm": 0.6399031281471252,
+      "learning_rate": 0.00019964061096136568,
+      "loss": 1.0219199657440186,
+      "step": 1112
+    },
+    {
+      "epoch": 0.48069039913700107,
+      "grad_norm": 0.3979159891605377,
+      "learning_rate": 0.0002,
+      "loss": 0.8189998269081116,
+      "step": 1114
+    },
+    {
+      "epoch": 0.4815533980582524,
+      "grad_norm": 0.4782681465148926,
+      "learning_rate": 0.0001999999879427254,
+      "loss": 0.83241868019104,
+      "step": 1116
+    },
+    {
+      "epoch": 0.4824163969795038,
+      "grad_norm": 0.5235620141029358,
+      "learning_rate": 0.00019999995177090454,
+      "loss": 0.9371466636657715,
+      "step": 1118
+    },
+    {
+      "epoch": 0.48327939590075514,
+      "grad_norm": 0.4543023407459259,
+      "learning_rate": 0.00019999989148454606,
+      "loss": 0.7767758369445801,
+      "step": 1120
+    },
+    {
+      "epoch": 0.4841423948220065,
+      "grad_norm": 0.6191229820251465,
+      "learning_rate": 0.00019999980708366457,
+      "loss": 1.0103063583374023,
+      "step": 1122
+    },
+    {
+      "epoch": 0.4850053937432578,
+      "grad_norm": 0.45392486453056335,
+      "learning_rate": 0.00019999969856828042,
+      "loss": 0.8720875382423401,
+      "step": 1124
+    },
+    {
+      "epoch": 0.48586839266450915,
+      "grad_norm": 0.42748701572418213,
+      "learning_rate": 0.00019999956593841974,
+      "loss": 0.7859150171279907,
+      "step": 1126
+    },
+    {
+      "epoch": 0.4867313915857605,
+      "grad_norm": 0.4952569603919983,
+      "learning_rate": 0.00019999940919411454,
+      "loss": 0.9154419898986816,
+      "step": 1128
+    },
+    {
+      "epoch": 0.48759439050701187,
+      "grad_norm": 0.5522173047065735,
+      "learning_rate": 0.00019999922833540264,
+      "loss": 0.9076330065727234,
+      "step": 1130
+    },
+    {
+      "epoch": 0.4884573894282632,
+      "grad_norm": 0.5355855226516724,
+      "learning_rate": 0.00019999902336232758,
+      "loss": 0.8933543562889099,
+      "step": 1132
+    },
+    {
+      "epoch": 0.4893203883495146,
+      "grad_norm": 0.4613489508628845,
+      "learning_rate": 0.00019999879427493885,
+      "loss": 0.9160735607147217,
+      "step": 1134
+    },
+    {
+      "epoch": 0.49018338727076594,
+      "grad_norm": 0.4758962094783783,
+      "learning_rate": 0.0001999985410732917,
+      "loss": 0.8552446961402893,
+      "step": 1136
+    },
+    {
+      "epoch": 0.49104638619201724,
+      "grad_norm": 0.4549376964569092,
+      "learning_rate": 0.00019999826375744715,
+      "loss": 0.9979530572891235,
+      "step": 1138
+    },
+    {
+      "epoch": 0.4919093851132686,
+      "grad_norm": 0.4363284409046173,
+      "learning_rate": 0.0001999979623274721,
+      "loss": 0.9295380115509033,
+      "step": 1140
+    },
+    {
+      "epoch": 0.49277238403451995,
+      "grad_norm": 0.5090877413749695,
+      "learning_rate": 0.0001999976367834392,
+      "loss": 0.8737252950668335,
+      "step": 1142
+    },
+    {
+      "epoch": 0.4936353829557713,
+      "grad_norm": 0.45340779423713684,
+      "learning_rate": 0.000199997287125427,
+      "loss": 0.8312779068946838,
+      "step": 1144
+    },
+    {
+      "epoch": 0.49449838187702266,
+      "grad_norm": 0.4771472215652466,
+      "learning_rate": 0.0001999969133535198,
+      "loss": 0.9105207324028015,
+      "step": 1146
+    },
+    {
+      "epoch": 0.495361380798274,
+      "grad_norm": 0.5251384377479553,
+      "learning_rate": 0.00019999651546780773,
+      "loss": 0.8578172922134399,
+      "step": 1148
+    },
+    {
+      "epoch": 0.4962243797195254,
+      "grad_norm": 0.49128198623657227,
+      "learning_rate": 0.00019999609346838676,
+      "loss": 0.9193941950798035,
+      "step": 1150
+    },
+    {
+      "epoch": 0.4970873786407767,
+      "grad_norm": 0.5558596849441528,
+      "learning_rate": 0.0001999956473553586,
+      "loss": 0.9141314625740051,
+      "step": 1152
+    },
+    {
+      "epoch": 0.49795037756202803,
+      "grad_norm": 0.45872750878334045,
+      "learning_rate": 0.00019999517712883087,
+      "loss": 0.9058388471603394,
+      "step": 1154
+    },
+    {
+      "epoch": 0.4988133764832794,
+      "grad_norm": 0.4710173010826111,
+      "learning_rate": 0.00019999468278891698,
+      "loss": 0.8462487459182739,
+      "step": 1156
+    },
+    {
+      "epoch": 0.49967637540453075,
+      "grad_norm": 0.4805637001991272,
+      "learning_rate": 0.0001999941643357361,
+      "loss": 0.8960906863212585,
+      "step": 1158
+    },
+    {
+      "epoch": 0.5005393743257821,
+      "grad_norm": 0.5108052492141724,
+      "learning_rate": 0.00019999362176941325,
+      "loss": 0.9074980020523071,
+      "step": 1160
+    },
+    {
+      "epoch": 0.5014023732470334,
+      "grad_norm": 0.49572333693504333,
+      "learning_rate": 0.00019999305509007932,
+      "loss": 0.9710080623626709,
+      "step": 1162
+    },
+    {
+      "epoch": 0.5022653721682848,
+      "grad_norm": 0.5304561257362366,
+      "learning_rate": 0.0001999924642978709,
+      "loss": 0.8877825140953064,
+      "step": 1164
+    },
+    {
+      "epoch": 0.5031283710895361,
+      "grad_norm": 0.5007328391075134,
+      "learning_rate": 0.0001999918493929305,
+      "loss": 0.8955381512641907,
+      "step": 1166
+    },
+    {
+      "epoch": 0.5039913700107875,
+      "grad_norm": 0.569549024105072,
+      "learning_rate": 0.0001999912103754064,
+      "loss": 0.9478562474250793,
+      "step": 1168
+    },
+    {
+      "epoch": 0.5048543689320388,
+      "grad_norm": 0.5354957580566406,
+      "learning_rate": 0.00019999054724545264,
+      "loss": 0.9685383439064026,
+      "step": 1170
+    },
+    {
+      "epoch": 0.5057173678532901,
+      "grad_norm": 0.547788143157959,
+      "learning_rate": 0.00019998986000322917,
+      "loss": 0.9221975207328796,
+      "step": 1172
+    },
+    {
+      "epoch": 0.5065803667745415,
+      "grad_norm": 0.4919529855251312,
+      "learning_rate": 0.00019998914864890175,
+      "loss": 0.9104788303375244,
+      "step": 1174
+    },
+    {
+      "epoch": 0.5074433656957928,
+      "grad_norm": 0.5274141430854797,
+      "learning_rate": 0.00019998841318264187,
+      "loss": 0.9176050424575806,
+      "step": 1176
+    },
+    {
+      "epoch": 0.5083063646170443,
+      "grad_norm": 0.4257420301437378,
+      "learning_rate": 0.00019998765360462688,
+      "loss": 0.8389710187911987,
+      "step": 1178
+    },
+    {
+      "epoch": 0.5091693635382956,
+      "grad_norm": 0.4947778880596161,
+      "learning_rate": 0.00019998686991504002,
+      "loss": 1.0164397954940796,
+      "step": 1180
+    },
+    {
+      "epoch": 0.510032362459547,
+      "grad_norm": 0.5540821552276611,
+      "learning_rate": 0.00019998606211407016,
+      "loss": 0.9900994300842285,
+      "step": 1182
+    },
+    {
+      "epoch": 0.5108953613807983,
+      "grad_norm": 0.4793289601802826,
+      "learning_rate": 0.0001999852302019122,
+      "loss": 0.8797636032104492,
+      "step": 1184
+    },
+    {
+      "epoch": 0.5117583603020496,
+      "grad_norm": 0.47429659962654114,
+      "learning_rate": 0.00019998437417876672,
+      "loss": 0.96225905418396,
+      "step": 1186
+    },
+    {
+      "epoch": 0.512621359223301,
+      "grad_norm": 0.44918450713157654,
+      "learning_rate": 0.00019998349404484013,
+      "loss": 0.8604235649108887,
+      "step": 1188
+    },
+    {
+      "epoch": 0.5134843581445523,
+      "grad_norm": 0.566977858543396,
+      "learning_rate": 0.00019998258980034468,
+      "loss": 1.0325366258621216,
+      "step": 1190
+    },
+    {
+      "epoch": 0.5143473570658037,
+      "grad_norm": 0.4671999514102936,
+      "learning_rate": 0.00019998166144549843,
+      "loss": 0.7658900022506714,
+      "step": 1192
+    },
+    {
+      "epoch": 0.515210355987055,
+      "grad_norm": 0.42312702536582947,
+      "learning_rate": 0.00019998070898052521,
+      "loss": 0.9365432858467102,
+      "step": 1194
+    },
+    {
+      "epoch": 0.5160733549083064,
+      "grad_norm": 0.4652721881866455,
+      "learning_rate": 0.00019997973240565476,
+      "loss": 0.771016538143158,
+      "step": 1196
+    },
+    {
+      "epoch": 0.5169363538295577,
+      "grad_norm": 0.5048499703407288,
+      "learning_rate": 0.00019997873172112254,
+      "loss": 0.9123705625534058,
+      "step": 1198
+    },
+    {
+      "epoch": 0.517799352750809,
+      "grad_norm": 0.5446439981460571,
+      "learning_rate": 0.0001999777069271699,
+      "loss": 0.8975751399993896,
+      "step": 1200
+    },
+    {
+      "epoch": 0.517799352750809,
+      "eval_loss": 0.9344067573547363,
+      "eval_runtime": 658.6934,
+      "eval_samples_per_second": 3.127,
+      "eval_steps_per_second": 3.127,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5186623516720604,
+      "grad_norm": 0.5044088959693909,
+      "learning_rate": 0.0001999766580240439,
+      "loss": 0.89097660779953,
+      "step": 1202
+    },
+    {
+      "epoch": 0.5195253505933117,
+      "grad_norm": 0.4672294855117798,
+      "learning_rate": 0.00019997558501199753,
+      "loss": 0.9138525128364563,
+      "step": 1204
+    },
+    {
+      "epoch": 0.5203883495145631,
+      "grad_norm": 0.45749008655548096,
+      "learning_rate": 0.00019997448789128952,
+      "loss": 0.8946340680122375,
+      "step": 1206
+    },
+    {
+      "epoch": 0.5212513484358144,
+      "grad_norm": 0.4828707277774811,
+      "learning_rate": 0.00019997336666218447,
+      "loss": 0.8661436438560486,
+      "step": 1208
+    },
+    {
+      "epoch": 0.5221143473570659,
+      "grad_norm": 0.3975147008895874,
+      "learning_rate": 0.0001999722213249527,
+      "loss": 0.7684835195541382,
+      "step": 1210
+    },
+    {
+      "epoch": 0.5229773462783172,
+      "grad_norm": 0.5642077326774597,
+      "learning_rate": 0.00019997105187987045,
+      "loss": 0.9667536616325378,
+      "step": 1212
+    },
+    {
+      "epoch": 0.5238403451995685,
+      "grad_norm": 0.4907105565071106,
+      "learning_rate": 0.00019996985832721972,
+      "loss": 0.8679366707801819,
+      "step": 1214
+    },
+    {
+      "epoch": 0.5247033441208199,
+      "grad_norm": 0.46214789152145386,
+      "learning_rate": 0.0001999686406672883,
+      "loss": 0.8802784085273743,
+      "step": 1216
+    },
+    {
+      "epoch": 0.5255663430420712,
+      "grad_norm": 0.4355131685733795,
+      "learning_rate": 0.00019996739890036985,
+      "loss": 0.8493598103523254,
+      "step": 1218
+    },
+    {
+      "epoch": 0.5264293419633226,
+      "grad_norm": 0.4293915331363678,
+      "learning_rate": 0.0001999661330267638,
+      "loss": 0.8949980735778809,
+      "step": 1220
+    },
+    {
+      "epoch": 0.5272923408845739,
+      "grad_norm": 0.5452485680580139,
+      "learning_rate": 0.00019996484304677544,
+      "loss": 0.9497376680374146,
+      "step": 1222
+    },
+    {
+      "epoch": 0.5281553398058253,
+      "grad_norm": 0.45874500274658203,
+      "learning_rate": 0.00019996352896071583,
+      "loss": 0.9170818328857422,
+      "step": 1224
+    },
+    {
+      "epoch": 0.5290183387270766,
+      "grad_norm": 0.4414025843143463,
+      "learning_rate": 0.00019996219076890182,
+      "loss": 0.7557252645492554,
+      "step": 1226
+    },
+    {
+      "epoch": 0.5298813376483279,
+      "grad_norm": 0.4891829192638397,
+      "learning_rate": 0.0001999608284716562,
+      "loss": 0.848960816860199,
+      "step": 1228
+    },
+    {
+      "epoch": 0.5307443365695793,
+      "grad_norm": 0.5048345327377319,
+      "learning_rate": 0.00019995944206930734,
+      "loss": 0.9555954933166504,
+      "step": 1230
+    },
+    {
+      "epoch": 0.5316073354908306,
+      "grad_norm": 0.5006756782531738,
+      "learning_rate": 0.00019995803156218968,
+      "loss": 0.8080939054489136,
+      "step": 1232
+    },
+    {
+      "epoch": 0.532470334412082,
+      "grad_norm": 0.5422173738479614,
+      "learning_rate": 0.00019995659695064332,
+      "loss": 0.8638371825218201,
+      "step": 1234
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.4535163640975952,
+      "learning_rate": 0.0001999551382350142,
+      "loss": 0.889068067073822,
+      "step": 1236
+    },
+    {
+      "epoch": 0.5341963322545846,
+      "grad_norm": 0.4588642418384552,
+      "learning_rate": 0.00019995365541565412,
+      "loss": 0.8803121447563171,
+      "step": 1238
+    },
+    {
+      "epoch": 0.535059331175836,
+      "grad_norm": 0.49366191029548645,
+      "learning_rate": 0.00019995214849292064,
+      "loss": 0.9694926738739014,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5359223300970873,
+      "grad_norm": 0.41988301277160645,
+      "learning_rate": 0.0001999506174671771,
+      "loss": 0.8367960453033447,
+      "step": 1242
+    },
+    {
+      "epoch": 0.5367853290183388,
+      "grad_norm": 0.5242130160331726,
+      "learning_rate": 0.00019994906233879273,
+      "loss": 0.942340612411499,
+      "step": 1244
+    },
+    {
+      "epoch": 0.53764832793959,
+      "grad_norm": 0.4899834096431732,
+      "learning_rate": 0.00019994748310814256,
+      "loss": 0.8926790356636047,
+      "step": 1246
+    },
+    {
+      "epoch": 0.5385113268608415,
+      "grad_norm": 0.5496823787689209,
+      "learning_rate": 0.00019994587977560744,
+      "loss": 0.99891597032547,
+      "step": 1248
+    },
+    {
+      "epoch": 0.5393743257820928,
+      "grad_norm": 0.4497414231300354,
+      "learning_rate": 0.00019994425234157396,
+      "loss": 0.8873116970062256,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5402373247033441,
+      "grad_norm": 0.4256928563117981,
+      "learning_rate": 0.00019994260080643454,
+      "loss": 0.9041396975517273,
+      "step": 1252
+    },
+    {
+      "epoch": 0.5411003236245955,
+      "grad_norm": 0.36910608410835266,
+      "learning_rate": 0.00019994092517058753,
+      "loss": 0.7647561430931091,
+      "step": 1254
+    },
+    {
+      "epoch": 0.5419633225458468,
+      "grad_norm": 0.537584125995636,
+      "learning_rate": 0.0001999392254344369,
+      "loss": 0.8892287015914917,
+      "step": 1256
+    },
+    {
+      "epoch": 0.5428263214670982,
+      "grad_norm": 0.49463894963264465,
+      "learning_rate": 0.00019993750159839264,
+      "loss": 0.8638571500778198,
+      "step": 1258
+    },
+    {
+      "epoch": 0.5436893203883495,
+      "grad_norm": 0.5052056908607483,
+      "learning_rate": 0.00019993575366287036,
+      "loss": 0.8165372014045715,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5445523193096009,
+      "grad_norm": 0.47367510199546814,
+      "learning_rate": 0.0001999339816282916,
+      "loss": 0.9099977016448975,
+      "step": 1262
+    },
+    {
+      "epoch": 0.5454153182308522,
+      "grad_norm": 0.4600350558757782,
+      "learning_rate": 0.00019993218549508364,
+      "loss": 0.8557311296463013,
+      "step": 1264
+    },
+    {
+      "epoch": 0.5462783171521035,
+      "grad_norm": 0.5684534311294556,
+      "learning_rate": 0.0001999303652636797,
+      "loss": 0.9136497974395752,
+      "step": 1266
+    },
+    {
+      "epoch": 0.5471413160733549,
+      "grad_norm": 0.5151359438896179,
+      "learning_rate": 0.00019992852093451865,
+      "loss": 0.7906932830810547,
+      "step": 1268
+    },
+    {
+      "epoch": 0.5480043149946062,
+      "grad_norm": 0.48577409982681274,
+      "learning_rate": 0.00019992665250804525,
+      "loss": 0.9326766133308411,
+      "step": 1270
+    },
+    {
+      "epoch": 0.5488673139158576,
+      "grad_norm": 0.490531325340271,
+      "learning_rate": 0.00019992475998471004,
+      "loss": 0.9734495878219604,
+      "step": 1272
+    },
+    {
+      "epoch": 0.5497303128371089,
+      "grad_norm": 0.5092435479164124,
+      "learning_rate": 0.00019992284336496947,
+      "loss": 0.8728410005569458,
+      "step": 1274
+    },
+    {
+      "epoch": 0.5505933117583603,
+      "grad_norm": 0.3843296766281128,
+      "learning_rate": 0.00019992090264928566,
+      "loss": 0.7572637796401978,
+      "step": 1276
+    },
+    {
+      "epoch": 0.5514563106796116,
+      "grad_norm": 0.534304678440094,
+      "learning_rate": 0.00019991893783812662,
+      "loss": 0.8895323872566223,
+      "step": 1278
+    },
+    {
+      "epoch": 0.552319309600863,
+      "grad_norm": 0.4567227363586426,
+      "learning_rate": 0.00019991694893196614,
+      "loss": 0.9318088293075562,
+      "step": 1280
+    },
+    {
+      "epoch": 0.5531823085221144,
+      "grad_norm": 0.48464900255203247,
+      "learning_rate": 0.0001999149359312839,
+      "loss": 0.8541979789733887,
+      "step": 1282
+    },
+    {
+      "epoch": 0.5540453074433657,
+      "grad_norm": 0.5569567084312439,
+      "learning_rate": 0.00019991289883656524,
+      "loss": 0.977894127368927,
+      "step": 1284
+    },
+    {
+      "epoch": 0.5549083063646171,
+      "grad_norm": 0.4637227952480316,
+      "learning_rate": 0.00019991083764830145,
+      "loss": 0.8860608339309692,
+      "step": 1286
+    },
+    {
+      "epoch": 0.5557713052858684,
+      "grad_norm": 0.4096687436103821,
+      "learning_rate": 0.00019990875236698956,
+      "loss": 0.8429648876190186,
+      "step": 1288
+    },
+    {
+      "epoch": 0.5566343042071198,
+      "grad_norm": 0.5221695303916931,
+      "learning_rate": 0.00019990664299313242,
+      "loss": 0.8510909080505371,
+      "step": 1290
+    },
+    {
+      "epoch": 0.5574973031283711,
+      "grad_norm": 0.5155899524688721,
+      "learning_rate": 0.00019990450952723872,
+      "loss": 0.8971074223518372,
+      "step": 1292
+    },
+    {
+      "epoch": 0.5583603020496224,
+      "grad_norm": 0.5064809322357178,
+      "learning_rate": 0.0001999023519698229,
+      "loss": 0.9030373096466064,
+      "step": 1294
+    },
+    {
+      "epoch": 0.5592233009708738,
+      "grad_norm": 0.40551698207855225,
+      "learning_rate": 0.00019990017032140526,
+      "loss": 0.7866057753562927,
+      "step": 1296
+    },
+    {
+      "epoch": 0.5600862998921251,
+      "grad_norm": 0.5009430050849915,
+      "learning_rate": 0.00019989796458251194,
+      "loss": 0.9477730989456177,
+      "step": 1298
+    },
+    {
+      "epoch": 0.5609492988133765,
+      "grad_norm": 0.5192028880119324,
+      "learning_rate": 0.00019989573475367477,
+      "loss": 0.9206778407096863,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5609492988133765,
+      "eval_loss": 0.9177446365356445,
+      "eval_runtime": 665.3245,
+      "eval_samples_per_second": 3.096,
+      "eval_steps_per_second": 3.096,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5618122977346278,
+      "grad_norm": 0.5580230951309204,
+      "learning_rate": 0.00019989348083543148,
+      "loss": 0.9516512155532837,
+      "step": 1302
+    },
+    {
+      "epoch": 0.5626752966558792,
+      "grad_norm": 0.4151005744934082,
+      "learning_rate": 0.00019989120282832564,
+      "loss": 0.7725991606712341,
+      "step": 1304
+    },
+    {
+      "epoch": 0.5635382955771305,
+      "grad_norm": 0.56330406665802,
+      "learning_rate": 0.00019988890073290656,
+      "loss": 0.9241501688957214,
+      "step": 1306
+    },
+    {
+      "epoch": 0.5644012944983818,
+      "grad_norm": 0.44836440682411194,
+      "learning_rate": 0.00019988657454972936,
+      "loss": 0.8351686000823975,
+      "step": 1308
+    },
+    {
+      "epoch": 0.5652642934196332,
+      "grad_norm": 0.5414754152297974,
+      "learning_rate": 0.00019988422427935496,
+      "loss": 0.9033217430114746,
+      "step": 1310
+    },
+    {
+      "epoch": 0.5661272923408845,
+      "grad_norm": 0.5283750891685486,
+      "learning_rate": 0.0001998818499223502,
+      "loss": 0.8885331153869629,
+      "step": 1312
+    },
+    {
+      "epoch": 0.566990291262136,
+      "grad_norm": 0.45846256613731384,
+      "learning_rate": 0.00019987945147928758,
+      "loss": 0.8359912037849426,
+      "step": 1314
+    },
+    {
+      "epoch": 0.5678532901833873,
+      "grad_norm": 0.44439879059791565,
+      "learning_rate": 0.0001998770289507455,
+      "loss": 0.8327895402908325,
+      "step": 1316
+    },
+    {
+      "epoch": 0.5687162891046387,
+      "grad_norm": 0.5491341948509216,
+      "learning_rate": 0.00019987458233730813,
+      "loss": 0.9354757070541382,
+      "step": 1318
+    },
+    {
+      "epoch": 0.56957928802589,
+      "grad_norm": 0.5502263307571411,
+      "learning_rate": 0.00019987211163956548,
+      "loss": 0.944054901599884,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5704422869471413,
+      "grad_norm": 0.47165682911872864,
+      "learning_rate": 0.00019986961685811334,
+      "loss": 0.9515072107315063,
+      "step": 1322
+    },
+    {
+      "epoch": 0.5713052858683927,
+      "grad_norm": 0.5136987566947937,
+      "learning_rate": 0.0001998670979935533,
+      "loss": 0.9455493688583374,
+      "step": 1324
+    },
+    {
+      "epoch": 0.572168284789644,
+      "grad_norm": 0.4822693169116974,
+      "learning_rate": 0.00019986455504649277,
+      "loss": 0.8626728057861328,
+      "step": 1326
+    },
+    {
+      "epoch": 0.5730312837108954,
+      "grad_norm": 0.4639468193054199,
+      "learning_rate": 0.000199861988017545,
+      "loss": 0.8857194781303406,
+      "step": 1328
+    },
+    {
+      "epoch": 0.5738942826321467,
+      "grad_norm": 0.5224950313568115,
+      "learning_rate": 0.00019985939690732898,
+      "loss": 0.9198446273803711,
+      "step": 1330
+    },
+    {
+      "epoch": 0.574757281553398,
+      "grad_norm": 0.47504499554634094,
+      "learning_rate": 0.00019985678171646954,
+      "loss": 0.8785439133644104,
+      "step": 1332
+    },
+    {
+      "epoch": 0.5756202804746494,
+      "grad_norm": 0.5022051930427551,
+      "learning_rate": 0.0001998541424455974,
+      "loss": 0.9593754410743713,
+      "step": 1334
+    },
+    {
+      "epoch": 0.5764832793959007,
+      "grad_norm": 0.4572875201702118,
+      "learning_rate": 0.00019985147909534897,
+      "loss": 0.986197292804718,
+      "step": 1336
+    },
+    {
+      "epoch": 0.5773462783171521,
+      "grad_norm": 0.5153827667236328,
+      "learning_rate": 0.00019984879166636644,
+      "loss": 0.9163863658905029,
+      "step": 1338
+    },
+    {
+      "epoch": 0.5782092772384034,
+      "grad_norm": 0.4813650846481323,
+      "learning_rate": 0.00019984608015929792,
+      "loss": 0.8815995454788208,
+      "step": 1340
+    },
+    {
+      "epoch": 0.5790722761596548,
+      "grad_norm": 0.4319819211959839,
+      "learning_rate": 0.0001998433445747973,
+      "loss": 0.857044517993927,
+      "step": 1342
+    },
+    {
+      "epoch": 0.5799352750809061,
+      "grad_norm": 0.5128870010375977,
+      "learning_rate": 0.00019984058491352423,
+      "loss": 0.8939256072044373,
+      "step": 1344
+    },
+    {
+      "epoch": 0.5807982740021574,
+      "grad_norm": 0.41450315713882446,
+      "learning_rate": 0.0001998378011761442,
+      "loss": 0.9267327785491943,
+      "step": 1346
+    },
+    {
+      "epoch": 0.5816612729234089,
+      "grad_norm": 0.42916348576545715,
+      "learning_rate": 0.00019983499336332844,
+      "loss": 0.8494639992713928,
+      "step": 1348
+    },
+    {
+      "epoch": 0.5825242718446602,
+      "grad_norm": 0.43995746970176697,
+      "learning_rate": 0.00019983216147575412,
+      "loss": 0.9720427989959717,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5833872707659116,
+      "grad_norm": 0.5063773989677429,
+      "learning_rate": 0.00019982930551410411,
+      "loss": 0.9400854706764221,
+      "step": 1352
+    },
+    {
+      "epoch": 0.5842502696871629,
+      "grad_norm": 0.5029586553573608,
+      "learning_rate": 0.0001998264254790671,
+      "loss": 0.8657845258712769,
+      "step": 1354
+    },
+    {
+      "epoch": 0.5851132686084143,
+      "grad_norm": 0.45519232749938965,
+      "learning_rate": 0.00019982352137133764,
+      "loss": 0.8593506813049316,
+      "step": 1356
+    },
+    {
+      "epoch": 0.5859762675296656,
+      "grad_norm": 0.49116215109825134,
+      "learning_rate": 0.000199820593191616,
+      "loss": 0.8658114671707153,
+      "step": 1358
+    },
+    {
+      "epoch": 0.5868392664509169,
+      "grad_norm": 0.45347318053245544,
+      "learning_rate": 0.00019981764094060826,
+      "loss": 0.8044605255126953,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5877022653721683,
+      "grad_norm": 0.5191754698753357,
+      "learning_rate": 0.00019981466461902643,
+      "loss": 0.9176861047744751,
+      "step": 1362
+    },
+    {
+      "epoch": 0.5885652642934196,
+      "grad_norm": 0.4791528284549713,
+      "learning_rate": 0.00019981166422758818,
+      "loss": 0.8453370928764343,
+      "step": 1364
+    },
+    {
+      "epoch": 0.589428263214671,
+      "grad_norm": 0.5105116367340088,
+      "learning_rate": 0.00019980863976701705,
+      "loss": 0.9343777298927307,
+      "step": 1366
+    },
+    {
+      "epoch": 0.5902912621359223,
+      "grad_norm": 0.44593656063079834,
+      "learning_rate": 0.00019980559123804236,
+      "loss": 0.8950760960578918,
+      "step": 1368
+    },
+    {
+      "epoch": 0.5911542610571737,
+      "grad_norm": 0.4375658631324768,
+      "learning_rate": 0.0001998025186413993,
+      "loss": 0.8613521456718445,
+      "step": 1370
+    },
+    {
+      "epoch": 0.592017259978425,
+      "grad_norm": 0.5138815641403198,
+      "learning_rate": 0.00019979942197782878,
+      "loss": 0.8982083201408386,
+      "step": 1372
+    },
+    {
+      "epoch": 0.5928802588996763,
+      "grad_norm": 0.45473602414131165,
+      "learning_rate": 0.00019979630124807753,
+      "loss": 0.9372450709342957,
+      "step": 1374
+    },
+    {
+      "epoch": 0.5937432578209277,
+      "grad_norm": 0.4961191713809967,
+      "learning_rate": 0.00019979315645289814,
+      "loss": 0.8758652806282043,
+      "step": 1376
+    },
+    {
+      "epoch": 0.594606256742179,
+      "grad_norm": 0.5672827363014221,
+      "learning_rate": 0.00019978998759304895,
+      "loss": 0.9852207899093628,
+      "step": 1378
+    },
+    {
+      "epoch": 0.5954692556634305,
+      "grad_norm": 0.44907906651496887,
+      "learning_rate": 0.00019978679466929407,
+      "loss": 0.8451287746429443,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5963322545846818,
+      "grad_norm": 0.4759652316570282,
+      "learning_rate": 0.00019978357768240352,
+      "loss": 0.8381558656692505,
+      "step": 1382
+    },
+    {
+      "epoch": 0.5971952535059332,
+      "grad_norm": 0.4936048686504364,
+      "learning_rate": 0.00019978033663315304,
+      "loss": 0.8820816874504089,
+      "step": 1384
+    },
+    {
+      "epoch": 0.5980582524271845,
+      "grad_norm": 0.44983741641044617,
+      "learning_rate": 0.00019977707152232416,
+      "loss": 0.9156787991523743,
+      "step": 1386
+    },
+    {
+      "epoch": 0.5989212513484358,
+      "grad_norm": 0.45198705792427063,
+      "learning_rate": 0.0001997737823507043,
+      "loss": 0.8285194039344788,
+      "step": 1388
+    },
+    {
+      "epoch": 0.5997842502696872,
+      "grad_norm": 0.45788463950157166,
+      "learning_rate": 0.00019977046911908664,
+      "loss": 0.8109505772590637,
+      "step": 1390
+    },
+    {
+      "epoch": 0.6006472491909385,
+      "grad_norm": 0.4795142412185669,
+      "learning_rate": 0.0001997671318282701,
+      "loss": 0.8285947442054749,
+      "step": 1392
+    },
+    {
+      "epoch": 0.6015102481121899,
+      "grad_norm": 0.5026728510856628,
+      "learning_rate": 0.00019976377047905945,
+      "loss": 0.9497535228729248,
+      "step": 1394
+    },
+    {
+      "epoch": 0.6023732470334412,
+      "grad_norm": 0.4994853734970093,
+      "learning_rate": 0.0001997603850722653,
+      "loss": 0.9171916246414185,
+      "step": 1396
+    },
+    {
+      "epoch": 0.6032362459546926,
+      "grad_norm": 0.4789866507053375,
+      "learning_rate": 0.00019975697560870403,
+      "loss": 0.7894434928894043,
+      "step": 1398
+    },
+    {
+      "epoch": 0.6040992448759439,
+      "grad_norm": 0.42282742261886597,
+      "learning_rate": 0.0001997535420891978,
+      "loss": 0.8942429423332214,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6040992448759439,
+      "eval_loss": 0.9080492854118347,
+      "eval_runtime": 661.4597,
+      "eval_samples_per_second": 3.114,
+      "eval_steps_per_second": 3.114,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6049622437971952,
+      "grad_norm": 0.5789905190467834,
+      "learning_rate": 0.00019975008451457454,
+      "loss": 0.8938372731208801,
+      "step": 1402
+    },
+    {
+      "epoch": 0.6058252427184466,
+      "grad_norm": 0.46121683716773987,
+      "learning_rate": 0.00019974660288566814,
+      "loss": 0.8746235370635986,
+      "step": 1404
+    },
+    {
+      "epoch": 0.6066882416396979,
+      "grad_norm": 0.5195551514625549,
+      "learning_rate": 0.00019974309720331807,
+      "loss": 0.8650617003440857,
+      "step": 1406
+    },
+    {
+      "epoch": 0.6075512405609493,
+      "grad_norm": 0.46930259466171265,
+      "learning_rate": 0.00019973956746836976,
+      "loss": 0.8853039145469666,
+      "step": 1408
+    },
+    {
+      "epoch": 0.6084142394822006,
+      "grad_norm": 0.40869632363319397,
+      "learning_rate": 0.0001997360136816744,
+      "loss": 0.7865594029426575,
+      "step": 1410
+    },
+    {
+      "epoch": 0.609277238403452,
+      "grad_norm": 0.5398361086845398,
+      "learning_rate": 0.00019973243584408895,
+      "loss": 0.907535970211029,
+      "step": 1412
+    },
+    {
+      "epoch": 0.6101402373247033,
+      "grad_norm": 0.5110154747962952,
+      "learning_rate": 0.00019972883395647615,
+      "loss": 0.8682730197906494,
+      "step": 1414
+    },
+    {
+      "epoch": 0.6110032362459547,
+      "grad_norm": 0.44484639167785645,
+      "learning_rate": 0.00019972520801970467,
+      "loss": 0.8786011338233948,
+      "step": 1416
+    },
+    {
+      "epoch": 0.6118662351672061,
+      "grad_norm": 0.4768071472644806,
+      "learning_rate": 0.0001997215580346488,
+      "loss": 0.9021878242492676,
+      "step": 1418
+    },
+    {
+      "epoch": 0.6127292340884574,
+      "grad_norm": 0.43265241384506226,
+      "learning_rate": 0.0001997178840021888,
+      "loss": 0.7737482786178589,
+      "step": 1420
+    },
+    {
+      "epoch": 0.6135922330097088,
+      "grad_norm": 0.525692343711853,
+      "learning_rate": 0.0001997141859232106,
+      "loss": 0.876280665397644,
+      "step": 1422
+    },
+    {
+      "epoch": 0.6144552319309601,
+      "grad_norm": 0.48206865787506104,
+      "learning_rate": 0.00019971046379860594,
+      "loss": 0.8503577709197998,
+      "step": 1424
+    },
+    {
+      "epoch": 0.6153182308522115,
+      "grad_norm": 0.6032769680023193,
+      "learning_rate": 0.00019970671762927246,
+      "loss": 0.9459730982780457,
+      "step": 1426
+    },
+    {
+      "epoch": 0.6161812297734628,
+      "grad_norm": 0.4491981863975525,
+      "learning_rate": 0.0001997029474161135,
+      "loss": 0.8836647868156433,
+      "step": 1428
+    },
+    {
+      "epoch": 0.6170442286947141,
+      "grad_norm": 0.47503358125686646,
+      "learning_rate": 0.00019969915316003824,
+      "loss": 0.8614388108253479,
+      "step": 1430
+    },
+    {
+      "epoch": 0.6179072276159655,
+      "grad_norm": 0.44801047444343567,
+      "learning_rate": 0.00019969533486196162,
+      "loss": 0.8420360684394836,
+      "step": 1432
+    },
+    {
+      "epoch": 0.6187702265372168,
+      "grad_norm": 0.45057111978530884,
+      "learning_rate": 0.00019969149252280446,
+      "loss": 0.8256269693374634,
+      "step": 1434
+    },
+    {
+      "epoch": 0.6196332254584682,
+      "grad_norm": 0.4589645266532898,
+      "learning_rate": 0.00019968762614349327,
+      "loss": 0.9130199551582336,
+      "step": 1436
+    },
+    {
+      "epoch": 0.6204962243797195,
+      "grad_norm": 0.48914027214050293,
+      "learning_rate": 0.00019968373572496045,
+      "loss": 0.74083012342453,
+      "step": 1438
+    },
+    {
+      "epoch": 0.6213592233009708,
+      "grad_norm": 0.4582098424434662,
+      "learning_rate": 0.00019967982126814412,
+      "loss": 0.8538379669189453,
+      "step": 1440
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.48722779750823975,
+      "learning_rate": 0.00019967588277398823,
+      "loss": 0.8780114054679871,
+      "step": 1442
+    },
+    {
+      "epoch": 0.6230852211434735,
+      "grad_norm": 0.4291327893733978,
+      "learning_rate": 0.00019967192024344254,
+      "loss": 0.8341028690338135,
+      "step": 1444
+    },
+    {
+      "epoch": 0.623948220064725,
+      "grad_norm": 0.4773139953613281,
+      "learning_rate": 0.00019966793367746265,
+      "loss": 0.8651667237281799,
+      "step": 1446
+    },
+    {
+      "epoch": 0.6248112189859762,
+      "grad_norm": 0.45556166768074036,
+      "learning_rate": 0.00019966392307700986,
+      "loss": 0.8339929580688477,
+      "step": 1448
+    },
+    {
+      "epoch": 0.6256742179072277,
+      "grad_norm": 0.5126671195030212,
+      "learning_rate": 0.00019965988844305129,
+      "loss": 0.9129340052604675,
+      "step": 1450
+    },
+    {
+      "epoch": 0.626537216828479,
+      "grad_norm": 0.6067109704017639,
+      "learning_rate": 0.00019965582977655988,
+      "loss": 0.9057610034942627,
+      "step": 1452
+    },
+    {
+      "epoch": 0.6274002157497303,
+      "grad_norm": 0.46425968408584595,
+      "learning_rate": 0.00019965174707851438,
+      "loss": 0.874100387096405,
+      "step": 1454
+    },
+    {
+      "epoch": 0.6282632146709817,
+      "grad_norm": 0.481077641248703,
+      "learning_rate": 0.0001996476403498993,
+      "loss": 0.915635347366333,
+      "step": 1456
+    },
+    {
+      "epoch": 0.629126213592233,
+      "grad_norm": 0.47299909591674805,
+      "learning_rate": 0.000199643509591705,
+      "loss": 0.9059650301933289,
+      "step": 1458
+    },
+    {
+      "epoch": 0.6299892125134844,
+      "grad_norm": 0.48924630880355835,
+      "learning_rate": 0.00019963935480492753,
+      "loss": 0.9775188565254211,
+      "step": 1460
+    },
+    {
+      "epoch": 0.6308522114347357,
+      "grad_norm": 0.4407665431499481,
+      "learning_rate": 0.0001996351759905688,
+      "loss": 0.8950685858726501,
+      "step": 1462
+    },
+    {
+      "epoch": 0.6317152103559871,
+      "grad_norm": 0.5018318295478821,
+      "learning_rate": 0.00019963097314963657,
+      "loss": 0.8532119989395142,
+      "step": 1464
+    },
+    {
+      "epoch": 0.6325782092772384,
+      "grad_norm": 0.43245720863342285,
+      "learning_rate": 0.0001996267462831443,
+      "loss": 0.7775963544845581,
+      "step": 1466
+    },
+    {
+      "epoch": 0.6334412081984897,
+      "grad_norm": 0.5028865337371826,
+      "learning_rate": 0.00019962249539211125,
+      "loss": 0.8315839767456055,
+      "step": 1468
+    },
+    {
+      "epoch": 0.6343042071197411,
+      "grad_norm": 0.4697185754776001,
+      "learning_rate": 0.0001996182204775626,
+      "loss": 0.849076509475708,
+      "step": 1470
+    },
+    {
+      "epoch": 0.6351672060409924,
+      "grad_norm": 0.46725034713745117,
+      "learning_rate": 0.00019961392154052912,
+      "loss": 0.8828577995300293,
+      "step": 1472
+    },
+    {
+      "epoch": 0.6360302049622438,
+      "grad_norm": 0.4301203489303589,
+      "learning_rate": 0.00019960959858204754,
+      "loss": 0.850115954875946,
+      "step": 1474
+    },
+    {
+      "epoch": 0.6368932038834951,
+      "grad_norm": 0.46635881066322327,
+      "learning_rate": 0.0001996052516031603,
+      "loss": 0.7912618517875671,
+      "step": 1476
+    },
+    {
+      "epoch": 0.6377562028047465,
+      "grad_norm": 0.44143620133399963,
+      "learning_rate": 0.00019960088060491565,
+      "loss": 0.9072504639625549,
+      "step": 1478
+    },
+    {
+      "epoch": 0.6386192017259978,
+      "grad_norm": 0.47458893060684204,
+      "learning_rate": 0.00019959648558836763,
+      "loss": 0.8976638317108154,
+      "step": 1480
+    },
+    {
+      "epoch": 0.6394822006472491,
+      "grad_norm": 0.4596816897392273,
+      "learning_rate": 0.00019959206655457612,
+      "loss": 0.8142043352127075,
+      "step": 1482
+    },
+    {
+      "epoch": 0.6403451995685006,
+      "grad_norm": 0.4839977025985718,
+      "learning_rate": 0.0001995876235046067,
+      "loss": 0.860643744468689,
+      "step": 1484
+    },
+    {
+      "epoch": 0.6412081984897519,
+      "grad_norm": 0.3542814552783966,
+      "learning_rate": 0.00019958315643953085,
+      "loss": 0.7586524486541748,
+      "step": 1486
+    },
+    {
+      "epoch": 0.6420711974110033,
+      "grad_norm": 0.5423269271850586,
+      "learning_rate": 0.00019957866536042572,
+      "loss": 0.9353570342063904,
+      "step": 1488
+    },
+    {
+      "epoch": 0.6429341963322546,
+      "grad_norm": 0.4580909013748169,
+      "learning_rate": 0.00019957415026837437,
+      "loss": 0.9919291138648987,
+      "step": 1490
+    },
+    {
+      "epoch": 0.643797195253506,
+      "grad_norm": 0.4211732745170593,
+      "learning_rate": 0.00019956961116446555,
+      "loss": 0.8720914125442505,
+      "step": 1492
+    },
+    {
+      "epoch": 0.6446601941747573,
+      "grad_norm": 0.4583161175251007,
+      "learning_rate": 0.00019956504804979384,
+      "loss": 0.8661212921142578,
+      "step": 1494
+    },
+    {
+      "epoch": 0.6455231930960086,
+      "grad_norm": 0.4359884262084961,
+      "learning_rate": 0.00019956046092545966,
+      "loss": 0.8170996308326721,
+      "step": 1496
+    },
+    {
+      "epoch": 0.64638619201726,
+      "grad_norm": 0.4642556607723236,
+      "learning_rate": 0.00019955584979256913,
+      "loss": 0.8607422113418579,
+      "step": 1498
+    },
+    {
+      "epoch": 0.6472491909385113,
+      "grad_norm": 0.4496007561683655,
+      "learning_rate": 0.00019955121465223426,
+      "loss": 0.837529182434082,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6472491909385113,
+      "eval_loss": 0.8972997665405273,
+      "eval_runtime": 649.796,
+      "eval_samples_per_second": 3.17,
+      "eval_steps_per_second": 3.17,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6481121898597627,
+      "grad_norm": 0.48363205790519714,
+      "learning_rate": 0.0001995465555055727,
+      "loss": 0.9355250000953674,
+      "step": 1502
+    },
+    {
+      "epoch": 0.648975188781014,
+      "grad_norm": 0.44681695103645325,
+      "learning_rate": 0.0001995418723537081,
+      "loss": 0.8286949396133423,
+      "step": 1504
+    },
+    {
+      "epoch": 0.6498381877022654,
+      "grad_norm": 0.5110394358634949,
+      "learning_rate": 0.00019953716519776967,
+      "loss": 0.890398383140564,
+      "step": 1506
+    },
+    {
+      "epoch": 0.6507011866235167,
+      "grad_norm": 0.4353160262107849,
+      "learning_rate": 0.00019953243403889257,
+      "loss": 0.8117311000823975,
+      "step": 1508
+    },
+    {
+      "epoch": 0.651564185544768,
+      "grad_norm": 0.4731789231300354,
+      "learning_rate": 0.0001995276788782177,
+      "loss": 0.8255904316902161,
+      "step": 1510
+    },
+    {
+      "epoch": 0.6524271844660194,
+      "grad_norm": 0.5447185039520264,
+      "learning_rate": 0.00019952289971689177,
+      "loss": 0.9371263384819031,
+      "step": 1512
+    },
+    {
+      "epoch": 0.6532901833872707,
+      "grad_norm": 0.47616517543792725,
+      "learning_rate": 0.0001995180965560672,
+      "loss": 0.8532910943031311,
+      "step": 1514
+    },
+    {
+      "epoch": 0.6541531823085222,
+      "grad_norm": 0.4412213861942291,
+      "learning_rate": 0.0001995132693969023,
+      "loss": 0.8799141645431519,
+      "step": 1516
+    },
+    {
+      "epoch": 0.6550161812297735,
+      "grad_norm": 0.469911128282547,
+      "learning_rate": 0.00019950841824056107,
+      "loss": 0.8395764827728271,
+      "step": 1518
+    },
+    {
+      "epoch": 0.6558791801510249,
+      "grad_norm": 0.5236243009567261,
+      "learning_rate": 0.00019950354308821336,
+      "loss": 0.9556697010993958,
+      "step": 1520
+    },
+    {
+      "epoch": 0.6567421790722762,
+      "grad_norm": 0.4441990256309509,
+      "learning_rate": 0.00019949864394103482,
+      "loss": 0.8524283170700073,
+      "step": 1522
+    },
+    {
+      "epoch": 0.6576051779935275,
+      "grad_norm": 0.4173077940940857,
+      "learning_rate": 0.00019949372080020682,
+      "loss": 0.9213772416114807,
+      "step": 1524
+    },
+    {
+      "epoch": 0.6584681769147789,
+      "grad_norm": 0.4404120147228241,
+      "learning_rate": 0.00019948877366691658,
+      "loss": 0.9236897230148315,
+      "step": 1526
+    },
+    {
+      "epoch": 0.6593311758360302,
+      "grad_norm": 0.4586230516433716,
+      "learning_rate": 0.00019948380254235706,
+      "loss": 0.8373230695724487,
+      "step": 1528
+    },
+    {
+      "epoch": 0.6601941747572816,
+      "grad_norm": 0.4136028587818146,
+      "learning_rate": 0.00019947880742772703,
+      "loss": 0.8256528377532959,
+      "step": 1530
+    },
+    {
+      "epoch": 0.6610571736785329,
+      "grad_norm": 0.5007129907608032,
+      "learning_rate": 0.00019947378832423107,
+      "loss": 0.8580789566040039,
+      "step": 1532
+    },
+    {
+      "epoch": 0.6619201725997842,
+      "grad_norm": 0.39050203561782837,
+      "learning_rate": 0.00019946874523307947,
+      "loss": 0.7647744417190552,
+      "step": 1534
+    },
+    {
+      "epoch": 0.6627831715210356,
+      "grad_norm": 0.4640588164329529,
+      "learning_rate": 0.00019946367815548835,
+      "loss": 0.9042545557022095,
+      "step": 1536
+    },
+    {
+      "epoch": 0.6636461704422869,
+      "grad_norm": 0.5304957032203674,
+      "learning_rate": 0.00019945858709267963,
+      "loss": 0.9114110469818115,
+      "step": 1538
+    },
+    {
+      "epoch": 0.6645091693635383,
+      "grad_norm": 0.5426004528999329,
+      "learning_rate": 0.000199453472045881,
+      "loss": 0.8239460587501526,
+      "step": 1540
+    },
+    {
+      "epoch": 0.6653721682847896,
+      "grad_norm": 0.44893568754196167,
+      "learning_rate": 0.00019944833301632593,
+      "loss": 0.8091367483139038,
+      "step": 1542
+    },
+    {
+      "epoch": 0.666235167206041,
+      "grad_norm": 0.4294016361236572,
+      "learning_rate": 0.00019944317000525366,
+      "loss": 0.9202280640602112,
+      "step": 1544
+    },
+    {
+      "epoch": 0.6670981661272923,
+      "grad_norm": 0.449633926153183,
+      "learning_rate": 0.00019943798301390927,
+      "loss": 0.8884767889976501,
+      "step": 1546
+    },
+    {
+      "epoch": 0.6679611650485436,
+      "grad_norm": 0.4516827166080475,
+      "learning_rate": 0.0001994327720435435,
+      "loss": 0.8390879034996033,
+      "step": 1548
+    },
+    {
+      "epoch": 0.668824163969795,
+      "grad_norm": 0.422270268201828,
+      "learning_rate": 0.000199427537095413,
+      "loss": 0.7388033270835876,
+      "step": 1550
+    },
+    {
+      "epoch": 0.6696871628910464,
+      "grad_norm": 0.580563485622406,
+      "learning_rate": 0.00019942227817078015,
+      "loss": 0.9268350601196289,
+      "step": 1552
+    },
+    {
+      "epoch": 0.6705501618122978,
+      "grad_norm": 0.4436347782611847,
+      "learning_rate": 0.00019941699527091316,
+      "loss": 0.7978561520576477,
+      "step": 1554
+    },
+    {
+      "epoch": 0.6714131607335491,
+      "grad_norm": 0.4149787127971649,
+      "learning_rate": 0.0001994116883970859,
+      "loss": 0.8229286670684814,
+      "step": 1556
+    },
+    {
+      "epoch": 0.6722761596548005,
+      "grad_norm": 0.49915504455566406,
+      "learning_rate": 0.00019940635755057813,
+      "loss": 0.8554545640945435,
+      "step": 1558
+    },
+    {
+      "epoch": 0.6731391585760518,
+      "grad_norm": 0.45326656103134155,
+      "learning_rate": 0.00019940100273267537,
+      "loss": 0.9135572910308838,
+      "step": 1560
+    },
+    {
+      "epoch": 0.6740021574973031,
+      "grad_norm": 0.48639237880706787,
+      "learning_rate": 0.0001993956239446689,
+      "loss": 0.7769742012023926,
+      "step": 1562
+    },
+    {
+      "epoch": 0.6748651564185545,
+      "grad_norm": 0.5072791576385498,
+      "learning_rate": 0.0001993902211878558,
+      "loss": 0.9626237154006958,
+      "step": 1564
+    },
+    {
+      "epoch": 0.6757281553398058,
+      "grad_norm": 0.4646652638912201,
+      "learning_rate": 0.00019938479446353892,
+      "loss": 0.8506941199302673,
+      "step": 1566
+    },
+    {
+      "epoch": 0.6765911542610572,
+      "grad_norm": 0.4343051314353943,
+      "learning_rate": 0.00019937934377302688,
+      "loss": 0.8172947764396667,
+      "step": 1568
+    },
+    {
+      "epoch": 0.6774541531823085,
+      "grad_norm": 0.46890193223953247,
+      "learning_rate": 0.00019937386911763407,
+      "loss": 0.9215856790542603,
+      "step": 1570
+    },
+    {
+      "epoch": 0.6783171521035599,
+      "grad_norm": 0.5121113061904907,
+      "learning_rate": 0.0001993683704986807,
+      "loss": 0.8099892139434814,
+      "step": 1572
+    },
+    {
+      "epoch": 0.6791801510248112,
+      "grad_norm": 0.4652405083179474,
+      "learning_rate": 0.0001993628479174928,
+      "loss": 0.8675104975700378,
+      "step": 1574
+    },
+    {
+      "epoch": 0.6800431499460625,
+      "grad_norm": 0.4599422812461853,
+      "learning_rate": 0.00019935730137540198,
+      "loss": 0.7938929200172424,
+      "step": 1576
+    },
+    {
+      "epoch": 0.6809061488673139,
+      "grad_norm": 0.4738059937953949,
+      "learning_rate": 0.0001993517308737459,
+      "loss": 0.8610570430755615,
+      "step": 1578
+    },
+    {
+      "epoch": 0.6817691477885652,
+      "grad_norm": 0.5161214470863342,
+      "learning_rate": 0.00019934613641386776,
+      "loss": 0.9199413657188416,
+      "step": 1580
+    },
+    {
+      "epoch": 0.6826321467098166,
+      "grad_norm": 0.4284999370574951,
+      "learning_rate": 0.00019934051799711672,
+      "loss": 0.771649181842804,
+      "step": 1582
+    },
+    {
+      "epoch": 0.683495145631068,
+      "grad_norm": 0.5117548704147339,
+      "learning_rate": 0.00019933487562484757,
+      "loss": 0.8861327767372131,
+      "step": 1584
+    },
+    {
+      "epoch": 0.6843581445523194,
+      "grad_norm": 0.4964369833469391,
+      "learning_rate": 0.00019932920929842095,
+      "loss": 0.806983232498169,
+      "step": 1586
+    },
+    {
+      "epoch": 0.6852211434735707,
+      "grad_norm": 0.4699532091617584,
+      "learning_rate": 0.00019932351901920327,
+      "loss": 0.7963525652885437,
+      "step": 1588
+    },
+    {
+      "epoch": 0.686084142394822,
+      "grad_norm": 0.5329220294952393,
+      "learning_rate": 0.00019931780478856678,
+      "loss": 0.9406430721282959,
+      "step": 1590
+    },
+    {
+      "epoch": 0.6869471413160734,
+      "grad_norm": 0.49823835492134094,
+      "learning_rate": 0.00019931206660788936,
+      "loss": 0.8517770171165466,
+      "step": 1592
+    },
+    {
+      "epoch": 0.6878101402373247,
+      "grad_norm": 0.45245134830474854,
+      "learning_rate": 0.00019930630447855482,
+      "loss": 0.8703644275665283,
+      "step": 1594
+    },
+    {
+      "epoch": 0.6886731391585761,
+      "grad_norm": 0.47524577379226685,
+      "learning_rate": 0.0001993005184019526,
+      "loss": 0.9035283327102661,
+      "step": 1596
+    },
+    {
+      "epoch": 0.6895361380798274,
+      "grad_norm": 0.4537610411643982,
+      "learning_rate": 0.00019929470837947802,
+      "loss": 0.9173959493637085,
+      "step": 1598
+    },
+    {
+      "epoch": 0.6903991370010788,
+      "grad_norm": 0.42469722032546997,
+      "learning_rate": 0.00019928887441253212,
+      "loss": 0.8573579788208008,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6903991370010788,
+      "eval_loss": 0.8880587220191956,
+      "eval_runtime": 653.9515,
+      "eval_samples_per_second": 3.15,
+      "eval_steps_per_second": 3.15,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6912621359223301,
+      "grad_norm": 0.4388251304626465,
+      "learning_rate": 0.00019928301650252176,
+      "loss": 0.849348247051239,
+      "step": 1602
+    },
+    {
+      "epoch": 0.6921251348435814,
+      "grad_norm": 0.46086886525154114,
+      "learning_rate": 0.00019927713465085956,
+      "loss": 0.8298451900482178,
+      "step": 1604
+    },
+    {
+      "epoch": 0.6929881337648328,
+      "grad_norm": 0.42972785234451294,
+      "learning_rate": 0.00019927122885896387,
+      "loss": 0.8860712647438049,
+      "step": 1606
+    },
+    {
+      "epoch": 0.6938511326860841,
+      "grad_norm": 0.43009471893310547,
+      "learning_rate": 0.00019926529912825888,
+      "loss": 0.7972728610038757,
+      "step": 1608
+    },
+    {
+      "epoch": 0.6947141316073355,
+      "grad_norm": 0.3705308437347412,
+      "learning_rate": 0.00019925934546017446,
+      "loss": 0.8661653995513916,
+      "step": 1610
+    },
+    {
+      "epoch": 0.6955771305285868,
+      "grad_norm": 0.405208945274353,
+      "learning_rate": 0.00019925336785614635,
+      "loss": 0.8350111246109009,
+      "step": 1612
+    },
+    {
+      "epoch": 0.6964401294498382,
+      "grad_norm": 0.4773033857345581,
+      "learning_rate": 0.00019924736631761602,
+      "loss": 0.7920925617218018,
+      "step": 1614
+    },
+    {
+      "epoch": 0.6973031283710895,
+      "grad_norm": 0.4682428240776062,
+      "learning_rate": 0.00019924134084603075,
+      "loss": 0.8644304871559143,
+      "step": 1616
+    },
+    {
+      "epoch": 0.6981661272923408,
+      "grad_norm": 0.5694834589958191,
+      "learning_rate": 0.00019923529144284346,
+      "loss": 0.9897904992103577,
+      "step": 1618
+    },
+    {
+      "epoch": 0.6990291262135923,
+      "grad_norm": 0.40137484669685364,
+      "learning_rate": 0.00019922921810951302,
+      "loss": 0.6910083293914795,
+      "step": 1620
+    },
+    {
+      "epoch": 0.6998921251348436,
+      "grad_norm": 0.42076537013053894,
+      "learning_rate": 0.000199223120847504,
+      "loss": 0.8295826315879822,
+      "step": 1622
+    },
+    {
+      "epoch": 0.700755124056095,
+      "grad_norm": 0.4473017752170563,
+      "learning_rate": 0.00019921699965828662,
+      "loss": 0.820871889591217,
+      "step": 1624
+    },
+    {
+      "epoch": 0.7016181229773463,
+      "grad_norm": 0.43914029002189636,
+      "learning_rate": 0.00019921085454333706,
+      "loss": 0.8319019079208374,
+      "step": 1626
+    },
+    {
+      "epoch": 0.7024811218985976,
+      "grad_norm": 0.4758487939834595,
+      "learning_rate": 0.0001992046855041372,
+      "loss": 0.8589251041412354,
+      "step": 1628
+    },
+    {
+      "epoch": 0.703344120819849,
+      "grad_norm": 0.506401538848877,
+      "learning_rate": 0.00019919849254217465,
+      "loss": 0.9219205975532532,
+      "step": 1630
+    },
+    {
+      "epoch": 0.7042071197411003,
+      "grad_norm": 0.4397984445095062,
+      "learning_rate": 0.00019919227565894277,
+      "loss": 0.7824978232383728,
+      "step": 1632
+    },
+    {
+      "epoch": 0.7050701186623517,
+      "grad_norm": 0.3879252076148987,
+      "learning_rate": 0.0001991860348559408,
+      "loss": 0.8472069501876831,
+      "step": 1634
+    },
+    {
+      "epoch": 0.705933117583603,
+      "grad_norm": 0.42238810658454895,
+      "learning_rate": 0.00019917977013467368,
+      "loss": 0.824957013130188,
+      "step": 1636
+    },
+    {
+      "epoch": 0.7067961165048544,
+      "grad_norm": 0.5235037207603455,
+      "learning_rate": 0.00019917348149665206,
+      "loss": 0.9490993022918701,
+      "step": 1638
+    },
+    {
+      "epoch": 0.7076591154261057,
+      "grad_norm": 0.5195287466049194,
+      "learning_rate": 0.0001991671689433925,
+      "loss": 0.960905909538269,
+      "step": 1640
+    },
+    {
+      "epoch": 0.708522114347357,
+      "grad_norm": 0.5016481876373291,
+      "learning_rate": 0.00019916083247641716,
+      "loss": 0.8961218595504761,
+      "step": 1642
+    },
+    {
+      "epoch": 0.7093851132686084,
+      "grad_norm": 0.5510191321372986,
+      "learning_rate": 0.00019915447209725408,
+      "loss": 0.8883417844772339,
+      "step": 1644
+    },
+    {
+      "epoch": 0.7102481121898597,
+      "grad_norm": 0.4492250084877014,
+      "learning_rate": 0.0001991480878074371,
+      "loss": 0.7968636751174927,
+      "step": 1646
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.4189683496952057,
+      "learning_rate": 0.00019914167960850563,
+      "loss": 0.7869221568107605,
+      "step": 1648
+    },
+    {
+      "epoch": 0.7119741100323624,
+      "grad_norm": 0.4590536653995514,
+      "learning_rate": 0.0001991352475020051,
+      "loss": 0.8423646092414856,
+      "step": 1650
+    },
+    {
+      "epoch": 0.7128371089536139,
+      "grad_norm": 0.5058966875076294,
+      "learning_rate": 0.00019912879148948652,
+      "loss": 0.895459771156311,
+      "step": 1652
+    },
+    {
+      "epoch": 0.7137001078748652,
+      "grad_norm": 0.4904550313949585,
+      "learning_rate": 0.00019912231157250676,
+      "loss": 0.8737894296646118,
+      "step": 1654
+    },
+    {
+      "epoch": 0.7145631067961165,
+      "grad_norm": 0.4670710861682892,
+      "learning_rate": 0.0001991158077526284,
+      "loss": 0.8019732236862183,
+      "step": 1656
+    },
+    {
+      "epoch": 0.7154261057173679,
+      "grad_norm": 0.530343770980835,
+      "learning_rate": 0.00019910928003141984,
+      "loss": 0.9474499821662903,
+      "step": 1658
+    },
+    {
+      "epoch": 0.7162891046386192,
+      "grad_norm": 0.4250960052013397,
+      "learning_rate": 0.00019910272841045518,
+      "loss": 0.8738601803779602,
+      "step": 1660
+    },
+    {
+      "epoch": 0.7171521035598706,
+      "grad_norm": 0.4896513819694519,
+      "learning_rate": 0.0001990961528913143,
+      "loss": 0.9578261971473694,
+      "step": 1662
+    },
+    {
+      "epoch": 0.7180151024811219,
+      "grad_norm": 0.4999626576900482,
+      "learning_rate": 0.00019908955347558291,
+      "loss": 0.8116445541381836,
+      "step": 1664
+    },
+    {
+      "epoch": 0.7188781014023733,
+      "grad_norm": 0.4335242807865143,
+      "learning_rate": 0.00019908293016485237,
+      "loss": 0.8783043622970581,
+      "step": 1666
+    },
+    {
+      "epoch": 0.7197411003236246,
+      "grad_norm": 0.43542763590812683,
+      "learning_rate": 0.00019907628296071992,
+      "loss": 0.8223029375076294,
+      "step": 1668
+    },
+    {
+      "epoch": 0.7206040992448759,
+      "grad_norm": 0.4907461702823639,
+      "learning_rate": 0.00019906961186478842,
+      "loss": 1.0053197145462036,
+      "step": 1670
+    },
+    {
+      "epoch": 0.7214670981661273,
+      "grad_norm": 0.4054848253726959,
+      "learning_rate": 0.00019906291687866667,
+      "loss": 0.8107786178588867,
+      "step": 1672
+    },
+    {
+      "epoch": 0.7223300970873786,
+      "grad_norm": 0.3818599283695221,
+      "learning_rate": 0.0001990561980039691,
+      "loss": 0.780781626701355,
+      "step": 1674
+    },
+    {
+      "epoch": 0.72319309600863,
+      "grad_norm": 0.4128594994544983,
+      "learning_rate": 0.00019904945524231587,
+      "loss": 0.8189221620559692,
+      "step": 1676
+    },
+    {
+      "epoch": 0.7240560949298813,
+      "grad_norm": 0.46902593970298767,
+      "learning_rate": 0.0001990426885953331,
+      "loss": 0.83652263879776,
+      "step": 1678
+    },
+    {
+      "epoch": 0.7249190938511327,
+      "grad_norm": 0.49305564165115356,
+      "learning_rate": 0.00019903589806465242,
+      "loss": 0.8057956695556641,
+      "step": 1680
+    },
+    {
+      "epoch": 0.725782092772384,
+      "grad_norm": 0.44408300518989563,
+      "learning_rate": 0.0001990290836519114,
+      "loss": 0.8523716926574707,
+      "step": 1682
+    },
+    {
+      "epoch": 0.7266450916936353,
+      "grad_norm": 0.5211108922958374,
+      "learning_rate": 0.00019902224535875326,
+      "loss": 0.9179236888885498,
+      "step": 1684
+    },
+    {
+      "epoch": 0.7275080906148867,
+      "grad_norm": 0.4736526608467102,
+      "learning_rate": 0.00019901538318682705,
+      "loss": 0.8229476809501648,
+      "step": 1686
+    },
+    {
+      "epoch": 0.728371089536138,
+      "grad_norm": 0.541716992855072,
+      "learning_rate": 0.00019900849713778756,
+      "loss": 0.924200713634491,
+      "step": 1688
+    },
+    {
+      "epoch": 0.7292340884573895,
+      "grad_norm": 0.4524400532245636,
+      "learning_rate": 0.00019900158721329532,
+      "loss": 0.88961261510849,
+      "step": 1690
+    },
+    {
+      "epoch": 0.7300970873786408,
+      "grad_norm": 0.45256128907203674,
+      "learning_rate": 0.00019899465341501662,
+      "loss": 0.8491015434265137,
+      "step": 1692
+    },
+    {
+      "epoch": 0.7309600862998922,
+      "grad_norm": 0.5346773266792297,
+      "learning_rate": 0.0001989876957446235,
+      "loss": 0.8833339810371399,
+      "step": 1694
+    },
+    {
+      "epoch": 0.7318230852211435,
+      "grad_norm": 0.4696357846260071,
+      "learning_rate": 0.0001989807142037938,
+      "loss": 0.8535294532775879,
+      "step": 1696
+    },
+    {
+      "epoch": 0.7326860841423948,
+      "grad_norm": 0.4304637908935547,
+      "learning_rate": 0.0001989737087942111,
+      "loss": 0.8273076415061951,
+      "step": 1698
+    },
+    {
+      "epoch": 0.7335490830636462,
+      "grad_norm": 0.5085629224777222,
+      "learning_rate": 0.00019896667951756466,
+      "loss": 0.8759240508079529,
+      "step": 1700
+    },
+    {
+      "epoch": 0.7335490830636462,
+      "eval_loss": 0.879119336605072,
+      "eval_runtime": 663.0553,
+      "eval_samples_per_second": 3.107,
+      "eval_steps_per_second": 3.107,
+      "step": 1700
+    },
+    {
+      "epoch": 0.7344120819848975,
+      "grad_norm": 0.484223872423172,
+      "learning_rate": 0.00019895962637554964,
+      "loss": 0.852645218372345,
+      "step": 1702
+    },
+    {
+      "epoch": 0.7352750809061489,
+      "grad_norm": 0.4819294214248657,
+      "learning_rate": 0.0001989525493698668,
+      "loss": 0.878247857093811,
+      "step": 1704
+    },
+    {
+      "epoch": 0.7361380798274002,
+      "grad_norm": 0.4170311689376831,
+      "learning_rate": 0.00019894544850222276,
+      "loss": 0.8964285254478455,
+      "step": 1706
+    },
+    {
+      "epoch": 0.7370010787486516,
+      "grad_norm": 0.42712801694869995,
+      "learning_rate": 0.0001989383237743299,
+      "loss": 0.7479548454284668,
+      "step": 1708
+    },
+    {
+      "epoch": 0.7378640776699029,
+      "grad_norm": 0.5051686763763428,
+      "learning_rate": 0.00019893117518790624,
+      "loss": 0.8190052509307861,
+      "step": 1710
+    },
+    {
+      "epoch": 0.7387270765911542,
+      "grad_norm": 0.44053253531455994,
+      "learning_rate": 0.0001989240027446757,
+      "loss": 0.8646742105484009,
+      "step": 1712
+    },
+    {
+      "epoch": 0.7395900755124056,
+      "grad_norm": 0.4451025724411011,
+      "learning_rate": 0.00019891680644636782,
+      "loss": 0.874261736869812,
+      "step": 1714
+    },
+    {
+      "epoch": 0.7404530744336569,
+      "grad_norm": 0.4590521454811096,
+      "learning_rate": 0.00019890958629471798,
+      "loss": 0.8892465233802795,
+      "step": 1716
+    },
+    {
+      "epoch": 0.7413160733549083,
+      "grad_norm": 0.39169448614120483,
+      "learning_rate": 0.00019890234229146732,
+      "loss": 0.7031586766242981,
+      "step": 1718
+    },
+    {
+      "epoch": 0.7421790722761596,
+      "grad_norm": 0.46946024894714355,
+      "learning_rate": 0.00019889507443836266,
+      "loss": 0.8548433184623718,
+      "step": 1720
+    },
+    {
+      "epoch": 0.7430420711974111,
+      "grad_norm": 0.42404699325561523,
+      "learning_rate": 0.0001988877827371566,
+      "loss": 0.8231223821640015,
+      "step": 1722
+    },
+    {
+      "epoch": 0.7439050701186624,
+      "grad_norm": 0.40419483184814453,
+      "learning_rate": 0.00019888046718960755,
+      "loss": 0.8443762063980103,
+      "step": 1724
+    },
+    {
+      "epoch": 0.7447680690399137,
+      "grad_norm": 0.4550437927246094,
+      "learning_rate": 0.0001988731277974796,
+      "loss": 0.8787111639976501,
+      "step": 1726
+    },
+    {
+      "epoch": 0.7456310679611651,
+      "grad_norm": 0.42264053225517273,
+      "learning_rate": 0.0001988657645625426,
+      "loss": 0.8440850377082825,
+      "step": 1728
+    },
+    {
+      "epoch": 0.7464940668824164,
+      "grad_norm": 0.4638359844684601,
+      "learning_rate": 0.0001988583774865721,
+      "loss": 0.839216947555542,
+      "step": 1730
+    },
+    {
+      "epoch": 0.7473570658036678,
+      "grad_norm": 0.42644429206848145,
+      "learning_rate": 0.0001988509665713496,
+      "loss": 0.8011161684989929,
+      "step": 1732
+    },
+    {
+      "epoch": 0.7482200647249191,
+      "grad_norm": 0.36932024359703064,
+      "learning_rate": 0.0001988435318186621,
+      "loss": 0.850246787071228,
+      "step": 1734
+    },
+    {
+      "epoch": 0.7490830636461704,
+      "grad_norm": 0.4771935045719147,
+      "learning_rate": 0.00019883607323030252,
+      "loss": 0.7782483100891113,
+      "step": 1736
+    },
+    {
+      "epoch": 0.7499460625674218,
+      "grad_norm": 0.40007370710372925,
+      "learning_rate": 0.00019882859080806942,
+      "loss": 0.8337594866752625,
+      "step": 1738
+    },
+    {
+      "epoch": 0.7508090614886731,
+      "grad_norm": 0.5007418394088745,
+      "learning_rate": 0.00019882108455376716,
+      "loss": 0.8287386894226074,
+      "step": 1740
+    },
+    {
+      "epoch": 0.7516720604099245,
+      "grad_norm": 0.43999138474464417,
+      "learning_rate": 0.00019881355446920584,
+      "loss": 0.8655616044998169,
+      "step": 1742
+    },
+    {
+      "epoch": 0.7525350593311758,
+      "grad_norm": 0.5115824937820435,
+      "learning_rate": 0.00019880600055620135,
+      "loss": 0.8695262670516968,
+      "step": 1744
+    },
+    {
+      "epoch": 0.7533980582524272,
+      "grad_norm": 0.5035707950592041,
+      "learning_rate": 0.0001987984228165752,
+      "loss": 0.9207013845443726,
+      "step": 1746
+    },
+    {
+      "epoch": 0.7542610571736785,
+      "grad_norm": 0.4689575731754303,
+      "learning_rate": 0.0001987908212521548,
+      "loss": 0.8798729777336121,
+      "step": 1748
+    },
+    {
+      "epoch": 0.7551240560949298,
+      "grad_norm": 0.4730616509914398,
+      "learning_rate": 0.00019878319586477322,
+      "loss": 0.7737767696380615,
+      "step": 1750
+    },
+    {
+      "epoch": 0.7559870550161812,
+      "grad_norm": 0.49012845754623413,
+      "learning_rate": 0.00019877554665626926,
+      "loss": 0.929466187953949,
+      "step": 1752
+    },
+    {
+      "epoch": 0.7568500539374325,
+      "grad_norm": 0.43468761444091797,
+      "learning_rate": 0.0001987678736284875,
+      "loss": 0.8155670166015625,
+      "step": 1754
+    },
+    {
+      "epoch": 0.757713052858684,
+      "grad_norm": 0.507399320602417,
+      "learning_rate": 0.00019876017678327826,
+      "loss": 0.8082395195960999,
+      "step": 1756
+    },
+    {
+      "epoch": 0.7585760517799353,
+      "grad_norm": 0.4733552634716034,
+      "learning_rate": 0.0001987524561224976,
+      "loss": 0.8905934691429138,
+      "step": 1758
+    },
+    {
+      "epoch": 0.7594390507011867,
+      "grad_norm": 0.4670012891292572,
+      "learning_rate": 0.00019874471164800733,
+      "loss": 0.8794633746147156,
+      "step": 1760
+    },
+    {
+      "epoch": 0.760302049622438,
+      "grad_norm": 0.4951624572277069,
+      "learning_rate": 0.000198736943361675,
+      "loss": 0.8413973450660706,
+      "step": 1762
+    },
+    {
+      "epoch": 0.7611650485436893,
+      "grad_norm": 0.5478648543357849,
+      "learning_rate": 0.00019872915126537387,
+      "loss": 0.9067897200584412,
+      "step": 1764
+    },
+    {
+      "epoch": 0.7620280474649407,
+      "grad_norm": 0.48215776681900024,
+      "learning_rate": 0.000198721335360983,
+      "loss": 0.8932394981384277,
+      "step": 1766
+    },
+    {
+      "epoch": 0.762891046386192,
+      "grad_norm": 0.4688864052295685,
+      "learning_rate": 0.00019871349565038715,
+      "loss": 0.8496726751327515,
+      "step": 1768
+    },
+    {
+      "epoch": 0.7637540453074434,
+      "grad_norm": 0.4728260636329651,
+      "learning_rate": 0.0001987056321354768,
+      "loss": 0.9232800602912903,
+      "step": 1770
+    },
+    {
+      "epoch": 0.7646170442286947,
+      "grad_norm": 0.44501692056655884,
+      "learning_rate": 0.00019869774481814828,
+      "loss": 0.849755585193634,
+      "step": 1772
+    },
+    {
+      "epoch": 0.7654800431499461,
+      "grad_norm": 0.4189201593399048,
+      "learning_rate": 0.00019868983370030348,
+      "loss": 0.8258485794067383,
+      "step": 1774
+    },
+    {
+      "epoch": 0.7663430420711974,
+      "grad_norm": 0.5144591927528381,
+      "learning_rate": 0.00019868189878385016,
+      "loss": 0.8762873411178589,
+      "step": 1776
+    },
+    {
+      "epoch": 0.7672060409924487,
+      "grad_norm": 0.5048011541366577,
+      "learning_rate": 0.00019867394007070188,
+      "loss": 0.8732464909553528,
+      "step": 1778
+    },
+    {
+      "epoch": 0.7680690399137001,
+      "grad_norm": 0.41639819741249084,
+      "learning_rate": 0.00019866595756277774,
+      "loss": 0.8732751607894897,
+      "step": 1780
+    },
+    {
+      "epoch": 0.7689320388349514,
+      "grad_norm": 0.526757538318634,
+      "learning_rate": 0.00019865795126200271,
+      "loss": 0.8453729748725891,
+      "step": 1782
+    },
+    {
+      "epoch": 0.7697950377562028,
+      "grad_norm": 0.47041091322898865,
+      "learning_rate": 0.0001986499211703075,
+      "loss": 0.8780192732810974,
+      "step": 1784
+    },
+    {
+      "epoch": 0.7706580366774541,
+      "grad_norm": 0.4535890221595764,
+      "learning_rate": 0.0001986418672896285,
+      "loss": 0.8508450388908386,
+      "step": 1786
+    },
+    {
+      "epoch": 0.7715210355987056,
+      "grad_norm": 0.4608050286769867,
+      "learning_rate": 0.00019863378962190788,
+      "loss": 0.822467565536499,
+      "step": 1788
+    },
+    {
+      "epoch": 0.7723840345199569,
+      "grad_norm": 0.5190523862838745,
+      "learning_rate": 0.00019862568816909356,
+      "loss": 0.844614565372467,
+      "step": 1790
+    },
+    {
+      "epoch": 0.7732470334412082,
+      "grad_norm": 0.42502254247665405,
+      "learning_rate": 0.00019861756293313912,
+      "loss": 0.8144394755363464,
+      "step": 1792
+    },
+    {
+      "epoch": 0.7741100323624596,
+      "grad_norm": 0.47112616896629333,
+      "learning_rate": 0.000198609413916004,
+      "loss": 0.8836341500282288,
+      "step": 1794
+    },
+    {
+      "epoch": 0.7749730312837109,
+      "grad_norm": 0.48414838314056396,
+      "learning_rate": 0.0001986012411196532,
+      "loss": 0.8846262693405151,
+      "step": 1796
+    },
+    {
+      "epoch": 0.7758360302049623,
+      "grad_norm": 0.4670039415359497,
+      "learning_rate": 0.00019859304454605763,
+      "loss": 0.7993118762969971,
+      "step": 1798
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "grad_norm": 0.41939061880111694,
+      "learning_rate": 0.0001985848241971938,
+      "loss": 0.8389407396316528,
+      "step": 1800
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "eval_loss": 0.8727664947509766,
+      "eval_runtime": 668.2062,
+      "eval_samples_per_second": 3.083,
+      "eval_steps_per_second": 3.083,
+      "step": 1800
+    },
+    {
+      "epoch": 0.777562028047465,
+      "grad_norm": 0.4566517174243927,
+      "learning_rate": 0.00019857658007504405,
+      "loss": 0.8824291825294495,
+      "step": 1802
+    },
+    {
+      "epoch": 0.7784250269687163,
+      "grad_norm": 0.4798925518989563,
+      "learning_rate": 0.0001985683121815964,
+      "loss": 0.808982789516449,
+      "step": 1804
+    },
+    {
+      "epoch": 0.7792880258899676,
+      "grad_norm": 0.4659746587276459,
+      "learning_rate": 0.00019856002051884462,
+      "loss": 0.955269992351532,
+      "step": 1806
+    },
+    {
+      "epoch": 0.780151024811219,
+      "grad_norm": 0.48573991656303406,
+      "learning_rate": 0.00019855170508878818,
+      "loss": 0.8142994046211243,
+      "step": 1808
+    },
+    {
+      "epoch": 0.7810140237324703,
+      "grad_norm": 0.4700213670730591,
+      "learning_rate": 0.00019854336589343236,
+      "loss": 0.8755695819854736,
+      "step": 1810
+    },
+    {
+      "epoch": 0.7818770226537217,
+      "grad_norm": 0.42113450169563293,
+      "learning_rate": 0.00019853500293478806,
+      "loss": 0.8098483681678772,
+      "step": 1812
+    },
+    {
+      "epoch": 0.782740021574973,
+      "grad_norm": 0.4218153655529022,
+      "learning_rate": 0.00019852661621487205,
+      "loss": 0.8219783306121826,
+      "step": 1814
+    },
+    {
+      "epoch": 0.7836030204962244,
+      "grad_norm": 0.499052494764328,
+      "learning_rate": 0.00019851820573570664,
+      "loss": 0.8314159512519836,
+      "step": 1816
+    },
+    {
+      "epoch": 0.7844660194174757,
+      "grad_norm": 0.42420193552970886,
+      "learning_rate": 0.00019850977149932008,
+      "loss": 0.7985323071479797,
+      "step": 1818
+    },
+    {
+      "epoch": 0.785329018338727,
+      "grad_norm": 0.46345841884613037,
+      "learning_rate": 0.0001985013135077462,
+      "loss": 0.8528217077255249,
+      "step": 1820
+    },
+    {
+      "epoch": 0.7861920172599784,
+      "grad_norm": 0.4433307945728302,
+      "learning_rate": 0.00019849283176302462,
+      "loss": 0.8659319877624512,
+      "step": 1822
+    },
+    {
+      "epoch": 0.7870550161812297,
+      "grad_norm": 0.48279091715812683,
+      "learning_rate": 0.00019848432626720067,
+      "loss": 0.8675655126571655,
+      "step": 1824
+    },
+    {
+      "epoch": 0.7879180151024812,
+      "grad_norm": 0.5439180731773376,
+      "learning_rate": 0.0001984757970223254,
+      "loss": 0.8550227284431458,
+      "step": 1826
+    },
+    {
+      "epoch": 0.7887810140237325,
+      "grad_norm": 0.45749521255493164,
+      "learning_rate": 0.0001984672440304556,
+      "loss": 0.7290607690811157,
+      "step": 1828
+    },
+    {
+      "epoch": 0.7896440129449838,
+      "grad_norm": 0.4654783606529236,
+      "learning_rate": 0.00019845866729365378,
+      "loss": 0.8619251251220703,
+      "step": 1830
+    },
+    {
+      "epoch": 0.7905070118662352,
+      "grad_norm": 0.42632243037223816,
+      "learning_rate": 0.00019845006681398823,
+      "loss": 0.8249601125717163,
+      "step": 1832
+    },
+    {
+      "epoch": 0.7913700107874865,
+      "grad_norm": 0.4747186005115509,
+      "learning_rate": 0.0001984414425935329,
+      "loss": 0.7138552069664001,
+      "step": 1834
+    },
+    {
+      "epoch": 0.7922330097087379,
+      "grad_norm": 0.4462338387966156,
+      "learning_rate": 0.0001984327946343674,
+      "loss": 0.903292715549469,
+      "step": 1836
+    },
+    {
+      "epoch": 0.7930960086299892,
+      "grad_norm": 0.4581359922885895,
+      "learning_rate": 0.00019842412293857726,
+      "loss": 0.7569618225097656,
+      "step": 1838
+    },
+    {
+      "epoch": 0.7939590075512406,
+      "grad_norm": 0.4183015525341034,
+      "learning_rate": 0.00019841542750825356,
+      "loss": 0.8063036203384399,
+      "step": 1840
+    },
+    {
+      "epoch": 0.7948220064724919,
+      "grad_norm": 0.3954181373119354,
+      "learning_rate": 0.0001984067083454932,
+      "loss": 0.81150221824646,
+      "step": 1842
+    },
+    {
+      "epoch": 0.7956850053937432,
+      "grad_norm": 0.46220019459724426,
+      "learning_rate": 0.0001983979654523987,
+      "loss": 0.841649055480957,
+      "step": 1844
+    },
+    {
+      "epoch": 0.7965480043149946,
+      "grad_norm": 0.47807541489601135,
+      "learning_rate": 0.00019838919883107843,
+      "loss": 0.8019483685493469,
+      "step": 1846
+    },
+    {
+      "epoch": 0.7974110032362459,
+      "grad_norm": 0.48015692830085754,
+      "learning_rate": 0.0001983804084836464,
+      "loss": 0.9343363046646118,
+      "step": 1848
+    },
+    {
+      "epoch": 0.7982740021574973,
+      "grad_norm": 0.4906708896160126,
+      "learning_rate": 0.00019837159441222238,
+      "loss": 0.9163194894790649,
+      "step": 1850
+    },
+    {
+      "epoch": 0.7991370010787486,
+      "grad_norm": 0.4856911599636078,
+      "learning_rate": 0.0001983627566189318,
+      "loss": 0.8017736077308655,
+      "step": 1852
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.49403145909309387,
+      "learning_rate": 0.0001983538951059059,
+      "loss": 0.8375223875045776,
+      "step": 1854
+    },
+    {
+      "epoch": 0.8008629989212513,
+      "grad_norm": 0.4237985908985138,
+      "learning_rate": 0.00019834500987528158,
+      "loss": 0.8213951587677002,
+      "step": 1856
+    },
+    {
+      "epoch": 0.8017259978425026,
+      "grad_norm": 0.3977980315685272,
+      "learning_rate": 0.00019833610092920149,
+      "loss": 0.8086028099060059,
+      "step": 1858
+    },
+    {
+      "epoch": 0.8025889967637541,
+      "grad_norm": 0.435253381729126,
+      "learning_rate": 0.00019832716826981392,
+      "loss": 0.9402202367782593,
+      "step": 1860
+    },
+    {
+      "epoch": 0.8034519956850054,
+      "grad_norm": 0.4074764847755432,
+      "learning_rate": 0.000198318211899273,
+      "loss": 0.7730796933174133,
+      "step": 1862
+    },
+    {
+      "epoch": 0.8043149946062568,
+      "grad_norm": 0.48804348707199097,
+      "learning_rate": 0.0001983092318197385,
+      "loss": 0.9185802936553955,
+      "step": 1864
+    },
+    {
+      "epoch": 0.8051779935275081,
+      "grad_norm": 0.44363343715667725,
+      "learning_rate": 0.00019830022803337592,
+      "loss": 0.8578243851661682,
+      "step": 1866
+    },
+    {
+      "epoch": 0.8060409924487595,
+      "grad_norm": 0.46645957231521606,
+      "learning_rate": 0.00019829120054235653,
+      "loss": 0.8682060241699219,
+      "step": 1868
+    },
+    {
+      "epoch": 0.8069039913700108,
+      "grad_norm": 0.4527221620082855,
+      "learning_rate": 0.00019828214934885718,
+      "loss": 0.7845040559768677,
+      "step": 1870
+    },
+    {
+      "epoch": 0.8077669902912621,
+      "grad_norm": 0.4103536307811737,
+      "learning_rate": 0.0001982730744550606,
+      "loss": 0.8768247961997986,
+      "step": 1872
+    },
+    {
+      "epoch": 0.8086299892125135,
+      "grad_norm": 0.5257515907287598,
+      "learning_rate": 0.00019826397586315513,
+      "loss": 0.850267231464386,
+      "step": 1874
+    },
+    {
+      "epoch": 0.8094929881337648,
+      "grad_norm": 0.46675893664360046,
+      "learning_rate": 0.00019825485357533485,
+      "loss": 0.8234293460845947,
+      "step": 1876
+    },
+    {
+      "epoch": 0.8103559870550162,
+      "grad_norm": 0.46315401792526245,
+      "learning_rate": 0.00019824570759379958,
+      "loss": 0.8131387829780579,
+      "step": 1878
+    },
+    {
+      "epoch": 0.8112189859762675,
+      "grad_norm": 0.4766870439052582,
+      "learning_rate": 0.00019823653792075478,
+      "loss": 0.7680494785308838,
+      "step": 1880
+    },
+    {
+      "epoch": 0.8120819848975189,
+      "grad_norm": 0.39025625586509705,
+      "learning_rate": 0.00019822734455841173,
+      "loss": 0.7891425490379333,
+      "step": 1882
+    },
+    {
+      "epoch": 0.8129449838187702,
+      "grad_norm": 0.4672441780567169,
+      "learning_rate": 0.0001982181275089874,
+      "loss": 0.7990400791168213,
+      "step": 1884
+    },
+    {
+      "epoch": 0.8138079827400215,
+      "grad_norm": 0.44310975074768066,
+      "learning_rate": 0.00019820888677470432,
+      "loss": 0.7828341722488403,
+      "step": 1886
+    },
+    {
+      "epoch": 0.8146709816612729,
+      "grad_norm": 0.45098716020584106,
+      "learning_rate": 0.00019819962235779096,
+      "loss": 0.897715151309967,
+      "step": 1888
+    },
+    {
+      "epoch": 0.8155339805825242,
+      "grad_norm": 0.466805100440979,
+      "learning_rate": 0.00019819033426048135,
+      "loss": 0.7987668514251709,
+      "step": 1890
+    },
+    {
+      "epoch": 0.8163969795037757,
+      "grad_norm": 0.4438319206237793,
+      "learning_rate": 0.00019818102248501528,
+      "loss": 0.7950236201286316,
+      "step": 1892
+    },
+    {
+      "epoch": 0.817259978425027,
+      "grad_norm": 0.42012497782707214,
+      "learning_rate": 0.00019817168703363823,
+      "loss": 0.8789975643157959,
+      "step": 1894
+    },
+    {
+      "epoch": 0.8181229773462784,
+      "grad_norm": 0.4359394311904907,
+      "learning_rate": 0.0001981623279086014,
+      "loss": 0.8159777522087097,
+      "step": 1896
+    },
+    {
+      "epoch": 0.8189859762675297,
+      "grad_norm": 0.44709593057632446,
+      "learning_rate": 0.00019815294511216173,
+      "loss": 0.84877610206604,
+      "step": 1898
+    },
+    {
+      "epoch": 0.819848975188781,
+      "grad_norm": 0.4315306544303894,
+      "learning_rate": 0.00019814353864658184,
+      "loss": 0.8467556834220886,
+      "step": 1900
+    },
+    {
+      "epoch": 0.819848975188781,
+      "eval_loss": 0.8643407821655273,
+      "eval_runtime": 658.6942,
+      "eval_samples_per_second": 3.127,
+      "eval_steps_per_second": 3.127,
+      "step": 1900
+    },
+    {
+      "epoch": 0.8207119741100324,
+      "grad_norm": 0.35530397295951843,
+      "learning_rate": 0.00019813410851412998,
+      "loss": 0.7398589849472046,
+      "step": 1902
+    },
+    {
+      "epoch": 0.8215749730312837,
+      "grad_norm": 0.46949300169944763,
+      "learning_rate": 0.00019812465471708032,
+      "loss": 0.8544237613677979,
+      "step": 1904
+    },
+    {
+      "epoch": 0.8224379719525351,
+      "grad_norm": 0.4961565434932709,
+      "learning_rate": 0.00019811517725771248,
+      "loss": 0.8242526054382324,
+      "step": 1906
+    },
+    {
+      "epoch": 0.8233009708737864,
+      "grad_norm": 0.45835059881210327,
+      "learning_rate": 0.00019810567613831194,
+      "loss": 0.7856690287590027,
+      "step": 1908
+    },
+    {
+      "epoch": 0.8241639697950378,
+      "grad_norm": 0.4446084797382355,
+      "learning_rate": 0.0001980961513611699,
+      "loss": 0.8361829519271851,
+      "step": 1910
+    },
+    {
+      "epoch": 0.8250269687162891,
+      "grad_norm": 0.4470907747745514,
+      "learning_rate": 0.00019808660292858313,
+      "loss": 0.8993050456047058,
+      "step": 1912
+    },
+    {
+      "epoch": 0.8258899676375404,
+      "grad_norm": 0.44883644580841064,
+      "learning_rate": 0.0001980770308428543,
+      "loss": 0.8702824711799622,
+      "step": 1914
+    },
+    {
+      "epoch": 0.8267529665587918,
+      "grad_norm": 0.43215686082839966,
+      "learning_rate": 0.00019806743510629159,
+      "loss": 0.8454389572143555,
+      "step": 1916
+    },
+    {
+      "epoch": 0.8276159654800431,
+      "grad_norm": 0.4525185823440552,
+      "learning_rate": 0.00019805781572120897,
+      "loss": 0.8621824383735657,
+      "step": 1918
+    },
+    {
+      "epoch": 0.8284789644012945,
+      "grad_norm": 0.4616840183734894,
+      "learning_rate": 0.00019804817268992615,
+      "loss": 0.8661681413650513,
+      "step": 1920
+    },
+    {
+      "epoch": 0.8293419633225458,
+      "grad_norm": 0.4252975583076477,
+      "learning_rate": 0.0001980385060147685,
+      "loss": 0.8376660346984863,
+      "step": 1922
+    },
+    {
+      "epoch": 0.8302049622437971,
+      "grad_norm": 0.44600266218185425,
+      "learning_rate": 0.00019802881569806706,
+      "loss": 0.9258401393890381,
+      "step": 1924
+    },
+    {
+      "epoch": 0.8310679611650486,
+      "grad_norm": 0.48872479796409607,
+      "learning_rate": 0.00019801910174215866,
+      "loss": 0.8804965615272522,
+      "step": 1926
+    },
+    {
+      "epoch": 0.8319309600862999,
+      "grad_norm": 0.5357037782669067,
+      "learning_rate": 0.00019800936414938574,
+      "loss": 0.8561494946479797,
+      "step": 1928
+    },
+    {
+      "epoch": 0.8327939590075513,
+      "grad_norm": 0.39637291431427,
+      "learning_rate": 0.00019799960292209647,
+      "loss": 0.782166063785553,
+      "step": 1930
+    },
+    {
+      "epoch": 0.8336569579288026,
+      "grad_norm": 0.521138072013855,
+      "learning_rate": 0.00019798981806264476,
+      "loss": 0.9048293232917786,
+      "step": 1932
+    },
+    {
+      "epoch": 0.834519956850054,
+      "grad_norm": 0.4723529815673828,
+      "learning_rate": 0.00019798000957339015,
+      "loss": 0.9269952774047852,
+      "step": 1934
+    },
+    {
+      "epoch": 0.8353829557713053,
+      "grad_norm": 0.42827340960502625,
+      "learning_rate": 0.0001979701774566979,
+      "loss": 0.8620670437812805,
+      "step": 1936
+    },
+    {
+      "epoch": 0.8362459546925566,
+      "grad_norm": 0.4305116534233093,
+      "learning_rate": 0.00019796032171493907,
+      "loss": 0.8016669750213623,
+      "step": 1938
+    },
+    {
+      "epoch": 0.837108953613808,
+      "grad_norm": 0.4995502233505249,
+      "learning_rate": 0.00019795044235049024,
+      "loss": 0.879247784614563,
+      "step": 1940
+    },
+    {
+      "epoch": 0.8379719525350593,
+      "grad_norm": 0.49229878187179565,
+      "learning_rate": 0.0001979405393657338,
+      "loss": 0.9476580023765564,
+      "step": 1942
+    },
+    {
+      "epoch": 0.8388349514563107,
+      "grad_norm": 0.45756596326828003,
+      "learning_rate": 0.0001979306127630578,
+      "loss": 0.8654064536094666,
+      "step": 1944
+    },
+    {
+      "epoch": 0.839697950377562,
+      "grad_norm": 0.4855344891548157,
+      "learning_rate": 0.00019792066254485603,
+      "loss": 0.7792956829071045,
+      "step": 1946
+    },
+    {
+      "epoch": 0.8405609492988134,
+      "grad_norm": 0.4358632266521454,
+      "learning_rate": 0.00019791068871352787,
+      "loss": 0.8000320792198181,
+      "step": 1948
+    },
+    {
+      "epoch": 0.8414239482200647,
+      "grad_norm": 0.4225342273712158,
+      "learning_rate": 0.00019790069127147852,
+      "loss": 0.818372368812561,
+      "step": 1950
+    },
+    {
+      "epoch": 0.842286947141316,
+      "grad_norm": 0.3894529938697815,
+      "learning_rate": 0.00019789067022111886,
+      "loss": 0.727220892906189,
+      "step": 1952
+    },
+    {
+      "epoch": 0.8431499460625674,
+      "grad_norm": 0.5060731768608093,
+      "learning_rate": 0.0001978806255648653,
+      "loss": 0.894101083278656,
+      "step": 1954
+    },
+    {
+      "epoch": 0.8440129449838187,
+      "grad_norm": 0.4165003001689911,
+      "learning_rate": 0.0001978705573051402,
+      "loss": 0.878365695476532,
+      "step": 1956
+    },
+    {
+      "epoch": 0.8448759439050701,
+      "grad_norm": 0.48767927289009094,
+      "learning_rate": 0.0001978604654443714,
+      "loss": 0.8390909433364868,
+      "step": 1958
+    },
+    {
+      "epoch": 0.8457389428263214,
+      "grad_norm": 0.43019410967826843,
+      "learning_rate": 0.00019785034998499247,
+      "loss": 0.8807769417762756,
+      "step": 1960
+    },
+    {
+      "epoch": 0.8466019417475729,
+      "grad_norm": 0.4430403709411621,
+      "learning_rate": 0.0001978402109294428,
+      "loss": 0.8037779331207275,
+      "step": 1962
+    },
+    {
+      "epoch": 0.8474649406688242,
+      "grad_norm": 0.41642463207244873,
+      "learning_rate": 0.0001978300482801673,
+      "loss": 0.8341337442398071,
+      "step": 1964
+    },
+    {
+      "epoch": 0.8483279395900755,
+      "grad_norm": 0.45358774065971375,
+      "learning_rate": 0.00019781986203961668,
+      "loss": 0.854821503162384,
+      "step": 1966
+    },
+    {
+      "epoch": 0.8491909385113269,
+      "grad_norm": 0.4316342771053314,
+      "learning_rate": 0.00019780965221024728,
+      "loss": 0.8527678847312927,
+      "step": 1968
+    },
+    {
+      "epoch": 0.8500539374325782,
+      "grad_norm": 0.4581106901168823,
+      "learning_rate": 0.00019779941879452122,
+      "loss": 0.7461717128753662,
+      "step": 1970
+    },
+    {
+      "epoch": 0.8509169363538296,
+      "grad_norm": 0.49578142166137695,
+      "learning_rate": 0.0001977891617949062,
+      "loss": 0.884441077709198,
+      "step": 1972
+    },
+    {
+      "epoch": 0.8517799352750809,
+      "grad_norm": 0.4366011917591095,
+      "learning_rate": 0.00019777888121387562,
+      "loss": 0.855915904045105,
+      "step": 1974
+    },
+    {
+      "epoch": 0.8526429341963323,
+      "grad_norm": 0.486162930727005,
+      "learning_rate": 0.00019776857705390864,
+      "loss": 0.7563765645027161,
+      "step": 1976
+    },
+    {
+      "epoch": 0.8535059331175836,
+      "grad_norm": 0.5162674784660339,
+      "learning_rate": 0.00019775824931749005,
+      "loss": 0.8346326947212219,
+      "step": 1978
+    },
+    {
+      "epoch": 0.8543689320388349,
+      "grad_norm": 0.5824693441390991,
+      "learning_rate": 0.0001977478980071103,
+      "loss": 0.8701820969581604,
+      "step": 1980
+    },
+    {
+      "epoch": 0.8552319309600863,
+      "grad_norm": 0.4297148883342743,
+      "learning_rate": 0.00019773752312526565,
+      "loss": 0.893528938293457,
+      "step": 1982
+    },
+    {
+      "epoch": 0.8560949298813376,
+      "grad_norm": 0.42978280782699585,
+      "learning_rate": 0.00019772712467445788,
+      "loss": 0.8201018571853638,
+      "step": 1984
+    },
+    {
+      "epoch": 0.856957928802589,
+      "grad_norm": 0.5192655324935913,
+      "learning_rate": 0.00019771670265719454,
+      "loss": 0.9080212116241455,
+      "step": 1986
+    },
+    {
+      "epoch": 0.8578209277238403,
+      "grad_norm": 0.452690452337265,
+      "learning_rate": 0.00019770625707598885,
+      "loss": 0.8518272638320923,
+      "step": 1988
+    },
+    {
+      "epoch": 0.8586839266450917,
+      "grad_norm": 0.4371768832206726,
+      "learning_rate": 0.00019769578793335976,
+      "loss": 0.9426717758178711,
+      "step": 1990
+    },
+    {
+      "epoch": 0.859546925566343,
+      "grad_norm": 0.44595038890838623,
+      "learning_rate": 0.0001976852952318318,
+      "loss": 0.8065400123596191,
+      "step": 1992
+    },
+    {
+      "epoch": 0.8604099244875943,
+      "grad_norm": 0.4355090260505676,
+      "learning_rate": 0.0001976747789739353,
+      "loss": 0.7674415707588196,
+      "step": 1994
+    },
+    {
+      "epoch": 0.8612729234088458,
+      "grad_norm": 0.43745186924934387,
+      "learning_rate": 0.00019766423916220616,
+      "loss": 0.813849925994873,
+      "step": 1996
+    },
+    {
+      "epoch": 0.8621359223300971,
+      "grad_norm": 0.4588927924633026,
+      "learning_rate": 0.00019765367579918598,
+      "loss": 0.7870585322380066,
+      "step": 1998
+    },
+    {
+      "epoch": 0.8629989212513485,
+      "grad_norm": 0.4170977473258972,
+      "learning_rate": 0.00019764308888742214,
+      "loss": 0.8383269309997559,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8629989212513485,
+      "eval_loss": 0.8567262887954712,
+      "eval_runtime": 646.6443,
+      "eval_samples_per_second": 3.186,
+      "eval_steps_per_second": 3.186,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 13908,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.001
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1995266703367885e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/sft_qwen_14B/checkpoints/checkpoint-2000/training_args.bin b/sft_qwen_14B/checkpoints/checkpoint-2000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b023888140f1fb107e8d5ebbfbcb9d9558b09d43
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-2000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4200830b23d19bc86049c280236c4a6b18c26d7061b5a57cc024888ec760920f
+size 5201
diff --git a/sft_qwen_14B/checkpoints/checkpoint-2500/README.md b/sft_qwen_14B/checkpoints/checkpoint-2500/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..779b6406e547b32301fef1d181301a873befe542
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-2500/README.md
@@ -0,0 +1,207 @@
+---
+base_model: runs/cpt_run_14b/merged_14b_cpt_lora
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:runs/cpt_run_14b/merged_14b_cpt_lora
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0
\ No newline at end of file
diff --git a/sft_qwen_14B/checkpoints/checkpoint-2500/adapter_config.json b/sft_qwen_14B/checkpoints/checkpoint-2500/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8ea271115c141fb10c6d899b06f46f21800e1ad6
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-2500/adapter_config.json
@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "runs/cpt_run_14b/merged_14b_cpt_lora",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/sft_qwen_14B/checkpoints/checkpoint-2500/adapter_model.safetensors b/sft_qwen_14B/checkpoints/checkpoint-2500/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..494fa3b872c6bce823c43af19481e06ef9ca3cde
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-2500/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be9580711ec346ace6d529831aa1885c08485e3841f57055b0bb9783a530ac14
+size 100715016
diff --git a/sft_qwen_14B/checkpoints/checkpoint-2500/optimizer.pt b/sft_qwen_14B/checkpoints/checkpoint-2500/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a7af783bd9fa4af56fabd3a6f6cc50fbe4b7ab35
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-2500/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f48f0a61449acbf6cb595fa231b8e2a5d5a08d8a1ce8639b35311b5b95adb22
+size 201650659
diff --git a/sft_qwen_14B/checkpoints/checkpoint-2500/rng_state.pth b/sft_qwen_14B/checkpoints/checkpoint-2500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8ec9bd6b199491c36693b293f2aaba5f7c35fdf9
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-2500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c6cf48875b5ffb30f6d449c0ad7793378c7b68f3e04492719377f35615e95c
+size 14645
diff --git a/sft_qwen_14B/checkpoints/checkpoint-2500/scheduler.pt b/sft_qwen_14B/checkpoints/checkpoint-2500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..43500d92728e45a937ab5db3f6b96389150f6639
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-2500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891dcd76bbab61fc7167559c72d346bfecbc331339a7dc5622e34b2bde10b46a
+size 1465
diff --git a/sft_qwen_14B/checkpoints/checkpoint-2500/trainer_state.json b/sft_qwen_14B/checkpoints/checkpoint-2500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..71846fe16ac78d726861f7ec04afdf03e5f5237d
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-2500/trainer_state.json
@@ -0,0 +1,8993 @@
+{
+  "best_global_step": 2500,
+  "best_metric": 0.8323014378547668,
+  "best_model_checkpoint": "runs/instruct_run_14b_v1/checkpoints/checkpoint-2500",
+  "epoch": 1.0785329018338727,
+  "eval_steps": 100,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008629989212513484,
+      "grad_norm": 0.36567428708076477,
+      "learning_rate": 1.7969451931716084e-07,
+      "loss": 1.6794371604919434,
+      "step": 2
+    },
+    {
+      "epoch": 0.001725997842502697,
+      "grad_norm": 0.4024646580219269,
+      "learning_rate": 5.390835579514825e-07,
+      "loss": 1.6853073835372925,
+      "step": 4
+    },
+    {
+      "epoch": 0.0025889967637540453,
+      "grad_norm": 0.40199393033981323,
+      "learning_rate": 8.984725965858042e-07,
+      "loss": 1.7621158361434937,
+      "step": 6
+    },
+    {
+      "epoch": 0.003451995685005394,
+      "grad_norm": 0.35409677028656006,
+      "learning_rate": 1.257861635220126e-06,
+      "loss": 1.633257269859314,
+      "step": 8
+    },
+    {
+      "epoch": 0.004314994606256742,
+      "grad_norm": 0.39087551832199097,
+      "learning_rate": 1.6172506738544475e-06,
+      "loss": 1.7374768257141113,
+      "step": 10
+    },
+    {
+      "epoch": 0.005177993527508091,
+      "grad_norm": 0.3586857318878174,
+      "learning_rate": 1.9766397124887693e-06,
+      "loss": 1.6955714225769043,
+      "step": 12
+    },
+    {
+      "epoch": 0.006040992448759439,
+      "grad_norm": 0.32755669951438904,
+      "learning_rate": 2.3360287511230908e-06,
+      "loss": 1.720664381980896,
+      "step": 14
+    },
+    {
+      "epoch": 0.006903991370010788,
+      "grad_norm": 0.4054872691631317,
+      "learning_rate": 2.6954177897574127e-06,
+      "loss": 1.6957035064697266,
+      "step": 16
+    },
+    {
+      "epoch": 0.007766990291262136,
+      "grad_norm": 0.37593814730644226,
+      "learning_rate": 3.0548068283917343e-06,
+      "loss": 1.7286947965621948,
+      "step": 18
+    },
+    {
+      "epoch": 0.008629989212513484,
+      "grad_norm": 0.3344813287258148,
+      "learning_rate": 3.414195867026056e-06,
+      "loss": 1.727295994758606,
+      "step": 20
+    },
+    {
+      "epoch": 0.009492988133764833,
+      "grad_norm": 0.357474148273468,
+      "learning_rate": 3.7735849056603773e-06,
+      "loss": 1.6727914810180664,
+      "step": 22
+    },
+    {
+      "epoch": 0.010355987055016181,
+      "grad_norm": 0.39115726947784424,
+      "learning_rate": 4.132973944294699e-06,
+      "loss": 1.6518884897232056,
+      "step": 24
+    },
+    {
+      "epoch": 0.01121898597626753,
+      "grad_norm": 0.4711727201938629,
+      "learning_rate": 4.492362982929021e-06,
+      "loss": 1.7868088483810425,
+      "step": 26
+    },
+    {
+      "epoch": 0.012081984897518877,
+      "grad_norm": 0.34112176299095154,
+      "learning_rate": 4.851752021563342e-06,
+      "loss": 1.6127634048461914,
+      "step": 28
+    },
+    {
+      "epoch": 0.012944983818770227,
+      "grad_norm": 0.5071991682052612,
+      "learning_rate": 5.211141060197664e-06,
+      "loss": 1.7858378887176514,
+      "step": 30
+    },
+    {
+      "epoch": 0.013807982740021575,
+      "grad_norm": 0.42048847675323486,
+      "learning_rate": 5.570530098831986e-06,
+      "loss": 1.7123326063156128,
+      "step": 32
+    },
+    {
+      "epoch": 0.014670981661272923,
+      "grad_norm": 0.48883870244026184,
+      "learning_rate": 5.929919137466308e-06,
+      "loss": 1.737749695777893,
+      "step": 34
+    },
+    {
+      "epoch": 0.015533980582524271,
+      "grad_norm": 0.3311465084552765,
+      "learning_rate": 6.289308176100629e-06,
+      "loss": 1.5578981637954712,
+      "step": 36
+    },
+    {
+      "epoch": 0.01639697950377562,
+      "grad_norm": 0.5178973078727722,
+      "learning_rate": 6.64869721473495e-06,
+      "loss": 1.719806432723999,
+      "step": 38
+    },
+    {
+      "epoch": 0.017259978425026967,
+      "grad_norm": 0.47097742557525635,
+      "learning_rate": 7.008086253369272e-06,
+      "loss": 1.728212833404541,
+      "step": 40
+    },
+    {
+      "epoch": 0.018122977346278317,
+      "grad_norm": 0.5051584243774414,
+      "learning_rate": 7.367475292003594e-06,
+      "loss": 1.6542466878890991,
+      "step": 42
+    },
+    {
+      "epoch": 0.018985976267529667,
+      "grad_norm": 0.4645111560821533,
+      "learning_rate": 7.726864330637915e-06,
+      "loss": 1.7087690830230713,
+      "step": 44
+    },
+    {
+      "epoch": 0.019848975188781013,
+      "grad_norm": 0.5184999704360962,
+      "learning_rate": 8.086253369272237e-06,
+      "loss": 1.7018946409225464,
+      "step": 46
+    },
+    {
+      "epoch": 0.020711974110032363,
+      "grad_norm": 0.4543815851211548,
+      "learning_rate": 8.44564240790656e-06,
+      "loss": 1.6818269491195679,
+      "step": 48
+    },
+    {
+      "epoch": 0.021574973031283712,
+      "grad_norm": 0.44411996006965637,
+      "learning_rate": 8.80503144654088e-06,
+      "loss": 1.5772877931594849,
+      "step": 50
+    },
+    {
+      "epoch": 0.02243797195253506,
+      "grad_norm": 0.3409404158592224,
+      "learning_rate": 9.164420485175203e-06,
+      "loss": 1.498152732849121,
+      "step": 52
+    },
+    {
+      "epoch": 0.02330097087378641,
+      "grad_norm": 0.42104434967041016,
+      "learning_rate": 9.523809523809523e-06,
+      "loss": 1.6189048290252686,
+      "step": 54
+    },
+    {
+      "epoch": 0.024163969795037755,
+      "grad_norm": 0.3756246268749237,
+      "learning_rate": 9.883198562443846e-06,
+      "loss": 1.4596441984176636,
+      "step": 56
+    },
+    {
+      "epoch": 0.025026968716289105,
+      "grad_norm": 0.36214128136634827,
+      "learning_rate": 1.0242587601078168e-05,
+      "loss": 1.503880500793457,
+      "step": 58
+    },
+    {
+      "epoch": 0.025889967637540454,
+      "grad_norm": 0.40893009305000305,
+      "learning_rate": 1.060197663971249e-05,
+      "loss": 1.5912823677062988,
+      "step": 60
+    },
+    {
+      "epoch": 0.0267529665587918,
+      "grad_norm": 0.28710272908210754,
+      "learning_rate": 1.0961365678346811e-05,
+      "loss": 1.2956721782684326,
+      "step": 62
+    },
+    {
+      "epoch": 0.02761596548004315,
+      "grad_norm": 0.304573118686676,
+      "learning_rate": 1.1320754716981132e-05,
+      "loss": 1.4648056030273438,
+      "step": 64
+    },
+    {
+      "epoch": 0.0284789644012945,
+      "grad_norm": 0.36523914337158203,
+      "learning_rate": 1.1680143755615454e-05,
+      "loss": 1.6078968048095703,
+      "step": 66
+    },
+    {
+      "epoch": 0.029341963322545846,
+      "grad_norm": 0.37929031252861023,
+      "learning_rate": 1.2039532794249775e-05,
+      "loss": 1.5969421863555908,
+      "step": 68
+    },
+    {
+      "epoch": 0.030204962243797196,
+      "grad_norm": 0.3053947389125824,
+      "learning_rate": 1.2398921832884097e-05,
+      "loss": 1.4312325716018677,
+      "step": 70
+    },
+    {
+      "epoch": 0.031067961165048542,
+      "grad_norm": 0.3028779923915863,
+      "learning_rate": 1.275831087151842e-05,
+      "loss": 1.4101300239562988,
+      "step": 72
+    },
+    {
+      "epoch": 0.03193096008629989,
+      "grad_norm": 0.29649803042411804,
+      "learning_rate": 1.3117699910152742e-05,
+      "loss": 1.4553817510604858,
+      "step": 74
+    },
+    {
+      "epoch": 0.03279395900755124,
+      "grad_norm": 0.26032644510269165,
+      "learning_rate": 1.3477088948787062e-05,
+      "loss": 1.4623000621795654,
+      "step": 76
+    },
+    {
+      "epoch": 0.03365695792880259,
+      "grad_norm": 0.33558446168899536,
+      "learning_rate": 1.3836477987421385e-05,
+      "loss": 1.5181745290756226,
+      "step": 78
+    },
+    {
+      "epoch": 0.034519956850053934,
+      "grad_norm": 0.28307804465293884,
+      "learning_rate": 1.4195867026055706e-05,
+      "loss": 1.4397861957550049,
+      "step": 80
+    },
+    {
+      "epoch": 0.035382955771305284,
+      "grad_norm": 0.3451690673828125,
+      "learning_rate": 1.455525606469003e-05,
+      "loss": 1.463841199874878,
+      "step": 82
+    },
+    {
+      "epoch": 0.036245954692556634,
+      "grad_norm": 0.3248669505119324,
+      "learning_rate": 1.4914645103324348e-05,
+      "loss": 1.3554227352142334,
+      "step": 84
+    },
+    {
+      "epoch": 0.037108953613807984,
+      "grad_norm": 0.2855011224746704,
+      "learning_rate": 1.527403414195867e-05,
+      "loss": 1.2810425758361816,
+      "step": 86
+    },
+    {
+      "epoch": 0.03797195253505933,
+      "grad_norm": 0.33365535736083984,
+      "learning_rate": 1.5633423180592992e-05,
+      "loss": 1.428163766860962,
+      "step": 88
+    },
+    {
+      "epoch": 0.038834951456310676,
+      "grad_norm": 0.34099438786506653,
+      "learning_rate": 1.5992812219227316e-05,
+      "loss": 1.3487578630447388,
+      "step": 90
+    },
+    {
+      "epoch": 0.039697950377562026,
+      "grad_norm": 0.39247506856918335,
+      "learning_rate": 1.6352201257861635e-05,
+      "loss": 1.30057954788208,
+      "step": 92
+    },
+    {
+      "epoch": 0.040560949298813376,
+      "grad_norm": 0.32692041993141174,
+      "learning_rate": 1.671159029649596e-05,
+      "loss": 1.2923580408096313,
+      "step": 94
+    },
+    {
+      "epoch": 0.041423948220064725,
+      "grad_norm": 0.43452519178390503,
+      "learning_rate": 1.707097933513028e-05,
+      "loss": 1.5002273321151733,
+      "step": 96
+    },
+    {
+      "epoch": 0.042286947141316075,
+      "grad_norm": 0.3251534402370453,
+      "learning_rate": 1.7430368373764602e-05,
+      "loss": 1.330254077911377,
+      "step": 98
+    },
+    {
+      "epoch": 0.043149946062567425,
+      "grad_norm": 0.3198273479938507,
+      "learning_rate": 1.778975741239892e-05,
+      "loss": 1.3054943084716797,
+      "step": 100
+    },
+    {
+      "epoch": 0.043149946062567425,
+      "eval_loss": 1.366738200187683,
+      "eval_runtime": 651.8198,
+      "eval_samples_per_second": 3.16,
+      "eval_steps_per_second": 3.16,
+      "step": 100
+    },
+    {
+      "epoch": 0.04401294498381877,
+      "grad_norm": 0.37364065647125244,
+      "learning_rate": 1.8149146451033245e-05,
+      "loss": 1.314281940460205,
+      "step": 102
+    },
+    {
+      "epoch": 0.04487594390507012,
+      "grad_norm": 0.39384758472442627,
+      "learning_rate": 1.8508535489667568e-05,
+      "loss": 1.2737246751785278,
+      "step": 104
+    },
+    {
+      "epoch": 0.04573894282632147,
+      "grad_norm": 0.3521905541419983,
+      "learning_rate": 1.8867924528301888e-05,
+      "loss": 1.3113226890563965,
+      "step": 106
+    },
+    {
+      "epoch": 0.04660194174757282,
+      "grad_norm": 0.33531463146209717,
+      "learning_rate": 1.9227313566936208e-05,
+      "loss": 1.3253653049468994,
+      "step": 108
+    },
+    {
+      "epoch": 0.04746494066882417,
+      "grad_norm": 0.35596340894699097,
+      "learning_rate": 1.958670260557053e-05,
+      "loss": 1.3236849308013916,
+      "step": 110
+    },
+    {
+      "epoch": 0.04832793959007551,
+      "grad_norm": 0.36028242111206055,
+      "learning_rate": 1.9946091644204854e-05,
+      "loss": 1.183128833770752,
+      "step": 112
+    },
+    {
+      "epoch": 0.04919093851132686,
+      "grad_norm": 0.42109814286231995,
+      "learning_rate": 2.0305480682839174e-05,
+      "loss": 1.2741888761520386,
+      "step": 114
+    },
+    {
+      "epoch": 0.05005393743257821,
+      "grad_norm": 0.39675939083099365,
+      "learning_rate": 2.0664869721473494e-05,
+      "loss": 1.3050109148025513,
+      "step": 116
+    },
+    {
+      "epoch": 0.05091693635382956,
+      "grad_norm": 0.4414141774177551,
+      "learning_rate": 2.1024258760107817e-05,
+      "loss": 1.2472094297409058,
+      "step": 118
+    },
+    {
+      "epoch": 0.05177993527508091,
+      "grad_norm": 0.42872729897499084,
+      "learning_rate": 2.138364779874214e-05,
+      "loss": 1.3338921070098877,
+      "step": 120
+    },
+    {
+      "epoch": 0.05264293419633225,
+      "grad_norm": 0.38336244225502014,
+      "learning_rate": 2.174303683737646e-05,
+      "loss": 1.322908878326416,
+      "step": 122
+    },
+    {
+      "epoch": 0.0535059331175836,
+      "grad_norm": 0.41046878695487976,
+      "learning_rate": 2.2102425876010783e-05,
+      "loss": 1.2169240713119507,
+      "step": 124
+    },
+    {
+      "epoch": 0.05436893203883495,
+      "grad_norm": 0.39460113644599915,
+      "learning_rate": 2.2461814914645103e-05,
+      "loss": 1.2085309028625488,
+      "step": 126
+    },
+    {
+      "epoch": 0.0552319309600863,
+      "grad_norm": 0.42829909920692444,
+      "learning_rate": 2.2821203953279426e-05,
+      "loss": 1.2969133853912354,
+      "step": 128
+    },
+    {
+      "epoch": 0.05609492988133765,
+      "grad_norm": 0.3940851390361786,
+      "learning_rate": 2.3180592991913746e-05,
+      "loss": 1.1892330646514893,
+      "step": 130
+    },
+    {
+      "epoch": 0.056957928802589,
+      "grad_norm": 0.45011839270591736,
+      "learning_rate": 2.353998203054807e-05,
+      "loss": 1.2082979679107666,
+      "step": 132
+    },
+    {
+      "epoch": 0.05782092772384034,
+      "grad_norm": 0.46059420704841614,
+      "learning_rate": 2.3899371069182393e-05,
+      "loss": 1.2388817071914673,
+      "step": 134
+    },
+    {
+      "epoch": 0.05868392664509169,
+      "grad_norm": 0.41085872054100037,
+      "learning_rate": 2.4258760107816713e-05,
+      "loss": 1.193917155265808,
+      "step": 136
+    },
+    {
+      "epoch": 0.05954692556634304,
+      "grad_norm": 0.4024205207824707,
+      "learning_rate": 2.4618149146451032e-05,
+      "loss": 1.1514034271240234,
+      "step": 138
+    },
+    {
+      "epoch": 0.06040992448759439,
+      "grad_norm": 0.3893793523311615,
+      "learning_rate": 2.4977538185085356e-05,
+      "loss": 1.1626157760620117,
+      "step": 140
+    },
+    {
+      "epoch": 0.06127292340884574,
+      "grad_norm": 0.4456317126750946,
+      "learning_rate": 2.5336927223719675e-05,
+      "loss": 1.1627076864242554,
+      "step": 142
+    },
+    {
+      "epoch": 0.062135922330097085,
+      "grad_norm": 0.5050215125083923,
+      "learning_rate": 2.5696316262354e-05,
+      "loss": 1.3038755655288696,
+      "step": 144
+    },
+    {
+      "epoch": 0.06299892125134844,
+      "grad_norm": 0.4071207642555237,
+      "learning_rate": 2.605570530098832e-05,
+      "loss": 1.1708844900131226,
+      "step": 146
+    },
+    {
+      "epoch": 0.06386192017259978,
+      "grad_norm": 0.4363228678703308,
+      "learning_rate": 2.641509433962264e-05,
+      "loss": 1.2149070501327515,
+      "step": 148
+    },
+    {
+      "epoch": 0.06472491909385113,
+      "grad_norm": 0.4436556398868561,
+      "learning_rate": 2.6774483378256965e-05,
+      "loss": 1.1942368745803833,
+      "step": 150
+    },
+    {
+      "epoch": 0.06558791801510248,
+      "grad_norm": 0.4068629741668701,
+      "learning_rate": 2.7133872416891288e-05,
+      "loss": 1.1799161434173584,
+      "step": 152
+    },
+    {
+      "epoch": 0.06645091693635383,
+      "grad_norm": 0.5291106700897217,
+      "learning_rate": 2.7493261455525608e-05,
+      "loss": 1.1832845211029053,
+      "step": 154
+    },
+    {
+      "epoch": 0.06731391585760518,
+      "grad_norm": 0.4410109221935272,
+      "learning_rate": 2.785265049415993e-05,
+      "loss": 1.1696993112564087,
+      "step": 156
+    },
+    {
+      "epoch": 0.06817691477885653,
+      "grad_norm": 0.4858371913433075,
+      "learning_rate": 2.8212039532794248e-05,
+      "loss": 1.2036973237991333,
+      "step": 158
+    },
+    {
+      "epoch": 0.06903991370010787,
+      "grad_norm": 0.45373693108558655,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 1.1145079135894775,
+      "step": 160
+    },
+    {
+      "epoch": 0.06990291262135923,
+      "grad_norm": 0.4881038963794708,
+      "learning_rate": 2.8930817610062894e-05,
+      "loss": 1.173502802848816,
+      "step": 162
+    },
+    {
+      "epoch": 0.07076591154261057,
+      "grad_norm": 0.576934814453125,
+      "learning_rate": 2.9290206648697217e-05,
+      "loss": 1.250414490699768,
+      "step": 164
+    },
+    {
+      "epoch": 0.07162891046386193,
+      "grad_norm": 0.4900001287460327,
+      "learning_rate": 2.9649595687331537e-05,
+      "loss": 1.0721495151519775,
+      "step": 166
+    },
+    {
+      "epoch": 0.07249190938511327,
+      "grad_norm": 0.4440019726753235,
+      "learning_rate": 3.000898472596586e-05,
+      "loss": 1.0689374208450317,
+      "step": 168
+    },
+    {
+      "epoch": 0.07335490830636461,
+      "grad_norm": 0.4267268180847168,
+      "learning_rate": 3.0368373764600184e-05,
+      "loss": 1.2095128297805786,
+      "step": 170
+    },
+    {
+      "epoch": 0.07421790722761597,
+      "grad_norm": 0.6062787771224976,
+      "learning_rate": 3.0727762803234503e-05,
+      "loss": 1.077776551246643,
+      "step": 172
+    },
+    {
+      "epoch": 0.07508090614886731,
+      "grad_norm": 0.49510180950164795,
+      "learning_rate": 3.108715184186882e-05,
+      "loss": 1.144006371498108,
+      "step": 174
+    },
+    {
+      "epoch": 0.07594390507011867,
+      "grad_norm": 0.4670701026916504,
+      "learning_rate": 3.144654088050314e-05,
+      "loss": 1.1663392782211304,
+      "step": 176
+    },
+    {
+      "epoch": 0.07680690399137001,
+      "grad_norm": 0.5615383386611938,
+      "learning_rate": 3.1805929919137466e-05,
+      "loss": 1.1665973663330078,
+      "step": 178
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "grad_norm": 0.47305551171302795,
+      "learning_rate": 3.216531895777179e-05,
+      "loss": 1.1337063312530518,
+      "step": 180
+    },
+    {
+      "epoch": 0.07853290183387271,
+      "grad_norm": 0.5127068758010864,
+      "learning_rate": 3.252470799640611e-05,
+      "loss": 1.072874903678894,
+      "step": 182
+    },
+    {
+      "epoch": 0.07939590075512405,
+      "grad_norm": 0.632448136806488,
+      "learning_rate": 3.2884097035040436e-05,
+      "loss": 1.1577240228652954,
+      "step": 184
+    },
+    {
+      "epoch": 0.08025889967637541,
+      "grad_norm": 0.4041025638580322,
+      "learning_rate": 3.324348607367476e-05,
+      "loss": 1.1186822652816772,
+      "step": 186
+    },
+    {
+      "epoch": 0.08112189859762675,
+      "grad_norm": 0.5239102244377136,
+      "learning_rate": 3.3602875112309076e-05,
+      "loss": 1.1468429565429688,
+      "step": 188
+    },
+    {
+      "epoch": 0.08198489751887811,
+      "grad_norm": 0.4486575424671173,
+      "learning_rate": 3.39622641509434e-05,
+      "loss": 1.0017019510269165,
+      "step": 190
+    },
+    {
+      "epoch": 0.08284789644012945,
+      "grad_norm": 0.4994317293167114,
+      "learning_rate": 3.4321653189577715e-05,
+      "loss": 1.1901532411575317,
+      "step": 192
+    },
+    {
+      "epoch": 0.0837108953613808,
+      "grad_norm": 0.5023699998855591,
+      "learning_rate": 3.468104222821204e-05,
+      "loss": 1.1398564577102661,
+      "step": 194
+    },
+    {
+      "epoch": 0.08457389428263215,
+      "grad_norm": 0.5077701807022095,
+      "learning_rate": 3.504043126684636e-05,
+      "loss": 1.1390413045883179,
+      "step": 196
+    },
+    {
+      "epoch": 0.0854368932038835,
+      "grad_norm": 0.5527892112731934,
+      "learning_rate": 3.5399820305480685e-05,
+      "loss": 1.1411432027816772,
+      "step": 198
+    },
+    {
+      "epoch": 0.08629989212513485,
+      "grad_norm": 0.5572488903999329,
+      "learning_rate": 3.575920934411501e-05,
+      "loss": 1.071260690689087,
+      "step": 200
+    },
+    {
+      "epoch": 0.08629989212513485,
+      "eval_loss": 1.1519012451171875,
+      "eval_runtime": 654.6055,
+      "eval_samples_per_second": 3.147,
+      "eval_steps_per_second": 3.147,
+      "step": 200
+    },
+    {
+      "epoch": 0.08716289104638619,
+      "grad_norm": 0.5134095549583435,
+      "learning_rate": 3.611859838274933e-05,
+      "loss": 1.138135552406311,
+      "step": 202
+    },
+    {
+      "epoch": 0.08802588996763754,
+      "grad_norm": 0.5166040658950806,
+      "learning_rate": 3.647798742138365e-05,
+      "loss": 1.111999273300171,
+      "step": 204
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.5336993336677551,
+      "learning_rate": 3.683737646001797e-05,
+      "loss": 1.1031352281570435,
+      "step": 206
+    },
+    {
+      "epoch": 0.08975188781014024,
+      "grad_norm": 0.8289600014686584,
+      "learning_rate": 3.7196765498652294e-05,
+      "loss": 1.0388667583465576,
+      "step": 208
+    },
+    {
+      "epoch": 0.09061488673139159,
+      "grad_norm": 0.47992637753486633,
+      "learning_rate": 3.755615453728661e-05,
+      "loss": 1.0950241088867188,
+      "step": 210
+    },
+    {
+      "epoch": 0.09147788565264293,
+      "grad_norm": 0.5629691481590271,
+      "learning_rate": 3.7915543575920934e-05,
+      "loss": 1.0361733436584473,
+      "step": 212
+    },
+    {
+      "epoch": 0.09234088457389428,
+      "grad_norm": 0.5515111684799194,
+      "learning_rate": 3.827493261455526e-05,
+      "loss": 1.0922447443008423,
+      "step": 214
+    },
+    {
+      "epoch": 0.09320388349514563,
+      "grad_norm": 0.5078643560409546,
+      "learning_rate": 3.863432165318958e-05,
+      "loss": 1.0866856575012207,
+      "step": 216
+    },
+    {
+      "epoch": 0.09406688241639698,
+      "grad_norm": 0.6046127676963806,
+      "learning_rate": 3.8993710691823904e-05,
+      "loss": 1.1231595277786255,
+      "step": 218
+    },
+    {
+      "epoch": 0.09492988133764833,
+      "grad_norm": 0.6255762577056885,
+      "learning_rate": 3.935309973045822e-05,
+      "loss": 1.099171757698059,
+      "step": 220
+    },
+    {
+      "epoch": 0.09579288025889968,
+      "grad_norm": 0.6036638021469116,
+      "learning_rate": 3.971248876909254e-05,
+      "loss": 1.0557761192321777,
+      "step": 222
+    },
+    {
+      "epoch": 0.09665587918015102,
+      "grad_norm": 0.5520529747009277,
+      "learning_rate": 4.0071877807726867e-05,
+      "loss": 1.0467877388000488,
+      "step": 224
+    },
+    {
+      "epoch": 0.09751887810140238,
+      "grad_norm": 0.5958684682846069,
+      "learning_rate": 4.043126684636119e-05,
+      "loss": 1.17941153049469,
+      "step": 226
+    },
+    {
+      "epoch": 0.09838187702265372,
+      "grad_norm": 0.5283281803131104,
+      "learning_rate": 4.079065588499551e-05,
+      "loss": 1.104217767715454,
+      "step": 228
+    },
+    {
+      "epoch": 0.09924487594390508,
+      "grad_norm": 0.5608792901039124,
+      "learning_rate": 4.115004492362983e-05,
+      "loss": 1.0900640487670898,
+      "step": 230
+    },
+    {
+      "epoch": 0.10010787486515642,
+      "grad_norm": 0.555964469909668,
+      "learning_rate": 4.150943396226415e-05,
+      "loss": 0.9887422323226929,
+      "step": 232
+    },
+    {
+      "epoch": 0.10097087378640776,
+      "grad_norm": 0.5875785946846008,
+      "learning_rate": 4.1868823000898476e-05,
+      "loss": 1.1298567056655884,
+      "step": 234
+    },
+    {
+      "epoch": 0.10183387270765912,
+      "grad_norm": 0.4544795751571655,
+      "learning_rate": 4.222821203953279e-05,
+      "loss": 1.0957067012786865,
+      "step": 236
+    },
+    {
+      "epoch": 0.10269687162891046,
+      "grad_norm": 0.564145565032959,
+      "learning_rate": 4.2587601078167116e-05,
+      "loss": 1.0328738689422607,
+      "step": 238
+    },
+    {
+      "epoch": 0.10355987055016182,
+      "grad_norm": 0.6285979747772217,
+      "learning_rate": 4.294699011680144e-05,
+      "loss": 1.1085515022277832,
+      "step": 240
+    },
+    {
+      "epoch": 0.10442286947141316,
+      "grad_norm": 0.6442288756370544,
+      "learning_rate": 4.330637915543576e-05,
+      "loss": 1.1291271448135376,
+      "step": 242
+    },
+    {
+      "epoch": 0.1052858683926645,
+      "grad_norm": 0.6137154698371887,
+      "learning_rate": 4.3665768194070085e-05,
+      "loss": 1.1759567260742188,
+      "step": 244
+    },
+    {
+      "epoch": 0.10614886731391586,
+      "grad_norm": 0.5906805992126465,
+      "learning_rate": 4.402515723270441e-05,
+      "loss": 1.148414969444275,
+      "step": 246
+    },
+    {
+      "epoch": 0.1070118662351672,
+      "grad_norm": 0.5382888913154602,
+      "learning_rate": 4.438454627133873e-05,
+      "loss": 1.0749616622924805,
+      "step": 248
+    },
+    {
+      "epoch": 0.10787486515641856,
+      "grad_norm": 0.6185492873191833,
+      "learning_rate": 4.474393530997305e-05,
+      "loss": 1.2235801219940186,
+      "step": 250
+    },
+    {
+      "epoch": 0.1087378640776699,
+      "grad_norm": 0.5981597900390625,
+      "learning_rate": 4.5103324348607365e-05,
+      "loss": 1.1390639543533325,
+      "step": 252
+    },
+    {
+      "epoch": 0.10960086299892124,
+      "grad_norm": 0.5664694905281067,
+      "learning_rate": 4.546271338724169e-05,
+      "loss": 1.171774983406067,
+      "step": 254
+    },
+    {
+      "epoch": 0.1104638619201726,
+      "grad_norm": 0.7071851491928101,
+      "learning_rate": 4.582210242587601e-05,
+      "loss": 1.1704237461090088,
+      "step": 256
+    },
+    {
+      "epoch": 0.11132686084142394,
+      "grad_norm": 0.5815614461898804,
+      "learning_rate": 4.6181491464510334e-05,
+      "loss": 1.0619677305221558,
+      "step": 258
+    },
+    {
+      "epoch": 0.1121898597626753,
+      "grad_norm": 0.6481915712356567,
+      "learning_rate": 4.654088050314466e-05,
+      "loss": 1.0824390649795532,
+      "step": 260
+    },
+    {
+      "epoch": 0.11305285868392664,
+      "grad_norm": 0.5988591313362122,
+      "learning_rate": 4.690026954177898e-05,
+      "loss": 1.087929606437683,
+      "step": 262
+    },
+    {
+      "epoch": 0.113915857605178,
+      "grad_norm": 0.6545296311378479,
+      "learning_rate": 4.7259658580413304e-05,
+      "loss": 1.0936195850372314,
+      "step": 264
+    },
+    {
+      "epoch": 0.11477885652642934,
+      "grad_norm": 0.5826204419136047,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 1.0433681011199951,
+      "step": 266
+    },
+    {
+      "epoch": 0.11564185544768069,
+      "grad_norm": 0.5907514095306396,
+      "learning_rate": 4.7978436657681944e-05,
+      "loss": 1.0719536542892456,
+      "step": 268
+    },
+    {
+      "epoch": 0.11650485436893204,
+      "grad_norm": 0.524394154548645,
+      "learning_rate": 4.833782569631627e-05,
+      "loss": 1.0231504440307617,
+      "step": 270
+    },
+    {
+      "epoch": 0.11736785329018339,
+      "grad_norm": 0.5472846031188965,
+      "learning_rate": 4.869721473495058e-05,
+      "loss": 0.9905915260314941,
+      "step": 272
+    },
+    {
+      "epoch": 0.11823085221143474,
+      "grad_norm": 0.727922260761261,
+      "learning_rate": 4.9056603773584906e-05,
+      "loss": 1.213677167892456,
+      "step": 274
+    },
+    {
+      "epoch": 0.11909385113268608,
+      "grad_norm": 0.6009684801101685,
+      "learning_rate": 4.941599281221923e-05,
+      "loss": 1.0052144527435303,
+      "step": 276
+    },
+    {
+      "epoch": 0.11995685005393743,
+      "grad_norm": 0.6564669013023376,
+      "learning_rate": 4.977538185085355e-05,
+      "loss": 1.108136773109436,
+      "step": 278
+    },
+    {
+      "epoch": 0.12081984897518878,
+      "grad_norm": 0.650074303150177,
+      "learning_rate": 5.013477088948787e-05,
+      "loss": 0.9700815677642822,
+      "step": 280
+    },
+    {
+      "epoch": 0.12168284789644013,
+      "grad_norm": 0.5772947072982788,
+      "learning_rate": 5.04941599281222e-05,
+      "loss": 1.038031816482544,
+      "step": 282
+    },
+    {
+      "epoch": 0.12254584681769148,
+      "grad_norm": 0.7293002009391785,
+      "learning_rate": 5.0853548966756516e-05,
+      "loss": 1.1063730716705322,
+      "step": 284
+    },
+    {
+      "epoch": 0.12340884573894283,
+      "grad_norm": 0.7937333583831787,
+      "learning_rate": 5.1212938005390846e-05,
+      "loss": 1.128495693206787,
+      "step": 286
+    },
+    {
+      "epoch": 0.12427184466019417,
+      "grad_norm": 0.48499324917793274,
+      "learning_rate": 5.157232704402516e-05,
+      "loss": 0.9438712000846863,
+      "step": 288
+    },
+    {
+      "epoch": 0.12513484358144553,
+      "grad_norm": 0.6010656952857971,
+      "learning_rate": 5.193171608265948e-05,
+      "loss": 1.0872881412506104,
+      "step": 290
+    },
+    {
+      "epoch": 0.12599784250269688,
+      "grad_norm": 0.6240811944007874,
+      "learning_rate": 5.22911051212938e-05,
+      "loss": 1.110992193222046,
+      "step": 292
+    },
+    {
+      "epoch": 0.1268608414239482,
+      "grad_norm": 0.7172768712043762,
+      "learning_rate": 5.265049415992812e-05,
+      "loss": 1.1109752655029297,
+      "step": 294
+    },
+    {
+      "epoch": 0.12772384034519957,
+      "grad_norm": 0.6442400217056274,
+      "learning_rate": 5.300988319856245e-05,
+      "loss": 1.05553138256073,
+      "step": 296
+    },
+    {
+      "epoch": 0.12858683926645093,
+      "grad_norm": 0.7074702382087708,
+      "learning_rate": 5.3369272237196765e-05,
+      "loss": 1.0717648267745972,
+      "step": 298
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "grad_norm": 0.5277591347694397,
+      "learning_rate": 5.3728661275831095e-05,
+      "loss": 0.9777541756629944,
+      "step": 300
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "eval_loss": 1.0977506637573242,
+      "eval_runtime": 662.1728,
+      "eval_samples_per_second": 3.111,
+      "eval_steps_per_second": 3.111,
+      "step": 300
+    },
+    {
+      "epoch": 0.1303128371089536,
+      "grad_norm": 0.7252246737480164,
+      "learning_rate": 5.408805031446541e-05,
+      "loss": 1.075905203819275,
+      "step": 302
+    },
+    {
+      "epoch": 0.13117583603020497,
+      "grad_norm": 0.7003294229507446,
+      "learning_rate": 5.444743935309974e-05,
+      "loss": 1.1117515563964844,
+      "step": 304
+    },
+    {
+      "epoch": 0.13203883495145632,
+      "grad_norm": 0.5878211259841919,
+      "learning_rate": 5.480682839173406e-05,
+      "loss": 1.0289191007614136,
+      "step": 306
+    },
+    {
+      "epoch": 0.13290183387270765,
+      "grad_norm": 0.7133644223213196,
+      "learning_rate": 5.5166217430368374e-05,
+      "loss": 1.0199183225631714,
+      "step": 308
+    },
+    {
+      "epoch": 0.133764832793959,
+      "grad_norm": 0.6098423600196838,
+      "learning_rate": 5.55256064690027e-05,
+      "loss": 1.0132375955581665,
+      "step": 310
+    },
+    {
+      "epoch": 0.13462783171521037,
+      "grad_norm": 0.6386916041374207,
+      "learning_rate": 5.5884995507637014e-05,
+      "loss": 1.1595754623413086,
+      "step": 312
+    },
+    {
+      "epoch": 0.1354908306364617,
+      "grad_norm": 0.6563469767570496,
+      "learning_rate": 5.6244384546271344e-05,
+      "loss": 1.0921307802200317,
+      "step": 314
+    },
+    {
+      "epoch": 0.13635382955771305,
+      "grad_norm": 0.6388015747070312,
+      "learning_rate": 5.660377358490566e-05,
+      "loss": 1.0200815200805664,
+      "step": 316
+    },
+    {
+      "epoch": 0.1372168284789644,
+      "grad_norm": 0.6026274561882019,
+      "learning_rate": 5.696316262353999e-05,
+      "loss": 0.9339485764503479,
+      "step": 318
+    },
+    {
+      "epoch": 0.13807982740021574,
+      "grad_norm": 0.619800865650177,
+      "learning_rate": 5.732255166217431e-05,
+      "loss": 1.0268478393554688,
+      "step": 320
+    },
+    {
+      "epoch": 0.1389428263214671,
+      "grad_norm": 0.5924715399742126,
+      "learning_rate": 5.768194070080862e-05,
+      "loss": 1.1394236087799072,
+      "step": 322
+    },
+    {
+      "epoch": 0.13980582524271845,
+      "grad_norm": 0.6829012036323547,
+      "learning_rate": 5.804132973944295e-05,
+      "loss": 1.002437949180603,
+      "step": 324
+    },
+    {
+      "epoch": 0.1406688241639698,
+      "grad_norm": 0.7012544274330139,
+      "learning_rate": 5.840071877807727e-05,
+      "loss": 1.132503628730774,
+      "step": 326
+    },
+    {
+      "epoch": 0.14153182308522114,
+      "grad_norm": 0.7921599745750427,
+      "learning_rate": 5.876010781671159e-05,
+      "loss": 1.1859129667282104,
+      "step": 328
+    },
+    {
+      "epoch": 0.1423948220064725,
+      "grad_norm": 0.6373353004455566,
+      "learning_rate": 5.9119496855345916e-05,
+      "loss": 1.0896776914596558,
+      "step": 330
+    },
+    {
+      "epoch": 0.14325782092772385,
+      "grad_norm": 0.6174030900001526,
+      "learning_rate": 5.947888589398024e-05,
+      "loss": 1.0691723823547363,
+      "step": 332
+    },
+    {
+      "epoch": 0.14412081984897518,
+      "grad_norm": 0.5110617280006409,
+      "learning_rate": 5.9838274932614556e-05,
+      "loss": 1.0144777297973633,
+      "step": 334
+    },
+    {
+      "epoch": 0.14498381877022654,
+      "grad_norm": 0.5580511093139648,
+      "learning_rate": 6.019766397124887e-05,
+      "loss": 0.9955101609230042,
+      "step": 336
+    },
+    {
+      "epoch": 0.1458468176914779,
+      "grad_norm": 0.6427345275878906,
+      "learning_rate": 6.05570530098832e-05,
+      "loss": 0.9863013625144958,
+      "step": 338
+    },
+    {
+      "epoch": 0.14670981661272922,
+      "grad_norm": 0.7464537024497986,
+      "learning_rate": 6.091644204851752e-05,
+      "loss": 1.0682255029678345,
+      "step": 340
+    },
+    {
+      "epoch": 0.14757281553398058,
+      "grad_norm": 0.599926769733429,
+      "learning_rate": 6.127583108715184e-05,
+      "loss": 1.034083366394043,
+      "step": 342
+    },
+    {
+      "epoch": 0.14843581445523193,
+      "grad_norm": 0.6320257186889648,
+      "learning_rate": 6.163522012578616e-05,
+      "loss": 1.0776089429855347,
+      "step": 344
+    },
+    {
+      "epoch": 0.1492988133764833,
+      "grad_norm": 0.6565091013908386,
+      "learning_rate": 6.199460916442049e-05,
+      "loss": 1.0493087768554688,
+      "step": 346
+    },
+    {
+      "epoch": 0.15016181229773462,
+      "grad_norm": 0.6512171626091003,
+      "learning_rate": 6.23539982030548e-05,
+      "loss": 1.0469218492507935,
+      "step": 348
+    },
+    {
+      "epoch": 0.15102481121898598,
+      "grad_norm": 0.8487282991409302,
+      "learning_rate": 6.271338724168913e-05,
+      "loss": 1.0985081195831299,
+      "step": 350
+    },
+    {
+      "epoch": 0.15188781014023733,
+      "grad_norm": 0.6718961596488953,
+      "learning_rate": 6.307277628032345e-05,
+      "loss": 1.0714176893234253,
+      "step": 352
+    },
+    {
+      "epoch": 0.15275080906148866,
+      "grad_norm": 0.8175088167190552,
+      "learning_rate": 6.343216531895777e-05,
+      "loss": 1.0599322319030762,
+      "step": 354
+    },
+    {
+      "epoch": 0.15361380798274002,
+      "grad_norm": 0.6359215378761292,
+      "learning_rate": 6.37915543575921e-05,
+      "loss": 0.9268131256103516,
+      "step": 356
+    },
+    {
+      "epoch": 0.15447680690399138,
+      "grad_norm": 0.6423866748809814,
+      "learning_rate": 6.415094339622641e-05,
+      "loss": 0.9838354587554932,
+      "step": 358
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "grad_norm": 0.6496716737747192,
+      "learning_rate": 6.451033243486074e-05,
+      "loss": 1.048566460609436,
+      "step": 360
+    },
+    {
+      "epoch": 0.15620280474649406,
+      "grad_norm": 0.6536920666694641,
+      "learning_rate": 6.486972147349506e-05,
+      "loss": 1.0910537242889404,
+      "step": 362
+    },
+    {
+      "epoch": 0.15706580366774542,
+      "grad_norm": 0.5832068920135498,
+      "learning_rate": 6.522911051212939e-05,
+      "loss": 0.9971448183059692,
+      "step": 364
+    },
+    {
+      "epoch": 0.15792880258899678,
+      "grad_norm": 0.6647719144821167,
+      "learning_rate": 6.558849955076371e-05,
+      "loss": 1.0496708154678345,
+      "step": 366
+    },
+    {
+      "epoch": 0.1587918015102481,
+      "grad_norm": 0.623252809047699,
+      "learning_rate": 6.594788858939802e-05,
+      "loss": 0.955894410610199,
+      "step": 368
+    },
+    {
+      "epoch": 0.15965480043149946,
+      "grad_norm": 0.6311860084533691,
+      "learning_rate": 6.630727762803235e-05,
+      "loss": 1.1304032802581787,
+      "step": 370
+    },
+    {
+      "epoch": 0.16051779935275082,
+      "grad_norm": 0.5306481122970581,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.8746405243873596,
+      "step": 372
+    },
+    {
+      "epoch": 0.16138079827400215,
+      "grad_norm": 0.6249631643295288,
+      "learning_rate": 6.7026055705301e-05,
+      "loss": 0.9104986786842346,
+      "step": 374
+    },
+    {
+      "epoch": 0.1622437971952535,
+      "grad_norm": 0.6243219971656799,
+      "learning_rate": 6.738544474393532e-05,
+      "loss": 1.043666124343872,
+      "step": 376
+    },
+    {
+      "epoch": 0.16310679611650486,
+      "grad_norm": 0.6833282113075256,
+      "learning_rate": 6.774483378256963e-05,
+      "loss": 1.0504906177520752,
+      "step": 378
+    },
+    {
+      "epoch": 0.16396979503775622,
+      "grad_norm": 0.7124452590942383,
+      "learning_rate": 6.810422282120395e-05,
+      "loss": 1.0608166456222534,
+      "step": 380
+    },
+    {
+      "epoch": 0.16483279395900755,
+      "grad_norm": 0.7520908117294312,
+      "learning_rate": 6.846361185983828e-05,
+      "loss": 1.1653732061386108,
+      "step": 382
+    },
+    {
+      "epoch": 0.1656957928802589,
+      "grad_norm": 0.7121814489364624,
+      "learning_rate": 6.88230008984726e-05,
+      "loss": 1.0626367330551147,
+      "step": 384
+    },
+    {
+      "epoch": 0.16655879180151026,
+      "grad_norm": 0.6825008988380432,
+      "learning_rate": 6.918238993710691e-05,
+      "loss": 1.012121319770813,
+      "step": 386
+    },
+    {
+      "epoch": 0.1674217907227616,
+      "grad_norm": 0.4922940135002136,
+      "learning_rate": 6.954177897574124e-05,
+      "loss": 1.0576211214065552,
+      "step": 388
+    },
+    {
+      "epoch": 0.16828478964401294,
+      "grad_norm": 0.6122089624404907,
+      "learning_rate": 6.990116801437556e-05,
+      "loss": 1.03916597366333,
+      "step": 390
+    },
+    {
+      "epoch": 0.1691477885652643,
+      "grad_norm": 0.6348981261253357,
+      "learning_rate": 7.026055705300989e-05,
+      "loss": 1.17647123336792,
+      "step": 392
+    },
+    {
+      "epoch": 0.17001078748651563,
+      "grad_norm": 0.6205878257751465,
+      "learning_rate": 7.06199460916442e-05,
+      "loss": 0.9095983505249023,
+      "step": 394
+    },
+    {
+      "epoch": 0.170873786407767,
+      "grad_norm": 0.61506187915802,
+      "learning_rate": 7.097933513027853e-05,
+      "loss": 1.082506775856018,
+      "step": 396
+    },
+    {
+      "epoch": 0.17173678532901834,
+      "grad_norm": 0.6481751799583435,
+      "learning_rate": 7.133872416891285e-05,
+      "loss": 1.0716280937194824,
+      "step": 398
+    },
+    {
+      "epoch": 0.1725997842502697,
+      "grad_norm": 0.4871014952659607,
+      "learning_rate": 7.169811320754717e-05,
+      "loss": 0.9616814851760864,
+      "step": 400
+    },
+    {
+      "epoch": 0.1725997842502697,
+      "eval_loss": 1.0649415254592896,
+      "eval_runtime": 668.6025,
+      "eval_samples_per_second": 3.081,
+      "eval_steps_per_second": 3.081,
+      "step": 400
+    },
+    {
+      "epoch": 0.17346278317152103,
+      "grad_norm": 0.5680040121078491,
+      "learning_rate": 7.20575022461815e-05,
+      "loss": 1.0475050210952759,
+      "step": 402
+    },
+    {
+      "epoch": 0.17432578209277239,
+      "grad_norm": 0.6417813897132874,
+      "learning_rate": 7.241689128481581e-05,
+      "loss": 0.9851161241531372,
+      "step": 404
+    },
+    {
+      "epoch": 0.17518878101402374,
+      "grad_norm": 0.6600468158721924,
+      "learning_rate": 7.277628032345014e-05,
+      "loss": 1.013339638710022,
+      "step": 406
+    },
+    {
+      "epoch": 0.17605177993527507,
+      "grad_norm": 0.6733932495117188,
+      "learning_rate": 7.313566936208446e-05,
+      "loss": 0.9346804022789001,
+      "step": 408
+    },
+    {
+      "epoch": 0.17691477885652643,
+      "grad_norm": 0.6812151074409485,
+      "learning_rate": 7.349505840071879e-05,
+      "loss": 0.9890368580818176,
+      "step": 410
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.6380394697189331,
+      "learning_rate": 7.385444743935311e-05,
+      "loss": 0.8787848949432373,
+      "step": 412
+    },
+    {
+      "epoch": 0.1786407766990291,
+      "grad_norm": 0.6004905700683594,
+      "learning_rate": 7.421383647798742e-05,
+      "loss": 1.0235728025436401,
+      "step": 414
+    },
+    {
+      "epoch": 0.17950377562028047,
+      "grad_norm": 0.6569193005561829,
+      "learning_rate": 7.457322551662175e-05,
+      "loss": 0.9972385168075562,
+      "step": 416
+    },
+    {
+      "epoch": 0.18036677454153183,
+      "grad_norm": 0.6761631369590759,
+      "learning_rate": 7.493261455525607e-05,
+      "loss": 0.9593698382377625,
+      "step": 418
+    },
+    {
+      "epoch": 0.18122977346278318,
+      "grad_norm": 0.7328561544418335,
+      "learning_rate": 7.529200359389039e-05,
+      "loss": 1.0426853895187378,
+      "step": 420
+    },
+    {
+      "epoch": 0.1820927723840345,
+      "grad_norm": 0.6256070137023926,
+      "learning_rate": 7.56513926325247e-05,
+      "loss": 0.9608182311058044,
+      "step": 422
+    },
+    {
+      "epoch": 0.18295577130528587,
+      "grad_norm": 1.2549844980239868,
+      "learning_rate": 7.601078167115903e-05,
+      "loss": 1.0162668228149414,
+      "step": 424
+    },
+    {
+      "epoch": 0.18381877022653723,
+      "grad_norm": 0.6751510500907898,
+      "learning_rate": 7.637017070979335e-05,
+      "loss": 1.130725383758545,
+      "step": 426
+    },
+    {
+      "epoch": 0.18468176914778855,
+      "grad_norm": 0.7029808163642883,
+      "learning_rate": 7.672955974842768e-05,
+      "loss": 1.0384817123413086,
+      "step": 428
+    },
+    {
+      "epoch": 0.1855447680690399,
+      "grad_norm": 0.644353449344635,
+      "learning_rate": 7.7088948787062e-05,
+      "loss": 1.017020344734192,
+      "step": 430
+    },
+    {
+      "epoch": 0.18640776699029127,
+      "grad_norm": 0.6784916520118713,
+      "learning_rate": 7.744833782569631e-05,
+      "loss": 1.005354404449463,
+      "step": 432
+    },
+    {
+      "epoch": 0.1872707659115426,
+      "grad_norm": 0.5989449620246887,
+      "learning_rate": 7.780772686433064e-05,
+      "loss": 1.026848316192627,
+      "step": 434
+    },
+    {
+      "epoch": 0.18813376483279395,
+      "grad_norm": 0.6502639651298523,
+      "learning_rate": 7.816711590296496e-05,
+      "loss": 0.9891080856323242,
+      "step": 436
+    },
+    {
+      "epoch": 0.1889967637540453,
+      "grad_norm": 0.6176205277442932,
+      "learning_rate": 7.852650494159929e-05,
+      "loss": 0.966316819190979,
+      "step": 438
+    },
+    {
+      "epoch": 0.18985976267529667,
+      "grad_norm": 0.6801626086235046,
+      "learning_rate": 7.88858939802336e-05,
+      "loss": 1.123063087463379,
+      "step": 440
+    },
+    {
+      "epoch": 0.190722761596548,
+      "grad_norm": 0.6718618273735046,
+      "learning_rate": 7.924528301886794e-05,
+      "loss": 1.0467073917388916,
+      "step": 442
+    },
+    {
+      "epoch": 0.19158576051779935,
+      "grad_norm": 0.6761009097099304,
+      "learning_rate": 7.960467205750225e-05,
+      "loss": 1.0952889919281006,
+      "step": 444
+    },
+    {
+      "epoch": 0.1924487594390507,
+      "grad_norm": 0.6356327533721924,
+      "learning_rate": 7.996406109613657e-05,
+      "loss": 0.954807698726654,
+      "step": 446
+    },
+    {
+      "epoch": 0.19331175836030204,
+      "grad_norm": 0.6798669695854187,
+      "learning_rate": 8.03234501347709e-05,
+      "loss": 0.9941422343254089,
+      "step": 448
+    },
+    {
+      "epoch": 0.1941747572815534,
+      "grad_norm": 0.6511302590370178,
+      "learning_rate": 8.068283917340521e-05,
+      "loss": 1.0351495742797852,
+      "step": 450
+    },
+    {
+      "epoch": 0.19503775620280475,
+      "grad_norm": 0.6061258912086487,
+      "learning_rate": 8.104222821203954e-05,
+      "loss": 1.00546133518219,
+      "step": 452
+    },
+    {
+      "epoch": 0.1959007551240561,
+      "grad_norm": 0.6278533935546875,
+      "learning_rate": 8.140161725067386e-05,
+      "loss": 1.0778460502624512,
+      "step": 454
+    },
+    {
+      "epoch": 0.19676375404530744,
+      "grad_norm": 0.6866298317909241,
+      "learning_rate": 8.176100628930818e-05,
+      "loss": 1.0344486236572266,
+      "step": 456
+    },
+    {
+      "epoch": 0.1976267529665588,
+      "grad_norm": 0.7338075041770935,
+      "learning_rate": 8.212039532794251e-05,
+      "loss": 1.0663033723831177,
+      "step": 458
+    },
+    {
+      "epoch": 0.19848975188781015,
+      "grad_norm": 0.6811459064483643,
+      "learning_rate": 8.247978436657682e-05,
+      "loss": 0.9665339589118958,
+      "step": 460
+    },
+    {
+      "epoch": 0.19935275080906148,
+      "grad_norm": 0.6779627799987793,
+      "learning_rate": 8.283917340521114e-05,
+      "loss": 1.024712324142456,
+      "step": 462
+    },
+    {
+      "epoch": 0.20021574973031284,
+      "grad_norm": 0.6486892700195312,
+      "learning_rate": 8.319856244384546e-05,
+      "loss": 0.9699305295944214,
+      "step": 464
+    },
+    {
+      "epoch": 0.2010787486515642,
+      "grad_norm": 0.7022278308868408,
+      "learning_rate": 8.355795148247979e-05,
+      "loss": 0.9540432095527649,
+      "step": 466
+    },
+    {
+      "epoch": 0.20194174757281552,
+      "grad_norm": 0.5922990441322327,
+      "learning_rate": 8.39173405211141e-05,
+      "loss": 0.9253339767456055,
+      "step": 468
+    },
+    {
+      "epoch": 0.20280474649406688,
+      "grad_norm": 0.7076792120933533,
+      "learning_rate": 8.427672955974843e-05,
+      "loss": 0.9987741112709045,
+      "step": 470
+    },
+    {
+      "epoch": 0.20366774541531824,
+      "grad_norm": 0.6491380333900452,
+      "learning_rate": 8.463611859838275e-05,
+      "loss": 1.0249329805374146,
+      "step": 472
+    },
+    {
+      "epoch": 0.2045307443365696,
+      "grad_norm": 0.6784211993217468,
+      "learning_rate": 8.499550763701708e-05,
+      "loss": 1.0577133893966675,
+      "step": 474
+    },
+    {
+      "epoch": 0.20539374325782092,
+      "grad_norm": 0.6453303694725037,
+      "learning_rate": 8.53548966756514e-05,
+      "loss": 1.1312458515167236,
+      "step": 476
+    },
+    {
+      "epoch": 0.20625674217907228,
+      "grad_norm": 0.7431377172470093,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 1.0592451095581055,
+      "step": 478
+    },
+    {
+      "epoch": 0.20711974110032363,
+      "grad_norm": 0.6097649931907654,
+      "learning_rate": 8.607367475292004e-05,
+      "loss": 0.9337235689163208,
+      "step": 480
+    },
+    {
+      "epoch": 0.20798274002157496,
+      "grad_norm": 0.5693124532699585,
+      "learning_rate": 8.643306379155436e-05,
+      "loss": 0.9088928699493408,
+      "step": 482
+    },
+    {
+      "epoch": 0.20884573894282632,
+      "grad_norm": 0.7377229332923889,
+      "learning_rate": 8.679245283018869e-05,
+      "loss": 1.0729358196258545,
+      "step": 484
+    },
+    {
+      "epoch": 0.20970873786407768,
+      "grad_norm": 0.7399470210075378,
+      "learning_rate": 8.7151841868823e-05,
+      "loss": 1.0428457260131836,
+      "step": 486
+    },
+    {
+      "epoch": 0.210571736785329,
+      "grad_norm": 0.677052915096283,
+      "learning_rate": 8.751123090745734e-05,
+      "loss": 0.9940266013145447,
+      "step": 488
+    },
+    {
+      "epoch": 0.21143473570658036,
+      "grad_norm": 0.7126721739768982,
+      "learning_rate": 8.787061994609165e-05,
+      "loss": 1.011808156967163,
+      "step": 490
+    },
+    {
+      "epoch": 0.21229773462783172,
+      "grad_norm": 0.6663792729377747,
+      "learning_rate": 8.823000898472597e-05,
+      "loss": 1.0054185390472412,
+      "step": 492
+    },
+    {
+      "epoch": 0.21316073354908308,
+      "grad_norm": 0.6661092042922974,
+      "learning_rate": 8.85893980233603e-05,
+      "loss": 1.0167138576507568,
+      "step": 494
+    },
+    {
+      "epoch": 0.2140237324703344,
+      "grad_norm": 0.6975740194320679,
+      "learning_rate": 8.894878706199461e-05,
+      "loss": 1.1470818519592285,
+      "step": 496
+    },
+    {
+      "epoch": 0.21488673139158576,
+      "grad_norm": 0.6594390869140625,
+      "learning_rate": 8.930817610062893e-05,
+      "loss": 0.9619631171226501,
+      "step": 498
+    },
+    {
+      "epoch": 0.21574973031283712,
+      "grad_norm": 0.7216679453849792,
+      "learning_rate": 8.966756513926325e-05,
+      "loss": 0.9971368312835693,
+      "step": 500
+    },
+    {
+      "epoch": 0.21574973031283712,
+      "eval_loss": 1.0417571067810059,
+      "eval_runtime": 659.3112,
+      "eval_samples_per_second": 3.124,
+      "eval_steps_per_second": 3.124,
+      "step": 500
+    },
+    {
+      "epoch": 0.21661272923408845,
+      "grad_norm": 0.6188210844993591,
+      "learning_rate": 9.002695417789758e-05,
+      "loss": 1.0307213068008423,
+      "step": 502
+    },
+    {
+      "epoch": 0.2174757281553398,
+      "grad_norm": 0.6716445088386536,
+      "learning_rate": 9.03863432165319e-05,
+      "loss": 1.0188794136047363,
+      "step": 504
+    },
+    {
+      "epoch": 0.21833872707659116,
+      "grad_norm": 0.6790863275527954,
+      "learning_rate": 9.074573225516622e-05,
+      "loss": 0.9764845967292786,
+      "step": 506
+    },
+    {
+      "epoch": 0.2192017259978425,
+      "grad_norm": 0.6764960289001465,
+      "learning_rate": 9.110512129380054e-05,
+      "loss": 0.948829174041748,
+      "step": 508
+    },
+    {
+      "epoch": 0.22006472491909385,
+      "grad_norm": 0.6210965514183044,
+      "learning_rate": 9.146451033243486e-05,
+      "loss": 1.008013129234314,
+      "step": 510
+    },
+    {
+      "epoch": 0.2209277238403452,
+      "grad_norm": 0.7739297747612,
+      "learning_rate": 9.182389937106919e-05,
+      "loss": 1.1662557125091553,
+      "step": 512
+    },
+    {
+      "epoch": 0.22179072276159656,
+      "grad_norm": 0.7055562138557434,
+      "learning_rate": 9.21832884097035e-05,
+      "loss": 1.0325161218643188,
+      "step": 514
+    },
+    {
+      "epoch": 0.2226537216828479,
+      "grad_norm": 0.6079210042953491,
+      "learning_rate": 9.254267744833783e-05,
+      "loss": 1.00056791305542,
+      "step": 516
+    },
+    {
+      "epoch": 0.22351672060409924,
+      "grad_norm": 0.5974318981170654,
+      "learning_rate": 9.290206648697215e-05,
+      "loss": 0.9422364234924316,
+      "step": 518
+    },
+    {
+      "epoch": 0.2243797195253506,
+      "grad_norm": 0.5963430404663086,
+      "learning_rate": 9.326145552560648e-05,
+      "loss": 0.936336100101471,
+      "step": 520
+    },
+    {
+      "epoch": 0.22524271844660193,
+      "grad_norm": 0.6823658347129822,
+      "learning_rate": 9.36208445642408e-05,
+      "loss": 1.0538607835769653,
+      "step": 522
+    },
+    {
+      "epoch": 0.2261057173678533,
+      "grad_norm": 0.6409855484962463,
+      "learning_rate": 9.398023360287511e-05,
+      "loss": 1.0483653545379639,
+      "step": 524
+    },
+    {
+      "epoch": 0.22696871628910464,
+      "grad_norm": 0.6867254376411438,
+      "learning_rate": 9.433962264150944e-05,
+      "loss": 0.9668049812316895,
+      "step": 526
+    },
+    {
+      "epoch": 0.227831715210356,
+      "grad_norm": 0.5690792798995972,
+      "learning_rate": 9.469901168014376e-05,
+      "loss": 1.008763313293457,
+      "step": 528
+    },
+    {
+      "epoch": 0.22869471413160733,
+      "grad_norm": 0.5964897274971008,
+      "learning_rate": 9.505840071877809e-05,
+      "loss": 1.0816441774368286,
+      "step": 530
+    },
+    {
+      "epoch": 0.2295577130528587,
+      "grad_norm": 0.627419114112854,
+      "learning_rate": 9.54177897574124e-05,
+      "loss": 0.9265700578689575,
+      "step": 532
+    },
+    {
+      "epoch": 0.23042071197411004,
+      "grad_norm": 0.5862151980400085,
+      "learning_rate": 9.577717879604674e-05,
+      "loss": 0.9804646372795105,
+      "step": 534
+    },
+    {
+      "epoch": 0.23128371089536137,
+      "grad_norm": 0.5573718547821045,
+      "learning_rate": 9.613656783468105e-05,
+      "loss": 0.9627988934516907,
+      "step": 536
+    },
+    {
+      "epoch": 0.23214670981661273,
+      "grad_norm": 0.6705166101455688,
+      "learning_rate": 9.649595687331537e-05,
+      "loss": 1.0012824535369873,
+      "step": 538
+    },
+    {
+      "epoch": 0.23300970873786409,
+      "grad_norm": 0.6251236796379089,
+      "learning_rate": 9.685534591194969e-05,
+      "loss": 0.9568162560462952,
+      "step": 540
+    },
+    {
+      "epoch": 0.23387270765911541,
+      "grad_norm": 0.6466493010520935,
+      "learning_rate": 9.7214734950584e-05,
+      "loss": 1.031549334526062,
+      "step": 542
+    },
+    {
+      "epoch": 0.23473570658036677,
+      "grad_norm": 0.5183866024017334,
+      "learning_rate": 9.757412398921833e-05,
+      "loss": 0.8603643774986267,
+      "step": 544
+    },
+    {
+      "epoch": 0.23559870550161813,
+      "grad_norm": 0.6725775599479675,
+      "learning_rate": 9.793351302785265e-05,
+      "loss": 1.0365077257156372,
+      "step": 546
+    },
+    {
+      "epoch": 0.23646170442286948,
+      "grad_norm": 0.5972357988357544,
+      "learning_rate": 9.829290206648698e-05,
+      "loss": 0.9304701089859009,
+      "step": 548
+    },
+    {
+      "epoch": 0.2373247033441208,
+      "grad_norm": 0.5319957733154297,
+      "learning_rate": 9.86522911051213e-05,
+      "loss": 0.9575805068016052,
+      "step": 550
+    },
+    {
+      "epoch": 0.23818770226537217,
+      "grad_norm": 0.6502835750579834,
+      "learning_rate": 9.901168014375562e-05,
+      "loss": 1.0307214260101318,
+      "step": 552
+    },
+    {
+      "epoch": 0.23905070118662353,
+      "grad_norm": 0.6734047532081604,
+      "learning_rate": 9.937106918238994e-05,
+      "loss": 1.05185067653656,
+      "step": 554
+    },
+    {
+      "epoch": 0.23991370010787486,
+      "grad_norm": 0.5667978525161743,
+      "learning_rate": 9.973045822102426e-05,
+      "loss": 1.0190176963806152,
+      "step": 556
+    },
+    {
+      "epoch": 0.2407766990291262,
+      "grad_norm": 0.6370418667793274,
+      "learning_rate": 0.00010008984725965857,
+      "loss": 1.076182246208191,
+      "step": 558
+    },
+    {
+      "epoch": 0.24163969795037757,
+      "grad_norm": 0.689719021320343,
+      "learning_rate": 0.0001004492362982929,
+      "loss": 1.0408724546432495,
+      "step": 560
+    },
+    {
+      "epoch": 0.2425026968716289,
+      "grad_norm": 0.6304254531860352,
+      "learning_rate": 0.00010080862533692723,
+      "loss": 0.9869902729988098,
+      "step": 562
+    },
+    {
+      "epoch": 0.24336569579288025,
+      "grad_norm": 0.6797420382499695,
+      "learning_rate": 0.00010116801437556156,
+      "loss": 1.0198370218276978,
+      "step": 564
+    },
+    {
+      "epoch": 0.2442286947141316,
+      "grad_norm": 0.5993657112121582,
+      "learning_rate": 0.00010152740341419587,
+      "loss": 0.9947441816329956,
+      "step": 566
+    },
+    {
+      "epoch": 0.24509169363538297,
+      "grad_norm": 0.6369836330413818,
+      "learning_rate": 0.0001018867924528302,
+      "loss": 0.9722896814346313,
+      "step": 568
+    },
+    {
+      "epoch": 0.2459546925566343,
+      "grad_norm": 0.6942457556724548,
+      "learning_rate": 0.00010224618149146453,
+      "loss": 0.9716570973396301,
+      "step": 570
+    },
+    {
+      "epoch": 0.24681769147788565,
+      "grad_norm": 0.5403370261192322,
+      "learning_rate": 0.00010260557053009883,
+      "loss": 0.9797524213790894,
+      "step": 572
+    },
+    {
+      "epoch": 0.247680690399137,
+      "grad_norm": 0.5207529067993164,
+      "learning_rate": 0.00010296495956873316,
+      "loss": 0.985367476940155,
+      "step": 574
+    },
+    {
+      "epoch": 0.24854368932038834,
+      "grad_norm": 0.6751103401184082,
+      "learning_rate": 0.00010332434860736748,
+      "loss": 1.075042724609375,
+      "step": 576
+    },
+    {
+      "epoch": 0.2494066882416397,
+      "grad_norm": 0.565331220626831,
+      "learning_rate": 0.0001036837376460018,
+      "loss": 0.9273878335952759,
+      "step": 578
+    },
+    {
+      "epoch": 0.25026968716289105,
+      "grad_norm": 0.6858948469161987,
+      "learning_rate": 0.00010404312668463612,
+      "loss": 0.9872279763221741,
+      "step": 580
+    },
+    {
+      "epoch": 0.2511326860841424,
+      "grad_norm": 0.7091426253318787,
+      "learning_rate": 0.00010440251572327044,
+      "loss": 1.0038671493530273,
+      "step": 582
+    },
+    {
+      "epoch": 0.25199568500539377,
+      "grad_norm": 0.6493771076202393,
+      "learning_rate": 0.00010476190476190477,
+      "loss": 1.0109868049621582,
+      "step": 584
+    },
+    {
+      "epoch": 0.25285868392664507,
+      "grad_norm": 0.6107586622238159,
+      "learning_rate": 0.00010512129380053907,
+      "loss": 1.0020402669906616,
+      "step": 586
+    },
+    {
+      "epoch": 0.2537216828478964,
+      "grad_norm": 0.6878048181533813,
+      "learning_rate": 0.0001054806828391734,
+      "loss": 0.961039662361145,
+      "step": 588
+    },
+    {
+      "epoch": 0.2545846817691478,
+      "grad_norm": 0.664034903049469,
+      "learning_rate": 0.00010584007187780773,
+      "loss": 0.9725209474563599,
+      "step": 590
+    },
+    {
+      "epoch": 0.25544768069039914,
+      "grad_norm": 0.6399680376052856,
+      "learning_rate": 0.00010619946091644206,
+      "loss": 0.9907437562942505,
+      "step": 592
+    },
+    {
+      "epoch": 0.2563106796116505,
+      "grad_norm": 0.6163286566734314,
+      "learning_rate": 0.00010655884995507636,
+      "loss": 0.9650095701217651,
+      "step": 594
+    },
+    {
+      "epoch": 0.25717367853290185,
+      "grad_norm": 0.6008322238922119,
+      "learning_rate": 0.0001069182389937107,
+      "loss": 1.0102758407592773,
+      "step": 596
+    },
+    {
+      "epoch": 0.2580366774541532,
+      "grad_norm": 0.6752071380615234,
+      "learning_rate": 0.00010727762803234502,
+      "loss": 0.9101885557174683,
+      "step": 598
+    },
+    {
+      "epoch": 0.2588996763754045,
+      "grad_norm": 0.6789175868034363,
+      "learning_rate": 0.00010763701707097935,
+      "loss": 1.0461398363113403,
+      "step": 600
+    },
+    {
+      "epoch": 0.2588996763754045,
+      "eval_loss": 1.021111011505127,
+      "eval_runtime": 648.1611,
+      "eval_samples_per_second": 3.178,
+      "eval_steps_per_second": 3.178,
+      "step": 600
+    },
+    {
+      "epoch": 0.25976267529665586,
+      "grad_norm": 0.5660730600357056,
+      "learning_rate": 0.00010799640610961366,
+      "loss": 0.9582418203353882,
+      "step": 602
+    },
+    {
+      "epoch": 0.2606256742179072,
+      "grad_norm": 0.6726544499397278,
+      "learning_rate": 0.00010835579514824799,
+      "loss": 1.0763746500015259,
+      "step": 604
+    },
+    {
+      "epoch": 0.2614886731391586,
+      "grad_norm": 0.6068508625030518,
+      "learning_rate": 0.00010871518418688232,
+      "loss": 1.0432032346725464,
+      "step": 606
+    },
+    {
+      "epoch": 0.26235167206040994,
+      "grad_norm": 0.5731637477874756,
+      "learning_rate": 0.00010907457322551662,
+      "loss": 0.9830516576766968,
+      "step": 608
+    },
+    {
+      "epoch": 0.2632146709816613,
+      "grad_norm": 0.6777567267417908,
+      "learning_rate": 0.00010943396226415095,
+      "loss": 1.0442042350769043,
+      "step": 610
+    },
+    {
+      "epoch": 0.26407766990291265,
+      "grad_norm": 0.6372506618499756,
+      "learning_rate": 0.00010979335130278528,
+      "loss": 1.0001944303512573,
+      "step": 612
+    },
+    {
+      "epoch": 0.26494066882416395,
+      "grad_norm": 0.6606221795082092,
+      "learning_rate": 0.0001101527403414196,
+      "loss": 1.035884141921997,
+      "step": 614
+    },
+    {
+      "epoch": 0.2658036677454153,
+      "grad_norm": 0.6083229780197144,
+      "learning_rate": 0.00011051212938005391,
+      "loss": 0.9403397440910339,
+      "step": 616
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.6318517923355103,
+      "learning_rate": 0.00011087151841868823,
+      "loss": 0.9274454116821289,
+      "step": 618
+    },
+    {
+      "epoch": 0.267529665587918,
+      "grad_norm": 0.628190279006958,
+      "learning_rate": 0.00011123090745732256,
+      "loss": 0.9883754253387451,
+      "step": 620
+    },
+    {
+      "epoch": 0.2683926645091694,
+      "grad_norm": 0.5961961150169373,
+      "learning_rate": 0.00011159029649595688,
+      "loss": 1.0317535400390625,
+      "step": 622
+    },
+    {
+      "epoch": 0.26925566343042073,
+      "grad_norm": 0.5995341539382935,
+      "learning_rate": 0.00011194968553459119,
+      "loss": 0.9776126742362976,
+      "step": 624
+    },
+    {
+      "epoch": 0.27011866235167203,
+      "grad_norm": 0.6639334559440613,
+      "learning_rate": 0.00011230907457322552,
+      "loss": 1.0112378597259521,
+      "step": 626
+    },
+    {
+      "epoch": 0.2709816612729234,
+      "grad_norm": 0.6348621249198914,
+      "learning_rate": 0.00011266846361185985,
+      "loss": 1.0553804636001587,
+      "step": 628
+    },
+    {
+      "epoch": 0.27184466019417475,
+      "grad_norm": 0.5929805040359497,
+      "learning_rate": 0.00011302785265049416,
+      "loss": 1.025888442993164,
+      "step": 630
+    },
+    {
+      "epoch": 0.2727076591154261,
+      "grad_norm": 0.6052366495132446,
+      "learning_rate": 0.00011338724168912849,
+      "loss": 1.02956223487854,
+      "step": 632
+    },
+    {
+      "epoch": 0.27357065803667746,
+      "grad_norm": 0.6494882106781006,
+      "learning_rate": 0.00011374663072776282,
+      "loss": 0.989752471446991,
+      "step": 634
+    },
+    {
+      "epoch": 0.2744336569579288,
+      "grad_norm": 0.6005767583847046,
+      "learning_rate": 0.00011410601976639712,
+      "loss": 1.0030683279037476,
+      "step": 636
+    },
+    {
+      "epoch": 0.2752966558791802,
+      "grad_norm": 0.6478356122970581,
+      "learning_rate": 0.00011446540880503145,
+      "loss": 1.002000093460083,
+      "step": 638
+    },
+    {
+      "epoch": 0.2761596548004315,
+      "grad_norm": 0.5804725289344788,
+      "learning_rate": 0.00011482479784366578,
+      "loss": 0.9807654023170471,
+      "step": 640
+    },
+    {
+      "epoch": 0.27702265372168283,
+      "grad_norm": 0.632530689239502,
+      "learning_rate": 0.00011518418688230011,
+      "loss": 0.9841892123222351,
+      "step": 642
+    },
+    {
+      "epoch": 0.2778856526429342,
+      "grad_norm": 0.5340113639831543,
+      "learning_rate": 0.00011554357592093441,
+      "loss": 0.8902478814125061,
+      "step": 644
+    },
+    {
+      "epoch": 0.27874865156418555,
+      "grad_norm": 0.5901665091514587,
+      "learning_rate": 0.00011590296495956874,
+      "loss": 0.9019404649734497,
+      "step": 646
+    },
+    {
+      "epoch": 0.2796116504854369,
+      "grad_norm": 0.666589617729187,
+      "learning_rate": 0.00011626235399820307,
+      "loss": 0.9384423494338989,
+      "step": 648
+    },
+    {
+      "epoch": 0.28047464940668826,
+      "grad_norm": 0.7000334858894348,
+      "learning_rate": 0.00011662174303683737,
+      "loss": 1.0666629076004028,
+      "step": 650
+    },
+    {
+      "epoch": 0.2813376483279396,
+      "grad_norm": 0.663663923740387,
+      "learning_rate": 0.0001169811320754717,
+      "loss": 1.000019907951355,
+      "step": 652
+    },
+    {
+      "epoch": 0.2822006472491909,
+      "grad_norm": 0.6097694039344788,
+      "learning_rate": 0.00011734052111410603,
+      "loss": 0.9450293183326721,
+      "step": 654
+    },
+    {
+      "epoch": 0.2830636461704423,
+      "grad_norm": 0.6130967140197754,
+      "learning_rate": 0.00011769991015274035,
+      "loss": 0.9480894207954407,
+      "step": 656
+    },
+    {
+      "epoch": 0.28392664509169363,
+      "grad_norm": 0.7091249227523804,
+      "learning_rate": 0.00011805929919137467,
+      "loss": 1.1377143859863281,
+      "step": 658
+    },
+    {
+      "epoch": 0.284789644012945,
+      "grad_norm": 0.6556766629219055,
+      "learning_rate": 0.00011841868823000898,
+      "loss": 0.9421243667602539,
+      "step": 660
+    },
+    {
+      "epoch": 0.28565264293419634,
+      "grad_norm": 0.6682968735694885,
+      "learning_rate": 0.00011877807726864331,
+      "loss": 0.9726828336715698,
+      "step": 662
+    },
+    {
+      "epoch": 0.2865156418554477,
+      "grad_norm": 0.5224708914756775,
+      "learning_rate": 0.00011913746630727762,
+      "loss": 0.8996511697769165,
+      "step": 664
+    },
+    {
+      "epoch": 0.287378640776699,
+      "grad_norm": 0.5914195775985718,
+      "learning_rate": 0.00011949685534591195,
+      "loss": 0.9679517149925232,
+      "step": 666
+    },
+    {
+      "epoch": 0.28824163969795036,
+      "grad_norm": 0.6175519824028015,
+      "learning_rate": 0.00011985624438454628,
+      "loss": 0.8743209838867188,
+      "step": 668
+    },
+    {
+      "epoch": 0.2891046386192017,
+      "grad_norm": 0.6019226312637329,
+      "learning_rate": 0.0001202156334231806,
+      "loss": 0.9741992354393005,
+      "step": 670
+    },
+    {
+      "epoch": 0.28996763754045307,
+      "grad_norm": 0.6080542206764221,
+      "learning_rate": 0.00012057502246181491,
+      "loss": 0.9516472816467285,
+      "step": 672
+    },
+    {
+      "epoch": 0.29083063646170443,
+      "grad_norm": 0.5885615944862366,
+      "learning_rate": 0.00012093441150044924,
+      "loss": 1.122761607170105,
+      "step": 674
+    },
+    {
+      "epoch": 0.2916936353829558,
+      "grad_norm": 0.6635209918022156,
+      "learning_rate": 0.00012129380053908357,
+      "loss": 1.0105189085006714,
+      "step": 676
+    },
+    {
+      "epoch": 0.29255663430420714,
+      "grad_norm": 0.5805009007453918,
+      "learning_rate": 0.0001216531895777179,
+      "loss": 0.906292200088501,
+      "step": 678
+    },
+    {
+      "epoch": 0.29341963322545844,
+      "grad_norm": 0.5980029702186584,
+      "learning_rate": 0.0001220125786163522,
+      "loss": 1.009568691253662,
+      "step": 680
+    },
+    {
+      "epoch": 0.2942826321467098,
+      "grad_norm": 0.6797705292701721,
+      "learning_rate": 0.00012237196765498652,
+      "loss": 1.0373667478561401,
+      "step": 682
+    },
+    {
+      "epoch": 0.29514563106796116,
+      "grad_norm": 0.6280547976493835,
+      "learning_rate": 0.00012273135669362085,
+      "loss": 0.9758188724517822,
+      "step": 684
+    },
+    {
+      "epoch": 0.2960086299892125,
+      "grad_norm": 0.511608898639679,
+      "learning_rate": 0.00012309074573225515,
+      "loss": 0.9111692905426025,
+      "step": 686
+    },
+    {
+      "epoch": 0.29687162891046387,
+      "grad_norm": 0.5781835317611694,
+      "learning_rate": 0.00012345013477088948,
+      "loss": 0.8865921497344971,
+      "step": 688
+    },
+    {
+      "epoch": 0.2977346278317152,
+      "grad_norm": 0.6514166593551636,
+      "learning_rate": 0.0001238095238095238,
+      "loss": 0.9768189191818237,
+      "step": 690
+    },
+    {
+      "epoch": 0.2985976267529666,
+      "grad_norm": 0.6109189987182617,
+      "learning_rate": 0.00012416891284815814,
+      "loss": 0.9991607069969177,
+      "step": 692
+    },
+    {
+      "epoch": 0.2994606256742179,
+      "grad_norm": 0.6598902344703674,
+      "learning_rate": 0.00012452830188679244,
+      "loss": 0.9548360705375671,
+      "step": 694
+    },
+    {
+      "epoch": 0.30032362459546924,
+      "grad_norm": 0.5633156895637512,
+      "learning_rate": 0.00012488769092542677,
+      "loss": 0.992988109588623,
+      "step": 696
+    },
+    {
+      "epoch": 0.3011866235167206,
+      "grad_norm": 0.6098802089691162,
+      "learning_rate": 0.0001252470799640611,
+      "loss": 0.9709890484809875,
+      "step": 698
+    },
+    {
+      "epoch": 0.30204962243797195,
+      "grad_norm": 0.6197102665901184,
+      "learning_rate": 0.0001256064690026954,
+      "loss": 1.018282175064087,
+      "step": 700
+    },
+    {
+      "epoch": 0.30204962243797195,
+      "eval_loss": 1.0030721426010132,
+      "eval_runtime": 655.4533,
+      "eval_samples_per_second": 3.143,
+      "eval_steps_per_second": 3.143,
+      "step": 700
+    },
+    {
+      "epoch": 0.3029126213592233,
+      "grad_norm": 0.5817480683326721,
+      "learning_rate": 0.00012596585804132974,
+      "loss": 0.9147283434867859,
+      "step": 702
+    },
+    {
+      "epoch": 0.30377562028047467,
+      "grad_norm": 0.5976696014404297,
+      "learning_rate": 0.00012632524707996407,
+      "loss": 0.9318362474441528,
+      "step": 704
+    },
+    {
+      "epoch": 0.304638619201726,
+      "grad_norm": 0.6389723420143127,
+      "learning_rate": 0.0001266846361185984,
+      "loss": 0.9500927925109863,
+      "step": 706
+    },
+    {
+      "epoch": 0.3055016181229773,
+      "grad_norm": 0.6485719084739685,
+      "learning_rate": 0.0001270440251572327,
+      "loss": 1.0271424055099487,
+      "step": 708
+    },
+    {
+      "epoch": 0.3063646170442287,
+      "grad_norm": 0.5802455544471741,
+      "learning_rate": 0.00012740341419586703,
+      "loss": 0.9781906008720398,
+      "step": 710
+    },
+    {
+      "epoch": 0.30722761596548004,
+      "grad_norm": 0.6359356641769409,
+      "learning_rate": 0.00012776280323450136,
+      "loss": 1.0195324420928955,
+      "step": 712
+    },
+    {
+      "epoch": 0.3080906148867314,
+      "grad_norm": 0.5975426435470581,
+      "learning_rate": 0.00012812219227313566,
+      "loss": 0.9250738024711609,
+      "step": 714
+    },
+    {
+      "epoch": 0.30895361380798275,
+      "grad_norm": 0.643110454082489,
+      "learning_rate": 0.00012848158131177,
+      "loss": 0.9888015985488892,
+      "step": 716
+    },
+    {
+      "epoch": 0.3098166127292341,
+      "grad_norm": 0.6043205261230469,
+      "learning_rate": 0.00012884097035040432,
+      "loss": 0.9709514379501343,
+      "step": 718
+    },
+    {
+      "epoch": 0.3106796116504854,
+      "grad_norm": 0.5687094926834106,
+      "learning_rate": 0.00012920035938903865,
+      "loss": 1.0272964239120483,
+      "step": 720
+    },
+    {
+      "epoch": 0.31154261057173677,
+      "grad_norm": 0.5688400864601135,
+      "learning_rate": 0.00012955974842767296,
+      "loss": 0.9370370507240295,
+      "step": 722
+    },
+    {
+      "epoch": 0.3124056094929881,
+      "grad_norm": 0.5610610246658325,
+      "learning_rate": 0.00012991913746630729,
+      "loss": 0.9535608291625977,
+      "step": 724
+    },
+    {
+      "epoch": 0.3132686084142395,
+      "grad_norm": 0.6338257193565369,
+      "learning_rate": 0.00013027852650494162,
+      "loss": 1.0188907384872437,
+      "step": 726
+    },
+    {
+      "epoch": 0.31413160733549084,
+      "grad_norm": 0.5365633368492126,
+      "learning_rate": 0.00013063791554357592,
+      "loss": 0.9253716468811035,
+      "step": 728
+    },
+    {
+      "epoch": 0.3149946062567422,
+      "grad_norm": 0.5599163174629211,
+      "learning_rate": 0.00013099730458221025,
+      "loss": 0.8941492438316345,
+      "step": 730
+    },
+    {
+      "epoch": 0.31585760517799355,
+      "grad_norm": 0.6059780716896057,
+      "learning_rate": 0.00013135669362084458,
+      "loss": 0.9831459522247314,
+      "step": 732
+    },
+    {
+      "epoch": 0.31672060409924485,
+      "grad_norm": 0.5596494078636169,
+      "learning_rate": 0.0001317160826594789,
+      "loss": 0.9332310557365417,
+      "step": 734
+    },
+    {
+      "epoch": 0.3175836030204962,
+      "grad_norm": 0.5618010759353638,
+      "learning_rate": 0.0001320754716981132,
+      "loss": 0.9082580208778381,
+      "step": 736
+    },
+    {
+      "epoch": 0.31844660194174756,
+      "grad_norm": 0.6412109732627869,
+      "learning_rate": 0.00013243486073674754,
+      "loss": 1.008690357208252,
+      "step": 738
+    },
+    {
+      "epoch": 0.3193096008629989,
+      "grad_norm": 0.5742355585098267,
+      "learning_rate": 0.00013279424977538187,
+      "loss": 0.9597798585891724,
+      "step": 740
+    },
+    {
+      "epoch": 0.3201725997842503,
+      "grad_norm": 0.6470226645469666,
+      "learning_rate": 0.00013315363881401617,
+      "loss": 0.989331841468811,
+      "step": 742
+    },
+    {
+      "epoch": 0.32103559870550163,
+      "grad_norm": 0.5598039031028748,
+      "learning_rate": 0.0001335130278526505,
+      "loss": 0.8677343130111694,
+      "step": 744
+    },
+    {
+      "epoch": 0.321898597626753,
+      "grad_norm": 0.5441372990608215,
+      "learning_rate": 0.00013387241689128483,
+      "loss": 0.9462730288505554,
+      "step": 746
+    },
+    {
+      "epoch": 0.3227615965480043,
+      "grad_norm": 0.5858626365661621,
+      "learning_rate": 0.00013423180592991916,
+      "loss": 0.994694173336029,
+      "step": 748
+    },
+    {
+      "epoch": 0.32362459546925565,
+      "grad_norm": 0.511372447013855,
+      "learning_rate": 0.00013459119496855347,
+      "loss": 0.9387269616127014,
+      "step": 750
+    },
+    {
+      "epoch": 0.324487594390507,
+      "grad_norm": 0.47798457741737366,
+      "learning_rate": 0.0001349505840071878,
+      "loss": 0.9473881721496582,
+      "step": 752
+    },
+    {
+      "epoch": 0.32535059331175836,
+      "grad_norm": 0.5907022953033447,
+      "learning_rate": 0.0001353099730458221,
+      "loss": 0.9375183582305908,
+      "step": 754
+    },
+    {
+      "epoch": 0.3262135922330097,
+      "grad_norm": 0.618733286857605,
+      "learning_rate": 0.00013566936208445643,
+      "loss": 1.028738260269165,
+      "step": 756
+    },
+    {
+      "epoch": 0.3270765911542611,
+      "grad_norm": 0.5234512090682983,
+      "learning_rate": 0.00013602875112309076,
+      "loss": 0.9420192241668701,
+      "step": 758
+    },
+    {
+      "epoch": 0.32793959007551243,
+      "grad_norm": 0.7036319971084595,
+      "learning_rate": 0.00013638814016172506,
+      "loss": 1.0252270698547363,
+      "step": 760
+    },
+    {
+      "epoch": 0.32880258899676373,
+      "grad_norm": 0.5543172359466553,
+      "learning_rate": 0.0001367475292003594,
+      "loss": 0.8453778028488159,
+      "step": 762
+    },
+    {
+      "epoch": 0.3296655879180151,
+      "grad_norm": 0.5438711643218994,
+      "learning_rate": 0.0001371069182389937,
+      "loss": 0.8659937977790833,
+      "step": 764
+    },
+    {
+      "epoch": 0.33052858683926645,
+      "grad_norm": 0.6390914916992188,
+      "learning_rate": 0.00013746630727762803,
+      "loss": 1.038142442703247,
+      "step": 766
+    },
+    {
+      "epoch": 0.3313915857605178,
+      "grad_norm": 0.50070720911026,
+      "learning_rate": 0.00013782569631626236,
+      "loss": 0.899932861328125,
+      "step": 768
+    },
+    {
+      "epoch": 0.33225458468176916,
+      "grad_norm": 0.5982286334037781,
+      "learning_rate": 0.00013818508535489669,
+      "loss": 0.9712884426116943,
+      "step": 770
+    },
+    {
+      "epoch": 0.3331175836030205,
+      "grad_norm": 0.6588822603225708,
+      "learning_rate": 0.000138544474393531,
+      "loss": 0.9427542686462402,
+      "step": 772
+    },
+    {
+      "epoch": 0.3339805825242718,
+      "grad_norm": 0.6022042632102966,
+      "learning_rate": 0.00013890386343216532,
+      "loss": 0.8961561918258667,
+      "step": 774
+    },
+    {
+      "epoch": 0.3348435814455232,
+      "grad_norm": 0.6595642566680908,
+      "learning_rate": 0.00013926325247079965,
+      "loss": 0.9525937438011169,
+      "step": 776
+    },
+    {
+      "epoch": 0.33570658036677453,
+      "grad_norm": 0.5210421681404114,
+      "learning_rate": 0.00013962264150943395,
+      "loss": 0.9218845367431641,
+      "step": 778
+    },
+    {
+      "epoch": 0.3365695792880259,
+      "grad_norm": 0.549669623374939,
+      "learning_rate": 0.00013998203054806828,
+      "loss": 0.877951443195343,
+      "step": 780
+    },
+    {
+      "epoch": 0.33743257820927725,
+      "grad_norm": 0.5360157489776611,
+      "learning_rate": 0.0001403414195867026,
+      "loss": 0.8670064210891724,
+      "step": 782
+    },
+    {
+      "epoch": 0.3382955771305286,
+      "grad_norm": 0.614734947681427,
+      "learning_rate": 0.00014070080862533694,
+      "loss": 0.9561367630958557,
+      "step": 784
+    },
+    {
+      "epoch": 0.33915857605177996,
+      "grad_norm": 0.5798251628875732,
+      "learning_rate": 0.00014106019766397124,
+      "loss": 0.9132505059242249,
+      "step": 786
+    },
+    {
+      "epoch": 0.34002157497303126,
+      "grad_norm": 0.6267077326774597,
+      "learning_rate": 0.00014141958670260557,
+      "loss": 0.9297707080841064,
+      "step": 788
+    },
+    {
+      "epoch": 0.3408845738942826,
+      "grad_norm": 0.6045349836349487,
+      "learning_rate": 0.0001417789757412399,
+      "loss": 0.9382412433624268,
+      "step": 790
+    },
+    {
+      "epoch": 0.341747572815534,
+      "grad_norm": 0.6125404834747314,
+      "learning_rate": 0.0001421383647798742,
+      "loss": 0.9078555107116699,
+      "step": 792
+    },
+    {
+      "epoch": 0.34261057173678533,
+      "grad_norm": 0.5927051901817322,
+      "learning_rate": 0.00014249775381850854,
+      "loss": 0.899101197719574,
+      "step": 794
+    },
+    {
+      "epoch": 0.3434735706580367,
+      "grad_norm": 0.6315743923187256,
+      "learning_rate": 0.00014285714285714287,
+      "loss": 1.028346300125122,
+      "step": 796
+    },
+    {
+      "epoch": 0.34433656957928804,
+      "grad_norm": 0.549271285533905,
+      "learning_rate": 0.0001432165318957772,
+      "loss": 0.8988189697265625,
+      "step": 798
+    },
+    {
+      "epoch": 0.3451995685005394,
+      "grad_norm": 0.6344245672225952,
+      "learning_rate": 0.0001435759209344115,
+      "loss": 1.0489003658294678,
+      "step": 800
+    },
+    {
+      "epoch": 0.3451995685005394,
+      "eval_loss": 0.9864639639854431,
+      "eval_runtime": 667.3516,
+      "eval_samples_per_second": 3.087,
+      "eval_steps_per_second": 3.087,
+      "step": 800
+    },
+    {
+      "epoch": 0.3460625674217907,
+      "grad_norm": 0.5625309348106384,
+      "learning_rate": 0.00014393530997304583,
+      "loss": 0.8773928284645081,
+      "step": 802
+    },
+    {
+      "epoch": 0.34692556634304206,
+      "grad_norm": 0.5931969285011292,
+      "learning_rate": 0.00014429469901168016,
+      "loss": 0.9116050004959106,
+      "step": 804
+    },
+    {
+      "epoch": 0.3477885652642934,
+      "grad_norm": 0.5189821720123291,
+      "learning_rate": 0.00014465408805031446,
+      "loss": 0.9124425649642944,
+      "step": 806
+    },
+    {
+      "epoch": 0.34865156418554477,
+      "grad_norm": 0.5392254590988159,
+      "learning_rate": 0.0001450134770889488,
+      "loss": 0.9517888426780701,
+      "step": 808
+    },
+    {
+      "epoch": 0.34951456310679613,
+      "grad_norm": 0.5584444999694824,
+      "learning_rate": 0.00014537286612758312,
+      "loss": 0.9947572350502014,
+      "step": 810
+    },
+    {
+      "epoch": 0.3503775620280475,
+      "grad_norm": 0.5188854932785034,
+      "learning_rate": 0.00014573225516621745,
+      "loss": 0.9314022660255432,
+      "step": 812
+    },
+    {
+      "epoch": 0.3512405609492988,
+      "grad_norm": 0.5783659815788269,
+      "learning_rate": 0.00014609164420485176,
+      "loss": 0.9135628938674927,
+      "step": 814
+    },
+    {
+      "epoch": 0.35210355987055014,
+      "grad_norm": 0.550959050655365,
+      "learning_rate": 0.0001464510332434861,
+      "loss": 0.9665075540542603,
+      "step": 816
+    },
+    {
+      "epoch": 0.3529665587918015,
+      "grad_norm": 0.6013346314430237,
+      "learning_rate": 0.00014681042228212042,
+      "loss": 0.9836555123329163,
+      "step": 818
+    },
+    {
+      "epoch": 0.35382955771305286,
+      "grad_norm": 0.49219194054603577,
+      "learning_rate": 0.00014716981132075472,
+      "loss": 0.8900108337402344,
+      "step": 820
+    },
+    {
+      "epoch": 0.3546925566343042,
+      "grad_norm": 0.5517411828041077,
+      "learning_rate": 0.00014752920035938905,
+      "loss": 0.8769304156303406,
+      "step": 822
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.6062695980072021,
+      "learning_rate": 0.00014788858939802338,
+      "loss": 0.9744759202003479,
+      "step": 824
+    },
+    {
+      "epoch": 0.3564185544768069,
+      "grad_norm": 0.5132041573524475,
+      "learning_rate": 0.0001482479784366577,
+      "loss": 0.8875447511672974,
+      "step": 826
+    },
+    {
+      "epoch": 0.3572815533980582,
+      "grad_norm": 0.551799476146698,
+      "learning_rate": 0.000148607367475292,
+      "loss": 0.962710440158844,
+      "step": 828
+    },
+    {
+      "epoch": 0.3581445523193096,
+      "grad_norm": 0.6046625971794128,
+      "learning_rate": 0.00014896675651392634,
+      "loss": 0.8997528553009033,
+      "step": 830
+    },
+    {
+      "epoch": 0.35900755124056094,
+      "grad_norm": 0.560025691986084,
+      "learning_rate": 0.00014932614555256067,
+      "loss": 0.9541417360305786,
+      "step": 832
+    },
+    {
+      "epoch": 0.3598705501618123,
+      "grad_norm": 0.6441047787666321,
+      "learning_rate": 0.00014968553459119498,
+      "loss": 0.907791018486023,
+      "step": 834
+    },
+    {
+      "epoch": 0.36073354908306365,
+      "grad_norm": 0.5636281967163086,
+      "learning_rate": 0.0001500449236298293,
+      "loss": 1.0295937061309814,
+      "step": 836
+    },
+    {
+      "epoch": 0.361596548004315,
+      "grad_norm": 0.5528303384780884,
+      "learning_rate": 0.0001504043126684636,
+      "loss": 0.8875265717506409,
+      "step": 838
+    },
+    {
+      "epoch": 0.36245954692556637,
+      "grad_norm": 0.5345163345336914,
+      "learning_rate": 0.00015076370170709794,
+      "loss": 0.9678915739059448,
+      "step": 840
+    },
+    {
+      "epoch": 0.36332254584681767,
+      "grad_norm": 0.5551225543022156,
+      "learning_rate": 0.00015112309074573224,
+      "loss": 0.9235162734985352,
+      "step": 842
+    },
+    {
+      "epoch": 0.364185544768069,
+      "grad_norm": 0.5131904482841492,
+      "learning_rate": 0.00015148247978436657,
+      "loss": 0.8624292016029358,
+      "step": 844
+    },
+    {
+      "epoch": 0.3650485436893204,
+      "grad_norm": 0.6811004281044006,
+      "learning_rate": 0.0001518418688230009,
+      "loss": 1.0360193252563477,
+      "step": 846
+    },
+    {
+      "epoch": 0.36591154261057174,
+      "grad_norm": 0.6409741640090942,
+      "learning_rate": 0.00015220125786163523,
+      "loss": 0.9254010915756226,
+      "step": 848
+    },
+    {
+      "epoch": 0.3667745415318231,
+      "grad_norm": 0.5534068942070007,
+      "learning_rate": 0.00015256064690026953,
+      "loss": 0.8900630474090576,
+      "step": 850
+    },
+    {
+      "epoch": 0.36763754045307445,
+      "grad_norm": 0.4999487102031708,
+      "learning_rate": 0.00015292003593890386,
+      "loss": 0.88521409034729,
+      "step": 852
+    },
+    {
+      "epoch": 0.3685005393743258,
+      "grad_norm": 0.5805923938751221,
+      "learning_rate": 0.0001532794249775382,
+      "loss": 0.9563921093940735,
+      "step": 854
+    },
+    {
+      "epoch": 0.3693635382955771,
+      "grad_norm": 0.5485470294952393,
+      "learning_rate": 0.0001536388140161725,
+      "loss": 0.8909372687339783,
+      "step": 856
+    },
+    {
+      "epoch": 0.37022653721682847,
+      "grad_norm": 0.5317923426628113,
+      "learning_rate": 0.00015399820305480683,
+      "loss": 0.9145731925964355,
+      "step": 858
+    },
+    {
+      "epoch": 0.3710895361380798,
+      "grad_norm": 0.6073495745658875,
+      "learning_rate": 0.00015435759209344116,
+      "loss": 1.01466965675354,
+      "step": 860
+    },
+    {
+      "epoch": 0.3719525350593312,
+      "grad_norm": 0.566655158996582,
+      "learning_rate": 0.0001547169811320755,
+      "loss": 0.9941825270652771,
+      "step": 862
+    },
+    {
+      "epoch": 0.37281553398058254,
+      "grad_norm": 0.5262459516525269,
+      "learning_rate": 0.0001550763701707098,
+      "loss": 1.0059782266616821,
+      "step": 864
+    },
+    {
+      "epoch": 0.3736785329018339,
+      "grad_norm": 0.6264083981513977,
+      "learning_rate": 0.00015543575920934412,
+      "loss": 1.0332856178283691,
+      "step": 866
+    },
+    {
+      "epoch": 0.3745415318230852,
+      "grad_norm": 0.6575480699539185,
+      "learning_rate": 0.00015579514824797845,
+      "loss": 1.022459626197815,
+      "step": 868
+    },
+    {
+      "epoch": 0.37540453074433655,
+      "grad_norm": 0.6291940212249756,
+      "learning_rate": 0.00015615453728661275,
+      "loss": 0.9550372362136841,
+      "step": 870
+    },
+    {
+      "epoch": 0.3762675296655879,
+      "grad_norm": 0.6710562109947205,
+      "learning_rate": 0.00015651392632524708,
+      "loss": 0.9861716628074646,
+      "step": 872
+    },
+    {
+      "epoch": 0.37713052858683926,
+      "grad_norm": 0.5505748987197876,
+      "learning_rate": 0.0001568733153638814,
+      "loss": 0.9719111919403076,
+      "step": 874
+    },
+    {
+      "epoch": 0.3779935275080906,
+      "grad_norm": 0.5055180788040161,
+      "learning_rate": 0.00015723270440251574,
+      "loss": 0.8698170185089111,
+      "step": 876
+    },
+    {
+      "epoch": 0.378856526429342,
+      "grad_norm": 0.5935947895050049,
+      "learning_rate": 0.00015759209344115005,
+      "loss": 1.029494285583496,
+      "step": 878
+    },
+    {
+      "epoch": 0.37971952535059333,
+      "grad_norm": 0.538325846195221,
+      "learning_rate": 0.00015795148247978438,
+      "loss": 0.923010528087616,
+      "step": 880
+    },
+    {
+      "epoch": 0.38058252427184464,
+      "grad_norm": 0.587297797203064,
+      "learning_rate": 0.0001583108715184187,
+      "loss": 0.9394056797027588,
+      "step": 882
+    },
+    {
+      "epoch": 0.381445523193096,
+      "grad_norm": 0.5910462737083435,
+      "learning_rate": 0.000158670260557053,
+      "loss": 0.9472483992576599,
+      "step": 884
+    },
+    {
+      "epoch": 0.38230852211434735,
+      "grad_norm": 0.629048764705658,
+      "learning_rate": 0.00015902964959568734,
+      "loss": 0.9028263688087463,
+      "step": 886
+    },
+    {
+      "epoch": 0.3831715210355987,
+      "grad_norm": 0.5028086304664612,
+      "learning_rate": 0.00015938903863432167,
+      "loss": 0.9579087495803833,
+      "step": 888
+    },
+    {
+      "epoch": 0.38403451995685006,
+      "grad_norm": 0.5372384190559387,
+      "learning_rate": 0.000159748427672956,
+      "loss": 0.8318673372268677,
+      "step": 890
+    },
+    {
+      "epoch": 0.3848975188781014,
+      "grad_norm": 0.6314184665679932,
+      "learning_rate": 0.0001601078167115903,
+      "loss": 0.9804943203926086,
+      "step": 892
+    },
+    {
+      "epoch": 0.3857605177993528,
+      "grad_norm": 0.5545229911804199,
+      "learning_rate": 0.00016046720575022463,
+      "loss": 1.0078438520431519,
+      "step": 894
+    },
+    {
+      "epoch": 0.3866235167206041,
+      "grad_norm": 0.4674014151096344,
+      "learning_rate": 0.00016082659478885896,
+      "loss": 0.9269036650657654,
+      "step": 896
+    },
+    {
+      "epoch": 0.38748651564185543,
+      "grad_norm": 1.5887153148651123,
+      "learning_rate": 0.00016118598382749326,
+      "loss": 0.8927953243255615,
+      "step": 898
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "grad_norm": 0.5217035412788391,
+      "learning_rate": 0.0001615453728661276,
+      "loss": 0.908074140548706,
+      "step": 900
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "eval_loss": 0.9741895794868469,
+      "eval_runtime": 667.2236,
+      "eval_samples_per_second": 3.087,
+      "eval_steps_per_second": 3.087,
+      "step": 900
+    },
+    {
+      "epoch": 0.38921251348435815,
+      "grad_norm": 0.470498651266098,
+      "learning_rate": 0.00016190476190476192,
+      "loss": 0.9660369157791138,
+      "step": 902
+    },
+    {
+      "epoch": 0.3900755124056095,
+      "grad_norm": 0.5111004114151001,
+      "learning_rate": 0.00016226415094339625,
+      "loss": 0.9236379265785217,
+      "step": 904
+    },
+    {
+      "epoch": 0.39093851132686086,
+      "grad_norm": 0.5872815251350403,
+      "learning_rate": 0.00016262353998203056,
+      "loss": 1.0061595439910889,
+      "step": 906
+    },
+    {
+      "epoch": 0.3918015102481122,
+      "grad_norm": 0.5150740742683411,
+      "learning_rate": 0.0001629829290206649,
+      "loss": 0.8347328901290894,
+      "step": 908
+    },
+    {
+      "epoch": 0.3926645091693635,
+      "grad_norm": 0.46554985642433167,
+      "learning_rate": 0.00016334231805929922,
+      "loss": 0.9091183543205261,
+      "step": 910
+    },
+    {
+      "epoch": 0.3935275080906149,
+      "grad_norm": 0.5292875170707703,
+      "learning_rate": 0.00016370170709793352,
+      "loss": 0.9299798011779785,
+      "step": 912
+    },
+    {
+      "epoch": 0.39439050701186623,
+      "grad_norm": 0.5177125930786133,
+      "learning_rate": 0.00016406109613656785,
+      "loss": 0.942286491394043,
+      "step": 914
+    },
+    {
+      "epoch": 0.3952535059331176,
+      "grad_norm": 0.5564161539077759,
+      "learning_rate": 0.00016442048517520215,
+      "loss": 0.825290858745575,
+      "step": 916
+    },
+    {
+      "epoch": 0.39611650485436894,
+      "grad_norm": 0.5572530031204224,
+      "learning_rate": 0.00016477987421383648,
+      "loss": 0.876898467540741,
+      "step": 918
+    },
+    {
+      "epoch": 0.3969795037756203,
+      "grad_norm": 0.7294673323631287,
+      "learning_rate": 0.0001651392632524708,
+      "loss": 0.8949798941612244,
+      "step": 920
+    },
+    {
+      "epoch": 0.3978425026968716,
+      "grad_norm": 0.5234251022338867,
+      "learning_rate": 0.00016549865229110512,
+      "loss": 0.8457819223403931,
+      "step": 922
+    },
+    {
+      "epoch": 0.39870550161812296,
+      "grad_norm": 0.5273709893226624,
+      "learning_rate": 0.00016585804132973945,
+      "loss": 0.9080174565315247,
+      "step": 924
+    },
+    {
+      "epoch": 0.3995685005393743,
+      "grad_norm": 0.5795063376426697,
+      "learning_rate": 0.00016621743036837378,
+      "loss": 1.0304023027420044,
+      "step": 926
+    },
+    {
+      "epoch": 0.4004314994606257,
+      "grad_norm": 0.6153313517570496,
+      "learning_rate": 0.00016657681940700808,
+      "loss": 0.8900477886199951,
+      "step": 928
+    },
+    {
+      "epoch": 0.40129449838187703,
+      "grad_norm": 0.6293173432350159,
+      "learning_rate": 0.0001669362084456424,
+      "loss": 1.0130009651184082,
+      "step": 930
+    },
+    {
+      "epoch": 0.4021574973031284,
+      "grad_norm": 0.5455223321914673,
+      "learning_rate": 0.00016729559748427674,
+      "loss": 0.9339282512664795,
+      "step": 932
+    },
+    {
+      "epoch": 0.40302049622437974,
+      "grad_norm": 0.5349094271659851,
+      "learning_rate": 0.00016765498652291104,
+      "loss": 0.9628980755805969,
+      "step": 934
+    },
+    {
+      "epoch": 0.40388349514563104,
+      "grad_norm": 0.491227924823761,
+      "learning_rate": 0.00016801437556154537,
+      "loss": 0.8922860026359558,
+      "step": 936
+    },
+    {
+      "epoch": 0.4047464940668824,
+      "grad_norm": 0.6331246495246887,
+      "learning_rate": 0.0001683737646001797,
+      "loss": 1.0470497608184814,
+      "step": 938
+    },
+    {
+      "epoch": 0.40560949298813376,
+      "grad_norm": 0.6079246401786804,
+      "learning_rate": 0.00016873315363881403,
+      "loss": 0.8868283629417419,
+      "step": 940
+    },
+    {
+      "epoch": 0.4064724919093851,
+      "grad_norm": 0.5326972603797913,
+      "learning_rate": 0.00016909254267744833,
+      "loss": 0.9938711524009705,
+      "step": 942
+    },
+    {
+      "epoch": 0.40733549083063647,
+      "grad_norm": 0.47754305601119995,
+      "learning_rate": 0.00016945193171608266,
+      "loss": 0.8280484676361084,
+      "step": 944
+    },
+    {
+      "epoch": 0.4081984897518878,
+      "grad_norm": 0.6683310270309448,
+      "learning_rate": 0.000169811320754717,
+      "loss": 1.089701533317566,
+      "step": 946
+    },
+    {
+      "epoch": 0.4090614886731392,
+      "grad_norm": 0.42798754572868347,
+      "learning_rate": 0.0001701707097933513,
+      "loss": 0.8535542488098145,
+      "step": 948
+    },
+    {
+      "epoch": 0.4099244875943905,
+      "grad_norm": 0.5999574065208435,
+      "learning_rate": 0.00017053009883198563,
+      "loss": 0.9039298295974731,
+      "step": 950
+    },
+    {
+      "epoch": 0.41078748651564184,
+      "grad_norm": 0.5752781629562378,
+      "learning_rate": 0.00017088948787061996,
+      "loss": 0.8786448240280151,
+      "step": 952
+    },
+    {
+      "epoch": 0.4116504854368932,
+      "grad_norm": 0.5121532678604126,
+      "learning_rate": 0.0001712488769092543,
+      "loss": 0.9206072688102722,
+      "step": 954
+    },
+    {
+      "epoch": 0.41251348435814456,
+      "grad_norm": 0.611078143119812,
+      "learning_rate": 0.0001716082659478886,
+      "loss": 0.9246986508369446,
+      "step": 956
+    },
+    {
+      "epoch": 0.4133764832793959,
+      "grad_norm": 0.5101020336151123,
+      "learning_rate": 0.00017196765498652292,
+      "loss": 0.9221894145011902,
+      "step": 958
+    },
+    {
+      "epoch": 0.41423948220064727,
+      "grad_norm": 0.5681450963020325,
+      "learning_rate": 0.00017232704402515725,
+      "loss": 0.9072799682617188,
+      "step": 960
+    },
+    {
+      "epoch": 0.41510248112189857,
+      "grad_norm": 0.47865498065948486,
+      "learning_rate": 0.00017268643306379155,
+      "loss": 0.9460896849632263,
+      "step": 962
+    },
+    {
+      "epoch": 0.4159654800431499,
+      "grad_norm": 0.49861401319503784,
+      "learning_rate": 0.00017304582210242588,
+      "loss": 0.9121519923210144,
+      "step": 964
+    },
+    {
+      "epoch": 0.4168284789644013,
+      "grad_norm": 0.43025892972946167,
+      "learning_rate": 0.0001734052111410602,
+      "loss": 0.8826848864555359,
+      "step": 966
+    },
+    {
+      "epoch": 0.41769147788565264,
+      "grad_norm": 0.4600491225719452,
+      "learning_rate": 0.00017376460017969454,
+      "loss": 0.8756251335144043,
+      "step": 968
+    },
+    {
+      "epoch": 0.418554476806904,
+      "grad_norm": 0.5297656059265137,
+      "learning_rate": 0.00017412398921832885,
+      "loss": 0.9171333312988281,
+      "step": 970
+    },
+    {
+      "epoch": 0.41941747572815535,
+      "grad_norm": 0.4906919002532959,
+      "learning_rate": 0.00017448337825696318,
+      "loss": 0.8887524008750916,
+      "step": 972
+    },
+    {
+      "epoch": 0.4202804746494067,
+      "grad_norm": 0.49263402819633484,
+      "learning_rate": 0.0001748427672955975,
+      "loss": 0.8345810174942017,
+      "step": 974
+    },
+    {
+      "epoch": 0.421143473570658,
+      "grad_norm": 0.5706565380096436,
+      "learning_rate": 0.0001752021563342318,
+      "loss": 0.968651294708252,
+      "step": 976
+    },
+    {
+      "epoch": 0.42200647249190937,
+      "grad_norm": 0.5269908308982849,
+      "learning_rate": 0.00017556154537286614,
+      "loss": 0.9729376435279846,
+      "step": 978
+    },
+    {
+      "epoch": 0.4228694714131607,
+      "grad_norm": 0.47058001160621643,
+      "learning_rate": 0.00017592093441150047,
+      "loss": 0.963884711265564,
+      "step": 980
+    },
+    {
+      "epoch": 0.4237324703344121,
+      "grad_norm": 0.5322962999343872,
+      "learning_rate": 0.0001762803234501348,
+      "loss": 0.8952447175979614,
+      "step": 982
+    },
+    {
+      "epoch": 0.42459546925566344,
+      "grad_norm": 0.5750975012779236,
+      "learning_rate": 0.0001766397124887691,
+      "loss": 0.8932783603668213,
+      "step": 984
+    },
+    {
+      "epoch": 0.4254584681769148,
+      "grad_norm": 0.5539655685424805,
+      "learning_rate": 0.00017699910152740343,
+      "loss": 0.916595458984375,
+      "step": 986
+    },
+    {
+      "epoch": 0.42632146709816615,
+      "grad_norm": 0.568000853061676,
+      "learning_rate": 0.00017735849056603776,
+      "loss": 0.9669626355171204,
+      "step": 988
+    },
+    {
+      "epoch": 0.42718446601941745,
+      "grad_norm": 0.6010684370994568,
+      "learning_rate": 0.00017771787960467206,
+      "loss": 1.0089105367660522,
+      "step": 990
+    },
+    {
+      "epoch": 0.4280474649406688,
+      "grad_norm": 0.6083462238311768,
+      "learning_rate": 0.0001780772686433064,
+      "loss": 0.9810921549797058,
+      "step": 992
+    },
+    {
+      "epoch": 0.42891046386192017,
+      "grad_norm": 0.5076655149459839,
+      "learning_rate": 0.0001784366576819407,
+      "loss": 0.9524372816085815,
+      "step": 994
+    },
+    {
+      "epoch": 0.4297734627831715,
+      "grad_norm": 0.5260922312736511,
+      "learning_rate": 0.00017879604672057503,
+      "loss": 0.881294846534729,
+      "step": 996
+    },
+    {
+      "epoch": 0.4306364617044229,
+      "grad_norm": 0.6130498051643372,
+      "learning_rate": 0.00017915543575920936,
+      "loss": 0.9138327836990356,
+      "step": 998
+    },
+    {
+      "epoch": 0.43149946062567424,
+      "grad_norm": 0.5346242785453796,
+      "learning_rate": 0.00017951482479784366,
+      "loss": 0.8861367106437683,
+      "step": 1000
+    },
+    {
+      "epoch": 0.43149946062567424,
+      "eval_loss": 0.9606748819351196,
+      "eval_runtime": 655.4358,
+      "eval_samples_per_second": 3.143,
+      "eval_steps_per_second": 3.143,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4323624595469256,
+      "grad_norm": 0.5977228879928589,
+      "learning_rate": 0.000179874213836478,
+      "loss": 0.8711628913879395,
+      "step": 1002
+    },
+    {
+      "epoch": 0.4332254584681769,
+      "grad_norm": 0.5547866821289062,
+      "learning_rate": 0.00018023360287511232,
+      "loss": 0.9393253326416016,
+      "step": 1004
+    },
+    {
+      "epoch": 0.43408845738942825,
+      "grad_norm": 0.536856472492218,
+      "learning_rate": 0.00018059299191374662,
+      "loss": 0.9486003518104553,
+      "step": 1006
+    },
+    {
+      "epoch": 0.4349514563106796,
+      "grad_norm": 0.4769814610481262,
+      "learning_rate": 0.00018095238095238095,
+      "loss": 0.9042052030563354,
+      "step": 1008
+    },
+    {
+      "epoch": 0.43581445523193096,
+      "grad_norm": 0.5554604530334473,
+      "learning_rate": 0.00018131176999101528,
+      "loss": 0.978546142578125,
+      "step": 1010
+    },
+    {
+      "epoch": 0.4366774541531823,
+      "grad_norm": 0.5112947225570679,
+      "learning_rate": 0.00018167115902964959,
+      "loss": 0.8382073640823364,
+      "step": 1012
+    },
+    {
+      "epoch": 0.4375404530744337,
+      "grad_norm": 0.45194941759109497,
+      "learning_rate": 0.00018203054806828392,
+      "loss": 0.8577026724815369,
+      "step": 1014
+    },
+    {
+      "epoch": 0.438403451995685,
+      "grad_norm": 0.5115043520927429,
+      "learning_rate": 0.00018238993710691825,
+      "loss": 0.8517863154411316,
+      "step": 1016
+    },
+    {
+      "epoch": 0.43926645091693634,
+      "grad_norm": 0.5485050082206726,
+      "learning_rate": 0.00018274932614555258,
+      "loss": 0.9597266912460327,
+      "step": 1018
+    },
+    {
+      "epoch": 0.4401294498381877,
+      "grad_norm": 0.5742959976196289,
+      "learning_rate": 0.00018310871518418688,
+      "loss": 1.0407187938690186,
+      "step": 1020
+    },
+    {
+      "epoch": 0.44099244875943905,
+      "grad_norm": 0.44870051741600037,
+      "learning_rate": 0.0001834681042228212,
+      "loss": 0.8696310520172119,
+      "step": 1022
+    },
+    {
+      "epoch": 0.4418554476806904,
+      "grad_norm": 0.5179623961448669,
+      "learning_rate": 0.00018382749326145554,
+      "loss": 0.9673634767532349,
+      "step": 1024
+    },
+    {
+      "epoch": 0.44271844660194176,
+      "grad_norm": 0.5404779314994812,
+      "learning_rate": 0.00018418688230008984,
+      "loss": 0.9596615433692932,
+      "step": 1026
+    },
+    {
+      "epoch": 0.4435814455231931,
+      "grad_norm": 0.47766315937042236,
+      "learning_rate": 0.00018454627133872417,
+      "loss": 0.8483878970146179,
+      "step": 1028
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.503380537033081,
+      "learning_rate": 0.0001849056603773585,
+      "loss": 0.9330979585647583,
+      "step": 1030
+    },
+    {
+      "epoch": 0.4453074433656958,
+      "grad_norm": 0.6129396557807922,
+      "learning_rate": 0.00018526504941599283,
+      "loss": 0.9341012239456177,
+      "step": 1032
+    },
+    {
+      "epoch": 0.44617044228694713,
+      "grad_norm": 0.4497876465320587,
+      "learning_rate": 0.00018562443845462713,
+      "loss": 0.9139068126678467,
+      "step": 1034
+    },
+    {
+      "epoch": 0.4470334412081985,
+      "grad_norm": 0.5369747281074524,
+      "learning_rate": 0.00018598382749326146,
+      "loss": 0.8874827027320862,
+      "step": 1036
+    },
+    {
+      "epoch": 0.44789644012944985,
+      "grad_norm": 0.5947322845458984,
+      "learning_rate": 0.0001863432165318958,
+      "loss": 0.9653725028038025,
+      "step": 1038
+    },
+    {
+      "epoch": 0.4487594390507012,
+      "grad_norm": 0.6649987101554871,
+      "learning_rate": 0.0001867026055705301,
+      "loss": 0.9553119540214539,
+      "step": 1040
+    },
+    {
+      "epoch": 0.44962243797195256,
+      "grad_norm": 0.5369387269020081,
+      "learning_rate": 0.00018706199460916443,
+      "loss": 0.904233992099762,
+      "step": 1042
+    },
+    {
+      "epoch": 0.45048543689320386,
+      "grad_norm": 0.4956842362880707,
+      "learning_rate": 0.00018742138364779876,
+      "loss": 0.8837952017784119,
+      "step": 1044
+    },
+    {
+      "epoch": 0.4513484358144552,
+      "grad_norm": 0.48045051097869873,
+      "learning_rate": 0.0001877807726864331,
+      "loss": 0.8964687585830688,
+      "step": 1046
+    },
+    {
+      "epoch": 0.4522114347357066,
+      "grad_norm": 0.4925530254840851,
+      "learning_rate": 0.0001881401617250674,
+      "loss": 0.9105878472328186,
+      "step": 1048
+    },
+    {
+      "epoch": 0.45307443365695793,
+      "grad_norm": 0.5131362080574036,
+      "learning_rate": 0.00018849955076370172,
+      "loss": 0.96272873878479,
+      "step": 1050
+    },
+    {
+      "epoch": 0.4539374325782093,
+      "grad_norm": 0.435739129781723,
+      "learning_rate": 0.00018885893980233605,
+      "loss": 0.8796783685684204,
+      "step": 1052
+    },
+    {
+      "epoch": 0.45480043149946064,
+      "grad_norm": 0.500938892364502,
+      "learning_rate": 0.00018921832884097035,
+      "loss": 0.9463814496994019,
+      "step": 1054
+    },
+    {
+      "epoch": 0.455663430420712,
+      "grad_norm": 0.4769900143146515,
+      "learning_rate": 0.00018957771787960468,
+      "loss": 0.9030335545539856,
+      "step": 1056
+    },
+    {
+      "epoch": 0.4565264293419633,
+      "grad_norm": 0.49585285782814026,
+      "learning_rate": 0.00018993710691823901,
+      "loss": 0.986995279788971,
+      "step": 1058
+    },
+    {
+      "epoch": 0.45738942826321466,
+      "grad_norm": 0.5875195264816284,
+      "learning_rate": 0.00019029649595687334,
+      "loss": 0.9297246932983398,
+      "step": 1060
+    },
+    {
+      "epoch": 0.458252427184466,
+      "grad_norm": 0.5552583932876587,
+      "learning_rate": 0.00019065588499550765,
+      "loss": 1.005869746208191,
+      "step": 1062
+    },
+    {
+      "epoch": 0.4591154261057174,
+      "grad_norm": 0.49282076954841614,
+      "learning_rate": 0.00019101527403414198,
+      "loss": 0.8949927091598511,
+      "step": 1064
+    },
+    {
+      "epoch": 0.45997842502696873,
+      "grad_norm": 0.4951777160167694,
+      "learning_rate": 0.0001913746630727763,
+      "loss": 0.9997886419296265,
+      "step": 1066
+    },
+    {
+      "epoch": 0.4608414239482201,
+      "grad_norm": 0.5154827237129211,
+      "learning_rate": 0.0001917340521114106,
+      "loss": 0.9532123804092407,
+      "step": 1068
+    },
+    {
+      "epoch": 0.4617044228694714,
+      "grad_norm": 0.5547500252723694,
+      "learning_rate": 0.00019209344115004494,
+      "loss": 0.8959843516349792,
+      "step": 1070
+    },
+    {
+      "epoch": 0.46256742179072274,
+      "grad_norm": 0.500188946723938,
+      "learning_rate": 0.00019245283018867927,
+      "loss": 0.8201484680175781,
+      "step": 1072
+    },
+    {
+      "epoch": 0.4634304207119741,
+      "grad_norm": 0.4181794822216034,
+      "learning_rate": 0.00019281221922731357,
+      "loss": 0.8255136609077454,
+      "step": 1074
+    },
+    {
+      "epoch": 0.46429341963322546,
+      "grad_norm": 0.5613874197006226,
+      "learning_rate": 0.0001931716082659479,
+      "loss": 0.896024763584137,
+      "step": 1076
+    },
+    {
+      "epoch": 0.4651564185544768,
+      "grad_norm": 0.5000972151756287,
+      "learning_rate": 0.0001935309973045822,
+      "loss": 0.8831873536109924,
+      "step": 1078
+    },
+    {
+      "epoch": 0.46601941747572817,
+      "grad_norm": 0.6321820616722107,
+      "learning_rate": 0.00019389038634321654,
+      "loss": 0.9787988662719727,
+      "step": 1080
+    },
+    {
+      "epoch": 0.4668824163969795,
+      "grad_norm": 0.4843652546405792,
+      "learning_rate": 0.00019424977538185087,
+      "loss": 0.933361828327179,
+      "step": 1082
+    },
+    {
+      "epoch": 0.46774541531823083,
+      "grad_norm": 0.537330150604248,
+      "learning_rate": 0.00019460916442048517,
+      "loss": 0.9046981334686279,
+      "step": 1084
+    },
+    {
+      "epoch": 0.4686084142394822,
+      "grad_norm": 0.5761371850967407,
+      "learning_rate": 0.0001949685534591195,
+      "loss": 0.9625781178474426,
+      "step": 1086
+    },
+    {
+      "epoch": 0.46947141316073354,
+      "grad_norm": 0.5209522843360901,
+      "learning_rate": 0.00019532794249775383,
+      "loss": 0.9280619025230408,
+      "step": 1088
+    },
+    {
+      "epoch": 0.4703344120819849,
+      "grad_norm": 0.5383933186531067,
+      "learning_rate": 0.00019568733153638813,
+      "loss": 0.8236247301101685,
+      "step": 1090
+    },
+    {
+      "epoch": 0.47119741100323626,
+      "grad_norm": 0.4994274377822876,
+      "learning_rate": 0.00019604672057502246,
+      "loss": 0.9404071569442749,
+      "step": 1092
+    },
+    {
+      "epoch": 0.4720604099244876,
+      "grad_norm": 0.5177807211875916,
+      "learning_rate": 0.0001964061096136568,
+      "loss": 0.8517536520957947,
+      "step": 1094
+    },
+    {
+      "epoch": 0.47292340884573897,
+      "grad_norm": 0.5374870896339417,
+      "learning_rate": 0.00019676549865229112,
+      "loss": 0.8214367032051086,
+      "step": 1096
+    },
+    {
+      "epoch": 0.47378640776699027,
+      "grad_norm": 0.5544074177742004,
+      "learning_rate": 0.00019712488769092542,
+      "loss": 1.016176700592041,
+      "step": 1098
+    },
+    {
+      "epoch": 0.4746494066882416,
+      "grad_norm": 0.5125867128372192,
+      "learning_rate": 0.00019748427672955975,
+      "loss": 0.8425421118736267,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4746494066882416,
+      "eval_loss": 0.944629430770874,
+      "eval_runtime": 649.9107,
+      "eval_samples_per_second": 3.17,
+      "eval_steps_per_second": 3.17,
+      "step": 1100
+    },
+    {
+      "epoch": 0.475512405609493,
+      "grad_norm": 0.5204418897628784,
+      "learning_rate": 0.00019784366576819408,
+      "loss": 0.9444556832313538,
+      "step": 1102
+    },
+    {
+      "epoch": 0.47637540453074434,
+      "grad_norm": 0.46085885167121887,
+      "learning_rate": 0.0001982030548068284,
+      "loss": 0.877082109451294,
+      "step": 1104
+    },
+    {
+      "epoch": 0.4772384034519957,
+      "grad_norm": 0.5269598960876465,
+      "learning_rate": 0.00019856244384546272,
+      "loss": 0.9214640259742737,
+      "step": 1106
+    },
+    {
+      "epoch": 0.47810140237324705,
+      "grad_norm": 0.4894753694534302,
+      "learning_rate": 0.00019892183288409705,
+      "loss": 0.8867175579071045,
+      "step": 1108
+    },
+    {
+      "epoch": 0.47896440129449835,
+      "grad_norm": 0.5204115509986877,
+      "learning_rate": 0.00019928122192273138,
+      "loss": 0.9641162753105164,
+      "step": 1110
+    },
+    {
+      "epoch": 0.4798274002157497,
+      "grad_norm": 0.6399031281471252,
+      "learning_rate": 0.00019964061096136568,
+      "loss": 1.0219199657440186,
+      "step": 1112
+    },
+    {
+      "epoch": 0.48069039913700107,
+      "grad_norm": 0.3979159891605377,
+      "learning_rate": 0.0002,
+      "loss": 0.8189998269081116,
+      "step": 1114
+    },
+    {
+      "epoch": 0.4815533980582524,
+      "grad_norm": 0.4782681465148926,
+      "learning_rate": 0.0001999999879427254,
+      "loss": 0.83241868019104,
+      "step": 1116
+    },
+    {
+      "epoch": 0.4824163969795038,
+      "grad_norm": 0.5235620141029358,
+      "learning_rate": 0.00019999995177090454,
+      "loss": 0.9371466636657715,
+      "step": 1118
+    },
+    {
+      "epoch": 0.48327939590075514,
+      "grad_norm": 0.4543023407459259,
+      "learning_rate": 0.00019999989148454606,
+      "loss": 0.7767758369445801,
+      "step": 1120
+    },
+    {
+      "epoch": 0.4841423948220065,
+      "grad_norm": 0.6191229820251465,
+      "learning_rate": 0.00019999980708366457,
+      "loss": 1.0103063583374023,
+      "step": 1122
+    },
+    {
+      "epoch": 0.4850053937432578,
+      "grad_norm": 0.45392486453056335,
+      "learning_rate": 0.00019999969856828042,
+      "loss": 0.8720875382423401,
+      "step": 1124
+    },
+    {
+      "epoch": 0.48586839266450915,
+      "grad_norm": 0.42748701572418213,
+      "learning_rate": 0.00019999956593841974,
+      "loss": 0.7859150171279907,
+      "step": 1126
+    },
+    {
+      "epoch": 0.4867313915857605,
+      "grad_norm": 0.4952569603919983,
+      "learning_rate": 0.00019999940919411454,
+      "loss": 0.9154419898986816,
+      "step": 1128
+    },
+    {
+      "epoch": 0.48759439050701187,
+      "grad_norm": 0.5522173047065735,
+      "learning_rate": 0.00019999922833540264,
+      "loss": 0.9076330065727234,
+      "step": 1130
+    },
+    {
+      "epoch": 0.4884573894282632,
+      "grad_norm": 0.5355855226516724,
+      "learning_rate": 0.00019999902336232758,
+      "loss": 0.8933543562889099,
+      "step": 1132
+    },
+    {
+      "epoch": 0.4893203883495146,
+      "grad_norm": 0.4613489508628845,
+      "learning_rate": 0.00019999879427493885,
+      "loss": 0.9160735607147217,
+      "step": 1134
+    },
+    {
+      "epoch": 0.49018338727076594,
+      "grad_norm": 0.4758962094783783,
+      "learning_rate": 0.0001999985410732917,
+      "loss": 0.8552446961402893,
+      "step": 1136
+    },
+    {
+      "epoch": 0.49104638619201724,
+      "grad_norm": 0.4549376964569092,
+      "learning_rate": 0.00019999826375744715,
+      "loss": 0.9979530572891235,
+      "step": 1138
+    },
+    {
+      "epoch": 0.4919093851132686,
+      "grad_norm": 0.4363284409046173,
+      "learning_rate": 0.0001999979623274721,
+      "loss": 0.9295380115509033,
+      "step": 1140
+    },
+    {
+      "epoch": 0.49277238403451995,
+      "grad_norm": 0.5090877413749695,
+      "learning_rate": 0.0001999976367834392,
+      "loss": 0.8737252950668335,
+      "step": 1142
+    },
+    {
+      "epoch": 0.4936353829557713,
+      "grad_norm": 0.45340779423713684,
+      "learning_rate": 0.000199997287125427,
+      "loss": 0.8312779068946838,
+      "step": 1144
+    },
+    {
+      "epoch": 0.49449838187702266,
+      "grad_norm": 0.4771472215652466,
+      "learning_rate": 0.0001999969133535198,
+      "loss": 0.9105207324028015,
+      "step": 1146
+    },
+    {
+      "epoch": 0.495361380798274,
+      "grad_norm": 0.5251384377479553,
+      "learning_rate": 0.00019999651546780773,
+      "loss": 0.8578172922134399,
+      "step": 1148
+    },
+    {
+      "epoch": 0.4962243797195254,
+      "grad_norm": 0.49128198623657227,
+      "learning_rate": 0.00019999609346838676,
+      "loss": 0.9193941950798035,
+      "step": 1150
+    },
+    {
+      "epoch": 0.4970873786407767,
+      "grad_norm": 0.5558596849441528,
+      "learning_rate": 0.0001999956473553586,
+      "loss": 0.9141314625740051,
+      "step": 1152
+    },
+    {
+      "epoch": 0.49795037756202803,
+      "grad_norm": 0.45872750878334045,
+      "learning_rate": 0.00019999517712883087,
+      "loss": 0.9058388471603394,
+      "step": 1154
+    },
+    {
+      "epoch": 0.4988133764832794,
+      "grad_norm": 0.4710173010826111,
+      "learning_rate": 0.00019999468278891698,
+      "loss": 0.8462487459182739,
+      "step": 1156
+    },
+    {
+      "epoch": 0.49967637540453075,
+      "grad_norm": 0.4805637001991272,
+      "learning_rate": 0.0001999941643357361,
+      "loss": 0.8960906863212585,
+      "step": 1158
+    },
+    {
+      "epoch": 0.5005393743257821,
+      "grad_norm": 0.5108052492141724,
+      "learning_rate": 0.00019999362176941325,
+      "loss": 0.9074980020523071,
+      "step": 1160
+    },
+    {
+      "epoch": 0.5014023732470334,
+      "grad_norm": 0.49572333693504333,
+      "learning_rate": 0.00019999305509007932,
+      "loss": 0.9710080623626709,
+      "step": 1162
+    },
+    {
+      "epoch": 0.5022653721682848,
+      "grad_norm": 0.5304561257362366,
+      "learning_rate": 0.0001999924642978709,
+      "loss": 0.8877825140953064,
+      "step": 1164
+    },
+    {
+      "epoch": 0.5031283710895361,
+      "grad_norm": 0.5007328391075134,
+      "learning_rate": 0.0001999918493929305,
+      "loss": 0.8955381512641907,
+      "step": 1166
+    },
+    {
+      "epoch": 0.5039913700107875,
+      "grad_norm": 0.569549024105072,
+      "learning_rate": 0.0001999912103754064,
+      "loss": 0.9478562474250793,
+      "step": 1168
+    },
+    {
+      "epoch": 0.5048543689320388,
+      "grad_norm": 0.5354957580566406,
+      "learning_rate": 0.00019999054724545264,
+      "loss": 0.9685383439064026,
+      "step": 1170
+    },
+    {
+      "epoch": 0.5057173678532901,
+      "grad_norm": 0.547788143157959,
+      "learning_rate": 0.00019998986000322917,
+      "loss": 0.9221975207328796,
+      "step": 1172
+    },
+    {
+      "epoch": 0.5065803667745415,
+      "grad_norm": 0.4919529855251312,
+      "learning_rate": 0.00019998914864890175,
+      "loss": 0.9104788303375244,
+      "step": 1174
+    },
+    {
+      "epoch": 0.5074433656957928,
+      "grad_norm": 0.5274141430854797,
+      "learning_rate": 0.00019998841318264187,
+      "loss": 0.9176050424575806,
+      "step": 1176
+    },
+    {
+      "epoch": 0.5083063646170443,
+      "grad_norm": 0.4257420301437378,
+      "learning_rate": 0.00019998765360462688,
+      "loss": 0.8389710187911987,
+      "step": 1178
+    },
+    {
+      "epoch": 0.5091693635382956,
+      "grad_norm": 0.4947778880596161,
+      "learning_rate": 0.00019998686991504002,
+      "loss": 1.0164397954940796,
+      "step": 1180
+    },
+    {
+      "epoch": 0.510032362459547,
+      "grad_norm": 0.5540821552276611,
+      "learning_rate": 0.00019998606211407016,
+      "loss": 0.9900994300842285,
+      "step": 1182
+    },
+    {
+      "epoch": 0.5108953613807983,
+      "grad_norm": 0.4793289601802826,
+      "learning_rate": 0.0001999852302019122,
+      "loss": 0.8797636032104492,
+      "step": 1184
+    },
+    {
+      "epoch": 0.5117583603020496,
+      "grad_norm": 0.47429659962654114,
+      "learning_rate": 0.00019998437417876672,
+      "loss": 0.96225905418396,
+      "step": 1186
+    },
+    {
+      "epoch": 0.512621359223301,
+      "grad_norm": 0.44918450713157654,
+      "learning_rate": 0.00019998349404484013,
+      "loss": 0.8604235649108887,
+      "step": 1188
+    },
+    {
+      "epoch": 0.5134843581445523,
+      "grad_norm": 0.566977858543396,
+      "learning_rate": 0.00019998258980034468,
+      "loss": 1.0325366258621216,
+      "step": 1190
+    },
+    {
+      "epoch": 0.5143473570658037,
+      "grad_norm": 0.4671999514102936,
+      "learning_rate": 0.00019998166144549843,
+      "loss": 0.7658900022506714,
+      "step": 1192
+    },
+    {
+      "epoch": 0.515210355987055,
+      "grad_norm": 0.42312702536582947,
+      "learning_rate": 0.00019998070898052521,
+      "loss": 0.9365432858467102,
+      "step": 1194
+    },
+    {
+      "epoch": 0.5160733549083064,
+      "grad_norm": 0.4652721881866455,
+      "learning_rate": 0.00019997973240565476,
+      "loss": 0.771016538143158,
+      "step": 1196
+    },
+    {
+      "epoch": 0.5169363538295577,
+      "grad_norm": 0.5048499703407288,
+      "learning_rate": 0.00019997873172112254,
+      "loss": 0.9123705625534058,
+      "step": 1198
+    },
+    {
+      "epoch": 0.517799352750809,
+      "grad_norm": 0.5446439981460571,
+      "learning_rate": 0.0001999777069271699,
+      "loss": 0.8975751399993896,
+      "step": 1200
+    },
+    {
+      "epoch": 0.517799352750809,
+      "eval_loss": 0.9344067573547363,
+      "eval_runtime": 658.6934,
+      "eval_samples_per_second": 3.127,
+      "eval_steps_per_second": 3.127,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5186623516720604,
+      "grad_norm": 0.5044088959693909,
+      "learning_rate": 0.0001999766580240439,
+      "loss": 0.89097660779953,
+      "step": 1202
+    },
+    {
+      "epoch": 0.5195253505933117,
+      "grad_norm": 0.4672294855117798,
+      "learning_rate": 0.00019997558501199753,
+      "loss": 0.9138525128364563,
+      "step": 1204
+    },
+    {
+      "epoch": 0.5203883495145631,
+      "grad_norm": 0.45749008655548096,
+      "learning_rate": 0.00019997448789128952,
+      "loss": 0.8946340680122375,
+      "step": 1206
+    },
+    {
+      "epoch": 0.5212513484358144,
+      "grad_norm": 0.4828707277774811,
+      "learning_rate": 0.00019997336666218447,
+      "loss": 0.8661436438560486,
+      "step": 1208
+    },
+    {
+      "epoch": 0.5221143473570659,
+      "grad_norm": 0.3975147008895874,
+      "learning_rate": 0.0001999722213249527,
+      "loss": 0.7684835195541382,
+      "step": 1210
+    },
+    {
+      "epoch": 0.5229773462783172,
+      "grad_norm": 0.5642077326774597,
+      "learning_rate": 0.00019997105187987045,
+      "loss": 0.9667536616325378,
+      "step": 1212
+    },
+    {
+      "epoch": 0.5238403451995685,
+      "grad_norm": 0.4907105565071106,
+      "learning_rate": 0.00019996985832721972,
+      "loss": 0.8679366707801819,
+      "step": 1214
+    },
+    {
+      "epoch": 0.5247033441208199,
+      "grad_norm": 0.46214789152145386,
+      "learning_rate": 0.0001999686406672883,
+      "loss": 0.8802784085273743,
+      "step": 1216
+    },
+    {
+      "epoch": 0.5255663430420712,
+      "grad_norm": 0.4355131685733795,
+      "learning_rate": 0.00019996739890036985,
+      "loss": 0.8493598103523254,
+      "step": 1218
+    },
+    {
+      "epoch": 0.5264293419633226,
+      "grad_norm": 0.4293915331363678,
+      "learning_rate": 0.0001999661330267638,
+      "loss": 0.8949980735778809,
+      "step": 1220
+    },
+    {
+      "epoch": 0.5272923408845739,
+      "grad_norm": 0.5452485680580139,
+      "learning_rate": 0.00019996484304677544,
+      "loss": 0.9497376680374146,
+      "step": 1222
+    },
+    {
+      "epoch": 0.5281553398058253,
+      "grad_norm": 0.45874500274658203,
+      "learning_rate": 0.00019996352896071583,
+      "loss": 0.9170818328857422,
+      "step": 1224
+    },
+    {
+      "epoch": 0.5290183387270766,
+      "grad_norm": 0.4414025843143463,
+      "learning_rate": 0.00019996219076890182,
+      "loss": 0.7557252645492554,
+      "step": 1226
+    },
+    {
+      "epoch": 0.5298813376483279,
+      "grad_norm": 0.4891829192638397,
+      "learning_rate": 0.0001999608284716562,
+      "loss": 0.848960816860199,
+      "step": 1228
+    },
+    {
+      "epoch": 0.5307443365695793,
+      "grad_norm": 0.5048345327377319,
+      "learning_rate": 0.00019995944206930734,
+      "loss": 0.9555954933166504,
+      "step": 1230
+    },
+    {
+      "epoch": 0.5316073354908306,
+      "grad_norm": 0.5006756782531738,
+      "learning_rate": 0.00019995803156218968,
+      "loss": 0.8080939054489136,
+      "step": 1232
+    },
+    {
+      "epoch": 0.532470334412082,
+      "grad_norm": 0.5422173738479614,
+      "learning_rate": 0.00019995659695064332,
+      "loss": 0.8638371825218201,
+      "step": 1234
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.4535163640975952,
+      "learning_rate": 0.0001999551382350142,
+      "loss": 0.889068067073822,
+      "step": 1236
+    },
+    {
+      "epoch": 0.5341963322545846,
+      "grad_norm": 0.4588642418384552,
+      "learning_rate": 0.00019995365541565412,
+      "loss": 0.8803121447563171,
+      "step": 1238
+    },
+    {
+      "epoch": 0.535059331175836,
+      "grad_norm": 0.49366191029548645,
+      "learning_rate": 0.00019995214849292064,
+      "loss": 0.9694926738739014,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5359223300970873,
+      "grad_norm": 0.41988301277160645,
+      "learning_rate": 0.0001999506174671771,
+      "loss": 0.8367960453033447,
+      "step": 1242
+    },
+    {
+      "epoch": 0.5367853290183388,
+      "grad_norm": 0.5242130160331726,
+      "learning_rate": 0.00019994906233879273,
+      "loss": 0.942340612411499,
+      "step": 1244
+    },
+    {
+      "epoch": 0.53764832793959,
+      "grad_norm": 0.4899834096431732,
+      "learning_rate": 0.00019994748310814256,
+      "loss": 0.8926790356636047,
+      "step": 1246
+    },
+    {
+      "epoch": 0.5385113268608415,
+      "grad_norm": 0.5496823787689209,
+      "learning_rate": 0.00019994587977560744,
+      "loss": 0.99891597032547,
+      "step": 1248
+    },
+    {
+      "epoch": 0.5393743257820928,
+      "grad_norm": 0.4497414231300354,
+      "learning_rate": 0.00019994425234157396,
+      "loss": 0.8873116970062256,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5402373247033441,
+      "grad_norm": 0.4256928563117981,
+      "learning_rate": 0.00019994260080643454,
+      "loss": 0.9041396975517273,
+      "step": 1252
+    },
+    {
+      "epoch": 0.5411003236245955,
+      "grad_norm": 0.36910608410835266,
+      "learning_rate": 0.00019994092517058753,
+      "loss": 0.7647561430931091,
+      "step": 1254
+    },
+    {
+      "epoch": 0.5419633225458468,
+      "grad_norm": 0.537584125995636,
+      "learning_rate": 0.0001999392254344369,
+      "loss": 0.8892287015914917,
+      "step": 1256
+    },
+    {
+      "epoch": 0.5428263214670982,
+      "grad_norm": 0.49463894963264465,
+      "learning_rate": 0.00019993750159839264,
+      "loss": 0.8638571500778198,
+      "step": 1258
+    },
+    {
+      "epoch": 0.5436893203883495,
+      "grad_norm": 0.5052056908607483,
+      "learning_rate": 0.00019993575366287036,
+      "loss": 0.8165372014045715,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5445523193096009,
+      "grad_norm": 0.47367510199546814,
+      "learning_rate": 0.0001999339816282916,
+      "loss": 0.9099977016448975,
+      "step": 1262
+    },
+    {
+      "epoch": 0.5454153182308522,
+      "grad_norm": 0.4600350558757782,
+      "learning_rate": 0.00019993218549508364,
+      "loss": 0.8557311296463013,
+      "step": 1264
+    },
+    {
+      "epoch": 0.5462783171521035,
+      "grad_norm": 0.5684534311294556,
+      "learning_rate": 0.0001999303652636797,
+      "loss": 0.9136497974395752,
+      "step": 1266
+    },
+    {
+      "epoch": 0.5471413160733549,
+      "grad_norm": 0.5151359438896179,
+      "learning_rate": 0.00019992852093451865,
+      "loss": 0.7906932830810547,
+      "step": 1268
+    },
+    {
+      "epoch": 0.5480043149946062,
+      "grad_norm": 0.48577409982681274,
+      "learning_rate": 0.00019992665250804525,
+      "loss": 0.9326766133308411,
+      "step": 1270
+    },
+    {
+      "epoch": 0.5488673139158576,
+      "grad_norm": 0.490531325340271,
+      "learning_rate": 0.00019992475998471004,
+      "loss": 0.9734495878219604,
+      "step": 1272
+    },
+    {
+      "epoch": 0.5497303128371089,
+      "grad_norm": 0.5092435479164124,
+      "learning_rate": 0.00019992284336496947,
+      "loss": 0.8728410005569458,
+      "step": 1274
+    },
+    {
+      "epoch": 0.5505933117583603,
+      "grad_norm": 0.3843296766281128,
+      "learning_rate": 0.00019992090264928566,
+      "loss": 0.7572637796401978,
+      "step": 1276
+    },
+    {
+      "epoch": 0.5514563106796116,
+      "grad_norm": 0.534304678440094,
+      "learning_rate": 0.00019991893783812662,
+      "loss": 0.8895323872566223,
+      "step": 1278
+    },
+    {
+      "epoch": 0.552319309600863,
+      "grad_norm": 0.4567227363586426,
+      "learning_rate": 0.00019991694893196614,
+      "loss": 0.9318088293075562,
+      "step": 1280
+    },
+    {
+      "epoch": 0.5531823085221144,
+      "grad_norm": 0.48464900255203247,
+      "learning_rate": 0.0001999149359312839,
+      "loss": 0.8541979789733887,
+      "step": 1282
+    },
+    {
+      "epoch": 0.5540453074433657,
+      "grad_norm": 0.5569567084312439,
+      "learning_rate": 0.00019991289883656524,
+      "loss": 0.977894127368927,
+      "step": 1284
+    },
+    {
+      "epoch": 0.5549083063646171,
+      "grad_norm": 0.4637227952480316,
+      "learning_rate": 0.00019991083764830145,
+      "loss": 0.8860608339309692,
+      "step": 1286
+    },
+    {
+      "epoch": 0.5557713052858684,
+      "grad_norm": 0.4096687436103821,
+      "learning_rate": 0.00019990875236698956,
+      "loss": 0.8429648876190186,
+      "step": 1288
+    },
+    {
+      "epoch": 0.5566343042071198,
+      "grad_norm": 0.5221695303916931,
+      "learning_rate": 0.00019990664299313242,
+      "loss": 0.8510909080505371,
+      "step": 1290
+    },
+    {
+      "epoch": 0.5574973031283711,
+      "grad_norm": 0.5155899524688721,
+      "learning_rate": 0.00019990450952723872,
+      "loss": 0.8971074223518372,
+      "step": 1292
+    },
+    {
+      "epoch": 0.5583603020496224,
+      "grad_norm": 0.5064809322357178,
+      "learning_rate": 0.0001999023519698229,
+      "loss": 0.9030373096466064,
+      "step": 1294
+    },
+    {
+      "epoch": 0.5592233009708738,
+      "grad_norm": 0.40551698207855225,
+      "learning_rate": 0.00019990017032140526,
+      "loss": 0.7866057753562927,
+      "step": 1296
+    },
+    {
+      "epoch": 0.5600862998921251,
+      "grad_norm": 0.5009430050849915,
+      "learning_rate": 0.00019989796458251194,
+      "loss": 0.9477730989456177,
+      "step": 1298
+    },
+    {
+      "epoch": 0.5609492988133765,
+      "grad_norm": 0.5192028880119324,
+      "learning_rate": 0.00019989573475367477,
+      "loss": 0.9206778407096863,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5609492988133765,
+      "eval_loss": 0.9177446365356445,
+      "eval_runtime": 665.3245,
+      "eval_samples_per_second": 3.096,
+      "eval_steps_per_second": 3.096,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5618122977346278,
+      "grad_norm": 0.5580230951309204,
+      "learning_rate": 0.00019989348083543148,
+      "loss": 0.9516512155532837,
+      "step": 1302
+    },
+    {
+      "epoch": 0.5626752966558792,
+      "grad_norm": 0.4151005744934082,
+      "learning_rate": 0.00019989120282832564,
+      "loss": 0.7725991606712341,
+      "step": 1304
+    },
+    {
+      "epoch": 0.5635382955771305,
+      "grad_norm": 0.56330406665802,
+      "learning_rate": 0.00019988890073290656,
+      "loss": 0.9241501688957214,
+      "step": 1306
+    },
+    {
+      "epoch": 0.5644012944983818,
+      "grad_norm": 0.44836440682411194,
+      "learning_rate": 0.00019988657454972936,
+      "loss": 0.8351686000823975,
+      "step": 1308
+    },
+    {
+      "epoch": 0.5652642934196332,
+      "grad_norm": 0.5414754152297974,
+      "learning_rate": 0.00019988422427935496,
+      "loss": 0.9033217430114746,
+      "step": 1310
+    },
+    {
+      "epoch": 0.5661272923408845,
+      "grad_norm": 0.5283750891685486,
+      "learning_rate": 0.0001998818499223502,
+      "loss": 0.8885331153869629,
+      "step": 1312
+    },
+    {
+      "epoch": 0.566990291262136,
+      "grad_norm": 0.45846256613731384,
+      "learning_rate": 0.00019987945147928758,
+      "loss": 0.8359912037849426,
+      "step": 1314
+    },
+    {
+      "epoch": 0.5678532901833873,
+      "grad_norm": 0.44439879059791565,
+      "learning_rate": 0.0001998770289507455,
+      "loss": 0.8327895402908325,
+      "step": 1316
+    },
+    {
+      "epoch": 0.5687162891046387,
+      "grad_norm": 0.5491341948509216,
+      "learning_rate": 0.00019987458233730813,
+      "loss": 0.9354757070541382,
+      "step": 1318
+    },
+    {
+      "epoch": 0.56957928802589,
+      "grad_norm": 0.5502263307571411,
+      "learning_rate": 0.00019987211163956548,
+      "loss": 0.944054901599884,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5704422869471413,
+      "grad_norm": 0.47165682911872864,
+      "learning_rate": 0.00019986961685811334,
+      "loss": 0.9515072107315063,
+      "step": 1322
+    },
+    {
+      "epoch": 0.5713052858683927,
+      "grad_norm": 0.5136987566947937,
+      "learning_rate": 0.0001998670979935533,
+      "loss": 0.9455493688583374,
+      "step": 1324
+    },
+    {
+      "epoch": 0.572168284789644,
+      "grad_norm": 0.4822693169116974,
+      "learning_rate": 0.00019986455504649277,
+      "loss": 0.8626728057861328,
+      "step": 1326
+    },
+    {
+      "epoch": 0.5730312837108954,
+      "grad_norm": 0.4639468193054199,
+      "learning_rate": 0.000199861988017545,
+      "loss": 0.8857194781303406,
+      "step": 1328
+    },
+    {
+      "epoch": 0.5738942826321467,
+      "grad_norm": 0.5224950313568115,
+      "learning_rate": 0.00019985939690732898,
+      "loss": 0.9198446273803711,
+      "step": 1330
+    },
+    {
+      "epoch": 0.574757281553398,
+      "grad_norm": 0.47504499554634094,
+      "learning_rate": 0.00019985678171646954,
+      "loss": 0.8785439133644104,
+      "step": 1332
+    },
+    {
+      "epoch": 0.5756202804746494,
+      "grad_norm": 0.5022051930427551,
+      "learning_rate": 0.0001998541424455974,
+      "loss": 0.9593754410743713,
+      "step": 1334
+    },
+    {
+      "epoch": 0.5764832793959007,
+      "grad_norm": 0.4572875201702118,
+      "learning_rate": 0.00019985147909534897,
+      "loss": 0.986197292804718,
+      "step": 1336
+    },
+    {
+      "epoch": 0.5773462783171521,
+      "grad_norm": 0.5153827667236328,
+      "learning_rate": 0.00019984879166636644,
+      "loss": 0.9163863658905029,
+      "step": 1338
+    },
+    {
+      "epoch": 0.5782092772384034,
+      "grad_norm": 0.4813650846481323,
+      "learning_rate": 0.00019984608015929792,
+      "loss": 0.8815995454788208,
+      "step": 1340
+    },
+    {
+      "epoch": 0.5790722761596548,
+      "grad_norm": 0.4319819211959839,
+      "learning_rate": 0.0001998433445747973,
+      "loss": 0.857044517993927,
+      "step": 1342
+    },
+    {
+      "epoch": 0.5799352750809061,
+      "grad_norm": 0.5128870010375977,
+      "learning_rate": 0.00019984058491352423,
+      "loss": 0.8939256072044373,
+      "step": 1344
+    },
+    {
+      "epoch": 0.5807982740021574,
+      "grad_norm": 0.41450315713882446,
+      "learning_rate": 0.0001998378011761442,
+      "loss": 0.9267327785491943,
+      "step": 1346
+    },
+    {
+      "epoch": 0.5816612729234089,
+      "grad_norm": 0.42916348576545715,
+      "learning_rate": 0.00019983499336332844,
+      "loss": 0.8494639992713928,
+      "step": 1348
+    },
+    {
+      "epoch": 0.5825242718446602,
+      "grad_norm": 0.43995746970176697,
+      "learning_rate": 0.00019983216147575412,
+      "loss": 0.9720427989959717,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5833872707659116,
+      "grad_norm": 0.5063773989677429,
+      "learning_rate": 0.00019982930551410411,
+      "loss": 0.9400854706764221,
+      "step": 1352
+    },
+    {
+      "epoch": 0.5842502696871629,
+      "grad_norm": 0.5029586553573608,
+      "learning_rate": 0.0001998264254790671,
+      "loss": 0.8657845258712769,
+      "step": 1354
+    },
+    {
+      "epoch": 0.5851132686084143,
+      "grad_norm": 0.45519232749938965,
+      "learning_rate": 0.00019982352137133764,
+      "loss": 0.8593506813049316,
+      "step": 1356
+    },
+    {
+      "epoch": 0.5859762675296656,
+      "grad_norm": 0.49116215109825134,
+      "learning_rate": 0.000199820593191616,
+      "loss": 0.8658114671707153,
+      "step": 1358
+    },
+    {
+      "epoch": 0.5868392664509169,
+      "grad_norm": 0.45347318053245544,
+      "learning_rate": 0.00019981764094060826,
+      "loss": 0.8044605255126953,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5877022653721683,
+      "grad_norm": 0.5191754698753357,
+      "learning_rate": 0.00019981466461902643,
+      "loss": 0.9176861047744751,
+      "step": 1362
+    },
+    {
+      "epoch": 0.5885652642934196,
+      "grad_norm": 0.4791528284549713,
+      "learning_rate": 0.00019981166422758818,
+      "loss": 0.8453370928764343,
+      "step": 1364
+    },
+    {
+      "epoch": 0.589428263214671,
+      "grad_norm": 0.5105116367340088,
+      "learning_rate": 0.00019980863976701705,
+      "loss": 0.9343777298927307,
+      "step": 1366
+    },
+    {
+      "epoch": 0.5902912621359223,
+      "grad_norm": 0.44593656063079834,
+      "learning_rate": 0.00019980559123804236,
+      "loss": 0.8950760960578918,
+      "step": 1368
+    },
+    {
+      "epoch": 0.5911542610571737,
+      "grad_norm": 0.4375658631324768,
+      "learning_rate": 0.0001998025186413993,
+      "loss": 0.8613521456718445,
+      "step": 1370
+    },
+    {
+      "epoch": 0.592017259978425,
+      "grad_norm": 0.5138815641403198,
+      "learning_rate": 0.00019979942197782878,
+      "loss": 0.8982083201408386,
+      "step": 1372
+    },
+    {
+      "epoch": 0.5928802588996763,
+      "grad_norm": 0.45473602414131165,
+      "learning_rate": 0.00019979630124807753,
+      "loss": 0.9372450709342957,
+      "step": 1374
+    },
+    {
+      "epoch": 0.5937432578209277,
+      "grad_norm": 0.4961191713809967,
+      "learning_rate": 0.00019979315645289814,
+      "loss": 0.8758652806282043,
+      "step": 1376
+    },
+    {
+      "epoch": 0.594606256742179,
+      "grad_norm": 0.5672827363014221,
+      "learning_rate": 0.00019978998759304895,
+      "loss": 0.9852207899093628,
+      "step": 1378
+    },
+    {
+      "epoch": 0.5954692556634305,
+      "grad_norm": 0.44907906651496887,
+      "learning_rate": 0.00019978679466929407,
+      "loss": 0.8451287746429443,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5963322545846818,
+      "grad_norm": 0.4759652316570282,
+      "learning_rate": 0.00019978357768240352,
+      "loss": 0.8381558656692505,
+      "step": 1382
+    },
+    {
+      "epoch": 0.5971952535059332,
+      "grad_norm": 0.4936048686504364,
+      "learning_rate": 0.00019978033663315304,
+      "loss": 0.8820816874504089,
+      "step": 1384
+    },
+    {
+      "epoch": 0.5980582524271845,
+      "grad_norm": 0.44983741641044617,
+      "learning_rate": 0.00019977707152232416,
+      "loss": 0.9156787991523743,
+      "step": 1386
+    },
+    {
+      "epoch": 0.5989212513484358,
+      "grad_norm": 0.45198705792427063,
+      "learning_rate": 0.0001997737823507043,
+      "loss": 0.8285194039344788,
+      "step": 1388
+    },
+    {
+      "epoch": 0.5997842502696872,
+      "grad_norm": 0.45788463950157166,
+      "learning_rate": 0.00019977046911908664,
+      "loss": 0.8109505772590637,
+      "step": 1390
+    },
+    {
+      "epoch": 0.6006472491909385,
+      "grad_norm": 0.4795142412185669,
+      "learning_rate": 0.0001997671318282701,
+      "loss": 0.8285947442054749,
+      "step": 1392
+    },
+    {
+      "epoch": 0.6015102481121899,
+      "grad_norm": 0.5026728510856628,
+      "learning_rate": 0.00019976377047905945,
+      "loss": 0.9497535228729248,
+      "step": 1394
+    },
+    {
+      "epoch": 0.6023732470334412,
+      "grad_norm": 0.4994853734970093,
+      "learning_rate": 0.0001997603850722653,
+      "loss": 0.9171916246414185,
+      "step": 1396
+    },
+    {
+      "epoch": 0.6032362459546926,
+      "grad_norm": 0.4789866507053375,
+      "learning_rate": 0.00019975697560870403,
+      "loss": 0.7894434928894043,
+      "step": 1398
+    },
+    {
+      "epoch": 0.6040992448759439,
+      "grad_norm": 0.42282742261886597,
+      "learning_rate": 0.0001997535420891978,
+      "loss": 0.8942429423332214,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6040992448759439,
+      "eval_loss": 0.9080492854118347,
+      "eval_runtime": 661.4597,
+      "eval_samples_per_second": 3.114,
+      "eval_steps_per_second": 3.114,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6049622437971952,
+      "grad_norm": 0.5789905190467834,
+      "learning_rate": 0.00019975008451457454,
+      "loss": 0.8938372731208801,
+      "step": 1402
+    },
+    {
+      "epoch": 0.6058252427184466,
+      "grad_norm": 0.46121683716773987,
+      "learning_rate": 0.00019974660288566814,
+      "loss": 0.8746235370635986,
+      "step": 1404
+    },
+    {
+      "epoch": 0.6066882416396979,
+      "grad_norm": 0.5195551514625549,
+      "learning_rate": 0.00019974309720331807,
+      "loss": 0.8650617003440857,
+      "step": 1406
+    },
+    {
+      "epoch": 0.6075512405609493,
+      "grad_norm": 0.46930259466171265,
+      "learning_rate": 0.00019973956746836976,
+      "loss": 0.8853039145469666,
+      "step": 1408
+    },
+    {
+      "epoch": 0.6084142394822006,
+      "grad_norm": 0.40869632363319397,
+      "learning_rate": 0.0001997360136816744,
+      "loss": 0.7865594029426575,
+      "step": 1410
+    },
+    {
+      "epoch": 0.609277238403452,
+      "grad_norm": 0.5398361086845398,
+      "learning_rate": 0.00019973243584408895,
+      "loss": 0.907535970211029,
+      "step": 1412
+    },
+    {
+      "epoch": 0.6101402373247033,
+      "grad_norm": 0.5110154747962952,
+      "learning_rate": 0.00019972883395647615,
+      "loss": 0.8682730197906494,
+      "step": 1414
+    },
+    {
+      "epoch": 0.6110032362459547,
+      "grad_norm": 0.44484639167785645,
+      "learning_rate": 0.00019972520801970467,
+      "loss": 0.8786011338233948,
+      "step": 1416
+    },
+    {
+      "epoch": 0.6118662351672061,
+      "grad_norm": 0.4768071472644806,
+      "learning_rate": 0.0001997215580346488,
+      "loss": 0.9021878242492676,
+      "step": 1418
+    },
+    {
+      "epoch": 0.6127292340884574,
+      "grad_norm": 0.43265241384506226,
+      "learning_rate": 0.0001997178840021888,
+      "loss": 0.7737482786178589,
+      "step": 1420
+    },
+    {
+      "epoch": 0.6135922330097088,
+      "grad_norm": 0.525692343711853,
+      "learning_rate": 0.0001997141859232106,
+      "loss": 0.876280665397644,
+      "step": 1422
+    },
+    {
+      "epoch": 0.6144552319309601,
+      "grad_norm": 0.48206865787506104,
+      "learning_rate": 0.00019971046379860594,
+      "loss": 0.8503577709197998,
+      "step": 1424
+    },
+    {
+      "epoch": 0.6153182308522115,
+      "grad_norm": 0.6032769680023193,
+      "learning_rate": 0.00019970671762927246,
+      "loss": 0.9459730982780457,
+      "step": 1426
+    },
+    {
+      "epoch": 0.6161812297734628,
+      "grad_norm": 0.4491981863975525,
+      "learning_rate": 0.0001997029474161135,
+      "loss": 0.8836647868156433,
+      "step": 1428
+    },
+    {
+      "epoch": 0.6170442286947141,
+      "grad_norm": 0.47503358125686646,
+      "learning_rate": 0.00019969915316003824,
+      "loss": 0.8614388108253479,
+      "step": 1430
+    },
+    {
+      "epoch": 0.6179072276159655,
+      "grad_norm": 0.44801047444343567,
+      "learning_rate": 0.00019969533486196162,
+      "loss": 0.8420360684394836,
+      "step": 1432
+    },
+    {
+      "epoch": 0.6187702265372168,
+      "grad_norm": 0.45057111978530884,
+      "learning_rate": 0.00019969149252280446,
+      "loss": 0.8256269693374634,
+      "step": 1434
+    },
+    {
+      "epoch": 0.6196332254584682,
+      "grad_norm": 0.4589645266532898,
+      "learning_rate": 0.00019968762614349327,
+      "loss": 0.9130199551582336,
+      "step": 1436
+    },
+    {
+      "epoch": 0.6204962243797195,
+      "grad_norm": 0.48914027214050293,
+      "learning_rate": 0.00019968373572496045,
+      "loss": 0.74083012342453,
+      "step": 1438
+    },
+    {
+      "epoch": 0.6213592233009708,
+      "grad_norm": 0.4582098424434662,
+      "learning_rate": 0.00019967982126814412,
+      "loss": 0.8538379669189453,
+      "step": 1440
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.48722779750823975,
+      "learning_rate": 0.00019967588277398823,
+      "loss": 0.8780114054679871,
+      "step": 1442
+    },
+    {
+      "epoch": 0.6230852211434735,
+      "grad_norm": 0.4291327893733978,
+      "learning_rate": 0.00019967192024344254,
+      "loss": 0.8341028690338135,
+      "step": 1444
+    },
+    {
+      "epoch": 0.623948220064725,
+      "grad_norm": 0.4773139953613281,
+      "learning_rate": 0.00019966793367746265,
+      "loss": 0.8651667237281799,
+      "step": 1446
+    },
+    {
+      "epoch": 0.6248112189859762,
+      "grad_norm": 0.45556166768074036,
+      "learning_rate": 0.00019966392307700986,
+      "loss": 0.8339929580688477,
+      "step": 1448
+    },
+    {
+      "epoch": 0.6256742179072277,
+      "grad_norm": 0.5126671195030212,
+      "learning_rate": 0.00019965988844305129,
+      "loss": 0.9129340052604675,
+      "step": 1450
+    },
+    {
+      "epoch": 0.626537216828479,
+      "grad_norm": 0.6067109704017639,
+      "learning_rate": 0.00019965582977655988,
+      "loss": 0.9057610034942627,
+      "step": 1452
+    },
+    {
+      "epoch": 0.6274002157497303,
+      "grad_norm": 0.46425968408584595,
+      "learning_rate": 0.00019965174707851438,
+      "loss": 0.874100387096405,
+      "step": 1454
+    },
+    {
+      "epoch": 0.6282632146709817,
+      "grad_norm": 0.481077641248703,
+      "learning_rate": 0.0001996476403498993,
+      "loss": 0.915635347366333,
+      "step": 1456
+    },
+    {
+      "epoch": 0.629126213592233,
+      "grad_norm": 0.47299909591674805,
+      "learning_rate": 0.000199643509591705,
+      "loss": 0.9059650301933289,
+      "step": 1458
+    },
+    {
+      "epoch": 0.6299892125134844,
+      "grad_norm": 0.48924630880355835,
+      "learning_rate": 0.00019963935480492753,
+      "loss": 0.9775188565254211,
+      "step": 1460
+    },
+    {
+      "epoch": 0.6308522114347357,
+      "grad_norm": 0.4407665431499481,
+      "learning_rate": 0.0001996351759905688,
+      "loss": 0.8950685858726501,
+      "step": 1462
+    },
+    {
+      "epoch": 0.6317152103559871,
+      "grad_norm": 0.5018318295478821,
+      "learning_rate": 0.00019963097314963657,
+      "loss": 0.8532119989395142,
+      "step": 1464
+    },
+    {
+      "epoch": 0.6325782092772384,
+      "grad_norm": 0.43245720863342285,
+      "learning_rate": 0.0001996267462831443,
+      "loss": 0.7775963544845581,
+      "step": 1466
+    },
+    {
+      "epoch": 0.6334412081984897,
+      "grad_norm": 0.5028865337371826,
+      "learning_rate": 0.00019962249539211125,
+      "loss": 0.8315839767456055,
+      "step": 1468
+    },
+    {
+      "epoch": 0.6343042071197411,
+      "grad_norm": 0.4697185754776001,
+      "learning_rate": 0.0001996182204775626,
+      "loss": 0.849076509475708,
+      "step": 1470
+    },
+    {
+      "epoch": 0.6351672060409924,
+      "grad_norm": 0.46725034713745117,
+      "learning_rate": 0.00019961392154052912,
+      "loss": 0.8828577995300293,
+      "step": 1472
+    },
+    {
+      "epoch": 0.6360302049622438,
+      "grad_norm": 0.4301203489303589,
+      "learning_rate": 0.00019960959858204754,
+      "loss": 0.850115954875946,
+      "step": 1474
+    },
+    {
+      "epoch": 0.6368932038834951,
+      "grad_norm": 0.46635881066322327,
+      "learning_rate": 0.0001996052516031603,
+      "loss": 0.7912618517875671,
+      "step": 1476
+    },
+    {
+      "epoch": 0.6377562028047465,
+      "grad_norm": 0.44143620133399963,
+      "learning_rate": 0.00019960088060491565,
+      "loss": 0.9072504639625549,
+      "step": 1478
+    },
+    {
+      "epoch": 0.6386192017259978,
+      "grad_norm": 0.47458893060684204,
+      "learning_rate": 0.00019959648558836763,
+      "loss": 0.8976638317108154,
+      "step": 1480
+    },
+    {
+      "epoch": 0.6394822006472491,
+      "grad_norm": 0.4596816897392273,
+      "learning_rate": 0.00019959206655457612,
+      "loss": 0.8142043352127075,
+      "step": 1482
+    },
+    {
+      "epoch": 0.6403451995685006,
+      "grad_norm": 0.4839977025985718,
+      "learning_rate": 0.0001995876235046067,
+      "loss": 0.860643744468689,
+      "step": 1484
+    },
+    {
+      "epoch": 0.6412081984897519,
+      "grad_norm": 0.3542814552783966,
+      "learning_rate": 0.00019958315643953085,
+      "loss": 0.7586524486541748,
+      "step": 1486
+    },
+    {
+      "epoch": 0.6420711974110033,
+      "grad_norm": 0.5423269271850586,
+      "learning_rate": 0.00019957866536042572,
+      "loss": 0.9353570342063904,
+      "step": 1488
+    },
+    {
+      "epoch": 0.6429341963322546,
+      "grad_norm": 0.4580909013748169,
+      "learning_rate": 0.00019957415026837437,
+      "loss": 0.9919291138648987,
+      "step": 1490
+    },
+    {
+      "epoch": 0.643797195253506,
+      "grad_norm": 0.4211732745170593,
+      "learning_rate": 0.00019956961116446555,
+      "loss": 0.8720914125442505,
+      "step": 1492
+    },
+    {
+      "epoch": 0.6446601941747573,
+      "grad_norm": 0.4583161175251007,
+      "learning_rate": 0.00019956504804979384,
+      "loss": 0.8661212921142578,
+      "step": 1494
+    },
+    {
+      "epoch": 0.6455231930960086,
+      "grad_norm": 0.4359884262084961,
+      "learning_rate": 0.00019956046092545966,
+      "loss": 0.8170996308326721,
+      "step": 1496
+    },
+    {
+      "epoch": 0.64638619201726,
+      "grad_norm": 0.4642556607723236,
+      "learning_rate": 0.00019955584979256913,
+      "loss": 0.8607422113418579,
+      "step": 1498
+    },
+    {
+      "epoch": 0.6472491909385113,
+      "grad_norm": 0.4496007561683655,
+      "learning_rate": 0.00019955121465223426,
+      "loss": 0.837529182434082,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6472491909385113,
+      "eval_loss": 0.8972997665405273,
+      "eval_runtime": 649.796,
+      "eval_samples_per_second": 3.17,
+      "eval_steps_per_second": 3.17,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6481121898597627,
+      "grad_norm": 0.48363205790519714,
+      "learning_rate": 0.0001995465555055727,
+      "loss": 0.9355250000953674,
+      "step": 1502
+    },
+    {
+      "epoch": 0.648975188781014,
+      "grad_norm": 0.44681695103645325,
+      "learning_rate": 0.0001995418723537081,
+      "loss": 0.8286949396133423,
+      "step": 1504
+    },
+    {
+      "epoch": 0.6498381877022654,
+      "grad_norm": 0.5110394358634949,
+      "learning_rate": 0.00019953716519776967,
+      "loss": 0.890398383140564,
+      "step": 1506
+    },
+    {
+      "epoch": 0.6507011866235167,
+      "grad_norm": 0.4353160262107849,
+      "learning_rate": 0.00019953243403889257,
+      "loss": 0.8117311000823975,
+      "step": 1508
+    },
+    {
+      "epoch": 0.651564185544768,
+      "grad_norm": 0.4731789231300354,
+      "learning_rate": 0.0001995276788782177,
+      "loss": 0.8255904316902161,
+      "step": 1510
+    },
+    {
+      "epoch": 0.6524271844660194,
+      "grad_norm": 0.5447185039520264,
+      "learning_rate": 0.00019952289971689177,
+      "loss": 0.9371263384819031,
+      "step": 1512
+    },
+    {
+      "epoch": 0.6532901833872707,
+      "grad_norm": 0.47616517543792725,
+      "learning_rate": 0.0001995180965560672,
+      "loss": 0.8532910943031311,
+      "step": 1514
+    },
+    {
+      "epoch": 0.6541531823085222,
+      "grad_norm": 0.4412213861942291,
+      "learning_rate": 0.0001995132693969023,
+      "loss": 0.8799141645431519,
+      "step": 1516
+    },
+    {
+      "epoch": 0.6550161812297735,
+      "grad_norm": 0.469911128282547,
+      "learning_rate": 0.00019950841824056107,
+      "loss": 0.8395764827728271,
+      "step": 1518
+    },
+    {
+      "epoch": 0.6558791801510249,
+      "grad_norm": 0.5236243009567261,
+      "learning_rate": 0.00019950354308821336,
+      "loss": 0.9556697010993958,
+      "step": 1520
+    },
+    {
+      "epoch": 0.6567421790722762,
+      "grad_norm": 0.4441990256309509,
+      "learning_rate": 0.00019949864394103482,
+      "loss": 0.8524283170700073,
+      "step": 1522
+    },
+    {
+      "epoch": 0.6576051779935275,
+      "grad_norm": 0.4173077940940857,
+      "learning_rate": 0.00019949372080020682,
+      "loss": 0.9213772416114807,
+      "step": 1524
+    },
+    {
+      "epoch": 0.6584681769147789,
+      "grad_norm": 0.4404120147228241,
+      "learning_rate": 0.00019948877366691658,
+      "loss": 0.9236897230148315,
+      "step": 1526
+    },
+    {
+      "epoch": 0.6593311758360302,
+      "grad_norm": 0.4586230516433716,
+      "learning_rate": 0.00019948380254235706,
+      "loss": 0.8373230695724487,
+      "step": 1528
+    },
+    {
+      "epoch": 0.6601941747572816,
+      "grad_norm": 0.4136028587818146,
+      "learning_rate": 0.00019947880742772703,
+      "loss": 0.8256528377532959,
+      "step": 1530
+    },
+    {
+      "epoch": 0.6610571736785329,
+      "grad_norm": 0.5007129907608032,
+      "learning_rate": 0.00019947378832423107,
+      "loss": 0.8580789566040039,
+      "step": 1532
+    },
+    {
+      "epoch": 0.6619201725997842,
+      "grad_norm": 0.39050203561782837,
+      "learning_rate": 0.00019946874523307947,
+      "loss": 0.7647744417190552,
+      "step": 1534
+    },
+    {
+      "epoch": 0.6627831715210356,
+      "grad_norm": 0.4640588164329529,
+      "learning_rate": 0.00019946367815548835,
+      "loss": 0.9042545557022095,
+      "step": 1536
+    },
+    {
+      "epoch": 0.6636461704422869,
+      "grad_norm": 0.5304957032203674,
+      "learning_rate": 0.00019945858709267963,
+      "loss": 0.9114110469818115,
+      "step": 1538
+    },
+    {
+      "epoch": 0.6645091693635383,
+      "grad_norm": 0.5426004528999329,
+      "learning_rate": 0.000199453472045881,
+      "loss": 0.8239460587501526,
+      "step": 1540
+    },
+    {
+      "epoch": 0.6653721682847896,
+      "grad_norm": 0.44893568754196167,
+      "learning_rate": 0.00019944833301632593,
+      "loss": 0.8091367483139038,
+      "step": 1542
+    },
+    {
+      "epoch": 0.666235167206041,
+      "grad_norm": 0.4294016361236572,
+      "learning_rate": 0.00019944317000525366,
+      "loss": 0.9202280640602112,
+      "step": 1544
+    },
+    {
+      "epoch": 0.6670981661272923,
+      "grad_norm": 0.449633926153183,
+      "learning_rate": 0.00019943798301390927,
+      "loss": 0.8884767889976501,
+      "step": 1546
+    },
+    {
+      "epoch": 0.6679611650485436,
+      "grad_norm": 0.4516827166080475,
+      "learning_rate": 0.0001994327720435435,
+      "loss": 0.8390879034996033,
+      "step": 1548
+    },
+    {
+      "epoch": 0.668824163969795,
+      "grad_norm": 0.422270268201828,
+      "learning_rate": 0.000199427537095413,
+      "loss": 0.7388033270835876,
+      "step": 1550
+    },
+    {
+      "epoch": 0.6696871628910464,
+      "grad_norm": 0.580563485622406,
+      "learning_rate": 0.00019942227817078015,
+      "loss": 0.9268350601196289,
+      "step": 1552
+    },
+    {
+      "epoch": 0.6705501618122978,
+      "grad_norm": 0.4436347782611847,
+      "learning_rate": 0.00019941699527091316,
+      "loss": 0.7978561520576477,
+      "step": 1554
+    },
+    {
+      "epoch": 0.6714131607335491,
+      "grad_norm": 0.4149787127971649,
+      "learning_rate": 0.0001994116883970859,
+      "loss": 0.8229286670684814,
+      "step": 1556
+    },
+    {
+      "epoch": 0.6722761596548005,
+      "grad_norm": 0.49915504455566406,
+      "learning_rate": 0.00019940635755057813,
+      "loss": 0.8554545640945435,
+      "step": 1558
+    },
+    {
+      "epoch": 0.6731391585760518,
+      "grad_norm": 0.45326656103134155,
+      "learning_rate": 0.00019940100273267537,
+      "loss": 0.9135572910308838,
+      "step": 1560
+    },
+    {
+      "epoch": 0.6740021574973031,
+      "grad_norm": 0.48639237880706787,
+      "learning_rate": 0.0001993956239446689,
+      "loss": 0.7769742012023926,
+      "step": 1562
+    },
+    {
+      "epoch": 0.6748651564185545,
+      "grad_norm": 0.5072791576385498,
+      "learning_rate": 0.0001993902211878558,
+      "loss": 0.9626237154006958,
+      "step": 1564
+    },
+    {
+      "epoch": 0.6757281553398058,
+      "grad_norm": 0.4646652638912201,
+      "learning_rate": 0.00019938479446353892,
+      "loss": 0.8506941199302673,
+      "step": 1566
+    },
+    {
+      "epoch": 0.6765911542610572,
+      "grad_norm": 0.4343051314353943,
+      "learning_rate": 0.00019937934377302688,
+      "loss": 0.8172947764396667,
+      "step": 1568
+    },
+    {
+      "epoch": 0.6774541531823085,
+      "grad_norm": 0.46890193223953247,
+      "learning_rate": 0.00019937386911763407,
+      "loss": 0.9215856790542603,
+      "step": 1570
+    },
+    {
+      "epoch": 0.6783171521035599,
+      "grad_norm": 0.5121113061904907,
+      "learning_rate": 0.0001993683704986807,
+      "loss": 0.8099892139434814,
+      "step": 1572
+    },
+    {
+      "epoch": 0.6791801510248112,
+      "grad_norm": 0.4652405083179474,
+      "learning_rate": 0.0001993628479174928,
+      "loss": 0.8675104975700378,
+      "step": 1574
+    },
+    {
+      "epoch": 0.6800431499460625,
+      "grad_norm": 0.4599422812461853,
+      "learning_rate": 0.00019935730137540198,
+      "loss": 0.7938929200172424,
+      "step": 1576
+    },
+    {
+      "epoch": 0.6809061488673139,
+      "grad_norm": 0.4738059937953949,
+      "learning_rate": 0.0001993517308737459,
+      "loss": 0.8610570430755615,
+      "step": 1578
+    },
+    {
+      "epoch": 0.6817691477885652,
+      "grad_norm": 0.5161214470863342,
+      "learning_rate": 0.00019934613641386776,
+      "loss": 0.9199413657188416,
+      "step": 1580
+    },
+    {
+      "epoch": 0.6826321467098166,
+      "grad_norm": 0.4284999370574951,
+      "learning_rate": 0.00019934051799711672,
+      "loss": 0.771649181842804,
+      "step": 1582
+    },
+    {
+      "epoch": 0.683495145631068,
+      "grad_norm": 0.5117548704147339,
+      "learning_rate": 0.00019933487562484757,
+      "loss": 0.8861327767372131,
+      "step": 1584
+    },
+    {
+      "epoch": 0.6843581445523194,
+      "grad_norm": 0.4964369833469391,
+      "learning_rate": 0.00019932920929842095,
+      "loss": 0.806983232498169,
+      "step": 1586
+    },
+    {
+      "epoch": 0.6852211434735707,
+      "grad_norm": 0.4699532091617584,
+      "learning_rate": 0.00019932351901920327,
+      "loss": 0.7963525652885437,
+      "step": 1588
+    },
+    {
+      "epoch": 0.686084142394822,
+      "grad_norm": 0.5329220294952393,
+      "learning_rate": 0.00019931780478856678,
+      "loss": 0.9406430721282959,
+      "step": 1590
+    },
+    {
+      "epoch": 0.6869471413160734,
+      "grad_norm": 0.49823835492134094,
+      "learning_rate": 0.00019931206660788936,
+      "loss": 0.8517770171165466,
+      "step": 1592
+    },
+    {
+      "epoch": 0.6878101402373247,
+      "grad_norm": 0.45245134830474854,
+      "learning_rate": 0.00019930630447855482,
+      "loss": 0.8703644275665283,
+      "step": 1594
+    },
+    {
+      "epoch": 0.6886731391585761,
+      "grad_norm": 0.47524577379226685,
+      "learning_rate": 0.0001993005184019526,
+      "loss": 0.9035283327102661,
+      "step": 1596
+    },
+    {
+      "epoch": 0.6895361380798274,
+      "grad_norm": 0.4537610411643982,
+      "learning_rate": 0.00019929470837947802,
+      "loss": 0.9173959493637085,
+      "step": 1598
+    },
+    {
+      "epoch": 0.6903991370010788,
+      "grad_norm": 0.42469722032546997,
+      "learning_rate": 0.00019928887441253212,
+      "loss": 0.8573579788208008,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6903991370010788,
+      "eval_loss": 0.8880587220191956,
+      "eval_runtime": 653.9515,
+      "eval_samples_per_second": 3.15,
+      "eval_steps_per_second": 3.15,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6912621359223301,
+      "grad_norm": 0.4388251304626465,
+      "learning_rate": 0.00019928301650252176,
+      "loss": 0.849348247051239,
+      "step": 1602
+    },
+    {
+      "epoch": 0.6921251348435814,
+      "grad_norm": 0.46086886525154114,
+      "learning_rate": 0.00019927713465085956,
+      "loss": 0.8298451900482178,
+      "step": 1604
+    },
+    {
+      "epoch": 0.6929881337648328,
+      "grad_norm": 0.42972785234451294,
+      "learning_rate": 0.00019927122885896387,
+      "loss": 0.8860712647438049,
+      "step": 1606
+    },
+    {
+      "epoch": 0.6938511326860841,
+      "grad_norm": 0.43009471893310547,
+      "learning_rate": 0.00019926529912825888,
+      "loss": 0.7972728610038757,
+      "step": 1608
+    },
+    {
+      "epoch": 0.6947141316073355,
+      "grad_norm": 0.3705308437347412,
+      "learning_rate": 0.00019925934546017446,
+      "loss": 0.8661653995513916,
+      "step": 1610
+    },
+    {
+      "epoch": 0.6955771305285868,
+      "grad_norm": 0.405208945274353,
+      "learning_rate": 0.00019925336785614635,
+      "loss": 0.8350111246109009,
+      "step": 1612
+    },
+    {
+      "epoch": 0.6964401294498382,
+      "grad_norm": 0.4773033857345581,
+      "learning_rate": 0.00019924736631761602,
+      "loss": 0.7920925617218018,
+      "step": 1614
+    },
+    {
+      "epoch": 0.6973031283710895,
+      "grad_norm": 0.4682428240776062,
+      "learning_rate": 0.00019924134084603075,
+      "loss": 0.8644304871559143,
+      "step": 1616
+    },
+    {
+      "epoch": 0.6981661272923408,
+      "grad_norm": 0.5694834589958191,
+      "learning_rate": 0.00019923529144284346,
+      "loss": 0.9897904992103577,
+      "step": 1618
+    },
+    {
+      "epoch": 0.6990291262135923,
+      "grad_norm": 0.40137484669685364,
+      "learning_rate": 0.00019922921810951302,
+      "loss": 0.6910083293914795,
+      "step": 1620
+    },
+    {
+      "epoch": 0.6998921251348436,
+      "grad_norm": 0.42076537013053894,
+      "learning_rate": 0.000199223120847504,
+      "loss": 0.8295826315879822,
+      "step": 1622
+    },
+    {
+      "epoch": 0.700755124056095,
+      "grad_norm": 0.4473017752170563,
+      "learning_rate": 0.00019921699965828662,
+      "loss": 0.820871889591217,
+      "step": 1624
+    },
+    {
+      "epoch": 0.7016181229773463,
+      "grad_norm": 0.43914029002189636,
+      "learning_rate": 0.00019921085454333706,
+      "loss": 0.8319019079208374,
+      "step": 1626
+    },
+    {
+      "epoch": 0.7024811218985976,
+      "grad_norm": 0.4758487939834595,
+      "learning_rate": 0.0001992046855041372,
+      "loss": 0.8589251041412354,
+      "step": 1628
+    },
+    {
+      "epoch": 0.703344120819849,
+      "grad_norm": 0.506401538848877,
+      "learning_rate": 0.00019919849254217465,
+      "loss": 0.9219205975532532,
+      "step": 1630
+    },
+    {
+      "epoch": 0.7042071197411003,
+      "grad_norm": 0.4397984445095062,
+      "learning_rate": 0.00019919227565894277,
+      "loss": 0.7824978232383728,
+      "step": 1632
+    },
+    {
+      "epoch": 0.7050701186623517,
+      "grad_norm": 0.3879252076148987,
+      "learning_rate": 0.0001991860348559408,
+      "loss": 0.8472069501876831,
+      "step": 1634
+    },
+    {
+      "epoch": 0.705933117583603,
+      "grad_norm": 0.42238810658454895,
+      "learning_rate": 0.00019917977013467368,
+      "loss": 0.824957013130188,
+      "step": 1636
+    },
+    {
+      "epoch": 0.7067961165048544,
+      "grad_norm": 0.5235037207603455,
+      "learning_rate": 0.00019917348149665206,
+      "loss": 0.9490993022918701,
+      "step": 1638
+    },
+    {
+      "epoch": 0.7076591154261057,
+      "grad_norm": 0.5195287466049194,
+      "learning_rate": 0.0001991671689433925,
+      "loss": 0.960905909538269,
+      "step": 1640
+    },
+    {
+      "epoch": 0.708522114347357,
+      "grad_norm": 0.5016481876373291,
+      "learning_rate": 0.00019916083247641716,
+      "loss": 0.8961218595504761,
+      "step": 1642
+    },
+    {
+      "epoch": 0.7093851132686084,
+      "grad_norm": 0.5510191321372986,
+      "learning_rate": 0.00019915447209725408,
+      "loss": 0.8883417844772339,
+      "step": 1644
+    },
+    {
+      "epoch": 0.7102481121898597,
+      "grad_norm": 0.4492250084877014,
+      "learning_rate": 0.0001991480878074371,
+      "loss": 0.7968636751174927,
+      "step": 1646
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.4189683496952057,
+      "learning_rate": 0.00019914167960850563,
+      "loss": 0.7869221568107605,
+      "step": 1648
+    },
+    {
+      "epoch": 0.7119741100323624,
+      "grad_norm": 0.4590536653995514,
+      "learning_rate": 0.0001991352475020051,
+      "loss": 0.8423646092414856,
+      "step": 1650
+    },
+    {
+      "epoch": 0.7128371089536139,
+      "grad_norm": 0.5058966875076294,
+      "learning_rate": 0.00019912879148948652,
+      "loss": 0.895459771156311,
+      "step": 1652
+    },
+    {
+      "epoch": 0.7137001078748652,
+      "grad_norm": 0.4904550313949585,
+      "learning_rate": 0.00019912231157250676,
+      "loss": 0.8737894296646118,
+      "step": 1654
+    },
+    {
+      "epoch": 0.7145631067961165,
+      "grad_norm": 0.4670710861682892,
+      "learning_rate": 0.0001991158077526284,
+      "loss": 0.8019732236862183,
+      "step": 1656
+    },
+    {
+      "epoch": 0.7154261057173679,
+      "grad_norm": 0.530343770980835,
+      "learning_rate": 0.00019910928003141984,
+      "loss": 0.9474499821662903,
+      "step": 1658
+    },
+    {
+      "epoch": 0.7162891046386192,
+      "grad_norm": 0.4250960052013397,
+      "learning_rate": 0.00019910272841045518,
+      "loss": 0.8738601803779602,
+      "step": 1660
+    },
+    {
+      "epoch": 0.7171521035598706,
+      "grad_norm": 0.4896513819694519,
+      "learning_rate": 0.0001990961528913143,
+      "loss": 0.9578261971473694,
+      "step": 1662
+    },
+    {
+      "epoch": 0.7180151024811219,
+      "grad_norm": 0.4999626576900482,
+      "learning_rate": 0.00019908955347558291,
+      "loss": 0.8116445541381836,
+      "step": 1664
+    },
+    {
+      "epoch": 0.7188781014023733,
+      "grad_norm": 0.4335242807865143,
+      "learning_rate": 0.00019908293016485237,
+      "loss": 0.8783043622970581,
+      "step": 1666
+    },
+    {
+      "epoch": 0.7197411003236246,
+      "grad_norm": 0.43542763590812683,
+      "learning_rate": 0.00019907628296071992,
+      "loss": 0.8223029375076294,
+      "step": 1668
+    },
+    {
+      "epoch": 0.7206040992448759,
+      "grad_norm": 0.4907461702823639,
+      "learning_rate": 0.00019906961186478842,
+      "loss": 1.0053197145462036,
+      "step": 1670
+    },
+    {
+      "epoch": 0.7214670981661273,
+      "grad_norm": 0.4054848253726959,
+      "learning_rate": 0.00019906291687866667,
+      "loss": 0.8107786178588867,
+      "step": 1672
+    },
+    {
+      "epoch": 0.7223300970873786,
+      "grad_norm": 0.3818599283695221,
+      "learning_rate": 0.0001990561980039691,
+      "loss": 0.780781626701355,
+      "step": 1674
+    },
+    {
+      "epoch": 0.72319309600863,
+      "grad_norm": 0.4128594994544983,
+      "learning_rate": 0.00019904945524231587,
+      "loss": 0.8189221620559692,
+      "step": 1676
+    },
+    {
+      "epoch": 0.7240560949298813,
+      "grad_norm": 0.46902593970298767,
+      "learning_rate": 0.0001990426885953331,
+      "loss": 0.83652263879776,
+      "step": 1678
+    },
+    {
+      "epoch": 0.7249190938511327,
+      "grad_norm": 0.49305564165115356,
+      "learning_rate": 0.00019903589806465242,
+      "loss": 0.8057956695556641,
+      "step": 1680
+    },
+    {
+      "epoch": 0.725782092772384,
+      "grad_norm": 0.44408300518989563,
+      "learning_rate": 0.0001990290836519114,
+      "loss": 0.8523716926574707,
+      "step": 1682
+    },
+    {
+      "epoch": 0.7266450916936353,
+      "grad_norm": 0.5211108922958374,
+      "learning_rate": 0.00019902224535875326,
+      "loss": 0.9179236888885498,
+      "step": 1684
+    },
+    {
+      "epoch": 0.7275080906148867,
+      "grad_norm": 0.4736526608467102,
+      "learning_rate": 0.00019901538318682705,
+      "loss": 0.8229476809501648,
+      "step": 1686
+    },
+    {
+      "epoch": 0.728371089536138,
+      "grad_norm": 0.541716992855072,
+      "learning_rate": 0.00019900849713778756,
+      "loss": 0.924200713634491,
+      "step": 1688
+    },
+    {
+      "epoch": 0.7292340884573895,
+      "grad_norm": 0.4524400532245636,
+      "learning_rate": 0.00019900158721329532,
+      "loss": 0.88961261510849,
+      "step": 1690
+    },
+    {
+      "epoch": 0.7300970873786408,
+      "grad_norm": 0.45256128907203674,
+      "learning_rate": 0.00019899465341501662,
+      "loss": 0.8491015434265137,
+      "step": 1692
+    },
+    {
+      "epoch": 0.7309600862998922,
+      "grad_norm": 0.5346773266792297,
+      "learning_rate": 0.0001989876957446235,
+      "loss": 0.8833339810371399,
+      "step": 1694
+    },
+    {
+      "epoch": 0.7318230852211435,
+      "grad_norm": 0.4696357846260071,
+      "learning_rate": 0.0001989807142037938,
+      "loss": 0.8535294532775879,
+      "step": 1696
+    },
+    {
+      "epoch": 0.7326860841423948,
+      "grad_norm": 0.4304637908935547,
+      "learning_rate": 0.0001989737087942111,
+      "loss": 0.8273076415061951,
+      "step": 1698
+    },
+    {
+      "epoch": 0.7335490830636462,
+      "grad_norm": 0.5085629224777222,
+      "learning_rate": 0.00019896667951756466,
+      "loss": 0.8759240508079529,
+      "step": 1700
+    },
+    {
+      "epoch": 0.7335490830636462,
+      "eval_loss": 0.879119336605072,
+      "eval_runtime": 663.0553,
+      "eval_samples_per_second": 3.107,
+      "eval_steps_per_second": 3.107,
+      "step": 1700
+    },
+    {
+      "epoch": 0.7344120819848975,
+      "grad_norm": 0.484223872423172,
+      "learning_rate": 0.00019895962637554964,
+      "loss": 0.852645218372345,
+      "step": 1702
+    },
+    {
+      "epoch": 0.7352750809061489,
+      "grad_norm": 0.4819294214248657,
+      "learning_rate": 0.0001989525493698668,
+      "loss": 0.878247857093811,
+      "step": 1704
+    },
+    {
+      "epoch": 0.7361380798274002,
+      "grad_norm": 0.4170311689376831,
+      "learning_rate": 0.00019894544850222276,
+      "loss": 0.8964285254478455,
+      "step": 1706
+    },
+    {
+      "epoch": 0.7370010787486516,
+      "grad_norm": 0.42712801694869995,
+      "learning_rate": 0.0001989383237743299,
+      "loss": 0.7479548454284668,
+      "step": 1708
+    },
+    {
+      "epoch": 0.7378640776699029,
+      "grad_norm": 0.5051686763763428,
+      "learning_rate": 0.00019893117518790624,
+      "loss": 0.8190052509307861,
+      "step": 1710
+    },
+    {
+      "epoch": 0.7387270765911542,
+      "grad_norm": 0.44053253531455994,
+      "learning_rate": 0.0001989240027446757,
+      "loss": 0.8646742105484009,
+      "step": 1712
+    },
+    {
+      "epoch": 0.7395900755124056,
+      "grad_norm": 0.4451025724411011,
+      "learning_rate": 0.00019891680644636782,
+      "loss": 0.874261736869812,
+      "step": 1714
+    },
+    {
+      "epoch": 0.7404530744336569,
+      "grad_norm": 0.4590521454811096,
+      "learning_rate": 0.00019890958629471798,
+      "loss": 0.8892465233802795,
+      "step": 1716
+    },
+    {
+      "epoch": 0.7413160733549083,
+      "grad_norm": 0.39169448614120483,
+      "learning_rate": 0.00019890234229146732,
+      "loss": 0.7031586766242981,
+      "step": 1718
+    },
+    {
+      "epoch": 0.7421790722761596,
+      "grad_norm": 0.46946024894714355,
+      "learning_rate": 0.00019889507443836266,
+      "loss": 0.8548433184623718,
+      "step": 1720
+    },
+    {
+      "epoch": 0.7430420711974111,
+      "grad_norm": 0.42404699325561523,
+      "learning_rate": 0.0001988877827371566,
+      "loss": 0.8231223821640015,
+      "step": 1722
+    },
+    {
+      "epoch": 0.7439050701186624,
+      "grad_norm": 0.40419483184814453,
+      "learning_rate": 0.00019888046718960755,
+      "loss": 0.8443762063980103,
+      "step": 1724
+    },
+    {
+      "epoch": 0.7447680690399137,
+      "grad_norm": 0.4550437927246094,
+      "learning_rate": 0.0001988731277974796,
+      "loss": 0.8787111639976501,
+      "step": 1726
+    },
+    {
+      "epoch": 0.7456310679611651,
+      "grad_norm": 0.42264053225517273,
+      "learning_rate": 0.0001988657645625426,
+      "loss": 0.8440850377082825,
+      "step": 1728
+    },
+    {
+      "epoch": 0.7464940668824164,
+      "grad_norm": 0.4638359844684601,
+      "learning_rate": 0.0001988583774865721,
+      "loss": 0.839216947555542,
+      "step": 1730
+    },
+    {
+      "epoch": 0.7473570658036678,
+      "grad_norm": 0.42644429206848145,
+      "learning_rate": 0.0001988509665713496,
+      "loss": 0.8011161684989929,
+      "step": 1732
+    },
+    {
+      "epoch": 0.7482200647249191,
+      "grad_norm": 0.36932024359703064,
+      "learning_rate": 0.0001988435318186621,
+      "loss": 0.850246787071228,
+      "step": 1734
+    },
+    {
+      "epoch": 0.7490830636461704,
+      "grad_norm": 0.4771935045719147,
+      "learning_rate": 0.00019883607323030252,
+      "loss": 0.7782483100891113,
+      "step": 1736
+    },
+    {
+      "epoch": 0.7499460625674218,
+      "grad_norm": 0.40007370710372925,
+      "learning_rate": 0.00019882859080806942,
+      "loss": 0.8337594866752625,
+      "step": 1738
+    },
+    {
+      "epoch": 0.7508090614886731,
+      "grad_norm": 0.5007418394088745,
+      "learning_rate": 0.00019882108455376716,
+      "loss": 0.8287386894226074,
+      "step": 1740
+    },
+    {
+      "epoch": 0.7516720604099245,
+      "grad_norm": 0.43999138474464417,
+      "learning_rate": 0.00019881355446920584,
+      "loss": 0.8655616044998169,
+      "step": 1742
+    },
+    {
+      "epoch": 0.7525350593311758,
+      "grad_norm": 0.5115824937820435,
+      "learning_rate": 0.00019880600055620135,
+      "loss": 0.8695262670516968,
+      "step": 1744
+    },
+    {
+      "epoch": 0.7533980582524272,
+      "grad_norm": 0.5035707950592041,
+      "learning_rate": 0.0001987984228165752,
+      "loss": 0.9207013845443726,
+      "step": 1746
+    },
+    {
+      "epoch": 0.7542610571736785,
+      "grad_norm": 0.4689575731754303,
+      "learning_rate": 0.0001987908212521548,
+      "loss": 0.8798729777336121,
+      "step": 1748
+    },
+    {
+      "epoch": 0.7551240560949298,
+      "grad_norm": 0.4730616509914398,
+      "learning_rate": 0.00019878319586477322,
+      "loss": 0.7737767696380615,
+      "step": 1750
+    },
+    {
+      "epoch": 0.7559870550161812,
+      "grad_norm": 0.49012845754623413,
+      "learning_rate": 0.00019877554665626926,
+      "loss": 0.929466187953949,
+      "step": 1752
+    },
+    {
+      "epoch": 0.7568500539374325,
+      "grad_norm": 0.43468761444091797,
+      "learning_rate": 0.0001987678736284875,
+      "loss": 0.8155670166015625,
+      "step": 1754
+    },
+    {
+      "epoch": 0.757713052858684,
+      "grad_norm": 0.507399320602417,
+      "learning_rate": 0.00019876017678327826,
+      "loss": 0.8082395195960999,
+      "step": 1756
+    },
+    {
+      "epoch": 0.7585760517799353,
+      "grad_norm": 0.4733552634716034,
+      "learning_rate": 0.0001987524561224976,
+      "loss": 0.8905934691429138,
+      "step": 1758
+    },
+    {
+      "epoch": 0.7594390507011867,
+      "grad_norm": 0.4670012891292572,
+      "learning_rate": 0.00019874471164800733,
+      "loss": 0.8794633746147156,
+      "step": 1760
+    },
+    {
+      "epoch": 0.760302049622438,
+      "grad_norm": 0.4951624572277069,
+      "learning_rate": 0.000198736943361675,
+      "loss": 0.8413973450660706,
+      "step": 1762
+    },
+    {
+      "epoch": 0.7611650485436893,
+      "grad_norm": 0.5478648543357849,
+      "learning_rate": 0.00019872915126537387,
+      "loss": 0.9067897200584412,
+      "step": 1764
+    },
+    {
+      "epoch": 0.7620280474649407,
+      "grad_norm": 0.48215776681900024,
+      "learning_rate": 0.000198721335360983,
+      "loss": 0.8932394981384277,
+      "step": 1766
+    },
+    {
+      "epoch": 0.762891046386192,
+      "grad_norm": 0.4688864052295685,
+      "learning_rate": 0.00019871349565038715,
+      "loss": 0.8496726751327515,
+      "step": 1768
+    },
+    {
+      "epoch": 0.7637540453074434,
+      "grad_norm": 0.4728260636329651,
+      "learning_rate": 0.0001987056321354768,
+      "loss": 0.9232800602912903,
+      "step": 1770
+    },
+    {
+      "epoch": 0.7646170442286947,
+      "grad_norm": 0.44501692056655884,
+      "learning_rate": 0.00019869774481814828,
+      "loss": 0.849755585193634,
+      "step": 1772
+    },
+    {
+      "epoch": 0.7654800431499461,
+      "grad_norm": 0.4189201593399048,
+      "learning_rate": 0.00019868983370030348,
+      "loss": 0.8258485794067383,
+      "step": 1774
+    },
+    {
+      "epoch": 0.7663430420711974,
+      "grad_norm": 0.5144591927528381,
+      "learning_rate": 0.00019868189878385016,
+      "loss": 0.8762873411178589,
+      "step": 1776
+    },
+    {
+      "epoch": 0.7672060409924487,
+      "grad_norm": 0.5048011541366577,
+      "learning_rate": 0.00019867394007070188,
+      "loss": 0.8732464909553528,
+      "step": 1778
+    },
+    {
+      "epoch": 0.7680690399137001,
+      "grad_norm": 0.41639819741249084,
+      "learning_rate": 0.00019866595756277774,
+      "loss": 0.8732751607894897,
+      "step": 1780
+    },
+    {
+      "epoch": 0.7689320388349514,
+      "grad_norm": 0.526757538318634,
+      "learning_rate": 0.00019865795126200271,
+      "loss": 0.8453729748725891,
+      "step": 1782
+    },
+    {
+      "epoch": 0.7697950377562028,
+      "grad_norm": 0.47041091322898865,
+      "learning_rate": 0.0001986499211703075,
+      "loss": 0.8780192732810974,
+      "step": 1784
+    },
+    {
+      "epoch": 0.7706580366774541,
+      "grad_norm": 0.4535890221595764,
+      "learning_rate": 0.0001986418672896285,
+      "loss": 0.8508450388908386,
+      "step": 1786
+    },
+    {
+      "epoch": 0.7715210355987056,
+      "grad_norm": 0.4608050286769867,
+      "learning_rate": 0.00019863378962190788,
+      "loss": 0.822467565536499,
+      "step": 1788
+    },
+    {
+      "epoch": 0.7723840345199569,
+      "grad_norm": 0.5190523862838745,
+      "learning_rate": 0.00019862568816909356,
+      "loss": 0.844614565372467,
+      "step": 1790
+    },
+    {
+      "epoch": 0.7732470334412082,
+      "grad_norm": 0.42502254247665405,
+      "learning_rate": 0.00019861756293313912,
+      "loss": 0.8144394755363464,
+      "step": 1792
+    },
+    {
+      "epoch": 0.7741100323624596,
+      "grad_norm": 0.47112616896629333,
+      "learning_rate": 0.000198609413916004,
+      "loss": 0.8836341500282288,
+      "step": 1794
+    },
+    {
+      "epoch": 0.7749730312837109,
+      "grad_norm": 0.48414838314056396,
+      "learning_rate": 0.0001986012411196532,
+      "loss": 0.8846262693405151,
+      "step": 1796
+    },
+    {
+      "epoch": 0.7758360302049623,
+      "grad_norm": 0.4670039415359497,
+      "learning_rate": 0.00019859304454605763,
+      "loss": 0.7993118762969971,
+      "step": 1798
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "grad_norm": 0.41939061880111694,
+      "learning_rate": 0.0001985848241971938,
+      "loss": 0.8389407396316528,
+      "step": 1800
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "eval_loss": 0.8727664947509766,
+      "eval_runtime": 668.2062,
+      "eval_samples_per_second": 3.083,
+      "eval_steps_per_second": 3.083,
+      "step": 1800
+    },
+    {
+      "epoch": 0.777562028047465,
+      "grad_norm": 0.4566517174243927,
+      "learning_rate": 0.00019857658007504405,
+      "loss": 0.8824291825294495,
+      "step": 1802
+    },
+    {
+      "epoch": 0.7784250269687163,
+      "grad_norm": 0.4798925518989563,
+      "learning_rate": 0.0001985683121815964,
+      "loss": 0.808982789516449,
+      "step": 1804
+    },
+    {
+      "epoch": 0.7792880258899676,
+      "grad_norm": 0.4659746587276459,
+      "learning_rate": 0.00019856002051884462,
+      "loss": 0.955269992351532,
+      "step": 1806
+    },
+    {
+      "epoch": 0.780151024811219,
+      "grad_norm": 0.48573991656303406,
+      "learning_rate": 0.00019855170508878818,
+      "loss": 0.8142994046211243,
+      "step": 1808
+    },
+    {
+      "epoch": 0.7810140237324703,
+      "grad_norm": 0.4700213670730591,
+      "learning_rate": 0.00019854336589343236,
+      "loss": 0.8755695819854736,
+      "step": 1810
+    },
+    {
+      "epoch": 0.7818770226537217,
+      "grad_norm": 0.42113450169563293,
+      "learning_rate": 0.00019853500293478806,
+      "loss": 0.8098483681678772,
+      "step": 1812
+    },
+    {
+      "epoch": 0.782740021574973,
+      "grad_norm": 0.4218153655529022,
+      "learning_rate": 0.00019852661621487205,
+      "loss": 0.8219783306121826,
+      "step": 1814
+    },
+    {
+      "epoch": 0.7836030204962244,
+      "grad_norm": 0.499052494764328,
+      "learning_rate": 0.00019851820573570664,
+      "loss": 0.8314159512519836,
+      "step": 1816
+    },
+    {
+      "epoch": 0.7844660194174757,
+      "grad_norm": 0.42420193552970886,
+      "learning_rate": 0.00019850977149932008,
+      "loss": 0.7985323071479797,
+      "step": 1818
+    },
+    {
+      "epoch": 0.785329018338727,
+      "grad_norm": 0.46345841884613037,
+      "learning_rate": 0.0001985013135077462,
+      "loss": 0.8528217077255249,
+      "step": 1820
+    },
+    {
+      "epoch": 0.7861920172599784,
+      "grad_norm": 0.4433307945728302,
+      "learning_rate": 0.00019849283176302462,
+      "loss": 0.8659319877624512,
+      "step": 1822
+    },
+    {
+      "epoch": 0.7870550161812297,
+      "grad_norm": 0.48279091715812683,
+      "learning_rate": 0.00019848432626720067,
+      "loss": 0.8675655126571655,
+      "step": 1824
+    },
+    {
+      "epoch": 0.7879180151024812,
+      "grad_norm": 0.5439180731773376,
+      "learning_rate": 0.0001984757970223254,
+      "loss": 0.8550227284431458,
+      "step": 1826
+    },
+    {
+      "epoch": 0.7887810140237325,
+      "grad_norm": 0.45749521255493164,
+      "learning_rate": 0.0001984672440304556,
+      "loss": 0.7290607690811157,
+      "step": 1828
+    },
+    {
+      "epoch": 0.7896440129449838,
+      "grad_norm": 0.4654783606529236,
+      "learning_rate": 0.00019845866729365378,
+      "loss": 0.8619251251220703,
+      "step": 1830
+    },
+    {
+      "epoch": 0.7905070118662352,
+      "grad_norm": 0.42632243037223816,
+      "learning_rate": 0.00019845006681398823,
+      "loss": 0.8249601125717163,
+      "step": 1832
+    },
+    {
+      "epoch": 0.7913700107874865,
+      "grad_norm": 0.4747186005115509,
+      "learning_rate": 0.0001984414425935329,
+      "loss": 0.7138552069664001,
+      "step": 1834
+    },
+    {
+      "epoch": 0.7922330097087379,
+      "grad_norm": 0.4462338387966156,
+      "learning_rate": 0.0001984327946343674,
+      "loss": 0.903292715549469,
+      "step": 1836
+    },
+    {
+      "epoch": 0.7930960086299892,
+      "grad_norm": 0.4581359922885895,
+      "learning_rate": 0.00019842412293857726,
+      "loss": 0.7569618225097656,
+      "step": 1838
+    },
+    {
+      "epoch": 0.7939590075512406,
+      "grad_norm": 0.4183015525341034,
+      "learning_rate": 0.00019841542750825356,
+      "loss": 0.8063036203384399,
+      "step": 1840
+    },
+    {
+      "epoch": 0.7948220064724919,
+      "grad_norm": 0.3954181373119354,
+      "learning_rate": 0.0001984067083454932,
+      "loss": 0.81150221824646,
+      "step": 1842
+    },
+    {
+      "epoch": 0.7956850053937432,
+      "grad_norm": 0.46220019459724426,
+      "learning_rate": 0.0001983979654523987,
+      "loss": 0.841649055480957,
+      "step": 1844
+    },
+    {
+      "epoch": 0.7965480043149946,
+      "grad_norm": 0.47807541489601135,
+      "learning_rate": 0.00019838919883107843,
+      "loss": 0.8019483685493469,
+      "step": 1846
+    },
+    {
+      "epoch": 0.7974110032362459,
+      "grad_norm": 0.48015692830085754,
+      "learning_rate": 0.0001983804084836464,
+      "loss": 0.9343363046646118,
+      "step": 1848
+    },
+    {
+      "epoch": 0.7982740021574973,
+      "grad_norm": 0.4906708896160126,
+      "learning_rate": 0.00019837159441222238,
+      "loss": 0.9163194894790649,
+      "step": 1850
+    },
+    {
+      "epoch": 0.7991370010787486,
+      "grad_norm": 0.4856911599636078,
+      "learning_rate": 0.0001983627566189318,
+      "loss": 0.8017736077308655,
+      "step": 1852
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.49403145909309387,
+      "learning_rate": 0.0001983538951059059,
+      "loss": 0.8375223875045776,
+      "step": 1854
+    },
+    {
+      "epoch": 0.8008629989212513,
+      "grad_norm": 0.4237985908985138,
+      "learning_rate": 0.00019834500987528158,
+      "loss": 0.8213951587677002,
+      "step": 1856
+    },
+    {
+      "epoch": 0.8017259978425026,
+      "grad_norm": 0.3977980315685272,
+      "learning_rate": 0.00019833610092920149,
+      "loss": 0.8086028099060059,
+      "step": 1858
+    },
+    {
+      "epoch": 0.8025889967637541,
+      "grad_norm": 0.435253381729126,
+      "learning_rate": 0.00019832716826981392,
+      "loss": 0.9402202367782593,
+      "step": 1860
+    },
+    {
+      "epoch": 0.8034519956850054,
+      "grad_norm": 0.4074764847755432,
+      "learning_rate": 0.000198318211899273,
+      "loss": 0.7730796933174133,
+      "step": 1862
+    },
+    {
+      "epoch": 0.8043149946062568,
+      "grad_norm": 0.48804348707199097,
+      "learning_rate": 0.0001983092318197385,
+      "loss": 0.9185802936553955,
+      "step": 1864
+    },
+    {
+      "epoch": 0.8051779935275081,
+      "grad_norm": 0.44363343715667725,
+      "learning_rate": 0.00019830022803337592,
+      "loss": 0.8578243851661682,
+      "step": 1866
+    },
+    {
+      "epoch": 0.8060409924487595,
+      "grad_norm": 0.46645957231521606,
+      "learning_rate": 0.00019829120054235653,
+      "loss": 0.8682060241699219,
+      "step": 1868
+    },
+    {
+      "epoch": 0.8069039913700108,
+      "grad_norm": 0.4527221620082855,
+      "learning_rate": 0.00019828214934885718,
+      "loss": 0.7845040559768677,
+      "step": 1870
+    },
+    {
+      "epoch": 0.8077669902912621,
+      "grad_norm": 0.4103536307811737,
+      "learning_rate": 0.0001982730744550606,
+      "loss": 0.8768247961997986,
+      "step": 1872
+    },
+    {
+      "epoch": 0.8086299892125135,
+      "grad_norm": 0.5257515907287598,
+      "learning_rate": 0.00019826397586315513,
+      "loss": 0.850267231464386,
+      "step": 1874
+    },
+    {
+      "epoch": 0.8094929881337648,
+      "grad_norm": 0.46675893664360046,
+      "learning_rate": 0.00019825485357533485,
+      "loss": 0.8234293460845947,
+      "step": 1876
+    },
+    {
+      "epoch": 0.8103559870550162,
+      "grad_norm": 0.46315401792526245,
+      "learning_rate": 0.00019824570759379958,
+      "loss": 0.8131387829780579,
+      "step": 1878
+    },
+    {
+      "epoch": 0.8112189859762675,
+      "grad_norm": 0.4766870439052582,
+      "learning_rate": 0.00019823653792075478,
+      "loss": 0.7680494785308838,
+      "step": 1880
+    },
+    {
+      "epoch": 0.8120819848975189,
+      "grad_norm": 0.39025625586509705,
+      "learning_rate": 0.00019822734455841173,
+      "loss": 0.7891425490379333,
+      "step": 1882
+    },
+    {
+      "epoch": 0.8129449838187702,
+      "grad_norm": 0.4672441780567169,
+      "learning_rate": 0.0001982181275089874,
+      "loss": 0.7990400791168213,
+      "step": 1884
+    },
+    {
+      "epoch": 0.8138079827400215,
+      "grad_norm": 0.44310975074768066,
+      "learning_rate": 0.00019820888677470432,
+      "loss": 0.7828341722488403,
+      "step": 1886
+    },
+    {
+      "epoch": 0.8146709816612729,
+      "grad_norm": 0.45098716020584106,
+      "learning_rate": 0.00019819962235779096,
+      "loss": 0.897715151309967,
+      "step": 1888
+    },
+    {
+      "epoch": 0.8155339805825242,
+      "grad_norm": 0.466805100440979,
+      "learning_rate": 0.00019819033426048135,
+      "loss": 0.7987668514251709,
+      "step": 1890
+    },
+    {
+      "epoch": 0.8163969795037757,
+      "grad_norm": 0.4438319206237793,
+      "learning_rate": 0.00019818102248501528,
+      "loss": 0.7950236201286316,
+      "step": 1892
+    },
+    {
+      "epoch": 0.817259978425027,
+      "grad_norm": 0.42012497782707214,
+      "learning_rate": 0.00019817168703363823,
+      "loss": 0.8789975643157959,
+      "step": 1894
+    },
+    {
+      "epoch": 0.8181229773462784,
+      "grad_norm": 0.4359394311904907,
+      "learning_rate": 0.0001981623279086014,
+      "loss": 0.8159777522087097,
+      "step": 1896
+    },
+    {
+      "epoch": 0.8189859762675297,
+      "grad_norm": 0.44709593057632446,
+      "learning_rate": 0.00019815294511216173,
+      "loss": 0.84877610206604,
+      "step": 1898
+    },
+    {
+      "epoch": 0.819848975188781,
+      "grad_norm": 0.4315306544303894,
+      "learning_rate": 0.00019814353864658184,
+      "loss": 0.8467556834220886,
+      "step": 1900
+    },
+    {
+      "epoch": 0.819848975188781,
+      "eval_loss": 0.8643407821655273,
+      "eval_runtime": 658.6942,
+      "eval_samples_per_second": 3.127,
+      "eval_steps_per_second": 3.127,
+      "step": 1900
+    },
+    {
+      "epoch": 0.8207119741100324,
+      "grad_norm": 0.35530397295951843,
+      "learning_rate": 0.00019813410851412998,
+      "loss": 0.7398589849472046,
+      "step": 1902
+    },
+    {
+      "epoch": 0.8215749730312837,
+      "grad_norm": 0.46949300169944763,
+      "learning_rate": 0.00019812465471708032,
+      "loss": 0.8544237613677979,
+      "step": 1904
+    },
+    {
+      "epoch": 0.8224379719525351,
+      "grad_norm": 0.4961565434932709,
+      "learning_rate": 0.00019811517725771248,
+      "loss": 0.8242526054382324,
+      "step": 1906
+    },
+    {
+      "epoch": 0.8233009708737864,
+      "grad_norm": 0.45835059881210327,
+      "learning_rate": 0.00019810567613831194,
+      "loss": 0.7856690287590027,
+      "step": 1908
+    },
+    {
+      "epoch": 0.8241639697950378,
+      "grad_norm": 0.4446084797382355,
+      "learning_rate": 0.0001980961513611699,
+      "loss": 0.8361829519271851,
+      "step": 1910
+    },
+    {
+      "epoch": 0.8250269687162891,
+      "grad_norm": 0.4470907747745514,
+      "learning_rate": 0.00019808660292858313,
+      "loss": 0.8993050456047058,
+      "step": 1912
+    },
+    {
+      "epoch": 0.8258899676375404,
+      "grad_norm": 0.44883644580841064,
+      "learning_rate": 0.0001980770308428543,
+      "loss": 0.8702824711799622,
+      "step": 1914
+    },
+    {
+      "epoch": 0.8267529665587918,
+      "grad_norm": 0.43215686082839966,
+      "learning_rate": 0.00019806743510629159,
+      "loss": 0.8454389572143555,
+      "step": 1916
+    },
+    {
+      "epoch": 0.8276159654800431,
+      "grad_norm": 0.4525185823440552,
+      "learning_rate": 0.00019805781572120897,
+      "loss": 0.8621824383735657,
+      "step": 1918
+    },
+    {
+      "epoch": 0.8284789644012945,
+      "grad_norm": 0.4616840183734894,
+      "learning_rate": 0.00019804817268992615,
+      "loss": 0.8661681413650513,
+      "step": 1920
+    },
+    {
+      "epoch": 0.8293419633225458,
+      "grad_norm": 0.4252975583076477,
+      "learning_rate": 0.0001980385060147685,
+      "loss": 0.8376660346984863,
+      "step": 1922
+    },
+    {
+      "epoch": 0.8302049622437971,
+      "grad_norm": 0.44600266218185425,
+      "learning_rate": 0.00019802881569806706,
+      "loss": 0.9258401393890381,
+      "step": 1924
+    },
+    {
+      "epoch": 0.8310679611650486,
+      "grad_norm": 0.48872479796409607,
+      "learning_rate": 0.00019801910174215866,
+      "loss": 0.8804965615272522,
+      "step": 1926
+    },
+    {
+      "epoch": 0.8319309600862999,
+      "grad_norm": 0.5357037782669067,
+      "learning_rate": 0.00019800936414938574,
+      "loss": 0.8561494946479797,
+      "step": 1928
+    },
+    {
+      "epoch": 0.8327939590075513,
+      "grad_norm": 0.39637291431427,
+      "learning_rate": 0.00019799960292209647,
+      "loss": 0.782166063785553,
+      "step": 1930
+    },
+    {
+      "epoch": 0.8336569579288026,
+      "grad_norm": 0.521138072013855,
+      "learning_rate": 0.00019798981806264476,
+      "loss": 0.9048293232917786,
+      "step": 1932
+    },
+    {
+      "epoch": 0.834519956850054,
+      "grad_norm": 0.4723529815673828,
+      "learning_rate": 0.00019798000957339015,
+      "loss": 0.9269952774047852,
+      "step": 1934
+    },
+    {
+      "epoch": 0.8353829557713053,
+      "grad_norm": 0.42827340960502625,
+      "learning_rate": 0.0001979701774566979,
+      "loss": 0.8620670437812805,
+      "step": 1936
+    },
+    {
+      "epoch": 0.8362459546925566,
+      "grad_norm": 0.4305116534233093,
+      "learning_rate": 0.00019796032171493907,
+      "loss": 0.8016669750213623,
+      "step": 1938
+    },
+    {
+      "epoch": 0.837108953613808,
+      "grad_norm": 0.4995502233505249,
+      "learning_rate": 0.00019795044235049024,
+      "loss": 0.879247784614563,
+      "step": 1940
+    },
+    {
+      "epoch": 0.8379719525350593,
+      "grad_norm": 0.49229878187179565,
+      "learning_rate": 0.0001979405393657338,
+      "loss": 0.9476580023765564,
+      "step": 1942
+    },
+    {
+      "epoch": 0.8388349514563107,
+      "grad_norm": 0.45756596326828003,
+      "learning_rate": 0.0001979306127630578,
+      "loss": 0.8654064536094666,
+      "step": 1944
+    },
+    {
+      "epoch": 0.839697950377562,
+      "grad_norm": 0.4855344891548157,
+      "learning_rate": 0.00019792066254485603,
+      "loss": 0.7792956829071045,
+      "step": 1946
+    },
+    {
+      "epoch": 0.8405609492988134,
+      "grad_norm": 0.4358632266521454,
+      "learning_rate": 0.00019791068871352787,
+      "loss": 0.8000320792198181,
+      "step": 1948
+    },
+    {
+      "epoch": 0.8414239482200647,
+      "grad_norm": 0.4225342273712158,
+      "learning_rate": 0.00019790069127147852,
+      "loss": 0.818372368812561,
+      "step": 1950
+    },
+    {
+      "epoch": 0.842286947141316,
+      "grad_norm": 0.3894529938697815,
+      "learning_rate": 0.00019789067022111886,
+      "loss": 0.727220892906189,
+      "step": 1952
+    },
+    {
+      "epoch": 0.8431499460625674,
+      "grad_norm": 0.5060731768608093,
+      "learning_rate": 0.0001978806255648653,
+      "loss": 0.894101083278656,
+      "step": 1954
+    },
+    {
+      "epoch": 0.8440129449838187,
+      "grad_norm": 0.4165003001689911,
+      "learning_rate": 0.0001978705573051402,
+      "loss": 0.878365695476532,
+      "step": 1956
+    },
+    {
+      "epoch": 0.8448759439050701,
+      "grad_norm": 0.48767927289009094,
+      "learning_rate": 0.0001978604654443714,
+      "loss": 0.8390909433364868,
+      "step": 1958
+    },
+    {
+      "epoch": 0.8457389428263214,
+      "grad_norm": 0.43019410967826843,
+      "learning_rate": 0.00019785034998499247,
+      "loss": 0.8807769417762756,
+      "step": 1960
+    },
+    {
+      "epoch": 0.8466019417475729,
+      "grad_norm": 0.4430403709411621,
+      "learning_rate": 0.0001978402109294428,
+      "loss": 0.8037779331207275,
+      "step": 1962
+    },
+    {
+      "epoch": 0.8474649406688242,
+      "grad_norm": 0.41642463207244873,
+      "learning_rate": 0.0001978300482801673,
+      "loss": 0.8341337442398071,
+      "step": 1964
+    },
+    {
+      "epoch": 0.8483279395900755,
+      "grad_norm": 0.45358774065971375,
+      "learning_rate": 0.00019781986203961668,
+      "loss": 0.854821503162384,
+      "step": 1966
+    },
+    {
+      "epoch": 0.8491909385113269,
+      "grad_norm": 0.4316342771053314,
+      "learning_rate": 0.00019780965221024728,
+      "loss": 0.8527678847312927,
+      "step": 1968
+    },
+    {
+      "epoch": 0.8500539374325782,
+      "grad_norm": 0.4581106901168823,
+      "learning_rate": 0.00019779941879452122,
+      "loss": 0.7461717128753662,
+      "step": 1970
+    },
+    {
+      "epoch": 0.8509169363538296,
+      "grad_norm": 0.49578142166137695,
+      "learning_rate": 0.0001977891617949062,
+      "loss": 0.884441077709198,
+      "step": 1972
+    },
+    {
+      "epoch": 0.8517799352750809,
+      "grad_norm": 0.4366011917591095,
+      "learning_rate": 0.00019777888121387562,
+      "loss": 0.855915904045105,
+      "step": 1974
+    },
+    {
+      "epoch": 0.8526429341963323,
+      "grad_norm": 0.486162930727005,
+      "learning_rate": 0.00019776857705390864,
+      "loss": 0.7563765645027161,
+      "step": 1976
+    },
+    {
+      "epoch": 0.8535059331175836,
+      "grad_norm": 0.5162674784660339,
+      "learning_rate": 0.00019775824931749005,
+      "loss": 0.8346326947212219,
+      "step": 1978
+    },
+    {
+      "epoch": 0.8543689320388349,
+      "grad_norm": 0.5824693441390991,
+      "learning_rate": 0.0001977478980071103,
+      "loss": 0.8701820969581604,
+      "step": 1980
+    },
+    {
+      "epoch": 0.8552319309600863,
+      "grad_norm": 0.4297148883342743,
+      "learning_rate": 0.00019773752312526565,
+      "loss": 0.893528938293457,
+      "step": 1982
+    },
+    {
+      "epoch": 0.8560949298813376,
+      "grad_norm": 0.42978280782699585,
+      "learning_rate": 0.00019772712467445788,
+      "loss": 0.8201018571853638,
+      "step": 1984
+    },
+    {
+      "epoch": 0.856957928802589,
+      "grad_norm": 0.5192655324935913,
+      "learning_rate": 0.00019771670265719454,
+      "loss": 0.9080212116241455,
+      "step": 1986
+    },
+    {
+      "epoch": 0.8578209277238403,
+      "grad_norm": 0.452690452337265,
+      "learning_rate": 0.00019770625707598885,
+      "loss": 0.8518272638320923,
+      "step": 1988
+    },
+    {
+      "epoch": 0.8586839266450917,
+      "grad_norm": 0.4371768832206726,
+      "learning_rate": 0.00019769578793335976,
+      "loss": 0.9426717758178711,
+      "step": 1990
+    },
+    {
+      "epoch": 0.859546925566343,
+      "grad_norm": 0.44595038890838623,
+      "learning_rate": 0.0001976852952318318,
+      "loss": 0.8065400123596191,
+      "step": 1992
+    },
+    {
+      "epoch": 0.8604099244875943,
+      "grad_norm": 0.4355090260505676,
+      "learning_rate": 0.0001976747789739353,
+      "loss": 0.7674415707588196,
+      "step": 1994
+    },
+    {
+      "epoch": 0.8612729234088458,
+      "grad_norm": 0.43745186924934387,
+      "learning_rate": 0.00019766423916220616,
+      "loss": 0.813849925994873,
+      "step": 1996
+    },
+    {
+      "epoch": 0.8621359223300971,
+      "grad_norm": 0.4588927924633026,
+      "learning_rate": 0.00019765367579918598,
+      "loss": 0.7870585322380066,
+      "step": 1998
+    },
+    {
+      "epoch": 0.8629989212513485,
+      "grad_norm": 0.4170977473258972,
+      "learning_rate": 0.00019764308888742214,
+      "loss": 0.8383269309997559,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8629989212513485,
+      "eval_loss": 0.8567262887954712,
+      "eval_runtime": 646.6443,
+      "eval_samples_per_second": 3.186,
+      "eval_steps_per_second": 3.186,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8638619201725998,
+      "grad_norm": 0.4819261431694031,
+      "learning_rate": 0.0001976324784294676,
+      "loss": 0.8261714577674866,
+      "step": 2002
+    },
+    {
+      "epoch": 0.8647249190938512,
+      "grad_norm": 0.4215400218963623,
+      "learning_rate": 0.00019762184442788098,
+      "loss": 0.8493392467498779,
+      "step": 2004
+    },
+    {
+      "epoch": 0.8655879180151025,
+      "grad_norm": 0.45448991656303406,
+      "learning_rate": 0.00019761118688522668,
+      "loss": 0.8645208477973938,
+      "step": 2006
+    },
+    {
+      "epoch": 0.8664509169363538,
+      "grad_norm": 0.4436458349227905,
+      "learning_rate": 0.0001976005058040747,
+      "loss": 0.8816449046134949,
+      "step": 2008
+    },
+    {
+      "epoch": 0.8673139158576052,
+      "grad_norm": 0.42662230134010315,
+      "learning_rate": 0.00019758980118700072,
+      "loss": 0.7622330784797668,
+      "step": 2010
+    },
+    {
+      "epoch": 0.8681769147788565,
+      "grad_norm": 0.3936038613319397,
+      "learning_rate": 0.0001975790730365861,
+      "loss": 0.7843833565711975,
+      "step": 2012
+    },
+    {
+      "epoch": 0.8690399137001079,
+      "grad_norm": 0.4460368752479553,
+      "learning_rate": 0.00019756832135541796,
+      "loss": 0.8294675946235657,
+      "step": 2014
+    },
+    {
+      "epoch": 0.8699029126213592,
+      "grad_norm": 0.47043702006340027,
+      "learning_rate": 0.00019755754614608892,
+      "loss": 0.851332426071167,
+      "step": 2016
+    },
+    {
+      "epoch": 0.8707659115426106,
+      "grad_norm": 0.4579448401927948,
+      "learning_rate": 0.00019754674741119746,
+      "loss": 0.8450362682342529,
+      "step": 2018
+    },
+    {
+      "epoch": 0.8716289104638619,
+      "grad_norm": 0.44362813234329224,
+      "learning_rate": 0.00019753592515334758,
+      "loss": 0.8585519194602966,
+      "step": 2020
+    },
+    {
+      "epoch": 0.8724919093851132,
+      "grad_norm": 0.4500923156738281,
+      "learning_rate": 0.00019752507937514905,
+      "loss": 0.8300179243087769,
+      "step": 2022
+    },
+    {
+      "epoch": 0.8733549083063646,
+      "grad_norm": 0.4330301582813263,
+      "learning_rate": 0.00019751421007921724,
+      "loss": 0.805014431476593,
+      "step": 2024
+    },
+    {
+      "epoch": 0.8742179072276159,
+      "grad_norm": 0.43873998522758484,
+      "learning_rate": 0.00019750331726817332,
+      "loss": 0.8228020071983337,
+      "step": 2026
+    },
+    {
+      "epoch": 0.8750809061488674,
+      "grad_norm": 0.47558829188346863,
+      "learning_rate": 0.00019749240094464395,
+      "loss": 0.8490906357765198,
+      "step": 2028
+    },
+    {
+      "epoch": 0.8759439050701187,
+      "grad_norm": 0.4285199046134949,
+      "learning_rate": 0.0001974814611112616,
+      "loss": 0.816324770450592,
+      "step": 2030
+    },
+    {
+      "epoch": 0.87680690399137,
+      "grad_norm": 0.4762725532054901,
+      "learning_rate": 0.0001974704977706644,
+      "loss": 0.9229121208190918,
+      "step": 2032
+    },
+    {
+      "epoch": 0.8776699029126214,
+      "grad_norm": 0.49856793880462646,
+      "learning_rate": 0.00019745951092549598,
+      "loss": 0.9847140908241272,
+      "step": 2034
+    },
+    {
+      "epoch": 0.8785329018338727,
+      "grad_norm": 0.5163881182670593,
+      "learning_rate": 0.00019744850057840587,
+      "loss": 0.8305321335792542,
+      "step": 2036
+    },
+    {
+      "epoch": 0.8793959007551241,
+      "grad_norm": 0.47826042771339417,
+      "learning_rate": 0.00019743746673204918,
+      "loss": 0.7909449934959412,
+      "step": 2038
+    },
+    {
+      "epoch": 0.8802588996763754,
+      "grad_norm": 0.44080349802970886,
+      "learning_rate": 0.0001974264093890866,
+      "loss": 0.809201180934906,
+      "step": 2040
+    },
+    {
+      "epoch": 0.8811218985976268,
+      "grad_norm": 0.46925660967826843,
+      "learning_rate": 0.00019741532855218464,
+      "loss": 0.8064218163490295,
+      "step": 2042
+    },
+    {
+      "epoch": 0.8819848975188781,
+      "grad_norm": 0.4223597049713135,
+      "learning_rate": 0.00019740422422401531,
+      "loss": 0.8135121464729309,
+      "step": 2044
+    },
+    {
+      "epoch": 0.8828478964401294,
+      "grad_norm": 0.46334266662597656,
+      "learning_rate": 0.00019739309640725642,
+      "loss": 0.8047984838485718,
+      "step": 2046
+    },
+    {
+      "epoch": 0.8837108953613808,
+      "grad_norm": 0.413682222366333,
+      "learning_rate": 0.0001973819451045914,
+      "loss": 0.7897430658340454,
+      "step": 2048
+    },
+    {
+      "epoch": 0.8845738942826321,
+      "grad_norm": 0.4276670515537262,
+      "learning_rate": 0.0001973707703187093,
+      "loss": 0.8411629796028137,
+      "step": 2050
+    },
+    {
+      "epoch": 0.8854368932038835,
+      "grad_norm": 0.4199331998825073,
+      "learning_rate": 0.0001973595720523049,
+      "loss": 0.7906913161277771,
+      "step": 2052
+    },
+    {
+      "epoch": 0.8862998921251348,
+      "grad_norm": 0.43233853578567505,
+      "learning_rate": 0.0001973483503080786,
+      "loss": 0.9042854309082031,
+      "step": 2054
+    },
+    {
+      "epoch": 0.8871628910463862,
+      "grad_norm": 0.41147297620773315,
+      "learning_rate": 0.00019733710508873647,
+      "loss": 0.8177635073661804,
+      "step": 2056
+    },
+    {
+      "epoch": 0.8880258899676375,
+      "grad_norm": 0.45957690477371216,
+      "learning_rate": 0.00019732583639699023,
+      "loss": 0.8867166042327881,
+      "step": 2058
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.3979831635951996,
+      "learning_rate": 0.00019731454423555728,
+      "loss": 0.7208530902862549,
+      "step": 2060
+    },
+    {
+      "epoch": 0.8897518878101403,
+      "grad_norm": 0.4434017837047577,
+      "learning_rate": 0.00019730322860716073,
+      "loss": 0.9158181548118591,
+      "step": 2062
+    },
+    {
+      "epoch": 0.8906148867313916,
+      "grad_norm": 0.40012025833129883,
+      "learning_rate": 0.00019729188951452922,
+      "loss": 0.8103255033493042,
+      "step": 2064
+    },
+    {
+      "epoch": 0.891477885652643,
+      "grad_norm": 0.41914620995521545,
+      "learning_rate": 0.00019728052696039715,
+      "loss": 0.7780100703239441,
+      "step": 2066
+    },
+    {
+      "epoch": 0.8923408845738943,
+      "grad_norm": 0.48365312814712524,
+      "learning_rate": 0.00019726914094750453,
+      "loss": 0.7105780839920044,
+      "step": 2068
+    },
+    {
+      "epoch": 0.8932038834951457,
+      "grad_norm": 0.4272058308124542,
+      "learning_rate": 0.0001972577314785971,
+      "loss": 0.7529635429382324,
+      "step": 2070
+    },
+    {
+      "epoch": 0.894066882416397,
+      "grad_norm": 0.48760271072387695,
+      "learning_rate": 0.00019724629855642612,
+      "loss": 0.836787223815918,
+      "step": 2072
+    },
+    {
+      "epoch": 0.8949298813376483,
+      "grad_norm": 0.47811925411224365,
+      "learning_rate": 0.00019723484218374865,
+      "loss": 0.8773119449615479,
+      "step": 2074
+    },
+    {
+      "epoch": 0.8957928802588997,
+      "grad_norm": 0.40109625458717346,
+      "learning_rate": 0.0001972233623633273,
+      "loss": 0.7151904106140137,
+      "step": 2076
+    },
+    {
+      "epoch": 0.896655879180151,
+      "grad_norm": 0.48640304803848267,
+      "learning_rate": 0.00019721185909793047,
+      "loss": 0.8348540663719177,
+      "step": 2078
+    },
+    {
+      "epoch": 0.8975188781014024,
+      "grad_norm": 0.45748841762542725,
+      "learning_rate": 0.000197200332390332,
+      "loss": 0.845246434211731,
+      "step": 2080
+    },
+    {
+      "epoch": 0.8983818770226537,
+      "grad_norm": 0.41650277376174927,
+      "learning_rate": 0.00019718878224331157,
+      "loss": 0.8746084570884705,
+      "step": 2082
+    },
+    {
+      "epoch": 0.8992448759439051,
+      "grad_norm": 0.45878589153289795,
+      "learning_rate": 0.00019717720865965443,
+      "loss": 0.8252862691879272,
+      "step": 2084
+    },
+    {
+      "epoch": 0.9001078748651564,
+      "grad_norm": 0.3710020184516907,
+      "learning_rate": 0.0001971656116421515,
+      "loss": 0.7056596875190735,
+      "step": 2086
+    },
+    {
+      "epoch": 0.9009708737864077,
+      "grad_norm": 0.4251181185245514,
+      "learning_rate": 0.00019715399119359935,
+      "loss": 0.8305537700653076,
+      "step": 2088
+    },
+    {
+      "epoch": 0.9018338727076591,
+      "grad_norm": 0.48429808020591736,
+      "learning_rate": 0.0001971423473168002,
+      "loss": 0.8431704044342041,
+      "step": 2090
+    },
+    {
+      "epoch": 0.9026968716289104,
+      "grad_norm": 0.5384030342102051,
+      "learning_rate": 0.00019713068001456186,
+      "loss": 0.8311790227890015,
+      "step": 2092
+    },
+    {
+      "epoch": 0.9035598705501618,
+      "grad_norm": 0.452029287815094,
+      "learning_rate": 0.00019711898928969796,
+      "loss": 0.8077114224433899,
+      "step": 2094
+    },
+    {
+      "epoch": 0.9044228694714131,
+      "grad_norm": 0.4427074193954468,
+      "learning_rate": 0.0001971072751450276,
+      "loss": 0.8454164266586304,
+      "step": 2096
+    },
+    {
+      "epoch": 0.9052858683926646,
+      "grad_norm": 0.4895693063735962,
+      "learning_rate": 0.00019709553758337557,
+      "loss": 0.8551414608955383,
+      "step": 2098
+    },
+    {
+      "epoch": 0.9061488673139159,
+      "grad_norm": 0.47199201583862305,
+      "learning_rate": 0.00019708377660757244,
+      "loss": 0.9158598184585571,
+      "step": 2100
+    },
+    {
+      "epoch": 0.9061488673139159,
+      "eval_loss": 0.8524587750434875,
+      "eval_runtime": 655.7682,
+      "eval_samples_per_second": 3.141,
+      "eval_steps_per_second": 3.141,
+      "step": 2100
+    },
+    {
+      "epoch": 0.9070118662351672,
+      "grad_norm": 0.45380064845085144,
+      "learning_rate": 0.00019707199222045415,
+      "loss": 0.8301376700401306,
+      "step": 2102
+    },
+    {
+      "epoch": 0.9078748651564186,
+      "grad_norm": 0.4775148034095764,
+      "learning_rate": 0.00019706018442486255,
+      "loss": 0.8191117644309998,
+      "step": 2104
+    },
+    {
+      "epoch": 0.9087378640776699,
+      "grad_norm": 0.40894538164138794,
+      "learning_rate": 0.00019704835322364506,
+      "loss": 0.8333686590194702,
+      "step": 2106
+    },
+    {
+      "epoch": 0.9096008629989213,
+      "grad_norm": 0.4202065169811249,
+      "learning_rate": 0.00019703649861965467,
+      "loss": 0.7916508913040161,
+      "step": 2108
+    },
+    {
+      "epoch": 0.9104638619201726,
+      "grad_norm": 0.39157143235206604,
+      "learning_rate": 0.00019702462061575008,
+      "loss": 0.8018013834953308,
+      "step": 2110
+    },
+    {
+      "epoch": 0.911326860841424,
+      "grad_norm": 0.4623039662837982,
+      "learning_rate": 0.00019701271921479565,
+      "loss": 0.8819739818572998,
+      "step": 2112
+    },
+    {
+      "epoch": 0.9121898597626753,
+      "grad_norm": 0.45183128118515015,
+      "learning_rate": 0.00019700079441966128,
+      "loss": 0.7652842402458191,
+      "step": 2114
+    },
+    {
+      "epoch": 0.9130528586839266,
+      "grad_norm": 0.4562322795391083,
+      "learning_rate": 0.00019698884623322262,
+      "loss": 0.817150890827179,
+      "step": 2116
+    },
+    {
+      "epoch": 0.913915857605178,
+      "grad_norm": 0.45955994725227356,
+      "learning_rate": 0.00019697687465836095,
+      "loss": 0.8223007917404175,
+      "step": 2118
+    },
+    {
+      "epoch": 0.9147788565264293,
+      "grad_norm": 0.44595572352409363,
+      "learning_rate": 0.00019696487969796307,
+      "loss": 0.7716509699821472,
+      "step": 2120
+    },
+    {
+      "epoch": 0.9156418554476807,
+      "grad_norm": 0.4380198121070862,
+      "learning_rate": 0.00019695286135492163,
+      "loss": 0.8205068111419678,
+      "step": 2122
+    },
+    {
+      "epoch": 0.916504854368932,
+      "grad_norm": 0.4025624692440033,
+      "learning_rate": 0.0001969408196321347,
+      "loss": 0.8126305341720581,
+      "step": 2124
+    },
+    {
+      "epoch": 0.9173678532901833,
+      "grad_norm": 0.424277663230896,
+      "learning_rate": 0.00019692875453250616,
+      "loss": 0.7840806841850281,
+      "step": 2126
+    },
+    {
+      "epoch": 0.9182308522114347,
+      "grad_norm": 0.4683000445365906,
+      "learning_rate": 0.00019691666605894538,
+      "loss": 0.9391030669212341,
+      "step": 2128
+    },
+    {
+      "epoch": 0.919093851132686,
+      "grad_norm": 0.47679048776626587,
+      "learning_rate": 0.00019690455421436754,
+      "loss": 0.8336083889007568,
+      "step": 2130
+    },
+    {
+      "epoch": 0.9199568500539375,
+      "grad_norm": 0.45669928193092346,
+      "learning_rate": 0.00019689241900169323,
+      "loss": 0.917514443397522,
+      "step": 2132
+    },
+    {
+      "epoch": 0.9208198489751888,
+      "grad_norm": 0.4372829794883728,
+      "learning_rate": 0.00019688026042384893,
+      "loss": 0.7798282504081726,
+      "step": 2134
+    },
+    {
+      "epoch": 0.9216828478964402,
+      "grad_norm": 0.4497234523296356,
+      "learning_rate": 0.00019686807848376655,
+      "loss": 0.7415590286254883,
+      "step": 2136
+    },
+    {
+      "epoch": 0.9225458468176915,
+      "grad_norm": 0.4892704486846924,
+      "learning_rate": 0.00019685587318438372,
+      "loss": 0.7713689208030701,
+      "step": 2138
+    },
+    {
+      "epoch": 0.9234088457389428,
+      "grad_norm": 0.490495502948761,
+      "learning_rate": 0.0001968436445286437,
+      "loss": 0.821044385433197,
+      "step": 2140
+    },
+    {
+      "epoch": 0.9242718446601942,
+      "grad_norm": 0.43616363406181335,
+      "learning_rate": 0.00019683139251949538,
+      "loss": 0.796081006526947,
+      "step": 2142
+    },
+    {
+      "epoch": 0.9251348435814455,
+      "grad_norm": 0.4199701249599457,
+      "learning_rate": 0.00019681911715989326,
+      "loss": 0.737835705280304,
+      "step": 2144
+    },
+    {
+      "epoch": 0.9259978425026969,
+      "grad_norm": 0.45367109775543213,
+      "learning_rate": 0.0001968068184527975,
+      "loss": 0.8224935531616211,
+      "step": 2146
+    },
+    {
+      "epoch": 0.9268608414239482,
+      "grad_norm": 0.43349263072013855,
+      "learning_rate": 0.0001967944964011739,
+      "loss": 0.826752245426178,
+      "step": 2148
+    },
+    {
+      "epoch": 0.9277238403451996,
+      "grad_norm": 0.4693690538406372,
+      "learning_rate": 0.00019678215100799384,
+      "loss": 0.8527786731719971,
+      "step": 2150
+    },
+    {
+      "epoch": 0.9285868392664509,
+      "grad_norm": 0.4281991124153137,
+      "learning_rate": 0.00019676978227623434,
+      "loss": 0.8101436495780945,
+      "step": 2152
+    },
+    {
+      "epoch": 0.9294498381877022,
+      "grad_norm": 0.4662301540374756,
+      "learning_rate": 0.0001967573902088781,
+      "loss": 0.8997542262077332,
+      "step": 2154
+    },
+    {
+      "epoch": 0.9303128371089536,
+      "grad_norm": 0.41807958483695984,
+      "learning_rate": 0.0001967449748089134,
+      "loss": 0.8378244638442993,
+      "step": 2156
+    },
+    {
+      "epoch": 0.9311758360302049,
+      "grad_norm": 0.4789344072341919,
+      "learning_rate": 0.00019673253607933416,
+      "loss": 0.8562051057815552,
+      "step": 2158
+    },
+    {
+      "epoch": 0.9320388349514563,
+      "grad_norm": 0.43706783652305603,
+      "learning_rate": 0.0001967200740231399,
+      "loss": 0.78457111120224,
+      "step": 2160
+    },
+    {
+      "epoch": 0.9329018338727076,
+      "grad_norm": 0.4441883862018585,
+      "learning_rate": 0.0001967075886433358,
+      "loss": 0.8058217763900757,
+      "step": 2162
+    },
+    {
+      "epoch": 0.933764832793959,
+      "grad_norm": 0.48960480093955994,
+      "learning_rate": 0.00019669507994293266,
+      "loss": 0.916145384311676,
+      "step": 2164
+    },
+    {
+      "epoch": 0.9346278317152104,
+      "grad_norm": 0.3990147113800049,
+      "learning_rate": 0.00019668254792494692,
+      "loss": 0.8805235028266907,
+      "step": 2166
+    },
+    {
+      "epoch": 0.9354908306364617,
+      "grad_norm": 0.4299201965332031,
+      "learning_rate": 0.00019666999259240056,
+      "loss": 0.8611101508140564,
+      "step": 2168
+    },
+    {
+      "epoch": 0.9363538295577131,
+      "grad_norm": 0.5267254114151001,
+      "learning_rate": 0.00019665741394832132,
+      "loss": 0.8429995179176331,
+      "step": 2170
+    },
+    {
+      "epoch": 0.9372168284789644,
+      "grad_norm": 0.46667975187301636,
+      "learning_rate": 0.0001966448119957424,
+      "loss": 0.8057775497436523,
+      "step": 2172
+    },
+    {
+      "epoch": 0.9380798274002158,
+      "grad_norm": 0.4140365421772003,
+      "learning_rate": 0.00019663218673770277,
+      "loss": 0.7456767559051514,
+      "step": 2174
+    },
+    {
+      "epoch": 0.9389428263214671,
+      "grad_norm": 0.4236559569835663,
+      "learning_rate": 0.00019661953817724692,
+      "loss": 0.7320394515991211,
+      "step": 2176
+    },
+    {
+      "epoch": 0.9398058252427185,
+      "grad_norm": 0.4075721800327301,
+      "learning_rate": 0.000196606866317425,
+      "loss": 0.7850301265716553,
+      "step": 2178
+    },
+    {
+      "epoch": 0.9406688241639698,
+      "grad_norm": 0.4638446271419525,
+      "learning_rate": 0.00019659417116129276,
+      "loss": 0.8228051662445068,
+      "step": 2180
+    },
+    {
+      "epoch": 0.9415318230852211,
+      "grad_norm": 0.4641942083835602,
+      "learning_rate": 0.00019658145271191164,
+      "loss": 0.8458912372589111,
+      "step": 2182
+    },
+    {
+      "epoch": 0.9423948220064725,
+      "grad_norm": 0.42868348956108093,
+      "learning_rate": 0.00019656871097234856,
+      "loss": 0.8002372980117798,
+      "step": 2184
+    },
+    {
+      "epoch": 0.9432578209277238,
+      "grad_norm": 0.4726828336715698,
+      "learning_rate": 0.00019655594594567615,
+      "loss": 0.9096182584762573,
+      "step": 2186
+    },
+    {
+      "epoch": 0.9441208198489752,
+      "grad_norm": 0.40363940596580505,
+      "learning_rate": 0.00019654315763497265,
+      "loss": 0.7508110404014587,
+      "step": 2188
+    },
+    {
+      "epoch": 0.9449838187702265,
+      "grad_norm": 0.46951010823249817,
+      "learning_rate": 0.00019653034604332192,
+      "loss": 0.8898510932922363,
+      "step": 2190
+    },
+    {
+      "epoch": 0.9458468176914779,
+      "grad_norm": 0.4564061164855957,
+      "learning_rate": 0.0001965175111738134,
+      "loss": 0.8604891896247864,
+      "step": 2192
+    },
+    {
+      "epoch": 0.9467098166127292,
+      "grad_norm": 0.4366895854473114,
+      "learning_rate": 0.00019650465302954219,
+      "loss": 0.8314935564994812,
+      "step": 2194
+    },
+    {
+      "epoch": 0.9475728155339805,
+      "grad_norm": 0.541490375995636,
+      "learning_rate": 0.0001964917716136089,
+      "loss": 0.851138174533844,
+      "step": 2196
+    },
+    {
+      "epoch": 0.948435814455232,
+      "grad_norm": 0.45251160860061646,
+      "learning_rate": 0.0001964788669291199,
+      "loss": 0.9248369336128235,
+      "step": 2198
+    },
+    {
+      "epoch": 0.9492988133764833,
+      "grad_norm": 0.46237683296203613,
+      "learning_rate": 0.00019646593897918707,
+      "loss": 0.8113608956336975,
+      "step": 2200
+    },
+    {
+      "epoch": 0.9492988133764833,
+      "eval_loss": 0.8443478941917419,
+      "eval_runtime": 666.5866,
+      "eval_samples_per_second": 3.09,
+      "eval_steps_per_second": 3.09,
+      "step": 2200
+    },
+    {
+      "epoch": 0.9501618122977347,
+      "grad_norm": 0.4506337344646454,
+      "learning_rate": 0.0001964529877669279,
+      "loss": 0.8151772618293762,
+      "step": 2202
+    },
+    {
+      "epoch": 0.951024811218986,
+      "grad_norm": 0.42866984009742737,
+      "learning_rate": 0.00019644001329546557,
+      "loss": 0.920696496963501,
+      "step": 2204
+    },
+    {
+      "epoch": 0.9518878101402374,
+      "grad_norm": 0.3899093270301819,
+      "learning_rate": 0.00019642701556792878,
+      "loss": 0.8228384256362915,
+      "step": 2206
+    },
+    {
+      "epoch": 0.9527508090614887,
+      "grad_norm": 0.42472460865974426,
+      "learning_rate": 0.00019641399458745186,
+      "loss": 0.7483987808227539,
+      "step": 2208
+    },
+    {
+      "epoch": 0.95361380798274,
+      "grad_norm": 0.4046783447265625,
+      "learning_rate": 0.00019640095035717482,
+      "loss": 0.7356619834899902,
+      "step": 2210
+    },
+    {
+      "epoch": 0.9544768069039914,
+      "grad_norm": 0.4608006179332733,
+      "learning_rate": 0.00019638788288024316,
+      "loss": 0.7374731302261353,
+      "step": 2212
+    },
+    {
+      "epoch": 0.9553398058252427,
+      "grad_norm": 0.448503315448761,
+      "learning_rate": 0.00019637479215980807,
+      "loss": 0.9128687977790833,
+      "step": 2214
+    },
+    {
+      "epoch": 0.9562028047464941,
+      "grad_norm": 0.4477374851703644,
+      "learning_rate": 0.0001963616781990263,
+      "loss": 0.6983766555786133,
+      "step": 2216
+    },
+    {
+      "epoch": 0.9570658036677454,
+      "grad_norm": 0.41463667154312134,
+      "learning_rate": 0.00019634854100106025,
+      "loss": 0.8543318510055542,
+      "step": 2218
+    },
+    {
+      "epoch": 0.9579288025889967,
+      "grad_norm": 0.5271132588386536,
+      "learning_rate": 0.00019633538056907786,
+      "loss": 0.8866401314735413,
+      "step": 2220
+    },
+    {
+      "epoch": 0.9587918015102481,
+      "grad_norm": 0.4496590495109558,
+      "learning_rate": 0.00019632219690625272,
+      "loss": 0.8414724469184875,
+      "step": 2222
+    },
+    {
+      "epoch": 0.9596548004314994,
+      "grad_norm": 0.4772113263607025,
+      "learning_rate": 0.00019630899001576405,
+      "loss": 0.8859618902206421,
+      "step": 2224
+    },
+    {
+      "epoch": 0.9605177993527508,
+      "grad_norm": 0.5249642729759216,
+      "learning_rate": 0.0001962957599007966,
+      "loss": 0.8347851037979126,
+      "step": 2226
+    },
+    {
+      "epoch": 0.9613807982740021,
+      "grad_norm": 0.4931469261646271,
+      "learning_rate": 0.0001962825065645407,
+      "loss": 0.7893235087394714,
+      "step": 2228
+    },
+    {
+      "epoch": 0.9622437971952535,
+      "grad_norm": 0.45010602474212646,
+      "learning_rate": 0.00019626923001019245,
+      "loss": 0.815602719783783,
+      "step": 2230
+    },
+    {
+      "epoch": 0.9631067961165048,
+      "grad_norm": 0.42947128415107727,
+      "learning_rate": 0.00019625593024095333,
+      "loss": 0.807309627532959,
+      "step": 2232
+    },
+    {
+      "epoch": 0.9639697950377561,
+      "grad_norm": 0.43500378727912903,
+      "learning_rate": 0.00019624260726003057,
+      "loss": 0.8135440945625305,
+      "step": 2234
+    },
+    {
+      "epoch": 0.9648327939590076,
+      "grad_norm": 0.41840270161628723,
+      "learning_rate": 0.00019622926107063692,
+      "loss": 0.802107036113739,
+      "step": 2236
+    },
+    {
+      "epoch": 0.9656957928802589,
+      "grad_norm": 0.4580598771572113,
+      "learning_rate": 0.00019621589167599077,
+      "loss": 0.7596800923347473,
+      "step": 2238
+    },
+    {
+      "epoch": 0.9665587918015103,
+      "grad_norm": 0.38064274191856384,
+      "learning_rate": 0.0001962024990793161,
+      "loss": 0.7609489560127258,
+      "step": 2240
+    },
+    {
+      "epoch": 0.9674217907227616,
+      "grad_norm": 0.39098140597343445,
+      "learning_rate": 0.00019618908328384246,
+      "loss": 0.7829734086990356,
+      "step": 2242
+    },
+    {
+      "epoch": 0.968284789644013,
+      "grad_norm": 0.38412022590637207,
+      "learning_rate": 0.00019617564429280502,
+      "loss": 0.7570722699165344,
+      "step": 2244
+    },
+    {
+      "epoch": 0.9691477885652643,
+      "grad_norm": 0.41451776027679443,
+      "learning_rate": 0.0001961621821094445,
+      "loss": 0.8634825348854065,
+      "step": 2246
+    },
+    {
+      "epoch": 0.9700107874865156,
+      "grad_norm": 0.4989950954914093,
+      "learning_rate": 0.00019614869673700725,
+      "loss": 0.9002810120582581,
+      "step": 2248
+    },
+    {
+      "epoch": 0.970873786407767,
+      "grad_norm": 0.4316846430301666,
+      "learning_rate": 0.00019613518817874524,
+      "loss": 0.7587819695472717,
+      "step": 2250
+    },
+    {
+      "epoch": 0.9717367853290183,
+      "grad_norm": 0.41293349862098694,
+      "learning_rate": 0.000196121656437916,
+      "loss": 0.686238706111908,
+      "step": 2252
+    },
+    {
+      "epoch": 0.9725997842502697,
+      "grad_norm": 0.40252262353897095,
+      "learning_rate": 0.00019610810151778258,
+      "loss": 0.7895162105560303,
+      "step": 2254
+    },
+    {
+      "epoch": 0.973462783171521,
+      "grad_norm": 0.42973560094833374,
+      "learning_rate": 0.0001960945234216138,
+      "loss": 0.8360300064086914,
+      "step": 2256
+    },
+    {
+      "epoch": 0.9743257820927724,
+      "grad_norm": 0.40562206506729126,
+      "learning_rate": 0.00019608092215268386,
+      "loss": 0.7624704241752625,
+      "step": 2258
+    },
+    {
+      "epoch": 0.9751887810140237,
+      "grad_norm": 0.4486660063266754,
+      "learning_rate": 0.00019606729771427266,
+      "loss": 0.8285008072853088,
+      "step": 2260
+    },
+    {
+      "epoch": 0.976051779935275,
+      "grad_norm": 0.37069520354270935,
+      "learning_rate": 0.0001960536501096657,
+      "loss": 0.7951943278312683,
+      "step": 2262
+    },
+    {
+      "epoch": 0.9769147788565264,
+      "grad_norm": 0.43367981910705566,
+      "learning_rate": 0.00019603997934215404,
+      "loss": 0.7641335129737854,
+      "step": 2264
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.42540937662124634,
+      "learning_rate": 0.00019602628541503432,
+      "loss": 0.8449530601501465,
+      "step": 2266
+    },
+    {
+      "epoch": 0.9786407766990292,
+      "grad_norm": 0.46175941824913025,
+      "learning_rate": 0.00019601256833160874,
+      "loss": 0.8207030296325684,
+      "step": 2268
+    },
+    {
+      "epoch": 0.9795037756202805,
+      "grad_norm": 0.3834969103336334,
+      "learning_rate": 0.00019599882809518513,
+      "loss": 0.7753700017929077,
+      "step": 2270
+    },
+    {
+      "epoch": 0.9803667745415319,
+      "grad_norm": 0.43960243463516235,
+      "learning_rate": 0.0001959850647090769,
+      "loss": 0.8844934701919556,
+      "step": 2272
+    },
+    {
+      "epoch": 0.9812297734627832,
+      "grad_norm": 0.4240610897541046,
+      "learning_rate": 0.00019597127817660303,
+      "loss": 0.7795814275741577,
+      "step": 2274
+    },
+    {
+      "epoch": 0.9820927723840345,
+      "grad_norm": 0.41870981454849243,
+      "learning_rate": 0.00019595746850108807,
+      "loss": 0.6960644721984863,
+      "step": 2276
+    },
+    {
+      "epoch": 0.9829557713052859,
+      "grad_norm": 0.43871861696243286,
+      "learning_rate": 0.00019594363568586215,
+      "loss": 0.7709649205207825,
+      "step": 2278
+    },
+    {
+      "epoch": 0.9838187702265372,
+      "grad_norm": 0.45331820845603943,
+      "learning_rate": 0.00019592977973426098,
+      "loss": 0.7324449419975281,
+      "step": 2280
+    },
+    {
+      "epoch": 0.9846817691477886,
+      "grad_norm": 0.4300173223018646,
+      "learning_rate": 0.00019591590064962593,
+      "loss": 0.8720724582672119,
+      "step": 2282
+    },
+    {
+      "epoch": 0.9855447680690399,
+      "grad_norm": 0.4478892982006073,
+      "learning_rate": 0.0001959019984353038,
+      "loss": 0.7396156191825867,
+      "step": 2284
+    },
+    {
+      "epoch": 0.9864077669902913,
+      "grad_norm": 0.4391026198863983,
+      "learning_rate": 0.00019588807309464708,
+      "loss": 0.8303509950637817,
+      "step": 2286
+    },
+    {
+      "epoch": 0.9872707659115426,
+      "grad_norm": 0.4046599268913269,
+      "learning_rate": 0.00019587412463101378,
+      "loss": 0.739641010761261,
+      "step": 2288
+    },
+    {
+      "epoch": 0.9881337648327939,
+      "grad_norm": 0.4619915187358856,
+      "learning_rate": 0.00019586015304776756,
+      "loss": 0.7448247671127319,
+      "step": 2290
+    },
+    {
+      "epoch": 0.9889967637540453,
+      "grad_norm": 0.4603526294231415,
+      "learning_rate": 0.00019584615834827753,
+      "loss": 0.8184107542037964,
+      "step": 2292
+    },
+    {
+      "epoch": 0.9898597626752966,
+      "grad_norm": 0.4828874170780182,
+      "learning_rate": 0.00019583214053591852,
+      "loss": 0.9069648385047913,
+      "step": 2294
+    },
+    {
+      "epoch": 0.990722761596548,
+      "grad_norm": 0.37467876076698303,
+      "learning_rate": 0.00019581809961407082,
+      "loss": 0.6628880500793457,
+      "step": 2296
+    },
+    {
+      "epoch": 0.9915857605177993,
+      "grad_norm": 0.4300445318222046,
+      "learning_rate": 0.00019580403558612037,
+      "loss": 0.7712231278419495,
+      "step": 2298
+    },
+    {
+      "epoch": 0.9924487594390508,
+      "grad_norm": 0.4368257522583008,
+      "learning_rate": 0.00019578994845545863,
+      "loss": 0.7796293497085571,
+      "step": 2300
+    },
+    {
+      "epoch": 0.9924487594390508,
+      "eval_loss": 0.839731752872467,
+      "eval_runtime": 666.2332,
+      "eval_samples_per_second": 3.092,
+      "eval_steps_per_second": 3.092,
+      "step": 2300
+    },
+    {
+      "epoch": 0.993311758360302,
+      "grad_norm": 0.4383920729160309,
+      "learning_rate": 0.00019577583822548262,
+      "loss": 0.7504367232322693,
+      "step": 2302
+    },
+    {
+      "epoch": 0.9941747572815534,
+      "grad_norm": 0.3895981013774872,
+      "learning_rate": 0.00019576170489959496,
+      "loss": 0.7298936247825623,
+      "step": 2304
+    },
+    {
+      "epoch": 0.9950377562028048,
+      "grad_norm": 0.4950196444988251,
+      "learning_rate": 0.00019574754848120392,
+      "loss": 0.9137371778488159,
+      "step": 2306
+    },
+    {
+      "epoch": 0.9959007551240561,
+      "grad_norm": 0.5115531086921692,
+      "learning_rate": 0.00019573336897372318,
+      "loss": 0.9203279614448547,
+      "step": 2308
+    },
+    {
+      "epoch": 0.9967637540453075,
+      "grad_norm": 0.43145665526390076,
+      "learning_rate": 0.000195719166380572,
+      "loss": 0.7708958387374878,
+      "step": 2310
+    },
+    {
+      "epoch": 0.9976267529665588,
+      "grad_norm": 0.39575520157814026,
+      "learning_rate": 0.00019570494070517545,
+      "loss": 0.7911062836647034,
+      "step": 2312
+    },
+    {
+      "epoch": 0.9984897518878102,
+      "grad_norm": 0.45690420269966125,
+      "learning_rate": 0.00019569069195096386,
+      "loss": 0.8282244205474854,
+      "step": 2314
+    },
+    {
+      "epoch": 0.9993527508090615,
+      "grad_norm": 0.43362128734588623,
+      "learning_rate": 0.00019567642012137325,
+      "loss": 0.8658884763717651,
+      "step": 2316
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6889842748641968,
+      "learning_rate": 0.00019566212521984527,
+      "loss": 0.7823468446731567,
+      "step": 2318
+    },
+    {
+      "epoch": 1.0008629989212514,
+      "grad_norm": 0.3945363759994507,
+      "learning_rate": 0.00019564780724982706,
+      "loss": 0.8244057297706604,
+      "step": 2320
+    },
+    {
+      "epoch": 1.0017259978425026,
+      "grad_norm": 0.5313655734062195,
+      "learning_rate": 0.00019563346621477129,
+      "loss": 0.8228418827056885,
+      "step": 2322
+    },
+    {
+      "epoch": 1.002588996763754,
+      "grad_norm": 0.47728294134140015,
+      "learning_rate": 0.00019561910211813625,
+      "loss": 0.8627800941467285,
+      "step": 2324
+    },
+    {
+      "epoch": 1.0034519956850054,
+      "grad_norm": 0.4706253111362457,
+      "learning_rate": 0.00019560471496338582,
+      "loss": 0.8810665011405945,
+      "step": 2326
+    },
+    {
+      "epoch": 1.0043149946062568,
+      "grad_norm": 0.4333725571632385,
+      "learning_rate": 0.0001955903047539893,
+      "loss": 0.7736411094665527,
+      "step": 2328
+    },
+    {
+      "epoch": 1.005177993527508,
+      "grad_norm": 0.49580323696136475,
+      "learning_rate": 0.00019557587149342178,
+      "loss": 0.9185295104980469,
+      "step": 2330
+    },
+    {
+      "epoch": 1.0060409924487594,
+      "grad_norm": 0.4362829029560089,
+      "learning_rate": 0.0001955614151851637,
+      "loss": 0.7387797832489014,
+      "step": 2332
+    },
+    {
+      "epoch": 1.0069039913700109,
+      "grad_norm": 0.42584139108657837,
+      "learning_rate": 0.00019554693583270113,
+      "loss": 0.672156810760498,
+      "step": 2334
+    },
+    {
+      "epoch": 1.007766990291262,
+      "grad_norm": 0.40073466300964355,
+      "learning_rate": 0.0001955324334395257,
+      "loss": 0.7638119459152222,
+      "step": 2336
+    },
+    {
+      "epoch": 1.0086299892125135,
+      "grad_norm": 0.49992597103118896,
+      "learning_rate": 0.00019551790800913458,
+      "loss": 0.7930200695991516,
+      "step": 2338
+    },
+    {
+      "epoch": 1.0094929881337649,
+      "grad_norm": 0.3825504779815674,
+      "learning_rate": 0.00019550335954503058,
+      "loss": 0.7128595113754272,
+      "step": 2340
+    },
+    {
+      "epoch": 1.0103559870550163,
+      "grad_norm": 0.4654180705547333,
+      "learning_rate": 0.00019548878805072196,
+      "loss": 0.7130335569381714,
+      "step": 2342
+    },
+    {
+      "epoch": 1.0112189859762675,
+      "grad_norm": 0.4199283719062805,
+      "learning_rate": 0.00019547419352972258,
+      "loss": 0.7843249440193176,
+      "step": 2344
+    },
+    {
+      "epoch": 1.0120819848975189,
+      "grad_norm": 0.43597257137298584,
+      "learning_rate": 0.0001954595759855518,
+      "loss": 0.676262617111206,
+      "step": 2346
+    },
+    {
+      "epoch": 1.0129449838187703,
+      "grad_norm": 0.47415891289711,
+      "learning_rate": 0.0001954449354217346,
+      "loss": 0.742564857006073,
+      "step": 2348
+    },
+    {
+      "epoch": 1.0138079827400215,
+      "grad_norm": 0.44753482937812805,
+      "learning_rate": 0.00019543027184180153,
+      "loss": 0.7419085502624512,
+      "step": 2350
+    },
+    {
+      "epoch": 1.014670981661273,
+      "grad_norm": 0.4175751209259033,
+      "learning_rate": 0.0001954155852492886,
+      "loss": 0.7373939752578735,
+      "step": 2352
+    },
+    {
+      "epoch": 1.0155339805825243,
+      "grad_norm": 0.40376800298690796,
+      "learning_rate": 0.00019540087564773738,
+      "loss": 0.7639825344085693,
+      "step": 2354
+    },
+    {
+      "epoch": 1.0163969795037757,
+      "grad_norm": 0.4166127145290375,
+      "learning_rate": 0.0001953861430406951,
+      "loss": 0.7797452211380005,
+      "step": 2356
+    },
+    {
+      "epoch": 1.017259978425027,
+      "grad_norm": 0.4340934753417969,
+      "learning_rate": 0.0001953713874317144,
+      "loss": 0.8258501887321472,
+      "step": 2358
+    },
+    {
+      "epoch": 1.0181229773462783,
+      "grad_norm": 0.47081413865089417,
+      "learning_rate": 0.0001953566088243536,
+      "loss": 0.7664495706558228,
+      "step": 2360
+    },
+    {
+      "epoch": 1.0189859762675297,
+      "grad_norm": 0.4126851260662079,
+      "learning_rate": 0.00019534180722217644,
+      "loss": 0.7411028742790222,
+      "step": 2362
+    },
+    {
+      "epoch": 1.019848975188781,
+      "grad_norm": 0.45279955863952637,
+      "learning_rate": 0.00019532698262875227,
+      "loss": 0.7514335513114929,
+      "step": 2364
+    },
+    {
+      "epoch": 1.0207119741100323,
+      "grad_norm": 0.4857143461704254,
+      "learning_rate": 0.00019531213504765595,
+      "loss": 0.7544763088226318,
+      "step": 2366
+    },
+    {
+      "epoch": 1.0215749730312838,
+      "grad_norm": 0.5232970714569092,
+      "learning_rate": 0.00019529726448246795,
+      "loss": 0.7246702313423157,
+      "step": 2368
+    },
+    {
+      "epoch": 1.0224379719525352,
+      "grad_norm": 0.4434663653373718,
+      "learning_rate": 0.00019528237093677424,
+      "loss": 0.7399187684059143,
+      "step": 2370
+    },
+    {
+      "epoch": 1.0233009708737864,
+      "grad_norm": 0.44713014364242554,
+      "learning_rate": 0.0001952674544141663,
+      "loss": 0.7208506464958191,
+      "step": 2372
+    },
+    {
+      "epoch": 1.0241639697950378,
+      "grad_norm": 0.43205446004867554,
+      "learning_rate": 0.0001952525149182412,
+      "loss": 0.761768639087677,
+      "step": 2374
+    },
+    {
+      "epoch": 1.0250269687162892,
+      "grad_norm": 0.4322265386581421,
+      "learning_rate": 0.0001952375524526015,
+      "loss": 0.6573513746261597,
+      "step": 2376
+    },
+    {
+      "epoch": 1.0258899676375404,
+      "grad_norm": 0.4776996970176697,
+      "learning_rate": 0.0001952225670208554,
+      "loss": 0.8118118047714233,
+      "step": 2378
+    },
+    {
+      "epoch": 1.0267529665587918,
+      "grad_norm": 0.5014623403549194,
+      "learning_rate": 0.00019520755862661648,
+      "loss": 0.781197190284729,
+      "step": 2380
+    },
+    {
+      "epoch": 1.0276159654800432,
+      "grad_norm": 0.5164223313331604,
+      "learning_rate": 0.00019519252727350403,
+      "loss": 0.8399010896682739,
+      "step": 2382
+    },
+    {
+      "epoch": 1.0284789644012946,
+      "grad_norm": 0.47874927520751953,
+      "learning_rate": 0.00019517747296514276,
+      "loss": 0.786519467830658,
+      "step": 2384
+    },
+    {
+      "epoch": 1.0293419633225458,
+      "grad_norm": 0.48447099328041077,
+      "learning_rate": 0.00019516239570516292,
+      "loss": 0.7837404012680054,
+      "step": 2386
+    },
+    {
+      "epoch": 1.0302049622437972,
+      "grad_norm": 0.4762440323829651,
+      "learning_rate": 0.0001951472954972004,
+      "loss": 0.833958625793457,
+      "step": 2388
+    },
+    {
+      "epoch": 1.0310679611650486,
+      "grad_norm": 0.42814165353775024,
+      "learning_rate": 0.00019513217234489645,
+      "loss": 0.7688734531402588,
+      "step": 2390
+    },
+    {
+      "epoch": 1.0319309600862998,
+      "grad_norm": 0.4784977436065674,
+      "learning_rate": 0.00019511702625189803,
+      "loss": 0.814251720905304,
+      "step": 2392
+    },
+    {
+      "epoch": 1.0327939590075512,
+      "grad_norm": 0.44989243149757385,
+      "learning_rate": 0.00019510185722185748,
+      "loss": 0.7277538180351257,
+      "step": 2394
+    },
+    {
+      "epoch": 1.0336569579288026,
+      "grad_norm": 0.5141931772232056,
+      "learning_rate": 0.0001950866652584328,
+      "loss": 0.844467282295227,
+      "step": 2396
+    },
+    {
+      "epoch": 1.0345199568500538,
+      "grad_norm": 0.48569414019584656,
+      "learning_rate": 0.00019507145036528747,
+      "loss": 0.7662147879600525,
+      "step": 2398
+    },
+    {
+      "epoch": 1.0353829557713052,
+      "grad_norm": 0.5075576901435852,
+      "learning_rate": 0.00019505621254609047,
+      "loss": 0.7628200054168701,
+      "step": 2400
+    },
+    {
+      "epoch": 1.0353829557713052,
+      "eval_loss": 0.8369861245155334,
+      "eval_runtime": 653.1661,
+      "eval_samples_per_second": 3.154,
+      "eval_steps_per_second": 3.154,
+      "step": 2400
+    },
+    {
+      "epoch": 1.0362459546925566,
+      "grad_norm": 0.49423643946647644,
+      "learning_rate": 0.00019504095180451628,
+      "loss": 0.8225719332695007,
+      "step": 2402
+    },
+    {
+      "epoch": 1.037108953613808,
+      "grad_norm": 0.4558854401111603,
+      "learning_rate": 0.00019502566814424505,
+      "loss": 0.8239169120788574,
+      "step": 2404
+    },
+    {
+      "epoch": 1.0379719525350593,
+      "grad_norm": 0.4864993691444397,
+      "learning_rate": 0.00019501036156896232,
+      "loss": 0.7805002331733704,
+      "step": 2406
+    },
+    {
+      "epoch": 1.0388349514563107,
+      "grad_norm": 0.44108837842941284,
+      "learning_rate": 0.00019499503208235918,
+      "loss": 0.866910994052887,
+      "step": 2408
+    },
+    {
+      "epoch": 1.039697950377562,
+      "grad_norm": 0.4616626799106598,
+      "learning_rate": 0.00019497967968813232,
+      "loss": 0.7601662874221802,
+      "step": 2410
+    },
+    {
+      "epoch": 1.0405609492988135,
+      "grad_norm": 0.4792969524860382,
+      "learning_rate": 0.00019496430438998387,
+      "loss": 0.8155668377876282,
+      "step": 2412
+    },
+    {
+      "epoch": 1.0414239482200647,
+      "grad_norm": 0.45400261878967285,
+      "learning_rate": 0.00019494890619162152,
+      "loss": 0.7879545092582703,
+      "step": 2414
+    },
+    {
+      "epoch": 1.042286947141316,
+      "grad_norm": 0.44541165232658386,
+      "learning_rate": 0.0001949334850967585,
+      "loss": 0.7196864485740662,
+      "step": 2416
+    },
+    {
+      "epoch": 1.0431499460625675,
+      "grad_norm": 0.44515085220336914,
+      "learning_rate": 0.00019491804110911343,
+      "loss": 0.7288097739219666,
+      "step": 2418
+    },
+    {
+      "epoch": 1.0440129449838187,
+      "grad_norm": 0.43586596846580505,
+      "learning_rate": 0.0001949025742324107,
+      "loss": 0.7182422280311584,
+      "step": 2420
+    },
+    {
+      "epoch": 1.04487594390507,
+      "grad_norm": 0.44399815797805786,
+      "learning_rate": 0.00019488708447038002,
+      "loss": 0.7005030512809753,
+      "step": 2422
+    },
+    {
+      "epoch": 1.0457389428263215,
+      "grad_norm": 0.4658401310443878,
+      "learning_rate": 0.00019487157182675665,
+      "loss": 0.715505063533783,
+      "step": 2424
+    },
+    {
+      "epoch": 1.0466019417475727,
+      "grad_norm": 0.4468056261539459,
+      "learning_rate": 0.00019485603630528143,
+      "loss": 0.7170135974884033,
+      "step": 2426
+    },
+    {
+      "epoch": 1.0474649406688241,
+      "grad_norm": 0.5302334427833557,
+      "learning_rate": 0.00019484047790970066,
+      "loss": 0.83464115858078,
+      "step": 2428
+    },
+    {
+      "epoch": 1.0483279395900755,
+      "grad_norm": 0.46583443880081177,
+      "learning_rate": 0.0001948248966437662,
+      "loss": 0.7129145264625549,
+      "step": 2430
+    },
+    {
+      "epoch": 1.049190938511327,
+      "grad_norm": 0.38922831416130066,
+      "learning_rate": 0.0001948092925112354,
+      "loss": 0.7990599870681763,
+      "step": 2432
+    },
+    {
+      "epoch": 1.0500539374325781,
+      "grad_norm": 0.4599211513996124,
+      "learning_rate": 0.00019479366551587108,
+      "loss": 0.8572773933410645,
+      "step": 2434
+    },
+    {
+      "epoch": 1.0509169363538295,
+      "grad_norm": 0.47514498233795166,
+      "learning_rate": 0.00019477801566144165,
+      "loss": 0.8107781410217285,
+      "step": 2436
+    },
+    {
+      "epoch": 1.051779935275081,
+      "grad_norm": 0.41368064284324646,
+      "learning_rate": 0.00019476234295172102,
+      "loss": 0.7433347702026367,
+      "step": 2438
+    },
+    {
+      "epoch": 1.0526429341963321,
+      "grad_norm": 0.4666398763656616,
+      "learning_rate": 0.00019474664739048858,
+      "loss": 0.8033983111381531,
+      "step": 2440
+    },
+    {
+      "epoch": 1.0535059331175836,
+      "grad_norm": 0.41621699929237366,
+      "learning_rate": 0.00019473092898152924,
+      "loss": 0.7320330142974854,
+      "step": 2442
+    },
+    {
+      "epoch": 1.054368932038835,
+      "grad_norm": 0.43523117899894714,
+      "learning_rate": 0.00019471518772863343,
+      "loss": 0.7742927074432373,
+      "step": 2444
+    },
+    {
+      "epoch": 1.0552319309600864,
+      "grad_norm": 0.5151914358139038,
+      "learning_rate": 0.0001946994236355971,
+      "loss": 0.8301699161529541,
+      "step": 2446
+    },
+    {
+      "epoch": 1.0560949298813376,
+      "grad_norm": 0.566112756729126,
+      "learning_rate": 0.0001946836367062216,
+      "loss": 0.837057888507843,
+      "step": 2448
+    },
+    {
+      "epoch": 1.056957928802589,
+      "grad_norm": 0.4257231652736664,
+      "learning_rate": 0.00019466782694431398,
+      "loss": 0.7323788404464722,
+      "step": 2450
+    },
+    {
+      "epoch": 1.0578209277238404,
+      "grad_norm": 0.5477433800697327,
+      "learning_rate": 0.0001946519943536867,
+      "loss": 0.7410078048706055,
+      "step": 2452
+    },
+    {
+      "epoch": 1.0586839266450916,
+      "grad_norm": 0.37357097864151,
+      "learning_rate": 0.00019463613893815762,
+      "loss": 0.6646532416343689,
+      "step": 2454
+    },
+    {
+      "epoch": 1.059546925566343,
+      "grad_norm": 0.438048779964447,
+      "learning_rate": 0.00019462026070155028,
+      "loss": 0.7773549556732178,
+      "step": 2456
+    },
+    {
+      "epoch": 1.0604099244875944,
+      "grad_norm": 0.5114307999610901,
+      "learning_rate": 0.0001946043596476936,
+      "loss": 0.8977773785591125,
+      "step": 2458
+    },
+    {
+      "epoch": 1.0612729234088458,
+      "grad_norm": 0.4340408146381378,
+      "learning_rate": 0.0001945884357804221,
+      "loss": 0.8128405809402466,
+      "step": 2460
+    },
+    {
+      "epoch": 1.062135922330097,
+      "grad_norm": 0.4922826290130615,
+      "learning_rate": 0.0001945724891035757,
+      "loss": 0.8096795678138733,
+      "step": 2462
+    },
+    {
+      "epoch": 1.0629989212513484,
+      "grad_norm": 0.47231894731521606,
+      "learning_rate": 0.00019455651962099987,
+      "loss": 0.7965760231018066,
+      "step": 2464
+    },
+    {
+      "epoch": 1.0638619201725998,
+      "grad_norm": 0.4519463777542114,
+      "learning_rate": 0.00019454052733654565,
+      "loss": 0.7136726975440979,
+      "step": 2466
+    },
+    {
+      "epoch": 1.064724919093851,
+      "grad_norm": 0.44883614778518677,
+      "learning_rate": 0.0001945245122540694,
+      "loss": 0.8136170506477356,
+      "step": 2468
+    },
+    {
+      "epoch": 1.0655879180151024,
+      "grad_norm": 0.4224080741405487,
+      "learning_rate": 0.00019450847437743317,
+      "loss": 0.7840399146080017,
+      "step": 2470
+    },
+    {
+      "epoch": 1.0664509169363539,
+      "grad_norm": 0.4979367256164551,
+      "learning_rate": 0.00019449241371050438,
+      "loss": 0.8202947378158569,
+      "step": 2472
+    },
+    {
+      "epoch": 1.0673139158576053,
+      "grad_norm": 0.5551356673240662,
+      "learning_rate": 0.000194476330257156,
+      "loss": 0.8608070611953735,
+      "step": 2474
+    },
+    {
+      "epoch": 1.0681769147788565,
+      "grad_norm": 0.3980900049209595,
+      "learning_rate": 0.00019446022402126647,
+      "loss": 0.7202636003494263,
+      "step": 2476
+    },
+    {
+      "epoch": 1.0690399137001079,
+      "grad_norm": 0.5393417477607727,
+      "learning_rate": 0.00019444409500671977,
+      "loss": 0.8301891684532166,
+      "step": 2478
+    },
+    {
+      "epoch": 1.0699029126213593,
+      "grad_norm": 0.47717350721359253,
+      "learning_rate": 0.0001944279432174053,
+      "loss": 0.700567901134491,
+      "step": 2480
+    },
+    {
+      "epoch": 1.0707659115426105,
+      "grad_norm": 0.5197957158088684,
+      "learning_rate": 0.000194411768657218,
+      "loss": 0.794978141784668,
+      "step": 2482
+    },
+    {
+      "epoch": 1.0716289104638619,
+      "grad_norm": 0.5289306044578552,
+      "learning_rate": 0.0001943955713300583,
+      "loss": 0.8052116632461548,
+      "step": 2484
+    },
+    {
+      "epoch": 1.0724919093851133,
+      "grad_norm": 0.4360409080982208,
+      "learning_rate": 0.00019437935123983212,
+      "loss": 0.750991702079773,
+      "step": 2486
+    },
+    {
+      "epoch": 1.0733549083063647,
+      "grad_norm": 0.38651731610298157,
+      "learning_rate": 0.00019436310839045085,
+      "loss": 0.6631898880004883,
+      "step": 2488
+    },
+    {
+      "epoch": 1.074217907227616,
+      "grad_norm": 0.4376210868358612,
+      "learning_rate": 0.00019434684278583138,
+      "loss": 0.7995471358299255,
+      "step": 2490
+    },
+    {
+      "epoch": 1.0750809061488673,
+      "grad_norm": 0.46636906266212463,
+      "learning_rate": 0.0001943305544298961,
+      "loss": 0.7633864879608154,
+      "step": 2492
+    },
+    {
+      "epoch": 1.0759439050701187,
+      "grad_norm": 0.43499618768692017,
+      "learning_rate": 0.00019431424332657288,
+      "loss": 0.7281562089920044,
+      "step": 2494
+    },
+    {
+      "epoch": 1.07680690399137,
+      "grad_norm": 0.39683374762535095,
+      "learning_rate": 0.000194297909479795,
+      "loss": 0.7313723564147949,
+      "step": 2496
+    },
+    {
+      "epoch": 1.0776699029126213,
+      "grad_norm": 0.4545603096485138,
+      "learning_rate": 0.0001942815528935014,
+      "loss": 0.7120141983032227,
+      "step": 2498
+    },
+    {
+      "epoch": 1.0785329018338727,
+      "grad_norm": 0.5040699243545532,
+      "learning_rate": 0.0001942651735716363,
+      "loss": 0.752600908279419,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0785329018338727,
+      "eval_loss": 0.8323014378547668,
+      "eval_runtime": 652.3791,
+      "eval_samples_per_second": 3.158,
+      "eval_steps_per_second": 3.158,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 13908,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.001
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4991027403059917e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/sft_qwen_14B/checkpoints/checkpoint-2500/training_args.bin b/sft_qwen_14B/checkpoints/checkpoint-2500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b023888140f1fb107e8d5ebbfbcb9d9558b09d43
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-2500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4200830b23d19bc86049c280236c4a6b18c26d7061b5a57cc024888ec760920f
+size 5201
diff --git a/sft_qwen_14B/checkpoints/checkpoint-3000/README.md b/sft_qwen_14B/checkpoints/checkpoint-3000/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..779b6406e547b32301fef1d181301a873befe542
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-3000/README.md
@@ -0,0 +1,207 @@
+---
+base_model: runs/cpt_run_14b/merged_14b_cpt_lora
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:runs/cpt_run_14b/merged_14b_cpt_lora
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0
\ No newline at end of file
diff --git a/sft_qwen_14B/checkpoints/checkpoint-3000/adapter_config.json b/sft_qwen_14B/checkpoints/checkpoint-3000/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8ea271115c141fb10c6d899b06f46f21800e1ad6
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-3000/adapter_config.json
@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "runs/cpt_run_14b/merged_14b_cpt_lora",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/sft_qwen_14B/checkpoints/checkpoint-3000/adapter_model.safetensors b/sft_qwen_14B/checkpoints/checkpoint-3000/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..dcc1bd9181ba4ecc9a1c1aeb46f773a77d6b85a6
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-3000/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dcbf833b9436fe1633c8c06b79c62eb27315805c72c93a87cf400578cca73bb
+size 100715016
diff --git a/sft_qwen_14B/checkpoints/checkpoint-3000/optimizer.pt b/sft_qwen_14B/checkpoints/checkpoint-3000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f80d0dff70719b2399babbc368578901a26ff9eb
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-3000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb6b77215c673d143314529902fe0e9c30346349f436c2b94e6287816a01931a
+size 201650659
diff --git a/sft_qwen_14B/checkpoints/checkpoint-3000/rng_state.pth b/sft_qwen_14B/checkpoints/checkpoint-3000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..03eadb0df2d9cd2a069e86ddefb39c61fe62dd75
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-3000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8acb52ffaa9f33f79559f4745e1edd981724d4af3b215ee913bccc7a86ea9435
+size 14645
diff --git a/sft_qwen_14B/checkpoints/checkpoint-3000/scheduler.pt b/sft_qwen_14B/checkpoints/checkpoint-3000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1565d233a60c1f175ff69a1df5d94e02f23a478f
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-3000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cbdba03d310bbbdcbbaef51ab8ce27fbdc8188e8f0659848963cbd94c6e7882
+size 1465
diff --git a/sft_qwen_14B/checkpoints/checkpoint-3000/trainer_state.json b/sft_qwen_14B/checkpoints/checkpoint-3000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..ccc8cd94200d7e444ee9ecc7dba5ac33b979f895
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-3000/trainer_state.json
@@ -0,0 +1,10783 @@
+{
+  "best_global_step": 3000,
+  "best_metric": 0.8127614259719849,
+  "best_model_checkpoint": "runs/instruct_run_14b_v1/checkpoints/checkpoint-3000",
+  "epoch": 1.2942826321467098,
+  "eval_steps": 100,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008629989212513484,
+      "grad_norm": 0.36567428708076477,
+      "learning_rate": 1.7969451931716084e-07,
+      "loss": 1.6794371604919434,
+      "step": 2
+    },
+    {
+      "epoch": 0.001725997842502697,
+      "grad_norm": 0.4024646580219269,
+      "learning_rate": 5.390835579514825e-07,
+      "loss": 1.6853073835372925,
+      "step": 4
+    },
+    {
+      "epoch": 0.0025889967637540453,
+      "grad_norm": 0.40199393033981323,
+      "learning_rate": 8.984725965858042e-07,
+      "loss": 1.7621158361434937,
+      "step": 6
+    },
+    {
+      "epoch": 0.003451995685005394,
+      "grad_norm": 0.35409677028656006,
+      "learning_rate": 1.257861635220126e-06,
+      "loss": 1.633257269859314,
+      "step": 8
+    },
+    {
+      "epoch": 0.004314994606256742,
+      "grad_norm": 0.39087551832199097,
+      "learning_rate": 1.6172506738544475e-06,
+      "loss": 1.7374768257141113,
+      "step": 10
+    },
+    {
+      "epoch": 0.005177993527508091,
+      "grad_norm": 0.3586857318878174,
+      "learning_rate": 1.9766397124887693e-06,
+      "loss": 1.6955714225769043,
+      "step": 12
+    },
+    {
+      "epoch": 0.006040992448759439,
+      "grad_norm": 0.32755669951438904,
+      "learning_rate": 2.3360287511230908e-06,
+      "loss": 1.720664381980896,
+      "step": 14
+    },
+    {
+      "epoch": 0.006903991370010788,
+      "grad_norm": 0.4054872691631317,
+      "learning_rate": 2.6954177897574127e-06,
+      "loss": 1.6957035064697266,
+      "step": 16
+    },
+    {
+      "epoch": 0.007766990291262136,
+      "grad_norm": 0.37593814730644226,
+      "learning_rate": 3.0548068283917343e-06,
+      "loss": 1.7286947965621948,
+      "step": 18
+    },
+    {
+      "epoch": 0.008629989212513484,
+      "grad_norm": 0.3344813287258148,
+      "learning_rate": 3.414195867026056e-06,
+      "loss": 1.727295994758606,
+      "step": 20
+    },
+    {
+      "epoch": 0.009492988133764833,
+      "grad_norm": 0.357474148273468,
+      "learning_rate": 3.7735849056603773e-06,
+      "loss": 1.6727914810180664,
+      "step": 22
+    },
+    {
+      "epoch": 0.010355987055016181,
+      "grad_norm": 0.39115726947784424,
+      "learning_rate": 4.132973944294699e-06,
+      "loss": 1.6518884897232056,
+      "step": 24
+    },
+    {
+      "epoch": 0.01121898597626753,
+      "grad_norm": 0.4711727201938629,
+      "learning_rate": 4.492362982929021e-06,
+      "loss": 1.7868088483810425,
+      "step": 26
+    },
+    {
+      "epoch": 0.012081984897518877,
+      "grad_norm": 0.34112176299095154,
+      "learning_rate": 4.851752021563342e-06,
+      "loss": 1.6127634048461914,
+      "step": 28
+    },
+    {
+      "epoch": 0.012944983818770227,
+      "grad_norm": 0.5071991682052612,
+      "learning_rate": 5.211141060197664e-06,
+      "loss": 1.7858378887176514,
+      "step": 30
+    },
+    {
+      "epoch": 0.013807982740021575,
+      "grad_norm": 0.42048847675323486,
+      "learning_rate": 5.570530098831986e-06,
+      "loss": 1.7123326063156128,
+      "step": 32
+    },
+    {
+      "epoch": 0.014670981661272923,
+      "grad_norm": 0.48883870244026184,
+      "learning_rate": 5.929919137466308e-06,
+      "loss": 1.737749695777893,
+      "step": 34
+    },
+    {
+      "epoch": 0.015533980582524271,
+      "grad_norm": 0.3311465084552765,
+      "learning_rate": 6.289308176100629e-06,
+      "loss": 1.5578981637954712,
+      "step": 36
+    },
+    {
+      "epoch": 0.01639697950377562,
+      "grad_norm": 0.5178973078727722,
+      "learning_rate": 6.64869721473495e-06,
+      "loss": 1.719806432723999,
+      "step": 38
+    },
+    {
+      "epoch": 0.017259978425026967,
+      "grad_norm": 0.47097742557525635,
+      "learning_rate": 7.008086253369272e-06,
+      "loss": 1.728212833404541,
+      "step": 40
+    },
+    {
+      "epoch": 0.018122977346278317,
+      "grad_norm": 0.5051584243774414,
+      "learning_rate": 7.367475292003594e-06,
+      "loss": 1.6542466878890991,
+      "step": 42
+    },
+    {
+      "epoch": 0.018985976267529667,
+      "grad_norm": 0.4645111560821533,
+      "learning_rate": 7.726864330637915e-06,
+      "loss": 1.7087690830230713,
+      "step": 44
+    },
+    {
+      "epoch": 0.019848975188781013,
+      "grad_norm": 0.5184999704360962,
+      "learning_rate": 8.086253369272237e-06,
+      "loss": 1.7018946409225464,
+      "step": 46
+    },
+    {
+      "epoch": 0.020711974110032363,
+      "grad_norm": 0.4543815851211548,
+      "learning_rate": 8.44564240790656e-06,
+      "loss": 1.6818269491195679,
+      "step": 48
+    },
+    {
+      "epoch": 0.021574973031283712,
+      "grad_norm": 0.44411996006965637,
+      "learning_rate": 8.80503144654088e-06,
+      "loss": 1.5772877931594849,
+      "step": 50
+    },
+    {
+      "epoch": 0.02243797195253506,
+      "grad_norm": 0.3409404158592224,
+      "learning_rate": 9.164420485175203e-06,
+      "loss": 1.498152732849121,
+      "step": 52
+    },
+    {
+      "epoch": 0.02330097087378641,
+      "grad_norm": 0.42104434967041016,
+      "learning_rate": 9.523809523809523e-06,
+      "loss": 1.6189048290252686,
+      "step": 54
+    },
+    {
+      "epoch": 0.024163969795037755,
+      "grad_norm": 0.3756246268749237,
+      "learning_rate": 9.883198562443846e-06,
+      "loss": 1.4596441984176636,
+      "step": 56
+    },
+    {
+      "epoch": 0.025026968716289105,
+      "grad_norm": 0.36214128136634827,
+      "learning_rate": 1.0242587601078168e-05,
+      "loss": 1.503880500793457,
+      "step": 58
+    },
+    {
+      "epoch": 0.025889967637540454,
+      "grad_norm": 0.40893009305000305,
+      "learning_rate": 1.060197663971249e-05,
+      "loss": 1.5912823677062988,
+      "step": 60
+    },
+    {
+      "epoch": 0.0267529665587918,
+      "grad_norm": 0.28710272908210754,
+      "learning_rate": 1.0961365678346811e-05,
+      "loss": 1.2956721782684326,
+      "step": 62
+    },
+    {
+      "epoch": 0.02761596548004315,
+      "grad_norm": 0.304573118686676,
+      "learning_rate": 1.1320754716981132e-05,
+      "loss": 1.4648056030273438,
+      "step": 64
+    },
+    {
+      "epoch": 0.0284789644012945,
+      "grad_norm": 0.36523914337158203,
+      "learning_rate": 1.1680143755615454e-05,
+      "loss": 1.6078968048095703,
+      "step": 66
+    },
+    {
+      "epoch": 0.029341963322545846,
+      "grad_norm": 0.37929031252861023,
+      "learning_rate": 1.2039532794249775e-05,
+      "loss": 1.5969421863555908,
+      "step": 68
+    },
+    {
+      "epoch": 0.030204962243797196,
+      "grad_norm": 0.3053947389125824,
+      "learning_rate": 1.2398921832884097e-05,
+      "loss": 1.4312325716018677,
+      "step": 70
+    },
+    {
+      "epoch": 0.031067961165048542,
+      "grad_norm": 0.3028779923915863,
+      "learning_rate": 1.275831087151842e-05,
+      "loss": 1.4101300239562988,
+      "step": 72
+    },
+    {
+      "epoch": 0.03193096008629989,
+      "grad_norm": 0.29649803042411804,
+      "learning_rate": 1.3117699910152742e-05,
+      "loss": 1.4553817510604858,
+      "step": 74
+    },
+    {
+      "epoch": 0.03279395900755124,
+      "grad_norm": 0.26032644510269165,
+      "learning_rate": 1.3477088948787062e-05,
+      "loss": 1.4623000621795654,
+      "step": 76
+    },
+    {
+      "epoch": 0.03365695792880259,
+      "grad_norm": 0.33558446168899536,
+      "learning_rate": 1.3836477987421385e-05,
+      "loss": 1.5181745290756226,
+      "step": 78
+    },
+    {
+      "epoch": 0.034519956850053934,
+      "grad_norm": 0.28307804465293884,
+      "learning_rate": 1.4195867026055706e-05,
+      "loss": 1.4397861957550049,
+      "step": 80
+    },
+    {
+      "epoch": 0.035382955771305284,
+      "grad_norm": 0.3451690673828125,
+      "learning_rate": 1.455525606469003e-05,
+      "loss": 1.463841199874878,
+      "step": 82
+    },
+    {
+      "epoch": 0.036245954692556634,
+      "grad_norm": 0.3248669505119324,
+      "learning_rate": 1.4914645103324348e-05,
+      "loss": 1.3554227352142334,
+      "step": 84
+    },
+    {
+      "epoch": 0.037108953613807984,
+      "grad_norm": 0.2855011224746704,
+      "learning_rate": 1.527403414195867e-05,
+      "loss": 1.2810425758361816,
+      "step": 86
+    },
+    {
+      "epoch": 0.03797195253505933,
+      "grad_norm": 0.33365535736083984,
+      "learning_rate": 1.5633423180592992e-05,
+      "loss": 1.428163766860962,
+      "step": 88
+    },
+    {
+      "epoch": 0.038834951456310676,
+      "grad_norm": 0.34099438786506653,
+      "learning_rate": 1.5992812219227316e-05,
+      "loss": 1.3487578630447388,
+      "step": 90
+    },
+    {
+      "epoch": 0.039697950377562026,
+      "grad_norm": 0.39247506856918335,
+      "learning_rate": 1.6352201257861635e-05,
+      "loss": 1.30057954788208,
+      "step": 92
+    },
+    {
+      "epoch": 0.040560949298813376,
+      "grad_norm": 0.32692041993141174,
+      "learning_rate": 1.671159029649596e-05,
+      "loss": 1.2923580408096313,
+      "step": 94
+    },
+    {
+      "epoch": 0.041423948220064725,
+      "grad_norm": 0.43452519178390503,
+      "learning_rate": 1.707097933513028e-05,
+      "loss": 1.5002273321151733,
+      "step": 96
+    },
+    {
+      "epoch": 0.042286947141316075,
+      "grad_norm": 0.3251534402370453,
+      "learning_rate": 1.7430368373764602e-05,
+      "loss": 1.330254077911377,
+      "step": 98
+    },
+    {
+      "epoch": 0.043149946062567425,
+      "grad_norm": 0.3198273479938507,
+      "learning_rate": 1.778975741239892e-05,
+      "loss": 1.3054943084716797,
+      "step": 100
+    },
+    {
+      "epoch": 0.043149946062567425,
+      "eval_loss": 1.366738200187683,
+      "eval_runtime": 651.8198,
+      "eval_samples_per_second": 3.16,
+      "eval_steps_per_second": 3.16,
+      "step": 100
+    },
+    {
+      "epoch": 0.04401294498381877,
+      "grad_norm": 0.37364065647125244,
+      "learning_rate": 1.8149146451033245e-05,
+      "loss": 1.314281940460205,
+      "step": 102
+    },
+    {
+      "epoch": 0.04487594390507012,
+      "grad_norm": 0.39384758472442627,
+      "learning_rate": 1.8508535489667568e-05,
+      "loss": 1.2737246751785278,
+      "step": 104
+    },
+    {
+      "epoch": 0.04573894282632147,
+      "grad_norm": 0.3521905541419983,
+      "learning_rate": 1.8867924528301888e-05,
+      "loss": 1.3113226890563965,
+      "step": 106
+    },
+    {
+      "epoch": 0.04660194174757282,
+      "grad_norm": 0.33531463146209717,
+      "learning_rate": 1.9227313566936208e-05,
+      "loss": 1.3253653049468994,
+      "step": 108
+    },
+    {
+      "epoch": 0.04746494066882417,
+      "grad_norm": 0.35596340894699097,
+      "learning_rate": 1.958670260557053e-05,
+      "loss": 1.3236849308013916,
+      "step": 110
+    },
+    {
+      "epoch": 0.04832793959007551,
+      "grad_norm": 0.36028242111206055,
+      "learning_rate": 1.9946091644204854e-05,
+      "loss": 1.183128833770752,
+      "step": 112
+    },
+    {
+      "epoch": 0.04919093851132686,
+      "grad_norm": 0.42109814286231995,
+      "learning_rate": 2.0305480682839174e-05,
+      "loss": 1.2741888761520386,
+      "step": 114
+    },
+    {
+      "epoch": 0.05005393743257821,
+      "grad_norm": 0.39675939083099365,
+      "learning_rate": 2.0664869721473494e-05,
+      "loss": 1.3050109148025513,
+      "step": 116
+    },
+    {
+      "epoch": 0.05091693635382956,
+      "grad_norm": 0.4414141774177551,
+      "learning_rate": 2.1024258760107817e-05,
+      "loss": 1.2472094297409058,
+      "step": 118
+    },
+    {
+      "epoch": 0.05177993527508091,
+      "grad_norm": 0.42872729897499084,
+      "learning_rate": 2.138364779874214e-05,
+      "loss": 1.3338921070098877,
+      "step": 120
+    },
+    {
+      "epoch": 0.05264293419633225,
+      "grad_norm": 0.38336244225502014,
+      "learning_rate": 2.174303683737646e-05,
+      "loss": 1.322908878326416,
+      "step": 122
+    },
+    {
+      "epoch": 0.0535059331175836,
+      "grad_norm": 0.41046878695487976,
+      "learning_rate": 2.2102425876010783e-05,
+      "loss": 1.2169240713119507,
+      "step": 124
+    },
+    {
+      "epoch": 0.05436893203883495,
+      "grad_norm": 0.39460113644599915,
+      "learning_rate": 2.2461814914645103e-05,
+      "loss": 1.2085309028625488,
+      "step": 126
+    },
+    {
+      "epoch": 0.0552319309600863,
+      "grad_norm": 0.42829909920692444,
+      "learning_rate": 2.2821203953279426e-05,
+      "loss": 1.2969133853912354,
+      "step": 128
+    },
+    {
+      "epoch": 0.05609492988133765,
+      "grad_norm": 0.3940851390361786,
+      "learning_rate": 2.3180592991913746e-05,
+      "loss": 1.1892330646514893,
+      "step": 130
+    },
+    {
+      "epoch": 0.056957928802589,
+      "grad_norm": 0.45011839270591736,
+      "learning_rate": 2.353998203054807e-05,
+      "loss": 1.2082979679107666,
+      "step": 132
+    },
+    {
+      "epoch": 0.05782092772384034,
+      "grad_norm": 0.46059420704841614,
+      "learning_rate": 2.3899371069182393e-05,
+      "loss": 1.2388817071914673,
+      "step": 134
+    },
+    {
+      "epoch": 0.05868392664509169,
+      "grad_norm": 0.41085872054100037,
+      "learning_rate": 2.4258760107816713e-05,
+      "loss": 1.193917155265808,
+      "step": 136
+    },
+    {
+      "epoch": 0.05954692556634304,
+      "grad_norm": 0.4024205207824707,
+      "learning_rate": 2.4618149146451032e-05,
+      "loss": 1.1514034271240234,
+      "step": 138
+    },
+    {
+      "epoch": 0.06040992448759439,
+      "grad_norm": 0.3893793523311615,
+      "learning_rate": 2.4977538185085356e-05,
+      "loss": 1.1626157760620117,
+      "step": 140
+    },
+    {
+      "epoch": 0.06127292340884574,
+      "grad_norm": 0.4456317126750946,
+      "learning_rate": 2.5336927223719675e-05,
+      "loss": 1.1627076864242554,
+      "step": 142
+    },
+    {
+      "epoch": 0.062135922330097085,
+      "grad_norm": 0.5050215125083923,
+      "learning_rate": 2.5696316262354e-05,
+      "loss": 1.3038755655288696,
+      "step": 144
+    },
+    {
+      "epoch": 0.06299892125134844,
+      "grad_norm": 0.4071207642555237,
+      "learning_rate": 2.605570530098832e-05,
+      "loss": 1.1708844900131226,
+      "step": 146
+    },
+    {
+      "epoch": 0.06386192017259978,
+      "grad_norm": 0.4363228678703308,
+      "learning_rate": 2.641509433962264e-05,
+      "loss": 1.2149070501327515,
+      "step": 148
+    },
+    {
+      "epoch": 0.06472491909385113,
+      "grad_norm": 0.4436556398868561,
+      "learning_rate": 2.6774483378256965e-05,
+      "loss": 1.1942368745803833,
+      "step": 150
+    },
+    {
+      "epoch": 0.06558791801510248,
+      "grad_norm": 0.4068629741668701,
+      "learning_rate": 2.7133872416891288e-05,
+      "loss": 1.1799161434173584,
+      "step": 152
+    },
+    {
+      "epoch": 0.06645091693635383,
+      "grad_norm": 0.5291106700897217,
+      "learning_rate": 2.7493261455525608e-05,
+      "loss": 1.1832845211029053,
+      "step": 154
+    },
+    {
+      "epoch": 0.06731391585760518,
+      "grad_norm": 0.4410109221935272,
+      "learning_rate": 2.785265049415993e-05,
+      "loss": 1.1696993112564087,
+      "step": 156
+    },
+    {
+      "epoch": 0.06817691477885653,
+      "grad_norm": 0.4858371913433075,
+      "learning_rate": 2.8212039532794248e-05,
+      "loss": 1.2036973237991333,
+      "step": 158
+    },
+    {
+      "epoch": 0.06903991370010787,
+      "grad_norm": 0.45373693108558655,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 1.1145079135894775,
+      "step": 160
+    },
+    {
+      "epoch": 0.06990291262135923,
+      "grad_norm": 0.4881038963794708,
+      "learning_rate": 2.8930817610062894e-05,
+      "loss": 1.173502802848816,
+      "step": 162
+    },
+    {
+      "epoch": 0.07076591154261057,
+      "grad_norm": 0.576934814453125,
+      "learning_rate": 2.9290206648697217e-05,
+      "loss": 1.250414490699768,
+      "step": 164
+    },
+    {
+      "epoch": 0.07162891046386193,
+      "grad_norm": 0.4900001287460327,
+      "learning_rate": 2.9649595687331537e-05,
+      "loss": 1.0721495151519775,
+      "step": 166
+    },
+    {
+      "epoch": 0.07249190938511327,
+      "grad_norm": 0.4440019726753235,
+      "learning_rate": 3.000898472596586e-05,
+      "loss": 1.0689374208450317,
+      "step": 168
+    },
+    {
+      "epoch": 0.07335490830636461,
+      "grad_norm": 0.4267268180847168,
+      "learning_rate": 3.0368373764600184e-05,
+      "loss": 1.2095128297805786,
+      "step": 170
+    },
+    {
+      "epoch": 0.07421790722761597,
+      "grad_norm": 0.6062787771224976,
+      "learning_rate": 3.0727762803234503e-05,
+      "loss": 1.077776551246643,
+      "step": 172
+    },
+    {
+      "epoch": 0.07508090614886731,
+      "grad_norm": 0.49510180950164795,
+      "learning_rate": 3.108715184186882e-05,
+      "loss": 1.144006371498108,
+      "step": 174
+    },
+    {
+      "epoch": 0.07594390507011867,
+      "grad_norm": 0.4670701026916504,
+      "learning_rate": 3.144654088050314e-05,
+      "loss": 1.1663392782211304,
+      "step": 176
+    },
+    {
+      "epoch": 0.07680690399137001,
+      "grad_norm": 0.5615383386611938,
+      "learning_rate": 3.1805929919137466e-05,
+      "loss": 1.1665973663330078,
+      "step": 178
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "grad_norm": 0.47305551171302795,
+      "learning_rate": 3.216531895777179e-05,
+      "loss": 1.1337063312530518,
+      "step": 180
+    },
+    {
+      "epoch": 0.07853290183387271,
+      "grad_norm": 0.5127068758010864,
+      "learning_rate": 3.252470799640611e-05,
+      "loss": 1.072874903678894,
+      "step": 182
+    },
+    {
+      "epoch": 0.07939590075512405,
+      "grad_norm": 0.632448136806488,
+      "learning_rate": 3.2884097035040436e-05,
+      "loss": 1.1577240228652954,
+      "step": 184
+    },
+    {
+      "epoch": 0.08025889967637541,
+      "grad_norm": 0.4041025638580322,
+      "learning_rate": 3.324348607367476e-05,
+      "loss": 1.1186822652816772,
+      "step": 186
+    },
+    {
+      "epoch": 0.08112189859762675,
+      "grad_norm": 0.5239102244377136,
+      "learning_rate": 3.3602875112309076e-05,
+      "loss": 1.1468429565429688,
+      "step": 188
+    },
+    {
+      "epoch": 0.08198489751887811,
+      "grad_norm": 0.4486575424671173,
+      "learning_rate": 3.39622641509434e-05,
+      "loss": 1.0017019510269165,
+      "step": 190
+    },
+    {
+      "epoch": 0.08284789644012945,
+      "grad_norm": 0.4994317293167114,
+      "learning_rate": 3.4321653189577715e-05,
+      "loss": 1.1901532411575317,
+      "step": 192
+    },
+    {
+      "epoch": 0.0837108953613808,
+      "grad_norm": 0.5023699998855591,
+      "learning_rate": 3.468104222821204e-05,
+      "loss": 1.1398564577102661,
+      "step": 194
+    },
+    {
+      "epoch": 0.08457389428263215,
+      "grad_norm": 0.5077701807022095,
+      "learning_rate": 3.504043126684636e-05,
+      "loss": 1.1390413045883179,
+      "step": 196
+    },
+    {
+      "epoch": 0.0854368932038835,
+      "grad_norm": 0.5527892112731934,
+      "learning_rate": 3.5399820305480685e-05,
+      "loss": 1.1411432027816772,
+      "step": 198
+    },
+    {
+      "epoch": 0.08629989212513485,
+      "grad_norm": 0.5572488903999329,
+      "learning_rate": 3.575920934411501e-05,
+      "loss": 1.071260690689087,
+      "step": 200
+    },
+    {
+      "epoch": 0.08629989212513485,
+      "eval_loss": 1.1519012451171875,
+      "eval_runtime": 654.6055,
+      "eval_samples_per_second": 3.147,
+      "eval_steps_per_second": 3.147,
+      "step": 200
+    },
+    {
+      "epoch": 0.08716289104638619,
+      "grad_norm": 0.5134095549583435,
+      "learning_rate": 3.611859838274933e-05,
+      "loss": 1.138135552406311,
+      "step": 202
+    },
+    {
+      "epoch": 0.08802588996763754,
+      "grad_norm": 0.5166040658950806,
+      "learning_rate": 3.647798742138365e-05,
+      "loss": 1.111999273300171,
+      "step": 204
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.5336993336677551,
+      "learning_rate": 3.683737646001797e-05,
+      "loss": 1.1031352281570435,
+      "step": 206
+    },
+    {
+      "epoch": 0.08975188781014024,
+      "grad_norm": 0.8289600014686584,
+      "learning_rate": 3.7196765498652294e-05,
+      "loss": 1.0388667583465576,
+      "step": 208
+    },
+    {
+      "epoch": 0.09061488673139159,
+      "grad_norm": 0.47992637753486633,
+      "learning_rate": 3.755615453728661e-05,
+      "loss": 1.0950241088867188,
+      "step": 210
+    },
+    {
+      "epoch": 0.09147788565264293,
+      "grad_norm": 0.5629691481590271,
+      "learning_rate": 3.7915543575920934e-05,
+      "loss": 1.0361733436584473,
+      "step": 212
+    },
+    {
+      "epoch": 0.09234088457389428,
+      "grad_norm": 0.5515111684799194,
+      "learning_rate": 3.827493261455526e-05,
+      "loss": 1.0922447443008423,
+      "step": 214
+    },
+    {
+      "epoch": 0.09320388349514563,
+      "grad_norm": 0.5078643560409546,
+      "learning_rate": 3.863432165318958e-05,
+      "loss": 1.0866856575012207,
+      "step": 216
+    },
+    {
+      "epoch": 0.09406688241639698,
+      "grad_norm": 0.6046127676963806,
+      "learning_rate": 3.8993710691823904e-05,
+      "loss": 1.1231595277786255,
+      "step": 218
+    },
+    {
+      "epoch": 0.09492988133764833,
+      "grad_norm": 0.6255762577056885,
+      "learning_rate": 3.935309973045822e-05,
+      "loss": 1.099171757698059,
+      "step": 220
+    },
+    {
+      "epoch": 0.09579288025889968,
+      "grad_norm": 0.6036638021469116,
+      "learning_rate": 3.971248876909254e-05,
+      "loss": 1.0557761192321777,
+      "step": 222
+    },
+    {
+      "epoch": 0.09665587918015102,
+      "grad_norm": 0.5520529747009277,
+      "learning_rate": 4.0071877807726867e-05,
+      "loss": 1.0467877388000488,
+      "step": 224
+    },
+    {
+      "epoch": 0.09751887810140238,
+      "grad_norm": 0.5958684682846069,
+      "learning_rate": 4.043126684636119e-05,
+      "loss": 1.17941153049469,
+      "step": 226
+    },
+    {
+      "epoch": 0.09838187702265372,
+      "grad_norm": 0.5283281803131104,
+      "learning_rate": 4.079065588499551e-05,
+      "loss": 1.104217767715454,
+      "step": 228
+    },
+    {
+      "epoch": 0.09924487594390508,
+      "grad_norm": 0.5608792901039124,
+      "learning_rate": 4.115004492362983e-05,
+      "loss": 1.0900640487670898,
+      "step": 230
+    },
+    {
+      "epoch": 0.10010787486515642,
+      "grad_norm": 0.555964469909668,
+      "learning_rate": 4.150943396226415e-05,
+      "loss": 0.9887422323226929,
+      "step": 232
+    },
+    {
+      "epoch": 0.10097087378640776,
+      "grad_norm": 0.5875785946846008,
+      "learning_rate": 4.1868823000898476e-05,
+      "loss": 1.1298567056655884,
+      "step": 234
+    },
+    {
+      "epoch": 0.10183387270765912,
+      "grad_norm": 0.4544795751571655,
+      "learning_rate": 4.222821203953279e-05,
+      "loss": 1.0957067012786865,
+      "step": 236
+    },
+    {
+      "epoch": 0.10269687162891046,
+      "grad_norm": 0.564145565032959,
+      "learning_rate": 4.2587601078167116e-05,
+      "loss": 1.0328738689422607,
+      "step": 238
+    },
+    {
+      "epoch": 0.10355987055016182,
+      "grad_norm": 0.6285979747772217,
+      "learning_rate": 4.294699011680144e-05,
+      "loss": 1.1085515022277832,
+      "step": 240
+    },
+    {
+      "epoch": 0.10442286947141316,
+      "grad_norm": 0.6442288756370544,
+      "learning_rate": 4.330637915543576e-05,
+      "loss": 1.1291271448135376,
+      "step": 242
+    },
+    {
+      "epoch": 0.1052858683926645,
+      "grad_norm": 0.6137154698371887,
+      "learning_rate": 4.3665768194070085e-05,
+      "loss": 1.1759567260742188,
+      "step": 244
+    },
+    {
+      "epoch": 0.10614886731391586,
+      "grad_norm": 0.5906805992126465,
+      "learning_rate": 4.402515723270441e-05,
+      "loss": 1.148414969444275,
+      "step": 246
+    },
+    {
+      "epoch": 0.1070118662351672,
+      "grad_norm": 0.5382888913154602,
+      "learning_rate": 4.438454627133873e-05,
+      "loss": 1.0749616622924805,
+      "step": 248
+    },
+    {
+      "epoch": 0.10787486515641856,
+      "grad_norm": 0.6185492873191833,
+      "learning_rate": 4.474393530997305e-05,
+      "loss": 1.2235801219940186,
+      "step": 250
+    },
+    {
+      "epoch": 0.1087378640776699,
+      "grad_norm": 0.5981597900390625,
+      "learning_rate": 4.5103324348607365e-05,
+      "loss": 1.1390639543533325,
+      "step": 252
+    },
+    {
+      "epoch": 0.10960086299892124,
+      "grad_norm": 0.5664694905281067,
+      "learning_rate": 4.546271338724169e-05,
+      "loss": 1.171774983406067,
+      "step": 254
+    },
+    {
+      "epoch": 0.1104638619201726,
+      "grad_norm": 0.7071851491928101,
+      "learning_rate": 4.582210242587601e-05,
+      "loss": 1.1704237461090088,
+      "step": 256
+    },
+    {
+      "epoch": 0.11132686084142394,
+      "grad_norm": 0.5815614461898804,
+      "learning_rate": 4.6181491464510334e-05,
+      "loss": 1.0619677305221558,
+      "step": 258
+    },
+    {
+      "epoch": 0.1121898597626753,
+      "grad_norm": 0.6481915712356567,
+      "learning_rate": 4.654088050314466e-05,
+      "loss": 1.0824390649795532,
+      "step": 260
+    },
+    {
+      "epoch": 0.11305285868392664,
+      "grad_norm": 0.5988591313362122,
+      "learning_rate": 4.690026954177898e-05,
+      "loss": 1.087929606437683,
+      "step": 262
+    },
+    {
+      "epoch": 0.113915857605178,
+      "grad_norm": 0.6545296311378479,
+      "learning_rate": 4.7259658580413304e-05,
+      "loss": 1.0936195850372314,
+      "step": 264
+    },
+    {
+      "epoch": 0.11477885652642934,
+      "grad_norm": 0.5826204419136047,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 1.0433681011199951,
+      "step": 266
+    },
+    {
+      "epoch": 0.11564185544768069,
+      "grad_norm": 0.5907514095306396,
+      "learning_rate": 4.7978436657681944e-05,
+      "loss": 1.0719536542892456,
+      "step": 268
+    },
+    {
+      "epoch": 0.11650485436893204,
+      "grad_norm": 0.524394154548645,
+      "learning_rate": 4.833782569631627e-05,
+      "loss": 1.0231504440307617,
+      "step": 270
+    },
+    {
+      "epoch": 0.11736785329018339,
+      "grad_norm": 0.5472846031188965,
+      "learning_rate": 4.869721473495058e-05,
+      "loss": 0.9905915260314941,
+      "step": 272
+    },
+    {
+      "epoch": 0.11823085221143474,
+      "grad_norm": 0.727922260761261,
+      "learning_rate": 4.9056603773584906e-05,
+      "loss": 1.213677167892456,
+      "step": 274
+    },
+    {
+      "epoch": 0.11909385113268608,
+      "grad_norm": 0.6009684801101685,
+      "learning_rate": 4.941599281221923e-05,
+      "loss": 1.0052144527435303,
+      "step": 276
+    },
+    {
+      "epoch": 0.11995685005393743,
+      "grad_norm": 0.6564669013023376,
+      "learning_rate": 4.977538185085355e-05,
+      "loss": 1.108136773109436,
+      "step": 278
+    },
+    {
+      "epoch": 0.12081984897518878,
+      "grad_norm": 0.650074303150177,
+      "learning_rate": 5.013477088948787e-05,
+      "loss": 0.9700815677642822,
+      "step": 280
+    },
+    {
+      "epoch": 0.12168284789644013,
+      "grad_norm": 0.5772947072982788,
+      "learning_rate": 5.04941599281222e-05,
+      "loss": 1.038031816482544,
+      "step": 282
+    },
+    {
+      "epoch": 0.12254584681769148,
+      "grad_norm": 0.7293002009391785,
+      "learning_rate": 5.0853548966756516e-05,
+      "loss": 1.1063730716705322,
+      "step": 284
+    },
+    {
+      "epoch": 0.12340884573894283,
+      "grad_norm": 0.7937333583831787,
+      "learning_rate": 5.1212938005390846e-05,
+      "loss": 1.128495693206787,
+      "step": 286
+    },
+    {
+      "epoch": 0.12427184466019417,
+      "grad_norm": 0.48499324917793274,
+      "learning_rate": 5.157232704402516e-05,
+      "loss": 0.9438712000846863,
+      "step": 288
+    },
+    {
+      "epoch": 0.12513484358144553,
+      "grad_norm": 0.6010656952857971,
+      "learning_rate": 5.193171608265948e-05,
+      "loss": 1.0872881412506104,
+      "step": 290
+    },
+    {
+      "epoch": 0.12599784250269688,
+      "grad_norm": 0.6240811944007874,
+      "learning_rate": 5.22911051212938e-05,
+      "loss": 1.110992193222046,
+      "step": 292
+    },
+    {
+      "epoch": 0.1268608414239482,
+      "grad_norm": 0.7172768712043762,
+      "learning_rate": 5.265049415992812e-05,
+      "loss": 1.1109752655029297,
+      "step": 294
+    },
+    {
+      "epoch": 0.12772384034519957,
+      "grad_norm": 0.6442400217056274,
+      "learning_rate": 5.300988319856245e-05,
+      "loss": 1.05553138256073,
+      "step": 296
+    },
+    {
+      "epoch": 0.12858683926645093,
+      "grad_norm": 0.7074702382087708,
+      "learning_rate": 5.3369272237196765e-05,
+      "loss": 1.0717648267745972,
+      "step": 298
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "grad_norm": 0.5277591347694397,
+      "learning_rate": 5.3728661275831095e-05,
+      "loss": 0.9777541756629944,
+      "step": 300
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "eval_loss": 1.0977506637573242,
+      "eval_runtime": 662.1728,
+      "eval_samples_per_second": 3.111,
+      "eval_steps_per_second": 3.111,
+      "step": 300
+    },
+    {
+      "epoch": 0.1303128371089536,
+      "grad_norm": 0.7252246737480164,
+      "learning_rate": 5.408805031446541e-05,
+      "loss": 1.075905203819275,
+      "step": 302
+    },
+    {
+      "epoch": 0.13117583603020497,
+      "grad_norm": 0.7003294229507446,
+      "learning_rate": 5.444743935309974e-05,
+      "loss": 1.1117515563964844,
+      "step": 304
+    },
+    {
+      "epoch": 0.13203883495145632,
+      "grad_norm": 0.5878211259841919,
+      "learning_rate": 5.480682839173406e-05,
+      "loss": 1.0289191007614136,
+      "step": 306
+    },
+    {
+      "epoch": 0.13290183387270765,
+      "grad_norm": 0.7133644223213196,
+      "learning_rate": 5.5166217430368374e-05,
+      "loss": 1.0199183225631714,
+      "step": 308
+    },
+    {
+      "epoch": 0.133764832793959,
+      "grad_norm": 0.6098423600196838,
+      "learning_rate": 5.55256064690027e-05,
+      "loss": 1.0132375955581665,
+      "step": 310
+    },
+    {
+      "epoch": 0.13462783171521037,
+      "grad_norm": 0.6386916041374207,
+      "learning_rate": 5.5884995507637014e-05,
+      "loss": 1.1595754623413086,
+      "step": 312
+    },
+    {
+      "epoch": 0.1354908306364617,
+      "grad_norm": 0.6563469767570496,
+      "learning_rate": 5.6244384546271344e-05,
+      "loss": 1.0921307802200317,
+      "step": 314
+    },
+    {
+      "epoch": 0.13635382955771305,
+      "grad_norm": 0.6388015747070312,
+      "learning_rate": 5.660377358490566e-05,
+      "loss": 1.0200815200805664,
+      "step": 316
+    },
+    {
+      "epoch": 0.1372168284789644,
+      "grad_norm": 0.6026274561882019,
+      "learning_rate": 5.696316262353999e-05,
+      "loss": 0.9339485764503479,
+      "step": 318
+    },
+    {
+      "epoch": 0.13807982740021574,
+      "grad_norm": 0.619800865650177,
+      "learning_rate": 5.732255166217431e-05,
+      "loss": 1.0268478393554688,
+      "step": 320
+    },
+    {
+      "epoch": 0.1389428263214671,
+      "grad_norm": 0.5924715399742126,
+      "learning_rate": 5.768194070080862e-05,
+      "loss": 1.1394236087799072,
+      "step": 322
+    },
+    {
+      "epoch": 0.13980582524271845,
+      "grad_norm": 0.6829012036323547,
+      "learning_rate": 5.804132973944295e-05,
+      "loss": 1.002437949180603,
+      "step": 324
+    },
+    {
+      "epoch": 0.1406688241639698,
+      "grad_norm": 0.7012544274330139,
+      "learning_rate": 5.840071877807727e-05,
+      "loss": 1.132503628730774,
+      "step": 326
+    },
+    {
+      "epoch": 0.14153182308522114,
+      "grad_norm": 0.7921599745750427,
+      "learning_rate": 5.876010781671159e-05,
+      "loss": 1.1859129667282104,
+      "step": 328
+    },
+    {
+      "epoch": 0.1423948220064725,
+      "grad_norm": 0.6373353004455566,
+      "learning_rate": 5.9119496855345916e-05,
+      "loss": 1.0896776914596558,
+      "step": 330
+    },
+    {
+      "epoch": 0.14325782092772385,
+      "grad_norm": 0.6174030900001526,
+      "learning_rate": 5.947888589398024e-05,
+      "loss": 1.0691723823547363,
+      "step": 332
+    },
+    {
+      "epoch": 0.14412081984897518,
+      "grad_norm": 0.5110617280006409,
+      "learning_rate": 5.9838274932614556e-05,
+      "loss": 1.0144777297973633,
+      "step": 334
+    },
+    {
+      "epoch": 0.14498381877022654,
+      "grad_norm": 0.5580511093139648,
+      "learning_rate": 6.019766397124887e-05,
+      "loss": 0.9955101609230042,
+      "step": 336
+    },
+    {
+      "epoch": 0.1458468176914779,
+      "grad_norm": 0.6427345275878906,
+      "learning_rate": 6.05570530098832e-05,
+      "loss": 0.9863013625144958,
+      "step": 338
+    },
+    {
+      "epoch": 0.14670981661272922,
+      "grad_norm": 0.7464537024497986,
+      "learning_rate": 6.091644204851752e-05,
+      "loss": 1.0682255029678345,
+      "step": 340
+    },
+    {
+      "epoch": 0.14757281553398058,
+      "grad_norm": 0.599926769733429,
+      "learning_rate": 6.127583108715184e-05,
+      "loss": 1.034083366394043,
+      "step": 342
+    },
+    {
+      "epoch": 0.14843581445523193,
+      "grad_norm": 0.6320257186889648,
+      "learning_rate": 6.163522012578616e-05,
+      "loss": 1.0776089429855347,
+      "step": 344
+    },
+    {
+      "epoch": 0.1492988133764833,
+      "grad_norm": 0.6565091013908386,
+      "learning_rate": 6.199460916442049e-05,
+      "loss": 1.0493087768554688,
+      "step": 346
+    },
+    {
+      "epoch": 0.15016181229773462,
+      "grad_norm": 0.6512171626091003,
+      "learning_rate": 6.23539982030548e-05,
+      "loss": 1.0469218492507935,
+      "step": 348
+    },
+    {
+      "epoch": 0.15102481121898598,
+      "grad_norm": 0.8487282991409302,
+      "learning_rate": 6.271338724168913e-05,
+      "loss": 1.0985081195831299,
+      "step": 350
+    },
+    {
+      "epoch": 0.15188781014023733,
+      "grad_norm": 0.6718961596488953,
+      "learning_rate": 6.307277628032345e-05,
+      "loss": 1.0714176893234253,
+      "step": 352
+    },
+    {
+      "epoch": 0.15275080906148866,
+      "grad_norm": 0.8175088167190552,
+      "learning_rate": 6.343216531895777e-05,
+      "loss": 1.0599322319030762,
+      "step": 354
+    },
+    {
+      "epoch": 0.15361380798274002,
+      "grad_norm": 0.6359215378761292,
+      "learning_rate": 6.37915543575921e-05,
+      "loss": 0.9268131256103516,
+      "step": 356
+    },
+    {
+      "epoch": 0.15447680690399138,
+      "grad_norm": 0.6423866748809814,
+      "learning_rate": 6.415094339622641e-05,
+      "loss": 0.9838354587554932,
+      "step": 358
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "grad_norm": 0.6496716737747192,
+      "learning_rate": 6.451033243486074e-05,
+      "loss": 1.048566460609436,
+      "step": 360
+    },
+    {
+      "epoch": 0.15620280474649406,
+      "grad_norm": 0.6536920666694641,
+      "learning_rate": 6.486972147349506e-05,
+      "loss": 1.0910537242889404,
+      "step": 362
+    },
+    {
+      "epoch": 0.15706580366774542,
+      "grad_norm": 0.5832068920135498,
+      "learning_rate": 6.522911051212939e-05,
+      "loss": 0.9971448183059692,
+      "step": 364
+    },
+    {
+      "epoch": 0.15792880258899678,
+      "grad_norm": 0.6647719144821167,
+      "learning_rate": 6.558849955076371e-05,
+      "loss": 1.0496708154678345,
+      "step": 366
+    },
+    {
+      "epoch": 0.1587918015102481,
+      "grad_norm": 0.623252809047699,
+      "learning_rate": 6.594788858939802e-05,
+      "loss": 0.955894410610199,
+      "step": 368
+    },
+    {
+      "epoch": 0.15965480043149946,
+      "grad_norm": 0.6311860084533691,
+      "learning_rate": 6.630727762803235e-05,
+      "loss": 1.1304032802581787,
+      "step": 370
+    },
+    {
+      "epoch": 0.16051779935275082,
+      "grad_norm": 0.5306481122970581,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.8746405243873596,
+      "step": 372
+    },
+    {
+      "epoch": 0.16138079827400215,
+      "grad_norm": 0.6249631643295288,
+      "learning_rate": 6.7026055705301e-05,
+      "loss": 0.9104986786842346,
+      "step": 374
+    },
+    {
+      "epoch": 0.1622437971952535,
+      "grad_norm": 0.6243219971656799,
+      "learning_rate": 6.738544474393532e-05,
+      "loss": 1.043666124343872,
+      "step": 376
+    },
+    {
+      "epoch": 0.16310679611650486,
+      "grad_norm": 0.6833282113075256,
+      "learning_rate": 6.774483378256963e-05,
+      "loss": 1.0504906177520752,
+      "step": 378
+    },
+    {
+      "epoch": 0.16396979503775622,
+      "grad_norm": 0.7124452590942383,
+      "learning_rate": 6.810422282120395e-05,
+      "loss": 1.0608166456222534,
+      "step": 380
+    },
+    {
+      "epoch": 0.16483279395900755,
+      "grad_norm": 0.7520908117294312,
+      "learning_rate": 6.846361185983828e-05,
+      "loss": 1.1653732061386108,
+      "step": 382
+    },
+    {
+      "epoch": 0.1656957928802589,
+      "grad_norm": 0.7121814489364624,
+      "learning_rate": 6.88230008984726e-05,
+      "loss": 1.0626367330551147,
+      "step": 384
+    },
+    {
+      "epoch": 0.16655879180151026,
+      "grad_norm": 0.6825008988380432,
+      "learning_rate": 6.918238993710691e-05,
+      "loss": 1.012121319770813,
+      "step": 386
+    },
+    {
+      "epoch": 0.1674217907227616,
+      "grad_norm": 0.4922940135002136,
+      "learning_rate": 6.954177897574124e-05,
+      "loss": 1.0576211214065552,
+      "step": 388
+    },
+    {
+      "epoch": 0.16828478964401294,
+      "grad_norm": 0.6122089624404907,
+      "learning_rate": 6.990116801437556e-05,
+      "loss": 1.03916597366333,
+      "step": 390
+    },
+    {
+      "epoch": 0.1691477885652643,
+      "grad_norm": 0.6348981261253357,
+      "learning_rate": 7.026055705300989e-05,
+      "loss": 1.17647123336792,
+      "step": 392
+    },
+    {
+      "epoch": 0.17001078748651563,
+      "grad_norm": 0.6205878257751465,
+      "learning_rate": 7.06199460916442e-05,
+      "loss": 0.9095983505249023,
+      "step": 394
+    },
+    {
+      "epoch": 0.170873786407767,
+      "grad_norm": 0.61506187915802,
+      "learning_rate": 7.097933513027853e-05,
+      "loss": 1.082506775856018,
+      "step": 396
+    },
+    {
+      "epoch": 0.17173678532901834,
+      "grad_norm": 0.6481751799583435,
+      "learning_rate": 7.133872416891285e-05,
+      "loss": 1.0716280937194824,
+      "step": 398
+    },
+    {
+      "epoch": 0.1725997842502697,
+      "grad_norm": 0.4871014952659607,
+      "learning_rate": 7.169811320754717e-05,
+      "loss": 0.9616814851760864,
+      "step": 400
+    },
+    {
+      "epoch": 0.1725997842502697,
+      "eval_loss": 1.0649415254592896,
+      "eval_runtime": 668.6025,
+      "eval_samples_per_second": 3.081,
+      "eval_steps_per_second": 3.081,
+      "step": 400
+    },
+    {
+      "epoch": 0.17346278317152103,
+      "grad_norm": 0.5680040121078491,
+      "learning_rate": 7.20575022461815e-05,
+      "loss": 1.0475050210952759,
+      "step": 402
+    },
+    {
+      "epoch": 0.17432578209277239,
+      "grad_norm": 0.6417813897132874,
+      "learning_rate": 7.241689128481581e-05,
+      "loss": 0.9851161241531372,
+      "step": 404
+    },
+    {
+      "epoch": 0.17518878101402374,
+      "grad_norm": 0.6600468158721924,
+      "learning_rate": 7.277628032345014e-05,
+      "loss": 1.013339638710022,
+      "step": 406
+    },
+    {
+      "epoch": 0.17605177993527507,
+      "grad_norm": 0.6733932495117188,
+      "learning_rate": 7.313566936208446e-05,
+      "loss": 0.9346804022789001,
+      "step": 408
+    },
+    {
+      "epoch": 0.17691477885652643,
+      "grad_norm": 0.6812151074409485,
+      "learning_rate": 7.349505840071879e-05,
+      "loss": 0.9890368580818176,
+      "step": 410
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.6380394697189331,
+      "learning_rate": 7.385444743935311e-05,
+      "loss": 0.8787848949432373,
+      "step": 412
+    },
+    {
+      "epoch": 0.1786407766990291,
+      "grad_norm": 0.6004905700683594,
+      "learning_rate": 7.421383647798742e-05,
+      "loss": 1.0235728025436401,
+      "step": 414
+    },
+    {
+      "epoch": 0.17950377562028047,
+      "grad_norm": 0.6569193005561829,
+      "learning_rate": 7.457322551662175e-05,
+      "loss": 0.9972385168075562,
+      "step": 416
+    },
+    {
+      "epoch": 0.18036677454153183,
+      "grad_norm": 0.6761631369590759,
+      "learning_rate": 7.493261455525607e-05,
+      "loss": 0.9593698382377625,
+      "step": 418
+    },
+    {
+      "epoch": 0.18122977346278318,
+      "grad_norm": 0.7328561544418335,
+      "learning_rate": 7.529200359389039e-05,
+      "loss": 1.0426853895187378,
+      "step": 420
+    },
+    {
+      "epoch": 0.1820927723840345,
+      "grad_norm": 0.6256070137023926,
+      "learning_rate": 7.56513926325247e-05,
+      "loss": 0.9608182311058044,
+      "step": 422
+    },
+    {
+      "epoch": 0.18295577130528587,
+      "grad_norm": 1.2549844980239868,
+      "learning_rate": 7.601078167115903e-05,
+      "loss": 1.0162668228149414,
+      "step": 424
+    },
+    {
+      "epoch": 0.18381877022653723,
+      "grad_norm": 0.6751510500907898,
+      "learning_rate": 7.637017070979335e-05,
+      "loss": 1.130725383758545,
+      "step": 426
+    },
+    {
+      "epoch": 0.18468176914778855,
+      "grad_norm": 0.7029808163642883,
+      "learning_rate": 7.672955974842768e-05,
+      "loss": 1.0384817123413086,
+      "step": 428
+    },
+    {
+      "epoch": 0.1855447680690399,
+      "grad_norm": 0.644353449344635,
+      "learning_rate": 7.7088948787062e-05,
+      "loss": 1.017020344734192,
+      "step": 430
+    },
+    {
+      "epoch": 0.18640776699029127,
+      "grad_norm": 0.6784916520118713,
+      "learning_rate": 7.744833782569631e-05,
+      "loss": 1.005354404449463,
+      "step": 432
+    },
+    {
+      "epoch": 0.1872707659115426,
+      "grad_norm": 0.5989449620246887,
+      "learning_rate": 7.780772686433064e-05,
+      "loss": 1.026848316192627,
+      "step": 434
+    },
+    {
+      "epoch": 0.18813376483279395,
+      "grad_norm": 0.6502639651298523,
+      "learning_rate": 7.816711590296496e-05,
+      "loss": 0.9891080856323242,
+      "step": 436
+    },
+    {
+      "epoch": 0.1889967637540453,
+      "grad_norm": 0.6176205277442932,
+      "learning_rate": 7.852650494159929e-05,
+      "loss": 0.966316819190979,
+      "step": 438
+    },
+    {
+      "epoch": 0.18985976267529667,
+      "grad_norm": 0.6801626086235046,
+      "learning_rate": 7.88858939802336e-05,
+      "loss": 1.123063087463379,
+      "step": 440
+    },
+    {
+      "epoch": 0.190722761596548,
+      "grad_norm": 0.6718618273735046,
+      "learning_rate": 7.924528301886794e-05,
+      "loss": 1.0467073917388916,
+      "step": 442
+    },
+    {
+      "epoch": 0.19158576051779935,
+      "grad_norm": 0.6761009097099304,
+      "learning_rate": 7.960467205750225e-05,
+      "loss": 1.0952889919281006,
+      "step": 444
+    },
+    {
+      "epoch": 0.1924487594390507,
+      "grad_norm": 0.6356327533721924,
+      "learning_rate": 7.996406109613657e-05,
+      "loss": 0.954807698726654,
+      "step": 446
+    },
+    {
+      "epoch": 0.19331175836030204,
+      "grad_norm": 0.6798669695854187,
+      "learning_rate": 8.03234501347709e-05,
+      "loss": 0.9941422343254089,
+      "step": 448
+    },
+    {
+      "epoch": 0.1941747572815534,
+      "grad_norm": 0.6511302590370178,
+      "learning_rate": 8.068283917340521e-05,
+      "loss": 1.0351495742797852,
+      "step": 450
+    },
+    {
+      "epoch": 0.19503775620280475,
+      "grad_norm": 0.6061258912086487,
+      "learning_rate": 8.104222821203954e-05,
+      "loss": 1.00546133518219,
+      "step": 452
+    },
+    {
+      "epoch": 0.1959007551240561,
+      "grad_norm": 0.6278533935546875,
+      "learning_rate": 8.140161725067386e-05,
+      "loss": 1.0778460502624512,
+      "step": 454
+    },
+    {
+      "epoch": 0.19676375404530744,
+      "grad_norm": 0.6866298317909241,
+      "learning_rate": 8.176100628930818e-05,
+      "loss": 1.0344486236572266,
+      "step": 456
+    },
+    {
+      "epoch": 0.1976267529665588,
+      "grad_norm": 0.7338075041770935,
+      "learning_rate": 8.212039532794251e-05,
+      "loss": 1.0663033723831177,
+      "step": 458
+    },
+    {
+      "epoch": 0.19848975188781015,
+      "grad_norm": 0.6811459064483643,
+      "learning_rate": 8.247978436657682e-05,
+      "loss": 0.9665339589118958,
+      "step": 460
+    },
+    {
+      "epoch": 0.19935275080906148,
+      "grad_norm": 0.6779627799987793,
+      "learning_rate": 8.283917340521114e-05,
+      "loss": 1.024712324142456,
+      "step": 462
+    },
+    {
+      "epoch": 0.20021574973031284,
+      "grad_norm": 0.6486892700195312,
+      "learning_rate": 8.319856244384546e-05,
+      "loss": 0.9699305295944214,
+      "step": 464
+    },
+    {
+      "epoch": 0.2010787486515642,
+      "grad_norm": 0.7022278308868408,
+      "learning_rate": 8.355795148247979e-05,
+      "loss": 0.9540432095527649,
+      "step": 466
+    },
+    {
+      "epoch": 0.20194174757281552,
+      "grad_norm": 0.5922990441322327,
+      "learning_rate": 8.39173405211141e-05,
+      "loss": 0.9253339767456055,
+      "step": 468
+    },
+    {
+      "epoch": 0.20280474649406688,
+      "grad_norm": 0.7076792120933533,
+      "learning_rate": 8.427672955974843e-05,
+      "loss": 0.9987741112709045,
+      "step": 470
+    },
+    {
+      "epoch": 0.20366774541531824,
+      "grad_norm": 0.6491380333900452,
+      "learning_rate": 8.463611859838275e-05,
+      "loss": 1.0249329805374146,
+      "step": 472
+    },
+    {
+      "epoch": 0.2045307443365696,
+      "grad_norm": 0.6784211993217468,
+      "learning_rate": 8.499550763701708e-05,
+      "loss": 1.0577133893966675,
+      "step": 474
+    },
+    {
+      "epoch": 0.20539374325782092,
+      "grad_norm": 0.6453303694725037,
+      "learning_rate": 8.53548966756514e-05,
+      "loss": 1.1312458515167236,
+      "step": 476
+    },
+    {
+      "epoch": 0.20625674217907228,
+      "grad_norm": 0.7431377172470093,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 1.0592451095581055,
+      "step": 478
+    },
+    {
+      "epoch": 0.20711974110032363,
+      "grad_norm": 0.6097649931907654,
+      "learning_rate": 8.607367475292004e-05,
+      "loss": 0.9337235689163208,
+      "step": 480
+    },
+    {
+      "epoch": 0.20798274002157496,
+      "grad_norm": 0.5693124532699585,
+      "learning_rate": 8.643306379155436e-05,
+      "loss": 0.9088928699493408,
+      "step": 482
+    },
+    {
+      "epoch": 0.20884573894282632,
+      "grad_norm": 0.7377229332923889,
+      "learning_rate": 8.679245283018869e-05,
+      "loss": 1.0729358196258545,
+      "step": 484
+    },
+    {
+      "epoch": 0.20970873786407768,
+      "grad_norm": 0.7399470210075378,
+      "learning_rate": 8.7151841868823e-05,
+      "loss": 1.0428457260131836,
+      "step": 486
+    },
+    {
+      "epoch": 0.210571736785329,
+      "grad_norm": 0.677052915096283,
+      "learning_rate": 8.751123090745734e-05,
+      "loss": 0.9940266013145447,
+      "step": 488
+    },
+    {
+      "epoch": 0.21143473570658036,
+      "grad_norm": 0.7126721739768982,
+      "learning_rate": 8.787061994609165e-05,
+      "loss": 1.011808156967163,
+      "step": 490
+    },
+    {
+      "epoch": 0.21229773462783172,
+      "grad_norm": 0.6663792729377747,
+      "learning_rate": 8.823000898472597e-05,
+      "loss": 1.0054185390472412,
+      "step": 492
+    },
+    {
+      "epoch": 0.21316073354908308,
+      "grad_norm": 0.6661092042922974,
+      "learning_rate": 8.85893980233603e-05,
+      "loss": 1.0167138576507568,
+      "step": 494
+    },
+    {
+      "epoch": 0.2140237324703344,
+      "grad_norm": 0.6975740194320679,
+      "learning_rate": 8.894878706199461e-05,
+      "loss": 1.1470818519592285,
+      "step": 496
+    },
+    {
+      "epoch": 0.21488673139158576,
+      "grad_norm": 0.6594390869140625,
+      "learning_rate": 8.930817610062893e-05,
+      "loss": 0.9619631171226501,
+      "step": 498
+    },
+    {
+      "epoch": 0.21574973031283712,
+      "grad_norm": 0.7216679453849792,
+      "learning_rate": 8.966756513926325e-05,
+      "loss": 0.9971368312835693,
+      "step": 500
+    },
+    {
+      "epoch": 0.21574973031283712,
+      "eval_loss": 1.0417571067810059,
+      "eval_runtime": 659.3112,
+      "eval_samples_per_second": 3.124,
+      "eval_steps_per_second": 3.124,
+      "step": 500
+    },
+    {
+      "epoch": 0.21661272923408845,
+      "grad_norm": 0.6188210844993591,
+      "learning_rate": 9.002695417789758e-05,
+      "loss": 1.0307213068008423,
+      "step": 502
+    },
+    {
+      "epoch": 0.2174757281553398,
+      "grad_norm": 0.6716445088386536,
+      "learning_rate": 9.03863432165319e-05,
+      "loss": 1.0188794136047363,
+      "step": 504
+    },
+    {
+      "epoch": 0.21833872707659116,
+      "grad_norm": 0.6790863275527954,
+      "learning_rate": 9.074573225516622e-05,
+      "loss": 0.9764845967292786,
+      "step": 506
+    },
+    {
+      "epoch": 0.2192017259978425,
+      "grad_norm": 0.6764960289001465,
+      "learning_rate": 9.110512129380054e-05,
+      "loss": 0.948829174041748,
+      "step": 508
+    },
+    {
+      "epoch": 0.22006472491909385,
+      "grad_norm": 0.6210965514183044,
+      "learning_rate": 9.146451033243486e-05,
+      "loss": 1.008013129234314,
+      "step": 510
+    },
+    {
+      "epoch": 0.2209277238403452,
+      "grad_norm": 0.7739297747612,
+      "learning_rate": 9.182389937106919e-05,
+      "loss": 1.1662557125091553,
+      "step": 512
+    },
+    {
+      "epoch": 0.22179072276159656,
+      "grad_norm": 0.7055562138557434,
+      "learning_rate": 9.21832884097035e-05,
+      "loss": 1.0325161218643188,
+      "step": 514
+    },
+    {
+      "epoch": 0.2226537216828479,
+      "grad_norm": 0.6079210042953491,
+      "learning_rate": 9.254267744833783e-05,
+      "loss": 1.00056791305542,
+      "step": 516
+    },
+    {
+      "epoch": 0.22351672060409924,
+      "grad_norm": 0.5974318981170654,
+      "learning_rate": 9.290206648697215e-05,
+      "loss": 0.9422364234924316,
+      "step": 518
+    },
+    {
+      "epoch": 0.2243797195253506,
+      "grad_norm": 0.5963430404663086,
+      "learning_rate": 9.326145552560648e-05,
+      "loss": 0.936336100101471,
+      "step": 520
+    },
+    {
+      "epoch": 0.22524271844660193,
+      "grad_norm": 0.6823658347129822,
+      "learning_rate": 9.36208445642408e-05,
+      "loss": 1.0538607835769653,
+      "step": 522
+    },
+    {
+      "epoch": 0.2261057173678533,
+      "grad_norm": 0.6409855484962463,
+      "learning_rate": 9.398023360287511e-05,
+      "loss": 1.0483653545379639,
+      "step": 524
+    },
+    {
+      "epoch": 0.22696871628910464,
+      "grad_norm": 0.6867254376411438,
+      "learning_rate": 9.433962264150944e-05,
+      "loss": 0.9668049812316895,
+      "step": 526
+    },
+    {
+      "epoch": 0.227831715210356,
+      "grad_norm": 0.5690792798995972,
+      "learning_rate": 9.469901168014376e-05,
+      "loss": 1.008763313293457,
+      "step": 528
+    },
+    {
+      "epoch": 0.22869471413160733,
+      "grad_norm": 0.5964897274971008,
+      "learning_rate": 9.505840071877809e-05,
+      "loss": 1.0816441774368286,
+      "step": 530
+    },
+    {
+      "epoch": 0.2295577130528587,
+      "grad_norm": 0.627419114112854,
+      "learning_rate": 9.54177897574124e-05,
+      "loss": 0.9265700578689575,
+      "step": 532
+    },
+    {
+      "epoch": 0.23042071197411004,
+      "grad_norm": 0.5862151980400085,
+      "learning_rate": 9.577717879604674e-05,
+      "loss": 0.9804646372795105,
+      "step": 534
+    },
+    {
+      "epoch": 0.23128371089536137,
+      "grad_norm": 0.5573718547821045,
+      "learning_rate": 9.613656783468105e-05,
+      "loss": 0.9627988934516907,
+      "step": 536
+    },
+    {
+      "epoch": 0.23214670981661273,
+      "grad_norm": 0.6705166101455688,
+      "learning_rate": 9.649595687331537e-05,
+      "loss": 1.0012824535369873,
+      "step": 538
+    },
+    {
+      "epoch": 0.23300970873786409,
+      "grad_norm": 0.6251236796379089,
+      "learning_rate": 9.685534591194969e-05,
+      "loss": 0.9568162560462952,
+      "step": 540
+    },
+    {
+      "epoch": 0.23387270765911541,
+      "grad_norm": 0.6466493010520935,
+      "learning_rate": 9.7214734950584e-05,
+      "loss": 1.031549334526062,
+      "step": 542
+    },
+    {
+      "epoch": 0.23473570658036677,
+      "grad_norm": 0.5183866024017334,
+      "learning_rate": 9.757412398921833e-05,
+      "loss": 0.8603643774986267,
+      "step": 544
+    },
+    {
+      "epoch": 0.23559870550161813,
+      "grad_norm": 0.6725775599479675,
+      "learning_rate": 9.793351302785265e-05,
+      "loss": 1.0365077257156372,
+      "step": 546
+    },
+    {
+      "epoch": 0.23646170442286948,
+      "grad_norm": 0.5972357988357544,
+      "learning_rate": 9.829290206648698e-05,
+      "loss": 0.9304701089859009,
+      "step": 548
+    },
+    {
+      "epoch": 0.2373247033441208,
+      "grad_norm": 0.5319957733154297,
+      "learning_rate": 9.86522911051213e-05,
+      "loss": 0.9575805068016052,
+      "step": 550
+    },
+    {
+      "epoch": 0.23818770226537217,
+      "grad_norm": 0.6502835750579834,
+      "learning_rate": 9.901168014375562e-05,
+      "loss": 1.0307214260101318,
+      "step": 552
+    },
+    {
+      "epoch": 0.23905070118662353,
+      "grad_norm": 0.6734047532081604,
+      "learning_rate": 9.937106918238994e-05,
+      "loss": 1.05185067653656,
+      "step": 554
+    },
+    {
+      "epoch": 0.23991370010787486,
+      "grad_norm": 0.5667978525161743,
+      "learning_rate": 9.973045822102426e-05,
+      "loss": 1.0190176963806152,
+      "step": 556
+    },
+    {
+      "epoch": 0.2407766990291262,
+      "grad_norm": 0.6370418667793274,
+      "learning_rate": 0.00010008984725965857,
+      "loss": 1.076182246208191,
+      "step": 558
+    },
+    {
+      "epoch": 0.24163969795037757,
+      "grad_norm": 0.689719021320343,
+      "learning_rate": 0.0001004492362982929,
+      "loss": 1.0408724546432495,
+      "step": 560
+    },
+    {
+      "epoch": 0.2425026968716289,
+      "grad_norm": 0.6304254531860352,
+      "learning_rate": 0.00010080862533692723,
+      "loss": 0.9869902729988098,
+      "step": 562
+    },
+    {
+      "epoch": 0.24336569579288025,
+      "grad_norm": 0.6797420382499695,
+      "learning_rate": 0.00010116801437556156,
+      "loss": 1.0198370218276978,
+      "step": 564
+    },
+    {
+      "epoch": 0.2442286947141316,
+      "grad_norm": 0.5993657112121582,
+      "learning_rate": 0.00010152740341419587,
+      "loss": 0.9947441816329956,
+      "step": 566
+    },
+    {
+      "epoch": 0.24509169363538297,
+      "grad_norm": 0.6369836330413818,
+      "learning_rate": 0.0001018867924528302,
+      "loss": 0.9722896814346313,
+      "step": 568
+    },
+    {
+      "epoch": 0.2459546925566343,
+      "grad_norm": 0.6942457556724548,
+      "learning_rate": 0.00010224618149146453,
+      "loss": 0.9716570973396301,
+      "step": 570
+    },
+    {
+      "epoch": 0.24681769147788565,
+      "grad_norm": 0.5403370261192322,
+      "learning_rate": 0.00010260557053009883,
+      "loss": 0.9797524213790894,
+      "step": 572
+    },
+    {
+      "epoch": 0.247680690399137,
+      "grad_norm": 0.5207529067993164,
+      "learning_rate": 0.00010296495956873316,
+      "loss": 0.985367476940155,
+      "step": 574
+    },
+    {
+      "epoch": 0.24854368932038834,
+      "grad_norm": 0.6751103401184082,
+      "learning_rate": 0.00010332434860736748,
+      "loss": 1.075042724609375,
+      "step": 576
+    },
+    {
+      "epoch": 0.2494066882416397,
+      "grad_norm": 0.565331220626831,
+      "learning_rate": 0.0001036837376460018,
+      "loss": 0.9273878335952759,
+      "step": 578
+    },
+    {
+      "epoch": 0.25026968716289105,
+      "grad_norm": 0.6858948469161987,
+      "learning_rate": 0.00010404312668463612,
+      "loss": 0.9872279763221741,
+      "step": 580
+    },
+    {
+      "epoch": 0.2511326860841424,
+      "grad_norm": 0.7091426253318787,
+      "learning_rate": 0.00010440251572327044,
+      "loss": 1.0038671493530273,
+      "step": 582
+    },
+    {
+      "epoch": 0.25199568500539377,
+      "grad_norm": 0.6493771076202393,
+      "learning_rate": 0.00010476190476190477,
+      "loss": 1.0109868049621582,
+      "step": 584
+    },
+    {
+      "epoch": 0.25285868392664507,
+      "grad_norm": 0.6107586622238159,
+      "learning_rate": 0.00010512129380053907,
+      "loss": 1.0020402669906616,
+      "step": 586
+    },
+    {
+      "epoch": 0.2537216828478964,
+      "grad_norm": 0.6878048181533813,
+      "learning_rate": 0.0001054806828391734,
+      "loss": 0.961039662361145,
+      "step": 588
+    },
+    {
+      "epoch": 0.2545846817691478,
+      "grad_norm": 0.664034903049469,
+      "learning_rate": 0.00010584007187780773,
+      "loss": 0.9725209474563599,
+      "step": 590
+    },
+    {
+      "epoch": 0.25544768069039914,
+      "grad_norm": 0.6399680376052856,
+      "learning_rate": 0.00010619946091644206,
+      "loss": 0.9907437562942505,
+      "step": 592
+    },
+    {
+      "epoch": 0.2563106796116505,
+      "grad_norm": 0.6163286566734314,
+      "learning_rate": 0.00010655884995507636,
+      "loss": 0.9650095701217651,
+      "step": 594
+    },
+    {
+      "epoch": 0.25717367853290185,
+      "grad_norm": 0.6008322238922119,
+      "learning_rate": 0.0001069182389937107,
+      "loss": 1.0102758407592773,
+      "step": 596
+    },
+    {
+      "epoch": 0.2580366774541532,
+      "grad_norm": 0.6752071380615234,
+      "learning_rate": 0.00010727762803234502,
+      "loss": 0.9101885557174683,
+      "step": 598
+    },
+    {
+      "epoch": 0.2588996763754045,
+      "grad_norm": 0.6789175868034363,
+      "learning_rate": 0.00010763701707097935,
+      "loss": 1.0461398363113403,
+      "step": 600
+    },
+    {
+      "epoch": 0.2588996763754045,
+      "eval_loss": 1.021111011505127,
+      "eval_runtime": 648.1611,
+      "eval_samples_per_second": 3.178,
+      "eval_steps_per_second": 3.178,
+      "step": 600
+    },
+    {
+      "epoch": 0.25976267529665586,
+      "grad_norm": 0.5660730600357056,
+      "learning_rate": 0.00010799640610961366,
+      "loss": 0.9582418203353882,
+      "step": 602
+    },
+    {
+      "epoch": 0.2606256742179072,
+      "grad_norm": 0.6726544499397278,
+      "learning_rate": 0.00010835579514824799,
+      "loss": 1.0763746500015259,
+      "step": 604
+    },
+    {
+      "epoch": 0.2614886731391586,
+      "grad_norm": 0.6068508625030518,
+      "learning_rate": 0.00010871518418688232,
+      "loss": 1.0432032346725464,
+      "step": 606
+    },
+    {
+      "epoch": 0.26235167206040994,
+      "grad_norm": 0.5731637477874756,
+      "learning_rate": 0.00010907457322551662,
+      "loss": 0.9830516576766968,
+      "step": 608
+    },
+    {
+      "epoch": 0.2632146709816613,
+      "grad_norm": 0.6777567267417908,
+      "learning_rate": 0.00010943396226415095,
+      "loss": 1.0442042350769043,
+      "step": 610
+    },
+    {
+      "epoch": 0.26407766990291265,
+      "grad_norm": 0.6372506618499756,
+      "learning_rate": 0.00010979335130278528,
+      "loss": 1.0001944303512573,
+      "step": 612
+    },
+    {
+      "epoch": 0.26494066882416395,
+      "grad_norm": 0.6606221795082092,
+      "learning_rate": 0.0001101527403414196,
+      "loss": 1.035884141921997,
+      "step": 614
+    },
+    {
+      "epoch": 0.2658036677454153,
+      "grad_norm": 0.6083229780197144,
+      "learning_rate": 0.00011051212938005391,
+      "loss": 0.9403397440910339,
+      "step": 616
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.6318517923355103,
+      "learning_rate": 0.00011087151841868823,
+      "loss": 0.9274454116821289,
+      "step": 618
+    },
+    {
+      "epoch": 0.267529665587918,
+      "grad_norm": 0.628190279006958,
+      "learning_rate": 0.00011123090745732256,
+      "loss": 0.9883754253387451,
+      "step": 620
+    },
+    {
+      "epoch": 0.2683926645091694,
+      "grad_norm": 0.5961961150169373,
+      "learning_rate": 0.00011159029649595688,
+      "loss": 1.0317535400390625,
+      "step": 622
+    },
+    {
+      "epoch": 0.26925566343042073,
+      "grad_norm": 0.5995341539382935,
+      "learning_rate": 0.00011194968553459119,
+      "loss": 0.9776126742362976,
+      "step": 624
+    },
+    {
+      "epoch": 0.27011866235167203,
+      "grad_norm": 0.6639334559440613,
+      "learning_rate": 0.00011230907457322552,
+      "loss": 1.0112378597259521,
+      "step": 626
+    },
+    {
+      "epoch": 0.2709816612729234,
+      "grad_norm": 0.6348621249198914,
+      "learning_rate": 0.00011266846361185985,
+      "loss": 1.0553804636001587,
+      "step": 628
+    },
+    {
+      "epoch": 0.27184466019417475,
+      "grad_norm": 0.5929805040359497,
+      "learning_rate": 0.00011302785265049416,
+      "loss": 1.025888442993164,
+      "step": 630
+    },
+    {
+      "epoch": 0.2727076591154261,
+      "grad_norm": 0.6052366495132446,
+      "learning_rate": 0.00011338724168912849,
+      "loss": 1.02956223487854,
+      "step": 632
+    },
+    {
+      "epoch": 0.27357065803667746,
+      "grad_norm": 0.6494882106781006,
+      "learning_rate": 0.00011374663072776282,
+      "loss": 0.989752471446991,
+      "step": 634
+    },
+    {
+      "epoch": 0.2744336569579288,
+      "grad_norm": 0.6005767583847046,
+      "learning_rate": 0.00011410601976639712,
+      "loss": 1.0030683279037476,
+      "step": 636
+    },
+    {
+      "epoch": 0.2752966558791802,
+      "grad_norm": 0.6478356122970581,
+      "learning_rate": 0.00011446540880503145,
+      "loss": 1.002000093460083,
+      "step": 638
+    },
+    {
+      "epoch": 0.2761596548004315,
+      "grad_norm": 0.5804725289344788,
+      "learning_rate": 0.00011482479784366578,
+      "loss": 0.9807654023170471,
+      "step": 640
+    },
+    {
+      "epoch": 0.27702265372168283,
+      "grad_norm": 0.632530689239502,
+      "learning_rate": 0.00011518418688230011,
+      "loss": 0.9841892123222351,
+      "step": 642
+    },
+    {
+      "epoch": 0.2778856526429342,
+      "grad_norm": 0.5340113639831543,
+      "learning_rate": 0.00011554357592093441,
+      "loss": 0.8902478814125061,
+      "step": 644
+    },
+    {
+      "epoch": 0.27874865156418555,
+      "grad_norm": 0.5901665091514587,
+      "learning_rate": 0.00011590296495956874,
+      "loss": 0.9019404649734497,
+      "step": 646
+    },
+    {
+      "epoch": 0.2796116504854369,
+      "grad_norm": 0.666589617729187,
+      "learning_rate": 0.00011626235399820307,
+      "loss": 0.9384423494338989,
+      "step": 648
+    },
+    {
+      "epoch": 0.28047464940668826,
+      "grad_norm": 0.7000334858894348,
+      "learning_rate": 0.00011662174303683737,
+      "loss": 1.0666629076004028,
+      "step": 650
+    },
+    {
+      "epoch": 0.2813376483279396,
+      "grad_norm": 0.663663923740387,
+      "learning_rate": 0.0001169811320754717,
+      "loss": 1.000019907951355,
+      "step": 652
+    },
+    {
+      "epoch": 0.2822006472491909,
+      "grad_norm": 0.6097694039344788,
+      "learning_rate": 0.00011734052111410603,
+      "loss": 0.9450293183326721,
+      "step": 654
+    },
+    {
+      "epoch": 0.2830636461704423,
+      "grad_norm": 0.6130967140197754,
+      "learning_rate": 0.00011769991015274035,
+      "loss": 0.9480894207954407,
+      "step": 656
+    },
+    {
+      "epoch": 0.28392664509169363,
+      "grad_norm": 0.7091249227523804,
+      "learning_rate": 0.00011805929919137467,
+      "loss": 1.1377143859863281,
+      "step": 658
+    },
+    {
+      "epoch": 0.284789644012945,
+      "grad_norm": 0.6556766629219055,
+      "learning_rate": 0.00011841868823000898,
+      "loss": 0.9421243667602539,
+      "step": 660
+    },
+    {
+      "epoch": 0.28565264293419634,
+      "grad_norm": 0.6682968735694885,
+      "learning_rate": 0.00011877807726864331,
+      "loss": 0.9726828336715698,
+      "step": 662
+    },
+    {
+      "epoch": 0.2865156418554477,
+      "grad_norm": 0.5224708914756775,
+      "learning_rate": 0.00011913746630727762,
+      "loss": 0.8996511697769165,
+      "step": 664
+    },
+    {
+      "epoch": 0.287378640776699,
+      "grad_norm": 0.5914195775985718,
+      "learning_rate": 0.00011949685534591195,
+      "loss": 0.9679517149925232,
+      "step": 666
+    },
+    {
+      "epoch": 0.28824163969795036,
+      "grad_norm": 0.6175519824028015,
+      "learning_rate": 0.00011985624438454628,
+      "loss": 0.8743209838867188,
+      "step": 668
+    },
+    {
+      "epoch": 0.2891046386192017,
+      "grad_norm": 0.6019226312637329,
+      "learning_rate": 0.0001202156334231806,
+      "loss": 0.9741992354393005,
+      "step": 670
+    },
+    {
+      "epoch": 0.28996763754045307,
+      "grad_norm": 0.6080542206764221,
+      "learning_rate": 0.00012057502246181491,
+      "loss": 0.9516472816467285,
+      "step": 672
+    },
+    {
+      "epoch": 0.29083063646170443,
+      "grad_norm": 0.5885615944862366,
+      "learning_rate": 0.00012093441150044924,
+      "loss": 1.122761607170105,
+      "step": 674
+    },
+    {
+      "epoch": 0.2916936353829558,
+      "grad_norm": 0.6635209918022156,
+      "learning_rate": 0.00012129380053908357,
+      "loss": 1.0105189085006714,
+      "step": 676
+    },
+    {
+      "epoch": 0.29255663430420714,
+      "grad_norm": 0.5805009007453918,
+      "learning_rate": 0.0001216531895777179,
+      "loss": 0.906292200088501,
+      "step": 678
+    },
+    {
+      "epoch": 0.29341963322545844,
+      "grad_norm": 0.5980029702186584,
+      "learning_rate": 0.0001220125786163522,
+      "loss": 1.009568691253662,
+      "step": 680
+    },
+    {
+      "epoch": 0.2942826321467098,
+      "grad_norm": 0.6797705292701721,
+      "learning_rate": 0.00012237196765498652,
+      "loss": 1.0373667478561401,
+      "step": 682
+    },
+    {
+      "epoch": 0.29514563106796116,
+      "grad_norm": 0.6280547976493835,
+      "learning_rate": 0.00012273135669362085,
+      "loss": 0.9758188724517822,
+      "step": 684
+    },
+    {
+      "epoch": 0.2960086299892125,
+      "grad_norm": 0.511608898639679,
+      "learning_rate": 0.00012309074573225515,
+      "loss": 0.9111692905426025,
+      "step": 686
+    },
+    {
+      "epoch": 0.29687162891046387,
+      "grad_norm": 0.5781835317611694,
+      "learning_rate": 0.00012345013477088948,
+      "loss": 0.8865921497344971,
+      "step": 688
+    },
+    {
+      "epoch": 0.2977346278317152,
+      "grad_norm": 0.6514166593551636,
+      "learning_rate": 0.0001238095238095238,
+      "loss": 0.9768189191818237,
+      "step": 690
+    },
+    {
+      "epoch": 0.2985976267529666,
+      "grad_norm": 0.6109189987182617,
+      "learning_rate": 0.00012416891284815814,
+      "loss": 0.9991607069969177,
+      "step": 692
+    },
+    {
+      "epoch": 0.2994606256742179,
+      "grad_norm": 0.6598902344703674,
+      "learning_rate": 0.00012452830188679244,
+      "loss": 0.9548360705375671,
+      "step": 694
+    },
+    {
+      "epoch": 0.30032362459546924,
+      "grad_norm": 0.5633156895637512,
+      "learning_rate": 0.00012488769092542677,
+      "loss": 0.992988109588623,
+      "step": 696
+    },
+    {
+      "epoch": 0.3011866235167206,
+      "grad_norm": 0.6098802089691162,
+      "learning_rate": 0.0001252470799640611,
+      "loss": 0.9709890484809875,
+      "step": 698
+    },
+    {
+      "epoch": 0.30204962243797195,
+      "grad_norm": 0.6197102665901184,
+      "learning_rate": 0.0001256064690026954,
+      "loss": 1.018282175064087,
+      "step": 700
+    },
+    {
+      "epoch": 0.30204962243797195,
+      "eval_loss": 1.0030721426010132,
+      "eval_runtime": 655.4533,
+      "eval_samples_per_second": 3.143,
+      "eval_steps_per_second": 3.143,
+      "step": 700
+    },
+    {
+      "epoch": 0.3029126213592233,
+      "grad_norm": 0.5817480683326721,
+      "learning_rate": 0.00012596585804132974,
+      "loss": 0.9147283434867859,
+      "step": 702
+    },
+    {
+      "epoch": 0.30377562028047467,
+      "grad_norm": 0.5976696014404297,
+      "learning_rate": 0.00012632524707996407,
+      "loss": 0.9318362474441528,
+      "step": 704
+    },
+    {
+      "epoch": 0.304638619201726,
+      "grad_norm": 0.6389723420143127,
+      "learning_rate": 0.0001266846361185984,
+      "loss": 0.9500927925109863,
+      "step": 706
+    },
+    {
+      "epoch": 0.3055016181229773,
+      "grad_norm": 0.6485719084739685,
+      "learning_rate": 0.0001270440251572327,
+      "loss": 1.0271424055099487,
+      "step": 708
+    },
+    {
+      "epoch": 0.3063646170442287,
+      "grad_norm": 0.5802455544471741,
+      "learning_rate": 0.00012740341419586703,
+      "loss": 0.9781906008720398,
+      "step": 710
+    },
+    {
+      "epoch": 0.30722761596548004,
+      "grad_norm": 0.6359356641769409,
+      "learning_rate": 0.00012776280323450136,
+      "loss": 1.0195324420928955,
+      "step": 712
+    },
+    {
+      "epoch": 0.3080906148867314,
+      "grad_norm": 0.5975426435470581,
+      "learning_rate": 0.00012812219227313566,
+      "loss": 0.9250738024711609,
+      "step": 714
+    },
+    {
+      "epoch": 0.30895361380798275,
+      "grad_norm": 0.643110454082489,
+      "learning_rate": 0.00012848158131177,
+      "loss": 0.9888015985488892,
+      "step": 716
+    },
+    {
+      "epoch": 0.3098166127292341,
+      "grad_norm": 0.6043205261230469,
+      "learning_rate": 0.00012884097035040432,
+      "loss": 0.9709514379501343,
+      "step": 718
+    },
+    {
+      "epoch": 0.3106796116504854,
+      "grad_norm": 0.5687094926834106,
+      "learning_rate": 0.00012920035938903865,
+      "loss": 1.0272964239120483,
+      "step": 720
+    },
+    {
+      "epoch": 0.31154261057173677,
+      "grad_norm": 0.5688400864601135,
+      "learning_rate": 0.00012955974842767296,
+      "loss": 0.9370370507240295,
+      "step": 722
+    },
+    {
+      "epoch": 0.3124056094929881,
+      "grad_norm": 0.5610610246658325,
+      "learning_rate": 0.00012991913746630729,
+      "loss": 0.9535608291625977,
+      "step": 724
+    },
+    {
+      "epoch": 0.3132686084142395,
+      "grad_norm": 0.6338257193565369,
+      "learning_rate": 0.00013027852650494162,
+      "loss": 1.0188907384872437,
+      "step": 726
+    },
+    {
+      "epoch": 0.31413160733549084,
+      "grad_norm": 0.5365633368492126,
+      "learning_rate": 0.00013063791554357592,
+      "loss": 0.9253716468811035,
+      "step": 728
+    },
+    {
+      "epoch": 0.3149946062567422,
+      "grad_norm": 0.5599163174629211,
+      "learning_rate": 0.00013099730458221025,
+      "loss": 0.8941492438316345,
+      "step": 730
+    },
+    {
+      "epoch": 0.31585760517799355,
+      "grad_norm": 0.6059780716896057,
+      "learning_rate": 0.00013135669362084458,
+      "loss": 0.9831459522247314,
+      "step": 732
+    },
+    {
+      "epoch": 0.31672060409924485,
+      "grad_norm": 0.5596494078636169,
+      "learning_rate": 0.0001317160826594789,
+      "loss": 0.9332310557365417,
+      "step": 734
+    },
+    {
+      "epoch": 0.3175836030204962,
+      "grad_norm": 0.5618010759353638,
+      "learning_rate": 0.0001320754716981132,
+      "loss": 0.9082580208778381,
+      "step": 736
+    },
+    {
+      "epoch": 0.31844660194174756,
+      "grad_norm": 0.6412109732627869,
+      "learning_rate": 0.00013243486073674754,
+      "loss": 1.008690357208252,
+      "step": 738
+    },
+    {
+      "epoch": 0.3193096008629989,
+      "grad_norm": 0.5742355585098267,
+      "learning_rate": 0.00013279424977538187,
+      "loss": 0.9597798585891724,
+      "step": 740
+    },
+    {
+      "epoch": 0.3201725997842503,
+      "grad_norm": 0.6470226645469666,
+      "learning_rate": 0.00013315363881401617,
+      "loss": 0.989331841468811,
+      "step": 742
+    },
+    {
+      "epoch": 0.32103559870550163,
+      "grad_norm": 0.5598039031028748,
+      "learning_rate": 0.0001335130278526505,
+      "loss": 0.8677343130111694,
+      "step": 744
+    },
+    {
+      "epoch": 0.321898597626753,
+      "grad_norm": 0.5441372990608215,
+      "learning_rate": 0.00013387241689128483,
+      "loss": 0.9462730288505554,
+      "step": 746
+    },
+    {
+      "epoch": 0.3227615965480043,
+      "grad_norm": 0.5858626365661621,
+      "learning_rate": 0.00013423180592991916,
+      "loss": 0.994694173336029,
+      "step": 748
+    },
+    {
+      "epoch": 0.32362459546925565,
+      "grad_norm": 0.511372447013855,
+      "learning_rate": 0.00013459119496855347,
+      "loss": 0.9387269616127014,
+      "step": 750
+    },
+    {
+      "epoch": 0.324487594390507,
+      "grad_norm": 0.47798457741737366,
+      "learning_rate": 0.0001349505840071878,
+      "loss": 0.9473881721496582,
+      "step": 752
+    },
+    {
+      "epoch": 0.32535059331175836,
+      "grad_norm": 0.5907022953033447,
+      "learning_rate": 0.0001353099730458221,
+      "loss": 0.9375183582305908,
+      "step": 754
+    },
+    {
+      "epoch": 0.3262135922330097,
+      "grad_norm": 0.618733286857605,
+      "learning_rate": 0.00013566936208445643,
+      "loss": 1.028738260269165,
+      "step": 756
+    },
+    {
+      "epoch": 0.3270765911542611,
+      "grad_norm": 0.5234512090682983,
+      "learning_rate": 0.00013602875112309076,
+      "loss": 0.9420192241668701,
+      "step": 758
+    },
+    {
+      "epoch": 0.32793959007551243,
+      "grad_norm": 0.7036319971084595,
+      "learning_rate": 0.00013638814016172506,
+      "loss": 1.0252270698547363,
+      "step": 760
+    },
+    {
+      "epoch": 0.32880258899676373,
+      "grad_norm": 0.5543172359466553,
+      "learning_rate": 0.0001367475292003594,
+      "loss": 0.8453778028488159,
+      "step": 762
+    },
+    {
+      "epoch": 0.3296655879180151,
+      "grad_norm": 0.5438711643218994,
+      "learning_rate": 0.0001371069182389937,
+      "loss": 0.8659937977790833,
+      "step": 764
+    },
+    {
+      "epoch": 0.33052858683926645,
+      "grad_norm": 0.6390914916992188,
+      "learning_rate": 0.00013746630727762803,
+      "loss": 1.038142442703247,
+      "step": 766
+    },
+    {
+      "epoch": 0.3313915857605178,
+      "grad_norm": 0.50070720911026,
+      "learning_rate": 0.00013782569631626236,
+      "loss": 0.899932861328125,
+      "step": 768
+    },
+    {
+      "epoch": 0.33225458468176916,
+      "grad_norm": 0.5982286334037781,
+      "learning_rate": 0.00013818508535489669,
+      "loss": 0.9712884426116943,
+      "step": 770
+    },
+    {
+      "epoch": 0.3331175836030205,
+      "grad_norm": 0.6588822603225708,
+      "learning_rate": 0.000138544474393531,
+      "loss": 0.9427542686462402,
+      "step": 772
+    },
+    {
+      "epoch": 0.3339805825242718,
+      "grad_norm": 0.6022042632102966,
+      "learning_rate": 0.00013890386343216532,
+      "loss": 0.8961561918258667,
+      "step": 774
+    },
+    {
+      "epoch": 0.3348435814455232,
+      "grad_norm": 0.6595642566680908,
+      "learning_rate": 0.00013926325247079965,
+      "loss": 0.9525937438011169,
+      "step": 776
+    },
+    {
+      "epoch": 0.33570658036677453,
+      "grad_norm": 0.5210421681404114,
+      "learning_rate": 0.00013962264150943395,
+      "loss": 0.9218845367431641,
+      "step": 778
+    },
+    {
+      "epoch": 0.3365695792880259,
+      "grad_norm": 0.549669623374939,
+      "learning_rate": 0.00013998203054806828,
+      "loss": 0.877951443195343,
+      "step": 780
+    },
+    {
+      "epoch": 0.33743257820927725,
+      "grad_norm": 0.5360157489776611,
+      "learning_rate": 0.0001403414195867026,
+      "loss": 0.8670064210891724,
+      "step": 782
+    },
+    {
+      "epoch": 0.3382955771305286,
+      "grad_norm": 0.614734947681427,
+      "learning_rate": 0.00014070080862533694,
+      "loss": 0.9561367630958557,
+      "step": 784
+    },
+    {
+      "epoch": 0.33915857605177996,
+      "grad_norm": 0.5798251628875732,
+      "learning_rate": 0.00014106019766397124,
+      "loss": 0.9132505059242249,
+      "step": 786
+    },
+    {
+      "epoch": 0.34002157497303126,
+      "grad_norm": 0.6267077326774597,
+      "learning_rate": 0.00014141958670260557,
+      "loss": 0.9297707080841064,
+      "step": 788
+    },
+    {
+      "epoch": 0.3408845738942826,
+      "grad_norm": 0.6045349836349487,
+      "learning_rate": 0.0001417789757412399,
+      "loss": 0.9382412433624268,
+      "step": 790
+    },
+    {
+      "epoch": 0.341747572815534,
+      "grad_norm": 0.6125404834747314,
+      "learning_rate": 0.0001421383647798742,
+      "loss": 0.9078555107116699,
+      "step": 792
+    },
+    {
+      "epoch": 0.34261057173678533,
+      "grad_norm": 0.5927051901817322,
+      "learning_rate": 0.00014249775381850854,
+      "loss": 0.899101197719574,
+      "step": 794
+    },
+    {
+      "epoch": 0.3434735706580367,
+      "grad_norm": 0.6315743923187256,
+      "learning_rate": 0.00014285714285714287,
+      "loss": 1.028346300125122,
+      "step": 796
+    },
+    {
+      "epoch": 0.34433656957928804,
+      "grad_norm": 0.549271285533905,
+      "learning_rate": 0.0001432165318957772,
+      "loss": 0.8988189697265625,
+      "step": 798
+    },
+    {
+      "epoch": 0.3451995685005394,
+      "grad_norm": 0.6344245672225952,
+      "learning_rate": 0.0001435759209344115,
+      "loss": 1.0489003658294678,
+      "step": 800
+    },
+    {
+      "epoch": 0.3451995685005394,
+      "eval_loss": 0.9864639639854431,
+      "eval_runtime": 667.3516,
+      "eval_samples_per_second": 3.087,
+      "eval_steps_per_second": 3.087,
+      "step": 800
+    },
+    {
+      "epoch": 0.3460625674217907,
+      "grad_norm": 0.5625309348106384,
+      "learning_rate": 0.00014393530997304583,
+      "loss": 0.8773928284645081,
+      "step": 802
+    },
+    {
+      "epoch": 0.34692556634304206,
+      "grad_norm": 0.5931969285011292,
+      "learning_rate": 0.00014429469901168016,
+      "loss": 0.9116050004959106,
+      "step": 804
+    },
+    {
+      "epoch": 0.3477885652642934,
+      "grad_norm": 0.5189821720123291,
+      "learning_rate": 0.00014465408805031446,
+      "loss": 0.9124425649642944,
+      "step": 806
+    },
+    {
+      "epoch": 0.34865156418554477,
+      "grad_norm": 0.5392254590988159,
+      "learning_rate": 0.0001450134770889488,
+      "loss": 0.9517888426780701,
+      "step": 808
+    },
+    {
+      "epoch": 0.34951456310679613,
+      "grad_norm": 0.5584444999694824,
+      "learning_rate": 0.00014537286612758312,
+      "loss": 0.9947572350502014,
+      "step": 810
+    },
+    {
+      "epoch": 0.3503775620280475,
+      "grad_norm": 0.5188854932785034,
+      "learning_rate": 0.00014573225516621745,
+      "loss": 0.9314022660255432,
+      "step": 812
+    },
+    {
+      "epoch": 0.3512405609492988,
+      "grad_norm": 0.5783659815788269,
+      "learning_rate": 0.00014609164420485176,
+      "loss": 0.9135628938674927,
+      "step": 814
+    },
+    {
+      "epoch": 0.35210355987055014,
+      "grad_norm": 0.550959050655365,
+      "learning_rate": 0.0001464510332434861,
+      "loss": 0.9665075540542603,
+      "step": 816
+    },
+    {
+      "epoch": 0.3529665587918015,
+      "grad_norm": 0.6013346314430237,
+      "learning_rate": 0.00014681042228212042,
+      "loss": 0.9836555123329163,
+      "step": 818
+    },
+    {
+      "epoch": 0.35382955771305286,
+      "grad_norm": 0.49219194054603577,
+      "learning_rate": 0.00014716981132075472,
+      "loss": 0.8900108337402344,
+      "step": 820
+    },
+    {
+      "epoch": 0.3546925566343042,
+      "grad_norm": 0.5517411828041077,
+      "learning_rate": 0.00014752920035938905,
+      "loss": 0.8769304156303406,
+      "step": 822
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.6062695980072021,
+      "learning_rate": 0.00014788858939802338,
+      "loss": 0.9744759202003479,
+      "step": 824
+    },
+    {
+      "epoch": 0.3564185544768069,
+      "grad_norm": 0.5132041573524475,
+      "learning_rate": 0.0001482479784366577,
+      "loss": 0.8875447511672974,
+      "step": 826
+    },
+    {
+      "epoch": 0.3572815533980582,
+      "grad_norm": 0.551799476146698,
+      "learning_rate": 0.000148607367475292,
+      "loss": 0.962710440158844,
+      "step": 828
+    },
+    {
+      "epoch": 0.3581445523193096,
+      "grad_norm": 0.6046625971794128,
+      "learning_rate": 0.00014896675651392634,
+      "loss": 0.8997528553009033,
+      "step": 830
+    },
+    {
+      "epoch": 0.35900755124056094,
+      "grad_norm": 0.560025691986084,
+      "learning_rate": 0.00014932614555256067,
+      "loss": 0.9541417360305786,
+      "step": 832
+    },
+    {
+      "epoch": 0.3598705501618123,
+      "grad_norm": 0.6441047787666321,
+      "learning_rate": 0.00014968553459119498,
+      "loss": 0.907791018486023,
+      "step": 834
+    },
+    {
+      "epoch": 0.36073354908306365,
+      "grad_norm": 0.5636281967163086,
+      "learning_rate": 0.0001500449236298293,
+      "loss": 1.0295937061309814,
+      "step": 836
+    },
+    {
+      "epoch": 0.361596548004315,
+      "grad_norm": 0.5528303384780884,
+      "learning_rate": 0.0001504043126684636,
+      "loss": 0.8875265717506409,
+      "step": 838
+    },
+    {
+      "epoch": 0.36245954692556637,
+      "grad_norm": 0.5345163345336914,
+      "learning_rate": 0.00015076370170709794,
+      "loss": 0.9678915739059448,
+      "step": 840
+    },
+    {
+      "epoch": 0.36332254584681767,
+      "grad_norm": 0.5551225543022156,
+      "learning_rate": 0.00015112309074573224,
+      "loss": 0.9235162734985352,
+      "step": 842
+    },
+    {
+      "epoch": 0.364185544768069,
+      "grad_norm": 0.5131904482841492,
+      "learning_rate": 0.00015148247978436657,
+      "loss": 0.8624292016029358,
+      "step": 844
+    },
+    {
+      "epoch": 0.3650485436893204,
+      "grad_norm": 0.6811004281044006,
+      "learning_rate": 0.0001518418688230009,
+      "loss": 1.0360193252563477,
+      "step": 846
+    },
+    {
+      "epoch": 0.36591154261057174,
+      "grad_norm": 0.6409741640090942,
+      "learning_rate": 0.00015220125786163523,
+      "loss": 0.9254010915756226,
+      "step": 848
+    },
+    {
+      "epoch": 0.3667745415318231,
+      "grad_norm": 0.5534068942070007,
+      "learning_rate": 0.00015256064690026953,
+      "loss": 0.8900630474090576,
+      "step": 850
+    },
+    {
+      "epoch": 0.36763754045307445,
+      "grad_norm": 0.4999487102031708,
+      "learning_rate": 0.00015292003593890386,
+      "loss": 0.88521409034729,
+      "step": 852
+    },
+    {
+      "epoch": 0.3685005393743258,
+      "grad_norm": 0.5805923938751221,
+      "learning_rate": 0.0001532794249775382,
+      "loss": 0.9563921093940735,
+      "step": 854
+    },
+    {
+      "epoch": 0.3693635382955771,
+      "grad_norm": 0.5485470294952393,
+      "learning_rate": 0.0001536388140161725,
+      "loss": 0.8909372687339783,
+      "step": 856
+    },
+    {
+      "epoch": 0.37022653721682847,
+      "grad_norm": 0.5317923426628113,
+      "learning_rate": 0.00015399820305480683,
+      "loss": 0.9145731925964355,
+      "step": 858
+    },
+    {
+      "epoch": 0.3710895361380798,
+      "grad_norm": 0.6073495745658875,
+      "learning_rate": 0.00015435759209344116,
+      "loss": 1.01466965675354,
+      "step": 860
+    },
+    {
+      "epoch": 0.3719525350593312,
+      "grad_norm": 0.566655158996582,
+      "learning_rate": 0.0001547169811320755,
+      "loss": 0.9941825270652771,
+      "step": 862
+    },
+    {
+      "epoch": 0.37281553398058254,
+      "grad_norm": 0.5262459516525269,
+      "learning_rate": 0.0001550763701707098,
+      "loss": 1.0059782266616821,
+      "step": 864
+    },
+    {
+      "epoch": 0.3736785329018339,
+      "grad_norm": 0.6264083981513977,
+      "learning_rate": 0.00015543575920934412,
+      "loss": 1.0332856178283691,
+      "step": 866
+    },
+    {
+      "epoch": 0.3745415318230852,
+      "grad_norm": 0.6575480699539185,
+      "learning_rate": 0.00015579514824797845,
+      "loss": 1.022459626197815,
+      "step": 868
+    },
+    {
+      "epoch": 0.37540453074433655,
+      "grad_norm": 0.6291940212249756,
+      "learning_rate": 0.00015615453728661275,
+      "loss": 0.9550372362136841,
+      "step": 870
+    },
+    {
+      "epoch": 0.3762675296655879,
+      "grad_norm": 0.6710562109947205,
+      "learning_rate": 0.00015651392632524708,
+      "loss": 0.9861716628074646,
+      "step": 872
+    },
+    {
+      "epoch": 0.37713052858683926,
+      "grad_norm": 0.5505748987197876,
+      "learning_rate": 0.0001568733153638814,
+      "loss": 0.9719111919403076,
+      "step": 874
+    },
+    {
+      "epoch": 0.3779935275080906,
+      "grad_norm": 0.5055180788040161,
+      "learning_rate": 0.00015723270440251574,
+      "loss": 0.8698170185089111,
+      "step": 876
+    },
+    {
+      "epoch": 0.378856526429342,
+      "grad_norm": 0.5935947895050049,
+      "learning_rate": 0.00015759209344115005,
+      "loss": 1.029494285583496,
+      "step": 878
+    },
+    {
+      "epoch": 0.37971952535059333,
+      "grad_norm": 0.538325846195221,
+      "learning_rate": 0.00015795148247978438,
+      "loss": 0.923010528087616,
+      "step": 880
+    },
+    {
+      "epoch": 0.38058252427184464,
+      "grad_norm": 0.587297797203064,
+      "learning_rate": 0.0001583108715184187,
+      "loss": 0.9394056797027588,
+      "step": 882
+    },
+    {
+      "epoch": 0.381445523193096,
+      "grad_norm": 0.5910462737083435,
+      "learning_rate": 0.000158670260557053,
+      "loss": 0.9472483992576599,
+      "step": 884
+    },
+    {
+      "epoch": 0.38230852211434735,
+      "grad_norm": 0.629048764705658,
+      "learning_rate": 0.00015902964959568734,
+      "loss": 0.9028263688087463,
+      "step": 886
+    },
+    {
+      "epoch": 0.3831715210355987,
+      "grad_norm": 0.5028086304664612,
+      "learning_rate": 0.00015938903863432167,
+      "loss": 0.9579087495803833,
+      "step": 888
+    },
+    {
+      "epoch": 0.38403451995685006,
+      "grad_norm": 0.5372384190559387,
+      "learning_rate": 0.000159748427672956,
+      "loss": 0.8318673372268677,
+      "step": 890
+    },
+    {
+      "epoch": 0.3848975188781014,
+      "grad_norm": 0.6314184665679932,
+      "learning_rate": 0.0001601078167115903,
+      "loss": 0.9804943203926086,
+      "step": 892
+    },
+    {
+      "epoch": 0.3857605177993528,
+      "grad_norm": 0.5545229911804199,
+      "learning_rate": 0.00016046720575022463,
+      "loss": 1.0078438520431519,
+      "step": 894
+    },
+    {
+      "epoch": 0.3866235167206041,
+      "grad_norm": 0.4674014151096344,
+      "learning_rate": 0.00016082659478885896,
+      "loss": 0.9269036650657654,
+      "step": 896
+    },
+    {
+      "epoch": 0.38748651564185543,
+      "grad_norm": 1.5887153148651123,
+      "learning_rate": 0.00016118598382749326,
+      "loss": 0.8927953243255615,
+      "step": 898
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "grad_norm": 0.5217035412788391,
+      "learning_rate": 0.0001615453728661276,
+      "loss": 0.908074140548706,
+      "step": 900
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "eval_loss": 0.9741895794868469,
+      "eval_runtime": 667.2236,
+      "eval_samples_per_second": 3.087,
+      "eval_steps_per_second": 3.087,
+      "step": 900
+    },
+    {
+      "epoch": 0.38921251348435815,
+      "grad_norm": 0.470498651266098,
+      "learning_rate": 0.00016190476190476192,
+      "loss": 0.9660369157791138,
+      "step": 902
+    },
+    {
+      "epoch": 0.3900755124056095,
+      "grad_norm": 0.5111004114151001,
+      "learning_rate": 0.00016226415094339625,
+      "loss": 0.9236379265785217,
+      "step": 904
+    },
+    {
+      "epoch": 0.39093851132686086,
+      "grad_norm": 0.5872815251350403,
+      "learning_rate": 0.00016262353998203056,
+      "loss": 1.0061595439910889,
+      "step": 906
+    },
+    {
+      "epoch": 0.3918015102481122,
+      "grad_norm": 0.5150740742683411,
+      "learning_rate": 0.0001629829290206649,
+      "loss": 0.8347328901290894,
+      "step": 908
+    },
+    {
+      "epoch": 0.3926645091693635,
+      "grad_norm": 0.46554985642433167,
+      "learning_rate": 0.00016334231805929922,
+      "loss": 0.9091183543205261,
+      "step": 910
+    },
+    {
+      "epoch": 0.3935275080906149,
+      "grad_norm": 0.5292875170707703,
+      "learning_rate": 0.00016370170709793352,
+      "loss": 0.9299798011779785,
+      "step": 912
+    },
+    {
+      "epoch": 0.39439050701186623,
+      "grad_norm": 0.5177125930786133,
+      "learning_rate": 0.00016406109613656785,
+      "loss": 0.942286491394043,
+      "step": 914
+    },
+    {
+      "epoch": 0.3952535059331176,
+      "grad_norm": 0.5564161539077759,
+      "learning_rate": 0.00016442048517520215,
+      "loss": 0.825290858745575,
+      "step": 916
+    },
+    {
+      "epoch": 0.39611650485436894,
+      "grad_norm": 0.5572530031204224,
+      "learning_rate": 0.00016477987421383648,
+      "loss": 0.876898467540741,
+      "step": 918
+    },
+    {
+      "epoch": 0.3969795037756203,
+      "grad_norm": 0.7294673323631287,
+      "learning_rate": 0.0001651392632524708,
+      "loss": 0.8949798941612244,
+      "step": 920
+    },
+    {
+      "epoch": 0.3978425026968716,
+      "grad_norm": 0.5234251022338867,
+      "learning_rate": 0.00016549865229110512,
+      "loss": 0.8457819223403931,
+      "step": 922
+    },
+    {
+      "epoch": 0.39870550161812296,
+      "grad_norm": 0.5273709893226624,
+      "learning_rate": 0.00016585804132973945,
+      "loss": 0.9080174565315247,
+      "step": 924
+    },
+    {
+      "epoch": 0.3995685005393743,
+      "grad_norm": 0.5795063376426697,
+      "learning_rate": 0.00016621743036837378,
+      "loss": 1.0304023027420044,
+      "step": 926
+    },
+    {
+      "epoch": 0.4004314994606257,
+      "grad_norm": 0.6153313517570496,
+      "learning_rate": 0.00016657681940700808,
+      "loss": 0.8900477886199951,
+      "step": 928
+    },
+    {
+      "epoch": 0.40129449838187703,
+      "grad_norm": 0.6293173432350159,
+      "learning_rate": 0.0001669362084456424,
+      "loss": 1.0130009651184082,
+      "step": 930
+    },
+    {
+      "epoch": 0.4021574973031284,
+      "grad_norm": 0.5455223321914673,
+      "learning_rate": 0.00016729559748427674,
+      "loss": 0.9339282512664795,
+      "step": 932
+    },
+    {
+      "epoch": 0.40302049622437974,
+      "grad_norm": 0.5349094271659851,
+      "learning_rate": 0.00016765498652291104,
+      "loss": 0.9628980755805969,
+      "step": 934
+    },
+    {
+      "epoch": 0.40388349514563104,
+      "grad_norm": 0.491227924823761,
+      "learning_rate": 0.00016801437556154537,
+      "loss": 0.8922860026359558,
+      "step": 936
+    },
+    {
+      "epoch": 0.4047464940668824,
+      "grad_norm": 0.6331246495246887,
+      "learning_rate": 0.0001683737646001797,
+      "loss": 1.0470497608184814,
+      "step": 938
+    },
+    {
+      "epoch": 0.40560949298813376,
+      "grad_norm": 0.6079246401786804,
+      "learning_rate": 0.00016873315363881403,
+      "loss": 0.8868283629417419,
+      "step": 940
+    },
+    {
+      "epoch": 0.4064724919093851,
+      "grad_norm": 0.5326972603797913,
+      "learning_rate": 0.00016909254267744833,
+      "loss": 0.9938711524009705,
+      "step": 942
+    },
+    {
+      "epoch": 0.40733549083063647,
+      "grad_norm": 0.47754305601119995,
+      "learning_rate": 0.00016945193171608266,
+      "loss": 0.8280484676361084,
+      "step": 944
+    },
+    {
+      "epoch": 0.4081984897518878,
+      "grad_norm": 0.6683310270309448,
+      "learning_rate": 0.000169811320754717,
+      "loss": 1.089701533317566,
+      "step": 946
+    },
+    {
+      "epoch": 0.4090614886731392,
+      "grad_norm": 0.42798754572868347,
+      "learning_rate": 0.0001701707097933513,
+      "loss": 0.8535542488098145,
+      "step": 948
+    },
+    {
+      "epoch": 0.4099244875943905,
+      "grad_norm": 0.5999574065208435,
+      "learning_rate": 0.00017053009883198563,
+      "loss": 0.9039298295974731,
+      "step": 950
+    },
+    {
+      "epoch": 0.41078748651564184,
+      "grad_norm": 0.5752781629562378,
+      "learning_rate": 0.00017088948787061996,
+      "loss": 0.8786448240280151,
+      "step": 952
+    },
+    {
+      "epoch": 0.4116504854368932,
+      "grad_norm": 0.5121532678604126,
+      "learning_rate": 0.0001712488769092543,
+      "loss": 0.9206072688102722,
+      "step": 954
+    },
+    {
+      "epoch": 0.41251348435814456,
+      "grad_norm": 0.611078143119812,
+      "learning_rate": 0.0001716082659478886,
+      "loss": 0.9246986508369446,
+      "step": 956
+    },
+    {
+      "epoch": 0.4133764832793959,
+      "grad_norm": 0.5101020336151123,
+      "learning_rate": 0.00017196765498652292,
+      "loss": 0.9221894145011902,
+      "step": 958
+    },
+    {
+      "epoch": 0.41423948220064727,
+      "grad_norm": 0.5681450963020325,
+      "learning_rate": 0.00017232704402515725,
+      "loss": 0.9072799682617188,
+      "step": 960
+    },
+    {
+      "epoch": 0.41510248112189857,
+      "grad_norm": 0.47865498065948486,
+      "learning_rate": 0.00017268643306379155,
+      "loss": 0.9460896849632263,
+      "step": 962
+    },
+    {
+      "epoch": 0.4159654800431499,
+      "grad_norm": 0.49861401319503784,
+      "learning_rate": 0.00017304582210242588,
+      "loss": 0.9121519923210144,
+      "step": 964
+    },
+    {
+      "epoch": 0.4168284789644013,
+      "grad_norm": 0.43025892972946167,
+      "learning_rate": 0.0001734052111410602,
+      "loss": 0.8826848864555359,
+      "step": 966
+    },
+    {
+      "epoch": 0.41769147788565264,
+      "grad_norm": 0.4600491225719452,
+      "learning_rate": 0.00017376460017969454,
+      "loss": 0.8756251335144043,
+      "step": 968
+    },
+    {
+      "epoch": 0.418554476806904,
+      "grad_norm": 0.5297656059265137,
+      "learning_rate": 0.00017412398921832885,
+      "loss": 0.9171333312988281,
+      "step": 970
+    },
+    {
+      "epoch": 0.41941747572815535,
+      "grad_norm": 0.4906919002532959,
+      "learning_rate": 0.00017448337825696318,
+      "loss": 0.8887524008750916,
+      "step": 972
+    },
+    {
+      "epoch": 0.4202804746494067,
+      "grad_norm": 0.49263402819633484,
+      "learning_rate": 0.0001748427672955975,
+      "loss": 0.8345810174942017,
+      "step": 974
+    },
+    {
+      "epoch": 0.421143473570658,
+      "grad_norm": 0.5706565380096436,
+      "learning_rate": 0.0001752021563342318,
+      "loss": 0.968651294708252,
+      "step": 976
+    },
+    {
+      "epoch": 0.42200647249190937,
+      "grad_norm": 0.5269908308982849,
+      "learning_rate": 0.00017556154537286614,
+      "loss": 0.9729376435279846,
+      "step": 978
+    },
+    {
+      "epoch": 0.4228694714131607,
+      "grad_norm": 0.47058001160621643,
+      "learning_rate": 0.00017592093441150047,
+      "loss": 0.963884711265564,
+      "step": 980
+    },
+    {
+      "epoch": 0.4237324703344121,
+      "grad_norm": 0.5322962999343872,
+      "learning_rate": 0.0001762803234501348,
+      "loss": 0.8952447175979614,
+      "step": 982
+    },
+    {
+      "epoch": 0.42459546925566344,
+      "grad_norm": 0.5750975012779236,
+      "learning_rate": 0.0001766397124887691,
+      "loss": 0.8932783603668213,
+      "step": 984
+    },
+    {
+      "epoch": 0.4254584681769148,
+      "grad_norm": 0.5539655685424805,
+      "learning_rate": 0.00017699910152740343,
+      "loss": 0.916595458984375,
+      "step": 986
+    },
+    {
+      "epoch": 0.42632146709816615,
+      "grad_norm": 0.568000853061676,
+      "learning_rate": 0.00017735849056603776,
+      "loss": 0.9669626355171204,
+      "step": 988
+    },
+    {
+      "epoch": 0.42718446601941745,
+      "grad_norm": 0.6010684370994568,
+      "learning_rate": 0.00017771787960467206,
+      "loss": 1.0089105367660522,
+      "step": 990
+    },
+    {
+      "epoch": 0.4280474649406688,
+      "grad_norm": 0.6083462238311768,
+      "learning_rate": 0.0001780772686433064,
+      "loss": 0.9810921549797058,
+      "step": 992
+    },
+    {
+      "epoch": 0.42891046386192017,
+      "grad_norm": 0.5076655149459839,
+      "learning_rate": 0.0001784366576819407,
+      "loss": 0.9524372816085815,
+      "step": 994
+    },
+    {
+      "epoch": 0.4297734627831715,
+      "grad_norm": 0.5260922312736511,
+      "learning_rate": 0.00017879604672057503,
+      "loss": 0.881294846534729,
+      "step": 996
+    },
+    {
+      "epoch": 0.4306364617044229,
+      "grad_norm": 0.6130498051643372,
+      "learning_rate": 0.00017915543575920936,
+      "loss": 0.9138327836990356,
+      "step": 998
+    },
+    {
+      "epoch": 0.43149946062567424,
+      "grad_norm": 0.5346242785453796,
+      "learning_rate": 0.00017951482479784366,
+      "loss": 0.8861367106437683,
+      "step": 1000
+    },
+    {
+      "epoch": 0.43149946062567424,
+      "eval_loss": 0.9606748819351196,
+      "eval_runtime": 655.4358,
+      "eval_samples_per_second": 3.143,
+      "eval_steps_per_second": 3.143,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4323624595469256,
+      "grad_norm": 0.5977228879928589,
+      "learning_rate": 0.000179874213836478,
+      "loss": 0.8711628913879395,
+      "step": 1002
+    },
+    {
+      "epoch": 0.4332254584681769,
+      "grad_norm": 0.5547866821289062,
+      "learning_rate": 0.00018023360287511232,
+      "loss": 0.9393253326416016,
+      "step": 1004
+    },
+    {
+      "epoch": 0.43408845738942825,
+      "grad_norm": 0.536856472492218,
+      "learning_rate": 0.00018059299191374662,
+      "loss": 0.9486003518104553,
+      "step": 1006
+    },
+    {
+      "epoch": 0.4349514563106796,
+      "grad_norm": 0.4769814610481262,
+      "learning_rate": 0.00018095238095238095,
+      "loss": 0.9042052030563354,
+      "step": 1008
+    },
+    {
+      "epoch": 0.43581445523193096,
+      "grad_norm": 0.5554604530334473,
+      "learning_rate": 0.00018131176999101528,
+      "loss": 0.978546142578125,
+      "step": 1010
+    },
+    {
+      "epoch": 0.4366774541531823,
+      "grad_norm": 0.5112947225570679,
+      "learning_rate": 0.00018167115902964959,
+      "loss": 0.8382073640823364,
+      "step": 1012
+    },
+    {
+      "epoch": 0.4375404530744337,
+      "grad_norm": 0.45194941759109497,
+      "learning_rate": 0.00018203054806828392,
+      "loss": 0.8577026724815369,
+      "step": 1014
+    },
+    {
+      "epoch": 0.438403451995685,
+      "grad_norm": 0.5115043520927429,
+      "learning_rate": 0.00018238993710691825,
+      "loss": 0.8517863154411316,
+      "step": 1016
+    },
+    {
+      "epoch": 0.43926645091693634,
+      "grad_norm": 0.5485050082206726,
+      "learning_rate": 0.00018274932614555258,
+      "loss": 0.9597266912460327,
+      "step": 1018
+    },
+    {
+      "epoch": 0.4401294498381877,
+      "grad_norm": 0.5742959976196289,
+      "learning_rate": 0.00018310871518418688,
+      "loss": 1.0407187938690186,
+      "step": 1020
+    },
+    {
+      "epoch": 0.44099244875943905,
+      "grad_norm": 0.44870051741600037,
+      "learning_rate": 0.0001834681042228212,
+      "loss": 0.8696310520172119,
+      "step": 1022
+    },
+    {
+      "epoch": 0.4418554476806904,
+      "grad_norm": 0.5179623961448669,
+      "learning_rate": 0.00018382749326145554,
+      "loss": 0.9673634767532349,
+      "step": 1024
+    },
+    {
+      "epoch": 0.44271844660194176,
+      "grad_norm": 0.5404779314994812,
+      "learning_rate": 0.00018418688230008984,
+      "loss": 0.9596615433692932,
+      "step": 1026
+    },
+    {
+      "epoch": 0.4435814455231931,
+      "grad_norm": 0.47766315937042236,
+      "learning_rate": 0.00018454627133872417,
+      "loss": 0.8483878970146179,
+      "step": 1028
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.503380537033081,
+      "learning_rate": 0.0001849056603773585,
+      "loss": 0.9330979585647583,
+      "step": 1030
+    },
+    {
+      "epoch": 0.4453074433656958,
+      "grad_norm": 0.6129396557807922,
+      "learning_rate": 0.00018526504941599283,
+      "loss": 0.9341012239456177,
+      "step": 1032
+    },
+    {
+      "epoch": 0.44617044228694713,
+      "grad_norm": 0.4497876465320587,
+      "learning_rate": 0.00018562443845462713,
+      "loss": 0.9139068126678467,
+      "step": 1034
+    },
+    {
+      "epoch": 0.4470334412081985,
+      "grad_norm": 0.5369747281074524,
+      "learning_rate": 0.00018598382749326146,
+      "loss": 0.8874827027320862,
+      "step": 1036
+    },
+    {
+      "epoch": 0.44789644012944985,
+      "grad_norm": 0.5947322845458984,
+      "learning_rate": 0.0001863432165318958,
+      "loss": 0.9653725028038025,
+      "step": 1038
+    },
+    {
+      "epoch": 0.4487594390507012,
+      "grad_norm": 0.6649987101554871,
+      "learning_rate": 0.0001867026055705301,
+      "loss": 0.9553119540214539,
+      "step": 1040
+    },
+    {
+      "epoch": 0.44962243797195256,
+      "grad_norm": 0.5369387269020081,
+      "learning_rate": 0.00018706199460916443,
+      "loss": 0.904233992099762,
+      "step": 1042
+    },
+    {
+      "epoch": 0.45048543689320386,
+      "grad_norm": 0.4956842362880707,
+      "learning_rate": 0.00018742138364779876,
+      "loss": 0.8837952017784119,
+      "step": 1044
+    },
+    {
+      "epoch": 0.4513484358144552,
+      "grad_norm": 0.48045051097869873,
+      "learning_rate": 0.0001877807726864331,
+      "loss": 0.8964687585830688,
+      "step": 1046
+    },
+    {
+      "epoch": 0.4522114347357066,
+      "grad_norm": 0.4925530254840851,
+      "learning_rate": 0.0001881401617250674,
+      "loss": 0.9105878472328186,
+      "step": 1048
+    },
+    {
+      "epoch": 0.45307443365695793,
+      "grad_norm": 0.5131362080574036,
+      "learning_rate": 0.00018849955076370172,
+      "loss": 0.96272873878479,
+      "step": 1050
+    },
+    {
+      "epoch": 0.4539374325782093,
+      "grad_norm": 0.435739129781723,
+      "learning_rate": 0.00018885893980233605,
+      "loss": 0.8796783685684204,
+      "step": 1052
+    },
+    {
+      "epoch": 0.45480043149946064,
+      "grad_norm": 0.500938892364502,
+      "learning_rate": 0.00018921832884097035,
+      "loss": 0.9463814496994019,
+      "step": 1054
+    },
+    {
+      "epoch": 0.455663430420712,
+      "grad_norm": 0.4769900143146515,
+      "learning_rate": 0.00018957771787960468,
+      "loss": 0.9030335545539856,
+      "step": 1056
+    },
+    {
+      "epoch": 0.4565264293419633,
+      "grad_norm": 0.49585285782814026,
+      "learning_rate": 0.00018993710691823901,
+      "loss": 0.986995279788971,
+      "step": 1058
+    },
+    {
+      "epoch": 0.45738942826321466,
+      "grad_norm": 0.5875195264816284,
+      "learning_rate": 0.00019029649595687334,
+      "loss": 0.9297246932983398,
+      "step": 1060
+    },
+    {
+      "epoch": 0.458252427184466,
+      "grad_norm": 0.5552583932876587,
+      "learning_rate": 0.00019065588499550765,
+      "loss": 1.005869746208191,
+      "step": 1062
+    },
+    {
+      "epoch": 0.4591154261057174,
+      "grad_norm": 0.49282076954841614,
+      "learning_rate": 0.00019101527403414198,
+      "loss": 0.8949927091598511,
+      "step": 1064
+    },
+    {
+      "epoch": 0.45997842502696873,
+      "grad_norm": 0.4951777160167694,
+      "learning_rate": 0.0001913746630727763,
+      "loss": 0.9997886419296265,
+      "step": 1066
+    },
+    {
+      "epoch": 0.4608414239482201,
+      "grad_norm": 0.5154827237129211,
+      "learning_rate": 0.0001917340521114106,
+      "loss": 0.9532123804092407,
+      "step": 1068
+    },
+    {
+      "epoch": 0.4617044228694714,
+      "grad_norm": 0.5547500252723694,
+      "learning_rate": 0.00019209344115004494,
+      "loss": 0.8959843516349792,
+      "step": 1070
+    },
+    {
+      "epoch": 0.46256742179072274,
+      "grad_norm": 0.500188946723938,
+      "learning_rate": 0.00019245283018867927,
+      "loss": 0.8201484680175781,
+      "step": 1072
+    },
+    {
+      "epoch": 0.4634304207119741,
+      "grad_norm": 0.4181794822216034,
+      "learning_rate": 0.00019281221922731357,
+      "loss": 0.8255136609077454,
+      "step": 1074
+    },
+    {
+      "epoch": 0.46429341963322546,
+      "grad_norm": 0.5613874197006226,
+      "learning_rate": 0.0001931716082659479,
+      "loss": 0.896024763584137,
+      "step": 1076
+    },
+    {
+      "epoch": 0.4651564185544768,
+      "grad_norm": 0.5000972151756287,
+      "learning_rate": 0.0001935309973045822,
+      "loss": 0.8831873536109924,
+      "step": 1078
+    },
+    {
+      "epoch": 0.46601941747572817,
+      "grad_norm": 0.6321820616722107,
+      "learning_rate": 0.00019389038634321654,
+      "loss": 0.9787988662719727,
+      "step": 1080
+    },
+    {
+      "epoch": 0.4668824163969795,
+      "grad_norm": 0.4843652546405792,
+      "learning_rate": 0.00019424977538185087,
+      "loss": 0.933361828327179,
+      "step": 1082
+    },
+    {
+      "epoch": 0.46774541531823083,
+      "grad_norm": 0.537330150604248,
+      "learning_rate": 0.00019460916442048517,
+      "loss": 0.9046981334686279,
+      "step": 1084
+    },
+    {
+      "epoch": 0.4686084142394822,
+      "grad_norm": 0.5761371850967407,
+      "learning_rate": 0.0001949685534591195,
+      "loss": 0.9625781178474426,
+      "step": 1086
+    },
+    {
+      "epoch": 0.46947141316073354,
+      "grad_norm": 0.5209522843360901,
+      "learning_rate": 0.00019532794249775383,
+      "loss": 0.9280619025230408,
+      "step": 1088
+    },
+    {
+      "epoch": 0.4703344120819849,
+      "grad_norm": 0.5383933186531067,
+      "learning_rate": 0.00019568733153638813,
+      "loss": 0.8236247301101685,
+      "step": 1090
+    },
+    {
+      "epoch": 0.47119741100323626,
+      "grad_norm": 0.4994274377822876,
+      "learning_rate": 0.00019604672057502246,
+      "loss": 0.9404071569442749,
+      "step": 1092
+    },
+    {
+      "epoch": 0.4720604099244876,
+      "grad_norm": 0.5177807211875916,
+      "learning_rate": 0.0001964061096136568,
+      "loss": 0.8517536520957947,
+      "step": 1094
+    },
+    {
+      "epoch": 0.47292340884573897,
+      "grad_norm": 0.5374870896339417,
+      "learning_rate": 0.00019676549865229112,
+      "loss": 0.8214367032051086,
+      "step": 1096
+    },
+    {
+      "epoch": 0.47378640776699027,
+      "grad_norm": 0.5544074177742004,
+      "learning_rate": 0.00019712488769092542,
+      "loss": 1.016176700592041,
+      "step": 1098
+    },
+    {
+      "epoch": 0.4746494066882416,
+      "grad_norm": 0.5125867128372192,
+      "learning_rate": 0.00019748427672955975,
+      "loss": 0.8425421118736267,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4746494066882416,
+      "eval_loss": 0.944629430770874,
+      "eval_runtime": 649.9107,
+      "eval_samples_per_second": 3.17,
+      "eval_steps_per_second": 3.17,
+      "step": 1100
+    },
+    {
+      "epoch": 0.475512405609493,
+      "grad_norm": 0.5204418897628784,
+      "learning_rate": 0.00019784366576819408,
+      "loss": 0.9444556832313538,
+      "step": 1102
+    },
+    {
+      "epoch": 0.47637540453074434,
+      "grad_norm": 0.46085885167121887,
+      "learning_rate": 0.0001982030548068284,
+      "loss": 0.877082109451294,
+      "step": 1104
+    },
+    {
+      "epoch": 0.4772384034519957,
+      "grad_norm": 0.5269598960876465,
+      "learning_rate": 0.00019856244384546272,
+      "loss": 0.9214640259742737,
+      "step": 1106
+    },
+    {
+      "epoch": 0.47810140237324705,
+      "grad_norm": 0.4894753694534302,
+      "learning_rate": 0.00019892183288409705,
+      "loss": 0.8867175579071045,
+      "step": 1108
+    },
+    {
+      "epoch": 0.47896440129449835,
+      "grad_norm": 0.5204115509986877,
+      "learning_rate": 0.00019928122192273138,
+      "loss": 0.9641162753105164,
+      "step": 1110
+    },
+    {
+      "epoch": 0.4798274002157497,
+      "grad_norm": 0.6399031281471252,
+      "learning_rate": 0.00019964061096136568,
+      "loss": 1.0219199657440186,
+      "step": 1112
+    },
+    {
+      "epoch": 0.48069039913700107,
+      "grad_norm": 0.3979159891605377,
+      "learning_rate": 0.0002,
+      "loss": 0.8189998269081116,
+      "step": 1114
+    },
+    {
+      "epoch": 0.4815533980582524,
+      "grad_norm": 0.4782681465148926,
+      "learning_rate": 0.0001999999879427254,
+      "loss": 0.83241868019104,
+      "step": 1116
+    },
+    {
+      "epoch": 0.4824163969795038,
+      "grad_norm": 0.5235620141029358,
+      "learning_rate": 0.00019999995177090454,
+      "loss": 0.9371466636657715,
+      "step": 1118
+    },
+    {
+      "epoch": 0.48327939590075514,
+      "grad_norm": 0.4543023407459259,
+      "learning_rate": 0.00019999989148454606,
+      "loss": 0.7767758369445801,
+      "step": 1120
+    },
+    {
+      "epoch": 0.4841423948220065,
+      "grad_norm": 0.6191229820251465,
+      "learning_rate": 0.00019999980708366457,
+      "loss": 1.0103063583374023,
+      "step": 1122
+    },
+    {
+      "epoch": 0.4850053937432578,
+      "grad_norm": 0.45392486453056335,
+      "learning_rate": 0.00019999969856828042,
+      "loss": 0.8720875382423401,
+      "step": 1124
+    },
+    {
+      "epoch": 0.48586839266450915,
+      "grad_norm": 0.42748701572418213,
+      "learning_rate": 0.00019999956593841974,
+      "loss": 0.7859150171279907,
+      "step": 1126
+    },
+    {
+      "epoch": 0.4867313915857605,
+      "grad_norm": 0.4952569603919983,
+      "learning_rate": 0.00019999940919411454,
+      "loss": 0.9154419898986816,
+      "step": 1128
+    },
+    {
+      "epoch": 0.48759439050701187,
+      "grad_norm": 0.5522173047065735,
+      "learning_rate": 0.00019999922833540264,
+      "loss": 0.9076330065727234,
+      "step": 1130
+    },
+    {
+      "epoch": 0.4884573894282632,
+      "grad_norm": 0.5355855226516724,
+      "learning_rate": 0.00019999902336232758,
+      "loss": 0.8933543562889099,
+      "step": 1132
+    },
+    {
+      "epoch": 0.4893203883495146,
+      "grad_norm": 0.4613489508628845,
+      "learning_rate": 0.00019999879427493885,
+      "loss": 0.9160735607147217,
+      "step": 1134
+    },
+    {
+      "epoch": 0.49018338727076594,
+      "grad_norm": 0.4758962094783783,
+      "learning_rate": 0.0001999985410732917,
+      "loss": 0.8552446961402893,
+      "step": 1136
+    },
+    {
+      "epoch": 0.49104638619201724,
+      "grad_norm": 0.4549376964569092,
+      "learning_rate": 0.00019999826375744715,
+      "loss": 0.9979530572891235,
+      "step": 1138
+    },
+    {
+      "epoch": 0.4919093851132686,
+      "grad_norm": 0.4363284409046173,
+      "learning_rate": 0.0001999979623274721,
+      "loss": 0.9295380115509033,
+      "step": 1140
+    },
+    {
+      "epoch": 0.49277238403451995,
+      "grad_norm": 0.5090877413749695,
+      "learning_rate": 0.0001999976367834392,
+      "loss": 0.8737252950668335,
+      "step": 1142
+    },
+    {
+      "epoch": 0.4936353829557713,
+      "grad_norm": 0.45340779423713684,
+      "learning_rate": 0.000199997287125427,
+      "loss": 0.8312779068946838,
+      "step": 1144
+    },
+    {
+      "epoch": 0.49449838187702266,
+      "grad_norm": 0.4771472215652466,
+      "learning_rate": 0.0001999969133535198,
+      "loss": 0.9105207324028015,
+      "step": 1146
+    },
+    {
+      "epoch": 0.495361380798274,
+      "grad_norm": 0.5251384377479553,
+      "learning_rate": 0.00019999651546780773,
+      "loss": 0.8578172922134399,
+      "step": 1148
+    },
+    {
+      "epoch": 0.4962243797195254,
+      "grad_norm": 0.49128198623657227,
+      "learning_rate": 0.00019999609346838676,
+      "loss": 0.9193941950798035,
+      "step": 1150
+    },
+    {
+      "epoch": 0.4970873786407767,
+      "grad_norm": 0.5558596849441528,
+      "learning_rate": 0.0001999956473553586,
+      "loss": 0.9141314625740051,
+      "step": 1152
+    },
+    {
+      "epoch": 0.49795037756202803,
+      "grad_norm": 0.45872750878334045,
+      "learning_rate": 0.00019999517712883087,
+      "loss": 0.9058388471603394,
+      "step": 1154
+    },
+    {
+      "epoch": 0.4988133764832794,
+      "grad_norm": 0.4710173010826111,
+      "learning_rate": 0.00019999468278891698,
+      "loss": 0.8462487459182739,
+      "step": 1156
+    },
+    {
+      "epoch": 0.49967637540453075,
+      "grad_norm": 0.4805637001991272,
+      "learning_rate": 0.0001999941643357361,
+      "loss": 0.8960906863212585,
+      "step": 1158
+    },
+    {
+      "epoch": 0.5005393743257821,
+      "grad_norm": 0.5108052492141724,
+      "learning_rate": 0.00019999362176941325,
+      "loss": 0.9074980020523071,
+      "step": 1160
+    },
+    {
+      "epoch": 0.5014023732470334,
+      "grad_norm": 0.49572333693504333,
+      "learning_rate": 0.00019999305509007932,
+      "loss": 0.9710080623626709,
+      "step": 1162
+    },
+    {
+      "epoch": 0.5022653721682848,
+      "grad_norm": 0.5304561257362366,
+      "learning_rate": 0.0001999924642978709,
+      "loss": 0.8877825140953064,
+      "step": 1164
+    },
+    {
+      "epoch": 0.5031283710895361,
+      "grad_norm": 0.5007328391075134,
+      "learning_rate": 0.0001999918493929305,
+      "loss": 0.8955381512641907,
+      "step": 1166
+    },
+    {
+      "epoch": 0.5039913700107875,
+      "grad_norm": 0.569549024105072,
+      "learning_rate": 0.0001999912103754064,
+      "loss": 0.9478562474250793,
+      "step": 1168
+    },
+    {
+      "epoch": 0.5048543689320388,
+      "grad_norm": 0.5354957580566406,
+      "learning_rate": 0.00019999054724545264,
+      "loss": 0.9685383439064026,
+      "step": 1170
+    },
+    {
+      "epoch": 0.5057173678532901,
+      "grad_norm": 0.547788143157959,
+      "learning_rate": 0.00019998986000322917,
+      "loss": 0.9221975207328796,
+      "step": 1172
+    },
+    {
+      "epoch": 0.5065803667745415,
+      "grad_norm": 0.4919529855251312,
+      "learning_rate": 0.00019998914864890175,
+      "loss": 0.9104788303375244,
+      "step": 1174
+    },
+    {
+      "epoch": 0.5074433656957928,
+      "grad_norm": 0.5274141430854797,
+      "learning_rate": 0.00019998841318264187,
+      "loss": 0.9176050424575806,
+      "step": 1176
+    },
+    {
+      "epoch": 0.5083063646170443,
+      "grad_norm": 0.4257420301437378,
+      "learning_rate": 0.00019998765360462688,
+      "loss": 0.8389710187911987,
+      "step": 1178
+    },
+    {
+      "epoch": 0.5091693635382956,
+      "grad_norm": 0.4947778880596161,
+      "learning_rate": 0.00019998686991504002,
+      "loss": 1.0164397954940796,
+      "step": 1180
+    },
+    {
+      "epoch": 0.510032362459547,
+      "grad_norm": 0.5540821552276611,
+      "learning_rate": 0.00019998606211407016,
+      "loss": 0.9900994300842285,
+      "step": 1182
+    },
+    {
+      "epoch": 0.5108953613807983,
+      "grad_norm": 0.4793289601802826,
+      "learning_rate": 0.0001999852302019122,
+      "loss": 0.8797636032104492,
+      "step": 1184
+    },
+    {
+      "epoch": 0.5117583603020496,
+      "grad_norm": 0.47429659962654114,
+      "learning_rate": 0.00019998437417876672,
+      "loss": 0.96225905418396,
+      "step": 1186
+    },
+    {
+      "epoch": 0.512621359223301,
+      "grad_norm": 0.44918450713157654,
+      "learning_rate": 0.00019998349404484013,
+      "loss": 0.8604235649108887,
+      "step": 1188
+    },
+    {
+      "epoch": 0.5134843581445523,
+      "grad_norm": 0.566977858543396,
+      "learning_rate": 0.00019998258980034468,
+      "loss": 1.0325366258621216,
+      "step": 1190
+    },
+    {
+      "epoch": 0.5143473570658037,
+      "grad_norm": 0.4671999514102936,
+      "learning_rate": 0.00019998166144549843,
+      "loss": 0.7658900022506714,
+      "step": 1192
+    },
+    {
+      "epoch": 0.515210355987055,
+      "grad_norm": 0.42312702536582947,
+      "learning_rate": 0.00019998070898052521,
+      "loss": 0.9365432858467102,
+      "step": 1194
+    },
+    {
+      "epoch": 0.5160733549083064,
+      "grad_norm": 0.4652721881866455,
+      "learning_rate": 0.00019997973240565476,
+      "loss": 0.771016538143158,
+      "step": 1196
+    },
+    {
+      "epoch": 0.5169363538295577,
+      "grad_norm": 0.5048499703407288,
+      "learning_rate": 0.00019997873172112254,
+      "loss": 0.9123705625534058,
+      "step": 1198
+    },
+    {
+      "epoch": 0.517799352750809,
+      "grad_norm": 0.5446439981460571,
+      "learning_rate": 0.0001999777069271699,
+      "loss": 0.8975751399993896,
+      "step": 1200
+    },
+    {
+      "epoch": 0.517799352750809,
+      "eval_loss": 0.9344067573547363,
+      "eval_runtime": 658.6934,
+      "eval_samples_per_second": 3.127,
+      "eval_steps_per_second": 3.127,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5186623516720604,
+      "grad_norm": 0.5044088959693909,
+      "learning_rate": 0.0001999766580240439,
+      "loss": 0.89097660779953,
+      "step": 1202
+    },
+    {
+      "epoch": 0.5195253505933117,
+      "grad_norm": 0.4672294855117798,
+      "learning_rate": 0.00019997558501199753,
+      "loss": 0.9138525128364563,
+      "step": 1204
+    },
+    {
+      "epoch": 0.5203883495145631,
+      "grad_norm": 0.45749008655548096,
+      "learning_rate": 0.00019997448789128952,
+      "loss": 0.8946340680122375,
+      "step": 1206
+    },
+    {
+      "epoch": 0.5212513484358144,
+      "grad_norm": 0.4828707277774811,
+      "learning_rate": 0.00019997336666218447,
+      "loss": 0.8661436438560486,
+      "step": 1208
+    },
+    {
+      "epoch": 0.5221143473570659,
+      "grad_norm": 0.3975147008895874,
+      "learning_rate": 0.0001999722213249527,
+      "loss": 0.7684835195541382,
+      "step": 1210
+    },
+    {
+      "epoch": 0.5229773462783172,
+      "grad_norm": 0.5642077326774597,
+      "learning_rate": 0.00019997105187987045,
+      "loss": 0.9667536616325378,
+      "step": 1212
+    },
+    {
+      "epoch": 0.5238403451995685,
+      "grad_norm": 0.4907105565071106,
+      "learning_rate": 0.00019996985832721972,
+      "loss": 0.8679366707801819,
+      "step": 1214
+    },
+    {
+      "epoch": 0.5247033441208199,
+      "grad_norm": 0.46214789152145386,
+      "learning_rate": 0.0001999686406672883,
+      "loss": 0.8802784085273743,
+      "step": 1216
+    },
+    {
+      "epoch": 0.5255663430420712,
+      "grad_norm": 0.4355131685733795,
+      "learning_rate": 0.00019996739890036985,
+      "loss": 0.8493598103523254,
+      "step": 1218
+    },
+    {
+      "epoch": 0.5264293419633226,
+      "grad_norm": 0.4293915331363678,
+      "learning_rate": 0.0001999661330267638,
+      "loss": 0.8949980735778809,
+      "step": 1220
+    },
+    {
+      "epoch": 0.5272923408845739,
+      "grad_norm": 0.5452485680580139,
+      "learning_rate": 0.00019996484304677544,
+      "loss": 0.9497376680374146,
+      "step": 1222
+    },
+    {
+      "epoch": 0.5281553398058253,
+      "grad_norm": 0.45874500274658203,
+      "learning_rate": 0.00019996352896071583,
+      "loss": 0.9170818328857422,
+      "step": 1224
+    },
+    {
+      "epoch": 0.5290183387270766,
+      "grad_norm": 0.4414025843143463,
+      "learning_rate": 0.00019996219076890182,
+      "loss": 0.7557252645492554,
+      "step": 1226
+    },
+    {
+      "epoch": 0.5298813376483279,
+      "grad_norm": 0.4891829192638397,
+      "learning_rate": 0.0001999608284716562,
+      "loss": 0.848960816860199,
+      "step": 1228
+    },
+    {
+      "epoch": 0.5307443365695793,
+      "grad_norm": 0.5048345327377319,
+      "learning_rate": 0.00019995944206930734,
+      "loss": 0.9555954933166504,
+      "step": 1230
+    },
+    {
+      "epoch": 0.5316073354908306,
+      "grad_norm": 0.5006756782531738,
+      "learning_rate": 0.00019995803156218968,
+      "loss": 0.8080939054489136,
+      "step": 1232
+    },
+    {
+      "epoch": 0.532470334412082,
+      "grad_norm": 0.5422173738479614,
+      "learning_rate": 0.00019995659695064332,
+      "loss": 0.8638371825218201,
+      "step": 1234
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.4535163640975952,
+      "learning_rate": 0.0001999551382350142,
+      "loss": 0.889068067073822,
+      "step": 1236
+    },
+    {
+      "epoch": 0.5341963322545846,
+      "grad_norm": 0.4588642418384552,
+      "learning_rate": 0.00019995365541565412,
+      "loss": 0.8803121447563171,
+      "step": 1238
+    },
+    {
+      "epoch": 0.535059331175836,
+      "grad_norm": 0.49366191029548645,
+      "learning_rate": 0.00019995214849292064,
+      "loss": 0.9694926738739014,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5359223300970873,
+      "grad_norm": 0.41988301277160645,
+      "learning_rate": 0.0001999506174671771,
+      "loss": 0.8367960453033447,
+      "step": 1242
+    },
+    {
+      "epoch": 0.5367853290183388,
+      "grad_norm": 0.5242130160331726,
+      "learning_rate": 0.00019994906233879273,
+      "loss": 0.942340612411499,
+      "step": 1244
+    },
+    {
+      "epoch": 0.53764832793959,
+      "grad_norm": 0.4899834096431732,
+      "learning_rate": 0.00019994748310814256,
+      "loss": 0.8926790356636047,
+      "step": 1246
+    },
+    {
+      "epoch": 0.5385113268608415,
+      "grad_norm": 0.5496823787689209,
+      "learning_rate": 0.00019994587977560744,
+      "loss": 0.99891597032547,
+      "step": 1248
+    },
+    {
+      "epoch": 0.5393743257820928,
+      "grad_norm": 0.4497414231300354,
+      "learning_rate": 0.00019994425234157396,
+      "loss": 0.8873116970062256,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5402373247033441,
+      "grad_norm": 0.4256928563117981,
+      "learning_rate": 0.00019994260080643454,
+      "loss": 0.9041396975517273,
+      "step": 1252
+    },
+    {
+      "epoch": 0.5411003236245955,
+      "grad_norm": 0.36910608410835266,
+      "learning_rate": 0.00019994092517058753,
+      "loss": 0.7647561430931091,
+      "step": 1254
+    },
+    {
+      "epoch": 0.5419633225458468,
+      "grad_norm": 0.537584125995636,
+      "learning_rate": 0.0001999392254344369,
+      "loss": 0.8892287015914917,
+      "step": 1256
+    },
+    {
+      "epoch": 0.5428263214670982,
+      "grad_norm": 0.49463894963264465,
+      "learning_rate": 0.00019993750159839264,
+      "loss": 0.8638571500778198,
+      "step": 1258
+    },
+    {
+      "epoch": 0.5436893203883495,
+      "grad_norm": 0.5052056908607483,
+      "learning_rate": 0.00019993575366287036,
+      "loss": 0.8165372014045715,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5445523193096009,
+      "grad_norm": 0.47367510199546814,
+      "learning_rate": 0.0001999339816282916,
+      "loss": 0.9099977016448975,
+      "step": 1262
+    },
+    {
+      "epoch": 0.5454153182308522,
+      "grad_norm": 0.4600350558757782,
+      "learning_rate": 0.00019993218549508364,
+      "loss": 0.8557311296463013,
+      "step": 1264
+    },
+    {
+      "epoch": 0.5462783171521035,
+      "grad_norm": 0.5684534311294556,
+      "learning_rate": 0.0001999303652636797,
+      "loss": 0.9136497974395752,
+      "step": 1266
+    },
+    {
+      "epoch": 0.5471413160733549,
+      "grad_norm": 0.5151359438896179,
+      "learning_rate": 0.00019992852093451865,
+      "loss": 0.7906932830810547,
+      "step": 1268
+    },
+    {
+      "epoch": 0.5480043149946062,
+      "grad_norm": 0.48577409982681274,
+      "learning_rate": 0.00019992665250804525,
+      "loss": 0.9326766133308411,
+      "step": 1270
+    },
+    {
+      "epoch": 0.5488673139158576,
+      "grad_norm": 0.490531325340271,
+      "learning_rate": 0.00019992475998471004,
+      "loss": 0.9734495878219604,
+      "step": 1272
+    },
+    {
+      "epoch": 0.5497303128371089,
+      "grad_norm": 0.5092435479164124,
+      "learning_rate": 0.00019992284336496947,
+      "loss": 0.8728410005569458,
+      "step": 1274
+    },
+    {
+      "epoch": 0.5505933117583603,
+      "grad_norm": 0.3843296766281128,
+      "learning_rate": 0.00019992090264928566,
+      "loss": 0.7572637796401978,
+      "step": 1276
+    },
+    {
+      "epoch": 0.5514563106796116,
+      "grad_norm": 0.534304678440094,
+      "learning_rate": 0.00019991893783812662,
+      "loss": 0.8895323872566223,
+      "step": 1278
+    },
+    {
+      "epoch": 0.552319309600863,
+      "grad_norm": 0.4567227363586426,
+      "learning_rate": 0.00019991694893196614,
+      "loss": 0.9318088293075562,
+      "step": 1280
+    },
+    {
+      "epoch": 0.5531823085221144,
+      "grad_norm": 0.48464900255203247,
+      "learning_rate": 0.0001999149359312839,
+      "loss": 0.8541979789733887,
+      "step": 1282
+    },
+    {
+      "epoch": 0.5540453074433657,
+      "grad_norm": 0.5569567084312439,
+      "learning_rate": 0.00019991289883656524,
+      "loss": 0.977894127368927,
+      "step": 1284
+    },
+    {
+      "epoch": 0.5549083063646171,
+      "grad_norm": 0.4637227952480316,
+      "learning_rate": 0.00019991083764830145,
+      "loss": 0.8860608339309692,
+      "step": 1286
+    },
+    {
+      "epoch": 0.5557713052858684,
+      "grad_norm": 0.4096687436103821,
+      "learning_rate": 0.00019990875236698956,
+      "loss": 0.8429648876190186,
+      "step": 1288
+    },
+    {
+      "epoch": 0.5566343042071198,
+      "grad_norm": 0.5221695303916931,
+      "learning_rate": 0.00019990664299313242,
+      "loss": 0.8510909080505371,
+      "step": 1290
+    },
+    {
+      "epoch": 0.5574973031283711,
+      "grad_norm": 0.5155899524688721,
+      "learning_rate": 0.00019990450952723872,
+      "loss": 0.8971074223518372,
+      "step": 1292
+    },
+    {
+      "epoch": 0.5583603020496224,
+      "grad_norm": 0.5064809322357178,
+      "learning_rate": 0.0001999023519698229,
+      "loss": 0.9030373096466064,
+      "step": 1294
+    },
+    {
+      "epoch": 0.5592233009708738,
+      "grad_norm": 0.40551698207855225,
+      "learning_rate": 0.00019990017032140526,
+      "loss": 0.7866057753562927,
+      "step": 1296
+    },
+    {
+      "epoch": 0.5600862998921251,
+      "grad_norm": 0.5009430050849915,
+      "learning_rate": 0.00019989796458251194,
+      "loss": 0.9477730989456177,
+      "step": 1298
+    },
+    {
+      "epoch": 0.5609492988133765,
+      "grad_norm": 0.5192028880119324,
+      "learning_rate": 0.00019989573475367477,
+      "loss": 0.9206778407096863,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5609492988133765,
+      "eval_loss": 0.9177446365356445,
+      "eval_runtime": 665.3245,
+      "eval_samples_per_second": 3.096,
+      "eval_steps_per_second": 3.096,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5618122977346278,
+      "grad_norm": 0.5580230951309204,
+      "learning_rate": 0.00019989348083543148,
+      "loss": 0.9516512155532837,
+      "step": 1302
+    },
+    {
+      "epoch": 0.5626752966558792,
+      "grad_norm": 0.4151005744934082,
+      "learning_rate": 0.00019989120282832564,
+      "loss": 0.7725991606712341,
+      "step": 1304
+    },
+    {
+      "epoch": 0.5635382955771305,
+      "grad_norm": 0.56330406665802,
+      "learning_rate": 0.00019988890073290656,
+      "loss": 0.9241501688957214,
+      "step": 1306
+    },
+    {
+      "epoch": 0.5644012944983818,
+      "grad_norm": 0.44836440682411194,
+      "learning_rate": 0.00019988657454972936,
+      "loss": 0.8351686000823975,
+      "step": 1308
+    },
+    {
+      "epoch": 0.5652642934196332,
+      "grad_norm": 0.5414754152297974,
+      "learning_rate": 0.00019988422427935496,
+      "loss": 0.9033217430114746,
+      "step": 1310
+    },
+    {
+      "epoch": 0.5661272923408845,
+      "grad_norm": 0.5283750891685486,
+      "learning_rate": 0.0001998818499223502,
+      "loss": 0.8885331153869629,
+      "step": 1312
+    },
+    {
+      "epoch": 0.566990291262136,
+      "grad_norm": 0.45846256613731384,
+      "learning_rate": 0.00019987945147928758,
+      "loss": 0.8359912037849426,
+      "step": 1314
+    },
+    {
+      "epoch": 0.5678532901833873,
+      "grad_norm": 0.44439879059791565,
+      "learning_rate": 0.0001998770289507455,
+      "loss": 0.8327895402908325,
+      "step": 1316
+    },
+    {
+      "epoch": 0.5687162891046387,
+      "grad_norm": 0.5491341948509216,
+      "learning_rate": 0.00019987458233730813,
+      "loss": 0.9354757070541382,
+      "step": 1318
+    },
+    {
+      "epoch": 0.56957928802589,
+      "grad_norm": 0.5502263307571411,
+      "learning_rate": 0.00019987211163956548,
+      "loss": 0.944054901599884,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5704422869471413,
+      "grad_norm": 0.47165682911872864,
+      "learning_rate": 0.00019986961685811334,
+      "loss": 0.9515072107315063,
+      "step": 1322
+    },
+    {
+      "epoch": 0.5713052858683927,
+      "grad_norm": 0.5136987566947937,
+      "learning_rate": 0.0001998670979935533,
+      "loss": 0.9455493688583374,
+      "step": 1324
+    },
+    {
+      "epoch": 0.572168284789644,
+      "grad_norm": 0.4822693169116974,
+      "learning_rate": 0.00019986455504649277,
+      "loss": 0.8626728057861328,
+      "step": 1326
+    },
+    {
+      "epoch": 0.5730312837108954,
+      "grad_norm": 0.4639468193054199,
+      "learning_rate": 0.000199861988017545,
+      "loss": 0.8857194781303406,
+      "step": 1328
+    },
+    {
+      "epoch": 0.5738942826321467,
+      "grad_norm": 0.5224950313568115,
+      "learning_rate": 0.00019985939690732898,
+      "loss": 0.9198446273803711,
+      "step": 1330
+    },
+    {
+      "epoch": 0.574757281553398,
+      "grad_norm": 0.47504499554634094,
+      "learning_rate": 0.00019985678171646954,
+      "loss": 0.8785439133644104,
+      "step": 1332
+    },
+    {
+      "epoch": 0.5756202804746494,
+      "grad_norm": 0.5022051930427551,
+      "learning_rate": 0.0001998541424455974,
+      "loss": 0.9593754410743713,
+      "step": 1334
+    },
+    {
+      "epoch": 0.5764832793959007,
+      "grad_norm": 0.4572875201702118,
+      "learning_rate": 0.00019985147909534897,
+      "loss": 0.986197292804718,
+      "step": 1336
+    },
+    {
+      "epoch": 0.5773462783171521,
+      "grad_norm": 0.5153827667236328,
+      "learning_rate": 0.00019984879166636644,
+      "loss": 0.9163863658905029,
+      "step": 1338
+    },
+    {
+      "epoch": 0.5782092772384034,
+      "grad_norm": 0.4813650846481323,
+      "learning_rate": 0.00019984608015929792,
+      "loss": 0.8815995454788208,
+      "step": 1340
+    },
+    {
+      "epoch": 0.5790722761596548,
+      "grad_norm": 0.4319819211959839,
+      "learning_rate": 0.0001998433445747973,
+      "loss": 0.857044517993927,
+      "step": 1342
+    },
+    {
+      "epoch": 0.5799352750809061,
+      "grad_norm": 0.5128870010375977,
+      "learning_rate": 0.00019984058491352423,
+      "loss": 0.8939256072044373,
+      "step": 1344
+    },
+    {
+      "epoch": 0.5807982740021574,
+      "grad_norm": 0.41450315713882446,
+      "learning_rate": 0.0001998378011761442,
+      "loss": 0.9267327785491943,
+      "step": 1346
+    },
+    {
+      "epoch": 0.5816612729234089,
+      "grad_norm": 0.42916348576545715,
+      "learning_rate": 0.00019983499336332844,
+      "loss": 0.8494639992713928,
+      "step": 1348
+    },
+    {
+      "epoch": 0.5825242718446602,
+      "grad_norm": 0.43995746970176697,
+      "learning_rate": 0.00019983216147575412,
+      "loss": 0.9720427989959717,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5833872707659116,
+      "grad_norm": 0.5063773989677429,
+      "learning_rate": 0.00019982930551410411,
+      "loss": 0.9400854706764221,
+      "step": 1352
+    },
+    {
+      "epoch": 0.5842502696871629,
+      "grad_norm": 0.5029586553573608,
+      "learning_rate": 0.0001998264254790671,
+      "loss": 0.8657845258712769,
+      "step": 1354
+    },
+    {
+      "epoch": 0.5851132686084143,
+      "grad_norm": 0.45519232749938965,
+      "learning_rate": 0.00019982352137133764,
+      "loss": 0.8593506813049316,
+      "step": 1356
+    },
+    {
+      "epoch": 0.5859762675296656,
+      "grad_norm": 0.49116215109825134,
+      "learning_rate": 0.000199820593191616,
+      "loss": 0.8658114671707153,
+      "step": 1358
+    },
+    {
+      "epoch": 0.5868392664509169,
+      "grad_norm": 0.45347318053245544,
+      "learning_rate": 0.00019981764094060826,
+      "loss": 0.8044605255126953,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5877022653721683,
+      "grad_norm": 0.5191754698753357,
+      "learning_rate": 0.00019981466461902643,
+      "loss": 0.9176861047744751,
+      "step": 1362
+    },
+    {
+      "epoch": 0.5885652642934196,
+      "grad_norm": 0.4791528284549713,
+      "learning_rate": 0.00019981166422758818,
+      "loss": 0.8453370928764343,
+      "step": 1364
+    },
+    {
+      "epoch": 0.589428263214671,
+      "grad_norm": 0.5105116367340088,
+      "learning_rate": 0.00019980863976701705,
+      "loss": 0.9343777298927307,
+      "step": 1366
+    },
+    {
+      "epoch": 0.5902912621359223,
+      "grad_norm": 0.44593656063079834,
+      "learning_rate": 0.00019980559123804236,
+      "loss": 0.8950760960578918,
+      "step": 1368
+    },
+    {
+      "epoch": 0.5911542610571737,
+      "grad_norm": 0.4375658631324768,
+      "learning_rate": 0.0001998025186413993,
+      "loss": 0.8613521456718445,
+      "step": 1370
+    },
+    {
+      "epoch": 0.592017259978425,
+      "grad_norm": 0.5138815641403198,
+      "learning_rate": 0.00019979942197782878,
+      "loss": 0.8982083201408386,
+      "step": 1372
+    },
+    {
+      "epoch": 0.5928802588996763,
+      "grad_norm": 0.45473602414131165,
+      "learning_rate": 0.00019979630124807753,
+      "loss": 0.9372450709342957,
+      "step": 1374
+    },
+    {
+      "epoch": 0.5937432578209277,
+      "grad_norm": 0.4961191713809967,
+      "learning_rate": 0.00019979315645289814,
+      "loss": 0.8758652806282043,
+      "step": 1376
+    },
+    {
+      "epoch": 0.594606256742179,
+      "grad_norm": 0.5672827363014221,
+      "learning_rate": 0.00019978998759304895,
+      "loss": 0.9852207899093628,
+      "step": 1378
+    },
+    {
+      "epoch": 0.5954692556634305,
+      "grad_norm": 0.44907906651496887,
+      "learning_rate": 0.00019978679466929407,
+      "loss": 0.8451287746429443,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5963322545846818,
+      "grad_norm": 0.4759652316570282,
+      "learning_rate": 0.00019978357768240352,
+      "loss": 0.8381558656692505,
+      "step": 1382
+    },
+    {
+      "epoch": 0.5971952535059332,
+      "grad_norm": 0.4936048686504364,
+      "learning_rate": 0.00019978033663315304,
+      "loss": 0.8820816874504089,
+      "step": 1384
+    },
+    {
+      "epoch": 0.5980582524271845,
+      "grad_norm": 0.44983741641044617,
+      "learning_rate": 0.00019977707152232416,
+      "loss": 0.9156787991523743,
+      "step": 1386
+    },
+    {
+      "epoch": 0.5989212513484358,
+      "grad_norm": 0.45198705792427063,
+      "learning_rate": 0.0001997737823507043,
+      "loss": 0.8285194039344788,
+      "step": 1388
+    },
+    {
+      "epoch": 0.5997842502696872,
+      "grad_norm": 0.45788463950157166,
+      "learning_rate": 0.00019977046911908664,
+      "loss": 0.8109505772590637,
+      "step": 1390
+    },
+    {
+      "epoch": 0.6006472491909385,
+      "grad_norm": 0.4795142412185669,
+      "learning_rate": 0.0001997671318282701,
+      "loss": 0.8285947442054749,
+      "step": 1392
+    },
+    {
+      "epoch": 0.6015102481121899,
+      "grad_norm": 0.5026728510856628,
+      "learning_rate": 0.00019976377047905945,
+      "loss": 0.9497535228729248,
+      "step": 1394
+    },
+    {
+      "epoch": 0.6023732470334412,
+      "grad_norm": 0.4994853734970093,
+      "learning_rate": 0.0001997603850722653,
+      "loss": 0.9171916246414185,
+      "step": 1396
+    },
+    {
+      "epoch": 0.6032362459546926,
+      "grad_norm": 0.4789866507053375,
+      "learning_rate": 0.00019975697560870403,
+      "loss": 0.7894434928894043,
+      "step": 1398
+    },
+    {
+      "epoch": 0.6040992448759439,
+      "grad_norm": 0.42282742261886597,
+      "learning_rate": 0.0001997535420891978,
+      "loss": 0.8942429423332214,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6040992448759439,
+      "eval_loss": 0.9080492854118347,
+      "eval_runtime": 661.4597,
+      "eval_samples_per_second": 3.114,
+      "eval_steps_per_second": 3.114,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6049622437971952,
+      "grad_norm": 0.5789905190467834,
+      "learning_rate": 0.00019975008451457454,
+      "loss": 0.8938372731208801,
+      "step": 1402
+    },
+    {
+      "epoch": 0.6058252427184466,
+      "grad_norm": 0.46121683716773987,
+      "learning_rate": 0.00019974660288566814,
+      "loss": 0.8746235370635986,
+      "step": 1404
+    },
+    {
+      "epoch": 0.6066882416396979,
+      "grad_norm": 0.5195551514625549,
+      "learning_rate": 0.00019974309720331807,
+      "loss": 0.8650617003440857,
+      "step": 1406
+    },
+    {
+      "epoch": 0.6075512405609493,
+      "grad_norm": 0.46930259466171265,
+      "learning_rate": 0.00019973956746836976,
+      "loss": 0.8853039145469666,
+      "step": 1408
+    },
+    {
+      "epoch": 0.6084142394822006,
+      "grad_norm": 0.40869632363319397,
+      "learning_rate": 0.0001997360136816744,
+      "loss": 0.7865594029426575,
+      "step": 1410
+    },
+    {
+      "epoch": 0.609277238403452,
+      "grad_norm": 0.5398361086845398,
+      "learning_rate": 0.00019973243584408895,
+      "loss": 0.907535970211029,
+      "step": 1412
+    },
+    {
+      "epoch": 0.6101402373247033,
+      "grad_norm": 0.5110154747962952,
+      "learning_rate": 0.00019972883395647615,
+      "loss": 0.8682730197906494,
+      "step": 1414
+    },
+    {
+      "epoch": 0.6110032362459547,
+      "grad_norm": 0.44484639167785645,
+      "learning_rate": 0.00019972520801970467,
+      "loss": 0.8786011338233948,
+      "step": 1416
+    },
+    {
+      "epoch": 0.6118662351672061,
+      "grad_norm": 0.4768071472644806,
+      "learning_rate": 0.0001997215580346488,
+      "loss": 0.9021878242492676,
+      "step": 1418
+    },
+    {
+      "epoch": 0.6127292340884574,
+      "grad_norm": 0.43265241384506226,
+      "learning_rate": 0.0001997178840021888,
+      "loss": 0.7737482786178589,
+      "step": 1420
+    },
+    {
+      "epoch": 0.6135922330097088,
+      "grad_norm": 0.525692343711853,
+      "learning_rate": 0.0001997141859232106,
+      "loss": 0.876280665397644,
+      "step": 1422
+    },
+    {
+      "epoch": 0.6144552319309601,
+      "grad_norm": 0.48206865787506104,
+      "learning_rate": 0.00019971046379860594,
+      "loss": 0.8503577709197998,
+      "step": 1424
+    },
+    {
+      "epoch": 0.6153182308522115,
+      "grad_norm": 0.6032769680023193,
+      "learning_rate": 0.00019970671762927246,
+      "loss": 0.9459730982780457,
+      "step": 1426
+    },
+    {
+      "epoch": 0.6161812297734628,
+      "grad_norm": 0.4491981863975525,
+      "learning_rate": 0.0001997029474161135,
+      "loss": 0.8836647868156433,
+      "step": 1428
+    },
+    {
+      "epoch": 0.6170442286947141,
+      "grad_norm": 0.47503358125686646,
+      "learning_rate": 0.00019969915316003824,
+      "loss": 0.8614388108253479,
+      "step": 1430
+    },
+    {
+      "epoch": 0.6179072276159655,
+      "grad_norm": 0.44801047444343567,
+      "learning_rate": 0.00019969533486196162,
+      "loss": 0.8420360684394836,
+      "step": 1432
+    },
+    {
+      "epoch": 0.6187702265372168,
+      "grad_norm": 0.45057111978530884,
+      "learning_rate": 0.00019969149252280446,
+      "loss": 0.8256269693374634,
+      "step": 1434
+    },
+    {
+      "epoch": 0.6196332254584682,
+      "grad_norm": 0.4589645266532898,
+      "learning_rate": 0.00019968762614349327,
+      "loss": 0.9130199551582336,
+      "step": 1436
+    },
+    {
+      "epoch": 0.6204962243797195,
+      "grad_norm": 0.48914027214050293,
+      "learning_rate": 0.00019968373572496045,
+      "loss": 0.74083012342453,
+      "step": 1438
+    },
+    {
+      "epoch": 0.6213592233009708,
+      "grad_norm": 0.4582098424434662,
+      "learning_rate": 0.00019967982126814412,
+      "loss": 0.8538379669189453,
+      "step": 1440
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.48722779750823975,
+      "learning_rate": 0.00019967588277398823,
+      "loss": 0.8780114054679871,
+      "step": 1442
+    },
+    {
+      "epoch": 0.6230852211434735,
+      "grad_norm": 0.4291327893733978,
+      "learning_rate": 0.00019967192024344254,
+      "loss": 0.8341028690338135,
+      "step": 1444
+    },
+    {
+      "epoch": 0.623948220064725,
+      "grad_norm": 0.4773139953613281,
+      "learning_rate": 0.00019966793367746265,
+      "loss": 0.8651667237281799,
+      "step": 1446
+    },
+    {
+      "epoch": 0.6248112189859762,
+      "grad_norm": 0.45556166768074036,
+      "learning_rate": 0.00019966392307700986,
+      "loss": 0.8339929580688477,
+      "step": 1448
+    },
+    {
+      "epoch": 0.6256742179072277,
+      "grad_norm": 0.5126671195030212,
+      "learning_rate": 0.00019965988844305129,
+      "loss": 0.9129340052604675,
+      "step": 1450
+    },
+    {
+      "epoch": 0.626537216828479,
+      "grad_norm": 0.6067109704017639,
+      "learning_rate": 0.00019965582977655988,
+      "loss": 0.9057610034942627,
+      "step": 1452
+    },
+    {
+      "epoch": 0.6274002157497303,
+      "grad_norm": 0.46425968408584595,
+      "learning_rate": 0.00019965174707851438,
+      "loss": 0.874100387096405,
+      "step": 1454
+    },
+    {
+      "epoch": 0.6282632146709817,
+      "grad_norm": 0.481077641248703,
+      "learning_rate": 0.0001996476403498993,
+      "loss": 0.915635347366333,
+      "step": 1456
+    },
+    {
+      "epoch": 0.629126213592233,
+      "grad_norm": 0.47299909591674805,
+      "learning_rate": 0.000199643509591705,
+      "loss": 0.9059650301933289,
+      "step": 1458
+    },
+    {
+      "epoch": 0.6299892125134844,
+      "grad_norm": 0.48924630880355835,
+      "learning_rate": 0.00019963935480492753,
+      "loss": 0.9775188565254211,
+      "step": 1460
+    },
+    {
+      "epoch": 0.6308522114347357,
+      "grad_norm": 0.4407665431499481,
+      "learning_rate": 0.0001996351759905688,
+      "loss": 0.8950685858726501,
+      "step": 1462
+    },
+    {
+      "epoch": 0.6317152103559871,
+      "grad_norm": 0.5018318295478821,
+      "learning_rate": 0.00019963097314963657,
+      "loss": 0.8532119989395142,
+      "step": 1464
+    },
+    {
+      "epoch": 0.6325782092772384,
+      "grad_norm": 0.43245720863342285,
+      "learning_rate": 0.0001996267462831443,
+      "loss": 0.7775963544845581,
+      "step": 1466
+    },
+    {
+      "epoch": 0.6334412081984897,
+      "grad_norm": 0.5028865337371826,
+      "learning_rate": 0.00019962249539211125,
+      "loss": 0.8315839767456055,
+      "step": 1468
+    },
+    {
+      "epoch": 0.6343042071197411,
+      "grad_norm": 0.4697185754776001,
+      "learning_rate": 0.0001996182204775626,
+      "loss": 0.849076509475708,
+      "step": 1470
+    },
+    {
+      "epoch": 0.6351672060409924,
+      "grad_norm": 0.46725034713745117,
+      "learning_rate": 0.00019961392154052912,
+      "loss": 0.8828577995300293,
+      "step": 1472
+    },
+    {
+      "epoch": 0.6360302049622438,
+      "grad_norm": 0.4301203489303589,
+      "learning_rate": 0.00019960959858204754,
+      "loss": 0.850115954875946,
+      "step": 1474
+    },
+    {
+      "epoch": 0.6368932038834951,
+      "grad_norm": 0.46635881066322327,
+      "learning_rate": 0.0001996052516031603,
+      "loss": 0.7912618517875671,
+      "step": 1476
+    },
+    {
+      "epoch": 0.6377562028047465,
+      "grad_norm": 0.44143620133399963,
+      "learning_rate": 0.00019960088060491565,
+      "loss": 0.9072504639625549,
+      "step": 1478
+    },
+    {
+      "epoch": 0.6386192017259978,
+      "grad_norm": 0.47458893060684204,
+      "learning_rate": 0.00019959648558836763,
+      "loss": 0.8976638317108154,
+      "step": 1480
+    },
+    {
+      "epoch": 0.6394822006472491,
+      "grad_norm": 0.4596816897392273,
+      "learning_rate": 0.00019959206655457612,
+      "loss": 0.8142043352127075,
+      "step": 1482
+    },
+    {
+      "epoch": 0.6403451995685006,
+      "grad_norm": 0.4839977025985718,
+      "learning_rate": 0.0001995876235046067,
+      "loss": 0.860643744468689,
+      "step": 1484
+    },
+    {
+      "epoch": 0.6412081984897519,
+      "grad_norm": 0.3542814552783966,
+      "learning_rate": 0.00019958315643953085,
+      "loss": 0.7586524486541748,
+      "step": 1486
+    },
+    {
+      "epoch": 0.6420711974110033,
+      "grad_norm": 0.5423269271850586,
+      "learning_rate": 0.00019957866536042572,
+      "loss": 0.9353570342063904,
+      "step": 1488
+    },
+    {
+      "epoch": 0.6429341963322546,
+      "grad_norm": 0.4580909013748169,
+      "learning_rate": 0.00019957415026837437,
+      "loss": 0.9919291138648987,
+      "step": 1490
+    },
+    {
+      "epoch": 0.643797195253506,
+      "grad_norm": 0.4211732745170593,
+      "learning_rate": 0.00019956961116446555,
+      "loss": 0.8720914125442505,
+      "step": 1492
+    },
+    {
+      "epoch": 0.6446601941747573,
+      "grad_norm": 0.4583161175251007,
+      "learning_rate": 0.00019956504804979384,
+      "loss": 0.8661212921142578,
+      "step": 1494
+    },
+    {
+      "epoch": 0.6455231930960086,
+      "grad_norm": 0.4359884262084961,
+      "learning_rate": 0.00019956046092545966,
+      "loss": 0.8170996308326721,
+      "step": 1496
+    },
+    {
+      "epoch": 0.64638619201726,
+      "grad_norm": 0.4642556607723236,
+      "learning_rate": 0.00019955584979256913,
+      "loss": 0.8607422113418579,
+      "step": 1498
+    },
+    {
+      "epoch": 0.6472491909385113,
+      "grad_norm": 0.4496007561683655,
+      "learning_rate": 0.00019955121465223426,
+      "loss": 0.837529182434082,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6472491909385113,
+      "eval_loss": 0.8972997665405273,
+      "eval_runtime": 649.796,
+      "eval_samples_per_second": 3.17,
+      "eval_steps_per_second": 3.17,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6481121898597627,
+      "grad_norm": 0.48363205790519714,
+      "learning_rate": 0.0001995465555055727,
+      "loss": 0.9355250000953674,
+      "step": 1502
+    },
+    {
+      "epoch": 0.648975188781014,
+      "grad_norm": 0.44681695103645325,
+      "learning_rate": 0.0001995418723537081,
+      "loss": 0.8286949396133423,
+      "step": 1504
+    },
+    {
+      "epoch": 0.6498381877022654,
+      "grad_norm": 0.5110394358634949,
+      "learning_rate": 0.00019953716519776967,
+      "loss": 0.890398383140564,
+      "step": 1506
+    },
+    {
+      "epoch": 0.6507011866235167,
+      "grad_norm": 0.4353160262107849,
+      "learning_rate": 0.00019953243403889257,
+      "loss": 0.8117311000823975,
+      "step": 1508
+    },
+    {
+      "epoch": 0.651564185544768,
+      "grad_norm": 0.4731789231300354,
+      "learning_rate": 0.0001995276788782177,
+      "loss": 0.8255904316902161,
+      "step": 1510
+    },
+    {
+      "epoch": 0.6524271844660194,
+      "grad_norm": 0.5447185039520264,
+      "learning_rate": 0.00019952289971689177,
+      "loss": 0.9371263384819031,
+      "step": 1512
+    },
+    {
+      "epoch": 0.6532901833872707,
+      "grad_norm": 0.47616517543792725,
+      "learning_rate": 0.0001995180965560672,
+      "loss": 0.8532910943031311,
+      "step": 1514
+    },
+    {
+      "epoch": 0.6541531823085222,
+      "grad_norm": 0.4412213861942291,
+      "learning_rate": 0.0001995132693969023,
+      "loss": 0.8799141645431519,
+      "step": 1516
+    },
+    {
+      "epoch": 0.6550161812297735,
+      "grad_norm": 0.469911128282547,
+      "learning_rate": 0.00019950841824056107,
+      "loss": 0.8395764827728271,
+      "step": 1518
+    },
+    {
+      "epoch": 0.6558791801510249,
+      "grad_norm": 0.5236243009567261,
+      "learning_rate": 0.00019950354308821336,
+      "loss": 0.9556697010993958,
+      "step": 1520
+    },
+    {
+      "epoch": 0.6567421790722762,
+      "grad_norm": 0.4441990256309509,
+      "learning_rate": 0.00019949864394103482,
+      "loss": 0.8524283170700073,
+      "step": 1522
+    },
+    {
+      "epoch": 0.6576051779935275,
+      "grad_norm": 0.4173077940940857,
+      "learning_rate": 0.00019949372080020682,
+      "loss": 0.9213772416114807,
+      "step": 1524
+    },
+    {
+      "epoch": 0.6584681769147789,
+      "grad_norm": 0.4404120147228241,
+      "learning_rate": 0.00019948877366691658,
+      "loss": 0.9236897230148315,
+      "step": 1526
+    },
+    {
+      "epoch": 0.6593311758360302,
+      "grad_norm": 0.4586230516433716,
+      "learning_rate": 0.00019948380254235706,
+      "loss": 0.8373230695724487,
+      "step": 1528
+    },
+    {
+      "epoch": 0.6601941747572816,
+      "grad_norm": 0.4136028587818146,
+      "learning_rate": 0.00019947880742772703,
+      "loss": 0.8256528377532959,
+      "step": 1530
+    },
+    {
+      "epoch": 0.6610571736785329,
+      "grad_norm": 0.5007129907608032,
+      "learning_rate": 0.00019947378832423107,
+      "loss": 0.8580789566040039,
+      "step": 1532
+    },
+    {
+      "epoch": 0.6619201725997842,
+      "grad_norm": 0.39050203561782837,
+      "learning_rate": 0.00019946874523307947,
+      "loss": 0.7647744417190552,
+      "step": 1534
+    },
+    {
+      "epoch": 0.6627831715210356,
+      "grad_norm": 0.4640588164329529,
+      "learning_rate": 0.00019946367815548835,
+      "loss": 0.9042545557022095,
+      "step": 1536
+    },
+    {
+      "epoch": 0.6636461704422869,
+      "grad_norm": 0.5304957032203674,
+      "learning_rate": 0.00019945858709267963,
+      "loss": 0.9114110469818115,
+      "step": 1538
+    },
+    {
+      "epoch": 0.6645091693635383,
+      "grad_norm": 0.5426004528999329,
+      "learning_rate": 0.000199453472045881,
+      "loss": 0.8239460587501526,
+      "step": 1540
+    },
+    {
+      "epoch": 0.6653721682847896,
+      "grad_norm": 0.44893568754196167,
+      "learning_rate": 0.00019944833301632593,
+      "loss": 0.8091367483139038,
+      "step": 1542
+    },
+    {
+      "epoch": 0.666235167206041,
+      "grad_norm": 0.4294016361236572,
+      "learning_rate": 0.00019944317000525366,
+      "loss": 0.9202280640602112,
+      "step": 1544
+    },
+    {
+      "epoch": 0.6670981661272923,
+      "grad_norm": 0.449633926153183,
+      "learning_rate": 0.00019943798301390927,
+      "loss": 0.8884767889976501,
+      "step": 1546
+    },
+    {
+      "epoch": 0.6679611650485436,
+      "grad_norm": 0.4516827166080475,
+      "learning_rate": 0.0001994327720435435,
+      "loss": 0.8390879034996033,
+      "step": 1548
+    },
+    {
+      "epoch": 0.668824163969795,
+      "grad_norm": 0.422270268201828,
+      "learning_rate": 0.000199427537095413,
+      "loss": 0.7388033270835876,
+      "step": 1550
+    },
+    {
+      "epoch": 0.6696871628910464,
+      "grad_norm": 0.580563485622406,
+      "learning_rate": 0.00019942227817078015,
+      "loss": 0.9268350601196289,
+      "step": 1552
+    },
+    {
+      "epoch": 0.6705501618122978,
+      "grad_norm": 0.4436347782611847,
+      "learning_rate": 0.00019941699527091316,
+      "loss": 0.7978561520576477,
+      "step": 1554
+    },
+    {
+      "epoch": 0.6714131607335491,
+      "grad_norm": 0.4149787127971649,
+      "learning_rate": 0.0001994116883970859,
+      "loss": 0.8229286670684814,
+      "step": 1556
+    },
+    {
+      "epoch": 0.6722761596548005,
+      "grad_norm": 0.49915504455566406,
+      "learning_rate": 0.00019940635755057813,
+      "loss": 0.8554545640945435,
+      "step": 1558
+    },
+    {
+      "epoch": 0.6731391585760518,
+      "grad_norm": 0.45326656103134155,
+      "learning_rate": 0.00019940100273267537,
+      "loss": 0.9135572910308838,
+      "step": 1560
+    },
+    {
+      "epoch": 0.6740021574973031,
+      "grad_norm": 0.48639237880706787,
+      "learning_rate": 0.0001993956239446689,
+      "loss": 0.7769742012023926,
+      "step": 1562
+    },
+    {
+      "epoch": 0.6748651564185545,
+      "grad_norm": 0.5072791576385498,
+      "learning_rate": 0.0001993902211878558,
+      "loss": 0.9626237154006958,
+      "step": 1564
+    },
+    {
+      "epoch": 0.6757281553398058,
+      "grad_norm": 0.4646652638912201,
+      "learning_rate": 0.00019938479446353892,
+      "loss": 0.8506941199302673,
+      "step": 1566
+    },
+    {
+      "epoch": 0.6765911542610572,
+      "grad_norm": 0.4343051314353943,
+      "learning_rate": 0.00019937934377302688,
+      "loss": 0.8172947764396667,
+      "step": 1568
+    },
+    {
+      "epoch": 0.6774541531823085,
+      "grad_norm": 0.46890193223953247,
+      "learning_rate": 0.00019937386911763407,
+      "loss": 0.9215856790542603,
+      "step": 1570
+    },
+    {
+      "epoch": 0.6783171521035599,
+      "grad_norm": 0.5121113061904907,
+      "learning_rate": 0.0001993683704986807,
+      "loss": 0.8099892139434814,
+      "step": 1572
+    },
+    {
+      "epoch": 0.6791801510248112,
+      "grad_norm": 0.4652405083179474,
+      "learning_rate": 0.0001993628479174928,
+      "loss": 0.8675104975700378,
+      "step": 1574
+    },
+    {
+      "epoch": 0.6800431499460625,
+      "grad_norm": 0.4599422812461853,
+      "learning_rate": 0.00019935730137540198,
+      "loss": 0.7938929200172424,
+      "step": 1576
+    },
+    {
+      "epoch": 0.6809061488673139,
+      "grad_norm": 0.4738059937953949,
+      "learning_rate": 0.0001993517308737459,
+      "loss": 0.8610570430755615,
+      "step": 1578
+    },
+    {
+      "epoch": 0.6817691477885652,
+      "grad_norm": 0.5161214470863342,
+      "learning_rate": 0.00019934613641386776,
+      "loss": 0.9199413657188416,
+      "step": 1580
+    },
+    {
+      "epoch": 0.6826321467098166,
+      "grad_norm": 0.4284999370574951,
+      "learning_rate": 0.00019934051799711672,
+      "loss": 0.771649181842804,
+      "step": 1582
+    },
+    {
+      "epoch": 0.683495145631068,
+      "grad_norm": 0.5117548704147339,
+      "learning_rate": 0.00019933487562484757,
+      "loss": 0.8861327767372131,
+      "step": 1584
+    },
+    {
+      "epoch": 0.6843581445523194,
+      "grad_norm": 0.4964369833469391,
+      "learning_rate": 0.00019932920929842095,
+      "loss": 0.806983232498169,
+      "step": 1586
+    },
+    {
+      "epoch": 0.6852211434735707,
+      "grad_norm": 0.4699532091617584,
+      "learning_rate": 0.00019932351901920327,
+      "loss": 0.7963525652885437,
+      "step": 1588
+    },
+    {
+      "epoch": 0.686084142394822,
+      "grad_norm": 0.5329220294952393,
+      "learning_rate": 0.00019931780478856678,
+      "loss": 0.9406430721282959,
+      "step": 1590
+    },
+    {
+      "epoch": 0.6869471413160734,
+      "grad_norm": 0.49823835492134094,
+      "learning_rate": 0.00019931206660788936,
+      "loss": 0.8517770171165466,
+      "step": 1592
+    },
+    {
+      "epoch": 0.6878101402373247,
+      "grad_norm": 0.45245134830474854,
+      "learning_rate": 0.00019930630447855482,
+      "loss": 0.8703644275665283,
+      "step": 1594
+    },
+    {
+      "epoch": 0.6886731391585761,
+      "grad_norm": 0.47524577379226685,
+      "learning_rate": 0.0001993005184019526,
+      "loss": 0.9035283327102661,
+      "step": 1596
+    },
+    {
+      "epoch": 0.6895361380798274,
+      "grad_norm": 0.4537610411643982,
+      "learning_rate": 0.00019929470837947802,
+      "loss": 0.9173959493637085,
+      "step": 1598
+    },
+    {
+      "epoch": 0.6903991370010788,
+      "grad_norm": 0.42469722032546997,
+      "learning_rate": 0.00019928887441253212,
+      "loss": 0.8573579788208008,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6903991370010788,
+      "eval_loss": 0.8880587220191956,
+      "eval_runtime": 653.9515,
+      "eval_samples_per_second": 3.15,
+      "eval_steps_per_second": 3.15,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6912621359223301,
+      "grad_norm": 0.4388251304626465,
+      "learning_rate": 0.00019928301650252176,
+      "loss": 0.849348247051239,
+      "step": 1602
+    },
+    {
+      "epoch": 0.6921251348435814,
+      "grad_norm": 0.46086886525154114,
+      "learning_rate": 0.00019927713465085956,
+      "loss": 0.8298451900482178,
+      "step": 1604
+    },
+    {
+      "epoch": 0.6929881337648328,
+      "grad_norm": 0.42972785234451294,
+      "learning_rate": 0.00019927122885896387,
+      "loss": 0.8860712647438049,
+      "step": 1606
+    },
+    {
+      "epoch": 0.6938511326860841,
+      "grad_norm": 0.43009471893310547,
+      "learning_rate": 0.00019926529912825888,
+      "loss": 0.7972728610038757,
+      "step": 1608
+    },
+    {
+      "epoch": 0.6947141316073355,
+      "grad_norm": 0.3705308437347412,
+      "learning_rate": 0.00019925934546017446,
+      "loss": 0.8661653995513916,
+      "step": 1610
+    },
+    {
+      "epoch": 0.6955771305285868,
+      "grad_norm": 0.405208945274353,
+      "learning_rate": 0.00019925336785614635,
+      "loss": 0.8350111246109009,
+      "step": 1612
+    },
+    {
+      "epoch": 0.6964401294498382,
+      "grad_norm": 0.4773033857345581,
+      "learning_rate": 0.00019924736631761602,
+      "loss": 0.7920925617218018,
+      "step": 1614
+    },
+    {
+      "epoch": 0.6973031283710895,
+      "grad_norm": 0.4682428240776062,
+      "learning_rate": 0.00019924134084603075,
+      "loss": 0.8644304871559143,
+      "step": 1616
+    },
+    {
+      "epoch": 0.6981661272923408,
+      "grad_norm": 0.5694834589958191,
+      "learning_rate": 0.00019923529144284346,
+      "loss": 0.9897904992103577,
+      "step": 1618
+    },
+    {
+      "epoch": 0.6990291262135923,
+      "grad_norm": 0.40137484669685364,
+      "learning_rate": 0.00019922921810951302,
+      "loss": 0.6910083293914795,
+      "step": 1620
+    },
+    {
+      "epoch": 0.6998921251348436,
+      "grad_norm": 0.42076537013053894,
+      "learning_rate": 0.000199223120847504,
+      "loss": 0.8295826315879822,
+      "step": 1622
+    },
+    {
+      "epoch": 0.700755124056095,
+      "grad_norm": 0.4473017752170563,
+      "learning_rate": 0.00019921699965828662,
+      "loss": 0.820871889591217,
+      "step": 1624
+    },
+    {
+      "epoch": 0.7016181229773463,
+      "grad_norm": 0.43914029002189636,
+      "learning_rate": 0.00019921085454333706,
+      "loss": 0.8319019079208374,
+      "step": 1626
+    },
+    {
+      "epoch": 0.7024811218985976,
+      "grad_norm": 0.4758487939834595,
+      "learning_rate": 0.0001992046855041372,
+      "loss": 0.8589251041412354,
+      "step": 1628
+    },
+    {
+      "epoch": 0.703344120819849,
+      "grad_norm": 0.506401538848877,
+      "learning_rate": 0.00019919849254217465,
+      "loss": 0.9219205975532532,
+      "step": 1630
+    },
+    {
+      "epoch": 0.7042071197411003,
+      "grad_norm": 0.4397984445095062,
+      "learning_rate": 0.00019919227565894277,
+      "loss": 0.7824978232383728,
+      "step": 1632
+    },
+    {
+      "epoch": 0.7050701186623517,
+      "grad_norm": 0.3879252076148987,
+      "learning_rate": 0.0001991860348559408,
+      "loss": 0.8472069501876831,
+      "step": 1634
+    },
+    {
+      "epoch": 0.705933117583603,
+      "grad_norm": 0.42238810658454895,
+      "learning_rate": 0.00019917977013467368,
+      "loss": 0.824957013130188,
+      "step": 1636
+    },
+    {
+      "epoch": 0.7067961165048544,
+      "grad_norm": 0.5235037207603455,
+      "learning_rate": 0.00019917348149665206,
+      "loss": 0.9490993022918701,
+      "step": 1638
+    },
+    {
+      "epoch": 0.7076591154261057,
+      "grad_norm": 0.5195287466049194,
+      "learning_rate": 0.0001991671689433925,
+      "loss": 0.960905909538269,
+      "step": 1640
+    },
+    {
+      "epoch": 0.708522114347357,
+      "grad_norm": 0.5016481876373291,
+      "learning_rate": 0.00019916083247641716,
+      "loss": 0.8961218595504761,
+      "step": 1642
+    },
+    {
+      "epoch": 0.7093851132686084,
+      "grad_norm": 0.5510191321372986,
+      "learning_rate": 0.00019915447209725408,
+      "loss": 0.8883417844772339,
+      "step": 1644
+    },
+    {
+      "epoch": 0.7102481121898597,
+      "grad_norm": 0.4492250084877014,
+      "learning_rate": 0.0001991480878074371,
+      "loss": 0.7968636751174927,
+      "step": 1646
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.4189683496952057,
+      "learning_rate": 0.00019914167960850563,
+      "loss": 0.7869221568107605,
+      "step": 1648
+    },
+    {
+      "epoch": 0.7119741100323624,
+      "grad_norm": 0.4590536653995514,
+      "learning_rate": 0.0001991352475020051,
+      "loss": 0.8423646092414856,
+      "step": 1650
+    },
+    {
+      "epoch": 0.7128371089536139,
+      "grad_norm": 0.5058966875076294,
+      "learning_rate": 0.00019912879148948652,
+      "loss": 0.895459771156311,
+      "step": 1652
+    },
+    {
+      "epoch": 0.7137001078748652,
+      "grad_norm": 0.4904550313949585,
+      "learning_rate": 0.00019912231157250676,
+      "loss": 0.8737894296646118,
+      "step": 1654
+    },
+    {
+      "epoch": 0.7145631067961165,
+      "grad_norm": 0.4670710861682892,
+      "learning_rate": 0.0001991158077526284,
+      "loss": 0.8019732236862183,
+      "step": 1656
+    },
+    {
+      "epoch": 0.7154261057173679,
+      "grad_norm": 0.530343770980835,
+      "learning_rate": 0.00019910928003141984,
+      "loss": 0.9474499821662903,
+      "step": 1658
+    },
+    {
+      "epoch": 0.7162891046386192,
+      "grad_norm": 0.4250960052013397,
+      "learning_rate": 0.00019910272841045518,
+      "loss": 0.8738601803779602,
+      "step": 1660
+    },
+    {
+      "epoch": 0.7171521035598706,
+      "grad_norm": 0.4896513819694519,
+      "learning_rate": 0.0001990961528913143,
+      "loss": 0.9578261971473694,
+      "step": 1662
+    },
+    {
+      "epoch": 0.7180151024811219,
+      "grad_norm": 0.4999626576900482,
+      "learning_rate": 0.00019908955347558291,
+      "loss": 0.8116445541381836,
+      "step": 1664
+    },
+    {
+      "epoch": 0.7188781014023733,
+      "grad_norm": 0.4335242807865143,
+      "learning_rate": 0.00019908293016485237,
+      "loss": 0.8783043622970581,
+      "step": 1666
+    },
+    {
+      "epoch": 0.7197411003236246,
+      "grad_norm": 0.43542763590812683,
+      "learning_rate": 0.00019907628296071992,
+      "loss": 0.8223029375076294,
+      "step": 1668
+    },
+    {
+      "epoch": 0.7206040992448759,
+      "grad_norm": 0.4907461702823639,
+      "learning_rate": 0.00019906961186478842,
+      "loss": 1.0053197145462036,
+      "step": 1670
+    },
+    {
+      "epoch": 0.7214670981661273,
+      "grad_norm": 0.4054848253726959,
+      "learning_rate": 0.00019906291687866667,
+      "loss": 0.8107786178588867,
+      "step": 1672
+    },
+    {
+      "epoch": 0.7223300970873786,
+      "grad_norm": 0.3818599283695221,
+      "learning_rate": 0.0001990561980039691,
+      "loss": 0.780781626701355,
+      "step": 1674
+    },
+    {
+      "epoch": 0.72319309600863,
+      "grad_norm": 0.4128594994544983,
+      "learning_rate": 0.00019904945524231587,
+      "loss": 0.8189221620559692,
+      "step": 1676
+    },
+    {
+      "epoch": 0.7240560949298813,
+      "grad_norm": 0.46902593970298767,
+      "learning_rate": 0.0001990426885953331,
+      "loss": 0.83652263879776,
+      "step": 1678
+    },
+    {
+      "epoch": 0.7249190938511327,
+      "grad_norm": 0.49305564165115356,
+      "learning_rate": 0.00019903589806465242,
+      "loss": 0.8057956695556641,
+      "step": 1680
+    },
+    {
+      "epoch": 0.725782092772384,
+      "grad_norm": 0.44408300518989563,
+      "learning_rate": 0.0001990290836519114,
+      "loss": 0.8523716926574707,
+      "step": 1682
+    },
+    {
+      "epoch": 0.7266450916936353,
+      "grad_norm": 0.5211108922958374,
+      "learning_rate": 0.00019902224535875326,
+      "loss": 0.9179236888885498,
+      "step": 1684
+    },
+    {
+      "epoch": 0.7275080906148867,
+      "grad_norm": 0.4736526608467102,
+      "learning_rate": 0.00019901538318682705,
+      "loss": 0.8229476809501648,
+      "step": 1686
+    },
+    {
+      "epoch": 0.728371089536138,
+      "grad_norm": 0.541716992855072,
+      "learning_rate": 0.00019900849713778756,
+      "loss": 0.924200713634491,
+      "step": 1688
+    },
+    {
+      "epoch": 0.7292340884573895,
+      "grad_norm": 0.4524400532245636,
+      "learning_rate": 0.00019900158721329532,
+      "loss": 0.88961261510849,
+      "step": 1690
+    },
+    {
+      "epoch": 0.7300970873786408,
+      "grad_norm": 0.45256128907203674,
+      "learning_rate": 0.00019899465341501662,
+      "loss": 0.8491015434265137,
+      "step": 1692
+    },
+    {
+      "epoch": 0.7309600862998922,
+      "grad_norm": 0.5346773266792297,
+      "learning_rate": 0.0001989876957446235,
+      "loss": 0.8833339810371399,
+      "step": 1694
+    },
+    {
+      "epoch": 0.7318230852211435,
+      "grad_norm": 0.4696357846260071,
+      "learning_rate": 0.0001989807142037938,
+      "loss": 0.8535294532775879,
+      "step": 1696
+    },
+    {
+      "epoch": 0.7326860841423948,
+      "grad_norm": 0.4304637908935547,
+      "learning_rate": 0.0001989737087942111,
+      "loss": 0.8273076415061951,
+      "step": 1698
+    },
+    {
+      "epoch": 0.7335490830636462,
+      "grad_norm": 0.5085629224777222,
+      "learning_rate": 0.00019896667951756466,
+      "loss": 0.8759240508079529,
+      "step": 1700
+    },
+    {
+      "epoch": 0.7335490830636462,
+      "eval_loss": 0.879119336605072,
+      "eval_runtime": 663.0553,
+      "eval_samples_per_second": 3.107,
+      "eval_steps_per_second": 3.107,
+      "step": 1700
+    },
+    {
+      "epoch": 0.7344120819848975,
+      "grad_norm": 0.484223872423172,
+      "learning_rate": 0.00019895962637554964,
+      "loss": 0.852645218372345,
+      "step": 1702
+    },
+    {
+      "epoch": 0.7352750809061489,
+      "grad_norm": 0.4819294214248657,
+      "learning_rate": 0.0001989525493698668,
+      "loss": 0.878247857093811,
+      "step": 1704
+    },
+    {
+      "epoch": 0.7361380798274002,
+      "grad_norm": 0.4170311689376831,
+      "learning_rate": 0.00019894544850222276,
+      "loss": 0.8964285254478455,
+      "step": 1706
+    },
+    {
+      "epoch": 0.7370010787486516,
+      "grad_norm": 0.42712801694869995,
+      "learning_rate": 0.0001989383237743299,
+      "loss": 0.7479548454284668,
+      "step": 1708
+    },
+    {
+      "epoch": 0.7378640776699029,
+      "grad_norm": 0.5051686763763428,
+      "learning_rate": 0.00019893117518790624,
+      "loss": 0.8190052509307861,
+      "step": 1710
+    },
+    {
+      "epoch": 0.7387270765911542,
+      "grad_norm": 0.44053253531455994,
+      "learning_rate": 0.0001989240027446757,
+      "loss": 0.8646742105484009,
+      "step": 1712
+    },
+    {
+      "epoch": 0.7395900755124056,
+      "grad_norm": 0.4451025724411011,
+      "learning_rate": 0.00019891680644636782,
+      "loss": 0.874261736869812,
+      "step": 1714
+    },
+    {
+      "epoch": 0.7404530744336569,
+      "grad_norm": 0.4590521454811096,
+      "learning_rate": 0.00019890958629471798,
+      "loss": 0.8892465233802795,
+      "step": 1716
+    },
+    {
+      "epoch": 0.7413160733549083,
+      "grad_norm": 0.39169448614120483,
+      "learning_rate": 0.00019890234229146732,
+      "loss": 0.7031586766242981,
+      "step": 1718
+    },
+    {
+      "epoch": 0.7421790722761596,
+      "grad_norm": 0.46946024894714355,
+      "learning_rate": 0.00019889507443836266,
+      "loss": 0.8548433184623718,
+      "step": 1720
+    },
+    {
+      "epoch": 0.7430420711974111,
+      "grad_norm": 0.42404699325561523,
+      "learning_rate": 0.0001988877827371566,
+      "loss": 0.8231223821640015,
+      "step": 1722
+    },
+    {
+      "epoch": 0.7439050701186624,
+      "grad_norm": 0.40419483184814453,
+      "learning_rate": 0.00019888046718960755,
+      "loss": 0.8443762063980103,
+      "step": 1724
+    },
+    {
+      "epoch": 0.7447680690399137,
+      "grad_norm": 0.4550437927246094,
+      "learning_rate": 0.0001988731277974796,
+      "loss": 0.8787111639976501,
+      "step": 1726
+    },
+    {
+      "epoch": 0.7456310679611651,
+      "grad_norm": 0.42264053225517273,
+      "learning_rate": 0.0001988657645625426,
+      "loss": 0.8440850377082825,
+      "step": 1728
+    },
+    {
+      "epoch": 0.7464940668824164,
+      "grad_norm": 0.4638359844684601,
+      "learning_rate": 0.0001988583774865721,
+      "loss": 0.839216947555542,
+      "step": 1730
+    },
+    {
+      "epoch": 0.7473570658036678,
+      "grad_norm": 0.42644429206848145,
+      "learning_rate": 0.0001988509665713496,
+      "loss": 0.8011161684989929,
+      "step": 1732
+    },
+    {
+      "epoch": 0.7482200647249191,
+      "grad_norm": 0.36932024359703064,
+      "learning_rate": 0.0001988435318186621,
+      "loss": 0.850246787071228,
+      "step": 1734
+    },
+    {
+      "epoch": 0.7490830636461704,
+      "grad_norm": 0.4771935045719147,
+      "learning_rate": 0.00019883607323030252,
+      "loss": 0.7782483100891113,
+      "step": 1736
+    },
+    {
+      "epoch": 0.7499460625674218,
+      "grad_norm": 0.40007370710372925,
+      "learning_rate": 0.00019882859080806942,
+      "loss": 0.8337594866752625,
+      "step": 1738
+    },
+    {
+      "epoch": 0.7508090614886731,
+      "grad_norm": 0.5007418394088745,
+      "learning_rate": 0.00019882108455376716,
+      "loss": 0.8287386894226074,
+      "step": 1740
+    },
+    {
+      "epoch": 0.7516720604099245,
+      "grad_norm": 0.43999138474464417,
+      "learning_rate": 0.00019881355446920584,
+      "loss": 0.8655616044998169,
+      "step": 1742
+    },
+    {
+      "epoch": 0.7525350593311758,
+      "grad_norm": 0.5115824937820435,
+      "learning_rate": 0.00019880600055620135,
+      "loss": 0.8695262670516968,
+      "step": 1744
+    },
+    {
+      "epoch": 0.7533980582524272,
+      "grad_norm": 0.5035707950592041,
+      "learning_rate": 0.0001987984228165752,
+      "loss": 0.9207013845443726,
+      "step": 1746
+    },
+    {
+      "epoch": 0.7542610571736785,
+      "grad_norm": 0.4689575731754303,
+      "learning_rate": 0.0001987908212521548,
+      "loss": 0.8798729777336121,
+      "step": 1748
+    },
+    {
+      "epoch": 0.7551240560949298,
+      "grad_norm": 0.4730616509914398,
+      "learning_rate": 0.00019878319586477322,
+      "loss": 0.7737767696380615,
+      "step": 1750
+    },
+    {
+      "epoch": 0.7559870550161812,
+      "grad_norm": 0.49012845754623413,
+      "learning_rate": 0.00019877554665626926,
+      "loss": 0.929466187953949,
+      "step": 1752
+    },
+    {
+      "epoch": 0.7568500539374325,
+      "grad_norm": 0.43468761444091797,
+      "learning_rate": 0.0001987678736284875,
+      "loss": 0.8155670166015625,
+      "step": 1754
+    },
+    {
+      "epoch": 0.757713052858684,
+      "grad_norm": 0.507399320602417,
+      "learning_rate": 0.00019876017678327826,
+      "loss": 0.8082395195960999,
+      "step": 1756
+    },
+    {
+      "epoch": 0.7585760517799353,
+      "grad_norm": 0.4733552634716034,
+      "learning_rate": 0.0001987524561224976,
+      "loss": 0.8905934691429138,
+      "step": 1758
+    },
+    {
+      "epoch": 0.7594390507011867,
+      "grad_norm": 0.4670012891292572,
+      "learning_rate": 0.00019874471164800733,
+      "loss": 0.8794633746147156,
+      "step": 1760
+    },
+    {
+      "epoch": 0.760302049622438,
+      "grad_norm": 0.4951624572277069,
+      "learning_rate": 0.000198736943361675,
+      "loss": 0.8413973450660706,
+      "step": 1762
+    },
+    {
+      "epoch": 0.7611650485436893,
+      "grad_norm": 0.5478648543357849,
+      "learning_rate": 0.00019872915126537387,
+      "loss": 0.9067897200584412,
+      "step": 1764
+    },
+    {
+      "epoch": 0.7620280474649407,
+      "grad_norm": 0.48215776681900024,
+      "learning_rate": 0.000198721335360983,
+      "loss": 0.8932394981384277,
+      "step": 1766
+    },
+    {
+      "epoch": 0.762891046386192,
+      "grad_norm": 0.4688864052295685,
+      "learning_rate": 0.00019871349565038715,
+      "loss": 0.8496726751327515,
+      "step": 1768
+    },
+    {
+      "epoch": 0.7637540453074434,
+      "grad_norm": 0.4728260636329651,
+      "learning_rate": 0.0001987056321354768,
+      "loss": 0.9232800602912903,
+      "step": 1770
+    },
+    {
+      "epoch": 0.7646170442286947,
+      "grad_norm": 0.44501692056655884,
+      "learning_rate": 0.00019869774481814828,
+      "loss": 0.849755585193634,
+      "step": 1772
+    },
+    {
+      "epoch": 0.7654800431499461,
+      "grad_norm": 0.4189201593399048,
+      "learning_rate": 0.00019868983370030348,
+      "loss": 0.8258485794067383,
+      "step": 1774
+    },
+    {
+      "epoch": 0.7663430420711974,
+      "grad_norm": 0.5144591927528381,
+      "learning_rate": 0.00019868189878385016,
+      "loss": 0.8762873411178589,
+      "step": 1776
+    },
+    {
+      "epoch": 0.7672060409924487,
+      "grad_norm": 0.5048011541366577,
+      "learning_rate": 0.00019867394007070188,
+      "loss": 0.8732464909553528,
+      "step": 1778
+    },
+    {
+      "epoch": 0.7680690399137001,
+      "grad_norm": 0.41639819741249084,
+      "learning_rate": 0.00019866595756277774,
+      "loss": 0.8732751607894897,
+      "step": 1780
+    },
+    {
+      "epoch": 0.7689320388349514,
+      "grad_norm": 0.526757538318634,
+      "learning_rate": 0.00019865795126200271,
+      "loss": 0.8453729748725891,
+      "step": 1782
+    },
+    {
+      "epoch": 0.7697950377562028,
+      "grad_norm": 0.47041091322898865,
+      "learning_rate": 0.0001986499211703075,
+      "loss": 0.8780192732810974,
+      "step": 1784
+    },
+    {
+      "epoch": 0.7706580366774541,
+      "grad_norm": 0.4535890221595764,
+      "learning_rate": 0.0001986418672896285,
+      "loss": 0.8508450388908386,
+      "step": 1786
+    },
+    {
+      "epoch": 0.7715210355987056,
+      "grad_norm": 0.4608050286769867,
+      "learning_rate": 0.00019863378962190788,
+      "loss": 0.822467565536499,
+      "step": 1788
+    },
+    {
+      "epoch": 0.7723840345199569,
+      "grad_norm": 0.5190523862838745,
+      "learning_rate": 0.00019862568816909356,
+      "loss": 0.844614565372467,
+      "step": 1790
+    },
+    {
+      "epoch": 0.7732470334412082,
+      "grad_norm": 0.42502254247665405,
+      "learning_rate": 0.00019861756293313912,
+      "loss": 0.8144394755363464,
+      "step": 1792
+    },
+    {
+      "epoch": 0.7741100323624596,
+      "grad_norm": 0.47112616896629333,
+      "learning_rate": 0.000198609413916004,
+      "loss": 0.8836341500282288,
+      "step": 1794
+    },
+    {
+      "epoch": 0.7749730312837109,
+      "grad_norm": 0.48414838314056396,
+      "learning_rate": 0.0001986012411196532,
+      "loss": 0.8846262693405151,
+      "step": 1796
+    },
+    {
+      "epoch": 0.7758360302049623,
+      "grad_norm": 0.4670039415359497,
+      "learning_rate": 0.00019859304454605763,
+      "loss": 0.7993118762969971,
+      "step": 1798
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "grad_norm": 0.41939061880111694,
+      "learning_rate": 0.0001985848241971938,
+      "loss": 0.8389407396316528,
+      "step": 1800
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "eval_loss": 0.8727664947509766,
+      "eval_runtime": 668.2062,
+      "eval_samples_per_second": 3.083,
+      "eval_steps_per_second": 3.083,
+      "step": 1800
+    },
+    {
+      "epoch": 0.777562028047465,
+      "grad_norm": 0.4566517174243927,
+      "learning_rate": 0.00019857658007504405,
+      "loss": 0.8824291825294495,
+      "step": 1802
+    },
+    {
+      "epoch": 0.7784250269687163,
+      "grad_norm": 0.4798925518989563,
+      "learning_rate": 0.0001985683121815964,
+      "loss": 0.808982789516449,
+      "step": 1804
+    },
+    {
+      "epoch": 0.7792880258899676,
+      "grad_norm": 0.4659746587276459,
+      "learning_rate": 0.00019856002051884462,
+      "loss": 0.955269992351532,
+      "step": 1806
+    },
+    {
+      "epoch": 0.780151024811219,
+      "grad_norm": 0.48573991656303406,
+      "learning_rate": 0.00019855170508878818,
+      "loss": 0.8142994046211243,
+      "step": 1808
+    },
+    {
+      "epoch": 0.7810140237324703,
+      "grad_norm": 0.4700213670730591,
+      "learning_rate": 0.00019854336589343236,
+      "loss": 0.8755695819854736,
+      "step": 1810
+    },
+    {
+      "epoch": 0.7818770226537217,
+      "grad_norm": 0.42113450169563293,
+      "learning_rate": 0.00019853500293478806,
+      "loss": 0.8098483681678772,
+      "step": 1812
+    },
+    {
+      "epoch": 0.782740021574973,
+      "grad_norm": 0.4218153655529022,
+      "learning_rate": 0.00019852661621487205,
+      "loss": 0.8219783306121826,
+      "step": 1814
+    },
+    {
+      "epoch": 0.7836030204962244,
+      "grad_norm": 0.499052494764328,
+      "learning_rate": 0.00019851820573570664,
+      "loss": 0.8314159512519836,
+      "step": 1816
+    },
+    {
+      "epoch": 0.7844660194174757,
+      "grad_norm": 0.42420193552970886,
+      "learning_rate": 0.00019850977149932008,
+      "loss": 0.7985323071479797,
+      "step": 1818
+    },
+    {
+      "epoch": 0.785329018338727,
+      "grad_norm": 0.46345841884613037,
+      "learning_rate": 0.0001985013135077462,
+      "loss": 0.8528217077255249,
+      "step": 1820
+    },
+    {
+      "epoch": 0.7861920172599784,
+      "grad_norm": 0.4433307945728302,
+      "learning_rate": 0.00019849283176302462,
+      "loss": 0.8659319877624512,
+      "step": 1822
+    },
+    {
+      "epoch": 0.7870550161812297,
+      "grad_norm": 0.48279091715812683,
+      "learning_rate": 0.00019848432626720067,
+      "loss": 0.8675655126571655,
+      "step": 1824
+    },
+    {
+      "epoch": 0.7879180151024812,
+      "grad_norm": 0.5439180731773376,
+      "learning_rate": 0.0001984757970223254,
+      "loss": 0.8550227284431458,
+      "step": 1826
+    },
+    {
+      "epoch": 0.7887810140237325,
+      "grad_norm": 0.45749521255493164,
+      "learning_rate": 0.0001984672440304556,
+      "loss": 0.7290607690811157,
+      "step": 1828
+    },
+    {
+      "epoch": 0.7896440129449838,
+      "grad_norm": 0.4654783606529236,
+      "learning_rate": 0.00019845866729365378,
+      "loss": 0.8619251251220703,
+      "step": 1830
+    },
+    {
+      "epoch": 0.7905070118662352,
+      "grad_norm": 0.42632243037223816,
+      "learning_rate": 0.00019845006681398823,
+      "loss": 0.8249601125717163,
+      "step": 1832
+    },
+    {
+      "epoch": 0.7913700107874865,
+      "grad_norm": 0.4747186005115509,
+      "learning_rate": 0.0001984414425935329,
+      "loss": 0.7138552069664001,
+      "step": 1834
+    },
+    {
+      "epoch": 0.7922330097087379,
+      "grad_norm": 0.4462338387966156,
+      "learning_rate": 0.0001984327946343674,
+      "loss": 0.903292715549469,
+      "step": 1836
+    },
+    {
+      "epoch": 0.7930960086299892,
+      "grad_norm": 0.4581359922885895,
+      "learning_rate": 0.00019842412293857726,
+      "loss": 0.7569618225097656,
+      "step": 1838
+    },
+    {
+      "epoch": 0.7939590075512406,
+      "grad_norm": 0.4183015525341034,
+      "learning_rate": 0.00019841542750825356,
+      "loss": 0.8063036203384399,
+      "step": 1840
+    },
+    {
+      "epoch": 0.7948220064724919,
+      "grad_norm": 0.3954181373119354,
+      "learning_rate": 0.0001984067083454932,
+      "loss": 0.81150221824646,
+      "step": 1842
+    },
+    {
+      "epoch": 0.7956850053937432,
+      "grad_norm": 0.46220019459724426,
+      "learning_rate": 0.0001983979654523987,
+      "loss": 0.841649055480957,
+      "step": 1844
+    },
+    {
+      "epoch": 0.7965480043149946,
+      "grad_norm": 0.47807541489601135,
+      "learning_rate": 0.00019838919883107843,
+      "loss": 0.8019483685493469,
+      "step": 1846
+    },
+    {
+      "epoch": 0.7974110032362459,
+      "grad_norm": 0.48015692830085754,
+      "learning_rate": 0.0001983804084836464,
+      "loss": 0.9343363046646118,
+      "step": 1848
+    },
+    {
+      "epoch": 0.7982740021574973,
+      "grad_norm": 0.4906708896160126,
+      "learning_rate": 0.00019837159441222238,
+      "loss": 0.9163194894790649,
+      "step": 1850
+    },
+    {
+      "epoch": 0.7991370010787486,
+      "grad_norm": 0.4856911599636078,
+      "learning_rate": 0.0001983627566189318,
+      "loss": 0.8017736077308655,
+      "step": 1852
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.49403145909309387,
+      "learning_rate": 0.0001983538951059059,
+      "loss": 0.8375223875045776,
+      "step": 1854
+    },
+    {
+      "epoch": 0.8008629989212513,
+      "grad_norm": 0.4237985908985138,
+      "learning_rate": 0.00019834500987528158,
+      "loss": 0.8213951587677002,
+      "step": 1856
+    },
+    {
+      "epoch": 0.8017259978425026,
+      "grad_norm": 0.3977980315685272,
+      "learning_rate": 0.00019833610092920149,
+      "loss": 0.8086028099060059,
+      "step": 1858
+    },
+    {
+      "epoch": 0.8025889967637541,
+      "grad_norm": 0.435253381729126,
+      "learning_rate": 0.00019832716826981392,
+      "loss": 0.9402202367782593,
+      "step": 1860
+    },
+    {
+      "epoch": 0.8034519956850054,
+      "grad_norm": 0.4074764847755432,
+      "learning_rate": 0.000198318211899273,
+      "loss": 0.7730796933174133,
+      "step": 1862
+    },
+    {
+      "epoch": 0.8043149946062568,
+      "grad_norm": 0.48804348707199097,
+      "learning_rate": 0.0001983092318197385,
+      "loss": 0.9185802936553955,
+      "step": 1864
+    },
+    {
+      "epoch": 0.8051779935275081,
+      "grad_norm": 0.44363343715667725,
+      "learning_rate": 0.00019830022803337592,
+      "loss": 0.8578243851661682,
+      "step": 1866
+    },
+    {
+      "epoch": 0.8060409924487595,
+      "grad_norm": 0.46645957231521606,
+      "learning_rate": 0.00019829120054235653,
+      "loss": 0.8682060241699219,
+      "step": 1868
+    },
+    {
+      "epoch": 0.8069039913700108,
+      "grad_norm": 0.4527221620082855,
+      "learning_rate": 0.00019828214934885718,
+      "loss": 0.7845040559768677,
+      "step": 1870
+    },
+    {
+      "epoch": 0.8077669902912621,
+      "grad_norm": 0.4103536307811737,
+      "learning_rate": 0.0001982730744550606,
+      "loss": 0.8768247961997986,
+      "step": 1872
+    },
+    {
+      "epoch": 0.8086299892125135,
+      "grad_norm": 0.5257515907287598,
+      "learning_rate": 0.00019826397586315513,
+      "loss": 0.850267231464386,
+      "step": 1874
+    },
+    {
+      "epoch": 0.8094929881337648,
+      "grad_norm": 0.46675893664360046,
+      "learning_rate": 0.00019825485357533485,
+      "loss": 0.8234293460845947,
+      "step": 1876
+    },
+    {
+      "epoch": 0.8103559870550162,
+      "grad_norm": 0.46315401792526245,
+      "learning_rate": 0.00019824570759379958,
+      "loss": 0.8131387829780579,
+      "step": 1878
+    },
+    {
+      "epoch": 0.8112189859762675,
+      "grad_norm": 0.4766870439052582,
+      "learning_rate": 0.00019823653792075478,
+      "loss": 0.7680494785308838,
+      "step": 1880
+    },
+    {
+      "epoch": 0.8120819848975189,
+      "grad_norm": 0.39025625586509705,
+      "learning_rate": 0.00019822734455841173,
+      "loss": 0.7891425490379333,
+      "step": 1882
+    },
+    {
+      "epoch": 0.8129449838187702,
+      "grad_norm": 0.4672441780567169,
+      "learning_rate": 0.0001982181275089874,
+      "loss": 0.7990400791168213,
+      "step": 1884
+    },
+    {
+      "epoch": 0.8138079827400215,
+      "grad_norm": 0.44310975074768066,
+      "learning_rate": 0.00019820888677470432,
+      "loss": 0.7828341722488403,
+      "step": 1886
+    },
+    {
+      "epoch": 0.8146709816612729,
+      "grad_norm": 0.45098716020584106,
+      "learning_rate": 0.00019819962235779096,
+      "loss": 0.897715151309967,
+      "step": 1888
+    },
+    {
+      "epoch": 0.8155339805825242,
+      "grad_norm": 0.466805100440979,
+      "learning_rate": 0.00019819033426048135,
+      "loss": 0.7987668514251709,
+      "step": 1890
+    },
+    {
+      "epoch": 0.8163969795037757,
+      "grad_norm": 0.4438319206237793,
+      "learning_rate": 0.00019818102248501528,
+      "loss": 0.7950236201286316,
+      "step": 1892
+    },
+    {
+      "epoch": 0.817259978425027,
+      "grad_norm": 0.42012497782707214,
+      "learning_rate": 0.00019817168703363823,
+      "loss": 0.8789975643157959,
+      "step": 1894
+    },
+    {
+      "epoch": 0.8181229773462784,
+      "grad_norm": 0.4359394311904907,
+      "learning_rate": 0.0001981623279086014,
+      "loss": 0.8159777522087097,
+      "step": 1896
+    },
+    {
+      "epoch": 0.8189859762675297,
+      "grad_norm": 0.44709593057632446,
+      "learning_rate": 0.00019815294511216173,
+      "loss": 0.84877610206604,
+      "step": 1898
+    },
+    {
+      "epoch": 0.819848975188781,
+      "grad_norm": 0.4315306544303894,
+      "learning_rate": 0.00019814353864658184,
+      "loss": 0.8467556834220886,
+      "step": 1900
+    },
+    {
+      "epoch": 0.819848975188781,
+      "eval_loss": 0.8643407821655273,
+      "eval_runtime": 658.6942,
+      "eval_samples_per_second": 3.127,
+      "eval_steps_per_second": 3.127,
+      "step": 1900
+    },
+    {
+      "epoch": 0.8207119741100324,
+      "grad_norm": 0.35530397295951843,
+      "learning_rate": 0.00019813410851412998,
+      "loss": 0.7398589849472046,
+      "step": 1902
+    },
+    {
+      "epoch": 0.8215749730312837,
+      "grad_norm": 0.46949300169944763,
+      "learning_rate": 0.00019812465471708032,
+      "loss": 0.8544237613677979,
+      "step": 1904
+    },
+    {
+      "epoch": 0.8224379719525351,
+      "grad_norm": 0.4961565434932709,
+      "learning_rate": 0.00019811517725771248,
+      "loss": 0.8242526054382324,
+      "step": 1906
+    },
+    {
+      "epoch": 0.8233009708737864,
+      "grad_norm": 0.45835059881210327,
+      "learning_rate": 0.00019810567613831194,
+      "loss": 0.7856690287590027,
+      "step": 1908
+    },
+    {
+      "epoch": 0.8241639697950378,
+      "grad_norm": 0.4446084797382355,
+      "learning_rate": 0.0001980961513611699,
+      "loss": 0.8361829519271851,
+      "step": 1910
+    },
+    {
+      "epoch": 0.8250269687162891,
+      "grad_norm": 0.4470907747745514,
+      "learning_rate": 0.00019808660292858313,
+      "loss": 0.8993050456047058,
+      "step": 1912
+    },
+    {
+      "epoch": 0.8258899676375404,
+      "grad_norm": 0.44883644580841064,
+      "learning_rate": 0.0001980770308428543,
+      "loss": 0.8702824711799622,
+      "step": 1914
+    },
+    {
+      "epoch": 0.8267529665587918,
+      "grad_norm": 0.43215686082839966,
+      "learning_rate": 0.00019806743510629159,
+      "loss": 0.8454389572143555,
+      "step": 1916
+    },
+    {
+      "epoch": 0.8276159654800431,
+      "grad_norm": 0.4525185823440552,
+      "learning_rate": 0.00019805781572120897,
+      "loss": 0.8621824383735657,
+      "step": 1918
+    },
+    {
+      "epoch": 0.8284789644012945,
+      "grad_norm": 0.4616840183734894,
+      "learning_rate": 0.00019804817268992615,
+      "loss": 0.8661681413650513,
+      "step": 1920
+    },
+    {
+      "epoch": 0.8293419633225458,
+      "grad_norm": 0.4252975583076477,
+      "learning_rate": 0.0001980385060147685,
+      "loss": 0.8376660346984863,
+      "step": 1922
+    },
+    {
+      "epoch": 0.8302049622437971,
+      "grad_norm": 0.44600266218185425,
+      "learning_rate": 0.00019802881569806706,
+      "loss": 0.9258401393890381,
+      "step": 1924
+    },
+    {
+      "epoch": 0.8310679611650486,
+      "grad_norm": 0.48872479796409607,
+      "learning_rate": 0.00019801910174215866,
+      "loss": 0.8804965615272522,
+      "step": 1926
+    },
+    {
+      "epoch": 0.8319309600862999,
+      "grad_norm": 0.5357037782669067,
+      "learning_rate": 0.00019800936414938574,
+      "loss": 0.8561494946479797,
+      "step": 1928
+    },
+    {
+      "epoch": 0.8327939590075513,
+      "grad_norm": 0.39637291431427,
+      "learning_rate": 0.00019799960292209647,
+      "loss": 0.782166063785553,
+      "step": 1930
+    },
+    {
+      "epoch": 0.8336569579288026,
+      "grad_norm": 0.521138072013855,
+      "learning_rate": 0.00019798981806264476,
+      "loss": 0.9048293232917786,
+      "step": 1932
+    },
+    {
+      "epoch": 0.834519956850054,
+      "grad_norm": 0.4723529815673828,
+      "learning_rate": 0.00019798000957339015,
+      "loss": 0.9269952774047852,
+      "step": 1934
+    },
+    {
+      "epoch": 0.8353829557713053,
+      "grad_norm": 0.42827340960502625,
+      "learning_rate": 0.0001979701774566979,
+      "loss": 0.8620670437812805,
+      "step": 1936
+    },
+    {
+      "epoch": 0.8362459546925566,
+      "grad_norm": 0.4305116534233093,
+      "learning_rate": 0.00019796032171493907,
+      "loss": 0.8016669750213623,
+      "step": 1938
+    },
+    {
+      "epoch": 0.837108953613808,
+      "grad_norm": 0.4995502233505249,
+      "learning_rate": 0.00019795044235049024,
+      "loss": 0.879247784614563,
+      "step": 1940
+    },
+    {
+      "epoch": 0.8379719525350593,
+      "grad_norm": 0.49229878187179565,
+      "learning_rate": 0.0001979405393657338,
+      "loss": 0.9476580023765564,
+      "step": 1942
+    },
+    {
+      "epoch": 0.8388349514563107,
+      "grad_norm": 0.45756596326828003,
+      "learning_rate": 0.0001979306127630578,
+      "loss": 0.8654064536094666,
+      "step": 1944
+    },
+    {
+      "epoch": 0.839697950377562,
+      "grad_norm": 0.4855344891548157,
+      "learning_rate": 0.00019792066254485603,
+      "loss": 0.7792956829071045,
+      "step": 1946
+    },
+    {
+      "epoch": 0.8405609492988134,
+      "grad_norm": 0.4358632266521454,
+      "learning_rate": 0.00019791068871352787,
+      "loss": 0.8000320792198181,
+      "step": 1948
+    },
+    {
+      "epoch": 0.8414239482200647,
+      "grad_norm": 0.4225342273712158,
+      "learning_rate": 0.00019790069127147852,
+      "loss": 0.818372368812561,
+      "step": 1950
+    },
+    {
+      "epoch": 0.842286947141316,
+      "grad_norm": 0.3894529938697815,
+      "learning_rate": 0.00019789067022111886,
+      "loss": 0.727220892906189,
+      "step": 1952
+    },
+    {
+      "epoch": 0.8431499460625674,
+      "grad_norm": 0.5060731768608093,
+      "learning_rate": 0.0001978806255648653,
+      "loss": 0.894101083278656,
+      "step": 1954
+    },
+    {
+      "epoch": 0.8440129449838187,
+      "grad_norm": 0.4165003001689911,
+      "learning_rate": 0.0001978705573051402,
+      "loss": 0.878365695476532,
+      "step": 1956
+    },
+    {
+      "epoch": 0.8448759439050701,
+      "grad_norm": 0.48767927289009094,
+      "learning_rate": 0.0001978604654443714,
+      "loss": 0.8390909433364868,
+      "step": 1958
+    },
+    {
+      "epoch": 0.8457389428263214,
+      "grad_norm": 0.43019410967826843,
+      "learning_rate": 0.00019785034998499247,
+      "loss": 0.8807769417762756,
+      "step": 1960
+    },
+    {
+      "epoch": 0.8466019417475729,
+      "grad_norm": 0.4430403709411621,
+      "learning_rate": 0.0001978402109294428,
+      "loss": 0.8037779331207275,
+      "step": 1962
+    },
+    {
+      "epoch": 0.8474649406688242,
+      "grad_norm": 0.41642463207244873,
+      "learning_rate": 0.0001978300482801673,
+      "loss": 0.8341337442398071,
+      "step": 1964
+    },
+    {
+      "epoch": 0.8483279395900755,
+      "grad_norm": 0.45358774065971375,
+      "learning_rate": 0.00019781986203961668,
+      "loss": 0.854821503162384,
+      "step": 1966
+    },
+    {
+      "epoch": 0.8491909385113269,
+      "grad_norm": 0.4316342771053314,
+      "learning_rate": 0.00019780965221024728,
+      "loss": 0.8527678847312927,
+      "step": 1968
+    },
+    {
+      "epoch": 0.8500539374325782,
+      "grad_norm": 0.4581106901168823,
+      "learning_rate": 0.00019779941879452122,
+      "loss": 0.7461717128753662,
+      "step": 1970
+    },
+    {
+      "epoch": 0.8509169363538296,
+      "grad_norm": 0.49578142166137695,
+      "learning_rate": 0.0001977891617949062,
+      "loss": 0.884441077709198,
+      "step": 1972
+    },
+    {
+      "epoch": 0.8517799352750809,
+      "grad_norm": 0.4366011917591095,
+      "learning_rate": 0.00019777888121387562,
+      "loss": 0.855915904045105,
+      "step": 1974
+    },
+    {
+      "epoch": 0.8526429341963323,
+      "grad_norm": 0.486162930727005,
+      "learning_rate": 0.00019776857705390864,
+      "loss": 0.7563765645027161,
+      "step": 1976
+    },
+    {
+      "epoch": 0.8535059331175836,
+      "grad_norm": 0.5162674784660339,
+      "learning_rate": 0.00019775824931749005,
+      "loss": 0.8346326947212219,
+      "step": 1978
+    },
+    {
+      "epoch": 0.8543689320388349,
+      "grad_norm": 0.5824693441390991,
+      "learning_rate": 0.0001977478980071103,
+      "loss": 0.8701820969581604,
+      "step": 1980
+    },
+    {
+      "epoch": 0.8552319309600863,
+      "grad_norm": 0.4297148883342743,
+      "learning_rate": 0.00019773752312526565,
+      "loss": 0.893528938293457,
+      "step": 1982
+    },
+    {
+      "epoch": 0.8560949298813376,
+      "grad_norm": 0.42978280782699585,
+      "learning_rate": 0.00019772712467445788,
+      "loss": 0.8201018571853638,
+      "step": 1984
+    },
+    {
+      "epoch": 0.856957928802589,
+      "grad_norm": 0.5192655324935913,
+      "learning_rate": 0.00019771670265719454,
+      "loss": 0.9080212116241455,
+      "step": 1986
+    },
+    {
+      "epoch": 0.8578209277238403,
+      "grad_norm": 0.452690452337265,
+      "learning_rate": 0.00019770625707598885,
+      "loss": 0.8518272638320923,
+      "step": 1988
+    },
+    {
+      "epoch": 0.8586839266450917,
+      "grad_norm": 0.4371768832206726,
+      "learning_rate": 0.00019769578793335976,
+      "loss": 0.9426717758178711,
+      "step": 1990
+    },
+    {
+      "epoch": 0.859546925566343,
+      "grad_norm": 0.44595038890838623,
+      "learning_rate": 0.0001976852952318318,
+      "loss": 0.8065400123596191,
+      "step": 1992
+    },
+    {
+      "epoch": 0.8604099244875943,
+      "grad_norm": 0.4355090260505676,
+      "learning_rate": 0.0001976747789739353,
+      "loss": 0.7674415707588196,
+      "step": 1994
+    },
+    {
+      "epoch": 0.8612729234088458,
+      "grad_norm": 0.43745186924934387,
+      "learning_rate": 0.00019766423916220616,
+      "loss": 0.813849925994873,
+      "step": 1996
+    },
+    {
+      "epoch": 0.8621359223300971,
+      "grad_norm": 0.4588927924633026,
+      "learning_rate": 0.00019765367579918598,
+      "loss": 0.7870585322380066,
+      "step": 1998
+    },
+    {
+      "epoch": 0.8629989212513485,
+      "grad_norm": 0.4170977473258972,
+      "learning_rate": 0.00019764308888742214,
+      "loss": 0.8383269309997559,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8629989212513485,
+      "eval_loss": 0.8567262887954712,
+      "eval_runtime": 646.6443,
+      "eval_samples_per_second": 3.186,
+      "eval_steps_per_second": 3.186,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8638619201725998,
+      "grad_norm": 0.4819261431694031,
+      "learning_rate": 0.0001976324784294676,
+      "loss": 0.8261714577674866,
+      "step": 2002
+    },
+    {
+      "epoch": 0.8647249190938512,
+      "grad_norm": 0.4215400218963623,
+      "learning_rate": 0.00019762184442788098,
+      "loss": 0.8493392467498779,
+      "step": 2004
+    },
+    {
+      "epoch": 0.8655879180151025,
+      "grad_norm": 0.45448991656303406,
+      "learning_rate": 0.00019761118688522668,
+      "loss": 0.8645208477973938,
+      "step": 2006
+    },
+    {
+      "epoch": 0.8664509169363538,
+      "grad_norm": 0.4436458349227905,
+      "learning_rate": 0.0001976005058040747,
+      "loss": 0.8816449046134949,
+      "step": 2008
+    },
+    {
+      "epoch": 0.8673139158576052,
+      "grad_norm": 0.42662230134010315,
+      "learning_rate": 0.00019758980118700072,
+      "loss": 0.7622330784797668,
+      "step": 2010
+    },
+    {
+      "epoch": 0.8681769147788565,
+      "grad_norm": 0.3936038613319397,
+      "learning_rate": 0.0001975790730365861,
+      "loss": 0.7843833565711975,
+      "step": 2012
+    },
+    {
+      "epoch": 0.8690399137001079,
+      "grad_norm": 0.4460368752479553,
+      "learning_rate": 0.00019756832135541796,
+      "loss": 0.8294675946235657,
+      "step": 2014
+    },
+    {
+      "epoch": 0.8699029126213592,
+      "grad_norm": 0.47043702006340027,
+      "learning_rate": 0.00019755754614608892,
+      "loss": 0.851332426071167,
+      "step": 2016
+    },
+    {
+      "epoch": 0.8707659115426106,
+      "grad_norm": 0.4579448401927948,
+      "learning_rate": 0.00019754674741119746,
+      "loss": 0.8450362682342529,
+      "step": 2018
+    },
+    {
+      "epoch": 0.8716289104638619,
+      "grad_norm": 0.44362813234329224,
+      "learning_rate": 0.00019753592515334758,
+      "loss": 0.8585519194602966,
+      "step": 2020
+    },
+    {
+      "epoch": 0.8724919093851132,
+      "grad_norm": 0.4500923156738281,
+      "learning_rate": 0.00019752507937514905,
+      "loss": 0.8300179243087769,
+      "step": 2022
+    },
+    {
+      "epoch": 0.8733549083063646,
+      "grad_norm": 0.4330301582813263,
+      "learning_rate": 0.00019751421007921724,
+      "loss": 0.805014431476593,
+      "step": 2024
+    },
+    {
+      "epoch": 0.8742179072276159,
+      "grad_norm": 0.43873998522758484,
+      "learning_rate": 0.00019750331726817332,
+      "loss": 0.8228020071983337,
+      "step": 2026
+    },
+    {
+      "epoch": 0.8750809061488674,
+      "grad_norm": 0.47558829188346863,
+      "learning_rate": 0.00019749240094464395,
+      "loss": 0.8490906357765198,
+      "step": 2028
+    },
+    {
+      "epoch": 0.8759439050701187,
+      "grad_norm": 0.4285199046134949,
+      "learning_rate": 0.0001974814611112616,
+      "loss": 0.816324770450592,
+      "step": 2030
+    },
+    {
+      "epoch": 0.87680690399137,
+      "grad_norm": 0.4762725532054901,
+      "learning_rate": 0.0001974704977706644,
+      "loss": 0.9229121208190918,
+      "step": 2032
+    },
+    {
+      "epoch": 0.8776699029126214,
+      "grad_norm": 0.49856793880462646,
+      "learning_rate": 0.00019745951092549598,
+      "loss": 0.9847140908241272,
+      "step": 2034
+    },
+    {
+      "epoch": 0.8785329018338727,
+      "grad_norm": 0.5163881182670593,
+      "learning_rate": 0.00019744850057840587,
+      "loss": 0.8305321335792542,
+      "step": 2036
+    },
+    {
+      "epoch": 0.8793959007551241,
+      "grad_norm": 0.47826042771339417,
+      "learning_rate": 0.00019743746673204918,
+      "loss": 0.7909449934959412,
+      "step": 2038
+    },
+    {
+      "epoch": 0.8802588996763754,
+      "grad_norm": 0.44080349802970886,
+      "learning_rate": 0.0001974264093890866,
+      "loss": 0.809201180934906,
+      "step": 2040
+    },
+    {
+      "epoch": 0.8811218985976268,
+      "grad_norm": 0.46925660967826843,
+      "learning_rate": 0.00019741532855218464,
+      "loss": 0.8064218163490295,
+      "step": 2042
+    },
+    {
+      "epoch": 0.8819848975188781,
+      "grad_norm": 0.4223597049713135,
+      "learning_rate": 0.00019740422422401531,
+      "loss": 0.8135121464729309,
+      "step": 2044
+    },
+    {
+      "epoch": 0.8828478964401294,
+      "grad_norm": 0.46334266662597656,
+      "learning_rate": 0.00019739309640725642,
+      "loss": 0.8047984838485718,
+      "step": 2046
+    },
+    {
+      "epoch": 0.8837108953613808,
+      "grad_norm": 0.413682222366333,
+      "learning_rate": 0.0001973819451045914,
+      "loss": 0.7897430658340454,
+      "step": 2048
+    },
+    {
+      "epoch": 0.8845738942826321,
+      "grad_norm": 0.4276670515537262,
+      "learning_rate": 0.0001973707703187093,
+      "loss": 0.8411629796028137,
+      "step": 2050
+    },
+    {
+      "epoch": 0.8854368932038835,
+      "grad_norm": 0.4199331998825073,
+      "learning_rate": 0.0001973595720523049,
+      "loss": 0.7906913161277771,
+      "step": 2052
+    },
+    {
+      "epoch": 0.8862998921251348,
+      "grad_norm": 0.43233853578567505,
+      "learning_rate": 0.0001973483503080786,
+      "loss": 0.9042854309082031,
+      "step": 2054
+    },
+    {
+      "epoch": 0.8871628910463862,
+      "grad_norm": 0.41147297620773315,
+      "learning_rate": 0.00019733710508873647,
+      "loss": 0.8177635073661804,
+      "step": 2056
+    },
+    {
+      "epoch": 0.8880258899676375,
+      "grad_norm": 0.45957690477371216,
+      "learning_rate": 0.00019732583639699023,
+      "loss": 0.8867166042327881,
+      "step": 2058
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.3979831635951996,
+      "learning_rate": 0.00019731454423555728,
+      "loss": 0.7208530902862549,
+      "step": 2060
+    },
+    {
+      "epoch": 0.8897518878101403,
+      "grad_norm": 0.4434017837047577,
+      "learning_rate": 0.00019730322860716073,
+      "loss": 0.9158181548118591,
+      "step": 2062
+    },
+    {
+      "epoch": 0.8906148867313916,
+      "grad_norm": 0.40012025833129883,
+      "learning_rate": 0.00019729188951452922,
+      "loss": 0.8103255033493042,
+      "step": 2064
+    },
+    {
+      "epoch": 0.891477885652643,
+      "grad_norm": 0.41914620995521545,
+      "learning_rate": 0.00019728052696039715,
+      "loss": 0.7780100703239441,
+      "step": 2066
+    },
+    {
+      "epoch": 0.8923408845738943,
+      "grad_norm": 0.48365312814712524,
+      "learning_rate": 0.00019726914094750453,
+      "loss": 0.7105780839920044,
+      "step": 2068
+    },
+    {
+      "epoch": 0.8932038834951457,
+      "grad_norm": 0.4272058308124542,
+      "learning_rate": 0.0001972577314785971,
+      "loss": 0.7529635429382324,
+      "step": 2070
+    },
+    {
+      "epoch": 0.894066882416397,
+      "grad_norm": 0.48760271072387695,
+      "learning_rate": 0.00019724629855642612,
+      "loss": 0.836787223815918,
+      "step": 2072
+    },
+    {
+      "epoch": 0.8949298813376483,
+      "grad_norm": 0.47811925411224365,
+      "learning_rate": 0.00019723484218374865,
+      "loss": 0.8773119449615479,
+      "step": 2074
+    },
+    {
+      "epoch": 0.8957928802588997,
+      "grad_norm": 0.40109625458717346,
+      "learning_rate": 0.0001972233623633273,
+      "loss": 0.7151904106140137,
+      "step": 2076
+    },
+    {
+      "epoch": 0.896655879180151,
+      "grad_norm": 0.48640304803848267,
+      "learning_rate": 0.00019721185909793047,
+      "loss": 0.8348540663719177,
+      "step": 2078
+    },
+    {
+      "epoch": 0.8975188781014024,
+      "grad_norm": 0.45748841762542725,
+      "learning_rate": 0.000197200332390332,
+      "loss": 0.845246434211731,
+      "step": 2080
+    },
+    {
+      "epoch": 0.8983818770226537,
+      "grad_norm": 0.41650277376174927,
+      "learning_rate": 0.00019718878224331157,
+      "loss": 0.8746084570884705,
+      "step": 2082
+    },
+    {
+      "epoch": 0.8992448759439051,
+      "grad_norm": 0.45878589153289795,
+      "learning_rate": 0.00019717720865965443,
+      "loss": 0.8252862691879272,
+      "step": 2084
+    },
+    {
+      "epoch": 0.9001078748651564,
+      "grad_norm": 0.3710020184516907,
+      "learning_rate": 0.0001971656116421515,
+      "loss": 0.7056596875190735,
+      "step": 2086
+    },
+    {
+      "epoch": 0.9009708737864077,
+      "grad_norm": 0.4251181185245514,
+      "learning_rate": 0.00019715399119359935,
+      "loss": 0.8305537700653076,
+      "step": 2088
+    },
+    {
+      "epoch": 0.9018338727076591,
+      "grad_norm": 0.48429808020591736,
+      "learning_rate": 0.0001971423473168002,
+      "loss": 0.8431704044342041,
+      "step": 2090
+    },
+    {
+      "epoch": 0.9026968716289104,
+      "grad_norm": 0.5384030342102051,
+      "learning_rate": 0.00019713068001456186,
+      "loss": 0.8311790227890015,
+      "step": 2092
+    },
+    {
+      "epoch": 0.9035598705501618,
+      "grad_norm": 0.452029287815094,
+      "learning_rate": 0.00019711898928969796,
+      "loss": 0.8077114224433899,
+      "step": 2094
+    },
+    {
+      "epoch": 0.9044228694714131,
+      "grad_norm": 0.4427074193954468,
+      "learning_rate": 0.0001971072751450276,
+      "loss": 0.8454164266586304,
+      "step": 2096
+    },
+    {
+      "epoch": 0.9052858683926646,
+      "grad_norm": 0.4895693063735962,
+      "learning_rate": 0.00019709553758337557,
+      "loss": 0.8551414608955383,
+      "step": 2098
+    },
+    {
+      "epoch": 0.9061488673139159,
+      "grad_norm": 0.47199201583862305,
+      "learning_rate": 0.00019708377660757244,
+      "loss": 0.9158598184585571,
+      "step": 2100
+    },
+    {
+      "epoch": 0.9061488673139159,
+      "eval_loss": 0.8524587750434875,
+      "eval_runtime": 655.7682,
+      "eval_samples_per_second": 3.141,
+      "eval_steps_per_second": 3.141,
+      "step": 2100
+    },
+    {
+      "epoch": 0.9070118662351672,
+      "grad_norm": 0.45380064845085144,
+      "learning_rate": 0.00019707199222045415,
+      "loss": 0.8301376700401306,
+      "step": 2102
+    },
+    {
+      "epoch": 0.9078748651564186,
+      "grad_norm": 0.4775148034095764,
+      "learning_rate": 0.00019706018442486255,
+      "loss": 0.8191117644309998,
+      "step": 2104
+    },
+    {
+      "epoch": 0.9087378640776699,
+      "grad_norm": 0.40894538164138794,
+      "learning_rate": 0.00019704835322364506,
+      "loss": 0.8333686590194702,
+      "step": 2106
+    },
+    {
+      "epoch": 0.9096008629989213,
+      "grad_norm": 0.4202065169811249,
+      "learning_rate": 0.00019703649861965467,
+      "loss": 0.7916508913040161,
+      "step": 2108
+    },
+    {
+      "epoch": 0.9104638619201726,
+      "grad_norm": 0.39157143235206604,
+      "learning_rate": 0.00019702462061575008,
+      "loss": 0.8018013834953308,
+      "step": 2110
+    },
+    {
+      "epoch": 0.911326860841424,
+      "grad_norm": 0.4623039662837982,
+      "learning_rate": 0.00019701271921479565,
+      "loss": 0.8819739818572998,
+      "step": 2112
+    },
+    {
+      "epoch": 0.9121898597626753,
+      "grad_norm": 0.45183128118515015,
+      "learning_rate": 0.00019700079441966128,
+      "loss": 0.7652842402458191,
+      "step": 2114
+    },
+    {
+      "epoch": 0.9130528586839266,
+      "grad_norm": 0.4562322795391083,
+      "learning_rate": 0.00019698884623322262,
+      "loss": 0.817150890827179,
+      "step": 2116
+    },
+    {
+      "epoch": 0.913915857605178,
+      "grad_norm": 0.45955994725227356,
+      "learning_rate": 0.00019697687465836095,
+      "loss": 0.8223007917404175,
+      "step": 2118
+    },
+    {
+      "epoch": 0.9147788565264293,
+      "grad_norm": 0.44595572352409363,
+      "learning_rate": 0.00019696487969796307,
+      "loss": 0.7716509699821472,
+      "step": 2120
+    },
+    {
+      "epoch": 0.9156418554476807,
+      "grad_norm": 0.4380198121070862,
+      "learning_rate": 0.00019695286135492163,
+      "loss": 0.8205068111419678,
+      "step": 2122
+    },
+    {
+      "epoch": 0.916504854368932,
+      "grad_norm": 0.4025624692440033,
+      "learning_rate": 0.0001969408196321347,
+      "loss": 0.8126305341720581,
+      "step": 2124
+    },
+    {
+      "epoch": 0.9173678532901833,
+      "grad_norm": 0.424277663230896,
+      "learning_rate": 0.00019692875453250616,
+      "loss": 0.7840806841850281,
+      "step": 2126
+    },
+    {
+      "epoch": 0.9182308522114347,
+      "grad_norm": 0.4683000445365906,
+      "learning_rate": 0.00019691666605894538,
+      "loss": 0.9391030669212341,
+      "step": 2128
+    },
+    {
+      "epoch": 0.919093851132686,
+      "grad_norm": 0.47679048776626587,
+      "learning_rate": 0.00019690455421436754,
+      "loss": 0.8336083889007568,
+      "step": 2130
+    },
+    {
+      "epoch": 0.9199568500539375,
+      "grad_norm": 0.45669928193092346,
+      "learning_rate": 0.00019689241900169323,
+      "loss": 0.917514443397522,
+      "step": 2132
+    },
+    {
+      "epoch": 0.9208198489751888,
+      "grad_norm": 0.4372829794883728,
+      "learning_rate": 0.00019688026042384893,
+      "loss": 0.7798282504081726,
+      "step": 2134
+    },
+    {
+      "epoch": 0.9216828478964402,
+      "grad_norm": 0.4497234523296356,
+      "learning_rate": 0.00019686807848376655,
+      "loss": 0.7415590286254883,
+      "step": 2136
+    },
+    {
+      "epoch": 0.9225458468176915,
+      "grad_norm": 0.4892704486846924,
+      "learning_rate": 0.00019685587318438372,
+      "loss": 0.7713689208030701,
+      "step": 2138
+    },
+    {
+      "epoch": 0.9234088457389428,
+      "grad_norm": 0.490495502948761,
+      "learning_rate": 0.0001968436445286437,
+      "loss": 0.821044385433197,
+      "step": 2140
+    },
+    {
+      "epoch": 0.9242718446601942,
+      "grad_norm": 0.43616363406181335,
+      "learning_rate": 0.00019683139251949538,
+      "loss": 0.796081006526947,
+      "step": 2142
+    },
+    {
+      "epoch": 0.9251348435814455,
+      "grad_norm": 0.4199701249599457,
+      "learning_rate": 0.00019681911715989326,
+      "loss": 0.737835705280304,
+      "step": 2144
+    },
+    {
+      "epoch": 0.9259978425026969,
+      "grad_norm": 0.45367109775543213,
+      "learning_rate": 0.0001968068184527975,
+      "loss": 0.8224935531616211,
+      "step": 2146
+    },
+    {
+      "epoch": 0.9268608414239482,
+      "grad_norm": 0.43349263072013855,
+      "learning_rate": 0.0001967944964011739,
+      "loss": 0.826752245426178,
+      "step": 2148
+    },
+    {
+      "epoch": 0.9277238403451996,
+      "grad_norm": 0.4693690538406372,
+      "learning_rate": 0.00019678215100799384,
+      "loss": 0.8527786731719971,
+      "step": 2150
+    },
+    {
+      "epoch": 0.9285868392664509,
+      "grad_norm": 0.4281991124153137,
+      "learning_rate": 0.00019676978227623434,
+      "loss": 0.8101436495780945,
+      "step": 2152
+    },
+    {
+      "epoch": 0.9294498381877022,
+      "grad_norm": 0.4662301540374756,
+      "learning_rate": 0.0001967573902088781,
+      "loss": 0.8997542262077332,
+      "step": 2154
+    },
+    {
+      "epoch": 0.9303128371089536,
+      "grad_norm": 0.41807958483695984,
+      "learning_rate": 0.0001967449748089134,
+      "loss": 0.8378244638442993,
+      "step": 2156
+    },
+    {
+      "epoch": 0.9311758360302049,
+      "grad_norm": 0.4789344072341919,
+      "learning_rate": 0.00019673253607933416,
+      "loss": 0.8562051057815552,
+      "step": 2158
+    },
+    {
+      "epoch": 0.9320388349514563,
+      "grad_norm": 0.43706783652305603,
+      "learning_rate": 0.0001967200740231399,
+      "loss": 0.78457111120224,
+      "step": 2160
+    },
+    {
+      "epoch": 0.9329018338727076,
+      "grad_norm": 0.4441883862018585,
+      "learning_rate": 0.0001967075886433358,
+      "loss": 0.8058217763900757,
+      "step": 2162
+    },
+    {
+      "epoch": 0.933764832793959,
+      "grad_norm": 0.48960480093955994,
+      "learning_rate": 0.00019669507994293266,
+      "loss": 0.916145384311676,
+      "step": 2164
+    },
+    {
+      "epoch": 0.9346278317152104,
+      "grad_norm": 0.3990147113800049,
+      "learning_rate": 0.00019668254792494692,
+      "loss": 0.8805235028266907,
+      "step": 2166
+    },
+    {
+      "epoch": 0.9354908306364617,
+      "grad_norm": 0.4299201965332031,
+      "learning_rate": 0.00019666999259240056,
+      "loss": 0.8611101508140564,
+      "step": 2168
+    },
+    {
+      "epoch": 0.9363538295577131,
+      "grad_norm": 0.5267254114151001,
+      "learning_rate": 0.00019665741394832132,
+      "loss": 0.8429995179176331,
+      "step": 2170
+    },
+    {
+      "epoch": 0.9372168284789644,
+      "grad_norm": 0.46667975187301636,
+      "learning_rate": 0.0001966448119957424,
+      "loss": 0.8057775497436523,
+      "step": 2172
+    },
+    {
+      "epoch": 0.9380798274002158,
+      "grad_norm": 0.4140365421772003,
+      "learning_rate": 0.00019663218673770277,
+      "loss": 0.7456767559051514,
+      "step": 2174
+    },
+    {
+      "epoch": 0.9389428263214671,
+      "grad_norm": 0.4236559569835663,
+      "learning_rate": 0.00019661953817724692,
+      "loss": 0.7320394515991211,
+      "step": 2176
+    },
+    {
+      "epoch": 0.9398058252427185,
+      "grad_norm": 0.4075721800327301,
+      "learning_rate": 0.000196606866317425,
+      "loss": 0.7850301265716553,
+      "step": 2178
+    },
+    {
+      "epoch": 0.9406688241639698,
+      "grad_norm": 0.4638446271419525,
+      "learning_rate": 0.00019659417116129276,
+      "loss": 0.8228051662445068,
+      "step": 2180
+    },
+    {
+      "epoch": 0.9415318230852211,
+      "grad_norm": 0.4641942083835602,
+      "learning_rate": 0.00019658145271191164,
+      "loss": 0.8458912372589111,
+      "step": 2182
+    },
+    {
+      "epoch": 0.9423948220064725,
+      "grad_norm": 0.42868348956108093,
+      "learning_rate": 0.00019656871097234856,
+      "loss": 0.8002372980117798,
+      "step": 2184
+    },
+    {
+      "epoch": 0.9432578209277238,
+      "grad_norm": 0.4726828336715698,
+      "learning_rate": 0.00019655594594567615,
+      "loss": 0.9096182584762573,
+      "step": 2186
+    },
+    {
+      "epoch": 0.9441208198489752,
+      "grad_norm": 0.40363940596580505,
+      "learning_rate": 0.00019654315763497265,
+      "loss": 0.7508110404014587,
+      "step": 2188
+    },
+    {
+      "epoch": 0.9449838187702265,
+      "grad_norm": 0.46951010823249817,
+      "learning_rate": 0.00019653034604332192,
+      "loss": 0.8898510932922363,
+      "step": 2190
+    },
+    {
+      "epoch": 0.9458468176914779,
+      "grad_norm": 0.4564061164855957,
+      "learning_rate": 0.0001965175111738134,
+      "loss": 0.8604891896247864,
+      "step": 2192
+    },
+    {
+      "epoch": 0.9467098166127292,
+      "grad_norm": 0.4366895854473114,
+      "learning_rate": 0.00019650465302954219,
+      "loss": 0.8314935564994812,
+      "step": 2194
+    },
+    {
+      "epoch": 0.9475728155339805,
+      "grad_norm": 0.541490375995636,
+      "learning_rate": 0.0001964917716136089,
+      "loss": 0.851138174533844,
+      "step": 2196
+    },
+    {
+      "epoch": 0.948435814455232,
+      "grad_norm": 0.45251160860061646,
+      "learning_rate": 0.0001964788669291199,
+      "loss": 0.9248369336128235,
+      "step": 2198
+    },
+    {
+      "epoch": 0.9492988133764833,
+      "grad_norm": 0.46237683296203613,
+      "learning_rate": 0.00019646593897918707,
+      "loss": 0.8113608956336975,
+      "step": 2200
+    },
+    {
+      "epoch": 0.9492988133764833,
+      "eval_loss": 0.8443478941917419,
+      "eval_runtime": 666.5866,
+      "eval_samples_per_second": 3.09,
+      "eval_steps_per_second": 3.09,
+      "step": 2200
+    },
+    {
+      "epoch": 0.9501618122977347,
+      "grad_norm": 0.4506337344646454,
+      "learning_rate": 0.0001964529877669279,
+      "loss": 0.8151772618293762,
+      "step": 2202
+    },
+    {
+      "epoch": 0.951024811218986,
+      "grad_norm": 0.42866984009742737,
+      "learning_rate": 0.00019644001329546557,
+      "loss": 0.920696496963501,
+      "step": 2204
+    },
+    {
+      "epoch": 0.9518878101402374,
+      "grad_norm": 0.3899093270301819,
+      "learning_rate": 0.00019642701556792878,
+      "loss": 0.8228384256362915,
+      "step": 2206
+    },
+    {
+      "epoch": 0.9527508090614887,
+      "grad_norm": 0.42472460865974426,
+      "learning_rate": 0.00019641399458745186,
+      "loss": 0.7483987808227539,
+      "step": 2208
+    },
+    {
+      "epoch": 0.95361380798274,
+      "grad_norm": 0.4046783447265625,
+      "learning_rate": 0.00019640095035717482,
+      "loss": 0.7356619834899902,
+      "step": 2210
+    },
+    {
+      "epoch": 0.9544768069039914,
+      "grad_norm": 0.4608006179332733,
+      "learning_rate": 0.00019638788288024316,
+      "loss": 0.7374731302261353,
+      "step": 2212
+    },
+    {
+      "epoch": 0.9553398058252427,
+      "grad_norm": 0.448503315448761,
+      "learning_rate": 0.00019637479215980807,
+      "loss": 0.9128687977790833,
+      "step": 2214
+    },
+    {
+      "epoch": 0.9562028047464941,
+      "grad_norm": 0.4477374851703644,
+      "learning_rate": 0.0001963616781990263,
+      "loss": 0.6983766555786133,
+      "step": 2216
+    },
+    {
+      "epoch": 0.9570658036677454,
+      "grad_norm": 0.41463667154312134,
+      "learning_rate": 0.00019634854100106025,
+      "loss": 0.8543318510055542,
+      "step": 2218
+    },
+    {
+      "epoch": 0.9579288025889967,
+      "grad_norm": 0.5271132588386536,
+      "learning_rate": 0.00019633538056907786,
+      "loss": 0.8866401314735413,
+      "step": 2220
+    },
+    {
+      "epoch": 0.9587918015102481,
+      "grad_norm": 0.4496590495109558,
+      "learning_rate": 0.00019632219690625272,
+      "loss": 0.8414724469184875,
+      "step": 2222
+    },
+    {
+      "epoch": 0.9596548004314994,
+      "grad_norm": 0.4772113263607025,
+      "learning_rate": 0.00019630899001576405,
+      "loss": 0.8859618902206421,
+      "step": 2224
+    },
+    {
+      "epoch": 0.9605177993527508,
+      "grad_norm": 0.5249642729759216,
+      "learning_rate": 0.0001962957599007966,
+      "loss": 0.8347851037979126,
+      "step": 2226
+    },
+    {
+      "epoch": 0.9613807982740021,
+      "grad_norm": 0.4931469261646271,
+      "learning_rate": 0.0001962825065645407,
+      "loss": 0.7893235087394714,
+      "step": 2228
+    },
+    {
+      "epoch": 0.9622437971952535,
+      "grad_norm": 0.45010602474212646,
+      "learning_rate": 0.00019626923001019245,
+      "loss": 0.815602719783783,
+      "step": 2230
+    },
+    {
+      "epoch": 0.9631067961165048,
+      "grad_norm": 0.42947128415107727,
+      "learning_rate": 0.00019625593024095333,
+      "loss": 0.807309627532959,
+      "step": 2232
+    },
+    {
+      "epoch": 0.9639697950377561,
+      "grad_norm": 0.43500378727912903,
+      "learning_rate": 0.00019624260726003057,
+      "loss": 0.8135440945625305,
+      "step": 2234
+    },
+    {
+      "epoch": 0.9648327939590076,
+      "grad_norm": 0.41840270161628723,
+      "learning_rate": 0.00019622926107063692,
+      "loss": 0.802107036113739,
+      "step": 2236
+    },
+    {
+      "epoch": 0.9656957928802589,
+      "grad_norm": 0.4580598771572113,
+      "learning_rate": 0.00019621589167599077,
+      "loss": 0.7596800923347473,
+      "step": 2238
+    },
+    {
+      "epoch": 0.9665587918015103,
+      "grad_norm": 0.38064274191856384,
+      "learning_rate": 0.0001962024990793161,
+      "loss": 0.7609489560127258,
+      "step": 2240
+    },
+    {
+      "epoch": 0.9674217907227616,
+      "grad_norm": 0.39098140597343445,
+      "learning_rate": 0.00019618908328384246,
+      "loss": 0.7829734086990356,
+      "step": 2242
+    },
+    {
+      "epoch": 0.968284789644013,
+      "grad_norm": 0.38412022590637207,
+      "learning_rate": 0.00019617564429280502,
+      "loss": 0.7570722699165344,
+      "step": 2244
+    },
+    {
+      "epoch": 0.9691477885652643,
+      "grad_norm": 0.41451776027679443,
+      "learning_rate": 0.0001961621821094445,
+      "loss": 0.8634825348854065,
+      "step": 2246
+    },
+    {
+      "epoch": 0.9700107874865156,
+      "grad_norm": 0.4989950954914093,
+      "learning_rate": 0.00019614869673700725,
+      "loss": 0.9002810120582581,
+      "step": 2248
+    },
+    {
+      "epoch": 0.970873786407767,
+      "grad_norm": 0.4316846430301666,
+      "learning_rate": 0.00019613518817874524,
+      "loss": 0.7587819695472717,
+      "step": 2250
+    },
+    {
+      "epoch": 0.9717367853290183,
+      "grad_norm": 0.41293349862098694,
+      "learning_rate": 0.000196121656437916,
+      "loss": 0.686238706111908,
+      "step": 2252
+    },
+    {
+      "epoch": 0.9725997842502697,
+      "grad_norm": 0.40252262353897095,
+      "learning_rate": 0.00019610810151778258,
+      "loss": 0.7895162105560303,
+      "step": 2254
+    },
+    {
+      "epoch": 0.973462783171521,
+      "grad_norm": 0.42973560094833374,
+      "learning_rate": 0.0001960945234216138,
+      "loss": 0.8360300064086914,
+      "step": 2256
+    },
+    {
+      "epoch": 0.9743257820927724,
+      "grad_norm": 0.40562206506729126,
+      "learning_rate": 0.00019608092215268386,
+      "loss": 0.7624704241752625,
+      "step": 2258
+    },
+    {
+      "epoch": 0.9751887810140237,
+      "grad_norm": 0.4486660063266754,
+      "learning_rate": 0.00019606729771427266,
+      "loss": 0.8285008072853088,
+      "step": 2260
+    },
+    {
+      "epoch": 0.976051779935275,
+      "grad_norm": 0.37069520354270935,
+      "learning_rate": 0.0001960536501096657,
+      "loss": 0.7951943278312683,
+      "step": 2262
+    },
+    {
+      "epoch": 0.9769147788565264,
+      "grad_norm": 0.43367981910705566,
+      "learning_rate": 0.00019603997934215404,
+      "loss": 0.7641335129737854,
+      "step": 2264
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.42540937662124634,
+      "learning_rate": 0.00019602628541503432,
+      "loss": 0.8449530601501465,
+      "step": 2266
+    },
+    {
+      "epoch": 0.9786407766990292,
+      "grad_norm": 0.46175941824913025,
+      "learning_rate": 0.00019601256833160874,
+      "loss": 0.8207030296325684,
+      "step": 2268
+    },
+    {
+      "epoch": 0.9795037756202805,
+      "grad_norm": 0.3834969103336334,
+      "learning_rate": 0.00019599882809518513,
+      "loss": 0.7753700017929077,
+      "step": 2270
+    },
+    {
+      "epoch": 0.9803667745415319,
+      "grad_norm": 0.43960243463516235,
+      "learning_rate": 0.0001959850647090769,
+      "loss": 0.8844934701919556,
+      "step": 2272
+    },
+    {
+      "epoch": 0.9812297734627832,
+      "grad_norm": 0.4240610897541046,
+      "learning_rate": 0.00019597127817660303,
+      "loss": 0.7795814275741577,
+      "step": 2274
+    },
+    {
+      "epoch": 0.9820927723840345,
+      "grad_norm": 0.41870981454849243,
+      "learning_rate": 0.00019595746850108807,
+      "loss": 0.6960644721984863,
+      "step": 2276
+    },
+    {
+      "epoch": 0.9829557713052859,
+      "grad_norm": 0.43871861696243286,
+      "learning_rate": 0.00019594363568586215,
+      "loss": 0.7709649205207825,
+      "step": 2278
+    },
+    {
+      "epoch": 0.9838187702265372,
+      "grad_norm": 0.45331820845603943,
+      "learning_rate": 0.00019592977973426098,
+      "loss": 0.7324449419975281,
+      "step": 2280
+    },
+    {
+      "epoch": 0.9846817691477886,
+      "grad_norm": 0.4300173223018646,
+      "learning_rate": 0.00019591590064962593,
+      "loss": 0.8720724582672119,
+      "step": 2282
+    },
+    {
+      "epoch": 0.9855447680690399,
+      "grad_norm": 0.4478892982006073,
+      "learning_rate": 0.0001959019984353038,
+      "loss": 0.7396156191825867,
+      "step": 2284
+    },
+    {
+      "epoch": 0.9864077669902913,
+      "grad_norm": 0.4391026198863983,
+      "learning_rate": 0.00019588807309464708,
+      "loss": 0.8303509950637817,
+      "step": 2286
+    },
+    {
+      "epoch": 0.9872707659115426,
+      "grad_norm": 0.4046599268913269,
+      "learning_rate": 0.00019587412463101378,
+      "loss": 0.739641010761261,
+      "step": 2288
+    },
+    {
+      "epoch": 0.9881337648327939,
+      "grad_norm": 0.4619915187358856,
+      "learning_rate": 0.00019586015304776756,
+      "loss": 0.7448247671127319,
+      "step": 2290
+    },
+    {
+      "epoch": 0.9889967637540453,
+      "grad_norm": 0.4603526294231415,
+      "learning_rate": 0.00019584615834827753,
+      "loss": 0.8184107542037964,
+      "step": 2292
+    },
+    {
+      "epoch": 0.9898597626752966,
+      "grad_norm": 0.4828874170780182,
+      "learning_rate": 0.00019583214053591852,
+      "loss": 0.9069648385047913,
+      "step": 2294
+    },
+    {
+      "epoch": 0.990722761596548,
+      "grad_norm": 0.37467876076698303,
+      "learning_rate": 0.00019581809961407082,
+      "loss": 0.6628880500793457,
+      "step": 2296
+    },
+    {
+      "epoch": 0.9915857605177993,
+      "grad_norm": 0.4300445318222046,
+      "learning_rate": 0.00019580403558612037,
+      "loss": 0.7712231278419495,
+      "step": 2298
+    },
+    {
+      "epoch": 0.9924487594390508,
+      "grad_norm": 0.4368257522583008,
+      "learning_rate": 0.00019578994845545863,
+      "loss": 0.7796293497085571,
+      "step": 2300
+    },
+    {
+      "epoch": 0.9924487594390508,
+      "eval_loss": 0.839731752872467,
+      "eval_runtime": 666.2332,
+      "eval_samples_per_second": 3.092,
+      "eval_steps_per_second": 3.092,
+      "step": 2300
+    },
+    {
+      "epoch": 0.993311758360302,
+      "grad_norm": 0.4383920729160309,
+      "learning_rate": 0.00019577583822548262,
+      "loss": 0.7504367232322693,
+      "step": 2302
+    },
+    {
+      "epoch": 0.9941747572815534,
+      "grad_norm": 0.3895981013774872,
+      "learning_rate": 0.00019576170489959496,
+      "loss": 0.7298936247825623,
+      "step": 2304
+    },
+    {
+      "epoch": 0.9950377562028048,
+      "grad_norm": 0.4950196444988251,
+      "learning_rate": 0.00019574754848120392,
+      "loss": 0.9137371778488159,
+      "step": 2306
+    },
+    {
+      "epoch": 0.9959007551240561,
+      "grad_norm": 0.5115531086921692,
+      "learning_rate": 0.00019573336897372318,
+      "loss": 0.9203279614448547,
+      "step": 2308
+    },
+    {
+      "epoch": 0.9967637540453075,
+      "grad_norm": 0.43145665526390076,
+      "learning_rate": 0.000195719166380572,
+      "loss": 0.7708958387374878,
+      "step": 2310
+    },
+    {
+      "epoch": 0.9976267529665588,
+      "grad_norm": 0.39575520157814026,
+      "learning_rate": 0.00019570494070517545,
+      "loss": 0.7911062836647034,
+      "step": 2312
+    },
+    {
+      "epoch": 0.9984897518878102,
+      "grad_norm": 0.45690420269966125,
+      "learning_rate": 0.00019569069195096386,
+      "loss": 0.8282244205474854,
+      "step": 2314
+    },
+    {
+      "epoch": 0.9993527508090615,
+      "grad_norm": 0.43362128734588623,
+      "learning_rate": 0.00019567642012137325,
+      "loss": 0.8658884763717651,
+      "step": 2316
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6889842748641968,
+      "learning_rate": 0.00019566212521984527,
+      "loss": 0.7823468446731567,
+      "step": 2318
+    },
+    {
+      "epoch": 1.0008629989212514,
+      "grad_norm": 0.3945363759994507,
+      "learning_rate": 0.00019564780724982706,
+      "loss": 0.8244057297706604,
+      "step": 2320
+    },
+    {
+      "epoch": 1.0017259978425026,
+      "grad_norm": 0.5313655734062195,
+      "learning_rate": 0.00019563346621477129,
+      "loss": 0.8228418827056885,
+      "step": 2322
+    },
+    {
+      "epoch": 1.002588996763754,
+      "grad_norm": 0.47728294134140015,
+      "learning_rate": 0.00019561910211813625,
+      "loss": 0.8627800941467285,
+      "step": 2324
+    },
+    {
+      "epoch": 1.0034519956850054,
+      "grad_norm": 0.4706253111362457,
+      "learning_rate": 0.00019560471496338582,
+      "loss": 0.8810665011405945,
+      "step": 2326
+    },
+    {
+      "epoch": 1.0043149946062568,
+      "grad_norm": 0.4333725571632385,
+      "learning_rate": 0.0001955903047539893,
+      "loss": 0.7736411094665527,
+      "step": 2328
+    },
+    {
+      "epoch": 1.005177993527508,
+      "grad_norm": 0.49580323696136475,
+      "learning_rate": 0.00019557587149342178,
+      "loss": 0.9185295104980469,
+      "step": 2330
+    },
+    {
+      "epoch": 1.0060409924487594,
+      "grad_norm": 0.4362829029560089,
+      "learning_rate": 0.0001955614151851637,
+      "loss": 0.7387797832489014,
+      "step": 2332
+    },
+    {
+      "epoch": 1.0069039913700109,
+      "grad_norm": 0.42584139108657837,
+      "learning_rate": 0.00019554693583270113,
+      "loss": 0.672156810760498,
+      "step": 2334
+    },
+    {
+      "epoch": 1.007766990291262,
+      "grad_norm": 0.40073466300964355,
+      "learning_rate": 0.0001955324334395257,
+      "loss": 0.7638119459152222,
+      "step": 2336
+    },
+    {
+      "epoch": 1.0086299892125135,
+      "grad_norm": 0.49992597103118896,
+      "learning_rate": 0.00019551790800913458,
+      "loss": 0.7930200695991516,
+      "step": 2338
+    },
+    {
+      "epoch": 1.0094929881337649,
+      "grad_norm": 0.3825504779815674,
+      "learning_rate": 0.00019550335954503058,
+      "loss": 0.7128595113754272,
+      "step": 2340
+    },
+    {
+      "epoch": 1.0103559870550163,
+      "grad_norm": 0.4654180705547333,
+      "learning_rate": 0.00019548878805072196,
+      "loss": 0.7130335569381714,
+      "step": 2342
+    },
+    {
+      "epoch": 1.0112189859762675,
+      "grad_norm": 0.4199283719062805,
+      "learning_rate": 0.00019547419352972258,
+      "loss": 0.7843249440193176,
+      "step": 2344
+    },
+    {
+      "epoch": 1.0120819848975189,
+      "grad_norm": 0.43597257137298584,
+      "learning_rate": 0.0001954595759855518,
+      "loss": 0.676262617111206,
+      "step": 2346
+    },
+    {
+      "epoch": 1.0129449838187703,
+      "grad_norm": 0.47415891289711,
+      "learning_rate": 0.0001954449354217346,
+      "loss": 0.742564857006073,
+      "step": 2348
+    },
+    {
+      "epoch": 1.0138079827400215,
+      "grad_norm": 0.44753482937812805,
+      "learning_rate": 0.00019543027184180153,
+      "loss": 0.7419085502624512,
+      "step": 2350
+    },
+    {
+      "epoch": 1.014670981661273,
+      "grad_norm": 0.4175751209259033,
+      "learning_rate": 0.0001954155852492886,
+      "loss": 0.7373939752578735,
+      "step": 2352
+    },
+    {
+      "epoch": 1.0155339805825243,
+      "grad_norm": 0.40376800298690796,
+      "learning_rate": 0.00019540087564773738,
+      "loss": 0.7639825344085693,
+      "step": 2354
+    },
+    {
+      "epoch": 1.0163969795037757,
+      "grad_norm": 0.4166127145290375,
+      "learning_rate": 0.0001953861430406951,
+      "loss": 0.7797452211380005,
+      "step": 2356
+    },
+    {
+      "epoch": 1.017259978425027,
+      "grad_norm": 0.4340934753417969,
+      "learning_rate": 0.0001953713874317144,
+      "loss": 0.8258501887321472,
+      "step": 2358
+    },
+    {
+      "epoch": 1.0181229773462783,
+      "grad_norm": 0.47081413865089417,
+      "learning_rate": 0.0001953566088243536,
+      "loss": 0.7664495706558228,
+      "step": 2360
+    },
+    {
+      "epoch": 1.0189859762675297,
+      "grad_norm": 0.4126851260662079,
+      "learning_rate": 0.00019534180722217644,
+      "loss": 0.7411028742790222,
+      "step": 2362
+    },
+    {
+      "epoch": 1.019848975188781,
+      "grad_norm": 0.45279955863952637,
+      "learning_rate": 0.00019532698262875227,
+      "loss": 0.7514335513114929,
+      "step": 2364
+    },
+    {
+      "epoch": 1.0207119741100323,
+      "grad_norm": 0.4857143461704254,
+      "learning_rate": 0.00019531213504765595,
+      "loss": 0.7544763088226318,
+      "step": 2366
+    },
+    {
+      "epoch": 1.0215749730312838,
+      "grad_norm": 0.5232970714569092,
+      "learning_rate": 0.00019529726448246795,
+      "loss": 0.7246702313423157,
+      "step": 2368
+    },
+    {
+      "epoch": 1.0224379719525352,
+      "grad_norm": 0.4434663653373718,
+      "learning_rate": 0.00019528237093677424,
+      "loss": 0.7399187684059143,
+      "step": 2370
+    },
+    {
+      "epoch": 1.0233009708737864,
+      "grad_norm": 0.44713014364242554,
+      "learning_rate": 0.0001952674544141663,
+      "loss": 0.7208506464958191,
+      "step": 2372
+    },
+    {
+      "epoch": 1.0241639697950378,
+      "grad_norm": 0.43205446004867554,
+      "learning_rate": 0.0001952525149182412,
+      "loss": 0.761768639087677,
+      "step": 2374
+    },
+    {
+      "epoch": 1.0250269687162892,
+      "grad_norm": 0.4322265386581421,
+      "learning_rate": 0.0001952375524526015,
+      "loss": 0.6573513746261597,
+      "step": 2376
+    },
+    {
+      "epoch": 1.0258899676375404,
+      "grad_norm": 0.4776996970176697,
+      "learning_rate": 0.0001952225670208554,
+      "loss": 0.8118118047714233,
+      "step": 2378
+    },
+    {
+      "epoch": 1.0267529665587918,
+      "grad_norm": 0.5014623403549194,
+      "learning_rate": 0.00019520755862661648,
+      "loss": 0.781197190284729,
+      "step": 2380
+    },
+    {
+      "epoch": 1.0276159654800432,
+      "grad_norm": 0.5164223313331604,
+      "learning_rate": 0.00019519252727350403,
+      "loss": 0.8399010896682739,
+      "step": 2382
+    },
+    {
+      "epoch": 1.0284789644012946,
+      "grad_norm": 0.47874927520751953,
+      "learning_rate": 0.00019517747296514276,
+      "loss": 0.786519467830658,
+      "step": 2384
+    },
+    {
+      "epoch": 1.0293419633225458,
+      "grad_norm": 0.48447099328041077,
+      "learning_rate": 0.00019516239570516292,
+      "loss": 0.7837404012680054,
+      "step": 2386
+    },
+    {
+      "epoch": 1.0302049622437972,
+      "grad_norm": 0.4762440323829651,
+      "learning_rate": 0.0001951472954972004,
+      "loss": 0.833958625793457,
+      "step": 2388
+    },
+    {
+      "epoch": 1.0310679611650486,
+      "grad_norm": 0.42814165353775024,
+      "learning_rate": 0.00019513217234489645,
+      "loss": 0.7688734531402588,
+      "step": 2390
+    },
+    {
+      "epoch": 1.0319309600862998,
+      "grad_norm": 0.4784977436065674,
+      "learning_rate": 0.00019511702625189803,
+      "loss": 0.814251720905304,
+      "step": 2392
+    },
+    {
+      "epoch": 1.0327939590075512,
+      "grad_norm": 0.44989243149757385,
+      "learning_rate": 0.00019510185722185748,
+      "loss": 0.7277538180351257,
+      "step": 2394
+    },
+    {
+      "epoch": 1.0336569579288026,
+      "grad_norm": 0.5141931772232056,
+      "learning_rate": 0.0001950866652584328,
+      "loss": 0.844467282295227,
+      "step": 2396
+    },
+    {
+      "epoch": 1.0345199568500538,
+      "grad_norm": 0.48569414019584656,
+      "learning_rate": 0.00019507145036528747,
+      "loss": 0.7662147879600525,
+      "step": 2398
+    },
+    {
+      "epoch": 1.0353829557713052,
+      "grad_norm": 0.5075576901435852,
+      "learning_rate": 0.00019505621254609047,
+      "loss": 0.7628200054168701,
+      "step": 2400
+    },
+    {
+      "epoch": 1.0353829557713052,
+      "eval_loss": 0.8369861245155334,
+      "eval_runtime": 653.1661,
+      "eval_samples_per_second": 3.154,
+      "eval_steps_per_second": 3.154,
+      "step": 2400
+    },
+    {
+      "epoch": 1.0362459546925566,
+      "grad_norm": 0.49423643946647644,
+      "learning_rate": 0.00019504095180451628,
+      "loss": 0.8225719332695007,
+      "step": 2402
+    },
+    {
+      "epoch": 1.037108953613808,
+      "grad_norm": 0.4558854401111603,
+      "learning_rate": 0.00019502566814424505,
+      "loss": 0.8239169120788574,
+      "step": 2404
+    },
+    {
+      "epoch": 1.0379719525350593,
+      "grad_norm": 0.4864993691444397,
+      "learning_rate": 0.00019501036156896232,
+      "loss": 0.7805002331733704,
+      "step": 2406
+    },
+    {
+      "epoch": 1.0388349514563107,
+      "grad_norm": 0.44108837842941284,
+      "learning_rate": 0.00019499503208235918,
+      "loss": 0.866910994052887,
+      "step": 2408
+    },
+    {
+      "epoch": 1.039697950377562,
+      "grad_norm": 0.4616626799106598,
+      "learning_rate": 0.00019497967968813232,
+      "loss": 0.7601662874221802,
+      "step": 2410
+    },
+    {
+      "epoch": 1.0405609492988135,
+      "grad_norm": 0.4792969524860382,
+      "learning_rate": 0.00019496430438998387,
+      "loss": 0.8155668377876282,
+      "step": 2412
+    },
+    {
+      "epoch": 1.0414239482200647,
+      "grad_norm": 0.45400261878967285,
+      "learning_rate": 0.00019494890619162152,
+      "loss": 0.7879545092582703,
+      "step": 2414
+    },
+    {
+      "epoch": 1.042286947141316,
+      "grad_norm": 0.44541165232658386,
+      "learning_rate": 0.0001949334850967585,
+      "loss": 0.7196864485740662,
+      "step": 2416
+    },
+    {
+      "epoch": 1.0431499460625675,
+      "grad_norm": 0.44515085220336914,
+      "learning_rate": 0.00019491804110911343,
+      "loss": 0.7288097739219666,
+      "step": 2418
+    },
+    {
+      "epoch": 1.0440129449838187,
+      "grad_norm": 0.43586596846580505,
+      "learning_rate": 0.0001949025742324107,
+      "loss": 0.7182422280311584,
+      "step": 2420
+    },
+    {
+      "epoch": 1.04487594390507,
+      "grad_norm": 0.44399815797805786,
+      "learning_rate": 0.00019488708447038002,
+      "loss": 0.7005030512809753,
+      "step": 2422
+    },
+    {
+      "epoch": 1.0457389428263215,
+      "grad_norm": 0.4658401310443878,
+      "learning_rate": 0.00019487157182675665,
+      "loss": 0.715505063533783,
+      "step": 2424
+    },
+    {
+      "epoch": 1.0466019417475727,
+      "grad_norm": 0.4468056261539459,
+      "learning_rate": 0.00019485603630528143,
+      "loss": 0.7170135974884033,
+      "step": 2426
+    },
+    {
+      "epoch": 1.0474649406688241,
+      "grad_norm": 0.5302334427833557,
+      "learning_rate": 0.00019484047790970066,
+      "loss": 0.83464115858078,
+      "step": 2428
+    },
+    {
+      "epoch": 1.0483279395900755,
+      "grad_norm": 0.46583443880081177,
+      "learning_rate": 0.0001948248966437662,
+      "loss": 0.7129145264625549,
+      "step": 2430
+    },
+    {
+      "epoch": 1.049190938511327,
+      "grad_norm": 0.38922831416130066,
+      "learning_rate": 0.0001948092925112354,
+      "loss": 0.7990599870681763,
+      "step": 2432
+    },
+    {
+      "epoch": 1.0500539374325781,
+      "grad_norm": 0.4599211513996124,
+      "learning_rate": 0.00019479366551587108,
+      "loss": 0.8572773933410645,
+      "step": 2434
+    },
+    {
+      "epoch": 1.0509169363538295,
+      "grad_norm": 0.47514498233795166,
+      "learning_rate": 0.00019477801566144165,
+      "loss": 0.8107781410217285,
+      "step": 2436
+    },
+    {
+      "epoch": 1.051779935275081,
+      "grad_norm": 0.41368064284324646,
+      "learning_rate": 0.00019476234295172102,
+      "loss": 0.7433347702026367,
+      "step": 2438
+    },
+    {
+      "epoch": 1.0526429341963321,
+      "grad_norm": 0.4666398763656616,
+      "learning_rate": 0.00019474664739048858,
+      "loss": 0.8033983111381531,
+      "step": 2440
+    },
+    {
+      "epoch": 1.0535059331175836,
+      "grad_norm": 0.41621699929237366,
+      "learning_rate": 0.00019473092898152924,
+      "loss": 0.7320330142974854,
+      "step": 2442
+    },
+    {
+      "epoch": 1.054368932038835,
+      "grad_norm": 0.43523117899894714,
+      "learning_rate": 0.00019471518772863343,
+      "loss": 0.7742927074432373,
+      "step": 2444
+    },
+    {
+      "epoch": 1.0552319309600864,
+      "grad_norm": 0.5151914358139038,
+      "learning_rate": 0.0001946994236355971,
+      "loss": 0.8301699161529541,
+      "step": 2446
+    },
+    {
+      "epoch": 1.0560949298813376,
+      "grad_norm": 0.566112756729126,
+      "learning_rate": 0.0001946836367062216,
+      "loss": 0.837057888507843,
+      "step": 2448
+    },
+    {
+      "epoch": 1.056957928802589,
+      "grad_norm": 0.4257231652736664,
+      "learning_rate": 0.00019466782694431398,
+      "loss": 0.7323788404464722,
+      "step": 2450
+    },
+    {
+      "epoch": 1.0578209277238404,
+      "grad_norm": 0.5477433800697327,
+      "learning_rate": 0.0001946519943536867,
+      "loss": 0.7410078048706055,
+      "step": 2452
+    },
+    {
+      "epoch": 1.0586839266450916,
+      "grad_norm": 0.37357097864151,
+      "learning_rate": 0.00019463613893815762,
+      "loss": 0.6646532416343689,
+      "step": 2454
+    },
+    {
+      "epoch": 1.059546925566343,
+      "grad_norm": 0.438048779964447,
+      "learning_rate": 0.00019462026070155028,
+      "loss": 0.7773549556732178,
+      "step": 2456
+    },
+    {
+      "epoch": 1.0604099244875944,
+      "grad_norm": 0.5114307999610901,
+      "learning_rate": 0.0001946043596476936,
+      "loss": 0.8977773785591125,
+      "step": 2458
+    },
+    {
+      "epoch": 1.0612729234088458,
+      "grad_norm": 0.4340408146381378,
+      "learning_rate": 0.0001945884357804221,
+      "loss": 0.8128405809402466,
+      "step": 2460
+    },
+    {
+      "epoch": 1.062135922330097,
+      "grad_norm": 0.4922826290130615,
+      "learning_rate": 0.0001945724891035757,
+      "loss": 0.8096795678138733,
+      "step": 2462
+    },
+    {
+      "epoch": 1.0629989212513484,
+      "grad_norm": 0.47231894731521606,
+      "learning_rate": 0.00019455651962099987,
+      "loss": 0.7965760231018066,
+      "step": 2464
+    },
+    {
+      "epoch": 1.0638619201725998,
+      "grad_norm": 0.4519463777542114,
+      "learning_rate": 0.00019454052733654565,
+      "loss": 0.7136726975440979,
+      "step": 2466
+    },
+    {
+      "epoch": 1.064724919093851,
+      "grad_norm": 0.44883614778518677,
+      "learning_rate": 0.0001945245122540694,
+      "loss": 0.8136170506477356,
+      "step": 2468
+    },
+    {
+      "epoch": 1.0655879180151024,
+      "grad_norm": 0.4224080741405487,
+      "learning_rate": 0.00019450847437743317,
+      "loss": 0.7840399146080017,
+      "step": 2470
+    },
+    {
+      "epoch": 1.0664509169363539,
+      "grad_norm": 0.4979367256164551,
+      "learning_rate": 0.00019449241371050438,
+      "loss": 0.8202947378158569,
+      "step": 2472
+    },
+    {
+      "epoch": 1.0673139158576053,
+      "grad_norm": 0.5551356673240662,
+      "learning_rate": 0.000194476330257156,
+      "loss": 0.8608070611953735,
+      "step": 2474
+    },
+    {
+      "epoch": 1.0681769147788565,
+      "grad_norm": 0.3980900049209595,
+      "learning_rate": 0.00019446022402126647,
+      "loss": 0.7202636003494263,
+      "step": 2476
+    },
+    {
+      "epoch": 1.0690399137001079,
+      "grad_norm": 0.5393417477607727,
+      "learning_rate": 0.00019444409500671977,
+      "loss": 0.8301891684532166,
+      "step": 2478
+    },
+    {
+      "epoch": 1.0699029126213593,
+      "grad_norm": 0.47717350721359253,
+      "learning_rate": 0.0001944279432174053,
+      "loss": 0.700567901134491,
+      "step": 2480
+    },
+    {
+      "epoch": 1.0707659115426105,
+      "grad_norm": 0.5197957158088684,
+      "learning_rate": 0.000194411768657218,
+      "loss": 0.794978141784668,
+      "step": 2482
+    },
+    {
+      "epoch": 1.0716289104638619,
+      "grad_norm": 0.5289306044578552,
+      "learning_rate": 0.0001943955713300583,
+      "loss": 0.8052116632461548,
+      "step": 2484
+    },
+    {
+      "epoch": 1.0724919093851133,
+      "grad_norm": 0.4360409080982208,
+      "learning_rate": 0.00019437935123983212,
+      "loss": 0.750991702079773,
+      "step": 2486
+    },
+    {
+      "epoch": 1.0733549083063647,
+      "grad_norm": 0.38651731610298157,
+      "learning_rate": 0.00019436310839045085,
+      "loss": 0.6631898880004883,
+      "step": 2488
+    },
+    {
+      "epoch": 1.074217907227616,
+      "grad_norm": 0.4376210868358612,
+      "learning_rate": 0.00019434684278583138,
+      "loss": 0.7995471358299255,
+      "step": 2490
+    },
+    {
+      "epoch": 1.0750809061488673,
+      "grad_norm": 0.46636906266212463,
+      "learning_rate": 0.0001943305544298961,
+      "loss": 0.7633864879608154,
+      "step": 2492
+    },
+    {
+      "epoch": 1.0759439050701187,
+      "grad_norm": 0.43499618768692017,
+      "learning_rate": 0.00019431424332657288,
+      "loss": 0.7281562089920044,
+      "step": 2494
+    },
+    {
+      "epoch": 1.07680690399137,
+      "grad_norm": 0.39683374762535095,
+      "learning_rate": 0.000194297909479795,
+      "loss": 0.7313723564147949,
+      "step": 2496
+    },
+    {
+      "epoch": 1.0776699029126213,
+      "grad_norm": 0.4545603096485138,
+      "learning_rate": 0.0001942815528935014,
+      "loss": 0.7120141983032227,
+      "step": 2498
+    },
+    {
+      "epoch": 1.0785329018338727,
+      "grad_norm": 0.5040699243545532,
+      "learning_rate": 0.0001942651735716363,
+      "loss": 0.752600908279419,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0785329018338727,
+      "eval_loss": 0.8323014378547668,
+      "eval_runtime": 652.3791,
+      "eval_samples_per_second": 3.158,
+      "eval_steps_per_second": 3.158,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0793959007551241,
+      "grad_norm": 0.48951438069343567,
+      "learning_rate": 0.00019424877151814958,
+      "loss": 0.7719982266426086,
+      "step": 2502
+    },
+    {
+      "epoch": 1.0802588996763753,
+      "grad_norm": 0.5009822845458984,
+      "learning_rate": 0.00019423234673699648,
+      "loss": 0.7921367883682251,
+      "step": 2504
+    },
+    {
+      "epoch": 1.0811218985976268,
+      "grad_norm": 0.4699440896511078,
+      "learning_rate": 0.00019421589923213772,
+      "loss": 0.7714369297027588,
+      "step": 2506
+    },
+    {
+      "epoch": 1.0819848975188782,
+      "grad_norm": 0.4438663125038147,
+      "learning_rate": 0.00019419942900753963,
+      "loss": 0.6981601119041443,
+      "step": 2508
+    },
+    {
+      "epoch": 1.0828478964401294,
+      "grad_norm": 0.49927031993865967,
+      "learning_rate": 0.00019418293606717385,
+      "loss": 0.7822043895721436,
+      "step": 2510
+    },
+    {
+      "epoch": 1.0837108953613808,
+      "grad_norm": 0.395433634519577,
+      "learning_rate": 0.00019416642041501767,
+      "loss": 0.7166627049446106,
+      "step": 2512
+    },
+    {
+      "epoch": 1.0845738942826322,
+      "grad_norm": 0.47293251752853394,
+      "learning_rate": 0.00019414988205505366,
+      "loss": 0.7287489771842957,
+      "step": 2514
+    },
+    {
+      "epoch": 1.0854368932038836,
+      "grad_norm": 0.43168675899505615,
+      "learning_rate": 0.00019413332099127008,
+      "loss": 0.7672322988510132,
+      "step": 2516
+    },
+    {
+      "epoch": 1.0862998921251348,
+      "grad_norm": 0.4542049765586853,
+      "learning_rate": 0.00019411673722766044,
+      "loss": 0.7427115440368652,
+      "step": 2518
+    },
+    {
+      "epoch": 1.0871628910463862,
+      "grad_norm": 0.4920838177204132,
+      "learning_rate": 0.00019410013076822394,
+      "loss": 0.742889404296875,
+      "step": 2520
+    },
+    {
+      "epoch": 1.0880258899676376,
+      "grad_norm": 0.5404410362243652,
+      "learning_rate": 0.0001940835016169651,
+      "loss": 0.767113208770752,
+      "step": 2522
+    },
+    {
+      "epoch": 1.0888888888888888,
+      "grad_norm": 0.4543033540248871,
+      "learning_rate": 0.00019406684977789395,
+      "loss": 0.6729961037635803,
+      "step": 2524
+    },
+    {
+      "epoch": 1.0897518878101402,
+      "grad_norm": 0.49171510338783264,
+      "learning_rate": 0.00019405017525502607,
+      "loss": 0.6907814145088196,
+      "step": 2526
+    },
+    {
+      "epoch": 1.0906148867313916,
+      "grad_norm": 0.491252601146698,
+      "learning_rate": 0.00019403347805238238,
+      "loss": 0.7643960118293762,
+      "step": 2528
+    },
+    {
+      "epoch": 1.091477885652643,
+      "grad_norm": 0.527920663356781,
+      "learning_rate": 0.0001940167581739894,
+      "loss": 0.8070526123046875,
+      "step": 2530
+    },
+    {
+      "epoch": 1.0923408845738942,
+      "grad_norm": 0.4318726658821106,
+      "learning_rate": 0.00019400001562387898,
+      "loss": 0.7900120615959167,
+      "step": 2532
+    },
+    {
+      "epoch": 1.0932038834951456,
+      "grad_norm": 0.4903397560119629,
+      "learning_rate": 0.00019398325040608855,
+      "loss": 0.7778371572494507,
+      "step": 2534
+    },
+    {
+      "epoch": 1.094066882416397,
+      "grad_norm": 0.4835105240345001,
+      "learning_rate": 0.00019396646252466097,
+      "loss": 0.7758864164352417,
+      "step": 2536
+    },
+    {
+      "epoch": 1.0949298813376482,
+      "grad_norm": 0.47125598788261414,
+      "learning_rate": 0.00019394965198364455,
+      "loss": 0.7927643656730652,
+      "step": 2538
+    },
+    {
+      "epoch": 1.0957928802588996,
+      "grad_norm": 0.46723976731300354,
+      "learning_rate": 0.0001939328187870931,
+      "loss": 0.7884714007377625,
+      "step": 2540
+    },
+    {
+      "epoch": 1.096655879180151,
+      "grad_norm": 0.46274980902671814,
+      "learning_rate": 0.00019391596293906582,
+      "loss": 0.7663765549659729,
+      "step": 2542
+    },
+    {
+      "epoch": 1.0975188781014025,
+      "grad_norm": 0.431887149810791,
+      "learning_rate": 0.00019389908444362747,
+      "loss": 0.6656131744384766,
+      "step": 2544
+    },
+    {
+      "epoch": 1.0983818770226537,
+      "grad_norm": 0.5138527750968933,
+      "learning_rate": 0.00019388218330484823,
+      "loss": 0.795498788356781,
+      "step": 2546
+    },
+    {
+      "epoch": 1.099244875943905,
+      "grad_norm": 0.4679732024669647,
+      "learning_rate": 0.00019386525952680365,
+      "loss": 0.807344377040863,
+      "step": 2548
+    },
+    {
+      "epoch": 1.1001078748651565,
+      "grad_norm": 0.473088800907135,
+      "learning_rate": 0.0001938483131135749,
+      "loss": 0.6828449368476868,
+      "step": 2550
+    },
+    {
+      "epoch": 1.1009708737864077,
+      "grad_norm": 0.49941009283065796,
+      "learning_rate": 0.00019383134406924856,
+      "loss": 0.8669595122337341,
+      "step": 2552
+    },
+    {
+      "epoch": 1.101833872707659,
+      "grad_norm": 0.47401952743530273,
+      "learning_rate": 0.00019381435239791656,
+      "loss": 0.7382985949516296,
+      "step": 2554
+    },
+    {
+      "epoch": 1.1026968716289105,
+      "grad_norm": 0.47803637385368347,
+      "learning_rate": 0.0001937973381036764,
+      "loss": 0.7240811586380005,
+      "step": 2556
+    },
+    {
+      "epoch": 1.103559870550162,
+      "grad_norm": 0.4534960985183716,
+      "learning_rate": 0.000193780301190631,
+      "loss": 0.736165463924408,
+      "step": 2558
+    },
+    {
+      "epoch": 1.104422869471413,
+      "grad_norm": 0.4594196677207947,
+      "learning_rate": 0.0001937632416628887,
+      "loss": 0.7364692091941833,
+      "step": 2560
+    },
+    {
+      "epoch": 1.1052858683926645,
+      "grad_norm": 0.45354577898979187,
+      "learning_rate": 0.0001937461595245634,
+      "loss": 0.803584635257721,
+      "step": 2562
+    },
+    {
+      "epoch": 1.106148867313916,
+      "grad_norm": 0.47314611077308655,
+      "learning_rate": 0.00019372905477977432,
+      "loss": 0.7224286794662476,
+      "step": 2564
+    },
+    {
+      "epoch": 1.1070118662351671,
+      "grad_norm": 0.4453343451023102,
+      "learning_rate": 0.0001937119274326462,
+      "loss": 0.7446297407150269,
+      "step": 2566
+    },
+    {
+      "epoch": 1.1078748651564185,
+      "grad_norm": 0.5266496539115906,
+      "learning_rate": 0.0001936947774873093,
+      "loss": 0.7666438817977905,
+      "step": 2568
+    },
+    {
+      "epoch": 1.10873786407767,
+      "grad_norm": 0.44142624735832214,
+      "learning_rate": 0.00019367760494789913,
+      "loss": 0.8593260049819946,
+      "step": 2570
+    },
+    {
+      "epoch": 1.1096008629989211,
+      "grad_norm": 0.552436888217926,
+      "learning_rate": 0.00019366040981855682,
+      "loss": 0.7768570184707642,
+      "step": 2572
+    },
+    {
+      "epoch": 1.1104638619201725,
+      "grad_norm": 0.4223164916038513,
+      "learning_rate": 0.0001936431921034289,
+      "loss": 0.7356681823730469,
+      "step": 2574
+    },
+    {
+      "epoch": 1.111326860841424,
+      "grad_norm": 0.5104808211326599,
+      "learning_rate": 0.0001936259518066674,
+      "loss": 0.7693892121315002,
+      "step": 2576
+    },
+    {
+      "epoch": 1.1121898597626754,
+      "grad_norm": 0.40713393688201904,
+      "learning_rate": 0.00019360868893242967,
+      "loss": 0.7651313543319702,
+      "step": 2578
+    },
+    {
+      "epoch": 1.1130528586839266,
+      "grad_norm": 0.4819444417953491,
+      "learning_rate": 0.00019359140348487858,
+      "loss": 0.8427110314369202,
+      "step": 2580
+    },
+    {
+      "epoch": 1.113915857605178,
+      "grad_norm": 0.45872536301612854,
+      "learning_rate": 0.00019357409546818247,
+      "loss": 0.7783478498458862,
+      "step": 2582
+    },
+    {
+      "epoch": 1.1147788565264294,
+      "grad_norm": 0.43954113125801086,
+      "learning_rate": 0.00019355676488651508,
+      "loss": 0.6625193357467651,
+      "step": 2584
+    },
+    {
+      "epoch": 1.1156418554476808,
+      "grad_norm": 0.4524446725845337,
+      "learning_rate": 0.00019353941174405558,
+      "loss": 0.7208001613616943,
+      "step": 2586
+    },
+    {
+      "epoch": 1.116504854368932,
+      "grad_norm": 0.4748269021511078,
+      "learning_rate": 0.0001935220360449886,
+      "loss": 0.7567161917686462,
+      "step": 2588
+    },
+    {
+      "epoch": 1.1173678532901834,
+      "grad_norm": 0.4493826925754547,
+      "learning_rate": 0.00019350463779350423,
+      "loss": 0.7631603479385376,
+      "step": 2590
+    },
+    {
+      "epoch": 1.1182308522114348,
+      "grad_norm": 0.45398685336112976,
+      "learning_rate": 0.00019348721699379798,
+      "loss": 0.7756917476654053,
+      "step": 2592
+    },
+    {
+      "epoch": 1.119093851132686,
+      "grad_norm": 0.4246262311935425,
+      "learning_rate": 0.0001934697736500708,
+      "loss": 0.7516605854034424,
+      "step": 2594
+    },
+    {
+      "epoch": 1.1199568500539374,
+      "grad_norm": 0.44801613688468933,
+      "learning_rate": 0.00019345230776652908,
+      "loss": 0.7058185338973999,
+      "step": 2596
+    },
+    {
+      "epoch": 1.1208198489751888,
+      "grad_norm": 0.4591200649738312,
+      "learning_rate": 0.00019343481934738462,
+      "loss": 0.8071328997612,
+      "step": 2598
+    },
+    {
+      "epoch": 1.12168284789644,
+      "grad_norm": 0.39467594027519226,
+      "learning_rate": 0.0001934173083968547,
+      "loss": 0.6992195844650269,
+      "step": 2600
+    },
+    {
+      "epoch": 1.12168284789644,
+      "eval_loss": 0.8300262093544006,
+      "eval_runtime": 658.9488,
+      "eval_samples_per_second": 3.126,
+      "eval_steps_per_second": 3.126,
+      "step": 2600
+    },
+    {
+      "epoch": 1.1225458468176914,
+      "grad_norm": 0.40905407071113586,
+      "learning_rate": 0.00019339977491916196,
+      "loss": 0.7683232426643372,
+      "step": 2602
+    },
+    {
+      "epoch": 1.1234088457389428,
+      "grad_norm": 0.42742034792900085,
+      "learning_rate": 0.00019338221891853453,
+      "loss": 0.7048685550689697,
+      "step": 2604
+    },
+    {
+      "epoch": 1.1242718446601943,
+      "grad_norm": 0.4435581564903259,
+      "learning_rate": 0.000193364640399206,
+      "loss": 0.7206799983978271,
+      "step": 2606
+    },
+    {
+      "epoch": 1.1251348435814454,
+      "grad_norm": 0.48409897089004517,
+      "learning_rate": 0.00019334703936541535,
+      "loss": 0.8230411410331726,
+      "step": 2608
+    },
+    {
+      "epoch": 1.1259978425026969,
+      "grad_norm": 0.5060800909996033,
+      "learning_rate": 0.00019332941582140693,
+      "loss": 0.7833203077316284,
+      "step": 2610
+    },
+    {
+      "epoch": 1.1268608414239483,
+      "grad_norm": 0.48900339007377625,
+      "learning_rate": 0.00019331176977143062,
+      "loss": 0.7785601615905762,
+      "step": 2612
+    },
+    {
+      "epoch": 1.1277238403451997,
+      "grad_norm": 0.46176961064338684,
+      "learning_rate": 0.0001932941012197417,
+      "loss": 0.800255537033081,
+      "step": 2614
+    },
+    {
+      "epoch": 1.1285868392664509,
+      "grad_norm": 0.4946233332157135,
+      "learning_rate": 0.00019327641017060084,
+      "loss": 0.7647190690040588,
+      "step": 2616
+    },
+    {
+      "epoch": 1.1294498381877023,
+      "grad_norm": 0.4153730571269989,
+      "learning_rate": 0.00019325869662827416,
+      "loss": 0.7271775007247925,
+      "step": 2618
+    },
+    {
+      "epoch": 1.1303128371089537,
+      "grad_norm": 0.46707460284233093,
+      "learning_rate": 0.0001932409605970332,
+      "loss": 0.7926952838897705,
+      "step": 2620
+    },
+    {
+      "epoch": 1.1311758360302049,
+      "grad_norm": 0.4980720579624176,
+      "learning_rate": 0.00019322320208115489,
+      "loss": 0.8106555938720703,
+      "step": 2622
+    },
+    {
+      "epoch": 1.1320388349514563,
+      "grad_norm": 0.4300958514213562,
+      "learning_rate": 0.0001932054210849217,
+      "loss": 0.7208700776100159,
+      "step": 2624
+    },
+    {
+      "epoch": 1.1329018338727077,
+      "grad_norm": 0.4756612479686737,
+      "learning_rate": 0.00019318761761262136,
+      "loss": 0.7212259769439697,
+      "step": 2626
+    },
+    {
+      "epoch": 1.133764832793959,
+      "grad_norm": 0.4502181112766266,
+      "learning_rate": 0.00019316979166854713,
+      "loss": 0.6725794672966003,
+      "step": 2628
+    },
+    {
+      "epoch": 1.1346278317152103,
+      "grad_norm": 0.4845540523529053,
+      "learning_rate": 0.00019315194325699765,
+      "loss": 0.7582959532737732,
+      "step": 2630
+    },
+    {
+      "epoch": 1.1354908306364617,
+      "grad_norm": 0.45892953872680664,
+      "learning_rate": 0.00019313407238227698,
+      "loss": 0.7707560062408447,
+      "step": 2632
+    },
+    {
+      "epoch": 1.1363538295577131,
+      "grad_norm": 0.4707877039909363,
+      "learning_rate": 0.00019311617904869464,
+      "loss": 0.7824680209159851,
+      "step": 2634
+    },
+    {
+      "epoch": 1.1372168284789643,
+      "grad_norm": 0.5212311744689941,
+      "learning_rate": 0.00019309826326056545,
+      "loss": 0.7750257253646851,
+      "step": 2636
+    },
+    {
+      "epoch": 1.1380798274002157,
+      "grad_norm": 0.4952082633972168,
+      "learning_rate": 0.0001930803250222098,
+      "loss": 0.7691953182220459,
+      "step": 2638
+    },
+    {
+      "epoch": 1.1389428263214671,
+      "grad_norm": 0.4428424835205078,
+      "learning_rate": 0.00019306236433795334,
+      "loss": 0.737209141254425,
+      "step": 2640
+    },
+    {
+      "epoch": 1.1398058252427186,
+      "grad_norm": 0.5063129663467407,
+      "learning_rate": 0.00019304438121212728,
+      "loss": 0.7487695813179016,
+      "step": 2642
+    },
+    {
+      "epoch": 1.1406688241639698,
+      "grad_norm": 0.4571828246116638,
+      "learning_rate": 0.00019302637564906814,
+      "loss": 0.7647218704223633,
+      "step": 2644
+    },
+    {
+      "epoch": 1.1415318230852212,
+      "grad_norm": 0.4918457567691803,
+      "learning_rate": 0.00019300834765311785,
+      "loss": 0.8173171877861023,
+      "step": 2646
+    },
+    {
+      "epoch": 1.1423948220064726,
+      "grad_norm": 0.40057408809661865,
+      "learning_rate": 0.0001929902972286238,
+      "loss": 0.6472562551498413,
+      "step": 2648
+    },
+    {
+      "epoch": 1.1432578209277238,
+      "grad_norm": 0.432763934135437,
+      "learning_rate": 0.0001929722243799388,
+      "loss": 0.8462889194488525,
+      "step": 2650
+    },
+    {
+      "epoch": 1.1441208198489752,
+      "grad_norm": 0.36540713906288147,
+      "learning_rate": 0.000192954129111421,
+      "loss": 0.808388352394104,
+      "step": 2652
+    },
+    {
+      "epoch": 1.1449838187702266,
+      "grad_norm": 0.4236038029193878,
+      "learning_rate": 0.00019293601142743403,
+      "loss": 0.7144365906715393,
+      "step": 2654
+    },
+    {
+      "epoch": 1.1458468176914778,
+      "grad_norm": 0.4316163957118988,
+      "learning_rate": 0.00019291787133234682,
+      "loss": 0.693168580532074,
+      "step": 2656
+    },
+    {
+      "epoch": 1.1467098166127292,
+      "grad_norm": 0.43088117241859436,
+      "learning_rate": 0.00019289970883053386,
+      "loss": 0.7981953024864197,
+      "step": 2658
+    },
+    {
+      "epoch": 1.1475728155339806,
+      "grad_norm": 0.4200972318649292,
+      "learning_rate": 0.00019288152392637486,
+      "loss": 0.7342561483383179,
+      "step": 2660
+    },
+    {
+      "epoch": 1.148435814455232,
+      "grad_norm": 0.4461527466773987,
+      "learning_rate": 0.00019286331662425512,
+      "loss": 0.7239733934402466,
+      "step": 2662
+    },
+    {
+      "epoch": 1.1492988133764832,
+      "grad_norm": 0.3945358097553253,
+      "learning_rate": 0.00019284508692856518,
+      "loss": 0.6575030088424683,
+      "step": 2664
+    },
+    {
+      "epoch": 1.1501618122977346,
+      "grad_norm": 0.4653085470199585,
+      "learning_rate": 0.0001928268348437011,
+      "loss": 0.7754159569740295,
+      "step": 2666
+    },
+    {
+      "epoch": 1.151024811218986,
+      "grad_norm": 0.47542640566825867,
+      "learning_rate": 0.00019280856037406422,
+      "loss": 0.683927595615387,
+      "step": 2668
+    },
+    {
+      "epoch": 1.1518878101402374,
+      "grad_norm": 0.4191996455192566,
+      "learning_rate": 0.00019279026352406143,
+      "loss": 0.6907603144645691,
+      "step": 2670
+    },
+    {
+      "epoch": 1.1527508090614886,
+      "grad_norm": 0.4643108546733856,
+      "learning_rate": 0.00019277194429810488,
+      "loss": 0.8362683653831482,
+      "step": 2672
+    },
+    {
+      "epoch": 1.15361380798274,
+      "grad_norm": 0.4213605225086212,
+      "learning_rate": 0.00019275360270061217,
+      "loss": 0.737736701965332,
+      "step": 2674
+    },
+    {
+      "epoch": 1.1544768069039915,
+      "grad_norm": 0.537070095539093,
+      "learning_rate": 0.0001927352387360063,
+      "loss": 0.7617850303649902,
+      "step": 2676
+    },
+    {
+      "epoch": 1.1553398058252426,
+      "grad_norm": 0.47798195481300354,
+      "learning_rate": 0.0001927168524087157,
+      "loss": 0.7252766489982605,
+      "step": 2678
+    },
+    {
+      "epoch": 1.156202804746494,
+      "grad_norm": 0.48654067516326904,
+      "learning_rate": 0.00019269844372317408,
+      "loss": 0.7671495676040649,
+      "step": 2680
+    },
+    {
+      "epoch": 1.1570658036677455,
+      "grad_norm": 0.5374535322189331,
+      "learning_rate": 0.00019268001268382066,
+      "loss": 0.8648670315742493,
+      "step": 2682
+    },
+    {
+      "epoch": 1.1579288025889967,
+      "grad_norm": 0.42167672514915466,
+      "learning_rate": 0.00019266155929509996,
+      "loss": 0.6848083138465881,
+      "step": 2684
+    },
+    {
+      "epoch": 1.158791801510248,
+      "grad_norm": 0.38867753744125366,
+      "learning_rate": 0.00019264308356146197,
+      "loss": 0.6890886425971985,
+      "step": 2686
+    },
+    {
+      "epoch": 1.1596548004314995,
+      "grad_norm": 0.42711013555526733,
+      "learning_rate": 0.000192624585487362,
+      "loss": 0.7399795651435852,
+      "step": 2688
+    },
+    {
+      "epoch": 1.160517799352751,
+      "grad_norm": 0.48802322149276733,
+      "learning_rate": 0.00019260606507726083,
+      "loss": 0.8026465773582458,
+      "step": 2690
+    },
+    {
+      "epoch": 1.161380798274002,
+      "grad_norm": 0.47166478633880615,
+      "learning_rate": 0.00019258752233562452,
+      "loss": 0.7589768171310425,
+      "step": 2692
+    },
+    {
+      "epoch": 1.1622437971952535,
+      "grad_norm": 0.47413256764411926,
+      "learning_rate": 0.00019256895726692459,
+      "loss": 0.7620571851730347,
+      "step": 2694
+    },
+    {
+      "epoch": 1.163106796116505,
+      "grad_norm": 0.5377517342567444,
+      "learning_rate": 0.0001925503698756379,
+      "loss": 0.798933207988739,
+      "step": 2696
+    },
+    {
+      "epoch": 1.1639697950377563,
+      "grad_norm": 0.44990095496177673,
+      "learning_rate": 0.00019253176016624678,
+      "loss": 0.7550637125968933,
+      "step": 2698
+    },
+    {
+      "epoch": 1.1648327939590075,
+      "grad_norm": 0.4633009433746338,
+      "learning_rate": 0.00019251312814323876,
+      "loss": 0.7919567227363586,
+      "step": 2700
+    },
+    {
+      "epoch": 1.1648327939590075,
+      "eval_loss": 0.8251468539237976,
+      "eval_runtime": 667.0436,
+      "eval_samples_per_second": 3.088,
+      "eval_steps_per_second": 3.088,
+      "step": 2700
+    },
+    {
+      "epoch": 1.165695792880259,
+      "grad_norm": 0.4339669942855835,
+      "learning_rate": 0.000192494473811107,
+      "loss": 0.8140546083450317,
+      "step": 2702
+    },
+    {
+      "epoch": 1.1665587918015103,
+      "grad_norm": 0.5794349312782288,
+      "learning_rate": 0.00019247579717434984,
+      "loss": 0.8462281823158264,
+      "step": 2704
+    },
+    {
+      "epoch": 1.1674217907227615,
+      "grad_norm": 0.41820067167282104,
+      "learning_rate": 0.00019245709823747102,
+      "loss": 0.7468760013580322,
+      "step": 2706
+    },
+    {
+      "epoch": 1.168284789644013,
+      "grad_norm": 0.4002464711666107,
+      "learning_rate": 0.0001924383770049798,
+      "loss": 0.694807767868042,
+      "step": 2708
+    },
+    {
+      "epoch": 1.1691477885652644,
+      "grad_norm": 0.47752025723457336,
+      "learning_rate": 0.00019241963348139068,
+      "loss": 0.7512534856796265,
+      "step": 2710
+    },
+    {
+      "epoch": 1.1700107874865155,
+      "grad_norm": 0.45852312445640564,
+      "learning_rate": 0.0001924008676712236,
+      "loss": 0.8069711923599243,
+      "step": 2712
+    },
+    {
+      "epoch": 1.170873786407767,
+      "grad_norm": 0.4336509108543396,
+      "learning_rate": 0.0001923820795790038,
+      "loss": 0.7022751569747925,
+      "step": 2714
+    },
+    {
+      "epoch": 1.1717367853290184,
+      "grad_norm": 0.40044888854026794,
+      "learning_rate": 0.00019236326920926193,
+      "loss": 0.6904252767562866,
+      "step": 2716
+    },
+    {
+      "epoch": 1.1725997842502698,
+      "grad_norm": 0.48451852798461914,
+      "learning_rate": 0.00019234443656653412,
+      "loss": 0.7924585938453674,
+      "step": 2718
+    },
+    {
+      "epoch": 1.173462783171521,
+      "grad_norm": 0.49168315529823303,
+      "learning_rate": 0.0001923255816553617,
+      "loss": 0.7383922338485718,
+      "step": 2720
+    },
+    {
+      "epoch": 1.1743257820927724,
+      "grad_norm": 0.4363260269165039,
+      "learning_rate": 0.00019230670448029148,
+      "loss": 0.7508589029312134,
+      "step": 2722
+    },
+    {
+      "epoch": 1.1751887810140238,
+      "grad_norm": 0.4520082175731659,
+      "learning_rate": 0.0001922878050458756,
+      "loss": 0.7814584970474243,
+      "step": 2724
+    },
+    {
+      "epoch": 1.176051779935275,
+      "grad_norm": 0.4675535559654236,
+      "learning_rate": 0.00019226888335667158,
+      "loss": 0.7011970281600952,
+      "step": 2726
+    },
+    {
+      "epoch": 1.1769147788565264,
+      "grad_norm": 0.47536277770996094,
+      "learning_rate": 0.00019224993941724226,
+      "loss": 0.7414659857749939,
+      "step": 2728
+    },
+    {
+      "epoch": 1.1777777777777778,
+      "grad_norm": 0.5455507040023804,
+      "learning_rate": 0.00019223097323215594,
+      "loss": 0.7949363589286804,
+      "step": 2730
+    },
+    {
+      "epoch": 1.1786407766990292,
+      "grad_norm": 0.4897938370704651,
+      "learning_rate": 0.00019221198480598616,
+      "loss": 0.813949465751648,
+      "step": 2732
+    },
+    {
+      "epoch": 1.1795037756202804,
+      "grad_norm": 0.46766766905784607,
+      "learning_rate": 0.000192192974143312,
+      "loss": 0.7444795966148376,
+      "step": 2734
+    },
+    {
+      "epoch": 1.1803667745415318,
+      "grad_norm": 0.41503575444221497,
+      "learning_rate": 0.00019217394124871768,
+      "loss": 0.7937621474266052,
+      "step": 2736
+    },
+    {
+      "epoch": 1.1812297734627832,
+      "grad_norm": 0.41906169056892395,
+      "learning_rate": 0.00019215488612679295,
+      "loss": 0.7342435717582703,
+      "step": 2738
+    },
+    {
+      "epoch": 1.1820927723840344,
+      "grad_norm": 0.47820931673049927,
+      "learning_rate": 0.00019213580878213292,
+      "loss": 0.7533642053604126,
+      "step": 2740
+    },
+    {
+      "epoch": 1.1829557713052858,
+      "grad_norm": 0.44907891750335693,
+      "learning_rate": 0.00019211670921933792,
+      "loss": 0.799866795539856,
+      "step": 2742
+    },
+    {
+      "epoch": 1.1838187702265373,
+      "grad_norm": 0.48050498962402344,
+      "learning_rate": 0.00019209758744301376,
+      "loss": 0.7468855381011963,
+      "step": 2744
+    },
+    {
+      "epoch": 1.1846817691477884,
+      "grad_norm": 0.4311312437057495,
+      "learning_rate": 0.00019207844345777155,
+      "loss": 0.7423141002655029,
+      "step": 2746
+    },
+    {
+      "epoch": 1.1855447680690399,
+      "grad_norm": 0.439386248588562,
+      "learning_rate": 0.0001920592772682278,
+      "loss": 0.7046169638633728,
+      "step": 2748
+    },
+    {
+      "epoch": 1.1864077669902913,
+      "grad_norm": 0.4230091869831085,
+      "learning_rate": 0.00019204008887900435,
+      "loss": 0.7284982204437256,
+      "step": 2750
+    },
+    {
+      "epoch": 1.1872707659115427,
+      "grad_norm": 0.4583308696746826,
+      "learning_rate": 0.0001920208782947284,
+      "loss": 0.7297943234443665,
+      "step": 2752
+    },
+    {
+      "epoch": 1.1881337648327939,
+      "grad_norm": 0.44526317715644836,
+      "learning_rate": 0.00019200164552003247,
+      "loss": 0.7170902490615845,
+      "step": 2754
+    },
+    {
+      "epoch": 1.1889967637540453,
+      "grad_norm": 0.46664097905158997,
+      "learning_rate": 0.00019198239055955444,
+      "loss": 0.7746089696884155,
+      "step": 2756
+    },
+    {
+      "epoch": 1.1898597626752967,
+      "grad_norm": 0.4023241102695465,
+      "learning_rate": 0.0001919631134179376,
+      "loss": 0.7381687760353088,
+      "step": 2758
+    },
+    {
+      "epoch": 1.190722761596548,
+      "grad_norm": 0.5126422047615051,
+      "learning_rate": 0.00019194381409983055,
+      "loss": 0.7951313853263855,
+      "step": 2760
+    },
+    {
+      "epoch": 1.1915857605177993,
+      "grad_norm": 0.4056018590927124,
+      "learning_rate": 0.0001919244926098872,
+      "loss": 0.692834198474884,
+      "step": 2762
+    },
+    {
+      "epoch": 1.1924487594390507,
+      "grad_norm": 0.49225106835365295,
+      "learning_rate": 0.00019190514895276687,
+      "loss": 0.7494171857833862,
+      "step": 2764
+    },
+    {
+      "epoch": 1.1933117583603021,
+      "grad_norm": 0.47823601961135864,
+      "learning_rate": 0.00019188578313313417,
+      "loss": 0.8541221022605896,
+      "step": 2766
+    },
+    {
+      "epoch": 1.1941747572815533,
+      "grad_norm": 0.461773544549942,
+      "learning_rate": 0.0001918663951556591,
+      "loss": 0.8017639517784119,
+      "step": 2768
+    },
+    {
+      "epoch": 1.1950377562028047,
+      "grad_norm": 0.48888009786605835,
+      "learning_rate": 0.00019184698502501695,
+      "loss": 0.7509341835975647,
+      "step": 2770
+    },
+    {
+      "epoch": 1.1959007551240561,
+      "grad_norm": 0.4140535295009613,
+      "learning_rate": 0.0001918275527458884,
+      "loss": 0.7123914361000061,
+      "step": 2772
+    },
+    {
+      "epoch": 1.1967637540453073,
+      "grad_norm": 0.4918449819087982,
+      "learning_rate": 0.00019180809832295952,
+      "loss": 0.73713219165802,
+      "step": 2774
+    },
+    {
+      "epoch": 1.1976267529665587,
+      "grad_norm": 0.48218831419944763,
+      "learning_rate": 0.00019178862176092159,
+      "loss": 0.708644688129425,
+      "step": 2776
+    },
+    {
+      "epoch": 1.1984897518878102,
+      "grad_norm": 0.45588797330856323,
+      "learning_rate": 0.0001917691230644713,
+      "loss": 0.7277385592460632,
+      "step": 2778
+    },
+    {
+      "epoch": 1.1993527508090616,
+      "grad_norm": 0.3959250748157501,
+      "learning_rate": 0.00019174960223831064,
+      "loss": 0.7501665949821472,
+      "step": 2780
+    },
+    {
+      "epoch": 1.2002157497303128,
+      "grad_norm": 0.6228574514389038,
+      "learning_rate": 0.00019173005928714703,
+      "loss": 0.8842931389808655,
+      "step": 2782
+    },
+    {
+      "epoch": 1.2010787486515642,
+      "grad_norm": 0.4346935749053955,
+      "learning_rate": 0.00019171049421569318,
+      "loss": 0.7008639574050903,
+      "step": 2784
+    },
+    {
+      "epoch": 1.2019417475728156,
+      "grad_norm": 0.691254198551178,
+      "learning_rate": 0.00019169090702866705,
+      "loss": 0.7203702330589294,
+      "step": 2786
+    },
+    {
+      "epoch": 1.202804746494067,
+      "grad_norm": 0.4219740331172943,
+      "learning_rate": 0.00019167129773079203,
+      "loss": 0.7170791029930115,
+      "step": 2788
+    },
+    {
+      "epoch": 1.2036677454153182,
+      "grad_norm": 0.4639855921268463,
+      "learning_rate": 0.00019165166632679686,
+      "loss": 0.7895086407661438,
+      "step": 2790
+    },
+    {
+      "epoch": 1.2045307443365696,
+      "grad_norm": 0.44938549399375916,
+      "learning_rate": 0.00019163201282141546,
+      "loss": 0.7323113679885864,
+      "step": 2792
+    },
+    {
+      "epoch": 1.205393743257821,
+      "grad_norm": 0.43633413314819336,
+      "learning_rate": 0.00019161233721938728,
+      "loss": 0.7486892342567444,
+      "step": 2794
+    },
+    {
+      "epoch": 1.2062567421790722,
+      "grad_norm": 0.42983385920524597,
+      "learning_rate": 0.00019159263952545698,
+      "loss": 0.777079701423645,
+      "step": 2796
+    },
+    {
+      "epoch": 1.2071197411003236,
+      "grad_norm": 0.4630664587020874,
+      "learning_rate": 0.00019157291974437456,
+      "loss": 0.800602912902832,
+      "step": 2798
+    },
+    {
+      "epoch": 1.207982740021575,
+      "grad_norm": 0.43607378005981445,
+      "learning_rate": 0.00019155317788089536,
+      "loss": 0.6763592958450317,
+      "step": 2800
+    },
+    {
+      "epoch": 1.207982740021575,
+      "eval_loss": 0.8219058513641357,
+      "eval_runtime": 661.5144,
+      "eval_samples_per_second": 3.114,
+      "eval_steps_per_second": 3.114,
+      "step": 2800
+    },
+    {
+      "epoch": 1.2088457389428262,
+      "grad_norm": 0.4910019338130951,
+      "learning_rate": 0.00019153341393978002,
+      "loss": 0.7569329738616943,
+      "step": 2802
+    },
+    {
+      "epoch": 1.2097087378640776,
+      "grad_norm": 0.4993135631084442,
+      "learning_rate": 0.00019151362792579457,
+      "loss": 0.734387218952179,
+      "step": 2804
+    },
+    {
+      "epoch": 1.210571736785329,
+      "grad_norm": 0.48742055892944336,
+      "learning_rate": 0.00019149381984371027,
+      "loss": 0.719099223613739,
+      "step": 2806
+    },
+    {
+      "epoch": 1.2114347357065804,
+      "grad_norm": 0.4083765149116516,
+      "learning_rate": 0.00019147398969830378,
+      "loss": 0.8490580320358276,
+      "step": 2808
+    },
+    {
+      "epoch": 1.2122977346278316,
+      "grad_norm": 0.4316021502017975,
+      "learning_rate": 0.00019145413749435702,
+      "loss": 0.7604904770851135,
+      "step": 2810
+    },
+    {
+      "epoch": 1.213160733549083,
+      "grad_norm": 0.4294895529747009,
+      "learning_rate": 0.0001914342632366573,
+      "loss": 0.7739580869674683,
+      "step": 2812
+    },
+    {
+      "epoch": 1.2140237324703345,
+      "grad_norm": 0.4773736000061035,
+      "learning_rate": 0.00019141436692999718,
+      "loss": 0.7625397443771362,
+      "step": 2814
+    },
+    {
+      "epoch": 1.2148867313915859,
+      "grad_norm": 0.46148404479026794,
+      "learning_rate": 0.00019139444857917457,
+      "loss": 0.7224686741828918,
+      "step": 2816
+    },
+    {
+      "epoch": 1.215749730312837,
+      "grad_norm": 0.436300128698349,
+      "learning_rate": 0.0001913745081889927,
+      "loss": 0.7708583474159241,
+      "step": 2818
+    },
+    {
+      "epoch": 1.2166127292340885,
+      "grad_norm": 0.4959073066711426,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.8550406098365784,
+      "step": 2820
+    },
+    {
+      "epoch": 1.2174757281553399,
+      "grad_norm": 0.4672411382198334,
+      "learning_rate": 0.00019133456130979062,
+      "loss": 0.781597912311554,
+      "step": 2822
+    },
+    {
+      "epoch": 1.218338727076591,
+      "grad_norm": 0.5249256491661072,
+      "learning_rate": 0.0001913145548304034,
+      "loss": 0.860835075378418,
+      "step": 2824
+    },
+    {
+      "epoch": 1.2192017259978425,
+      "grad_norm": 0.5132579207420349,
+      "learning_rate": 0.00019129452633092294,
+      "loss": 0.715717613697052,
+      "step": 2826
+    },
+    {
+      "epoch": 1.220064724919094,
+      "grad_norm": 0.4291874170303345,
+      "learning_rate": 0.00019127447581617903,
+      "loss": 0.727998673915863,
+      "step": 2828
+    },
+    {
+      "epoch": 1.220927723840345,
+      "grad_norm": 0.3698529005050659,
+      "learning_rate": 0.00019125440329100673,
+      "loss": 0.7164589762687683,
+      "step": 2830
+    },
+    {
+      "epoch": 1.2217907227615965,
+      "grad_norm": 0.5034273266792297,
+      "learning_rate": 0.00019123430876024646,
+      "loss": 0.8113957643508911,
+      "step": 2832
+    },
+    {
+      "epoch": 1.222653721682848,
+      "grad_norm": 0.4612481892108917,
+      "learning_rate": 0.0001912141922287439,
+      "loss": 0.7350133061408997,
+      "step": 2834
+    },
+    {
+      "epoch": 1.2235167206040993,
+      "grad_norm": 0.4433611035346985,
+      "learning_rate": 0.00019119405370135012,
+      "loss": 0.8156216144561768,
+      "step": 2836
+    },
+    {
+      "epoch": 1.2243797195253505,
+      "grad_norm": 0.4700625240802765,
+      "learning_rate": 0.00019117389318292136,
+      "loss": 0.7824334502220154,
+      "step": 2838
+    },
+    {
+      "epoch": 1.225242718446602,
+      "grad_norm": 0.4854332208633423,
+      "learning_rate": 0.00019115371067831928,
+      "loss": 0.8136369585990906,
+      "step": 2840
+    },
+    {
+      "epoch": 1.2261057173678533,
+      "grad_norm": 0.4403935372829437,
+      "learning_rate": 0.00019113350619241078,
+      "loss": 0.7042210102081299,
+      "step": 2842
+    },
+    {
+      "epoch": 1.2269687162891048,
+      "grad_norm": 0.4311469793319702,
+      "learning_rate": 0.00019111327973006813,
+      "loss": 0.7598573565483093,
+      "step": 2844
+    },
+    {
+      "epoch": 1.227831715210356,
+      "grad_norm": 0.5551521182060242,
+      "learning_rate": 0.0001910930312961688,
+      "loss": 0.8001043796539307,
+      "step": 2846
+    },
+    {
+      "epoch": 1.2286947141316074,
+      "grad_norm": 0.44149601459503174,
+      "learning_rate": 0.0001910727608955956,
+      "loss": 0.6874746084213257,
+      "step": 2848
+    },
+    {
+      "epoch": 1.2295577130528588,
+      "grad_norm": 0.44726014137268066,
+      "learning_rate": 0.00019105246853323672,
+      "loss": 0.7484437823295593,
+      "step": 2850
+    },
+    {
+      "epoch": 1.23042071197411,
+      "grad_norm": 0.4710492193698883,
+      "learning_rate": 0.00019103215421398546,
+      "loss": 0.7512558102607727,
+      "step": 2852
+    },
+    {
+      "epoch": 1.2312837108953614,
+      "grad_norm": 0.4304901957511902,
+      "learning_rate": 0.0001910118179427406,
+      "loss": 0.7161203622817993,
+      "step": 2854
+    },
+    {
+      "epoch": 1.2321467098166128,
+      "grad_norm": 0.4651104509830475,
+      "learning_rate": 0.00019099145972440614,
+      "loss": 0.722236156463623,
+      "step": 2856
+    },
+    {
+      "epoch": 1.233009708737864,
+      "grad_norm": 0.5231161117553711,
+      "learning_rate": 0.00019097107956389135,
+      "loss": 0.8200751543045044,
+      "step": 2858
+    },
+    {
+      "epoch": 1.2338727076591154,
+      "grad_norm": 0.45574283599853516,
+      "learning_rate": 0.00019095067746611083,
+      "loss": 0.7529966235160828,
+      "step": 2860
+    },
+    {
+      "epoch": 1.2347357065803668,
+      "grad_norm": 0.4451949894428253,
+      "learning_rate": 0.00019093025343598448,
+      "loss": 0.7574380040168762,
+      "step": 2862
+    },
+    {
+      "epoch": 1.2355987055016182,
+      "grad_norm": 0.4557603597640991,
+      "learning_rate": 0.00019090980747843737,
+      "loss": 0.8461237549781799,
+      "step": 2864
+    },
+    {
+      "epoch": 1.2364617044228694,
+      "grad_norm": 0.41115859150886536,
+      "learning_rate": 0.00019088933959840004,
+      "loss": 0.7910104990005493,
+      "step": 2866
+    },
+    {
+      "epoch": 1.2373247033441208,
+      "grad_norm": 0.5087599158287048,
+      "learning_rate": 0.0001908688498008082,
+      "loss": 0.8318688273429871,
+      "step": 2868
+    },
+    {
+      "epoch": 1.2381877022653722,
+      "grad_norm": 0.4243653118610382,
+      "learning_rate": 0.00019084833809060285,
+      "loss": 0.713392436504364,
+      "step": 2870
+    },
+    {
+      "epoch": 1.2390507011866236,
+      "grad_norm": 0.3965010344982147,
+      "learning_rate": 0.00019082780447273034,
+      "loss": 0.7697778344154358,
+      "step": 2872
+    },
+    {
+      "epoch": 1.2399137001078748,
+      "grad_norm": 0.4493406116962433,
+      "learning_rate": 0.00019080724895214222,
+      "loss": 0.7437527179718018,
+      "step": 2874
+    },
+    {
+      "epoch": 1.2407766990291262,
+      "grad_norm": 0.5189685821533203,
+      "learning_rate": 0.00019078667153379537,
+      "loss": 0.858138918876648,
+      "step": 2876
+    },
+    {
+      "epoch": 1.2416396979503777,
+      "grad_norm": 0.39455580711364746,
+      "learning_rate": 0.00019076607222265197,
+      "loss": 0.7235360145568848,
+      "step": 2878
+    },
+    {
+      "epoch": 1.2425026968716288,
+      "grad_norm": 0.524804413318634,
+      "learning_rate": 0.00019074545102367943,
+      "loss": 0.7995675206184387,
+      "step": 2880
+    },
+    {
+      "epoch": 1.2433656957928803,
+      "grad_norm": 0.4873242974281311,
+      "learning_rate": 0.00019072480794185044,
+      "loss": 0.8404105305671692,
+      "step": 2882
+    },
+    {
+      "epoch": 1.2442286947141317,
+      "grad_norm": 0.4591716527938843,
+      "learning_rate": 0.000190704142982143,
+      "loss": 0.7540513277053833,
+      "step": 2884
+    },
+    {
+      "epoch": 1.2450916936353829,
+      "grad_norm": 0.48403632640838623,
+      "learning_rate": 0.0001906834561495404,
+      "loss": 0.7566621899604797,
+      "step": 2886
+    },
+    {
+      "epoch": 1.2459546925566343,
+      "grad_norm": 0.4854280948638916,
+      "learning_rate": 0.00019066274744903113,
+      "loss": 0.7141375541687012,
+      "step": 2888
+    },
+    {
+      "epoch": 1.2468176914778857,
+      "grad_norm": 0.45851001143455505,
+      "learning_rate": 0.00019064201688560902,
+      "loss": 0.7798115611076355,
+      "step": 2890
+    },
+    {
+      "epoch": 1.247680690399137,
+      "grad_norm": 0.4584810435771942,
+      "learning_rate": 0.00019062126446427318,
+      "loss": 0.7212263941764832,
+      "step": 2892
+    },
+    {
+      "epoch": 1.2485436893203883,
+      "grad_norm": 0.5282798409461975,
+      "learning_rate": 0.00019060049019002792,
+      "loss": 0.8268418312072754,
+      "step": 2894
+    },
+    {
+      "epoch": 1.2494066882416397,
+      "grad_norm": 0.40996623039245605,
+      "learning_rate": 0.00019057969406788289,
+      "loss": 0.7512726783752441,
+      "step": 2896
+    },
+    {
+      "epoch": 1.250269687162891,
+      "grad_norm": 0.39559319615364075,
+      "learning_rate": 0.00019055887610285296,
+      "loss": 0.6680556535720825,
+      "step": 2898
+    },
+    {
+      "epoch": 1.2511326860841425,
+      "grad_norm": 0.42002710700035095,
+      "learning_rate": 0.0001905380362999583,
+      "loss": 0.7307850122451782,
+      "step": 2900
+    },
+    {
+      "epoch": 1.2511326860841425,
+      "eval_loss": 0.8155517578125,
+      "eval_runtime": 650.62,
+      "eval_samples_per_second": 3.166,
+      "eval_steps_per_second": 3.166,
+      "step": 2900
+    },
+    {
+      "epoch": 1.2519956850053937,
+      "grad_norm": 0.3914625644683838,
+      "learning_rate": 0.00019051717466422435,
+      "loss": 0.7316054701805115,
+      "step": 2902
+    },
+    {
+      "epoch": 1.2528586839266451,
+      "grad_norm": 0.48939383029937744,
+      "learning_rate": 0.00019049629120068175,
+      "loss": 0.8977305889129639,
+      "step": 2904
+    },
+    {
+      "epoch": 1.2537216828478965,
+      "grad_norm": 0.4892135262489319,
+      "learning_rate": 0.0001904753859143665,
+      "loss": 0.7962324619293213,
+      "step": 2906
+    },
+    {
+      "epoch": 1.2545846817691477,
+      "grad_norm": 0.5323660969734192,
+      "learning_rate": 0.00019045445881031982,
+      "loss": 0.791375458240509,
+      "step": 2908
+    },
+    {
+      "epoch": 1.2554476806903991,
+      "grad_norm": 0.44778114557266235,
+      "learning_rate": 0.00019043350989358818,
+      "loss": 0.7218163013458252,
+      "step": 2910
+    },
+    {
+      "epoch": 1.2563106796116505,
+      "grad_norm": 0.4763379991054535,
+      "learning_rate": 0.00019041253916922326,
+      "loss": 0.7380548119544983,
+      "step": 2912
+    },
+    {
+      "epoch": 1.2571736785329017,
+      "grad_norm": 0.4979628026485443,
+      "learning_rate": 0.00019039154664228213,
+      "loss": 0.7586072683334351,
+      "step": 2914
+    },
+    {
+      "epoch": 1.2580366774541532,
+      "grad_norm": 0.46175920963287354,
+      "learning_rate": 0.000190370532317827,
+      "loss": 0.763477623462677,
+      "step": 2916
+    },
+    {
+      "epoch": 1.2588996763754046,
+      "grad_norm": 0.43192169070243835,
+      "learning_rate": 0.0001903494962009254,
+      "loss": 0.7479409575462341,
+      "step": 2918
+    },
+    {
+      "epoch": 1.2597626752966558,
+      "grad_norm": 0.42883434891700745,
+      "learning_rate": 0.0001903284382966501,
+      "loss": 0.7355074882507324,
+      "step": 2920
+    },
+    {
+      "epoch": 1.2606256742179072,
+      "grad_norm": 0.47708168625831604,
+      "learning_rate": 0.00019030735861007912,
+      "loss": 0.7762811183929443,
+      "step": 2922
+    },
+    {
+      "epoch": 1.2614886731391586,
+      "grad_norm": 0.4478151500225067,
+      "learning_rate": 0.0001902862571462957,
+      "loss": 0.6964467763900757,
+      "step": 2924
+    },
+    {
+      "epoch": 1.26235167206041,
+      "grad_norm": 0.4531081020832062,
+      "learning_rate": 0.00019026513391038837,
+      "loss": 0.7414857745170593,
+      "step": 2926
+    },
+    {
+      "epoch": 1.2632146709816614,
+      "grad_norm": 0.4623842239379883,
+      "learning_rate": 0.00019024398890745092,
+      "loss": 0.7639371156692505,
+      "step": 2928
+    },
+    {
+      "epoch": 1.2640776699029126,
+      "grad_norm": 0.4362739622592926,
+      "learning_rate": 0.00019022282214258238,
+      "loss": 0.800457239151001,
+      "step": 2930
+    },
+    {
+      "epoch": 1.264940668824164,
+      "grad_norm": 0.42854052782058716,
+      "learning_rate": 0.000190201633620887,
+      "loss": 0.7960386872291565,
+      "step": 2932
+    },
+    {
+      "epoch": 1.2658036677454154,
+      "grad_norm": 0.47477999329566956,
+      "learning_rate": 0.0001901804233474743,
+      "loss": 0.7544003129005432,
+      "step": 2934
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 0.4584832191467285,
+      "learning_rate": 0.00019015919132745905,
+      "loss": 0.7819825410842896,
+      "step": 2936
+    },
+    {
+      "epoch": 1.267529665587918,
+      "grad_norm": 0.5465012192726135,
+      "learning_rate": 0.00019013793756596123,
+      "loss": 0.7719182372093201,
+      "step": 2938
+    },
+    {
+      "epoch": 1.2683926645091694,
+      "grad_norm": 0.42024123668670654,
+      "learning_rate": 0.00019011666206810614,
+      "loss": 0.7442063093185425,
+      "step": 2940
+    },
+    {
+      "epoch": 1.2692556634304206,
+      "grad_norm": 0.4374787211418152,
+      "learning_rate": 0.00019009536483902424,
+      "loss": 0.6696176528930664,
+      "step": 2942
+    },
+    {
+      "epoch": 1.270118662351672,
+      "grad_norm": 0.4136449992656708,
+      "learning_rate": 0.00019007404588385125,
+      "loss": 0.7048487663269043,
+      "step": 2944
+    },
+    {
+      "epoch": 1.2709816612729234,
+      "grad_norm": 0.4463474452495575,
+      "learning_rate": 0.00019005270520772817,
+      "loss": 0.7587971687316895,
+      "step": 2946
+    },
+    {
+      "epoch": 1.2718446601941746,
+      "grad_norm": 0.43167322874069214,
+      "learning_rate": 0.00019003134281580115,
+      "loss": 0.7741286754608154,
+      "step": 2948
+    },
+    {
+      "epoch": 1.272707659115426,
+      "grad_norm": 0.5189676284790039,
+      "learning_rate": 0.0001900099587132217,
+      "loss": 0.7572245597839355,
+      "step": 2950
+    },
+    {
+      "epoch": 1.2735706580366775,
+      "grad_norm": 0.4256224036216736,
+      "learning_rate": 0.00018998855290514646,
+      "loss": 0.7743186354637146,
+      "step": 2952
+    },
+    {
+      "epoch": 1.2744336569579289,
+      "grad_norm": 0.4304806888103485,
+      "learning_rate": 0.00018996712539673735,
+      "loss": 0.7287778854370117,
+      "step": 2954
+    },
+    {
+      "epoch": 1.2752966558791803,
+      "grad_norm": 0.489372193813324,
+      "learning_rate": 0.00018994567619316156,
+      "loss": 0.7930773496627808,
+      "step": 2956
+    },
+    {
+      "epoch": 1.2761596548004315,
+      "grad_norm": 0.3855830430984497,
+      "learning_rate": 0.0001899242052995914,
+      "loss": 0.7283111214637756,
+      "step": 2958
+    },
+    {
+      "epoch": 1.2770226537216829,
+      "grad_norm": 0.46708667278289795,
+      "learning_rate": 0.00018990271272120452,
+      "loss": 0.721849262714386,
+      "step": 2960
+    },
+    {
+      "epoch": 1.2778856526429343,
+      "grad_norm": 0.3663526773452759,
+      "learning_rate": 0.00018988119846318377,
+      "loss": 0.6678964495658875,
+      "step": 2962
+    },
+    {
+      "epoch": 1.2787486515641855,
+      "grad_norm": 0.5074638724327087,
+      "learning_rate": 0.00018985966253071718,
+      "loss": 0.8021678924560547,
+      "step": 2964
+    },
+    {
+      "epoch": 1.279611650485437,
+      "grad_norm": 0.4902975857257843,
+      "learning_rate": 0.00018983810492899806,
+      "loss": 0.8313384056091309,
+      "step": 2966
+    },
+    {
+      "epoch": 1.2804746494066883,
+      "grad_norm": 0.5023161768913269,
+      "learning_rate": 0.00018981652566322493,
+      "loss": 0.8330302834510803,
+      "step": 2968
+    },
+    {
+      "epoch": 1.2813376483279395,
+      "grad_norm": 0.48227089643478394,
+      "learning_rate": 0.00018979492473860155,
+      "loss": 0.8806158304214478,
+      "step": 2970
+    },
+    {
+      "epoch": 1.282200647249191,
+      "grad_norm": 0.40143465995788574,
+      "learning_rate": 0.00018977330216033683,
+      "loss": 0.6835185885429382,
+      "step": 2972
+    },
+    {
+      "epoch": 1.2830636461704423,
+      "grad_norm": 0.4368304908275604,
+      "learning_rate": 0.00018975165793364503,
+      "loss": 0.7207706570625305,
+      "step": 2974
+    },
+    {
+      "epoch": 1.2839266450916935,
+      "grad_norm": 0.39989250898361206,
+      "learning_rate": 0.0001897299920637455,
+      "loss": 0.6909692883491516,
+      "step": 2976
+    },
+    {
+      "epoch": 1.284789644012945,
+      "grad_norm": 0.4826473593711853,
+      "learning_rate": 0.0001897083045558629,
+      "loss": 0.838360071182251,
+      "step": 2978
+    },
+    {
+      "epoch": 1.2856526429341963,
+      "grad_norm": 0.4860877990722656,
+      "learning_rate": 0.00018968659541522705,
+      "loss": 0.7693317532539368,
+      "step": 2980
+    },
+    {
+      "epoch": 1.2865156418554478,
+      "grad_norm": 0.4361511170864105,
+      "learning_rate": 0.00018966486464707305,
+      "loss": 0.7662015557289124,
+      "step": 2982
+    },
+    {
+      "epoch": 1.287378640776699,
+      "grad_norm": 0.45333993434906006,
+      "learning_rate": 0.00018964311225664113,
+      "loss": 0.752369225025177,
+      "step": 2984
+    },
+    {
+      "epoch": 1.2882416396979504,
+      "grad_norm": 0.4825304448604584,
+      "learning_rate": 0.0001896213382491768,
+      "loss": 0.7524476051330566,
+      "step": 2986
+    },
+    {
+      "epoch": 1.2891046386192018,
+      "grad_norm": 0.5303854942321777,
+      "learning_rate": 0.00018959954262993077,
+      "loss": 0.8564903736114502,
+      "step": 2988
+    },
+    {
+      "epoch": 1.2899676375404532,
+      "grad_norm": 0.43856459856033325,
+      "learning_rate": 0.00018957772540415896,
+      "loss": 0.7839077711105347,
+      "step": 2990
+    },
+    {
+      "epoch": 1.2908306364617044,
+      "grad_norm": 0.438041627407074,
+      "learning_rate": 0.00018955588657712248,
+      "loss": 0.7580918669700623,
+      "step": 2992
+    },
+    {
+      "epoch": 1.2916936353829558,
+      "grad_norm": 0.4497842490673065,
+      "learning_rate": 0.00018953402615408768,
+      "loss": 0.7014032602310181,
+      "step": 2994
+    },
+    {
+      "epoch": 1.2925566343042072,
+      "grad_norm": 0.5659869313240051,
+      "learning_rate": 0.0001895121441403261,
+      "loss": 0.8220269083976746,
+      "step": 2996
+    },
+    {
+      "epoch": 1.2934196332254584,
+      "grad_norm": 0.4850102961063385,
+      "learning_rate": 0.00018949024054111448,
+      "loss": 0.6880294680595398,
+      "step": 2998
+    },
+    {
+      "epoch": 1.2942826321467098,
+      "grad_norm": 0.4253626763820648,
+      "learning_rate": 0.00018946831536173476,
+      "loss": 0.7443753480911255,
+      "step": 3000
+    },
+    {
+      "epoch": 1.2942826321467098,
+      "eval_loss": 0.8127614259719849,
+      "eval_runtime": 650.4396,
+      "eval_samples_per_second": 3.167,
+      "eval_steps_per_second": 3.167,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 13908,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.001
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.798339635818705e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/sft_qwen_14B/checkpoints/checkpoint-3000/training_args.bin b/sft_qwen_14B/checkpoints/checkpoint-3000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b023888140f1fb107e8d5ebbfbcb9d9558b09d43
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-3000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4200830b23d19bc86049c280236c4a6b18c26d7061b5a57cc024888ec760920f
+size 5201
diff --git a/sft_qwen_14B/checkpoints/checkpoint-3500/README.md b/sft_qwen_14B/checkpoints/checkpoint-3500/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..779b6406e547b32301fef1d181301a873befe542
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-3500/README.md
@@ -0,0 +1,207 @@
+---
+base_model: runs/cpt_run_14b/merged_14b_cpt_lora
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:runs/cpt_run_14b/merged_14b_cpt_lora
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0
\ No newline at end of file
diff --git a/sft_qwen_14B/checkpoints/checkpoint-3500/adapter_config.json b/sft_qwen_14B/checkpoints/checkpoint-3500/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8ea271115c141fb10c6d899b06f46f21800e1ad6
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-3500/adapter_config.json
@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "runs/cpt_run_14b/merged_14b_cpt_lora",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/sft_qwen_14B/checkpoints/checkpoint-3500/adapter_model.safetensors b/sft_qwen_14B/checkpoints/checkpoint-3500/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d64816b60f7a99dfe4a43c7cc070d2b940509a89
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-3500/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e37c343dccf5c3a247692acad99797a99a1793a9cf387c8e79c5fda28b092489
+size 100715016
diff --git a/sft_qwen_14B/checkpoints/checkpoint-3500/optimizer.pt b/sft_qwen_14B/checkpoints/checkpoint-3500/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..28ecbe14c901ccbe53653695b9b0086bba4a3a52
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-3500/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab23160d343da52f73e074d13df36e94f9b1537165702ffffb28f4b3a03240be
+size 201650659
diff --git a/sft_qwen_14B/checkpoints/checkpoint-3500/rng_state.pth b/sft_qwen_14B/checkpoints/checkpoint-3500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b99104e9ec28c3761589e5e6fd5e3438549b894f
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-3500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c29f86833d3e2e183be7c52441966ecc0b80af7d1582cff4eabb3312f82d2029
+size 14645
diff --git a/sft_qwen_14B/checkpoints/checkpoint-3500/scheduler.pt b/sft_qwen_14B/checkpoints/checkpoint-3500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f5d96a340dc324efc973a60a68f54656141790bc
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-3500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b865d53bc9e6f8139871295f7bbed85bd8e25825528f2ce2b942f327371df18e
+size 1465
diff --git a/sft_qwen_14B/checkpoints/checkpoint-3500/trainer_state.json b/sft_qwen_14B/checkpoints/checkpoint-3500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..d729a20cb735ff5b3efd1fe131afdfc8f627993a
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-3500/trainer_state.json
@@ -0,0 +1,12573 @@
+{
+  "best_global_step": 3500,
+  "best_metric": 0.7970634698867798,
+  "best_model_checkpoint": "runs/instruct_run_14b_v1/checkpoints/checkpoint-3500",
+  "epoch": 1.510032362459547,
+  "eval_steps": 100,
+  "global_step": 3500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008629989212513484,
+      "grad_norm": 0.36567428708076477,
+      "learning_rate": 1.7969451931716084e-07,
+      "loss": 1.6794371604919434,
+      "step": 2
+    },
+    {
+      "epoch": 0.001725997842502697,
+      "grad_norm": 0.4024646580219269,
+      "learning_rate": 5.390835579514825e-07,
+      "loss": 1.6853073835372925,
+      "step": 4
+    },
+    {
+      "epoch": 0.0025889967637540453,
+      "grad_norm": 0.40199393033981323,
+      "learning_rate": 8.984725965858042e-07,
+      "loss": 1.7621158361434937,
+      "step": 6
+    },
+    {
+      "epoch": 0.003451995685005394,
+      "grad_norm": 0.35409677028656006,
+      "learning_rate": 1.257861635220126e-06,
+      "loss": 1.633257269859314,
+      "step": 8
+    },
+    {
+      "epoch": 0.004314994606256742,
+      "grad_norm": 0.39087551832199097,
+      "learning_rate": 1.6172506738544475e-06,
+      "loss": 1.7374768257141113,
+      "step": 10
+    },
+    {
+      "epoch": 0.005177993527508091,
+      "grad_norm": 0.3586857318878174,
+      "learning_rate": 1.9766397124887693e-06,
+      "loss": 1.6955714225769043,
+      "step": 12
+    },
+    {
+      "epoch": 0.006040992448759439,
+      "grad_norm": 0.32755669951438904,
+      "learning_rate": 2.3360287511230908e-06,
+      "loss": 1.720664381980896,
+      "step": 14
+    },
+    {
+      "epoch": 0.006903991370010788,
+      "grad_norm": 0.4054872691631317,
+      "learning_rate": 2.6954177897574127e-06,
+      "loss": 1.6957035064697266,
+      "step": 16
+    },
+    {
+      "epoch": 0.007766990291262136,
+      "grad_norm": 0.37593814730644226,
+      "learning_rate": 3.0548068283917343e-06,
+      "loss": 1.7286947965621948,
+      "step": 18
+    },
+    {
+      "epoch": 0.008629989212513484,
+      "grad_norm": 0.3344813287258148,
+      "learning_rate": 3.414195867026056e-06,
+      "loss": 1.727295994758606,
+      "step": 20
+    },
+    {
+      "epoch": 0.009492988133764833,
+      "grad_norm": 0.357474148273468,
+      "learning_rate": 3.7735849056603773e-06,
+      "loss": 1.6727914810180664,
+      "step": 22
+    },
+    {
+      "epoch": 0.010355987055016181,
+      "grad_norm": 0.39115726947784424,
+      "learning_rate": 4.132973944294699e-06,
+      "loss": 1.6518884897232056,
+      "step": 24
+    },
+    {
+      "epoch": 0.01121898597626753,
+      "grad_norm": 0.4711727201938629,
+      "learning_rate": 4.492362982929021e-06,
+      "loss": 1.7868088483810425,
+      "step": 26
+    },
+    {
+      "epoch": 0.012081984897518877,
+      "grad_norm": 0.34112176299095154,
+      "learning_rate": 4.851752021563342e-06,
+      "loss": 1.6127634048461914,
+      "step": 28
+    },
+    {
+      "epoch": 0.012944983818770227,
+      "grad_norm": 0.5071991682052612,
+      "learning_rate": 5.211141060197664e-06,
+      "loss": 1.7858378887176514,
+      "step": 30
+    },
+    {
+      "epoch": 0.013807982740021575,
+      "grad_norm": 0.42048847675323486,
+      "learning_rate": 5.570530098831986e-06,
+      "loss": 1.7123326063156128,
+      "step": 32
+    },
+    {
+      "epoch": 0.014670981661272923,
+      "grad_norm": 0.48883870244026184,
+      "learning_rate": 5.929919137466308e-06,
+      "loss": 1.737749695777893,
+      "step": 34
+    },
+    {
+      "epoch": 0.015533980582524271,
+      "grad_norm": 0.3311465084552765,
+      "learning_rate": 6.289308176100629e-06,
+      "loss": 1.5578981637954712,
+      "step": 36
+    },
+    {
+      "epoch": 0.01639697950377562,
+      "grad_norm": 0.5178973078727722,
+      "learning_rate": 6.64869721473495e-06,
+      "loss": 1.719806432723999,
+      "step": 38
+    },
+    {
+      "epoch": 0.017259978425026967,
+      "grad_norm": 0.47097742557525635,
+      "learning_rate": 7.008086253369272e-06,
+      "loss": 1.728212833404541,
+      "step": 40
+    },
+    {
+      "epoch": 0.018122977346278317,
+      "grad_norm": 0.5051584243774414,
+      "learning_rate": 7.367475292003594e-06,
+      "loss": 1.6542466878890991,
+      "step": 42
+    },
+    {
+      "epoch": 0.018985976267529667,
+      "grad_norm": 0.4645111560821533,
+      "learning_rate": 7.726864330637915e-06,
+      "loss": 1.7087690830230713,
+      "step": 44
+    },
+    {
+      "epoch": 0.019848975188781013,
+      "grad_norm": 0.5184999704360962,
+      "learning_rate": 8.086253369272237e-06,
+      "loss": 1.7018946409225464,
+      "step": 46
+    },
+    {
+      "epoch": 0.020711974110032363,
+      "grad_norm": 0.4543815851211548,
+      "learning_rate": 8.44564240790656e-06,
+      "loss": 1.6818269491195679,
+      "step": 48
+    },
+    {
+      "epoch": 0.021574973031283712,
+      "grad_norm": 0.44411996006965637,
+      "learning_rate": 8.80503144654088e-06,
+      "loss": 1.5772877931594849,
+      "step": 50
+    },
+    {
+      "epoch": 0.02243797195253506,
+      "grad_norm": 0.3409404158592224,
+      "learning_rate": 9.164420485175203e-06,
+      "loss": 1.498152732849121,
+      "step": 52
+    },
+    {
+      "epoch": 0.02330097087378641,
+      "grad_norm": 0.42104434967041016,
+      "learning_rate": 9.523809523809523e-06,
+      "loss": 1.6189048290252686,
+      "step": 54
+    },
+    {
+      "epoch": 0.024163969795037755,
+      "grad_norm": 0.3756246268749237,
+      "learning_rate": 9.883198562443846e-06,
+      "loss": 1.4596441984176636,
+      "step": 56
+    },
+    {
+      "epoch": 0.025026968716289105,
+      "grad_norm": 0.36214128136634827,
+      "learning_rate": 1.0242587601078168e-05,
+      "loss": 1.503880500793457,
+      "step": 58
+    },
+    {
+      "epoch": 0.025889967637540454,
+      "grad_norm": 0.40893009305000305,
+      "learning_rate": 1.060197663971249e-05,
+      "loss": 1.5912823677062988,
+      "step": 60
+    },
+    {
+      "epoch": 0.0267529665587918,
+      "grad_norm": 0.28710272908210754,
+      "learning_rate": 1.0961365678346811e-05,
+      "loss": 1.2956721782684326,
+      "step": 62
+    },
+    {
+      "epoch": 0.02761596548004315,
+      "grad_norm": 0.304573118686676,
+      "learning_rate": 1.1320754716981132e-05,
+      "loss": 1.4648056030273438,
+      "step": 64
+    },
+    {
+      "epoch": 0.0284789644012945,
+      "grad_norm": 0.36523914337158203,
+      "learning_rate": 1.1680143755615454e-05,
+      "loss": 1.6078968048095703,
+      "step": 66
+    },
+    {
+      "epoch": 0.029341963322545846,
+      "grad_norm": 0.37929031252861023,
+      "learning_rate": 1.2039532794249775e-05,
+      "loss": 1.5969421863555908,
+      "step": 68
+    },
+    {
+      "epoch": 0.030204962243797196,
+      "grad_norm": 0.3053947389125824,
+      "learning_rate": 1.2398921832884097e-05,
+      "loss": 1.4312325716018677,
+      "step": 70
+    },
+    {
+      "epoch": 0.031067961165048542,
+      "grad_norm": 0.3028779923915863,
+      "learning_rate": 1.275831087151842e-05,
+      "loss": 1.4101300239562988,
+      "step": 72
+    },
+    {
+      "epoch": 0.03193096008629989,
+      "grad_norm": 0.29649803042411804,
+      "learning_rate": 1.3117699910152742e-05,
+      "loss": 1.4553817510604858,
+      "step": 74
+    },
+    {
+      "epoch": 0.03279395900755124,
+      "grad_norm": 0.26032644510269165,
+      "learning_rate": 1.3477088948787062e-05,
+      "loss": 1.4623000621795654,
+      "step": 76
+    },
+    {
+      "epoch": 0.03365695792880259,
+      "grad_norm": 0.33558446168899536,
+      "learning_rate": 1.3836477987421385e-05,
+      "loss": 1.5181745290756226,
+      "step": 78
+    },
+    {
+      "epoch": 0.034519956850053934,
+      "grad_norm": 0.28307804465293884,
+      "learning_rate": 1.4195867026055706e-05,
+      "loss": 1.4397861957550049,
+      "step": 80
+    },
+    {
+      "epoch": 0.035382955771305284,
+      "grad_norm": 0.3451690673828125,
+      "learning_rate": 1.455525606469003e-05,
+      "loss": 1.463841199874878,
+      "step": 82
+    },
+    {
+      "epoch": 0.036245954692556634,
+      "grad_norm": 0.3248669505119324,
+      "learning_rate": 1.4914645103324348e-05,
+      "loss": 1.3554227352142334,
+      "step": 84
+    },
+    {
+      "epoch": 0.037108953613807984,
+      "grad_norm": 0.2855011224746704,
+      "learning_rate": 1.527403414195867e-05,
+      "loss": 1.2810425758361816,
+      "step": 86
+    },
+    {
+      "epoch": 0.03797195253505933,
+      "grad_norm": 0.33365535736083984,
+      "learning_rate": 1.5633423180592992e-05,
+      "loss": 1.428163766860962,
+      "step": 88
+    },
+    {
+      "epoch": 0.038834951456310676,
+      "grad_norm": 0.34099438786506653,
+      "learning_rate": 1.5992812219227316e-05,
+      "loss": 1.3487578630447388,
+      "step": 90
+    },
+    {
+      "epoch": 0.039697950377562026,
+      "grad_norm": 0.39247506856918335,
+      "learning_rate": 1.6352201257861635e-05,
+      "loss": 1.30057954788208,
+      "step": 92
+    },
+    {
+      "epoch": 0.040560949298813376,
+      "grad_norm": 0.32692041993141174,
+      "learning_rate": 1.671159029649596e-05,
+      "loss": 1.2923580408096313,
+      "step": 94
+    },
+    {
+      "epoch": 0.041423948220064725,
+      "grad_norm": 0.43452519178390503,
+      "learning_rate": 1.707097933513028e-05,
+      "loss": 1.5002273321151733,
+      "step": 96
+    },
+    {
+      "epoch": 0.042286947141316075,
+      "grad_norm": 0.3251534402370453,
+      "learning_rate": 1.7430368373764602e-05,
+      "loss": 1.330254077911377,
+      "step": 98
+    },
+    {
+      "epoch": 0.043149946062567425,
+      "grad_norm": 0.3198273479938507,
+      "learning_rate": 1.778975741239892e-05,
+      "loss": 1.3054943084716797,
+      "step": 100
+    },
+    {
+      "epoch": 0.043149946062567425,
+      "eval_loss": 1.366738200187683,
+      "eval_runtime": 651.8198,
+      "eval_samples_per_second": 3.16,
+      "eval_steps_per_second": 3.16,
+      "step": 100
+    },
+    {
+      "epoch": 0.04401294498381877,
+      "grad_norm": 0.37364065647125244,
+      "learning_rate": 1.8149146451033245e-05,
+      "loss": 1.314281940460205,
+      "step": 102
+    },
+    {
+      "epoch": 0.04487594390507012,
+      "grad_norm": 0.39384758472442627,
+      "learning_rate": 1.8508535489667568e-05,
+      "loss": 1.2737246751785278,
+      "step": 104
+    },
+    {
+      "epoch": 0.04573894282632147,
+      "grad_norm": 0.3521905541419983,
+      "learning_rate": 1.8867924528301888e-05,
+      "loss": 1.3113226890563965,
+      "step": 106
+    },
+    {
+      "epoch": 0.04660194174757282,
+      "grad_norm": 0.33531463146209717,
+      "learning_rate": 1.9227313566936208e-05,
+      "loss": 1.3253653049468994,
+      "step": 108
+    },
+    {
+      "epoch": 0.04746494066882417,
+      "grad_norm": 0.35596340894699097,
+      "learning_rate": 1.958670260557053e-05,
+      "loss": 1.3236849308013916,
+      "step": 110
+    },
+    {
+      "epoch": 0.04832793959007551,
+      "grad_norm": 0.36028242111206055,
+      "learning_rate": 1.9946091644204854e-05,
+      "loss": 1.183128833770752,
+      "step": 112
+    },
+    {
+      "epoch": 0.04919093851132686,
+      "grad_norm": 0.42109814286231995,
+      "learning_rate": 2.0305480682839174e-05,
+      "loss": 1.2741888761520386,
+      "step": 114
+    },
+    {
+      "epoch": 0.05005393743257821,
+      "grad_norm": 0.39675939083099365,
+      "learning_rate": 2.0664869721473494e-05,
+      "loss": 1.3050109148025513,
+      "step": 116
+    },
+    {
+      "epoch": 0.05091693635382956,
+      "grad_norm": 0.4414141774177551,
+      "learning_rate": 2.1024258760107817e-05,
+      "loss": 1.2472094297409058,
+      "step": 118
+    },
+    {
+      "epoch": 0.05177993527508091,
+      "grad_norm": 0.42872729897499084,
+      "learning_rate": 2.138364779874214e-05,
+      "loss": 1.3338921070098877,
+      "step": 120
+    },
+    {
+      "epoch": 0.05264293419633225,
+      "grad_norm": 0.38336244225502014,
+      "learning_rate": 2.174303683737646e-05,
+      "loss": 1.322908878326416,
+      "step": 122
+    },
+    {
+      "epoch": 0.0535059331175836,
+      "grad_norm": 0.41046878695487976,
+      "learning_rate": 2.2102425876010783e-05,
+      "loss": 1.2169240713119507,
+      "step": 124
+    },
+    {
+      "epoch": 0.05436893203883495,
+      "grad_norm": 0.39460113644599915,
+      "learning_rate": 2.2461814914645103e-05,
+      "loss": 1.2085309028625488,
+      "step": 126
+    },
+    {
+      "epoch": 0.0552319309600863,
+      "grad_norm": 0.42829909920692444,
+      "learning_rate": 2.2821203953279426e-05,
+      "loss": 1.2969133853912354,
+      "step": 128
+    },
+    {
+      "epoch": 0.05609492988133765,
+      "grad_norm": 0.3940851390361786,
+      "learning_rate": 2.3180592991913746e-05,
+      "loss": 1.1892330646514893,
+      "step": 130
+    },
+    {
+      "epoch": 0.056957928802589,
+      "grad_norm": 0.45011839270591736,
+      "learning_rate": 2.353998203054807e-05,
+      "loss": 1.2082979679107666,
+      "step": 132
+    },
+    {
+      "epoch": 0.05782092772384034,
+      "grad_norm": 0.46059420704841614,
+      "learning_rate": 2.3899371069182393e-05,
+      "loss": 1.2388817071914673,
+      "step": 134
+    },
+    {
+      "epoch": 0.05868392664509169,
+      "grad_norm": 0.41085872054100037,
+      "learning_rate": 2.4258760107816713e-05,
+      "loss": 1.193917155265808,
+      "step": 136
+    },
+    {
+      "epoch": 0.05954692556634304,
+      "grad_norm": 0.4024205207824707,
+      "learning_rate": 2.4618149146451032e-05,
+      "loss": 1.1514034271240234,
+      "step": 138
+    },
+    {
+      "epoch": 0.06040992448759439,
+      "grad_norm": 0.3893793523311615,
+      "learning_rate": 2.4977538185085356e-05,
+      "loss": 1.1626157760620117,
+      "step": 140
+    },
+    {
+      "epoch": 0.06127292340884574,
+      "grad_norm": 0.4456317126750946,
+      "learning_rate": 2.5336927223719675e-05,
+      "loss": 1.1627076864242554,
+      "step": 142
+    },
+    {
+      "epoch": 0.062135922330097085,
+      "grad_norm": 0.5050215125083923,
+      "learning_rate": 2.5696316262354e-05,
+      "loss": 1.3038755655288696,
+      "step": 144
+    },
+    {
+      "epoch": 0.06299892125134844,
+      "grad_norm": 0.4071207642555237,
+      "learning_rate": 2.605570530098832e-05,
+      "loss": 1.1708844900131226,
+      "step": 146
+    },
+    {
+      "epoch": 0.06386192017259978,
+      "grad_norm": 0.4363228678703308,
+      "learning_rate": 2.641509433962264e-05,
+      "loss": 1.2149070501327515,
+      "step": 148
+    },
+    {
+      "epoch": 0.06472491909385113,
+      "grad_norm": 0.4436556398868561,
+      "learning_rate": 2.6774483378256965e-05,
+      "loss": 1.1942368745803833,
+      "step": 150
+    },
+    {
+      "epoch": 0.06558791801510248,
+      "grad_norm": 0.4068629741668701,
+      "learning_rate": 2.7133872416891288e-05,
+      "loss": 1.1799161434173584,
+      "step": 152
+    },
+    {
+      "epoch": 0.06645091693635383,
+      "grad_norm": 0.5291106700897217,
+      "learning_rate": 2.7493261455525608e-05,
+      "loss": 1.1832845211029053,
+      "step": 154
+    },
+    {
+      "epoch": 0.06731391585760518,
+      "grad_norm": 0.4410109221935272,
+      "learning_rate": 2.785265049415993e-05,
+      "loss": 1.1696993112564087,
+      "step": 156
+    },
+    {
+      "epoch": 0.06817691477885653,
+      "grad_norm": 0.4858371913433075,
+      "learning_rate": 2.8212039532794248e-05,
+      "loss": 1.2036973237991333,
+      "step": 158
+    },
+    {
+      "epoch": 0.06903991370010787,
+      "grad_norm": 0.45373693108558655,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 1.1145079135894775,
+      "step": 160
+    },
+    {
+      "epoch": 0.06990291262135923,
+      "grad_norm": 0.4881038963794708,
+      "learning_rate": 2.8930817610062894e-05,
+      "loss": 1.173502802848816,
+      "step": 162
+    },
+    {
+      "epoch": 0.07076591154261057,
+      "grad_norm": 0.576934814453125,
+      "learning_rate": 2.9290206648697217e-05,
+      "loss": 1.250414490699768,
+      "step": 164
+    },
+    {
+      "epoch": 0.07162891046386193,
+      "grad_norm": 0.4900001287460327,
+      "learning_rate": 2.9649595687331537e-05,
+      "loss": 1.0721495151519775,
+      "step": 166
+    },
+    {
+      "epoch": 0.07249190938511327,
+      "grad_norm": 0.4440019726753235,
+      "learning_rate": 3.000898472596586e-05,
+      "loss": 1.0689374208450317,
+      "step": 168
+    },
+    {
+      "epoch": 0.07335490830636461,
+      "grad_norm": 0.4267268180847168,
+      "learning_rate": 3.0368373764600184e-05,
+      "loss": 1.2095128297805786,
+      "step": 170
+    },
+    {
+      "epoch": 0.07421790722761597,
+      "grad_norm": 0.6062787771224976,
+      "learning_rate": 3.0727762803234503e-05,
+      "loss": 1.077776551246643,
+      "step": 172
+    },
+    {
+      "epoch": 0.07508090614886731,
+      "grad_norm": 0.49510180950164795,
+      "learning_rate": 3.108715184186882e-05,
+      "loss": 1.144006371498108,
+      "step": 174
+    },
+    {
+      "epoch": 0.07594390507011867,
+      "grad_norm": 0.4670701026916504,
+      "learning_rate": 3.144654088050314e-05,
+      "loss": 1.1663392782211304,
+      "step": 176
+    },
+    {
+      "epoch": 0.07680690399137001,
+      "grad_norm": 0.5615383386611938,
+      "learning_rate": 3.1805929919137466e-05,
+      "loss": 1.1665973663330078,
+      "step": 178
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "grad_norm": 0.47305551171302795,
+      "learning_rate": 3.216531895777179e-05,
+      "loss": 1.1337063312530518,
+      "step": 180
+    },
+    {
+      "epoch": 0.07853290183387271,
+      "grad_norm": 0.5127068758010864,
+      "learning_rate": 3.252470799640611e-05,
+      "loss": 1.072874903678894,
+      "step": 182
+    },
+    {
+      "epoch": 0.07939590075512405,
+      "grad_norm": 0.632448136806488,
+      "learning_rate": 3.2884097035040436e-05,
+      "loss": 1.1577240228652954,
+      "step": 184
+    },
+    {
+      "epoch": 0.08025889967637541,
+      "grad_norm": 0.4041025638580322,
+      "learning_rate": 3.324348607367476e-05,
+      "loss": 1.1186822652816772,
+      "step": 186
+    },
+    {
+      "epoch": 0.08112189859762675,
+      "grad_norm": 0.5239102244377136,
+      "learning_rate": 3.3602875112309076e-05,
+      "loss": 1.1468429565429688,
+      "step": 188
+    },
+    {
+      "epoch": 0.08198489751887811,
+      "grad_norm": 0.4486575424671173,
+      "learning_rate": 3.39622641509434e-05,
+      "loss": 1.0017019510269165,
+      "step": 190
+    },
+    {
+      "epoch": 0.08284789644012945,
+      "grad_norm": 0.4994317293167114,
+      "learning_rate": 3.4321653189577715e-05,
+      "loss": 1.1901532411575317,
+      "step": 192
+    },
+    {
+      "epoch": 0.0837108953613808,
+      "grad_norm": 0.5023699998855591,
+      "learning_rate": 3.468104222821204e-05,
+      "loss": 1.1398564577102661,
+      "step": 194
+    },
+    {
+      "epoch": 0.08457389428263215,
+      "grad_norm": 0.5077701807022095,
+      "learning_rate": 3.504043126684636e-05,
+      "loss": 1.1390413045883179,
+      "step": 196
+    },
+    {
+      "epoch": 0.0854368932038835,
+      "grad_norm": 0.5527892112731934,
+      "learning_rate": 3.5399820305480685e-05,
+      "loss": 1.1411432027816772,
+      "step": 198
+    },
+    {
+      "epoch": 0.08629989212513485,
+      "grad_norm": 0.5572488903999329,
+      "learning_rate": 3.575920934411501e-05,
+      "loss": 1.071260690689087,
+      "step": 200
+    },
+    {
+      "epoch": 0.08629989212513485,
+      "eval_loss": 1.1519012451171875,
+      "eval_runtime": 654.6055,
+      "eval_samples_per_second": 3.147,
+      "eval_steps_per_second": 3.147,
+      "step": 200
+    },
+    {
+      "epoch": 0.08716289104638619,
+      "grad_norm": 0.5134095549583435,
+      "learning_rate": 3.611859838274933e-05,
+      "loss": 1.138135552406311,
+      "step": 202
+    },
+    {
+      "epoch": 0.08802588996763754,
+      "grad_norm": 0.5166040658950806,
+      "learning_rate": 3.647798742138365e-05,
+      "loss": 1.111999273300171,
+      "step": 204
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.5336993336677551,
+      "learning_rate": 3.683737646001797e-05,
+      "loss": 1.1031352281570435,
+      "step": 206
+    },
+    {
+      "epoch": 0.08975188781014024,
+      "grad_norm": 0.8289600014686584,
+      "learning_rate": 3.7196765498652294e-05,
+      "loss": 1.0388667583465576,
+      "step": 208
+    },
+    {
+      "epoch": 0.09061488673139159,
+      "grad_norm": 0.47992637753486633,
+      "learning_rate": 3.755615453728661e-05,
+      "loss": 1.0950241088867188,
+      "step": 210
+    },
+    {
+      "epoch": 0.09147788565264293,
+      "grad_norm": 0.5629691481590271,
+      "learning_rate": 3.7915543575920934e-05,
+      "loss": 1.0361733436584473,
+      "step": 212
+    },
+    {
+      "epoch": 0.09234088457389428,
+      "grad_norm": 0.5515111684799194,
+      "learning_rate": 3.827493261455526e-05,
+      "loss": 1.0922447443008423,
+      "step": 214
+    },
+    {
+      "epoch": 0.09320388349514563,
+      "grad_norm": 0.5078643560409546,
+      "learning_rate": 3.863432165318958e-05,
+      "loss": 1.0866856575012207,
+      "step": 216
+    },
+    {
+      "epoch": 0.09406688241639698,
+      "grad_norm": 0.6046127676963806,
+      "learning_rate": 3.8993710691823904e-05,
+      "loss": 1.1231595277786255,
+      "step": 218
+    },
+    {
+      "epoch": 0.09492988133764833,
+      "grad_norm": 0.6255762577056885,
+      "learning_rate": 3.935309973045822e-05,
+      "loss": 1.099171757698059,
+      "step": 220
+    },
+    {
+      "epoch": 0.09579288025889968,
+      "grad_norm": 0.6036638021469116,
+      "learning_rate": 3.971248876909254e-05,
+      "loss": 1.0557761192321777,
+      "step": 222
+    },
+    {
+      "epoch": 0.09665587918015102,
+      "grad_norm": 0.5520529747009277,
+      "learning_rate": 4.0071877807726867e-05,
+      "loss": 1.0467877388000488,
+      "step": 224
+    },
+    {
+      "epoch": 0.09751887810140238,
+      "grad_norm": 0.5958684682846069,
+      "learning_rate": 4.043126684636119e-05,
+      "loss": 1.17941153049469,
+      "step": 226
+    },
+    {
+      "epoch": 0.09838187702265372,
+      "grad_norm": 0.5283281803131104,
+      "learning_rate": 4.079065588499551e-05,
+      "loss": 1.104217767715454,
+      "step": 228
+    },
+    {
+      "epoch": 0.09924487594390508,
+      "grad_norm": 0.5608792901039124,
+      "learning_rate": 4.115004492362983e-05,
+      "loss": 1.0900640487670898,
+      "step": 230
+    },
+    {
+      "epoch": 0.10010787486515642,
+      "grad_norm": 0.555964469909668,
+      "learning_rate": 4.150943396226415e-05,
+      "loss": 0.9887422323226929,
+      "step": 232
+    },
+    {
+      "epoch": 0.10097087378640776,
+      "grad_norm": 0.5875785946846008,
+      "learning_rate": 4.1868823000898476e-05,
+      "loss": 1.1298567056655884,
+      "step": 234
+    },
+    {
+      "epoch": 0.10183387270765912,
+      "grad_norm": 0.4544795751571655,
+      "learning_rate": 4.222821203953279e-05,
+      "loss": 1.0957067012786865,
+      "step": 236
+    },
+    {
+      "epoch": 0.10269687162891046,
+      "grad_norm": 0.564145565032959,
+      "learning_rate": 4.2587601078167116e-05,
+      "loss": 1.0328738689422607,
+      "step": 238
+    },
+    {
+      "epoch": 0.10355987055016182,
+      "grad_norm": 0.6285979747772217,
+      "learning_rate": 4.294699011680144e-05,
+      "loss": 1.1085515022277832,
+      "step": 240
+    },
+    {
+      "epoch": 0.10442286947141316,
+      "grad_norm": 0.6442288756370544,
+      "learning_rate": 4.330637915543576e-05,
+      "loss": 1.1291271448135376,
+      "step": 242
+    },
+    {
+      "epoch": 0.1052858683926645,
+      "grad_norm": 0.6137154698371887,
+      "learning_rate": 4.3665768194070085e-05,
+      "loss": 1.1759567260742188,
+      "step": 244
+    },
+    {
+      "epoch": 0.10614886731391586,
+      "grad_norm": 0.5906805992126465,
+      "learning_rate": 4.402515723270441e-05,
+      "loss": 1.148414969444275,
+      "step": 246
+    },
+    {
+      "epoch": 0.1070118662351672,
+      "grad_norm": 0.5382888913154602,
+      "learning_rate": 4.438454627133873e-05,
+      "loss": 1.0749616622924805,
+      "step": 248
+    },
+    {
+      "epoch": 0.10787486515641856,
+      "grad_norm": 0.6185492873191833,
+      "learning_rate": 4.474393530997305e-05,
+      "loss": 1.2235801219940186,
+      "step": 250
+    },
+    {
+      "epoch": 0.1087378640776699,
+      "grad_norm": 0.5981597900390625,
+      "learning_rate": 4.5103324348607365e-05,
+      "loss": 1.1390639543533325,
+      "step": 252
+    },
+    {
+      "epoch": 0.10960086299892124,
+      "grad_norm": 0.5664694905281067,
+      "learning_rate": 4.546271338724169e-05,
+      "loss": 1.171774983406067,
+      "step": 254
+    },
+    {
+      "epoch": 0.1104638619201726,
+      "grad_norm": 0.7071851491928101,
+      "learning_rate": 4.582210242587601e-05,
+      "loss": 1.1704237461090088,
+      "step": 256
+    },
+    {
+      "epoch": 0.11132686084142394,
+      "grad_norm": 0.5815614461898804,
+      "learning_rate": 4.6181491464510334e-05,
+      "loss": 1.0619677305221558,
+      "step": 258
+    },
+    {
+      "epoch": 0.1121898597626753,
+      "grad_norm": 0.6481915712356567,
+      "learning_rate": 4.654088050314466e-05,
+      "loss": 1.0824390649795532,
+      "step": 260
+    },
+    {
+      "epoch": 0.11305285868392664,
+      "grad_norm": 0.5988591313362122,
+      "learning_rate": 4.690026954177898e-05,
+      "loss": 1.087929606437683,
+      "step": 262
+    },
+    {
+      "epoch": 0.113915857605178,
+      "grad_norm": 0.6545296311378479,
+      "learning_rate": 4.7259658580413304e-05,
+      "loss": 1.0936195850372314,
+      "step": 264
+    },
+    {
+      "epoch": 0.11477885652642934,
+      "grad_norm": 0.5826204419136047,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 1.0433681011199951,
+      "step": 266
+    },
+    {
+      "epoch": 0.11564185544768069,
+      "grad_norm": 0.5907514095306396,
+      "learning_rate": 4.7978436657681944e-05,
+      "loss": 1.0719536542892456,
+      "step": 268
+    },
+    {
+      "epoch": 0.11650485436893204,
+      "grad_norm": 0.524394154548645,
+      "learning_rate": 4.833782569631627e-05,
+      "loss": 1.0231504440307617,
+      "step": 270
+    },
+    {
+      "epoch": 0.11736785329018339,
+      "grad_norm": 0.5472846031188965,
+      "learning_rate": 4.869721473495058e-05,
+      "loss": 0.9905915260314941,
+      "step": 272
+    },
+    {
+      "epoch": 0.11823085221143474,
+      "grad_norm": 0.727922260761261,
+      "learning_rate": 4.9056603773584906e-05,
+      "loss": 1.213677167892456,
+      "step": 274
+    },
+    {
+      "epoch": 0.11909385113268608,
+      "grad_norm": 0.6009684801101685,
+      "learning_rate": 4.941599281221923e-05,
+      "loss": 1.0052144527435303,
+      "step": 276
+    },
+    {
+      "epoch": 0.11995685005393743,
+      "grad_norm": 0.6564669013023376,
+      "learning_rate": 4.977538185085355e-05,
+      "loss": 1.108136773109436,
+      "step": 278
+    },
+    {
+      "epoch": 0.12081984897518878,
+      "grad_norm": 0.650074303150177,
+      "learning_rate": 5.013477088948787e-05,
+      "loss": 0.9700815677642822,
+      "step": 280
+    },
+    {
+      "epoch": 0.12168284789644013,
+      "grad_norm": 0.5772947072982788,
+      "learning_rate": 5.04941599281222e-05,
+      "loss": 1.038031816482544,
+      "step": 282
+    },
+    {
+      "epoch": 0.12254584681769148,
+      "grad_norm": 0.7293002009391785,
+      "learning_rate": 5.0853548966756516e-05,
+      "loss": 1.1063730716705322,
+      "step": 284
+    },
+    {
+      "epoch": 0.12340884573894283,
+      "grad_norm": 0.7937333583831787,
+      "learning_rate": 5.1212938005390846e-05,
+      "loss": 1.128495693206787,
+      "step": 286
+    },
+    {
+      "epoch": 0.12427184466019417,
+      "grad_norm": 0.48499324917793274,
+      "learning_rate": 5.157232704402516e-05,
+      "loss": 0.9438712000846863,
+      "step": 288
+    },
+    {
+      "epoch": 0.12513484358144553,
+      "grad_norm": 0.6010656952857971,
+      "learning_rate": 5.193171608265948e-05,
+      "loss": 1.0872881412506104,
+      "step": 290
+    },
+    {
+      "epoch": 0.12599784250269688,
+      "grad_norm": 0.6240811944007874,
+      "learning_rate": 5.22911051212938e-05,
+      "loss": 1.110992193222046,
+      "step": 292
+    },
+    {
+      "epoch": 0.1268608414239482,
+      "grad_norm": 0.7172768712043762,
+      "learning_rate": 5.265049415992812e-05,
+      "loss": 1.1109752655029297,
+      "step": 294
+    },
+    {
+      "epoch": 0.12772384034519957,
+      "grad_norm": 0.6442400217056274,
+      "learning_rate": 5.300988319856245e-05,
+      "loss": 1.05553138256073,
+      "step": 296
+    },
+    {
+      "epoch": 0.12858683926645093,
+      "grad_norm": 0.7074702382087708,
+      "learning_rate": 5.3369272237196765e-05,
+      "loss": 1.0717648267745972,
+      "step": 298
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "grad_norm": 0.5277591347694397,
+      "learning_rate": 5.3728661275831095e-05,
+      "loss": 0.9777541756629944,
+      "step": 300
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "eval_loss": 1.0977506637573242,
+      "eval_runtime": 662.1728,
+      "eval_samples_per_second": 3.111,
+      "eval_steps_per_second": 3.111,
+      "step": 300
+    },
+    {
+      "epoch": 0.1303128371089536,
+      "grad_norm": 0.7252246737480164,
+      "learning_rate": 5.408805031446541e-05,
+      "loss": 1.075905203819275,
+      "step": 302
+    },
+    {
+      "epoch": 0.13117583603020497,
+      "grad_norm": 0.7003294229507446,
+      "learning_rate": 5.444743935309974e-05,
+      "loss": 1.1117515563964844,
+      "step": 304
+    },
+    {
+      "epoch": 0.13203883495145632,
+      "grad_norm": 0.5878211259841919,
+      "learning_rate": 5.480682839173406e-05,
+      "loss": 1.0289191007614136,
+      "step": 306
+    },
+    {
+      "epoch": 0.13290183387270765,
+      "grad_norm": 0.7133644223213196,
+      "learning_rate": 5.5166217430368374e-05,
+      "loss": 1.0199183225631714,
+      "step": 308
+    },
+    {
+      "epoch": 0.133764832793959,
+      "grad_norm": 0.6098423600196838,
+      "learning_rate": 5.55256064690027e-05,
+      "loss": 1.0132375955581665,
+      "step": 310
+    },
+    {
+      "epoch": 0.13462783171521037,
+      "grad_norm": 0.6386916041374207,
+      "learning_rate": 5.5884995507637014e-05,
+      "loss": 1.1595754623413086,
+      "step": 312
+    },
+    {
+      "epoch": 0.1354908306364617,
+      "grad_norm": 0.6563469767570496,
+      "learning_rate": 5.6244384546271344e-05,
+      "loss": 1.0921307802200317,
+      "step": 314
+    },
+    {
+      "epoch": 0.13635382955771305,
+      "grad_norm": 0.6388015747070312,
+      "learning_rate": 5.660377358490566e-05,
+      "loss": 1.0200815200805664,
+      "step": 316
+    },
+    {
+      "epoch": 0.1372168284789644,
+      "grad_norm": 0.6026274561882019,
+      "learning_rate": 5.696316262353999e-05,
+      "loss": 0.9339485764503479,
+      "step": 318
+    },
+    {
+      "epoch": 0.13807982740021574,
+      "grad_norm": 0.619800865650177,
+      "learning_rate": 5.732255166217431e-05,
+      "loss": 1.0268478393554688,
+      "step": 320
+    },
+    {
+      "epoch": 0.1389428263214671,
+      "grad_norm": 0.5924715399742126,
+      "learning_rate": 5.768194070080862e-05,
+      "loss": 1.1394236087799072,
+      "step": 322
+    },
+    {
+      "epoch": 0.13980582524271845,
+      "grad_norm": 0.6829012036323547,
+      "learning_rate": 5.804132973944295e-05,
+      "loss": 1.002437949180603,
+      "step": 324
+    },
+    {
+      "epoch": 0.1406688241639698,
+      "grad_norm": 0.7012544274330139,
+      "learning_rate": 5.840071877807727e-05,
+      "loss": 1.132503628730774,
+      "step": 326
+    },
+    {
+      "epoch": 0.14153182308522114,
+      "grad_norm": 0.7921599745750427,
+      "learning_rate": 5.876010781671159e-05,
+      "loss": 1.1859129667282104,
+      "step": 328
+    },
+    {
+      "epoch": 0.1423948220064725,
+      "grad_norm": 0.6373353004455566,
+      "learning_rate": 5.9119496855345916e-05,
+      "loss": 1.0896776914596558,
+      "step": 330
+    },
+    {
+      "epoch": 0.14325782092772385,
+      "grad_norm": 0.6174030900001526,
+      "learning_rate": 5.947888589398024e-05,
+      "loss": 1.0691723823547363,
+      "step": 332
+    },
+    {
+      "epoch": 0.14412081984897518,
+      "grad_norm": 0.5110617280006409,
+      "learning_rate": 5.9838274932614556e-05,
+      "loss": 1.0144777297973633,
+      "step": 334
+    },
+    {
+      "epoch": 0.14498381877022654,
+      "grad_norm": 0.5580511093139648,
+      "learning_rate": 6.019766397124887e-05,
+      "loss": 0.9955101609230042,
+      "step": 336
+    },
+    {
+      "epoch": 0.1458468176914779,
+      "grad_norm": 0.6427345275878906,
+      "learning_rate": 6.05570530098832e-05,
+      "loss": 0.9863013625144958,
+      "step": 338
+    },
+    {
+      "epoch": 0.14670981661272922,
+      "grad_norm": 0.7464537024497986,
+      "learning_rate": 6.091644204851752e-05,
+      "loss": 1.0682255029678345,
+      "step": 340
+    },
+    {
+      "epoch": 0.14757281553398058,
+      "grad_norm": 0.599926769733429,
+      "learning_rate": 6.127583108715184e-05,
+      "loss": 1.034083366394043,
+      "step": 342
+    },
+    {
+      "epoch": 0.14843581445523193,
+      "grad_norm": 0.6320257186889648,
+      "learning_rate": 6.163522012578616e-05,
+      "loss": 1.0776089429855347,
+      "step": 344
+    },
+    {
+      "epoch": 0.1492988133764833,
+      "grad_norm": 0.6565091013908386,
+      "learning_rate": 6.199460916442049e-05,
+      "loss": 1.0493087768554688,
+      "step": 346
+    },
+    {
+      "epoch": 0.15016181229773462,
+      "grad_norm": 0.6512171626091003,
+      "learning_rate": 6.23539982030548e-05,
+      "loss": 1.0469218492507935,
+      "step": 348
+    },
+    {
+      "epoch": 0.15102481121898598,
+      "grad_norm": 0.8487282991409302,
+      "learning_rate": 6.271338724168913e-05,
+      "loss": 1.0985081195831299,
+      "step": 350
+    },
+    {
+      "epoch": 0.15188781014023733,
+      "grad_norm": 0.6718961596488953,
+      "learning_rate": 6.307277628032345e-05,
+      "loss": 1.0714176893234253,
+      "step": 352
+    },
+    {
+      "epoch": 0.15275080906148866,
+      "grad_norm": 0.8175088167190552,
+      "learning_rate": 6.343216531895777e-05,
+      "loss": 1.0599322319030762,
+      "step": 354
+    },
+    {
+      "epoch": 0.15361380798274002,
+      "grad_norm": 0.6359215378761292,
+      "learning_rate": 6.37915543575921e-05,
+      "loss": 0.9268131256103516,
+      "step": 356
+    },
+    {
+      "epoch": 0.15447680690399138,
+      "grad_norm": 0.6423866748809814,
+      "learning_rate": 6.415094339622641e-05,
+      "loss": 0.9838354587554932,
+      "step": 358
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "grad_norm": 0.6496716737747192,
+      "learning_rate": 6.451033243486074e-05,
+      "loss": 1.048566460609436,
+      "step": 360
+    },
+    {
+      "epoch": 0.15620280474649406,
+      "grad_norm": 0.6536920666694641,
+      "learning_rate": 6.486972147349506e-05,
+      "loss": 1.0910537242889404,
+      "step": 362
+    },
+    {
+      "epoch": 0.15706580366774542,
+      "grad_norm": 0.5832068920135498,
+      "learning_rate": 6.522911051212939e-05,
+      "loss": 0.9971448183059692,
+      "step": 364
+    },
+    {
+      "epoch": 0.15792880258899678,
+      "grad_norm": 0.6647719144821167,
+      "learning_rate": 6.558849955076371e-05,
+      "loss": 1.0496708154678345,
+      "step": 366
+    },
+    {
+      "epoch": 0.1587918015102481,
+      "grad_norm": 0.623252809047699,
+      "learning_rate": 6.594788858939802e-05,
+      "loss": 0.955894410610199,
+      "step": 368
+    },
+    {
+      "epoch": 0.15965480043149946,
+      "grad_norm": 0.6311860084533691,
+      "learning_rate": 6.630727762803235e-05,
+      "loss": 1.1304032802581787,
+      "step": 370
+    },
+    {
+      "epoch": 0.16051779935275082,
+      "grad_norm": 0.5306481122970581,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.8746405243873596,
+      "step": 372
+    },
+    {
+      "epoch": 0.16138079827400215,
+      "grad_norm": 0.6249631643295288,
+      "learning_rate": 6.7026055705301e-05,
+      "loss": 0.9104986786842346,
+      "step": 374
+    },
+    {
+      "epoch": 0.1622437971952535,
+      "grad_norm": 0.6243219971656799,
+      "learning_rate": 6.738544474393532e-05,
+      "loss": 1.043666124343872,
+      "step": 376
+    },
+    {
+      "epoch": 0.16310679611650486,
+      "grad_norm": 0.6833282113075256,
+      "learning_rate": 6.774483378256963e-05,
+      "loss": 1.0504906177520752,
+      "step": 378
+    },
+    {
+      "epoch": 0.16396979503775622,
+      "grad_norm": 0.7124452590942383,
+      "learning_rate": 6.810422282120395e-05,
+      "loss": 1.0608166456222534,
+      "step": 380
+    },
+    {
+      "epoch": 0.16483279395900755,
+      "grad_norm": 0.7520908117294312,
+      "learning_rate": 6.846361185983828e-05,
+      "loss": 1.1653732061386108,
+      "step": 382
+    },
+    {
+      "epoch": 0.1656957928802589,
+      "grad_norm": 0.7121814489364624,
+      "learning_rate": 6.88230008984726e-05,
+      "loss": 1.0626367330551147,
+      "step": 384
+    },
+    {
+      "epoch": 0.16655879180151026,
+      "grad_norm": 0.6825008988380432,
+      "learning_rate": 6.918238993710691e-05,
+      "loss": 1.012121319770813,
+      "step": 386
+    },
+    {
+      "epoch": 0.1674217907227616,
+      "grad_norm": 0.4922940135002136,
+      "learning_rate": 6.954177897574124e-05,
+      "loss": 1.0576211214065552,
+      "step": 388
+    },
+    {
+      "epoch": 0.16828478964401294,
+      "grad_norm": 0.6122089624404907,
+      "learning_rate": 6.990116801437556e-05,
+      "loss": 1.03916597366333,
+      "step": 390
+    },
+    {
+      "epoch": 0.1691477885652643,
+      "grad_norm": 0.6348981261253357,
+      "learning_rate": 7.026055705300989e-05,
+      "loss": 1.17647123336792,
+      "step": 392
+    },
+    {
+      "epoch": 0.17001078748651563,
+      "grad_norm": 0.6205878257751465,
+      "learning_rate": 7.06199460916442e-05,
+      "loss": 0.9095983505249023,
+      "step": 394
+    },
+    {
+      "epoch": 0.170873786407767,
+      "grad_norm": 0.61506187915802,
+      "learning_rate": 7.097933513027853e-05,
+      "loss": 1.082506775856018,
+      "step": 396
+    },
+    {
+      "epoch": 0.17173678532901834,
+      "grad_norm": 0.6481751799583435,
+      "learning_rate": 7.133872416891285e-05,
+      "loss": 1.0716280937194824,
+      "step": 398
+    },
+    {
+      "epoch": 0.1725997842502697,
+      "grad_norm": 0.4871014952659607,
+      "learning_rate": 7.169811320754717e-05,
+      "loss": 0.9616814851760864,
+      "step": 400
+    },
+    {
+      "epoch": 0.1725997842502697,
+      "eval_loss": 1.0649415254592896,
+      "eval_runtime": 668.6025,
+      "eval_samples_per_second": 3.081,
+      "eval_steps_per_second": 3.081,
+      "step": 400
+    },
+    {
+      "epoch": 0.17346278317152103,
+      "grad_norm": 0.5680040121078491,
+      "learning_rate": 7.20575022461815e-05,
+      "loss": 1.0475050210952759,
+      "step": 402
+    },
+    {
+      "epoch": 0.17432578209277239,
+      "grad_norm": 0.6417813897132874,
+      "learning_rate": 7.241689128481581e-05,
+      "loss": 0.9851161241531372,
+      "step": 404
+    },
+    {
+      "epoch": 0.17518878101402374,
+      "grad_norm": 0.6600468158721924,
+      "learning_rate": 7.277628032345014e-05,
+      "loss": 1.013339638710022,
+      "step": 406
+    },
+    {
+      "epoch": 0.17605177993527507,
+      "grad_norm": 0.6733932495117188,
+      "learning_rate": 7.313566936208446e-05,
+      "loss": 0.9346804022789001,
+      "step": 408
+    },
+    {
+      "epoch": 0.17691477885652643,
+      "grad_norm": 0.6812151074409485,
+      "learning_rate": 7.349505840071879e-05,
+      "loss": 0.9890368580818176,
+      "step": 410
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.6380394697189331,
+      "learning_rate": 7.385444743935311e-05,
+      "loss": 0.8787848949432373,
+      "step": 412
+    },
+    {
+      "epoch": 0.1786407766990291,
+      "grad_norm": 0.6004905700683594,
+      "learning_rate": 7.421383647798742e-05,
+      "loss": 1.0235728025436401,
+      "step": 414
+    },
+    {
+      "epoch": 0.17950377562028047,
+      "grad_norm": 0.6569193005561829,
+      "learning_rate": 7.457322551662175e-05,
+      "loss": 0.9972385168075562,
+      "step": 416
+    },
+    {
+      "epoch": 0.18036677454153183,
+      "grad_norm": 0.6761631369590759,
+      "learning_rate": 7.493261455525607e-05,
+      "loss": 0.9593698382377625,
+      "step": 418
+    },
+    {
+      "epoch": 0.18122977346278318,
+      "grad_norm": 0.7328561544418335,
+      "learning_rate": 7.529200359389039e-05,
+      "loss": 1.0426853895187378,
+      "step": 420
+    },
+    {
+      "epoch": 0.1820927723840345,
+      "grad_norm": 0.6256070137023926,
+      "learning_rate": 7.56513926325247e-05,
+      "loss": 0.9608182311058044,
+      "step": 422
+    },
+    {
+      "epoch": 0.18295577130528587,
+      "grad_norm": 1.2549844980239868,
+      "learning_rate": 7.601078167115903e-05,
+      "loss": 1.0162668228149414,
+      "step": 424
+    },
+    {
+      "epoch": 0.18381877022653723,
+      "grad_norm": 0.6751510500907898,
+      "learning_rate": 7.637017070979335e-05,
+      "loss": 1.130725383758545,
+      "step": 426
+    },
+    {
+      "epoch": 0.18468176914778855,
+      "grad_norm": 0.7029808163642883,
+      "learning_rate": 7.672955974842768e-05,
+      "loss": 1.0384817123413086,
+      "step": 428
+    },
+    {
+      "epoch": 0.1855447680690399,
+      "grad_norm": 0.644353449344635,
+      "learning_rate": 7.7088948787062e-05,
+      "loss": 1.017020344734192,
+      "step": 430
+    },
+    {
+      "epoch": 0.18640776699029127,
+      "grad_norm": 0.6784916520118713,
+      "learning_rate": 7.744833782569631e-05,
+      "loss": 1.005354404449463,
+      "step": 432
+    },
+    {
+      "epoch": 0.1872707659115426,
+      "grad_norm": 0.5989449620246887,
+      "learning_rate": 7.780772686433064e-05,
+      "loss": 1.026848316192627,
+      "step": 434
+    },
+    {
+      "epoch": 0.18813376483279395,
+      "grad_norm": 0.6502639651298523,
+      "learning_rate": 7.816711590296496e-05,
+      "loss": 0.9891080856323242,
+      "step": 436
+    },
+    {
+      "epoch": 0.1889967637540453,
+      "grad_norm": 0.6176205277442932,
+      "learning_rate": 7.852650494159929e-05,
+      "loss": 0.966316819190979,
+      "step": 438
+    },
+    {
+      "epoch": 0.18985976267529667,
+      "grad_norm": 0.6801626086235046,
+      "learning_rate": 7.88858939802336e-05,
+      "loss": 1.123063087463379,
+      "step": 440
+    },
+    {
+      "epoch": 0.190722761596548,
+      "grad_norm": 0.6718618273735046,
+      "learning_rate": 7.924528301886794e-05,
+      "loss": 1.0467073917388916,
+      "step": 442
+    },
+    {
+      "epoch": 0.19158576051779935,
+      "grad_norm": 0.6761009097099304,
+      "learning_rate": 7.960467205750225e-05,
+      "loss": 1.0952889919281006,
+      "step": 444
+    },
+    {
+      "epoch": 0.1924487594390507,
+      "grad_norm": 0.6356327533721924,
+      "learning_rate": 7.996406109613657e-05,
+      "loss": 0.954807698726654,
+      "step": 446
+    },
+    {
+      "epoch": 0.19331175836030204,
+      "grad_norm": 0.6798669695854187,
+      "learning_rate": 8.03234501347709e-05,
+      "loss": 0.9941422343254089,
+      "step": 448
+    },
+    {
+      "epoch": 0.1941747572815534,
+      "grad_norm": 0.6511302590370178,
+      "learning_rate": 8.068283917340521e-05,
+      "loss": 1.0351495742797852,
+      "step": 450
+    },
+    {
+      "epoch": 0.19503775620280475,
+      "grad_norm": 0.6061258912086487,
+      "learning_rate": 8.104222821203954e-05,
+      "loss": 1.00546133518219,
+      "step": 452
+    },
+    {
+      "epoch": 0.1959007551240561,
+      "grad_norm": 0.6278533935546875,
+      "learning_rate": 8.140161725067386e-05,
+      "loss": 1.0778460502624512,
+      "step": 454
+    },
+    {
+      "epoch": 0.19676375404530744,
+      "grad_norm": 0.6866298317909241,
+      "learning_rate": 8.176100628930818e-05,
+      "loss": 1.0344486236572266,
+      "step": 456
+    },
+    {
+      "epoch": 0.1976267529665588,
+      "grad_norm": 0.7338075041770935,
+      "learning_rate": 8.212039532794251e-05,
+      "loss": 1.0663033723831177,
+      "step": 458
+    },
+    {
+      "epoch": 0.19848975188781015,
+      "grad_norm": 0.6811459064483643,
+      "learning_rate": 8.247978436657682e-05,
+      "loss": 0.9665339589118958,
+      "step": 460
+    },
+    {
+      "epoch": 0.19935275080906148,
+      "grad_norm": 0.6779627799987793,
+      "learning_rate": 8.283917340521114e-05,
+      "loss": 1.024712324142456,
+      "step": 462
+    },
+    {
+      "epoch": 0.20021574973031284,
+      "grad_norm": 0.6486892700195312,
+      "learning_rate": 8.319856244384546e-05,
+      "loss": 0.9699305295944214,
+      "step": 464
+    },
+    {
+      "epoch": 0.2010787486515642,
+      "grad_norm": 0.7022278308868408,
+      "learning_rate": 8.355795148247979e-05,
+      "loss": 0.9540432095527649,
+      "step": 466
+    },
+    {
+      "epoch": 0.20194174757281552,
+      "grad_norm": 0.5922990441322327,
+      "learning_rate": 8.39173405211141e-05,
+      "loss": 0.9253339767456055,
+      "step": 468
+    },
+    {
+      "epoch": 0.20280474649406688,
+      "grad_norm": 0.7076792120933533,
+      "learning_rate": 8.427672955974843e-05,
+      "loss": 0.9987741112709045,
+      "step": 470
+    },
+    {
+      "epoch": 0.20366774541531824,
+      "grad_norm": 0.6491380333900452,
+      "learning_rate": 8.463611859838275e-05,
+      "loss": 1.0249329805374146,
+      "step": 472
+    },
+    {
+      "epoch": 0.2045307443365696,
+      "grad_norm": 0.6784211993217468,
+      "learning_rate": 8.499550763701708e-05,
+      "loss": 1.0577133893966675,
+      "step": 474
+    },
+    {
+      "epoch": 0.20539374325782092,
+      "grad_norm": 0.6453303694725037,
+      "learning_rate": 8.53548966756514e-05,
+      "loss": 1.1312458515167236,
+      "step": 476
+    },
+    {
+      "epoch": 0.20625674217907228,
+      "grad_norm": 0.7431377172470093,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 1.0592451095581055,
+      "step": 478
+    },
+    {
+      "epoch": 0.20711974110032363,
+      "grad_norm": 0.6097649931907654,
+      "learning_rate": 8.607367475292004e-05,
+      "loss": 0.9337235689163208,
+      "step": 480
+    },
+    {
+      "epoch": 0.20798274002157496,
+      "grad_norm": 0.5693124532699585,
+      "learning_rate": 8.643306379155436e-05,
+      "loss": 0.9088928699493408,
+      "step": 482
+    },
+    {
+      "epoch": 0.20884573894282632,
+      "grad_norm": 0.7377229332923889,
+      "learning_rate": 8.679245283018869e-05,
+      "loss": 1.0729358196258545,
+      "step": 484
+    },
+    {
+      "epoch": 0.20970873786407768,
+      "grad_norm": 0.7399470210075378,
+      "learning_rate": 8.7151841868823e-05,
+      "loss": 1.0428457260131836,
+      "step": 486
+    },
+    {
+      "epoch": 0.210571736785329,
+      "grad_norm": 0.677052915096283,
+      "learning_rate": 8.751123090745734e-05,
+      "loss": 0.9940266013145447,
+      "step": 488
+    },
+    {
+      "epoch": 0.21143473570658036,
+      "grad_norm": 0.7126721739768982,
+      "learning_rate": 8.787061994609165e-05,
+      "loss": 1.011808156967163,
+      "step": 490
+    },
+    {
+      "epoch": 0.21229773462783172,
+      "grad_norm": 0.6663792729377747,
+      "learning_rate": 8.823000898472597e-05,
+      "loss": 1.0054185390472412,
+      "step": 492
+    },
+    {
+      "epoch": 0.21316073354908308,
+      "grad_norm": 0.6661092042922974,
+      "learning_rate": 8.85893980233603e-05,
+      "loss": 1.0167138576507568,
+      "step": 494
+    },
+    {
+      "epoch": 0.2140237324703344,
+      "grad_norm": 0.6975740194320679,
+      "learning_rate": 8.894878706199461e-05,
+      "loss": 1.1470818519592285,
+      "step": 496
+    },
+    {
+      "epoch": 0.21488673139158576,
+      "grad_norm": 0.6594390869140625,
+      "learning_rate": 8.930817610062893e-05,
+      "loss": 0.9619631171226501,
+      "step": 498
+    },
+    {
+      "epoch": 0.21574973031283712,
+      "grad_norm": 0.7216679453849792,
+      "learning_rate": 8.966756513926325e-05,
+      "loss": 0.9971368312835693,
+      "step": 500
+    },
+    {
+      "epoch": 0.21574973031283712,
+      "eval_loss": 1.0417571067810059,
+      "eval_runtime": 659.3112,
+      "eval_samples_per_second": 3.124,
+      "eval_steps_per_second": 3.124,
+      "step": 500
+    },
+    {
+      "epoch": 0.21661272923408845,
+      "grad_norm": 0.6188210844993591,
+      "learning_rate": 9.002695417789758e-05,
+      "loss": 1.0307213068008423,
+      "step": 502
+    },
+    {
+      "epoch": 0.2174757281553398,
+      "grad_norm": 0.6716445088386536,
+      "learning_rate": 9.03863432165319e-05,
+      "loss": 1.0188794136047363,
+      "step": 504
+    },
+    {
+      "epoch": 0.21833872707659116,
+      "grad_norm": 0.6790863275527954,
+      "learning_rate": 9.074573225516622e-05,
+      "loss": 0.9764845967292786,
+      "step": 506
+    },
+    {
+      "epoch": 0.2192017259978425,
+      "grad_norm": 0.6764960289001465,
+      "learning_rate": 9.110512129380054e-05,
+      "loss": 0.948829174041748,
+      "step": 508
+    },
+    {
+      "epoch": 0.22006472491909385,
+      "grad_norm": 0.6210965514183044,
+      "learning_rate": 9.146451033243486e-05,
+      "loss": 1.008013129234314,
+      "step": 510
+    },
+    {
+      "epoch": 0.2209277238403452,
+      "grad_norm": 0.7739297747612,
+      "learning_rate": 9.182389937106919e-05,
+      "loss": 1.1662557125091553,
+      "step": 512
+    },
+    {
+      "epoch": 0.22179072276159656,
+      "grad_norm": 0.7055562138557434,
+      "learning_rate": 9.21832884097035e-05,
+      "loss": 1.0325161218643188,
+      "step": 514
+    },
+    {
+      "epoch": 0.2226537216828479,
+      "grad_norm": 0.6079210042953491,
+      "learning_rate": 9.254267744833783e-05,
+      "loss": 1.00056791305542,
+      "step": 516
+    },
+    {
+      "epoch": 0.22351672060409924,
+      "grad_norm": 0.5974318981170654,
+      "learning_rate": 9.290206648697215e-05,
+      "loss": 0.9422364234924316,
+      "step": 518
+    },
+    {
+      "epoch": 0.2243797195253506,
+      "grad_norm": 0.5963430404663086,
+      "learning_rate": 9.326145552560648e-05,
+      "loss": 0.936336100101471,
+      "step": 520
+    },
+    {
+      "epoch": 0.22524271844660193,
+      "grad_norm": 0.6823658347129822,
+      "learning_rate": 9.36208445642408e-05,
+      "loss": 1.0538607835769653,
+      "step": 522
+    },
+    {
+      "epoch": 0.2261057173678533,
+      "grad_norm": 0.6409855484962463,
+      "learning_rate": 9.398023360287511e-05,
+      "loss": 1.0483653545379639,
+      "step": 524
+    },
+    {
+      "epoch": 0.22696871628910464,
+      "grad_norm": 0.6867254376411438,
+      "learning_rate": 9.433962264150944e-05,
+      "loss": 0.9668049812316895,
+      "step": 526
+    },
+    {
+      "epoch": 0.227831715210356,
+      "grad_norm": 0.5690792798995972,
+      "learning_rate": 9.469901168014376e-05,
+      "loss": 1.008763313293457,
+      "step": 528
+    },
+    {
+      "epoch": 0.22869471413160733,
+      "grad_norm": 0.5964897274971008,
+      "learning_rate": 9.505840071877809e-05,
+      "loss": 1.0816441774368286,
+      "step": 530
+    },
+    {
+      "epoch": 0.2295577130528587,
+      "grad_norm": 0.627419114112854,
+      "learning_rate": 9.54177897574124e-05,
+      "loss": 0.9265700578689575,
+      "step": 532
+    },
+    {
+      "epoch": 0.23042071197411004,
+      "grad_norm": 0.5862151980400085,
+      "learning_rate": 9.577717879604674e-05,
+      "loss": 0.9804646372795105,
+      "step": 534
+    },
+    {
+      "epoch": 0.23128371089536137,
+      "grad_norm": 0.5573718547821045,
+      "learning_rate": 9.613656783468105e-05,
+      "loss": 0.9627988934516907,
+      "step": 536
+    },
+    {
+      "epoch": 0.23214670981661273,
+      "grad_norm": 0.6705166101455688,
+      "learning_rate": 9.649595687331537e-05,
+      "loss": 1.0012824535369873,
+      "step": 538
+    },
+    {
+      "epoch": 0.23300970873786409,
+      "grad_norm": 0.6251236796379089,
+      "learning_rate": 9.685534591194969e-05,
+      "loss": 0.9568162560462952,
+      "step": 540
+    },
+    {
+      "epoch": 0.23387270765911541,
+      "grad_norm": 0.6466493010520935,
+      "learning_rate": 9.7214734950584e-05,
+      "loss": 1.031549334526062,
+      "step": 542
+    },
+    {
+      "epoch": 0.23473570658036677,
+      "grad_norm": 0.5183866024017334,
+      "learning_rate": 9.757412398921833e-05,
+      "loss": 0.8603643774986267,
+      "step": 544
+    },
+    {
+      "epoch": 0.23559870550161813,
+      "grad_norm": 0.6725775599479675,
+      "learning_rate": 9.793351302785265e-05,
+      "loss": 1.0365077257156372,
+      "step": 546
+    },
+    {
+      "epoch": 0.23646170442286948,
+      "grad_norm": 0.5972357988357544,
+      "learning_rate": 9.829290206648698e-05,
+      "loss": 0.9304701089859009,
+      "step": 548
+    },
+    {
+      "epoch": 0.2373247033441208,
+      "grad_norm": 0.5319957733154297,
+      "learning_rate": 9.86522911051213e-05,
+      "loss": 0.9575805068016052,
+      "step": 550
+    },
+    {
+      "epoch": 0.23818770226537217,
+      "grad_norm": 0.6502835750579834,
+      "learning_rate": 9.901168014375562e-05,
+      "loss": 1.0307214260101318,
+      "step": 552
+    },
+    {
+      "epoch": 0.23905070118662353,
+      "grad_norm": 0.6734047532081604,
+      "learning_rate": 9.937106918238994e-05,
+      "loss": 1.05185067653656,
+      "step": 554
+    },
+    {
+      "epoch": 0.23991370010787486,
+      "grad_norm": 0.5667978525161743,
+      "learning_rate": 9.973045822102426e-05,
+      "loss": 1.0190176963806152,
+      "step": 556
+    },
+    {
+      "epoch": 0.2407766990291262,
+      "grad_norm": 0.6370418667793274,
+      "learning_rate": 0.00010008984725965857,
+      "loss": 1.076182246208191,
+      "step": 558
+    },
+    {
+      "epoch": 0.24163969795037757,
+      "grad_norm": 0.689719021320343,
+      "learning_rate": 0.0001004492362982929,
+      "loss": 1.0408724546432495,
+      "step": 560
+    },
+    {
+      "epoch": 0.2425026968716289,
+      "grad_norm": 0.6304254531860352,
+      "learning_rate": 0.00010080862533692723,
+      "loss": 0.9869902729988098,
+      "step": 562
+    },
+    {
+      "epoch": 0.24336569579288025,
+      "grad_norm": 0.6797420382499695,
+      "learning_rate": 0.00010116801437556156,
+      "loss": 1.0198370218276978,
+      "step": 564
+    },
+    {
+      "epoch": 0.2442286947141316,
+      "grad_norm": 0.5993657112121582,
+      "learning_rate": 0.00010152740341419587,
+      "loss": 0.9947441816329956,
+      "step": 566
+    },
+    {
+      "epoch": 0.24509169363538297,
+      "grad_norm": 0.6369836330413818,
+      "learning_rate": 0.0001018867924528302,
+      "loss": 0.9722896814346313,
+      "step": 568
+    },
+    {
+      "epoch": 0.2459546925566343,
+      "grad_norm": 0.6942457556724548,
+      "learning_rate": 0.00010224618149146453,
+      "loss": 0.9716570973396301,
+      "step": 570
+    },
+    {
+      "epoch": 0.24681769147788565,
+      "grad_norm": 0.5403370261192322,
+      "learning_rate": 0.00010260557053009883,
+      "loss": 0.9797524213790894,
+      "step": 572
+    },
+    {
+      "epoch": 0.247680690399137,
+      "grad_norm": 0.5207529067993164,
+      "learning_rate": 0.00010296495956873316,
+      "loss": 0.985367476940155,
+      "step": 574
+    },
+    {
+      "epoch": 0.24854368932038834,
+      "grad_norm": 0.6751103401184082,
+      "learning_rate": 0.00010332434860736748,
+      "loss": 1.075042724609375,
+      "step": 576
+    },
+    {
+      "epoch": 0.2494066882416397,
+      "grad_norm": 0.565331220626831,
+      "learning_rate": 0.0001036837376460018,
+      "loss": 0.9273878335952759,
+      "step": 578
+    },
+    {
+      "epoch": 0.25026968716289105,
+      "grad_norm": 0.6858948469161987,
+      "learning_rate": 0.00010404312668463612,
+      "loss": 0.9872279763221741,
+      "step": 580
+    },
+    {
+      "epoch": 0.2511326860841424,
+      "grad_norm": 0.7091426253318787,
+      "learning_rate": 0.00010440251572327044,
+      "loss": 1.0038671493530273,
+      "step": 582
+    },
+    {
+      "epoch": 0.25199568500539377,
+      "grad_norm": 0.6493771076202393,
+      "learning_rate": 0.00010476190476190477,
+      "loss": 1.0109868049621582,
+      "step": 584
+    },
+    {
+      "epoch": 0.25285868392664507,
+      "grad_norm": 0.6107586622238159,
+      "learning_rate": 0.00010512129380053907,
+      "loss": 1.0020402669906616,
+      "step": 586
+    },
+    {
+      "epoch": 0.2537216828478964,
+      "grad_norm": 0.6878048181533813,
+      "learning_rate": 0.0001054806828391734,
+      "loss": 0.961039662361145,
+      "step": 588
+    },
+    {
+      "epoch": 0.2545846817691478,
+      "grad_norm": 0.664034903049469,
+      "learning_rate": 0.00010584007187780773,
+      "loss": 0.9725209474563599,
+      "step": 590
+    },
+    {
+      "epoch": 0.25544768069039914,
+      "grad_norm": 0.6399680376052856,
+      "learning_rate": 0.00010619946091644206,
+      "loss": 0.9907437562942505,
+      "step": 592
+    },
+    {
+      "epoch": 0.2563106796116505,
+      "grad_norm": 0.6163286566734314,
+      "learning_rate": 0.00010655884995507636,
+      "loss": 0.9650095701217651,
+      "step": 594
+    },
+    {
+      "epoch": 0.25717367853290185,
+      "grad_norm": 0.6008322238922119,
+      "learning_rate": 0.0001069182389937107,
+      "loss": 1.0102758407592773,
+      "step": 596
+    },
+    {
+      "epoch": 0.2580366774541532,
+      "grad_norm": 0.6752071380615234,
+      "learning_rate": 0.00010727762803234502,
+      "loss": 0.9101885557174683,
+      "step": 598
+    },
+    {
+      "epoch": 0.2588996763754045,
+      "grad_norm": 0.6789175868034363,
+      "learning_rate": 0.00010763701707097935,
+      "loss": 1.0461398363113403,
+      "step": 600
+    },
+    {
+      "epoch": 0.2588996763754045,
+      "eval_loss": 1.021111011505127,
+      "eval_runtime": 648.1611,
+      "eval_samples_per_second": 3.178,
+      "eval_steps_per_second": 3.178,
+      "step": 600
+    },
+    {
+      "epoch": 0.25976267529665586,
+      "grad_norm": 0.5660730600357056,
+      "learning_rate": 0.00010799640610961366,
+      "loss": 0.9582418203353882,
+      "step": 602
+    },
+    {
+      "epoch": 0.2606256742179072,
+      "grad_norm": 0.6726544499397278,
+      "learning_rate": 0.00010835579514824799,
+      "loss": 1.0763746500015259,
+      "step": 604
+    },
+    {
+      "epoch": 0.2614886731391586,
+      "grad_norm": 0.6068508625030518,
+      "learning_rate": 0.00010871518418688232,
+      "loss": 1.0432032346725464,
+      "step": 606
+    },
+    {
+      "epoch": 0.26235167206040994,
+      "grad_norm": 0.5731637477874756,
+      "learning_rate": 0.00010907457322551662,
+      "loss": 0.9830516576766968,
+      "step": 608
+    },
+    {
+      "epoch": 0.2632146709816613,
+      "grad_norm": 0.6777567267417908,
+      "learning_rate": 0.00010943396226415095,
+      "loss": 1.0442042350769043,
+      "step": 610
+    },
+    {
+      "epoch": 0.26407766990291265,
+      "grad_norm": 0.6372506618499756,
+      "learning_rate": 0.00010979335130278528,
+      "loss": 1.0001944303512573,
+      "step": 612
+    },
+    {
+      "epoch": 0.26494066882416395,
+      "grad_norm": 0.6606221795082092,
+      "learning_rate": 0.0001101527403414196,
+      "loss": 1.035884141921997,
+      "step": 614
+    },
+    {
+      "epoch": 0.2658036677454153,
+      "grad_norm": 0.6083229780197144,
+      "learning_rate": 0.00011051212938005391,
+      "loss": 0.9403397440910339,
+      "step": 616
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.6318517923355103,
+      "learning_rate": 0.00011087151841868823,
+      "loss": 0.9274454116821289,
+      "step": 618
+    },
+    {
+      "epoch": 0.267529665587918,
+      "grad_norm": 0.628190279006958,
+      "learning_rate": 0.00011123090745732256,
+      "loss": 0.9883754253387451,
+      "step": 620
+    },
+    {
+      "epoch": 0.2683926645091694,
+      "grad_norm": 0.5961961150169373,
+      "learning_rate": 0.00011159029649595688,
+      "loss": 1.0317535400390625,
+      "step": 622
+    },
+    {
+      "epoch": 0.26925566343042073,
+      "grad_norm": 0.5995341539382935,
+      "learning_rate": 0.00011194968553459119,
+      "loss": 0.9776126742362976,
+      "step": 624
+    },
+    {
+      "epoch": 0.27011866235167203,
+      "grad_norm": 0.6639334559440613,
+      "learning_rate": 0.00011230907457322552,
+      "loss": 1.0112378597259521,
+      "step": 626
+    },
+    {
+      "epoch": 0.2709816612729234,
+      "grad_norm": 0.6348621249198914,
+      "learning_rate": 0.00011266846361185985,
+      "loss": 1.0553804636001587,
+      "step": 628
+    },
+    {
+      "epoch": 0.27184466019417475,
+      "grad_norm": 0.5929805040359497,
+      "learning_rate": 0.00011302785265049416,
+      "loss": 1.025888442993164,
+      "step": 630
+    },
+    {
+      "epoch": 0.2727076591154261,
+      "grad_norm": 0.6052366495132446,
+      "learning_rate": 0.00011338724168912849,
+      "loss": 1.02956223487854,
+      "step": 632
+    },
+    {
+      "epoch": 0.27357065803667746,
+      "grad_norm": 0.6494882106781006,
+      "learning_rate": 0.00011374663072776282,
+      "loss": 0.989752471446991,
+      "step": 634
+    },
+    {
+      "epoch": 0.2744336569579288,
+      "grad_norm": 0.6005767583847046,
+      "learning_rate": 0.00011410601976639712,
+      "loss": 1.0030683279037476,
+      "step": 636
+    },
+    {
+      "epoch": 0.2752966558791802,
+      "grad_norm": 0.6478356122970581,
+      "learning_rate": 0.00011446540880503145,
+      "loss": 1.002000093460083,
+      "step": 638
+    },
+    {
+      "epoch": 0.2761596548004315,
+      "grad_norm": 0.5804725289344788,
+      "learning_rate": 0.00011482479784366578,
+      "loss": 0.9807654023170471,
+      "step": 640
+    },
+    {
+      "epoch": 0.27702265372168283,
+      "grad_norm": 0.632530689239502,
+      "learning_rate": 0.00011518418688230011,
+      "loss": 0.9841892123222351,
+      "step": 642
+    },
+    {
+      "epoch": 0.2778856526429342,
+      "grad_norm": 0.5340113639831543,
+      "learning_rate": 0.00011554357592093441,
+      "loss": 0.8902478814125061,
+      "step": 644
+    },
+    {
+      "epoch": 0.27874865156418555,
+      "grad_norm": 0.5901665091514587,
+      "learning_rate": 0.00011590296495956874,
+      "loss": 0.9019404649734497,
+      "step": 646
+    },
+    {
+      "epoch": 0.2796116504854369,
+      "grad_norm": 0.666589617729187,
+      "learning_rate": 0.00011626235399820307,
+      "loss": 0.9384423494338989,
+      "step": 648
+    },
+    {
+      "epoch": 0.28047464940668826,
+      "grad_norm": 0.7000334858894348,
+      "learning_rate": 0.00011662174303683737,
+      "loss": 1.0666629076004028,
+      "step": 650
+    },
+    {
+      "epoch": 0.2813376483279396,
+      "grad_norm": 0.663663923740387,
+      "learning_rate": 0.0001169811320754717,
+      "loss": 1.000019907951355,
+      "step": 652
+    },
+    {
+      "epoch": 0.2822006472491909,
+      "grad_norm": 0.6097694039344788,
+      "learning_rate": 0.00011734052111410603,
+      "loss": 0.9450293183326721,
+      "step": 654
+    },
+    {
+      "epoch": 0.2830636461704423,
+      "grad_norm": 0.6130967140197754,
+      "learning_rate": 0.00011769991015274035,
+      "loss": 0.9480894207954407,
+      "step": 656
+    },
+    {
+      "epoch": 0.28392664509169363,
+      "grad_norm": 0.7091249227523804,
+      "learning_rate": 0.00011805929919137467,
+      "loss": 1.1377143859863281,
+      "step": 658
+    },
+    {
+      "epoch": 0.284789644012945,
+      "grad_norm": 0.6556766629219055,
+      "learning_rate": 0.00011841868823000898,
+      "loss": 0.9421243667602539,
+      "step": 660
+    },
+    {
+      "epoch": 0.28565264293419634,
+      "grad_norm": 0.6682968735694885,
+      "learning_rate": 0.00011877807726864331,
+      "loss": 0.9726828336715698,
+      "step": 662
+    },
+    {
+      "epoch": 0.2865156418554477,
+      "grad_norm": 0.5224708914756775,
+      "learning_rate": 0.00011913746630727762,
+      "loss": 0.8996511697769165,
+      "step": 664
+    },
+    {
+      "epoch": 0.287378640776699,
+      "grad_norm": 0.5914195775985718,
+      "learning_rate": 0.00011949685534591195,
+      "loss": 0.9679517149925232,
+      "step": 666
+    },
+    {
+      "epoch": 0.28824163969795036,
+      "grad_norm": 0.6175519824028015,
+      "learning_rate": 0.00011985624438454628,
+      "loss": 0.8743209838867188,
+      "step": 668
+    },
+    {
+      "epoch": 0.2891046386192017,
+      "grad_norm": 0.6019226312637329,
+      "learning_rate": 0.0001202156334231806,
+      "loss": 0.9741992354393005,
+      "step": 670
+    },
+    {
+      "epoch": 0.28996763754045307,
+      "grad_norm": 0.6080542206764221,
+      "learning_rate": 0.00012057502246181491,
+      "loss": 0.9516472816467285,
+      "step": 672
+    },
+    {
+      "epoch": 0.29083063646170443,
+      "grad_norm": 0.5885615944862366,
+      "learning_rate": 0.00012093441150044924,
+      "loss": 1.122761607170105,
+      "step": 674
+    },
+    {
+      "epoch": 0.2916936353829558,
+      "grad_norm": 0.6635209918022156,
+      "learning_rate": 0.00012129380053908357,
+      "loss": 1.0105189085006714,
+      "step": 676
+    },
+    {
+      "epoch": 0.29255663430420714,
+      "grad_norm": 0.5805009007453918,
+      "learning_rate": 0.0001216531895777179,
+      "loss": 0.906292200088501,
+      "step": 678
+    },
+    {
+      "epoch": 0.29341963322545844,
+      "grad_norm": 0.5980029702186584,
+      "learning_rate": 0.0001220125786163522,
+      "loss": 1.009568691253662,
+      "step": 680
+    },
+    {
+      "epoch": 0.2942826321467098,
+      "grad_norm": 0.6797705292701721,
+      "learning_rate": 0.00012237196765498652,
+      "loss": 1.0373667478561401,
+      "step": 682
+    },
+    {
+      "epoch": 0.29514563106796116,
+      "grad_norm": 0.6280547976493835,
+      "learning_rate": 0.00012273135669362085,
+      "loss": 0.9758188724517822,
+      "step": 684
+    },
+    {
+      "epoch": 0.2960086299892125,
+      "grad_norm": 0.511608898639679,
+      "learning_rate": 0.00012309074573225515,
+      "loss": 0.9111692905426025,
+      "step": 686
+    },
+    {
+      "epoch": 0.29687162891046387,
+      "grad_norm": 0.5781835317611694,
+      "learning_rate": 0.00012345013477088948,
+      "loss": 0.8865921497344971,
+      "step": 688
+    },
+    {
+      "epoch": 0.2977346278317152,
+      "grad_norm": 0.6514166593551636,
+      "learning_rate": 0.0001238095238095238,
+      "loss": 0.9768189191818237,
+      "step": 690
+    },
+    {
+      "epoch": 0.2985976267529666,
+      "grad_norm": 0.6109189987182617,
+      "learning_rate": 0.00012416891284815814,
+      "loss": 0.9991607069969177,
+      "step": 692
+    },
+    {
+      "epoch": 0.2994606256742179,
+      "grad_norm": 0.6598902344703674,
+      "learning_rate": 0.00012452830188679244,
+      "loss": 0.9548360705375671,
+      "step": 694
+    },
+    {
+      "epoch": 0.30032362459546924,
+      "grad_norm": 0.5633156895637512,
+      "learning_rate": 0.00012488769092542677,
+      "loss": 0.992988109588623,
+      "step": 696
+    },
+    {
+      "epoch": 0.3011866235167206,
+      "grad_norm": 0.6098802089691162,
+      "learning_rate": 0.0001252470799640611,
+      "loss": 0.9709890484809875,
+      "step": 698
+    },
+    {
+      "epoch": 0.30204962243797195,
+      "grad_norm": 0.6197102665901184,
+      "learning_rate": 0.0001256064690026954,
+      "loss": 1.018282175064087,
+      "step": 700
+    },
+    {
+      "epoch": 0.30204962243797195,
+      "eval_loss": 1.0030721426010132,
+      "eval_runtime": 655.4533,
+      "eval_samples_per_second": 3.143,
+      "eval_steps_per_second": 3.143,
+      "step": 700
+    },
+    {
+      "epoch": 0.3029126213592233,
+      "grad_norm": 0.5817480683326721,
+      "learning_rate": 0.00012596585804132974,
+      "loss": 0.9147283434867859,
+      "step": 702
+    },
+    {
+      "epoch": 0.30377562028047467,
+      "grad_norm": 0.5976696014404297,
+      "learning_rate": 0.00012632524707996407,
+      "loss": 0.9318362474441528,
+      "step": 704
+    },
+    {
+      "epoch": 0.304638619201726,
+      "grad_norm": 0.6389723420143127,
+      "learning_rate": 0.0001266846361185984,
+      "loss": 0.9500927925109863,
+      "step": 706
+    },
+    {
+      "epoch": 0.3055016181229773,
+      "grad_norm": 0.6485719084739685,
+      "learning_rate": 0.0001270440251572327,
+      "loss": 1.0271424055099487,
+      "step": 708
+    },
+    {
+      "epoch": 0.3063646170442287,
+      "grad_norm": 0.5802455544471741,
+      "learning_rate": 0.00012740341419586703,
+      "loss": 0.9781906008720398,
+      "step": 710
+    },
+    {
+      "epoch": 0.30722761596548004,
+      "grad_norm": 0.6359356641769409,
+      "learning_rate": 0.00012776280323450136,
+      "loss": 1.0195324420928955,
+      "step": 712
+    },
+    {
+      "epoch": 0.3080906148867314,
+      "grad_norm": 0.5975426435470581,
+      "learning_rate": 0.00012812219227313566,
+      "loss": 0.9250738024711609,
+      "step": 714
+    },
+    {
+      "epoch": 0.30895361380798275,
+      "grad_norm": 0.643110454082489,
+      "learning_rate": 0.00012848158131177,
+      "loss": 0.9888015985488892,
+      "step": 716
+    },
+    {
+      "epoch": 0.3098166127292341,
+      "grad_norm": 0.6043205261230469,
+      "learning_rate": 0.00012884097035040432,
+      "loss": 0.9709514379501343,
+      "step": 718
+    },
+    {
+      "epoch": 0.3106796116504854,
+      "grad_norm": 0.5687094926834106,
+      "learning_rate": 0.00012920035938903865,
+      "loss": 1.0272964239120483,
+      "step": 720
+    },
+    {
+      "epoch": 0.31154261057173677,
+      "grad_norm": 0.5688400864601135,
+      "learning_rate": 0.00012955974842767296,
+      "loss": 0.9370370507240295,
+      "step": 722
+    },
+    {
+      "epoch": 0.3124056094929881,
+      "grad_norm": 0.5610610246658325,
+      "learning_rate": 0.00012991913746630729,
+      "loss": 0.9535608291625977,
+      "step": 724
+    },
+    {
+      "epoch": 0.3132686084142395,
+      "grad_norm": 0.6338257193565369,
+      "learning_rate": 0.00013027852650494162,
+      "loss": 1.0188907384872437,
+      "step": 726
+    },
+    {
+      "epoch": 0.31413160733549084,
+      "grad_norm": 0.5365633368492126,
+      "learning_rate": 0.00013063791554357592,
+      "loss": 0.9253716468811035,
+      "step": 728
+    },
+    {
+      "epoch": 0.3149946062567422,
+      "grad_norm": 0.5599163174629211,
+      "learning_rate": 0.00013099730458221025,
+      "loss": 0.8941492438316345,
+      "step": 730
+    },
+    {
+      "epoch": 0.31585760517799355,
+      "grad_norm": 0.6059780716896057,
+      "learning_rate": 0.00013135669362084458,
+      "loss": 0.9831459522247314,
+      "step": 732
+    },
+    {
+      "epoch": 0.31672060409924485,
+      "grad_norm": 0.5596494078636169,
+      "learning_rate": 0.0001317160826594789,
+      "loss": 0.9332310557365417,
+      "step": 734
+    },
+    {
+      "epoch": 0.3175836030204962,
+      "grad_norm": 0.5618010759353638,
+      "learning_rate": 0.0001320754716981132,
+      "loss": 0.9082580208778381,
+      "step": 736
+    },
+    {
+      "epoch": 0.31844660194174756,
+      "grad_norm": 0.6412109732627869,
+      "learning_rate": 0.00013243486073674754,
+      "loss": 1.008690357208252,
+      "step": 738
+    },
+    {
+      "epoch": 0.3193096008629989,
+      "grad_norm": 0.5742355585098267,
+      "learning_rate": 0.00013279424977538187,
+      "loss": 0.9597798585891724,
+      "step": 740
+    },
+    {
+      "epoch": 0.3201725997842503,
+      "grad_norm": 0.6470226645469666,
+      "learning_rate": 0.00013315363881401617,
+      "loss": 0.989331841468811,
+      "step": 742
+    },
+    {
+      "epoch": 0.32103559870550163,
+      "grad_norm": 0.5598039031028748,
+      "learning_rate": 0.0001335130278526505,
+      "loss": 0.8677343130111694,
+      "step": 744
+    },
+    {
+      "epoch": 0.321898597626753,
+      "grad_norm": 0.5441372990608215,
+      "learning_rate": 0.00013387241689128483,
+      "loss": 0.9462730288505554,
+      "step": 746
+    },
+    {
+      "epoch": 0.3227615965480043,
+      "grad_norm": 0.5858626365661621,
+      "learning_rate": 0.00013423180592991916,
+      "loss": 0.994694173336029,
+      "step": 748
+    },
+    {
+      "epoch": 0.32362459546925565,
+      "grad_norm": 0.511372447013855,
+      "learning_rate": 0.00013459119496855347,
+      "loss": 0.9387269616127014,
+      "step": 750
+    },
+    {
+      "epoch": 0.324487594390507,
+      "grad_norm": 0.47798457741737366,
+      "learning_rate": 0.0001349505840071878,
+      "loss": 0.9473881721496582,
+      "step": 752
+    },
+    {
+      "epoch": 0.32535059331175836,
+      "grad_norm": 0.5907022953033447,
+      "learning_rate": 0.0001353099730458221,
+      "loss": 0.9375183582305908,
+      "step": 754
+    },
+    {
+      "epoch": 0.3262135922330097,
+      "grad_norm": 0.618733286857605,
+      "learning_rate": 0.00013566936208445643,
+      "loss": 1.028738260269165,
+      "step": 756
+    },
+    {
+      "epoch": 0.3270765911542611,
+      "grad_norm": 0.5234512090682983,
+      "learning_rate": 0.00013602875112309076,
+      "loss": 0.9420192241668701,
+      "step": 758
+    },
+    {
+      "epoch": 0.32793959007551243,
+      "grad_norm": 0.7036319971084595,
+      "learning_rate": 0.00013638814016172506,
+      "loss": 1.0252270698547363,
+      "step": 760
+    },
+    {
+      "epoch": 0.32880258899676373,
+      "grad_norm": 0.5543172359466553,
+      "learning_rate": 0.0001367475292003594,
+      "loss": 0.8453778028488159,
+      "step": 762
+    },
+    {
+      "epoch": 0.3296655879180151,
+      "grad_norm": 0.5438711643218994,
+      "learning_rate": 0.0001371069182389937,
+      "loss": 0.8659937977790833,
+      "step": 764
+    },
+    {
+      "epoch": 0.33052858683926645,
+      "grad_norm": 0.6390914916992188,
+      "learning_rate": 0.00013746630727762803,
+      "loss": 1.038142442703247,
+      "step": 766
+    },
+    {
+      "epoch": 0.3313915857605178,
+      "grad_norm": 0.50070720911026,
+      "learning_rate": 0.00013782569631626236,
+      "loss": 0.899932861328125,
+      "step": 768
+    },
+    {
+      "epoch": 0.33225458468176916,
+      "grad_norm": 0.5982286334037781,
+      "learning_rate": 0.00013818508535489669,
+      "loss": 0.9712884426116943,
+      "step": 770
+    },
+    {
+      "epoch": 0.3331175836030205,
+      "grad_norm": 0.6588822603225708,
+      "learning_rate": 0.000138544474393531,
+      "loss": 0.9427542686462402,
+      "step": 772
+    },
+    {
+      "epoch": 0.3339805825242718,
+      "grad_norm": 0.6022042632102966,
+      "learning_rate": 0.00013890386343216532,
+      "loss": 0.8961561918258667,
+      "step": 774
+    },
+    {
+      "epoch": 0.3348435814455232,
+      "grad_norm": 0.6595642566680908,
+      "learning_rate": 0.00013926325247079965,
+      "loss": 0.9525937438011169,
+      "step": 776
+    },
+    {
+      "epoch": 0.33570658036677453,
+      "grad_norm": 0.5210421681404114,
+      "learning_rate": 0.00013962264150943395,
+      "loss": 0.9218845367431641,
+      "step": 778
+    },
+    {
+      "epoch": 0.3365695792880259,
+      "grad_norm": 0.549669623374939,
+      "learning_rate": 0.00013998203054806828,
+      "loss": 0.877951443195343,
+      "step": 780
+    },
+    {
+      "epoch": 0.33743257820927725,
+      "grad_norm": 0.5360157489776611,
+      "learning_rate": 0.0001403414195867026,
+      "loss": 0.8670064210891724,
+      "step": 782
+    },
+    {
+      "epoch": 0.3382955771305286,
+      "grad_norm": 0.614734947681427,
+      "learning_rate": 0.00014070080862533694,
+      "loss": 0.9561367630958557,
+      "step": 784
+    },
+    {
+      "epoch": 0.33915857605177996,
+      "grad_norm": 0.5798251628875732,
+      "learning_rate": 0.00014106019766397124,
+      "loss": 0.9132505059242249,
+      "step": 786
+    },
+    {
+      "epoch": 0.34002157497303126,
+      "grad_norm": 0.6267077326774597,
+      "learning_rate": 0.00014141958670260557,
+      "loss": 0.9297707080841064,
+      "step": 788
+    },
+    {
+      "epoch": 0.3408845738942826,
+      "grad_norm": 0.6045349836349487,
+      "learning_rate": 0.0001417789757412399,
+      "loss": 0.9382412433624268,
+      "step": 790
+    },
+    {
+      "epoch": 0.341747572815534,
+      "grad_norm": 0.6125404834747314,
+      "learning_rate": 0.0001421383647798742,
+      "loss": 0.9078555107116699,
+      "step": 792
+    },
+    {
+      "epoch": 0.34261057173678533,
+      "grad_norm": 0.5927051901817322,
+      "learning_rate": 0.00014249775381850854,
+      "loss": 0.899101197719574,
+      "step": 794
+    },
+    {
+      "epoch": 0.3434735706580367,
+      "grad_norm": 0.6315743923187256,
+      "learning_rate": 0.00014285714285714287,
+      "loss": 1.028346300125122,
+      "step": 796
+    },
+    {
+      "epoch": 0.34433656957928804,
+      "grad_norm": 0.549271285533905,
+      "learning_rate": 0.0001432165318957772,
+      "loss": 0.8988189697265625,
+      "step": 798
+    },
+    {
+      "epoch": 0.3451995685005394,
+      "grad_norm": 0.6344245672225952,
+      "learning_rate": 0.0001435759209344115,
+      "loss": 1.0489003658294678,
+      "step": 800
+    },
+    {
+      "epoch": 0.3451995685005394,
+      "eval_loss": 0.9864639639854431,
+      "eval_runtime": 667.3516,
+      "eval_samples_per_second": 3.087,
+      "eval_steps_per_second": 3.087,
+      "step": 800
+    },
+    {
+      "epoch": 0.3460625674217907,
+      "grad_norm": 0.5625309348106384,
+      "learning_rate": 0.00014393530997304583,
+      "loss": 0.8773928284645081,
+      "step": 802
+    },
+    {
+      "epoch": 0.34692556634304206,
+      "grad_norm": 0.5931969285011292,
+      "learning_rate": 0.00014429469901168016,
+      "loss": 0.9116050004959106,
+      "step": 804
+    },
+    {
+      "epoch": 0.3477885652642934,
+      "grad_norm": 0.5189821720123291,
+      "learning_rate": 0.00014465408805031446,
+      "loss": 0.9124425649642944,
+      "step": 806
+    },
+    {
+      "epoch": 0.34865156418554477,
+      "grad_norm": 0.5392254590988159,
+      "learning_rate": 0.0001450134770889488,
+      "loss": 0.9517888426780701,
+      "step": 808
+    },
+    {
+      "epoch": 0.34951456310679613,
+      "grad_norm": 0.5584444999694824,
+      "learning_rate": 0.00014537286612758312,
+      "loss": 0.9947572350502014,
+      "step": 810
+    },
+    {
+      "epoch": 0.3503775620280475,
+      "grad_norm": 0.5188854932785034,
+      "learning_rate": 0.00014573225516621745,
+      "loss": 0.9314022660255432,
+      "step": 812
+    },
+    {
+      "epoch": 0.3512405609492988,
+      "grad_norm": 0.5783659815788269,
+      "learning_rate": 0.00014609164420485176,
+      "loss": 0.9135628938674927,
+      "step": 814
+    },
+    {
+      "epoch": 0.35210355987055014,
+      "grad_norm": 0.550959050655365,
+      "learning_rate": 0.0001464510332434861,
+      "loss": 0.9665075540542603,
+      "step": 816
+    },
+    {
+      "epoch": 0.3529665587918015,
+      "grad_norm": 0.6013346314430237,
+      "learning_rate": 0.00014681042228212042,
+      "loss": 0.9836555123329163,
+      "step": 818
+    },
+    {
+      "epoch": 0.35382955771305286,
+      "grad_norm": 0.49219194054603577,
+      "learning_rate": 0.00014716981132075472,
+      "loss": 0.8900108337402344,
+      "step": 820
+    },
+    {
+      "epoch": 0.3546925566343042,
+      "grad_norm": 0.5517411828041077,
+      "learning_rate": 0.00014752920035938905,
+      "loss": 0.8769304156303406,
+      "step": 822
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.6062695980072021,
+      "learning_rate": 0.00014788858939802338,
+      "loss": 0.9744759202003479,
+      "step": 824
+    },
+    {
+      "epoch": 0.3564185544768069,
+      "grad_norm": 0.5132041573524475,
+      "learning_rate": 0.0001482479784366577,
+      "loss": 0.8875447511672974,
+      "step": 826
+    },
+    {
+      "epoch": 0.3572815533980582,
+      "grad_norm": 0.551799476146698,
+      "learning_rate": 0.000148607367475292,
+      "loss": 0.962710440158844,
+      "step": 828
+    },
+    {
+      "epoch": 0.3581445523193096,
+      "grad_norm": 0.6046625971794128,
+      "learning_rate": 0.00014896675651392634,
+      "loss": 0.8997528553009033,
+      "step": 830
+    },
+    {
+      "epoch": 0.35900755124056094,
+      "grad_norm": 0.560025691986084,
+      "learning_rate": 0.00014932614555256067,
+      "loss": 0.9541417360305786,
+      "step": 832
+    },
+    {
+      "epoch": 0.3598705501618123,
+      "grad_norm": 0.6441047787666321,
+      "learning_rate": 0.00014968553459119498,
+      "loss": 0.907791018486023,
+      "step": 834
+    },
+    {
+      "epoch": 0.36073354908306365,
+      "grad_norm": 0.5636281967163086,
+      "learning_rate": 0.0001500449236298293,
+      "loss": 1.0295937061309814,
+      "step": 836
+    },
+    {
+      "epoch": 0.361596548004315,
+      "grad_norm": 0.5528303384780884,
+      "learning_rate": 0.0001504043126684636,
+      "loss": 0.8875265717506409,
+      "step": 838
+    },
+    {
+      "epoch": 0.36245954692556637,
+      "grad_norm": 0.5345163345336914,
+      "learning_rate": 0.00015076370170709794,
+      "loss": 0.9678915739059448,
+      "step": 840
+    },
+    {
+      "epoch": 0.36332254584681767,
+      "grad_norm": 0.5551225543022156,
+      "learning_rate": 0.00015112309074573224,
+      "loss": 0.9235162734985352,
+      "step": 842
+    },
+    {
+      "epoch": 0.364185544768069,
+      "grad_norm": 0.5131904482841492,
+      "learning_rate": 0.00015148247978436657,
+      "loss": 0.8624292016029358,
+      "step": 844
+    },
+    {
+      "epoch": 0.3650485436893204,
+      "grad_norm": 0.6811004281044006,
+      "learning_rate": 0.0001518418688230009,
+      "loss": 1.0360193252563477,
+      "step": 846
+    },
+    {
+      "epoch": 0.36591154261057174,
+      "grad_norm": 0.6409741640090942,
+      "learning_rate": 0.00015220125786163523,
+      "loss": 0.9254010915756226,
+      "step": 848
+    },
+    {
+      "epoch": 0.3667745415318231,
+      "grad_norm": 0.5534068942070007,
+      "learning_rate": 0.00015256064690026953,
+      "loss": 0.8900630474090576,
+      "step": 850
+    },
+    {
+      "epoch": 0.36763754045307445,
+      "grad_norm": 0.4999487102031708,
+      "learning_rate": 0.00015292003593890386,
+      "loss": 0.88521409034729,
+      "step": 852
+    },
+    {
+      "epoch": 0.3685005393743258,
+      "grad_norm": 0.5805923938751221,
+      "learning_rate": 0.0001532794249775382,
+      "loss": 0.9563921093940735,
+      "step": 854
+    },
+    {
+      "epoch": 0.3693635382955771,
+      "grad_norm": 0.5485470294952393,
+      "learning_rate": 0.0001536388140161725,
+      "loss": 0.8909372687339783,
+      "step": 856
+    },
+    {
+      "epoch": 0.37022653721682847,
+      "grad_norm": 0.5317923426628113,
+      "learning_rate": 0.00015399820305480683,
+      "loss": 0.9145731925964355,
+      "step": 858
+    },
+    {
+      "epoch": 0.3710895361380798,
+      "grad_norm": 0.6073495745658875,
+      "learning_rate": 0.00015435759209344116,
+      "loss": 1.01466965675354,
+      "step": 860
+    },
+    {
+      "epoch": 0.3719525350593312,
+      "grad_norm": 0.566655158996582,
+      "learning_rate": 0.0001547169811320755,
+      "loss": 0.9941825270652771,
+      "step": 862
+    },
+    {
+      "epoch": 0.37281553398058254,
+      "grad_norm": 0.5262459516525269,
+      "learning_rate": 0.0001550763701707098,
+      "loss": 1.0059782266616821,
+      "step": 864
+    },
+    {
+      "epoch": 0.3736785329018339,
+      "grad_norm": 0.6264083981513977,
+      "learning_rate": 0.00015543575920934412,
+      "loss": 1.0332856178283691,
+      "step": 866
+    },
+    {
+      "epoch": 0.3745415318230852,
+      "grad_norm": 0.6575480699539185,
+      "learning_rate": 0.00015579514824797845,
+      "loss": 1.022459626197815,
+      "step": 868
+    },
+    {
+      "epoch": 0.37540453074433655,
+      "grad_norm": 0.6291940212249756,
+      "learning_rate": 0.00015615453728661275,
+      "loss": 0.9550372362136841,
+      "step": 870
+    },
+    {
+      "epoch": 0.3762675296655879,
+      "grad_norm": 0.6710562109947205,
+      "learning_rate": 0.00015651392632524708,
+      "loss": 0.9861716628074646,
+      "step": 872
+    },
+    {
+      "epoch": 0.37713052858683926,
+      "grad_norm": 0.5505748987197876,
+      "learning_rate": 0.0001568733153638814,
+      "loss": 0.9719111919403076,
+      "step": 874
+    },
+    {
+      "epoch": 0.3779935275080906,
+      "grad_norm": 0.5055180788040161,
+      "learning_rate": 0.00015723270440251574,
+      "loss": 0.8698170185089111,
+      "step": 876
+    },
+    {
+      "epoch": 0.378856526429342,
+      "grad_norm": 0.5935947895050049,
+      "learning_rate": 0.00015759209344115005,
+      "loss": 1.029494285583496,
+      "step": 878
+    },
+    {
+      "epoch": 0.37971952535059333,
+      "grad_norm": 0.538325846195221,
+      "learning_rate": 0.00015795148247978438,
+      "loss": 0.923010528087616,
+      "step": 880
+    },
+    {
+      "epoch": 0.38058252427184464,
+      "grad_norm": 0.587297797203064,
+      "learning_rate": 0.0001583108715184187,
+      "loss": 0.9394056797027588,
+      "step": 882
+    },
+    {
+      "epoch": 0.381445523193096,
+      "grad_norm": 0.5910462737083435,
+      "learning_rate": 0.000158670260557053,
+      "loss": 0.9472483992576599,
+      "step": 884
+    },
+    {
+      "epoch": 0.38230852211434735,
+      "grad_norm": 0.629048764705658,
+      "learning_rate": 0.00015902964959568734,
+      "loss": 0.9028263688087463,
+      "step": 886
+    },
+    {
+      "epoch": 0.3831715210355987,
+      "grad_norm": 0.5028086304664612,
+      "learning_rate": 0.00015938903863432167,
+      "loss": 0.9579087495803833,
+      "step": 888
+    },
+    {
+      "epoch": 0.38403451995685006,
+      "grad_norm": 0.5372384190559387,
+      "learning_rate": 0.000159748427672956,
+      "loss": 0.8318673372268677,
+      "step": 890
+    },
+    {
+      "epoch": 0.3848975188781014,
+      "grad_norm": 0.6314184665679932,
+      "learning_rate": 0.0001601078167115903,
+      "loss": 0.9804943203926086,
+      "step": 892
+    },
+    {
+      "epoch": 0.3857605177993528,
+      "grad_norm": 0.5545229911804199,
+      "learning_rate": 0.00016046720575022463,
+      "loss": 1.0078438520431519,
+      "step": 894
+    },
+    {
+      "epoch": 0.3866235167206041,
+      "grad_norm": 0.4674014151096344,
+      "learning_rate": 0.00016082659478885896,
+      "loss": 0.9269036650657654,
+      "step": 896
+    },
+    {
+      "epoch": 0.38748651564185543,
+      "grad_norm": 1.5887153148651123,
+      "learning_rate": 0.00016118598382749326,
+      "loss": 0.8927953243255615,
+      "step": 898
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "grad_norm": 0.5217035412788391,
+      "learning_rate": 0.0001615453728661276,
+      "loss": 0.908074140548706,
+      "step": 900
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "eval_loss": 0.9741895794868469,
+      "eval_runtime": 667.2236,
+      "eval_samples_per_second": 3.087,
+      "eval_steps_per_second": 3.087,
+      "step": 900
+    },
+    {
+      "epoch": 0.38921251348435815,
+      "grad_norm": 0.470498651266098,
+      "learning_rate": 0.00016190476190476192,
+      "loss": 0.9660369157791138,
+      "step": 902
+    },
+    {
+      "epoch": 0.3900755124056095,
+      "grad_norm": 0.5111004114151001,
+      "learning_rate": 0.00016226415094339625,
+      "loss": 0.9236379265785217,
+      "step": 904
+    },
+    {
+      "epoch": 0.39093851132686086,
+      "grad_norm": 0.5872815251350403,
+      "learning_rate": 0.00016262353998203056,
+      "loss": 1.0061595439910889,
+      "step": 906
+    },
+    {
+      "epoch": 0.3918015102481122,
+      "grad_norm": 0.5150740742683411,
+      "learning_rate": 0.0001629829290206649,
+      "loss": 0.8347328901290894,
+      "step": 908
+    },
+    {
+      "epoch": 0.3926645091693635,
+      "grad_norm": 0.46554985642433167,
+      "learning_rate": 0.00016334231805929922,
+      "loss": 0.9091183543205261,
+      "step": 910
+    },
+    {
+      "epoch": 0.3935275080906149,
+      "grad_norm": 0.5292875170707703,
+      "learning_rate": 0.00016370170709793352,
+      "loss": 0.9299798011779785,
+      "step": 912
+    },
+    {
+      "epoch": 0.39439050701186623,
+      "grad_norm": 0.5177125930786133,
+      "learning_rate": 0.00016406109613656785,
+      "loss": 0.942286491394043,
+      "step": 914
+    },
+    {
+      "epoch": 0.3952535059331176,
+      "grad_norm": 0.5564161539077759,
+      "learning_rate": 0.00016442048517520215,
+      "loss": 0.825290858745575,
+      "step": 916
+    },
+    {
+      "epoch": 0.39611650485436894,
+      "grad_norm": 0.5572530031204224,
+      "learning_rate": 0.00016477987421383648,
+      "loss": 0.876898467540741,
+      "step": 918
+    },
+    {
+      "epoch": 0.3969795037756203,
+      "grad_norm": 0.7294673323631287,
+      "learning_rate": 0.0001651392632524708,
+      "loss": 0.8949798941612244,
+      "step": 920
+    },
+    {
+      "epoch": 0.3978425026968716,
+      "grad_norm": 0.5234251022338867,
+      "learning_rate": 0.00016549865229110512,
+      "loss": 0.8457819223403931,
+      "step": 922
+    },
+    {
+      "epoch": 0.39870550161812296,
+      "grad_norm": 0.5273709893226624,
+      "learning_rate": 0.00016585804132973945,
+      "loss": 0.9080174565315247,
+      "step": 924
+    },
+    {
+      "epoch": 0.3995685005393743,
+      "grad_norm": 0.5795063376426697,
+      "learning_rate": 0.00016621743036837378,
+      "loss": 1.0304023027420044,
+      "step": 926
+    },
+    {
+      "epoch": 0.4004314994606257,
+      "grad_norm": 0.6153313517570496,
+      "learning_rate": 0.00016657681940700808,
+      "loss": 0.8900477886199951,
+      "step": 928
+    },
+    {
+      "epoch": 0.40129449838187703,
+      "grad_norm": 0.6293173432350159,
+      "learning_rate": 0.0001669362084456424,
+      "loss": 1.0130009651184082,
+      "step": 930
+    },
+    {
+      "epoch": 0.4021574973031284,
+      "grad_norm": 0.5455223321914673,
+      "learning_rate": 0.00016729559748427674,
+      "loss": 0.9339282512664795,
+      "step": 932
+    },
+    {
+      "epoch": 0.40302049622437974,
+      "grad_norm": 0.5349094271659851,
+      "learning_rate": 0.00016765498652291104,
+      "loss": 0.9628980755805969,
+      "step": 934
+    },
+    {
+      "epoch": 0.40388349514563104,
+      "grad_norm": 0.491227924823761,
+      "learning_rate": 0.00016801437556154537,
+      "loss": 0.8922860026359558,
+      "step": 936
+    },
+    {
+      "epoch": 0.4047464940668824,
+      "grad_norm": 0.6331246495246887,
+      "learning_rate": 0.0001683737646001797,
+      "loss": 1.0470497608184814,
+      "step": 938
+    },
+    {
+      "epoch": 0.40560949298813376,
+      "grad_norm": 0.6079246401786804,
+      "learning_rate": 0.00016873315363881403,
+      "loss": 0.8868283629417419,
+      "step": 940
+    },
+    {
+      "epoch": 0.4064724919093851,
+      "grad_norm": 0.5326972603797913,
+      "learning_rate": 0.00016909254267744833,
+      "loss": 0.9938711524009705,
+      "step": 942
+    },
+    {
+      "epoch": 0.40733549083063647,
+      "grad_norm": 0.47754305601119995,
+      "learning_rate": 0.00016945193171608266,
+      "loss": 0.8280484676361084,
+      "step": 944
+    },
+    {
+      "epoch": 0.4081984897518878,
+      "grad_norm": 0.6683310270309448,
+      "learning_rate": 0.000169811320754717,
+      "loss": 1.089701533317566,
+      "step": 946
+    },
+    {
+      "epoch": 0.4090614886731392,
+      "grad_norm": 0.42798754572868347,
+      "learning_rate": 0.0001701707097933513,
+      "loss": 0.8535542488098145,
+      "step": 948
+    },
+    {
+      "epoch": 0.4099244875943905,
+      "grad_norm": 0.5999574065208435,
+      "learning_rate": 0.00017053009883198563,
+      "loss": 0.9039298295974731,
+      "step": 950
+    },
+    {
+      "epoch": 0.41078748651564184,
+      "grad_norm": 0.5752781629562378,
+      "learning_rate": 0.00017088948787061996,
+      "loss": 0.8786448240280151,
+      "step": 952
+    },
+    {
+      "epoch": 0.4116504854368932,
+      "grad_norm": 0.5121532678604126,
+      "learning_rate": 0.0001712488769092543,
+      "loss": 0.9206072688102722,
+      "step": 954
+    },
+    {
+      "epoch": 0.41251348435814456,
+      "grad_norm": 0.611078143119812,
+      "learning_rate": 0.0001716082659478886,
+      "loss": 0.9246986508369446,
+      "step": 956
+    },
+    {
+      "epoch": 0.4133764832793959,
+      "grad_norm": 0.5101020336151123,
+      "learning_rate": 0.00017196765498652292,
+      "loss": 0.9221894145011902,
+      "step": 958
+    },
+    {
+      "epoch": 0.41423948220064727,
+      "grad_norm": 0.5681450963020325,
+      "learning_rate": 0.00017232704402515725,
+      "loss": 0.9072799682617188,
+      "step": 960
+    },
+    {
+      "epoch": 0.41510248112189857,
+      "grad_norm": 0.47865498065948486,
+      "learning_rate": 0.00017268643306379155,
+      "loss": 0.9460896849632263,
+      "step": 962
+    },
+    {
+      "epoch": 0.4159654800431499,
+      "grad_norm": 0.49861401319503784,
+      "learning_rate": 0.00017304582210242588,
+      "loss": 0.9121519923210144,
+      "step": 964
+    },
+    {
+      "epoch": 0.4168284789644013,
+      "grad_norm": 0.43025892972946167,
+      "learning_rate": 0.0001734052111410602,
+      "loss": 0.8826848864555359,
+      "step": 966
+    },
+    {
+      "epoch": 0.41769147788565264,
+      "grad_norm": 0.4600491225719452,
+      "learning_rate": 0.00017376460017969454,
+      "loss": 0.8756251335144043,
+      "step": 968
+    },
+    {
+      "epoch": 0.418554476806904,
+      "grad_norm": 0.5297656059265137,
+      "learning_rate": 0.00017412398921832885,
+      "loss": 0.9171333312988281,
+      "step": 970
+    },
+    {
+      "epoch": 0.41941747572815535,
+      "grad_norm": 0.4906919002532959,
+      "learning_rate": 0.00017448337825696318,
+      "loss": 0.8887524008750916,
+      "step": 972
+    },
+    {
+      "epoch": 0.4202804746494067,
+      "grad_norm": 0.49263402819633484,
+      "learning_rate": 0.0001748427672955975,
+      "loss": 0.8345810174942017,
+      "step": 974
+    },
+    {
+      "epoch": 0.421143473570658,
+      "grad_norm": 0.5706565380096436,
+      "learning_rate": 0.0001752021563342318,
+      "loss": 0.968651294708252,
+      "step": 976
+    },
+    {
+      "epoch": 0.42200647249190937,
+      "grad_norm": 0.5269908308982849,
+      "learning_rate": 0.00017556154537286614,
+      "loss": 0.9729376435279846,
+      "step": 978
+    },
+    {
+      "epoch": 0.4228694714131607,
+      "grad_norm": 0.47058001160621643,
+      "learning_rate": 0.00017592093441150047,
+      "loss": 0.963884711265564,
+      "step": 980
+    },
+    {
+      "epoch": 0.4237324703344121,
+      "grad_norm": 0.5322962999343872,
+      "learning_rate": 0.0001762803234501348,
+      "loss": 0.8952447175979614,
+      "step": 982
+    },
+    {
+      "epoch": 0.42459546925566344,
+      "grad_norm": 0.5750975012779236,
+      "learning_rate": 0.0001766397124887691,
+      "loss": 0.8932783603668213,
+      "step": 984
+    },
+    {
+      "epoch": 0.4254584681769148,
+      "grad_norm": 0.5539655685424805,
+      "learning_rate": 0.00017699910152740343,
+      "loss": 0.916595458984375,
+      "step": 986
+    },
+    {
+      "epoch": 0.42632146709816615,
+      "grad_norm": 0.568000853061676,
+      "learning_rate": 0.00017735849056603776,
+      "loss": 0.9669626355171204,
+      "step": 988
+    },
+    {
+      "epoch": 0.42718446601941745,
+      "grad_norm": 0.6010684370994568,
+      "learning_rate": 0.00017771787960467206,
+      "loss": 1.0089105367660522,
+      "step": 990
+    },
+    {
+      "epoch": 0.4280474649406688,
+      "grad_norm": 0.6083462238311768,
+      "learning_rate": 0.0001780772686433064,
+      "loss": 0.9810921549797058,
+      "step": 992
+    },
+    {
+      "epoch": 0.42891046386192017,
+      "grad_norm": 0.5076655149459839,
+      "learning_rate": 0.0001784366576819407,
+      "loss": 0.9524372816085815,
+      "step": 994
+    },
+    {
+      "epoch": 0.4297734627831715,
+      "grad_norm": 0.5260922312736511,
+      "learning_rate": 0.00017879604672057503,
+      "loss": 0.881294846534729,
+      "step": 996
+    },
+    {
+      "epoch": 0.4306364617044229,
+      "grad_norm": 0.6130498051643372,
+      "learning_rate": 0.00017915543575920936,
+      "loss": 0.9138327836990356,
+      "step": 998
+    },
+    {
+      "epoch": 0.43149946062567424,
+      "grad_norm": 0.5346242785453796,
+      "learning_rate": 0.00017951482479784366,
+      "loss": 0.8861367106437683,
+      "step": 1000
+    },
+    {
+      "epoch": 0.43149946062567424,
+      "eval_loss": 0.9606748819351196,
+      "eval_runtime": 655.4358,
+      "eval_samples_per_second": 3.143,
+      "eval_steps_per_second": 3.143,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4323624595469256,
+      "grad_norm": 0.5977228879928589,
+      "learning_rate": 0.000179874213836478,
+      "loss": 0.8711628913879395,
+      "step": 1002
+    },
+    {
+      "epoch": 0.4332254584681769,
+      "grad_norm": 0.5547866821289062,
+      "learning_rate": 0.00018023360287511232,
+      "loss": 0.9393253326416016,
+      "step": 1004
+    },
+    {
+      "epoch": 0.43408845738942825,
+      "grad_norm": 0.536856472492218,
+      "learning_rate": 0.00018059299191374662,
+      "loss": 0.9486003518104553,
+      "step": 1006
+    },
+    {
+      "epoch": 0.4349514563106796,
+      "grad_norm": 0.4769814610481262,
+      "learning_rate": 0.00018095238095238095,
+      "loss": 0.9042052030563354,
+      "step": 1008
+    },
+    {
+      "epoch": 0.43581445523193096,
+      "grad_norm": 0.5554604530334473,
+      "learning_rate": 0.00018131176999101528,
+      "loss": 0.978546142578125,
+      "step": 1010
+    },
+    {
+      "epoch": 0.4366774541531823,
+      "grad_norm": 0.5112947225570679,
+      "learning_rate": 0.00018167115902964959,
+      "loss": 0.8382073640823364,
+      "step": 1012
+    },
+    {
+      "epoch": 0.4375404530744337,
+      "grad_norm": 0.45194941759109497,
+      "learning_rate": 0.00018203054806828392,
+      "loss": 0.8577026724815369,
+      "step": 1014
+    },
+    {
+      "epoch": 0.438403451995685,
+      "grad_norm": 0.5115043520927429,
+      "learning_rate": 0.00018238993710691825,
+      "loss": 0.8517863154411316,
+      "step": 1016
+    },
+    {
+      "epoch": 0.43926645091693634,
+      "grad_norm": 0.5485050082206726,
+      "learning_rate": 0.00018274932614555258,
+      "loss": 0.9597266912460327,
+      "step": 1018
+    },
+    {
+      "epoch": 0.4401294498381877,
+      "grad_norm": 0.5742959976196289,
+      "learning_rate": 0.00018310871518418688,
+      "loss": 1.0407187938690186,
+      "step": 1020
+    },
+    {
+      "epoch": 0.44099244875943905,
+      "grad_norm": 0.44870051741600037,
+      "learning_rate": 0.0001834681042228212,
+      "loss": 0.8696310520172119,
+      "step": 1022
+    },
+    {
+      "epoch": 0.4418554476806904,
+      "grad_norm": 0.5179623961448669,
+      "learning_rate": 0.00018382749326145554,
+      "loss": 0.9673634767532349,
+      "step": 1024
+    },
+    {
+      "epoch": 0.44271844660194176,
+      "grad_norm": 0.5404779314994812,
+      "learning_rate": 0.00018418688230008984,
+      "loss": 0.9596615433692932,
+      "step": 1026
+    },
+    {
+      "epoch": 0.4435814455231931,
+      "grad_norm": 0.47766315937042236,
+      "learning_rate": 0.00018454627133872417,
+      "loss": 0.8483878970146179,
+      "step": 1028
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.503380537033081,
+      "learning_rate": 0.0001849056603773585,
+      "loss": 0.9330979585647583,
+      "step": 1030
+    },
+    {
+      "epoch": 0.4453074433656958,
+      "grad_norm": 0.6129396557807922,
+      "learning_rate": 0.00018526504941599283,
+      "loss": 0.9341012239456177,
+      "step": 1032
+    },
+    {
+      "epoch": 0.44617044228694713,
+      "grad_norm": 0.4497876465320587,
+      "learning_rate": 0.00018562443845462713,
+      "loss": 0.9139068126678467,
+      "step": 1034
+    },
+    {
+      "epoch": 0.4470334412081985,
+      "grad_norm": 0.5369747281074524,
+      "learning_rate": 0.00018598382749326146,
+      "loss": 0.8874827027320862,
+      "step": 1036
+    },
+    {
+      "epoch": 0.44789644012944985,
+      "grad_norm": 0.5947322845458984,
+      "learning_rate": 0.0001863432165318958,
+      "loss": 0.9653725028038025,
+      "step": 1038
+    },
+    {
+      "epoch": 0.4487594390507012,
+      "grad_norm": 0.6649987101554871,
+      "learning_rate": 0.0001867026055705301,
+      "loss": 0.9553119540214539,
+      "step": 1040
+    },
+    {
+      "epoch": 0.44962243797195256,
+      "grad_norm": 0.5369387269020081,
+      "learning_rate": 0.00018706199460916443,
+      "loss": 0.904233992099762,
+      "step": 1042
+    },
+    {
+      "epoch": 0.45048543689320386,
+      "grad_norm": 0.4956842362880707,
+      "learning_rate": 0.00018742138364779876,
+      "loss": 0.8837952017784119,
+      "step": 1044
+    },
+    {
+      "epoch": 0.4513484358144552,
+      "grad_norm": 0.48045051097869873,
+      "learning_rate": 0.0001877807726864331,
+      "loss": 0.8964687585830688,
+      "step": 1046
+    },
+    {
+      "epoch": 0.4522114347357066,
+      "grad_norm": 0.4925530254840851,
+      "learning_rate": 0.0001881401617250674,
+      "loss": 0.9105878472328186,
+      "step": 1048
+    },
+    {
+      "epoch": 0.45307443365695793,
+      "grad_norm": 0.5131362080574036,
+      "learning_rate": 0.00018849955076370172,
+      "loss": 0.96272873878479,
+      "step": 1050
+    },
+    {
+      "epoch": 0.4539374325782093,
+      "grad_norm": 0.435739129781723,
+      "learning_rate": 0.00018885893980233605,
+      "loss": 0.8796783685684204,
+      "step": 1052
+    },
+    {
+      "epoch": 0.45480043149946064,
+      "grad_norm": 0.500938892364502,
+      "learning_rate": 0.00018921832884097035,
+      "loss": 0.9463814496994019,
+      "step": 1054
+    },
+    {
+      "epoch": 0.455663430420712,
+      "grad_norm": 0.4769900143146515,
+      "learning_rate": 0.00018957771787960468,
+      "loss": 0.9030335545539856,
+      "step": 1056
+    },
+    {
+      "epoch": 0.4565264293419633,
+      "grad_norm": 0.49585285782814026,
+      "learning_rate": 0.00018993710691823901,
+      "loss": 0.986995279788971,
+      "step": 1058
+    },
+    {
+      "epoch": 0.45738942826321466,
+      "grad_norm": 0.5875195264816284,
+      "learning_rate": 0.00019029649595687334,
+      "loss": 0.9297246932983398,
+      "step": 1060
+    },
+    {
+      "epoch": 0.458252427184466,
+      "grad_norm": 0.5552583932876587,
+      "learning_rate": 0.00019065588499550765,
+      "loss": 1.005869746208191,
+      "step": 1062
+    },
+    {
+      "epoch": 0.4591154261057174,
+      "grad_norm": 0.49282076954841614,
+      "learning_rate": 0.00019101527403414198,
+      "loss": 0.8949927091598511,
+      "step": 1064
+    },
+    {
+      "epoch": 0.45997842502696873,
+      "grad_norm": 0.4951777160167694,
+      "learning_rate": 0.0001913746630727763,
+      "loss": 0.9997886419296265,
+      "step": 1066
+    },
+    {
+      "epoch": 0.4608414239482201,
+      "grad_norm": 0.5154827237129211,
+      "learning_rate": 0.0001917340521114106,
+      "loss": 0.9532123804092407,
+      "step": 1068
+    },
+    {
+      "epoch": 0.4617044228694714,
+      "grad_norm": 0.5547500252723694,
+      "learning_rate": 0.00019209344115004494,
+      "loss": 0.8959843516349792,
+      "step": 1070
+    },
+    {
+      "epoch": 0.46256742179072274,
+      "grad_norm": 0.500188946723938,
+      "learning_rate": 0.00019245283018867927,
+      "loss": 0.8201484680175781,
+      "step": 1072
+    },
+    {
+      "epoch": 0.4634304207119741,
+      "grad_norm": 0.4181794822216034,
+      "learning_rate": 0.00019281221922731357,
+      "loss": 0.8255136609077454,
+      "step": 1074
+    },
+    {
+      "epoch": 0.46429341963322546,
+      "grad_norm": 0.5613874197006226,
+      "learning_rate": 0.0001931716082659479,
+      "loss": 0.896024763584137,
+      "step": 1076
+    },
+    {
+      "epoch": 0.4651564185544768,
+      "grad_norm": 0.5000972151756287,
+      "learning_rate": 0.0001935309973045822,
+      "loss": 0.8831873536109924,
+      "step": 1078
+    },
+    {
+      "epoch": 0.46601941747572817,
+      "grad_norm": 0.6321820616722107,
+      "learning_rate": 0.00019389038634321654,
+      "loss": 0.9787988662719727,
+      "step": 1080
+    },
+    {
+      "epoch": 0.4668824163969795,
+      "grad_norm": 0.4843652546405792,
+      "learning_rate": 0.00019424977538185087,
+      "loss": 0.933361828327179,
+      "step": 1082
+    },
+    {
+      "epoch": 0.46774541531823083,
+      "grad_norm": 0.537330150604248,
+      "learning_rate": 0.00019460916442048517,
+      "loss": 0.9046981334686279,
+      "step": 1084
+    },
+    {
+      "epoch": 0.4686084142394822,
+      "grad_norm": 0.5761371850967407,
+      "learning_rate": 0.0001949685534591195,
+      "loss": 0.9625781178474426,
+      "step": 1086
+    },
+    {
+      "epoch": 0.46947141316073354,
+      "grad_norm": 0.5209522843360901,
+      "learning_rate": 0.00019532794249775383,
+      "loss": 0.9280619025230408,
+      "step": 1088
+    },
+    {
+      "epoch": 0.4703344120819849,
+      "grad_norm": 0.5383933186531067,
+      "learning_rate": 0.00019568733153638813,
+      "loss": 0.8236247301101685,
+      "step": 1090
+    },
+    {
+      "epoch": 0.47119741100323626,
+      "grad_norm": 0.4994274377822876,
+      "learning_rate": 0.00019604672057502246,
+      "loss": 0.9404071569442749,
+      "step": 1092
+    },
+    {
+      "epoch": 0.4720604099244876,
+      "grad_norm": 0.5177807211875916,
+      "learning_rate": 0.0001964061096136568,
+      "loss": 0.8517536520957947,
+      "step": 1094
+    },
+    {
+      "epoch": 0.47292340884573897,
+      "grad_norm": 0.5374870896339417,
+      "learning_rate": 0.00019676549865229112,
+      "loss": 0.8214367032051086,
+      "step": 1096
+    },
+    {
+      "epoch": 0.47378640776699027,
+      "grad_norm": 0.5544074177742004,
+      "learning_rate": 0.00019712488769092542,
+      "loss": 1.016176700592041,
+      "step": 1098
+    },
+    {
+      "epoch": 0.4746494066882416,
+      "grad_norm": 0.5125867128372192,
+      "learning_rate": 0.00019748427672955975,
+      "loss": 0.8425421118736267,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4746494066882416,
+      "eval_loss": 0.944629430770874,
+      "eval_runtime": 649.9107,
+      "eval_samples_per_second": 3.17,
+      "eval_steps_per_second": 3.17,
+      "step": 1100
+    },
+    {
+      "epoch": 0.475512405609493,
+      "grad_norm": 0.5204418897628784,
+      "learning_rate": 0.00019784366576819408,
+      "loss": 0.9444556832313538,
+      "step": 1102
+    },
+    {
+      "epoch": 0.47637540453074434,
+      "grad_norm": 0.46085885167121887,
+      "learning_rate": 0.0001982030548068284,
+      "loss": 0.877082109451294,
+      "step": 1104
+    },
+    {
+      "epoch": 0.4772384034519957,
+      "grad_norm": 0.5269598960876465,
+      "learning_rate": 0.00019856244384546272,
+      "loss": 0.9214640259742737,
+      "step": 1106
+    },
+    {
+      "epoch": 0.47810140237324705,
+      "grad_norm": 0.4894753694534302,
+      "learning_rate": 0.00019892183288409705,
+      "loss": 0.8867175579071045,
+      "step": 1108
+    },
+    {
+      "epoch": 0.47896440129449835,
+      "grad_norm": 0.5204115509986877,
+      "learning_rate": 0.00019928122192273138,
+      "loss": 0.9641162753105164,
+      "step": 1110
+    },
+    {
+      "epoch": 0.4798274002157497,
+      "grad_norm": 0.6399031281471252,
+      "learning_rate": 0.00019964061096136568,
+      "loss": 1.0219199657440186,
+      "step": 1112
+    },
+    {
+      "epoch": 0.48069039913700107,
+      "grad_norm": 0.3979159891605377,
+      "learning_rate": 0.0002,
+      "loss": 0.8189998269081116,
+      "step": 1114
+    },
+    {
+      "epoch": 0.4815533980582524,
+      "grad_norm": 0.4782681465148926,
+      "learning_rate": 0.0001999999879427254,
+      "loss": 0.83241868019104,
+      "step": 1116
+    },
+    {
+      "epoch": 0.4824163969795038,
+      "grad_norm": 0.5235620141029358,
+      "learning_rate": 0.00019999995177090454,
+      "loss": 0.9371466636657715,
+      "step": 1118
+    },
+    {
+      "epoch": 0.48327939590075514,
+      "grad_norm": 0.4543023407459259,
+      "learning_rate": 0.00019999989148454606,
+      "loss": 0.7767758369445801,
+      "step": 1120
+    },
+    {
+      "epoch": 0.4841423948220065,
+      "grad_norm": 0.6191229820251465,
+      "learning_rate": 0.00019999980708366457,
+      "loss": 1.0103063583374023,
+      "step": 1122
+    },
+    {
+      "epoch": 0.4850053937432578,
+      "grad_norm": 0.45392486453056335,
+      "learning_rate": 0.00019999969856828042,
+      "loss": 0.8720875382423401,
+      "step": 1124
+    },
+    {
+      "epoch": 0.48586839266450915,
+      "grad_norm": 0.42748701572418213,
+      "learning_rate": 0.00019999956593841974,
+      "loss": 0.7859150171279907,
+      "step": 1126
+    },
+    {
+      "epoch": 0.4867313915857605,
+      "grad_norm": 0.4952569603919983,
+      "learning_rate": 0.00019999940919411454,
+      "loss": 0.9154419898986816,
+      "step": 1128
+    },
+    {
+      "epoch": 0.48759439050701187,
+      "grad_norm": 0.5522173047065735,
+      "learning_rate": 0.00019999922833540264,
+      "loss": 0.9076330065727234,
+      "step": 1130
+    },
+    {
+      "epoch": 0.4884573894282632,
+      "grad_norm": 0.5355855226516724,
+      "learning_rate": 0.00019999902336232758,
+      "loss": 0.8933543562889099,
+      "step": 1132
+    },
+    {
+      "epoch": 0.4893203883495146,
+      "grad_norm": 0.4613489508628845,
+      "learning_rate": 0.00019999879427493885,
+      "loss": 0.9160735607147217,
+      "step": 1134
+    },
+    {
+      "epoch": 0.49018338727076594,
+      "grad_norm": 0.4758962094783783,
+      "learning_rate": 0.0001999985410732917,
+      "loss": 0.8552446961402893,
+      "step": 1136
+    },
+    {
+      "epoch": 0.49104638619201724,
+      "grad_norm": 0.4549376964569092,
+      "learning_rate": 0.00019999826375744715,
+      "loss": 0.9979530572891235,
+      "step": 1138
+    },
+    {
+      "epoch": 0.4919093851132686,
+      "grad_norm": 0.4363284409046173,
+      "learning_rate": 0.0001999979623274721,
+      "loss": 0.9295380115509033,
+      "step": 1140
+    },
+    {
+      "epoch": 0.49277238403451995,
+      "grad_norm": 0.5090877413749695,
+      "learning_rate": 0.0001999976367834392,
+      "loss": 0.8737252950668335,
+      "step": 1142
+    },
+    {
+      "epoch": 0.4936353829557713,
+      "grad_norm": 0.45340779423713684,
+      "learning_rate": 0.000199997287125427,
+      "loss": 0.8312779068946838,
+      "step": 1144
+    },
+    {
+      "epoch": 0.49449838187702266,
+      "grad_norm": 0.4771472215652466,
+      "learning_rate": 0.0001999969133535198,
+      "loss": 0.9105207324028015,
+      "step": 1146
+    },
+    {
+      "epoch": 0.495361380798274,
+      "grad_norm": 0.5251384377479553,
+      "learning_rate": 0.00019999651546780773,
+      "loss": 0.8578172922134399,
+      "step": 1148
+    },
+    {
+      "epoch": 0.4962243797195254,
+      "grad_norm": 0.49128198623657227,
+      "learning_rate": 0.00019999609346838676,
+      "loss": 0.9193941950798035,
+      "step": 1150
+    },
+    {
+      "epoch": 0.4970873786407767,
+      "grad_norm": 0.5558596849441528,
+      "learning_rate": 0.0001999956473553586,
+      "loss": 0.9141314625740051,
+      "step": 1152
+    },
+    {
+      "epoch": 0.49795037756202803,
+      "grad_norm": 0.45872750878334045,
+      "learning_rate": 0.00019999517712883087,
+      "loss": 0.9058388471603394,
+      "step": 1154
+    },
+    {
+      "epoch": 0.4988133764832794,
+      "grad_norm": 0.4710173010826111,
+      "learning_rate": 0.00019999468278891698,
+      "loss": 0.8462487459182739,
+      "step": 1156
+    },
+    {
+      "epoch": 0.49967637540453075,
+      "grad_norm": 0.4805637001991272,
+      "learning_rate": 0.0001999941643357361,
+      "loss": 0.8960906863212585,
+      "step": 1158
+    },
+    {
+      "epoch": 0.5005393743257821,
+      "grad_norm": 0.5108052492141724,
+      "learning_rate": 0.00019999362176941325,
+      "loss": 0.9074980020523071,
+      "step": 1160
+    },
+    {
+      "epoch": 0.5014023732470334,
+      "grad_norm": 0.49572333693504333,
+      "learning_rate": 0.00019999305509007932,
+      "loss": 0.9710080623626709,
+      "step": 1162
+    },
+    {
+      "epoch": 0.5022653721682848,
+      "grad_norm": 0.5304561257362366,
+      "learning_rate": 0.0001999924642978709,
+      "loss": 0.8877825140953064,
+      "step": 1164
+    },
+    {
+      "epoch": 0.5031283710895361,
+      "grad_norm": 0.5007328391075134,
+      "learning_rate": 0.0001999918493929305,
+      "loss": 0.8955381512641907,
+      "step": 1166
+    },
+    {
+      "epoch": 0.5039913700107875,
+      "grad_norm": 0.569549024105072,
+      "learning_rate": 0.0001999912103754064,
+      "loss": 0.9478562474250793,
+      "step": 1168
+    },
+    {
+      "epoch": 0.5048543689320388,
+      "grad_norm": 0.5354957580566406,
+      "learning_rate": 0.00019999054724545264,
+      "loss": 0.9685383439064026,
+      "step": 1170
+    },
+    {
+      "epoch": 0.5057173678532901,
+      "grad_norm": 0.547788143157959,
+      "learning_rate": 0.00019998986000322917,
+      "loss": 0.9221975207328796,
+      "step": 1172
+    },
+    {
+      "epoch": 0.5065803667745415,
+      "grad_norm": 0.4919529855251312,
+      "learning_rate": 0.00019998914864890175,
+      "loss": 0.9104788303375244,
+      "step": 1174
+    },
+    {
+      "epoch": 0.5074433656957928,
+      "grad_norm": 0.5274141430854797,
+      "learning_rate": 0.00019998841318264187,
+      "loss": 0.9176050424575806,
+      "step": 1176
+    },
+    {
+      "epoch": 0.5083063646170443,
+      "grad_norm": 0.4257420301437378,
+      "learning_rate": 0.00019998765360462688,
+      "loss": 0.8389710187911987,
+      "step": 1178
+    },
+    {
+      "epoch": 0.5091693635382956,
+      "grad_norm": 0.4947778880596161,
+      "learning_rate": 0.00019998686991504002,
+      "loss": 1.0164397954940796,
+      "step": 1180
+    },
+    {
+      "epoch": 0.510032362459547,
+      "grad_norm": 0.5540821552276611,
+      "learning_rate": 0.00019998606211407016,
+      "loss": 0.9900994300842285,
+      "step": 1182
+    },
+    {
+      "epoch": 0.5108953613807983,
+      "grad_norm": 0.4793289601802826,
+      "learning_rate": 0.0001999852302019122,
+      "loss": 0.8797636032104492,
+      "step": 1184
+    },
+    {
+      "epoch": 0.5117583603020496,
+      "grad_norm": 0.47429659962654114,
+      "learning_rate": 0.00019998437417876672,
+      "loss": 0.96225905418396,
+      "step": 1186
+    },
+    {
+      "epoch": 0.512621359223301,
+      "grad_norm": 0.44918450713157654,
+      "learning_rate": 0.00019998349404484013,
+      "loss": 0.8604235649108887,
+      "step": 1188
+    },
+    {
+      "epoch": 0.5134843581445523,
+      "grad_norm": 0.566977858543396,
+      "learning_rate": 0.00019998258980034468,
+      "loss": 1.0325366258621216,
+      "step": 1190
+    },
+    {
+      "epoch": 0.5143473570658037,
+      "grad_norm": 0.4671999514102936,
+      "learning_rate": 0.00019998166144549843,
+      "loss": 0.7658900022506714,
+      "step": 1192
+    },
+    {
+      "epoch": 0.515210355987055,
+      "grad_norm": 0.42312702536582947,
+      "learning_rate": 0.00019998070898052521,
+      "loss": 0.9365432858467102,
+      "step": 1194
+    },
+    {
+      "epoch": 0.5160733549083064,
+      "grad_norm": 0.4652721881866455,
+      "learning_rate": 0.00019997973240565476,
+      "loss": 0.771016538143158,
+      "step": 1196
+    },
+    {
+      "epoch": 0.5169363538295577,
+      "grad_norm": 0.5048499703407288,
+      "learning_rate": 0.00019997873172112254,
+      "loss": 0.9123705625534058,
+      "step": 1198
+    },
+    {
+      "epoch": 0.517799352750809,
+      "grad_norm": 0.5446439981460571,
+      "learning_rate": 0.0001999777069271699,
+      "loss": 0.8975751399993896,
+      "step": 1200
+    },
+    {
+      "epoch": 0.517799352750809,
+      "eval_loss": 0.9344067573547363,
+      "eval_runtime": 658.6934,
+      "eval_samples_per_second": 3.127,
+      "eval_steps_per_second": 3.127,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5186623516720604,
+      "grad_norm": 0.5044088959693909,
+      "learning_rate": 0.0001999766580240439,
+      "loss": 0.89097660779953,
+      "step": 1202
+    },
+    {
+      "epoch": 0.5195253505933117,
+      "grad_norm": 0.4672294855117798,
+      "learning_rate": 0.00019997558501199753,
+      "loss": 0.9138525128364563,
+      "step": 1204
+    },
+    {
+      "epoch": 0.5203883495145631,
+      "grad_norm": 0.45749008655548096,
+      "learning_rate": 0.00019997448789128952,
+      "loss": 0.8946340680122375,
+      "step": 1206
+    },
+    {
+      "epoch": 0.5212513484358144,
+      "grad_norm": 0.4828707277774811,
+      "learning_rate": 0.00019997336666218447,
+      "loss": 0.8661436438560486,
+      "step": 1208
+    },
+    {
+      "epoch": 0.5221143473570659,
+      "grad_norm": 0.3975147008895874,
+      "learning_rate": 0.0001999722213249527,
+      "loss": 0.7684835195541382,
+      "step": 1210
+    },
+    {
+      "epoch": 0.5229773462783172,
+      "grad_norm": 0.5642077326774597,
+      "learning_rate": 0.00019997105187987045,
+      "loss": 0.9667536616325378,
+      "step": 1212
+    },
+    {
+      "epoch": 0.5238403451995685,
+      "grad_norm": 0.4907105565071106,
+      "learning_rate": 0.00019996985832721972,
+      "loss": 0.8679366707801819,
+      "step": 1214
+    },
+    {
+      "epoch": 0.5247033441208199,
+      "grad_norm": 0.46214789152145386,
+      "learning_rate": 0.0001999686406672883,
+      "loss": 0.8802784085273743,
+      "step": 1216
+    },
+    {
+      "epoch": 0.5255663430420712,
+      "grad_norm": 0.4355131685733795,
+      "learning_rate": 0.00019996739890036985,
+      "loss": 0.8493598103523254,
+      "step": 1218
+    },
+    {
+      "epoch": 0.5264293419633226,
+      "grad_norm": 0.4293915331363678,
+      "learning_rate": 0.0001999661330267638,
+      "loss": 0.8949980735778809,
+      "step": 1220
+    },
+    {
+      "epoch": 0.5272923408845739,
+      "grad_norm": 0.5452485680580139,
+      "learning_rate": 0.00019996484304677544,
+      "loss": 0.9497376680374146,
+      "step": 1222
+    },
+    {
+      "epoch": 0.5281553398058253,
+      "grad_norm": 0.45874500274658203,
+      "learning_rate": 0.00019996352896071583,
+      "loss": 0.9170818328857422,
+      "step": 1224
+    },
+    {
+      "epoch": 0.5290183387270766,
+      "grad_norm": 0.4414025843143463,
+      "learning_rate": 0.00019996219076890182,
+      "loss": 0.7557252645492554,
+      "step": 1226
+    },
+    {
+      "epoch": 0.5298813376483279,
+      "grad_norm": 0.4891829192638397,
+      "learning_rate": 0.0001999608284716562,
+      "loss": 0.848960816860199,
+      "step": 1228
+    },
+    {
+      "epoch": 0.5307443365695793,
+      "grad_norm": 0.5048345327377319,
+      "learning_rate": 0.00019995944206930734,
+      "loss": 0.9555954933166504,
+      "step": 1230
+    },
+    {
+      "epoch": 0.5316073354908306,
+      "grad_norm": 0.5006756782531738,
+      "learning_rate": 0.00019995803156218968,
+      "loss": 0.8080939054489136,
+      "step": 1232
+    },
+    {
+      "epoch": 0.532470334412082,
+      "grad_norm": 0.5422173738479614,
+      "learning_rate": 0.00019995659695064332,
+      "loss": 0.8638371825218201,
+      "step": 1234
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.4535163640975952,
+      "learning_rate": 0.0001999551382350142,
+      "loss": 0.889068067073822,
+      "step": 1236
+    },
+    {
+      "epoch": 0.5341963322545846,
+      "grad_norm": 0.4588642418384552,
+      "learning_rate": 0.00019995365541565412,
+      "loss": 0.8803121447563171,
+      "step": 1238
+    },
+    {
+      "epoch": 0.535059331175836,
+      "grad_norm": 0.49366191029548645,
+      "learning_rate": 0.00019995214849292064,
+      "loss": 0.9694926738739014,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5359223300970873,
+      "grad_norm": 0.41988301277160645,
+      "learning_rate": 0.0001999506174671771,
+      "loss": 0.8367960453033447,
+      "step": 1242
+    },
+    {
+      "epoch": 0.5367853290183388,
+      "grad_norm": 0.5242130160331726,
+      "learning_rate": 0.00019994906233879273,
+      "loss": 0.942340612411499,
+      "step": 1244
+    },
+    {
+      "epoch": 0.53764832793959,
+      "grad_norm": 0.4899834096431732,
+      "learning_rate": 0.00019994748310814256,
+      "loss": 0.8926790356636047,
+      "step": 1246
+    },
+    {
+      "epoch": 0.5385113268608415,
+      "grad_norm": 0.5496823787689209,
+      "learning_rate": 0.00019994587977560744,
+      "loss": 0.99891597032547,
+      "step": 1248
+    },
+    {
+      "epoch": 0.5393743257820928,
+      "grad_norm": 0.4497414231300354,
+      "learning_rate": 0.00019994425234157396,
+      "loss": 0.8873116970062256,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5402373247033441,
+      "grad_norm": 0.4256928563117981,
+      "learning_rate": 0.00019994260080643454,
+      "loss": 0.9041396975517273,
+      "step": 1252
+    },
+    {
+      "epoch": 0.5411003236245955,
+      "grad_norm": 0.36910608410835266,
+      "learning_rate": 0.00019994092517058753,
+      "loss": 0.7647561430931091,
+      "step": 1254
+    },
+    {
+      "epoch": 0.5419633225458468,
+      "grad_norm": 0.537584125995636,
+      "learning_rate": 0.0001999392254344369,
+      "loss": 0.8892287015914917,
+      "step": 1256
+    },
+    {
+      "epoch": 0.5428263214670982,
+      "grad_norm": 0.49463894963264465,
+      "learning_rate": 0.00019993750159839264,
+      "loss": 0.8638571500778198,
+      "step": 1258
+    },
+    {
+      "epoch": 0.5436893203883495,
+      "grad_norm": 0.5052056908607483,
+      "learning_rate": 0.00019993575366287036,
+      "loss": 0.8165372014045715,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5445523193096009,
+      "grad_norm": 0.47367510199546814,
+      "learning_rate": 0.0001999339816282916,
+      "loss": 0.9099977016448975,
+      "step": 1262
+    },
+    {
+      "epoch": 0.5454153182308522,
+      "grad_norm": 0.4600350558757782,
+      "learning_rate": 0.00019993218549508364,
+      "loss": 0.8557311296463013,
+      "step": 1264
+    },
+    {
+      "epoch": 0.5462783171521035,
+      "grad_norm": 0.5684534311294556,
+      "learning_rate": 0.0001999303652636797,
+      "loss": 0.9136497974395752,
+      "step": 1266
+    },
+    {
+      "epoch": 0.5471413160733549,
+      "grad_norm": 0.5151359438896179,
+      "learning_rate": 0.00019992852093451865,
+      "loss": 0.7906932830810547,
+      "step": 1268
+    },
+    {
+      "epoch": 0.5480043149946062,
+      "grad_norm": 0.48577409982681274,
+      "learning_rate": 0.00019992665250804525,
+      "loss": 0.9326766133308411,
+      "step": 1270
+    },
+    {
+      "epoch": 0.5488673139158576,
+      "grad_norm": 0.490531325340271,
+      "learning_rate": 0.00019992475998471004,
+      "loss": 0.9734495878219604,
+      "step": 1272
+    },
+    {
+      "epoch": 0.5497303128371089,
+      "grad_norm": 0.5092435479164124,
+      "learning_rate": 0.00019992284336496947,
+      "loss": 0.8728410005569458,
+      "step": 1274
+    },
+    {
+      "epoch": 0.5505933117583603,
+      "grad_norm": 0.3843296766281128,
+      "learning_rate": 0.00019992090264928566,
+      "loss": 0.7572637796401978,
+      "step": 1276
+    },
+    {
+      "epoch": 0.5514563106796116,
+      "grad_norm": 0.534304678440094,
+      "learning_rate": 0.00019991893783812662,
+      "loss": 0.8895323872566223,
+      "step": 1278
+    },
+    {
+      "epoch": 0.552319309600863,
+      "grad_norm": 0.4567227363586426,
+      "learning_rate": 0.00019991694893196614,
+      "loss": 0.9318088293075562,
+      "step": 1280
+    },
+    {
+      "epoch": 0.5531823085221144,
+      "grad_norm": 0.48464900255203247,
+      "learning_rate": 0.0001999149359312839,
+      "loss": 0.8541979789733887,
+      "step": 1282
+    },
+    {
+      "epoch": 0.5540453074433657,
+      "grad_norm": 0.5569567084312439,
+      "learning_rate": 0.00019991289883656524,
+      "loss": 0.977894127368927,
+      "step": 1284
+    },
+    {
+      "epoch": 0.5549083063646171,
+      "grad_norm": 0.4637227952480316,
+      "learning_rate": 0.00019991083764830145,
+      "loss": 0.8860608339309692,
+      "step": 1286
+    },
+    {
+      "epoch": 0.5557713052858684,
+      "grad_norm": 0.4096687436103821,
+      "learning_rate": 0.00019990875236698956,
+      "loss": 0.8429648876190186,
+      "step": 1288
+    },
+    {
+      "epoch": 0.5566343042071198,
+      "grad_norm": 0.5221695303916931,
+      "learning_rate": 0.00019990664299313242,
+      "loss": 0.8510909080505371,
+      "step": 1290
+    },
+    {
+      "epoch": 0.5574973031283711,
+      "grad_norm": 0.5155899524688721,
+      "learning_rate": 0.00019990450952723872,
+      "loss": 0.8971074223518372,
+      "step": 1292
+    },
+    {
+      "epoch": 0.5583603020496224,
+      "grad_norm": 0.5064809322357178,
+      "learning_rate": 0.0001999023519698229,
+      "loss": 0.9030373096466064,
+      "step": 1294
+    },
+    {
+      "epoch": 0.5592233009708738,
+      "grad_norm": 0.40551698207855225,
+      "learning_rate": 0.00019990017032140526,
+      "loss": 0.7866057753562927,
+      "step": 1296
+    },
+    {
+      "epoch": 0.5600862998921251,
+      "grad_norm": 0.5009430050849915,
+      "learning_rate": 0.00019989796458251194,
+      "loss": 0.9477730989456177,
+      "step": 1298
+    },
+    {
+      "epoch": 0.5609492988133765,
+      "grad_norm": 0.5192028880119324,
+      "learning_rate": 0.00019989573475367477,
+      "loss": 0.9206778407096863,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5609492988133765,
+      "eval_loss": 0.9177446365356445,
+      "eval_runtime": 665.3245,
+      "eval_samples_per_second": 3.096,
+      "eval_steps_per_second": 3.096,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5618122977346278,
+      "grad_norm": 0.5580230951309204,
+      "learning_rate": 0.00019989348083543148,
+      "loss": 0.9516512155532837,
+      "step": 1302
+    },
+    {
+      "epoch": 0.5626752966558792,
+      "grad_norm": 0.4151005744934082,
+      "learning_rate": 0.00019989120282832564,
+      "loss": 0.7725991606712341,
+      "step": 1304
+    },
+    {
+      "epoch": 0.5635382955771305,
+      "grad_norm": 0.56330406665802,
+      "learning_rate": 0.00019988890073290656,
+      "loss": 0.9241501688957214,
+      "step": 1306
+    },
+    {
+      "epoch": 0.5644012944983818,
+      "grad_norm": 0.44836440682411194,
+      "learning_rate": 0.00019988657454972936,
+      "loss": 0.8351686000823975,
+      "step": 1308
+    },
+    {
+      "epoch": 0.5652642934196332,
+      "grad_norm": 0.5414754152297974,
+      "learning_rate": 0.00019988422427935496,
+      "loss": 0.9033217430114746,
+      "step": 1310
+    },
+    {
+      "epoch": 0.5661272923408845,
+      "grad_norm": 0.5283750891685486,
+      "learning_rate": 0.0001998818499223502,
+      "loss": 0.8885331153869629,
+      "step": 1312
+    },
+    {
+      "epoch": 0.566990291262136,
+      "grad_norm": 0.45846256613731384,
+      "learning_rate": 0.00019987945147928758,
+      "loss": 0.8359912037849426,
+      "step": 1314
+    },
+    {
+      "epoch": 0.5678532901833873,
+      "grad_norm": 0.44439879059791565,
+      "learning_rate": 0.0001998770289507455,
+      "loss": 0.8327895402908325,
+      "step": 1316
+    },
+    {
+      "epoch": 0.5687162891046387,
+      "grad_norm": 0.5491341948509216,
+      "learning_rate": 0.00019987458233730813,
+      "loss": 0.9354757070541382,
+      "step": 1318
+    },
+    {
+      "epoch": 0.56957928802589,
+      "grad_norm": 0.5502263307571411,
+      "learning_rate": 0.00019987211163956548,
+      "loss": 0.944054901599884,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5704422869471413,
+      "grad_norm": 0.47165682911872864,
+      "learning_rate": 0.00019986961685811334,
+      "loss": 0.9515072107315063,
+      "step": 1322
+    },
+    {
+      "epoch": 0.5713052858683927,
+      "grad_norm": 0.5136987566947937,
+      "learning_rate": 0.0001998670979935533,
+      "loss": 0.9455493688583374,
+      "step": 1324
+    },
+    {
+      "epoch": 0.572168284789644,
+      "grad_norm": 0.4822693169116974,
+      "learning_rate": 0.00019986455504649277,
+      "loss": 0.8626728057861328,
+      "step": 1326
+    },
+    {
+      "epoch": 0.5730312837108954,
+      "grad_norm": 0.4639468193054199,
+      "learning_rate": 0.000199861988017545,
+      "loss": 0.8857194781303406,
+      "step": 1328
+    },
+    {
+      "epoch": 0.5738942826321467,
+      "grad_norm": 0.5224950313568115,
+      "learning_rate": 0.00019985939690732898,
+      "loss": 0.9198446273803711,
+      "step": 1330
+    },
+    {
+      "epoch": 0.574757281553398,
+      "grad_norm": 0.47504499554634094,
+      "learning_rate": 0.00019985678171646954,
+      "loss": 0.8785439133644104,
+      "step": 1332
+    },
+    {
+      "epoch": 0.5756202804746494,
+      "grad_norm": 0.5022051930427551,
+      "learning_rate": 0.0001998541424455974,
+      "loss": 0.9593754410743713,
+      "step": 1334
+    },
+    {
+      "epoch": 0.5764832793959007,
+      "grad_norm": 0.4572875201702118,
+      "learning_rate": 0.00019985147909534897,
+      "loss": 0.986197292804718,
+      "step": 1336
+    },
+    {
+      "epoch": 0.5773462783171521,
+      "grad_norm": 0.5153827667236328,
+      "learning_rate": 0.00019984879166636644,
+      "loss": 0.9163863658905029,
+      "step": 1338
+    },
+    {
+      "epoch": 0.5782092772384034,
+      "grad_norm": 0.4813650846481323,
+      "learning_rate": 0.00019984608015929792,
+      "loss": 0.8815995454788208,
+      "step": 1340
+    },
+    {
+      "epoch": 0.5790722761596548,
+      "grad_norm": 0.4319819211959839,
+      "learning_rate": 0.0001998433445747973,
+      "loss": 0.857044517993927,
+      "step": 1342
+    },
+    {
+      "epoch": 0.5799352750809061,
+      "grad_norm": 0.5128870010375977,
+      "learning_rate": 0.00019984058491352423,
+      "loss": 0.8939256072044373,
+      "step": 1344
+    },
+    {
+      "epoch": 0.5807982740021574,
+      "grad_norm": 0.41450315713882446,
+      "learning_rate": 0.0001998378011761442,
+      "loss": 0.9267327785491943,
+      "step": 1346
+    },
+    {
+      "epoch": 0.5816612729234089,
+      "grad_norm": 0.42916348576545715,
+      "learning_rate": 0.00019983499336332844,
+      "loss": 0.8494639992713928,
+      "step": 1348
+    },
+    {
+      "epoch": 0.5825242718446602,
+      "grad_norm": 0.43995746970176697,
+      "learning_rate": 0.00019983216147575412,
+      "loss": 0.9720427989959717,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5833872707659116,
+      "grad_norm": 0.5063773989677429,
+      "learning_rate": 0.00019982930551410411,
+      "loss": 0.9400854706764221,
+      "step": 1352
+    },
+    {
+      "epoch": 0.5842502696871629,
+      "grad_norm": 0.5029586553573608,
+      "learning_rate": 0.0001998264254790671,
+      "loss": 0.8657845258712769,
+      "step": 1354
+    },
+    {
+      "epoch": 0.5851132686084143,
+      "grad_norm": 0.45519232749938965,
+      "learning_rate": 0.00019982352137133764,
+      "loss": 0.8593506813049316,
+      "step": 1356
+    },
+    {
+      "epoch": 0.5859762675296656,
+      "grad_norm": 0.49116215109825134,
+      "learning_rate": 0.000199820593191616,
+      "loss": 0.8658114671707153,
+      "step": 1358
+    },
+    {
+      "epoch": 0.5868392664509169,
+      "grad_norm": 0.45347318053245544,
+      "learning_rate": 0.00019981764094060826,
+      "loss": 0.8044605255126953,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5877022653721683,
+      "grad_norm": 0.5191754698753357,
+      "learning_rate": 0.00019981466461902643,
+      "loss": 0.9176861047744751,
+      "step": 1362
+    },
+    {
+      "epoch": 0.5885652642934196,
+      "grad_norm": 0.4791528284549713,
+      "learning_rate": 0.00019981166422758818,
+      "loss": 0.8453370928764343,
+      "step": 1364
+    },
+    {
+      "epoch": 0.589428263214671,
+      "grad_norm": 0.5105116367340088,
+      "learning_rate": 0.00019980863976701705,
+      "loss": 0.9343777298927307,
+      "step": 1366
+    },
+    {
+      "epoch": 0.5902912621359223,
+      "grad_norm": 0.44593656063079834,
+      "learning_rate": 0.00019980559123804236,
+      "loss": 0.8950760960578918,
+      "step": 1368
+    },
+    {
+      "epoch": 0.5911542610571737,
+      "grad_norm": 0.4375658631324768,
+      "learning_rate": 0.0001998025186413993,
+      "loss": 0.8613521456718445,
+      "step": 1370
+    },
+    {
+      "epoch": 0.592017259978425,
+      "grad_norm": 0.5138815641403198,
+      "learning_rate": 0.00019979942197782878,
+      "loss": 0.8982083201408386,
+      "step": 1372
+    },
+    {
+      "epoch": 0.5928802588996763,
+      "grad_norm": 0.45473602414131165,
+      "learning_rate": 0.00019979630124807753,
+      "loss": 0.9372450709342957,
+      "step": 1374
+    },
+    {
+      "epoch": 0.5937432578209277,
+      "grad_norm": 0.4961191713809967,
+      "learning_rate": 0.00019979315645289814,
+      "loss": 0.8758652806282043,
+      "step": 1376
+    },
+    {
+      "epoch": 0.594606256742179,
+      "grad_norm": 0.5672827363014221,
+      "learning_rate": 0.00019978998759304895,
+      "loss": 0.9852207899093628,
+      "step": 1378
+    },
+    {
+      "epoch": 0.5954692556634305,
+      "grad_norm": 0.44907906651496887,
+      "learning_rate": 0.00019978679466929407,
+      "loss": 0.8451287746429443,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5963322545846818,
+      "grad_norm": 0.4759652316570282,
+      "learning_rate": 0.00019978357768240352,
+      "loss": 0.8381558656692505,
+      "step": 1382
+    },
+    {
+      "epoch": 0.5971952535059332,
+      "grad_norm": 0.4936048686504364,
+      "learning_rate": 0.00019978033663315304,
+      "loss": 0.8820816874504089,
+      "step": 1384
+    },
+    {
+      "epoch": 0.5980582524271845,
+      "grad_norm": 0.44983741641044617,
+      "learning_rate": 0.00019977707152232416,
+      "loss": 0.9156787991523743,
+      "step": 1386
+    },
+    {
+      "epoch": 0.5989212513484358,
+      "grad_norm": 0.45198705792427063,
+      "learning_rate": 0.0001997737823507043,
+      "loss": 0.8285194039344788,
+      "step": 1388
+    },
+    {
+      "epoch": 0.5997842502696872,
+      "grad_norm": 0.45788463950157166,
+      "learning_rate": 0.00019977046911908664,
+      "loss": 0.8109505772590637,
+      "step": 1390
+    },
+    {
+      "epoch": 0.6006472491909385,
+      "grad_norm": 0.4795142412185669,
+      "learning_rate": 0.0001997671318282701,
+      "loss": 0.8285947442054749,
+      "step": 1392
+    },
+    {
+      "epoch": 0.6015102481121899,
+      "grad_norm": 0.5026728510856628,
+      "learning_rate": 0.00019976377047905945,
+      "loss": 0.9497535228729248,
+      "step": 1394
+    },
+    {
+      "epoch": 0.6023732470334412,
+      "grad_norm": 0.4994853734970093,
+      "learning_rate": 0.0001997603850722653,
+      "loss": 0.9171916246414185,
+      "step": 1396
+    },
+    {
+      "epoch": 0.6032362459546926,
+      "grad_norm": 0.4789866507053375,
+      "learning_rate": 0.00019975697560870403,
+      "loss": 0.7894434928894043,
+      "step": 1398
+    },
+    {
+      "epoch": 0.6040992448759439,
+      "grad_norm": 0.42282742261886597,
+      "learning_rate": 0.0001997535420891978,
+      "loss": 0.8942429423332214,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6040992448759439,
+      "eval_loss": 0.9080492854118347,
+      "eval_runtime": 661.4597,
+      "eval_samples_per_second": 3.114,
+      "eval_steps_per_second": 3.114,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6049622437971952,
+      "grad_norm": 0.5789905190467834,
+      "learning_rate": 0.00019975008451457454,
+      "loss": 0.8938372731208801,
+      "step": 1402
+    },
+    {
+      "epoch": 0.6058252427184466,
+      "grad_norm": 0.46121683716773987,
+      "learning_rate": 0.00019974660288566814,
+      "loss": 0.8746235370635986,
+      "step": 1404
+    },
+    {
+      "epoch": 0.6066882416396979,
+      "grad_norm": 0.5195551514625549,
+      "learning_rate": 0.00019974309720331807,
+      "loss": 0.8650617003440857,
+      "step": 1406
+    },
+    {
+      "epoch": 0.6075512405609493,
+      "grad_norm": 0.46930259466171265,
+      "learning_rate": 0.00019973956746836976,
+      "loss": 0.8853039145469666,
+      "step": 1408
+    },
+    {
+      "epoch": 0.6084142394822006,
+      "grad_norm": 0.40869632363319397,
+      "learning_rate": 0.0001997360136816744,
+      "loss": 0.7865594029426575,
+      "step": 1410
+    },
+    {
+      "epoch": 0.609277238403452,
+      "grad_norm": 0.5398361086845398,
+      "learning_rate": 0.00019973243584408895,
+      "loss": 0.907535970211029,
+      "step": 1412
+    },
+    {
+      "epoch": 0.6101402373247033,
+      "grad_norm": 0.5110154747962952,
+      "learning_rate": 0.00019972883395647615,
+      "loss": 0.8682730197906494,
+      "step": 1414
+    },
+    {
+      "epoch": 0.6110032362459547,
+      "grad_norm": 0.44484639167785645,
+      "learning_rate": 0.00019972520801970467,
+      "loss": 0.8786011338233948,
+      "step": 1416
+    },
+    {
+      "epoch": 0.6118662351672061,
+      "grad_norm": 0.4768071472644806,
+      "learning_rate": 0.0001997215580346488,
+      "loss": 0.9021878242492676,
+      "step": 1418
+    },
+    {
+      "epoch": 0.6127292340884574,
+      "grad_norm": 0.43265241384506226,
+      "learning_rate": 0.0001997178840021888,
+      "loss": 0.7737482786178589,
+      "step": 1420
+    },
+    {
+      "epoch": 0.6135922330097088,
+      "grad_norm": 0.525692343711853,
+      "learning_rate": 0.0001997141859232106,
+      "loss": 0.876280665397644,
+      "step": 1422
+    },
+    {
+      "epoch": 0.6144552319309601,
+      "grad_norm": 0.48206865787506104,
+      "learning_rate": 0.00019971046379860594,
+      "loss": 0.8503577709197998,
+      "step": 1424
+    },
+    {
+      "epoch": 0.6153182308522115,
+      "grad_norm": 0.6032769680023193,
+      "learning_rate": 0.00019970671762927246,
+      "loss": 0.9459730982780457,
+      "step": 1426
+    },
+    {
+      "epoch": 0.6161812297734628,
+      "grad_norm": 0.4491981863975525,
+      "learning_rate": 0.0001997029474161135,
+      "loss": 0.8836647868156433,
+      "step": 1428
+    },
+    {
+      "epoch": 0.6170442286947141,
+      "grad_norm": 0.47503358125686646,
+      "learning_rate": 0.00019969915316003824,
+      "loss": 0.8614388108253479,
+      "step": 1430
+    },
+    {
+      "epoch": 0.6179072276159655,
+      "grad_norm": 0.44801047444343567,
+      "learning_rate": 0.00019969533486196162,
+      "loss": 0.8420360684394836,
+      "step": 1432
+    },
+    {
+      "epoch": 0.6187702265372168,
+      "grad_norm": 0.45057111978530884,
+      "learning_rate": 0.00019969149252280446,
+      "loss": 0.8256269693374634,
+      "step": 1434
+    },
+    {
+      "epoch": 0.6196332254584682,
+      "grad_norm": 0.4589645266532898,
+      "learning_rate": 0.00019968762614349327,
+      "loss": 0.9130199551582336,
+      "step": 1436
+    },
+    {
+      "epoch": 0.6204962243797195,
+      "grad_norm": 0.48914027214050293,
+      "learning_rate": 0.00019968373572496045,
+      "loss": 0.74083012342453,
+      "step": 1438
+    },
+    {
+      "epoch": 0.6213592233009708,
+      "grad_norm": 0.4582098424434662,
+      "learning_rate": 0.00019967982126814412,
+      "loss": 0.8538379669189453,
+      "step": 1440
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.48722779750823975,
+      "learning_rate": 0.00019967588277398823,
+      "loss": 0.8780114054679871,
+      "step": 1442
+    },
+    {
+      "epoch": 0.6230852211434735,
+      "grad_norm": 0.4291327893733978,
+      "learning_rate": 0.00019967192024344254,
+      "loss": 0.8341028690338135,
+      "step": 1444
+    },
+    {
+      "epoch": 0.623948220064725,
+      "grad_norm": 0.4773139953613281,
+      "learning_rate": 0.00019966793367746265,
+      "loss": 0.8651667237281799,
+      "step": 1446
+    },
+    {
+      "epoch": 0.6248112189859762,
+      "grad_norm": 0.45556166768074036,
+      "learning_rate": 0.00019966392307700986,
+      "loss": 0.8339929580688477,
+      "step": 1448
+    },
+    {
+      "epoch": 0.6256742179072277,
+      "grad_norm": 0.5126671195030212,
+      "learning_rate": 0.00019965988844305129,
+      "loss": 0.9129340052604675,
+      "step": 1450
+    },
+    {
+      "epoch": 0.626537216828479,
+      "grad_norm": 0.6067109704017639,
+      "learning_rate": 0.00019965582977655988,
+      "loss": 0.9057610034942627,
+      "step": 1452
+    },
+    {
+      "epoch": 0.6274002157497303,
+      "grad_norm": 0.46425968408584595,
+      "learning_rate": 0.00019965174707851438,
+      "loss": 0.874100387096405,
+      "step": 1454
+    },
+    {
+      "epoch": 0.6282632146709817,
+      "grad_norm": 0.481077641248703,
+      "learning_rate": 0.0001996476403498993,
+      "loss": 0.915635347366333,
+      "step": 1456
+    },
+    {
+      "epoch": 0.629126213592233,
+      "grad_norm": 0.47299909591674805,
+      "learning_rate": 0.000199643509591705,
+      "loss": 0.9059650301933289,
+      "step": 1458
+    },
+    {
+      "epoch": 0.6299892125134844,
+      "grad_norm": 0.48924630880355835,
+      "learning_rate": 0.00019963935480492753,
+      "loss": 0.9775188565254211,
+      "step": 1460
+    },
+    {
+      "epoch": 0.6308522114347357,
+      "grad_norm": 0.4407665431499481,
+      "learning_rate": 0.0001996351759905688,
+      "loss": 0.8950685858726501,
+      "step": 1462
+    },
+    {
+      "epoch": 0.6317152103559871,
+      "grad_norm": 0.5018318295478821,
+      "learning_rate": 0.00019963097314963657,
+      "loss": 0.8532119989395142,
+      "step": 1464
+    },
+    {
+      "epoch": 0.6325782092772384,
+      "grad_norm": 0.43245720863342285,
+      "learning_rate": 0.0001996267462831443,
+      "loss": 0.7775963544845581,
+      "step": 1466
+    },
+    {
+      "epoch": 0.6334412081984897,
+      "grad_norm": 0.5028865337371826,
+      "learning_rate": 0.00019962249539211125,
+      "loss": 0.8315839767456055,
+      "step": 1468
+    },
+    {
+      "epoch": 0.6343042071197411,
+      "grad_norm": 0.4697185754776001,
+      "learning_rate": 0.0001996182204775626,
+      "loss": 0.849076509475708,
+      "step": 1470
+    },
+    {
+      "epoch": 0.6351672060409924,
+      "grad_norm": 0.46725034713745117,
+      "learning_rate": 0.00019961392154052912,
+      "loss": 0.8828577995300293,
+      "step": 1472
+    },
+    {
+      "epoch": 0.6360302049622438,
+      "grad_norm": 0.4301203489303589,
+      "learning_rate": 0.00019960959858204754,
+      "loss": 0.850115954875946,
+      "step": 1474
+    },
+    {
+      "epoch": 0.6368932038834951,
+      "grad_norm": 0.46635881066322327,
+      "learning_rate": 0.0001996052516031603,
+      "loss": 0.7912618517875671,
+      "step": 1476
+    },
+    {
+      "epoch": 0.6377562028047465,
+      "grad_norm": 0.44143620133399963,
+      "learning_rate": 0.00019960088060491565,
+      "loss": 0.9072504639625549,
+      "step": 1478
+    },
+    {
+      "epoch": 0.6386192017259978,
+      "grad_norm": 0.47458893060684204,
+      "learning_rate": 0.00019959648558836763,
+      "loss": 0.8976638317108154,
+      "step": 1480
+    },
+    {
+      "epoch": 0.6394822006472491,
+      "grad_norm": 0.4596816897392273,
+      "learning_rate": 0.00019959206655457612,
+      "loss": 0.8142043352127075,
+      "step": 1482
+    },
+    {
+      "epoch": 0.6403451995685006,
+      "grad_norm": 0.4839977025985718,
+      "learning_rate": 0.0001995876235046067,
+      "loss": 0.860643744468689,
+      "step": 1484
+    },
+    {
+      "epoch": 0.6412081984897519,
+      "grad_norm": 0.3542814552783966,
+      "learning_rate": 0.00019958315643953085,
+      "loss": 0.7586524486541748,
+      "step": 1486
+    },
+    {
+      "epoch": 0.6420711974110033,
+      "grad_norm": 0.5423269271850586,
+      "learning_rate": 0.00019957866536042572,
+      "loss": 0.9353570342063904,
+      "step": 1488
+    },
+    {
+      "epoch": 0.6429341963322546,
+      "grad_norm": 0.4580909013748169,
+      "learning_rate": 0.00019957415026837437,
+      "loss": 0.9919291138648987,
+      "step": 1490
+    },
+    {
+      "epoch": 0.643797195253506,
+      "grad_norm": 0.4211732745170593,
+      "learning_rate": 0.00019956961116446555,
+      "loss": 0.8720914125442505,
+      "step": 1492
+    },
+    {
+      "epoch": 0.6446601941747573,
+      "grad_norm": 0.4583161175251007,
+      "learning_rate": 0.00019956504804979384,
+      "loss": 0.8661212921142578,
+      "step": 1494
+    },
+    {
+      "epoch": 0.6455231930960086,
+      "grad_norm": 0.4359884262084961,
+      "learning_rate": 0.00019956046092545966,
+      "loss": 0.8170996308326721,
+      "step": 1496
+    },
+    {
+      "epoch": 0.64638619201726,
+      "grad_norm": 0.4642556607723236,
+      "learning_rate": 0.00019955584979256913,
+      "loss": 0.8607422113418579,
+      "step": 1498
+    },
+    {
+      "epoch": 0.6472491909385113,
+      "grad_norm": 0.4496007561683655,
+      "learning_rate": 0.00019955121465223426,
+      "loss": 0.837529182434082,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6472491909385113,
+      "eval_loss": 0.8972997665405273,
+      "eval_runtime": 649.796,
+      "eval_samples_per_second": 3.17,
+      "eval_steps_per_second": 3.17,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6481121898597627,
+      "grad_norm": 0.48363205790519714,
+      "learning_rate": 0.0001995465555055727,
+      "loss": 0.9355250000953674,
+      "step": 1502
+    },
+    {
+      "epoch": 0.648975188781014,
+      "grad_norm": 0.44681695103645325,
+      "learning_rate": 0.0001995418723537081,
+      "loss": 0.8286949396133423,
+      "step": 1504
+    },
+    {
+      "epoch": 0.6498381877022654,
+      "grad_norm": 0.5110394358634949,
+      "learning_rate": 0.00019953716519776967,
+      "loss": 0.890398383140564,
+      "step": 1506
+    },
+    {
+      "epoch": 0.6507011866235167,
+      "grad_norm": 0.4353160262107849,
+      "learning_rate": 0.00019953243403889257,
+      "loss": 0.8117311000823975,
+      "step": 1508
+    },
+    {
+      "epoch": 0.651564185544768,
+      "grad_norm": 0.4731789231300354,
+      "learning_rate": 0.0001995276788782177,
+      "loss": 0.8255904316902161,
+      "step": 1510
+    },
+    {
+      "epoch": 0.6524271844660194,
+      "grad_norm": 0.5447185039520264,
+      "learning_rate": 0.00019952289971689177,
+      "loss": 0.9371263384819031,
+      "step": 1512
+    },
+    {
+      "epoch": 0.6532901833872707,
+      "grad_norm": 0.47616517543792725,
+      "learning_rate": 0.0001995180965560672,
+      "loss": 0.8532910943031311,
+      "step": 1514
+    },
+    {
+      "epoch": 0.6541531823085222,
+      "grad_norm": 0.4412213861942291,
+      "learning_rate": 0.0001995132693969023,
+      "loss": 0.8799141645431519,
+      "step": 1516
+    },
+    {
+      "epoch": 0.6550161812297735,
+      "grad_norm": 0.469911128282547,
+      "learning_rate": 0.00019950841824056107,
+      "loss": 0.8395764827728271,
+      "step": 1518
+    },
+    {
+      "epoch": 0.6558791801510249,
+      "grad_norm": 0.5236243009567261,
+      "learning_rate": 0.00019950354308821336,
+      "loss": 0.9556697010993958,
+      "step": 1520
+    },
+    {
+      "epoch": 0.6567421790722762,
+      "grad_norm": 0.4441990256309509,
+      "learning_rate": 0.00019949864394103482,
+      "loss": 0.8524283170700073,
+      "step": 1522
+    },
+    {
+      "epoch": 0.6576051779935275,
+      "grad_norm": 0.4173077940940857,
+      "learning_rate": 0.00019949372080020682,
+      "loss": 0.9213772416114807,
+      "step": 1524
+    },
+    {
+      "epoch": 0.6584681769147789,
+      "grad_norm": 0.4404120147228241,
+      "learning_rate": 0.00019948877366691658,
+      "loss": 0.9236897230148315,
+      "step": 1526
+    },
+    {
+      "epoch": 0.6593311758360302,
+      "grad_norm": 0.4586230516433716,
+      "learning_rate": 0.00019948380254235706,
+      "loss": 0.8373230695724487,
+      "step": 1528
+    },
+    {
+      "epoch": 0.6601941747572816,
+      "grad_norm": 0.4136028587818146,
+      "learning_rate": 0.00019947880742772703,
+      "loss": 0.8256528377532959,
+      "step": 1530
+    },
+    {
+      "epoch": 0.6610571736785329,
+      "grad_norm": 0.5007129907608032,
+      "learning_rate": 0.00019947378832423107,
+      "loss": 0.8580789566040039,
+      "step": 1532
+    },
+    {
+      "epoch": 0.6619201725997842,
+      "grad_norm": 0.39050203561782837,
+      "learning_rate": 0.00019946874523307947,
+      "loss": 0.7647744417190552,
+      "step": 1534
+    },
+    {
+      "epoch": 0.6627831715210356,
+      "grad_norm": 0.4640588164329529,
+      "learning_rate": 0.00019946367815548835,
+      "loss": 0.9042545557022095,
+      "step": 1536
+    },
+    {
+      "epoch": 0.6636461704422869,
+      "grad_norm": 0.5304957032203674,
+      "learning_rate": 0.00019945858709267963,
+      "loss": 0.9114110469818115,
+      "step": 1538
+    },
+    {
+      "epoch": 0.6645091693635383,
+      "grad_norm": 0.5426004528999329,
+      "learning_rate": 0.000199453472045881,
+      "loss": 0.8239460587501526,
+      "step": 1540
+    },
+    {
+      "epoch": 0.6653721682847896,
+      "grad_norm": 0.44893568754196167,
+      "learning_rate": 0.00019944833301632593,
+      "loss": 0.8091367483139038,
+      "step": 1542
+    },
+    {
+      "epoch": 0.666235167206041,
+      "grad_norm": 0.4294016361236572,
+      "learning_rate": 0.00019944317000525366,
+      "loss": 0.9202280640602112,
+      "step": 1544
+    },
+    {
+      "epoch": 0.6670981661272923,
+      "grad_norm": 0.449633926153183,
+      "learning_rate": 0.00019943798301390927,
+      "loss": 0.8884767889976501,
+      "step": 1546
+    },
+    {
+      "epoch": 0.6679611650485436,
+      "grad_norm": 0.4516827166080475,
+      "learning_rate": 0.0001994327720435435,
+      "loss": 0.8390879034996033,
+      "step": 1548
+    },
+    {
+      "epoch": 0.668824163969795,
+      "grad_norm": 0.422270268201828,
+      "learning_rate": 0.000199427537095413,
+      "loss": 0.7388033270835876,
+      "step": 1550
+    },
+    {
+      "epoch": 0.6696871628910464,
+      "grad_norm": 0.580563485622406,
+      "learning_rate": 0.00019942227817078015,
+      "loss": 0.9268350601196289,
+      "step": 1552
+    },
+    {
+      "epoch": 0.6705501618122978,
+      "grad_norm": 0.4436347782611847,
+      "learning_rate": 0.00019941699527091316,
+      "loss": 0.7978561520576477,
+      "step": 1554
+    },
+    {
+      "epoch": 0.6714131607335491,
+      "grad_norm": 0.4149787127971649,
+      "learning_rate": 0.0001994116883970859,
+      "loss": 0.8229286670684814,
+      "step": 1556
+    },
+    {
+      "epoch": 0.6722761596548005,
+      "grad_norm": 0.49915504455566406,
+      "learning_rate": 0.00019940635755057813,
+      "loss": 0.8554545640945435,
+      "step": 1558
+    },
+    {
+      "epoch": 0.6731391585760518,
+      "grad_norm": 0.45326656103134155,
+      "learning_rate": 0.00019940100273267537,
+      "loss": 0.9135572910308838,
+      "step": 1560
+    },
+    {
+      "epoch": 0.6740021574973031,
+      "grad_norm": 0.48639237880706787,
+      "learning_rate": 0.0001993956239446689,
+      "loss": 0.7769742012023926,
+      "step": 1562
+    },
+    {
+      "epoch": 0.6748651564185545,
+      "grad_norm": 0.5072791576385498,
+      "learning_rate": 0.0001993902211878558,
+      "loss": 0.9626237154006958,
+      "step": 1564
+    },
+    {
+      "epoch": 0.6757281553398058,
+      "grad_norm": 0.4646652638912201,
+      "learning_rate": 0.00019938479446353892,
+      "loss": 0.8506941199302673,
+      "step": 1566
+    },
+    {
+      "epoch": 0.6765911542610572,
+      "grad_norm": 0.4343051314353943,
+      "learning_rate": 0.00019937934377302688,
+      "loss": 0.8172947764396667,
+      "step": 1568
+    },
+    {
+      "epoch": 0.6774541531823085,
+      "grad_norm": 0.46890193223953247,
+      "learning_rate": 0.00019937386911763407,
+      "loss": 0.9215856790542603,
+      "step": 1570
+    },
+    {
+      "epoch": 0.6783171521035599,
+      "grad_norm": 0.5121113061904907,
+      "learning_rate": 0.0001993683704986807,
+      "loss": 0.8099892139434814,
+      "step": 1572
+    },
+    {
+      "epoch": 0.6791801510248112,
+      "grad_norm": 0.4652405083179474,
+      "learning_rate": 0.0001993628479174928,
+      "loss": 0.8675104975700378,
+      "step": 1574
+    },
+    {
+      "epoch": 0.6800431499460625,
+      "grad_norm": 0.4599422812461853,
+      "learning_rate": 0.00019935730137540198,
+      "loss": 0.7938929200172424,
+      "step": 1576
+    },
+    {
+      "epoch": 0.6809061488673139,
+      "grad_norm": 0.4738059937953949,
+      "learning_rate": 0.0001993517308737459,
+      "loss": 0.8610570430755615,
+      "step": 1578
+    },
+    {
+      "epoch": 0.6817691477885652,
+      "grad_norm": 0.5161214470863342,
+      "learning_rate": 0.00019934613641386776,
+      "loss": 0.9199413657188416,
+      "step": 1580
+    },
+    {
+      "epoch": 0.6826321467098166,
+      "grad_norm": 0.4284999370574951,
+      "learning_rate": 0.00019934051799711672,
+      "loss": 0.771649181842804,
+      "step": 1582
+    },
+    {
+      "epoch": 0.683495145631068,
+      "grad_norm": 0.5117548704147339,
+      "learning_rate": 0.00019933487562484757,
+      "loss": 0.8861327767372131,
+      "step": 1584
+    },
+    {
+      "epoch": 0.6843581445523194,
+      "grad_norm": 0.4964369833469391,
+      "learning_rate": 0.00019932920929842095,
+      "loss": 0.806983232498169,
+      "step": 1586
+    },
+    {
+      "epoch": 0.6852211434735707,
+      "grad_norm": 0.4699532091617584,
+      "learning_rate": 0.00019932351901920327,
+      "loss": 0.7963525652885437,
+      "step": 1588
+    },
+    {
+      "epoch": 0.686084142394822,
+      "grad_norm": 0.5329220294952393,
+      "learning_rate": 0.00019931780478856678,
+      "loss": 0.9406430721282959,
+      "step": 1590
+    },
+    {
+      "epoch": 0.6869471413160734,
+      "grad_norm": 0.49823835492134094,
+      "learning_rate": 0.00019931206660788936,
+      "loss": 0.8517770171165466,
+      "step": 1592
+    },
+    {
+      "epoch": 0.6878101402373247,
+      "grad_norm": 0.45245134830474854,
+      "learning_rate": 0.00019930630447855482,
+      "loss": 0.8703644275665283,
+      "step": 1594
+    },
+    {
+      "epoch": 0.6886731391585761,
+      "grad_norm": 0.47524577379226685,
+      "learning_rate": 0.0001993005184019526,
+      "loss": 0.9035283327102661,
+      "step": 1596
+    },
+    {
+      "epoch": 0.6895361380798274,
+      "grad_norm": 0.4537610411643982,
+      "learning_rate": 0.00019929470837947802,
+      "loss": 0.9173959493637085,
+      "step": 1598
+    },
+    {
+      "epoch": 0.6903991370010788,
+      "grad_norm": 0.42469722032546997,
+      "learning_rate": 0.00019928887441253212,
+      "loss": 0.8573579788208008,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6903991370010788,
+      "eval_loss": 0.8880587220191956,
+      "eval_runtime": 653.9515,
+      "eval_samples_per_second": 3.15,
+      "eval_steps_per_second": 3.15,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6912621359223301,
+      "grad_norm": 0.4388251304626465,
+      "learning_rate": 0.00019928301650252176,
+      "loss": 0.849348247051239,
+      "step": 1602
+    },
+    {
+      "epoch": 0.6921251348435814,
+      "grad_norm": 0.46086886525154114,
+      "learning_rate": 0.00019927713465085956,
+      "loss": 0.8298451900482178,
+      "step": 1604
+    },
+    {
+      "epoch": 0.6929881337648328,
+      "grad_norm": 0.42972785234451294,
+      "learning_rate": 0.00019927122885896387,
+      "loss": 0.8860712647438049,
+      "step": 1606
+    },
+    {
+      "epoch": 0.6938511326860841,
+      "grad_norm": 0.43009471893310547,
+      "learning_rate": 0.00019926529912825888,
+      "loss": 0.7972728610038757,
+      "step": 1608
+    },
+    {
+      "epoch": 0.6947141316073355,
+      "grad_norm": 0.3705308437347412,
+      "learning_rate": 0.00019925934546017446,
+      "loss": 0.8661653995513916,
+      "step": 1610
+    },
+    {
+      "epoch": 0.6955771305285868,
+      "grad_norm": 0.405208945274353,
+      "learning_rate": 0.00019925336785614635,
+      "loss": 0.8350111246109009,
+      "step": 1612
+    },
+    {
+      "epoch": 0.6964401294498382,
+      "grad_norm": 0.4773033857345581,
+      "learning_rate": 0.00019924736631761602,
+      "loss": 0.7920925617218018,
+      "step": 1614
+    },
+    {
+      "epoch": 0.6973031283710895,
+      "grad_norm": 0.4682428240776062,
+      "learning_rate": 0.00019924134084603075,
+      "loss": 0.8644304871559143,
+      "step": 1616
+    },
+    {
+      "epoch": 0.6981661272923408,
+      "grad_norm": 0.5694834589958191,
+      "learning_rate": 0.00019923529144284346,
+      "loss": 0.9897904992103577,
+      "step": 1618
+    },
+    {
+      "epoch": 0.6990291262135923,
+      "grad_norm": 0.40137484669685364,
+      "learning_rate": 0.00019922921810951302,
+      "loss": 0.6910083293914795,
+      "step": 1620
+    },
+    {
+      "epoch": 0.6998921251348436,
+      "grad_norm": 0.42076537013053894,
+      "learning_rate": 0.000199223120847504,
+      "loss": 0.8295826315879822,
+      "step": 1622
+    },
+    {
+      "epoch": 0.700755124056095,
+      "grad_norm": 0.4473017752170563,
+      "learning_rate": 0.00019921699965828662,
+      "loss": 0.820871889591217,
+      "step": 1624
+    },
+    {
+      "epoch": 0.7016181229773463,
+      "grad_norm": 0.43914029002189636,
+      "learning_rate": 0.00019921085454333706,
+      "loss": 0.8319019079208374,
+      "step": 1626
+    },
+    {
+      "epoch": 0.7024811218985976,
+      "grad_norm": 0.4758487939834595,
+      "learning_rate": 0.0001992046855041372,
+      "loss": 0.8589251041412354,
+      "step": 1628
+    },
+    {
+      "epoch": 0.703344120819849,
+      "grad_norm": 0.506401538848877,
+      "learning_rate": 0.00019919849254217465,
+      "loss": 0.9219205975532532,
+      "step": 1630
+    },
+    {
+      "epoch": 0.7042071197411003,
+      "grad_norm": 0.4397984445095062,
+      "learning_rate": 0.00019919227565894277,
+      "loss": 0.7824978232383728,
+      "step": 1632
+    },
+    {
+      "epoch": 0.7050701186623517,
+      "grad_norm": 0.3879252076148987,
+      "learning_rate": 0.0001991860348559408,
+      "loss": 0.8472069501876831,
+      "step": 1634
+    },
+    {
+      "epoch": 0.705933117583603,
+      "grad_norm": 0.42238810658454895,
+      "learning_rate": 0.00019917977013467368,
+      "loss": 0.824957013130188,
+      "step": 1636
+    },
+    {
+      "epoch": 0.7067961165048544,
+      "grad_norm": 0.5235037207603455,
+      "learning_rate": 0.00019917348149665206,
+      "loss": 0.9490993022918701,
+      "step": 1638
+    },
+    {
+      "epoch": 0.7076591154261057,
+      "grad_norm": 0.5195287466049194,
+      "learning_rate": 0.0001991671689433925,
+      "loss": 0.960905909538269,
+      "step": 1640
+    },
+    {
+      "epoch": 0.708522114347357,
+      "grad_norm": 0.5016481876373291,
+      "learning_rate": 0.00019916083247641716,
+      "loss": 0.8961218595504761,
+      "step": 1642
+    },
+    {
+      "epoch": 0.7093851132686084,
+      "grad_norm": 0.5510191321372986,
+      "learning_rate": 0.00019915447209725408,
+      "loss": 0.8883417844772339,
+      "step": 1644
+    },
+    {
+      "epoch": 0.7102481121898597,
+      "grad_norm": 0.4492250084877014,
+      "learning_rate": 0.0001991480878074371,
+      "loss": 0.7968636751174927,
+      "step": 1646
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.4189683496952057,
+      "learning_rate": 0.00019914167960850563,
+      "loss": 0.7869221568107605,
+      "step": 1648
+    },
+    {
+      "epoch": 0.7119741100323624,
+      "grad_norm": 0.4590536653995514,
+      "learning_rate": 0.0001991352475020051,
+      "loss": 0.8423646092414856,
+      "step": 1650
+    },
+    {
+      "epoch": 0.7128371089536139,
+      "grad_norm": 0.5058966875076294,
+      "learning_rate": 0.00019912879148948652,
+      "loss": 0.895459771156311,
+      "step": 1652
+    },
+    {
+      "epoch": 0.7137001078748652,
+      "grad_norm": 0.4904550313949585,
+      "learning_rate": 0.00019912231157250676,
+      "loss": 0.8737894296646118,
+      "step": 1654
+    },
+    {
+      "epoch": 0.7145631067961165,
+      "grad_norm": 0.4670710861682892,
+      "learning_rate": 0.0001991158077526284,
+      "loss": 0.8019732236862183,
+      "step": 1656
+    },
+    {
+      "epoch": 0.7154261057173679,
+      "grad_norm": 0.530343770980835,
+      "learning_rate": 0.00019910928003141984,
+      "loss": 0.9474499821662903,
+      "step": 1658
+    },
+    {
+      "epoch": 0.7162891046386192,
+      "grad_norm": 0.4250960052013397,
+      "learning_rate": 0.00019910272841045518,
+      "loss": 0.8738601803779602,
+      "step": 1660
+    },
+    {
+      "epoch": 0.7171521035598706,
+      "grad_norm": 0.4896513819694519,
+      "learning_rate": 0.0001990961528913143,
+      "loss": 0.9578261971473694,
+      "step": 1662
+    },
+    {
+      "epoch": 0.7180151024811219,
+      "grad_norm": 0.4999626576900482,
+      "learning_rate": 0.00019908955347558291,
+      "loss": 0.8116445541381836,
+      "step": 1664
+    },
+    {
+      "epoch": 0.7188781014023733,
+      "grad_norm": 0.4335242807865143,
+      "learning_rate": 0.00019908293016485237,
+      "loss": 0.8783043622970581,
+      "step": 1666
+    },
+    {
+      "epoch": 0.7197411003236246,
+      "grad_norm": 0.43542763590812683,
+      "learning_rate": 0.00019907628296071992,
+      "loss": 0.8223029375076294,
+      "step": 1668
+    },
+    {
+      "epoch": 0.7206040992448759,
+      "grad_norm": 0.4907461702823639,
+      "learning_rate": 0.00019906961186478842,
+      "loss": 1.0053197145462036,
+      "step": 1670
+    },
+    {
+      "epoch": 0.7214670981661273,
+      "grad_norm": 0.4054848253726959,
+      "learning_rate": 0.00019906291687866667,
+      "loss": 0.8107786178588867,
+      "step": 1672
+    },
+    {
+      "epoch": 0.7223300970873786,
+      "grad_norm": 0.3818599283695221,
+      "learning_rate": 0.0001990561980039691,
+      "loss": 0.780781626701355,
+      "step": 1674
+    },
+    {
+      "epoch": 0.72319309600863,
+      "grad_norm": 0.4128594994544983,
+      "learning_rate": 0.00019904945524231587,
+      "loss": 0.8189221620559692,
+      "step": 1676
+    },
+    {
+      "epoch": 0.7240560949298813,
+      "grad_norm": 0.46902593970298767,
+      "learning_rate": 0.0001990426885953331,
+      "loss": 0.83652263879776,
+      "step": 1678
+    },
+    {
+      "epoch": 0.7249190938511327,
+      "grad_norm": 0.49305564165115356,
+      "learning_rate": 0.00019903589806465242,
+      "loss": 0.8057956695556641,
+      "step": 1680
+    },
+    {
+      "epoch": 0.725782092772384,
+      "grad_norm": 0.44408300518989563,
+      "learning_rate": 0.0001990290836519114,
+      "loss": 0.8523716926574707,
+      "step": 1682
+    },
+    {
+      "epoch": 0.7266450916936353,
+      "grad_norm": 0.5211108922958374,
+      "learning_rate": 0.00019902224535875326,
+      "loss": 0.9179236888885498,
+      "step": 1684
+    },
+    {
+      "epoch": 0.7275080906148867,
+      "grad_norm": 0.4736526608467102,
+      "learning_rate": 0.00019901538318682705,
+      "loss": 0.8229476809501648,
+      "step": 1686
+    },
+    {
+      "epoch": 0.728371089536138,
+      "grad_norm": 0.541716992855072,
+      "learning_rate": 0.00019900849713778756,
+      "loss": 0.924200713634491,
+      "step": 1688
+    },
+    {
+      "epoch": 0.7292340884573895,
+      "grad_norm": 0.4524400532245636,
+      "learning_rate": 0.00019900158721329532,
+      "loss": 0.88961261510849,
+      "step": 1690
+    },
+    {
+      "epoch": 0.7300970873786408,
+      "grad_norm": 0.45256128907203674,
+      "learning_rate": 0.00019899465341501662,
+      "loss": 0.8491015434265137,
+      "step": 1692
+    },
+    {
+      "epoch": 0.7309600862998922,
+      "grad_norm": 0.5346773266792297,
+      "learning_rate": 0.0001989876957446235,
+      "loss": 0.8833339810371399,
+      "step": 1694
+    },
+    {
+      "epoch": 0.7318230852211435,
+      "grad_norm": 0.4696357846260071,
+      "learning_rate": 0.0001989807142037938,
+      "loss": 0.8535294532775879,
+      "step": 1696
+    },
+    {
+      "epoch": 0.7326860841423948,
+      "grad_norm": 0.4304637908935547,
+      "learning_rate": 0.0001989737087942111,
+      "loss": 0.8273076415061951,
+      "step": 1698
+    },
+    {
+      "epoch": 0.7335490830636462,
+      "grad_norm": 0.5085629224777222,
+      "learning_rate": 0.00019896667951756466,
+      "loss": 0.8759240508079529,
+      "step": 1700
+    },
+    {
+      "epoch": 0.7335490830636462,
+      "eval_loss": 0.879119336605072,
+      "eval_runtime": 663.0553,
+      "eval_samples_per_second": 3.107,
+      "eval_steps_per_second": 3.107,
+      "step": 1700
+    },
+    {
+      "epoch": 0.7344120819848975,
+      "grad_norm": 0.484223872423172,
+      "learning_rate": 0.00019895962637554964,
+      "loss": 0.852645218372345,
+      "step": 1702
+    },
+    {
+      "epoch": 0.7352750809061489,
+      "grad_norm": 0.4819294214248657,
+      "learning_rate": 0.0001989525493698668,
+      "loss": 0.878247857093811,
+      "step": 1704
+    },
+    {
+      "epoch": 0.7361380798274002,
+      "grad_norm": 0.4170311689376831,
+      "learning_rate": 0.00019894544850222276,
+      "loss": 0.8964285254478455,
+      "step": 1706
+    },
+    {
+      "epoch": 0.7370010787486516,
+      "grad_norm": 0.42712801694869995,
+      "learning_rate": 0.0001989383237743299,
+      "loss": 0.7479548454284668,
+      "step": 1708
+    },
+    {
+      "epoch": 0.7378640776699029,
+      "grad_norm": 0.5051686763763428,
+      "learning_rate": 0.00019893117518790624,
+      "loss": 0.8190052509307861,
+      "step": 1710
+    },
+    {
+      "epoch": 0.7387270765911542,
+      "grad_norm": 0.44053253531455994,
+      "learning_rate": 0.0001989240027446757,
+      "loss": 0.8646742105484009,
+      "step": 1712
+    },
+    {
+      "epoch": 0.7395900755124056,
+      "grad_norm": 0.4451025724411011,
+      "learning_rate": 0.00019891680644636782,
+      "loss": 0.874261736869812,
+      "step": 1714
+    },
+    {
+      "epoch": 0.7404530744336569,
+      "grad_norm": 0.4590521454811096,
+      "learning_rate": 0.00019890958629471798,
+      "loss": 0.8892465233802795,
+      "step": 1716
+    },
+    {
+      "epoch": 0.7413160733549083,
+      "grad_norm": 0.39169448614120483,
+      "learning_rate": 0.00019890234229146732,
+      "loss": 0.7031586766242981,
+      "step": 1718
+    },
+    {
+      "epoch": 0.7421790722761596,
+      "grad_norm": 0.46946024894714355,
+      "learning_rate": 0.00019889507443836266,
+      "loss": 0.8548433184623718,
+      "step": 1720
+    },
+    {
+      "epoch": 0.7430420711974111,
+      "grad_norm": 0.42404699325561523,
+      "learning_rate": 0.0001988877827371566,
+      "loss": 0.8231223821640015,
+      "step": 1722
+    },
+    {
+      "epoch": 0.7439050701186624,
+      "grad_norm": 0.40419483184814453,
+      "learning_rate": 0.00019888046718960755,
+      "loss": 0.8443762063980103,
+      "step": 1724
+    },
+    {
+      "epoch": 0.7447680690399137,
+      "grad_norm": 0.4550437927246094,
+      "learning_rate": 0.0001988731277974796,
+      "loss": 0.8787111639976501,
+      "step": 1726
+    },
+    {
+      "epoch": 0.7456310679611651,
+      "grad_norm": 0.42264053225517273,
+      "learning_rate": 0.0001988657645625426,
+      "loss": 0.8440850377082825,
+      "step": 1728
+    },
+    {
+      "epoch": 0.7464940668824164,
+      "grad_norm": 0.4638359844684601,
+      "learning_rate": 0.0001988583774865721,
+      "loss": 0.839216947555542,
+      "step": 1730
+    },
+    {
+      "epoch": 0.7473570658036678,
+      "grad_norm": 0.42644429206848145,
+      "learning_rate": 0.0001988509665713496,
+      "loss": 0.8011161684989929,
+      "step": 1732
+    },
+    {
+      "epoch": 0.7482200647249191,
+      "grad_norm": 0.36932024359703064,
+      "learning_rate": 0.0001988435318186621,
+      "loss": 0.850246787071228,
+      "step": 1734
+    },
+    {
+      "epoch": 0.7490830636461704,
+      "grad_norm": 0.4771935045719147,
+      "learning_rate": 0.00019883607323030252,
+      "loss": 0.7782483100891113,
+      "step": 1736
+    },
+    {
+      "epoch": 0.7499460625674218,
+      "grad_norm": 0.40007370710372925,
+      "learning_rate": 0.00019882859080806942,
+      "loss": 0.8337594866752625,
+      "step": 1738
+    },
+    {
+      "epoch": 0.7508090614886731,
+      "grad_norm": 0.5007418394088745,
+      "learning_rate": 0.00019882108455376716,
+      "loss": 0.8287386894226074,
+      "step": 1740
+    },
+    {
+      "epoch": 0.7516720604099245,
+      "grad_norm": 0.43999138474464417,
+      "learning_rate": 0.00019881355446920584,
+      "loss": 0.8655616044998169,
+      "step": 1742
+    },
+    {
+      "epoch": 0.7525350593311758,
+      "grad_norm": 0.5115824937820435,
+      "learning_rate": 0.00019880600055620135,
+      "loss": 0.8695262670516968,
+      "step": 1744
+    },
+    {
+      "epoch": 0.7533980582524272,
+      "grad_norm": 0.5035707950592041,
+      "learning_rate": 0.0001987984228165752,
+      "loss": 0.9207013845443726,
+      "step": 1746
+    },
+    {
+      "epoch": 0.7542610571736785,
+      "grad_norm": 0.4689575731754303,
+      "learning_rate": 0.0001987908212521548,
+      "loss": 0.8798729777336121,
+      "step": 1748
+    },
+    {
+      "epoch": 0.7551240560949298,
+      "grad_norm": 0.4730616509914398,
+      "learning_rate": 0.00019878319586477322,
+      "loss": 0.7737767696380615,
+      "step": 1750
+    },
+    {
+      "epoch": 0.7559870550161812,
+      "grad_norm": 0.49012845754623413,
+      "learning_rate": 0.00019877554665626926,
+      "loss": 0.929466187953949,
+      "step": 1752
+    },
+    {
+      "epoch": 0.7568500539374325,
+      "grad_norm": 0.43468761444091797,
+      "learning_rate": 0.0001987678736284875,
+      "loss": 0.8155670166015625,
+      "step": 1754
+    },
+    {
+      "epoch": 0.757713052858684,
+      "grad_norm": 0.507399320602417,
+      "learning_rate": 0.00019876017678327826,
+      "loss": 0.8082395195960999,
+      "step": 1756
+    },
+    {
+      "epoch": 0.7585760517799353,
+      "grad_norm": 0.4733552634716034,
+      "learning_rate": 0.0001987524561224976,
+      "loss": 0.8905934691429138,
+      "step": 1758
+    },
+    {
+      "epoch": 0.7594390507011867,
+      "grad_norm": 0.4670012891292572,
+      "learning_rate": 0.00019874471164800733,
+      "loss": 0.8794633746147156,
+      "step": 1760
+    },
+    {
+      "epoch": 0.760302049622438,
+      "grad_norm": 0.4951624572277069,
+      "learning_rate": 0.000198736943361675,
+      "loss": 0.8413973450660706,
+      "step": 1762
+    },
+    {
+      "epoch": 0.7611650485436893,
+      "grad_norm": 0.5478648543357849,
+      "learning_rate": 0.00019872915126537387,
+      "loss": 0.9067897200584412,
+      "step": 1764
+    },
+    {
+      "epoch": 0.7620280474649407,
+      "grad_norm": 0.48215776681900024,
+      "learning_rate": 0.000198721335360983,
+      "loss": 0.8932394981384277,
+      "step": 1766
+    },
+    {
+      "epoch": 0.762891046386192,
+      "grad_norm": 0.4688864052295685,
+      "learning_rate": 0.00019871349565038715,
+      "loss": 0.8496726751327515,
+      "step": 1768
+    },
+    {
+      "epoch": 0.7637540453074434,
+      "grad_norm": 0.4728260636329651,
+      "learning_rate": 0.0001987056321354768,
+      "loss": 0.9232800602912903,
+      "step": 1770
+    },
+    {
+      "epoch": 0.7646170442286947,
+      "grad_norm": 0.44501692056655884,
+      "learning_rate": 0.00019869774481814828,
+      "loss": 0.849755585193634,
+      "step": 1772
+    },
+    {
+      "epoch": 0.7654800431499461,
+      "grad_norm": 0.4189201593399048,
+      "learning_rate": 0.00019868983370030348,
+      "loss": 0.8258485794067383,
+      "step": 1774
+    },
+    {
+      "epoch": 0.7663430420711974,
+      "grad_norm": 0.5144591927528381,
+      "learning_rate": 0.00019868189878385016,
+      "loss": 0.8762873411178589,
+      "step": 1776
+    },
+    {
+      "epoch": 0.7672060409924487,
+      "grad_norm": 0.5048011541366577,
+      "learning_rate": 0.00019867394007070188,
+      "loss": 0.8732464909553528,
+      "step": 1778
+    },
+    {
+      "epoch": 0.7680690399137001,
+      "grad_norm": 0.41639819741249084,
+      "learning_rate": 0.00019866595756277774,
+      "loss": 0.8732751607894897,
+      "step": 1780
+    },
+    {
+      "epoch": 0.7689320388349514,
+      "grad_norm": 0.526757538318634,
+      "learning_rate": 0.00019865795126200271,
+      "loss": 0.8453729748725891,
+      "step": 1782
+    },
+    {
+      "epoch": 0.7697950377562028,
+      "grad_norm": 0.47041091322898865,
+      "learning_rate": 0.0001986499211703075,
+      "loss": 0.8780192732810974,
+      "step": 1784
+    },
+    {
+      "epoch": 0.7706580366774541,
+      "grad_norm": 0.4535890221595764,
+      "learning_rate": 0.0001986418672896285,
+      "loss": 0.8508450388908386,
+      "step": 1786
+    },
+    {
+      "epoch": 0.7715210355987056,
+      "grad_norm": 0.4608050286769867,
+      "learning_rate": 0.00019863378962190788,
+      "loss": 0.822467565536499,
+      "step": 1788
+    },
+    {
+      "epoch": 0.7723840345199569,
+      "grad_norm": 0.5190523862838745,
+      "learning_rate": 0.00019862568816909356,
+      "loss": 0.844614565372467,
+      "step": 1790
+    },
+    {
+      "epoch": 0.7732470334412082,
+      "grad_norm": 0.42502254247665405,
+      "learning_rate": 0.00019861756293313912,
+      "loss": 0.8144394755363464,
+      "step": 1792
+    },
+    {
+      "epoch": 0.7741100323624596,
+      "grad_norm": 0.47112616896629333,
+      "learning_rate": 0.000198609413916004,
+      "loss": 0.8836341500282288,
+      "step": 1794
+    },
+    {
+      "epoch": 0.7749730312837109,
+      "grad_norm": 0.48414838314056396,
+      "learning_rate": 0.0001986012411196532,
+      "loss": 0.8846262693405151,
+      "step": 1796
+    },
+    {
+      "epoch": 0.7758360302049623,
+      "grad_norm": 0.4670039415359497,
+      "learning_rate": 0.00019859304454605763,
+      "loss": 0.7993118762969971,
+      "step": 1798
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "grad_norm": 0.41939061880111694,
+      "learning_rate": 0.0001985848241971938,
+      "loss": 0.8389407396316528,
+      "step": 1800
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "eval_loss": 0.8727664947509766,
+      "eval_runtime": 668.2062,
+      "eval_samples_per_second": 3.083,
+      "eval_steps_per_second": 3.083,
+      "step": 1800
+    },
+    {
+      "epoch": 0.777562028047465,
+      "grad_norm": 0.4566517174243927,
+      "learning_rate": 0.00019857658007504405,
+      "loss": 0.8824291825294495,
+      "step": 1802
+    },
+    {
+      "epoch": 0.7784250269687163,
+      "grad_norm": 0.4798925518989563,
+      "learning_rate": 0.0001985683121815964,
+      "loss": 0.808982789516449,
+      "step": 1804
+    },
+    {
+      "epoch": 0.7792880258899676,
+      "grad_norm": 0.4659746587276459,
+      "learning_rate": 0.00019856002051884462,
+      "loss": 0.955269992351532,
+      "step": 1806
+    },
+    {
+      "epoch": 0.780151024811219,
+      "grad_norm": 0.48573991656303406,
+      "learning_rate": 0.00019855170508878818,
+      "loss": 0.8142994046211243,
+      "step": 1808
+    },
+    {
+      "epoch": 0.7810140237324703,
+      "grad_norm": 0.4700213670730591,
+      "learning_rate": 0.00019854336589343236,
+      "loss": 0.8755695819854736,
+      "step": 1810
+    },
+    {
+      "epoch": 0.7818770226537217,
+      "grad_norm": 0.42113450169563293,
+      "learning_rate": 0.00019853500293478806,
+      "loss": 0.8098483681678772,
+      "step": 1812
+    },
+    {
+      "epoch": 0.782740021574973,
+      "grad_norm": 0.4218153655529022,
+      "learning_rate": 0.00019852661621487205,
+      "loss": 0.8219783306121826,
+      "step": 1814
+    },
+    {
+      "epoch": 0.7836030204962244,
+      "grad_norm": 0.499052494764328,
+      "learning_rate": 0.00019851820573570664,
+      "loss": 0.8314159512519836,
+      "step": 1816
+    },
+    {
+      "epoch": 0.7844660194174757,
+      "grad_norm": 0.42420193552970886,
+      "learning_rate": 0.00019850977149932008,
+      "loss": 0.7985323071479797,
+      "step": 1818
+    },
+    {
+      "epoch": 0.785329018338727,
+      "grad_norm": 0.46345841884613037,
+      "learning_rate": 0.0001985013135077462,
+      "loss": 0.8528217077255249,
+      "step": 1820
+    },
+    {
+      "epoch": 0.7861920172599784,
+      "grad_norm": 0.4433307945728302,
+      "learning_rate": 0.00019849283176302462,
+      "loss": 0.8659319877624512,
+      "step": 1822
+    },
+    {
+      "epoch": 0.7870550161812297,
+      "grad_norm": 0.48279091715812683,
+      "learning_rate": 0.00019848432626720067,
+      "loss": 0.8675655126571655,
+      "step": 1824
+    },
+    {
+      "epoch": 0.7879180151024812,
+      "grad_norm": 0.5439180731773376,
+      "learning_rate": 0.0001984757970223254,
+      "loss": 0.8550227284431458,
+      "step": 1826
+    },
+    {
+      "epoch": 0.7887810140237325,
+      "grad_norm": 0.45749521255493164,
+      "learning_rate": 0.0001984672440304556,
+      "loss": 0.7290607690811157,
+      "step": 1828
+    },
+    {
+      "epoch": 0.7896440129449838,
+      "grad_norm": 0.4654783606529236,
+      "learning_rate": 0.00019845866729365378,
+      "loss": 0.8619251251220703,
+      "step": 1830
+    },
+    {
+      "epoch": 0.7905070118662352,
+      "grad_norm": 0.42632243037223816,
+      "learning_rate": 0.00019845006681398823,
+      "loss": 0.8249601125717163,
+      "step": 1832
+    },
+    {
+      "epoch": 0.7913700107874865,
+      "grad_norm": 0.4747186005115509,
+      "learning_rate": 0.0001984414425935329,
+      "loss": 0.7138552069664001,
+      "step": 1834
+    },
+    {
+      "epoch": 0.7922330097087379,
+      "grad_norm": 0.4462338387966156,
+      "learning_rate": 0.0001984327946343674,
+      "loss": 0.903292715549469,
+      "step": 1836
+    },
+    {
+      "epoch": 0.7930960086299892,
+      "grad_norm": 0.4581359922885895,
+      "learning_rate": 0.00019842412293857726,
+      "loss": 0.7569618225097656,
+      "step": 1838
+    },
+    {
+      "epoch": 0.7939590075512406,
+      "grad_norm": 0.4183015525341034,
+      "learning_rate": 0.00019841542750825356,
+      "loss": 0.8063036203384399,
+      "step": 1840
+    },
+    {
+      "epoch": 0.7948220064724919,
+      "grad_norm": 0.3954181373119354,
+      "learning_rate": 0.0001984067083454932,
+      "loss": 0.81150221824646,
+      "step": 1842
+    },
+    {
+      "epoch": 0.7956850053937432,
+      "grad_norm": 0.46220019459724426,
+      "learning_rate": 0.0001983979654523987,
+      "loss": 0.841649055480957,
+      "step": 1844
+    },
+    {
+      "epoch": 0.7965480043149946,
+      "grad_norm": 0.47807541489601135,
+      "learning_rate": 0.00019838919883107843,
+      "loss": 0.8019483685493469,
+      "step": 1846
+    },
+    {
+      "epoch": 0.7974110032362459,
+      "grad_norm": 0.48015692830085754,
+      "learning_rate": 0.0001983804084836464,
+      "loss": 0.9343363046646118,
+      "step": 1848
+    },
+    {
+      "epoch": 0.7982740021574973,
+      "grad_norm": 0.4906708896160126,
+      "learning_rate": 0.00019837159441222238,
+      "loss": 0.9163194894790649,
+      "step": 1850
+    },
+    {
+      "epoch": 0.7991370010787486,
+      "grad_norm": 0.4856911599636078,
+      "learning_rate": 0.0001983627566189318,
+      "loss": 0.8017736077308655,
+      "step": 1852
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.49403145909309387,
+      "learning_rate": 0.0001983538951059059,
+      "loss": 0.8375223875045776,
+      "step": 1854
+    },
+    {
+      "epoch": 0.8008629989212513,
+      "grad_norm": 0.4237985908985138,
+      "learning_rate": 0.00019834500987528158,
+      "loss": 0.8213951587677002,
+      "step": 1856
+    },
+    {
+      "epoch": 0.8017259978425026,
+      "grad_norm": 0.3977980315685272,
+      "learning_rate": 0.00019833610092920149,
+      "loss": 0.8086028099060059,
+      "step": 1858
+    },
+    {
+      "epoch": 0.8025889967637541,
+      "grad_norm": 0.435253381729126,
+      "learning_rate": 0.00019832716826981392,
+      "loss": 0.9402202367782593,
+      "step": 1860
+    },
+    {
+      "epoch": 0.8034519956850054,
+      "grad_norm": 0.4074764847755432,
+      "learning_rate": 0.000198318211899273,
+      "loss": 0.7730796933174133,
+      "step": 1862
+    },
+    {
+      "epoch": 0.8043149946062568,
+      "grad_norm": 0.48804348707199097,
+      "learning_rate": 0.0001983092318197385,
+      "loss": 0.9185802936553955,
+      "step": 1864
+    },
+    {
+      "epoch": 0.8051779935275081,
+      "grad_norm": 0.44363343715667725,
+      "learning_rate": 0.00019830022803337592,
+      "loss": 0.8578243851661682,
+      "step": 1866
+    },
+    {
+      "epoch": 0.8060409924487595,
+      "grad_norm": 0.46645957231521606,
+      "learning_rate": 0.00019829120054235653,
+      "loss": 0.8682060241699219,
+      "step": 1868
+    },
+    {
+      "epoch": 0.8069039913700108,
+      "grad_norm": 0.4527221620082855,
+      "learning_rate": 0.00019828214934885718,
+      "loss": 0.7845040559768677,
+      "step": 1870
+    },
+    {
+      "epoch": 0.8077669902912621,
+      "grad_norm": 0.4103536307811737,
+      "learning_rate": 0.0001982730744550606,
+      "loss": 0.8768247961997986,
+      "step": 1872
+    },
+    {
+      "epoch": 0.8086299892125135,
+      "grad_norm": 0.5257515907287598,
+      "learning_rate": 0.00019826397586315513,
+      "loss": 0.850267231464386,
+      "step": 1874
+    },
+    {
+      "epoch": 0.8094929881337648,
+      "grad_norm": 0.46675893664360046,
+      "learning_rate": 0.00019825485357533485,
+      "loss": 0.8234293460845947,
+      "step": 1876
+    },
+    {
+      "epoch": 0.8103559870550162,
+      "grad_norm": 0.46315401792526245,
+      "learning_rate": 0.00019824570759379958,
+      "loss": 0.8131387829780579,
+      "step": 1878
+    },
+    {
+      "epoch": 0.8112189859762675,
+      "grad_norm": 0.4766870439052582,
+      "learning_rate": 0.00019823653792075478,
+      "loss": 0.7680494785308838,
+      "step": 1880
+    },
+    {
+      "epoch": 0.8120819848975189,
+      "grad_norm": 0.39025625586509705,
+      "learning_rate": 0.00019822734455841173,
+      "loss": 0.7891425490379333,
+      "step": 1882
+    },
+    {
+      "epoch": 0.8129449838187702,
+      "grad_norm": 0.4672441780567169,
+      "learning_rate": 0.0001982181275089874,
+      "loss": 0.7990400791168213,
+      "step": 1884
+    },
+    {
+      "epoch": 0.8138079827400215,
+      "grad_norm": 0.44310975074768066,
+      "learning_rate": 0.00019820888677470432,
+      "loss": 0.7828341722488403,
+      "step": 1886
+    },
+    {
+      "epoch": 0.8146709816612729,
+      "grad_norm": 0.45098716020584106,
+      "learning_rate": 0.00019819962235779096,
+      "loss": 0.897715151309967,
+      "step": 1888
+    },
+    {
+      "epoch": 0.8155339805825242,
+      "grad_norm": 0.466805100440979,
+      "learning_rate": 0.00019819033426048135,
+      "loss": 0.7987668514251709,
+      "step": 1890
+    },
+    {
+      "epoch": 0.8163969795037757,
+      "grad_norm": 0.4438319206237793,
+      "learning_rate": 0.00019818102248501528,
+      "loss": 0.7950236201286316,
+      "step": 1892
+    },
+    {
+      "epoch": 0.817259978425027,
+      "grad_norm": 0.42012497782707214,
+      "learning_rate": 0.00019817168703363823,
+      "loss": 0.8789975643157959,
+      "step": 1894
+    },
+    {
+      "epoch": 0.8181229773462784,
+      "grad_norm": 0.4359394311904907,
+      "learning_rate": 0.0001981623279086014,
+      "loss": 0.8159777522087097,
+      "step": 1896
+    },
+    {
+      "epoch": 0.8189859762675297,
+      "grad_norm": 0.44709593057632446,
+      "learning_rate": 0.00019815294511216173,
+      "loss": 0.84877610206604,
+      "step": 1898
+    },
+    {
+      "epoch": 0.819848975188781,
+      "grad_norm": 0.4315306544303894,
+      "learning_rate": 0.00019814353864658184,
+      "loss": 0.8467556834220886,
+      "step": 1900
+    },
+    {
+      "epoch": 0.819848975188781,
+      "eval_loss": 0.8643407821655273,
+      "eval_runtime": 658.6942,
+      "eval_samples_per_second": 3.127,
+      "eval_steps_per_second": 3.127,
+      "step": 1900
+    },
+    {
+      "epoch": 0.8207119741100324,
+      "grad_norm": 0.35530397295951843,
+      "learning_rate": 0.00019813410851412998,
+      "loss": 0.7398589849472046,
+      "step": 1902
+    },
+    {
+      "epoch": 0.8215749730312837,
+      "grad_norm": 0.46949300169944763,
+      "learning_rate": 0.00019812465471708032,
+      "loss": 0.8544237613677979,
+      "step": 1904
+    },
+    {
+      "epoch": 0.8224379719525351,
+      "grad_norm": 0.4961565434932709,
+      "learning_rate": 0.00019811517725771248,
+      "loss": 0.8242526054382324,
+      "step": 1906
+    },
+    {
+      "epoch": 0.8233009708737864,
+      "grad_norm": 0.45835059881210327,
+      "learning_rate": 0.00019810567613831194,
+      "loss": 0.7856690287590027,
+      "step": 1908
+    },
+    {
+      "epoch": 0.8241639697950378,
+      "grad_norm": 0.4446084797382355,
+      "learning_rate": 0.0001980961513611699,
+      "loss": 0.8361829519271851,
+      "step": 1910
+    },
+    {
+      "epoch": 0.8250269687162891,
+      "grad_norm": 0.4470907747745514,
+      "learning_rate": 0.00019808660292858313,
+      "loss": 0.8993050456047058,
+      "step": 1912
+    },
+    {
+      "epoch": 0.8258899676375404,
+      "grad_norm": 0.44883644580841064,
+      "learning_rate": 0.0001980770308428543,
+      "loss": 0.8702824711799622,
+      "step": 1914
+    },
+    {
+      "epoch": 0.8267529665587918,
+      "grad_norm": 0.43215686082839966,
+      "learning_rate": 0.00019806743510629159,
+      "loss": 0.8454389572143555,
+      "step": 1916
+    },
+    {
+      "epoch": 0.8276159654800431,
+      "grad_norm": 0.4525185823440552,
+      "learning_rate": 0.00019805781572120897,
+      "loss": 0.8621824383735657,
+      "step": 1918
+    },
+    {
+      "epoch": 0.8284789644012945,
+      "grad_norm": 0.4616840183734894,
+      "learning_rate": 0.00019804817268992615,
+      "loss": 0.8661681413650513,
+      "step": 1920
+    },
+    {
+      "epoch": 0.8293419633225458,
+      "grad_norm": 0.4252975583076477,
+      "learning_rate": 0.0001980385060147685,
+      "loss": 0.8376660346984863,
+      "step": 1922
+    },
+    {
+      "epoch": 0.8302049622437971,
+      "grad_norm": 0.44600266218185425,
+      "learning_rate": 0.00019802881569806706,
+      "loss": 0.9258401393890381,
+      "step": 1924
+    },
+    {
+      "epoch": 0.8310679611650486,
+      "grad_norm": 0.48872479796409607,
+      "learning_rate": 0.00019801910174215866,
+      "loss": 0.8804965615272522,
+      "step": 1926
+    },
+    {
+      "epoch": 0.8319309600862999,
+      "grad_norm": 0.5357037782669067,
+      "learning_rate": 0.00019800936414938574,
+      "loss": 0.8561494946479797,
+      "step": 1928
+    },
+    {
+      "epoch": 0.8327939590075513,
+      "grad_norm": 0.39637291431427,
+      "learning_rate": 0.00019799960292209647,
+      "loss": 0.782166063785553,
+      "step": 1930
+    },
+    {
+      "epoch": 0.8336569579288026,
+      "grad_norm": 0.521138072013855,
+      "learning_rate": 0.00019798981806264476,
+      "loss": 0.9048293232917786,
+      "step": 1932
+    },
+    {
+      "epoch": 0.834519956850054,
+      "grad_norm": 0.4723529815673828,
+      "learning_rate": 0.00019798000957339015,
+      "loss": 0.9269952774047852,
+      "step": 1934
+    },
+    {
+      "epoch": 0.8353829557713053,
+      "grad_norm": 0.42827340960502625,
+      "learning_rate": 0.0001979701774566979,
+      "loss": 0.8620670437812805,
+      "step": 1936
+    },
+    {
+      "epoch": 0.8362459546925566,
+      "grad_norm": 0.4305116534233093,
+      "learning_rate": 0.00019796032171493907,
+      "loss": 0.8016669750213623,
+      "step": 1938
+    },
+    {
+      "epoch": 0.837108953613808,
+      "grad_norm": 0.4995502233505249,
+      "learning_rate": 0.00019795044235049024,
+      "loss": 0.879247784614563,
+      "step": 1940
+    },
+    {
+      "epoch": 0.8379719525350593,
+      "grad_norm": 0.49229878187179565,
+      "learning_rate": 0.0001979405393657338,
+      "loss": 0.9476580023765564,
+      "step": 1942
+    },
+    {
+      "epoch": 0.8388349514563107,
+      "grad_norm": 0.45756596326828003,
+      "learning_rate": 0.0001979306127630578,
+      "loss": 0.8654064536094666,
+      "step": 1944
+    },
+    {
+      "epoch": 0.839697950377562,
+      "grad_norm": 0.4855344891548157,
+      "learning_rate": 0.00019792066254485603,
+      "loss": 0.7792956829071045,
+      "step": 1946
+    },
+    {
+      "epoch": 0.8405609492988134,
+      "grad_norm": 0.4358632266521454,
+      "learning_rate": 0.00019791068871352787,
+      "loss": 0.8000320792198181,
+      "step": 1948
+    },
+    {
+      "epoch": 0.8414239482200647,
+      "grad_norm": 0.4225342273712158,
+      "learning_rate": 0.00019790069127147852,
+      "loss": 0.818372368812561,
+      "step": 1950
+    },
+    {
+      "epoch": 0.842286947141316,
+      "grad_norm": 0.3894529938697815,
+      "learning_rate": 0.00019789067022111886,
+      "loss": 0.727220892906189,
+      "step": 1952
+    },
+    {
+      "epoch": 0.8431499460625674,
+      "grad_norm": 0.5060731768608093,
+      "learning_rate": 0.0001978806255648653,
+      "loss": 0.894101083278656,
+      "step": 1954
+    },
+    {
+      "epoch": 0.8440129449838187,
+      "grad_norm": 0.4165003001689911,
+      "learning_rate": 0.0001978705573051402,
+      "loss": 0.878365695476532,
+      "step": 1956
+    },
+    {
+      "epoch": 0.8448759439050701,
+      "grad_norm": 0.48767927289009094,
+      "learning_rate": 0.0001978604654443714,
+      "loss": 0.8390909433364868,
+      "step": 1958
+    },
+    {
+      "epoch": 0.8457389428263214,
+      "grad_norm": 0.43019410967826843,
+      "learning_rate": 0.00019785034998499247,
+      "loss": 0.8807769417762756,
+      "step": 1960
+    },
+    {
+      "epoch": 0.8466019417475729,
+      "grad_norm": 0.4430403709411621,
+      "learning_rate": 0.0001978402109294428,
+      "loss": 0.8037779331207275,
+      "step": 1962
+    },
+    {
+      "epoch": 0.8474649406688242,
+      "grad_norm": 0.41642463207244873,
+      "learning_rate": 0.0001978300482801673,
+      "loss": 0.8341337442398071,
+      "step": 1964
+    },
+    {
+      "epoch": 0.8483279395900755,
+      "grad_norm": 0.45358774065971375,
+      "learning_rate": 0.00019781986203961668,
+      "loss": 0.854821503162384,
+      "step": 1966
+    },
+    {
+      "epoch": 0.8491909385113269,
+      "grad_norm": 0.4316342771053314,
+      "learning_rate": 0.00019780965221024728,
+      "loss": 0.8527678847312927,
+      "step": 1968
+    },
+    {
+      "epoch": 0.8500539374325782,
+      "grad_norm": 0.4581106901168823,
+      "learning_rate": 0.00019779941879452122,
+      "loss": 0.7461717128753662,
+      "step": 1970
+    },
+    {
+      "epoch": 0.8509169363538296,
+      "grad_norm": 0.49578142166137695,
+      "learning_rate": 0.0001977891617949062,
+      "loss": 0.884441077709198,
+      "step": 1972
+    },
+    {
+      "epoch": 0.8517799352750809,
+      "grad_norm": 0.4366011917591095,
+      "learning_rate": 0.00019777888121387562,
+      "loss": 0.855915904045105,
+      "step": 1974
+    },
+    {
+      "epoch": 0.8526429341963323,
+      "grad_norm": 0.486162930727005,
+      "learning_rate": 0.00019776857705390864,
+      "loss": 0.7563765645027161,
+      "step": 1976
+    },
+    {
+      "epoch": 0.8535059331175836,
+      "grad_norm": 0.5162674784660339,
+      "learning_rate": 0.00019775824931749005,
+      "loss": 0.8346326947212219,
+      "step": 1978
+    },
+    {
+      "epoch": 0.8543689320388349,
+      "grad_norm": 0.5824693441390991,
+      "learning_rate": 0.0001977478980071103,
+      "loss": 0.8701820969581604,
+      "step": 1980
+    },
+    {
+      "epoch": 0.8552319309600863,
+      "grad_norm": 0.4297148883342743,
+      "learning_rate": 0.00019773752312526565,
+      "loss": 0.893528938293457,
+      "step": 1982
+    },
+    {
+      "epoch": 0.8560949298813376,
+      "grad_norm": 0.42978280782699585,
+      "learning_rate": 0.00019772712467445788,
+      "loss": 0.8201018571853638,
+      "step": 1984
+    },
+    {
+      "epoch": 0.856957928802589,
+      "grad_norm": 0.5192655324935913,
+      "learning_rate": 0.00019771670265719454,
+      "loss": 0.9080212116241455,
+      "step": 1986
+    },
+    {
+      "epoch": 0.8578209277238403,
+      "grad_norm": 0.452690452337265,
+      "learning_rate": 0.00019770625707598885,
+      "loss": 0.8518272638320923,
+      "step": 1988
+    },
+    {
+      "epoch": 0.8586839266450917,
+      "grad_norm": 0.4371768832206726,
+      "learning_rate": 0.00019769578793335976,
+      "loss": 0.9426717758178711,
+      "step": 1990
+    },
+    {
+      "epoch": 0.859546925566343,
+      "grad_norm": 0.44595038890838623,
+      "learning_rate": 0.0001976852952318318,
+      "loss": 0.8065400123596191,
+      "step": 1992
+    },
+    {
+      "epoch": 0.8604099244875943,
+      "grad_norm": 0.4355090260505676,
+      "learning_rate": 0.0001976747789739353,
+      "loss": 0.7674415707588196,
+      "step": 1994
+    },
+    {
+      "epoch": 0.8612729234088458,
+      "grad_norm": 0.43745186924934387,
+      "learning_rate": 0.00019766423916220616,
+      "loss": 0.813849925994873,
+      "step": 1996
+    },
+    {
+      "epoch": 0.8621359223300971,
+      "grad_norm": 0.4588927924633026,
+      "learning_rate": 0.00019765367579918598,
+      "loss": 0.7870585322380066,
+      "step": 1998
+    },
+    {
+      "epoch": 0.8629989212513485,
+      "grad_norm": 0.4170977473258972,
+      "learning_rate": 0.00019764308888742214,
+      "loss": 0.8383269309997559,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8629989212513485,
+      "eval_loss": 0.8567262887954712,
+      "eval_runtime": 646.6443,
+      "eval_samples_per_second": 3.186,
+      "eval_steps_per_second": 3.186,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8638619201725998,
+      "grad_norm": 0.4819261431694031,
+      "learning_rate": 0.0001976324784294676,
+      "loss": 0.8261714577674866,
+      "step": 2002
+    },
+    {
+      "epoch": 0.8647249190938512,
+      "grad_norm": 0.4215400218963623,
+      "learning_rate": 0.00019762184442788098,
+      "loss": 0.8493392467498779,
+      "step": 2004
+    },
+    {
+      "epoch": 0.8655879180151025,
+      "grad_norm": 0.45448991656303406,
+      "learning_rate": 0.00019761118688522668,
+      "loss": 0.8645208477973938,
+      "step": 2006
+    },
+    {
+      "epoch": 0.8664509169363538,
+      "grad_norm": 0.4436458349227905,
+      "learning_rate": 0.0001976005058040747,
+      "loss": 0.8816449046134949,
+      "step": 2008
+    },
+    {
+      "epoch": 0.8673139158576052,
+      "grad_norm": 0.42662230134010315,
+      "learning_rate": 0.00019758980118700072,
+      "loss": 0.7622330784797668,
+      "step": 2010
+    },
+    {
+      "epoch": 0.8681769147788565,
+      "grad_norm": 0.3936038613319397,
+      "learning_rate": 0.0001975790730365861,
+      "loss": 0.7843833565711975,
+      "step": 2012
+    },
+    {
+      "epoch": 0.8690399137001079,
+      "grad_norm": 0.4460368752479553,
+      "learning_rate": 0.00019756832135541796,
+      "loss": 0.8294675946235657,
+      "step": 2014
+    },
+    {
+      "epoch": 0.8699029126213592,
+      "grad_norm": 0.47043702006340027,
+      "learning_rate": 0.00019755754614608892,
+      "loss": 0.851332426071167,
+      "step": 2016
+    },
+    {
+      "epoch": 0.8707659115426106,
+      "grad_norm": 0.4579448401927948,
+      "learning_rate": 0.00019754674741119746,
+      "loss": 0.8450362682342529,
+      "step": 2018
+    },
+    {
+      "epoch": 0.8716289104638619,
+      "grad_norm": 0.44362813234329224,
+      "learning_rate": 0.00019753592515334758,
+      "loss": 0.8585519194602966,
+      "step": 2020
+    },
+    {
+      "epoch": 0.8724919093851132,
+      "grad_norm": 0.4500923156738281,
+      "learning_rate": 0.00019752507937514905,
+      "loss": 0.8300179243087769,
+      "step": 2022
+    },
+    {
+      "epoch": 0.8733549083063646,
+      "grad_norm": 0.4330301582813263,
+      "learning_rate": 0.00019751421007921724,
+      "loss": 0.805014431476593,
+      "step": 2024
+    },
+    {
+      "epoch": 0.8742179072276159,
+      "grad_norm": 0.43873998522758484,
+      "learning_rate": 0.00019750331726817332,
+      "loss": 0.8228020071983337,
+      "step": 2026
+    },
+    {
+      "epoch": 0.8750809061488674,
+      "grad_norm": 0.47558829188346863,
+      "learning_rate": 0.00019749240094464395,
+      "loss": 0.8490906357765198,
+      "step": 2028
+    },
+    {
+      "epoch": 0.8759439050701187,
+      "grad_norm": 0.4285199046134949,
+      "learning_rate": 0.0001974814611112616,
+      "loss": 0.816324770450592,
+      "step": 2030
+    },
+    {
+      "epoch": 0.87680690399137,
+      "grad_norm": 0.4762725532054901,
+      "learning_rate": 0.0001974704977706644,
+      "loss": 0.9229121208190918,
+      "step": 2032
+    },
+    {
+      "epoch": 0.8776699029126214,
+      "grad_norm": 0.49856793880462646,
+      "learning_rate": 0.00019745951092549598,
+      "loss": 0.9847140908241272,
+      "step": 2034
+    },
+    {
+      "epoch": 0.8785329018338727,
+      "grad_norm": 0.5163881182670593,
+      "learning_rate": 0.00019744850057840587,
+      "loss": 0.8305321335792542,
+      "step": 2036
+    },
+    {
+      "epoch": 0.8793959007551241,
+      "grad_norm": 0.47826042771339417,
+      "learning_rate": 0.00019743746673204918,
+      "loss": 0.7909449934959412,
+      "step": 2038
+    },
+    {
+      "epoch": 0.8802588996763754,
+      "grad_norm": 0.44080349802970886,
+      "learning_rate": 0.0001974264093890866,
+      "loss": 0.809201180934906,
+      "step": 2040
+    },
+    {
+      "epoch": 0.8811218985976268,
+      "grad_norm": 0.46925660967826843,
+      "learning_rate": 0.00019741532855218464,
+      "loss": 0.8064218163490295,
+      "step": 2042
+    },
+    {
+      "epoch": 0.8819848975188781,
+      "grad_norm": 0.4223597049713135,
+      "learning_rate": 0.00019740422422401531,
+      "loss": 0.8135121464729309,
+      "step": 2044
+    },
+    {
+      "epoch": 0.8828478964401294,
+      "grad_norm": 0.46334266662597656,
+      "learning_rate": 0.00019739309640725642,
+      "loss": 0.8047984838485718,
+      "step": 2046
+    },
+    {
+      "epoch": 0.8837108953613808,
+      "grad_norm": 0.413682222366333,
+      "learning_rate": 0.0001973819451045914,
+      "loss": 0.7897430658340454,
+      "step": 2048
+    },
+    {
+      "epoch": 0.8845738942826321,
+      "grad_norm": 0.4276670515537262,
+      "learning_rate": 0.0001973707703187093,
+      "loss": 0.8411629796028137,
+      "step": 2050
+    },
+    {
+      "epoch": 0.8854368932038835,
+      "grad_norm": 0.4199331998825073,
+      "learning_rate": 0.0001973595720523049,
+      "loss": 0.7906913161277771,
+      "step": 2052
+    },
+    {
+      "epoch": 0.8862998921251348,
+      "grad_norm": 0.43233853578567505,
+      "learning_rate": 0.0001973483503080786,
+      "loss": 0.9042854309082031,
+      "step": 2054
+    },
+    {
+      "epoch": 0.8871628910463862,
+      "grad_norm": 0.41147297620773315,
+      "learning_rate": 0.00019733710508873647,
+      "loss": 0.8177635073661804,
+      "step": 2056
+    },
+    {
+      "epoch": 0.8880258899676375,
+      "grad_norm": 0.45957690477371216,
+      "learning_rate": 0.00019732583639699023,
+      "loss": 0.8867166042327881,
+      "step": 2058
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.3979831635951996,
+      "learning_rate": 0.00019731454423555728,
+      "loss": 0.7208530902862549,
+      "step": 2060
+    },
+    {
+      "epoch": 0.8897518878101403,
+      "grad_norm": 0.4434017837047577,
+      "learning_rate": 0.00019730322860716073,
+      "loss": 0.9158181548118591,
+      "step": 2062
+    },
+    {
+      "epoch": 0.8906148867313916,
+      "grad_norm": 0.40012025833129883,
+      "learning_rate": 0.00019729188951452922,
+      "loss": 0.8103255033493042,
+      "step": 2064
+    },
+    {
+      "epoch": 0.891477885652643,
+      "grad_norm": 0.41914620995521545,
+      "learning_rate": 0.00019728052696039715,
+      "loss": 0.7780100703239441,
+      "step": 2066
+    },
+    {
+      "epoch": 0.8923408845738943,
+      "grad_norm": 0.48365312814712524,
+      "learning_rate": 0.00019726914094750453,
+      "loss": 0.7105780839920044,
+      "step": 2068
+    },
+    {
+      "epoch": 0.8932038834951457,
+      "grad_norm": 0.4272058308124542,
+      "learning_rate": 0.0001972577314785971,
+      "loss": 0.7529635429382324,
+      "step": 2070
+    },
+    {
+      "epoch": 0.894066882416397,
+      "grad_norm": 0.48760271072387695,
+      "learning_rate": 0.00019724629855642612,
+      "loss": 0.836787223815918,
+      "step": 2072
+    },
+    {
+      "epoch": 0.8949298813376483,
+      "grad_norm": 0.47811925411224365,
+      "learning_rate": 0.00019723484218374865,
+      "loss": 0.8773119449615479,
+      "step": 2074
+    },
+    {
+      "epoch": 0.8957928802588997,
+      "grad_norm": 0.40109625458717346,
+      "learning_rate": 0.0001972233623633273,
+      "loss": 0.7151904106140137,
+      "step": 2076
+    },
+    {
+      "epoch": 0.896655879180151,
+      "grad_norm": 0.48640304803848267,
+      "learning_rate": 0.00019721185909793047,
+      "loss": 0.8348540663719177,
+      "step": 2078
+    },
+    {
+      "epoch": 0.8975188781014024,
+      "grad_norm": 0.45748841762542725,
+      "learning_rate": 0.000197200332390332,
+      "loss": 0.845246434211731,
+      "step": 2080
+    },
+    {
+      "epoch": 0.8983818770226537,
+      "grad_norm": 0.41650277376174927,
+      "learning_rate": 0.00019718878224331157,
+      "loss": 0.8746084570884705,
+      "step": 2082
+    },
+    {
+      "epoch": 0.8992448759439051,
+      "grad_norm": 0.45878589153289795,
+      "learning_rate": 0.00019717720865965443,
+      "loss": 0.8252862691879272,
+      "step": 2084
+    },
+    {
+      "epoch": 0.9001078748651564,
+      "grad_norm": 0.3710020184516907,
+      "learning_rate": 0.0001971656116421515,
+      "loss": 0.7056596875190735,
+      "step": 2086
+    },
+    {
+      "epoch": 0.9009708737864077,
+      "grad_norm": 0.4251181185245514,
+      "learning_rate": 0.00019715399119359935,
+      "loss": 0.8305537700653076,
+      "step": 2088
+    },
+    {
+      "epoch": 0.9018338727076591,
+      "grad_norm": 0.48429808020591736,
+      "learning_rate": 0.0001971423473168002,
+      "loss": 0.8431704044342041,
+      "step": 2090
+    },
+    {
+      "epoch": 0.9026968716289104,
+      "grad_norm": 0.5384030342102051,
+      "learning_rate": 0.00019713068001456186,
+      "loss": 0.8311790227890015,
+      "step": 2092
+    },
+    {
+      "epoch": 0.9035598705501618,
+      "grad_norm": 0.452029287815094,
+      "learning_rate": 0.00019711898928969796,
+      "loss": 0.8077114224433899,
+      "step": 2094
+    },
+    {
+      "epoch": 0.9044228694714131,
+      "grad_norm": 0.4427074193954468,
+      "learning_rate": 0.0001971072751450276,
+      "loss": 0.8454164266586304,
+      "step": 2096
+    },
+    {
+      "epoch": 0.9052858683926646,
+      "grad_norm": 0.4895693063735962,
+      "learning_rate": 0.00019709553758337557,
+      "loss": 0.8551414608955383,
+      "step": 2098
+    },
+    {
+      "epoch": 0.9061488673139159,
+      "grad_norm": 0.47199201583862305,
+      "learning_rate": 0.00019708377660757244,
+      "loss": 0.9158598184585571,
+      "step": 2100
+    },
+    {
+      "epoch": 0.9061488673139159,
+      "eval_loss": 0.8524587750434875,
+      "eval_runtime": 655.7682,
+      "eval_samples_per_second": 3.141,
+      "eval_steps_per_second": 3.141,
+      "step": 2100
+    },
+    {
+      "epoch": 0.9070118662351672,
+      "grad_norm": 0.45380064845085144,
+      "learning_rate": 0.00019707199222045415,
+      "loss": 0.8301376700401306,
+      "step": 2102
+    },
+    {
+      "epoch": 0.9078748651564186,
+      "grad_norm": 0.4775148034095764,
+      "learning_rate": 0.00019706018442486255,
+      "loss": 0.8191117644309998,
+      "step": 2104
+    },
+    {
+      "epoch": 0.9087378640776699,
+      "grad_norm": 0.40894538164138794,
+      "learning_rate": 0.00019704835322364506,
+      "loss": 0.8333686590194702,
+      "step": 2106
+    },
+    {
+      "epoch": 0.9096008629989213,
+      "grad_norm": 0.4202065169811249,
+      "learning_rate": 0.00019703649861965467,
+      "loss": 0.7916508913040161,
+      "step": 2108
+    },
+    {
+      "epoch": 0.9104638619201726,
+      "grad_norm": 0.39157143235206604,
+      "learning_rate": 0.00019702462061575008,
+      "loss": 0.8018013834953308,
+      "step": 2110
+    },
+    {
+      "epoch": 0.911326860841424,
+      "grad_norm": 0.4623039662837982,
+      "learning_rate": 0.00019701271921479565,
+      "loss": 0.8819739818572998,
+      "step": 2112
+    },
+    {
+      "epoch": 0.9121898597626753,
+      "grad_norm": 0.45183128118515015,
+      "learning_rate": 0.00019700079441966128,
+      "loss": 0.7652842402458191,
+      "step": 2114
+    },
+    {
+      "epoch": 0.9130528586839266,
+      "grad_norm": 0.4562322795391083,
+      "learning_rate": 0.00019698884623322262,
+      "loss": 0.817150890827179,
+      "step": 2116
+    },
+    {
+      "epoch": 0.913915857605178,
+      "grad_norm": 0.45955994725227356,
+      "learning_rate": 0.00019697687465836095,
+      "loss": 0.8223007917404175,
+      "step": 2118
+    },
+    {
+      "epoch": 0.9147788565264293,
+      "grad_norm": 0.44595572352409363,
+      "learning_rate": 0.00019696487969796307,
+      "loss": 0.7716509699821472,
+      "step": 2120
+    },
+    {
+      "epoch": 0.9156418554476807,
+      "grad_norm": 0.4380198121070862,
+      "learning_rate": 0.00019695286135492163,
+      "loss": 0.8205068111419678,
+      "step": 2122
+    },
+    {
+      "epoch": 0.916504854368932,
+      "grad_norm": 0.4025624692440033,
+      "learning_rate": 0.0001969408196321347,
+      "loss": 0.8126305341720581,
+      "step": 2124
+    },
+    {
+      "epoch": 0.9173678532901833,
+      "grad_norm": 0.424277663230896,
+      "learning_rate": 0.00019692875453250616,
+      "loss": 0.7840806841850281,
+      "step": 2126
+    },
+    {
+      "epoch": 0.9182308522114347,
+      "grad_norm": 0.4683000445365906,
+      "learning_rate": 0.00019691666605894538,
+      "loss": 0.9391030669212341,
+      "step": 2128
+    },
+    {
+      "epoch": 0.919093851132686,
+      "grad_norm": 0.47679048776626587,
+      "learning_rate": 0.00019690455421436754,
+      "loss": 0.8336083889007568,
+      "step": 2130
+    },
+    {
+      "epoch": 0.9199568500539375,
+      "grad_norm": 0.45669928193092346,
+      "learning_rate": 0.00019689241900169323,
+      "loss": 0.917514443397522,
+      "step": 2132
+    },
+    {
+      "epoch": 0.9208198489751888,
+      "grad_norm": 0.4372829794883728,
+      "learning_rate": 0.00019688026042384893,
+      "loss": 0.7798282504081726,
+      "step": 2134
+    },
+    {
+      "epoch": 0.9216828478964402,
+      "grad_norm": 0.4497234523296356,
+      "learning_rate": 0.00019686807848376655,
+      "loss": 0.7415590286254883,
+      "step": 2136
+    },
+    {
+      "epoch": 0.9225458468176915,
+      "grad_norm": 0.4892704486846924,
+      "learning_rate": 0.00019685587318438372,
+      "loss": 0.7713689208030701,
+      "step": 2138
+    },
+    {
+      "epoch": 0.9234088457389428,
+      "grad_norm": 0.490495502948761,
+      "learning_rate": 0.0001968436445286437,
+      "loss": 0.821044385433197,
+      "step": 2140
+    },
+    {
+      "epoch": 0.9242718446601942,
+      "grad_norm": 0.43616363406181335,
+      "learning_rate": 0.00019683139251949538,
+      "loss": 0.796081006526947,
+      "step": 2142
+    },
+    {
+      "epoch": 0.9251348435814455,
+      "grad_norm": 0.4199701249599457,
+      "learning_rate": 0.00019681911715989326,
+      "loss": 0.737835705280304,
+      "step": 2144
+    },
+    {
+      "epoch": 0.9259978425026969,
+      "grad_norm": 0.45367109775543213,
+      "learning_rate": 0.0001968068184527975,
+      "loss": 0.8224935531616211,
+      "step": 2146
+    },
+    {
+      "epoch": 0.9268608414239482,
+      "grad_norm": 0.43349263072013855,
+      "learning_rate": 0.0001967944964011739,
+      "loss": 0.826752245426178,
+      "step": 2148
+    },
+    {
+      "epoch": 0.9277238403451996,
+      "grad_norm": 0.4693690538406372,
+      "learning_rate": 0.00019678215100799384,
+      "loss": 0.8527786731719971,
+      "step": 2150
+    },
+    {
+      "epoch": 0.9285868392664509,
+      "grad_norm": 0.4281991124153137,
+      "learning_rate": 0.00019676978227623434,
+      "loss": 0.8101436495780945,
+      "step": 2152
+    },
+    {
+      "epoch": 0.9294498381877022,
+      "grad_norm": 0.4662301540374756,
+      "learning_rate": 0.0001967573902088781,
+      "loss": 0.8997542262077332,
+      "step": 2154
+    },
+    {
+      "epoch": 0.9303128371089536,
+      "grad_norm": 0.41807958483695984,
+      "learning_rate": 0.0001967449748089134,
+      "loss": 0.8378244638442993,
+      "step": 2156
+    },
+    {
+      "epoch": 0.9311758360302049,
+      "grad_norm": 0.4789344072341919,
+      "learning_rate": 0.00019673253607933416,
+      "loss": 0.8562051057815552,
+      "step": 2158
+    },
+    {
+      "epoch": 0.9320388349514563,
+      "grad_norm": 0.43706783652305603,
+      "learning_rate": 0.0001967200740231399,
+      "loss": 0.78457111120224,
+      "step": 2160
+    },
+    {
+      "epoch": 0.9329018338727076,
+      "grad_norm": 0.4441883862018585,
+      "learning_rate": 0.0001967075886433358,
+      "loss": 0.8058217763900757,
+      "step": 2162
+    },
+    {
+      "epoch": 0.933764832793959,
+      "grad_norm": 0.48960480093955994,
+      "learning_rate": 0.00019669507994293266,
+      "loss": 0.916145384311676,
+      "step": 2164
+    },
+    {
+      "epoch": 0.9346278317152104,
+      "grad_norm": 0.3990147113800049,
+      "learning_rate": 0.00019668254792494692,
+      "loss": 0.8805235028266907,
+      "step": 2166
+    },
+    {
+      "epoch": 0.9354908306364617,
+      "grad_norm": 0.4299201965332031,
+      "learning_rate": 0.00019666999259240056,
+      "loss": 0.8611101508140564,
+      "step": 2168
+    },
+    {
+      "epoch": 0.9363538295577131,
+      "grad_norm": 0.5267254114151001,
+      "learning_rate": 0.00019665741394832132,
+      "loss": 0.8429995179176331,
+      "step": 2170
+    },
+    {
+      "epoch": 0.9372168284789644,
+      "grad_norm": 0.46667975187301636,
+      "learning_rate": 0.0001966448119957424,
+      "loss": 0.8057775497436523,
+      "step": 2172
+    },
+    {
+      "epoch": 0.9380798274002158,
+      "grad_norm": 0.4140365421772003,
+      "learning_rate": 0.00019663218673770277,
+      "loss": 0.7456767559051514,
+      "step": 2174
+    },
+    {
+      "epoch": 0.9389428263214671,
+      "grad_norm": 0.4236559569835663,
+      "learning_rate": 0.00019661953817724692,
+      "loss": 0.7320394515991211,
+      "step": 2176
+    },
+    {
+      "epoch": 0.9398058252427185,
+      "grad_norm": 0.4075721800327301,
+      "learning_rate": 0.000196606866317425,
+      "loss": 0.7850301265716553,
+      "step": 2178
+    },
+    {
+      "epoch": 0.9406688241639698,
+      "grad_norm": 0.4638446271419525,
+      "learning_rate": 0.00019659417116129276,
+      "loss": 0.8228051662445068,
+      "step": 2180
+    },
+    {
+      "epoch": 0.9415318230852211,
+      "grad_norm": 0.4641942083835602,
+      "learning_rate": 0.00019658145271191164,
+      "loss": 0.8458912372589111,
+      "step": 2182
+    },
+    {
+      "epoch": 0.9423948220064725,
+      "grad_norm": 0.42868348956108093,
+      "learning_rate": 0.00019656871097234856,
+      "loss": 0.8002372980117798,
+      "step": 2184
+    },
+    {
+      "epoch": 0.9432578209277238,
+      "grad_norm": 0.4726828336715698,
+      "learning_rate": 0.00019655594594567615,
+      "loss": 0.9096182584762573,
+      "step": 2186
+    },
+    {
+      "epoch": 0.9441208198489752,
+      "grad_norm": 0.40363940596580505,
+      "learning_rate": 0.00019654315763497265,
+      "loss": 0.7508110404014587,
+      "step": 2188
+    },
+    {
+      "epoch": 0.9449838187702265,
+      "grad_norm": 0.46951010823249817,
+      "learning_rate": 0.00019653034604332192,
+      "loss": 0.8898510932922363,
+      "step": 2190
+    },
+    {
+      "epoch": 0.9458468176914779,
+      "grad_norm": 0.4564061164855957,
+      "learning_rate": 0.0001965175111738134,
+      "loss": 0.8604891896247864,
+      "step": 2192
+    },
+    {
+      "epoch": 0.9467098166127292,
+      "grad_norm": 0.4366895854473114,
+      "learning_rate": 0.00019650465302954219,
+      "loss": 0.8314935564994812,
+      "step": 2194
+    },
+    {
+      "epoch": 0.9475728155339805,
+      "grad_norm": 0.541490375995636,
+      "learning_rate": 0.0001964917716136089,
+      "loss": 0.851138174533844,
+      "step": 2196
+    },
+    {
+      "epoch": 0.948435814455232,
+      "grad_norm": 0.45251160860061646,
+      "learning_rate": 0.0001964788669291199,
+      "loss": 0.9248369336128235,
+      "step": 2198
+    },
+    {
+      "epoch": 0.9492988133764833,
+      "grad_norm": 0.46237683296203613,
+      "learning_rate": 0.00019646593897918707,
+      "loss": 0.8113608956336975,
+      "step": 2200
+    },
+    {
+      "epoch": 0.9492988133764833,
+      "eval_loss": 0.8443478941917419,
+      "eval_runtime": 666.5866,
+      "eval_samples_per_second": 3.09,
+      "eval_steps_per_second": 3.09,
+      "step": 2200
+    },
+    {
+      "epoch": 0.9501618122977347,
+      "grad_norm": 0.4506337344646454,
+      "learning_rate": 0.0001964529877669279,
+      "loss": 0.8151772618293762,
+      "step": 2202
+    },
+    {
+      "epoch": 0.951024811218986,
+      "grad_norm": 0.42866984009742737,
+      "learning_rate": 0.00019644001329546557,
+      "loss": 0.920696496963501,
+      "step": 2204
+    },
+    {
+      "epoch": 0.9518878101402374,
+      "grad_norm": 0.3899093270301819,
+      "learning_rate": 0.00019642701556792878,
+      "loss": 0.8228384256362915,
+      "step": 2206
+    },
+    {
+      "epoch": 0.9527508090614887,
+      "grad_norm": 0.42472460865974426,
+      "learning_rate": 0.00019641399458745186,
+      "loss": 0.7483987808227539,
+      "step": 2208
+    },
+    {
+      "epoch": 0.95361380798274,
+      "grad_norm": 0.4046783447265625,
+      "learning_rate": 0.00019640095035717482,
+      "loss": 0.7356619834899902,
+      "step": 2210
+    },
+    {
+      "epoch": 0.9544768069039914,
+      "grad_norm": 0.4608006179332733,
+      "learning_rate": 0.00019638788288024316,
+      "loss": 0.7374731302261353,
+      "step": 2212
+    },
+    {
+      "epoch": 0.9553398058252427,
+      "grad_norm": 0.448503315448761,
+      "learning_rate": 0.00019637479215980807,
+      "loss": 0.9128687977790833,
+      "step": 2214
+    },
+    {
+      "epoch": 0.9562028047464941,
+      "grad_norm": 0.4477374851703644,
+      "learning_rate": 0.0001963616781990263,
+      "loss": 0.6983766555786133,
+      "step": 2216
+    },
+    {
+      "epoch": 0.9570658036677454,
+      "grad_norm": 0.41463667154312134,
+      "learning_rate": 0.00019634854100106025,
+      "loss": 0.8543318510055542,
+      "step": 2218
+    },
+    {
+      "epoch": 0.9579288025889967,
+      "grad_norm": 0.5271132588386536,
+      "learning_rate": 0.00019633538056907786,
+      "loss": 0.8866401314735413,
+      "step": 2220
+    },
+    {
+      "epoch": 0.9587918015102481,
+      "grad_norm": 0.4496590495109558,
+      "learning_rate": 0.00019632219690625272,
+      "loss": 0.8414724469184875,
+      "step": 2222
+    },
+    {
+      "epoch": 0.9596548004314994,
+      "grad_norm": 0.4772113263607025,
+      "learning_rate": 0.00019630899001576405,
+      "loss": 0.8859618902206421,
+      "step": 2224
+    },
+    {
+      "epoch": 0.9605177993527508,
+      "grad_norm": 0.5249642729759216,
+      "learning_rate": 0.0001962957599007966,
+      "loss": 0.8347851037979126,
+      "step": 2226
+    },
+    {
+      "epoch": 0.9613807982740021,
+      "grad_norm": 0.4931469261646271,
+      "learning_rate": 0.0001962825065645407,
+      "loss": 0.7893235087394714,
+      "step": 2228
+    },
+    {
+      "epoch": 0.9622437971952535,
+      "grad_norm": 0.45010602474212646,
+      "learning_rate": 0.00019626923001019245,
+      "loss": 0.815602719783783,
+      "step": 2230
+    },
+    {
+      "epoch": 0.9631067961165048,
+      "grad_norm": 0.42947128415107727,
+      "learning_rate": 0.00019625593024095333,
+      "loss": 0.807309627532959,
+      "step": 2232
+    },
+    {
+      "epoch": 0.9639697950377561,
+      "grad_norm": 0.43500378727912903,
+      "learning_rate": 0.00019624260726003057,
+      "loss": 0.8135440945625305,
+      "step": 2234
+    },
+    {
+      "epoch": 0.9648327939590076,
+      "grad_norm": 0.41840270161628723,
+      "learning_rate": 0.00019622926107063692,
+      "loss": 0.802107036113739,
+      "step": 2236
+    },
+    {
+      "epoch": 0.9656957928802589,
+      "grad_norm": 0.4580598771572113,
+      "learning_rate": 0.00019621589167599077,
+      "loss": 0.7596800923347473,
+      "step": 2238
+    },
+    {
+      "epoch": 0.9665587918015103,
+      "grad_norm": 0.38064274191856384,
+      "learning_rate": 0.0001962024990793161,
+      "loss": 0.7609489560127258,
+      "step": 2240
+    },
+    {
+      "epoch": 0.9674217907227616,
+      "grad_norm": 0.39098140597343445,
+      "learning_rate": 0.00019618908328384246,
+      "loss": 0.7829734086990356,
+      "step": 2242
+    },
+    {
+      "epoch": 0.968284789644013,
+      "grad_norm": 0.38412022590637207,
+      "learning_rate": 0.00019617564429280502,
+      "loss": 0.7570722699165344,
+      "step": 2244
+    },
+    {
+      "epoch": 0.9691477885652643,
+      "grad_norm": 0.41451776027679443,
+      "learning_rate": 0.0001961621821094445,
+      "loss": 0.8634825348854065,
+      "step": 2246
+    },
+    {
+      "epoch": 0.9700107874865156,
+      "grad_norm": 0.4989950954914093,
+      "learning_rate": 0.00019614869673700725,
+      "loss": 0.9002810120582581,
+      "step": 2248
+    },
+    {
+      "epoch": 0.970873786407767,
+      "grad_norm": 0.4316846430301666,
+      "learning_rate": 0.00019613518817874524,
+      "loss": 0.7587819695472717,
+      "step": 2250
+    },
+    {
+      "epoch": 0.9717367853290183,
+      "grad_norm": 0.41293349862098694,
+      "learning_rate": 0.000196121656437916,
+      "loss": 0.686238706111908,
+      "step": 2252
+    },
+    {
+      "epoch": 0.9725997842502697,
+      "grad_norm": 0.40252262353897095,
+      "learning_rate": 0.00019610810151778258,
+      "loss": 0.7895162105560303,
+      "step": 2254
+    },
+    {
+      "epoch": 0.973462783171521,
+      "grad_norm": 0.42973560094833374,
+      "learning_rate": 0.0001960945234216138,
+      "loss": 0.8360300064086914,
+      "step": 2256
+    },
+    {
+      "epoch": 0.9743257820927724,
+      "grad_norm": 0.40562206506729126,
+      "learning_rate": 0.00019608092215268386,
+      "loss": 0.7624704241752625,
+      "step": 2258
+    },
+    {
+      "epoch": 0.9751887810140237,
+      "grad_norm": 0.4486660063266754,
+      "learning_rate": 0.00019606729771427266,
+      "loss": 0.8285008072853088,
+      "step": 2260
+    },
+    {
+      "epoch": 0.976051779935275,
+      "grad_norm": 0.37069520354270935,
+      "learning_rate": 0.0001960536501096657,
+      "loss": 0.7951943278312683,
+      "step": 2262
+    },
+    {
+      "epoch": 0.9769147788565264,
+      "grad_norm": 0.43367981910705566,
+      "learning_rate": 0.00019603997934215404,
+      "loss": 0.7641335129737854,
+      "step": 2264
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.42540937662124634,
+      "learning_rate": 0.00019602628541503432,
+      "loss": 0.8449530601501465,
+      "step": 2266
+    },
+    {
+      "epoch": 0.9786407766990292,
+      "grad_norm": 0.46175941824913025,
+      "learning_rate": 0.00019601256833160874,
+      "loss": 0.8207030296325684,
+      "step": 2268
+    },
+    {
+      "epoch": 0.9795037756202805,
+      "grad_norm": 0.3834969103336334,
+      "learning_rate": 0.00019599882809518513,
+      "loss": 0.7753700017929077,
+      "step": 2270
+    },
+    {
+      "epoch": 0.9803667745415319,
+      "grad_norm": 0.43960243463516235,
+      "learning_rate": 0.0001959850647090769,
+      "loss": 0.8844934701919556,
+      "step": 2272
+    },
+    {
+      "epoch": 0.9812297734627832,
+      "grad_norm": 0.4240610897541046,
+      "learning_rate": 0.00019597127817660303,
+      "loss": 0.7795814275741577,
+      "step": 2274
+    },
+    {
+      "epoch": 0.9820927723840345,
+      "grad_norm": 0.41870981454849243,
+      "learning_rate": 0.00019595746850108807,
+      "loss": 0.6960644721984863,
+      "step": 2276
+    },
+    {
+      "epoch": 0.9829557713052859,
+      "grad_norm": 0.43871861696243286,
+      "learning_rate": 0.00019594363568586215,
+      "loss": 0.7709649205207825,
+      "step": 2278
+    },
+    {
+      "epoch": 0.9838187702265372,
+      "grad_norm": 0.45331820845603943,
+      "learning_rate": 0.00019592977973426098,
+      "loss": 0.7324449419975281,
+      "step": 2280
+    },
+    {
+      "epoch": 0.9846817691477886,
+      "grad_norm": 0.4300173223018646,
+      "learning_rate": 0.00019591590064962593,
+      "loss": 0.8720724582672119,
+      "step": 2282
+    },
+    {
+      "epoch": 0.9855447680690399,
+      "grad_norm": 0.4478892982006073,
+      "learning_rate": 0.0001959019984353038,
+      "loss": 0.7396156191825867,
+      "step": 2284
+    },
+    {
+      "epoch": 0.9864077669902913,
+      "grad_norm": 0.4391026198863983,
+      "learning_rate": 0.00019588807309464708,
+      "loss": 0.8303509950637817,
+      "step": 2286
+    },
+    {
+      "epoch": 0.9872707659115426,
+      "grad_norm": 0.4046599268913269,
+      "learning_rate": 0.00019587412463101378,
+      "loss": 0.739641010761261,
+      "step": 2288
+    },
+    {
+      "epoch": 0.9881337648327939,
+      "grad_norm": 0.4619915187358856,
+      "learning_rate": 0.00019586015304776756,
+      "loss": 0.7448247671127319,
+      "step": 2290
+    },
+    {
+      "epoch": 0.9889967637540453,
+      "grad_norm": 0.4603526294231415,
+      "learning_rate": 0.00019584615834827753,
+      "loss": 0.8184107542037964,
+      "step": 2292
+    },
+    {
+      "epoch": 0.9898597626752966,
+      "grad_norm": 0.4828874170780182,
+      "learning_rate": 0.00019583214053591852,
+      "loss": 0.9069648385047913,
+      "step": 2294
+    },
+    {
+      "epoch": 0.990722761596548,
+      "grad_norm": 0.37467876076698303,
+      "learning_rate": 0.00019581809961407082,
+      "loss": 0.6628880500793457,
+      "step": 2296
+    },
+    {
+      "epoch": 0.9915857605177993,
+      "grad_norm": 0.4300445318222046,
+      "learning_rate": 0.00019580403558612037,
+      "loss": 0.7712231278419495,
+      "step": 2298
+    },
+    {
+      "epoch": 0.9924487594390508,
+      "grad_norm": 0.4368257522583008,
+      "learning_rate": 0.00019578994845545863,
+      "loss": 0.7796293497085571,
+      "step": 2300
+    },
+    {
+      "epoch": 0.9924487594390508,
+      "eval_loss": 0.839731752872467,
+      "eval_runtime": 666.2332,
+      "eval_samples_per_second": 3.092,
+      "eval_steps_per_second": 3.092,
+      "step": 2300
+    },
+    {
+      "epoch": 0.993311758360302,
+      "grad_norm": 0.4383920729160309,
+      "learning_rate": 0.00019577583822548262,
+      "loss": 0.7504367232322693,
+      "step": 2302
+    },
+    {
+      "epoch": 0.9941747572815534,
+      "grad_norm": 0.3895981013774872,
+      "learning_rate": 0.00019576170489959496,
+      "loss": 0.7298936247825623,
+      "step": 2304
+    },
+    {
+      "epoch": 0.9950377562028048,
+      "grad_norm": 0.4950196444988251,
+      "learning_rate": 0.00019574754848120392,
+      "loss": 0.9137371778488159,
+      "step": 2306
+    },
+    {
+      "epoch": 0.9959007551240561,
+      "grad_norm": 0.5115531086921692,
+      "learning_rate": 0.00019573336897372318,
+      "loss": 0.9203279614448547,
+      "step": 2308
+    },
+    {
+      "epoch": 0.9967637540453075,
+      "grad_norm": 0.43145665526390076,
+      "learning_rate": 0.000195719166380572,
+      "loss": 0.7708958387374878,
+      "step": 2310
+    },
+    {
+      "epoch": 0.9976267529665588,
+      "grad_norm": 0.39575520157814026,
+      "learning_rate": 0.00019570494070517545,
+      "loss": 0.7911062836647034,
+      "step": 2312
+    },
+    {
+      "epoch": 0.9984897518878102,
+      "grad_norm": 0.45690420269966125,
+      "learning_rate": 0.00019569069195096386,
+      "loss": 0.8282244205474854,
+      "step": 2314
+    },
+    {
+      "epoch": 0.9993527508090615,
+      "grad_norm": 0.43362128734588623,
+      "learning_rate": 0.00019567642012137325,
+      "loss": 0.8658884763717651,
+      "step": 2316
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6889842748641968,
+      "learning_rate": 0.00019566212521984527,
+      "loss": 0.7823468446731567,
+      "step": 2318
+    },
+    {
+      "epoch": 1.0008629989212514,
+      "grad_norm": 0.3945363759994507,
+      "learning_rate": 0.00019564780724982706,
+      "loss": 0.8244057297706604,
+      "step": 2320
+    },
+    {
+      "epoch": 1.0017259978425026,
+      "grad_norm": 0.5313655734062195,
+      "learning_rate": 0.00019563346621477129,
+      "loss": 0.8228418827056885,
+      "step": 2322
+    },
+    {
+      "epoch": 1.002588996763754,
+      "grad_norm": 0.47728294134140015,
+      "learning_rate": 0.00019561910211813625,
+      "loss": 0.8627800941467285,
+      "step": 2324
+    },
+    {
+      "epoch": 1.0034519956850054,
+      "grad_norm": 0.4706253111362457,
+      "learning_rate": 0.00019560471496338582,
+      "loss": 0.8810665011405945,
+      "step": 2326
+    },
+    {
+      "epoch": 1.0043149946062568,
+      "grad_norm": 0.4333725571632385,
+      "learning_rate": 0.0001955903047539893,
+      "loss": 0.7736411094665527,
+      "step": 2328
+    },
+    {
+      "epoch": 1.005177993527508,
+      "grad_norm": 0.49580323696136475,
+      "learning_rate": 0.00019557587149342178,
+      "loss": 0.9185295104980469,
+      "step": 2330
+    },
+    {
+      "epoch": 1.0060409924487594,
+      "grad_norm": 0.4362829029560089,
+      "learning_rate": 0.0001955614151851637,
+      "loss": 0.7387797832489014,
+      "step": 2332
+    },
+    {
+      "epoch": 1.0069039913700109,
+      "grad_norm": 0.42584139108657837,
+      "learning_rate": 0.00019554693583270113,
+      "loss": 0.672156810760498,
+      "step": 2334
+    },
+    {
+      "epoch": 1.007766990291262,
+      "grad_norm": 0.40073466300964355,
+      "learning_rate": 0.0001955324334395257,
+      "loss": 0.7638119459152222,
+      "step": 2336
+    },
+    {
+      "epoch": 1.0086299892125135,
+      "grad_norm": 0.49992597103118896,
+      "learning_rate": 0.00019551790800913458,
+      "loss": 0.7930200695991516,
+      "step": 2338
+    },
+    {
+      "epoch": 1.0094929881337649,
+      "grad_norm": 0.3825504779815674,
+      "learning_rate": 0.00019550335954503058,
+      "loss": 0.7128595113754272,
+      "step": 2340
+    },
+    {
+      "epoch": 1.0103559870550163,
+      "grad_norm": 0.4654180705547333,
+      "learning_rate": 0.00019548878805072196,
+      "loss": 0.7130335569381714,
+      "step": 2342
+    },
+    {
+      "epoch": 1.0112189859762675,
+      "grad_norm": 0.4199283719062805,
+      "learning_rate": 0.00019547419352972258,
+      "loss": 0.7843249440193176,
+      "step": 2344
+    },
+    {
+      "epoch": 1.0120819848975189,
+      "grad_norm": 0.43597257137298584,
+      "learning_rate": 0.0001954595759855518,
+      "loss": 0.676262617111206,
+      "step": 2346
+    },
+    {
+      "epoch": 1.0129449838187703,
+      "grad_norm": 0.47415891289711,
+      "learning_rate": 0.0001954449354217346,
+      "loss": 0.742564857006073,
+      "step": 2348
+    },
+    {
+      "epoch": 1.0138079827400215,
+      "grad_norm": 0.44753482937812805,
+      "learning_rate": 0.00019543027184180153,
+      "loss": 0.7419085502624512,
+      "step": 2350
+    },
+    {
+      "epoch": 1.014670981661273,
+      "grad_norm": 0.4175751209259033,
+      "learning_rate": 0.0001954155852492886,
+      "loss": 0.7373939752578735,
+      "step": 2352
+    },
+    {
+      "epoch": 1.0155339805825243,
+      "grad_norm": 0.40376800298690796,
+      "learning_rate": 0.00019540087564773738,
+      "loss": 0.7639825344085693,
+      "step": 2354
+    },
+    {
+      "epoch": 1.0163969795037757,
+      "grad_norm": 0.4166127145290375,
+      "learning_rate": 0.0001953861430406951,
+      "loss": 0.7797452211380005,
+      "step": 2356
+    },
+    {
+      "epoch": 1.017259978425027,
+      "grad_norm": 0.4340934753417969,
+      "learning_rate": 0.0001953713874317144,
+      "loss": 0.8258501887321472,
+      "step": 2358
+    },
+    {
+      "epoch": 1.0181229773462783,
+      "grad_norm": 0.47081413865089417,
+      "learning_rate": 0.0001953566088243536,
+      "loss": 0.7664495706558228,
+      "step": 2360
+    },
+    {
+      "epoch": 1.0189859762675297,
+      "grad_norm": 0.4126851260662079,
+      "learning_rate": 0.00019534180722217644,
+      "loss": 0.7411028742790222,
+      "step": 2362
+    },
+    {
+      "epoch": 1.019848975188781,
+      "grad_norm": 0.45279955863952637,
+      "learning_rate": 0.00019532698262875227,
+      "loss": 0.7514335513114929,
+      "step": 2364
+    },
+    {
+      "epoch": 1.0207119741100323,
+      "grad_norm": 0.4857143461704254,
+      "learning_rate": 0.00019531213504765595,
+      "loss": 0.7544763088226318,
+      "step": 2366
+    },
+    {
+      "epoch": 1.0215749730312838,
+      "grad_norm": 0.5232970714569092,
+      "learning_rate": 0.00019529726448246795,
+      "loss": 0.7246702313423157,
+      "step": 2368
+    },
+    {
+      "epoch": 1.0224379719525352,
+      "grad_norm": 0.4434663653373718,
+      "learning_rate": 0.00019528237093677424,
+      "loss": 0.7399187684059143,
+      "step": 2370
+    },
+    {
+      "epoch": 1.0233009708737864,
+      "grad_norm": 0.44713014364242554,
+      "learning_rate": 0.0001952674544141663,
+      "loss": 0.7208506464958191,
+      "step": 2372
+    },
+    {
+      "epoch": 1.0241639697950378,
+      "grad_norm": 0.43205446004867554,
+      "learning_rate": 0.0001952525149182412,
+      "loss": 0.761768639087677,
+      "step": 2374
+    },
+    {
+      "epoch": 1.0250269687162892,
+      "grad_norm": 0.4322265386581421,
+      "learning_rate": 0.0001952375524526015,
+      "loss": 0.6573513746261597,
+      "step": 2376
+    },
+    {
+      "epoch": 1.0258899676375404,
+      "grad_norm": 0.4776996970176697,
+      "learning_rate": 0.0001952225670208554,
+      "loss": 0.8118118047714233,
+      "step": 2378
+    },
+    {
+      "epoch": 1.0267529665587918,
+      "grad_norm": 0.5014623403549194,
+      "learning_rate": 0.00019520755862661648,
+      "loss": 0.781197190284729,
+      "step": 2380
+    },
+    {
+      "epoch": 1.0276159654800432,
+      "grad_norm": 0.5164223313331604,
+      "learning_rate": 0.00019519252727350403,
+      "loss": 0.8399010896682739,
+      "step": 2382
+    },
+    {
+      "epoch": 1.0284789644012946,
+      "grad_norm": 0.47874927520751953,
+      "learning_rate": 0.00019517747296514276,
+      "loss": 0.786519467830658,
+      "step": 2384
+    },
+    {
+      "epoch": 1.0293419633225458,
+      "grad_norm": 0.48447099328041077,
+      "learning_rate": 0.00019516239570516292,
+      "loss": 0.7837404012680054,
+      "step": 2386
+    },
+    {
+      "epoch": 1.0302049622437972,
+      "grad_norm": 0.4762440323829651,
+      "learning_rate": 0.0001951472954972004,
+      "loss": 0.833958625793457,
+      "step": 2388
+    },
+    {
+      "epoch": 1.0310679611650486,
+      "grad_norm": 0.42814165353775024,
+      "learning_rate": 0.00019513217234489645,
+      "loss": 0.7688734531402588,
+      "step": 2390
+    },
+    {
+      "epoch": 1.0319309600862998,
+      "grad_norm": 0.4784977436065674,
+      "learning_rate": 0.00019511702625189803,
+      "loss": 0.814251720905304,
+      "step": 2392
+    },
+    {
+      "epoch": 1.0327939590075512,
+      "grad_norm": 0.44989243149757385,
+      "learning_rate": 0.00019510185722185748,
+      "loss": 0.7277538180351257,
+      "step": 2394
+    },
+    {
+      "epoch": 1.0336569579288026,
+      "grad_norm": 0.5141931772232056,
+      "learning_rate": 0.0001950866652584328,
+      "loss": 0.844467282295227,
+      "step": 2396
+    },
+    {
+      "epoch": 1.0345199568500538,
+      "grad_norm": 0.48569414019584656,
+      "learning_rate": 0.00019507145036528747,
+      "loss": 0.7662147879600525,
+      "step": 2398
+    },
+    {
+      "epoch": 1.0353829557713052,
+      "grad_norm": 0.5075576901435852,
+      "learning_rate": 0.00019505621254609047,
+      "loss": 0.7628200054168701,
+      "step": 2400
+    },
+    {
+      "epoch": 1.0353829557713052,
+      "eval_loss": 0.8369861245155334,
+      "eval_runtime": 653.1661,
+      "eval_samples_per_second": 3.154,
+      "eval_steps_per_second": 3.154,
+      "step": 2400
+    },
+    {
+      "epoch": 1.0362459546925566,
+      "grad_norm": 0.49423643946647644,
+      "learning_rate": 0.00019504095180451628,
+      "loss": 0.8225719332695007,
+      "step": 2402
+    },
+    {
+      "epoch": 1.037108953613808,
+      "grad_norm": 0.4558854401111603,
+      "learning_rate": 0.00019502566814424505,
+      "loss": 0.8239169120788574,
+      "step": 2404
+    },
+    {
+      "epoch": 1.0379719525350593,
+      "grad_norm": 0.4864993691444397,
+      "learning_rate": 0.00019501036156896232,
+      "loss": 0.7805002331733704,
+      "step": 2406
+    },
+    {
+      "epoch": 1.0388349514563107,
+      "grad_norm": 0.44108837842941284,
+      "learning_rate": 0.00019499503208235918,
+      "loss": 0.866910994052887,
+      "step": 2408
+    },
+    {
+      "epoch": 1.039697950377562,
+      "grad_norm": 0.4616626799106598,
+      "learning_rate": 0.00019497967968813232,
+      "loss": 0.7601662874221802,
+      "step": 2410
+    },
+    {
+      "epoch": 1.0405609492988135,
+      "grad_norm": 0.4792969524860382,
+      "learning_rate": 0.00019496430438998387,
+      "loss": 0.8155668377876282,
+      "step": 2412
+    },
+    {
+      "epoch": 1.0414239482200647,
+      "grad_norm": 0.45400261878967285,
+      "learning_rate": 0.00019494890619162152,
+      "loss": 0.7879545092582703,
+      "step": 2414
+    },
+    {
+      "epoch": 1.042286947141316,
+      "grad_norm": 0.44541165232658386,
+      "learning_rate": 0.0001949334850967585,
+      "loss": 0.7196864485740662,
+      "step": 2416
+    },
+    {
+      "epoch": 1.0431499460625675,
+      "grad_norm": 0.44515085220336914,
+      "learning_rate": 0.00019491804110911343,
+      "loss": 0.7288097739219666,
+      "step": 2418
+    },
+    {
+      "epoch": 1.0440129449838187,
+      "grad_norm": 0.43586596846580505,
+      "learning_rate": 0.0001949025742324107,
+      "loss": 0.7182422280311584,
+      "step": 2420
+    },
+    {
+      "epoch": 1.04487594390507,
+      "grad_norm": 0.44399815797805786,
+      "learning_rate": 0.00019488708447038002,
+      "loss": 0.7005030512809753,
+      "step": 2422
+    },
+    {
+      "epoch": 1.0457389428263215,
+      "grad_norm": 0.4658401310443878,
+      "learning_rate": 0.00019487157182675665,
+      "loss": 0.715505063533783,
+      "step": 2424
+    },
+    {
+      "epoch": 1.0466019417475727,
+      "grad_norm": 0.4468056261539459,
+      "learning_rate": 0.00019485603630528143,
+      "loss": 0.7170135974884033,
+      "step": 2426
+    },
+    {
+      "epoch": 1.0474649406688241,
+      "grad_norm": 0.5302334427833557,
+      "learning_rate": 0.00019484047790970066,
+      "loss": 0.83464115858078,
+      "step": 2428
+    },
+    {
+      "epoch": 1.0483279395900755,
+      "grad_norm": 0.46583443880081177,
+      "learning_rate": 0.0001948248966437662,
+      "loss": 0.7129145264625549,
+      "step": 2430
+    },
+    {
+      "epoch": 1.049190938511327,
+      "grad_norm": 0.38922831416130066,
+      "learning_rate": 0.0001948092925112354,
+      "loss": 0.7990599870681763,
+      "step": 2432
+    },
+    {
+      "epoch": 1.0500539374325781,
+      "grad_norm": 0.4599211513996124,
+      "learning_rate": 0.00019479366551587108,
+      "loss": 0.8572773933410645,
+      "step": 2434
+    },
+    {
+      "epoch": 1.0509169363538295,
+      "grad_norm": 0.47514498233795166,
+      "learning_rate": 0.00019477801566144165,
+      "loss": 0.8107781410217285,
+      "step": 2436
+    },
+    {
+      "epoch": 1.051779935275081,
+      "grad_norm": 0.41368064284324646,
+      "learning_rate": 0.00019476234295172102,
+      "loss": 0.7433347702026367,
+      "step": 2438
+    },
+    {
+      "epoch": 1.0526429341963321,
+      "grad_norm": 0.4666398763656616,
+      "learning_rate": 0.00019474664739048858,
+      "loss": 0.8033983111381531,
+      "step": 2440
+    },
+    {
+      "epoch": 1.0535059331175836,
+      "grad_norm": 0.41621699929237366,
+      "learning_rate": 0.00019473092898152924,
+      "loss": 0.7320330142974854,
+      "step": 2442
+    },
+    {
+      "epoch": 1.054368932038835,
+      "grad_norm": 0.43523117899894714,
+      "learning_rate": 0.00019471518772863343,
+      "loss": 0.7742927074432373,
+      "step": 2444
+    },
+    {
+      "epoch": 1.0552319309600864,
+      "grad_norm": 0.5151914358139038,
+      "learning_rate": 0.0001946994236355971,
+      "loss": 0.8301699161529541,
+      "step": 2446
+    },
+    {
+      "epoch": 1.0560949298813376,
+      "grad_norm": 0.566112756729126,
+      "learning_rate": 0.0001946836367062216,
+      "loss": 0.837057888507843,
+      "step": 2448
+    },
+    {
+      "epoch": 1.056957928802589,
+      "grad_norm": 0.4257231652736664,
+      "learning_rate": 0.00019466782694431398,
+      "loss": 0.7323788404464722,
+      "step": 2450
+    },
+    {
+      "epoch": 1.0578209277238404,
+      "grad_norm": 0.5477433800697327,
+      "learning_rate": 0.0001946519943536867,
+      "loss": 0.7410078048706055,
+      "step": 2452
+    },
+    {
+      "epoch": 1.0586839266450916,
+      "grad_norm": 0.37357097864151,
+      "learning_rate": 0.00019463613893815762,
+      "loss": 0.6646532416343689,
+      "step": 2454
+    },
+    {
+      "epoch": 1.059546925566343,
+      "grad_norm": 0.438048779964447,
+      "learning_rate": 0.00019462026070155028,
+      "loss": 0.7773549556732178,
+      "step": 2456
+    },
+    {
+      "epoch": 1.0604099244875944,
+      "grad_norm": 0.5114307999610901,
+      "learning_rate": 0.0001946043596476936,
+      "loss": 0.8977773785591125,
+      "step": 2458
+    },
+    {
+      "epoch": 1.0612729234088458,
+      "grad_norm": 0.4340408146381378,
+      "learning_rate": 0.0001945884357804221,
+      "loss": 0.8128405809402466,
+      "step": 2460
+    },
+    {
+      "epoch": 1.062135922330097,
+      "grad_norm": 0.4922826290130615,
+      "learning_rate": 0.0001945724891035757,
+      "loss": 0.8096795678138733,
+      "step": 2462
+    },
+    {
+      "epoch": 1.0629989212513484,
+      "grad_norm": 0.47231894731521606,
+      "learning_rate": 0.00019455651962099987,
+      "loss": 0.7965760231018066,
+      "step": 2464
+    },
+    {
+      "epoch": 1.0638619201725998,
+      "grad_norm": 0.4519463777542114,
+      "learning_rate": 0.00019454052733654565,
+      "loss": 0.7136726975440979,
+      "step": 2466
+    },
+    {
+      "epoch": 1.064724919093851,
+      "grad_norm": 0.44883614778518677,
+      "learning_rate": 0.0001945245122540694,
+      "loss": 0.8136170506477356,
+      "step": 2468
+    },
+    {
+      "epoch": 1.0655879180151024,
+      "grad_norm": 0.4224080741405487,
+      "learning_rate": 0.00019450847437743317,
+      "loss": 0.7840399146080017,
+      "step": 2470
+    },
+    {
+      "epoch": 1.0664509169363539,
+      "grad_norm": 0.4979367256164551,
+      "learning_rate": 0.00019449241371050438,
+      "loss": 0.8202947378158569,
+      "step": 2472
+    },
+    {
+      "epoch": 1.0673139158576053,
+      "grad_norm": 0.5551356673240662,
+      "learning_rate": 0.000194476330257156,
+      "loss": 0.8608070611953735,
+      "step": 2474
+    },
+    {
+      "epoch": 1.0681769147788565,
+      "grad_norm": 0.3980900049209595,
+      "learning_rate": 0.00019446022402126647,
+      "loss": 0.7202636003494263,
+      "step": 2476
+    },
+    {
+      "epoch": 1.0690399137001079,
+      "grad_norm": 0.5393417477607727,
+      "learning_rate": 0.00019444409500671977,
+      "loss": 0.8301891684532166,
+      "step": 2478
+    },
+    {
+      "epoch": 1.0699029126213593,
+      "grad_norm": 0.47717350721359253,
+      "learning_rate": 0.0001944279432174053,
+      "loss": 0.700567901134491,
+      "step": 2480
+    },
+    {
+      "epoch": 1.0707659115426105,
+      "grad_norm": 0.5197957158088684,
+      "learning_rate": 0.000194411768657218,
+      "loss": 0.794978141784668,
+      "step": 2482
+    },
+    {
+      "epoch": 1.0716289104638619,
+      "grad_norm": 0.5289306044578552,
+      "learning_rate": 0.0001943955713300583,
+      "loss": 0.8052116632461548,
+      "step": 2484
+    },
+    {
+      "epoch": 1.0724919093851133,
+      "grad_norm": 0.4360409080982208,
+      "learning_rate": 0.00019437935123983212,
+      "loss": 0.750991702079773,
+      "step": 2486
+    },
+    {
+      "epoch": 1.0733549083063647,
+      "grad_norm": 0.38651731610298157,
+      "learning_rate": 0.00019436310839045085,
+      "loss": 0.6631898880004883,
+      "step": 2488
+    },
+    {
+      "epoch": 1.074217907227616,
+      "grad_norm": 0.4376210868358612,
+      "learning_rate": 0.00019434684278583138,
+      "loss": 0.7995471358299255,
+      "step": 2490
+    },
+    {
+      "epoch": 1.0750809061488673,
+      "grad_norm": 0.46636906266212463,
+      "learning_rate": 0.0001943305544298961,
+      "loss": 0.7633864879608154,
+      "step": 2492
+    },
+    {
+      "epoch": 1.0759439050701187,
+      "grad_norm": 0.43499618768692017,
+      "learning_rate": 0.00019431424332657288,
+      "loss": 0.7281562089920044,
+      "step": 2494
+    },
+    {
+      "epoch": 1.07680690399137,
+      "grad_norm": 0.39683374762535095,
+      "learning_rate": 0.000194297909479795,
+      "loss": 0.7313723564147949,
+      "step": 2496
+    },
+    {
+      "epoch": 1.0776699029126213,
+      "grad_norm": 0.4545603096485138,
+      "learning_rate": 0.0001942815528935014,
+      "loss": 0.7120141983032227,
+      "step": 2498
+    },
+    {
+      "epoch": 1.0785329018338727,
+      "grad_norm": 0.5040699243545532,
+      "learning_rate": 0.0001942651735716363,
+      "loss": 0.752600908279419,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0785329018338727,
+      "eval_loss": 0.8323014378547668,
+      "eval_runtime": 652.3791,
+      "eval_samples_per_second": 3.158,
+      "eval_steps_per_second": 3.158,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0793959007551241,
+      "grad_norm": 0.48951438069343567,
+      "learning_rate": 0.00019424877151814958,
+      "loss": 0.7719982266426086,
+      "step": 2502
+    },
+    {
+      "epoch": 1.0802588996763753,
+      "grad_norm": 0.5009822845458984,
+      "learning_rate": 0.00019423234673699648,
+      "loss": 0.7921367883682251,
+      "step": 2504
+    },
+    {
+      "epoch": 1.0811218985976268,
+      "grad_norm": 0.4699440896511078,
+      "learning_rate": 0.00019421589923213772,
+      "loss": 0.7714369297027588,
+      "step": 2506
+    },
+    {
+      "epoch": 1.0819848975188782,
+      "grad_norm": 0.4438663125038147,
+      "learning_rate": 0.00019419942900753963,
+      "loss": 0.6981601119041443,
+      "step": 2508
+    },
+    {
+      "epoch": 1.0828478964401294,
+      "grad_norm": 0.49927031993865967,
+      "learning_rate": 0.00019418293606717385,
+      "loss": 0.7822043895721436,
+      "step": 2510
+    },
+    {
+      "epoch": 1.0837108953613808,
+      "grad_norm": 0.395433634519577,
+      "learning_rate": 0.00019416642041501767,
+      "loss": 0.7166627049446106,
+      "step": 2512
+    },
+    {
+      "epoch": 1.0845738942826322,
+      "grad_norm": 0.47293251752853394,
+      "learning_rate": 0.00019414988205505366,
+      "loss": 0.7287489771842957,
+      "step": 2514
+    },
+    {
+      "epoch": 1.0854368932038836,
+      "grad_norm": 0.43168675899505615,
+      "learning_rate": 0.00019413332099127008,
+      "loss": 0.7672322988510132,
+      "step": 2516
+    },
+    {
+      "epoch": 1.0862998921251348,
+      "grad_norm": 0.4542049765586853,
+      "learning_rate": 0.00019411673722766044,
+      "loss": 0.7427115440368652,
+      "step": 2518
+    },
+    {
+      "epoch": 1.0871628910463862,
+      "grad_norm": 0.4920838177204132,
+      "learning_rate": 0.00019410013076822394,
+      "loss": 0.742889404296875,
+      "step": 2520
+    },
+    {
+      "epoch": 1.0880258899676376,
+      "grad_norm": 0.5404410362243652,
+      "learning_rate": 0.0001940835016169651,
+      "loss": 0.767113208770752,
+      "step": 2522
+    },
+    {
+      "epoch": 1.0888888888888888,
+      "grad_norm": 0.4543033540248871,
+      "learning_rate": 0.00019406684977789395,
+      "loss": 0.6729961037635803,
+      "step": 2524
+    },
+    {
+      "epoch": 1.0897518878101402,
+      "grad_norm": 0.49171510338783264,
+      "learning_rate": 0.00019405017525502607,
+      "loss": 0.6907814145088196,
+      "step": 2526
+    },
+    {
+      "epoch": 1.0906148867313916,
+      "grad_norm": 0.491252601146698,
+      "learning_rate": 0.00019403347805238238,
+      "loss": 0.7643960118293762,
+      "step": 2528
+    },
+    {
+      "epoch": 1.091477885652643,
+      "grad_norm": 0.527920663356781,
+      "learning_rate": 0.0001940167581739894,
+      "loss": 0.8070526123046875,
+      "step": 2530
+    },
+    {
+      "epoch": 1.0923408845738942,
+      "grad_norm": 0.4318726658821106,
+      "learning_rate": 0.00019400001562387898,
+      "loss": 0.7900120615959167,
+      "step": 2532
+    },
+    {
+      "epoch": 1.0932038834951456,
+      "grad_norm": 0.4903397560119629,
+      "learning_rate": 0.00019398325040608855,
+      "loss": 0.7778371572494507,
+      "step": 2534
+    },
+    {
+      "epoch": 1.094066882416397,
+      "grad_norm": 0.4835105240345001,
+      "learning_rate": 0.00019396646252466097,
+      "loss": 0.7758864164352417,
+      "step": 2536
+    },
+    {
+      "epoch": 1.0949298813376482,
+      "grad_norm": 0.47125598788261414,
+      "learning_rate": 0.00019394965198364455,
+      "loss": 0.7927643656730652,
+      "step": 2538
+    },
+    {
+      "epoch": 1.0957928802588996,
+      "grad_norm": 0.46723976731300354,
+      "learning_rate": 0.0001939328187870931,
+      "loss": 0.7884714007377625,
+      "step": 2540
+    },
+    {
+      "epoch": 1.096655879180151,
+      "grad_norm": 0.46274980902671814,
+      "learning_rate": 0.00019391596293906582,
+      "loss": 0.7663765549659729,
+      "step": 2542
+    },
+    {
+      "epoch": 1.0975188781014025,
+      "grad_norm": 0.431887149810791,
+      "learning_rate": 0.00019389908444362747,
+      "loss": 0.6656131744384766,
+      "step": 2544
+    },
+    {
+      "epoch": 1.0983818770226537,
+      "grad_norm": 0.5138527750968933,
+      "learning_rate": 0.00019388218330484823,
+      "loss": 0.795498788356781,
+      "step": 2546
+    },
+    {
+      "epoch": 1.099244875943905,
+      "grad_norm": 0.4679732024669647,
+      "learning_rate": 0.00019386525952680365,
+      "loss": 0.807344377040863,
+      "step": 2548
+    },
+    {
+      "epoch": 1.1001078748651565,
+      "grad_norm": 0.473088800907135,
+      "learning_rate": 0.0001938483131135749,
+      "loss": 0.6828449368476868,
+      "step": 2550
+    },
+    {
+      "epoch": 1.1009708737864077,
+      "grad_norm": 0.49941009283065796,
+      "learning_rate": 0.00019383134406924856,
+      "loss": 0.8669595122337341,
+      "step": 2552
+    },
+    {
+      "epoch": 1.101833872707659,
+      "grad_norm": 0.47401952743530273,
+      "learning_rate": 0.00019381435239791656,
+      "loss": 0.7382985949516296,
+      "step": 2554
+    },
+    {
+      "epoch": 1.1026968716289105,
+      "grad_norm": 0.47803637385368347,
+      "learning_rate": 0.0001937973381036764,
+      "loss": 0.7240811586380005,
+      "step": 2556
+    },
+    {
+      "epoch": 1.103559870550162,
+      "grad_norm": 0.4534960985183716,
+      "learning_rate": 0.000193780301190631,
+      "loss": 0.736165463924408,
+      "step": 2558
+    },
+    {
+      "epoch": 1.104422869471413,
+      "grad_norm": 0.4594196677207947,
+      "learning_rate": 0.0001937632416628887,
+      "loss": 0.7364692091941833,
+      "step": 2560
+    },
+    {
+      "epoch": 1.1052858683926645,
+      "grad_norm": 0.45354577898979187,
+      "learning_rate": 0.0001937461595245634,
+      "loss": 0.803584635257721,
+      "step": 2562
+    },
+    {
+      "epoch": 1.106148867313916,
+      "grad_norm": 0.47314611077308655,
+      "learning_rate": 0.00019372905477977432,
+      "loss": 0.7224286794662476,
+      "step": 2564
+    },
+    {
+      "epoch": 1.1070118662351671,
+      "grad_norm": 0.4453343451023102,
+      "learning_rate": 0.0001937119274326462,
+      "loss": 0.7446297407150269,
+      "step": 2566
+    },
+    {
+      "epoch": 1.1078748651564185,
+      "grad_norm": 0.5266496539115906,
+      "learning_rate": 0.0001936947774873093,
+      "loss": 0.7666438817977905,
+      "step": 2568
+    },
+    {
+      "epoch": 1.10873786407767,
+      "grad_norm": 0.44142624735832214,
+      "learning_rate": 0.00019367760494789913,
+      "loss": 0.8593260049819946,
+      "step": 2570
+    },
+    {
+      "epoch": 1.1096008629989211,
+      "grad_norm": 0.552436888217926,
+      "learning_rate": 0.00019366040981855682,
+      "loss": 0.7768570184707642,
+      "step": 2572
+    },
+    {
+      "epoch": 1.1104638619201725,
+      "grad_norm": 0.4223164916038513,
+      "learning_rate": 0.0001936431921034289,
+      "loss": 0.7356681823730469,
+      "step": 2574
+    },
+    {
+      "epoch": 1.111326860841424,
+      "grad_norm": 0.5104808211326599,
+      "learning_rate": 0.0001936259518066674,
+      "loss": 0.7693892121315002,
+      "step": 2576
+    },
+    {
+      "epoch": 1.1121898597626754,
+      "grad_norm": 0.40713393688201904,
+      "learning_rate": 0.00019360868893242967,
+      "loss": 0.7651313543319702,
+      "step": 2578
+    },
+    {
+      "epoch": 1.1130528586839266,
+      "grad_norm": 0.4819444417953491,
+      "learning_rate": 0.00019359140348487858,
+      "loss": 0.8427110314369202,
+      "step": 2580
+    },
+    {
+      "epoch": 1.113915857605178,
+      "grad_norm": 0.45872536301612854,
+      "learning_rate": 0.00019357409546818247,
+      "loss": 0.7783478498458862,
+      "step": 2582
+    },
+    {
+      "epoch": 1.1147788565264294,
+      "grad_norm": 0.43954113125801086,
+      "learning_rate": 0.00019355676488651508,
+      "loss": 0.6625193357467651,
+      "step": 2584
+    },
+    {
+      "epoch": 1.1156418554476808,
+      "grad_norm": 0.4524446725845337,
+      "learning_rate": 0.00019353941174405558,
+      "loss": 0.7208001613616943,
+      "step": 2586
+    },
+    {
+      "epoch": 1.116504854368932,
+      "grad_norm": 0.4748269021511078,
+      "learning_rate": 0.0001935220360449886,
+      "loss": 0.7567161917686462,
+      "step": 2588
+    },
+    {
+      "epoch": 1.1173678532901834,
+      "grad_norm": 0.4493826925754547,
+      "learning_rate": 0.00019350463779350423,
+      "loss": 0.7631603479385376,
+      "step": 2590
+    },
+    {
+      "epoch": 1.1182308522114348,
+      "grad_norm": 0.45398685336112976,
+      "learning_rate": 0.00019348721699379798,
+      "loss": 0.7756917476654053,
+      "step": 2592
+    },
+    {
+      "epoch": 1.119093851132686,
+      "grad_norm": 0.4246262311935425,
+      "learning_rate": 0.0001934697736500708,
+      "loss": 0.7516605854034424,
+      "step": 2594
+    },
+    {
+      "epoch": 1.1199568500539374,
+      "grad_norm": 0.44801613688468933,
+      "learning_rate": 0.00019345230776652908,
+      "loss": 0.7058185338973999,
+      "step": 2596
+    },
+    {
+      "epoch": 1.1208198489751888,
+      "grad_norm": 0.4591200649738312,
+      "learning_rate": 0.00019343481934738462,
+      "loss": 0.8071328997612,
+      "step": 2598
+    },
+    {
+      "epoch": 1.12168284789644,
+      "grad_norm": 0.39467594027519226,
+      "learning_rate": 0.0001934173083968547,
+      "loss": 0.6992195844650269,
+      "step": 2600
+    },
+    {
+      "epoch": 1.12168284789644,
+      "eval_loss": 0.8300262093544006,
+      "eval_runtime": 658.9488,
+      "eval_samples_per_second": 3.126,
+      "eval_steps_per_second": 3.126,
+      "step": 2600
+    },
+    {
+      "epoch": 1.1225458468176914,
+      "grad_norm": 0.40905407071113586,
+      "learning_rate": 0.00019339977491916196,
+      "loss": 0.7683232426643372,
+      "step": 2602
+    },
+    {
+      "epoch": 1.1234088457389428,
+      "grad_norm": 0.42742034792900085,
+      "learning_rate": 0.00019338221891853453,
+      "loss": 0.7048685550689697,
+      "step": 2604
+    },
+    {
+      "epoch": 1.1242718446601943,
+      "grad_norm": 0.4435581564903259,
+      "learning_rate": 0.000193364640399206,
+      "loss": 0.7206799983978271,
+      "step": 2606
+    },
+    {
+      "epoch": 1.1251348435814454,
+      "grad_norm": 0.48409897089004517,
+      "learning_rate": 0.00019334703936541535,
+      "loss": 0.8230411410331726,
+      "step": 2608
+    },
+    {
+      "epoch": 1.1259978425026969,
+      "grad_norm": 0.5060800909996033,
+      "learning_rate": 0.00019332941582140693,
+      "loss": 0.7833203077316284,
+      "step": 2610
+    },
+    {
+      "epoch": 1.1268608414239483,
+      "grad_norm": 0.48900339007377625,
+      "learning_rate": 0.00019331176977143062,
+      "loss": 0.7785601615905762,
+      "step": 2612
+    },
+    {
+      "epoch": 1.1277238403451997,
+      "grad_norm": 0.46176961064338684,
+      "learning_rate": 0.0001932941012197417,
+      "loss": 0.800255537033081,
+      "step": 2614
+    },
+    {
+      "epoch": 1.1285868392664509,
+      "grad_norm": 0.4946233332157135,
+      "learning_rate": 0.00019327641017060084,
+      "loss": 0.7647190690040588,
+      "step": 2616
+    },
+    {
+      "epoch": 1.1294498381877023,
+      "grad_norm": 0.4153730571269989,
+      "learning_rate": 0.00019325869662827416,
+      "loss": 0.7271775007247925,
+      "step": 2618
+    },
+    {
+      "epoch": 1.1303128371089537,
+      "grad_norm": 0.46707460284233093,
+      "learning_rate": 0.0001932409605970332,
+      "loss": 0.7926952838897705,
+      "step": 2620
+    },
+    {
+      "epoch": 1.1311758360302049,
+      "grad_norm": 0.4980720579624176,
+      "learning_rate": 0.00019322320208115489,
+      "loss": 0.8106555938720703,
+      "step": 2622
+    },
+    {
+      "epoch": 1.1320388349514563,
+      "grad_norm": 0.4300958514213562,
+      "learning_rate": 0.0001932054210849217,
+      "loss": 0.7208700776100159,
+      "step": 2624
+    },
+    {
+      "epoch": 1.1329018338727077,
+      "grad_norm": 0.4756612479686737,
+      "learning_rate": 0.00019318761761262136,
+      "loss": 0.7212259769439697,
+      "step": 2626
+    },
+    {
+      "epoch": 1.133764832793959,
+      "grad_norm": 0.4502181112766266,
+      "learning_rate": 0.00019316979166854713,
+      "loss": 0.6725794672966003,
+      "step": 2628
+    },
+    {
+      "epoch": 1.1346278317152103,
+      "grad_norm": 0.4845540523529053,
+      "learning_rate": 0.00019315194325699765,
+      "loss": 0.7582959532737732,
+      "step": 2630
+    },
+    {
+      "epoch": 1.1354908306364617,
+      "grad_norm": 0.45892953872680664,
+      "learning_rate": 0.00019313407238227698,
+      "loss": 0.7707560062408447,
+      "step": 2632
+    },
+    {
+      "epoch": 1.1363538295577131,
+      "grad_norm": 0.4707877039909363,
+      "learning_rate": 0.00019311617904869464,
+      "loss": 0.7824680209159851,
+      "step": 2634
+    },
+    {
+      "epoch": 1.1372168284789643,
+      "grad_norm": 0.5212311744689941,
+      "learning_rate": 0.00019309826326056545,
+      "loss": 0.7750257253646851,
+      "step": 2636
+    },
+    {
+      "epoch": 1.1380798274002157,
+      "grad_norm": 0.4952082633972168,
+      "learning_rate": 0.0001930803250222098,
+      "loss": 0.7691953182220459,
+      "step": 2638
+    },
+    {
+      "epoch": 1.1389428263214671,
+      "grad_norm": 0.4428424835205078,
+      "learning_rate": 0.00019306236433795334,
+      "loss": 0.737209141254425,
+      "step": 2640
+    },
+    {
+      "epoch": 1.1398058252427186,
+      "grad_norm": 0.5063129663467407,
+      "learning_rate": 0.00019304438121212728,
+      "loss": 0.7487695813179016,
+      "step": 2642
+    },
+    {
+      "epoch": 1.1406688241639698,
+      "grad_norm": 0.4571828246116638,
+      "learning_rate": 0.00019302637564906814,
+      "loss": 0.7647218704223633,
+      "step": 2644
+    },
+    {
+      "epoch": 1.1415318230852212,
+      "grad_norm": 0.4918457567691803,
+      "learning_rate": 0.00019300834765311785,
+      "loss": 0.8173171877861023,
+      "step": 2646
+    },
+    {
+      "epoch": 1.1423948220064726,
+      "grad_norm": 0.40057408809661865,
+      "learning_rate": 0.0001929902972286238,
+      "loss": 0.6472562551498413,
+      "step": 2648
+    },
+    {
+      "epoch": 1.1432578209277238,
+      "grad_norm": 0.432763934135437,
+      "learning_rate": 0.0001929722243799388,
+      "loss": 0.8462889194488525,
+      "step": 2650
+    },
+    {
+      "epoch": 1.1441208198489752,
+      "grad_norm": 0.36540713906288147,
+      "learning_rate": 0.000192954129111421,
+      "loss": 0.808388352394104,
+      "step": 2652
+    },
+    {
+      "epoch": 1.1449838187702266,
+      "grad_norm": 0.4236038029193878,
+      "learning_rate": 0.00019293601142743403,
+      "loss": 0.7144365906715393,
+      "step": 2654
+    },
+    {
+      "epoch": 1.1458468176914778,
+      "grad_norm": 0.4316163957118988,
+      "learning_rate": 0.00019291787133234682,
+      "loss": 0.693168580532074,
+      "step": 2656
+    },
+    {
+      "epoch": 1.1467098166127292,
+      "grad_norm": 0.43088117241859436,
+      "learning_rate": 0.00019289970883053386,
+      "loss": 0.7981953024864197,
+      "step": 2658
+    },
+    {
+      "epoch": 1.1475728155339806,
+      "grad_norm": 0.4200972318649292,
+      "learning_rate": 0.00019288152392637486,
+      "loss": 0.7342561483383179,
+      "step": 2660
+    },
+    {
+      "epoch": 1.148435814455232,
+      "grad_norm": 0.4461527466773987,
+      "learning_rate": 0.00019286331662425512,
+      "loss": 0.7239733934402466,
+      "step": 2662
+    },
+    {
+      "epoch": 1.1492988133764832,
+      "grad_norm": 0.3945358097553253,
+      "learning_rate": 0.00019284508692856518,
+      "loss": 0.6575030088424683,
+      "step": 2664
+    },
+    {
+      "epoch": 1.1501618122977346,
+      "grad_norm": 0.4653085470199585,
+      "learning_rate": 0.0001928268348437011,
+      "loss": 0.7754159569740295,
+      "step": 2666
+    },
+    {
+      "epoch": 1.151024811218986,
+      "grad_norm": 0.47542640566825867,
+      "learning_rate": 0.00019280856037406422,
+      "loss": 0.683927595615387,
+      "step": 2668
+    },
+    {
+      "epoch": 1.1518878101402374,
+      "grad_norm": 0.4191996455192566,
+      "learning_rate": 0.00019279026352406143,
+      "loss": 0.6907603144645691,
+      "step": 2670
+    },
+    {
+      "epoch": 1.1527508090614886,
+      "grad_norm": 0.4643108546733856,
+      "learning_rate": 0.00019277194429810488,
+      "loss": 0.8362683653831482,
+      "step": 2672
+    },
+    {
+      "epoch": 1.15361380798274,
+      "grad_norm": 0.4213605225086212,
+      "learning_rate": 0.00019275360270061217,
+      "loss": 0.737736701965332,
+      "step": 2674
+    },
+    {
+      "epoch": 1.1544768069039915,
+      "grad_norm": 0.537070095539093,
+      "learning_rate": 0.0001927352387360063,
+      "loss": 0.7617850303649902,
+      "step": 2676
+    },
+    {
+      "epoch": 1.1553398058252426,
+      "grad_norm": 0.47798195481300354,
+      "learning_rate": 0.0001927168524087157,
+      "loss": 0.7252766489982605,
+      "step": 2678
+    },
+    {
+      "epoch": 1.156202804746494,
+      "grad_norm": 0.48654067516326904,
+      "learning_rate": 0.00019269844372317408,
+      "loss": 0.7671495676040649,
+      "step": 2680
+    },
+    {
+      "epoch": 1.1570658036677455,
+      "grad_norm": 0.5374535322189331,
+      "learning_rate": 0.00019268001268382066,
+      "loss": 0.8648670315742493,
+      "step": 2682
+    },
+    {
+      "epoch": 1.1579288025889967,
+      "grad_norm": 0.42167672514915466,
+      "learning_rate": 0.00019266155929509996,
+      "loss": 0.6848083138465881,
+      "step": 2684
+    },
+    {
+      "epoch": 1.158791801510248,
+      "grad_norm": 0.38867753744125366,
+      "learning_rate": 0.00019264308356146197,
+      "loss": 0.6890886425971985,
+      "step": 2686
+    },
+    {
+      "epoch": 1.1596548004314995,
+      "grad_norm": 0.42711013555526733,
+      "learning_rate": 0.000192624585487362,
+      "loss": 0.7399795651435852,
+      "step": 2688
+    },
+    {
+      "epoch": 1.160517799352751,
+      "grad_norm": 0.48802322149276733,
+      "learning_rate": 0.00019260606507726083,
+      "loss": 0.8026465773582458,
+      "step": 2690
+    },
+    {
+      "epoch": 1.161380798274002,
+      "grad_norm": 0.47166478633880615,
+      "learning_rate": 0.00019258752233562452,
+      "loss": 0.7589768171310425,
+      "step": 2692
+    },
+    {
+      "epoch": 1.1622437971952535,
+      "grad_norm": 0.47413256764411926,
+      "learning_rate": 0.00019256895726692459,
+      "loss": 0.7620571851730347,
+      "step": 2694
+    },
+    {
+      "epoch": 1.163106796116505,
+      "grad_norm": 0.5377517342567444,
+      "learning_rate": 0.0001925503698756379,
+      "loss": 0.798933207988739,
+      "step": 2696
+    },
+    {
+      "epoch": 1.1639697950377563,
+      "grad_norm": 0.44990095496177673,
+      "learning_rate": 0.00019253176016624678,
+      "loss": 0.7550637125968933,
+      "step": 2698
+    },
+    {
+      "epoch": 1.1648327939590075,
+      "grad_norm": 0.4633009433746338,
+      "learning_rate": 0.00019251312814323876,
+      "loss": 0.7919567227363586,
+      "step": 2700
+    },
+    {
+      "epoch": 1.1648327939590075,
+      "eval_loss": 0.8251468539237976,
+      "eval_runtime": 667.0436,
+      "eval_samples_per_second": 3.088,
+      "eval_steps_per_second": 3.088,
+      "step": 2700
+    },
+    {
+      "epoch": 1.165695792880259,
+      "grad_norm": 0.4339669942855835,
+      "learning_rate": 0.000192494473811107,
+      "loss": 0.8140546083450317,
+      "step": 2702
+    },
+    {
+      "epoch": 1.1665587918015103,
+      "grad_norm": 0.5794349312782288,
+      "learning_rate": 0.00019247579717434984,
+      "loss": 0.8462281823158264,
+      "step": 2704
+    },
+    {
+      "epoch": 1.1674217907227615,
+      "grad_norm": 0.41820067167282104,
+      "learning_rate": 0.00019245709823747102,
+      "loss": 0.7468760013580322,
+      "step": 2706
+    },
+    {
+      "epoch": 1.168284789644013,
+      "grad_norm": 0.4002464711666107,
+      "learning_rate": 0.0001924383770049798,
+      "loss": 0.694807767868042,
+      "step": 2708
+    },
+    {
+      "epoch": 1.1691477885652644,
+      "grad_norm": 0.47752025723457336,
+      "learning_rate": 0.00019241963348139068,
+      "loss": 0.7512534856796265,
+      "step": 2710
+    },
+    {
+      "epoch": 1.1700107874865155,
+      "grad_norm": 0.45852312445640564,
+      "learning_rate": 0.0001924008676712236,
+      "loss": 0.8069711923599243,
+      "step": 2712
+    },
+    {
+      "epoch": 1.170873786407767,
+      "grad_norm": 0.4336509108543396,
+      "learning_rate": 0.0001923820795790038,
+      "loss": 0.7022751569747925,
+      "step": 2714
+    },
+    {
+      "epoch": 1.1717367853290184,
+      "grad_norm": 0.40044888854026794,
+      "learning_rate": 0.00019236326920926193,
+      "loss": 0.6904252767562866,
+      "step": 2716
+    },
+    {
+      "epoch": 1.1725997842502698,
+      "grad_norm": 0.48451852798461914,
+      "learning_rate": 0.00019234443656653412,
+      "loss": 0.7924585938453674,
+      "step": 2718
+    },
+    {
+      "epoch": 1.173462783171521,
+      "grad_norm": 0.49168315529823303,
+      "learning_rate": 0.0001923255816553617,
+      "loss": 0.7383922338485718,
+      "step": 2720
+    },
+    {
+      "epoch": 1.1743257820927724,
+      "grad_norm": 0.4363260269165039,
+      "learning_rate": 0.00019230670448029148,
+      "loss": 0.7508589029312134,
+      "step": 2722
+    },
+    {
+      "epoch": 1.1751887810140238,
+      "grad_norm": 0.4520082175731659,
+      "learning_rate": 0.0001922878050458756,
+      "loss": 0.7814584970474243,
+      "step": 2724
+    },
+    {
+      "epoch": 1.176051779935275,
+      "grad_norm": 0.4675535559654236,
+      "learning_rate": 0.00019226888335667158,
+      "loss": 0.7011970281600952,
+      "step": 2726
+    },
+    {
+      "epoch": 1.1769147788565264,
+      "grad_norm": 0.47536277770996094,
+      "learning_rate": 0.00019224993941724226,
+      "loss": 0.7414659857749939,
+      "step": 2728
+    },
+    {
+      "epoch": 1.1777777777777778,
+      "grad_norm": 0.5455507040023804,
+      "learning_rate": 0.00019223097323215594,
+      "loss": 0.7949363589286804,
+      "step": 2730
+    },
+    {
+      "epoch": 1.1786407766990292,
+      "grad_norm": 0.4897938370704651,
+      "learning_rate": 0.00019221198480598616,
+      "loss": 0.813949465751648,
+      "step": 2732
+    },
+    {
+      "epoch": 1.1795037756202804,
+      "grad_norm": 0.46766766905784607,
+      "learning_rate": 0.000192192974143312,
+      "loss": 0.7444795966148376,
+      "step": 2734
+    },
+    {
+      "epoch": 1.1803667745415318,
+      "grad_norm": 0.41503575444221497,
+      "learning_rate": 0.00019217394124871768,
+      "loss": 0.7937621474266052,
+      "step": 2736
+    },
+    {
+      "epoch": 1.1812297734627832,
+      "grad_norm": 0.41906169056892395,
+      "learning_rate": 0.00019215488612679295,
+      "loss": 0.7342435717582703,
+      "step": 2738
+    },
+    {
+      "epoch": 1.1820927723840344,
+      "grad_norm": 0.47820931673049927,
+      "learning_rate": 0.00019213580878213292,
+      "loss": 0.7533642053604126,
+      "step": 2740
+    },
+    {
+      "epoch": 1.1829557713052858,
+      "grad_norm": 0.44907891750335693,
+      "learning_rate": 0.00019211670921933792,
+      "loss": 0.799866795539856,
+      "step": 2742
+    },
+    {
+      "epoch": 1.1838187702265373,
+      "grad_norm": 0.48050498962402344,
+      "learning_rate": 0.00019209758744301376,
+      "loss": 0.7468855381011963,
+      "step": 2744
+    },
+    {
+      "epoch": 1.1846817691477884,
+      "grad_norm": 0.4311312437057495,
+      "learning_rate": 0.00019207844345777155,
+      "loss": 0.7423141002655029,
+      "step": 2746
+    },
+    {
+      "epoch": 1.1855447680690399,
+      "grad_norm": 0.439386248588562,
+      "learning_rate": 0.0001920592772682278,
+      "loss": 0.7046169638633728,
+      "step": 2748
+    },
+    {
+      "epoch": 1.1864077669902913,
+      "grad_norm": 0.4230091869831085,
+      "learning_rate": 0.00019204008887900435,
+      "loss": 0.7284982204437256,
+      "step": 2750
+    },
+    {
+      "epoch": 1.1872707659115427,
+      "grad_norm": 0.4583308696746826,
+      "learning_rate": 0.0001920208782947284,
+      "loss": 0.7297943234443665,
+      "step": 2752
+    },
+    {
+      "epoch": 1.1881337648327939,
+      "grad_norm": 0.44526317715644836,
+      "learning_rate": 0.00019200164552003247,
+      "loss": 0.7170902490615845,
+      "step": 2754
+    },
+    {
+      "epoch": 1.1889967637540453,
+      "grad_norm": 0.46664097905158997,
+      "learning_rate": 0.00019198239055955444,
+      "loss": 0.7746089696884155,
+      "step": 2756
+    },
+    {
+      "epoch": 1.1898597626752967,
+      "grad_norm": 0.4023241102695465,
+      "learning_rate": 0.0001919631134179376,
+      "loss": 0.7381687760353088,
+      "step": 2758
+    },
+    {
+      "epoch": 1.190722761596548,
+      "grad_norm": 0.5126422047615051,
+      "learning_rate": 0.00019194381409983055,
+      "loss": 0.7951313853263855,
+      "step": 2760
+    },
+    {
+      "epoch": 1.1915857605177993,
+      "grad_norm": 0.4056018590927124,
+      "learning_rate": 0.0001919244926098872,
+      "loss": 0.692834198474884,
+      "step": 2762
+    },
+    {
+      "epoch": 1.1924487594390507,
+      "grad_norm": 0.49225106835365295,
+      "learning_rate": 0.00019190514895276687,
+      "loss": 0.7494171857833862,
+      "step": 2764
+    },
+    {
+      "epoch": 1.1933117583603021,
+      "grad_norm": 0.47823601961135864,
+      "learning_rate": 0.00019188578313313417,
+      "loss": 0.8541221022605896,
+      "step": 2766
+    },
+    {
+      "epoch": 1.1941747572815533,
+      "grad_norm": 0.461773544549942,
+      "learning_rate": 0.0001918663951556591,
+      "loss": 0.8017639517784119,
+      "step": 2768
+    },
+    {
+      "epoch": 1.1950377562028047,
+      "grad_norm": 0.48888009786605835,
+      "learning_rate": 0.00019184698502501695,
+      "loss": 0.7509341835975647,
+      "step": 2770
+    },
+    {
+      "epoch": 1.1959007551240561,
+      "grad_norm": 0.4140535295009613,
+      "learning_rate": 0.0001918275527458884,
+      "loss": 0.7123914361000061,
+      "step": 2772
+    },
+    {
+      "epoch": 1.1967637540453073,
+      "grad_norm": 0.4918449819087982,
+      "learning_rate": 0.00019180809832295952,
+      "loss": 0.73713219165802,
+      "step": 2774
+    },
+    {
+      "epoch": 1.1976267529665587,
+      "grad_norm": 0.48218831419944763,
+      "learning_rate": 0.00019178862176092159,
+      "loss": 0.708644688129425,
+      "step": 2776
+    },
+    {
+      "epoch": 1.1984897518878102,
+      "grad_norm": 0.45588797330856323,
+      "learning_rate": 0.0001917691230644713,
+      "loss": 0.7277385592460632,
+      "step": 2778
+    },
+    {
+      "epoch": 1.1993527508090616,
+      "grad_norm": 0.3959250748157501,
+      "learning_rate": 0.00019174960223831064,
+      "loss": 0.7501665949821472,
+      "step": 2780
+    },
+    {
+      "epoch": 1.2002157497303128,
+      "grad_norm": 0.6228574514389038,
+      "learning_rate": 0.00019173005928714703,
+      "loss": 0.8842931389808655,
+      "step": 2782
+    },
+    {
+      "epoch": 1.2010787486515642,
+      "grad_norm": 0.4346935749053955,
+      "learning_rate": 0.00019171049421569318,
+      "loss": 0.7008639574050903,
+      "step": 2784
+    },
+    {
+      "epoch": 1.2019417475728156,
+      "grad_norm": 0.691254198551178,
+      "learning_rate": 0.00019169090702866705,
+      "loss": 0.7203702330589294,
+      "step": 2786
+    },
+    {
+      "epoch": 1.202804746494067,
+      "grad_norm": 0.4219740331172943,
+      "learning_rate": 0.00019167129773079203,
+      "loss": 0.7170791029930115,
+      "step": 2788
+    },
+    {
+      "epoch": 1.2036677454153182,
+      "grad_norm": 0.4639855921268463,
+      "learning_rate": 0.00019165166632679686,
+      "loss": 0.7895086407661438,
+      "step": 2790
+    },
+    {
+      "epoch": 1.2045307443365696,
+      "grad_norm": 0.44938549399375916,
+      "learning_rate": 0.00019163201282141546,
+      "loss": 0.7323113679885864,
+      "step": 2792
+    },
+    {
+      "epoch": 1.205393743257821,
+      "grad_norm": 0.43633413314819336,
+      "learning_rate": 0.00019161233721938728,
+      "loss": 0.7486892342567444,
+      "step": 2794
+    },
+    {
+      "epoch": 1.2062567421790722,
+      "grad_norm": 0.42983385920524597,
+      "learning_rate": 0.00019159263952545698,
+      "loss": 0.777079701423645,
+      "step": 2796
+    },
+    {
+      "epoch": 1.2071197411003236,
+      "grad_norm": 0.4630664587020874,
+      "learning_rate": 0.00019157291974437456,
+      "loss": 0.800602912902832,
+      "step": 2798
+    },
+    {
+      "epoch": 1.207982740021575,
+      "grad_norm": 0.43607378005981445,
+      "learning_rate": 0.00019155317788089536,
+      "loss": 0.6763592958450317,
+      "step": 2800
+    },
+    {
+      "epoch": 1.207982740021575,
+      "eval_loss": 0.8219058513641357,
+      "eval_runtime": 661.5144,
+      "eval_samples_per_second": 3.114,
+      "eval_steps_per_second": 3.114,
+      "step": 2800
+    },
+    {
+      "epoch": 1.2088457389428262,
+      "grad_norm": 0.4910019338130951,
+      "learning_rate": 0.00019153341393978002,
+      "loss": 0.7569329738616943,
+      "step": 2802
+    },
+    {
+      "epoch": 1.2097087378640776,
+      "grad_norm": 0.4993135631084442,
+      "learning_rate": 0.00019151362792579457,
+      "loss": 0.734387218952179,
+      "step": 2804
+    },
+    {
+      "epoch": 1.210571736785329,
+      "grad_norm": 0.48742055892944336,
+      "learning_rate": 0.00019149381984371027,
+      "loss": 0.719099223613739,
+      "step": 2806
+    },
+    {
+      "epoch": 1.2114347357065804,
+      "grad_norm": 0.4083765149116516,
+      "learning_rate": 0.00019147398969830378,
+      "loss": 0.8490580320358276,
+      "step": 2808
+    },
+    {
+      "epoch": 1.2122977346278316,
+      "grad_norm": 0.4316021502017975,
+      "learning_rate": 0.00019145413749435702,
+      "loss": 0.7604904770851135,
+      "step": 2810
+    },
+    {
+      "epoch": 1.213160733549083,
+      "grad_norm": 0.4294895529747009,
+      "learning_rate": 0.0001914342632366573,
+      "loss": 0.7739580869674683,
+      "step": 2812
+    },
+    {
+      "epoch": 1.2140237324703345,
+      "grad_norm": 0.4773736000061035,
+      "learning_rate": 0.00019141436692999718,
+      "loss": 0.7625397443771362,
+      "step": 2814
+    },
+    {
+      "epoch": 1.2148867313915859,
+      "grad_norm": 0.46148404479026794,
+      "learning_rate": 0.00019139444857917457,
+      "loss": 0.7224686741828918,
+      "step": 2816
+    },
+    {
+      "epoch": 1.215749730312837,
+      "grad_norm": 0.436300128698349,
+      "learning_rate": 0.0001913745081889927,
+      "loss": 0.7708583474159241,
+      "step": 2818
+    },
+    {
+      "epoch": 1.2166127292340885,
+      "grad_norm": 0.4959073066711426,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.8550406098365784,
+      "step": 2820
+    },
+    {
+      "epoch": 1.2174757281553399,
+      "grad_norm": 0.4672411382198334,
+      "learning_rate": 0.00019133456130979062,
+      "loss": 0.781597912311554,
+      "step": 2822
+    },
+    {
+      "epoch": 1.218338727076591,
+      "grad_norm": 0.5249256491661072,
+      "learning_rate": 0.0001913145548304034,
+      "loss": 0.860835075378418,
+      "step": 2824
+    },
+    {
+      "epoch": 1.2192017259978425,
+      "grad_norm": 0.5132579207420349,
+      "learning_rate": 0.00019129452633092294,
+      "loss": 0.715717613697052,
+      "step": 2826
+    },
+    {
+      "epoch": 1.220064724919094,
+      "grad_norm": 0.4291874170303345,
+      "learning_rate": 0.00019127447581617903,
+      "loss": 0.727998673915863,
+      "step": 2828
+    },
+    {
+      "epoch": 1.220927723840345,
+      "grad_norm": 0.3698529005050659,
+      "learning_rate": 0.00019125440329100673,
+      "loss": 0.7164589762687683,
+      "step": 2830
+    },
+    {
+      "epoch": 1.2217907227615965,
+      "grad_norm": 0.5034273266792297,
+      "learning_rate": 0.00019123430876024646,
+      "loss": 0.8113957643508911,
+      "step": 2832
+    },
+    {
+      "epoch": 1.222653721682848,
+      "grad_norm": 0.4612481892108917,
+      "learning_rate": 0.0001912141922287439,
+      "loss": 0.7350133061408997,
+      "step": 2834
+    },
+    {
+      "epoch": 1.2235167206040993,
+      "grad_norm": 0.4433611035346985,
+      "learning_rate": 0.00019119405370135012,
+      "loss": 0.8156216144561768,
+      "step": 2836
+    },
+    {
+      "epoch": 1.2243797195253505,
+      "grad_norm": 0.4700625240802765,
+      "learning_rate": 0.00019117389318292136,
+      "loss": 0.7824334502220154,
+      "step": 2838
+    },
+    {
+      "epoch": 1.225242718446602,
+      "grad_norm": 0.4854332208633423,
+      "learning_rate": 0.00019115371067831928,
+      "loss": 0.8136369585990906,
+      "step": 2840
+    },
+    {
+      "epoch": 1.2261057173678533,
+      "grad_norm": 0.4403935372829437,
+      "learning_rate": 0.00019113350619241078,
+      "loss": 0.7042210102081299,
+      "step": 2842
+    },
+    {
+      "epoch": 1.2269687162891048,
+      "grad_norm": 0.4311469793319702,
+      "learning_rate": 0.00019111327973006813,
+      "loss": 0.7598573565483093,
+      "step": 2844
+    },
+    {
+      "epoch": 1.227831715210356,
+      "grad_norm": 0.5551521182060242,
+      "learning_rate": 0.0001910930312961688,
+      "loss": 0.8001043796539307,
+      "step": 2846
+    },
+    {
+      "epoch": 1.2286947141316074,
+      "grad_norm": 0.44149601459503174,
+      "learning_rate": 0.0001910727608955956,
+      "loss": 0.6874746084213257,
+      "step": 2848
+    },
+    {
+      "epoch": 1.2295577130528588,
+      "grad_norm": 0.44726014137268066,
+      "learning_rate": 0.00019105246853323672,
+      "loss": 0.7484437823295593,
+      "step": 2850
+    },
+    {
+      "epoch": 1.23042071197411,
+      "grad_norm": 0.4710492193698883,
+      "learning_rate": 0.00019103215421398546,
+      "loss": 0.7512558102607727,
+      "step": 2852
+    },
+    {
+      "epoch": 1.2312837108953614,
+      "grad_norm": 0.4304901957511902,
+      "learning_rate": 0.0001910118179427406,
+      "loss": 0.7161203622817993,
+      "step": 2854
+    },
+    {
+      "epoch": 1.2321467098166128,
+      "grad_norm": 0.4651104509830475,
+      "learning_rate": 0.00019099145972440614,
+      "loss": 0.722236156463623,
+      "step": 2856
+    },
+    {
+      "epoch": 1.233009708737864,
+      "grad_norm": 0.5231161117553711,
+      "learning_rate": 0.00019097107956389135,
+      "loss": 0.8200751543045044,
+      "step": 2858
+    },
+    {
+      "epoch": 1.2338727076591154,
+      "grad_norm": 0.45574283599853516,
+      "learning_rate": 0.00019095067746611083,
+      "loss": 0.7529966235160828,
+      "step": 2860
+    },
+    {
+      "epoch": 1.2347357065803668,
+      "grad_norm": 0.4451949894428253,
+      "learning_rate": 0.00019093025343598448,
+      "loss": 0.7574380040168762,
+      "step": 2862
+    },
+    {
+      "epoch": 1.2355987055016182,
+      "grad_norm": 0.4557603597640991,
+      "learning_rate": 0.00019090980747843737,
+      "loss": 0.8461237549781799,
+      "step": 2864
+    },
+    {
+      "epoch": 1.2364617044228694,
+      "grad_norm": 0.41115859150886536,
+      "learning_rate": 0.00019088933959840004,
+      "loss": 0.7910104990005493,
+      "step": 2866
+    },
+    {
+      "epoch": 1.2373247033441208,
+      "grad_norm": 0.5087599158287048,
+      "learning_rate": 0.0001908688498008082,
+      "loss": 0.8318688273429871,
+      "step": 2868
+    },
+    {
+      "epoch": 1.2381877022653722,
+      "grad_norm": 0.4243653118610382,
+      "learning_rate": 0.00019084833809060285,
+      "loss": 0.713392436504364,
+      "step": 2870
+    },
+    {
+      "epoch": 1.2390507011866236,
+      "grad_norm": 0.3965010344982147,
+      "learning_rate": 0.00019082780447273034,
+      "loss": 0.7697778344154358,
+      "step": 2872
+    },
+    {
+      "epoch": 1.2399137001078748,
+      "grad_norm": 0.4493406116962433,
+      "learning_rate": 0.00019080724895214222,
+      "loss": 0.7437527179718018,
+      "step": 2874
+    },
+    {
+      "epoch": 1.2407766990291262,
+      "grad_norm": 0.5189685821533203,
+      "learning_rate": 0.00019078667153379537,
+      "loss": 0.858138918876648,
+      "step": 2876
+    },
+    {
+      "epoch": 1.2416396979503777,
+      "grad_norm": 0.39455580711364746,
+      "learning_rate": 0.00019076607222265197,
+      "loss": 0.7235360145568848,
+      "step": 2878
+    },
+    {
+      "epoch": 1.2425026968716288,
+      "grad_norm": 0.524804413318634,
+      "learning_rate": 0.00019074545102367943,
+      "loss": 0.7995675206184387,
+      "step": 2880
+    },
+    {
+      "epoch": 1.2433656957928803,
+      "grad_norm": 0.4873242974281311,
+      "learning_rate": 0.00019072480794185044,
+      "loss": 0.8404105305671692,
+      "step": 2882
+    },
+    {
+      "epoch": 1.2442286947141317,
+      "grad_norm": 0.4591716527938843,
+      "learning_rate": 0.000190704142982143,
+      "loss": 0.7540513277053833,
+      "step": 2884
+    },
+    {
+      "epoch": 1.2450916936353829,
+      "grad_norm": 0.48403632640838623,
+      "learning_rate": 0.0001906834561495404,
+      "loss": 0.7566621899604797,
+      "step": 2886
+    },
+    {
+      "epoch": 1.2459546925566343,
+      "grad_norm": 0.4854280948638916,
+      "learning_rate": 0.00019066274744903113,
+      "loss": 0.7141375541687012,
+      "step": 2888
+    },
+    {
+      "epoch": 1.2468176914778857,
+      "grad_norm": 0.45851001143455505,
+      "learning_rate": 0.00019064201688560902,
+      "loss": 0.7798115611076355,
+      "step": 2890
+    },
+    {
+      "epoch": 1.247680690399137,
+      "grad_norm": 0.4584810435771942,
+      "learning_rate": 0.00019062126446427318,
+      "loss": 0.7212263941764832,
+      "step": 2892
+    },
+    {
+      "epoch": 1.2485436893203883,
+      "grad_norm": 0.5282798409461975,
+      "learning_rate": 0.00019060049019002792,
+      "loss": 0.8268418312072754,
+      "step": 2894
+    },
+    {
+      "epoch": 1.2494066882416397,
+      "grad_norm": 0.40996623039245605,
+      "learning_rate": 0.00019057969406788289,
+      "loss": 0.7512726783752441,
+      "step": 2896
+    },
+    {
+      "epoch": 1.250269687162891,
+      "grad_norm": 0.39559319615364075,
+      "learning_rate": 0.00019055887610285296,
+      "loss": 0.6680556535720825,
+      "step": 2898
+    },
+    {
+      "epoch": 1.2511326860841425,
+      "grad_norm": 0.42002710700035095,
+      "learning_rate": 0.0001905380362999583,
+      "loss": 0.7307850122451782,
+      "step": 2900
+    },
+    {
+      "epoch": 1.2511326860841425,
+      "eval_loss": 0.8155517578125,
+      "eval_runtime": 650.62,
+      "eval_samples_per_second": 3.166,
+      "eval_steps_per_second": 3.166,
+      "step": 2900
+    },
+    {
+      "epoch": 1.2519956850053937,
+      "grad_norm": 0.3914625644683838,
+      "learning_rate": 0.00019051717466422435,
+      "loss": 0.7316054701805115,
+      "step": 2902
+    },
+    {
+      "epoch": 1.2528586839266451,
+      "grad_norm": 0.48939383029937744,
+      "learning_rate": 0.00019049629120068175,
+      "loss": 0.8977305889129639,
+      "step": 2904
+    },
+    {
+      "epoch": 1.2537216828478965,
+      "grad_norm": 0.4892135262489319,
+      "learning_rate": 0.0001904753859143665,
+      "loss": 0.7962324619293213,
+      "step": 2906
+    },
+    {
+      "epoch": 1.2545846817691477,
+      "grad_norm": 0.5323660969734192,
+      "learning_rate": 0.00019045445881031982,
+      "loss": 0.791375458240509,
+      "step": 2908
+    },
+    {
+      "epoch": 1.2554476806903991,
+      "grad_norm": 0.44778114557266235,
+      "learning_rate": 0.00019043350989358818,
+      "loss": 0.7218163013458252,
+      "step": 2910
+    },
+    {
+      "epoch": 1.2563106796116505,
+      "grad_norm": 0.4763379991054535,
+      "learning_rate": 0.00019041253916922326,
+      "loss": 0.7380548119544983,
+      "step": 2912
+    },
+    {
+      "epoch": 1.2571736785329017,
+      "grad_norm": 0.4979628026485443,
+      "learning_rate": 0.00019039154664228213,
+      "loss": 0.7586072683334351,
+      "step": 2914
+    },
+    {
+      "epoch": 1.2580366774541532,
+      "grad_norm": 0.46175920963287354,
+      "learning_rate": 0.000190370532317827,
+      "loss": 0.763477623462677,
+      "step": 2916
+    },
+    {
+      "epoch": 1.2588996763754046,
+      "grad_norm": 0.43192169070243835,
+      "learning_rate": 0.0001903494962009254,
+      "loss": 0.7479409575462341,
+      "step": 2918
+    },
+    {
+      "epoch": 1.2597626752966558,
+      "grad_norm": 0.42883434891700745,
+      "learning_rate": 0.0001903284382966501,
+      "loss": 0.7355074882507324,
+      "step": 2920
+    },
+    {
+      "epoch": 1.2606256742179072,
+      "grad_norm": 0.47708168625831604,
+      "learning_rate": 0.00019030735861007912,
+      "loss": 0.7762811183929443,
+      "step": 2922
+    },
+    {
+      "epoch": 1.2614886731391586,
+      "grad_norm": 0.4478151500225067,
+      "learning_rate": 0.0001902862571462957,
+      "loss": 0.6964467763900757,
+      "step": 2924
+    },
+    {
+      "epoch": 1.26235167206041,
+      "grad_norm": 0.4531081020832062,
+      "learning_rate": 0.00019026513391038837,
+      "loss": 0.7414857745170593,
+      "step": 2926
+    },
+    {
+      "epoch": 1.2632146709816614,
+      "grad_norm": 0.4623842239379883,
+      "learning_rate": 0.00019024398890745092,
+      "loss": 0.7639371156692505,
+      "step": 2928
+    },
+    {
+      "epoch": 1.2640776699029126,
+      "grad_norm": 0.4362739622592926,
+      "learning_rate": 0.00019022282214258238,
+      "loss": 0.800457239151001,
+      "step": 2930
+    },
+    {
+      "epoch": 1.264940668824164,
+      "grad_norm": 0.42854052782058716,
+      "learning_rate": 0.000190201633620887,
+      "loss": 0.7960386872291565,
+      "step": 2932
+    },
+    {
+      "epoch": 1.2658036677454154,
+      "grad_norm": 0.47477999329566956,
+      "learning_rate": 0.0001901804233474743,
+      "loss": 0.7544003129005432,
+      "step": 2934
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 0.4584832191467285,
+      "learning_rate": 0.00019015919132745905,
+      "loss": 0.7819825410842896,
+      "step": 2936
+    },
+    {
+      "epoch": 1.267529665587918,
+      "grad_norm": 0.5465012192726135,
+      "learning_rate": 0.00019013793756596123,
+      "loss": 0.7719182372093201,
+      "step": 2938
+    },
+    {
+      "epoch": 1.2683926645091694,
+      "grad_norm": 0.42024123668670654,
+      "learning_rate": 0.00019011666206810614,
+      "loss": 0.7442063093185425,
+      "step": 2940
+    },
+    {
+      "epoch": 1.2692556634304206,
+      "grad_norm": 0.4374787211418152,
+      "learning_rate": 0.00019009536483902424,
+      "loss": 0.6696176528930664,
+      "step": 2942
+    },
+    {
+      "epoch": 1.270118662351672,
+      "grad_norm": 0.4136449992656708,
+      "learning_rate": 0.00019007404588385125,
+      "loss": 0.7048487663269043,
+      "step": 2944
+    },
+    {
+      "epoch": 1.2709816612729234,
+      "grad_norm": 0.4463474452495575,
+      "learning_rate": 0.00019005270520772817,
+      "loss": 0.7587971687316895,
+      "step": 2946
+    },
+    {
+      "epoch": 1.2718446601941746,
+      "grad_norm": 0.43167322874069214,
+      "learning_rate": 0.00019003134281580115,
+      "loss": 0.7741286754608154,
+      "step": 2948
+    },
+    {
+      "epoch": 1.272707659115426,
+      "grad_norm": 0.5189676284790039,
+      "learning_rate": 0.0001900099587132217,
+      "loss": 0.7572245597839355,
+      "step": 2950
+    },
+    {
+      "epoch": 1.2735706580366775,
+      "grad_norm": 0.4256224036216736,
+      "learning_rate": 0.00018998855290514646,
+      "loss": 0.7743186354637146,
+      "step": 2952
+    },
+    {
+      "epoch": 1.2744336569579289,
+      "grad_norm": 0.4304806888103485,
+      "learning_rate": 0.00018996712539673735,
+      "loss": 0.7287778854370117,
+      "step": 2954
+    },
+    {
+      "epoch": 1.2752966558791803,
+      "grad_norm": 0.489372193813324,
+      "learning_rate": 0.00018994567619316156,
+      "loss": 0.7930773496627808,
+      "step": 2956
+    },
+    {
+      "epoch": 1.2761596548004315,
+      "grad_norm": 0.3855830430984497,
+      "learning_rate": 0.0001899242052995914,
+      "loss": 0.7283111214637756,
+      "step": 2958
+    },
+    {
+      "epoch": 1.2770226537216829,
+      "grad_norm": 0.46708667278289795,
+      "learning_rate": 0.00018990271272120452,
+      "loss": 0.721849262714386,
+      "step": 2960
+    },
+    {
+      "epoch": 1.2778856526429343,
+      "grad_norm": 0.3663526773452759,
+      "learning_rate": 0.00018988119846318377,
+      "loss": 0.6678964495658875,
+      "step": 2962
+    },
+    {
+      "epoch": 1.2787486515641855,
+      "grad_norm": 0.5074638724327087,
+      "learning_rate": 0.00018985966253071718,
+      "loss": 0.8021678924560547,
+      "step": 2964
+    },
+    {
+      "epoch": 1.279611650485437,
+      "grad_norm": 0.4902975857257843,
+      "learning_rate": 0.00018983810492899806,
+      "loss": 0.8313384056091309,
+      "step": 2966
+    },
+    {
+      "epoch": 1.2804746494066883,
+      "grad_norm": 0.5023161768913269,
+      "learning_rate": 0.00018981652566322493,
+      "loss": 0.8330302834510803,
+      "step": 2968
+    },
+    {
+      "epoch": 1.2813376483279395,
+      "grad_norm": 0.48227089643478394,
+      "learning_rate": 0.00018979492473860155,
+      "loss": 0.8806158304214478,
+      "step": 2970
+    },
+    {
+      "epoch": 1.282200647249191,
+      "grad_norm": 0.40143465995788574,
+      "learning_rate": 0.00018977330216033683,
+      "loss": 0.6835185885429382,
+      "step": 2972
+    },
+    {
+      "epoch": 1.2830636461704423,
+      "grad_norm": 0.4368304908275604,
+      "learning_rate": 0.00018975165793364503,
+      "loss": 0.7207706570625305,
+      "step": 2974
+    },
+    {
+      "epoch": 1.2839266450916935,
+      "grad_norm": 0.39989250898361206,
+      "learning_rate": 0.0001897299920637455,
+      "loss": 0.6909692883491516,
+      "step": 2976
+    },
+    {
+      "epoch": 1.284789644012945,
+      "grad_norm": 0.4826473593711853,
+      "learning_rate": 0.0001897083045558629,
+      "loss": 0.838360071182251,
+      "step": 2978
+    },
+    {
+      "epoch": 1.2856526429341963,
+      "grad_norm": 0.4860877990722656,
+      "learning_rate": 0.00018968659541522705,
+      "loss": 0.7693317532539368,
+      "step": 2980
+    },
+    {
+      "epoch": 1.2865156418554478,
+      "grad_norm": 0.4361511170864105,
+      "learning_rate": 0.00018966486464707305,
+      "loss": 0.7662015557289124,
+      "step": 2982
+    },
+    {
+      "epoch": 1.287378640776699,
+      "grad_norm": 0.45333993434906006,
+      "learning_rate": 0.00018964311225664113,
+      "loss": 0.752369225025177,
+      "step": 2984
+    },
+    {
+      "epoch": 1.2882416396979504,
+      "grad_norm": 0.4825304448604584,
+      "learning_rate": 0.0001896213382491768,
+      "loss": 0.7524476051330566,
+      "step": 2986
+    },
+    {
+      "epoch": 1.2891046386192018,
+      "grad_norm": 0.5303854942321777,
+      "learning_rate": 0.00018959954262993077,
+      "loss": 0.8564903736114502,
+      "step": 2988
+    },
+    {
+      "epoch": 1.2899676375404532,
+      "grad_norm": 0.43856459856033325,
+      "learning_rate": 0.00018957772540415896,
+      "loss": 0.7839077711105347,
+      "step": 2990
+    },
+    {
+      "epoch": 1.2908306364617044,
+      "grad_norm": 0.438041627407074,
+      "learning_rate": 0.00018955588657712248,
+      "loss": 0.7580918669700623,
+      "step": 2992
+    },
+    {
+      "epoch": 1.2916936353829558,
+      "grad_norm": 0.4497842490673065,
+      "learning_rate": 0.00018953402615408768,
+      "loss": 0.7014032602310181,
+      "step": 2994
+    },
+    {
+      "epoch": 1.2925566343042072,
+      "grad_norm": 0.5659869313240051,
+      "learning_rate": 0.0001895121441403261,
+      "loss": 0.8220269083976746,
+      "step": 2996
+    },
+    {
+      "epoch": 1.2934196332254584,
+      "grad_norm": 0.4850102961063385,
+      "learning_rate": 0.00018949024054111448,
+      "loss": 0.6880294680595398,
+      "step": 2998
+    },
+    {
+      "epoch": 1.2942826321467098,
+      "grad_norm": 0.4253626763820648,
+      "learning_rate": 0.00018946831536173476,
+      "loss": 0.7443753480911255,
+      "step": 3000
+    },
+    {
+      "epoch": 1.2942826321467098,
+      "eval_loss": 0.8127614259719849,
+      "eval_runtime": 650.4396,
+      "eval_samples_per_second": 3.167,
+      "eval_steps_per_second": 3.167,
+      "step": 3000
+    },
+    {
+      "epoch": 1.2951456310679612,
+      "grad_norm": 0.3746396005153656,
+      "learning_rate": 0.00018944636860747412,
+      "loss": 0.6588667631149292,
+      "step": 3002
+    },
+    {
+      "epoch": 1.2960086299892124,
+      "grad_norm": 0.4039393663406372,
+      "learning_rate": 0.00018942440028362493,
+      "loss": 0.7135416865348816,
+      "step": 3004
+    },
+    {
+      "epoch": 1.2968716289104638,
+      "grad_norm": 0.457533061504364,
+      "learning_rate": 0.00018940241039548474,
+      "loss": 0.7895556688308716,
+      "step": 3006
+    },
+    {
+      "epoch": 1.2977346278317152,
+      "grad_norm": 0.4989747107028961,
+      "learning_rate": 0.0001893803989483563,
+      "loss": 0.7863595485687256,
+      "step": 3008
+    },
+    {
+      "epoch": 1.2985976267529666,
+      "grad_norm": 0.470002681016922,
+      "learning_rate": 0.00018935836594754756,
+      "loss": 0.795306921005249,
+      "step": 3010
+    },
+    {
+      "epoch": 1.2994606256742178,
+      "grad_norm": 0.43668872117996216,
+      "learning_rate": 0.00018933631139837176,
+      "loss": 0.7313401699066162,
+      "step": 3012
+    },
+    {
+      "epoch": 1.3003236245954692,
+      "grad_norm": 0.4843446910381317,
+      "learning_rate": 0.00018931423530614715,
+      "loss": 0.7331582903862,
+      "step": 3014
+    },
+    {
+      "epoch": 1.3011866235167207,
+      "grad_norm": 0.4233832359313965,
+      "learning_rate": 0.00018929213767619735,
+      "loss": 0.7046043872833252,
+      "step": 3016
+    },
+    {
+      "epoch": 1.302049622437972,
+      "grad_norm": 0.6326188445091248,
+      "learning_rate": 0.00018927001851385108,
+      "loss": 0.8217260241508484,
+      "step": 3018
+    },
+    {
+      "epoch": 1.3029126213592233,
+      "grad_norm": 0.409653902053833,
+      "learning_rate": 0.00018924787782444223,
+      "loss": 0.6477662324905396,
+      "step": 3020
+    },
+    {
+      "epoch": 1.3037756202804747,
+      "grad_norm": 0.3869863748550415,
+      "learning_rate": 0.00018922571561331004,
+      "loss": 0.6408766508102417,
+      "step": 3022
+    },
+    {
+      "epoch": 1.304638619201726,
+      "grad_norm": 0.4400722086429596,
+      "learning_rate": 0.00018920353188579874,
+      "loss": 0.7396708726882935,
+      "step": 3024
+    },
+    {
+      "epoch": 1.3055016181229773,
+      "grad_norm": 0.39694252610206604,
+      "learning_rate": 0.00018918132664725784,
+      "loss": 0.6409308314323425,
+      "step": 3026
+    },
+    {
+      "epoch": 1.3063646170442287,
+      "grad_norm": 0.49937903881073,
+      "learning_rate": 0.00018915909990304205,
+      "loss": 0.7825533151626587,
+      "step": 3028
+    },
+    {
+      "epoch": 1.30722761596548,
+      "grad_norm": 0.43940550088882446,
+      "learning_rate": 0.0001891368516585113,
+      "loss": 0.7182250022888184,
+      "step": 3030
+    },
+    {
+      "epoch": 1.3080906148867313,
+      "grad_norm": 0.43905356526374817,
+      "learning_rate": 0.00018911458191903053,
+      "loss": 0.7602632641792297,
+      "step": 3032
+    },
+    {
+      "epoch": 1.3089536138079827,
+      "grad_norm": 0.4172695279121399,
+      "learning_rate": 0.0001890922906899701,
+      "loss": 0.7307555675506592,
+      "step": 3034
+    },
+    {
+      "epoch": 1.309816612729234,
+      "grad_norm": 0.49642932415008545,
+      "learning_rate": 0.00018906997797670544,
+      "loss": 0.782136857509613,
+      "step": 3036
+    },
+    {
+      "epoch": 1.3106796116504853,
+      "grad_norm": 0.49893322587013245,
+      "learning_rate": 0.00018904764378461705,
+      "loss": 0.787925124168396,
+      "step": 3038
+    },
+    {
+      "epoch": 1.3115426105717367,
+      "grad_norm": 0.42691150307655334,
+      "learning_rate": 0.00018902528811909081,
+      "loss": 0.6731302738189697,
+      "step": 3040
+    },
+    {
+      "epoch": 1.3124056094929881,
+      "grad_norm": 0.4961661696434021,
+      "learning_rate": 0.00018900291098551767,
+      "loss": 0.7211409211158752,
+      "step": 3042
+    },
+    {
+      "epoch": 1.3132686084142395,
+      "grad_norm": 0.45150521397590637,
+      "learning_rate": 0.00018898051238929378,
+      "loss": 0.7317034602165222,
+      "step": 3044
+    },
+    {
+      "epoch": 1.314131607335491,
+      "grad_norm": 0.5012714266777039,
+      "learning_rate": 0.00018895809233582047,
+      "loss": 0.7838613390922546,
+      "step": 3046
+    },
+    {
+      "epoch": 1.3149946062567421,
+      "grad_norm": 0.5605086088180542,
+      "learning_rate": 0.0001889356508305042,
+      "loss": 0.8206616640090942,
+      "step": 3048
+    },
+    {
+      "epoch": 1.3158576051779936,
+      "grad_norm": 0.4337491989135742,
+      "learning_rate": 0.00018891318787875666,
+      "loss": 0.7460386753082275,
+      "step": 3050
+    },
+    {
+      "epoch": 1.316720604099245,
+      "grad_norm": 0.4392184913158417,
+      "learning_rate": 0.00018889070348599468,
+      "loss": 0.7973155379295349,
+      "step": 3052
+    },
+    {
+      "epoch": 1.3175836030204962,
+      "grad_norm": 0.4550181031227112,
+      "learning_rate": 0.00018886819765764028,
+      "loss": 0.6951689720153809,
+      "step": 3054
+    },
+    {
+      "epoch": 1.3184466019417476,
+      "grad_norm": 0.4058854877948761,
+      "learning_rate": 0.00018884567039912062,
+      "loss": 0.7353226542472839,
+      "step": 3056
+    },
+    {
+      "epoch": 1.319309600862999,
+      "grad_norm": 0.4157969057559967,
+      "learning_rate": 0.00018882312171586806,
+      "loss": 0.7758772969245911,
+      "step": 3058
+    },
+    {
+      "epoch": 1.3201725997842502,
+      "grad_norm": 0.44122767448425293,
+      "learning_rate": 0.00018880055161332016,
+      "loss": 0.6808486580848694,
+      "step": 3060
+    },
+    {
+      "epoch": 1.3210355987055016,
+      "grad_norm": 0.4674125015735626,
+      "learning_rate": 0.0001887779600969195,
+      "loss": 0.7781010270118713,
+      "step": 3062
+    },
+    {
+      "epoch": 1.321898597626753,
+      "grad_norm": 0.4414712190628052,
+      "learning_rate": 0.000188755347172114,
+      "loss": 0.7759971022605896,
+      "step": 3064
+    },
+    {
+      "epoch": 1.3227615965480042,
+      "grad_norm": 0.4804554283618927,
+      "learning_rate": 0.00018873271284435664,
+      "loss": 0.7430314421653748,
+      "step": 3066
+    },
+    {
+      "epoch": 1.3236245954692556,
+      "grad_norm": 0.4891934096813202,
+      "learning_rate": 0.00018871005711910562,
+      "loss": 0.6974785923957825,
+      "step": 3068
+    },
+    {
+      "epoch": 1.324487594390507,
+      "grad_norm": 0.4103528559207916,
+      "learning_rate": 0.0001886873800018242,
+      "loss": 0.6832907199859619,
+      "step": 3070
+    },
+    {
+      "epoch": 1.3253505933117584,
+      "grad_norm": 0.45092564821243286,
+      "learning_rate": 0.00018866468149798089,
+      "loss": 0.7700413465499878,
+      "step": 3072
+    },
+    {
+      "epoch": 1.3262135922330098,
+      "grad_norm": 0.47934943437576294,
+      "learning_rate": 0.00018864196161304933,
+      "loss": 0.7441738843917847,
+      "step": 3074
+    },
+    {
+      "epoch": 1.327076591154261,
+      "grad_norm": 0.756400465965271,
+      "learning_rate": 0.00018861922035250835,
+      "loss": 0.7195783853530884,
+      "step": 3076
+    },
+    {
+      "epoch": 1.3279395900755124,
+      "grad_norm": 0.47899410128593445,
+      "learning_rate": 0.00018859645772184187,
+      "loss": 0.6692811846733093,
+      "step": 3078
+    },
+    {
+      "epoch": 1.3288025889967638,
+      "grad_norm": 0.43265631794929504,
+      "learning_rate": 0.000188573673726539,
+      "loss": 0.6882596611976624,
+      "step": 3080
+    },
+    {
+      "epoch": 1.329665587918015,
+      "grad_norm": 0.4955349266529083,
+      "learning_rate": 0.00018855086837209401,
+      "loss": 0.9300010204315186,
+      "step": 3082
+    },
+    {
+      "epoch": 1.3305285868392664,
+      "grad_norm": 0.4638696312904358,
+      "learning_rate": 0.0001885280416640063,
+      "loss": 0.8391118049621582,
+      "step": 3084
+    },
+    {
+      "epoch": 1.3313915857605179,
+      "grad_norm": 0.4086083471775055,
+      "learning_rate": 0.00018850519360778044,
+      "loss": 0.7136397957801819,
+      "step": 3086
+    },
+    {
+      "epoch": 1.332254584681769,
+      "grad_norm": 0.4455646574497223,
+      "learning_rate": 0.0001884823242089261,
+      "loss": 0.6886621117591858,
+      "step": 3088
+    },
+    {
+      "epoch": 1.3331175836030205,
+      "grad_norm": 0.43355703353881836,
+      "learning_rate": 0.0001884594334729582,
+      "loss": 0.7261496782302856,
+      "step": 3090
+    },
+    {
+      "epoch": 1.3339805825242719,
+      "grad_norm": 0.5322562456130981,
+      "learning_rate": 0.00018843652140539664,
+      "loss": 0.8529927134513855,
+      "step": 3092
+    },
+    {
+      "epoch": 1.334843581445523,
+      "grad_norm": 0.4504645764827728,
+      "learning_rate": 0.00018841358801176668,
+      "loss": 0.8131585121154785,
+      "step": 3094
+    },
+    {
+      "epoch": 1.3357065803667745,
+      "grad_norm": 0.44101089239120483,
+      "learning_rate": 0.0001883906332975985,
+      "loss": 0.800965428352356,
+      "step": 3096
+    },
+    {
+      "epoch": 1.3365695792880259,
+      "grad_norm": 0.46587181091308594,
+      "learning_rate": 0.00018836765726842759,
+      "loss": 0.711025059223175,
+      "step": 3098
+    },
+    {
+      "epoch": 1.3374325782092773,
+      "grad_norm": 0.4656004011631012,
+      "learning_rate": 0.00018834465992979447,
+      "loss": 0.7824587225914001,
+      "step": 3100
+    },
+    {
+      "epoch": 1.3374325782092773,
+      "eval_loss": 0.8109187483787537,
+      "eval_runtime": 662.5843,
+      "eval_samples_per_second": 3.109,
+      "eval_steps_per_second": 3.109,
+      "step": 3100
+    },
+    {
+      "epoch": 1.3382955771305287,
+      "grad_norm": 0.4942762851715088,
+      "learning_rate": 0.00018832164128724488,
+      "loss": 0.7444300651550293,
+      "step": 3102
+    },
+    {
+      "epoch": 1.33915857605178,
+      "grad_norm": 0.5280060172080994,
+      "learning_rate": 0.00018829860134632963,
+      "loss": 0.8248856067657471,
+      "step": 3104
+    },
+    {
+      "epoch": 1.3400215749730313,
+      "grad_norm": 0.4131146967411041,
+      "learning_rate": 0.00018827554011260474,
+      "loss": 0.7753435373306274,
+      "step": 3106
+    },
+    {
+      "epoch": 1.3408845738942827,
+      "grad_norm": 0.38460803031921387,
+      "learning_rate": 0.0001882524575916313,
+      "loss": 0.7512242197990417,
+      "step": 3108
+    },
+    {
+      "epoch": 1.341747572815534,
+      "grad_norm": 0.4719627797603607,
+      "learning_rate": 0.00018822935378897554,
+      "loss": 0.7760549783706665,
+      "step": 3110
+    },
+    {
+      "epoch": 1.3426105717367853,
+      "grad_norm": 0.47593894600868225,
+      "learning_rate": 0.00018820622871020887,
+      "loss": 0.7802333831787109,
+      "step": 3112
+    },
+    {
+      "epoch": 1.3434735706580367,
+      "grad_norm": 0.46464505791664124,
+      "learning_rate": 0.00018818308236090778,
+      "loss": 0.7037042379379272,
+      "step": 3114
+    },
+    {
+      "epoch": 1.344336569579288,
+      "grad_norm": 0.4358392059803009,
+      "learning_rate": 0.0001881599147466539,
+      "loss": 0.7476377487182617,
+      "step": 3116
+    },
+    {
+      "epoch": 1.3451995685005393,
+      "grad_norm": 0.5236833095550537,
+      "learning_rate": 0.000188136725873034,
+      "loss": 0.8273758292198181,
+      "step": 3118
+    },
+    {
+      "epoch": 1.3460625674217908,
+      "grad_norm": 0.5240068435668945,
+      "learning_rate": 0.00018811351574564,
+      "loss": 0.7407519817352295,
+      "step": 3120
+    },
+    {
+      "epoch": 1.346925566343042,
+      "grad_norm": 0.44454488158226013,
+      "learning_rate": 0.00018809028437006888,
+      "loss": 0.708732008934021,
+      "step": 3122
+    },
+    {
+      "epoch": 1.3477885652642934,
+      "grad_norm": 0.43769216537475586,
+      "learning_rate": 0.00018806703175192283,
+      "loss": 0.7243810296058655,
+      "step": 3124
+    },
+    {
+      "epoch": 1.3486515641855448,
+      "grad_norm": 0.4477781355381012,
+      "learning_rate": 0.00018804375789680905,
+      "loss": 0.7603667974472046,
+      "step": 3126
+    },
+    {
+      "epoch": 1.3495145631067962,
+      "grad_norm": 0.4425322115421295,
+      "learning_rate": 0.00018802046281033997,
+      "loss": 0.7545933127403259,
+      "step": 3128
+    },
+    {
+      "epoch": 1.3503775620280476,
+      "grad_norm": 0.458310604095459,
+      "learning_rate": 0.00018799714649813304,
+      "loss": 0.7925270795822144,
+      "step": 3130
+    },
+    {
+      "epoch": 1.3512405609492988,
+      "grad_norm": 0.4328557848930359,
+      "learning_rate": 0.00018797380896581095,
+      "loss": 0.7392709851264954,
+      "step": 3132
+    },
+    {
+      "epoch": 1.3521035598705502,
+      "grad_norm": 0.4476810693740845,
+      "learning_rate": 0.00018795045021900144,
+      "loss": 0.7340229153633118,
+      "step": 3134
+    },
+    {
+      "epoch": 1.3529665587918016,
+      "grad_norm": 0.3931216895580292,
+      "learning_rate": 0.00018792707026333734,
+      "loss": 0.6678531765937805,
+      "step": 3136
+    },
+    {
+      "epoch": 1.3538295577130528,
+      "grad_norm": 0.4768988788127899,
+      "learning_rate": 0.0001879036691044566,
+      "loss": 0.8059957027435303,
+      "step": 3138
+    },
+    {
+      "epoch": 1.3546925566343042,
+      "grad_norm": 0.4464127719402313,
+      "learning_rate": 0.00018788024674800234,
+      "loss": 0.7618262767791748,
+      "step": 3140
+    },
+    {
+      "epoch": 1.3555555555555556,
+      "grad_norm": 0.4115859866142273,
+      "learning_rate": 0.00018785680319962272,
+      "loss": 0.7277366518974304,
+      "step": 3142
+    },
+    {
+      "epoch": 1.3564185544768068,
+      "grad_norm": 0.40479758381843567,
+      "learning_rate": 0.0001878333384649711,
+      "loss": 0.7587567567825317,
+      "step": 3144
+    },
+    {
+      "epoch": 1.3572815533980582,
+      "grad_norm": 0.5233479738235474,
+      "learning_rate": 0.00018780985254970584,
+      "loss": 0.7896765470504761,
+      "step": 3146
+    },
+    {
+      "epoch": 1.3581445523193096,
+      "grad_norm": 0.5604038834571838,
+      "learning_rate": 0.00018778634545949053,
+      "loss": 0.8300224542617798,
+      "step": 3148
+    },
+    {
+      "epoch": 1.3590075512405608,
+      "grad_norm": 0.48418891429901123,
+      "learning_rate": 0.00018776281719999372,
+      "loss": 0.8129078149795532,
+      "step": 3150
+    },
+    {
+      "epoch": 1.3598705501618122,
+      "grad_norm": 0.4338721036911011,
+      "learning_rate": 0.00018773926777688918,
+      "loss": 0.72742760181427,
+      "step": 3152
+    },
+    {
+      "epoch": 1.3607335490830637,
+      "grad_norm": 0.48870885372161865,
+      "learning_rate": 0.00018771569719585576,
+      "loss": 0.8129846453666687,
+      "step": 3154
+    },
+    {
+      "epoch": 1.361596548004315,
+      "grad_norm": 0.5070347785949707,
+      "learning_rate": 0.00018769210546257736,
+      "loss": 0.7692790031433105,
+      "step": 3156
+    },
+    {
+      "epoch": 1.3624595469255665,
+      "grad_norm": 0.4609982669353485,
+      "learning_rate": 0.0001876684925827431,
+      "loss": 0.6610854864120483,
+      "step": 3158
+    },
+    {
+      "epoch": 1.3633225458468177,
+      "grad_norm": 0.4481177031993866,
+      "learning_rate": 0.000187644858562047,
+      "loss": 0.7724031805992126,
+      "step": 3160
+    },
+    {
+      "epoch": 1.364185544768069,
+      "grad_norm": 0.38047513365745544,
+      "learning_rate": 0.0001876212034061884,
+      "loss": 0.7166935801506042,
+      "step": 3162
+    },
+    {
+      "epoch": 1.3650485436893205,
+      "grad_norm": 0.4010603427886963,
+      "learning_rate": 0.00018759752712087157,
+      "loss": 0.7535263299942017,
+      "step": 3164
+    },
+    {
+      "epoch": 1.3659115426105717,
+      "grad_norm": 0.411430299282074,
+      "learning_rate": 0.00018757382971180598,
+      "loss": 0.7471357583999634,
+      "step": 3166
+    },
+    {
+      "epoch": 1.366774541531823,
+      "grad_norm": 0.36775025725364685,
+      "learning_rate": 0.00018755011118470617,
+      "loss": 0.6910786032676697,
+      "step": 3168
+    },
+    {
+      "epoch": 1.3676375404530745,
+      "grad_norm": 0.5100153684616089,
+      "learning_rate": 0.0001875263715452917,
+      "loss": 0.7566528916358948,
+      "step": 3170
+    },
+    {
+      "epoch": 1.3685005393743257,
+      "grad_norm": 0.43466782569885254,
+      "learning_rate": 0.00018750261079928727,
+      "loss": 0.722017765045166,
+      "step": 3172
+    },
+    {
+      "epoch": 1.369363538295577,
+      "grad_norm": 0.4221585988998413,
+      "learning_rate": 0.00018747882895242275,
+      "loss": 0.7369917035102844,
+      "step": 3174
+    },
+    {
+      "epoch": 1.3702265372168285,
+      "grad_norm": 0.4663652777671814,
+      "learning_rate": 0.00018745502601043298,
+      "loss": 0.7522714138031006,
+      "step": 3176
+    },
+    {
+      "epoch": 1.3710895361380797,
+      "grad_norm": 0.4493909478187561,
+      "learning_rate": 0.0001874312019790579,
+      "loss": 0.7403551340103149,
+      "step": 3178
+    },
+    {
+      "epoch": 1.3719525350593311,
+      "grad_norm": 0.4245595932006836,
+      "learning_rate": 0.00018740735686404266,
+      "loss": 0.6998772025108337,
+      "step": 3180
+    },
+    {
+      "epoch": 1.3728155339805825,
+      "grad_norm": 0.4703865051269531,
+      "learning_rate": 0.00018738349067113735,
+      "loss": 0.6735976934432983,
+      "step": 3182
+    },
+    {
+      "epoch": 1.373678532901834,
+      "grad_norm": 0.5369067788124084,
+      "learning_rate": 0.00018735960340609715,
+      "loss": 0.764581561088562,
+      "step": 3184
+    },
+    {
+      "epoch": 1.3745415318230851,
+      "grad_norm": 0.4964922368526459,
+      "learning_rate": 0.00018733569507468242,
+      "loss": 0.7491477131843567,
+      "step": 3186
+    },
+    {
+      "epoch": 1.3754045307443366,
+      "grad_norm": 0.4167616665363312,
+      "learning_rate": 0.00018731176568265854,
+      "loss": 0.687139093875885,
+      "step": 3188
+    },
+    {
+      "epoch": 1.376267529665588,
+      "grad_norm": 0.4885561764240265,
+      "learning_rate": 0.00018728781523579598,
+      "loss": 0.76422518491745,
+      "step": 3190
+    },
+    {
+      "epoch": 1.3771305285868394,
+      "grad_norm": 0.45865342020988464,
+      "learning_rate": 0.00018726384373987025,
+      "loss": 0.7054057121276855,
+      "step": 3192
+    },
+    {
+      "epoch": 1.3779935275080906,
+      "grad_norm": 0.4557322561740875,
+      "learning_rate": 0.000187239851200662,
+      "loss": 0.7476370334625244,
+      "step": 3194
+    },
+    {
+      "epoch": 1.378856526429342,
+      "grad_norm": 0.4359823763370514,
+      "learning_rate": 0.00018721583762395692,
+      "loss": 0.7450100183486938,
+      "step": 3196
+    },
+    {
+      "epoch": 1.3797195253505934,
+      "grad_norm": 0.45140165090560913,
+      "learning_rate": 0.00018719180301554576,
+      "loss": 0.6332225799560547,
+      "step": 3198
+    },
+    {
+      "epoch": 1.3805825242718446,
+      "grad_norm": 0.4051663875579834,
+      "learning_rate": 0.00018716774738122436,
+      "loss": 0.6999903917312622,
+      "step": 3200
+    },
+    {
+      "epoch": 1.3805825242718446,
+      "eval_loss": 0.8053163290023804,
+      "eval_runtime": 668.3288,
+      "eval_samples_per_second": 3.082,
+      "eval_steps_per_second": 3.082,
+      "step": 3200
+    },
+    {
+      "epoch": 1.381445523193096,
+      "grad_norm": 0.43624332547187805,
+      "learning_rate": 0.00018714367072679365,
+      "loss": 0.675305962562561,
+      "step": 3202
+    },
+    {
+      "epoch": 1.3823085221143474,
+      "grad_norm": 0.5163410902023315,
+      "learning_rate": 0.00018711957305805955,
+      "loss": 0.8098652958869934,
+      "step": 3204
+    },
+    {
+      "epoch": 1.3831715210355986,
+      "grad_norm": 0.5261862277984619,
+      "learning_rate": 0.00018709545438083317,
+      "loss": 0.7265567779541016,
+      "step": 3206
+    },
+    {
+      "epoch": 1.38403451995685,
+      "grad_norm": 0.5289353728294373,
+      "learning_rate": 0.0001870713147009306,
+      "loss": 0.8171496987342834,
+      "step": 3208
+    },
+    {
+      "epoch": 1.3848975188781014,
+      "grad_norm": 0.45589691400527954,
+      "learning_rate": 0.000187047154024173,
+      "loss": 0.800773024559021,
+      "step": 3210
+    },
+    {
+      "epoch": 1.3857605177993528,
+      "grad_norm": 0.4709073603153229,
+      "learning_rate": 0.00018702297235638664,
+      "loss": 0.7034035921096802,
+      "step": 3212
+    },
+    {
+      "epoch": 1.386623516720604,
+      "grad_norm": 0.41431429982185364,
+      "learning_rate": 0.00018699876970340278,
+      "loss": 0.6707210540771484,
+      "step": 3214
+    },
+    {
+      "epoch": 1.3874865156418554,
+      "grad_norm": 0.4663850963115692,
+      "learning_rate": 0.0001869745460710578,
+      "loss": 0.7554471492767334,
+      "step": 3216
+    },
+    {
+      "epoch": 1.3883495145631068,
+      "grad_norm": 0.3720403015613556,
+      "learning_rate": 0.00018695030146519313,
+      "loss": 0.6852688193321228,
+      "step": 3218
+    },
+    {
+      "epoch": 1.3892125134843583,
+      "grad_norm": 0.46755164861679077,
+      "learning_rate": 0.00018692603589165523,
+      "loss": 0.7974506616592407,
+      "step": 3220
+    },
+    {
+      "epoch": 1.3900755124056094,
+      "grad_norm": 0.4087965786457062,
+      "learning_rate": 0.00018690174935629563,
+      "loss": 0.6643959283828735,
+      "step": 3222
+    },
+    {
+      "epoch": 1.3909385113268609,
+      "grad_norm": 0.43572601675987244,
+      "learning_rate": 0.00018687744186497092,
+      "loss": 0.6455117464065552,
+      "step": 3224
+    },
+    {
+      "epoch": 1.3918015102481123,
+      "grad_norm": 0.4832928776741028,
+      "learning_rate": 0.00018685311342354276,
+      "loss": 0.7152265310287476,
+      "step": 3226
+    },
+    {
+      "epoch": 1.3926645091693635,
+      "grad_norm": 0.44429874420166016,
+      "learning_rate": 0.00018682876403787783,
+      "loss": 0.714832067489624,
+      "step": 3228
+    },
+    {
+      "epoch": 1.3935275080906149,
+      "grad_norm": 0.4570554494857788,
+      "learning_rate": 0.0001868043937138479,
+      "loss": 0.7785174250602722,
+      "step": 3230
+    },
+    {
+      "epoch": 1.3943905070118663,
+      "grad_norm": 0.4618188738822937,
+      "learning_rate": 0.00018678000245732972,
+      "loss": 0.7226384878158569,
+      "step": 3232
+    },
+    {
+      "epoch": 1.3952535059331175,
+      "grad_norm": 0.5473061203956604,
+      "learning_rate": 0.00018675559027420515,
+      "loss": 0.741666316986084,
+      "step": 3234
+    },
+    {
+      "epoch": 1.396116504854369,
+      "grad_norm": 0.45633625984191895,
+      "learning_rate": 0.0001867311571703611,
+      "loss": 0.7774195671081543,
+      "step": 3236
+    },
+    {
+      "epoch": 1.3969795037756203,
+      "grad_norm": 0.4549288749694824,
+      "learning_rate": 0.00018670670315168946,
+      "loss": 0.7062699794769287,
+      "step": 3238
+    },
+    {
+      "epoch": 1.3978425026968715,
+      "grad_norm": 0.4530162513256073,
+      "learning_rate": 0.00018668222822408725,
+      "loss": 0.7901433110237122,
+      "step": 3240
+    },
+    {
+      "epoch": 1.398705501618123,
+      "grad_norm": 0.4526861608028412,
+      "learning_rate": 0.00018665773239345647,
+      "loss": 0.7321763038635254,
+      "step": 3242
+    },
+    {
+      "epoch": 1.3995685005393743,
+      "grad_norm": 0.471683531999588,
+      "learning_rate": 0.00018663321566570417,
+      "loss": 0.780885636806488,
+      "step": 3244
+    },
+    {
+      "epoch": 1.4004314994606257,
+      "grad_norm": 0.4421135187149048,
+      "learning_rate": 0.00018660867804674248,
+      "loss": 0.7124532461166382,
+      "step": 3246
+    },
+    {
+      "epoch": 1.4012944983818771,
+      "grad_norm": 0.45071855187416077,
+      "learning_rate": 0.00018658411954248849,
+      "loss": 0.7868198156356812,
+      "step": 3248
+    },
+    {
+      "epoch": 1.4021574973031283,
+      "grad_norm": 0.45456045866012573,
+      "learning_rate": 0.0001865595401588644,
+      "loss": 0.7364398837089539,
+      "step": 3250
+    },
+    {
+      "epoch": 1.4030204962243797,
+      "grad_norm": 0.4487321972846985,
+      "learning_rate": 0.0001865349399017974,
+      "loss": 0.7381253838539124,
+      "step": 3252
+    },
+    {
+      "epoch": 1.4038834951456312,
+      "grad_norm": 0.433517724275589,
+      "learning_rate": 0.00018651031877721976,
+      "loss": 0.6974755525588989,
+      "step": 3254
+    },
+    {
+      "epoch": 1.4047464940668823,
+      "grad_norm": 0.45759329199790955,
+      "learning_rate": 0.00018648567679106873,
+      "loss": 0.7638785243034363,
+      "step": 3256
+    },
+    {
+      "epoch": 1.4056094929881338,
+      "grad_norm": 0.4451565742492676,
+      "learning_rate": 0.00018646101394928662,
+      "loss": 0.7301747798919678,
+      "step": 3258
+    },
+    {
+      "epoch": 1.4064724919093852,
+      "grad_norm": 0.5451349020004272,
+      "learning_rate": 0.0001864363302578208,
+      "loss": 0.770787239074707,
+      "step": 3260
+    },
+    {
+      "epoch": 1.4073354908306364,
+      "grad_norm": 0.47335579991340637,
+      "learning_rate": 0.00018641162572262355,
+      "loss": 0.7637011408805847,
+      "step": 3262
+    },
+    {
+      "epoch": 1.4081984897518878,
+      "grad_norm": 0.480887234210968,
+      "learning_rate": 0.0001863869003496523,
+      "loss": 0.7140913009643555,
+      "step": 3264
+    },
+    {
+      "epoch": 1.4090614886731392,
+      "grad_norm": 0.4122021496295929,
+      "learning_rate": 0.0001863621541448695,
+      "loss": 0.6538959741592407,
+      "step": 3266
+    },
+    {
+      "epoch": 1.4099244875943904,
+      "grad_norm": 0.4456968605518341,
+      "learning_rate": 0.00018633738711424253,
+      "loss": 0.7153927087783813,
+      "step": 3268
+    },
+    {
+      "epoch": 1.4107874865156418,
+      "grad_norm": 0.4152887761592865,
+      "learning_rate": 0.00018631259926374388,
+      "loss": 0.7140036821365356,
+      "step": 3270
+    },
+    {
+      "epoch": 1.4116504854368932,
+      "grad_norm": 0.47110119462013245,
+      "learning_rate": 0.00018628779059935103,
+      "loss": 0.7193810939788818,
+      "step": 3272
+    },
+    {
+      "epoch": 1.4125134843581446,
+      "grad_norm": 0.39739692211151123,
+      "learning_rate": 0.0001862629611270464,
+      "loss": 0.7133702039718628,
+      "step": 3274
+    },
+    {
+      "epoch": 1.413376483279396,
+      "grad_norm": 0.4808974862098694,
+      "learning_rate": 0.00018623811085281765,
+      "loss": 0.811927855014801,
+      "step": 3276
+    },
+    {
+      "epoch": 1.4142394822006472,
+      "grad_norm": 0.4607976973056793,
+      "learning_rate": 0.00018621323978265718,
+      "loss": 0.8125779032707214,
+      "step": 3278
+    },
+    {
+      "epoch": 1.4151024811218986,
+      "grad_norm": 0.41523823142051697,
+      "learning_rate": 0.00018618834792256261,
+      "loss": 0.7065606117248535,
+      "step": 3280
+    },
+    {
+      "epoch": 1.41596548004315,
+      "grad_norm": 0.46665191650390625,
+      "learning_rate": 0.00018616343527853645,
+      "loss": 0.7346477508544922,
+      "step": 3282
+    },
+    {
+      "epoch": 1.4168284789644012,
+      "grad_norm": 0.4744371473789215,
+      "learning_rate": 0.00018613850185658634,
+      "loss": 0.7590131759643555,
+      "step": 3284
+    },
+    {
+      "epoch": 1.4176914778856526,
+      "grad_norm": 0.4905717074871063,
+      "learning_rate": 0.0001861135476627248,
+      "loss": 0.786243200302124,
+      "step": 3286
+    },
+    {
+      "epoch": 1.418554476806904,
+      "grad_norm": 0.45114004611968994,
+      "learning_rate": 0.00018608857270296944,
+      "loss": 0.6855072379112244,
+      "step": 3288
+    },
+    {
+      "epoch": 1.4194174757281552,
+      "grad_norm": 0.5547319054603577,
+      "learning_rate": 0.00018606357698334284,
+      "loss": 0.8294073343276978,
+      "step": 3290
+    },
+    {
+      "epoch": 1.4202804746494067,
+      "grad_norm": 0.4100660979747772,
+      "learning_rate": 0.00018603856050987267,
+      "loss": 0.6352306604385376,
+      "step": 3292
+    },
+    {
+      "epoch": 1.421143473570658,
+      "grad_norm": 0.47723907232284546,
+      "learning_rate": 0.00018601352328859148,
+      "loss": 0.7822797298431396,
+      "step": 3294
+    },
+    {
+      "epoch": 1.4220064724919093,
+      "grad_norm": 0.45811668038368225,
+      "learning_rate": 0.00018598846532553691,
+      "loss": 0.7675215601921082,
+      "step": 3296
+    },
+    {
+      "epoch": 1.4228694714131607,
+      "grad_norm": 0.4794461131095886,
+      "learning_rate": 0.00018596338662675154,
+      "loss": 0.7994555234909058,
+      "step": 3298
+    },
+    {
+      "epoch": 1.423732470334412,
+      "grad_norm": 0.458723783493042,
+      "learning_rate": 0.00018593828719828303,
+      "loss": 0.7676554918289185,
+      "step": 3300
+    },
+    {
+      "epoch": 1.423732470334412,
+      "eval_loss": 0.8030428886413574,
+      "eval_runtime": 658.5495,
+      "eval_samples_per_second": 3.128,
+      "eval_steps_per_second": 3.128,
+      "step": 3300
+    },
+    {
+      "epoch": 1.4245954692556635,
+      "grad_norm": 0.4599555432796478,
+      "learning_rate": 0.00018591316704618397,
+      "loss": 0.7642499804496765,
+      "step": 3302
+    },
+    {
+      "epoch": 1.425458468176915,
+      "grad_norm": 0.5012795925140381,
+      "learning_rate": 0.000185888026176512,
+      "loss": 0.7753090262413025,
+      "step": 3304
+    },
+    {
+      "epoch": 1.426321467098166,
+      "grad_norm": 0.4497458040714264,
+      "learning_rate": 0.00018586286459532967,
+      "loss": 0.7226543426513672,
+      "step": 3306
+    },
+    {
+      "epoch": 1.4271844660194175,
+      "grad_norm": 0.47314873337745667,
+      "learning_rate": 0.0001858376823087046,
+      "loss": 0.752973735332489,
+      "step": 3308
+    },
+    {
+      "epoch": 1.428047464940669,
+      "grad_norm": 0.45765072107315063,
+      "learning_rate": 0.00018581247932270944,
+      "loss": 0.7653468251228333,
+      "step": 3310
+    },
+    {
+      "epoch": 1.42891046386192,
+      "grad_norm": 0.4725930392742157,
+      "learning_rate": 0.0001857872556434217,
+      "loss": 0.8080248832702637,
+      "step": 3312
+    },
+    {
+      "epoch": 1.4297734627831715,
+      "grad_norm": 0.4430061876773834,
+      "learning_rate": 0.00018576201127692402,
+      "loss": 0.8083968162536621,
+      "step": 3314
+    },
+    {
+      "epoch": 1.430636461704423,
+      "grad_norm": 0.4197101294994354,
+      "learning_rate": 0.00018573674622930392,
+      "loss": 0.7861490249633789,
+      "step": 3316
+    },
+    {
+      "epoch": 1.4314994606256741,
+      "grad_norm": 0.4047538936138153,
+      "learning_rate": 0.00018571146050665397,
+      "loss": 0.8125455379486084,
+      "step": 3318
+    },
+    {
+      "epoch": 1.4323624595469255,
+      "grad_norm": 0.5689038634300232,
+      "learning_rate": 0.00018568615411507174,
+      "loss": 0.779180645942688,
+      "step": 3320
+    },
+    {
+      "epoch": 1.433225458468177,
+      "grad_norm": 0.47798338532447815,
+      "learning_rate": 0.00018566082706065969,
+      "loss": 0.7555606961250305,
+      "step": 3322
+    },
+    {
+      "epoch": 1.4340884573894281,
+      "grad_norm": 0.4296347200870514,
+      "learning_rate": 0.00018563547934952537,
+      "loss": 0.6761099696159363,
+      "step": 3324
+    },
+    {
+      "epoch": 1.4349514563106796,
+      "grad_norm": 0.4605977237224579,
+      "learning_rate": 0.00018561011098778126,
+      "loss": 0.7465946078300476,
+      "step": 3326
+    },
+    {
+      "epoch": 1.435814455231931,
+      "grad_norm": 0.48226889967918396,
+      "learning_rate": 0.00018558472198154478,
+      "loss": 0.7459924817085266,
+      "step": 3328
+    },
+    {
+      "epoch": 1.4366774541531824,
+      "grad_norm": 0.4655393362045288,
+      "learning_rate": 0.00018555931233693845,
+      "loss": 0.6451191306114197,
+      "step": 3330
+    },
+    {
+      "epoch": 1.4375404530744338,
+      "grad_norm": 0.4614768922328949,
+      "learning_rate": 0.00018553388206008961,
+      "loss": 0.764894962310791,
+      "step": 3332
+    },
+    {
+      "epoch": 1.438403451995685,
+      "grad_norm": 0.47503674030303955,
+      "learning_rate": 0.00018550843115713072,
+      "loss": 0.7709850072860718,
+      "step": 3334
+    },
+    {
+      "epoch": 1.4392664509169364,
+      "grad_norm": 0.5408021807670593,
+      "learning_rate": 0.00018548295963419914,
+      "loss": 0.8470542430877686,
+      "step": 3336
+    },
+    {
+      "epoch": 1.4401294498381878,
+      "grad_norm": 0.44747427105903625,
+      "learning_rate": 0.0001854574674974372,
+      "loss": 0.770861804485321,
+      "step": 3338
+    },
+    {
+      "epoch": 1.440992448759439,
+      "grad_norm": 0.3823722004890442,
+      "learning_rate": 0.00018543195475299222,
+      "loss": 0.6909842491149902,
+      "step": 3340
+    },
+    {
+      "epoch": 1.4418554476806904,
+      "grad_norm": 0.42207640409469604,
+      "learning_rate": 0.0001854064214070165,
+      "loss": 0.7684979438781738,
+      "step": 3342
+    },
+    {
+      "epoch": 1.4427184466019418,
+      "grad_norm": 0.4514349400997162,
+      "learning_rate": 0.00018538086746566724,
+      "loss": 0.754643440246582,
+      "step": 3344
+    },
+    {
+      "epoch": 1.443581445523193,
+      "grad_norm": 0.4289906620979309,
+      "learning_rate": 0.0001853552929351067,
+      "loss": 0.7302715182304382,
+      "step": 3346
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 0.4458511173725128,
+      "learning_rate": 0.00018532969782150205,
+      "loss": 0.7611445188522339,
+      "step": 3348
+    },
+    {
+      "epoch": 1.4453074433656958,
+      "grad_norm": 0.4370715022087097,
+      "learning_rate": 0.00018530408213102546,
+      "loss": 0.7713651061058044,
+      "step": 3350
+    },
+    {
+      "epoch": 1.446170442286947,
+      "grad_norm": 0.40230461955070496,
+      "learning_rate": 0.000185278445869854,
+      "loss": 0.6728963851928711,
+      "step": 3352
+    },
+    {
+      "epoch": 1.4470334412081984,
+      "grad_norm": 0.43601900339126587,
+      "learning_rate": 0.00018525278904416975,
+      "loss": 0.7662684321403503,
+      "step": 3354
+    },
+    {
+      "epoch": 1.4478964401294498,
+      "grad_norm": 0.45813488960266113,
+      "learning_rate": 0.00018522711166015974,
+      "loss": 0.8269308805465698,
+      "step": 3356
+    },
+    {
+      "epoch": 1.4487594390507013,
+      "grad_norm": 0.48386695981025696,
+      "learning_rate": 0.00018520141372401595,
+      "loss": 0.8171968460083008,
+      "step": 3358
+    },
+    {
+      "epoch": 1.4496224379719527,
+      "grad_norm": 0.41737180948257446,
+      "learning_rate": 0.00018517569524193535,
+      "loss": 0.8057414889335632,
+      "step": 3360
+    },
+    {
+      "epoch": 1.4504854368932039,
+      "grad_norm": 0.41048938035964966,
+      "learning_rate": 0.0001851499562201198,
+      "loss": 0.7350438833236694,
+      "step": 3362
+    },
+    {
+      "epoch": 1.4513484358144553,
+      "grad_norm": 0.49414724111557007,
+      "learning_rate": 0.0001851241966647762,
+      "loss": 0.7771334052085876,
+      "step": 3364
+    },
+    {
+      "epoch": 1.4522114347357067,
+      "grad_norm": 0.48357486724853516,
+      "learning_rate": 0.00018509841658211632,
+      "loss": 0.8041897416114807,
+      "step": 3366
+    },
+    {
+      "epoch": 1.4530744336569579,
+      "grad_norm": 0.44553041458129883,
+      "learning_rate": 0.00018507261597835686,
+      "loss": 0.7079073786735535,
+      "step": 3368
+    },
+    {
+      "epoch": 1.4539374325782093,
+      "grad_norm": 0.4198709726333618,
+      "learning_rate": 0.0001850467948597196,
+      "loss": 0.7564307451248169,
+      "step": 3370
+    },
+    {
+      "epoch": 1.4548004314994607,
+      "grad_norm": 0.4005102217197418,
+      "learning_rate": 0.00018502095323243113,
+      "loss": 0.6955130696296692,
+      "step": 3372
+    },
+    {
+      "epoch": 1.455663430420712,
+      "grad_norm": 0.43197157979011536,
+      "learning_rate": 0.00018499509110272308,
+      "loss": 0.6564432978630066,
+      "step": 3374
+    },
+    {
+      "epoch": 1.4565264293419633,
+      "grad_norm": 0.4266451299190521,
+      "learning_rate": 0.00018496920847683196,
+      "loss": 0.6715503931045532,
+      "step": 3376
+    },
+    {
+      "epoch": 1.4573894282632147,
+      "grad_norm": 0.4835279583930969,
+      "learning_rate": 0.00018494330536099926,
+      "loss": 0.7800700068473816,
+      "step": 3378
+    },
+    {
+      "epoch": 1.458252427184466,
+      "grad_norm": 0.5084423422813416,
+      "learning_rate": 0.00018491738176147139,
+      "loss": 0.7650374174118042,
+      "step": 3380
+    },
+    {
+      "epoch": 1.4591154261057173,
+      "grad_norm": 0.41681453585624695,
+      "learning_rate": 0.00018489143768449974,
+      "loss": 0.7307957410812378,
+      "step": 3382
+    },
+    {
+      "epoch": 1.4599784250269687,
+      "grad_norm": 0.4184363782405853,
+      "learning_rate": 0.00018486547313634058,
+      "loss": 0.7257798910140991,
+      "step": 3384
+    },
+    {
+      "epoch": 1.4608414239482201,
+      "grad_norm": 0.5055010318756104,
+      "learning_rate": 0.00018483948812325512,
+      "loss": 0.7981155514717102,
+      "step": 3386
+    },
+    {
+      "epoch": 1.4617044228694713,
+      "grad_norm": 0.4449431300163269,
+      "learning_rate": 0.00018481348265150961,
+      "loss": 0.7802942395210266,
+      "step": 3388
+    },
+    {
+      "epoch": 1.4625674217907227,
+      "grad_norm": 0.3826743960380554,
+      "learning_rate": 0.00018478745672737508,
+      "loss": 0.6799795031547546,
+      "step": 3390
+    },
+    {
+      "epoch": 1.4634304207119742,
+      "grad_norm": 0.4156678318977356,
+      "learning_rate": 0.00018476141035712757,
+      "loss": 0.7275620698928833,
+      "step": 3392
+    },
+    {
+      "epoch": 1.4642934196332256,
+      "grad_norm": 0.47241929173469543,
+      "learning_rate": 0.00018473534354704807,
+      "loss": 0.6979914903640747,
+      "step": 3394
+    },
+    {
+      "epoch": 1.4651564185544768,
+      "grad_norm": 0.4340677261352539,
+      "learning_rate": 0.00018470925630342247,
+      "loss": 0.7208709120750427,
+      "step": 3396
+    },
+    {
+      "epoch": 1.4660194174757282,
+      "grad_norm": 0.39896467328071594,
+      "learning_rate": 0.00018468314863254154,
+      "loss": 0.6596860885620117,
+      "step": 3398
+    },
+    {
+      "epoch": 1.4668824163969796,
+      "grad_norm": 0.4282037317752838,
+      "learning_rate": 0.00018465702054070113,
+      "loss": 0.7703273892402649,
+      "step": 3400
+    },
+    {
+      "epoch": 1.4668824163969796,
+      "eval_loss": 0.8002338409423828,
+      "eval_runtime": 649.7427,
+      "eval_samples_per_second": 3.17,
+      "eval_steps_per_second": 3.17,
+      "step": 3400
+    },
+    {
+      "epoch": 1.4677454153182308,
+      "grad_norm": 0.39301496744155884,
+      "learning_rate": 0.00018463087203420182,
+      "loss": 0.740729033946991,
+      "step": 3402
+    },
+    {
+      "epoch": 1.4686084142394822,
+      "grad_norm": 0.4466440677642822,
+      "learning_rate": 0.00018460470311934923,
+      "loss": 0.6625239253044128,
+      "step": 3404
+    },
+    {
+      "epoch": 1.4694714131607336,
+      "grad_norm": 0.48659050464630127,
+      "learning_rate": 0.00018457851380245392,
+      "loss": 0.7232626080513,
+      "step": 3406
+    },
+    {
+      "epoch": 1.4703344120819848,
+      "grad_norm": 0.44322678446769714,
+      "learning_rate": 0.00018455230408983124,
+      "loss": 0.6909189224243164,
+      "step": 3408
+    },
+    {
+      "epoch": 1.4711974110032362,
+      "grad_norm": 0.4537222683429718,
+      "learning_rate": 0.0001845260739878016,
+      "loss": 0.728760302066803,
+      "step": 3410
+    },
+    {
+      "epoch": 1.4720604099244876,
+      "grad_norm": 0.426753968000412,
+      "learning_rate": 0.0001844998235026903,
+      "loss": 0.6631523966789246,
+      "step": 3412
+    },
+    {
+      "epoch": 1.472923408845739,
+      "grad_norm": 0.46893343329429626,
+      "learning_rate": 0.0001844735526408275,
+      "loss": 0.7257310748100281,
+      "step": 3414
+    },
+    {
+      "epoch": 1.4737864077669902,
+      "grad_norm": 0.41580045223236084,
+      "learning_rate": 0.00018444726140854823,
+      "loss": 0.7732333540916443,
+      "step": 3416
+    },
+    {
+      "epoch": 1.4746494066882416,
+      "grad_norm": 0.42891791462898254,
+      "learning_rate": 0.00018442094981219257,
+      "loss": 0.6602647304534912,
+      "step": 3418
+    },
+    {
+      "epoch": 1.475512405609493,
+      "grad_norm": 0.45967262983322144,
+      "learning_rate": 0.00018439461785810547,
+      "loss": 0.7164129018783569,
+      "step": 3420
+    },
+    {
+      "epoch": 1.4763754045307445,
+      "grad_norm": 0.4251352846622467,
+      "learning_rate": 0.0001843682655526367,
+      "loss": 0.7289180755615234,
+      "step": 3422
+    },
+    {
+      "epoch": 1.4772384034519956,
+      "grad_norm": 0.3898853361606598,
+      "learning_rate": 0.00018434189290214106,
+      "loss": 0.7455880641937256,
+      "step": 3424
+    },
+    {
+      "epoch": 1.478101402373247,
+      "grad_norm": 0.4341840445995331,
+      "learning_rate": 0.00018431549991297815,
+      "loss": 0.7042546272277832,
+      "step": 3426
+    },
+    {
+      "epoch": 1.4789644012944985,
+      "grad_norm": 0.41306495666503906,
+      "learning_rate": 0.00018428908659151252,
+      "loss": 0.7600736021995544,
+      "step": 3428
+    },
+    {
+      "epoch": 1.4798274002157497,
+      "grad_norm": 0.41544052958488464,
+      "learning_rate": 0.00018426265294411363,
+      "loss": 0.7219595909118652,
+      "step": 3430
+    },
+    {
+      "epoch": 1.480690399137001,
+      "grad_norm": 0.45290282368659973,
+      "learning_rate": 0.00018423619897715585,
+      "loss": 0.8417305946350098,
+      "step": 3432
+    },
+    {
+      "epoch": 1.4815533980582525,
+      "grad_norm": 0.4438819885253906,
+      "learning_rate": 0.00018420972469701842,
+      "loss": 0.7625543475151062,
+      "step": 3434
+    },
+    {
+      "epoch": 1.4824163969795037,
+      "grad_norm": 0.49848470091819763,
+      "learning_rate": 0.00018418323011008548,
+      "loss": 0.7759302258491516,
+      "step": 3436
+    },
+    {
+      "epoch": 1.483279395900755,
+      "grad_norm": 0.3774218261241913,
+      "learning_rate": 0.00018415671522274614,
+      "loss": 0.6921430826187134,
+      "step": 3438
+    },
+    {
+      "epoch": 1.4841423948220065,
+      "grad_norm": 0.4494822919368744,
+      "learning_rate": 0.0001841301800413943,
+      "loss": 0.6789629459381104,
+      "step": 3440
+    },
+    {
+      "epoch": 1.4850053937432577,
+      "grad_norm": 0.4084416329860687,
+      "learning_rate": 0.00018410362457242876,
+      "loss": 0.6904259324073792,
+      "step": 3442
+    },
+    {
+      "epoch": 1.485868392664509,
+      "grad_norm": 0.4472881257534027,
+      "learning_rate": 0.0001840770488222533,
+      "loss": 0.7037150263786316,
+      "step": 3444
+    },
+    {
+      "epoch": 1.4867313915857605,
+      "grad_norm": 0.4696385860443115,
+      "learning_rate": 0.0001840504527972766,
+      "loss": 0.7732300758361816,
+      "step": 3446
+    },
+    {
+      "epoch": 1.487594390507012,
+      "grad_norm": 0.4683626592159271,
+      "learning_rate": 0.00018402383650391207,
+      "loss": 0.767594039440155,
+      "step": 3448
+    },
+    {
+      "epoch": 1.4884573894282633,
+      "grad_norm": 0.47404953837394714,
+      "learning_rate": 0.00018399719994857816,
+      "loss": 0.8145772218704224,
+      "step": 3450
+    },
+    {
+      "epoch": 1.4893203883495145,
+      "grad_norm": 0.5147852897644043,
+      "learning_rate": 0.00018397054313769814,
+      "loss": 0.784772515296936,
+      "step": 3452
+    },
+    {
+      "epoch": 1.490183387270766,
+      "grad_norm": 0.5376461744308472,
+      "learning_rate": 0.00018394386607770017,
+      "loss": 0.7849431037902832,
+      "step": 3454
+    },
+    {
+      "epoch": 1.4910463861920173,
+      "grad_norm": 0.4688630700111389,
+      "learning_rate": 0.0001839171687750173,
+      "loss": 0.7196945548057556,
+      "step": 3456
+    },
+    {
+      "epoch": 1.4919093851132685,
+      "grad_norm": 0.5115576386451721,
+      "learning_rate": 0.00018389045123608753,
+      "loss": 0.8277292251586914,
+      "step": 3458
+    },
+    {
+      "epoch": 1.49277238403452,
+      "grad_norm": 0.3999786674976349,
+      "learning_rate": 0.0001838637134673536,
+      "loss": 0.7628065943717957,
+      "step": 3460
+    },
+    {
+      "epoch": 1.4936353829557714,
+      "grad_norm": 0.4474492371082306,
+      "learning_rate": 0.00018383695547526322,
+      "loss": 0.717315673828125,
+      "step": 3462
+    },
+    {
+      "epoch": 1.4944983818770226,
+      "grad_norm": 0.4175044596195221,
+      "learning_rate": 0.00018381017726626896,
+      "loss": 0.7365549206733704,
+      "step": 3464
+    },
+    {
+      "epoch": 1.495361380798274,
+      "grad_norm": 0.4938793480396271,
+      "learning_rate": 0.0001837833788468283,
+      "loss": 0.7562727928161621,
+      "step": 3466
+    },
+    {
+      "epoch": 1.4962243797195254,
+      "grad_norm": 0.4369599521160126,
+      "learning_rate": 0.0001837565602234035,
+      "loss": 0.82245272397995,
+      "step": 3468
+    },
+    {
+      "epoch": 1.4970873786407766,
+      "grad_norm": 0.4824387729167938,
+      "learning_rate": 0.00018372972140246182,
+      "loss": 0.7570599913597107,
+      "step": 3470
+    },
+    {
+      "epoch": 1.497950377562028,
+      "grad_norm": 0.46261459589004517,
+      "learning_rate": 0.00018370286239047522,
+      "loss": 0.7152431607246399,
+      "step": 3472
+    },
+    {
+      "epoch": 1.4988133764832794,
+      "grad_norm": 0.4452435076236725,
+      "learning_rate": 0.0001836759831939207,
+      "loss": 0.6635003089904785,
+      "step": 3474
+    },
+    {
+      "epoch": 1.4996763754045308,
+      "grad_norm": 0.4698450267314911,
+      "learning_rate": 0.0001836490838192801,
+      "loss": 0.7814362645149231,
+      "step": 3476
+    },
+    {
+      "epoch": 1.5005393743257822,
+      "grad_norm": 0.44320493936538696,
+      "learning_rate": 0.00018362216427303998,
+      "loss": 0.6941080689430237,
+      "step": 3478
+    },
+    {
+      "epoch": 1.5014023732470334,
+      "grad_norm": 0.467252254486084,
+      "learning_rate": 0.00018359522456169193,
+      "loss": 0.7583049535751343,
+      "step": 3480
+    },
+    {
+      "epoch": 1.5022653721682848,
+      "grad_norm": 0.5454360842704773,
+      "learning_rate": 0.00018356826469173232,
+      "loss": 0.9017908573150635,
+      "step": 3482
+    },
+    {
+      "epoch": 1.5031283710895362,
+      "grad_norm": 0.5124768614768982,
+      "learning_rate": 0.00018354128466966242,
+      "loss": 0.8088064789772034,
+      "step": 3484
+    },
+    {
+      "epoch": 1.5039913700107874,
+      "grad_norm": 0.4634758234024048,
+      "learning_rate": 0.00018351428450198834,
+      "loss": 0.7869967222213745,
+      "step": 3486
+    },
+    {
+      "epoch": 1.5048543689320388,
+      "grad_norm": 0.39626801013946533,
+      "learning_rate": 0.00018348726419522098,
+      "loss": 0.7509294152259827,
+      "step": 3488
+    },
+    {
+      "epoch": 1.5057173678532902,
+      "grad_norm": 0.48879387974739075,
+      "learning_rate": 0.00018346022375587628,
+      "loss": 0.710981011390686,
+      "step": 3490
+    },
+    {
+      "epoch": 1.5065803667745414,
+      "grad_norm": 0.4784195125102997,
+      "learning_rate": 0.00018343316319047482,
+      "loss": 0.7631853222846985,
+      "step": 3492
+    },
+    {
+      "epoch": 1.5074433656957928,
+      "grad_norm": 0.45802050828933716,
+      "learning_rate": 0.00018340608250554222,
+      "loss": 0.7416844964027405,
+      "step": 3494
+    },
+    {
+      "epoch": 1.5083063646170443,
+      "grad_norm": 0.42670297622680664,
+      "learning_rate": 0.0001833789817076088,
+      "loss": 0.8117082715034485,
+      "step": 3496
+    },
+    {
+      "epoch": 1.5091693635382954,
+      "grad_norm": 0.48401451110839844,
+      "learning_rate": 0.00018335186080320983,
+      "loss": 0.724604606628418,
+      "step": 3498
+    },
+    {
+      "epoch": 1.510032362459547,
+      "grad_norm": 0.5217538475990295,
+      "learning_rate": 0.00018332471979888535,
+      "loss": 0.8395941257476807,
+      "step": 3500
+    },
+    {
+      "epoch": 1.510032362459547,
+      "eval_loss": 0.7970634698867798,
+      "eval_runtime": 655.3078,
+      "eval_samples_per_second": 3.144,
+      "eval_steps_per_second": 3.144,
+      "step": 3500
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 13908,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.001
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.0977490200024474e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/sft_qwen_14B/checkpoints/checkpoint-3500/training_args.bin b/sft_qwen_14B/checkpoints/checkpoint-3500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b023888140f1fb107e8d5ebbfbcb9d9558b09d43
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-3500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4200830b23d19bc86049c280236c4a6b18c26d7061b5a57cc024888ec760920f
+size 5201
diff --git a/sft_qwen_14B/checkpoints/checkpoint-4000/README.md b/sft_qwen_14B/checkpoints/checkpoint-4000/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..779b6406e547b32301fef1d181301a873befe542
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-4000/README.md
@@ -0,0 +1,207 @@
+---
+base_model: runs/cpt_run_14b/merged_14b_cpt_lora
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:runs/cpt_run_14b/merged_14b_cpt_lora
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0
\ No newline at end of file
diff --git a/sft_qwen_14B/checkpoints/checkpoint-4000/adapter_config.json b/sft_qwen_14B/checkpoints/checkpoint-4000/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8ea271115c141fb10c6d899b06f46f21800e1ad6
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-4000/adapter_config.json
@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "runs/cpt_run_14b/merged_14b_cpt_lora",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/sft_qwen_14B/checkpoints/checkpoint-4000/adapter_model.safetensors b/sft_qwen_14B/checkpoints/checkpoint-4000/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d69dcb885931b172c82b1d85f30effa56847e39e
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-4000/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba121b72e174d0ac1cfc8cc3d13e60344be1471b61cf3507166cbf8d31d404ed
+size 100715016
diff --git a/sft_qwen_14B/checkpoints/checkpoint-4000/optimizer.pt b/sft_qwen_14B/checkpoints/checkpoint-4000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..df196bd424431e4f33775675588a27371dce2832
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-4000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:941b2f450fcc686e77bc407c9c317e3f6b231a03808fd3f99d478c561c4cda03
+size 201650659
diff --git a/sft_qwen_14B/checkpoints/checkpoint-4000/rng_state.pth b/sft_qwen_14B/checkpoints/checkpoint-4000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7d8a9814afd86344be9b211222b43ca2947c85c0
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-4000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b70749013f56fe9ef079f48fcfd9ad9aaab5306844c51961b3523a26676dc73
+size 14645
diff --git a/sft_qwen_14B/checkpoints/checkpoint-4000/scheduler.pt b/sft_qwen_14B/checkpoints/checkpoint-4000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a48c73ee103d09ce8660c1fb89381803f9f97372
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-4000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e92f0d7ff380af27c33758840b17c9ff530ab57bf17d071b05c4aae9bc5818d
+size 1465
diff --git a/sft_qwen_14B/checkpoints/checkpoint-4000/trainer_state.json b/sft_qwen_14B/checkpoints/checkpoint-4000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..a70245a8c024c8eef791c620b0c12c90a247d92e
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-4000/trainer_state.json
@@ -0,0 +1,14363 @@
+{
+  "best_global_step": 4000,
+  "best_metric": 0.7843562960624695,
+  "best_model_checkpoint": "runs/instruct_run_14b_v1/checkpoints/checkpoint-4000",
+  "epoch": 1.7257820927723841,
+  "eval_steps": 100,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008629989212513484,
+      "grad_norm": 0.36567428708076477,
+      "learning_rate": 1.7969451931716084e-07,
+      "loss": 1.6794371604919434,
+      "step": 2
+    },
+    {
+      "epoch": 0.001725997842502697,
+      "grad_norm": 0.4024646580219269,
+      "learning_rate": 5.390835579514825e-07,
+      "loss": 1.6853073835372925,
+      "step": 4
+    },
+    {
+      "epoch": 0.0025889967637540453,
+      "grad_norm": 0.40199393033981323,
+      "learning_rate": 8.984725965858042e-07,
+      "loss": 1.7621158361434937,
+      "step": 6
+    },
+    {
+      "epoch": 0.003451995685005394,
+      "grad_norm": 0.35409677028656006,
+      "learning_rate": 1.257861635220126e-06,
+      "loss": 1.633257269859314,
+      "step": 8
+    },
+    {
+      "epoch": 0.004314994606256742,
+      "grad_norm": 0.39087551832199097,
+      "learning_rate": 1.6172506738544475e-06,
+      "loss": 1.7374768257141113,
+      "step": 10
+    },
+    {
+      "epoch": 0.005177993527508091,
+      "grad_norm": 0.3586857318878174,
+      "learning_rate": 1.9766397124887693e-06,
+      "loss": 1.6955714225769043,
+      "step": 12
+    },
+    {
+      "epoch": 0.006040992448759439,
+      "grad_norm": 0.32755669951438904,
+      "learning_rate": 2.3360287511230908e-06,
+      "loss": 1.720664381980896,
+      "step": 14
+    },
+    {
+      "epoch": 0.006903991370010788,
+      "grad_norm": 0.4054872691631317,
+      "learning_rate": 2.6954177897574127e-06,
+      "loss": 1.6957035064697266,
+      "step": 16
+    },
+    {
+      "epoch": 0.007766990291262136,
+      "grad_norm": 0.37593814730644226,
+      "learning_rate": 3.0548068283917343e-06,
+      "loss": 1.7286947965621948,
+      "step": 18
+    },
+    {
+      "epoch": 0.008629989212513484,
+      "grad_norm": 0.3344813287258148,
+      "learning_rate": 3.414195867026056e-06,
+      "loss": 1.727295994758606,
+      "step": 20
+    },
+    {
+      "epoch": 0.009492988133764833,
+      "grad_norm": 0.357474148273468,
+      "learning_rate": 3.7735849056603773e-06,
+      "loss": 1.6727914810180664,
+      "step": 22
+    },
+    {
+      "epoch": 0.010355987055016181,
+      "grad_norm": 0.39115726947784424,
+      "learning_rate": 4.132973944294699e-06,
+      "loss": 1.6518884897232056,
+      "step": 24
+    },
+    {
+      "epoch": 0.01121898597626753,
+      "grad_norm": 0.4711727201938629,
+      "learning_rate": 4.492362982929021e-06,
+      "loss": 1.7868088483810425,
+      "step": 26
+    },
+    {
+      "epoch": 0.012081984897518877,
+      "grad_norm": 0.34112176299095154,
+      "learning_rate": 4.851752021563342e-06,
+      "loss": 1.6127634048461914,
+      "step": 28
+    },
+    {
+      "epoch": 0.012944983818770227,
+      "grad_norm": 0.5071991682052612,
+      "learning_rate": 5.211141060197664e-06,
+      "loss": 1.7858378887176514,
+      "step": 30
+    },
+    {
+      "epoch": 0.013807982740021575,
+      "grad_norm": 0.42048847675323486,
+      "learning_rate": 5.570530098831986e-06,
+      "loss": 1.7123326063156128,
+      "step": 32
+    },
+    {
+      "epoch": 0.014670981661272923,
+      "grad_norm": 0.48883870244026184,
+      "learning_rate": 5.929919137466308e-06,
+      "loss": 1.737749695777893,
+      "step": 34
+    },
+    {
+      "epoch": 0.015533980582524271,
+      "grad_norm": 0.3311465084552765,
+      "learning_rate": 6.289308176100629e-06,
+      "loss": 1.5578981637954712,
+      "step": 36
+    },
+    {
+      "epoch": 0.01639697950377562,
+      "grad_norm": 0.5178973078727722,
+      "learning_rate": 6.64869721473495e-06,
+      "loss": 1.719806432723999,
+      "step": 38
+    },
+    {
+      "epoch": 0.017259978425026967,
+      "grad_norm": 0.47097742557525635,
+      "learning_rate": 7.008086253369272e-06,
+      "loss": 1.728212833404541,
+      "step": 40
+    },
+    {
+      "epoch": 0.018122977346278317,
+      "grad_norm": 0.5051584243774414,
+      "learning_rate": 7.367475292003594e-06,
+      "loss": 1.6542466878890991,
+      "step": 42
+    },
+    {
+      "epoch": 0.018985976267529667,
+      "grad_norm": 0.4645111560821533,
+      "learning_rate": 7.726864330637915e-06,
+      "loss": 1.7087690830230713,
+      "step": 44
+    },
+    {
+      "epoch": 0.019848975188781013,
+      "grad_norm": 0.5184999704360962,
+      "learning_rate": 8.086253369272237e-06,
+      "loss": 1.7018946409225464,
+      "step": 46
+    },
+    {
+      "epoch": 0.020711974110032363,
+      "grad_norm": 0.4543815851211548,
+      "learning_rate": 8.44564240790656e-06,
+      "loss": 1.6818269491195679,
+      "step": 48
+    },
+    {
+      "epoch": 0.021574973031283712,
+      "grad_norm": 0.44411996006965637,
+      "learning_rate": 8.80503144654088e-06,
+      "loss": 1.5772877931594849,
+      "step": 50
+    },
+    {
+      "epoch": 0.02243797195253506,
+      "grad_norm": 0.3409404158592224,
+      "learning_rate": 9.164420485175203e-06,
+      "loss": 1.498152732849121,
+      "step": 52
+    },
+    {
+      "epoch": 0.02330097087378641,
+      "grad_norm": 0.42104434967041016,
+      "learning_rate": 9.523809523809523e-06,
+      "loss": 1.6189048290252686,
+      "step": 54
+    },
+    {
+      "epoch": 0.024163969795037755,
+      "grad_norm": 0.3756246268749237,
+      "learning_rate": 9.883198562443846e-06,
+      "loss": 1.4596441984176636,
+      "step": 56
+    },
+    {
+      "epoch": 0.025026968716289105,
+      "grad_norm": 0.36214128136634827,
+      "learning_rate": 1.0242587601078168e-05,
+      "loss": 1.503880500793457,
+      "step": 58
+    },
+    {
+      "epoch": 0.025889967637540454,
+      "grad_norm": 0.40893009305000305,
+      "learning_rate": 1.060197663971249e-05,
+      "loss": 1.5912823677062988,
+      "step": 60
+    },
+    {
+      "epoch": 0.0267529665587918,
+      "grad_norm": 0.28710272908210754,
+      "learning_rate": 1.0961365678346811e-05,
+      "loss": 1.2956721782684326,
+      "step": 62
+    },
+    {
+      "epoch": 0.02761596548004315,
+      "grad_norm": 0.304573118686676,
+      "learning_rate": 1.1320754716981132e-05,
+      "loss": 1.4648056030273438,
+      "step": 64
+    },
+    {
+      "epoch": 0.0284789644012945,
+      "grad_norm": 0.36523914337158203,
+      "learning_rate": 1.1680143755615454e-05,
+      "loss": 1.6078968048095703,
+      "step": 66
+    },
+    {
+      "epoch": 0.029341963322545846,
+      "grad_norm": 0.37929031252861023,
+      "learning_rate": 1.2039532794249775e-05,
+      "loss": 1.5969421863555908,
+      "step": 68
+    },
+    {
+      "epoch": 0.030204962243797196,
+      "grad_norm": 0.3053947389125824,
+      "learning_rate": 1.2398921832884097e-05,
+      "loss": 1.4312325716018677,
+      "step": 70
+    },
+    {
+      "epoch": 0.031067961165048542,
+      "grad_norm": 0.3028779923915863,
+      "learning_rate": 1.275831087151842e-05,
+      "loss": 1.4101300239562988,
+      "step": 72
+    },
+    {
+      "epoch": 0.03193096008629989,
+      "grad_norm": 0.29649803042411804,
+      "learning_rate": 1.3117699910152742e-05,
+      "loss": 1.4553817510604858,
+      "step": 74
+    },
+    {
+      "epoch": 0.03279395900755124,
+      "grad_norm": 0.26032644510269165,
+      "learning_rate": 1.3477088948787062e-05,
+      "loss": 1.4623000621795654,
+      "step": 76
+    },
+    {
+      "epoch": 0.03365695792880259,
+      "grad_norm": 0.33558446168899536,
+      "learning_rate": 1.3836477987421385e-05,
+      "loss": 1.5181745290756226,
+      "step": 78
+    },
+    {
+      "epoch": 0.034519956850053934,
+      "grad_norm": 0.28307804465293884,
+      "learning_rate": 1.4195867026055706e-05,
+      "loss": 1.4397861957550049,
+      "step": 80
+    },
+    {
+      "epoch": 0.035382955771305284,
+      "grad_norm": 0.3451690673828125,
+      "learning_rate": 1.455525606469003e-05,
+      "loss": 1.463841199874878,
+      "step": 82
+    },
+    {
+      "epoch": 0.036245954692556634,
+      "grad_norm": 0.3248669505119324,
+      "learning_rate": 1.4914645103324348e-05,
+      "loss": 1.3554227352142334,
+      "step": 84
+    },
+    {
+      "epoch": 0.037108953613807984,
+      "grad_norm": 0.2855011224746704,
+      "learning_rate": 1.527403414195867e-05,
+      "loss": 1.2810425758361816,
+      "step": 86
+    },
+    {
+      "epoch": 0.03797195253505933,
+      "grad_norm": 0.33365535736083984,
+      "learning_rate": 1.5633423180592992e-05,
+      "loss": 1.428163766860962,
+      "step": 88
+    },
+    {
+      "epoch": 0.038834951456310676,
+      "grad_norm": 0.34099438786506653,
+      "learning_rate": 1.5992812219227316e-05,
+      "loss": 1.3487578630447388,
+      "step": 90
+    },
+    {
+      "epoch": 0.039697950377562026,
+      "grad_norm": 0.39247506856918335,
+      "learning_rate": 1.6352201257861635e-05,
+      "loss": 1.30057954788208,
+      "step": 92
+    },
+    {
+      "epoch": 0.040560949298813376,
+      "grad_norm": 0.32692041993141174,
+      "learning_rate": 1.671159029649596e-05,
+      "loss": 1.2923580408096313,
+      "step": 94
+    },
+    {
+      "epoch": 0.041423948220064725,
+      "grad_norm": 0.43452519178390503,
+      "learning_rate": 1.707097933513028e-05,
+      "loss": 1.5002273321151733,
+      "step": 96
+    },
+    {
+      "epoch": 0.042286947141316075,
+      "grad_norm": 0.3251534402370453,
+      "learning_rate": 1.7430368373764602e-05,
+      "loss": 1.330254077911377,
+      "step": 98
+    },
+    {
+      "epoch": 0.043149946062567425,
+      "grad_norm": 0.3198273479938507,
+      "learning_rate": 1.778975741239892e-05,
+      "loss": 1.3054943084716797,
+      "step": 100
+    },
+    {
+      "epoch": 0.043149946062567425,
+      "eval_loss": 1.366738200187683,
+      "eval_runtime": 651.8198,
+      "eval_samples_per_second": 3.16,
+      "eval_steps_per_second": 3.16,
+      "step": 100
+    },
+    {
+      "epoch": 0.04401294498381877,
+      "grad_norm": 0.37364065647125244,
+      "learning_rate": 1.8149146451033245e-05,
+      "loss": 1.314281940460205,
+      "step": 102
+    },
+    {
+      "epoch": 0.04487594390507012,
+      "grad_norm": 0.39384758472442627,
+      "learning_rate": 1.8508535489667568e-05,
+      "loss": 1.2737246751785278,
+      "step": 104
+    },
+    {
+      "epoch": 0.04573894282632147,
+      "grad_norm": 0.3521905541419983,
+      "learning_rate": 1.8867924528301888e-05,
+      "loss": 1.3113226890563965,
+      "step": 106
+    },
+    {
+      "epoch": 0.04660194174757282,
+      "grad_norm": 0.33531463146209717,
+      "learning_rate": 1.9227313566936208e-05,
+      "loss": 1.3253653049468994,
+      "step": 108
+    },
+    {
+      "epoch": 0.04746494066882417,
+      "grad_norm": 0.35596340894699097,
+      "learning_rate": 1.958670260557053e-05,
+      "loss": 1.3236849308013916,
+      "step": 110
+    },
+    {
+      "epoch": 0.04832793959007551,
+      "grad_norm": 0.36028242111206055,
+      "learning_rate": 1.9946091644204854e-05,
+      "loss": 1.183128833770752,
+      "step": 112
+    },
+    {
+      "epoch": 0.04919093851132686,
+      "grad_norm": 0.42109814286231995,
+      "learning_rate": 2.0305480682839174e-05,
+      "loss": 1.2741888761520386,
+      "step": 114
+    },
+    {
+      "epoch": 0.05005393743257821,
+      "grad_norm": 0.39675939083099365,
+      "learning_rate": 2.0664869721473494e-05,
+      "loss": 1.3050109148025513,
+      "step": 116
+    },
+    {
+      "epoch": 0.05091693635382956,
+      "grad_norm": 0.4414141774177551,
+      "learning_rate": 2.1024258760107817e-05,
+      "loss": 1.2472094297409058,
+      "step": 118
+    },
+    {
+      "epoch": 0.05177993527508091,
+      "grad_norm": 0.42872729897499084,
+      "learning_rate": 2.138364779874214e-05,
+      "loss": 1.3338921070098877,
+      "step": 120
+    },
+    {
+      "epoch": 0.05264293419633225,
+      "grad_norm": 0.38336244225502014,
+      "learning_rate": 2.174303683737646e-05,
+      "loss": 1.322908878326416,
+      "step": 122
+    },
+    {
+      "epoch": 0.0535059331175836,
+      "grad_norm": 0.41046878695487976,
+      "learning_rate": 2.2102425876010783e-05,
+      "loss": 1.2169240713119507,
+      "step": 124
+    },
+    {
+      "epoch": 0.05436893203883495,
+      "grad_norm": 0.39460113644599915,
+      "learning_rate": 2.2461814914645103e-05,
+      "loss": 1.2085309028625488,
+      "step": 126
+    },
+    {
+      "epoch": 0.0552319309600863,
+      "grad_norm": 0.42829909920692444,
+      "learning_rate": 2.2821203953279426e-05,
+      "loss": 1.2969133853912354,
+      "step": 128
+    },
+    {
+      "epoch": 0.05609492988133765,
+      "grad_norm": 0.3940851390361786,
+      "learning_rate": 2.3180592991913746e-05,
+      "loss": 1.1892330646514893,
+      "step": 130
+    },
+    {
+      "epoch": 0.056957928802589,
+      "grad_norm": 0.45011839270591736,
+      "learning_rate": 2.353998203054807e-05,
+      "loss": 1.2082979679107666,
+      "step": 132
+    },
+    {
+      "epoch": 0.05782092772384034,
+      "grad_norm": 0.46059420704841614,
+      "learning_rate": 2.3899371069182393e-05,
+      "loss": 1.2388817071914673,
+      "step": 134
+    },
+    {
+      "epoch": 0.05868392664509169,
+      "grad_norm": 0.41085872054100037,
+      "learning_rate": 2.4258760107816713e-05,
+      "loss": 1.193917155265808,
+      "step": 136
+    },
+    {
+      "epoch": 0.05954692556634304,
+      "grad_norm": 0.4024205207824707,
+      "learning_rate": 2.4618149146451032e-05,
+      "loss": 1.1514034271240234,
+      "step": 138
+    },
+    {
+      "epoch": 0.06040992448759439,
+      "grad_norm": 0.3893793523311615,
+      "learning_rate": 2.4977538185085356e-05,
+      "loss": 1.1626157760620117,
+      "step": 140
+    },
+    {
+      "epoch": 0.06127292340884574,
+      "grad_norm": 0.4456317126750946,
+      "learning_rate": 2.5336927223719675e-05,
+      "loss": 1.1627076864242554,
+      "step": 142
+    },
+    {
+      "epoch": 0.062135922330097085,
+      "grad_norm": 0.5050215125083923,
+      "learning_rate": 2.5696316262354e-05,
+      "loss": 1.3038755655288696,
+      "step": 144
+    },
+    {
+      "epoch": 0.06299892125134844,
+      "grad_norm": 0.4071207642555237,
+      "learning_rate": 2.605570530098832e-05,
+      "loss": 1.1708844900131226,
+      "step": 146
+    },
+    {
+      "epoch": 0.06386192017259978,
+      "grad_norm": 0.4363228678703308,
+      "learning_rate": 2.641509433962264e-05,
+      "loss": 1.2149070501327515,
+      "step": 148
+    },
+    {
+      "epoch": 0.06472491909385113,
+      "grad_norm": 0.4436556398868561,
+      "learning_rate": 2.6774483378256965e-05,
+      "loss": 1.1942368745803833,
+      "step": 150
+    },
+    {
+      "epoch": 0.06558791801510248,
+      "grad_norm": 0.4068629741668701,
+      "learning_rate": 2.7133872416891288e-05,
+      "loss": 1.1799161434173584,
+      "step": 152
+    },
+    {
+      "epoch": 0.06645091693635383,
+      "grad_norm": 0.5291106700897217,
+      "learning_rate": 2.7493261455525608e-05,
+      "loss": 1.1832845211029053,
+      "step": 154
+    },
+    {
+      "epoch": 0.06731391585760518,
+      "grad_norm": 0.4410109221935272,
+      "learning_rate": 2.785265049415993e-05,
+      "loss": 1.1696993112564087,
+      "step": 156
+    },
+    {
+      "epoch": 0.06817691477885653,
+      "grad_norm": 0.4858371913433075,
+      "learning_rate": 2.8212039532794248e-05,
+      "loss": 1.2036973237991333,
+      "step": 158
+    },
+    {
+      "epoch": 0.06903991370010787,
+      "grad_norm": 0.45373693108558655,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 1.1145079135894775,
+      "step": 160
+    },
+    {
+      "epoch": 0.06990291262135923,
+      "grad_norm": 0.4881038963794708,
+      "learning_rate": 2.8930817610062894e-05,
+      "loss": 1.173502802848816,
+      "step": 162
+    },
+    {
+      "epoch": 0.07076591154261057,
+      "grad_norm": 0.576934814453125,
+      "learning_rate": 2.9290206648697217e-05,
+      "loss": 1.250414490699768,
+      "step": 164
+    },
+    {
+      "epoch": 0.07162891046386193,
+      "grad_norm": 0.4900001287460327,
+      "learning_rate": 2.9649595687331537e-05,
+      "loss": 1.0721495151519775,
+      "step": 166
+    },
+    {
+      "epoch": 0.07249190938511327,
+      "grad_norm": 0.4440019726753235,
+      "learning_rate": 3.000898472596586e-05,
+      "loss": 1.0689374208450317,
+      "step": 168
+    },
+    {
+      "epoch": 0.07335490830636461,
+      "grad_norm": 0.4267268180847168,
+      "learning_rate": 3.0368373764600184e-05,
+      "loss": 1.2095128297805786,
+      "step": 170
+    },
+    {
+      "epoch": 0.07421790722761597,
+      "grad_norm": 0.6062787771224976,
+      "learning_rate": 3.0727762803234503e-05,
+      "loss": 1.077776551246643,
+      "step": 172
+    },
+    {
+      "epoch": 0.07508090614886731,
+      "grad_norm": 0.49510180950164795,
+      "learning_rate": 3.108715184186882e-05,
+      "loss": 1.144006371498108,
+      "step": 174
+    },
+    {
+      "epoch": 0.07594390507011867,
+      "grad_norm": 0.4670701026916504,
+      "learning_rate": 3.144654088050314e-05,
+      "loss": 1.1663392782211304,
+      "step": 176
+    },
+    {
+      "epoch": 0.07680690399137001,
+      "grad_norm": 0.5615383386611938,
+      "learning_rate": 3.1805929919137466e-05,
+      "loss": 1.1665973663330078,
+      "step": 178
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "grad_norm": 0.47305551171302795,
+      "learning_rate": 3.216531895777179e-05,
+      "loss": 1.1337063312530518,
+      "step": 180
+    },
+    {
+      "epoch": 0.07853290183387271,
+      "grad_norm": 0.5127068758010864,
+      "learning_rate": 3.252470799640611e-05,
+      "loss": 1.072874903678894,
+      "step": 182
+    },
+    {
+      "epoch": 0.07939590075512405,
+      "grad_norm": 0.632448136806488,
+      "learning_rate": 3.2884097035040436e-05,
+      "loss": 1.1577240228652954,
+      "step": 184
+    },
+    {
+      "epoch": 0.08025889967637541,
+      "grad_norm": 0.4041025638580322,
+      "learning_rate": 3.324348607367476e-05,
+      "loss": 1.1186822652816772,
+      "step": 186
+    },
+    {
+      "epoch": 0.08112189859762675,
+      "grad_norm": 0.5239102244377136,
+      "learning_rate": 3.3602875112309076e-05,
+      "loss": 1.1468429565429688,
+      "step": 188
+    },
+    {
+      "epoch": 0.08198489751887811,
+      "grad_norm": 0.4486575424671173,
+      "learning_rate": 3.39622641509434e-05,
+      "loss": 1.0017019510269165,
+      "step": 190
+    },
+    {
+      "epoch": 0.08284789644012945,
+      "grad_norm": 0.4994317293167114,
+      "learning_rate": 3.4321653189577715e-05,
+      "loss": 1.1901532411575317,
+      "step": 192
+    },
+    {
+      "epoch": 0.0837108953613808,
+      "grad_norm": 0.5023699998855591,
+      "learning_rate": 3.468104222821204e-05,
+      "loss": 1.1398564577102661,
+      "step": 194
+    },
+    {
+      "epoch": 0.08457389428263215,
+      "grad_norm": 0.5077701807022095,
+      "learning_rate": 3.504043126684636e-05,
+      "loss": 1.1390413045883179,
+      "step": 196
+    },
+    {
+      "epoch": 0.0854368932038835,
+      "grad_norm": 0.5527892112731934,
+      "learning_rate": 3.5399820305480685e-05,
+      "loss": 1.1411432027816772,
+      "step": 198
+    },
+    {
+      "epoch": 0.08629989212513485,
+      "grad_norm": 0.5572488903999329,
+      "learning_rate": 3.575920934411501e-05,
+      "loss": 1.071260690689087,
+      "step": 200
+    },
+    {
+      "epoch": 0.08629989212513485,
+      "eval_loss": 1.1519012451171875,
+      "eval_runtime": 654.6055,
+      "eval_samples_per_second": 3.147,
+      "eval_steps_per_second": 3.147,
+      "step": 200
+    },
+    {
+      "epoch": 0.08716289104638619,
+      "grad_norm": 0.5134095549583435,
+      "learning_rate": 3.611859838274933e-05,
+      "loss": 1.138135552406311,
+      "step": 202
+    },
+    {
+      "epoch": 0.08802588996763754,
+      "grad_norm": 0.5166040658950806,
+      "learning_rate": 3.647798742138365e-05,
+      "loss": 1.111999273300171,
+      "step": 204
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.5336993336677551,
+      "learning_rate": 3.683737646001797e-05,
+      "loss": 1.1031352281570435,
+      "step": 206
+    },
+    {
+      "epoch": 0.08975188781014024,
+      "grad_norm": 0.8289600014686584,
+      "learning_rate": 3.7196765498652294e-05,
+      "loss": 1.0388667583465576,
+      "step": 208
+    },
+    {
+      "epoch": 0.09061488673139159,
+      "grad_norm": 0.47992637753486633,
+      "learning_rate": 3.755615453728661e-05,
+      "loss": 1.0950241088867188,
+      "step": 210
+    },
+    {
+      "epoch": 0.09147788565264293,
+      "grad_norm": 0.5629691481590271,
+      "learning_rate": 3.7915543575920934e-05,
+      "loss": 1.0361733436584473,
+      "step": 212
+    },
+    {
+      "epoch": 0.09234088457389428,
+      "grad_norm": 0.5515111684799194,
+      "learning_rate": 3.827493261455526e-05,
+      "loss": 1.0922447443008423,
+      "step": 214
+    },
+    {
+      "epoch": 0.09320388349514563,
+      "grad_norm": 0.5078643560409546,
+      "learning_rate": 3.863432165318958e-05,
+      "loss": 1.0866856575012207,
+      "step": 216
+    },
+    {
+      "epoch": 0.09406688241639698,
+      "grad_norm": 0.6046127676963806,
+      "learning_rate": 3.8993710691823904e-05,
+      "loss": 1.1231595277786255,
+      "step": 218
+    },
+    {
+      "epoch": 0.09492988133764833,
+      "grad_norm": 0.6255762577056885,
+      "learning_rate": 3.935309973045822e-05,
+      "loss": 1.099171757698059,
+      "step": 220
+    },
+    {
+      "epoch": 0.09579288025889968,
+      "grad_norm": 0.6036638021469116,
+      "learning_rate": 3.971248876909254e-05,
+      "loss": 1.0557761192321777,
+      "step": 222
+    },
+    {
+      "epoch": 0.09665587918015102,
+      "grad_norm": 0.5520529747009277,
+      "learning_rate": 4.0071877807726867e-05,
+      "loss": 1.0467877388000488,
+      "step": 224
+    },
+    {
+      "epoch": 0.09751887810140238,
+      "grad_norm": 0.5958684682846069,
+      "learning_rate": 4.043126684636119e-05,
+      "loss": 1.17941153049469,
+      "step": 226
+    },
+    {
+      "epoch": 0.09838187702265372,
+      "grad_norm": 0.5283281803131104,
+      "learning_rate": 4.079065588499551e-05,
+      "loss": 1.104217767715454,
+      "step": 228
+    },
+    {
+      "epoch": 0.09924487594390508,
+      "grad_norm": 0.5608792901039124,
+      "learning_rate": 4.115004492362983e-05,
+      "loss": 1.0900640487670898,
+      "step": 230
+    },
+    {
+      "epoch": 0.10010787486515642,
+      "grad_norm": 0.555964469909668,
+      "learning_rate": 4.150943396226415e-05,
+      "loss": 0.9887422323226929,
+      "step": 232
+    },
+    {
+      "epoch": 0.10097087378640776,
+      "grad_norm": 0.5875785946846008,
+      "learning_rate": 4.1868823000898476e-05,
+      "loss": 1.1298567056655884,
+      "step": 234
+    },
+    {
+      "epoch": 0.10183387270765912,
+      "grad_norm": 0.4544795751571655,
+      "learning_rate": 4.222821203953279e-05,
+      "loss": 1.0957067012786865,
+      "step": 236
+    },
+    {
+      "epoch": 0.10269687162891046,
+      "grad_norm": 0.564145565032959,
+      "learning_rate": 4.2587601078167116e-05,
+      "loss": 1.0328738689422607,
+      "step": 238
+    },
+    {
+      "epoch": 0.10355987055016182,
+      "grad_norm": 0.6285979747772217,
+      "learning_rate": 4.294699011680144e-05,
+      "loss": 1.1085515022277832,
+      "step": 240
+    },
+    {
+      "epoch": 0.10442286947141316,
+      "grad_norm": 0.6442288756370544,
+      "learning_rate": 4.330637915543576e-05,
+      "loss": 1.1291271448135376,
+      "step": 242
+    },
+    {
+      "epoch": 0.1052858683926645,
+      "grad_norm": 0.6137154698371887,
+      "learning_rate": 4.3665768194070085e-05,
+      "loss": 1.1759567260742188,
+      "step": 244
+    },
+    {
+      "epoch": 0.10614886731391586,
+      "grad_norm": 0.5906805992126465,
+      "learning_rate": 4.402515723270441e-05,
+      "loss": 1.148414969444275,
+      "step": 246
+    },
+    {
+      "epoch": 0.1070118662351672,
+      "grad_norm": 0.5382888913154602,
+      "learning_rate": 4.438454627133873e-05,
+      "loss": 1.0749616622924805,
+      "step": 248
+    },
+    {
+      "epoch": 0.10787486515641856,
+      "grad_norm": 0.6185492873191833,
+      "learning_rate": 4.474393530997305e-05,
+      "loss": 1.2235801219940186,
+      "step": 250
+    },
+    {
+      "epoch": 0.1087378640776699,
+      "grad_norm": 0.5981597900390625,
+      "learning_rate": 4.5103324348607365e-05,
+      "loss": 1.1390639543533325,
+      "step": 252
+    },
+    {
+      "epoch": 0.10960086299892124,
+      "grad_norm": 0.5664694905281067,
+      "learning_rate": 4.546271338724169e-05,
+      "loss": 1.171774983406067,
+      "step": 254
+    },
+    {
+      "epoch": 0.1104638619201726,
+      "grad_norm": 0.7071851491928101,
+      "learning_rate": 4.582210242587601e-05,
+      "loss": 1.1704237461090088,
+      "step": 256
+    },
+    {
+      "epoch": 0.11132686084142394,
+      "grad_norm": 0.5815614461898804,
+      "learning_rate": 4.6181491464510334e-05,
+      "loss": 1.0619677305221558,
+      "step": 258
+    },
+    {
+      "epoch": 0.1121898597626753,
+      "grad_norm": 0.6481915712356567,
+      "learning_rate": 4.654088050314466e-05,
+      "loss": 1.0824390649795532,
+      "step": 260
+    },
+    {
+      "epoch": 0.11305285868392664,
+      "grad_norm": 0.5988591313362122,
+      "learning_rate": 4.690026954177898e-05,
+      "loss": 1.087929606437683,
+      "step": 262
+    },
+    {
+      "epoch": 0.113915857605178,
+      "grad_norm": 0.6545296311378479,
+      "learning_rate": 4.7259658580413304e-05,
+      "loss": 1.0936195850372314,
+      "step": 264
+    },
+    {
+      "epoch": 0.11477885652642934,
+      "grad_norm": 0.5826204419136047,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 1.0433681011199951,
+      "step": 266
+    },
+    {
+      "epoch": 0.11564185544768069,
+      "grad_norm": 0.5907514095306396,
+      "learning_rate": 4.7978436657681944e-05,
+      "loss": 1.0719536542892456,
+      "step": 268
+    },
+    {
+      "epoch": 0.11650485436893204,
+      "grad_norm": 0.524394154548645,
+      "learning_rate": 4.833782569631627e-05,
+      "loss": 1.0231504440307617,
+      "step": 270
+    },
+    {
+      "epoch": 0.11736785329018339,
+      "grad_norm": 0.5472846031188965,
+      "learning_rate": 4.869721473495058e-05,
+      "loss": 0.9905915260314941,
+      "step": 272
+    },
+    {
+      "epoch": 0.11823085221143474,
+      "grad_norm": 0.727922260761261,
+      "learning_rate": 4.9056603773584906e-05,
+      "loss": 1.213677167892456,
+      "step": 274
+    },
+    {
+      "epoch": 0.11909385113268608,
+      "grad_norm": 0.6009684801101685,
+      "learning_rate": 4.941599281221923e-05,
+      "loss": 1.0052144527435303,
+      "step": 276
+    },
+    {
+      "epoch": 0.11995685005393743,
+      "grad_norm": 0.6564669013023376,
+      "learning_rate": 4.977538185085355e-05,
+      "loss": 1.108136773109436,
+      "step": 278
+    },
+    {
+      "epoch": 0.12081984897518878,
+      "grad_norm": 0.650074303150177,
+      "learning_rate": 5.013477088948787e-05,
+      "loss": 0.9700815677642822,
+      "step": 280
+    },
+    {
+      "epoch": 0.12168284789644013,
+      "grad_norm": 0.5772947072982788,
+      "learning_rate": 5.04941599281222e-05,
+      "loss": 1.038031816482544,
+      "step": 282
+    },
+    {
+      "epoch": 0.12254584681769148,
+      "grad_norm": 0.7293002009391785,
+      "learning_rate": 5.0853548966756516e-05,
+      "loss": 1.1063730716705322,
+      "step": 284
+    },
+    {
+      "epoch": 0.12340884573894283,
+      "grad_norm": 0.7937333583831787,
+      "learning_rate": 5.1212938005390846e-05,
+      "loss": 1.128495693206787,
+      "step": 286
+    },
+    {
+      "epoch": 0.12427184466019417,
+      "grad_norm": 0.48499324917793274,
+      "learning_rate": 5.157232704402516e-05,
+      "loss": 0.9438712000846863,
+      "step": 288
+    },
+    {
+      "epoch": 0.12513484358144553,
+      "grad_norm": 0.6010656952857971,
+      "learning_rate": 5.193171608265948e-05,
+      "loss": 1.0872881412506104,
+      "step": 290
+    },
+    {
+      "epoch": 0.12599784250269688,
+      "grad_norm": 0.6240811944007874,
+      "learning_rate": 5.22911051212938e-05,
+      "loss": 1.110992193222046,
+      "step": 292
+    },
+    {
+      "epoch": 0.1268608414239482,
+      "grad_norm": 0.7172768712043762,
+      "learning_rate": 5.265049415992812e-05,
+      "loss": 1.1109752655029297,
+      "step": 294
+    },
+    {
+      "epoch": 0.12772384034519957,
+      "grad_norm": 0.6442400217056274,
+      "learning_rate": 5.300988319856245e-05,
+      "loss": 1.05553138256073,
+      "step": 296
+    },
+    {
+      "epoch": 0.12858683926645093,
+      "grad_norm": 0.7074702382087708,
+      "learning_rate": 5.3369272237196765e-05,
+      "loss": 1.0717648267745972,
+      "step": 298
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "grad_norm": 0.5277591347694397,
+      "learning_rate": 5.3728661275831095e-05,
+      "loss": 0.9777541756629944,
+      "step": 300
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "eval_loss": 1.0977506637573242,
+      "eval_runtime": 662.1728,
+      "eval_samples_per_second": 3.111,
+      "eval_steps_per_second": 3.111,
+      "step": 300
+    },
+    {
+      "epoch": 0.1303128371089536,
+      "grad_norm": 0.7252246737480164,
+      "learning_rate": 5.408805031446541e-05,
+      "loss": 1.075905203819275,
+      "step": 302
+    },
+    {
+      "epoch": 0.13117583603020497,
+      "grad_norm": 0.7003294229507446,
+      "learning_rate": 5.444743935309974e-05,
+      "loss": 1.1117515563964844,
+      "step": 304
+    },
+    {
+      "epoch": 0.13203883495145632,
+      "grad_norm": 0.5878211259841919,
+      "learning_rate": 5.480682839173406e-05,
+      "loss": 1.0289191007614136,
+      "step": 306
+    },
+    {
+      "epoch": 0.13290183387270765,
+      "grad_norm": 0.7133644223213196,
+      "learning_rate": 5.5166217430368374e-05,
+      "loss": 1.0199183225631714,
+      "step": 308
+    },
+    {
+      "epoch": 0.133764832793959,
+      "grad_norm": 0.6098423600196838,
+      "learning_rate": 5.55256064690027e-05,
+      "loss": 1.0132375955581665,
+      "step": 310
+    },
+    {
+      "epoch": 0.13462783171521037,
+      "grad_norm": 0.6386916041374207,
+      "learning_rate": 5.5884995507637014e-05,
+      "loss": 1.1595754623413086,
+      "step": 312
+    },
+    {
+      "epoch": 0.1354908306364617,
+      "grad_norm": 0.6563469767570496,
+      "learning_rate": 5.6244384546271344e-05,
+      "loss": 1.0921307802200317,
+      "step": 314
+    },
+    {
+      "epoch": 0.13635382955771305,
+      "grad_norm": 0.6388015747070312,
+      "learning_rate": 5.660377358490566e-05,
+      "loss": 1.0200815200805664,
+      "step": 316
+    },
+    {
+      "epoch": 0.1372168284789644,
+      "grad_norm": 0.6026274561882019,
+      "learning_rate": 5.696316262353999e-05,
+      "loss": 0.9339485764503479,
+      "step": 318
+    },
+    {
+      "epoch": 0.13807982740021574,
+      "grad_norm": 0.619800865650177,
+      "learning_rate": 5.732255166217431e-05,
+      "loss": 1.0268478393554688,
+      "step": 320
+    },
+    {
+      "epoch": 0.1389428263214671,
+      "grad_norm": 0.5924715399742126,
+      "learning_rate": 5.768194070080862e-05,
+      "loss": 1.1394236087799072,
+      "step": 322
+    },
+    {
+      "epoch": 0.13980582524271845,
+      "grad_norm": 0.6829012036323547,
+      "learning_rate": 5.804132973944295e-05,
+      "loss": 1.002437949180603,
+      "step": 324
+    },
+    {
+      "epoch": 0.1406688241639698,
+      "grad_norm": 0.7012544274330139,
+      "learning_rate": 5.840071877807727e-05,
+      "loss": 1.132503628730774,
+      "step": 326
+    },
+    {
+      "epoch": 0.14153182308522114,
+      "grad_norm": 0.7921599745750427,
+      "learning_rate": 5.876010781671159e-05,
+      "loss": 1.1859129667282104,
+      "step": 328
+    },
+    {
+      "epoch": 0.1423948220064725,
+      "grad_norm": 0.6373353004455566,
+      "learning_rate": 5.9119496855345916e-05,
+      "loss": 1.0896776914596558,
+      "step": 330
+    },
+    {
+      "epoch": 0.14325782092772385,
+      "grad_norm": 0.6174030900001526,
+      "learning_rate": 5.947888589398024e-05,
+      "loss": 1.0691723823547363,
+      "step": 332
+    },
+    {
+      "epoch": 0.14412081984897518,
+      "grad_norm": 0.5110617280006409,
+      "learning_rate": 5.9838274932614556e-05,
+      "loss": 1.0144777297973633,
+      "step": 334
+    },
+    {
+      "epoch": 0.14498381877022654,
+      "grad_norm": 0.5580511093139648,
+      "learning_rate": 6.019766397124887e-05,
+      "loss": 0.9955101609230042,
+      "step": 336
+    },
+    {
+      "epoch": 0.1458468176914779,
+      "grad_norm": 0.6427345275878906,
+      "learning_rate": 6.05570530098832e-05,
+      "loss": 0.9863013625144958,
+      "step": 338
+    },
+    {
+      "epoch": 0.14670981661272922,
+      "grad_norm": 0.7464537024497986,
+      "learning_rate": 6.091644204851752e-05,
+      "loss": 1.0682255029678345,
+      "step": 340
+    },
+    {
+      "epoch": 0.14757281553398058,
+      "grad_norm": 0.599926769733429,
+      "learning_rate": 6.127583108715184e-05,
+      "loss": 1.034083366394043,
+      "step": 342
+    },
+    {
+      "epoch": 0.14843581445523193,
+      "grad_norm": 0.6320257186889648,
+      "learning_rate": 6.163522012578616e-05,
+      "loss": 1.0776089429855347,
+      "step": 344
+    },
+    {
+      "epoch": 0.1492988133764833,
+      "grad_norm": 0.6565091013908386,
+      "learning_rate": 6.199460916442049e-05,
+      "loss": 1.0493087768554688,
+      "step": 346
+    },
+    {
+      "epoch": 0.15016181229773462,
+      "grad_norm": 0.6512171626091003,
+      "learning_rate": 6.23539982030548e-05,
+      "loss": 1.0469218492507935,
+      "step": 348
+    },
+    {
+      "epoch": 0.15102481121898598,
+      "grad_norm": 0.8487282991409302,
+      "learning_rate": 6.271338724168913e-05,
+      "loss": 1.0985081195831299,
+      "step": 350
+    },
+    {
+      "epoch": 0.15188781014023733,
+      "grad_norm": 0.6718961596488953,
+      "learning_rate": 6.307277628032345e-05,
+      "loss": 1.0714176893234253,
+      "step": 352
+    },
+    {
+      "epoch": 0.15275080906148866,
+      "grad_norm": 0.8175088167190552,
+      "learning_rate": 6.343216531895777e-05,
+      "loss": 1.0599322319030762,
+      "step": 354
+    },
+    {
+      "epoch": 0.15361380798274002,
+      "grad_norm": 0.6359215378761292,
+      "learning_rate": 6.37915543575921e-05,
+      "loss": 0.9268131256103516,
+      "step": 356
+    },
+    {
+      "epoch": 0.15447680690399138,
+      "grad_norm": 0.6423866748809814,
+      "learning_rate": 6.415094339622641e-05,
+      "loss": 0.9838354587554932,
+      "step": 358
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "grad_norm": 0.6496716737747192,
+      "learning_rate": 6.451033243486074e-05,
+      "loss": 1.048566460609436,
+      "step": 360
+    },
+    {
+      "epoch": 0.15620280474649406,
+      "grad_norm": 0.6536920666694641,
+      "learning_rate": 6.486972147349506e-05,
+      "loss": 1.0910537242889404,
+      "step": 362
+    },
+    {
+      "epoch": 0.15706580366774542,
+      "grad_norm": 0.5832068920135498,
+      "learning_rate": 6.522911051212939e-05,
+      "loss": 0.9971448183059692,
+      "step": 364
+    },
+    {
+      "epoch": 0.15792880258899678,
+      "grad_norm": 0.6647719144821167,
+      "learning_rate": 6.558849955076371e-05,
+      "loss": 1.0496708154678345,
+      "step": 366
+    },
+    {
+      "epoch": 0.1587918015102481,
+      "grad_norm": 0.623252809047699,
+      "learning_rate": 6.594788858939802e-05,
+      "loss": 0.955894410610199,
+      "step": 368
+    },
+    {
+      "epoch": 0.15965480043149946,
+      "grad_norm": 0.6311860084533691,
+      "learning_rate": 6.630727762803235e-05,
+      "loss": 1.1304032802581787,
+      "step": 370
+    },
+    {
+      "epoch": 0.16051779935275082,
+      "grad_norm": 0.5306481122970581,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.8746405243873596,
+      "step": 372
+    },
+    {
+      "epoch": 0.16138079827400215,
+      "grad_norm": 0.6249631643295288,
+      "learning_rate": 6.7026055705301e-05,
+      "loss": 0.9104986786842346,
+      "step": 374
+    },
+    {
+      "epoch": 0.1622437971952535,
+      "grad_norm": 0.6243219971656799,
+      "learning_rate": 6.738544474393532e-05,
+      "loss": 1.043666124343872,
+      "step": 376
+    },
+    {
+      "epoch": 0.16310679611650486,
+      "grad_norm": 0.6833282113075256,
+      "learning_rate": 6.774483378256963e-05,
+      "loss": 1.0504906177520752,
+      "step": 378
+    },
+    {
+      "epoch": 0.16396979503775622,
+      "grad_norm": 0.7124452590942383,
+      "learning_rate": 6.810422282120395e-05,
+      "loss": 1.0608166456222534,
+      "step": 380
+    },
+    {
+      "epoch": 0.16483279395900755,
+      "grad_norm": 0.7520908117294312,
+      "learning_rate": 6.846361185983828e-05,
+      "loss": 1.1653732061386108,
+      "step": 382
+    },
+    {
+      "epoch": 0.1656957928802589,
+      "grad_norm": 0.7121814489364624,
+      "learning_rate": 6.88230008984726e-05,
+      "loss": 1.0626367330551147,
+      "step": 384
+    },
+    {
+      "epoch": 0.16655879180151026,
+      "grad_norm": 0.6825008988380432,
+      "learning_rate": 6.918238993710691e-05,
+      "loss": 1.012121319770813,
+      "step": 386
+    },
+    {
+      "epoch": 0.1674217907227616,
+      "grad_norm": 0.4922940135002136,
+      "learning_rate": 6.954177897574124e-05,
+      "loss": 1.0576211214065552,
+      "step": 388
+    },
+    {
+      "epoch": 0.16828478964401294,
+      "grad_norm": 0.6122089624404907,
+      "learning_rate": 6.990116801437556e-05,
+      "loss": 1.03916597366333,
+      "step": 390
+    },
+    {
+      "epoch": 0.1691477885652643,
+      "grad_norm": 0.6348981261253357,
+      "learning_rate": 7.026055705300989e-05,
+      "loss": 1.17647123336792,
+      "step": 392
+    },
+    {
+      "epoch": 0.17001078748651563,
+      "grad_norm": 0.6205878257751465,
+      "learning_rate": 7.06199460916442e-05,
+      "loss": 0.9095983505249023,
+      "step": 394
+    },
+    {
+      "epoch": 0.170873786407767,
+      "grad_norm": 0.61506187915802,
+      "learning_rate": 7.097933513027853e-05,
+      "loss": 1.082506775856018,
+      "step": 396
+    },
+    {
+      "epoch": 0.17173678532901834,
+      "grad_norm": 0.6481751799583435,
+      "learning_rate": 7.133872416891285e-05,
+      "loss": 1.0716280937194824,
+      "step": 398
+    },
+    {
+      "epoch": 0.1725997842502697,
+      "grad_norm": 0.4871014952659607,
+      "learning_rate": 7.169811320754717e-05,
+      "loss": 0.9616814851760864,
+      "step": 400
+    },
+    {
+      "epoch": 0.1725997842502697,
+      "eval_loss": 1.0649415254592896,
+      "eval_runtime": 668.6025,
+      "eval_samples_per_second": 3.081,
+      "eval_steps_per_second": 3.081,
+      "step": 400
+    },
+    {
+      "epoch": 0.17346278317152103,
+      "grad_norm": 0.5680040121078491,
+      "learning_rate": 7.20575022461815e-05,
+      "loss": 1.0475050210952759,
+      "step": 402
+    },
+    {
+      "epoch": 0.17432578209277239,
+      "grad_norm": 0.6417813897132874,
+      "learning_rate": 7.241689128481581e-05,
+      "loss": 0.9851161241531372,
+      "step": 404
+    },
+    {
+      "epoch": 0.17518878101402374,
+      "grad_norm": 0.6600468158721924,
+      "learning_rate": 7.277628032345014e-05,
+      "loss": 1.013339638710022,
+      "step": 406
+    },
+    {
+      "epoch": 0.17605177993527507,
+      "grad_norm": 0.6733932495117188,
+      "learning_rate": 7.313566936208446e-05,
+      "loss": 0.9346804022789001,
+      "step": 408
+    },
+    {
+      "epoch": 0.17691477885652643,
+      "grad_norm": 0.6812151074409485,
+      "learning_rate": 7.349505840071879e-05,
+      "loss": 0.9890368580818176,
+      "step": 410
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.6380394697189331,
+      "learning_rate": 7.385444743935311e-05,
+      "loss": 0.8787848949432373,
+      "step": 412
+    },
+    {
+      "epoch": 0.1786407766990291,
+      "grad_norm": 0.6004905700683594,
+      "learning_rate": 7.421383647798742e-05,
+      "loss": 1.0235728025436401,
+      "step": 414
+    },
+    {
+      "epoch": 0.17950377562028047,
+      "grad_norm": 0.6569193005561829,
+      "learning_rate": 7.457322551662175e-05,
+      "loss": 0.9972385168075562,
+      "step": 416
+    },
+    {
+      "epoch": 0.18036677454153183,
+      "grad_norm": 0.6761631369590759,
+      "learning_rate": 7.493261455525607e-05,
+      "loss": 0.9593698382377625,
+      "step": 418
+    },
+    {
+      "epoch": 0.18122977346278318,
+      "grad_norm": 0.7328561544418335,
+      "learning_rate": 7.529200359389039e-05,
+      "loss": 1.0426853895187378,
+      "step": 420
+    },
+    {
+      "epoch": 0.1820927723840345,
+      "grad_norm": 0.6256070137023926,
+      "learning_rate": 7.56513926325247e-05,
+      "loss": 0.9608182311058044,
+      "step": 422
+    },
+    {
+      "epoch": 0.18295577130528587,
+      "grad_norm": 1.2549844980239868,
+      "learning_rate": 7.601078167115903e-05,
+      "loss": 1.0162668228149414,
+      "step": 424
+    },
+    {
+      "epoch": 0.18381877022653723,
+      "grad_norm": 0.6751510500907898,
+      "learning_rate": 7.637017070979335e-05,
+      "loss": 1.130725383758545,
+      "step": 426
+    },
+    {
+      "epoch": 0.18468176914778855,
+      "grad_norm": 0.7029808163642883,
+      "learning_rate": 7.672955974842768e-05,
+      "loss": 1.0384817123413086,
+      "step": 428
+    },
+    {
+      "epoch": 0.1855447680690399,
+      "grad_norm": 0.644353449344635,
+      "learning_rate": 7.7088948787062e-05,
+      "loss": 1.017020344734192,
+      "step": 430
+    },
+    {
+      "epoch": 0.18640776699029127,
+      "grad_norm": 0.6784916520118713,
+      "learning_rate": 7.744833782569631e-05,
+      "loss": 1.005354404449463,
+      "step": 432
+    },
+    {
+      "epoch": 0.1872707659115426,
+      "grad_norm": 0.5989449620246887,
+      "learning_rate": 7.780772686433064e-05,
+      "loss": 1.026848316192627,
+      "step": 434
+    },
+    {
+      "epoch": 0.18813376483279395,
+      "grad_norm": 0.6502639651298523,
+      "learning_rate": 7.816711590296496e-05,
+      "loss": 0.9891080856323242,
+      "step": 436
+    },
+    {
+      "epoch": 0.1889967637540453,
+      "grad_norm": 0.6176205277442932,
+      "learning_rate": 7.852650494159929e-05,
+      "loss": 0.966316819190979,
+      "step": 438
+    },
+    {
+      "epoch": 0.18985976267529667,
+      "grad_norm": 0.6801626086235046,
+      "learning_rate": 7.88858939802336e-05,
+      "loss": 1.123063087463379,
+      "step": 440
+    },
+    {
+      "epoch": 0.190722761596548,
+      "grad_norm": 0.6718618273735046,
+      "learning_rate": 7.924528301886794e-05,
+      "loss": 1.0467073917388916,
+      "step": 442
+    },
+    {
+      "epoch": 0.19158576051779935,
+      "grad_norm": 0.6761009097099304,
+      "learning_rate": 7.960467205750225e-05,
+      "loss": 1.0952889919281006,
+      "step": 444
+    },
+    {
+      "epoch": 0.1924487594390507,
+      "grad_norm": 0.6356327533721924,
+      "learning_rate": 7.996406109613657e-05,
+      "loss": 0.954807698726654,
+      "step": 446
+    },
+    {
+      "epoch": 0.19331175836030204,
+      "grad_norm": 0.6798669695854187,
+      "learning_rate": 8.03234501347709e-05,
+      "loss": 0.9941422343254089,
+      "step": 448
+    },
+    {
+      "epoch": 0.1941747572815534,
+      "grad_norm": 0.6511302590370178,
+      "learning_rate": 8.068283917340521e-05,
+      "loss": 1.0351495742797852,
+      "step": 450
+    },
+    {
+      "epoch": 0.19503775620280475,
+      "grad_norm": 0.6061258912086487,
+      "learning_rate": 8.104222821203954e-05,
+      "loss": 1.00546133518219,
+      "step": 452
+    },
+    {
+      "epoch": 0.1959007551240561,
+      "grad_norm": 0.6278533935546875,
+      "learning_rate": 8.140161725067386e-05,
+      "loss": 1.0778460502624512,
+      "step": 454
+    },
+    {
+      "epoch": 0.19676375404530744,
+      "grad_norm": 0.6866298317909241,
+      "learning_rate": 8.176100628930818e-05,
+      "loss": 1.0344486236572266,
+      "step": 456
+    },
+    {
+      "epoch": 0.1976267529665588,
+      "grad_norm": 0.7338075041770935,
+      "learning_rate": 8.212039532794251e-05,
+      "loss": 1.0663033723831177,
+      "step": 458
+    },
+    {
+      "epoch": 0.19848975188781015,
+      "grad_norm": 0.6811459064483643,
+      "learning_rate": 8.247978436657682e-05,
+      "loss": 0.9665339589118958,
+      "step": 460
+    },
+    {
+      "epoch": 0.19935275080906148,
+      "grad_norm": 0.6779627799987793,
+      "learning_rate": 8.283917340521114e-05,
+      "loss": 1.024712324142456,
+      "step": 462
+    },
+    {
+      "epoch": 0.20021574973031284,
+      "grad_norm": 0.6486892700195312,
+      "learning_rate": 8.319856244384546e-05,
+      "loss": 0.9699305295944214,
+      "step": 464
+    },
+    {
+      "epoch": 0.2010787486515642,
+      "grad_norm": 0.7022278308868408,
+      "learning_rate": 8.355795148247979e-05,
+      "loss": 0.9540432095527649,
+      "step": 466
+    },
+    {
+      "epoch": 0.20194174757281552,
+      "grad_norm": 0.5922990441322327,
+      "learning_rate": 8.39173405211141e-05,
+      "loss": 0.9253339767456055,
+      "step": 468
+    },
+    {
+      "epoch": 0.20280474649406688,
+      "grad_norm": 0.7076792120933533,
+      "learning_rate": 8.427672955974843e-05,
+      "loss": 0.9987741112709045,
+      "step": 470
+    },
+    {
+      "epoch": 0.20366774541531824,
+      "grad_norm": 0.6491380333900452,
+      "learning_rate": 8.463611859838275e-05,
+      "loss": 1.0249329805374146,
+      "step": 472
+    },
+    {
+      "epoch": 0.2045307443365696,
+      "grad_norm": 0.6784211993217468,
+      "learning_rate": 8.499550763701708e-05,
+      "loss": 1.0577133893966675,
+      "step": 474
+    },
+    {
+      "epoch": 0.20539374325782092,
+      "grad_norm": 0.6453303694725037,
+      "learning_rate": 8.53548966756514e-05,
+      "loss": 1.1312458515167236,
+      "step": 476
+    },
+    {
+      "epoch": 0.20625674217907228,
+      "grad_norm": 0.7431377172470093,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 1.0592451095581055,
+      "step": 478
+    },
+    {
+      "epoch": 0.20711974110032363,
+      "grad_norm": 0.6097649931907654,
+      "learning_rate": 8.607367475292004e-05,
+      "loss": 0.9337235689163208,
+      "step": 480
+    },
+    {
+      "epoch": 0.20798274002157496,
+      "grad_norm": 0.5693124532699585,
+      "learning_rate": 8.643306379155436e-05,
+      "loss": 0.9088928699493408,
+      "step": 482
+    },
+    {
+      "epoch": 0.20884573894282632,
+      "grad_norm": 0.7377229332923889,
+      "learning_rate": 8.679245283018869e-05,
+      "loss": 1.0729358196258545,
+      "step": 484
+    },
+    {
+      "epoch": 0.20970873786407768,
+      "grad_norm": 0.7399470210075378,
+      "learning_rate": 8.7151841868823e-05,
+      "loss": 1.0428457260131836,
+      "step": 486
+    },
+    {
+      "epoch": 0.210571736785329,
+      "grad_norm": 0.677052915096283,
+      "learning_rate": 8.751123090745734e-05,
+      "loss": 0.9940266013145447,
+      "step": 488
+    },
+    {
+      "epoch": 0.21143473570658036,
+      "grad_norm": 0.7126721739768982,
+      "learning_rate": 8.787061994609165e-05,
+      "loss": 1.011808156967163,
+      "step": 490
+    },
+    {
+      "epoch": 0.21229773462783172,
+      "grad_norm": 0.6663792729377747,
+      "learning_rate": 8.823000898472597e-05,
+      "loss": 1.0054185390472412,
+      "step": 492
+    },
+    {
+      "epoch": 0.21316073354908308,
+      "grad_norm": 0.6661092042922974,
+      "learning_rate": 8.85893980233603e-05,
+      "loss": 1.0167138576507568,
+      "step": 494
+    },
+    {
+      "epoch": 0.2140237324703344,
+      "grad_norm": 0.6975740194320679,
+      "learning_rate": 8.894878706199461e-05,
+      "loss": 1.1470818519592285,
+      "step": 496
+    },
+    {
+      "epoch": 0.21488673139158576,
+      "grad_norm": 0.6594390869140625,
+      "learning_rate": 8.930817610062893e-05,
+      "loss": 0.9619631171226501,
+      "step": 498
+    },
+    {
+      "epoch": 0.21574973031283712,
+      "grad_norm": 0.7216679453849792,
+      "learning_rate": 8.966756513926325e-05,
+      "loss": 0.9971368312835693,
+      "step": 500
+    },
+    {
+      "epoch": 0.21574973031283712,
+      "eval_loss": 1.0417571067810059,
+      "eval_runtime": 659.3112,
+      "eval_samples_per_second": 3.124,
+      "eval_steps_per_second": 3.124,
+      "step": 500
+    },
+    {
+      "epoch": 0.21661272923408845,
+      "grad_norm": 0.6188210844993591,
+      "learning_rate": 9.002695417789758e-05,
+      "loss": 1.0307213068008423,
+      "step": 502
+    },
+    {
+      "epoch": 0.2174757281553398,
+      "grad_norm": 0.6716445088386536,
+      "learning_rate": 9.03863432165319e-05,
+      "loss": 1.0188794136047363,
+      "step": 504
+    },
+    {
+      "epoch": 0.21833872707659116,
+      "grad_norm": 0.6790863275527954,
+      "learning_rate": 9.074573225516622e-05,
+      "loss": 0.9764845967292786,
+      "step": 506
+    },
+    {
+      "epoch": 0.2192017259978425,
+      "grad_norm": 0.6764960289001465,
+      "learning_rate": 9.110512129380054e-05,
+      "loss": 0.948829174041748,
+      "step": 508
+    },
+    {
+      "epoch": 0.22006472491909385,
+      "grad_norm": 0.6210965514183044,
+      "learning_rate": 9.146451033243486e-05,
+      "loss": 1.008013129234314,
+      "step": 510
+    },
+    {
+      "epoch": 0.2209277238403452,
+      "grad_norm": 0.7739297747612,
+      "learning_rate": 9.182389937106919e-05,
+      "loss": 1.1662557125091553,
+      "step": 512
+    },
+    {
+      "epoch": 0.22179072276159656,
+      "grad_norm": 0.7055562138557434,
+      "learning_rate": 9.21832884097035e-05,
+      "loss": 1.0325161218643188,
+      "step": 514
+    },
+    {
+      "epoch": 0.2226537216828479,
+      "grad_norm": 0.6079210042953491,
+      "learning_rate": 9.254267744833783e-05,
+      "loss": 1.00056791305542,
+      "step": 516
+    },
+    {
+      "epoch": 0.22351672060409924,
+      "grad_norm": 0.5974318981170654,
+      "learning_rate": 9.290206648697215e-05,
+      "loss": 0.9422364234924316,
+      "step": 518
+    },
+    {
+      "epoch": 0.2243797195253506,
+      "grad_norm": 0.5963430404663086,
+      "learning_rate": 9.326145552560648e-05,
+      "loss": 0.936336100101471,
+      "step": 520
+    },
+    {
+      "epoch": 0.22524271844660193,
+      "grad_norm": 0.6823658347129822,
+      "learning_rate": 9.36208445642408e-05,
+      "loss": 1.0538607835769653,
+      "step": 522
+    },
+    {
+      "epoch": 0.2261057173678533,
+      "grad_norm": 0.6409855484962463,
+      "learning_rate": 9.398023360287511e-05,
+      "loss": 1.0483653545379639,
+      "step": 524
+    },
+    {
+      "epoch": 0.22696871628910464,
+      "grad_norm": 0.6867254376411438,
+      "learning_rate": 9.433962264150944e-05,
+      "loss": 0.9668049812316895,
+      "step": 526
+    },
+    {
+      "epoch": 0.227831715210356,
+      "grad_norm": 0.5690792798995972,
+      "learning_rate": 9.469901168014376e-05,
+      "loss": 1.008763313293457,
+      "step": 528
+    },
+    {
+      "epoch": 0.22869471413160733,
+      "grad_norm": 0.5964897274971008,
+      "learning_rate": 9.505840071877809e-05,
+      "loss": 1.0816441774368286,
+      "step": 530
+    },
+    {
+      "epoch": 0.2295577130528587,
+      "grad_norm": 0.627419114112854,
+      "learning_rate": 9.54177897574124e-05,
+      "loss": 0.9265700578689575,
+      "step": 532
+    },
+    {
+      "epoch": 0.23042071197411004,
+      "grad_norm": 0.5862151980400085,
+      "learning_rate": 9.577717879604674e-05,
+      "loss": 0.9804646372795105,
+      "step": 534
+    },
+    {
+      "epoch": 0.23128371089536137,
+      "grad_norm": 0.5573718547821045,
+      "learning_rate": 9.613656783468105e-05,
+      "loss": 0.9627988934516907,
+      "step": 536
+    },
+    {
+      "epoch": 0.23214670981661273,
+      "grad_norm": 0.6705166101455688,
+      "learning_rate": 9.649595687331537e-05,
+      "loss": 1.0012824535369873,
+      "step": 538
+    },
+    {
+      "epoch": 0.23300970873786409,
+      "grad_norm": 0.6251236796379089,
+      "learning_rate": 9.685534591194969e-05,
+      "loss": 0.9568162560462952,
+      "step": 540
+    },
+    {
+      "epoch": 0.23387270765911541,
+      "grad_norm": 0.6466493010520935,
+      "learning_rate": 9.7214734950584e-05,
+      "loss": 1.031549334526062,
+      "step": 542
+    },
+    {
+      "epoch": 0.23473570658036677,
+      "grad_norm": 0.5183866024017334,
+      "learning_rate": 9.757412398921833e-05,
+      "loss": 0.8603643774986267,
+      "step": 544
+    },
+    {
+      "epoch": 0.23559870550161813,
+      "grad_norm": 0.6725775599479675,
+      "learning_rate": 9.793351302785265e-05,
+      "loss": 1.0365077257156372,
+      "step": 546
+    },
+    {
+      "epoch": 0.23646170442286948,
+      "grad_norm": 0.5972357988357544,
+      "learning_rate": 9.829290206648698e-05,
+      "loss": 0.9304701089859009,
+      "step": 548
+    },
+    {
+      "epoch": 0.2373247033441208,
+      "grad_norm": 0.5319957733154297,
+      "learning_rate": 9.86522911051213e-05,
+      "loss": 0.9575805068016052,
+      "step": 550
+    },
+    {
+      "epoch": 0.23818770226537217,
+      "grad_norm": 0.6502835750579834,
+      "learning_rate": 9.901168014375562e-05,
+      "loss": 1.0307214260101318,
+      "step": 552
+    },
+    {
+      "epoch": 0.23905070118662353,
+      "grad_norm": 0.6734047532081604,
+      "learning_rate": 9.937106918238994e-05,
+      "loss": 1.05185067653656,
+      "step": 554
+    },
+    {
+      "epoch": 0.23991370010787486,
+      "grad_norm": 0.5667978525161743,
+      "learning_rate": 9.973045822102426e-05,
+      "loss": 1.0190176963806152,
+      "step": 556
+    },
+    {
+      "epoch": 0.2407766990291262,
+      "grad_norm": 0.6370418667793274,
+      "learning_rate": 0.00010008984725965857,
+      "loss": 1.076182246208191,
+      "step": 558
+    },
+    {
+      "epoch": 0.24163969795037757,
+      "grad_norm": 0.689719021320343,
+      "learning_rate": 0.0001004492362982929,
+      "loss": 1.0408724546432495,
+      "step": 560
+    },
+    {
+      "epoch": 0.2425026968716289,
+      "grad_norm": 0.6304254531860352,
+      "learning_rate": 0.00010080862533692723,
+      "loss": 0.9869902729988098,
+      "step": 562
+    },
+    {
+      "epoch": 0.24336569579288025,
+      "grad_norm": 0.6797420382499695,
+      "learning_rate": 0.00010116801437556156,
+      "loss": 1.0198370218276978,
+      "step": 564
+    },
+    {
+      "epoch": 0.2442286947141316,
+      "grad_norm": 0.5993657112121582,
+      "learning_rate": 0.00010152740341419587,
+      "loss": 0.9947441816329956,
+      "step": 566
+    },
+    {
+      "epoch": 0.24509169363538297,
+      "grad_norm": 0.6369836330413818,
+      "learning_rate": 0.0001018867924528302,
+      "loss": 0.9722896814346313,
+      "step": 568
+    },
+    {
+      "epoch": 0.2459546925566343,
+      "grad_norm": 0.6942457556724548,
+      "learning_rate": 0.00010224618149146453,
+      "loss": 0.9716570973396301,
+      "step": 570
+    },
+    {
+      "epoch": 0.24681769147788565,
+      "grad_norm": 0.5403370261192322,
+      "learning_rate": 0.00010260557053009883,
+      "loss": 0.9797524213790894,
+      "step": 572
+    },
+    {
+      "epoch": 0.247680690399137,
+      "grad_norm": 0.5207529067993164,
+      "learning_rate": 0.00010296495956873316,
+      "loss": 0.985367476940155,
+      "step": 574
+    },
+    {
+      "epoch": 0.24854368932038834,
+      "grad_norm": 0.6751103401184082,
+      "learning_rate": 0.00010332434860736748,
+      "loss": 1.075042724609375,
+      "step": 576
+    },
+    {
+      "epoch": 0.2494066882416397,
+      "grad_norm": 0.565331220626831,
+      "learning_rate": 0.0001036837376460018,
+      "loss": 0.9273878335952759,
+      "step": 578
+    },
+    {
+      "epoch": 0.25026968716289105,
+      "grad_norm": 0.6858948469161987,
+      "learning_rate": 0.00010404312668463612,
+      "loss": 0.9872279763221741,
+      "step": 580
+    },
+    {
+      "epoch": 0.2511326860841424,
+      "grad_norm": 0.7091426253318787,
+      "learning_rate": 0.00010440251572327044,
+      "loss": 1.0038671493530273,
+      "step": 582
+    },
+    {
+      "epoch": 0.25199568500539377,
+      "grad_norm": 0.6493771076202393,
+      "learning_rate": 0.00010476190476190477,
+      "loss": 1.0109868049621582,
+      "step": 584
+    },
+    {
+      "epoch": 0.25285868392664507,
+      "grad_norm": 0.6107586622238159,
+      "learning_rate": 0.00010512129380053907,
+      "loss": 1.0020402669906616,
+      "step": 586
+    },
+    {
+      "epoch": 0.2537216828478964,
+      "grad_norm": 0.6878048181533813,
+      "learning_rate": 0.0001054806828391734,
+      "loss": 0.961039662361145,
+      "step": 588
+    },
+    {
+      "epoch": 0.2545846817691478,
+      "grad_norm": 0.664034903049469,
+      "learning_rate": 0.00010584007187780773,
+      "loss": 0.9725209474563599,
+      "step": 590
+    },
+    {
+      "epoch": 0.25544768069039914,
+      "grad_norm": 0.6399680376052856,
+      "learning_rate": 0.00010619946091644206,
+      "loss": 0.9907437562942505,
+      "step": 592
+    },
+    {
+      "epoch": 0.2563106796116505,
+      "grad_norm": 0.6163286566734314,
+      "learning_rate": 0.00010655884995507636,
+      "loss": 0.9650095701217651,
+      "step": 594
+    },
+    {
+      "epoch": 0.25717367853290185,
+      "grad_norm": 0.6008322238922119,
+      "learning_rate": 0.0001069182389937107,
+      "loss": 1.0102758407592773,
+      "step": 596
+    },
+    {
+      "epoch": 0.2580366774541532,
+      "grad_norm": 0.6752071380615234,
+      "learning_rate": 0.00010727762803234502,
+      "loss": 0.9101885557174683,
+      "step": 598
+    },
+    {
+      "epoch": 0.2588996763754045,
+      "grad_norm": 0.6789175868034363,
+      "learning_rate": 0.00010763701707097935,
+      "loss": 1.0461398363113403,
+      "step": 600
+    },
+    {
+      "epoch": 0.2588996763754045,
+      "eval_loss": 1.021111011505127,
+      "eval_runtime": 648.1611,
+      "eval_samples_per_second": 3.178,
+      "eval_steps_per_second": 3.178,
+      "step": 600
+    },
+    {
+      "epoch": 0.25976267529665586,
+      "grad_norm": 0.5660730600357056,
+      "learning_rate": 0.00010799640610961366,
+      "loss": 0.9582418203353882,
+      "step": 602
+    },
+    {
+      "epoch": 0.2606256742179072,
+      "grad_norm": 0.6726544499397278,
+      "learning_rate": 0.00010835579514824799,
+      "loss": 1.0763746500015259,
+      "step": 604
+    },
+    {
+      "epoch": 0.2614886731391586,
+      "grad_norm": 0.6068508625030518,
+      "learning_rate": 0.00010871518418688232,
+      "loss": 1.0432032346725464,
+      "step": 606
+    },
+    {
+      "epoch": 0.26235167206040994,
+      "grad_norm": 0.5731637477874756,
+      "learning_rate": 0.00010907457322551662,
+      "loss": 0.9830516576766968,
+      "step": 608
+    },
+    {
+      "epoch": 0.2632146709816613,
+      "grad_norm": 0.6777567267417908,
+      "learning_rate": 0.00010943396226415095,
+      "loss": 1.0442042350769043,
+      "step": 610
+    },
+    {
+      "epoch": 0.26407766990291265,
+      "grad_norm": 0.6372506618499756,
+      "learning_rate": 0.00010979335130278528,
+      "loss": 1.0001944303512573,
+      "step": 612
+    },
+    {
+      "epoch": 0.26494066882416395,
+      "grad_norm": 0.6606221795082092,
+      "learning_rate": 0.0001101527403414196,
+      "loss": 1.035884141921997,
+      "step": 614
+    },
+    {
+      "epoch": 0.2658036677454153,
+      "grad_norm": 0.6083229780197144,
+      "learning_rate": 0.00011051212938005391,
+      "loss": 0.9403397440910339,
+      "step": 616
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.6318517923355103,
+      "learning_rate": 0.00011087151841868823,
+      "loss": 0.9274454116821289,
+      "step": 618
+    },
+    {
+      "epoch": 0.267529665587918,
+      "grad_norm": 0.628190279006958,
+      "learning_rate": 0.00011123090745732256,
+      "loss": 0.9883754253387451,
+      "step": 620
+    },
+    {
+      "epoch": 0.2683926645091694,
+      "grad_norm": 0.5961961150169373,
+      "learning_rate": 0.00011159029649595688,
+      "loss": 1.0317535400390625,
+      "step": 622
+    },
+    {
+      "epoch": 0.26925566343042073,
+      "grad_norm": 0.5995341539382935,
+      "learning_rate": 0.00011194968553459119,
+      "loss": 0.9776126742362976,
+      "step": 624
+    },
+    {
+      "epoch": 0.27011866235167203,
+      "grad_norm": 0.6639334559440613,
+      "learning_rate": 0.00011230907457322552,
+      "loss": 1.0112378597259521,
+      "step": 626
+    },
+    {
+      "epoch": 0.2709816612729234,
+      "grad_norm": 0.6348621249198914,
+      "learning_rate": 0.00011266846361185985,
+      "loss": 1.0553804636001587,
+      "step": 628
+    },
+    {
+      "epoch": 0.27184466019417475,
+      "grad_norm": 0.5929805040359497,
+      "learning_rate": 0.00011302785265049416,
+      "loss": 1.025888442993164,
+      "step": 630
+    },
+    {
+      "epoch": 0.2727076591154261,
+      "grad_norm": 0.6052366495132446,
+      "learning_rate": 0.00011338724168912849,
+      "loss": 1.02956223487854,
+      "step": 632
+    },
+    {
+      "epoch": 0.27357065803667746,
+      "grad_norm": 0.6494882106781006,
+      "learning_rate": 0.00011374663072776282,
+      "loss": 0.989752471446991,
+      "step": 634
+    },
+    {
+      "epoch": 0.2744336569579288,
+      "grad_norm": 0.6005767583847046,
+      "learning_rate": 0.00011410601976639712,
+      "loss": 1.0030683279037476,
+      "step": 636
+    },
+    {
+      "epoch": 0.2752966558791802,
+      "grad_norm": 0.6478356122970581,
+      "learning_rate": 0.00011446540880503145,
+      "loss": 1.002000093460083,
+      "step": 638
+    },
+    {
+      "epoch": 0.2761596548004315,
+      "grad_norm": 0.5804725289344788,
+      "learning_rate": 0.00011482479784366578,
+      "loss": 0.9807654023170471,
+      "step": 640
+    },
+    {
+      "epoch": 0.27702265372168283,
+      "grad_norm": 0.632530689239502,
+      "learning_rate": 0.00011518418688230011,
+      "loss": 0.9841892123222351,
+      "step": 642
+    },
+    {
+      "epoch": 0.2778856526429342,
+      "grad_norm": 0.5340113639831543,
+      "learning_rate": 0.00011554357592093441,
+      "loss": 0.8902478814125061,
+      "step": 644
+    },
+    {
+      "epoch": 0.27874865156418555,
+      "grad_norm": 0.5901665091514587,
+      "learning_rate": 0.00011590296495956874,
+      "loss": 0.9019404649734497,
+      "step": 646
+    },
+    {
+      "epoch": 0.2796116504854369,
+      "grad_norm": 0.666589617729187,
+      "learning_rate": 0.00011626235399820307,
+      "loss": 0.9384423494338989,
+      "step": 648
+    },
+    {
+      "epoch": 0.28047464940668826,
+      "grad_norm": 0.7000334858894348,
+      "learning_rate": 0.00011662174303683737,
+      "loss": 1.0666629076004028,
+      "step": 650
+    },
+    {
+      "epoch": 0.2813376483279396,
+      "grad_norm": 0.663663923740387,
+      "learning_rate": 0.0001169811320754717,
+      "loss": 1.000019907951355,
+      "step": 652
+    },
+    {
+      "epoch": 0.2822006472491909,
+      "grad_norm": 0.6097694039344788,
+      "learning_rate": 0.00011734052111410603,
+      "loss": 0.9450293183326721,
+      "step": 654
+    },
+    {
+      "epoch": 0.2830636461704423,
+      "grad_norm": 0.6130967140197754,
+      "learning_rate": 0.00011769991015274035,
+      "loss": 0.9480894207954407,
+      "step": 656
+    },
+    {
+      "epoch": 0.28392664509169363,
+      "grad_norm": 0.7091249227523804,
+      "learning_rate": 0.00011805929919137467,
+      "loss": 1.1377143859863281,
+      "step": 658
+    },
+    {
+      "epoch": 0.284789644012945,
+      "grad_norm": 0.6556766629219055,
+      "learning_rate": 0.00011841868823000898,
+      "loss": 0.9421243667602539,
+      "step": 660
+    },
+    {
+      "epoch": 0.28565264293419634,
+      "grad_norm": 0.6682968735694885,
+      "learning_rate": 0.00011877807726864331,
+      "loss": 0.9726828336715698,
+      "step": 662
+    },
+    {
+      "epoch": 0.2865156418554477,
+      "grad_norm": 0.5224708914756775,
+      "learning_rate": 0.00011913746630727762,
+      "loss": 0.8996511697769165,
+      "step": 664
+    },
+    {
+      "epoch": 0.287378640776699,
+      "grad_norm": 0.5914195775985718,
+      "learning_rate": 0.00011949685534591195,
+      "loss": 0.9679517149925232,
+      "step": 666
+    },
+    {
+      "epoch": 0.28824163969795036,
+      "grad_norm": 0.6175519824028015,
+      "learning_rate": 0.00011985624438454628,
+      "loss": 0.8743209838867188,
+      "step": 668
+    },
+    {
+      "epoch": 0.2891046386192017,
+      "grad_norm": 0.6019226312637329,
+      "learning_rate": 0.0001202156334231806,
+      "loss": 0.9741992354393005,
+      "step": 670
+    },
+    {
+      "epoch": 0.28996763754045307,
+      "grad_norm": 0.6080542206764221,
+      "learning_rate": 0.00012057502246181491,
+      "loss": 0.9516472816467285,
+      "step": 672
+    },
+    {
+      "epoch": 0.29083063646170443,
+      "grad_norm": 0.5885615944862366,
+      "learning_rate": 0.00012093441150044924,
+      "loss": 1.122761607170105,
+      "step": 674
+    },
+    {
+      "epoch": 0.2916936353829558,
+      "grad_norm": 0.6635209918022156,
+      "learning_rate": 0.00012129380053908357,
+      "loss": 1.0105189085006714,
+      "step": 676
+    },
+    {
+      "epoch": 0.29255663430420714,
+      "grad_norm": 0.5805009007453918,
+      "learning_rate": 0.0001216531895777179,
+      "loss": 0.906292200088501,
+      "step": 678
+    },
+    {
+      "epoch": 0.29341963322545844,
+      "grad_norm": 0.5980029702186584,
+      "learning_rate": 0.0001220125786163522,
+      "loss": 1.009568691253662,
+      "step": 680
+    },
+    {
+      "epoch": 0.2942826321467098,
+      "grad_norm": 0.6797705292701721,
+      "learning_rate": 0.00012237196765498652,
+      "loss": 1.0373667478561401,
+      "step": 682
+    },
+    {
+      "epoch": 0.29514563106796116,
+      "grad_norm": 0.6280547976493835,
+      "learning_rate": 0.00012273135669362085,
+      "loss": 0.9758188724517822,
+      "step": 684
+    },
+    {
+      "epoch": 0.2960086299892125,
+      "grad_norm": 0.511608898639679,
+      "learning_rate": 0.00012309074573225515,
+      "loss": 0.9111692905426025,
+      "step": 686
+    },
+    {
+      "epoch": 0.29687162891046387,
+      "grad_norm": 0.5781835317611694,
+      "learning_rate": 0.00012345013477088948,
+      "loss": 0.8865921497344971,
+      "step": 688
+    },
+    {
+      "epoch": 0.2977346278317152,
+      "grad_norm": 0.6514166593551636,
+      "learning_rate": 0.0001238095238095238,
+      "loss": 0.9768189191818237,
+      "step": 690
+    },
+    {
+      "epoch": 0.2985976267529666,
+      "grad_norm": 0.6109189987182617,
+      "learning_rate": 0.00012416891284815814,
+      "loss": 0.9991607069969177,
+      "step": 692
+    },
+    {
+      "epoch": 0.2994606256742179,
+      "grad_norm": 0.6598902344703674,
+      "learning_rate": 0.00012452830188679244,
+      "loss": 0.9548360705375671,
+      "step": 694
+    },
+    {
+      "epoch": 0.30032362459546924,
+      "grad_norm": 0.5633156895637512,
+      "learning_rate": 0.00012488769092542677,
+      "loss": 0.992988109588623,
+      "step": 696
+    },
+    {
+      "epoch": 0.3011866235167206,
+      "grad_norm": 0.6098802089691162,
+      "learning_rate": 0.0001252470799640611,
+      "loss": 0.9709890484809875,
+      "step": 698
+    },
+    {
+      "epoch": 0.30204962243797195,
+      "grad_norm": 0.6197102665901184,
+      "learning_rate": 0.0001256064690026954,
+      "loss": 1.018282175064087,
+      "step": 700
+    },
+    {
+      "epoch": 0.30204962243797195,
+      "eval_loss": 1.0030721426010132,
+      "eval_runtime": 655.4533,
+      "eval_samples_per_second": 3.143,
+      "eval_steps_per_second": 3.143,
+      "step": 700
+    },
+    {
+      "epoch": 0.3029126213592233,
+      "grad_norm": 0.5817480683326721,
+      "learning_rate": 0.00012596585804132974,
+      "loss": 0.9147283434867859,
+      "step": 702
+    },
+    {
+      "epoch": 0.30377562028047467,
+      "grad_norm": 0.5976696014404297,
+      "learning_rate": 0.00012632524707996407,
+      "loss": 0.9318362474441528,
+      "step": 704
+    },
+    {
+      "epoch": 0.304638619201726,
+      "grad_norm": 0.6389723420143127,
+      "learning_rate": 0.0001266846361185984,
+      "loss": 0.9500927925109863,
+      "step": 706
+    },
+    {
+      "epoch": 0.3055016181229773,
+      "grad_norm": 0.6485719084739685,
+      "learning_rate": 0.0001270440251572327,
+      "loss": 1.0271424055099487,
+      "step": 708
+    },
+    {
+      "epoch": 0.3063646170442287,
+      "grad_norm": 0.5802455544471741,
+      "learning_rate": 0.00012740341419586703,
+      "loss": 0.9781906008720398,
+      "step": 710
+    },
+    {
+      "epoch": 0.30722761596548004,
+      "grad_norm": 0.6359356641769409,
+      "learning_rate": 0.00012776280323450136,
+      "loss": 1.0195324420928955,
+      "step": 712
+    },
+    {
+      "epoch": 0.3080906148867314,
+      "grad_norm": 0.5975426435470581,
+      "learning_rate": 0.00012812219227313566,
+      "loss": 0.9250738024711609,
+      "step": 714
+    },
+    {
+      "epoch": 0.30895361380798275,
+      "grad_norm": 0.643110454082489,
+      "learning_rate": 0.00012848158131177,
+      "loss": 0.9888015985488892,
+      "step": 716
+    },
+    {
+      "epoch": 0.3098166127292341,
+      "grad_norm": 0.6043205261230469,
+      "learning_rate": 0.00012884097035040432,
+      "loss": 0.9709514379501343,
+      "step": 718
+    },
+    {
+      "epoch": 0.3106796116504854,
+      "grad_norm": 0.5687094926834106,
+      "learning_rate": 0.00012920035938903865,
+      "loss": 1.0272964239120483,
+      "step": 720
+    },
+    {
+      "epoch": 0.31154261057173677,
+      "grad_norm": 0.5688400864601135,
+      "learning_rate": 0.00012955974842767296,
+      "loss": 0.9370370507240295,
+      "step": 722
+    },
+    {
+      "epoch": 0.3124056094929881,
+      "grad_norm": 0.5610610246658325,
+      "learning_rate": 0.00012991913746630729,
+      "loss": 0.9535608291625977,
+      "step": 724
+    },
+    {
+      "epoch": 0.3132686084142395,
+      "grad_norm": 0.6338257193565369,
+      "learning_rate": 0.00013027852650494162,
+      "loss": 1.0188907384872437,
+      "step": 726
+    },
+    {
+      "epoch": 0.31413160733549084,
+      "grad_norm": 0.5365633368492126,
+      "learning_rate": 0.00013063791554357592,
+      "loss": 0.9253716468811035,
+      "step": 728
+    },
+    {
+      "epoch": 0.3149946062567422,
+      "grad_norm": 0.5599163174629211,
+      "learning_rate": 0.00013099730458221025,
+      "loss": 0.8941492438316345,
+      "step": 730
+    },
+    {
+      "epoch": 0.31585760517799355,
+      "grad_norm": 0.6059780716896057,
+      "learning_rate": 0.00013135669362084458,
+      "loss": 0.9831459522247314,
+      "step": 732
+    },
+    {
+      "epoch": 0.31672060409924485,
+      "grad_norm": 0.5596494078636169,
+      "learning_rate": 0.0001317160826594789,
+      "loss": 0.9332310557365417,
+      "step": 734
+    },
+    {
+      "epoch": 0.3175836030204962,
+      "grad_norm": 0.5618010759353638,
+      "learning_rate": 0.0001320754716981132,
+      "loss": 0.9082580208778381,
+      "step": 736
+    },
+    {
+      "epoch": 0.31844660194174756,
+      "grad_norm": 0.6412109732627869,
+      "learning_rate": 0.00013243486073674754,
+      "loss": 1.008690357208252,
+      "step": 738
+    },
+    {
+      "epoch": 0.3193096008629989,
+      "grad_norm": 0.5742355585098267,
+      "learning_rate": 0.00013279424977538187,
+      "loss": 0.9597798585891724,
+      "step": 740
+    },
+    {
+      "epoch": 0.3201725997842503,
+      "grad_norm": 0.6470226645469666,
+      "learning_rate": 0.00013315363881401617,
+      "loss": 0.989331841468811,
+      "step": 742
+    },
+    {
+      "epoch": 0.32103559870550163,
+      "grad_norm": 0.5598039031028748,
+      "learning_rate": 0.0001335130278526505,
+      "loss": 0.8677343130111694,
+      "step": 744
+    },
+    {
+      "epoch": 0.321898597626753,
+      "grad_norm": 0.5441372990608215,
+      "learning_rate": 0.00013387241689128483,
+      "loss": 0.9462730288505554,
+      "step": 746
+    },
+    {
+      "epoch": 0.3227615965480043,
+      "grad_norm": 0.5858626365661621,
+      "learning_rate": 0.00013423180592991916,
+      "loss": 0.994694173336029,
+      "step": 748
+    },
+    {
+      "epoch": 0.32362459546925565,
+      "grad_norm": 0.511372447013855,
+      "learning_rate": 0.00013459119496855347,
+      "loss": 0.9387269616127014,
+      "step": 750
+    },
+    {
+      "epoch": 0.324487594390507,
+      "grad_norm": 0.47798457741737366,
+      "learning_rate": 0.0001349505840071878,
+      "loss": 0.9473881721496582,
+      "step": 752
+    },
+    {
+      "epoch": 0.32535059331175836,
+      "grad_norm": 0.5907022953033447,
+      "learning_rate": 0.0001353099730458221,
+      "loss": 0.9375183582305908,
+      "step": 754
+    },
+    {
+      "epoch": 0.3262135922330097,
+      "grad_norm": 0.618733286857605,
+      "learning_rate": 0.00013566936208445643,
+      "loss": 1.028738260269165,
+      "step": 756
+    },
+    {
+      "epoch": 0.3270765911542611,
+      "grad_norm": 0.5234512090682983,
+      "learning_rate": 0.00013602875112309076,
+      "loss": 0.9420192241668701,
+      "step": 758
+    },
+    {
+      "epoch": 0.32793959007551243,
+      "grad_norm": 0.7036319971084595,
+      "learning_rate": 0.00013638814016172506,
+      "loss": 1.0252270698547363,
+      "step": 760
+    },
+    {
+      "epoch": 0.32880258899676373,
+      "grad_norm": 0.5543172359466553,
+      "learning_rate": 0.0001367475292003594,
+      "loss": 0.8453778028488159,
+      "step": 762
+    },
+    {
+      "epoch": 0.3296655879180151,
+      "grad_norm": 0.5438711643218994,
+      "learning_rate": 0.0001371069182389937,
+      "loss": 0.8659937977790833,
+      "step": 764
+    },
+    {
+      "epoch": 0.33052858683926645,
+      "grad_norm": 0.6390914916992188,
+      "learning_rate": 0.00013746630727762803,
+      "loss": 1.038142442703247,
+      "step": 766
+    },
+    {
+      "epoch": 0.3313915857605178,
+      "grad_norm": 0.50070720911026,
+      "learning_rate": 0.00013782569631626236,
+      "loss": 0.899932861328125,
+      "step": 768
+    },
+    {
+      "epoch": 0.33225458468176916,
+      "grad_norm": 0.5982286334037781,
+      "learning_rate": 0.00013818508535489669,
+      "loss": 0.9712884426116943,
+      "step": 770
+    },
+    {
+      "epoch": 0.3331175836030205,
+      "grad_norm": 0.6588822603225708,
+      "learning_rate": 0.000138544474393531,
+      "loss": 0.9427542686462402,
+      "step": 772
+    },
+    {
+      "epoch": 0.3339805825242718,
+      "grad_norm": 0.6022042632102966,
+      "learning_rate": 0.00013890386343216532,
+      "loss": 0.8961561918258667,
+      "step": 774
+    },
+    {
+      "epoch": 0.3348435814455232,
+      "grad_norm": 0.6595642566680908,
+      "learning_rate": 0.00013926325247079965,
+      "loss": 0.9525937438011169,
+      "step": 776
+    },
+    {
+      "epoch": 0.33570658036677453,
+      "grad_norm": 0.5210421681404114,
+      "learning_rate": 0.00013962264150943395,
+      "loss": 0.9218845367431641,
+      "step": 778
+    },
+    {
+      "epoch": 0.3365695792880259,
+      "grad_norm": 0.549669623374939,
+      "learning_rate": 0.00013998203054806828,
+      "loss": 0.877951443195343,
+      "step": 780
+    },
+    {
+      "epoch": 0.33743257820927725,
+      "grad_norm": 0.5360157489776611,
+      "learning_rate": 0.0001403414195867026,
+      "loss": 0.8670064210891724,
+      "step": 782
+    },
+    {
+      "epoch": 0.3382955771305286,
+      "grad_norm": 0.614734947681427,
+      "learning_rate": 0.00014070080862533694,
+      "loss": 0.9561367630958557,
+      "step": 784
+    },
+    {
+      "epoch": 0.33915857605177996,
+      "grad_norm": 0.5798251628875732,
+      "learning_rate": 0.00014106019766397124,
+      "loss": 0.9132505059242249,
+      "step": 786
+    },
+    {
+      "epoch": 0.34002157497303126,
+      "grad_norm": 0.6267077326774597,
+      "learning_rate": 0.00014141958670260557,
+      "loss": 0.9297707080841064,
+      "step": 788
+    },
+    {
+      "epoch": 0.3408845738942826,
+      "grad_norm": 0.6045349836349487,
+      "learning_rate": 0.0001417789757412399,
+      "loss": 0.9382412433624268,
+      "step": 790
+    },
+    {
+      "epoch": 0.341747572815534,
+      "grad_norm": 0.6125404834747314,
+      "learning_rate": 0.0001421383647798742,
+      "loss": 0.9078555107116699,
+      "step": 792
+    },
+    {
+      "epoch": 0.34261057173678533,
+      "grad_norm": 0.5927051901817322,
+      "learning_rate": 0.00014249775381850854,
+      "loss": 0.899101197719574,
+      "step": 794
+    },
+    {
+      "epoch": 0.3434735706580367,
+      "grad_norm": 0.6315743923187256,
+      "learning_rate": 0.00014285714285714287,
+      "loss": 1.028346300125122,
+      "step": 796
+    },
+    {
+      "epoch": 0.34433656957928804,
+      "grad_norm": 0.549271285533905,
+      "learning_rate": 0.0001432165318957772,
+      "loss": 0.8988189697265625,
+      "step": 798
+    },
+    {
+      "epoch": 0.3451995685005394,
+      "grad_norm": 0.6344245672225952,
+      "learning_rate": 0.0001435759209344115,
+      "loss": 1.0489003658294678,
+      "step": 800
+    },
+    {
+      "epoch": 0.3451995685005394,
+      "eval_loss": 0.9864639639854431,
+      "eval_runtime": 667.3516,
+      "eval_samples_per_second": 3.087,
+      "eval_steps_per_second": 3.087,
+      "step": 800
+    },
+    {
+      "epoch": 0.3460625674217907,
+      "grad_norm": 0.5625309348106384,
+      "learning_rate": 0.00014393530997304583,
+      "loss": 0.8773928284645081,
+      "step": 802
+    },
+    {
+      "epoch": 0.34692556634304206,
+      "grad_norm": 0.5931969285011292,
+      "learning_rate": 0.00014429469901168016,
+      "loss": 0.9116050004959106,
+      "step": 804
+    },
+    {
+      "epoch": 0.3477885652642934,
+      "grad_norm": 0.5189821720123291,
+      "learning_rate": 0.00014465408805031446,
+      "loss": 0.9124425649642944,
+      "step": 806
+    },
+    {
+      "epoch": 0.34865156418554477,
+      "grad_norm": 0.5392254590988159,
+      "learning_rate": 0.0001450134770889488,
+      "loss": 0.9517888426780701,
+      "step": 808
+    },
+    {
+      "epoch": 0.34951456310679613,
+      "grad_norm": 0.5584444999694824,
+      "learning_rate": 0.00014537286612758312,
+      "loss": 0.9947572350502014,
+      "step": 810
+    },
+    {
+      "epoch": 0.3503775620280475,
+      "grad_norm": 0.5188854932785034,
+      "learning_rate": 0.00014573225516621745,
+      "loss": 0.9314022660255432,
+      "step": 812
+    },
+    {
+      "epoch": 0.3512405609492988,
+      "grad_norm": 0.5783659815788269,
+      "learning_rate": 0.00014609164420485176,
+      "loss": 0.9135628938674927,
+      "step": 814
+    },
+    {
+      "epoch": 0.35210355987055014,
+      "grad_norm": 0.550959050655365,
+      "learning_rate": 0.0001464510332434861,
+      "loss": 0.9665075540542603,
+      "step": 816
+    },
+    {
+      "epoch": 0.3529665587918015,
+      "grad_norm": 0.6013346314430237,
+      "learning_rate": 0.00014681042228212042,
+      "loss": 0.9836555123329163,
+      "step": 818
+    },
+    {
+      "epoch": 0.35382955771305286,
+      "grad_norm": 0.49219194054603577,
+      "learning_rate": 0.00014716981132075472,
+      "loss": 0.8900108337402344,
+      "step": 820
+    },
+    {
+      "epoch": 0.3546925566343042,
+      "grad_norm": 0.5517411828041077,
+      "learning_rate": 0.00014752920035938905,
+      "loss": 0.8769304156303406,
+      "step": 822
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.6062695980072021,
+      "learning_rate": 0.00014788858939802338,
+      "loss": 0.9744759202003479,
+      "step": 824
+    },
+    {
+      "epoch": 0.3564185544768069,
+      "grad_norm": 0.5132041573524475,
+      "learning_rate": 0.0001482479784366577,
+      "loss": 0.8875447511672974,
+      "step": 826
+    },
+    {
+      "epoch": 0.3572815533980582,
+      "grad_norm": 0.551799476146698,
+      "learning_rate": 0.000148607367475292,
+      "loss": 0.962710440158844,
+      "step": 828
+    },
+    {
+      "epoch": 0.3581445523193096,
+      "grad_norm": 0.6046625971794128,
+      "learning_rate": 0.00014896675651392634,
+      "loss": 0.8997528553009033,
+      "step": 830
+    },
+    {
+      "epoch": 0.35900755124056094,
+      "grad_norm": 0.560025691986084,
+      "learning_rate": 0.00014932614555256067,
+      "loss": 0.9541417360305786,
+      "step": 832
+    },
+    {
+      "epoch": 0.3598705501618123,
+      "grad_norm": 0.6441047787666321,
+      "learning_rate": 0.00014968553459119498,
+      "loss": 0.907791018486023,
+      "step": 834
+    },
+    {
+      "epoch": 0.36073354908306365,
+      "grad_norm": 0.5636281967163086,
+      "learning_rate": 0.0001500449236298293,
+      "loss": 1.0295937061309814,
+      "step": 836
+    },
+    {
+      "epoch": 0.361596548004315,
+      "grad_norm": 0.5528303384780884,
+      "learning_rate": 0.0001504043126684636,
+      "loss": 0.8875265717506409,
+      "step": 838
+    },
+    {
+      "epoch": 0.36245954692556637,
+      "grad_norm": 0.5345163345336914,
+      "learning_rate": 0.00015076370170709794,
+      "loss": 0.9678915739059448,
+      "step": 840
+    },
+    {
+      "epoch": 0.36332254584681767,
+      "grad_norm": 0.5551225543022156,
+      "learning_rate": 0.00015112309074573224,
+      "loss": 0.9235162734985352,
+      "step": 842
+    },
+    {
+      "epoch": 0.364185544768069,
+      "grad_norm": 0.5131904482841492,
+      "learning_rate": 0.00015148247978436657,
+      "loss": 0.8624292016029358,
+      "step": 844
+    },
+    {
+      "epoch": 0.3650485436893204,
+      "grad_norm": 0.6811004281044006,
+      "learning_rate": 0.0001518418688230009,
+      "loss": 1.0360193252563477,
+      "step": 846
+    },
+    {
+      "epoch": 0.36591154261057174,
+      "grad_norm": 0.6409741640090942,
+      "learning_rate": 0.00015220125786163523,
+      "loss": 0.9254010915756226,
+      "step": 848
+    },
+    {
+      "epoch": 0.3667745415318231,
+      "grad_norm": 0.5534068942070007,
+      "learning_rate": 0.00015256064690026953,
+      "loss": 0.8900630474090576,
+      "step": 850
+    },
+    {
+      "epoch": 0.36763754045307445,
+      "grad_norm": 0.4999487102031708,
+      "learning_rate": 0.00015292003593890386,
+      "loss": 0.88521409034729,
+      "step": 852
+    },
+    {
+      "epoch": 0.3685005393743258,
+      "grad_norm": 0.5805923938751221,
+      "learning_rate": 0.0001532794249775382,
+      "loss": 0.9563921093940735,
+      "step": 854
+    },
+    {
+      "epoch": 0.3693635382955771,
+      "grad_norm": 0.5485470294952393,
+      "learning_rate": 0.0001536388140161725,
+      "loss": 0.8909372687339783,
+      "step": 856
+    },
+    {
+      "epoch": 0.37022653721682847,
+      "grad_norm": 0.5317923426628113,
+      "learning_rate": 0.00015399820305480683,
+      "loss": 0.9145731925964355,
+      "step": 858
+    },
+    {
+      "epoch": 0.3710895361380798,
+      "grad_norm": 0.6073495745658875,
+      "learning_rate": 0.00015435759209344116,
+      "loss": 1.01466965675354,
+      "step": 860
+    },
+    {
+      "epoch": 0.3719525350593312,
+      "grad_norm": 0.566655158996582,
+      "learning_rate": 0.0001547169811320755,
+      "loss": 0.9941825270652771,
+      "step": 862
+    },
+    {
+      "epoch": 0.37281553398058254,
+      "grad_norm": 0.5262459516525269,
+      "learning_rate": 0.0001550763701707098,
+      "loss": 1.0059782266616821,
+      "step": 864
+    },
+    {
+      "epoch": 0.3736785329018339,
+      "grad_norm": 0.6264083981513977,
+      "learning_rate": 0.00015543575920934412,
+      "loss": 1.0332856178283691,
+      "step": 866
+    },
+    {
+      "epoch": 0.3745415318230852,
+      "grad_norm": 0.6575480699539185,
+      "learning_rate": 0.00015579514824797845,
+      "loss": 1.022459626197815,
+      "step": 868
+    },
+    {
+      "epoch": 0.37540453074433655,
+      "grad_norm": 0.6291940212249756,
+      "learning_rate": 0.00015615453728661275,
+      "loss": 0.9550372362136841,
+      "step": 870
+    },
+    {
+      "epoch": 0.3762675296655879,
+      "grad_norm": 0.6710562109947205,
+      "learning_rate": 0.00015651392632524708,
+      "loss": 0.9861716628074646,
+      "step": 872
+    },
+    {
+      "epoch": 0.37713052858683926,
+      "grad_norm": 0.5505748987197876,
+      "learning_rate": 0.0001568733153638814,
+      "loss": 0.9719111919403076,
+      "step": 874
+    },
+    {
+      "epoch": 0.3779935275080906,
+      "grad_norm": 0.5055180788040161,
+      "learning_rate": 0.00015723270440251574,
+      "loss": 0.8698170185089111,
+      "step": 876
+    },
+    {
+      "epoch": 0.378856526429342,
+      "grad_norm": 0.5935947895050049,
+      "learning_rate": 0.00015759209344115005,
+      "loss": 1.029494285583496,
+      "step": 878
+    },
+    {
+      "epoch": 0.37971952535059333,
+      "grad_norm": 0.538325846195221,
+      "learning_rate": 0.00015795148247978438,
+      "loss": 0.923010528087616,
+      "step": 880
+    },
+    {
+      "epoch": 0.38058252427184464,
+      "grad_norm": 0.587297797203064,
+      "learning_rate": 0.0001583108715184187,
+      "loss": 0.9394056797027588,
+      "step": 882
+    },
+    {
+      "epoch": 0.381445523193096,
+      "grad_norm": 0.5910462737083435,
+      "learning_rate": 0.000158670260557053,
+      "loss": 0.9472483992576599,
+      "step": 884
+    },
+    {
+      "epoch": 0.38230852211434735,
+      "grad_norm": 0.629048764705658,
+      "learning_rate": 0.00015902964959568734,
+      "loss": 0.9028263688087463,
+      "step": 886
+    },
+    {
+      "epoch": 0.3831715210355987,
+      "grad_norm": 0.5028086304664612,
+      "learning_rate": 0.00015938903863432167,
+      "loss": 0.9579087495803833,
+      "step": 888
+    },
+    {
+      "epoch": 0.38403451995685006,
+      "grad_norm": 0.5372384190559387,
+      "learning_rate": 0.000159748427672956,
+      "loss": 0.8318673372268677,
+      "step": 890
+    },
+    {
+      "epoch": 0.3848975188781014,
+      "grad_norm": 0.6314184665679932,
+      "learning_rate": 0.0001601078167115903,
+      "loss": 0.9804943203926086,
+      "step": 892
+    },
+    {
+      "epoch": 0.3857605177993528,
+      "grad_norm": 0.5545229911804199,
+      "learning_rate": 0.00016046720575022463,
+      "loss": 1.0078438520431519,
+      "step": 894
+    },
+    {
+      "epoch": 0.3866235167206041,
+      "grad_norm": 0.4674014151096344,
+      "learning_rate": 0.00016082659478885896,
+      "loss": 0.9269036650657654,
+      "step": 896
+    },
+    {
+      "epoch": 0.38748651564185543,
+      "grad_norm": 1.5887153148651123,
+      "learning_rate": 0.00016118598382749326,
+      "loss": 0.8927953243255615,
+      "step": 898
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "grad_norm": 0.5217035412788391,
+      "learning_rate": 0.0001615453728661276,
+      "loss": 0.908074140548706,
+      "step": 900
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "eval_loss": 0.9741895794868469,
+      "eval_runtime": 667.2236,
+      "eval_samples_per_second": 3.087,
+      "eval_steps_per_second": 3.087,
+      "step": 900
+    },
+    {
+      "epoch": 0.38921251348435815,
+      "grad_norm": 0.470498651266098,
+      "learning_rate": 0.00016190476190476192,
+      "loss": 0.9660369157791138,
+      "step": 902
+    },
+    {
+      "epoch": 0.3900755124056095,
+      "grad_norm": 0.5111004114151001,
+      "learning_rate": 0.00016226415094339625,
+      "loss": 0.9236379265785217,
+      "step": 904
+    },
+    {
+      "epoch": 0.39093851132686086,
+      "grad_norm": 0.5872815251350403,
+      "learning_rate": 0.00016262353998203056,
+      "loss": 1.0061595439910889,
+      "step": 906
+    },
+    {
+      "epoch": 0.3918015102481122,
+      "grad_norm": 0.5150740742683411,
+      "learning_rate": 0.0001629829290206649,
+      "loss": 0.8347328901290894,
+      "step": 908
+    },
+    {
+      "epoch": 0.3926645091693635,
+      "grad_norm": 0.46554985642433167,
+      "learning_rate": 0.00016334231805929922,
+      "loss": 0.9091183543205261,
+      "step": 910
+    },
+    {
+      "epoch": 0.3935275080906149,
+      "grad_norm": 0.5292875170707703,
+      "learning_rate": 0.00016370170709793352,
+      "loss": 0.9299798011779785,
+      "step": 912
+    },
+    {
+      "epoch": 0.39439050701186623,
+      "grad_norm": 0.5177125930786133,
+      "learning_rate": 0.00016406109613656785,
+      "loss": 0.942286491394043,
+      "step": 914
+    },
+    {
+      "epoch": 0.3952535059331176,
+      "grad_norm": 0.5564161539077759,
+      "learning_rate": 0.00016442048517520215,
+      "loss": 0.825290858745575,
+      "step": 916
+    },
+    {
+      "epoch": 0.39611650485436894,
+      "grad_norm": 0.5572530031204224,
+      "learning_rate": 0.00016477987421383648,
+      "loss": 0.876898467540741,
+      "step": 918
+    },
+    {
+      "epoch": 0.3969795037756203,
+      "grad_norm": 0.7294673323631287,
+      "learning_rate": 0.0001651392632524708,
+      "loss": 0.8949798941612244,
+      "step": 920
+    },
+    {
+      "epoch": 0.3978425026968716,
+      "grad_norm": 0.5234251022338867,
+      "learning_rate": 0.00016549865229110512,
+      "loss": 0.8457819223403931,
+      "step": 922
+    },
+    {
+      "epoch": 0.39870550161812296,
+      "grad_norm": 0.5273709893226624,
+      "learning_rate": 0.00016585804132973945,
+      "loss": 0.9080174565315247,
+      "step": 924
+    },
+    {
+      "epoch": 0.3995685005393743,
+      "grad_norm": 0.5795063376426697,
+      "learning_rate": 0.00016621743036837378,
+      "loss": 1.0304023027420044,
+      "step": 926
+    },
+    {
+      "epoch": 0.4004314994606257,
+      "grad_norm": 0.6153313517570496,
+      "learning_rate": 0.00016657681940700808,
+      "loss": 0.8900477886199951,
+      "step": 928
+    },
+    {
+      "epoch": 0.40129449838187703,
+      "grad_norm": 0.6293173432350159,
+      "learning_rate": 0.0001669362084456424,
+      "loss": 1.0130009651184082,
+      "step": 930
+    },
+    {
+      "epoch": 0.4021574973031284,
+      "grad_norm": 0.5455223321914673,
+      "learning_rate": 0.00016729559748427674,
+      "loss": 0.9339282512664795,
+      "step": 932
+    },
+    {
+      "epoch": 0.40302049622437974,
+      "grad_norm": 0.5349094271659851,
+      "learning_rate": 0.00016765498652291104,
+      "loss": 0.9628980755805969,
+      "step": 934
+    },
+    {
+      "epoch": 0.40388349514563104,
+      "grad_norm": 0.491227924823761,
+      "learning_rate": 0.00016801437556154537,
+      "loss": 0.8922860026359558,
+      "step": 936
+    },
+    {
+      "epoch": 0.4047464940668824,
+      "grad_norm": 0.6331246495246887,
+      "learning_rate": 0.0001683737646001797,
+      "loss": 1.0470497608184814,
+      "step": 938
+    },
+    {
+      "epoch": 0.40560949298813376,
+      "grad_norm": 0.6079246401786804,
+      "learning_rate": 0.00016873315363881403,
+      "loss": 0.8868283629417419,
+      "step": 940
+    },
+    {
+      "epoch": 0.4064724919093851,
+      "grad_norm": 0.5326972603797913,
+      "learning_rate": 0.00016909254267744833,
+      "loss": 0.9938711524009705,
+      "step": 942
+    },
+    {
+      "epoch": 0.40733549083063647,
+      "grad_norm": 0.47754305601119995,
+      "learning_rate": 0.00016945193171608266,
+      "loss": 0.8280484676361084,
+      "step": 944
+    },
+    {
+      "epoch": 0.4081984897518878,
+      "grad_norm": 0.6683310270309448,
+      "learning_rate": 0.000169811320754717,
+      "loss": 1.089701533317566,
+      "step": 946
+    },
+    {
+      "epoch": 0.4090614886731392,
+      "grad_norm": 0.42798754572868347,
+      "learning_rate": 0.0001701707097933513,
+      "loss": 0.8535542488098145,
+      "step": 948
+    },
+    {
+      "epoch": 0.4099244875943905,
+      "grad_norm": 0.5999574065208435,
+      "learning_rate": 0.00017053009883198563,
+      "loss": 0.9039298295974731,
+      "step": 950
+    },
+    {
+      "epoch": 0.41078748651564184,
+      "grad_norm": 0.5752781629562378,
+      "learning_rate": 0.00017088948787061996,
+      "loss": 0.8786448240280151,
+      "step": 952
+    },
+    {
+      "epoch": 0.4116504854368932,
+      "grad_norm": 0.5121532678604126,
+      "learning_rate": 0.0001712488769092543,
+      "loss": 0.9206072688102722,
+      "step": 954
+    },
+    {
+      "epoch": 0.41251348435814456,
+      "grad_norm": 0.611078143119812,
+      "learning_rate": 0.0001716082659478886,
+      "loss": 0.9246986508369446,
+      "step": 956
+    },
+    {
+      "epoch": 0.4133764832793959,
+      "grad_norm": 0.5101020336151123,
+      "learning_rate": 0.00017196765498652292,
+      "loss": 0.9221894145011902,
+      "step": 958
+    },
+    {
+      "epoch": 0.41423948220064727,
+      "grad_norm": 0.5681450963020325,
+      "learning_rate": 0.00017232704402515725,
+      "loss": 0.9072799682617188,
+      "step": 960
+    },
+    {
+      "epoch": 0.41510248112189857,
+      "grad_norm": 0.47865498065948486,
+      "learning_rate": 0.00017268643306379155,
+      "loss": 0.9460896849632263,
+      "step": 962
+    },
+    {
+      "epoch": 0.4159654800431499,
+      "grad_norm": 0.49861401319503784,
+      "learning_rate": 0.00017304582210242588,
+      "loss": 0.9121519923210144,
+      "step": 964
+    },
+    {
+      "epoch": 0.4168284789644013,
+      "grad_norm": 0.43025892972946167,
+      "learning_rate": 0.0001734052111410602,
+      "loss": 0.8826848864555359,
+      "step": 966
+    },
+    {
+      "epoch": 0.41769147788565264,
+      "grad_norm": 0.4600491225719452,
+      "learning_rate": 0.00017376460017969454,
+      "loss": 0.8756251335144043,
+      "step": 968
+    },
+    {
+      "epoch": 0.418554476806904,
+      "grad_norm": 0.5297656059265137,
+      "learning_rate": 0.00017412398921832885,
+      "loss": 0.9171333312988281,
+      "step": 970
+    },
+    {
+      "epoch": 0.41941747572815535,
+      "grad_norm": 0.4906919002532959,
+      "learning_rate": 0.00017448337825696318,
+      "loss": 0.8887524008750916,
+      "step": 972
+    },
+    {
+      "epoch": 0.4202804746494067,
+      "grad_norm": 0.49263402819633484,
+      "learning_rate": 0.0001748427672955975,
+      "loss": 0.8345810174942017,
+      "step": 974
+    },
+    {
+      "epoch": 0.421143473570658,
+      "grad_norm": 0.5706565380096436,
+      "learning_rate": 0.0001752021563342318,
+      "loss": 0.968651294708252,
+      "step": 976
+    },
+    {
+      "epoch": 0.42200647249190937,
+      "grad_norm": 0.5269908308982849,
+      "learning_rate": 0.00017556154537286614,
+      "loss": 0.9729376435279846,
+      "step": 978
+    },
+    {
+      "epoch": 0.4228694714131607,
+      "grad_norm": 0.47058001160621643,
+      "learning_rate": 0.00017592093441150047,
+      "loss": 0.963884711265564,
+      "step": 980
+    },
+    {
+      "epoch": 0.4237324703344121,
+      "grad_norm": 0.5322962999343872,
+      "learning_rate": 0.0001762803234501348,
+      "loss": 0.8952447175979614,
+      "step": 982
+    },
+    {
+      "epoch": 0.42459546925566344,
+      "grad_norm": 0.5750975012779236,
+      "learning_rate": 0.0001766397124887691,
+      "loss": 0.8932783603668213,
+      "step": 984
+    },
+    {
+      "epoch": 0.4254584681769148,
+      "grad_norm": 0.5539655685424805,
+      "learning_rate": 0.00017699910152740343,
+      "loss": 0.916595458984375,
+      "step": 986
+    },
+    {
+      "epoch": 0.42632146709816615,
+      "grad_norm": 0.568000853061676,
+      "learning_rate": 0.00017735849056603776,
+      "loss": 0.9669626355171204,
+      "step": 988
+    },
+    {
+      "epoch": 0.42718446601941745,
+      "grad_norm": 0.6010684370994568,
+      "learning_rate": 0.00017771787960467206,
+      "loss": 1.0089105367660522,
+      "step": 990
+    },
+    {
+      "epoch": 0.4280474649406688,
+      "grad_norm": 0.6083462238311768,
+      "learning_rate": 0.0001780772686433064,
+      "loss": 0.9810921549797058,
+      "step": 992
+    },
+    {
+      "epoch": 0.42891046386192017,
+      "grad_norm": 0.5076655149459839,
+      "learning_rate": 0.0001784366576819407,
+      "loss": 0.9524372816085815,
+      "step": 994
+    },
+    {
+      "epoch": 0.4297734627831715,
+      "grad_norm": 0.5260922312736511,
+      "learning_rate": 0.00017879604672057503,
+      "loss": 0.881294846534729,
+      "step": 996
+    },
+    {
+      "epoch": 0.4306364617044229,
+      "grad_norm": 0.6130498051643372,
+      "learning_rate": 0.00017915543575920936,
+      "loss": 0.9138327836990356,
+      "step": 998
+    },
+    {
+      "epoch": 0.43149946062567424,
+      "grad_norm": 0.5346242785453796,
+      "learning_rate": 0.00017951482479784366,
+      "loss": 0.8861367106437683,
+      "step": 1000
+    },
+    {
+      "epoch": 0.43149946062567424,
+      "eval_loss": 0.9606748819351196,
+      "eval_runtime": 655.4358,
+      "eval_samples_per_second": 3.143,
+      "eval_steps_per_second": 3.143,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4323624595469256,
+      "grad_norm": 0.5977228879928589,
+      "learning_rate": 0.000179874213836478,
+      "loss": 0.8711628913879395,
+      "step": 1002
+    },
+    {
+      "epoch": 0.4332254584681769,
+      "grad_norm": 0.5547866821289062,
+      "learning_rate": 0.00018023360287511232,
+      "loss": 0.9393253326416016,
+      "step": 1004
+    },
+    {
+      "epoch": 0.43408845738942825,
+      "grad_norm": 0.536856472492218,
+      "learning_rate": 0.00018059299191374662,
+      "loss": 0.9486003518104553,
+      "step": 1006
+    },
+    {
+      "epoch": 0.4349514563106796,
+      "grad_norm": 0.4769814610481262,
+      "learning_rate": 0.00018095238095238095,
+      "loss": 0.9042052030563354,
+      "step": 1008
+    },
+    {
+      "epoch": 0.43581445523193096,
+      "grad_norm": 0.5554604530334473,
+      "learning_rate": 0.00018131176999101528,
+      "loss": 0.978546142578125,
+      "step": 1010
+    },
+    {
+      "epoch": 0.4366774541531823,
+      "grad_norm": 0.5112947225570679,
+      "learning_rate": 0.00018167115902964959,
+      "loss": 0.8382073640823364,
+      "step": 1012
+    },
+    {
+      "epoch": 0.4375404530744337,
+      "grad_norm": 0.45194941759109497,
+      "learning_rate": 0.00018203054806828392,
+      "loss": 0.8577026724815369,
+      "step": 1014
+    },
+    {
+      "epoch": 0.438403451995685,
+      "grad_norm": 0.5115043520927429,
+      "learning_rate": 0.00018238993710691825,
+      "loss": 0.8517863154411316,
+      "step": 1016
+    },
+    {
+      "epoch": 0.43926645091693634,
+      "grad_norm": 0.5485050082206726,
+      "learning_rate": 0.00018274932614555258,
+      "loss": 0.9597266912460327,
+      "step": 1018
+    },
+    {
+      "epoch": 0.4401294498381877,
+      "grad_norm": 0.5742959976196289,
+      "learning_rate": 0.00018310871518418688,
+      "loss": 1.0407187938690186,
+      "step": 1020
+    },
+    {
+      "epoch": 0.44099244875943905,
+      "grad_norm": 0.44870051741600037,
+      "learning_rate": 0.0001834681042228212,
+      "loss": 0.8696310520172119,
+      "step": 1022
+    },
+    {
+      "epoch": 0.4418554476806904,
+      "grad_norm": 0.5179623961448669,
+      "learning_rate": 0.00018382749326145554,
+      "loss": 0.9673634767532349,
+      "step": 1024
+    },
+    {
+      "epoch": 0.44271844660194176,
+      "grad_norm": 0.5404779314994812,
+      "learning_rate": 0.00018418688230008984,
+      "loss": 0.9596615433692932,
+      "step": 1026
+    },
+    {
+      "epoch": 0.4435814455231931,
+      "grad_norm": 0.47766315937042236,
+      "learning_rate": 0.00018454627133872417,
+      "loss": 0.8483878970146179,
+      "step": 1028
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.503380537033081,
+      "learning_rate": 0.0001849056603773585,
+      "loss": 0.9330979585647583,
+      "step": 1030
+    },
+    {
+      "epoch": 0.4453074433656958,
+      "grad_norm": 0.6129396557807922,
+      "learning_rate": 0.00018526504941599283,
+      "loss": 0.9341012239456177,
+      "step": 1032
+    },
+    {
+      "epoch": 0.44617044228694713,
+      "grad_norm": 0.4497876465320587,
+      "learning_rate": 0.00018562443845462713,
+      "loss": 0.9139068126678467,
+      "step": 1034
+    },
+    {
+      "epoch": 0.4470334412081985,
+      "grad_norm": 0.5369747281074524,
+      "learning_rate": 0.00018598382749326146,
+      "loss": 0.8874827027320862,
+      "step": 1036
+    },
+    {
+      "epoch": 0.44789644012944985,
+      "grad_norm": 0.5947322845458984,
+      "learning_rate": 0.0001863432165318958,
+      "loss": 0.9653725028038025,
+      "step": 1038
+    },
+    {
+      "epoch": 0.4487594390507012,
+      "grad_norm": 0.6649987101554871,
+      "learning_rate": 0.0001867026055705301,
+      "loss": 0.9553119540214539,
+      "step": 1040
+    },
+    {
+      "epoch": 0.44962243797195256,
+      "grad_norm": 0.5369387269020081,
+      "learning_rate": 0.00018706199460916443,
+      "loss": 0.904233992099762,
+      "step": 1042
+    },
+    {
+      "epoch": 0.45048543689320386,
+      "grad_norm": 0.4956842362880707,
+      "learning_rate": 0.00018742138364779876,
+      "loss": 0.8837952017784119,
+      "step": 1044
+    },
+    {
+      "epoch": 0.4513484358144552,
+      "grad_norm": 0.48045051097869873,
+      "learning_rate": 0.0001877807726864331,
+      "loss": 0.8964687585830688,
+      "step": 1046
+    },
+    {
+      "epoch": 0.4522114347357066,
+      "grad_norm": 0.4925530254840851,
+      "learning_rate": 0.0001881401617250674,
+      "loss": 0.9105878472328186,
+      "step": 1048
+    },
+    {
+      "epoch": 0.45307443365695793,
+      "grad_norm": 0.5131362080574036,
+      "learning_rate": 0.00018849955076370172,
+      "loss": 0.96272873878479,
+      "step": 1050
+    },
+    {
+      "epoch": 0.4539374325782093,
+      "grad_norm": 0.435739129781723,
+      "learning_rate": 0.00018885893980233605,
+      "loss": 0.8796783685684204,
+      "step": 1052
+    },
+    {
+      "epoch": 0.45480043149946064,
+      "grad_norm": 0.500938892364502,
+      "learning_rate": 0.00018921832884097035,
+      "loss": 0.9463814496994019,
+      "step": 1054
+    },
+    {
+      "epoch": 0.455663430420712,
+      "grad_norm": 0.4769900143146515,
+      "learning_rate": 0.00018957771787960468,
+      "loss": 0.9030335545539856,
+      "step": 1056
+    },
+    {
+      "epoch": 0.4565264293419633,
+      "grad_norm": 0.49585285782814026,
+      "learning_rate": 0.00018993710691823901,
+      "loss": 0.986995279788971,
+      "step": 1058
+    },
+    {
+      "epoch": 0.45738942826321466,
+      "grad_norm": 0.5875195264816284,
+      "learning_rate": 0.00019029649595687334,
+      "loss": 0.9297246932983398,
+      "step": 1060
+    },
+    {
+      "epoch": 0.458252427184466,
+      "grad_norm": 0.5552583932876587,
+      "learning_rate": 0.00019065588499550765,
+      "loss": 1.005869746208191,
+      "step": 1062
+    },
+    {
+      "epoch": 0.4591154261057174,
+      "grad_norm": 0.49282076954841614,
+      "learning_rate": 0.00019101527403414198,
+      "loss": 0.8949927091598511,
+      "step": 1064
+    },
+    {
+      "epoch": 0.45997842502696873,
+      "grad_norm": 0.4951777160167694,
+      "learning_rate": 0.0001913746630727763,
+      "loss": 0.9997886419296265,
+      "step": 1066
+    },
+    {
+      "epoch": 0.4608414239482201,
+      "grad_norm": 0.5154827237129211,
+      "learning_rate": 0.0001917340521114106,
+      "loss": 0.9532123804092407,
+      "step": 1068
+    },
+    {
+      "epoch": 0.4617044228694714,
+      "grad_norm": 0.5547500252723694,
+      "learning_rate": 0.00019209344115004494,
+      "loss": 0.8959843516349792,
+      "step": 1070
+    },
+    {
+      "epoch": 0.46256742179072274,
+      "grad_norm": 0.500188946723938,
+      "learning_rate": 0.00019245283018867927,
+      "loss": 0.8201484680175781,
+      "step": 1072
+    },
+    {
+      "epoch": 0.4634304207119741,
+      "grad_norm": 0.4181794822216034,
+      "learning_rate": 0.00019281221922731357,
+      "loss": 0.8255136609077454,
+      "step": 1074
+    },
+    {
+      "epoch": 0.46429341963322546,
+      "grad_norm": 0.5613874197006226,
+      "learning_rate": 0.0001931716082659479,
+      "loss": 0.896024763584137,
+      "step": 1076
+    },
+    {
+      "epoch": 0.4651564185544768,
+      "grad_norm": 0.5000972151756287,
+      "learning_rate": 0.0001935309973045822,
+      "loss": 0.8831873536109924,
+      "step": 1078
+    },
+    {
+      "epoch": 0.46601941747572817,
+      "grad_norm": 0.6321820616722107,
+      "learning_rate": 0.00019389038634321654,
+      "loss": 0.9787988662719727,
+      "step": 1080
+    },
+    {
+      "epoch": 0.4668824163969795,
+      "grad_norm": 0.4843652546405792,
+      "learning_rate": 0.00019424977538185087,
+      "loss": 0.933361828327179,
+      "step": 1082
+    },
+    {
+      "epoch": 0.46774541531823083,
+      "grad_norm": 0.537330150604248,
+      "learning_rate": 0.00019460916442048517,
+      "loss": 0.9046981334686279,
+      "step": 1084
+    },
+    {
+      "epoch": 0.4686084142394822,
+      "grad_norm": 0.5761371850967407,
+      "learning_rate": 0.0001949685534591195,
+      "loss": 0.9625781178474426,
+      "step": 1086
+    },
+    {
+      "epoch": 0.46947141316073354,
+      "grad_norm": 0.5209522843360901,
+      "learning_rate": 0.00019532794249775383,
+      "loss": 0.9280619025230408,
+      "step": 1088
+    },
+    {
+      "epoch": 0.4703344120819849,
+      "grad_norm": 0.5383933186531067,
+      "learning_rate": 0.00019568733153638813,
+      "loss": 0.8236247301101685,
+      "step": 1090
+    },
+    {
+      "epoch": 0.47119741100323626,
+      "grad_norm": 0.4994274377822876,
+      "learning_rate": 0.00019604672057502246,
+      "loss": 0.9404071569442749,
+      "step": 1092
+    },
+    {
+      "epoch": 0.4720604099244876,
+      "grad_norm": 0.5177807211875916,
+      "learning_rate": 0.0001964061096136568,
+      "loss": 0.8517536520957947,
+      "step": 1094
+    },
+    {
+      "epoch": 0.47292340884573897,
+      "grad_norm": 0.5374870896339417,
+      "learning_rate": 0.00019676549865229112,
+      "loss": 0.8214367032051086,
+      "step": 1096
+    },
+    {
+      "epoch": 0.47378640776699027,
+      "grad_norm": 0.5544074177742004,
+      "learning_rate": 0.00019712488769092542,
+      "loss": 1.016176700592041,
+      "step": 1098
+    },
+    {
+      "epoch": 0.4746494066882416,
+      "grad_norm": 0.5125867128372192,
+      "learning_rate": 0.00019748427672955975,
+      "loss": 0.8425421118736267,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4746494066882416,
+      "eval_loss": 0.944629430770874,
+      "eval_runtime": 649.9107,
+      "eval_samples_per_second": 3.17,
+      "eval_steps_per_second": 3.17,
+      "step": 1100
+    },
+    {
+      "epoch": 0.475512405609493,
+      "grad_norm": 0.5204418897628784,
+      "learning_rate": 0.00019784366576819408,
+      "loss": 0.9444556832313538,
+      "step": 1102
+    },
+    {
+      "epoch": 0.47637540453074434,
+      "grad_norm": 0.46085885167121887,
+      "learning_rate": 0.0001982030548068284,
+      "loss": 0.877082109451294,
+      "step": 1104
+    },
+    {
+      "epoch": 0.4772384034519957,
+      "grad_norm": 0.5269598960876465,
+      "learning_rate": 0.00019856244384546272,
+      "loss": 0.9214640259742737,
+      "step": 1106
+    },
+    {
+      "epoch": 0.47810140237324705,
+      "grad_norm": 0.4894753694534302,
+      "learning_rate": 0.00019892183288409705,
+      "loss": 0.8867175579071045,
+      "step": 1108
+    },
+    {
+      "epoch": 0.47896440129449835,
+      "grad_norm": 0.5204115509986877,
+      "learning_rate": 0.00019928122192273138,
+      "loss": 0.9641162753105164,
+      "step": 1110
+    },
+    {
+      "epoch": 0.4798274002157497,
+      "grad_norm": 0.6399031281471252,
+      "learning_rate": 0.00019964061096136568,
+      "loss": 1.0219199657440186,
+      "step": 1112
+    },
+    {
+      "epoch": 0.48069039913700107,
+      "grad_norm": 0.3979159891605377,
+      "learning_rate": 0.0002,
+      "loss": 0.8189998269081116,
+      "step": 1114
+    },
+    {
+      "epoch": 0.4815533980582524,
+      "grad_norm": 0.4782681465148926,
+      "learning_rate": 0.0001999999879427254,
+      "loss": 0.83241868019104,
+      "step": 1116
+    },
+    {
+      "epoch": 0.4824163969795038,
+      "grad_norm": 0.5235620141029358,
+      "learning_rate": 0.00019999995177090454,
+      "loss": 0.9371466636657715,
+      "step": 1118
+    },
+    {
+      "epoch": 0.48327939590075514,
+      "grad_norm": 0.4543023407459259,
+      "learning_rate": 0.00019999989148454606,
+      "loss": 0.7767758369445801,
+      "step": 1120
+    },
+    {
+      "epoch": 0.4841423948220065,
+      "grad_norm": 0.6191229820251465,
+      "learning_rate": 0.00019999980708366457,
+      "loss": 1.0103063583374023,
+      "step": 1122
+    },
+    {
+      "epoch": 0.4850053937432578,
+      "grad_norm": 0.45392486453056335,
+      "learning_rate": 0.00019999969856828042,
+      "loss": 0.8720875382423401,
+      "step": 1124
+    },
+    {
+      "epoch": 0.48586839266450915,
+      "grad_norm": 0.42748701572418213,
+      "learning_rate": 0.00019999956593841974,
+      "loss": 0.7859150171279907,
+      "step": 1126
+    },
+    {
+      "epoch": 0.4867313915857605,
+      "grad_norm": 0.4952569603919983,
+      "learning_rate": 0.00019999940919411454,
+      "loss": 0.9154419898986816,
+      "step": 1128
+    },
+    {
+      "epoch": 0.48759439050701187,
+      "grad_norm": 0.5522173047065735,
+      "learning_rate": 0.00019999922833540264,
+      "loss": 0.9076330065727234,
+      "step": 1130
+    },
+    {
+      "epoch": 0.4884573894282632,
+      "grad_norm": 0.5355855226516724,
+      "learning_rate": 0.00019999902336232758,
+      "loss": 0.8933543562889099,
+      "step": 1132
+    },
+    {
+      "epoch": 0.4893203883495146,
+      "grad_norm": 0.4613489508628845,
+      "learning_rate": 0.00019999879427493885,
+      "loss": 0.9160735607147217,
+      "step": 1134
+    },
+    {
+      "epoch": 0.49018338727076594,
+      "grad_norm": 0.4758962094783783,
+      "learning_rate": 0.0001999985410732917,
+      "loss": 0.8552446961402893,
+      "step": 1136
+    },
+    {
+      "epoch": 0.49104638619201724,
+      "grad_norm": 0.4549376964569092,
+      "learning_rate": 0.00019999826375744715,
+      "loss": 0.9979530572891235,
+      "step": 1138
+    },
+    {
+      "epoch": 0.4919093851132686,
+      "grad_norm": 0.4363284409046173,
+      "learning_rate": 0.0001999979623274721,
+      "loss": 0.9295380115509033,
+      "step": 1140
+    },
+    {
+      "epoch": 0.49277238403451995,
+      "grad_norm": 0.5090877413749695,
+      "learning_rate": 0.0001999976367834392,
+      "loss": 0.8737252950668335,
+      "step": 1142
+    },
+    {
+      "epoch": 0.4936353829557713,
+      "grad_norm": 0.45340779423713684,
+      "learning_rate": 0.000199997287125427,
+      "loss": 0.8312779068946838,
+      "step": 1144
+    },
+    {
+      "epoch": 0.49449838187702266,
+      "grad_norm": 0.4771472215652466,
+      "learning_rate": 0.0001999969133535198,
+      "loss": 0.9105207324028015,
+      "step": 1146
+    },
+    {
+      "epoch": 0.495361380798274,
+      "grad_norm": 0.5251384377479553,
+      "learning_rate": 0.00019999651546780773,
+      "loss": 0.8578172922134399,
+      "step": 1148
+    },
+    {
+      "epoch": 0.4962243797195254,
+      "grad_norm": 0.49128198623657227,
+      "learning_rate": 0.00019999609346838676,
+      "loss": 0.9193941950798035,
+      "step": 1150
+    },
+    {
+      "epoch": 0.4970873786407767,
+      "grad_norm": 0.5558596849441528,
+      "learning_rate": 0.0001999956473553586,
+      "loss": 0.9141314625740051,
+      "step": 1152
+    },
+    {
+      "epoch": 0.49795037756202803,
+      "grad_norm": 0.45872750878334045,
+      "learning_rate": 0.00019999517712883087,
+      "loss": 0.9058388471603394,
+      "step": 1154
+    },
+    {
+      "epoch": 0.4988133764832794,
+      "grad_norm": 0.4710173010826111,
+      "learning_rate": 0.00019999468278891698,
+      "loss": 0.8462487459182739,
+      "step": 1156
+    },
+    {
+      "epoch": 0.49967637540453075,
+      "grad_norm": 0.4805637001991272,
+      "learning_rate": 0.0001999941643357361,
+      "loss": 0.8960906863212585,
+      "step": 1158
+    },
+    {
+      "epoch": 0.5005393743257821,
+      "grad_norm": 0.5108052492141724,
+      "learning_rate": 0.00019999362176941325,
+      "loss": 0.9074980020523071,
+      "step": 1160
+    },
+    {
+      "epoch": 0.5014023732470334,
+      "grad_norm": 0.49572333693504333,
+      "learning_rate": 0.00019999305509007932,
+      "loss": 0.9710080623626709,
+      "step": 1162
+    },
+    {
+      "epoch": 0.5022653721682848,
+      "grad_norm": 0.5304561257362366,
+      "learning_rate": 0.0001999924642978709,
+      "loss": 0.8877825140953064,
+      "step": 1164
+    },
+    {
+      "epoch": 0.5031283710895361,
+      "grad_norm": 0.5007328391075134,
+      "learning_rate": 0.0001999918493929305,
+      "loss": 0.8955381512641907,
+      "step": 1166
+    },
+    {
+      "epoch": 0.5039913700107875,
+      "grad_norm": 0.569549024105072,
+      "learning_rate": 0.0001999912103754064,
+      "loss": 0.9478562474250793,
+      "step": 1168
+    },
+    {
+      "epoch": 0.5048543689320388,
+      "grad_norm": 0.5354957580566406,
+      "learning_rate": 0.00019999054724545264,
+      "loss": 0.9685383439064026,
+      "step": 1170
+    },
+    {
+      "epoch": 0.5057173678532901,
+      "grad_norm": 0.547788143157959,
+      "learning_rate": 0.00019998986000322917,
+      "loss": 0.9221975207328796,
+      "step": 1172
+    },
+    {
+      "epoch": 0.5065803667745415,
+      "grad_norm": 0.4919529855251312,
+      "learning_rate": 0.00019998914864890175,
+      "loss": 0.9104788303375244,
+      "step": 1174
+    },
+    {
+      "epoch": 0.5074433656957928,
+      "grad_norm": 0.5274141430854797,
+      "learning_rate": 0.00019998841318264187,
+      "loss": 0.9176050424575806,
+      "step": 1176
+    },
+    {
+      "epoch": 0.5083063646170443,
+      "grad_norm": 0.4257420301437378,
+      "learning_rate": 0.00019998765360462688,
+      "loss": 0.8389710187911987,
+      "step": 1178
+    },
+    {
+      "epoch": 0.5091693635382956,
+      "grad_norm": 0.4947778880596161,
+      "learning_rate": 0.00019998686991504002,
+      "loss": 1.0164397954940796,
+      "step": 1180
+    },
+    {
+      "epoch": 0.510032362459547,
+      "grad_norm": 0.5540821552276611,
+      "learning_rate": 0.00019998606211407016,
+      "loss": 0.9900994300842285,
+      "step": 1182
+    },
+    {
+      "epoch": 0.5108953613807983,
+      "grad_norm": 0.4793289601802826,
+      "learning_rate": 0.0001999852302019122,
+      "loss": 0.8797636032104492,
+      "step": 1184
+    },
+    {
+      "epoch": 0.5117583603020496,
+      "grad_norm": 0.47429659962654114,
+      "learning_rate": 0.00019998437417876672,
+      "loss": 0.96225905418396,
+      "step": 1186
+    },
+    {
+      "epoch": 0.512621359223301,
+      "grad_norm": 0.44918450713157654,
+      "learning_rate": 0.00019998349404484013,
+      "loss": 0.8604235649108887,
+      "step": 1188
+    },
+    {
+      "epoch": 0.5134843581445523,
+      "grad_norm": 0.566977858543396,
+      "learning_rate": 0.00019998258980034468,
+      "loss": 1.0325366258621216,
+      "step": 1190
+    },
+    {
+      "epoch": 0.5143473570658037,
+      "grad_norm": 0.4671999514102936,
+      "learning_rate": 0.00019998166144549843,
+      "loss": 0.7658900022506714,
+      "step": 1192
+    },
+    {
+      "epoch": 0.515210355987055,
+      "grad_norm": 0.42312702536582947,
+      "learning_rate": 0.00019998070898052521,
+      "loss": 0.9365432858467102,
+      "step": 1194
+    },
+    {
+      "epoch": 0.5160733549083064,
+      "grad_norm": 0.4652721881866455,
+      "learning_rate": 0.00019997973240565476,
+      "loss": 0.771016538143158,
+      "step": 1196
+    },
+    {
+      "epoch": 0.5169363538295577,
+      "grad_norm": 0.5048499703407288,
+      "learning_rate": 0.00019997873172112254,
+      "loss": 0.9123705625534058,
+      "step": 1198
+    },
+    {
+      "epoch": 0.517799352750809,
+      "grad_norm": 0.5446439981460571,
+      "learning_rate": 0.0001999777069271699,
+      "loss": 0.8975751399993896,
+      "step": 1200
+    },
+    {
+      "epoch": 0.517799352750809,
+      "eval_loss": 0.9344067573547363,
+      "eval_runtime": 658.6934,
+      "eval_samples_per_second": 3.127,
+      "eval_steps_per_second": 3.127,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5186623516720604,
+      "grad_norm": 0.5044088959693909,
+      "learning_rate": 0.0001999766580240439,
+      "loss": 0.89097660779953,
+      "step": 1202
+    },
+    {
+      "epoch": 0.5195253505933117,
+      "grad_norm": 0.4672294855117798,
+      "learning_rate": 0.00019997558501199753,
+      "loss": 0.9138525128364563,
+      "step": 1204
+    },
+    {
+      "epoch": 0.5203883495145631,
+      "grad_norm": 0.45749008655548096,
+      "learning_rate": 0.00019997448789128952,
+      "loss": 0.8946340680122375,
+      "step": 1206
+    },
+    {
+      "epoch": 0.5212513484358144,
+      "grad_norm": 0.4828707277774811,
+      "learning_rate": 0.00019997336666218447,
+      "loss": 0.8661436438560486,
+      "step": 1208
+    },
+    {
+      "epoch": 0.5221143473570659,
+      "grad_norm": 0.3975147008895874,
+      "learning_rate": 0.0001999722213249527,
+      "loss": 0.7684835195541382,
+      "step": 1210
+    },
+    {
+      "epoch": 0.5229773462783172,
+      "grad_norm": 0.5642077326774597,
+      "learning_rate": 0.00019997105187987045,
+      "loss": 0.9667536616325378,
+      "step": 1212
+    },
+    {
+      "epoch": 0.5238403451995685,
+      "grad_norm": 0.4907105565071106,
+      "learning_rate": 0.00019996985832721972,
+      "loss": 0.8679366707801819,
+      "step": 1214
+    },
+    {
+      "epoch": 0.5247033441208199,
+      "grad_norm": 0.46214789152145386,
+      "learning_rate": 0.0001999686406672883,
+      "loss": 0.8802784085273743,
+      "step": 1216
+    },
+    {
+      "epoch": 0.5255663430420712,
+      "grad_norm": 0.4355131685733795,
+      "learning_rate": 0.00019996739890036985,
+      "loss": 0.8493598103523254,
+      "step": 1218
+    },
+    {
+      "epoch": 0.5264293419633226,
+      "grad_norm": 0.4293915331363678,
+      "learning_rate": 0.0001999661330267638,
+      "loss": 0.8949980735778809,
+      "step": 1220
+    },
+    {
+      "epoch": 0.5272923408845739,
+      "grad_norm": 0.5452485680580139,
+      "learning_rate": 0.00019996484304677544,
+      "loss": 0.9497376680374146,
+      "step": 1222
+    },
+    {
+      "epoch": 0.5281553398058253,
+      "grad_norm": 0.45874500274658203,
+      "learning_rate": 0.00019996352896071583,
+      "loss": 0.9170818328857422,
+      "step": 1224
+    },
+    {
+      "epoch": 0.5290183387270766,
+      "grad_norm": 0.4414025843143463,
+      "learning_rate": 0.00019996219076890182,
+      "loss": 0.7557252645492554,
+      "step": 1226
+    },
+    {
+      "epoch": 0.5298813376483279,
+      "grad_norm": 0.4891829192638397,
+      "learning_rate": 0.0001999608284716562,
+      "loss": 0.848960816860199,
+      "step": 1228
+    },
+    {
+      "epoch": 0.5307443365695793,
+      "grad_norm": 0.5048345327377319,
+      "learning_rate": 0.00019995944206930734,
+      "loss": 0.9555954933166504,
+      "step": 1230
+    },
+    {
+      "epoch": 0.5316073354908306,
+      "grad_norm": 0.5006756782531738,
+      "learning_rate": 0.00019995803156218968,
+      "loss": 0.8080939054489136,
+      "step": 1232
+    },
+    {
+      "epoch": 0.532470334412082,
+      "grad_norm": 0.5422173738479614,
+      "learning_rate": 0.00019995659695064332,
+      "loss": 0.8638371825218201,
+      "step": 1234
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.4535163640975952,
+      "learning_rate": 0.0001999551382350142,
+      "loss": 0.889068067073822,
+      "step": 1236
+    },
+    {
+      "epoch": 0.5341963322545846,
+      "grad_norm": 0.4588642418384552,
+      "learning_rate": 0.00019995365541565412,
+      "loss": 0.8803121447563171,
+      "step": 1238
+    },
+    {
+      "epoch": 0.535059331175836,
+      "grad_norm": 0.49366191029548645,
+      "learning_rate": 0.00019995214849292064,
+      "loss": 0.9694926738739014,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5359223300970873,
+      "grad_norm": 0.41988301277160645,
+      "learning_rate": 0.0001999506174671771,
+      "loss": 0.8367960453033447,
+      "step": 1242
+    },
+    {
+      "epoch": 0.5367853290183388,
+      "grad_norm": 0.5242130160331726,
+      "learning_rate": 0.00019994906233879273,
+      "loss": 0.942340612411499,
+      "step": 1244
+    },
+    {
+      "epoch": 0.53764832793959,
+      "grad_norm": 0.4899834096431732,
+      "learning_rate": 0.00019994748310814256,
+      "loss": 0.8926790356636047,
+      "step": 1246
+    },
+    {
+      "epoch": 0.5385113268608415,
+      "grad_norm": 0.5496823787689209,
+      "learning_rate": 0.00019994587977560744,
+      "loss": 0.99891597032547,
+      "step": 1248
+    },
+    {
+      "epoch": 0.5393743257820928,
+      "grad_norm": 0.4497414231300354,
+      "learning_rate": 0.00019994425234157396,
+      "loss": 0.8873116970062256,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5402373247033441,
+      "grad_norm": 0.4256928563117981,
+      "learning_rate": 0.00019994260080643454,
+      "loss": 0.9041396975517273,
+      "step": 1252
+    },
+    {
+      "epoch": 0.5411003236245955,
+      "grad_norm": 0.36910608410835266,
+      "learning_rate": 0.00019994092517058753,
+      "loss": 0.7647561430931091,
+      "step": 1254
+    },
+    {
+      "epoch": 0.5419633225458468,
+      "grad_norm": 0.537584125995636,
+      "learning_rate": 0.0001999392254344369,
+      "loss": 0.8892287015914917,
+      "step": 1256
+    },
+    {
+      "epoch": 0.5428263214670982,
+      "grad_norm": 0.49463894963264465,
+      "learning_rate": 0.00019993750159839264,
+      "loss": 0.8638571500778198,
+      "step": 1258
+    },
+    {
+      "epoch": 0.5436893203883495,
+      "grad_norm": 0.5052056908607483,
+      "learning_rate": 0.00019993575366287036,
+      "loss": 0.8165372014045715,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5445523193096009,
+      "grad_norm": 0.47367510199546814,
+      "learning_rate": 0.0001999339816282916,
+      "loss": 0.9099977016448975,
+      "step": 1262
+    },
+    {
+      "epoch": 0.5454153182308522,
+      "grad_norm": 0.4600350558757782,
+      "learning_rate": 0.00019993218549508364,
+      "loss": 0.8557311296463013,
+      "step": 1264
+    },
+    {
+      "epoch": 0.5462783171521035,
+      "grad_norm": 0.5684534311294556,
+      "learning_rate": 0.0001999303652636797,
+      "loss": 0.9136497974395752,
+      "step": 1266
+    },
+    {
+      "epoch": 0.5471413160733549,
+      "grad_norm": 0.5151359438896179,
+      "learning_rate": 0.00019992852093451865,
+      "loss": 0.7906932830810547,
+      "step": 1268
+    },
+    {
+      "epoch": 0.5480043149946062,
+      "grad_norm": 0.48577409982681274,
+      "learning_rate": 0.00019992665250804525,
+      "loss": 0.9326766133308411,
+      "step": 1270
+    },
+    {
+      "epoch": 0.5488673139158576,
+      "grad_norm": 0.490531325340271,
+      "learning_rate": 0.00019992475998471004,
+      "loss": 0.9734495878219604,
+      "step": 1272
+    },
+    {
+      "epoch": 0.5497303128371089,
+      "grad_norm": 0.5092435479164124,
+      "learning_rate": 0.00019992284336496947,
+      "loss": 0.8728410005569458,
+      "step": 1274
+    },
+    {
+      "epoch": 0.5505933117583603,
+      "grad_norm": 0.3843296766281128,
+      "learning_rate": 0.00019992090264928566,
+      "loss": 0.7572637796401978,
+      "step": 1276
+    },
+    {
+      "epoch": 0.5514563106796116,
+      "grad_norm": 0.534304678440094,
+      "learning_rate": 0.00019991893783812662,
+      "loss": 0.8895323872566223,
+      "step": 1278
+    },
+    {
+      "epoch": 0.552319309600863,
+      "grad_norm": 0.4567227363586426,
+      "learning_rate": 0.00019991694893196614,
+      "loss": 0.9318088293075562,
+      "step": 1280
+    },
+    {
+      "epoch": 0.5531823085221144,
+      "grad_norm": 0.48464900255203247,
+      "learning_rate": 0.0001999149359312839,
+      "loss": 0.8541979789733887,
+      "step": 1282
+    },
+    {
+      "epoch": 0.5540453074433657,
+      "grad_norm": 0.5569567084312439,
+      "learning_rate": 0.00019991289883656524,
+      "loss": 0.977894127368927,
+      "step": 1284
+    },
+    {
+      "epoch": 0.5549083063646171,
+      "grad_norm": 0.4637227952480316,
+      "learning_rate": 0.00019991083764830145,
+      "loss": 0.8860608339309692,
+      "step": 1286
+    },
+    {
+      "epoch": 0.5557713052858684,
+      "grad_norm": 0.4096687436103821,
+      "learning_rate": 0.00019990875236698956,
+      "loss": 0.8429648876190186,
+      "step": 1288
+    },
+    {
+      "epoch": 0.5566343042071198,
+      "grad_norm": 0.5221695303916931,
+      "learning_rate": 0.00019990664299313242,
+      "loss": 0.8510909080505371,
+      "step": 1290
+    },
+    {
+      "epoch": 0.5574973031283711,
+      "grad_norm": 0.5155899524688721,
+      "learning_rate": 0.00019990450952723872,
+      "loss": 0.8971074223518372,
+      "step": 1292
+    },
+    {
+      "epoch": 0.5583603020496224,
+      "grad_norm": 0.5064809322357178,
+      "learning_rate": 0.0001999023519698229,
+      "loss": 0.9030373096466064,
+      "step": 1294
+    },
+    {
+      "epoch": 0.5592233009708738,
+      "grad_norm": 0.40551698207855225,
+      "learning_rate": 0.00019990017032140526,
+      "loss": 0.7866057753562927,
+      "step": 1296
+    },
+    {
+      "epoch": 0.5600862998921251,
+      "grad_norm": 0.5009430050849915,
+      "learning_rate": 0.00019989796458251194,
+      "loss": 0.9477730989456177,
+      "step": 1298
+    },
+    {
+      "epoch": 0.5609492988133765,
+      "grad_norm": 0.5192028880119324,
+      "learning_rate": 0.00019989573475367477,
+      "loss": 0.9206778407096863,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5609492988133765,
+      "eval_loss": 0.9177446365356445,
+      "eval_runtime": 665.3245,
+      "eval_samples_per_second": 3.096,
+      "eval_steps_per_second": 3.096,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5618122977346278,
+      "grad_norm": 0.5580230951309204,
+      "learning_rate": 0.00019989348083543148,
+      "loss": 0.9516512155532837,
+      "step": 1302
+    },
+    {
+      "epoch": 0.5626752966558792,
+      "grad_norm": 0.4151005744934082,
+      "learning_rate": 0.00019989120282832564,
+      "loss": 0.7725991606712341,
+      "step": 1304
+    },
+    {
+      "epoch": 0.5635382955771305,
+      "grad_norm": 0.56330406665802,
+      "learning_rate": 0.00019988890073290656,
+      "loss": 0.9241501688957214,
+      "step": 1306
+    },
+    {
+      "epoch": 0.5644012944983818,
+      "grad_norm": 0.44836440682411194,
+      "learning_rate": 0.00019988657454972936,
+      "loss": 0.8351686000823975,
+      "step": 1308
+    },
+    {
+      "epoch": 0.5652642934196332,
+      "grad_norm": 0.5414754152297974,
+      "learning_rate": 0.00019988422427935496,
+      "loss": 0.9033217430114746,
+      "step": 1310
+    },
+    {
+      "epoch": 0.5661272923408845,
+      "grad_norm": 0.5283750891685486,
+      "learning_rate": 0.0001998818499223502,
+      "loss": 0.8885331153869629,
+      "step": 1312
+    },
+    {
+      "epoch": 0.566990291262136,
+      "grad_norm": 0.45846256613731384,
+      "learning_rate": 0.00019987945147928758,
+      "loss": 0.8359912037849426,
+      "step": 1314
+    },
+    {
+      "epoch": 0.5678532901833873,
+      "grad_norm": 0.44439879059791565,
+      "learning_rate": 0.0001998770289507455,
+      "loss": 0.8327895402908325,
+      "step": 1316
+    },
+    {
+      "epoch": 0.5687162891046387,
+      "grad_norm": 0.5491341948509216,
+      "learning_rate": 0.00019987458233730813,
+      "loss": 0.9354757070541382,
+      "step": 1318
+    },
+    {
+      "epoch": 0.56957928802589,
+      "grad_norm": 0.5502263307571411,
+      "learning_rate": 0.00019987211163956548,
+      "loss": 0.944054901599884,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5704422869471413,
+      "grad_norm": 0.47165682911872864,
+      "learning_rate": 0.00019986961685811334,
+      "loss": 0.9515072107315063,
+      "step": 1322
+    },
+    {
+      "epoch": 0.5713052858683927,
+      "grad_norm": 0.5136987566947937,
+      "learning_rate": 0.0001998670979935533,
+      "loss": 0.9455493688583374,
+      "step": 1324
+    },
+    {
+      "epoch": 0.572168284789644,
+      "grad_norm": 0.4822693169116974,
+      "learning_rate": 0.00019986455504649277,
+      "loss": 0.8626728057861328,
+      "step": 1326
+    },
+    {
+      "epoch": 0.5730312837108954,
+      "grad_norm": 0.4639468193054199,
+      "learning_rate": 0.000199861988017545,
+      "loss": 0.8857194781303406,
+      "step": 1328
+    },
+    {
+      "epoch": 0.5738942826321467,
+      "grad_norm": 0.5224950313568115,
+      "learning_rate": 0.00019985939690732898,
+      "loss": 0.9198446273803711,
+      "step": 1330
+    },
+    {
+      "epoch": 0.574757281553398,
+      "grad_norm": 0.47504499554634094,
+      "learning_rate": 0.00019985678171646954,
+      "loss": 0.8785439133644104,
+      "step": 1332
+    },
+    {
+      "epoch": 0.5756202804746494,
+      "grad_norm": 0.5022051930427551,
+      "learning_rate": 0.0001998541424455974,
+      "loss": 0.9593754410743713,
+      "step": 1334
+    },
+    {
+      "epoch": 0.5764832793959007,
+      "grad_norm": 0.4572875201702118,
+      "learning_rate": 0.00019985147909534897,
+      "loss": 0.986197292804718,
+      "step": 1336
+    },
+    {
+      "epoch": 0.5773462783171521,
+      "grad_norm": 0.5153827667236328,
+      "learning_rate": 0.00019984879166636644,
+      "loss": 0.9163863658905029,
+      "step": 1338
+    },
+    {
+      "epoch": 0.5782092772384034,
+      "grad_norm": 0.4813650846481323,
+      "learning_rate": 0.00019984608015929792,
+      "loss": 0.8815995454788208,
+      "step": 1340
+    },
+    {
+      "epoch": 0.5790722761596548,
+      "grad_norm": 0.4319819211959839,
+      "learning_rate": 0.0001998433445747973,
+      "loss": 0.857044517993927,
+      "step": 1342
+    },
+    {
+      "epoch": 0.5799352750809061,
+      "grad_norm": 0.5128870010375977,
+      "learning_rate": 0.00019984058491352423,
+      "loss": 0.8939256072044373,
+      "step": 1344
+    },
+    {
+      "epoch": 0.5807982740021574,
+      "grad_norm": 0.41450315713882446,
+      "learning_rate": 0.0001998378011761442,
+      "loss": 0.9267327785491943,
+      "step": 1346
+    },
+    {
+      "epoch": 0.5816612729234089,
+      "grad_norm": 0.42916348576545715,
+      "learning_rate": 0.00019983499336332844,
+      "loss": 0.8494639992713928,
+      "step": 1348
+    },
+    {
+      "epoch": 0.5825242718446602,
+      "grad_norm": 0.43995746970176697,
+      "learning_rate": 0.00019983216147575412,
+      "loss": 0.9720427989959717,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5833872707659116,
+      "grad_norm": 0.5063773989677429,
+      "learning_rate": 0.00019982930551410411,
+      "loss": 0.9400854706764221,
+      "step": 1352
+    },
+    {
+      "epoch": 0.5842502696871629,
+      "grad_norm": 0.5029586553573608,
+      "learning_rate": 0.0001998264254790671,
+      "loss": 0.8657845258712769,
+      "step": 1354
+    },
+    {
+      "epoch": 0.5851132686084143,
+      "grad_norm": 0.45519232749938965,
+      "learning_rate": 0.00019982352137133764,
+      "loss": 0.8593506813049316,
+      "step": 1356
+    },
+    {
+      "epoch": 0.5859762675296656,
+      "grad_norm": 0.49116215109825134,
+      "learning_rate": 0.000199820593191616,
+      "loss": 0.8658114671707153,
+      "step": 1358
+    },
+    {
+      "epoch": 0.5868392664509169,
+      "grad_norm": 0.45347318053245544,
+      "learning_rate": 0.00019981764094060826,
+      "loss": 0.8044605255126953,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5877022653721683,
+      "grad_norm": 0.5191754698753357,
+      "learning_rate": 0.00019981466461902643,
+      "loss": 0.9176861047744751,
+      "step": 1362
+    },
+    {
+      "epoch": 0.5885652642934196,
+      "grad_norm": 0.4791528284549713,
+      "learning_rate": 0.00019981166422758818,
+      "loss": 0.8453370928764343,
+      "step": 1364
+    },
+    {
+      "epoch": 0.589428263214671,
+      "grad_norm": 0.5105116367340088,
+      "learning_rate": 0.00019980863976701705,
+      "loss": 0.9343777298927307,
+      "step": 1366
+    },
+    {
+      "epoch": 0.5902912621359223,
+      "grad_norm": 0.44593656063079834,
+      "learning_rate": 0.00019980559123804236,
+      "loss": 0.8950760960578918,
+      "step": 1368
+    },
+    {
+      "epoch": 0.5911542610571737,
+      "grad_norm": 0.4375658631324768,
+      "learning_rate": 0.0001998025186413993,
+      "loss": 0.8613521456718445,
+      "step": 1370
+    },
+    {
+      "epoch": 0.592017259978425,
+      "grad_norm": 0.5138815641403198,
+      "learning_rate": 0.00019979942197782878,
+      "loss": 0.8982083201408386,
+      "step": 1372
+    },
+    {
+      "epoch": 0.5928802588996763,
+      "grad_norm": 0.45473602414131165,
+      "learning_rate": 0.00019979630124807753,
+      "loss": 0.9372450709342957,
+      "step": 1374
+    },
+    {
+      "epoch": 0.5937432578209277,
+      "grad_norm": 0.4961191713809967,
+      "learning_rate": 0.00019979315645289814,
+      "loss": 0.8758652806282043,
+      "step": 1376
+    },
+    {
+      "epoch": 0.594606256742179,
+      "grad_norm": 0.5672827363014221,
+      "learning_rate": 0.00019978998759304895,
+      "loss": 0.9852207899093628,
+      "step": 1378
+    },
+    {
+      "epoch": 0.5954692556634305,
+      "grad_norm": 0.44907906651496887,
+      "learning_rate": 0.00019978679466929407,
+      "loss": 0.8451287746429443,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5963322545846818,
+      "grad_norm": 0.4759652316570282,
+      "learning_rate": 0.00019978357768240352,
+      "loss": 0.8381558656692505,
+      "step": 1382
+    },
+    {
+      "epoch": 0.5971952535059332,
+      "grad_norm": 0.4936048686504364,
+      "learning_rate": 0.00019978033663315304,
+      "loss": 0.8820816874504089,
+      "step": 1384
+    },
+    {
+      "epoch": 0.5980582524271845,
+      "grad_norm": 0.44983741641044617,
+      "learning_rate": 0.00019977707152232416,
+      "loss": 0.9156787991523743,
+      "step": 1386
+    },
+    {
+      "epoch": 0.5989212513484358,
+      "grad_norm": 0.45198705792427063,
+      "learning_rate": 0.0001997737823507043,
+      "loss": 0.8285194039344788,
+      "step": 1388
+    },
+    {
+      "epoch": 0.5997842502696872,
+      "grad_norm": 0.45788463950157166,
+      "learning_rate": 0.00019977046911908664,
+      "loss": 0.8109505772590637,
+      "step": 1390
+    },
+    {
+      "epoch": 0.6006472491909385,
+      "grad_norm": 0.4795142412185669,
+      "learning_rate": 0.0001997671318282701,
+      "loss": 0.8285947442054749,
+      "step": 1392
+    },
+    {
+      "epoch": 0.6015102481121899,
+      "grad_norm": 0.5026728510856628,
+      "learning_rate": 0.00019976377047905945,
+      "loss": 0.9497535228729248,
+      "step": 1394
+    },
+    {
+      "epoch": 0.6023732470334412,
+      "grad_norm": 0.4994853734970093,
+      "learning_rate": 0.0001997603850722653,
+      "loss": 0.9171916246414185,
+      "step": 1396
+    },
+    {
+      "epoch": 0.6032362459546926,
+      "grad_norm": 0.4789866507053375,
+      "learning_rate": 0.00019975697560870403,
+      "loss": 0.7894434928894043,
+      "step": 1398
+    },
+    {
+      "epoch": 0.6040992448759439,
+      "grad_norm": 0.42282742261886597,
+      "learning_rate": 0.0001997535420891978,
+      "loss": 0.8942429423332214,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6040992448759439,
+      "eval_loss": 0.9080492854118347,
+      "eval_runtime": 661.4597,
+      "eval_samples_per_second": 3.114,
+      "eval_steps_per_second": 3.114,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6049622437971952,
+      "grad_norm": 0.5789905190467834,
+      "learning_rate": 0.00019975008451457454,
+      "loss": 0.8938372731208801,
+      "step": 1402
+    },
+    {
+      "epoch": 0.6058252427184466,
+      "grad_norm": 0.46121683716773987,
+      "learning_rate": 0.00019974660288566814,
+      "loss": 0.8746235370635986,
+      "step": 1404
+    },
+    {
+      "epoch": 0.6066882416396979,
+      "grad_norm": 0.5195551514625549,
+      "learning_rate": 0.00019974309720331807,
+      "loss": 0.8650617003440857,
+      "step": 1406
+    },
+    {
+      "epoch": 0.6075512405609493,
+      "grad_norm": 0.46930259466171265,
+      "learning_rate": 0.00019973956746836976,
+      "loss": 0.8853039145469666,
+      "step": 1408
+    },
+    {
+      "epoch": 0.6084142394822006,
+      "grad_norm": 0.40869632363319397,
+      "learning_rate": 0.0001997360136816744,
+      "loss": 0.7865594029426575,
+      "step": 1410
+    },
+    {
+      "epoch": 0.609277238403452,
+      "grad_norm": 0.5398361086845398,
+      "learning_rate": 0.00019973243584408895,
+      "loss": 0.907535970211029,
+      "step": 1412
+    },
+    {
+      "epoch": 0.6101402373247033,
+      "grad_norm": 0.5110154747962952,
+      "learning_rate": 0.00019972883395647615,
+      "loss": 0.8682730197906494,
+      "step": 1414
+    },
+    {
+      "epoch": 0.6110032362459547,
+      "grad_norm": 0.44484639167785645,
+      "learning_rate": 0.00019972520801970467,
+      "loss": 0.8786011338233948,
+      "step": 1416
+    },
+    {
+      "epoch": 0.6118662351672061,
+      "grad_norm": 0.4768071472644806,
+      "learning_rate": 0.0001997215580346488,
+      "loss": 0.9021878242492676,
+      "step": 1418
+    },
+    {
+      "epoch": 0.6127292340884574,
+      "grad_norm": 0.43265241384506226,
+      "learning_rate": 0.0001997178840021888,
+      "loss": 0.7737482786178589,
+      "step": 1420
+    },
+    {
+      "epoch": 0.6135922330097088,
+      "grad_norm": 0.525692343711853,
+      "learning_rate": 0.0001997141859232106,
+      "loss": 0.876280665397644,
+      "step": 1422
+    },
+    {
+      "epoch": 0.6144552319309601,
+      "grad_norm": 0.48206865787506104,
+      "learning_rate": 0.00019971046379860594,
+      "loss": 0.8503577709197998,
+      "step": 1424
+    },
+    {
+      "epoch": 0.6153182308522115,
+      "grad_norm": 0.6032769680023193,
+      "learning_rate": 0.00019970671762927246,
+      "loss": 0.9459730982780457,
+      "step": 1426
+    },
+    {
+      "epoch": 0.6161812297734628,
+      "grad_norm": 0.4491981863975525,
+      "learning_rate": 0.0001997029474161135,
+      "loss": 0.8836647868156433,
+      "step": 1428
+    },
+    {
+      "epoch": 0.6170442286947141,
+      "grad_norm": 0.47503358125686646,
+      "learning_rate": 0.00019969915316003824,
+      "loss": 0.8614388108253479,
+      "step": 1430
+    },
+    {
+      "epoch": 0.6179072276159655,
+      "grad_norm": 0.44801047444343567,
+      "learning_rate": 0.00019969533486196162,
+      "loss": 0.8420360684394836,
+      "step": 1432
+    },
+    {
+      "epoch": 0.6187702265372168,
+      "grad_norm": 0.45057111978530884,
+      "learning_rate": 0.00019969149252280446,
+      "loss": 0.8256269693374634,
+      "step": 1434
+    },
+    {
+      "epoch": 0.6196332254584682,
+      "grad_norm": 0.4589645266532898,
+      "learning_rate": 0.00019968762614349327,
+      "loss": 0.9130199551582336,
+      "step": 1436
+    },
+    {
+      "epoch": 0.6204962243797195,
+      "grad_norm": 0.48914027214050293,
+      "learning_rate": 0.00019968373572496045,
+      "loss": 0.74083012342453,
+      "step": 1438
+    },
+    {
+      "epoch": 0.6213592233009708,
+      "grad_norm": 0.4582098424434662,
+      "learning_rate": 0.00019967982126814412,
+      "loss": 0.8538379669189453,
+      "step": 1440
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.48722779750823975,
+      "learning_rate": 0.00019967588277398823,
+      "loss": 0.8780114054679871,
+      "step": 1442
+    },
+    {
+      "epoch": 0.6230852211434735,
+      "grad_norm": 0.4291327893733978,
+      "learning_rate": 0.00019967192024344254,
+      "loss": 0.8341028690338135,
+      "step": 1444
+    },
+    {
+      "epoch": 0.623948220064725,
+      "grad_norm": 0.4773139953613281,
+      "learning_rate": 0.00019966793367746265,
+      "loss": 0.8651667237281799,
+      "step": 1446
+    },
+    {
+      "epoch": 0.6248112189859762,
+      "grad_norm": 0.45556166768074036,
+      "learning_rate": 0.00019966392307700986,
+      "loss": 0.8339929580688477,
+      "step": 1448
+    },
+    {
+      "epoch": 0.6256742179072277,
+      "grad_norm": 0.5126671195030212,
+      "learning_rate": 0.00019965988844305129,
+      "loss": 0.9129340052604675,
+      "step": 1450
+    },
+    {
+      "epoch": 0.626537216828479,
+      "grad_norm": 0.6067109704017639,
+      "learning_rate": 0.00019965582977655988,
+      "loss": 0.9057610034942627,
+      "step": 1452
+    },
+    {
+      "epoch": 0.6274002157497303,
+      "grad_norm": 0.46425968408584595,
+      "learning_rate": 0.00019965174707851438,
+      "loss": 0.874100387096405,
+      "step": 1454
+    },
+    {
+      "epoch": 0.6282632146709817,
+      "grad_norm": 0.481077641248703,
+      "learning_rate": 0.0001996476403498993,
+      "loss": 0.915635347366333,
+      "step": 1456
+    },
+    {
+      "epoch": 0.629126213592233,
+      "grad_norm": 0.47299909591674805,
+      "learning_rate": 0.000199643509591705,
+      "loss": 0.9059650301933289,
+      "step": 1458
+    },
+    {
+      "epoch": 0.6299892125134844,
+      "grad_norm": 0.48924630880355835,
+      "learning_rate": 0.00019963935480492753,
+      "loss": 0.9775188565254211,
+      "step": 1460
+    },
+    {
+      "epoch": 0.6308522114347357,
+      "grad_norm": 0.4407665431499481,
+      "learning_rate": 0.0001996351759905688,
+      "loss": 0.8950685858726501,
+      "step": 1462
+    },
+    {
+      "epoch": 0.6317152103559871,
+      "grad_norm": 0.5018318295478821,
+      "learning_rate": 0.00019963097314963657,
+      "loss": 0.8532119989395142,
+      "step": 1464
+    },
+    {
+      "epoch": 0.6325782092772384,
+      "grad_norm": 0.43245720863342285,
+      "learning_rate": 0.0001996267462831443,
+      "loss": 0.7775963544845581,
+      "step": 1466
+    },
+    {
+      "epoch": 0.6334412081984897,
+      "grad_norm": 0.5028865337371826,
+      "learning_rate": 0.00019962249539211125,
+      "loss": 0.8315839767456055,
+      "step": 1468
+    },
+    {
+      "epoch": 0.6343042071197411,
+      "grad_norm": 0.4697185754776001,
+      "learning_rate": 0.0001996182204775626,
+      "loss": 0.849076509475708,
+      "step": 1470
+    },
+    {
+      "epoch": 0.6351672060409924,
+      "grad_norm": 0.46725034713745117,
+      "learning_rate": 0.00019961392154052912,
+      "loss": 0.8828577995300293,
+      "step": 1472
+    },
+    {
+      "epoch": 0.6360302049622438,
+      "grad_norm": 0.4301203489303589,
+      "learning_rate": 0.00019960959858204754,
+      "loss": 0.850115954875946,
+      "step": 1474
+    },
+    {
+      "epoch": 0.6368932038834951,
+      "grad_norm": 0.46635881066322327,
+      "learning_rate": 0.0001996052516031603,
+      "loss": 0.7912618517875671,
+      "step": 1476
+    },
+    {
+      "epoch": 0.6377562028047465,
+      "grad_norm": 0.44143620133399963,
+      "learning_rate": 0.00019960088060491565,
+      "loss": 0.9072504639625549,
+      "step": 1478
+    },
+    {
+      "epoch": 0.6386192017259978,
+      "grad_norm": 0.47458893060684204,
+      "learning_rate": 0.00019959648558836763,
+      "loss": 0.8976638317108154,
+      "step": 1480
+    },
+    {
+      "epoch": 0.6394822006472491,
+      "grad_norm": 0.4596816897392273,
+      "learning_rate": 0.00019959206655457612,
+      "loss": 0.8142043352127075,
+      "step": 1482
+    },
+    {
+      "epoch": 0.6403451995685006,
+      "grad_norm": 0.4839977025985718,
+      "learning_rate": 0.0001995876235046067,
+      "loss": 0.860643744468689,
+      "step": 1484
+    },
+    {
+      "epoch": 0.6412081984897519,
+      "grad_norm": 0.3542814552783966,
+      "learning_rate": 0.00019958315643953085,
+      "loss": 0.7586524486541748,
+      "step": 1486
+    },
+    {
+      "epoch": 0.6420711974110033,
+      "grad_norm": 0.5423269271850586,
+      "learning_rate": 0.00019957866536042572,
+      "loss": 0.9353570342063904,
+      "step": 1488
+    },
+    {
+      "epoch": 0.6429341963322546,
+      "grad_norm": 0.4580909013748169,
+      "learning_rate": 0.00019957415026837437,
+      "loss": 0.9919291138648987,
+      "step": 1490
+    },
+    {
+      "epoch": 0.643797195253506,
+      "grad_norm": 0.4211732745170593,
+      "learning_rate": 0.00019956961116446555,
+      "loss": 0.8720914125442505,
+      "step": 1492
+    },
+    {
+      "epoch": 0.6446601941747573,
+      "grad_norm": 0.4583161175251007,
+      "learning_rate": 0.00019956504804979384,
+      "loss": 0.8661212921142578,
+      "step": 1494
+    },
+    {
+      "epoch": 0.6455231930960086,
+      "grad_norm": 0.4359884262084961,
+      "learning_rate": 0.00019956046092545966,
+      "loss": 0.8170996308326721,
+      "step": 1496
+    },
+    {
+      "epoch": 0.64638619201726,
+      "grad_norm": 0.4642556607723236,
+      "learning_rate": 0.00019955584979256913,
+      "loss": 0.8607422113418579,
+      "step": 1498
+    },
+    {
+      "epoch": 0.6472491909385113,
+      "grad_norm": 0.4496007561683655,
+      "learning_rate": 0.00019955121465223426,
+      "loss": 0.837529182434082,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6472491909385113,
+      "eval_loss": 0.8972997665405273,
+      "eval_runtime": 649.796,
+      "eval_samples_per_second": 3.17,
+      "eval_steps_per_second": 3.17,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6481121898597627,
+      "grad_norm": 0.48363205790519714,
+      "learning_rate": 0.0001995465555055727,
+      "loss": 0.9355250000953674,
+      "step": 1502
+    },
+    {
+      "epoch": 0.648975188781014,
+      "grad_norm": 0.44681695103645325,
+      "learning_rate": 0.0001995418723537081,
+      "loss": 0.8286949396133423,
+      "step": 1504
+    },
+    {
+      "epoch": 0.6498381877022654,
+      "grad_norm": 0.5110394358634949,
+      "learning_rate": 0.00019953716519776967,
+      "loss": 0.890398383140564,
+      "step": 1506
+    },
+    {
+      "epoch": 0.6507011866235167,
+      "grad_norm": 0.4353160262107849,
+      "learning_rate": 0.00019953243403889257,
+      "loss": 0.8117311000823975,
+      "step": 1508
+    },
+    {
+      "epoch": 0.651564185544768,
+      "grad_norm": 0.4731789231300354,
+      "learning_rate": 0.0001995276788782177,
+      "loss": 0.8255904316902161,
+      "step": 1510
+    },
+    {
+      "epoch": 0.6524271844660194,
+      "grad_norm": 0.5447185039520264,
+      "learning_rate": 0.00019952289971689177,
+      "loss": 0.9371263384819031,
+      "step": 1512
+    },
+    {
+      "epoch": 0.6532901833872707,
+      "grad_norm": 0.47616517543792725,
+      "learning_rate": 0.0001995180965560672,
+      "loss": 0.8532910943031311,
+      "step": 1514
+    },
+    {
+      "epoch": 0.6541531823085222,
+      "grad_norm": 0.4412213861942291,
+      "learning_rate": 0.0001995132693969023,
+      "loss": 0.8799141645431519,
+      "step": 1516
+    },
+    {
+      "epoch": 0.6550161812297735,
+      "grad_norm": 0.469911128282547,
+      "learning_rate": 0.00019950841824056107,
+      "loss": 0.8395764827728271,
+      "step": 1518
+    },
+    {
+      "epoch": 0.6558791801510249,
+      "grad_norm": 0.5236243009567261,
+      "learning_rate": 0.00019950354308821336,
+      "loss": 0.9556697010993958,
+      "step": 1520
+    },
+    {
+      "epoch": 0.6567421790722762,
+      "grad_norm": 0.4441990256309509,
+      "learning_rate": 0.00019949864394103482,
+      "loss": 0.8524283170700073,
+      "step": 1522
+    },
+    {
+      "epoch": 0.6576051779935275,
+      "grad_norm": 0.4173077940940857,
+      "learning_rate": 0.00019949372080020682,
+      "loss": 0.9213772416114807,
+      "step": 1524
+    },
+    {
+      "epoch": 0.6584681769147789,
+      "grad_norm": 0.4404120147228241,
+      "learning_rate": 0.00019948877366691658,
+      "loss": 0.9236897230148315,
+      "step": 1526
+    },
+    {
+      "epoch": 0.6593311758360302,
+      "grad_norm": 0.4586230516433716,
+      "learning_rate": 0.00019948380254235706,
+      "loss": 0.8373230695724487,
+      "step": 1528
+    },
+    {
+      "epoch": 0.6601941747572816,
+      "grad_norm": 0.4136028587818146,
+      "learning_rate": 0.00019947880742772703,
+      "loss": 0.8256528377532959,
+      "step": 1530
+    },
+    {
+      "epoch": 0.6610571736785329,
+      "grad_norm": 0.5007129907608032,
+      "learning_rate": 0.00019947378832423107,
+      "loss": 0.8580789566040039,
+      "step": 1532
+    },
+    {
+      "epoch": 0.6619201725997842,
+      "grad_norm": 0.39050203561782837,
+      "learning_rate": 0.00019946874523307947,
+      "loss": 0.7647744417190552,
+      "step": 1534
+    },
+    {
+      "epoch": 0.6627831715210356,
+      "grad_norm": 0.4640588164329529,
+      "learning_rate": 0.00019946367815548835,
+      "loss": 0.9042545557022095,
+      "step": 1536
+    },
+    {
+      "epoch": 0.6636461704422869,
+      "grad_norm": 0.5304957032203674,
+      "learning_rate": 0.00019945858709267963,
+      "loss": 0.9114110469818115,
+      "step": 1538
+    },
+    {
+      "epoch": 0.6645091693635383,
+      "grad_norm": 0.5426004528999329,
+      "learning_rate": 0.000199453472045881,
+      "loss": 0.8239460587501526,
+      "step": 1540
+    },
+    {
+      "epoch": 0.6653721682847896,
+      "grad_norm": 0.44893568754196167,
+      "learning_rate": 0.00019944833301632593,
+      "loss": 0.8091367483139038,
+      "step": 1542
+    },
+    {
+      "epoch": 0.666235167206041,
+      "grad_norm": 0.4294016361236572,
+      "learning_rate": 0.00019944317000525366,
+      "loss": 0.9202280640602112,
+      "step": 1544
+    },
+    {
+      "epoch": 0.6670981661272923,
+      "grad_norm": 0.449633926153183,
+      "learning_rate": 0.00019943798301390927,
+      "loss": 0.8884767889976501,
+      "step": 1546
+    },
+    {
+      "epoch": 0.6679611650485436,
+      "grad_norm": 0.4516827166080475,
+      "learning_rate": 0.0001994327720435435,
+      "loss": 0.8390879034996033,
+      "step": 1548
+    },
+    {
+      "epoch": 0.668824163969795,
+      "grad_norm": 0.422270268201828,
+      "learning_rate": 0.000199427537095413,
+      "loss": 0.7388033270835876,
+      "step": 1550
+    },
+    {
+      "epoch": 0.6696871628910464,
+      "grad_norm": 0.580563485622406,
+      "learning_rate": 0.00019942227817078015,
+      "loss": 0.9268350601196289,
+      "step": 1552
+    },
+    {
+      "epoch": 0.6705501618122978,
+      "grad_norm": 0.4436347782611847,
+      "learning_rate": 0.00019941699527091316,
+      "loss": 0.7978561520576477,
+      "step": 1554
+    },
+    {
+      "epoch": 0.6714131607335491,
+      "grad_norm": 0.4149787127971649,
+      "learning_rate": 0.0001994116883970859,
+      "loss": 0.8229286670684814,
+      "step": 1556
+    },
+    {
+      "epoch": 0.6722761596548005,
+      "grad_norm": 0.49915504455566406,
+      "learning_rate": 0.00019940635755057813,
+      "loss": 0.8554545640945435,
+      "step": 1558
+    },
+    {
+      "epoch": 0.6731391585760518,
+      "grad_norm": 0.45326656103134155,
+      "learning_rate": 0.00019940100273267537,
+      "loss": 0.9135572910308838,
+      "step": 1560
+    },
+    {
+      "epoch": 0.6740021574973031,
+      "grad_norm": 0.48639237880706787,
+      "learning_rate": 0.0001993956239446689,
+      "loss": 0.7769742012023926,
+      "step": 1562
+    },
+    {
+      "epoch": 0.6748651564185545,
+      "grad_norm": 0.5072791576385498,
+      "learning_rate": 0.0001993902211878558,
+      "loss": 0.9626237154006958,
+      "step": 1564
+    },
+    {
+      "epoch": 0.6757281553398058,
+      "grad_norm": 0.4646652638912201,
+      "learning_rate": 0.00019938479446353892,
+      "loss": 0.8506941199302673,
+      "step": 1566
+    },
+    {
+      "epoch": 0.6765911542610572,
+      "grad_norm": 0.4343051314353943,
+      "learning_rate": 0.00019937934377302688,
+      "loss": 0.8172947764396667,
+      "step": 1568
+    },
+    {
+      "epoch": 0.6774541531823085,
+      "grad_norm": 0.46890193223953247,
+      "learning_rate": 0.00019937386911763407,
+      "loss": 0.9215856790542603,
+      "step": 1570
+    },
+    {
+      "epoch": 0.6783171521035599,
+      "grad_norm": 0.5121113061904907,
+      "learning_rate": 0.0001993683704986807,
+      "loss": 0.8099892139434814,
+      "step": 1572
+    },
+    {
+      "epoch": 0.6791801510248112,
+      "grad_norm": 0.4652405083179474,
+      "learning_rate": 0.0001993628479174928,
+      "loss": 0.8675104975700378,
+      "step": 1574
+    },
+    {
+      "epoch": 0.6800431499460625,
+      "grad_norm": 0.4599422812461853,
+      "learning_rate": 0.00019935730137540198,
+      "loss": 0.7938929200172424,
+      "step": 1576
+    },
+    {
+      "epoch": 0.6809061488673139,
+      "grad_norm": 0.4738059937953949,
+      "learning_rate": 0.0001993517308737459,
+      "loss": 0.8610570430755615,
+      "step": 1578
+    },
+    {
+      "epoch": 0.6817691477885652,
+      "grad_norm": 0.5161214470863342,
+      "learning_rate": 0.00019934613641386776,
+      "loss": 0.9199413657188416,
+      "step": 1580
+    },
+    {
+      "epoch": 0.6826321467098166,
+      "grad_norm": 0.4284999370574951,
+      "learning_rate": 0.00019934051799711672,
+      "loss": 0.771649181842804,
+      "step": 1582
+    },
+    {
+      "epoch": 0.683495145631068,
+      "grad_norm": 0.5117548704147339,
+      "learning_rate": 0.00019933487562484757,
+      "loss": 0.8861327767372131,
+      "step": 1584
+    },
+    {
+      "epoch": 0.6843581445523194,
+      "grad_norm": 0.4964369833469391,
+      "learning_rate": 0.00019932920929842095,
+      "loss": 0.806983232498169,
+      "step": 1586
+    },
+    {
+      "epoch": 0.6852211434735707,
+      "grad_norm": 0.4699532091617584,
+      "learning_rate": 0.00019932351901920327,
+      "loss": 0.7963525652885437,
+      "step": 1588
+    },
+    {
+      "epoch": 0.686084142394822,
+      "grad_norm": 0.5329220294952393,
+      "learning_rate": 0.00019931780478856678,
+      "loss": 0.9406430721282959,
+      "step": 1590
+    },
+    {
+      "epoch": 0.6869471413160734,
+      "grad_norm": 0.49823835492134094,
+      "learning_rate": 0.00019931206660788936,
+      "loss": 0.8517770171165466,
+      "step": 1592
+    },
+    {
+      "epoch": 0.6878101402373247,
+      "grad_norm": 0.45245134830474854,
+      "learning_rate": 0.00019930630447855482,
+      "loss": 0.8703644275665283,
+      "step": 1594
+    },
+    {
+      "epoch": 0.6886731391585761,
+      "grad_norm": 0.47524577379226685,
+      "learning_rate": 0.0001993005184019526,
+      "loss": 0.9035283327102661,
+      "step": 1596
+    },
+    {
+      "epoch": 0.6895361380798274,
+      "grad_norm": 0.4537610411643982,
+      "learning_rate": 0.00019929470837947802,
+      "loss": 0.9173959493637085,
+      "step": 1598
+    },
+    {
+      "epoch": 0.6903991370010788,
+      "grad_norm": 0.42469722032546997,
+      "learning_rate": 0.00019928887441253212,
+      "loss": 0.8573579788208008,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6903991370010788,
+      "eval_loss": 0.8880587220191956,
+      "eval_runtime": 653.9515,
+      "eval_samples_per_second": 3.15,
+      "eval_steps_per_second": 3.15,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6912621359223301,
+      "grad_norm": 0.4388251304626465,
+      "learning_rate": 0.00019928301650252176,
+      "loss": 0.849348247051239,
+      "step": 1602
+    },
+    {
+      "epoch": 0.6921251348435814,
+      "grad_norm": 0.46086886525154114,
+      "learning_rate": 0.00019927713465085956,
+      "loss": 0.8298451900482178,
+      "step": 1604
+    },
+    {
+      "epoch": 0.6929881337648328,
+      "grad_norm": 0.42972785234451294,
+      "learning_rate": 0.00019927122885896387,
+      "loss": 0.8860712647438049,
+      "step": 1606
+    },
+    {
+      "epoch": 0.6938511326860841,
+      "grad_norm": 0.43009471893310547,
+      "learning_rate": 0.00019926529912825888,
+      "loss": 0.7972728610038757,
+      "step": 1608
+    },
+    {
+      "epoch": 0.6947141316073355,
+      "grad_norm": 0.3705308437347412,
+      "learning_rate": 0.00019925934546017446,
+      "loss": 0.8661653995513916,
+      "step": 1610
+    },
+    {
+      "epoch": 0.6955771305285868,
+      "grad_norm": 0.405208945274353,
+      "learning_rate": 0.00019925336785614635,
+      "loss": 0.8350111246109009,
+      "step": 1612
+    },
+    {
+      "epoch": 0.6964401294498382,
+      "grad_norm": 0.4773033857345581,
+      "learning_rate": 0.00019924736631761602,
+      "loss": 0.7920925617218018,
+      "step": 1614
+    },
+    {
+      "epoch": 0.6973031283710895,
+      "grad_norm": 0.4682428240776062,
+      "learning_rate": 0.00019924134084603075,
+      "loss": 0.8644304871559143,
+      "step": 1616
+    },
+    {
+      "epoch": 0.6981661272923408,
+      "grad_norm": 0.5694834589958191,
+      "learning_rate": 0.00019923529144284346,
+      "loss": 0.9897904992103577,
+      "step": 1618
+    },
+    {
+      "epoch": 0.6990291262135923,
+      "grad_norm": 0.40137484669685364,
+      "learning_rate": 0.00019922921810951302,
+      "loss": 0.6910083293914795,
+      "step": 1620
+    },
+    {
+      "epoch": 0.6998921251348436,
+      "grad_norm": 0.42076537013053894,
+      "learning_rate": 0.000199223120847504,
+      "loss": 0.8295826315879822,
+      "step": 1622
+    },
+    {
+      "epoch": 0.700755124056095,
+      "grad_norm": 0.4473017752170563,
+      "learning_rate": 0.00019921699965828662,
+      "loss": 0.820871889591217,
+      "step": 1624
+    },
+    {
+      "epoch": 0.7016181229773463,
+      "grad_norm": 0.43914029002189636,
+      "learning_rate": 0.00019921085454333706,
+      "loss": 0.8319019079208374,
+      "step": 1626
+    },
+    {
+      "epoch": 0.7024811218985976,
+      "grad_norm": 0.4758487939834595,
+      "learning_rate": 0.0001992046855041372,
+      "loss": 0.8589251041412354,
+      "step": 1628
+    },
+    {
+      "epoch": 0.703344120819849,
+      "grad_norm": 0.506401538848877,
+      "learning_rate": 0.00019919849254217465,
+      "loss": 0.9219205975532532,
+      "step": 1630
+    },
+    {
+      "epoch": 0.7042071197411003,
+      "grad_norm": 0.4397984445095062,
+      "learning_rate": 0.00019919227565894277,
+      "loss": 0.7824978232383728,
+      "step": 1632
+    },
+    {
+      "epoch": 0.7050701186623517,
+      "grad_norm": 0.3879252076148987,
+      "learning_rate": 0.0001991860348559408,
+      "loss": 0.8472069501876831,
+      "step": 1634
+    },
+    {
+      "epoch": 0.705933117583603,
+      "grad_norm": 0.42238810658454895,
+      "learning_rate": 0.00019917977013467368,
+      "loss": 0.824957013130188,
+      "step": 1636
+    },
+    {
+      "epoch": 0.7067961165048544,
+      "grad_norm": 0.5235037207603455,
+      "learning_rate": 0.00019917348149665206,
+      "loss": 0.9490993022918701,
+      "step": 1638
+    },
+    {
+      "epoch": 0.7076591154261057,
+      "grad_norm": 0.5195287466049194,
+      "learning_rate": 0.0001991671689433925,
+      "loss": 0.960905909538269,
+      "step": 1640
+    },
+    {
+      "epoch": 0.708522114347357,
+      "grad_norm": 0.5016481876373291,
+      "learning_rate": 0.00019916083247641716,
+      "loss": 0.8961218595504761,
+      "step": 1642
+    },
+    {
+      "epoch": 0.7093851132686084,
+      "grad_norm": 0.5510191321372986,
+      "learning_rate": 0.00019915447209725408,
+      "loss": 0.8883417844772339,
+      "step": 1644
+    },
+    {
+      "epoch": 0.7102481121898597,
+      "grad_norm": 0.4492250084877014,
+      "learning_rate": 0.0001991480878074371,
+      "loss": 0.7968636751174927,
+      "step": 1646
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.4189683496952057,
+      "learning_rate": 0.00019914167960850563,
+      "loss": 0.7869221568107605,
+      "step": 1648
+    },
+    {
+      "epoch": 0.7119741100323624,
+      "grad_norm": 0.4590536653995514,
+      "learning_rate": 0.0001991352475020051,
+      "loss": 0.8423646092414856,
+      "step": 1650
+    },
+    {
+      "epoch": 0.7128371089536139,
+      "grad_norm": 0.5058966875076294,
+      "learning_rate": 0.00019912879148948652,
+      "loss": 0.895459771156311,
+      "step": 1652
+    },
+    {
+      "epoch": 0.7137001078748652,
+      "grad_norm": 0.4904550313949585,
+      "learning_rate": 0.00019912231157250676,
+      "loss": 0.8737894296646118,
+      "step": 1654
+    },
+    {
+      "epoch": 0.7145631067961165,
+      "grad_norm": 0.4670710861682892,
+      "learning_rate": 0.0001991158077526284,
+      "loss": 0.8019732236862183,
+      "step": 1656
+    },
+    {
+      "epoch": 0.7154261057173679,
+      "grad_norm": 0.530343770980835,
+      "learning_rate": 0.00019910928003141984,
+      "loss": 0.9474499821662903,
+      "step": 1658
+    },
+    {
+      "epoch": 0.7162891046386192,
+      "grad_norm": 0.4250960052013397,
+      "learning_rate": 0.00019910272841045518,
+      "loss": 0.8738601803779602,
+      "step": 1660
+    },
+    {
+      "epoch": 0.7171521035598706,
+      "grad_norm": 0.4896513819694519,
+      "learning_rate": 0.0001990961528913143,
+      "loss": 0.9578261971473694,
+      "step": 1662
+    },
+    {
+      "epoch": 0.7180151024811219,
+      "grad_norm": 0.4999626576900482,
+      "learning_rate": 0.00019908955347558291,
+      "loss": 0.8116445541381836,
+      "step": 1664
+    },
+    {
+      "epoch": 0.7188781014023733,
+      "grad_norm": 0.4335242807865143,
+      "learning_rate": 0.00019908293016485237,
+      "loss": 0.8783043622970581,
+      "step": 1666
+    },
+    {
+      "epoch": 0.7197411003236246,
+      "grad_norm": 0.43542763590812683,
+      "learning_rate": 0.00019907628296071992,
+      "loss": 0.8223029375076294,
+      "step": 1668
+    },
+    {
+      "epoch": 0.7206040992448759,
+      "grad_norm": 0.4907461702823639,
+      "learning_rate": 0.00019906961186478842,
+      "loss": 1.0053197145462036,
+      "step": 1670
+    },
+    {
+      "epoch": 0.7214670981661273,
+      "grad_norm": 0.4054848253726959,
+      "learning_rate": 0.00019906291687866667,
+      "loss": 0.8107786178588867,
+      "step": 1672
+    },
+    {
+      "epoch": 0.7223300970873786,
+      "grad_norm": 0.3818599283695221,
+      "learning_rate": 0.0001990561980039691,
+      "loss": 0.780781626701355,
+      "step": 1674
+    },
+    {
+      "epoch": 0.72319309600863,
+      "grad_norm": 0.4128594994544983,
+      "learning_rate": 0.00019904945524231587,
+      "loss": 0.8189221620559692,
+      "step": 1676
+    },
+    {
+      "epoch": 0.7240560949298813,
+      "grad_norm": 0.46902593970298767,
+      "learning_rate": 0.0001990426885953331,
+      "loss": 0.83652263879776,
+      "step": 1678
+    },
+    {
+      "epoch": 0.7249190938511327,
+      "grad_norm": 0.49305564165115356,
+      "learning_rate": 0.00019903589806465242,
+      "loss": 0.8057956695556641,
+      "step": 1680
+    },
+    {
+      "epoch": 0.725782092772384,
+      "grad_norm": 0.44408300518989563,
+      "learning_rate": 0.0001990290836519114,
+      "loss": 0.8523716926574707,
+      "step": 1682
+    },
+    {
+      "epoch": 0.7266450916936353,
+      "grad_norm": 0.5211108922958374,
+      "learning_rate": 0.00019902224535875326,
+      "loss": 0.9179236888885498,
+      "step": 1684
+    },
+    {
+      "epoch": 0.7275080906148867,
+      "grad_norm": 0.4736526608467102,
+      "learning_rate": 0.00019901538318682705,
+      "loss": 0.8229476809501648,
+      "step": 1686
+    },
+    {
+      "epoch": 0.728371089536138,
+      "grad_norm": 0.541716992855072,
+      "learning_rate": 0.00019900849713778756,
+      "loss": 0.924200713634491,
+      "step": 1688
+    },
+    {
+      "epoch": 0.7292340884573895,
+      "grad_norm": 0.4524400532245636,
+      "learning_rate": 0.00019900158721329532,
+      "loss": 0.88961261510849,
+      "step": 1690
+    },
+    {
+      "epoch": 0.7300970873786408,
+      "grad_norm": 0.45256128907203674,
+      "learning_rate": 0.00019899465341501662,
+      "loss": 0.8491015434265137,
+      "step": 1692
+    },
+    {
+      "epoch": 0.7309600862998922,
+      "grad_norm": 0.5346773266792297,
+      "learning_rate": 0.0001989876957446235,
+      "loss": 0.8833339810371399,
+      "step": 1694
+    },
+    {
+      "epoch": 0.7318230852211435,
+      "grad_norm": 0.4696357846260071,
+      "learning_rate": 0.0001989807142037938,
+      "loss": 0.8535294532775879,
+      "step": 1696
+    },
+    {
+      "epoch": 0.7326860841423948,
+      "grad_norm": 0.4304637908935547,
+      "learning_rate": 0.0001989737087942111,
+      "loss": 0.8273076415061951,
+      "step": 1698
+    },
+    {
+      "epoch": 0.7335490830636462,
+      "grad_norm": 0.5085629224777222,
+      "learning_rate": 0.00019896667951756466,
+      "loss": 0.8759240508079529,
+      "step": 1700
+    },
+    {
+      "epoch": 0.7335490830636462,
+      "eval_loss": 0.879119336605072,
+      "eval_runtime": 663.0553,
+      "eval_samples_per_second": 3.107,
+      "eval_steps_per_second": 3.107,
+      "step": 1700
+    },
+    {
+      "epoch": 0.7344120819848975,
+      "grad_norm": 0.484223872423172,
+      "learning_rate": 0.00019895962637554964,
+      "loss": 0.852645218372345,
+      "step": 1702
+    },
+    {
+      "epoch": 0.7352750809061489,
+      "grad_norm": 0.4819294214248657,
+      "learning_rate": 0.0001989525493698668,
+      "loss": 0.878247857093811,
+      "step": 1704
+    },
+    {
+      "epoch": 0.7361380798274002,
+      "grad_norm": 0.4170311689376831,
+      "learning_rate": 0.00019894544850222276,
+      "loss": 0.8964285254478455,
+      "step": 1706
+    },
+    {
+      "epoch": 0.7370010787486516,
+      "grad_norm": 0.42712801694869995,
+      "learning_rate": 0.0001989383237743299,
+      "loss": 0.7479548454284668,
+      "step": 1708
+    },
+    {
+      "epoch": 0.7378640776699029,
+      "grad_norm": 0.5051686763763428,
+      "learning_rate": 0.00019893117518790624,
+      "loss": 0.8190052509307861,
+      "step": 1710
+    },
+    {
+      "epoch": 0.7387270765911542,
+      "grad_norm": 0.44053253531455994,
+      "learning_rate": 0.0001989240027446757,
+      "loss": 0.8646742105484009,
+      "step": 1712
+    },
+    {
+      "epoch": 0.7395900755124056,
+      "grad_norm": 0.4451025724411011,
+      "learning_rate": 0.00019891680644636782,
+      "loss": 0.874261736869812,
+      "step": 1714
+    },
+    {
+      "epoch": 0.7404530744336569,
+      "grad_norm": 0.4590521454811096,
+      "learning_rate": 0.00019890958629471798,
+      "loss": 0.8892465233802795,
+      "step": 1716
+    },
+    {
+      "epoch": 0.7413160733549083,
+      "grad_norm": 0.39169448614120483,
+      "learning_rate": 0.00019890234229146732,
+      "loss": 0.7031586766242981,
+      "step": 1718
+    },
+    {
+      "epoch": 0.7421790722761596,
+      "grad_norm": 0.46946024894714355,
+      "learning_rate": 0.00019889507443836266,
+      "loss": 0.8548433184623718,
+      "step": 1720
+    },
+    {
+      "epoch": 0.7430420711974111,
+      "grad_norm": 0.42404699325561523,
+      "learning_rate": 0.0001988877827371566,
+      "loss": 0.8231223821640015,
+      "step": 1722
+    },
+    {
+      "epoch": 0.7439050701186624,
+      "grad_norm": 0.40419483184814453,
+      "learning_rate": 0.00019888046718960755,
+      "loss": 0.8443762063980103,
+      "step": 1724
+    },
+    {
+      "epoch": 0.7447680690399137,
+      "grad_norm": 0.4550437927246094,
+      "learning_rate": 0.0001988731277974796,
+      "loss": 0.8787111639976501,
+      "step": 1726
+    },
+    {
+      "epoch": 0.7456310679611651,
+      "grad_norm": 0.42264053225517273,
+      "learning_rate": 0.0001988657645625426,
+      "loss": 0.8440850377082825,
+      "step": 1728
+    },
+    {
+      "epoch": 0.7464940668824164,
+      "grad_norm": 0.4638359844684601,
+      "learning_rate": 0.0001988583774865721,
+      "loss": 0.839216947555542,
+      "step": 1730
+    },
+    {
+      "epoch": 0.7473570658036678,
+      "grad_norm": 0.42644429206848145,
+      "learning_rate": 0.0001988509665713496,
+      "loss": 0.8011161684989929,
+      "step": 1732
+    },
+    {
+      "epoch": 0.7482200647249191,
+      "grad_norm": 0.36932024359703064,
+      "learning_rate": 0.0001988435318186621,
+      "loss": 0.850246787071228,
+      "step": 1734
+    },
+    {
+      "epoch": 0.7490830636461704,
+      "grad_norm": 0.4771935045719147,
+      "learning_rate": 0.00019883607323030252,
+      "loss": 0.7782483100891113,
+      "step": 1736
+    },
+    {
+      "epoch": 0.7499460625674218,
+      "grad_norm": 0.40007370710372925,
+      "learning_rate": 0.00019882859080806942,
+      "loss": 0.8337594866752625,
+      "step": 1738
+    },
+    {
+      "epoch": 0.7508090614886731,
+      "grad_norm": 0.5007418394088745,
+      "learning_rate": 0.00019882108455376716,
+      "loss": 0.8287386894226074,
+      "step": 1740
+    },
+    {
+      "epoch": 0.7516720604099245,
+      "grad_norm": 0.43999138474464417,
+      "learning_rate": 0.00019881355446920584,
+      "loss": 0.8655616044998169,
+      "step": 1742
+    },
+    {
+      "epoch": 0.7525350593311758,
+      "grad_norm": 0.5115824937820435,
+      "learning_rate": 0.00019880600055620135,
+      "loss": 0.8695262670516968,
+      "step": 1744
+    },
+    {
+      "epoch": 0.7533980582524272,
+      "grad_norm": 0.5035707950592041,
+      "learning_rate": 0.0001987984228165752,
+      "loss": 0.9207013845443726,
+      "step": 1746
+    },
+    {
+      "epoch": 0.7542610571736785,
+      "grad_norm": 0.4689575731754303,
+      "learning_rate": 0.0001987908212521548,
+      "loss": 0.8798729777336121,
+      "step": 1748
+    },
+    {
+      "epoch": 0.7551240560949298,
+      "grad_norm": 0.4730616509914398,
+      "learning_rate": 0.00019878319586477322,
+      "loss": 0.7737767696380615,
+      "step": 1750
+    },
+    {
+      "epoch": 0.7559870550161812,
+      "grad_norm": 0.49012845754623413,
+      "learning_rate": 0.00019877554665626926,
+      "loss": 0.929466187953949,
+      "step": 1752
+    },
+    {
+      "epoch": 0.7568500539374325,
+      "grad_norm": 0.43468761444091797,
+      "learning_rate": 0.0001987678736284875,
+      "loss": 0.8155670166015625,
+      "step": 1754
+    },
+    {
+      "epoch": 0.757713052858684,
+      "grad_norm": 0.507399320602417,
+      "learning_rate": 0.00019876017678327826,
+      "loss": 0.8082395195960999,
+      "step": 1756
+    },
+    {
+      "epoch": 0.7585760517799353,
+      "grad_norm": 0.4733552634716034,
+      "learning_rate": 0.0001987524561224976,
+      "loss": 0.8905934691429138,
+      "step": 1758
+    },
+    {
+      "epoch": 0.7594390507011867,
+      "grad_norm": 0.4670012891292572,
+      "learning_rate": 0.00019874471164800733,
+      "loss": 0.8794633746147156,
+      "step": 1760
+    },
+    {
+      "epoch": 0.760302049622438,
+      "grad_norm": 0.4951624572277069,
+      "learning_rate": 0.000198736943361675,
+      "loss": 0.8413973450660706,
+      "step": 1762
+    },
+    {
+      "epoch": 0.7611650485436893,
+      "grad_norm": 0.5478648543357849,
+      "learning_rate": 0.00019872915126537387,
+      "loss": 0.9067897200584412,
+      "step": 1764
+    },
+    {
+      "epoch": 0.7620280474649407,
+      "grad_norm": 0.48215776681900024,
+      "learning_rate": 0.000198721335360983,
+      "loss": 0.8932394981384277,
+      "step": 1766
+    },
+    {
+      "epoch": 0.762891046386192,
+      "grad_norm": 0.4688864052295685,
+      "learning_rate": 0.00019871349565038715,
+      "loss": 0.8496726751327515,
+      "step": 1768
+    },
+    {
+      "epoch": 0.7637540453074434,
+      "grad_norm": 0.4728260636329651,
+      "learning_rate": 0.0001987056321354768,
+      "loss": 0.9232800602912903,
+      "step": 1770
+    },
+    {
+      "epoch": 0.7646170442286947,
+      "grad_norm": 0.44501692056655884,
+      "learning_rate": 0.00019869774481814828,
+      "loss": 0.849755585193634,
+      "step": 1772
+    },
+    {
+      "epoch": 0.7654800431499461,
+      "grad_norm": 0.4189201593399048,
+      "learning_rate": 0.00019868983370030348,
+      "loss": 0.8258485794067383,
+      "step": 1774
+    },
+    {
+      "epoch": 0.7663430420711974,
+      "grad_norm": 0.5144591927528381,
+      "learning_rate": 0.00019868189878385016,
+      "loss": 0.8762873411178589,
+      "step": 1776
+    },
+    {
+      "epoch": 0.7672060409924487,
+      "grad_norm": 0.5048011541366577,
+      "learning_rate": 0.00019867394007070188,
+      "loss": 0.8732464909553528,
+      "step": 1778
+    },
+    {
+      "epoch": 0.7680690399137001,
+      "grad_norm": 0.41639819741249084,
+      "learning_rate": 0.00019866595756277774,
+      "loss": 0.8732751607894897,
+      "step": 1780
+    },
+    {
+      "epoch": 0.7689320388349514,
+      "grad_norm": 0.526757538318634,
+      "learning_rate": 0.00019865795126200271,
+      "loss": 0.8453729748725891,
+      "step": 1782
+    },
+    {
+      "epoch": 0.7697950377562028,
+      "grad_norm": 0.47041091322898865,
+      "learning_rate": 0.0001986499211703075,
+      "loss": 0.8780192732810974,
+      "step": 1784
+    },
+    {
+      "epoch": 0.7706580366774541,
+      "grad_norm": 0.4535890221595764,
+      "learning_rate": 0.0001986418672896285,
+      "loss": 0.8508450388908386,
+      "step": 1786
+    },
+    {
+      "epoch": 0.7715210355987056,
+      "grad_norm": 0.4608050286769867,
+      "learning_rate": 0.00019863378962190788,
+      "loss": 0.822467565536499,
+      "step": 1788
+    },
+    {
+      "epoch": 0.7723840345199569,
+      "grad_norm": 0.5190523862838745,
+      "learning_rate": 0.00019862568816909356,
+      "loss": 0.844614565372467,
+      "step": 1790
+    },
+    {
+      "epoch": 0.7732470334412082,
+      "grad_norm": 0.42502254247665405,
+      "learning_rate": 0.00019861756293313912,
+      "loss": 0.8144394755363464,
+      "step": 1792
+    },
+    {
+      "epoch": 0.7741100323624596,
+      "grad_norm": 0.47112616896629333,
+      "learning_rate": 0.000198609413916004,
+      "loss": 0.8836341500282288,
+      "step": 1794
+    },
+    {
+      "epoch": 0.7749730312837109,
+      "grad_norm": 0.48414838314056396,
+      "learning_rate": 0.0001986012411196532,
+      "loss": 0.8846262693405151,
+      "step": 1796
+    },
+    {
+      "epoch": 0.7758360302049623,
+      "grad_norm": 0.4670039415359497,
+      "learning_rate": 0.00019859304454605763,
+      "loss": 0.7993118762969971,
+      "step": 1798
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "grad_norm": 0.41939061880111694,
+      "learning_rate": 0.0001985848241971938,
+      "loss": 0.8389407396316528,
+      "step": 1800
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "eval_loss": 0.8727664947509766,
+      "eval_runtime": 668.2062,
+      "eval_samples_per_second": 3.083,
+      "eval_steps_per_second": 3.083,
+      "step": 1800
+    },
+    {
+      "epoch": 0.777562028047465,
+      "grad_norm": 0.4566517174243927,
+      "learning_rate": 0.00019857658007504405,
+      "loss": 0.8824291825294495,
+      "step": 1802
+    },
+    {
+      "epoch": 0.7784250269687163,
+      "grad_norm": 0.4798925518989563,
+      "learning_rate": 0.0001985683121815964,
+      "loss": 0.808982789516449,
+      "step": 1804
+    },
+    {
+      "epoch": 0.7792880258899676,
+      "grad_norm": 0.4659746587276459,
+      "learning_rate": 0.00019856002051884462,
+      "loss": 0.955269992351532,
+      "step": 1806
+    },
+    {
+      "epoch": 0.780151024811219,
+      "grad_norm": 0.48573991656303406,
+      "learning_rate": 0.00019855170508878818,
+      "loss": 0.8142994046211243,
+      "step": 1808
+    },
+    {
+      "epoch": 0.7810140237324703,
+      "grad_norm": 0.4700213670730591,
+      "learning_rate": 0.00019854336589343236,
+      "loss": 0.8755695819854736,
+      "step": 1810
+    },
+    {
+      "epoch": 0.7818770226537217,
+      "grad_norm": 0.42113450169563293,
+      "learning_rate": 0.00019853500293478806,
+      "loss": 0.8098483681678772,
+      "step": 1812
+    },
+    {
+      "epoch": 0.782740021574973,
+      "grad_norm": 0.4218153655529022,
+      "learning_rate": 0.00019852661621487205,
+      "loss": 0.8219783306121826,
+      "step": 1814
+    },
+    {
+      "epoch": 0.7836030204962244,
+      "grad_norm": 0.499052494764328,
+      "learning_rate": 0.00019851820573570664,
+      "loss": 0.8314159512519836,
+      "step": 1816
+    },
+    {
+      "epoch": 0.7844660194174757,
+      "grad_norm": 0.42420193552970886,
+      "learning_rate": 0.00019850977149932008,
+      "loss": 0.7985323071479797,
+      "step": 1818
+    },
+    {
+      "epoch": 0.785329018338727,
+      "grad_norm": 0.46345841884613037,
+      "learning_rate": 0.0001985013135077462,
+      "loss": 0.8528217077255249,
+      "step": 1820
+    },
+    {
+      "epoch": 0.7861920172599784,
+      "grad_norm": 0.4433307945728302,
+      "learning_rate": 0.00019849283176302462,
+      "loss": 0.8659319877624512,
+      "step": 1822
+    },
+    {
+      "epoch": 0.7870550161812297,
+      "grad_norm": 0.48279091715812683,
+      "learning_rate": 0.00019848432626720067,
+      "loss": 0.8675655126571655,
+      "step": 1824
+    },
+    {
+      "epoch": 0.7879180151024812,
+      "grad_norm": 0.5439180731773376,
+      "learning_rate": 0.0001984757970223254,
+      "loss": 0.8550227284431458,
+      "step": 1826
+    },
+    {
+      "epoch": 0.7887810140237325,
+      "grad_norm": 0.45749521255493164,
+      "learning_rate": 0.0001984672440304556,
+      "loss": 0.7290607690811157,
+      "step": 1828
+    },
+    {
+      "epoch": 0.7896440129449838,
+      "grad_norm": 0.4654783606529236,
+      "learning_rate": 0.00019845866729365378,
+      "loss": 0.8619251251220703,
+      "step": 1830
+    },
+    {
+      "epoch": 0.7905070118662352,
+      "grad_norm": 0.42632243037223816,
+      "learning_rate": 0.00019845006681398823,
+      "loss": 0.8249601125717163,
+      "step": 1832
+    },
+    {
+      "epoch": 0.7913700107874865,
+      "grad_norm": 0.4747186005115509,
+      "learning_rate": 0.0001984414425935329,
+      "loss": 0.7138552069664001,
+      "step": 1834
+    },
+    {
+      "epoch": 0.7922330097087379,
+      "grad_norm": 0.4462338387966156,
+      "learning_rate": 0.0001984327946343674,
+      "loss": 0.903292715549469,
+      "step": 1836
+    },
+    {
+      "epoch": 0.7930960086299892,
+      "grad_norm": 0.4581359922885895,
+      "learning_rate": 0.00019842412293857726,
+      "loss": 0.7569618225097656,
+      "step": 1838
+    },
+    {
+      "epoch": 0.7939590075512406,
+      "grad_norm": 0.4183015525341034,
+      "learning_rate": 0.00019841542750825356,
+      "loss": 0.8063036203384399,
+      "step": 1840
+    },
+    {
+      "epoch": 0.7948220064724919,
+      "grad_norm": 0.3954181373119354,
+      "learning_rate": 0.0001984067083454932,
+      "loss": 0.81150221824646,
+      "step": 1842
+    },
+    {
+      "epoch": 0.7956850053937432,
+      "grad_norm": 0.46220019459724426,
+      "learning_rate": 0.0001983979654523987,
+      "loss": 0.841649055480957,
+      "step": 1844
+    },
+    {
+      "epoch": 0.7965480043149946,
+      "grad_norm": 0.47807541489601135,
+      "learning_rate": 0.00019838919883107843,
+      "loss": 0.8019483685493469,
+      "step": 1846
+    },
+    {
+      "epoch": 0.7974110032362459,
+      "grad_norm": 0.48015692830085754,
+      "learning_rate": 0.0001983804084836464,
+      "loss": 0.9343363046646118,
+      "step": 1848
+    },
+    {
+      "epoch": 0.7982740021574973,
+      "grad_norm": 0.4906708896160126,
+      "learning_rate": 0.00019837159441222238,
+      "loss": 0.9163194894790649,
+      "step": 1850
+    },
+    {
+      "epoch": 0.7991370010787486,
+      "grad_norm": 0.4856911599636078,
+      "learning_rate": 0.0001983627566189318,
+      "loss": 0.8017736077308655,
+      "step": 1852
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.49403145909309387,
+      "learning_rate": 0.0001983538951059059,
+      "loss": 0.8375223875045776,
+      "step": 1854
+    },
+    {
+      "epoch": 0.8008629989212513,
+      "grad_norm": 0.4237985908985138,
+      "learning_rate": 0.00019834500987528158,
+      "loss": 0.8213951587677002,
+      "step": 1856
+    },
+    {
+      "epoch": 0.8017259978425026,
+      "grad_norm": 0.3977980315685272,
+      "learning_rate": 0.00019833610092920149,
+      "loss": 0.8086028099060059,
+      "step": 1858
+    },
+    {
+      "epoch": 0.8025889967637541,
+      "grad_norm": 0.435253381729126,
+      "learning_rate": 0.00019832716826981392,
+      "loss": 0.9402202367782593,
+      "step": 1860
+    },
+    {
+      "epoch": 0.8034519956850054,
+      "grad_norm": 0.4074764847755432,
+      "learning_rate": 0.000198318211899273,
+      "loss": 0.7730796933174133,
+      "step": 1862
+    },
+    {
+      "epoch": 0.8043149946062568,
+      "grad_norm": 0.48804348707199097,
+      "learning_rate": 0.0001983092318197385,
+      "loss": 0.9185802936553955,
+      "step": 1864
+    },
+    {
+      "epoch": 0.8051779935275081,
+      "grad_norm": 0.44363343715667725,
+      "learning_rate": 0.00019830022803337592,
+      "loss": 0.8578243851661682,
+      "step": 1866
+    },
+    {
+      "epoch": 0.8060409924487595,
+      "grad_norm": 0.46645957231521606,
+      "learning_rate": 0.00019829120054235653,
+      "loss": 0.8682060241699219,
+      "step": 1868
+    },
+    {
+      "epoch": 0.8069039913700108,
+      "grad_norm": 0.4527221620082855,
+      "learning_rate": 0.00019828214934885718,
+      "loss": 0.7845040559768677,
+      "step": 1870
+    },
+    {
+      "epoch": 0.8077669902912621,
+      "grad_norm": 0.4103536307811737,
+      "learning_rate": 0.0001982730744550606,
+      "loss": 0.8768247961997986,
+      "step": 1872
+    },
+    {
+      "epoch": 0.8086299892125135,
+      "grad_norm": 0.5257515907287598,
+      "learning_rate": 0.00019826397586315513,
+      "loss": 0.850267231464386,
+      "step": 1874
+    },
+    {
+      "epoch": 0.8094929881337648,
+      "grad_norm": 0.46675893664360046,
+      "learning_rate": 0.00019825485357533485,
+      "loss": 0.8234293460845947,
+      "step": 1876
+    },
+    {
+      "epoch": 0.8103559870550162,
+      "grad_norm": 0.46315401792526245,
+      "learning_rate": 0.00019824570759379958,
+      "loss": 0.8131387829780579,
+      "step": 1878
+    },
+    {
+      "epoch": 0.8112189859762675,
+      "grad_norm": 0.4766870439052582,
+      "learning_rate": 0.00019823653792075478,
+      "loss": 0.7680494785308838,
+      "step": 1880
+    },
+    {
+      "epoch": 0.8120819848975189,
+      "grad_norm": 0.39025625586509705,
+      "learning_rate": 0.00019822734455841173,
+      "loss": 0.7891425490379333,
+      "step": 1882
+    },
+    {
+      "epoch": 0.8129449838187702,
+      "grad_norm": 0.4672441780567169,
+      "learning_rate": 0.0001982181275089874,
+      "loss": 0.7990400791168213,
+      "step": 1884
+    },
+    {
+      "epoch": 0.8138079827400215,
+      "grad_norm": 0.44310975074768066,
+      "learning_rate": 0.00019820888677470432,
+      "loss": 0.7828341722488403,
+      "step": 1886
+    },
+    {
+      "epoch": 0.8146709816612729,
+      "grad_norm": 0.45098716020584106,
+      "learning_rate": 0.00019819962235779096,
+      "loss": 0.897715151309967,
+      "step": 1888
+    },
+    {
+      "epoch": 0.8155339805825242,
+      "grad_norm": 0.466805100440979,
+      "learning_rate": 0.00019819033426048135,
+      "loss": 0.7987668514251709,
+      "step": 1890
+    },
+    {
+      "epoch": 0.8163969795037757,
+      "grad_norm": 0.4438319206237793,
+      "learning_rate": 0.00019818102248501528,
+      "loss": 0.7950236201286316,
+      "step": 1892
+    },
+    {
+      "epoch": 0.817259978425027,
+      "grad_norm": 0.42012497782707214,
+      "learning_rate": 0.00019817168703363823,
+      "loss": 0.8789975643157959,
+      "step": 1894
+    },
+    {
+      "epoch": 0.8181229773462784,
+      "grad_norm": 0.4359394311904907,
+      "learning_rate": 0.0001981623279086014,
+      "loss": 0.8159777522087097,
+      "step": 1896
+    },
+    {
+      "epoch": 0.8189859762675297,
+      "grad_norm": 0.44709593057632446,
+      "learning_rate": 0.00019815294511216173,
+      "loss": 0.84877610206604,
+      "step": 1898
+    },
+    {
+      "epoch": 0.819848975188781,
+      "grad_norm": 0.4315306544303894,
+      "learning_rate": 0.00019814353864658184,
+      "loss": 0.8467556834220886,
+      "step": 1900
+    },
+    {
+      "epoch": 0.819848975188781,
+      "eval_loss": 0.8643407821655273,
+      "eval_runtime": 658.6942,
+      "eval_samples_per_second": 3.127,
+      "eval_steps_per_second": 3.127,
+      "step": 1900
+    },
+    {
+      "epoch": 0.8207119741100324,
+      "grad_norm": 0.35530397295951843,
+      "learning_rate": 0.00019813410851412998,
+      "loss": 0.7398589849472046,
+      "step": 1902
+    },
+    {
+      "epoch": 0.8215749730312837,
+      "grad_norm": 0.46949300169944763,
+      "learning_rate": 0.00019812465471708032,
+      "loss": 0.8544237613677979,
+      "step": 1904
+    },
+    {
+      "epoch": 0.8224379719525351,
+      "grad_norm": 0.4961565434932709,
+      "learning_rate": 0.00019811517725771248,
+      "loss": 0.8242526054382324,
+      "step": 1906
+    },
+    {
+      "epoch": 0.8233009708737864,
+      "grad_norm": 0.45835059881210327,
+      "learning_rate": 0.00019810567613831194,
+      "loss": 0.7856690287590027,
+      "step": 1908
+    },
+    {
+      "epoch": 0.8241639697950378,
+      "grad_norm": 0.4446084797382355,
+      "learning_rate": 0.0001980961513611699,
+      "loss": 0.8361829519271851,
+      "step": 1910
+    },
+    {
+      "epoch": 0.8250269687162891,
+      "grad_norm": 0.4470907747745514,
+      "learning_rate": 0.00019808660292858313,
+      "loss": 0.8993050456047058,
+      "step": 1912
+    },
+    {
+      "epoch": 0.8258899676375404,
+      "grad_norm": 0.44883644580841064,
+      "learning_rate": 0.0001980770308428543,
+      "loss": 0.8702824711799622,
+      "step": 1914
+    },
+    {
+      "epoch": 0.8267529665587918,
+      "grad_norm": 0.43215686082839966,
+      "learning_rate": 0.00019806743510629159,
+      "loss": 0.8454389572143555,
+      "step": 1916
+    },
+    {
+      "epoch": 0.8276159654800431,
+      "grad_norm": 0.4525185823440552,
+      "learning_rate": 0.00019805781572120897,
+      "loss": 0.8621824383735657,
+      "step": 1918
+    },
+    {
+      "epoch": 0.8284789644012945,
+      "grad_norm": 0.4616840183734894,
+      "learning_rate": 0.00019804817268992615,
+      "loss": 0.8661681413650513,
+      "step": 1920
+    },
+    {
+      "epoch": 0.8293419633225458,
+      "grad_norm": 0.4252975583076477,
+      "learning_rate": 0.0001980385060147685,
+      "loss": 0.8376660346984863,
+      "step": 1922
+    },
+    {
+      "epoch": 0.8302049622437971,
+      "grad_norm": 0.44600266218185425,
+      "learning_rate": 0.00019802881569806706,
+      "loss": 0.9258401393890381,
+      "step": 1924
+    },
+    {
+      "epoch": 0.8310679611650486,
+      "grad_norm": 0.48872479796409607,
+      "learning_rate": 0.00019801910174215866,
+      "loss": 0.8804965615272522,
+      "step": 1926
+    },
+    {
+      "epoch": 0.8319309600862999,
+      "grad_norm": 0.5357037782669067,
+      "learning_rate": 0.00019800936414938574,
+      "loss": 0.8561494946479797,
+      "step": 1928
+    },
+    {
+      "epoch": 0.8327939590075513,
+      "grad_norm": 0.39637291431427,
+      "learning_rate": 0.00019799960292209647,
+      "loss": 0.782166063785553,
+      "step": 1930
+    },
+    {
+      "epoch": 0.8336569579288026,
+      "grad_norm": 0.521138072013855,
+      "learning_rate": 0.00019798981806264476,
+      "loss": 0.9048293232917786,
+      "step": 1932
+    },
+    {
+      "epoch": 0.834519956850054,
+      "grad_norm": 0.4723529815673828,
+      "learning_rate": 0.00019798000957339015,
+      "loss": 0.9269952774047852,
+      "step": 1934
+    },
+    {
+      "epoch": 0.8353829557713053,
+      "grad_norm": 0.42827340960502625,
+      "learning_rate": 0.0001979701774566979,
+      "loss": 0.8620670437812805,
+      "step": 1936
+    },
+    {
+      "epoch": 0.8362459546925566,
+      "grad_norm": 0.4305116534233093,
+      "learning_rate": 0.00019796032171493907,
+      "loss": 0.8016669750213623,
+      "step": 1938
+    },
+    {
+      "epoch": 0.837108953613808,
+      "grad_norm": 0.4995502233505249,
+      "learning_rate": 0.00019795044235049024,
+      "loss": 0.879247784614563,
+      "step": 1940
+    },
+    {
+      "epoch": 0.8379719525350593,
+      "grad_norm": 0.49229878187179565,
+      "learning_rate": 0.0001979405393657338,
+      "loss": 0.9476580023765564,
+      "step": 1942
+    },
+    {
+      "epoch": 0.8388349514563107,
+      "grad_norm": 0.45756596326828003,
+      "learning_rate": 0.0001979306127630578,
+      "loss": 0.8654064536094666,
+      "step": 1944
+    },
+    {
+      "epoch": 0.839697950377562,
+      "grad_norm": 0.4855344891548157,
+      "learning_rate": 0.00019792066254485603,
+      "loss": 0.7792956829071045,
+      "step": 1946
+    },
+    {
+      "epoch": 0.8405609492988134,
+      "grad_norm": 0.4358632266521454,
+      "learning_rate": 0.00019791068871352787,
+      "loss": 0.8000320792198181,
+      "step": 1948
+    },
+    {
+      "epoch": 0.8414239482200647,
+      "grad_norm": 0.4225342273712158,
+      "learning_rate": 0.00019790069127147852,
+      "loss": 0.818372368812561,
+      "step": 1950
+    },
+    {
+      "epoch": 0.842286947141316,
+      "grad_norm": 0.3894529938697815,
+      "learning_rate": 0.00019789067022111886,
+      "loss": 0.727220892906189,
+      "step": 1952
+    },
+    {
+      "epoch": 0.8431499460625674,
+      "grad_norm": 0.5060731768608093,
+      "learning_rate": 0.0001978806255648653,
+      "loss": 0.894101083278656,
+      "step": 1954
+    },
+    {
+      "epoch": 0.8440129449838187,
+      "grad_norm": 0.4165003001689911,
+      "learning_rate": 0.0001978705573051402,
+      "loss": 0.878365695476532,
+      "step": 1956
+    },
+    {
+      "epoch": 0.8448759439050701,
+      "grad_norm": 0.48767927289009094,
+      "learning_rate": 0.0001978604654443714,
+      "loss": 0.8390909433364868,
+      "step": 1958
+    },
+    {
+      "epoch": 0.8457389428263214,
+      "grad_norm": 0.43019410967826843,
+      "learning_rate": 0.00019785034998499247,
+      "loss": 0.8807769417762756,
+      "step": 1960
+    },
+    {
+      "epoch": 0.8466019417475729,
+      "grad_norm": 0.4430403709411621,
+      "learning_rate": 0.0001978402109294428,
+      "loss": 0.8037779331207275,
+      "step": 1962
+    },
+    {
+      "epoch": 0.8474649406688242,
+      "grad_norm": 0.41642463207244873,
+      "learning_rate": 0.0001978300482801673,
+      "loss": 0.8341337442398071,
+      "step": 1964
+    },
+    {
+      "epoch": 0.8483279395900755,
+      "grad_norm": 0.45358774065971375,
+      "learning_rate": 0.00019781986203961668,
+      "loss": 0.854821503162384,
+      "step": 1966
+    },
+    {
+      "epoch": 0.8491909385113269,
+      "grad_norm": 0.4316342771053314,
+      "learning_rate": 0.00019780965221024728,
+      "loss": 0.8527678847312927,
+      "step": 1968
+    },
+    {
+      "epoch": 0.8500539374325782,
+      "grad_norm": 0.4581106901168823,
+      "learning_rate": 0.00019779941879452122,
+      "loss": 0.7461717128753662,
+      "step": 1970
+    },
+    {
+      "epoch": 0.8509169363538296,
+      "grad_norm": 0.49578142166137695,
+      "learning_rate": 0.0001977891617949062,
+      "loss": 0.884441077709198,
+      "step": 1972
+    },
+    {
+      "epoch": 0.8517799352750809,
+      "grad_norm": 0.4366011917591095,
+      "learning_rate": 0.00019777888121387562,
+      "loss": 0.855915904045105,
+      "step": 1974
+    },
+    {
+      "epoch": 0.8526429341963323,
+      "grad_norm": 0.486162930727005,
+      "learning_rate": 0.00019776857705390864,
+      "loss": 0.7563765645027161,
+      "step": 1976
+    },
+    {
+      "epoch": 0.8535059331175836,
+      "grad_norm": 0.5162674784660339,
+      "learning_rate": 0.00019775824931749005,
+      "loss": 0.8346326947212219,
+      "step": 1978
+    },
+    {
+      "epoch": 0.8543689320388349,
+      "grad_norm": 0.5824693441390991,
+      "learning_rate": 0.0001977478980071103,
+      "loss": 0.8701820969581604,
+      "step": 1980
+    },
+    {
+      "epoch": 0.8552319309600863,
+      "grad_norm": 0.4297148883342743,
+      "learning_rate": 0.00019773752312526565,
+      "loss": 0.893528938293457,
+      "step": 1982
+    },
+    {
+      "epoch": 0.8560949298813376,
+      "grad_norm": 0.42978280782699585,
+      "learning_rate": 0.00019772712467445788,
+      "loss": 0.8201018571853638,
+      "step": 1984
+    },
+    {
+      "epoch": 0.856957928802589,
+      "grad_norm": 0.5192655324935913,
+      "learning_rate": 0.00019771670265719454,
+      "loss": 0.9080212116241455,
+      "step": 1986
+    },
+    {
+      "epoch": 0.8578209277238403,
+      "grad_norm": 0.452690452337265,
+      "learning_rate": 0.00019770625707598885,
+      "loss": 0.8518272638320923,
+      "step": 1988
+    },
+    {
+      "epoch": 0.8586839266450917,
+      "grad_norm": 0.4371768832206726,
+      "learning_rate": 0.00019769578793335976,
+      "loss": 0.9426717758178711,
+      "step": 1990
+    },
+    {
+      "epoch": 0.859546925566343,
+      "grad_norm": 0.44595038890838623,
+      "learning_rate": 0.0001976852952318318,
+      "loss": 0.8065400123596191,
+      "step": 1992
+    },
+    {
+      "epoch": 0.8604099244875943,
+      "grad_norm": 0.4355090260505676,
+      "learning_rate": 0.0001976747789739353,
+      "loss": 0.7674415707588196,
+      "step": 1994
+    },
+    {
+      "epoch": 0.8612729234088458,
+      "grad_norm": 0.43745186924934387,
+      "learning_rate": 0.00019766423916220616,
+      "loss": 0.813849925994873,
+      "step": 1996
+    },
+    {
+      "epoch": 0.8621359223300971,
+      "grad_norm": 0.4588927924633026,
+      "learning_rate": 0.00019765367579918598,
+      "loss": 0.7870585322380066,
+      "step": 1998
+    },
+    {
+      "epoch": 0.8629989212513485,
+      "grad_norm": 0.4170977473258972,
+      "learning_rate": 0.00019764308888742214,
+      "loss": 0.8383269309997559,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8629989212513485,
+      "eval_loss": 0.8567262887954712,
+      "eval_runtime": 646.6443,
+      "eval_samples_per_second": 3.186,
+      "eval_steps_per_second": 3.186,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8638619201725998,
+      "grad_norm": 0.4819261431694031,
+      "learning_rate": 0.0001976324784294676,
+      "loss": 0.8261714577674866,
+      "step": 2002
+    },
+    {
+      "epoch": 0.8647249190938512,
+      "grad_norm": 0.4215400218963623,
+      "learning_rate": 0.00019762184442788098,
+      "loss": 0.8493392467498779,
+      "step": 2004
+    },
+    {
+      "epoch": 0.8655879180151025,
+      "grad_norm": 0.45448991656303406,
+      "learning_rate": 0.00019761118688522668,
+      "loss": 0.8645208477973938,
+      "step": 2006
+    },
+    {
+      "epoch": 0.8664509169363538,
+      "grad_norm": 0.4436458349227905,
+      "learning_rate": 0.0001976005058040747,
+      "loss": 0.8816449046134949,
+      "step": 2008
+    },
+    {
+      "epoch": 0.8673139158576052,
+      "grad_norm": 0.42662230134010315,
+      "learning_rate": 0.00019758980118700072,
+      "loss": 0.7622330784797668,
+      "step": 2010
+    },
+    {
+      "epoch": 0.8681769147788565,
+      "grad_norm": 0.3936038613319397,
+      "learning_rate": 0.0001975790730365861,
+      "loss": 0.7843833565711975,
+      "step": 2012
+    },
+    {
+      "epoch": 0.8690399137001079,
+      "grad_norm": 0.4460368752479553,
+      "learning_rate": 0.00019756832135541796,
+      "loss": 0.8294675946235657,
+      "step": 2014
+    },
+    {
+      "epoch": 0.8699029126213592,
+      "grad_norm": 0.47043702006340027,
+      "learning_rate": 0.00019755754614608892,
+      "loss": 0.851332426071167,
+      "step": 2016
+    },
+    {
+      "epoch": 0.8707659115426106,
+      "grad_norm": 0.4579448401927948,
+      "learning_rate": 0.00019754674741119746,
+      "loss": 0.8450362682342529,
+      "step": 2018
+    },
+    {
+      "epoch": 0.8716289104638619,
+      "grad_norm": 0.44362813234329224,
+      "learning_rate": 0.00019753592515334758,
+      "loss": 0.8585519194602966,
+      "step": 2020
+    },
+    {
+      "epoch": 0.8724919093851132,
+      "grad_norm": 0.4500923156738281,
+      "learning_rate": 0.00019752507937514905,
+      "loss": 0.8300179243087769,
+      "step": 2022
+    },
+    {
+      "epoch": 0.8733549083063646,
+      "grad_norm": 0.4330301582813263,
+      "learning_rate": 0.00019751421007921724,
+      "loss": 0.805014431476593,
+      "step": 2024
+    },
+    {
+      "epoch": 0.8742179072276159,
+      "grad_norm": 0.43873998522758484,
+      "learning_rate": 0.00019750331726817332,
+      "loss": 0.8228020071983337,
+      "step": 2026
+    },
+    {
+      "epoch": 0.8750809061488674,
+      "grad_norm": 0.47558829188346863,
+      "learning_rate": 0.00019749240094464395,
+      "loss": 0.8490906357765198,
+      "step": 2028
+    },
+    {
+      "epoch": 0.8759439050701187,
+      "grad_norm": 0.4285199046134949,
+      "learning_rate": 0.0001974814611112616,
+      "loss": 0.816324770450592,
+      "step": 2030
+    },
+    {
+      "epoch": 0.87680690399137,
+      "grad_norm": 0.4762725532054901,
+      "learning_rate": 0.0001974704977706644,
+      "loss": 0.9229121208190918,
+      "step": 2032
+    },
+    {
+      "epoch": 0.8776699029126214,
+      "grad_norm": 0.49856793880462646,
+      "learning_rate": 0.00019745951092549598,
+      "loss": 0.9847140908241272,
+      "step": 2034
+    },
+    {
+      "epoch": 0.8785329018338727,
+      "grad_norm": 0.5163881182670593,
+      "learning_rate": 0.00019744850057840587,
+      "loss": 0.8305321335792542,
+      "step": 2036
+    },
+    {
+      "epoch": 0.8793959007551241,
+      "grad_norm": 0.47826042771339417,
+      "learning_rate": 0.00019743746673204918,
+      "loss": 0.7909449934959412,
+      "step": 2038
+    },
+    {
+      "epoch": 0.8802588996763754,
+      "grad_norm": 0.44080349802970886,
+      "learning_rate": 0.0001974264093890866,
+      "loss": 0.809201180934906,
+      "step": 2040
+    },
+    {
+      "epoch": 0.8811218985976268,
+      "grad_norm": 0.46925660967826843,
+      "learning_rate": 0.00019741532855218464,
+      "loss": 0.8064218163490295,
+      "step": 2042
+    },
+    {
+      "epoch": 0.8819848975188781,
+      "grad_norm": 0.4223597049713135,
+      "learning_rate": 0.00019740422422401531,
+      "loss": 0.8135121464729309,
+      "step": 2044
+    },
+    {
+      "epoch": 0.8828478964401294,
+      "grad_norm": 0.46334266662597656,
+      "learning_rate": 0.00019739309640725642,
+      "loss": 0.8047984838485718,
+      "step": 2046
+    },
+    {
+      "epoch": 0.8837108953613808,
+      "grad_norm": 0.413682222366333,
+      "learning_rate": 0.0001973819451045914,
+      "loss": 0.7897430658340454,
+      "step": 2048
+    },
+    {
+      "epoch": 0.8845738942826321,
+      "grad_norm": 0.4276670515537262,
+      "learning_rate": 0.0001973707703187093,
+      "loss": 0.8411629796028137,
+      "step": 2050
+    },
+    {
+      "epoch": 0.8854368932038835,
+      "grad_norm": 0.4199331998825073,
+      "learning_rate": 0.0001973595720523049,
+      "loss": 0.7906913161277771,
+      "step": 2052
+    },
+    {
+      "epoch": 0.8862998921251348,
+      "grad_norm": 0.43233853578567505,
+      "learning_rate": 0.0001973483503080786,
+      "loss": 0.9042854309082031,
+      "step": 2054
+    },
+    {
+      "epoch": 0.8871628910463862,
+      "grad_norm": 0.41147297620773315,
+      "learning_rate": 0.00019733710508873647,
+      "loss": 0.8177635073661804,
+      "step": 2056
+    },
+    {
+      "epoch": 0.8880258899676375,
+      "grad_norm": 0.45957690477371216,
+      "learning_rate": 0.00019732583639699023,
+      "loss": 0.8867166042327881,
+      "step": 2058
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.3979831635951996,
+      "learning_rate": 0.00019731454423555728,
+      "loss": 0.7208530902862549,
+      "step": 2060
+    },
+    {
+      "epoch": 0.8897518878101403,
+      "grad_norm": 0.4434017837047577,
+      "learning_rate": 0.00019730322860716073,
+      "loss": 0.9158181548118591,
+      "step": 2062
+    },
+    {
+      "epoch": 0.8906148867313916,
+      "grad_norm": 0.40012025833129883,
+      "learning_rate": 0.00019729188951452922,
+      "loss": 0.8103255033493042,
+      "step": 2064
+    },
+    {
+      "epoch": 0.891477885652643,
+      "grad_norm": 0.41914620995521545,
+      "learning_rate": 0.00019728052696039715,
+      "loss": 0.7780100703239441,
+      "step": 2066
+    },
+    {
+      "epoch": 0.8923408845738943,
+      "grad_norm": 0.48365312814712524,
+      "learning_rate": 0.00019726914094750453,
+      "loss": 0.7105780839920044,
+      "step": 2068
+    },
+    {
+      "epoch": 0.8932038834951457,
+      "grad_norm": 0.4272058308124542,
+      "learning_rate": 0.0001972577314785971,
+      "loss": 0.7529635429382324,
+      "step": 2070
+    },
+    {
+      "epoch": 0.894066882416397,
+      "grad_norm": 0.48760271072387695,
+      "learning_rate": 0.00019724629855642612,
+      "loss": 0.836787223815918,
+      "step": 2072
+    },
+    {
+      "epoch": 0.8949298813376483,
+      "grad_norm": 0.47811925411224365,
+      "learning_rate": 0.00019723484218374865,
+      "loss": 0.8773119449615479,
+      "step": 2074
+    },
+    {
+      "epoch": 0.8957928802588997,
+      "grad_norm": 0.40109625458717346,
+      "learning_rate": 0.0001972233623633273,
+      "loss": 0.7151904106140137,
+      "step": 2076
+    },
+    {
+      "epoch": 0.896655879180151,
+      "grad_norm": 0.48640304803848267,
+      "learning_rate": 0.00019721185909793047,
+      "loss": 0.8348540663719177,
+      "step": 2078
+    },
+    {
+      "epoch": 0.8975188781014024,
+      "grad_norm": 0.45748841762542725,
+      "learning_rate": 0.000197200332390332,
+      "loss": 0.845246434211731,
+      "step": 2080
+    },
+    {
+      "epoch": 0.8983818770226537,
+      "grad_norm": 0.41650277376174927,
+      "learning_rate": 0.00019718878224331157,
+      "loss": 0.8746084570884705,
+      "step": 2082
+    },
+    {
+      "epoch": 0.8992448759439051,
+      "grad_norm": 0.45878589153289795,
+      "learning_rate": 0.00019717720865965443,
+      "loss": 0.8252862691879272,
+      "step": 2084
+    },
+    {
+      "epoch": 0.9001078748651564,
+      "grad_norm": 0.3710020184516907,
+      "learning_rate": 0.0001971656116421515,
+      "loss": 0.7056596875190735,
+      "step": 2086
+    },
+    {
+      "epoch": 0.9009708737864077,
+      "grad_norm": 0.4251181185245514,
+      "learning_rate": 0.00019715399119359935,
+      "loss": 0.8305537700653076,
+      "step": 2088
+    },
+    {
+      "epoch": 0.9018338727076591,
+      "grad_norm": 0.48429808020591736,
+      "learning_rate": 0.0001971423473168002,
+      "loss": 0.8431704044342041,
+      "step": 2090
+    },
+    {
+      "epoch": 0.9026968716289104,
+      "grad_norm": 0.5384030342102051,
+      "learning_rate": 0.00019713068001456186,
+      "loss": 0.8311790227890015,
+      "step": 2092
+    },
+    {
+      "epoch": 0.9035598705501618,
+      "grad_norm": 0.452029287815094,
+      "learning_rate": 0.00019711898928969796,
+      "loss": 0.8077114224433899,
+      "step": 2094
+    },
+    {
+      "epoch": 0.9044228694714131,
+      "grad_norm": 0.4427074193954468,
+      "learning_rate": 0.0001971072751450276,
+      "loss": 0.8454164266586304,
+      "step": 2096
+    },
+    {
+      "epoch": 0.9052858683926646,
+      "grad_norm": 0.4895693063735962,
+      "learning_rate": 0.00019709553758337557,
+      "loss": 0.8551414608955383,
+      "step": 2098
+    },
+    {
+      "epoch": 0.9061488673139159,
+      "grad_norm": 0.47199201583862305,
+      "learning_rate": 0.00019708377660757244,
+      "loss": 0.9158598184585571,
+      "step": 2100
+    },
+    {
+      "epoch": 0.9061488673139159,
+      "eval_loss": 0.8524587750434875,
+      "eval_runtime": 655.7682,
+      "eval_samples_per_second": 3.141,
+      "eval_steps_per_second": 3.141,
+      "step": 2100
+    },
+    {
+      "epoch": 0.9070118662351672,
+      "grad_norm": 0.45380064845085144,
+      "learning_rate": 0.00019707199222045415,
+      "loss": 0.8301376700401306,
+      "step": 2102
+    },
+    {
+      "epoch": 0.9078748651564186,
+      "grad_norm": 0.4775148034095764,
+      "learning_rate": 0.00019706018442486255,
+      "loss": 0.8191117644309998,
+      "step": 2104
+    },
+    {
+      "epoch": 0.9087378640776699,
+      "grad_norm": 0.40894538164138794,
+      "learning_rate": 0.00019704835322364506,
+      "loss": 0.8333686590194702,
+      "step": 2106
+    },
+    {
+      "epoch": 0.9096008629989213,
+      "grad_norm": 0.4202065169811249,
+      "learning_rate": 0.00019703649861965467,
+      "loss": 0.7916508913040161,
+      "step": 2108
+    },
+    {
+      "epoch": 0.9104638619201726,
+      "grad_norm": 0.39157143235206604,
+      "learning_rate": 0.00019702462061575008,
+      "loss": 0.8018013834953308,
+      "step": 2110
+    },
+    {
+      "epoch": 0.911326860841424,
+      "grad_norm": 0.4623039662837982,
+      "learning_rate": 0.00019701271921479565,
+      "loss": 0.8819739818572998,
+      "step": 2112
+    },
+    {
+      "epoch": 0.9121898597626753,
+      "grad_norm": 0.45183128118515015,
+      "learning_rate": 0.00019700079441966128,
+      "loss": 0.7652842402458191,
+      "step": 2114
+    },
+    {
+      "epoch": 0.9130528586839266,
+      "grad_norm": 0.4562322795391083,
+      "learning_rate": 0.00019698884623322262,
+      "loss": 0.817150890827179,
+      "step": 2116
+    },
+    {
+      "epoch": 0.913915857605178,
+      "grad_norm": 0.45955994725227356,
+      "learning_rate": 0.00019697687465836095,
+      "loss": 0.8223007917404175,
+      "step": 2118
+    },
+    {
+      "epoch": 0.9147788565264293,
+      "grad_norm": 0.44595572352409363,
+      "learning_rate": 0.00019696487969796307,
+      "loss": 0.7716509699821472,
+      "step": 2120
+    },
+    {
+      "epoch": 0.9156418554476807,
+      "grad_norm": 0.4380198121070862,
+      "learning_rate": 0.00019695286135492163,
+      "loss": 0.8205068111419678,
+      "step": 2122
+    },
+    {
+      "epoch": 0.916504854368932,
+      "grad_norm": 0.4025624692440033,
+      "learning_rate": 0.0001969408196321347,
+      "loss": 0.8126305341720581,
+      "step": 2124
+    },
+    {
+      "epoch": 0.9173678532901833,
+      "grad_norm": 0.424277663230896,
+      "learning_rate": 0.00019692875453250616,
+      "loss": 0.7840806841850281,
+      "step": 2126
+    },
+    {
+      "epoch": 0.9182308522114347,
+      "grad_norm": 0.4683000445365906,
+      "learning_rate": 0.00019691666605894538,
+      "loss": 0.9391030669212341,
+      "step": 2128
+    },
+    {
+      "epoch": 0.919093851132686,
+      "grad_norm": 0.47679048776626587,
+      "learning_rate": 0.00019690455421436754,
+      "loss": 0.8336083889007568,
+      "step": 2130
+    },
+    {
+      "epoch": 0.9199568500539375,
+      "grad_norm": 0.45669928193092346,
+      "learning_rate": 0.00019689241900169323,
+      "loss": 0.917514443397522,
+      "step": 2132
+    },
+    {
+      "epoch": 0.9208198489751888,
+      "grad_norm": 0.4372829794883728,
+      "learning_rate": 0.00019688026042384893,
+      "loss": 0.7798282504081726,
+      "step": 2134
+    },
+    {
+      "epoch": 0.9216828478964402,
+      "grad_norm": 0.4497234523296356,
+      "learning_rate": 0.00019686807848376655,
+      "loss": 0.7415590286254883,
+      "step": 2136
+    },
+    {
+      "epoch": 0.9225458468176915,
+      "grad_norm": 0.4892704486846924,
+      "learning_rate": 0.00019685587318438372,
+      "loss": 0.7713689208030701,
+      "step": 2138
+    },
+    {
+      "epoch": 0.9234088457389428,
+      "grad_norm": 0.490495502948761,
+      "learning_rate": 0.0001968436445286437,
+      "loss": 0.821044385433197,
+      "step": 2140
+    },
+    {
+      "epoch": 0.9242718446601942,
+      "grad_norm": 0.43616363406181335,
+      "learning_rate": 0.00019683139251949538,
+      "loss": 0.796081006526947,
+      "step": 2142
+    },
+    {
+      "epoch": 0.9251348435814455,
+      "grad_norm": 0.4199701249599457,
+      "learning_rate": 0.00019681911715989326,
+      "loss": 0.737835705280304,
+      "step": 2144
+    },
+    {
+      "epoch": 0.9259978425026969,
+      "grad_norm": 0.45367109775543213,
+      "learning_rate": 0.0001968068184527975,
+      "loss": 0.8224935531616211,
+      "step": 2146
+    },
+    {
+      "epoch": 0.9268608414239482,
+      "grad_norm": 0.43349263072013855,
+      "learning_rate": 0.0001967944964011739,
+      "loss": 0.826752245426178,
+      "step": 2148
+    },
+    {
+      "epoch": 0.9277238403451996,
+      "grad_norm": 0.4693690538406372,
+      "learning_rate": 0.00019678215100799384,
+      "loss": 0.8527786731719971,
+      "step": 2150
+    },
+    {
+      "epoch": 0.9285868392664509,
+      "grad_norm": 0.4281991124153137,
+      "learning_rate": 0.00019676978227623434,
+      "loss": 0.8101436495780945,
+      "step": 2152
+    },
+    {
+      "epoch": 0.9294498381877022,
+      "grad_norm": 0.4662301540374756,
+      "learning_rate": 0.0001967573902088781,
+      "loss": 0.8997542262077332,
+      "step": 2154
+    },
+    {
+      "epoch": 0.9303128371089536,
+      "grad_norm": 0.41807958483695984,
+      "learning_rate": 0.0001967449748089134,
+      "loss": 0.8378244638442993,
+      "step": 2156
+    },
+    {
+      "epoch": 0.9311758360302049,
+      "grad_norm": 0.4789344072341919,
+      "learning_rate": 0.00019673253607933416,
+      "loss": 0.8562051057815552,
+      "step": 2158
+    },
+    {
+      "epoch": 0.9320388349514563,
+      "grad_norm": 0.43706783652305603,
+      "learning_rate": 0.0001967200740231399,
+      "loss": 0.78457111120224,
+      "step": 2160
+    },
+    {
+      "epoch": 0.9329018338727076,
+      "grad_norm": 0.4441883862018585,
+      "learning_rate": 0.0001967075886433358,
+      "loss": 0.8058217763900757,
+      "step": 2162
+    },
+    {
+      "epoch": 0.933764832793959,
+      "grad_norm": 0.48960480093955994,
+      "learning_rate": 0.00019669507994293266,
+      "loss": 0.916145384311676,
+      "step": 2164
+    },
+    {
+      "epoch": 0.9346278317152104,
+      "grad_norm": 0.3990147113800049,
+      "learning_rate": 0.00019668254792494692,
+      "loss": 0.8805235028266907,
+      "step": 2166
+    },
+    {
+      "epoch": 0.9354908306364617,
+      "grad_norm": 0.4299201965332031,
+      "learning_rate": 0.00019666999259240056,
+      "loss": 0.8611101508140564,
+      "step": 2168
+    },
+    {
+      "epoch": 0.9363538295577131,
+      "grad_norm": 0.5267254114151001,
+      "learning_rate": 0.00019665741394832132,
+      "loss": 0.8429995179176331,
+      "step": 2170
+    },
+    {
+      "epoch": 0.9372168284789644,
+      "grad_norm": 0.46667975187301636,
+      "learning_rate": 0.0001966448119957424,
+      "loss": 0.8057775497436523,
+      "step": 2172
+    },
+    {
+      "epoch": 0.9380798274002158,
+      "grad_norm": 0.4140365421772003,
+      "learning_rate": 0.00019663218673770277,
+      "loss": 0.7456767559051514,
+      "step": 2174
+    },
+    {
+      "epoch": 0.9389428263214671,
+      "grad_norm": 0.4236559569835663,
+      "learning_rate": 0.00019661953817724692,
+      "loss": 0.7320394515991211,
+      "step": 2176
+    },
+    {
+      "epoch": 0.9398058252427185,
+      "grad_norm": 0.4075721800327301,
+      "learning_rate": 0.000196606866317425,
+      "loss": 0.7850301265716553,
+      "step": 2178
+    },
+    {
+      "epoch": 0.9406688241639698,
+      "grad_norm": 0.4638446271419525,
+      "learning_rate": 0.00019659417116129276,
+      "loss": 0.8228051662445068,
+      "step": 2180
+    },
+    {
+      "epoch": 0.9415318230852211,
+      "grad_norm": 0.4641942083835602,
+      "learning_rate": 0.00019658145271191164,
+      "loss": 0.8458912372589111,
+      "step": 2182
+    },
+    {
+      "epoch": 0.9423948220064725,
+      "grad_norm": 0.42868348956108093,
+      "learning_rate": 0.00019656871097234856,
+      "loss": 0.8002372980117798,
+      "step": 2184
+    },
+    {
+      "epoch": 0.9432578209277238,
+      "grad_norm": 0.4726828336715698,
+      "learning_rate": 0.00019655594594567615,
+      "loss": 0.9096182584762573,
+      "step": 2186
+    },
+    {
+      "epoch": 0.9441208198489752,
+      "grad_norm": 0.40363940596580505,
+      "learning_rate": 0.00019654315763497265,
+      "loss": 0.7508110404014587,
+      "step": 2188
+    },
+    {
+      "epoch": 0.9449838187702265,
+      "grad_norm": 0.46951010823249817,
+      "learning_rate": 0.00019653034604332192,
+      "loss": 0.8898510932922363,
+      "step": 2190
+    },
+    {
+      "epoch": 0.9458468176914779,
+      "grad_norm": 0.4564061164855957,
+      "learning_rate": 0.0001965175111738134,
+      "loss": 0.8604891896247864,
+      "step": 2192
+    },
+    {
+      "epoch": 0.9467098166127292,
+      "grad_norm": 0.4366895854473114,
+      "learning_rate": 0.00019650465302954219,
+      "loss": 0.8314935564994812,
+      "step": 2194
+    },
+    {
+      "epoch": 0.9475728155339805,
+      "grad_norm": 0.541490375995636,
+      "learning_rate": 0.0001964917716136089,
+      "loss": 0.851138174533844,
+      "step": 2196
+    },
+    {
+      "epoch": 0.948435814455232,
+      "grad_norm": 0.45251160860061646,
+      "learning_rate": 0.0001964788669291199,
+      "loss": 0.9248369336128235,
+      "step": 2198
+    },
+    {
+      "epoch": 0.9492988133764833,
+      "grad_norm": 0.46237683296203613,
+      "learning_rate": 0.00019646593897918707,
+      "loss": 0.8113608956336975,
+      "step": 2200
+    },
+    {
+      "epoch": 0.9492988133764833,
+      "eval_loss": 0.8443478941917419,
+      "eval_runtime": 666.5866,
+      "eval_samples_per_second": 3.09,
+      "eval_steps_per_second": 3.09,
+      "step": 2200
+    },
+    {
+      "epoch": 0.9501618122977347,
+      "grad_norm": 0.4506337344646454,
+      "learning_rate": 0.0001964529877669279,
+      "loss": 0.8151772618293762,
+      "step": 2202
+    },
+    {
+      "epoch": 0.951024811218986,
+      "grad_norm": 0.42866984009742737,
+      "learning_rate": 0.00019644001329546557,
+      "loss": 0.920696496963501,
+      "step": 2204
+    },
+    {
+      "epoch": 0.9518878101402374,
+      "grad_norm": 0.3899093270301819,
+      "learning_rate": 0.00019642701556792878,
+      "loss": 0.8228384256362915,
+      "step": 2206
+    },
+    {
+      "epoch": 0.9527508090614887,
+      "grad_norm": 0.42472460865974426,
+      "learning_rate": 0.00019641399458745186,
+      "loss": 0.7483987808227539,
+      "step": 2208
+    },
+    {
+      "epoch": 0.95361380798274,
+      "grad_norm": 0.4046783447265625,
+      "learning_rate": 0.00019640095035717482,
+      "loss": 0.7356619834899902,
+      "step": 2210
+    },
+    {
+      "epoch": 0.9544768069039914,
+      "grad_norm": 0.4608006179332733,
+      "learning_rate": 0.00019638788288024316,
+      "loss": 0.7374731302261353,
+      "step": 2212
+    },
+    {
+      "epoch": 0.9553398058252427,
+      "grad_norm": 0.448503315448761,
+      "learning_rate": 0.00019637479215980807,
+      "loss": 0.9128687977790833,
+      "step": 2214
+    },
+    {
+      "epoch": 0.9562028047464941,
+      "grad_norm": 0.4477374851703644,
+      "learning_rate": 0.0001963616781990263,
+      "loss": 0.6983766555786133,
+      "step": 2216
+    },
+    {
+      "epoch": 0.9570658036677454,
+      "grad_norm": 0.41463667154312134,
+      "learning_rate": 0.00019634854100106025,
+      "loss": 0.8543318510055542,
+      "step": 2218
+    },
+    {
+      "epoch": 0.9579288025889967,
+      "grad_norm": 0.5271132588386536,
+      "learning_rate": 0.00019633538056907786,
+      "loss": 0.8866401314735413,
+      "step": 2220
+    },
+    {
+      "epoch": 0.9587918015102481,
+      "grad_norm": 0.4496590495109558,
+      "learning_rate": 0.00019632219690625272,
+      "loss": 0.8414724469184875,
+      "step": 2222
+    },
+    {
+      "epoch": 0.9596548004314994,
+      "grad_norm": 0.4772113263607025,
+      "learning_rate": 0.00019630899001576405,
+      "loss": 0.8859618902206421,
+      "step": 2224
+    },
+    {
+      "epoch": 0.9605177993527508,
+      "grad_norm": 0.5249642729759216,
+      "learning_rate": 0.0001962957599007966,
+      "loss": 0.8347851037979126,
+      "step": 2226
+    },
+    {
+      "epoch": 0.9613807982740021,
+      "grad_norm": 0.4931469261646271,
+      "learning_rate": 0.0001962825065645407,
+      "loss": 0.7893235087394714,
+      "step": 2228
+    },
+    {
+      "epoch": 0.9622437971952535,
+      "grad_norm": 0.45010602474212646,
+      "learning_rate": 0.00019626923001019245,
+      "loss": 0.815602719783783,
+      "step": 2230
+    },
+    {
+      "epoch": 0.9631067961165048,
+      "grad_norm": 0.42947128415107727,
+      "learning_rate": 0.00019625593024095333,
+      "loss": 0.807309627532959,
+      "step": 2232
+    },
+    {
+      "epoch": 0.9639697950377561,
+      "grad_norm": 0.43500378727912903,
+      "learning_rate": 0.00019624260726003057,
+      "loss": 0.8135440945625305,
+      "step": 2234
+    },
+    {
+      "epoch": 0.9648327939590076,
+      "grad_norm": 0.41840270161628723,
+      "learning_rate": 0.00019622926107063692,
+      "loss": 0.802107036113739,
+      "step": 2236
+    },
+    {
+      "epoch": 0.9656957928802589,
+      "grad_norm": 0.4580598771572113,
+      "learning_rate": 0.00019621589167599077,
+      "loss": 0.7596800923347473,
+      "step": 2238
+    },
+    {
+      "epoch": 0.9665587918015103,
+      "grad_norm": 0.38064274191856384,
+      "learning_rate": 0.0001962024990793161,
+      "loss": 0.7609489560127258,
+      "step": 2240
+    },
+    {
+      "epoch": 0.9674217907227616,
+      "grad_norm": 0.39098140597343445,
+      "learning_rate": 0.00019618908328384246,
+      "loss": 0.7829734086990356,
+      "step": 2242
+    },
+    {
+      "epoch": 0.968284789644013,
+      "grad_norm": 0.38412022590637207,
+      "learning_rate": 0.00019617564429280502,
+      "loss": 0.7570722699165344,
+      "step": 2244
+    },
+    {
+      "epoch": 0.9691477885652643,
+      "grad_norm": 0.41451776027679443,
+      "learning_rate": 0.0001961621821094445,
+      "loss": 0.8634825348854065,
+      "step": 2246
+    },
+    {
+      "epoch": 0.9700107874865156,
+      "grad_norm": 0.4989950954914093,
+      "learning_rate": 0.00019614869673700725,
+      "loss": 0.9002810120582581,
+      "step": 2248
+    },
+    {
+      "epoch": 0.970873786407767,
+      "grad_norm": 0.4316846430301666,
+      "learning_rate": 0.00019613518817874524,
+      "loss": 0.7587819695472717,
+      "step": 2250
+    },
+    {
+      "epoch": 0.9717367853290183,
+      "grad_norm": 0.41293349862098694,
+      "learning_rate": 0.000196121656437916,
+      "loss": 0.686238706111908,
+      "step": 2252
+    },
+    {
+      "epoch": 0.9725997842502697,
+      "grad_norm": 0.40252262353897095,
+      "learning_rate": 0.00019610810151778258,
+      "loss": 0.7895162105560303,
+      "step": 2254
+    },
+    {
+      "epoch": 0.973462783171521,
+      "grad_norm": 0.42973560094833374,
+      "learning_rate": 0.0001960945234216138,
+      "loss": 0.8360300064086914,
+      "step": 2256
+    },
+    {
+      "epoch": 0.9743257820927724,
+      "grad_norm": 0.40562206506729126,
+      "learning_rate": 0.00019608092215268386,
+      "loss": 0.7624704241752625,
+      "step": 2258
+    },
+    {
+      "epoch": 0.9751887810140237,
+      "grad_norm": 0.4486660063266754,
+      "learning_rate": 0.00019606729771427266,
+      "loss": 0.8285008072853088,
+      "step": 2260
+    },
+    {
+      "epoch": 0.976051779935275,
+      "grad_norm": 0.37069520354270935,
+      "learning_rate": 0.0001960536501096657,
+      "loss": 0.7951943278312683,
+      "step": 2262
+    },
+    {
+      "epoch": 0.9769147788565264,
+      "grad_norm": 0.43367981910705566,
+      "learning_rate": 0.00019603997934215404,
+      "loss": 0.7641335129737854,
+      "step": 2264
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.42540937662124634,
+      "learning_rate": 0.00019602628541503432,
+      "loss": 0.8449530601501465,
+      "step": 2266
+    },
+    {
+      "epoch": 0.9786407766990292,
+      "grad_norm": 0.46175941824913025,
+      "learning_rate": 0.00019601256833160874,
+      "loss": 0.8207030296325684,
+      "step": 2268
+    },
+    {
+      "epoch": 0.9795037756202805,
+      "grad_norm": 0.3834969103336334,
+      "learning_rate": 0.00019599882809518513,
+      "loss": 0.7753700017929077,
+      "step": 2270
+    },
+    {
+      "epoch": 0.9803667745415319,
+      "grad_norm": 0.43960243463516235,
+      "learning_rate": 0.0001959850647090769,
+      "loss": 0.8844934701919556,
+      "step": 2272
+    },
+    {
+      "epoch": 0.9812297734627832,
+      "grad_norm": 0.4240610897541046,
+      "learning_rate": 0.00019597127817660303,
+      "loss": 0.7795814275741577,
+      "step": 2274
+    },
+    {
+      "epoch": 0.9820927723840345,
+      "grad_norm": 0.41870981454849243,
+      "learning_rate": 0.00019595746850108807,
+      "loss": 0.6960644721984863,
+      "step": 2276
+    },
+    {
+      "epoch": 0.9829557713052859,
+      "grad_norm": 0.43871861696243286,
+      "learning_rate": 0.00019594363568586215,
+      "loss": 0.7709649205207825,
+      "step": 2278
+    },
+    {
+      "epoch": 0.9838187702265372,
+      "grad_norm": 0.45331820845603943,
+      "learning_rate": 0.00019592977973426098,
+      "loss": 0.7324449419975281,
+      "step": 2280
+    },
+    {
+      "epoch": 0.9846817691477886,
+      "grad_norm": 0.4300173223018646,
+      "learning_rate": 0.00019591590064962593,
+      "loss": 0.8720724582672119,
+      "step": 2282
+    },
+    {
+      "epoch": 0.9855447680690399,
+      "grad_norm": 0.4478892982006073,
+      "learning_rate": 0.0001959019984353038,
+      "loss": 0.7396156191825867,
+      "step": 2284
+    },
+    {
+      "epoch": 0.9864077669902913,
+      "grad_norm": 0.4391026198863983,
+      "learning_rate": 0.00019588807309464708,
+      "loss": 0.8303509950637817,
+      "step": 2286
+    },
+    {
+      "epoch": 0.9872707659115426,
+      "grad_norm": 0.4046599268913269,
+      "learning_rate": 0.00019587412463101378,
+      "loss": 0.739641010761261,
+      "step": 2288
+    },
+    {
+      "epoch": 0.9881337648327939,
+      "grad_norm": 0.4619915187358856,
+      "learning_rate": 0.00019586015304776756,
+      "loss": 0.7448247671127319,
+      "step": 2290
+    },
+    {
+      "epoch": 0.9889967637540453,
+      "grad_norm": 0.4603526294231415,
+      "learning_rate": 0.00019584615834827753,
+      "loss": 0.8184107542037964,
+      "step": 2292
+    },
+    {
+      "epoch": 0.9898597626752966,
+      "grad_norm": 0.4828874170780182,
+      "learning_rate": 0.00019583214053591852,
+      "loss": 0.9069648385047913,
+      "step": 2294
+    },
+    {
+      "epoch": 0.990722761596548,
+      "grad_norm": 0.37467876076698303,
+      "learning_rate": 0.00019581809961407082,
+      "loss": 0.6628880500793457,
+      "step": 2296
+    },
+    {
+      "epoch": 0.9915857605177993,
+      "grad_norm": 0.4300445318222046,
+      "learning_rate": 0.00019580403558612037,
+      "loss": 0.7712231278419495,
+      "step": 2298
+    },
+    {
+      "epoch": 0.9924487594390508,
+      "grad_norm": 0.4368257522583008,
+      "learning_rate": 0.00019578994845545863,
+      "loss": 0.7796293497085571,
+      "step": 2300
+    },
+    {
+      "epoch": 0.9924487594390508,
+      "eval_loss": 0.839731752872467,
+      "eval_runtime": 666.2332,
+      "eval_samples_per_second": 3.092,
+      "eval_steps_per_second": 3.092,
+      "step": 2300
+    },
+    {
+      "epoch": 0.993311758360302,
+      "grad_norm": 0.4383920729160309,
+      "learning_rate": 0.00019577583822548262,
+      "loss": 0.7504367232322693,
+      "step": 2302
+    },
+    {
+      "epoch": 0.9941747572815534,
+      "grad_norm": 0.3895981013774872,
+      "learning_rate": 0.00019576170489959496,
+      "loss": 0.7298936247825623,
+      "step": 2304
+    },
+    {
+      "epoch": 0.9950377562028048,
+      "grad_norm": 0.4950196444988251,
+      "learning_rate": 0.00019574754848120392,
+      "loss": 0.9137371778488159,
+      "step": 2306
+    },
+    {
+      "epoch": 0.9959007551240561,
+      "grad_norm": 0.5115531086921692,
+      "learning_rate": 0.00019573336897372318,
+      "loss": 0.9203279614448547,
+      "step": 2308
+    },
+    {
+      "epoch": 0.9967637540453075,
+      "grad_norm": 0.43145665526390076,
+      "learning_rate": 0.000195719166380572,
+      "loss": 0.7708958387374878,
+      "step": 2310
+    },
+    {
+      "epoch": 0.9976267529665588,
+      "grad_norm": 0.39575520157814026,
+      "learning_rate": 0.00019570494070517545,
+      "loss": 0.7911062836647034,
+      "step": 2312
+    },
+    {
+      "epoch": 0.9984897518878102,
+      "grad_norm": 0.45690420269966125,
+      "learning_rate": 0.00019569069195096386,
+      "loss": 0.8282244205474854,
+      "step": 2314
+    },
+    {
+      "epoch": 0.9993527508090615,
+      "grad_norm": 0.43362128734588623,
+      "learning_rate": 0.00019567642012137325,
+      "loss": 0.8658884763717651,
+      "step": 2316
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6889842748641968,
+      "learning_rate": 0.00019566212521984527,
+      "loss": 0.7823468446731567,
+      "step": 2318
+    },
+    {
+      "epoch": 1.0008629989212514,
+      "grad_norm": 0.3945363759994507,
+      "learning_rate": 0.00019564780724982706,
+      "loss": 0.8244057297706604,
+      "step": 2320
+    },
+    {
+      "epoch": 1.0017259978425026,
+      "grad_norm": 0.5313655734062195,
+      "learning_rate": 0.00019563346621477129,
+      "loss": 0.8228418827056885,
+      "step": 2322
+    },
+    {
+      "epoch": 1.002588996763754,
+      "grad_norm": 0.47728294134140015,
+      "learning_rate": 0.00019561910211813625,
+      "loss": 0.8627800941467285,
+      "step": 2324
+    },
+    {
+      "epoch": 1.0034519956850054,
+      "grad_norm": 0.4706253111362457,
+      "learning_rate": 0.00019560471496338582,
+      "loss": 0.8810665011405945,
+      "step": 2326
+    },
+    {
+      "epoch": 1.0043149946062568,
+      "grad_norm": 0.4333725571632385,
+      "learning_rate": 0.0001955903047539893,
+      "loss": 0.7736411094665527,
+      "step": 2328
+    },
+    {
+      "epoch": 1.005177993527508,
+      "grad_norm": 0.49580323696136475,
+      "learning_rate": 0.00019557587149342178,
+      "loss": 0.9185295104980469,
+      "step": 2330
+    },
+    {
+      "epoch": 1.0060409924487594,
+      "grad_norm": 0.4362829029560089,
+      "learning_rate": 0.0001955614151851637,
+      "loss": 0.7387797832489014,
+      "step": 2332
+    },
+    {
+      "epoch": 1.0069039913700109,
+      "grad_norm": 0.42584139108657837,
+      "learning_rate": 0.00019554693583270113,
+      "loss": 0.672156810760498,
+      "step": 2334
+    },
+    {
+      "epoch": 1.007766990291262,
+      "grad_norm": 0.40073466300964355,
+      "learning_rate": 0.0001955324334395257,
+      "loss": 0.7638119459152222,
+      "step": 2336
+    },
+    {
+      "epoch": 1.0086299892125135,
+      "grad_norm": 0.49992597103118896,
+      "learning_rate": 0.00019551790800913458,
+      "loss": 0.7930200695991516,
+      "step": 2338
+    },
+    {
+      "epoch": 1.0094929881337649,
+      "grad_norm": 0.3825504779815674,
+      "learning_rate": 0.00019550335954503058,
+      "loss": 0.7128595113754272,
+      "step": 2340
+    },
+    {
+      "epoch": 1.0103559870550163,
+      "grad_norm": 0.4654180705547333,
+      "learning_rate": 0.00019548878805072196,
+      "loss": 0.7130335569381714,
+      "step": 2342
+    },
+    {
+      "epoch": 1.0112189859762675,
+      "grad_norm": 0.4199283719062805,
+      "learning_rate": 0.00019547419352972258,
+      "loss": 0.7843249440193176,
+      "step": 2344
+    },
+    {
+      "epoch": 1.0120819848975189,
+      "grad_norm": 0.43597257137298584,
+      "learning_rate": 0.0001954595759855518,
+      "loss": 0.676262617111206,
+      "step": 2346
+    },
+    {
+      "epoch": 1.0129449838187703,
+      "grad_norm": 0.47415891289711,
+      "learning_rate": 0.0001954449354217346,
+      "loss": 0.742564857006073,
+      "step": 2348
+    },
+    {
+      "epoch": 1.0138079827400215,
+      "grad_norm": 0.44753482937812805,
+      "learning_rate": 0.00019543027184180153,
+      "loss": 0.7419085502624512,
+      "step": 2350
+    },
+    {
+      "epoch": 1.014670981661273,
+      "grad_norm": 0.4175751209259033,
+      "learning_rate": 0.0001954155852492886,
+      "loss": 0.7373939752578735,
+      "step": 2352
+    },
+    {
+      "epoch": 1.0155339805825243,
+      "grad_norm": 0.40376800298690796,
+      "learning_rate": 0.00019540087564773738,
+      "loss": 0.7639825344085693,
+      "step": 2354
+    },
+    {
+      "epoch": 1.0163969795037757,
+      "grad_norm": 0.4166127145290375,
+      "learning_rate": 0.0001953861430406951,
+      "loss": 0.7797452211380005,
+      "step": 2356
+    },
+    {
+      "epoch": 1.017259978425027,
+      "grad_norm": 0.4340934753417969,
+      "learning_rate": 0.0001953713874317144,
+      "loss": 0.8258501887321472,
+      "step": 2358
+    },
+    {
+      "epoch": 1.0181229773462783,
+      "grad_norm": 0.47081413865089417,
+      "learning_rate": 0.0001953566088243536,
+      "loss": 0.7664495706558228,
+      "step": 2360
+    },
+    {
+      "epoch": 1.0189859762675297,
+      "grad_norm": 0.4126851260662079,
+      "learning_rate": 0.00019534180722217644,
+      "loss": 0.7411028742790222,
+      "step": 2362
+    },
+    {
+      "epoch": 1.019848975188781,
+      "grad_norm": 0.45279955863952637,
+      "learning_rate": 0.00019532698262875227,
+      "loss": 0.7514335513114929,
+      "step": 2364
+    },
+    {
+      "epoch": 1.0207119741100323,
+      "grad_norm": 0.4857143461704254,
+      "learning_rate": 0.00019531213504765595,
+      "loss": 0.7544763088226318,
+      "step": 2366
+    },
+    {
+      "epoch": 1.0215749730312838,
+      "grad_norm": 0.5232970714569092,
+      "learning_rate": 0.00019529726448246795,
+      "loss": 0.7246702313423157,
+      "step": 2368
+    },
+    {
+      "epoch": 1.0224379719525352,
+      "grad_norm": 0.4434663653373718,
+      "learning_rate": 0.00019528237093677424,
+      "loss": 0.7399187684059143,
+      "step": 2370
+    },
+    {
+      "epoch": 1.0233009708737864,
+      "grad_norm": 0.44713014364242554,
+      "learning_rate": 0.0001952674544141663,
+      "loss": 0.7208506464958191,
+      "step": 2372
+    },
+    {
+      "epoch": 1.0241639697950378,
+      "grad_norm": 0.43205446004867554,
+      "learning_rate": 0.0001952525149182412,
+      "loss": 0.761768639087677,
+      "step": 2374
+    },
+    {
+      "epoch": 1.0250269687162892,
+      "grad_norm": 0.4322265386581421,
+      "learning_rate": 0.0001952375524526015,
+      "loss": 0.6573513746261597,
+      "step": 2376
+    },
+    {
+      "epoch": 1.0258899676375404,
+      "grad_norm": 0.4776996970176697,
+      "learning_rate": 0.0001952225670208554,
+      "loss": 0.8118118047714233,
+      "step": 2378
+    },
+    {
+      "epoch": 1.0267529665587918,
+      "grad_norm": 0.5014623403549194,
+      "learning_rate": 0.00019520755862661648,
+      "loss": 0.781197190284729,
+      "step": 2380
+    },
+    {
+      "epoch": 1.0276159654800432,
+      "grad_norm": 0.5164223313331604,
+      "learning_rate": 0.00019519252727350403,
+      "loss": 0.8399010896682739,
+      "step": 2382
+    },
+    {
+      "epoch": 1.0284789644012946,
+      "grad_norm": 0.47874927520751953,
+      "learning_rate": 0.00019517747296514276,
+      "loss": 0.786519467830658,
+      "step": 2384
+    },
+    {
+      "epoch": 1.0293419633225458,
+      "grad_norm": 0.48447099328041077,
+      "learning_rate": 0.00019516239570516292,
+      "loss": 0.7837404012680054,
+      "step": 2386
+    },
+    {
+      "epoch": 1.0302049622437972,
+      "grad_norm": 0.4762440323829651,
+      "learning_rate": 0.0001951472954972004,
+      "loss": 0.833958625793457,
+      "step": 2388
+    },
+    {
+      "epoch": 1.0310679611650486,
+      "grad_norm": 0.42814165353775024,
+      "learning_rate": 0.00019513217234489645,
+      "loss": 0.7688734531402588,
+      "step": 2390
+    },
+    {
+      "epoch": 1.0319309600862998,
+      "grad_norm": 0.4784977436065674,
+      "learning_rate": 0.00019511702625189803,
+      "loss": 0.814251720905304,
+      "step": 2392
+    },
+    {
+      "epoch": 1.0327939590075512,
+      "grad_norm": 0.44989243149757385,
+      "learning_rate": 0.00019510185722185748,
+      "loss": 0.7277538180351257,
+      "step": 2394
+    },
+    {
+      "epoch": 1.0336569579288026,
+      "grad_norm": 0.5141931772232056,
+      "learning_rate": 0.0001950866652584328,
+      "loss": 0.844467282295227,
+      "step": 2396
+    },
+    {
+      "epoch": 1.0345199568500538,
+      "grad_norm": 0.48569414019584656,
+      "learning_rate": 0.00019507145036528747,
+      "loss": 0.7662147879600525,
+      "step": 2398
+    },
+    {
+      "epoch": 1.0353829557713052,
+      "grad_norm": 0.5075576901435852,
+      "learning_rate": 0.00019505621254609047,
+      "loss": 0.7628200054168701,
+      "step": 2400
+    },
+    {
+      "epoch": 1.0353829557713052,
+      "eval_loss": 0.8369861245155334,
+      "eval_runtime": 653.1661,
+      "eval_samples_per_second": 3.154,
+      "eval_steps_per_second": 3.154,
+      "step": 2400
+    },
+    {
+      "epoch": 1.0362459546925566,
+      "grad_norm": 0.49423643946647644,
+      "learning_rate": 0.00019504095180451628,
+      "loss": 0.8225719332695007,
+      "step": 2402
+    },
+    {
+      "epoch": 1.037108953613808,
+      "grad_norm": 0.4558854401111603,
+      "learning_rate": 0.00019502566814424505,
+      "loss": 0.8239169120788574,
+      "step": 2404
+    },
+    {
+      "epoch": 1.0379719525350593,
+      "grad_norm": 0.4864993691444397,
+      "learning_rate": 0.00019501036156896232,
+      "loss": 0.7805002331733704,
+      "step": 2406
+    },
+    {
+      "epoch": 1.0388349514563107,
+      "grad_norm": 0.44108837842941284,
+      "learning_rate": 0.00019499503208235918,
+      "loss": 0.866910994052887,
+      "step": 2408
+    },
+    {
+      "epoch": 1.039697950377562,
+      "grad_norm": 0.4616626799106598,
+      "learning_rate": 0.00019497967968813232,
+      "loss": 0.7601662874221802,
+      "step": 2410
+    },
+    {
+      "epoch": 1.0405609492988135,
+      "grad_norm": 0.4792969524860382,
+      "learning_rate": 0.00019496430438998387,
+      "loss": 0.8155668377876282,
+      "step": 2412
+    },
+    {
+      "epoch": 1.0414239482200647,
+      "grad_norm": 0.45400261878967285,
+      "learning_rate": 0.00019494890619162152,
+      "loss": 0.7879545092582703,
+      "step": 2414
+    },
+    {
+      "epoch": 1.042286947141316,
+      "grad_norm": 0.44541165232658386,
+      "learning_rate": 0.0001949334850967585,
+      "loss": 0.7196864485740662,
+      "step": 2416
+    },
+    {
+      "epoch": 1.0431499460625675,
+      "grad_norm": 0.44515085220336914,
+      "learning_rate": 0.00019491804110911343,
+      "loss": 0.7288097739219666,
+      "step": 2418
+    },
+    {
+      "epoch": 1.0440129449838187,
+      "grad_norm": 0.43586596846580505,
+      "learning_rate": 0.0001949025742324107,
+      "loss": 0.7182422280311584,
+      "step": 2420
+    },
+    {
+      "epoch": 1.04487594390507,
+      "grad_norm": 0.44399815797805786,
+      "learning_rate": 0.00019488708447038002,
+      "loss": 0.7005030512809753,
+      "step": 2422
+    },
+    {
+      "epoch": 1.0457389428263215,
+      "grad_norm": 0.4658401310443878,
+      "learning_rate": 0.00019487157182675665,
+      "loss": 0.715505063533783,
+      "step": 2424
+    },
+    {
+      "epoch": 1.0466019417475727,
+      "grad_norm": 0.4468056261539459,
+      "learning_rate": 0.00019485603630528143,
+      "loss": 0.7170135974884033,
+      "step": 2426
+    },
+    {
+      "epoch": 1.0474649406688241,
+      "grad_norm": 0.5302334427833557,
+      "learning_rate": 0.00019484047790970066,
+      "loss": 0.83464115858078,
+      "step": 2428
+    },
+    {
+      "epoch": 1.0483279395900755,
+      "grad_norm": 0.46583443880081177,
+      "learning_rate": 0.0001948248966437662,
+      "loss": 0.7129145264625549,
+      "step": 2430
+    },
+    {
+      "epoch": 1.049190938511327,
+      "grad_norm": 0.38922831416130066,
+      "learning_rate": 0.0001948092925112354,
+      "loss": 0.7990599870681763,
+      "step": 2432
+    },
+    {
+      "epoch": 1.0500539374325781,
+      "grad_norm": 0.4599211513996124,
+      "learning_rate": 0.00019479366551587108,
+      "loss": 0.8572773933410645,
+      "step": 2434
+    },
+    {
+      "epoch": 1.0509169363538295,
+      "grad_norm": 0.47514498233795166,
+      "learning_rate": 0.00019477801566144165,
+      "loss": 0.8107781410217285,
+      "step": 2436
+    },
+    {
+      "epoch": 1.051779935275081,
+      "grad_norm": 0.41368064284324646,
+      "learning_rate": 0.00019476234295172102,
+      "loss": 0.7433347702026367,
+      "step": 2438
+    },
+    {
+      "epoch": 1.0526429341963321,
+      "grad_norm": 0.4666398763656616,
+      "learning_rate": 0.00019474664739048858,
+      "loss": 0.8033983111381531,
+      "step": 2440
+    },
+    {
+      "epoch": 1.0535059331175836,
+      "grad_norm": 0.41621699929237366,
+      "learning_rate": 0.00019473092898152924,
+      "loss": 0.7320330142974854,
+      "step": 2442
+    },
+    {
+      "epoch": 1.054368932038835,
+      "grad_norm": 0.43523117899894714,
+      "learning_rate": 0.00019471518772863343,
+      "loss": 0.7742927074432373,
+      "step": 2444
+    },
+    {
+      "epoch": 1.0552319309600864,
+      "grad_norm": 0.5151914358139038,
+      "learning_rate": 0.0001946994236355971,
+      "loss": 0.8301699161529541,
+      "step": 2446
+    },
+    {
+      "epoch": 1.0560949298813376,
+      "grad_norm": 0.566112756729126,
+      "learning_rate": 0.0001946836367062216,
+      "loss": 0.837057888507843,
+      "step": 2448
+    },
+    {
+      "epoch": 1.056957928802589,
+      "grad_norm": 0.4257231652736664,
+      "learning_rate": 0.00019466782694431398,
+      "loss": 0.7323788404464722,
+      "step": 2450
+    },
+    {
+      "epoch": 1.0578209277238404,
+      "grad_norm": 0.5477433800697327,
+      "learning_rate": 0.0001946519943536867,
+      "loss": 0.7410078048706055,
+      "step": 2452
+    },
+    {
+      "epoch": 1.0586839266450916,
+      "grad_norm": 0.37357097864151,
+      "learning_rate": 0.00019463613893815762,
+      "loss": 0.6646532416343689,
+      "step": 2454
+    },
+    {
+      "epoch": 1.059546925566343,
+      "grad_norm": 0.438048779964447,
+      "learning_rate": 0.00019462026070155028,
+      "loss": 0.7773549556732178,
+      "step": 2456
+    },
+    {
+      "epoch": 1.0604099244875944,
+      "grad_norm": 0.5114307999610901,
+      "learning_rate": 0.0001946043596476936,
+      "loss": 0.8977773785591125,
+      "step": 2458
+    },
+    {
+      "epoch": 1.0612729234088458,
+      "grad_norm": 0.4340408146381378,
+      "learning_rate": 0.0001945884357804221,
+      "loss": 0.8128405809402466,
+      "step": 2460
+    },
+    {
+      "epoch": 1.062135922330097,
+      "grad_norm": 0.4922826290130615,
+      "learning_rate": 0.0001945724891035757,
+      "loss": 0.8096795678138733,
+      "step": 2462
+    },
+    {
+      "epoch": 1.0629989212513484,
+      "grad_norm": 0.47231894731521606,
+      "learning_rate": 0.00019455651962099987,
+      "loss": 0.7965760231018066,
+      "step": 2464
+    },
+    {
+      "epoch": 1.0638619201725998,
+      "grad_norm": 0.4519463777542114,
+      "learning_rate": 0.00019454052733654565,
+      "loss": 0.7136726975440979,
+      "step": 2466
+    },
+    {
+      "epoch": 1.064724919093851,
+      "grad_norm": 0.44883614778518677,
+      "learning_rate": 0.0001945245122540694,
+      "loss": 0.8136170506477356,
+      "step": 2468
+    },
+    {
+      "epoch": 1.0655879180151024,
+      "grad_norm": 0.4224080741405487,
+      "learning_rate": 0.00019450847437743317,
+      "loss": 0.7840399146080017,
+      "step": 2470
+    },
+    {
+      "epoch": 1.0664509169363539,
+      "grad_norm": 0.4979367256164551,
+      "learning_rate": 0.00019449241371050438,
+      "loss": 0.8202947378158569,
+      "step": 2472
+    },
+    {
+      "epoch": 1.0673139158576053,
+      "grad_norm": 0.5551356673240662,
+      "learning_rate": 0.000194476330257156,
+      "loss": 0.8608070611953735,
+      "step": 2474
+    },
+    {
+      "epoch": 1.0681769147788565,
+      "grad_norm": 0.3980900049209595,
+      "learning_rate": 0.00019446022402126647,
+      "loss": 0.7202636003494263,
+      "step": 2476
+    },
+    {
+      "epoch": 1.0690399137001079,
+      "grad_norm": 0.5393417477607727,
+      "learning_rate": 0.00019444409500671977,
+      "loss": 0.8301891684532166,
+      "step": 2478
+    },
+    {
+      "epoch": 1.0699029126213593,
+      "grad_norm": 0.47717350721359253,
+      "learning_rate": 0.0001944279432174053,
+      "loss": 0.700567901134491,
+      "step": 2480
+    },
+    {
+      "epoch": 1.0707659115426105,
+      "grad_norm": 0.5197957158088684,
+      "learning_rate": 0.000194411768657218,
+      "loss": 0.794978141784668,
+      "step": 2482
+    },
+    {
+      "epoch": 1.0716289104638619,
+      "grad_norm": 0.5289306044578552,
+      "learning_rate": 0.0001943955713300583,
+      "loss": 0.8052116632461548,
+      "step": 2484
+    },
+    {
+      "epoch": 1.0724919093851133,
+      "grad_norm": 0.4360409080982208,
+      "learning_rate": 0.00019437935123983212,
+      "loss": 0.750991702079773,
+      "step": 2486
+    },
+    {
+      "epoch": 1.0733549083063647,
+      "grad_norm": 0.38651731610298157,
+      "learning_rate": 0.00019436310839045085,
+      "loss": 0.6631898880004883,
+      "step": 2488
+    },
+    {
+      "epoch": 1.074217907227616,
+      "grad_norm": 0.4376210868358612,
+      "learning_rate": 0.00019434684278583138,
+      "loss": 0.7995471358299255,
+      "step": 2490
+    },
+    {
+      "epoch": 1.0750809061488673,
+      "grad_norm": 0.46636906266212463,
+      "learning_rate": 0.0001943305544298961,
+      "loss": 0.7633864879608154,
+      "step": 2492
+    },
+    {
+      "epoch": 1.0759439050701187,
+      "grad_norm": 0.43499618768692017,
+      "learning_rate": 0.00019431424332657288,
+      "loss": 0.7281562089920044,
+      "step": 2494
+    },
+    {
+      "epoch": 1.07680690399137,
+      "grad_norm": 0.39683374762535095,
+      "learning_rate": 0.000194297909479795,
+      "loss": 0.7313723564147949,
+      "step": 2496
+    },
+    {
+      "epoch": 1.0776699029126213,
+      "grad_norm": 0.4545603096485138,
+      "learning_rate": 0.0001942815528935014,
+      "loss": 0.7120141983032227,
+      "step": 2498
+    },
+    {
+      "epoch": 1.0785329018338727,
+      "grad_norm": 0.5040699243545532,
+      "learning_rate": 0.0001942651735716363,
+      "loss": 0.752600908279419,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0785329018338727,
+      "eval_loss": 0.8323014378547668,
+      "eval_runtime": 652.3791,
+      "eval_samples_per_second": 3.158,
+      "eval_steps_per_second": 3.158,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0793959007551241,
+      "grad_norm": 0.48951438069343567,
+      "learning_rate": 0.00019424877151814958,
+      "loss": 0.7719982266426086,
+      "step": 2502
+    },
+    {
+      "epoch": 1.0802588996763753,
+      "grad_norm": 0.5009822845458984,
+      "learning_rate": 0.00019423234673699648,
+      "loss": 0.7921367883682251,
+      "step": 2504
+    },
+    {
+      "epoch": 1.0811218985976268,
+      "grad_norm": 0.4699440896511078,
+      "learning_rate": 0.00019421589923213772,
+      "loss": 0.7714369297027588,
+      "step": 2506
+    },
+    {
+      "epoch": 1.0819848975188782,
+      "grad_norm": 0.4438663125038147,
+      "learning_rate": 0.00019419942900753963,
+      "loss": 0.6981601119041443,
+      "step": 2508
+    },
+    {
+      "epoch": 1.0828478964401294,
+      "grad_norm": 0.49927031993865967,
+      "learning_rate": 0.00019418293606717385,
+      "loss": 0.7822043895721436,
+      "step": 2510
+    },
+    {
+      "epoch": 1.0837108953613808,
+      "grad_norm": 0.395433634519577,
+      "learning_rate": 0.00019416642041501767,
+      "loss": 0.7166627049446106,
+      "step": 2512
+    },
+    {
+      "epoch": 1.0845738942826322,
+      "grad_norm": 0.47293251752853394,
+      "learning_rate": 0.00019414988205505366,
+      "loss": 0.7287489771842957,
+      "step": 2514
+    },
+    {
+      "epoch": 1.0854368932038836,
+      "grad_norm": 0.43168675899505615,
+      "learning_rate": 0.00019413332099127008,
+      "loss": 0.7672322988510132,
+      "step": 2516
+    },
+    {
+      "epoch": 1.0862998921251348,
+      "grad_norm": 0.4542049765586853,
+      "learning_rate": 0.00019411673722766044,
+      "loss": 0.7427115440368652,
+      "step": 2518
+    },
+    {
+      "epoch": 1.0871628910463862,
+      "grad_norm": 0.4920838177204132,
+      "learning_rate": 0.00019410013076822394,
+      "loss": 0.742889404296875,
+      "step": 2520
+    },
+    {
+      "epoch": 1.0880258899676376,
+      "grad_norm": 0.5404410362243652,
+      "learning_rate": 0.0001940835016169651,
+      "loss": 0.767113208770752,
+      "step": 2522
+    },
+    {
+      "epoch": 1.0888888888888888,
+      "grad_norm": 0.4543033540248871,
+      "learning_rate": 0.00019406684977789395,
+      "loss": 0.6729961037635803,
+      "step": 2524
+    },
+    {
+      "epoch": 1.0897518878101402,
+      "grad_norm": 0.49171510338783264,
+      "learning_rate": 0.00019405017525502607,
+      "loss": 0.6907814145088196,
+      "step": 2526
+    },
+    {
+      "epoch": 1.0906148867313916,
+      "grad_norm": 0.491252601146698,
+      "learning_rate": 0.00019403347805238238,
+      "loss": 0.7643960118293762,
+      "step": 2528
+    },
+    {
+      "epoch": 1.091477885652643,
+      "grad_norm": 0.527920663356781,
+      "learning_rate": 0.0001940167581739894,
+      "loss": 0.8070526123046875,
+      "step": 2530
+    },
+    {
+      "epoch": 1.0923408845738942,
+      "grad_norm": 0.4318726658821106,
+      "learning_rate": 0.00019400001562387898,
+      "loss": 0.7900120615959167,
+      "step": 2532
+    },
+    {
+      "epoch": 1.0932038834951456,
+      "grad_norm": 0.4903397560119629,
+      "learning_rate": 0.00019398325040608855,
+      "loss": 0.7778371572494507,
+      "step": 2534
+    },
+    {
+      "epoch": 1.094066882416397,
+      "grad_norm": 0.4835105240345001,
+      "learning_rate": 0.00019396646252466097,
+      "loss": 0.7758864164352417,
+      "step": 2536
+    },
+    {
+      "epoch": 1.0949298813376482,
+      "grad_norm": 0.47125598788261414,
+      "learning_rate": 0.00019394965198364455,
+      "loss": 0.7927643656730652,
+      "step": 2538
+    },
+    {
+      "epoch": 1.0957928802588996,
+      "grad_norm": 0.46723976731300354,
+      "learning_rate": 0.0001939328187870931,
+      "loss": 0.7884714007377625,
+      "step": 2540
+    },
+    {
+      "epoch": 1.096655879180151,
+      "grad_norm": 0.46274980902671814,
+      "learning_rate": 0.00019391596293906582,
+      "loss": 0.7663765549659729,
+      "step": 2542
+    },
+    {
+      "epoch": 1.0975188781014025,
+      "grad_norm": 0.431887149810791,
+      "learning_rate": 0.00019389908444362747,
+      "loss": 0.6656131744384766,
+      "step": 2544
+    },
+    {
+      "epoch": 1.0983818770226537,
+      "grad_norm": 0.5138527750968933,
+      "learning_rate": 0.00019388218330484823,
+      "loss": 0.795498788356781,
+      "step": 2546
+    },
+    {
+      "epoch": 1.099244875943905,
+      "grad_norm": 0.4679732024669647,
+      "learning_rate": 0.00019386525952680365,
+      "loss": 0.807344377040863,
+      "step": 2548
+    },
+    {
+      "epoch": 1.1001078748651565,
+      "grad_norm": 0.473088800907135,
+      "learning_rate": 0.0001938483131135749,
+      "loss": 0.6828449368476868,
+      "step": 2550
+    },
+    {
+      "epoch": 1.1009708737864077,
+      "grad_norm": 0.49941009283065796,
+      "learning_rate": 0.00019383134406924856,
+      "loss": 0.8669595122337341,
+      "step": 2552
+    },
+    {
+      "epoch": 1.101833872707659,
+      "grad_norm": 0.47401952743530273,
+      "learning_rate": 0.00019381435239791656,
+      "loss": 0.7382985949516296,
+      "step": 2554
+    },
+    {
+      "epoch": 1.1026968716289105,
+      "grad_norm": 0.47803637385368347,
+      "learning_rate": 0.0001937973381036764,
+      "loss": 0.7240811586380005,
+      "step": 2556
+    },
+    {
+      "epoch": 1.103559870550162,
+      "grad_norm": 0.4534960985183716,
+      "learning_rate": 0.000193780301190631,
+      "loss": 0.736165463924408,
+      "step": 2558
+    },
+    {
+      "epoch": 1.104422869471413,
+      "grad_norm": 0.4594196677207947,
+      "learning_rate": 0.0001937632416628887,
+      "loss": 0.7364692091941833,
+      "step": 2560
+    },
+    {
+      "epoch": 1.1052858683926645,
+      "grad_norm": 0.45354577898979187,
+      "learning_rate": 0.0001937461595245634,
+      "loss": 0.803584635257721,
+      "step": 2562
+    },
+    {
+      "epoch": 1.106148867313916,
+      "grad_norm": 0.47314611077308655,
+      "learning_rate": 0.00019372905477977432,
+      "loss": 0.7224286794662476,
+      "step": 2564
+    },
+    {
+      "epoch": 1.1070118662351671,
+      "grad_norm": 0.4453343451023102,
+      "learning_rate": 0.0001937119274326462,
+      "loss": 0.7446297407150269,
+      "step": 2566
+    },
+    {
+      "epoch": 1.1078748651564185,
+      "grad_norm": 0.5266496539115906,
+      "learning_rate": 0.0001936947774873093,
+      "loss": 0.7666438817977905,
+      "step": 2568
+    },
+    {
+      "epoch": 1.10873786407767,
+      "grad_norm": 0.44142624735832214,
+      "learning_rate": 0.00019367760494789913,
+      "loss": 0.8593260049819946,
+      "step": 2570
+    },
+    {
+      "epoch": 1.1096008629989211,
+      "grad_norm": 0.552436888217926,
+      "learning_rate": 0.00019366040981855682,
+      "loss": 0.7768570184707642,
+      "step": 2572
+    },
+    {
+      "epoch": 1.1104638619201725,
+      "grad_norm": 0.4223164916038513,
+      "learning_rate": 0.0001936431921034289,
+      "loss": 0.7356681823730469,
+      "step": 2574
+    },
+    {
+      "epoch": 1.111326860841424,
+      "grad_norm": 0.5104808211326599,
+      "learning_rate": 0.0001936259518066674,
+      "loss": 0.7693892121315002,
+      "step": 2576
+    },
+    {
+      "epoch": 1.1121898597626754,
+      "grad_norm": 0.40713393688201904,
+      "learning_rate": 0.00019360868893242967,
+      "loss": 0.7651313543319702,
+      "step": 2578
+    },
+    {
+      "epoch": 1.1130528586839266,
+      "grad_norm": 0.4819444417953491,
+      "learning_rate": 0.00019359140348487858,
+      "loss": 0.8427110314369202,
+      "step": 2580
+    },
+    {
+      "epoch": 1.113915857605178,
+      "grad_norm": 0.45872536301612854,
+      "learning_rate": 0.00019357409546818247,
+      "loss": 0.7783478498458862,
+      "step": 2582
+    },
+    {
+      "epoch": 1.1147788565264294,
+      "grad_norm": 0.43954113125801086,
+      "learning_rate": 0.00019355676488651508,
+      "loss": 0.6625193357467651,
+      "step": 2584
+    },
+    {
+      "epoch": 1.1156418554476808,
+      "grad_norm": 0.4524446725845337,
+      "learning_rate": 0.00019353941174405558,
+      "loss": 0.7208001613616943,
+      "step": 2586
+    },
+    {
+      "epoch": 1.116504854368932,
+      "grad_norm": 0.4748269021511078,
+      "learning_rate": 0.0001935220360449886,
+      "loss": 0.7567161917686462,
+      "step": 2588
+    },
+    {
+      "epoch": 1.1173678532901834,
+      "grad_norm": 0.4493826925754547,
+      "learning_rate": 0.00019350463779350423,
+      "loss": 0.7631603479385376,
+      "step": 2590
+    },
+    {
+      "epoch": 1.1182308522114348,
+      "grad_norm": 0.45398685336112976,
+      "learning_rate": 0.00019348721699379798,
+      "loss": 0.7756917476654053,
+      "step": 2592
+    },
+    {
+      "epoch": 1.119093851132686,
+      "grad_norm": 0.4246262311935425,
+      "learning_rate": 0.0001934697736500708,
+      "loss": 0.7516605854034424,
+      "step": 2594
+    },
+    {
+      "epoch": 1.1199568500539374,
+      "grad_norm": 0.44801613688468933,
+      "learning_rate": 0.00019345230776652908,
+      "loss": 0.7058185338973999,
+      "step": 2596
+    },
+    {
+      "epoch": 1.1208198489751888,
+      "grad_norm": 0.4591200649738312,
+      "learning_rate": 0.00019343481934738462,
+      "loss": 0.8071328997612,
+      "step": 2598
+    },
+    {
+      "epoch": 1.12168284789644,
+      "grad_norm": 0.39467594027519226,
+      "learning_rate": 0.0001934173083968547,
+      "loss": 0.6992195844650269,
+      "step": 2600
+    },
+    {
+      "epoch": 1.12168284789644,
+      "eval_loss": 0.8300262093544006,
+      "eval_runtime": 658.9488,
+      "eval_samples_per_second": 3.126,
+      "eval_steps_per_second": 3.126,
+      "step": 2600
+    },
+    {
+      "epoch": 1.1225458468176914,
+      "grad_norm": 0.40905407071113586,
+      "learning_rate": 0.00019339977491916196,
+      "loss": 0.7683232426643372,
+      "step": 2602
+    },
+    {
+      "epoch": 1.1234088457389428,
+      "grad_norm": 0.42742034792900085,
+      "learning_rate": 0.00019338221891853453,
+      "loss": 0.7048685550689697,
+      "step": 2604
+    },
+    {
+      "epoch": 1.1242718446601943,
+      "grad_norm": 0.4435581564903259,
+      "learning_rate": 0.000193364640399206,
+      "loss": 0.7206799983978271,
+      "step": 2606
+    },
+    {
+      "epoch": 1.1251348435814454,
+      "grad_norm": 0.48409897089004517,
+      "learning_rate": 0.00019334703936541535,
+      "loss": 0.8230411410331726,
+      "step": 2608
+    },
+    {
+      "epoch": 1.1259978425026969,
+      "grad_norm": 0.5060800909996033,
+      "learning_rate": 0.00019332941582140693,
+      "loss": 0.7833203077316284,
+      "step": 2610
+    },
+    {
+      "epoch": 1.1268608414239483,
+      "grad_norm": 0.48900339007377625,
+      "learning_rate": 0.00019331176977143062,
+      "loss": 0.7785601615905762,
+      "step": 2612
+    },
+    {
+      "epoch": 1.1277238403451997,
+      "grad_norm": 0.46176961064338684,
+      "learning_rate": 0.0001932941012197417,
+      "loss": 0.800255537033081,
+      "step": 2614
+    },
+    {
+      "epoch": 1.1285868392664509,
+      "grad_norm": 0.4946233332157135,
+      "learning_rate": 0.00019327641017060084,
+      "loss": 0.7647190690040588,
+      "step": 2616
+    },
+    {
+      "epoch": 1.1294498381877023,
+      "grad_norm": 0.4153730571269989,
+      "learning_rate": 0.00019325869662827416,
+      "loss": 0.7271775007247925,
+      "step": 2618
+    },
+    {
+      "epoch": 1.1303128371089537,
+      "grad_norm": 0.46707460284233093,
+      "learning_rate": 0.0001932409605970332,
+      "loss": 0.7926952838897705,
+      "step": 2620
+    },
+    {
+      "epoch": 1.1311758360302049,
+      "grad_norm": 0.4980720579624176,
+      "learning_rate": 0.00019322320208115489,
+      "loss": 0.8106555938720703,
+      "step": 2622
+    },
+    {
+      "epoch": 1.1320388349514563,
+      "grad_norm": 0.4300958514213562,
+      "learning_rate": 0.0001932054210849217,
+      "loss": 0.7208700776100159,
+      "step": 2624
+    },
+    {
+      "epoch": 1.1329018338727077,
+      "grad_norm": 0.4756612479686737,
+      "learning_rate": 0.00019318761761262136,
+      "loss": 0.7212259769439697,
+      "step": 2626
+    },
+    {
+      "epoch": 1.133764832793959,
+      "grad_norm": 0.4502181112766266,
+      "learning_rate": 0.00019316979166854713,
+      "loss": 0.6725794672966003,
+      "step": 2628
+    },
+    {
+      "epoch": 1.1346278317152103,
+      "grad_norm": 0.4845540523529053,
+      "learning_rate": 0.00019315194325699765,
+      "loss": 0.7582959532737732,
+      "step": 2630
+    },
+    {
+      "epoch": 1.1354908306364617,
+      "grad_norm": 0.45892953872680664,
+      "learning_rate": 0.00019313407238227698,
+      "loss": 0.7707560062408447,
+      "step": 2632
+    },
+    {
+      "epoch": 1.1363538295577131,
+      "grad_norm": 0.4707877039909363,
+      "learning_rate": 0.00019311617904869464,
+      "loss": 0.7824680209159851,
+      "step": 2634
+    },
+    {
+      "epoch": 1.1372168284789643,
+      "grad_norm": 0.5212311744689941,
+      "learning_rate": 0.00019309826326056545,
+      "loss": 0.7750257253646851,
+      "step": 2636
+    },
+    {
+      "epoch": 1.1380798274002157,
+      "grad_norm": 0.4952082633972168,
+      "learning_rate": 0.0001930803250222098,
+      "loss": 0.7691953182220459,
+      "step": 2638
+    },
+    {
+      "epoch": 1.1389428263214671,
+      "grad_norm": 0.4428424835205078,
+      "learning_rate": 0.00019306236433795334,
+      "loss": 0.737209141254425,
+      "step": 2640
+    },
+    {
+      "epoch": 1.1398058252427186,
+      "grad_norm": 0.5063129663467407,
+      "learning_rate": 0.00019304438121212728,
+      "loss": 0.7487695813179016,
+      "step": 2642
+    },
+    {
+      "epoch": 1.1406688241639698,
+      "grad_norm": 0.4571828246116638,
+      "learning_rate": 0.00019302637564906814,
+      "loss": 0.7647218704223633,
+      "step": 2644
+    },
+    {
+      "epoch": 1.1415318230852212,
+      "grad_norm": 0.4918457567691803,
+      "learning_rate": 0.00019300834765311785,
+      "loss": 0.8173171877861023,
+      "step": 2646
+    },
+    {
+      "epoch": 1.1423948220064726,
+      "grad_norm": 0.40057408809661865,
+      "learning_rate": 0.0001929902972286238,
+      "loss": 0.6472562551498413,
+      "step": 2648
+    },
+    {
+      "epoch": 1.1432578209277238,
+      "grad_norm": 0.432763934135437,
+      "learning_rate": 0.0001929722243799388,
+      "loss": 0.8462889194488525,
+      "step": 2650
+    },
+    {
+      "epoch": 1.1441208198489752,
+      "grad_norm": 0.36540713906288147,
+      "learning_rate": 0.000192954129111421,
+      "loss": 0.808388352394104,
+      "step": 2652
+    },
+    {
+      "epoch": 1.1449838187702266,
+      "grad_norm": 0.4236038029193878,
+      "learning_rate": 0.00019293601142743403,
+      "loss": 0.7144365906715393,
+      "step": 2654
+    },
+    {
+      "epoch": 1.1458468176914778,
+      "grad_norm": 0.4316163957118988,
+      "learning_rate": 0.00019291787133234682,
+      "loss": 0.693168580532074,
+      "step": 2656
+    },
+    {
+      "epoch": 1.1467098166127292,
+      "grad_norm": 0.43088117241859436,
+      "learning_rate": 0.00019289970883053386,
+      "loss": 0.7981953024864197,
+      "step": 2658
+    },
+    {
+      "epoch": 1.1475728155339806,
+      "grad_norm": 0.4200972318649292,
+      "learning_rate": 0.00019288152392637486,
+      "loss": 0.7342561483383179,
+      "step": 2660
+    },
+    {
+      "epoch": 1.148435814455232,
+      "grad_norm": 0.4461527466773987,
+      "learning_rate": 0.00019286331662425512,
+      "loss": 0.7239733934402466,
+      "step": 2662
+    },
+    {
+      "epoch": 1.1492988133764832,
+      "grad_norm": 0.3945358097553253,
+      "learning_rate": 0.00019284508692856518,
+      "loss": 0.6575030088424683,
+      "step": 2664
+    },
+    {
+      "epoch": 1.1501618122977346,
+      "grad_norm": 0.4653085470199585,
+      "learning_rate": 0.0001928268348437011,
+      "loss": 0.7754159569740295,
+      "step": 2666
+    },
+    {
+      "epoch": 1.151024811218986,
+      "grad_norm": 0.47542640566825867,
+      "learning_rate": 0.00019280856037406422,
+      "loss": 0.683927595615387,
+      "step": 2668
+    },
+    {
+      "epoch": 1.1518878101402374,
+      "grad_norm": 0.4191996455192566,
+      "learning_rate": 0.00019279026352406143,
+      "loss": 0.6907603144645691,
+      "step": 2670
+    },
+    {
+      "epoch": 1.1527508090614886,
+      "grad_norm": 0.4643108546733856,
+      "learning_rate": 0.00019277194429810488,
+      "loss": 0.8362683653831482,
+      "step": 2672
+    },
+    {
+      "epoch": 1.15361380798274,
+      "grad_norm": 0.4213605225086212,
+      "learning_rate": 0.00019275360270061217,
+      "loss": 0.737736701965332,
+      "step": 2674
+    },
+    {
+      "epoch": 1.1544768069039915,
+      "grad_norm": 0.537070095539093,
+      "learning_rate": 0.0001927352387360063,
+      "loss": 0.7617850303649902,
+      "step": 2676
+    },
+    {
+      "epoch": 1.1553398058252426,
+      "grad_norm": 0.47798195481300354,
+      "learning_rate": 0.0001927168524087157,
+      "loss": 0.7252766489982605,
+      "step": 2678
+    },
+    {
+      "epoch": 1.156202804746494,
+      "grad_norm": 0.48654067516326904,
+      "learning_rate": 0.00019269844372317408,
+      "loss": 0.7671495676040649,
+      "step": 2680
+    },
+    {
+      "epoch": 1.1570658036677455,
+      "grad_norm": 0.5374535322189331,
+      "learning_rate": 0.00019268001268382066,
+      "loss": 0.8648670315742493,
+      "step": 2682
+    },
+    {
+      "epoch": 1.1579288025889967,
+      "grad_norm": 0.42167672514915466,
+      "learning_rate": 0.00019266155929509996,
+      "loss": 0.6848083138465881,
+      "step": 2684
+    },
+    {
+      "epoch": 1.158791801510248,
+      "grad_norm": 0.38867753744125366,
+      "learning_rate": 0.00019264308356146197,
+      "loss": 0.6890886425971985,
+      "step": 2686
+    },
+    {
+      "epoch": 1.1596548004314995,
+      "grad_norm": 0.42711013555526733,
+      "learning_rate": 0.000192624585487362,
+      "loss": 0.7399795651435852,
+      "step": 2688
+    },
+    {
+      "epoch": 1.160517799352751,
+      "grad_norm": 0.48802322149276733,
+      "learning_rate": 0.00019260606507726083,
+      "loss": 0.8026465773582458,
+      "step": 2690
+    },
+    {
+      "epoch": 1.161380798274002,
+      "grad_norm": 0.47166478633880615,
+      "learning_rate": 0.00019258752233562452,
+      "loss": 0.7589768171310425,
+      "step": 2692
+    },
+    {
+      "epoch": 1.1622437971952535,
+      "grad_norm": 0.47413256764411926,
+      "learning_rate": 0.00019256895726692459,
+      "loss": 0.7620571851730347,
+      "step": 2694
+    },
+    {
+      "epoch": 1.163106796116505,
+      "grad_norm": 0.5377517342567444,
+      "learning_rate": 0.0001925503698756379,
+      "loss": 0.798933207988739,
+      "step": 2696
+    },
+    {
+      "epoch": 1.1639697950377563,
+      "grad_norm": 0.44990095496177673,
+      "learning_rate": 0.00019253176016624678,
+      "loss": 0.7550637125968933,
+      "step": 2698
+    },
+    {
+      "epoch": 1.1648327939590075,
+      "grad_norm": 0.4633009433746338,
+      "learning_rate": 0.00019251312814323876,
+      "loss": 0.7919567227363586,
+      "step": 2700
+    },
+    {
+      "epoch": 1.1648327939590075,
+      "eval_loss": 0.8251468539237976,
+      "eval_runtime": 667.0436,
+      "eval_samples_per_second": 3.088,
+      "eval_steps_per_second": 3.088,
+      "step": 2700
+    },
+    {
+      "epoch": 1.165695792880259,
+      "grad_norm": 0.4339669942855835,
+      "learning_rate": 0.000192494473811107,
+      "loss": 0.8140546083450317,
+      "step": 2702
+    },
+    {
+      "epoch": 1.1665587918015103,
+      "grad_norm": 0.5794349312782288,
+      "learning_rate": 0.00019247579717434984,
+      "loss": 0.8462281823158264,
+      "step": 2704
+    },
+    {
+      "epoch": 1.1674217907227615,
+      "grad_norm": 0.41820067167282104,
+      "learning_rate": 0.00019245709823747102,
+      "loss": 0.7468760013580322,
+      "step": 2706
+    },
+    {
+      "epoch": 1.168284789644013,
+      "grad_norm": 0.4002464711666107,
+      "learning_rate": 0.0001924383770049798,
+      "loss": 0.694807767868042,
+      "step": 2708
+    },
+    {
+      "epoch": 1.1691477885652644,
+      "grad_norm": 0.47752025723457336,
+      "learning_rate": 0.00019241963348139068,
+      "loss": 0.7512534856796265,
+      "step": 2710
+    },
+    {
+      "epoch": 1.1700107874865155,
+      "grad_norm": 0.45852312445640564,
+      "learning_rate": 0.0001924008676712236,
+      "loss": 0.8069711923599243,
+      "step": 2712
+    },
+    {
+      "epoch": 1.170873786407767,
+      "grad_norm": 0.4336509108543396,
+      "learning_rate": 0.0001923820795790038,
+      "loss": 0.7022751569747925,
+      "step": 2714
+    },
+    {
+      "epoch": 1.1717367853290184,
+      "grad_norm": 0.40044888854026794,
+      "learning_rate": 0.00019236326920926193,
+      "loss": 0.6904252767562866,
+      "step": 2716
+    },
+    {
+      "epoch": 1.1725997842502698,
+      "grad_norm": 0.48451852798461914,
+      "learning_rate": 0.00019234443656653412,
+      "loss": 0.7924585938453674,
+      "step": 2718
+    },
+    {
+      "epoch": 1.173462783171521,
+      "grad_norm": 0.49168315529823303,
+      "learning_rate": 0.0001923255816553617,
+      "loss": 0.7383922338485718,
+      "step": 2720
+    },
+    {
+      "epoch": 1.1743257820927724,
+      "grad_norm": 0.4363260269165039,
+      "learning_rate": 0.00019230670448029148,
+      "loss": 0.7508589029312134,
+      "step": 2722
+    },
+    {
+      "epoch": 1.1751887810140238,
+      "grad_norm": 0.4520082175731659,
+      "learning_rate": 0.0001922878050458756,
+      "loss": 0.7814584970474243,
+      "step": 2724
+    },
+    {
+      "epoch": 1.176051779935275,
+      "grad_norm": 0.4675535559654236,
+      "learning_rate": 0.00019226888335667158,
+      "loss": 0.7011970281600952,
+      "step": 2726
+    },
+    {
+      "epoch": 1.1769147788565264,
+      "grad_norm": 0.47536277770996094,
+      "learning_rate": 0.00019224993941724226,
+      "loss": 0.7414659857749939,
+      "step": 2728
+    },
+    {
+      "epoch": 1.1777777777777778,
+      "grad_norm": 0.5455507040023804,
+      "learning_rate": 0.00019223097323215594,
+      "loss": 0.7949363589286804,
+      "step": 2730
+    },
+    {
+      "epoch": 1.1786407766990292,
+      "grad_norm": 0.4897938370704651,
+      "learning_rate": 0.00019221198480598616,
+      "loss": 0.813949465751648,
+      "step": 2732
+    },
+    {
+      "epoch": 1.1795037756202804,
+      "grad_norm": 0.46766766905784607,
+      "learning_rate": 0.000192192974143312,
+      "loss": 0.7444795966148376,
+      "step": 2734
+    },
+    {
+      "epoch": 1.1803667745415318,
+      "grad_norm": 0.41503575444221497,
+      "learning_rate": 0.00019217394124871768,
+      "loss": 0.7937621474266052,
+      "step": 2736
+    },
+    {
+      "epoch": 1.1812297734627832,
+      "grad_norm": 0.41906169056892395,
+      "learning_rate": 0.00019215488612679295,
+      "loss": 0.7342435717582703,
+      "step": 2738
+    },
+    {
+      "epoch": 1.1820927723840344,
+      "grad_norm": 0.47820931673049927,
+      "learning_rate": 0.00019213580878213292,
+      "loss": 0.7533642053604126,
+      "step": 2740
+    },
+    {
+      "epoch": 1.1829557713052858,
+      "grad_norm": 0.44907891750335693,
+      "learning_rate": 0.00019211670921933792,
+      "loss": 0.799866795539856,
+      "step": 2742
+    },
+    {
+      "epoch": 1.1838187702265373,
+      "grad_norm": 0.48050498962402344,
+      "learning_rate": 0.00019209758744301376,
+      "loss": 0.7468855381011963,
+      "step": 2744
+    },
+    {
+      "epoch": 1.1846817691477884,
+      "grad_norm": 0.4311312437057495,
+      "learning_rate": 0.00019207844345777155,
+      "loss": 0.7423141002655029,
+      "step": 2746
+    },
+    {
+      "epoch": 1.1855447680690399,
+      "grad_norm": 0.439386248588562,
+      "learning_rate": 0.0001920592772682278,
+      "loss": 0.7046169638633728,
+      "step": 2748
+    },
+    {
+      "epoch": 1.1864077669902913,
+      "grad_norm": 0.4230091869831085,
+      "learning_rate": 0.00019204008887900435,
+      "loss": 0.7284982204437256,
+      "step": 2750
+    },
+    {
+      "epoch": 1.1872707659115427,
+      "grad_norm": 0.4583308696746826,
+      "learning_rate": 0.0001920208782947284,
+      "loss": 0.7297943234443665,
+      "step": 2752
+    },
+    {
+      "epoch": 1.1881337648327939,
+      "grad_norm": 0.44526317715644836,
+      "learning_rate": 0.00019200164552003247,
+      "loss": 0.7170902490615845,
+      "step": 2754
+    },
+    {
+      "epoch": 1.1889967637540453,
+      "grad_norm": 0.46664097905158997,
+      "learning_rate": 0.00019198239055955444,
+      "loss": 0.7746089696884155,
+      "step": 2756
+    },
+    {
+      "epoch": 1.1898597626752967,
+      "grad_norm": 0.4023241102695465,
+      "learning_rate": 0.0001919631134179376,
+      "loss": 0.7381687760353088,
+      "step": 2758
+    },
+    {
+      "epoch": 1.190722761596548,
+      "grad_norm": 0.5126422047615051,
+      "learning_rate": 0.00019194381409983055,
+      "loss": 0.7951313853263855,
+      "step": 2760
+    },
+    {
+      "epoch": 1.1915857605177993,
+      "grad_norm": 0.4056018590927124,
+      "learning_rate": 0.0001919244926098872,
+      "loss": 0.692834198474884,
+      "step": 2762
+    },
+    {
+      "epoch": 1.1924487594390507,
+      "grad_norm": 0.49225106835365295,
+      "learning_rate": 0.00019190514895276687,
+      "loss": 0.7494171857833862,
+      "step": 2764
+    },
+    {
+      "epoch": 1.1933117583603021,
+      "grad_norm": 0.47823601961135864,
+      "learning_rate": 0.00019188578313313417,
+      "loss": 0.8541221022605896,
+      "step": 2766
+    },
+    {
+      "epoch": 1.1941747572815533,
+      "grad_norm": 0.461773544549942,
+      "learning_rate": 0.0001918663951556591,
+      "loss": 0.8017639517784119,
+      "step": 2768
+    },
+    {
+      "epoch": 1.1950377562028047,
+      "grad_norm": 0.48888009786605835,
+      "learning_rate": 0.00019184698502501695,
+      "loss": 0.7509341835975647,
+      "step": 2770
+    },
+    {
+      "epoch": 1.1959007551240561,
+      "grad_norm": 0.4140535295009613,
+      "learning_rate": 0.0001918275527458884,
+      "loss": 0.7123914361000061,
+      "step": 2772
+    },
+    {
+      "epoch": 1.1967637540453073,
+      "grad_norm": 0.4918449819087982,
+      "learning_rate": 0.00019180809832295952,
+      "loss": 0.73713219165802,
+      "step": 2774
+    },
+    {
+      "epoch": 1.1976267529665587,
+      "grad_norm": 0.48218831419944763,
+      "learning_rate": 0.00019178862176092159,
+      "loss": 0.708644688129425,
+      "step": 2776
+    },
+    {
+      "epoch": 1.1984897518878102,
+      "grad_norm": 0.45588797330856323,
+      "learning_rate": 0.0001917691230644713,
+      "loss": 0.7277385592460632,
+      "step": 2778
+    },
+    {
+      "epoch": 1.1993527508090616,
+      "grad_norm": 0.3959250748157501,
+      "learning_rate": 0.00019174960223831064,
+      "loss": 0.7501665949821472,
+      "step": 2780
+    },
+    {
+      "epoch": 1.2002157497303128,
+      "grad_norm": 0.6228574514389038,
+      "learning_rate": 0.00019173005928714703,
+      "loss": 0.8842931389808655,
+      "step": 2782
+    },
+    {
+      "epoch": 1.2010787486515642,
+      "grad_norm": 0.4346935749053955,
+      "learning_rate": 0.00019171049421569318,
+      "loss": 0.7008639574050903,
+      "step": 2784
+    },
+    {
+      "epoch": 1.2019417475728156,
+      "grad_norm": 0.691254198551178,
+      "learning_rate": 0.00019169090702866705,
+      "loss": 0.7203702330589294,
+      "step": 2786
+    },
+    {
+      "epoch": 1.202804746494067,
+      "grad_norm": 0.4219740331172943,
+      "learning_rate": 0.00019167129773079203,
+      "loss": 0.7170791029930115,
+      "step": 2788
+    },
+    {
+      "epoch": 1.2036677454153182,
+      "grad_norm": 0.4639855921268463,
+      "learning_rate": 0.00019165166632679686,
+      "loss": 0.7895086407661438,
+      "step": 2790
+    },
+    {
+      "epoch": 1.2045307443365696,
+      "grad_norm": 0.44938549399375916,
+      "learning_rate": 0.00019163201282141546,
+      "loss": 0.7323113679885864,
+      "step": 2792
+    },
+    {
+      "epoch": 1.205393743257821,
+      "grad_norm": 0.43633413314819336,
+      "learning_rate": 0.00019161233721938728,
+      "loss": 0.7486892342567444,
+      "step": 2794
+    },
+    {
+      "epoch": 1.2062567421790722,
+      "grad_norm": 0.42983385920524597,
+      "learning_rate": 0.00019159263952545698,
+      "loss": 0.777079701423645,
+      "step": 2796
+    },
+    {
+      "epoch": 1.2071197411003236,
+      "grad_norm": 0.4630664587020874,
+      "learning_rate": 0.00019157291974437456,
+      "loss": 0.800602912902832,
+      "step": 2798
+    },
+    {
+      "epoch": 1.207982740021575,
+      "grad_norm": 0.43607378005981445,
+      "learning_rate": 0.00019155317788089536,
+      "loss": 0.6763592958450317,
+      "step": 2800
+    },
+    {
+      "epoch": 1.207982740021575,
+      "eval_loss": 0.8219058513641357,
+      "eval_runtime": 661.5144,
+      "eval_samples_per_second": 3.114,
+      "eval_steps_per_second": 3.114,
+      "step": 2800
+    },
+    {
+      "epoch": 1.2088457389428262,
+      "grad_norm": 0.4910019338130951,
+      "learning_rate": 0.00019153341393978002,
+      "loss": 0.7569329738616943,
+      "step": 2802
+    },
+    {
+      "epoch": 1.2097087378640776,
+      "grad_norm": 0.4993135631084442,
+      "learning_rate": 0.00019151362792579457,
+      "loss": 0.734387218952179,
+      "step": 2804
+    },
+    {
+      "epoch": 1.210571736785329,
+      "grad_norm": 0.48742055892944336,
+      "learning_rate": 0.00019149381984371027,
+      "loss": 0.719099223613739,
+      "step": 2806
+    },
+    {
+      "epoch": 1.2114347357065804,
+      "grad_norm": 0.4083765149116516,
+      "learning_rate": 0.00019147398969830378,
+      "loss": 0.8490580320358276,
+      "step": 2808
+    },
+    {
+      "epoch": 1.2122977346278316,
+      "grad_norm": 0.4316021502017975,
+      "learning_rate": 0.00019145413749435702,
+      "loss": 0.7604904770851135,
+      "step": 2810
+    },
+    {
+      "epoch": 1.213160733549083,
+      "grad_norm": 0.4294895529747009,
+      "learning_rate": 0.0001914342632366573,
+      "loss": 0.7739580869674683,
+      "step": 2812
+    },
+    {
+      "epoch": 1.2140237324703345,
+      "grad_norm": 0.4773736000061035,
+      "learning_rate": 0.00019141436692999718,
+      "loss": 0.7625397443771362,
+      "step": 2814
+    },
+    {
+      "epoch": 1.2148867313915859,
+      "grad_norm": 0.46148404479026794,
+      "learning_rate": 0.00019139444857917457,
+      "loss": 0.7224686741828918,
+      "step": 2816
+    },
+    {
+      "epoch": 1.215749730312837,
+      "grad_norm": 0.436300128698349,
+      "learning_rate": 0.0001913745081889927,
+      "loss": 0.7708583474159241,
+      "step": 2818
+    },
+    {
+      "epoch": 1.2166127292340885,
+      "grad_norm": 0.4959073066711426,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.8550406098365784,
+      "step": 2820
+    },
+    {
+      "epoch": 1.2174757281553399,
+      "grad_norm": 0.4672411382198334,
+      "learning_rate": 0.00019133456130979062,
+      "loss": 0.781597912311554,
+      "step": 2822
+    },
+    {
+      "epoch": 1.218338727076591,
+      "grad_norm": 0.5249256491661072,
+      "learning_rate": 0.0001913145548304034,
+      "loss": 0.860835075378418,
+      "step": 2824
+    },
+    {
+      "epoch": 1.2192017259978425,
+      "grad_norm": 0.5132579207420349,
+      "learning_rate": 0.00019129452633092294,
+      "loss": 0.715717613697052,
+      "step": 2826
+    },
+    {
+      "epoch": 1.220064724919094,
+      "grad_norm": 0.4291874170303345,
+      "learning_rate": 0.00019127447581617903,
+      "loss": 0.727998673915863,
+      "step": 2828
+    },
+    {
+      "epoch": 1.220927723840345,
+      "grad_norm": 0.3698529005050659,
+      "learning_rate": 0.00019125440329100673,
+      "loss": 0.7164589762687683,
+      "step": 2830
+    },
+    {
+      "epoch": 1.2217907227615965,
+      "grad_norm": 0.5034273266792297,
+      "learning_rate": 0.00019123430876024646,
+      "loss": 0.8113957643508911,
+      "step": 2832
+    },
+    {
+      "epoch": 1.222653721682848,
+      "grad_norm": 0.4612481892108917,
+      "learning_rate": 0.0001912141922287439,
+      "loss": 0.7350133061408997,
+      "step": 2834
+    },
+    {
+      "epoch": 1.2235167206040993,
+      "grad_norm": 0.4433611035346985,
+      "learning_rate": 0.00019119405370135012,
+      "loss": 0.8156216144561768,
+      "step": 2836
+    },
+    {
+      "epoch": 1.2243797195253505,
+      "grad_norm": 0.4700625240802765,
+      "learning_rate": 0.00019117389318292136,
+      "loss": 0.7824334502220154,
+      "step": 2838
+    },
+    {
+      "epoch": 1.225242718446602,
+      "grad_norm": 0.4854332208633423,
+      "learning_rate": 0.00019115371067831928,
+      "loss": 0.8136369585990906,
+      "step": 2840
+    },
+    {
+      "epoch": 1.2261057173678533,
+      "grad_norm": 0.4403935372829437,
+      "learning_rate": 0.00019113350619241078,
+      "loss": 0.7042210102081299,
+      "step": 2842
+    },
+    {
+      "epoch": 1.2269687162891048,
+      "grad_norm": 0.4311469793319702,
+      "learning_rate": 0.00019111327973006813,
+      "loss": 0.7598573565483093,
+      "step": 2844
+    },
+    {
+      "epoch": 1.227831715210356,
+      "grad_norm": 0.5551521182060242,
+      "learning_rate": 0.0001910930312961688,
+      "loss": 0.8001043796539307,
+      "step": 2846
+    },
+    {
+      "epoch": 1.2286947141316074,
+      "grad_norm": 0.44149601459503174,
+      "learning_rate": 0.0001910727608955956,
+      "loss": 0.6874746084213257,
+      "step": 2848
+    },
+    {
+      "epoch": 1.2295577130528588,
+      "grad_norm": 0.44726014137268066,
+      "learning_rate": 0.00019105246853323672,
+      "loss": 0.7484437823295593,
+      "step": 2850
+    },
+    {
+      "epoch": 1.23042071197411,
+      "grad_norm": 0.4710492193698883,
+      "learning_rate": 0.00019103215421398546,
+      "loss": 0.7512558102607727,
+      "step": 2852
+    },
+    {
+      "epoch": 1.2312837108953614,
+      "grad_norm": 0.4304901957511902,
+      "learning_rate": 0.0001910118179427406,
+      "loss": 0.7161203622817993,
+      "step": 2854
+    },
+    {
+      "epoch": 1.2321467098166128,
+      "grad_norm": 0.4651104509830475,
+      "learning_rate": 0.00019099145972440614,
+      "loss": 0.722236156463623,
+      "step": 2856
+    },
+    {
+      "epoch": 1.233009708737864,
+      "grad_norm": 0.5231161117553711,
+      "learning_rate": 0.00019097107956389135,
+      "loss": 0.8200751543045044,
+      "step": 2858
+    },
+    {
+      "epoch": 1.2338727076591154,
+      "grad_norm": 0.45574283599853516,
+      "learning_rate": 0.00019095067746611083,
+      "loss": 0.7529966235160828,
+      "step": 2860
+    },
+    {
+      "epoch": 1.2347357065803668,
+      "grad_norm": 0.4451949894428253,
+      "learning_rate": 0.00019093025343598448,
+      "loss": 0.7574380040168762,
+      "step": 2862
+    },
+    {
+      "epoch": 1.2355987055016182,
+      "grad_norm": 0.4557603597640991,
+      "learning_rate": 0.00019090980747843737,
+      "loss": 0.8461237549781799,
+      "step": 2864
+    },
+    {
+      "epoch": 1.2364617044228694,
+      "grad_norm": 0.41115859150886536,
+      "learning_rate": 0.00019088933959840004,
+      "loss": 0.7910104990005493,
+      "step": 2866
+    },
+    {
+      "epoch": 1.2373247033441208,
+      "grad_norm": 0.5087599158287048,
+      "learning_rate": 0.0001908688498008082,
+      "loss": 0.8318688273429871,
+      "step": 2868
+    },
+    {
+      "epoch": 1.2381877022653722,
+      "grad_norm": 0.4243653118610382,
+      "learning_rate": 0.00019084833809060285,
+      "loss": 0.713392436504364,
+      "step": 2870
+    },
+    {
+      "epoch": 1.2390507011866236,
+      "grad_norm": 0.3965010344982147,
+      "learning_rate": 0.00019082780447273034,
+      "loss": 0.7697778344154358,
+      "step": 2872
+    },
+    {
+      "epoch": 1.2399137001078748,
+      "grad_norm": 0.4493406116962433,
+      "learning_rate": 0.00019080724895214222,
+      "loss": 0.7437527179718018,
+      "step": 2874
+    },
+    {
+      "epoch": 1.2407766990291262,
+      "grad_norm": 0.5189685821533203,
+      "learning_rate": 0.00019078667153379537,
+      "loss": 0.858138918876648,
+      "step": 2876
+    },
+    {
+      "epoch": 1.2416396979503777,
+      "grad_norm": 0.39455580711364746,
+      "learning_rate": 0.00019076607222265197,
+      "loss": 0.7235360145568848,
+      "step": 2878
+    },
+    {
+      "epoch": 1.2425026968716288,
+      "grad_norm": 0.524804413318634,
+      "learning_rate": 0.00019074545102367943,
+      "loss": 0.7995675206184387,
+      "step": 2880
+    },
+    {
+      "epoch": 1.2433656957928803,
+      "grad_norm": 0.4873242974281311,
+      "learning_rate": 0.00019072480794185044,
+      "loss": 0.8404105305671692,
+      "step": 2882
+    },
+    {
+      "epoch": 1.2442286947141317,
+      "grad_norm": 0.4591716527938843,
+      "learning_rate": 0.000190704142982143,
+      "loss": 0.7540513277053833,
+      "step": 2884
+    },
+    {
+      "epoch": 1.2450916936353829,
+      "grad_norm": 0.48403632640838623,
+      "learning_rate": 0.0001906834561495404,
+      "loss": 0.7566621899604797,
+      "step": 2886
+    },
+    {
+      "epoch": 1.2459546925566343,
+      "grad_norm": 0.4854280948638916,
+      "learning_rate": 0.00019066274744903113,
+      "loss": 0.7141375541687012,
+      "step": 2888
+    },
+    {
+      "epoch": 1.2468176914778857,
+      "grad_norm": 0.45851001143455505,
+      "learning_rate": 0.00019064201688560902,
+      "loss": 0.7798115611076355,
+      "step": 2890
+    },
+    {
+      "epoch": 1.247680690399137,
+      "grad_norm": 0.4584810435771942,
+      "learning_rate": 0.00019062126446427318,
+      "loss": 0.7212263941764832,
+      "step": 2892
+    },
+    {
+      "epoch": 1.2485436893203883,
+      "grad_norm": 0.5282798409461975,
+      "learning_rate": 0.00019060049019002792,
+      "loss": 0.8268418312072754,
+      "step": 2894
+    },
+    {
+      "epoch": 1.2494066882416397,
+      "grad_norm": 0.40996623039245605,
+      "learning_rate": 0.00019057969406788289,
+      "loss": 0.7512726783752441,
+      "step": 2896
+    },
+    {
+      "epoch": 1.250269687162891,
+      "grad_norm": 0.39559319615364075,
+      "learning_rate": 0.00019055887610285296,
+      "loss": 0.6680556535720825,
+      "step": 2898
+    },
+    {
+      "epoch": 1.2511326860841425,
+      "grad_norm": 0.42002710700035095,
+      "learning_rate": 0.0001905380362999583,
+      "loss": 0.7307850122451782,
+      "step": 2900
+    },
+    {
+      "epoch": 1.2511326860841425,
+      "eval_loss": 0.8155517578125,
+      "eval_runtime": 650.62,
+      "eval_samples_per_second": 3.166,
+      "eval_steps_per_second": 3.166,
+      "step": 2900
+    },
+    {
+      "epoch": 1.2519956850053937,
+      "grad_norm": 0.3914625644683838,
+      "learning_rate": 0.00019051717466422435,
+      "loss": 0.7316054701805115,
+      "step": 2902
+    },
+    {
+      "epoch": 1.2528586839266451,
+      "grad_norm": 0.48939383029937744,
+      "learning_rate": 0.00019049629120068175,
+      "loss": 0.8977305889129639,
+      "step": 2904
+    },
+    {
+      "epoch": 1.2537216828478965,
+      "grad_norm": 0.4892135262489319,
+      "learning_rate": 0.0001904753859143665,
+      "loss": 0.7962324619293213,
+      "step": 2906
+    },
+    {
+      "epoch": 1.2545846817691477,
+      "grad_norm": 0.5323660969734192,
+      "learning_rate": 0.00019045445881031982,
+      "loss": 0.791375458240509,
+      "step": 2908
+    },
+    {
+      "epoch": 1.2554476806903991,
+      "grad_norm": 0.44778114557266235,
+      "learning_rate": 0.00019043350989358818,
+      "loss": 0.7218163013458252,
+      "step": 2910
+    },
+    {
+      "epoch": 1.2563106796116505,
+      "grad_norm": 0.4763379991054535,
+      "learning_rate": 0.00019041253916922326,
+      "loss": 0.7380548119544983,
+      "step": 2912
+    },
+    {
+      "epoch": 1.2571736785329017,
+      "grad_norm": 0.4979628026485443,
+      "learning_rate": 0.00019039154664228213,
+      "loss": 0.7586072683334351,
+      "step": 2914
+    },
+    {
+      "epoch": 1.2580366774541532,
+      "grad_norm": 0.46175920963287354,
+      "learning_rate": 0.000190370532317827,
+      "loss": 0.763477623462677,
+      "step": 2916
+    },
+    {
+      "epoch": 1.2588996763754046,
+      "grad_norm": 0.43192169070243835,
+      "learning_rate": 0.0001903494962009254,
+      "loss": 0.7479409575462341,
+      "step": 2918
+    },
+    {
+      "epoch": 1.2597626752966558,
+      "grad_norm": 0.42883434891700745,
+      "learning_rate": 0.0001903284382966501,
+      "loss": 0.7355074882507324,
+      "step": 2920
+    },
+    {
+      "epoch": 1.2606256742179072,
+      "grad_norm": 0.47708168625831604,
+      "learning_rate": 0.00019030735861007912,
+      "loss": 0.7762811183929443,
+      "step": 2922
+    },
+    {
+      "epoch": 1.2614886731391586,
+      "grad_norm": 0.4478151500225067,
+      "learning_rate": 0.0001902862571462957,
+      "loss": 0.6964467763900757,
+      "step": 2924
+    },
+    {
+      "epoch": 1.26235167206041,
+      "grad_norm": 0.4531081020832062,
+      "learning_rate": 0.00019026513391038837,
+      "loss": 0.7414857745170593,
+      "step": 2926
+    },
+    {
+      "epoch": 1.2632146709816614,
+      "grad_norm": 0.4623842239379883,
+      "learning_rate": 0.00019024398890745092,
+      "loss": 0.7639371156692505,
+      "step": 2928
+    },
+    {
+      "epoch": 1.2640776699029126,
+      "grad_norm": 0.4362739622592926,
+      "learning_rate": 0.00019022282214258238,
+      "loss": 0.800457239151001,
+      "step": 2930
+    },
+    {
+      "epoch": 1.264940668824164,
+      "grad_norm": 0.42854052782058716,
+      "learning_rate": 0.000190201633620887,
+      "loss": 0.7960386872291565,
+      "step": 2932
+    },
+    {
+      "epoch": 1.2658036677454154,
+      "grad_norm": 0.47477999329566956,
+      "learning_rate": 0.0001901804233474743,
+      "loss": 0.7544003129005432,
+      "step": 2934
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 0.4584832191467285,
+      "learning_rate": 0.00019015919132745905,
+      "loss": 0.7819825410842896,
+      "step": 2936
+    },
+    {
+      "epoch": 1.267529665587918,
+      "grad_norm": 0.5465012192726135,
+      "learning_rate": 0.00019013793756596123,
+      "loss": 0.7719182372093201,
+      "step": 2938
+    },
+    {
+      "epoch": 1.2683926645091694,
+      "grad_norm": 0.42024123668670654,
+      "learning_rate": 0.00019011666206810614,
+      "loss": 0.7442063093185425,
+      "step": 2940
+    },
+    {
+      "epoch": 1.2692556634304206,
+      "grad_norm": 0.4374787211418152,
+      "learning_rate": 0.00019009536483902424,
+      "loss": 0.6696176528930664,
+      "step": 2942
+    },
+    {
+      "epoch": 1.270118662351672,
+      "grad_norm": 0.4136449992656708,
+      "learning_rate": 0.00019007404588385125,
+      "loss": 0.7048487663269043,
+      "step": 2944
+    },
+    {
+      "epoch": 1.2709816612729234,
+      "grad_norm": 0.4463474452495575,
+      "learning_rate": 0.00019005270520772817,
+      "loss": 0.7587971687316895,
+      "step": 2946
+    },
+    {
+      "epoch": 1.2718446601941746,
+      "grad_norm": 0.43167322874069214,
+      "learning_rate": 0.00019003134281580115,
+      "loss": 0.7741286754608154,
+      "step": 2948
+    },
+    {
+      "epoch": 1.272707659115426,
+      "grad_norm": 0.5189676284790039,
+      "learning_rate": 0.0001900099587132217,
+      "loss": 0.7572245597839355,
+      "step": 2950
+    },
+    {
+      "epoch": 1.2735706580366775,
+      "grad_norm": 0.4256224036216736,
+      "learning_rate": 0.00018998855290514646,
+      "loss": 0.7743186354637146,
+      "step": 2952
+    },
+    {
+      "epoch": 1.2744336569579289,
+      "grad_norm": 0.4304806888103485,
+      "learning_rate": 0.00018996712539673735,
+      "loss": 0.7287778854370117,
+      "step": 2954
+    },
+    {
+      "epoch": 1.2752966558791803,
+      "grad_norm": 0.489372193813324,
+      "learning_rate": 0.00018994567619316156,
+      "loss": 0.7930773496627808,
+      "step": 2956
+    },
+    {
+      "epoch": 1.2761596548004315,
+      "grad_norm": 0.3855830430984497,
+      "learning_rate": 0.0001899242052995914,
+      "loss": 0.7283111214637756,
+      "step": 2958
+    },
+    {
+      "epoch": 1.2770226537216829,
+      "grad_norm": 0.46708667278289795,
+      "learning_rate": 0.00018990271272120452,
+      "loss": 0.721849262714386,
+      "step": 2960
+    },
+    {
+      "epoch": 1.2778856526429343,
+      "grad_norm": 0.3663526773452759,
+      "learning_rate": 0.00018988119846318377,
+      "loss": 0.6678964495658875,
+      "step": 2962
+    },
+    {
+      "epoch": 1.2787486515641855,
+      "grad_norm": 0.5074638724327087,
+      "learning_rate": 0.00018985966253071718,
+      "loss": 0.8021678924560547,
+      "step": 2964
+    },
+    {
+      "epoch": 1.279611650485437,
+      "grad_norm": 0.4902975857257843,
+      "learning_rate": 0.00018983810492899806,
+      "loss": 0.8313384056091309,
+      "step": 2966
+    },
+    {
+      "epoch": 1.2804746494066883,
+      "grad_norm": 0.5023161768913269,
+      "learning_rate": 0.00018981652566322493,
+      "loss": 0.8330302834510803,
+      "step": 2968
+    },
+    {
+      "epoch": 1.2813376483279395,
+      "grad_norm": 0.48227089643478394,
+      "learning_rate": 0.00018979492473860155,
+      "loss": 0.8806158304214478,
+      "step": 2970
+    },
+    {
+      "epoch": 1.282200647249191,
+      "grad_norm": 0.40143465995788574,
+      "learning_rate": 0.00018977330216033683,
+      "loss": 0.6835185885429382,
+      "step": 2972
+    },
+    {
+      "epoch": 1.2830636461704423,
+      "grad_norm": 0.4368304908275604,
+      "learning_rate": 0.00018975165793364503,
+      "loss": 0.7207706570625305,
+      "step": 2974
+    },
+    {
+      "epoch": 1.2839266450916935,
+      "grad_norm": 0.39989250898361206,
+      "learning_rate": 0.0001897299920637455,
+      "loss": 0.6909692883491516,
+      "step": 2976
+    },
+    {
+      "epoch": 1.284789644012945,
+      "grad_norm": 0.4826473593711853,
+      "learning_rate": 0.0001897083045558629,
+      "loss": 0.838360071182251,
+      "step": 2978
+    },
+    {
+      "epoch": 1.2856526429341963,
+      "grad_norm": 0.4860877990722656,
+      "learning_rate": 0.00018968659541522705,
+      "loss": 0.7693317532539368,
+      "step": 2980
+    },
+    {
+      "epoch": 1.2865156418554478,
+      "grad_norm": 0.4361511170864105,
+      "learning_rate": 0.00018966486464707305,
+      "loss": 0.7662015557289124,
+      "step": 2982
+    },
+    {
+      "epoch": 1.287378640776699,
+      "grad_norm": 0.45333993434906006,
+      "learning_rate": 0.00018964311225664113,
+      "loss": 0.752369225025177,
+      "step": 2984
+    },
+    {
+      "epoch": 1.2882416396979504,
+      "grad_norm": 0.4825304448604584,
+      "learning_rate": 0.0001896213382491768,
+      "loss": 0.7524476051330566,
+      "step": 2986
+    },
+    {
+      "epoch": 1.2891046386192018,
+      "grad_norm": 0.5303854942321777,
+      "learning_rate": 0.00018959954262993077,
+      "loss": 0.8564903736114502,
+      "step": 2988
+    },
+    {
+      "epoch": 1.2899676375404532,
+      "grad_norm": 0.43856459856033325,
+      "learning_rate": 0.00018957772540415896,
+      "loss": 0.7839077711105347,
+      "step": 2990
+    },
+    {
+      "epoch": 1.2908306364617044,
+      "grad_norm": 0.438041627407074,
+      "learning_rate": 0.00018955588657712248,
+      "loss": 0.7580918669700623,
+      "step": 2992
+    },
+    {
+      "epoch": 1.2916936353829558,
+      "grad_norm": 0.4497842490673065,
+      "learning_rate": 0.00018953402615408768,
+      "loss": 0.7014032602310181,
+      "step": 2994
+    },
+    {
+      "epoch": 1.2925566343042072,
+      "grad_norm": 0.5659869313240051,
+      "learning_rate": 0.0001895121441403261,
+      "loss": 0.8220269083976746,
+      "step": 2996
+    },
+    {
+      "epoch": 1.2934196332254584,
+      "grad_norm": 0.4850102961063385,
+      "learning_rate": 0.00018949024054111448,
+      "loss": 0.6880294680595398,
+      "step": 2998
+    },
+    {
+      "epoch": 1.2942826321467098,
+      "grad_norm": 0.4253626763820648,
+      "learning_rate": 0.00018946831536173476,
+      "loss": 0.7443753480911255,
+      "step": 3000
+    },
+    {
+      "epoch": 1.2942826321467098,
+      "eval_loss": 0.8127614259719849,
+      "eval_runtime": 650.4396,
+      "eval_samples_per_second": 3.167,
+      "eval_steps_per_second": 3.167,
+      "step": 3000
+    },
+    {
+      "epoch": 1.2951456310679612,
+      "grad_norm": 0.3746396005153656,
+      "learning_rate": 0.00018944636860747412,
+      "loss": 0.6588667631149292,
+      "step": 3002
+    },
+    {
+      "epoch": 1.2960086299892124,
+      "grad_norm": 0.4039393663406372,
+      "learning_rate": 0.00018942440028362493,
+      "loss": 0.7135416865348816,
+      "step": 3004
+    },
+    {
+      "epoch": 1.2968716289104638,
+      "grad_norm": 0.457533061504364,
+      "learning_rate": 0.00018940241039548474,
+      "loss": 0.7895556688308716,
+      "step": 3006
+    },
+    {
+      "epoch": 1.2977346278317152,
+      "grad_norm": 0.4989747107028961,
+      "learning_rate": 0.0001893803989483563,
+      "loss": 0.7863595485687256,
+      "step": 3008
+    },
+    {
+      "epoch": 1.2985976267529666,
+      "grad_norm": 0.470002681016922,
+      "learning_rate": 0.00018935836594754756,
+      "loss": 0.795306921005249,
+      "step": 3010
+    },
+    {
+      "epoch": 1.2994606256742178,
+      "grad_norm": 0.43668872117996216,
+      "learning_rate": 0.00018933631139837176,
+      "loss": 0.7313401699066162,
+      "step": 3012
+    },
+    {
+      "epoch": 1.3003236245954692,
+      "grad_norm": 0.4843446910381317,
+      "learning_rate": 0.00018931423530614715,
+      "loss": 0.7331582903862,
+      "step": 3014
+    },
+    {
+      "epoch": 1.3011866235167207,
+      "grad_norm": 0.4233832359313965,
+      "learning_rate": 0.00018929213767619735,
+      "loss": 0.7046043872833252,
+      "step": 3016
+    },
+    {
+      "epoch": 1.302049622437972,
+      "grad_norm": 0.6326188445091248,
+      "learning_rate": 0.00018927001851385108,
+      "loss": 0.8217260241508484,
+      "step": 3018
+    },
+    {
+      "epoch": 1.3029126213592233,
+      "grad_norm": 0.409653902053833,
+      "learning_rate": 0.00018924787782444223,
+      "loss": 0.6477662324905396,
+      "step": 3020
+    },
+    {
+      "epoch": 1.3037756202804747,
+      "grad_norm": 0.3869863748550415,
+      "learning_rate": 0.00018922571561331004,
+      "loss": 0.6408766508102417,
+      "step": 3022
+    },
+    {
+      "epoch": 1.304638619201726,
+      "grad_norm": 0.4400722086429596,
+      "learning_rate": 0.00018920353188579874,
+      "loss": 0.7396708726882935,
+      "step": 3024
+    },
+    {
+      "epoch": 1.3055016181229773,
+      "grad_norm": 0.39694252610206604,
+      "learning_rate": 0.00018918132664725784,
+      "loss": 0.6409308314323425,
+      "step": 3026
+    },
+    {
+      "epoch": 1.3063646170442287,
+      "grad_norm": 0.49937903881073,
+      "learning_rate": 0.00018915909990304205,
+      "loss": 0.7825533151626587,
+      "step": 3028
+    },
+    {
+      "epoch": 1.30722761596548,
+      "grad_norm": 0.43940550088882446,
+      "learning_rate": 0.0001891368516585113,
+      "loss": 0.7182250022888184,
+      "step": 3030
+    },
+    {
+      "epoch": 1.3080906148867313,
+      "grad_norm": 0.43905356526374817,
+      "learning_rate": 0.00018911458191903053,
+      "loss": 0.7602632641792297,
+      "step": 3032
+    },
+    {
+      "epoch": 1.3089536138079827,
+      "grad_norm": 0.4172695279121399,
+      "learning_rate": 0.0001890922906899701,
+      "loss": 0.7307555675506592,
+      "step": 3034
+    },
+    {
+      "epoch": 1.309816612729234,
+      "grad_norm": 0.49642932415008545,
+      "learning_rate": 0.00018906997797670544,
+      "loss": 0.782136857509613,
+      "step": 3036
+    },
+    {
+      "epoch": 1.3106796116504853,
+      "grad_norm": 0.49893322587013245,
+      "learning_rate": 0.00018904764378461705,
+      "loss": 0.787925124168396,
+      "step": 3038
+    },
+    {
+      "epoch": 1.3115426105717367,
+      "grad_norm": 0.42691150307655334,
+      "learning_rate": 0.00018902528811909081,
+      "loss": 0.6731302738189697,
+      "step": 3040
+    },
+    {
+      "epoch": 1.3124056094929881,
+      "grad_norm": 0.4961661696434021,
+      "learning_rate": 0.00018900291098551767,
+      "loss": 0.7211409211158752,
+      "step": 3042
+    },
+    {
+      "epoch": 1.3132686084142395,
+      "grad_norm": 0.45150521397590637,
+      "learning_rate": 0.00018898051238929378,
+      "loss": 0.7317034602165222,
+      "step": 3044
+    },
+    {
+      "epoch": 1.314131607335491,
+      "grad_norm": 0.5012714266777039,
+      "learning_rate": 0.00018895809233582047,
+      "loss": 0.7838613390922546,
+      "step": 3046
+    },
+    {
+      "epoch": 1.3149946062567421,
+      "grad_norm": 0.5605086088180542,
+      "learning_rate": 0.0001889356508305042,
+      "loss": 0.8206616640090942,
+      "step": 3048
+    },
+    {
+      "epoch": 1.3158576051779936,
+      "grad_norm": 0.4337491989135742,
+      "learning_rate": 0.00018891318787875666,
+      "loss": 0.7460386753082275,
+      "step": 3050
+    },
+    {
+      "epoch": 1.316720604099245,
+      "grad_norm": 0.4392184913158417,
+      "learning_rate": 0.00018889070348599468,
+      "loss": 0.7973155379295349,
+      "step": 3052
+    },
+    {
+      "epoch": 1.3175836030204962,
+      "grad_norm": 0.4550181031227112,
+      "learning_rate": 0.00018886819765764028,
+      "loss": 0.6951689720153809,
+      "step": 3054
+    },
+    {
+      "epoch": 1.3184466019417476,
+      "grad_norm": 0.4058854877948761,
+      "learning_rate": 0.00018884567039912062,
+      "loss": 0.7353226542472839,
+      "step": 3056
+    },
+    {
+      "epoch": 1.319309600862999,
+      "grad_norm": 0.4157969057559967,
+      "learning_rate": 0.00018882312171586806,
+      "loss": 0.7758772969245911,
+      "step": 3058
+    },
+    {
+      "epoch": 1.3201725997842502,
+      "grad_norm": 0.44122767448425293,
+      "learning_rate": 0.00018880055161332016,
+      "loss": 0.6808486580848694,
+      "step": 3060
+    },
+    {
+      "epoch": 1.3210355987055016,
+      "grad_norm": 0.4674125015735626,
+      "learning_rate": 0.0001887779600969195,
+      "loss": 0.7781010270118713,
+      "step": 3062
+    },
+    {
+      "epoch": 1.321898597626753,
+      "grad_norm": 0.4414712190628052,
+      "learning_rate": 0.000188755347172114,
+      "loss": 0.7759971022605896,
+      "step": 3064
+    },
+    {
+      "epoch": 1.3227615965480042,
+      "grad_norm": 0.4804554283618927,
+      "learning_rate": 0.00018873271284435664,
+      "loss": 0.7430314421653748,
+      "step": 3066
+    },
+    {
+      "epoch": 1.3236245954692556,
+      "grad_norm": 0.4891934096813202,
+      "learning_rate": 0.00018871005711910562,
+      "loss": 0.6974785923957825,
+      "step": 3068
+    },
+    {
+      "epoch": 1.324487594390507,
+      "grad_norm": 0.4103528559207916,
+      "learning_rate": 0.0001886873800018242,
+      "loss": 0.6832907199859619,
+      "step": 3070
+    },
+    {
+      "epoch": 1.3253505933117584,
+      "grad_norm": 0.45092564821243286,
+      "learning_rate": 0.00018866468149798089,
+      "loss": 0.7700413465499878,
+      "step": 3072
+    },
+    {
+      "epoch": 1.3262135922330098,
+      "grad_norm": 0.47934943437576294,
+      "learning_rate": 0.00018864196161304933,
+      "loss": 0.7441738843917847,
+      "step": 3074
+    },
+    {
+      "epoch": 1.327076591154261,
+      "grad_norm": 0.756400465965271,
+      "learning_rate": 0.00018861922035250835,
+      "loss": 0.7195783853530884,
+      "step": 3076
+    },
+    {
+      "epoch": 1.3279395900755124,
+      "grad_norm": 0.47899410128593445,
+      "learning_rate": 0.00018859645772184187,
+      "loss": 0.6692811846733093,
+      "step": 3078
+    },
+    {
+      "epoch": 1.3288025889967638,
+      "grad_norm": 0.43265631794929504,
+      "learning_rate": 0.000188573673726539,
+      "loss": 0.6882596611976624,
+      "step": 3080
+    },
+    {
+      "epoch": 1.329665587918015,
+      "grad_norm": 0.4955349266529083,
+      "learning_rate": 0.00018855086837209401,
+      "loss": 0.9300010204315186,
+      "step": 3082
+    },
+    {
+      "epoch": 1.3305285868392664,
+      "grad_norm": 0.4638696312904358,
+      "learning_rate": 0.0001885280416640063,
+      "loss": 0.8391118049621582,
+      "step": 3084
+    },
+    {
+      "epoch": 1.3313915857605179,
+      "grad_norm": 0.4086083471775055,
+      "learning_rate": 0.00018850519360778044,
+      "loss": 0.7136397957801819,
+      "step": 3086
+    },
+    {
+      "epoch": 1.332254584681769,
+      "grad_norm": 0.4455646574497223,
+      "learning_rate": 0.0001884823242089261,
+      "loss": 0.6886621117591858,
+      "step": 3088
+    },
+    {
+      "epoch": 1.3331175836030205,
+      "grad_norm": 0.43355703353881836,
+      "learning_rate": 0.0001884594334729582,
+      "loss": 0.7261496782302856,
+      "step": 3090
+    },
+    {
+      "epoch": 1.3339805825242719,
+      "grad_norm": 0.5322562456130981,
+      "learning_rate": 0.00018843652140539664,
+      "loss": 0.8529927134513855,
+      "step": 3092
+    },
+    {
+      "epoch": 1.334843581445523,
+      "grad_norm": 0.4504645764827728,
+      "learning_rate": 0.00018841358801176668,
+      "loss": 0.8131585121154785,
+      "step": 3094
+    },
+    {
+      "epoch": 1.3357065803667745,
+      "grad_norm": 0.44101089239120483,
+      "learning_rate": 0.0001883906332975985,
+      "loss": 0.800965428352356,
+      "step": 3096
+    },
+    {
+      "epoch": 1.3365695792880259,
+      "grad_norm": 0.46587181091308594,
+      "learning_rate": 0.00018836765726842759,
+      "loss": 0.711025059223175,
+      "step": 3098
+    },
+    {
+      "epoch": 1.3374325782092773,
+      "grad_norm": 0.4656004011631012,
+      "learning_rate": 0.00018834465992979447,
+      "loss": 0.7824587225914001,
+      "step": 3100
+    },
+    {
+      "epoch": 1.3374325782092773,
+      "eval_loss": 0.8109187483787537,
+      "eval_runtime": 662.5843,
+      "eval_samples_per_second": 3.109,
+      "eval_steps_per_second": 3.109,
+      "step": 3100
+    },
+    {
+      "epoch": 1.3382955771305287,
+      "grad_norm": 0.4942762851715088,
+      "learning_rate": 0.00018832164128724488,
+      "loss": 0.7444300651550293,
+      "step": 3102
+    },
+    {
+      "epoch": 1.33915857605178,
+      "grad_norm": 0.5280060172080994,
+      "learning_rate": 0.00018829860134632963,
+      "loss": 0.8248856067657471,
+      "step": 3104
+    },
+    {
+      "epoch": 1.3400215749730313,
+      "grad_norm": 0.4131146967411041,
+      "learning_rate": 0.00018827554011260474,
+      "loss": 0.7753435373306274,
+      "step": 3106
+    },
+    {
+      "epoch": 1.3408845738942827,
+      "grad_norm": 0.38460803031921387,
+      "learning_rate": 0.0001882524575916313,
+      "loss": 0.7512242197990417,
+      "step": 3108
+    },
+    {
+      "epoch": 1.341747572815534,
+      "grad_norm": 0.4719627797603607,
+      "learning_rate": 0.00018822935378897554,
+      "loss": 0.7760549783706665,
+      "step": 3110
+    },
+    {
+      "epoch": 1.3426105717367853,
+      "grad_norm": 0.47593894600868225,
+      "learning_rate": 0.00018820622871020887,
+      "loss": 0.7802333831787109,
+      "step": 3112
+    },
+    {
+      "epoch": 1.3434735706580367,
+      "grad_norm": 0.46464505791664124,
+      "learning_rate": 0.00018818308236090778,
+      "loss": 0.7037042379379272,
+      "step": 3114
+    },
+    {
+      "epoch": 1.344336569579288,
+      "grad_norm": 0.4358392059803009,
+      "learning_rate": 0.0001881599147466539,
+      "loss": 0.7476377487182617,
+      "step": 3116
+    },
+    {
+      "epoch": 1.3451995685005393,
+      "grad_norm": 0.5236833095550537,
+      "learning_rate": 0.000188136725873034,
+      "loss": 0.8273758292198181,
+      "step": 3118
+    },
+    {
+      "epoch": 1.3460625674217908,
+      "grad_norm": 0.5240068435668945,
+      "learning_rate": 0.00018811351574564,
+      "loss": 0.7407519817352295,
+      "step": 3120
+    },
+    {
+      "epoch": 1.346925566343042,
+      "grad_norm": 0.44454488158226013,
+      "learning_rate": 0.00018809028437006888,
+      "loss": 0.708732008934021,
+      "step": 3122
+    },
+    {
+      "epoch": 1.3477885652642934,
+      "grad_norm": 0.43769216537475586,
+      "learning_rate": 0.00018806703175192283,
+      "loss": 0.7243810296058655,
+      "step": 3124
+    },
+    {
+      "epoch": 1.3486515641855448,
+      "grad_norm": 0.4477781355381012,
+      "learning_rate": 0.00018804375789680905,
+      "loss": 0.7603667974472046,
+      "step": 3126
+    },
+    {
+      "epoch": 1.3495145631067962,
+      "grad_norm": 0.4425322115421295,
+      "learning_rate": 0.00018802046281033997,
+      "loss": 0.7545933127403259,
+      "step": 3128
+    },
+    {
+      "epoch": 1.3503775620280476,
+      "grad_norm": 0.458310604095459,
+      "learning_rate": 0.00018799714649813304,
+      "loss": 0.7925270795822144,
+      "step": 3130
+    },
+    {
+      "epoch": 1.3512405609492988,
+      "grad_norm": 0.4328557848930359,
+      "learning_rate": 0.00018797380896581095,
+      "loss": 0.7392709851264954,
+      "step": 3132
+    },
+    {
+      "epoch": 1.3521035598705502,
+      "grad_norm": 0.4476810693740845,
+      "learning_rate": 0.00018795045021900144,
+      "loss": 0.7340229153633118,
+      "step": 3134
+    },
+    {
+      "epoch": 1.3529665587918016,
+      "grad_norm": 0.3931216895580292,
+      "learning_rate": 0.00018792707026333734,
+      "loss": 0.6678531765937805,
+      "step": 3136
+    },
+    {
+      "epoch": 1.3538295577130528,
+      "grad_norm": 0.4768988788127899,
+      "learning_rate": 0.0001879036691044566,
+      "loss": 0.8059957027435303,
+      "step": 3138
+    },
+    {
+      "epoch": 1.3546925566343042,
+      "grad_norm": 0.4464127719402313,
+      "learning_rate": 0.00018788024674800234,
+      "loss": 0.7618262767791748,
+      "step": 3140
+    },
+    {
+      "epoch": 1.3555555555555556,
+      "grad_norm": 0.4115859866142273,
+      "learning_rate": 0.00018785680319962272,
+      "loss": 0.7277366518974304,
+      "step": 3142
+    },
+    {
+      "epoch": 1.3564185544768068,
+      "grad_norm": 0.40479758381843567,
+      "learning_rate": 0.0001878333384649711,
+      "loss": 0.7587567567825317,
+      "step": 3144
+    },
+    {
+      "epoch": 1.3572815533980582,
+      "grad_norm": 0.5233479738235474,
+      "learning_rate": 0.00018780985254970584,
+      "loss": 0.7896765470504761,
+      "step": 3146
+    },
+    {
+      "epoch": 1.3581445523193096,
+      "grad_norm": 0.5604038834571838,
+      "learning_rate": 0.00018778634545949053,
+      "loss": 0.8300224542617798,
+      "step": 3148
+    },
+    {
+      "epoch": 1.3590075512405608,
+      "grad_norm": 0.48418891429901123,
+      "learning_rate": 0.00018776281719999372,
+      "loss": 0.8129078149795532,
+      "step": 3150
+    },
+    {
+      "epoch": 1.3598705501618122,
+      "grad_norm": 0.4338721036911011,
+      "learning_rate": 0.00018773926777688918,
+      "loss": 0.72742760181427,
+      "step": 3152
+    },
+    {
+      "epoch": 1.3607335490830637,
+      "grad_norm": 0.48870885372161865,
+      "learning_rate": 0.00018771569719585576,
+      "loss": 0.8129846453666687,
+      "step": 3154
+    },
+    {
+      "epoch": 1.361596548004315,
+      "grad_norm": 0.5070347785949707,
+      "learning_rate": 0.00018769210546257736,
+      "loss": 0.7692790031433105,
+      "step": 3156
+    },
+    {
+      "epoch": 1.3624595469255665,
+      "grad_norm": 0.4609982669353485,
+      "learning_rate": 0.0001876684925827431,
+      "loss": 0.6610854864120483,
+      "step": 3158
+    },
+    {
+      "epoch": 1.3633225458468177,
+      "grad_norm": 0.4481177031993866,
+      "learning_rate": 0.000187644858562047,
+      "loss": 0.7724031805992126,
+      "step": 3160
+    },
+    {
+      "epoch": 1.364185544768069,
+      "grad_norm": 0.38047513365745544,
+      "learning_rate": 0.0001876212034061884,
+      "loss": 0.7166935801506042,
+      "step": 3162
+    },
+    {
+      "epoch": 1.3650485436893205,
+      "grad_norm": 0.4010603427886963,
+      "learning_rate": 0.00018759752712087157,
+      "loss": 0.7535263299942017,
+      "step": 3164
+    },
+    {
+      "epoch": 1.3659115426105717,
+      "grad_norm": 0.411430299282074,
+      "learning_rate": 0.00018757382971180598,
+      "loss": 0.7471357583999634,
+      "step": 3166
+    },
+    {
+      "epoch": 1.366774541531823,
+      "grad_norm": 0.36775025725364685,
+      "learning_rate": 0.00018755011118470617,
+      "loss": 0.6910786032676697,
+      "step": 3168
+    },
+    {
+      "epoch": 1.3676375404530745,
+      "grad_norm": 0.5100153684616089,
+      "learning_rate": 0.0001875263715452917,
+      "loss": 0.7566528916358948,
+      "step": 3170
+    },
+    {
+      "epoch": 1.3685005393743257,
+      "grad_norm": 0.43466782569885254,
+      "learning_rate": 0.00018750261079928727,
+      "loss": 0.722017765045166,
+      "step": 3172
+    },
+    {
+      "epoch": 1.369363538295577,
+      "grad_norm": 0.4221585988998413,
+      "learning_rate": 0.00018747882895242275,
+      "loss": 0.7369917035102844,
+      "step": 3174
+    },
+    {
+      "epoch": 1.3702265372168285,
+      "grad_norm": 0.4663652777671814,
+      "learning_rate": 0.00018745502601043298,
+      "loss": 0.7522714138031006,
+      "step": 3176
+    },
+    {
+      "epoch": 1.3710895361380797,
+      "grad_norm": 0.4493909478187561,
+      "learning_rate": 0.0001874312019790579,
+      "loss": 0.7403551340103149,
+      "step": 3178
+    },
+    {
+      "epoch": 1.3719525350593311,
+      "grad_norm": 0.4245595932006836,
+      "learning_rate": 0.00018740735686404266,
+      "loss": 0.6998772025108337,
+      "step": 3180
+    },
+    {
+      "epoch": 1.3728155339805825,
+      "grad_norm": 0.4703865051269531,
+      "learning_rate": 0.00018738349067113735,
+      "loss": 0.6735976934432983,
+      "step": 3182
+    },
+    {
+      "epoch": 1.373678532901834,
+      "grad_norm": 0.5369067788124084,
+      "learning_rate": 0.00018735960340609715,
+      "loss": 0.764581561088562,
+      "step": 3184
+    },
+    {
+      "epoch": 1.3745415318230851,
+      "grad_norm": 0.4964922368526459,
+      "learning_rate": 0.00018733569507468242,
+      "loss": 0.7491477131843567,
+      "step": 3186
+    },
+    {
+      "epoch": 1.3754045307443366,
+      "grad_norm": 0.4167616665363312,
+      "learning_rate": 0.00018731176568265854,
+      "loss": 0.687139093875885,
+      "step": 3188
+    },
+    {
+      "epoch": 1.376267529665588,
+      "grad_norm": 0.4885561764240265,
+      "learning_rate": 0.00018728781523579598,
+      "loss": 0.76422518491745,
+      "step": 3190
+    },
+    {
+      "epoch": 1.3771305285868394,
+      "grad_norm": 0.45865342020988464,
+      "learning_rate": 0.00018726384373987025,
+      "loss": 0.7054057121276855,
+      "step": 3192
+    },
+    {
+      "epoch": 1.3779935275080906,
+      "grad_norm": 0.4557322561740875,
+      "learning_rate": 0.000187239851200662,
+      "loss": 0.7476370334625244,
+      "step": 3194
+    },
+    {
+      "epoch": 1.378856526429342,
+      "grad_norm": 0.4359823763370514,
+      "learning_rate": 0.00018721583762395692,
+      "loss": 0.7450100183486938,
+      "step": 3196
+    },
+    {
+      "epoch": 1.3797195253505934,
+      "grad_norm": 0.45140165090560913,
+      "learning_rate": 0.00018719180301554576,
+      "loss": 0.6332225799560547,
+      "step": 3198
+    },
+    {
+      "epoch": 1.3805825242718446,
+      "grad_norm": 0.4051663875579834,
+      "learning_rate": 0.00018716774738122436,
+      "loss": 0.6999903917312622,
+      "step": 3200
+    },
+    {
+      "epoch": 1.3805825242718446,
+      "eval_loss": 0.8053163290023804,
+      "eval_runtime": 668.3288,
+      "eval_samples_per_second": 3.082,
+      "eval_steps_per_second": 3.082,
+      "step": 3200
+    },
+    {
+      "epoch": 1.381445523193096,
+      "grad_norm": 0.43624332547187805,
+      "learning_rate": 0.00018714367072679365,
+      "loss": 0.675305962562561,
+      "step": 3202
+    },
+    {
+      "epoch": 1.3823085221143474,
+      "grad_norm": 0.5163410902023315,
+      "learning_rate": 0.00018711957305805955,
+      "loss": 0.8098652958869934,
+      "step": 3204
+    },
+    {
+      "epoch": 1.3831715210355986,
+      "grad_norm": 0.5261862277984619,
+      "learning_rate": 0.00018709545438083317,
+      "loss": 0.7265567779541016,
+      "step": 3206
+    },
+    {
+      "epoch": 1.38403451995685,
+      "grad_norm": 0.5289353728294373,
+      "learning_rate": 0.0001870713147009306,
+      "loss": 0.8171496987342834,
+      "step": 3208
+    },
+    {
+      "epoch": 1.3848975188781014,
+      "grad_norm": 0.45589691400527954,
+      "learning_rate": 0.000187047154024173,
+      "loss": 0.800773024559021,
+      "step": 3210
+    },
+    {
+      "epoch": 1.3857605177993528,
+      "grad_norm": 0.4709073603153229,
+      "learning_rate": 0.00018702297235638664,
+      "loss": 0.7034035921096802,
+      "step": 3212
+    },
+    {
+      "epoch": 1.386623516720604,
+      "grad_norm": 0.41431429982185364,
+      "learning_rate": 0.00018699876970340278,
+      "loss": 0.6707210540771484,
+      "step": 3214
+    },
+    {
+      "epoch": 1.3874865156418554,
+      "grad_norm": 0.4663850963115692,
+      "learning_rate": 0.0001869745460710578,
+      "loss": 0.7554471492767334,
+      "step": 3216
+    },
+    {
+      "epoch": 1.3883495145631068,
+      "grad_norm": 0.3720403015613556,
+      "learning_rate": 0.00018695030146519313,
+      "loss": 0.6852688193321228,
+      "step": 3218
+    },
+    {
+      "epoch": 1.3892125134843583,
+      "grad_norm": 0.46755164861679077,
+      "learning_rate": 0.00018692603589165523,
+      "loss": 0.7974506616592407,
+      "step": 3220
+    },
+    {
+      "epoch": 1.3900755124056094,
+      "grad_norm": 0.4087965786457062,
+      "learning_rate": 0.00018690174935629563,
+      "loss": 0.6643959283828735,
+      "step": 3222
+    },
+    {
+      "epoch": 1.3909385113268609,
+      "grad_norm": 0.43572601675987244,
+      "learning_rate": 0.00018687744186497092,
+      "loss": 0.6455117464065552,
+      "step": 3224
+    },
+    {
+      "epoch": 1.3918015102481123,
+      "grad_norm": 0.4832928776741028,
+      "learning_rate": 0.00018685311342354276,
+      "loss": 0.7152265310287476,
+      "step": 3226
+    },
+    {
+      "epoch": 1.3926645091693635,
+      "grad_norm": 0.44429874420166016,
+      "learning_rate": 0.00018682876403787783,
+      "loss": 0.714832067489624,
+      "step": 3228
+    },
+    {
+      "epoch": 1.3935275080906149,
+      "grad_norm": 0.4570554494857788,
+      "learning_rate": 0.0001868043937138479,
+      "loss": 0.7785174250602722,
+      "step": 3230
+    },
+    {
+      "epoch": 1.3943905070118663,
+      "grad_norm": 0.4618188738822937,
+      "learning_rate": 0.00018678000245732972,
+      "loss": 0.7226384878158569,
+      "step": 3232
+    },
+    {
+      "epoch": 1.3952535059331175,
+      "grad_norm": 0.5473061203956604,
+      "learning_rate": 0.00018675559027420515,
+      "loss": 0.741666316986084,
+      "step": 3234
+    },
+    {
+      "epoch": 1.396116504854369,
+      "grad_norm": 0.45633625984191895,
+      "learning_rate": 0.0001867311571703611,
+      "loss": 0.7774195671081543,
+      "step": 3236
+    },
+    {
+      "epoch": 1.3969795037756203,
+      "grad_norm": 0.4549288749694824,
+      "learning_rate": 0.00018670670315168946,
+      "loss": 0.7062699794769287,
+      "step": 3238
+    },
+    {
+      "epoch": 1.3978425026968715,
+      "grad_norm": 0.4530162513256073,
+      "learning_rate": 0.00018668222822408725,
+      "loss": 0.7901433110237122,
+      "step": 3240
+    },
+    {
+      "epoch": 1.398705501618123,
+      "grad_norm": 0.4526861608028412,
+      "learning_rate": 0.00018665773239345647,
+      "loss": 0.7321763038635254,
+      "step": 3242
+    },
+    {
+      "epoch": 1.3995685005393743,
+      "grad_norm": 0.471683531999588,
+      "learning_rate": 0.00018663321566570417,
+      "loss": 0.780885636806488,
+      "step": 3244
+    },
+    {
+      "epoch": 1.4004314994606257,
+      "grad_norm": 0.4421135187149048,
+      "learning_rate": 0.00018660867804674248,
+      "loss": 0.7124532461166382,
+      "step": 3246
+    },
+    {
+      "epoch": 1.4012944983818771,
+      "grad_norm": 0.45071855187416077,
+      "learning_rate": 0.00018658411954248849,
+      "loss": 0.7868198156356812,
+      "step": 3248
+    },
+    {
+      "epoch": 1.4021574973031283,
+      "grad_norm": 0.45456045866012573,
+      "learning_rate": 0.0001865595401588644,
+      "loss": 0.7364398837089539,
+      "step": 3250
+    },
+    {
+      "epoch": 1.4030204962243797,
+      "grad_norm": 0.4487321972846985,
+      "learning_rate": 0.0001865349399017974,
+      "loss": 0.7381253838539124,
+      "step": 3252
+    },
+    {
+      "epoch": 1.4038834951456312,
+      "grad_norm": 0.433517724275589,
+      "learning_rate": 0.00018651031877721976,
+      "loss": 0.6974755525588989,
+      "step": 3254
+    },
+    {
+      "epoch": 1.4047464940668823,
+      "grad_norm": 0.45759329199790955,
+      "learning_rate": 0.00018648567679106873,
+      "loss": 0.7638785243034363,
+      "step": 3256
+    },
+    {
+      "epoch": 1.4056094929881338,
+      "grad_norm": 0.4451565742492676,
+      "learning_rate": 0.00018646101394928662,
+      "loss": 0.7301747798919678,
+      "step": 3258
+    },
+    {
+      "epoch": 1.4064724919093852,
+      "grad_norm": 0.5451349020004272,
+      "learning_rate": 0.0001864363302578208,
+      "loss": 0.770787239074707,
+      "step": 3260
+    },
+    {
+      "epoch": 1.4073354908306364,
+      "grad_norm": 0.47335579991340637,
+      "learning_rate": 0.00018641162572262355,
+      "loss": 0.7637011408805847,
+      "step": 3262
+    },
+    {
+      "epoch": 1.4081984897518878,
+      "grad_norm": 0.480887234210968,
+      "learning_rate": 0.0001863869003496523,
+      "loss": 0.7140913009643555,
+      "step": 3264
+    },
+    {
+      "epoch": 1.4090614886731392,
+      "grad_norm": 0.4122021496295929,
+      "learning_rate": 0.0001863621541448695,
+      "loss": 0.6538959741592407,
+      "step": 3266
+    },
+    {
+      "epoch": 1.4099244875943904,
+      "grad_norm": 0.4456968605518341,
+      "learning_rate": 0.00018633738711424253,
+      "loss": 0.7153927087783813,
+      "step": 3268
+    },
+    {
+      "epoch": 1.4107874865156418,
+      "grad_norm": 0.4152887761592865,
+      "learning_rate": 0.00018631259926374388,
+      "loss": 0.7140036821365356,
+      "step": 3270
+    },
+    {
+      "epoch": 1.4116504854368932,
+      "grad_norm": 0.47110119462013245,
+      "learning_rate": 0.00018628779059935103,
+      "loss": 0.7193810939788818,
+      "step": 3272
+    },
+    {
+      "epoch": 1.4125134843581446,
+      "grad_norm": 0.39739692211151123,
+      "learning_rate": 0.0001862629611270464,
+      "loss": 0.7133702039718628,
+      "step": 3274
+    },
+    {
+      "epoch": 1.413376483279396,
+      "grad_norm": 0.4808974862098694,
+      "learning_rate": 0.00018623811085281765,
+      "loss": 0.811927855014801,
+      "step": 3276
+    },
+    {
+      "epoch": 1.4142394822006472,
+      "grad_norm": 0.4607976973056793,
+      "learning_rate": 0.00018621323978265718,
+      "loss": 0.8125779032707214,
+      "step": 3278
+    },
+    {
+      "epoch": 1.4151024811218986,
+      "grad_norm": 0.41523823142051697,
+      "learning_rate": 0.00018618834792256261,
+      "loss": 0.7065606117248535,
+      "step": 3280
+    },
+    {
+      "epoch": 1.41596548004315,
+      "grad_norm": 0.46665191650390625,
+      "learning_rate": 0.00018616343527853645,
+      "loss": 0.7346477508544922,
+      "step": 3282
+    },
+    {
+      "epoch": 1.4168284789644012,
+      "grad_norm": 0.4744371473789215,
+      "learning_rate": 0.00018613850185658634,
+      "loss": 0.7590131759643555,
+      "step": 3284
+    },
+    {
+      "epoch": 1.4176914778856526,
+      "grad_norm": 0.4905717074871063,
+      "learning_rate": 0.0001861135476627248,
+      "loss": 0.786243200302124,
+      "step": 3286
+    },
+    {
+      "epoch": 1.418554476806904,
+      "grad_norm": 0.45114004611968994,
+      "learning_rate": 0.00018608857270296944,
+      "loss": 0.6855072379112244,
+      "step": 3288
+    },
+    {
+      "epoch": 1.4194174757281552,
+      "grad_norm": 0.5547319054603577,
+      "learning_rate": 0.00018606357698334284,
+      "loss": 0.8294073343276978,
+      "step": 3290
+    },
+    {
+      "epoch": 1.4202804746494067,
+      "grad_norm": 0.4100660979747772,
+      "learning_rate": 0.00018603856050987267,
+      "loss": 0.6352306604385376,
+      "step": 3292
+    },
+    {
+      "epoch": 1.421143473570658,
+      "grad_norm": 0.47723907232284546,
+      "learning_rate": 0.00018601352328859148,
+      "loss": 0.7822797298431396,
+      "step": 3294
+    },
+    {
+      "epoch": 1.4220064724919093,
+      "grad_norm": 0.45811668038368225,
+      "learning_rate": 0.00018598846532553691,
+      "loss": 0.7675215601921082,
+      "step": 3296
+    },
+    {
+      "epoch": 1.4228694714131607,
+      "grad_norm": 0.4794461131095886,
+      "learning_rate": 0.00018596338662675154,
+      "loss": 0.7994555234909058,
+      "step": 3298
+    },
+    {
+      "epoch": 1.423732470334412,
+      "grad_norm": 0.458723783493042,
+      "learning_rate": 0.00018593828719828303,
+      "loss": 0.7676554918289185,
+      "step": 3300
+    },
+    {
+      "epoch": 1.423732470334412,
+      "eval_loss": 0.8030428886413574,
+      "eval_runtime": 658.5495,
+      "eval_samples_per_second": 3.128,
+      "eval_steps_per_second": 3.128,
+      "step": 3300
+    },
+    {
+      "epoch": 1.4245954692556635,
+      "grad_norm": 0.4599555432796478,
+      "learning_rate": 0.00018591316704618397,
+      "loss": 0.7642499804496765,
+      "step": 3302
+    },
+    {
+      "epoch": 1.425458468176915,
+      "grad_norm": 0.5012795925140381,
+      "learning_rate": 0.000185888026176512,
+      "loss": 0.7753090262413025,
+      "step": 3304
+    },
+    {
+      "epoch": 1.426321467098166,
+      "grad_norm": 0.4497458040714264,
+      "learning_rate": 0.00018586286459532967,
+      "loss": 0.7226543426513672,
+      "step": 3306
+    },
+    {
+      "epoch": 1.4271844660194175,
+      "grad_norm": 0.47314873337745667,
+      "learning_rate": 0.0001858376823087046,
+      "loss": 0.752973735332489,
+      "step": 3308
+    },
+    {
+      "epoch": 1.428047464940669,
+      "grad_norm": 0.45765072107315063,
+      "learning_rate": 0.00018581247932270944,
+      "loss": 0.7653468251228333,
+      "step": 3310
+    },
+    {
+      "epoch": 1.42891046386192,
+      "grad_norm": 0.4725930392742157,
+      "learning_rate": 0.0001857872556434217,
+      "loss": 0.8080248832702637,
+      "step": 3312
+    },
+    {
+      "epoch": 1.4297734627831715,
+      "grad_norm": 0.4430061876773834,
+      "learning_rate": 0.00018576201127692402,
+      "loss": 0.8083968162536621,
+      "step": 3314
+    },
+    {
+      "epoch": 1.430636461704423,
+      "grad_norm": 0.4197101294994354,
+      "learning_rate": 0.00018573674622930392,
+      "loss": 0.7861490249633789,
+      "step": 3316
+    },
+    {
+      "epoch": 1.4314994606256741,
+      "grad_norm": 0.4047538936138153,
+      "learning_rate": 0.00018571146050665397,
+      "loss": 0.8125455379486084,
+      "step": 3318
+    },
+    {
+      "epoch": 1.4323624595469255,
+      "grad_norm": 0.5689038634300232,
+      "learning_rate": 0.00018568615411507174,
+      "loss": 0.779180645942688,
+      "step": 3320
+    },
+    {
+      "epoch": 1.433225458468177,
+      "grad_norm": 0.47798338532447815,
+      "learning_rate": 0.00018566082706065969,
+      "loss": 0.7555606961250305,
+      "step": 3322
+    },
+    {
+      "epoch": 1.4340884573894281,
+      "grad_norm": 0.4296347200870514,
+      "learning_rate": 0.00018563547934952537,
+      "loss": 0.6761099696159363,
+      "step": 3324
+    },
+    {
+      "epoch": 1.4349514563106796,
+      "grad_norm": 0.4605977237224579,
+      "learning_rate": 0.00018561011098778126,
+      "loss": 0.7465946078300476,
+      "step": 3326
+    },
+    {
+      "epoch": 1.435814455231931,
+      "grad_norm": 0.48226889967918396,
+      "learning_rate": 0.00018558472198154478,
+      "loss": 0.7459924817085266,
+      "step": 3328
+    },
+    {
+      "epoch": 1.4366774541531824,
+      "grad_norm": 0.4655393362045288,
+      "learning_rate": 0.00018555931233693845,
+      "loss": 0.6451191306114197,
+      "step": 3330
+    },
+    {
+      "epoch": 1.4375404530744338,
+      "grad_norm": 0.4614768922328949,
+      "learning_rate": 0.00018553388206008961,
+      "loss": 0.764894962310791,
+      "step": 3332
+    },
+    {
+      "epoch": 1.438403451995685,
+      "grad_norm": 0.47503674030303955,
+      "learning_rate": 0.00018550843115713072,
+      "loss": 0.7709850072860718,
+      "step": 3334
+    },
+    {
+      "epoch": 1.4392664509169364,
+      "grad_norm": 0.5408021807670593,
+      "learning_rate": 0.00018548295963419914,
+      "loss": 0.8470542430877686,
+      "step": 3336
+    },
+    {
+      "epoch": 1.4401294498381878,
+      "grad_norm": 0.44747427105903625,
+      "learning_rate": 0.0001854574674974372,
+      "loss": 0.770861804485321,
+      "step": 3338
+    },
+    {
+      "epoch": 1.440992448759439,
+      "grad_norm": 0.3823722004890442,
+      "learning_rate": 0.00018543195475299222,
+      "loss": 0.6909842491149902,
+      "step": 3340
+    },
+    {
+      "epoch": 1.4418554476806904,
+      "grad_norm": 0.42207640409469604,
+      "learning_rate": 0.0001854064214070165,
+      "loss": 0.7684979438781738,
+      "step": 3342
+    },
+    {
+      "epoch": 1.4427184466019418,
+      "grad_norm": 0.4514349400997162,
+      "learning_rate": 0.00018538086746566724,
+      "loss": 0.754643440246582,
+      "step": 3344
+    },
+    {
+      "epoch": 1.443581445523193,
+      "grad_norm": 0.4289906620979309,
+      "learning_rate": 0.0001853552929351067,
+      "loss": 0.7302715182304382,
+      "step": 3346
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 0.4458511173725128,
+      "learning_rate": 0.00018532969782150205,
+      "loss": 0.7611445188522339,
+      "step": 3348
+    },
+    {
+      "epoch": 1.4453074433656958,
+      "grad_norm": 0.4370715022087097,
+      "learning_rate": 0.00018530408213102546,
+      "loss": 0.7713651061058044,
+      "step": 3350
+    },
+    {
+      "epoch": 1.446170442286947,
+      "grad_norm": 0.40230461955070496,
+      "learning_rate": 0.000185278445869854,
+      "loss": 0.6728963851928711,
+      "step": 3352
+    },
+    {
+      "epoch": 1.4470334412081984,
+      "grad_norm": 0.43601900339126587,
+      "learning_rate": 0.00018525278904416975,
+      "loss": 0.7662684321403503,
+      "step": 3354
+    },
+    {
+      "epoch": 1.4478964401294498,
+      "grad_norm": 0.45813488960266113,
+      "learning_rate": 0.00018522711166015974,
+      "loss": 0.8269308805465698,
+      "step": 3356
+    },
+    {
+      "epoch": 1.4487594390507013,
+      "grad_norm": 0.48386695981025696,
+      "learning_rate": 0.00018520141372401595,
+      "loss": 0.8171968460083008,
+      "step": 3358
+    },
+    {
+      "epoch": 1.4496224379719527,
+      "grad_norm": 0.41737180948257446,
+      "learning_rate": 0.00018517569524193535,
+      "loss": 0.8057414889335632,
+      "step": 3360
+    },
+    {
+      "epoch": 1.4504854368932039,
+      "grad_norm": 0.41048938035964966,
+      "learning_rate": 0.0001851499562201198,
+      "loss": 0.7350438833236694,
+      "step": 3362
+    },
+    {
+      "epoch": 1.4513484358144553,
+      "grad_norm": 0.49414724111557007,
+      "learning_rate": 0.0001851241966647762,
+      "loss": 0.7771334052085876,
+      "step": 3364
+    },
+    {
+      "epoch": 1.4522114347357067,
+      "grad_norm": 0.48357486724853516,
+      "learning_rate": 0.00018509841658211632,
+      "loss": 0.8041897416114807,
+      "step": 3366
+    },
+    {
+      "epoch": 1.4530744336569579,
+      "grad_norm": 0.44553041458129883,
+      "learning_rate": 0.00018507261597835686,
+      "loss": 0.7079073786735535,
+      "step": 3368
+    },
+    {
+      "epoch": 1.4539374325782093,
+      "grad_norm": 0.4198709726333618,
+      "learning_rate": 0.0001850467948597196,
+      "loss": 0.7564307451248169,
+      "step": 3370
+    },
+    {
+      "epoch": 1.4548004314994607,
+      "grad_norm": 0.4005102217197418,
+      "learning_rate": 0.00018502095323243113,
+      "loss": 0.6955130696296692,
+      "step": 3372
+    },
+    {
+      "epoch": 1.455663430420712,
+      "grad_norm": 0.43197157979011536,
+      "learning_rate": 0.00018499509110272308,
+      "loss": 0.6564432978630066,
+      "step": 3374
+    },
+    {
+      "epoch": 1.4565264293419633,
+      "grad_norm": 0.4266451299190521,
+      "learning_rate": 0.00018496920847683196,
+      "loss": 0.6715503931045532,
+      "step": 3376
+    },
+    {
+      "epoch": 1.4573894282632147,
+      "grad_norm": 0.4835279583930969,
+      "learning_rate": 0.00018494330536099926,
+      "loss": 0.7800700068473816,
+      "step": 3378
+    },
+    {
+      "epoch": 1.458252427184466,
+      "grad_norm": 0.5084423422813416,
+      "learning_rate": 0.00018491738176147139,
+      "loss": 0.7650374174118042,
+      "step": 3380
+    },
+    {
+      "epoch": 1.4591154261057173,
+      "grad_norm": 0.41681453585624695,
+      "learning_rate": 0.00018489143768449974,
+      "loss": 0.7307957410812378,
+      "step": 3382
+    },
+    {
+      "epoch": 1.4599784250269687,
+      "grad_norm": 0.4184363782405853,
+      "learning_rate": 0.00018486547313634058,
+      "loss": 0.7257798910140991,
+      "step": 3384
+    },
+    {
+      "epoch": 1.4608414239482201,
+      "grad_norm": 0.5055010318756104,
+      "learning_rate": 0.00018483948812325512,
+      "loss": 0.7981155514717102,
+      "step": 3386
+    },
+    {
+      "epoch": 1.4617044228694713,
+      "grad_norm": 0.4449431300163269,
+      "learning_rate": 0.00018481348265150961,
+      "loss": 0.7802942395210266,
+      "step": 3388
+    },
+    {
+      "epoch": 1.4625674217907227,
+      "grad_norm": 0.3826743960380554,
+      "learning_rate": 0.00018478745672737508,
+      "loss": 0.6799795031547546,
+      "step": 3390
+    },
+    {
+      "epoch": 1.4634304207119742,
+      "grad_norm": 0.4156678318977356,
+      "learning_rate": 0.00018476141035712757,
+      "loss": 0.7275620698928833,
+      "step": 3392
+    },
+    {
+      "epoch": 1.4642934196332256,
+      "grad_norm": 0.47241929173469543,
+      "learning_rate": 0.00018473534354704807,
+      "loss": 0.6979914903640747,
+      "step": 3394
+    },
+    {
+      "epoch": 1.4651564185544768,
+      "grad_norm": 0.4340677261352539,
+      "learning_rate": 0.00018470925630342247,
+      "loss": 0.7208709120750427,
+      "step": 3396
+    },
+    {
+      "epoch": 1.4660194174757282,
+      "grad_norm": 0.39896467328071594,
+      "learning_rate": 0.00018468314863254154,
+      "loss": 0.6596860885620117,
+      "step": 3398
+    },
+    {
+      "epoch": 1.4668824163969796,
+      "grad_norm": 0.4282037317752838,
+      "learning_rate": 0.00018465702054070113,
+      "loss": 0.7703273892402649,
+      "step": 3400
+    },
+    {
+      "epoch": 1.4668824163969796,
+      "eval_loss": 0.8002338409423828,
+      "eval_runtime": 649.7427,
+      "eval_samples_per_second": 3.17,
+      "eval_steps_per_second": 3.17,
+      "step": 3400
+    },
+    {
+      "epoch": 1.4677454153182308,
+      "grad_norm": 0.39301496744155884,
+      "learning_rate": 0.00018463087203420182,
+      "loss": 0.740729033946991,
+      "step": 3402
+    },
+    {
+      "epoch": 1.4686084142394822,
+      "grad_norm": 0.4466440677642822,
+      "learning_rate": 0.00018460470311934923,
+      "loss": 0.6625239253044128,
+      "step": 3404
+    },
+    {
+      "epoch": 1.4694714131607336,
+      "grad_norm": 0.48659050464630127,
+      "learning_rate": 0.00018457851380245392,
+      "loss": 0.7232626080513,
+      "step": 3406
+    },
+    {
+      "epoch": 1.4703344120819848,
+      "grad_norm": 0.44322678446769714,
+      "learning_rate": 0.00018455230408983124,
+      "loss": 0.6909189224243164,
+      "step": 3408
+    },
+    {
+      "epoch": 1.4711974110032362,
+      "grad_norm": 0.4537222683429718,
+      "learning_rate": 0.0001845260739878016,
+      "loss": 0.728760302066803,
+      "step": 3410
+    },
+    {
+      "epoch": 1.4720604099244876,
+      "grad_norm": 0.426753968000412,
+      "learning_rate": 0.0001844998235026903,
+      "loss": 0.6631523966789246,
+      "step": 3412
+    },
+    {
+      "epoch": 1.472923408845739,
+      "grad_norm": 0.46893343329429626,
+      "learning_rate": 0.0001844735526408275,
+      "loss": 0.7257310748100281,
+      "step": 3414
+    },
+    {
+      "epoch": 1.4737864077669902,
+      "grad_norm": 0.41580045223236084,
+      "learning_rate": 0.00018444726140854823,
+      "loss": 0.7732333540916443,
+      "step": 3416
+    },
+    {
+      "epoch": 1.4746494066882416,
+      "grad_norm": 0.42891791462898254,
+      "learning_rate": 0.00018442094981219257,
+      "loss": 0.6602647304534912,
+      "step": 3418
+    },
+    {
+      "epoch": 1.475512405609493,
+      "grad_norm": 0.45967262983322144,
+      "learning_rate": 0.00018439461785810547,
+      "loss": 0.7164129018783569,
+      "step": 3420
+    },
+    {
+      "epoch": 1.4763754045307445,
+      "grad_norm": 0.4251352846622467,
+      "learning_rate": 0.0001843682655526367,
+      "loss": 0.7289180755615234,
+      "step": 3422
+    },
+    {
+      "epoch": 1.4772384034519956,
+      "grad_norm": 0.3898853361606598,
+      "learning_rate": 0.00018434189290214106,
+      "loss": 0.7455880641937256,
+      "step": 3424
+    },
+    {
+      "epoch": 1.478101402373247,
+      "grad_norm": 0.4341840445995331,
+      "learning_rate": 0.00018431549991297815,
+      "loss": 0.7042546272277832,
+      "step": 3426
+    },
+    {
+      "epoch": 1.4789644012944985,
+      "grad_norm": 0.41306495666503906,
+      "learning_rate": 0.00018428908659151252,
+      "loss": 0.7600736021995544,
+      "step": 3428
+    },
+    {
+      "epoch": 1.4798274002157497,
+      "grad_norm": 0.41544052958488464,
+      "learning_rate": 0.00018426265294411363,
+      "loss": 0.7219595909118652,
+      "step": 3430
+    },
+    {
+      "epoch": 1.480690399137001,
+      "grad_norm": 0.45290282368659973,
+      "learning_rate": 0.00018423619897715585,
+      "loss": 0.8417305946350098,
+      "step": 3432
+    },
+    {
+      "epoch": 1.4815533980582525,
+      "grad_norm": 0.4438819885253906,
+      "learning_rate": 0.00018420972469701842,
+      "loss": 0.7625543475151062,
+      "step": 3434
+    },
+    {
+      "epoch": 1.4824163969795037,
+      "grad_norm": 0.49848470091819763,
+      "learning_rate": 0.00018418323011008548,
+      "loss": 0.7759302258491516,
+      "step": 3436
+    },
+    {
+      "epoch": 1.483279395900755,
+      "grad_norm": 0.3774218261241913,
+      "learning_rate": 0.00018415671522274614,
+      "loss": 0.6921430826187134,
+      "step": 3438
+    },
+    {
+      "epoch": 1.4841423948220065,
+      "grad_norm": 0.4494822919368744,
+      "learning_rate": 0.0001841301800413943,
+      "loss": 0.6789629459381104,
+      "step": 3440
+    },
+    {
+      "epoch": 1.4850053937432577,
+      "grad_norm": 0.4084416329860687,
+      "learning_rate": 0.00018410362457242876,
+      "loss": 0.6904259324073792,
+      "step": 3442
+    },
+    {
+      "epoch": 1.485868392664509,
+      "grad_norm": 0.4472881257534027,
+      "learning_rate": 0.0001840770488222533,
+      "loss": 0.7037150263786316,
+      "step": 3444
+    },
+    {
+      "epoch": 1.4867313915857605,
+      "grad_norm": 0.4696385860443115,
+      "learning_rate": 0.0001840504527972766,
+      "loss": 0.7732300758361816,
+      "step": 3446
+    },
+    {
+      "epoch": 1.487594390507012,
+      "grad_norm": 0.4683626592159271,
+      "learning_rate": 0.00018402383650391207,
+      "loss": 0.767594039440155,
+      "step": 3448
+    },
+    {
+      "epoch": 1.4884573894282633,
+      "grad_norm": 0.47404953837394714,
+      "learning_rate": 0.00018399719994857816,
+      "loss": 0.8145772218704224,
+      "step": 3450
+    },
+    {
+      "epoch": 1.4893203883495145,
+      "grad_norm": 0.5147852897644043,
+      "learning_rate": 0.00018397054313769814,
+      "loss": 0.784772515296936,
+      "step": 3452
+    },
+    {
+      "epoch": 1.490183387270766,
+      "grad_norm": 0.5376461744308472,
+      "learning_rate": 0.00018394386607770017,
+      "loss": 0.7849431037902832,
+      "step": 3454
+    },
+    {
+      "epoch": 1.4910463861920173,
+      "grad_norm": 0.4688630700111389,
+      "learning_rate": 0.0001839171687750173,
+      "loss": 0.7196945548057556,
+      "step": 3456
+    },
+    {
+      "epoch": 1.4919093851132685,
+      "grad_norm": 0.5115576386451721,
+      "learning_rate": 0.00018389045123608753,
+      "loss": 0.8277292251586914,
+      "step": 3458
+    },
+    {
+      "epoch": 1.49277238403452,
+      "grad_norm": 0.3999786674976349,
+      "learning_rate": 0.0001838637134673536,
+      "loss": 0.7628065943717957,
+      "step": 3460
+    },
+    {
+      "epoch": 1.4936353829557714,
+      "grad_norm": 0.4474492371082306,
+      "learning_rate": 0.00018383695547526322,
+      "loss": 0.717315673828125,
+      "step": 3462
+    },
+    {
+      "epoch": 1.4944983818770226,
+      "grad_norm": 0.4175044596195221,
+      "learning_rate": 0.00018381017726626896,
+      "loss": 0.7365549206733704,
+      "step": 3464
+    },
+    {
+      "epoch": 1.495361380798274,
+      "grad_norm": 0.4938793480396271,
+      "learning_rate": 0.0001837833788468283,
+      "loss": 0.7562727928161621,
+      "step": 3466
+    },
+    {
+      "epoch": 1.4962243797195254,
+      "grad_norm": 0.4369599521160126,
+      "learning_rate": 0.0001837565602234035,
+      "loss": 0.82245272397995,
+      "step": 3468
+    },
+    {
+      "epoch": 1.4970873786407766,
+      "grad_norm": 0.4824387729167938,
+      "learning_rate": 0.00018372972140246182,
+      "loss": 0.7570599913597107,
+      "step": 3470
+    },
+    {
+      "epoch": 1.497950377562028,
+      "grad_norm": 0.46261459589004517,
+      "learning_rate": 0.00018370286239047522,
+      "loss": 0.7152431607246399,
+      "step": 3472
+    },
+    {
+      "epoch": 1.4988133764832794,
+      "grad_norm": 0.4452435076236725,
+      "learning_rate": 0.0001836759831939207,
+      "loss": 0.6635003089904785,
+      "step": 3474
+    },
+    {
+      "epoch": 1.4996763754045308,
+      "grad_norm": 0.4698450267314911,
+      "learning_rate": 0.0001836490838192801,
+      "loss": 0.7814362645149231,
+      "step": 3476
+    },
+    {
+      "epoch": 1.5005393743257822,
+      "grad_norm": 0.44320493936538696,
+      "learning_rate": 0.00018362216427303998,
+      "loss": 0.6941080689430237,
+      "step": 3478
+    },
+    {
+      "epoch": 1.5014023732470334,
+      "grad_norm": 0.467252254486084,
+      "learning_rate": 0.00018359522456169193,
+      "loss": 0.7583049535751343,
+      "step": 3480
+    },
+    {
+      "epoch": 1.5022653721682848,
+      "grad_norm": 0.5454360842704773,
+      "learning_rate": 0.00018356826469173232,
+      "loss": 0.9017908573150635,
+      "step": 3482
+    },
+    {
+      "epoch": 1.5031283710895362,
+      "grad_norm": 0.5124768614768982,
+      "learning_rate": 0.00018354128466966242,
+      "loss": 0.8088064789772034,
+      "step": 3484
+    },
+    {
+      "epoch": 1.5039913700107874,
+      "grad_norm": 0.4634758234024048,
+      "learning_rate": 0.00018351428450198834,
+      "loss": 0.7869967222213745,
+      "step": 3486
+    },
+    {
+      "epoch": 1.5048543689320388,
+      "grad_norm": 0.39626801013946533,
+      "learning_rate": 0.00018348726419522098,
+      "loss": 0.7509294152259827,
+      "step": 3488
+    },
+    {
+      "epoch": 1.5057173678532902,
+      "grad_norm": 0.48879387974739075,
+      "learning_rate": 0.00018346022375587628,
+      "loss": 0.710981011390686,
+      "step": 3490
+    },
+    {
+      "epoch": 1.5065803667745414,
+      "grad_norm": 0.4784195125102997,
+      "learning_rate": 0.00018343316319047482,
+      "loss": 0.7631853222846985,
+      "step": 3492
+    },
+    {
+      "epoch": 1.5074433656957928,
+      "grad_norm": 0.45802050828933716,
+      "learning_rate": 0.00018340608250554222,
+      "loss": 0.7416844964027405,
+      "step": 3494
+    },
+    {
+      "epoch": 1.5083063646170443,
+      "grad_norm": 0.42670297622680664,
+      "learning_rate": 0.0001833789817076088,
+      "loss": 0.8117082715034485,
+      "step": 3496
+    },
+    {
+      "epoch": 1.5091693635382954,
+      "grad_norm": 0.48401451110839844,
+      "learning_rate": 0.00018335186080320983,
+      "loss": 0.724604606628418,
+      "step": 3498
+    },
+    {
+      "epoch": 1.510032362459547,
+      "grad_norm": 0.5217538475990295,
+      "learning_rate": 0.00018332471979888535,
+      "loss": 0.8395941257476807,
+      "step": 3500
+    },
+    {
+      "epoch": 1.510032362459547,
+      "eval_loss": 0.7970634698867798,
+      "eval_runtime": 655.3078,
+      "eval_samples_per_second": 3.144,
+      "eval_steps_per_second": 3.144,
+      "step": 3500
+    },
+    {
+      "epoch": 1.5108953613807983,
+      "grad_norm": 0.4357616901397705,
+      "learning_rate": 0.00018329755870118033,
+      "loss": 0.7151007056236267,
+      "step": 3502
+    },
+    {
+      "epoch": 1.5117583603020495,
+      "grad_norm": 0.4224613606929779,
+      "learning_rate": 0.00018327037751664454,
+      "loss": 0.6745702028274536,
+      "step": 3504
+    },
+    {
+      "epoch": 1.512621359223301,
+      "grad_norm": 0.4674745500087738,
+      "learning_rate": 0.0001832431762518326,
+      "loss": 0.7870205640792847,
+      "step": 3506
+    },
+    {
+      "epoch": 1.5134843581445523,
+      "grad_norm": 0.44136863946914673,
+      "learning_rate": 0.00018321595491330397,
+      "loss": 0.777145504951477,
+      "step": 3508
+    },
+    {
+      "epoch": 1.5143473570658037,
+      "grad_norm": 0.5091800093650818,
+      "learning_rate": 0.00018318871350762295,
+      "loss": 0.7991534471511841,
+      "step": 3510
+    },
+    {
+      "epoch": 1.5152103559870551,
+      "grad_norm": 0.42728134989738464,
+      "learning_rate": 0.00018316145204135865,
+      "loss": 0.7678582072257996,
+      "step": 3512
+    },
+    {
+      "epoch": 1.5160733549083063,
+      "grad_norm": 0.47067728638648987,
+      "learning_rate": 0.00018313417052108513,
+      "loss": 0.7971519231796265,
+      "step": 3514
+    },
+    {
+      "epoch": 1.5169363538295577,
+      "grad_norm": 0.4250936210155487,
+      "learning_rate": 0.00018310686895338117,
+      "loss": 0.7281476259231567,
+      "step": 3516
+    },
+    {
+      "epoch": 1.5177993527508091,
+      "grad_norm": 0.4261043667793274,
+      "learning_rate": 0.00018307954734483038,
+      "loss": 0.7346498966217041,
+      "step": 3518
+    },
+    {
+      "epoch": 1.5186623516720603,
+      "grad_norm": 0.4935494363307953,
+      "learning_rate": 0.0001830522057020213,
+      "loss": 0.765254557132721,
+      "step": 3520
+    },
+    {
+      "epoch": 1.5195253505933117,
+      "grad_norm": 0.4546700119972229,
+      "learning_rate": 0.00018302484403154718,
+      "loss": 0.7073609828948975,
+      "step": 3522
+    },
+    {
+      "epoch": 1.5203883495145631,
+      "grad_norm": 0.4881356656551361,
+      "learning_rate": 0.0001829974623400062,
+      "loss": 0.681342363357544,
+      "step": 3524
+    },
+    {
+      "epoch": 1.5212513484358143,
+      "grad_norm": 0.4397423565387726,
+      "learning_rate": 0.00018297006063400134,
+      "loss": 0.6735935211181641,
+      "step": 3526
+    },
+    {
+      "epoch": 1.522114347357066,
+      "grad_norm": 0.4426570236682892,
+      "learning_rate": 0.00018294263892014038,
+      "loss": 0.721441924571991,
+      "step": 3528
+    },
+    {
+      "epoch": 1.5229773462783172,
+      "grad_norm": 0.5235413908958435,
+      "learning_rate": 0.00018291519720503599,
+      "loss": 0.8269463777542114,
+      "step": 3530
+    },
+    {
+      "epoch": 1.5238403451995683,
+      "grad_norm": 0.4708006978034973,
+      "learning_rate": 0.00018288773549530557,
+      "loss": 0.7080397605895996,
+      "step": 3532
+    },
+    {
+      "epoch": 1.52470334412082,
+      "grad_norm": 0.47188836336135864,
+      "learning_rate": 0.00018286025379757136,
+      "loss": 0.7505635023117065,
+      "step": 3534
+    },
+    {
+      "epoch": 1.5255663430420712,
+      "grad_norm": 0.4706624746322632,
+      "learning_rate": 0.00018283275211846052,
+      "loss": 0.743853747844696,
+      "step": 3536
+    },
+    {
+      "epoch": 1.5264293419633226,
+      "grad_norm": 0.42075470089912415,
+      "learning_rate": 0.0001828052304646049,
+      "loss": 0.7527500987052917,
+      "step": 3538
+    },
+    {
+      "epoch": 1.527292340884574,
+      "grad_norm": 0.47468745708465576,
+      "learning_rate": 0.00018277768884264123,
+      "loss": 0.7295951247215271,
+      "step": 3540
+    },
+    {
+      "epoch": 1.5281553398058252,
+      "grad_norm": 0.49890658259391785,
+      "learning_rate": 0.00018275012725921106,
+      "loss": 0.7707282900810242,
+      "step": 3542
+    },
+    {
+      "epoch": 1.5290183387270766,
+      "grad_norm": 0.44301101565361023,
+      "learning_rate": 0.00018272254572096076,
+      "loss": 0.7032204270362854,
+      "step": 3544
+    },
+    {
+      "epoch": 1.529881337648328,
+      "grad_norm": 0.4144493043422699,
+      "learning_rate": 0.00018269494423454148,
+      "loss": 0.6652095317840576,
+      "step": 3546
+    },
+    {
+      "epoch": 1.5307443365695792,
+      "grad_norm": 0.41546186804771423,
+      "learning_rate": 0.00018266732280660915,
+      "loss": 0.7446690797805786,
+      "step": 3548
+    },
+    {
+      "epoch": 1.5316073354908306,
+      "grad_norm": 0.46266189217567444,
+      "learning_rate": 0.00018263968144382464,
+      "loss": 0.800329327583313,
+      "step": 3550
+    },
+    {
+      "epoch": 1.532470334412082,
+      "grad_norm": 0.46991246938705444,
+      "learning_rate": 0.00018261202015285347,
+      "loss": 0.8398324251174927,
+      "step": 3552
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.45873361825942993,
+      "learning_rate": 0.00018258433894036605,
+      "loss": 0.7080168724060059,
+      "step": 3554
+    },
+    {
+      "epoch": 1.5341963322545846,
+      "grad_norm": 0.4650769531726837,
+      "learning_rate": 0.00018255663781303758,
+      "loss": 0.7790565490722656,
+      "step": 3556
+    },
+    {
+      "epoch": 1.535059331175836,
+      "grad_norm": 0.4353472590446472,
+      "learning_rate": 0.00018252891677754808,
+      "loss": 0.7548949122428894,
+      "step": 3558
+    },
+    {
+      "epoch": 1.5359223300970872,
+      "grad_norm": 0.4259464740753174,
+      "learning_rate": 0.00018250117584058236,
+      "loss": 0.7493187189102173,
+      "step": 3560
+    },
+    {
+      "epoch": 1.5367853290183389,
+      "grad_norm": 0.4781721234321594,
+      "learning_rate": 0.00018247341500883,
+      "loss": 0.8031244277954102,
+      "step": 3562
+    },
+    {
+      "epoch": 1.53764832793959,
+      "grad_norm": 0.4471439719200134,
+      "learning_rate": 0.00018244563428898537,
+      "loss": 0.74393630027771,
+      "step": 3564
+    },
+    {
+      "epoch": 1.5385113268608415,
+      "grad_norm": 0.4181448519229889,
+      "learning_rate": 0.00018241783368774773,
+      "loss": 0.8052780628204346,
+      "step": 3566
+    },
+    {
+      "epoch": 1.5393743257820929,
+      "grad_norm": 0.5136722326278687,
+      "learning_rate": 0.000182390013211821,
+      "loss": 0.825944721698761,
+      "step": 3568
+    },
+    {
+      "epoch": 1.540237324703344,
+      "grad_norm": 0.43782681226730347,
+      "learning_rate": 0.00018236217286791403,
+      "loss": 0.70372474193573,
+      "step": 3570
+    },
+    {
+      "epoch": 1.5411003236245955,
+      "grad_norm": 0.44272729754447937,
+      "learning_rate": 0.00018233431266274038,
+      "loss": 0.7298035621643066,
+      "step": 3572
+    },
+    {
+      "epoch": 1.541963322545847,
+      "grad_norm": 0.44322386384010315,
+      "learning_rate": 0.00018230643260301838,
+      "loss": 0.7507740259170532,
+      "step": 3574
+    },
+    {
+      "epoch": 1.542826321467098,
+      "grad_norm": 0.48743686079978943,
+      "learning_rate": 0.00018227853269547117,
+      "loss": 0.7720011472702026,
+      "step": 3576
+    },
+    {
+      "epoch": 1.5436893203883495,
+      "grad_norm": 0.4608381390571594,
+      "learning_rate": 0.00018225061294682674,
+      "loss": 0.8001248240470886,
+      "step": 3578
+    },
+    {
+      "epoch": 1.544552319309601,
+      "grad_norm": 0.45625007152557373,
+      "learning_rate": 0.00018222267336381778,
+      "loss": 0.7971346378326416,
+      "step": 3580
+    },
+    {
+      "epoch": 1.545415318230852,
+      "grad_norm": 0.4687005579471588,
+      "learning_rate": 0.00018219471395318178,
+      "loss": 0.7254680395126343,
+      "step": 3582
+    },
+    {
+      "epoch": 1.5462783171521035,
+      "grad_norm": 0.48081183433532715,
+      "learning_rate": 0.00018216673472166108,
+      "loss": 0.7372352480888367,
+      "step": 3584
+    },
+    {
+      "epoch": 1.547141316073355,
+      "grad_norm": 0.42272305488586426,
+      "learning_rate": 0.0001821387356760027,
+      "loss": 0.6276986598968506,
+      "step": 3586
+    },
+    {
+      "epoch": 1.5480043149946061,
+      "grad_norm": 0.42225342988967896,
+      "learning_rate": 0.0001821107168229585,
+      "loss": 0.7299351692199707,
+      "step": 3588
+    },
+    {
+      "epoch": 1.5488673139158577,
+      "grad_norm": 0.4649020731449127,
+      "learning_rate": 0.00018208267816928507,
+      "loss": 0.6684783101081848,
+      "step": 3590
+    },
+    {
+      "epoch": 1.549730312837109,
+      "grad_norm": 0.3961552679538727,
+      "learning_rate": 0.00018205461972174388,
+      "loss": 0.6579244136810303,
+      "step": 3592
+    },
+    {
+      "epoch": 1.5505933117583603,
+      "grad_norm": 0.500170111656189,
+      "learning_rate": 0.00018202654148710102,
+      "loss": 0.6955749988555908,
+      "step": 3594
+    },
+    {
+      "epoch": 1.5514563106796118,
+      "grad_norm": 0.5200181603431702,
+      "learning_rate": 0.00018199844347212746,
+      "loss": 0.6725539565086365,
+      "step": 3596
+    },
+    {
+      "epoch": 1.552319309600863,
+      "grad_norm": 0.4894106984138489,
+      "learning_rate": 0.0001819703256835989,
+      "loss": 0.7726914882659912,
+      "step": 3598
+    },
+    {
+      "epoch": 1.5531823085221144,
+      "grad_norm": 0.487623006105423,
+      "learning_rate": 0.00018194218812829583,
+      "loss": 0.8290923833847046,
+      "step": 3600
+    },
+    {
+      "epoch": 1.5531823085221144,
+      "eval_loss": 0.7935511469841003,
+      "eval_runtime": 666.5283,
+      "eval_samples_per_second": 3.091,
+      "eval_steps_per_second": 3.091,
+      "step": 3600
+    },
+    {
+      "epoch": 1.5540453074433658,
+      "grad_norm": 0.4056689441204071,
+      "learning_rate": 0.0001819140308130035,
+      "loss": 0.6819650530815125,
+      "step": 3602
+    },
+    {
+      "epoch": 1.554908306364617,
+      "grad_norm": 0.4337533712387085,
+      "learning_rate": 0.0001818858537445119,
+      "loss": 0.6709993481636047,
+      "step": 3604
+    },
+    {
+      "epoch": 1.5557713052858684,
+      "grad_norm": 0.4365732967853546,
+      "learning_rate": 0.0001818576569296158,
+      "loss": 0.6784732937812805,
+      "step": 3606
+    },
+    {
+      "epoch": 1.5566343042071198,
+      "grad_norm": 0.4632627069950104,
+      "learning_rate": 0.00018182944037511476,
+      "loss": 0.7771052718162537,
+      "step": 3608
+    },
+    {
+      "epoch": 1.557497303128371,
+      "grad_norm": 0.45411452651023865,
+      "learning_rate": 0.00018180120408781305,
+      "loss": 0.8117473125457764,
+      "step": 3610
+    },
+    {
+      "epoch": 1.5583603020496224,
+      "grad_norm": 0.4931472837924957,
+      "learning_rate": 0.00018177294807451974,
+      "loss": 0.7268829941749573,
+      "step": 3612
+    },
+    {
+      "epoch": 1.5592233009708738,
+      "grad_norm": 0.4711272418498993,
+      "learning_rate": 0.00018174467234204867,
+      "loss": 0.7986008524894714,
+      "step": 3614
+    },
+    {
+      "epoch": 1.560086299892125,
+      "grad_norm": 0.47048646211624146,
+      "learning_rate": 0.00018171637689721833,
+      "loss": 0.7606064081192017,
+      "step": 3616
+    },
+    {
+      "epoch": 1.5609492988133766,
+      "grad_norm": 0.4612944424152374,
+      "learning_rate": 0.00018168806174685212,
+      "loss": 0.7444906234741211,
+      "step": 3618
+    },
+    {
+      "epoch": 1.5618122977346278,
+      "grad_norm": 0.4275529980659485,
+      "learning_rate": 0.00018165972689777803,
+      "loss": 0.7393948435783386,
+      "step": 3620
+    },
+    {
+      "epoch": 1.5626752966558792,
+      "grad_norm": 0.5759958028793335,
+      "learning_rate": 0.00018163137235682893,
+      "loss": 0.7669101357460022,
+      "step": 3622
+    },
+    {
+      "epoch": 1.5635382955771306,
+      "grad_norm": 0.41767528653144836,
+      "learning_rate": 0.00018160299813084238,
+      "loss": 0.7250568270683289,
+      "step": 3624
+    },
+    {
+      "epoch": 1.5644012944983818,
+      "grad_norm": 0.40168496966362,
+      "learning_rate": 0.00018157460422666075,
+      "loss": 0.7880772352218628,
+      "step": 3626
+    },
+    {
+      "epoch": 1.5652642934196332,
+      "grad_norm": 0.4270237386226654,
+      "learning_rate": 0.00018154619065113102,
+      "loss": 0.7754803895950317,
+      "step": 3628
+    },
+    {
+      "epoch": 1.5661272923408847,
+      "grad_norm": 0.46184200048446655,
+      "learning_rate": 0.000181517757411105,
+      "loss": 0.701246976852417,
+      "step": 3630
+    },
+    {
+      "epoch": 1.5669902912621358,
+      "grad_norm": 0.39403679966926575,
+      "learning_rate": 0.0001814893045134393,
+      "loss": 0.7201641201972961,
+      "step": 3632
+    },
+    {
+      "epoch": 1.5678532901833873,
+      "grad_norm": 0.4320994019508362,
+      "learning_rate": 0.00018146083196499512,
+      "loss": 0.6649395823478699,
+      "step": 3634
+    },
+    {
+      "epoch": 1.5687162891046387,
+      "grad_norm": 0.46719890832901,
+      "learning_rate": 0.0001814323397726386,
+      "loss": 0.7596995234489441,
+      "step": 3636
+    },
+    {
+      "epoch": 1.5695792880258899,
+      "grad_norm": 0.49942320585250854,
+      "learning_rate": 0.0001814038279432404,
+      "loss": 0.7265456914901733,
+      "step": 3638
+    },
+    {
+      "epoch": 1.5704422869471413,
+      "grad_norm": 0.41604548692703247,
+      "learning_rate": 0.00018137529648367607,
+      "loss": 0.6903387308120728,
+      "step": 3640
+    },
+    {
+      "epoch": 1.5713052858683927,
+      "grad_norm": 0.4712325930595398,
+      "learning_rate": 0.00018134674540082587,
+      "loss": 0.7590459585189819,
+      "step": 3642
+    },
+    {
+      "epoch": 1.5721682847896439,
+      "grad_norm": 0.5137260556221008,
+      "learning_rate": 0.00018131817470157471,
+      "loss": 0.7304242253303528,
+      "step": 3644
+    },
+    {
+      "epoch": 1.5730312837108955,
+      "grad_norm": 0.459363728761673,
+      "learning_rate": 0.0001812895843928123,
+      "loss": 0.6472513675689697,
+      "step": 3646
+    },
+    {
+      "epoch": 1.5738942826321467,
+      "grad_norm": 0.518924355506897,
+      "learning_rate": 0.00018126097448143306,
+      "loss": 0.7312461733818054,
+      "step": 3648
+    },
+    {
+      "epoch": 1.574757281553398,
+      "grad_norm": 0.491247296333313,
+      "learning_rate": 0.00018123234497433615,
+      "loss": 0.7790979146957397,
+      "step": 3650
+    },
+    {
+      "epoch": 1.5756202804746495,
+      "grad_norm": 0.4290984570980072,
+      "learning_rate": 0.00018120369587842547,
+      "loss": 0.7140002846717834,
+      "step": 3652
+    },
+    {
+      "epoch": 1.5764832793959007,
+      "grad_norm": 0.4229796528816223,
+      "learning_rate": 0.0001811750272006096,
+      "loss": 0.7497822046279907,
+      "step": 3654
+    },
+    {
+      "epoch": 1.5773462783171521,
+      "grad_norm": 0.444733589887619,
+      "learning_rate": 0.00018114633894780182,
+      "loss": 0.769322395324707,
+      "step": 3656
+    },
+    {
+      "epoch": 1.5782092772384035,
+      "grad_norm": 0.4415557384490967,
+      "learning_rate": 0.00018111763112692024,
+      "loss": 0.7770668268203735,
+      "step": 3658
+    },
+    {
+      "epoch": 1.5790722761596547,
+      "grad_norm": 0.42115989327430725,
+      "learning_rate": 0.00018108890374488759,
+      "loss": 0.7666043639183044,
+      "step": 3660
+    },
+    {
+      "epoch": 1.5799352750809061,
+      "grad_norm": 0.4013395607471466,
+      "learning_rate": 0.00018106015680863132,
+      "loss": 0.7253396511077881,
+      "step": 3662
+    },
+    {
+      "epoch": 1.5807982740021576,
+      "grad_norm": 0.37566566467285156,
+      "learning_rate": 0.0001810313903250837,
+      "loss": 0.6983510255813599,
+      "step": 3664
+    },
+    {
+      "epoch": 1.5816612729234087,
+      "grad_norm": 0.4788576364517212,
+      "learning_rate": 0.00018100260430118162,
+      "loss": 0.7309481501579285,
+      "step": 3666
+    },
+    {
+      "epoch": 1.5825242718446602,
+      "grad_norm": 0.43960556387901306,
+      "learning_rate": 0.0001809737987438666,
+      "loss": 0.7518695592880249,
+      "step": 3668
+    },
+    {
+      "epoch": 1.5833872707659116,
+      "grad_norm": 0.4018779993057251,
+      "learning_rate": 0.0001809449736600851,
+      "loss": 0.6877766251564026,
+      "step": 3670
+    },
+    {
+      "epoch": 1.5842502696871628,
+      "grad_norm": 0.43951910734176636,
+      "learning_rate": 0.00018091612905678808,
+      "loss": 0.7189319729804993,
+      "step": 3672
+    },
+    {
+      "epoch": 1.5851132686084144,
+      "grad_norm": 0.42398321628570557,
+      "learning_rate": 0.0001808872649409313,
+      "loss": 0.6966261863708496,
+      "step": 3674
+    },
+    {
+      "epoch": 1.5859762675296656,
+      "grad_norm": 0.4551796019077301,
+      "learning_rate": 0.00018085838131947526,
+      "loss": 0.6944435834884644,
+      "step": 3676
+    },
+    {
+      "epoch": 1.5868392664509168,
+      "grad_norm": 0.487661212682724,
+      "learning_rate": 0.00018082947819938504,
+      "loss": 0.7711076736450195,
+      "step": 3678
+    },
+    {
+      "epoch": 1.5877022653721684,
+      "grad_norm": 0.45423412322998047,
+      "learning_rate": 0.00018080055558763057,
+      "loss": 0.7488799691200256,
+      "step": 3680
+    },
+    {
+      "epoch": 1.5885652642934196,
+      "grad_norm": 0.40377750992774963,
+      "learning_rate": 0.00018077161349118633,
+      "loss": 0.6809216737747192,
+      "step": 3682
+    },
+    {
+      "epoch": 1.589428263214671,
+      "grad_norm": 0.5005835294723511,
+      "learning_rate": 0.00018074265191703163,
+      "loss": 0.7147122621536255,
+      "step": 3684
+    },
+    {
+      "epoch": 1.5902912621359224,
+      "grad_norm": 0.5540063381195068,
+      "learning_rate": 0.00018071367087215044,
+      "loss": 0.7934401035308838,
+      "step": 3686
+    },
+    {
+      "epoch": 1.5911542610571736,
+      "grad_norm": 0.41316506266593933,
+      "learning_rate": 0.00018068467036353133,
+      "loss": 0.6978628039360046,
+      "step": 3688
+    },
+    {
+      "epoch": 1.592017259978425,
+      "grad_norm": 0.5138319134712219,
+      "learning_rate": 0.00018065565039816772,
+      "loss": 0.8193445205688477,
+      "step": 3690
+    },
+    {
+      "epoch": 1.5928802588996764,
+      "grad_norm": 0.4598786234855652,
+      "learning_rate": 0.00018062661098305763,
+      "loss": 0.7386526465415955,
+      "step": 3692
+    },
+    {
+      "epoch": 1.5937432578209276,
+      "grad_norm": 0.446444034576416,
+      "learning_rate": 0.00018059755212520372,
+      "loss": 0.7734212875366211,
+      "step": 3694
+    },
+    {
+      "epoch": 1.594606256742179,
+      "grad_norm": 0.41883963346481323,
+      "learning_rate": 0.0001805684738316135,
+      "loss": 0.718011200428009,
+      "step": 3696
+    },
+    {
+      "epoch": 1.5954692556634305,
+      "grad_norm": 0.4579313397407532,
+      "learning_rate": 0.00018053937610929897,
+      "loss": 0.7522324919700623,
+      "step": 3698
+    },
+    {
+      "epoch": 1.5963322545846816,
+      "grad_norm": 0.43380051851272583,
+      "learning_rate": 0.000180510258965277,
+      "loss": 0.6498246788978577,
+      "step": 3700
+    },
+    {
+      "epoch": 1.5963322545846816,
+      "eval_loss": 0.7914894223213196,
+      "eval_runtime": 668.9887,
+      "eval_samples_per_second": 3.079,
+      "eval_steps_per_second": 3.079,
+      "step": 3700
+    },
+    {
+      "epoch": 1.5971952535059333,
+      "grad_norm": 0.39354878664016724,
+      "learning_rate": 0.000180481122406569,
+      "loss": 0.7064145803451538,
+      "step": 3702
+    },
+    {
+      "epoch": 1.5980582524271845,
+      "grad_norm": 0.3876212239265442,
+      "learning_rate": 0.00018045196644020118,
+      "loss": 0.6859980821609497,
+      "step": 3704
+    },
+    {
+      "epoch": 1.5989212513484357,
+      "grad_norm": 0.48381999135017395,
+      "learning_rate": 0.00018042279107320427,
+      "loss": 0.8459084630012512,
+      "step": 3706
+    },
+    {
+      "epoch": 1.5997842502696873,
+      "grad_norm": 0.4688359797000885,
+      "learning_rate": 0.0001803935963126139,
+      "loss": 0.6574559211730957,
+      "step": 3708
+    },
+    {
+      "epoch": 1.6006472491909385,
+      "grad_norm": 0.537028968334198,
+      "learning_rate": 0.0001803643821654702,
+      "loss": 0.8127812147140503,
+      "step": 3710
+    },
+    {
+      "epoch": 1.60151024811219,
+      "grad_norm": 0.3990524113178253,
+      "learning_rate": 0.00018033514863881797,
+      "loss": 0.7411133050918579,
+      "step": 3712
+    },
+    {
+      "epoch": 1.6023732470334413,
+      "grad_norm": 0.38037553429603577,
+      "learning_rate": 0.00018030589573970684,
+      "loss": 0.7164896130561829,
+      "step": 3714
+    },
+    {
+      "epoch": 1.6032362459546925,
+      "grad_norm": 0.45911267399787903,
+      "learning_rate": 0.00018027662347519096,
+      "loss": 0.7164638638496399,
+      "step": 3716
+    },
+    {
+      "epoch": 1.604099244875944,
+      "grad_norm": 0.37456580996513367,
+      "learning_rate": 0.00018024733185232922,
+      "loss": 0.6928568482398987,
+      "step": 3718
+    },
+    {
+      "epoch": 1.6049622437971953,
+      "grad_norm": 0.4336542785167694,
+      "learning_rate": 0.00018021802087818517,
+      "loss": 0.6571218371391296,
+      "step": 3720
+    },
+    {
+      "epoch": 1.6058252427184465,
+      "grad_norm": 0.41265374422073364,
+      "learning_rate": 0.00018018869055982698,
+      "loss": 0.6813036203384399,
+      "step": 3722
+    },
+    {
+      "epoch": 1.606688241639698,
+      "grad_norm": 0.4339812695980072,
+      "learning_rate": 0.00018015934090432757,
+      "loss": 0.753751277923584,
+      "step": 3724
+    },
+    {
+      "epoch": 1.6075512405609493,
+      "grad_norm": 0.41123342514038086,
+      "learning_rate": 0.00018012997191876447,
+      "loss": 0.676802396774292,
+      "step": 3726
+    },
+    {
+      "epoch": 1.6084142394822005,
+      "grad_norm": 0.4282870292663574,
+      "learning_rate": 0.00018010058361021987,
+      "loss": 0.7151802778244019,
+      "step": 3728
+    },
+    {
+      "epoch": 1.6092772384034522,
+      "grad_norm": 0.44637587666511536,
+      "learning_rate": 0.00018007117598578063,
+      "loss": 0.815374493598938,
+      "step": 3730
+    },
+    {
+      "epoch": 1.6101402373247033,
+      "grad_norm": 0.41761815547943115,
+      "learning_rate": 0.00018004174905253826,
+      "loss": 0.7119425535202026,
+      "step": 3732
+    },
+    {
+      "epoch": 1.6110032362459545,
+      "grad_norm": 0.4224661886692047,
+      "learning_rate": 0.0001800123028175889,
+      "loss": 0.7779671549797058,
+      "step": 3734
+    },
+    {
+      "epoch": 1.6118662351672062,
+      "grad_norm": 0.476329505443573,
+      "learning_rate": 0.00017998283728803345,
+      "loss": 0.5716424584388733,
+      "step": 3736
+    },
+    {
+      "epoch": 1.6127292340884574,
+      "grad_norm": 0.4721233546733856,
+      "learning_rate": 0.00017995335247097738,
+      "loss": 0.7326773405075073,
+      "step": 3738
+    },
+    {
+      "epoch": 1.6135922330097088,
+      "grad_norm": 0.38915106654167175,
+      "learning_rate": 0.00017992384837353073,
+      "loss": 0.7872865200042725,
+      "step": 3740
+    },
+    {
+      "epoch": 1.6144552319309602,
+      "grad_norm": 0.4306866526603699,
+      "learning_rate": 0.00017989432500280838,
+      "loss": 0.8006538152694702,
+      "step": 3742
+    },
+    {
+      "epoch": 1.6153182308522114,
+      "grad_norm": 0.3983909487724304,
+      "learning_rate": 0.00017986478236592973,
+      "loss": 0.7693750858306885,
+      "step": 3744
+    },
+    {
+      "epoch": 1.6161812297734628,
+      "grad_norm": 0.4322768747806549,
+      "learning_rate": 0.00017983522047001883,
+      "loss": 0.7483386993408203,
+      "step": 3746
+    },
+    {
+      "epoch": 1.6170442286947142,
+      "grad_norm": 0.5202714204788208,
+      "learning_rate": 0.00017980563932220442,
+      "loss": 0.7642959356307983,
+      "step": 3748
+    },
+    {
+      "epoch": 1.6179072276159654,
+      "grad_norm": 0.4318627119064331,
+      "learning_rate": 0.00017977603892961982,
+      "loss": 0.741479754447937,
+      "step": 3750
+    },
+    {
+      "epoch": 1.6187702265372168,
+      "grad_norm": 0.4942893981933594,
+      "learning_rate": 0.0001797464192994031,
+      "loss": 0.7392295598983765,
+      "step": 3752
+    },
+    {
+      "epoch": 1.6196332254584682,
+      "grad_norm": 0.46874746680259705,
+      "learning_rate": 0.00017971678043869686,
+      "loss": 0.7523542046546936,
+      "step": 3754
+    },
+    {
+      "epoch": 1.6204962243797194,
+      "grad_norm": 0.47045233845710754,
+      "learning_rate": 0.00017968712235464837,
+      "loss": 0.6766729950904846,
+      "step": 3756
+    },
+    {
+      "epoch": 1.6213592233009708,
+      "grad_norm": 0.43984928727149963,
+      "learning_rate": 0.00017965744505440956,
+      "loss": 0.7277816534042358,
+      "step": 3758
+    },
+    {
+      "epoch": 1.6222222222222222,
+      "grad_norm": 0.41389113664627075,
+      "learning_rate": 0.00017962774854513697,
+      "loss": 0.7649447917938232,
+      "step": 3760
+    },
+    {
+      "epoch": 1.6230852211434734,
+      "grad_norm": 0.461200475692749,
+      "learning_rate": 0.00017959803283399182,
+      "loss": 0.7033944129943848,
+      "step": 3762
+    },
+    {
+      "epoch": 1.623948220064725,
+      "grad_norm": 0.4776712954044342,
+      "learning_rate": 0.00017956829792813985,
+      "loss": 0.8075087070465088,
+      "step": 3764
+    },
+    {
+      "epoch": 1.6248112189859762,
+      "grad_norm": 0.5021974444389343,
+      "learning_rate": 0.00017953854383475154,
+      "loss": 0.7541269063949585,
+      "step": 3766
+    },
+    {
+      "epoch": 1.6256742179072277,
+      "grad_norm": 0.46222755312919617,
+      "learning_rate": 0.0001795087705610019,
+      "loss": 0.703751266002655,
+      "step": 3768
+    },
+    {
+      "epoch": 1.626537216828479,
+      "grad_norm": 0.34487178921699524,
+      "learning_rate": 0.0001794789781140707,
+      "loss": 0.6657921671867371,
+      "step": 3770
+    },
+    {
+      "epoch": 1.6274002157497303,
+      "grad_norm": 0.38064146041870117,
+      "learning_rate": 0.00017944916650114223,
+      "loss": 0.7999282479286194,
+      "step": 3772
+    },
+    {
+      "epoch": 1.6282632146709817,
+      "grad_norm": 0.48815488815307617,
+      "learning_rate": 0.00017941933572940543,
+      "loss": 0.7157361507415771,
+      "step": 3774
+    },
+    {
+      "epoch": 1.629126213592233,
+      "grad_norm": 0.42136189341545105,
+      "learning_rate": 0.00017938948580605382,
+      "loss": 0.6897950768470764,
+      "step": 3776
+    },
+    {
+      "epoch": 1.6299892125134843,
+      "grad_norm": 0.388630747795105,
+      "learning_rate": 0.0001793596167382856,
+      "loss": 0.6738383173942566,
+      "step": 3778
+    },
+    {
+      "epoch": 1.6308522114347357,
+      "grad_norm": 0.4050692617893219,
+      "learning_rate": 0.00017932972853330355,
+      "loss": 0.6531928777694702,
+      "step": 3780
+    },
+    {
+      "epoch": 1.631715210355987,
+      "grad_norm": 0.542385995388031,
+      "learning_rate": 0.0001792998211983151,
+      "loss": 0.8739076256752014,
+      "step": 3782
+    },
+    {
+      "epoch": 1.6325782092772383,
+      "grad_norm": 0.4323846995830536,
+      "learning_rate": 0.00017926989474053223,
+      "loss": 0.7771362662315369,
+      "step": 3784
+    },
+    {
+      "epoch": 1.6334412081984897,
+      "grad_norm": 0.47487086057662964,
+      "learning_rate": 0.00017923994916717163,
+      "loss": 0.7664928436279297,
+      "step": 3786
+    },
+    {
+      "epoch": 1.6343042071197411,
+      "grad_norm": 0.3801349401473999,
+      "learning_rate": 0.0001792099844854545,
+      "loss": 0.6508067846298218,
+      "step": 3788
+    },
+    {
+      "epoch": 1.6351672060409923,
+      "grad_norm": 0.38995426893234253,
+      "learning_rate": 0.00017918000070260668,
+      "loss": 0.6948919892311096,
+      "step": 3790
+    },
+    {
+      "epoch": 1.636030204962244,
+      "grad_norm": 0.4038735628128052,
+      "learning_rate": 0.00017914999782585862,
+      "loss": 0.7225003242492676,
+      "step": 3792
+    },
+    {
+      "epoch": 1.6368932038834951,
+      "grad_norm": 0.45372122526168823,
+      "learning_rate": 0.00017911997586244542,
+      "loss": 0.7177075147628784,
+      "step": 3794
+    },
+    {
+      "epoch": 1.6377562028047465,
+      "grad_norm": 0.5123688578605652,
+      "learning_rate": 0.00017908993481960669,
+      "loss": 0.8427615165710449,
+      "step": 3796
+    },
+    {
+      "epoch": 1.638619201725998,
+      "grad_norm": 0.505483865737915,
+      "learning_rate": 0.00017905987470458675,
+      "loss": 0.7884581089019775,
+      "step": 3798
+    },
+    {
+      "epoch": 1.6394822006472491,
+      "grad_norm": 0.5441710948944092,
+      "learning_rate": 0.0001790297955246344,
+      "loss": 0.8026853799819946,
+      "step": 3800
+    },
+    {
+      "epoch": 1.6394822006472491,
+      "eval_loss": 0.7887746691703796,
+      "eval_runtime": 655.8201,
+      "eval_samples_per_second": 3.141,
+      "eval_steps_per_second": 3.141,
+      "step": 3800
+    },
+    {
+      "epoch": 1.6403451995685006,
+      "grad_norm": 0.3747040033340454,
+      "learning_rate": 0.00017899969728700315,
+      "loss": 0.6836490035057068,
+      "step": 3802
+    },
+    {
+      "epoch": 1.641208198489752,
+      "grad_norm": 0.4163338243961334,
+      "learning_rate": 0.000178969579998951,
+      "loss": 0.748136579990387,
+      "step": 3804
+    },
+    {
+      "epoch": 1.6420711974110032,
+      "grad_norm": 0.4737973213195801,
+      "learning_rate": 0.00017893944366774065,
+      "loss": 0.7534400224685669,
+      "step": 3806
+    },
+    {
+      "epoch": 1.6429341963322546,
+      "grad_norm": 0.4687727093696594,
+      "learning_rate": 0.00017890928830063932,
+      "loss": 0.7779349088668823,
+      "step": 3808
+    },
+    {
+      "epoch": 1.643797195253506,
+      "grad_norm": 0.43674737215042114,
+      "learning_rate": 0.00017887911390491884,
+      "loss": 0.6942368149757385,
+      "step": 3810
+    },
+    {
+      "epoch": 1.6446601941747572,
+      "grad_norm": 0.43343719840049744,
+      "learning_rate": 0.00017884892048785565,
+      "loss": 0.7554087042808533,
+      "step": 3812
+    },
+    {
+      "epoch": 1.6455231930960086,
+      "grad_norm": 0.4790881276130676,
+      "learning_rate": 0.0001788187080567307,
+      "loss": 0.7387835383415222,
+      "step": 3814
+    },
+    {
+      "epoch": 1.64638619201726,
+      "grad_norm": 0.4524185061454773,
+      "learning_rate": 0.00017878847661882965,
+      "loss": 0.7229949235916138,
+      "step": 3816
+    },
+    {
+      "epoch": 1.6472491909385112,
+      "grad_norm": 0.4563996195793152,
+      "learning_rate": 0.00017875822618144263,
+      "loss": 0.6808197498321533,
+      "step": 3818
+    },
+    {
+      "epoch": 1.6481121898597628,
+      "grad_norm": 0.452282190322876,
+      "learning_rate": 0.00017872795675186442,
+      "loss": 0.6958807110786438,
+      "step": 3820
+    },
+    {
+      "epoch": 1.648975188781014,
+      "grad_norm": 0.5677687525749207,
+      "learning_rate": 0.00017869766833739434,
+      "loss": 0.7347233295440674,
+      "step": 3822
+    },
+    {
+      "epoch": 1.6498381877022654,
+      "grad_norm": 0.5028979778289795,
+      "learning_rate": 0.00017866736094533628,
+      "loss": 0.7279980182647705,
+      "step": 3824
+    },
+    {
+      "epoch": 1.6507011866235168,
+      "grad_norm": 0.4216834604740143,
+      "learning_rate": 0.0001786370345829988,
+      "loss": 0.7350833415985107,
+      "step": 3826
+    },
+    {
+      "epoch": 1.651564185544768,
+      "grad_norm": 0.4700584411621094,
+      "learning_rate": 0.00017860668925769494,
+      "loss": 0.8165807127952576,
+      "step": 3828
+    },
+    {
+      "epoch": 1.6524271844660194,
+      "grad_norm": 0.41511070728302,
+      "learning_rate": 0.0001785763249767423,
+      "loss": 0.7146443128585815,
+      "step": 3830
+    },
+    {
+      "epoch": 1.6532901833872709,
+      "grad_norm": 0.5240047574043274,
+      "learning_rate": 0.00017854594174746314,
+      "loss": 0.7849907875061035,
+      "step": 3832
+    },
+    {
+      "epoch": 1.654153182308522,
+      "grad_norm": 0.4594099223613739,
+      "learning_rate": 0.0001785155395771842,
+      "loss": 0.6815205812454224,
+      "step": 3834
+    },
+    {
+      "epoch": 1.6550161812297735,
+      "grad_norm": 0.41762664914131165,
+      "learning_rate": 0.00017848511847323682,
+      "loss": 0.7110051512718201,
+      "step": 3836
+    },
+    {
+      "epoch": 1.6558791801510249,
+      "grad_norm": 0.4596463143825531,
+      "learning_rate": 0.00017845467844295696,
+      "loss": 0.7868525981903076,
+      "step": 3838
+    },
+    {
+      "epoch": 1.656742179072276,
+      "grad_norm": 0.3694678246974945,
+      "learning_rate": 0.00017842421949368505,
+      "loss": 0.7308529615402222,
+      "step": 3840
+    },
+    {
+      "epoch": 1.6576051779935275,
+      "grad_norm": 0.4251806139945984,
+      "learning_rate": 0.00017839374163276616,
+      "loss": 0.6846014857292175,
+      "step": 3842
+    },
+    {
+      "epoch": 1.6584681769147789,
+      "grad_norm": 0.4015883207321167,
+      "learning_rate": 0.00017836324486754986,
+      "loss": 0.7137831449508667,
+      "step": 3844
+    },
+    {
+      "epoch": 1.65933117583603,
+      "grad_norm": 0.4787199795246124,
+      "learning_rate": 0.00017833272920539034,
+      "loss": 0.7908329367637634,
+      "step": 3846
+    },
+    {
+      "epoch": 1.6601941747572817,
+      "grad_norm": 0.4505045711994171,
+      "learning_rate": 0.0001783021946536463,
+      "loss": 0.6918519139289856,
+      "step": 3848
+    },
+    {
+      "epoch": 1.661057173678533,
+      "grad_norm": 0.43013763427734375,
+      "learning_rate": 0.00017827164121968103,
+      "loss": 0.7223191857337952,
+      "step": 3850
+    },
+    {
+      "epoch": 1.661920172599784,
+      "grad_norm": 0.47614169120788574,
+      "learning_rate": 0.00017824106891086228,
+      "loss": 0.8076598644256592,
+      "step": 3852
+    },
+    {
+      "epoch": 1.6627831715210357,
+      "grad_norm": 0.48056647181510925,
+      "learning_rate": 0.0001782104777345625,
+      "loss": 0.7656319737434387,
+      "step": 3854
+    },
+    {
+      "epoch": 1.663646170442287,
+      "grad_norm": 0.38120999932289124,
+      "learning_rate": 0.00017817986769815857,
+      "loss": 0.7252323031425476,
+      "step": 3856
+    },
+    {
+      "epoch": 1.6645091693635383,
+      "grad_norm": 0.478983074426651,
+      "learning_rate": 0.00017814923880903202,
+      "loss": 0.747683048248291,
+      "step": 3858
+    },
+    {
+      "epoch": 1.6653721682847897,
+      "grad_norm": 0.4553819000720978,
+      "learning_rate": 0.0001781185910745688,
+      "loss": 0.69855135679245,
+      "step": 3860
+    },
+    {
+      "epoch": 1.666235167206041,
+      "grad_norm": 0.49657294154167175,
+      "learning_rate": 0.0001780879245021595,
+      "loss": 0.8340141773223877,
+      "step": 3862
+    },
+    {
+      "epoch": 1.6670981661272923,
+      "grad_norm": 0.40509313344955444,
+      "learning_rate": 0.00017805723909919925,
+      "loss": 0.7290753722190857,
+      "step": 3864
+    },
+    {
+      "epoch": 1.6679611650485437,
+      "grad_norm": 0.4422856271266937,
+      "learning_rate": 0.00017802653487308768,
+      "loss": 0.7971621751785278,
+      "step": 3866
+    },
+    {
+      "epoch": 1.668824163969795,
+      "grad_norm": 0.4734835624694824,
+      "learning_rate": 0.00017799581183122894,
+      "loss": 0.7099016904830933,
+      "step": 3868
+    },
+    {
+      "epoch": 1.6696871628910464,
+      "grad_norm": 0.3835538625717163,
+      "learning_rate": 0.0001779650699810318,
+      "loss": 0.7210022211074829,
+      "step": 3870
+    },
+    {
+      "epoch": 1.6705501618122978,
+      "grad_norm": 0.3696903884410858,
+      "learning_rate": 0.00017793430932990951,
+      "loss": 0.6639223694801331,
+      "step": 3872
+    },
+    {
+      "epoch": 1.671413160733549,
+      "grad_norm": 0.4560008645057678,
+      "learning_rate": 0.00017790352988527984,
+      "loss": 0.8337125182151794,
+      "step": 3874
+    },
+    {
+      "epoch": 1.6722761596548006,
+      "grad_norm": 0.43672001361846924,
+      "learning_rate": 0.00017787273165456515,
+      "loss": 0.6761727929115295,
+      "step": 3876
+    },
+    {
+      "epoch": 1.6731391585760518,
+      "grad_norm": 0.37448835372924805,
+      "learning_rate": 0.00017784191464519225,
+      "loss": 0.6976995468139648,
+      "step": 3878
+    },
+    {
+      "epoch": 1.674002157497303,
+      "grad_norm": 0.37624600529670715,
+      "learning_rate": 0.00017781107886459253,
+      "loss": 0.6759265661239624,
+      "step": 3880
+    },
+    {
+      "epoch": 1.6748651564185546,
+      "grad_norm": 0.4134359359741211,
+      "learning_rate": 0.00017778022432020198,
+      "loss": 0.6577118039131165,
+      "step": 3882
+    },
+    {
+      "epoch": 1.6757281553398058,
+      "grad_norm": 0.41737261414527893,
+      "learning_rate": 0.00017774935101946092,
+      "loss": 0.7117277979850769,
+      "step": 3884
+    },
+    {
+      "epoch": 1.6765911542610572,
+      "grad_norm": 0.41871723532676697,
+      "learning_rate": 0.00017771845896981438,
+      "loss": 0.6871168613433838,
+      "step": 3886
+    },
+    {
+      "epoch": 1.6774541531823086,
+      "grad_norm": 0.4778793156147003,
+      "learning_rate": 0.00017768754817871178,
+      "loss": 0.7382785677909851,
+      "step": 3888
+    },
+    {
+      "epoch": 1.6783171521035598,
+      "grad_norm": 0.4502207338809967,
+      "learning_rate": 0.00017765661865360718,
+      "loss": 0.6783252358436584,
+      "step": 3890
+    },
+    {
+      "epoch": 1.6791801510248112,
+      "grad_norm": 0.4124210774898529,
+      "learning_rate": 0.00017762567040195907,
+      "loss": 0.7115309238433838,
+      "step": 3892
+    },
+    {
+      "epoch": 1.6800431499460626,
+      "grad_norm": 0.45017218589782715,
+      "learning_rate": 0.0001775947034312305,
+      "loss": 0.6698686480522156,
+      "step": 3894
+    },
+    {
+      "epoch": 1.6809061488673138,
+      "grad_norm": 0.4965505301952362,
+      "learning_rate": 0.00017756371774888896,
+      "loss": 0.7978704571723938,
+      "step": 3896
+    },
+    {
+      "epoch": 1.6817691477885652,
+      "grad_norm": 0.44287896156311035,
+      "learning_rate": 0.00017753271336240655,
+      "loss": 0.7991471290588379,
+      "step": 3898
+    },
+    {
+      "epoch": 1.6826321467098166,
+      "grad_norm": 0.4569724500179291,
+      "learning_rate": 0.00017750169027925985,
+      "loss": 0.7351664900779724,
+      "step": 3900
+    },
+    {
+      "epoch": 1.6826321467098166,
+      "eval_loss": 0.7847991585731506,
+      "eval_runtime": 648.2009,
+      "eval_samples_per_second": 3.178,
+      "eval_steps_per_second": 3.178,
+      "step": 3900
+    },
+    {
+      "epoch": 1.6834951456310678,
+      "grad_norm": 0.39483416080474854,
+      "learning_rate": 0.00017747064850692993,
+      "loss": 0.744560182094574,
+      "step": 3902
+    },
+    {
+      "epoch": 1.6843581445523195,
+      "grad_norm": 0.4636281430721283,
+      "learning_rate": 0.00017743958805290232,
+      "loss": 0.7506792545318604,
+      "step": 3904
+    },
+    {
+      "epoch": 1.6852211434735707,
+      "grad_norm": 0.43549975752830505,
+      "learning_rate": 0.00017740850892466719,
+      "loss": 0.7190370559692383,
+      "step": 3906
+    },
+    {
+      "epoch": 1.6860841423948218,
+      "grad_norm": 0.4514775276184082,
+      "learning_rate": 0.00017737741112971907,
+      "loss": 0.7768138647079468,
+      "step": 3908
+    },
+    {
+      "epoch": 1.6869471413160735,
+      "grad_norm": 0.45857131481170654,
+      "learning_rate": 0.0001773462946755571,
+      "loss": 0.7726560831069946,
+      "step": 3910
+    },
+    {
+      "epoch": 1.6878101402373247,
+      "grad_norm": 0.4479610323905945,
+      "learning_rate": 0.00017731515956968482,
+      "loss": 0.6987468600273132,
+      "step": 3912
+    },
+    {
+      "epoch": 1.688673139158576,
+      "grad_norm": 0.489849716424942,
+      "learning_rate": 0.00017728400581961036,
+      "loss": 0.6895362734794617,
+      "step": 3914
+    },
+    {
+      "epoch": 1.6895361380798275,
+      "grad_norm": 0.48648950457572937,
+      "learning_rate": 0.00017725283343284629,
+      "loss": 0.7460364699363708,
+      "step": 3916
+    },
+    {
+      "epoch": 1.6903991370010787,
+      "grad_norm": 0.5052891969680786,
+      "learning_rate": 0.0001772216424169097,
+      "loss": 0.7300586104393005,
+      "step": 3918
+    },
+    {
+      "epoch": 1.69126213592233,
+      "grad_norm": 0.48179247975349426,
+      "learning_rate": 0.00017719043277932215,
+      "loss": 0.7635855674743652,
+      "step": 3920
+    },
+    {
+      "epoch": 1.6921251348435815,
+      "grad_norm": 0.5296869277954102,
+      "learning_rate": 0.00017715920452760972,
+      "loss": 0.7760766744613647,
+      "step": 3922
+    },
+    {
+      "epoch": 1.6929881337648327,
+      "grad_norm": 0.5226309895515442,
+      "learning_rate": 0.00017712795766930298,
+      "loss": 0.798885703086853,
+      "step": 3924
+    },
+    {
+      "epoch": 1.6938511326860841,
+      "grad_norm": 0.3812384605407715,
+      "learning_rate": 0.0001770966922119369,
+      "loss": 0.7614596486091614,
+      "step": 3926
+    },
+    {
+      "epoch": 1.6947141316073355,
+      "grad_norm": 0.4084458649158478,
+      "learning_rate": 0.00017706540816305103,
+      "loss": 0.7634122967720032,
+      "step": 3928
+    },
+    {
+      "epoch": 1.6955771305285867,
+      "grad_norm": 0.49413034319877625,
+      "learning_rate": 0.00017703410553018944,
+      "loss": 0.7364476323127747,
+      "step": 3930
+    },
+    {
+      "epoch": 1.6964401294498384,
+      "grad_norm": 0.4119735658168793,
+      "learning_rate": 0.00017700278432090057,
+      "loss": 0.6874673366546631,
+      "step": 3932
+    },
+    {
+      "epoch": 1.6973031283710895,
+      "grad_norm": 0.5013890266418457,
+      "learning_rate": 0.00017697144454273736,
+      "loss": 0.7503598928451538,
+      "step": 3934
+    },
+    {
+      "epoch": 1.6981661272923407,
+      "grad_norm": 0.4563339054584503,
+      "learning_rate": 0.0001769400862032573,
+      "loss": 0.7193819880485535,
+      "step": 3936
+    },
+    {
+      "epoch": 1.6990291262135924,
+      "grad_norm": 0.4373779892921448,
+      "learning_rate": 0.00017690870931002232,
+      "loss": 0.7516534328460693,
+      "step": 3938
+    },
+    {
+      "epoch": 1.6998921251348436,
+      "grad_norm": 0.40220266580581665,
+      "learning_rate": 0.0001768773138705988,
+      "loss": 0.7319802045822144,
+      "step": 3940
+    },
+    {
+      "epoch": 1.700755124056095,
+      "grad_norm": 0.42924389243125916,
+      "learning_rate": 0.00017684589989255757,
+      "loss": 0.6950404644012451,
+      "step": 3942
+    },
+    {
+      "epoch": 1.7016181229773464,
+      "grad_norm": 0.4453158378601074,
+      "learning_rate": 0.00017681446738347404,
+      "loss": 0.697744607925415,
+      "step": 3944
+    },
+    {
+      "epoch": 1.7024811218985976,
+      "grad_norm": 0.4532380998134613,
+      "learning_rate": 0.00017678301635092795,
+      "loss": 0.6951707601547241,
+      "step": 3946
+    },
+    {
+      "epoch": 1.703344120819849,
+      "grad_norm": 0.4668843448162079,
+      "learning_rate": 0.00017675154680250361,
+      "loss": 0.781558096408844,
+      "step": 3948
+    },
+    {
+      "epoch": 1.7042071197411004,
+      "grad_norm": 0.48179176449775696,
+      "learning_rate": 0.00017672005874578978,
+      "loss": 0.7811654806137085,
+      "step": 3950
+    },
+    {
+      "epoch": 1.7050701186623516,
+      "grad_norm": 0.40447115898132324,
+      "learning_rate": 0.00017668855218837962,
+      "loss": 0.7350773215293884,
+      "step": 3952
+    },
+    {
+      "epoch": 1.705933117583603,
+      "grad_norm": 0.45968949794769287,
+      "learning_rate": 0.00017665702713787082,
+      "loss": 0.7492660284042358,
+      "step": 3954
+    },
+    {
+      "epoch": 1.7067961165048544,
+      "grad_norm": 0.5223715901374817,
+      "learning_rate": 0.0001766254836018655,
+      "loss": 0.7472123503684998,
+      "step": 3956
+    },
+    {
+      "epoch": 1.7076591154261056,
+      "grad_norm": 0.4571165144443512,
+      "learning_rate": 0.00017659392158797023,
+      "loss": 0.7836515307426453,
+      "step": 3958
+    },
+    {
+      "epoch": 1.708522114347357,
+      "grad_norm": 0.4370459318161011,
+      "learning_rate": 0.00017656234110379607,
+      "loss": 0.7453757524490356,
+      "step": 3960
+    },
+    {
+      "epoch": 1.7093851132686084,
+      "grad_norm": 0.4259219467639923,
+      "learning_rate": 0.0001765307421569585,
+      "loss": 0.7094024419784546,
+      "step": 3962
+    },
+    {
+      "epoch": 1.7102481121898596,
+      "grad_norm": 0.41195449233055115,
+      "learning_rate": 0.00017649912475507744,
+      "loss": 0.7037264108657837,
+      "step": 3964
+    },
+    {
+      "epoch": 1.7111111111111112,
+      "grad_norm": 0.40624237060546875,
+      "learning_rate": 0.0001764674889057773,
+      "loss": 0.7216715216636658,
+      "step": 3966
+    },
+    {
+      "epoch": 1.7119741100323624,
+      "grad_norm": 0.46490001678466797,
+      "learning_rate": 0.00017643583461668695,
+      "loss": 0.7317749261856079,
+      "step": 3968
+    },
+    {
+      "epoch": 1.7128371089536139,
+      "grad_norm": 0.4935937821865082,
+      "learning_rate": 0.00017640416189543964,
+      "loss": 0.7064663767814636,
+      "step": 3970
+    },
+    {
+      "epoch": 1.7137001078748653,
+      "grad_norm": 0.454501211643219,
+      "learning_rate": 0.00017637247074967315,
+      "loss": 0.6983333826065063,
+      "step": 3972
+    },
+    {
+      "epoch": 1.7145631067961165,
+      "grad_norm": 0.4357846975326538,
+      "learning_rate": 0.00017634076118702962,
+      "loss": 0.7516914010047913,
+      "step": 3974
+    },
+    {
+      "epoch": 1.7154261057173679,
+      "grad_norm": 0.421758234500885,
+      "learning_rate": 0.00017630903321515565,
+      "loss": 0.7914417386054993,
+      "step": 3976
+    },
+    {
+      "epoch": 1.7162891046386193,
+      "grad_norm": 0.4549725353717804,
+      "learning_rate": 0.00017627728684170235,
+      "loss": 0.7100850343704224,
+      "step": 3978
+    },
+    {
+      "epoch": 1.7171521035598705,
+      "grad_norm": 0.4313303530216217,
+      "learning_rate": 0.00017624552207432518,
+      "loss": 0.7711127400398254,
+      "step": 3980
+    },
+    {
+      "epoch": 1.7180151024811219,
+      "grad_norm": 0.46351364254951477,
+      "learning_rate": 0.00017621373892068407,
+      "loss": 0.681434690952301,
+      "step": 3982
+    },
+    {
+      "epoch": 1.7188781014023733,
+      "grad_norm": 0.5010084509849548,
+      "learning_rate": 0.0001761819373884434,
+      "loss": 0.7418093681335449,
+      "step": 3984
+    },
+    {
+      "epoch": 1.7197411003236245,
+      "grad_norm": 0.4252820909023285,
+      "learning_rate": 0.00017615011748527194,
+      "loss": 0.7767686247825623,
+      "step": 3986
+    },
+    {
+      "epoch": 1.720604099244876,
+      "grad_norm": 0.48956605792045593,
+      "learning_rate": 0.00017611827921884296,
+      "loss": 0.7049045562744141,
+      "step": 3988
+    },
+    {
+      "epoch": 1.7214670981661273,
+      "grad_norm": 0.42927032709121704,
+      "learning_rate": 0.00017608642259683407,
+      "loss": 0.7224108576774597,
+      "step": 3990
+    },
+    {
+      "epoch": 1.7223300970873785,
+      "grad_norm": 0.49601903557777405,
+      "learning_rate": 0.0001760545476269274,
+      "loss": 0.7203757166862488,
+      "step": 3992
+    },
+    {
+      "epoch": 1.7231930960086301,
+      "grad_norm": 0.38675686717033386,
+      "learning_rate": 0.0001760226543168094,
+      "loss": 0.6614230871200562,
+      "step": 3994
+    },
+    {
+      "epoch": 1.7240560949298813,
+      "grad_norm": 0.4299238622188568,
+      "learning_rate": 0.00017599074267417105,
+      "loss": 0.7201424837112427,
+      "step": 3996
+    },
+    {
+      "epoch": 1.7249190938511327,
+      "grad_norm": 0.43249231576919556,
+      "learning_rate": 0.00017595881270670763,
+      "loss": 0.7156208753585815,
+      "step": 3998
+    },
+    {
+      "epoch": 1.7257820927723841,
+      "grad_norm": 0.426278680562973,
+      "learning_rate": 0.00017592686442211898,
+      "loss": 0.7258728742599487,
+      "step": 4000
+    },
+    {
+      "epoch": 1.7257820927723841,
+      "eval_loss": 0.7843562960624695,
+      "eval_runtime": 657.9206,
+      "eval_samples_per_second": 3.131,
+      "eval_steps_per_second": 3.131,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 13908,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.001
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 1
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.3987519270231777e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/sft_qwen_14B/checkpoints/checkpoint-4000/training_args.bin b/sft_qwen_14B/checkpoints/checkpoint-4000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b023888140f1fb107e8d5ebbfbcb9d9558b09d43
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-4000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4200830b23d19bc86049c280236c4a6b18c26d7061b5a57cc024888ec760920f
+size 5201
diff --git a/sft_qwen_14B/checkpoints/checkpoint-4500/README.md b/sft_qwen_14B/checkpoints/checkpoint-4500/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..779b6406e547b32301fef1d181301a873befe542
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-4500/README.md
@@ -0,0 +1,207 @@
+---
+base_model: runs/cpt_run_14b/merged_14b_cpt_lora
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:runs/cpt_run_14b/merged_14b_cpt_lora
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0
\ No newline at end of file
diff --git a/sft_qwen_14B/checkpoints/checkpoint-4500/adapter_config.json b/sft_qwen_14B/checkpoints/checkpoint-4500/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8ea271115c141fb10c6d899b06f46f21800e1ad6
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-4500/adapter_config.json
@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "runs/cpt_run_14b/merged_14b_cpt_lora",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/sft_qwen_14B/checkpoints/checkpoint-4500/adapter_model.safetensors b/sft_qwen_14B/checkpoints/checkpoint-4500/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b2ec2989386a7dc70e84257fe7c09f5b18e7ee8c
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-4500/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3726a3859050973f5670196544ebe752cfffa4253f1767f5b0af266df2ace6b
+size 100715016
diff --git a/sft_qwen_14B/checkpoints/checkpoint-4500/optimizer.pt b/sft_qwen_14B/checkpoints/checkpoint-4500/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9599ef7754e1738104233151848137e78df9fa8e
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-4500/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:497ba06c0ad679d5e0f0bccb8769c8f8c084fc00a5f722fe12adb21662063382
+size 201650659
diff --git a/sft_qwen_14B/checkpoints/checkpoint-4500/rng_state.pth b/sft_qwen_14B/checkpoints/checkpoint-4500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..45bcf16a8788eb0e7e59154c6df337e74818f6f9
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-4500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:474efbe2a29787773dfb68710e591f30e509bc960d66b9abc6e327a6a1ee9932
+size 14645
diff --git a/sft_qwen_14B/checkpoints/checkpoint-4500/scheduler.pt b/sft_qwen_14B/checkpoints/checkpoint-4500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5a727aa04cb89192c952660b9bc9de8a255c8d4a
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-4500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15bf709800f2fa19405181cc98f0961bcdd990ba3736a1feb3c98c0bfc6c9ff1
+size 1465
diff --git a/sft_qwen_14B/checkpoints/checkpoint-4500/trainer_state.json b/sft_qwen_14B/checkpoints/checkpoint-4500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..7efdd1bc2002aca171af2df86b64408e2a9035e8
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-4500/trainer_state.json
@@ -0,0 +1,16153 @@
+{
+  "best_global_step": 4500,
+  "best_metric": 0.771009087562561,
+  "best_model_checkpoint": "runs/instruct_run_14b_v1/checkpoints/checkpoint-4500",
+  "epoch": 1.9415318230852212,
+  "eval_steps": 100,
+  "global_step": 4500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008629989212513484,
+      "grad_norm": 0.36567428708076477,
+      "learning_rate": 1.7969451931716084e-07,
+      "loss": 1.6794371604919434,
+      "step": 2
+    },
+    {
+      "epoch": 0.001725997842502697,
+      "grad_norm": 0.4024646580219269,
+      "learning_rate": 5.390835579514825e-07,
+      "loss": 1.6853073835372925,
+      "step": 4
+    },
+    {
+      "epoch": 0.0025889967637540453,
+      "grad_norm": 0.40199393033981323,
+      "learning_rate": 8.984725965858042e-07,
+      "loss": 1.7621158361434937,
+      "step": 6
+    },
+    {
+      "epoch": 0.003451995685005394,
+      "grad_norm": 0.35409677028656006,
+      "learning_rate": 1.257861635220126e-06,
+      "loss": 1.633257269859314,
+      "step": 8
+    },
+    {
+      "epoch": 0.004314994606256742,
+      "grad_norm": 0.39087551832199097,
+      "learning_rate": 1.6172506738544475e-06,
+      "loss": 1.7374768257141113,
+      "step": 10
+    },
+    {
+      "epoch": 0.005177993527508091,
+      "grad_norm": 0.3586857318878174,
+      "learning_rate": 1.9766397124887693e-06,
+      "loss": 1.6955714225769043,
+      "step": 12
+    },
+    {
+      "epoch": 0.006040992448759439,
+      "grad_norm": 0.32755669951438904,
+      "learning_rate": 2.3360287511230908e-06,
+      "loss": 1.720664381980896,
+      "step": 14
+    },
+    {
+      "epoch": 0.006903991370010788,
+      "grad_norm": 0.4054872691631317,
+      "learning_rate": 2.6954177897574127e-06,
+      "loss": 1.6957035064697266,
+      "step": 16
+    },
+    {
+      "epoch": 0.007766990291262136,
+      "grad_norm": 0.37593814730644226,
+      "learning_rate": 3.0548068283917343e-06,
+      "loss": 1.7286947965621948,
+      "step": 18
+    },
+    {
+      "epoch": 0.008629989212513484,
+      "grad_norm": 0.3344813287258148,
+      "learning_rate": 3.414195867026056e-06,
+      "loss": 1.727295994758606,
+      "step": 20
+    },
+    {
+      "epoch": 0.009492988133764833,
+      "grad_norm": 0.357474148273468,
+      "learning_rate": 3.7735849056603773e-06,
+      "loss": 1.6727914810180664,
+      "step": 22
+    },
+    {
+      "epoch": 0.010355987055016181,
+      "grad_norm": 0.39115726947784424,
+      "learning_rate": 4.132973944294699e-06,
+      "loss": 1.6518884897232056,
+      "step": 24
+    },
+    {
+      "epoch": 0.01121898597626753,
+      "grad_norm": 0.4711727201938629,
+      "learning_rate": 4.492362982929021e-06,
+      "loss": 1.7868088483810425,
+      "step": 26
+    },
+    {
+      "epoch": 0.012081984897518877,
+      "grad_norm": 0.34112176299095154,
+      "learning_rate": 4.851752021563342e-06,
+      "loss": 1.6127634048461914,
+      "step": 28
+    },
+    {
+      "epoch": 0.012944983818770227,
+      "grad_norm": 0.5071991682052612,
+      "learning_rate": 5.211141060197664e-06,
+      "loss": 1.7858378887176514,
+      "step": 30
+    },
+    {
+      "epoch": 0.013807982740021575,
+      "grad_norm": 0.42048847675323486,
+      "learning_rate": 5.570530098831986e-06,
+      "loss": 1.7123326063156128,
+      "step": 32
+    },
+    {
+      "epoch": 0.014670981661272923,
+      "grad_norm": 0.48883870244026184,
+      "learning_rate": 5.929919137466308e-06,
+      "loss": 1.737749695777893,
+      "step": 34
+    },
+    {
+      "epoch": 0.015533980582524271,
+      "grad_norm": 0.3311465084552765,
+      "learning_rate": 6.289308176100629e-06,
+      "loss": 1.5578981637954712,
+      "step": 36
+    },
+    {
+      "epoch": 0.01639697950377562,
+      "grad_norm": 0.5178973078727722,
+      "learning_rate": 6.64869721473495e-06,
+      "loss": 1.719806432723999,
+      "step": 38
+    },
+    {
+      "epoch": 0.017259978425026967,
+      "grad_norm": 0.47097742557525635,
+      "learning_rate": 7.008086253369272e-06,
+      "loss": 1.728212833404541,
+      "step": 40
+    },
+    {
+      "epoch": 0.018122977346278317,
+      "grad_norm": 0.5051584243774414,
+      "learning_rate": 7.367475292003594e-06,
+      "loss": 1.6542466878890991,
+      "step": 42
+    },
+    {
+      "epoch": 0.018985976267529667,
+      "grad_norm": 0.4645111560821533,
+      "learning_rate": 7.726864330637915e-06,
+      "loss": 1.7087690830230713,
+      "step": 44
+    },
+    {
+      "epoch": 0.019848975188781013,
+      "grad_norm": 0.5184999704360962,
+      "learning_rate": 8.086253369272237e-06,
+      "loss": 1.7018946409225464,
+      "step": 46
+    },
+    {
+      "epoch": 0.020711974110032363,
+      "grad_norm": 0.4543815851211548,
+      "learning_rate": 8.44564240790656e-06,
+      "loss": 1.6818269491195679,
+      "step": 48
+    },
+    {
+      "epoch": 0.021574973031283712,
+      "grad_norm": 0.44411996006965637,
+      "learning_rate": 8.80503144654088e-06,
+      "loss": 1.5772877931594849,
+      "step": 50
+    },
+    {
+      "epoch": 0.02243797195253506,
+      "grad_norm": 0.3409404158592224,
+      "learning_rate": 9.164420485175203e-06,
+      "loss": 1.498152732849121,
+      "step": 52
+    },
+    {
+      "epoch": 0.02330097087378641,
+      "grad_norm": 0.42104434967041016,
+      "learning_rate": 9.523809523809523e-06,
+      "loss": 1.6189048290252686,
+      "step": 54
+    },
+    {
+      "epoch": 0.024163969795037755,
+      "grad_norm": 0.3756246268749237,
+      "learning_rate": 9.883198562443846e-06,
+      "loss": 1.4596441984176636,
+      "step": 56
+    },
+    {
+      "epoch": 0.025026968716289105,
+      "grad_norm": 0.36214128136634827,
+      "learning_rate": 1.0242587601078168e-05,
+      "loss": 1.503880500793457,
+      "step": 58
+    },
+    {
+      "epoch": 0.025889967637540454,
+      "grad_norm": 0.40893009305000305,
+      "learning_rate": 1.060197663971249e-05,
+      "loss": 1.5912823677062988,
+      "step": 60
+    },
+    {
+      "epoch": 0.0267529665587918,
+      "grad_norm": 0.28710272908210754,
+      "learning_rate": 1.0961365678346811e-05,
+      "loss": 1.2956721782684326,
+      "step": 62
+    },
+    {
+      "epoch": 0.02761596548004315,
+      "grad_norm": 0.304573118686676,
+      "learning_rate": 1.1320754716981132e-05,
+      "loss": 1.4648056030273438,
+      "step": 64
+    },
+    {
+      "epoch": 0.0284789644012945,
+      "grad_norm": 0.36523914337158203,
+      "learning_rate": 1.1680143755615454e-05,
+      "loss": 1.6078968048095703,
+      "step": 66
+    },
+    {
+      "epoch": 0.029341963322545846,
+      "grad_norm": 0.37929031252861023,
+      "learning_rate": 1.2039532794249775e-05,
+      "loss": 1.5969421863555908,
+      "step": 68
+    },
+    {
+      "epoch": 0.030204962243797196,
+      "grad_norm": 0.3053947389125824,
+      "learning_rate": 1.2398921832884097e-05,
+      "loss": 1.4312325716018677,
+      "step": 70
+    },
+    {
+      "epoch": 0.031067961165048542,
+      "grad_norm": 0.3028779923915863,
+      "learning_rate": 1.275831087151842e-05,
+      "loss": 1.4101300239562988,
+      "step": 72
+    },
+    {
+      "epoch": 0.03193096008629989,
+      "grad_norm": 0.29649803042411804,
+      "learning_rate": 1.3117699910152742e-05,
+      "loss": 1.4553817510604858,
+      "step": 74
+    },
+    {
+      "epoch": 0.03279395900755124,
+      "grad_norm": 0.26032644510269165,
+      "learning_rate": 1.3477088948787062e-05,
+      "loss": 1.4623000621795654,
+      "step": 76
+    },
+    {
+      "epoch": 0.03365695792880259,
+      "grad_norm": 0.33558446168899536,
+      "learning_rate": 1.3836477987421385e-05,
+      "loss": 1.5181745290756226,
+      "step": 78
+    },
+    {
+      "epoch": 0.034519956850053934,
+      "grad_norm": 0.28307804465293884,
+      "learning_rate": 1.4195867026055706e-05,
+      "loss": 1.4397861957550049,
+      "step": 80
+    },
+    {
+      "epoch": 0.035382955771305284,
+      "grad_norm": 0.3451690673828125,
+      "learning_rate": 1.455525606469003e-05,
+      "loss": 1.463841199874878,
+      "step": 82
+    },
+    {
+      "epoch": 0.036245954692556634,
+      "grad_norm": 0.3248669505119324,
+      "learning_rate": 1.4914645103324348e-05,
+      "loss": 1.3554227352142334,
+      "step": 84
+    },
+    {
+      "epoch": 0.037108953613807984,
+      "grad_norm": 0.2855011224746704,
+      "learning_rate": 1.527403414195867e-05,
+      "loss": 1.2810425758361816,
+      "step": 86
+    },
+    {
+      "epoch": 0.03797195253505933,
+      "grad_norm": 0.33365535736083984,
+      "learning_rate": 1.5633423180592992e-05,
+      "loss": 1.428163766860962,
+      "step": 88
+    },
+    {
+      "epoch": 0.038834951456310676,
+      "grad_norm": 0.34099438786506653,
+      "learning_rate": 1.5992812219227316e-05,
+      "loss": 1.3487578630447388,
+      "step": 90
+    },
+    {
+      "epoch": 0.039697950377562026,
+      "grad_norm": 0.39247506856918335,
+      "learning_rate": 1.6352201257861635e-05,
+      "loss": 1.30057954788208,
+      "step": 92
+    },
+    {
+      "epoch": 0.040560949298813376,
+      "grad_norm": 0.32692041993141174,
+      "learning_rate": 1.671159029649596e-05,
+      "loss": 1.2923580408096313,
+      "step": 94
+    },
+    {
+      "epoch": 0.041423948220064725,
+      "grad_norm": 0.43452519178390503,
+      "learning_rate": 1.707097933513028e-05,
+      "loss": 1.5002273321151733,
+      "step": 96
+    },
+    {
+      "epoch": 0.042286947141316075,
+      "grad_norm": 0.3251534402370453,
+      "learning_rate": 1.7430368373764602e-05,
+      "loss": 1.330254077911377,
+      "step": 98
+    },
+    {
+      "epoch": 0.043149946062567425,
+      "grad_norm": 0.3198273479938507,
+      "learning_rate": 1.778975741239892e-05,
+      "loss": 1.3054943084716797,
+      "step": 100
+    },
+    {
+      "epoch": 0.043149946062567425,
+      "eval_loss": 1.366738200187683,
+      "eval_runtime": 651.8198,
+      "eval_samples_per_second": 3.16,
+      "eval_steps_per_second": 3.16,
+      "step": 100
+    },
+    {
+      "epoch": 0.04401294498381877,
+      "grad_norm": 0.37364065647125244,
+      "learning_rate": 1.8149146451033245e-05,
+      "loss": 1.314281940460205,
+      "step": 102
+    },
+    {
+      "epoch": 0.04487594390507012,
+      "grad_norm": 0.39384758472442627,
+      "learning_rate": 1.8508535489667568e-05,
+      "loss": 1.2737246751785278,
+      "step": 104
+    },
+    {
+      "epoch": 0.04573894282632147,
+      "grad_norm": 0.3521905541419983,
+      "learning_rate": 1.8867924528301888e-05,
+      "loss": 1.3113226890563965,
+      "step": 106
+    },
+    {
+      "epoch": 0.04660194174757282,
+      "grad_norm": 0.33531463146209717,
+      "learning_rate": 1.9227313566936208e-05,
+      "loss": 1.3253653049468994,
+      "step": 108
+    },
+    {
+      "epoch": 0.04746494066882417,
+      "grad_norm": 0.35596340894699097,
+      "learning_rate": 1.958670260557053e-05,
+      "loss": 1.3236849308013916,
+      "step": 110
+    },
+    {
+      "epoch": 0.04832793959007551,
+      "grad_norm": 0.36028242111206055,
+      "learning_rate": 1.9946091644204854e-05,
+      "loss": 1.183128833770752,
+      "step": 112
+    },
+    {
+      "epoch": 0.04919093851132686,
+      "grad_norm": 0.42109814286231995,
+      "learning_rate": 2.0305480682839174e-05,
+      "loss": 1.2741888761520386,
+      "step": 114
+    },
+    {
+      "epoch": 0.05005393743257821,
+      "grad_norm": 0.39675939083099365,
+      "learning_rate": 2.0664869721473494e-05,
+      "loss": 1.3050109148025513,
+      "step": 116
+    },
+    {
+      "epoch": 0.05091693635382956,
+      "grad_norm": 0.4414141774177551,
+      "learning_rate": 2.1024258760107817e-05,
+      "loss": 1.2472094297409058,
+      "step": 118
+    },
+    {
+      "epoch": 0.05177993527508091,
+      "grad_norm": 0.42872729897499084,
+      "learning_rate": 2.138364779874214e-05,
+      "loss": 1.3338921070098877,
+      "step": 120
+    },
+    {
+      "epoch": 0.05264293419633225,
+      "grad_norm": 0.38336244225502014,
+      "learning_rate": 2.174303683737646e-05,
+      "loss": 1.322908878326416,
+      "step": 122
+    },
+    {
+      "epoch": 0.0535059331175836,
+      "grad_norm": 0.41046878695487976,
+      "learning_rate": 2.2102425876010783e-05,
+      "loss": 1.2169240713119507,
+      "step": 124
+    },
+    {
+      "epoch": 0.05436893203883495,
+      "grad_norm": 0.39460113644599915,
+      "learning_rate": 2.2461814914645103e-05,
+      "loss": 1.2085309028625488,
+      "step": 126
+    },
+    {
+      "epoch": 0.0552319309600863,
+      "grad_norm": 0.42829909920692444,
+      "learning_rate": 2.2821203953279426e-05,
+      "loss": 1.2969133853912354,
+      "step": 128
+    },
+    {
+      "epoch": 0.05609492988133765,
+      "grad_norm": 0.3940851390361786,
+      "learning_rate": 2.3180592991913746e-05,
+      "loss": 1.1892330646514893,
+      "step": 130
+    },
+    {
+      "epoch": 0.056957928802589,
+      "grad_norm": 0.45011839270591736,
+      "learning_rate": 2.353998203054807e-05,
+      "loss": 1.2082979679107666,
+      "step": 132
+    },
+    {
+      "epoch": 0.05782092772384034,
+      "grad_norm": 0.46059420704841614,
+      "learning_rate": 2.3899371069182393e-05,
+      "loss": 1.2388817071914673,
+      "step": 134
+    },
+    {
+      "epoch": 0.05868392664509169,
+      "grad_norm": 0.41085872054100037,
+      "learning_rate": 2.4258760107816713e-05,
+      "loss": 1.193917155265808,
+      "step": 136
+    },
+    {
+      "epoch": 0.05954692556634304,
+      "grad_norm": 0.4024205207824707,
+      "learning_rate": 2.4618149146451032e-05,
+      "loss": 1.1514034271240234,
+      "step": 138
+    },
+    {
+      "epoch": 0.06040992448759439,
+      "grad_norm": 0.3893793523311615,
+      "learning_rate": 2.4977538185085356e-05,
+      "loss": 1.1626157760620117,
+      "step": 140
+    },
+    {
+      "epoch": 0.06127292340884574,
+      "grad_norm": 0.4456317126750946,
+      "learning_rate": 2.5336927223719675e-05,
+      "loss": 1.1627076864242554,
+      "step": 142
+    },
+    {
+      "epoch": 0.062135922330097085,
+      "grad_norm": 0.5050215125083923,
+      "learning_rate": 2.5696316262354e-05,
+      "loss": 1.3038755655288696,
+      "step": 144
+    },
+    {
+      "epoch": 0.06299892125134844,
+      "grad_norm": 0.4071207642555237,
+      "learning_rate": 2.605570530098832e-05,
+      "loss": 1.1708844900131226,
+      "step": 146
+    },
+    {
+      "epoch": 0.06386192017259978,
+      "grad_norm": 0.4363228678703308,
+      "learning_rate": 2.641509433962264e-05,
+      "loss": 1.2149070501327515,
+      "step": 148
+    },
+    {
+      "epoch": 0.06472491909385113,
+      "grad_norm": 0.4436556398868561,
+      "learning_rate": 2.6774483378256965e-05,
+      "loss": 1.1942368745803833,
+      "step": 150
+    },
+    {
+      "epoch": 0.06558791801510248,
+      "grad_norm": 0.4068629741668701,
+      "learning_rate": 2.7133872416891288e-05,
+      "loss": 1.1799161434173584,
+      "step": 152
+    },
+    {
+      "epoch": 0.06645091693635383,
+      "grad_norm": 0.5291106700897217,
+      "learning_rate": 2.7493261455525608e-05,
+      "loss": 1.1832845211029053,
+      "step": 154
+    },
+    {
+      "epoch": 0.06731391585760518,
+      "grad_norm": 0.4410109221935272,
+      "learning_rate": 2.785265049415993e-05,
+      "loss": 1.1696993112564087,
+      "step": 156
+    },
+    {
+      "epoch": 0.06817691477885653,
+      "grad_norm": 0.4858371913433075,
+      "learning_rate": 2.8212039532794248e-05,
+      "loss": 1.2036973237991333,
+      "step": 158
+    },
+    {
+      "epoch": 0.06903991370010787,
+      "grad_norm": 0.45373693108558655,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 1.1145079135894775,
+      "step": 160
+    },
+    {
+      "epoch": 0.06990291262135923,
+      "grad_norm": 0.4881038963794708,
+      "learning_rate": 2.8930817610062894e-05,
+      "loss": 1.173502802848816,
+      "step": 162
+    },
+    {
+      "epoch": 0.07076591154261057,
+      "grad_norm": 0.576934814453125,
+      "learning_rate": 2.9290206648697217e-05,
+      "loss": 1.250414490699768,
+      "step": 164
+    },
+    {
+      "epoch": 0.07162891046386193,
+      "grad_norm": 0.4900001287460327,
+      "learning_rate": 2.9649595687331537e-05,
+      "loss": 1.0721495151519775,
+      "step": 166
+    },
+    {
+      "epoch": 0.07249190938511327,
+      "grad_norm": 0.4440019726753235,
+      "learning_rate": 3.000898472596586e-05,
+      "loss": 1.0689374208450317,
+      "step": 168
+    },
+    {
+      "epoch": 0.07335490830636461,
+      "grad_norm": 0.4267268180847168,
+      "learning_rate": 3.0368373764600184e-05,
+      "loss": 1.2095128297805786,
+      "step": 170
+    },
+    {
+      "epoch": 0.07421790722761597,
+      "grad_norm": 0.6062787771224976,
+      "learning_rate": 3.0727762803234503e-05,
+      "loss": 1.077776551246643,
+      "step": 172
+    },
+    {
+      "epoch": 0.07508090614886731,
+      "grad_norm": 0.49510180950164795,
+      "learning_rate": 3.108715184186882e-05,
+      "loss": 1.144006371498108,
+      "step": 174
+    },
+    {
+      "epoch": 0.07594390507011867,
+      "grad_norm": 0.4670701026916504,
+      "learning_rate": 3.144654088050314e-05,
+      "loss": 1.1663392782211304,
+      "step": 176
+    },
+    {
+      "epoch": 0.07680690399137001,
+      "grad_norm": 0.5615383386611938,
+      "learning_rate": 3.1805929919137466e-05,
+      "loss": 1.1665973663330078,
+      "step": 178
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "grad_norm": 0.47305551171302795,
+      "learning_rate": 3.216531895777179e-05,
+      "loss": 1.1337063312530518,
+      "step": 180
+    },
+    {
+      "epoch": 0.07853290183387271,
+      "grad_norm": 0.5127068758010864,
+      "learning_rate": 3.252470799640611e-05,
+      "loss": 1.072874903678894,
+      "step": 182
+    },
+    {
+      "epoch": 0.07939590075512405,
+      "grad_norm": 0.632448136806488,
+      "learning_rate": 3.2884097035040436e-05,
+      "loss": 1.1577240228652954,
+      "step": 184
+    },
+    {
+      "epoch": 0.08025889967637541,
+      "grad_norm": 0.4041025638580322,
+      "learning_rate": 3.324348607367476e-05,
+      "loss": 1.1186822652816772,
+      "step": 186
+    },
+    {
+      "epoch": 0.08112189859762675,
+      "grad_norm": 0.5239102244377136,
+      "learning_rate": 3.3602875112309076e-05,
+      "loss": 1.1468429565429688,
+      "step": 188
+    },
+    {
+      "epoch": 0.08198489751887811,
+      "grad_norm": 0.4486575424671173,
+      "learning_rate": 3.39622641509434e-05,
+      "loss": 1.0017019510269165,
+      "step": 190
+    },
+    {
+      "epoch": 0.08284789644012945,
+      "grad_norm": 0.4994317293167114,
+      "learning_rate": 3.4321653189577715e-05,
+      "loss": 1.1901532411575317,
+      "step": 192
+    },
+    {
+      "epoch": 0.0837108953613808,
+      "grad_norm": 0.5023699998855591,
+      "learning_rate": 3.468104222821204e-05,
+      "loss": 1.1398564577102661,
+      "step": 194
+    },
+    {
+      "epoch": 0.08457389428263215,
+      "grad_norm": 0.5077701807022095,
+      "learning_rate": 3.504043126684636e-05,
+      "loss": 1.1390413045883179,
+      "step": 196
+    },
+    {
+      "epoch": 0.0854368932038835,
+      "grad_norm": 0.5527892112731934,
+      "learning_rate": 3.5399820305480685e-05,
+      "loss": 1.1411432027816772,
+      "step": 198
+    },
+    {
+      "epoch": 0.08629989212513485,
+      "grad_norm": 0.5572488903999329,
+      "learning_rate": 3.575920934411501e-05,
+      "loss": 1.071260690689087,
+      "step": 200
+    },
+    {
+      "epoch": 0.08629989212513485,
+      "eval_loss": 1.1519012451171875,
+      "eval_runtime": 654.6055,
+      "eval_samples_per_second": 3.147,
+      "eval_steps_per_second": 3.147,
+      "step": 200
+    },
+    {
+      "epoch": 0.08716289104638619,
+      "grad_norm": 0.5134095549583435,
+      "learning_rate": 3.611859838274933e-05,
+      "loss": 1.138135552406311,
+      "step": 202
+    },
+    {
+      "epoch": 0.08802588996763754,
+      "grad_norm": 0.5166040658950806,
+      "learning_rate": 3.647798742138365e-05,
+      "loss": 1.111999273300171,
+      "step": 204
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.5336993336677551,
+      "learning_rate": 3.683737646001797e-05,
+      "loss": 1.1031352281570435,
+      "step": 206
+    },
+    {
+      "epoch": 0.08975188781014024,
+      "grad_norm": 0.8289600014686584,
+      "learning_rate": 3.7196765498652294e-05,
+      "loss": 1.0388667583465576,
+      "step": 208
+    },
+    {
+      "epoch": 0.09061488673139159,
+      "grad_norm": 0.47992637753486633,
+      "learning_rate": 3.755615453728661e-05,
+      "loss": 1.0950241088867188,
+      "step": 210
+    },
+    {
+      "epoch": 0.09147788565264293,
+      "grad_norm": 0.5629691481590271,
+      "learning_rate": 3.7915543575920934e-05,
+      "loss": 1.0361733436584473,
+      "step": 212
+    },
+    {
+      "epoch": 0.09234088457389428,
+      "grad_norm": 0.5515111684799194,
+      "learning_rate": 3.827493261455526e-05,
+      "loss": 1.0922447443008423,
+      "step": 214
+    },
+    {
+      "epoch": 0.09320388349514563,
+      "grad_norm": 0.5078643560409546,
+      "learning_rate": 3.863432165318958e-05,
+      "loss": 1.0866856575012207,
+      "step": 216
+    },
+    {
+      "epoch": 0.09406688241639698,
+      "grad_norm": 0.6046127676963806,
+      "learning_rate": 3.8993710691823904e-05,
+      "loss": 1.1231595277786255,
+      "step": 218
+    },
+    {
+      "epoch": 0.09492988133764833,
+      "grad_norm": 0.6255762577056885,
+      "learning_rate": 3.935309973045822e-05,
+      "loss": 1.099171757698059,
+      "step": 220
+    },
+    {
+      "epoch": 0.09579288025889968,
+      "grad_norm": 0.6036638021469116,
+      "learning_rate": 3.971248876909254e-05,
+      "loss": 1.0557761192321777,
+      "step": 222
+    },
+    {
+      "epoch": 0.09665587918015102,
+      "grad_norm": 0.5520529747009277,
+      "learning_rate": 4.0071877807726867e-05,
+      "loss": 1.0467877388000488,
+      "step": 224
+    },
+    {
+      "epoch": 0.09751887810140238,
+      "grad_norm": 0.5958684682846069,
+      "learning_rate": 4.043126684636119e-05,
+      "loss": 1.17941153049469,
+      "step": 226
+    },
+    {
+      "epoch": 0.09838187702265372,
+      "grad_norm": 0.5283281803131104,
+      "learning_rate": 4.079065588499551e-05,
+      "loss": 1.104217767715454,
+      "step": 228
+    },
+    {
+      "epoch": 0.09924487594390508,
+      "grad_norm": 0.5608792901039124,
+      "learning_rate": 4.115004492362983e-05,
+      "loss": 1.0900640487670898,
+      "step": 230
+    },
+    {
+      "epoch": 0.10010787486515642,
+      "grad_norm": 0.555964469909668,
+      "learning_rate": 4.150943396226415e-05,
+      "loss": 0.9887422323226929,
+      "step": 232
+    },
+    {
+      "epoch": 0.10097087378640776,
+      "grad_norm": 0.5875785946846008,
+      "learning_rate": 4.1868823000898476e-05,
+      "loss": 1.1298567056655884,
+      "step": 234
+    },
+    {
+      "epoch": 0.10183387270765912,
+      "grad_norm": 0.4544795751571655,
+      "learning_rate": 4.222821203953279e-05,
+      "loss": 1.0957067012786865,
+      "step": 236
+    },
+    {
+      "epoch": 0.10269687162891046,
+      "grad_norm": 0.564145565032959,
+      "learning_rate": 4.2587601078167116e-05,
+      "loss": 1.0328738689422607,
+      "step": 238
+    },
+    {
+      "epoch": 0.10355987055016182,
+      "grad_norm": 0.6285979747772217,
+      "learning_rate": 4.294699011680144e-05,
+      "loss": 1.1085515022277832,
+      "step": 240
+    },
+    {
+      "epoch": 0.10442286947141316,
+      "grad_norm": 0.6442288756370544,
+      "learning_rate": 4.330637915543576e-05,
+      "loss": 1.1291271448135376,
+      "step": 242
+    },
+    {
+      "epoch": 0.1052858683926645,
+      "grad_norm": 0.6137154698371887,
+      "learning_rate": 4.3665768194070085e-05,
+      "loss": 1.1759567260742188,
+      "step": 244
+    },
+    {
+      "epoch": 0.10614886731391586,
+      "grad_norm": 0.5906805992126465,
+      "learning_rate": 4.402515723270441e-05,
+      "loss": 1.148414969444275,
+      "step": 246
+    },
+    {
+      "epoch": 0.1070118662351672,
+      "grad_norm": 0.5382888913154602,
+      "learning_rate": 4.438454627133873e-05,
+      "loss": 1.0749616622924805,
+      "step": 248
+    },
+    {
+      "epoch": 0.10787486515641856,
+      "grad_norm": 0.6185492873191833,
+      "learning_rate": 4.474393530997305e-05,
+      "loss": 1.2235801219940186,
+      "step": 250
+    },
+    {
+      "epoch": 0.1087378640776699,
+      "grad_norm": 0.5981597900390625,
+      "learning_rate": 4.5103324348607365e-05,
+      "loss": 1.1390639543533325,
+      "step": 252
+    },
+    {
+      "epoch": 0.10960086299892124,
+      "grad_norm": 0.5664694905281067,
+      "learning_rate": 4.546271338724169e-05,
+      "loss": 1.171774983406067,
+      "step": 254
+    },
+    {
+      "epoch": 0.1104638619201726,
+      "grad_norm": 0.7071851491928101,
+      "learning_rate": 4.582210242587601e-05,
+      "loss": 1.1704237461090088,
+      "step": 256
+    },
+    {
+      "epoch": 0.11132686084142394,
+      "grad_norm": 0.5815614461898804,
+      "learning_rate": 4.6181491464510334e-05,
+      "loss": 1.0619677305221558,
+      "step": 258
+    },
+    {
+      "epoch": 0.1121898597626753,
+      "grad_norm": 0.6481915712356567,
+      "learning_rate": 4.654088050314466e-05,
+      "loss": 1.0824390649795532,
+      "step": 260
+    },
+    {
+      "epoch": 0.11305285868392664,
+      "grad_norm": 0.5988591313362122,
+      "learning_rate": 4.690026954177898e-05,
+      "loss": 1.087929606437683,
+      "step": 262
+    },
+    {
+      "epoch": 0.113915857605178,
+      "grad_norm": 0.6545296311378479,
+      "learning_rate": 4.7259658580413304e-05,
+      "loss": 1.0936195850372314,
+      "step": 264
+    },
+    {
+      "epoch": 0.11477885652642934,
+      "grad_norm": 0.5826204419136047,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 1.0433681011199951,
+      "step": 266
+    },
+    {
+      "epoch": 0.11564185544768069,
+      "grad_norm": 0.5907514095306396,
+      "learning_rate": 4.7978436657681944e-05,
+      "loss": 1.0719536542892456,
+      "step": 268
+    },
+    {
+      "epoch": 0.11650485436893204,
+      "grad_norm": 0.524394154548645,
+      "learning_rate": 4.833782569631627e-05,
+      "loss": 1.0231504440307617,
+      "step": 270
+    },
+    {
+      "epoch": 0.11736785329018339,
+      "grad_norm": 0.5472846031188965,
+      "learning_rate": 4.869721473495058e-05,
+      "loss": 0.9905915260314941,
+      "step": 272
+    },
+    {
+      "epoch": 0.11823085221143474,
+      "grad_norm": 0.727922260761261,
+      "learning_rate": 4.9056603773584906e-05,
+      "loss": 1.213677167892456,
+      "step": 274
+    },
+    {
+      "epoch": 0.11909385113268608,
+      "grad_norm": 0.6009684801101685,
+      "learning_rate": 4.941599281221923e-05,
+      "loss": 1.0052144527435303,
+      "step": 276
+    },
+    {
+      "epoch": 0.11995685005393743,
+      "grad_norm": 0.6564669013023376,
+      "learning_rate": 4.977538185085355e-05,
+      "loss": 1.108136773109436,
+      "step": 278
+    },
+    {
+      "epoch": 0.12081984897518878,
+      "grad_norm": 0.650074303150177,
+      "learning_rate": 5.013477088948787e-05,
+      "loss": 0.9700815677642822,
+      "step": 280
+    },
+    {
+      "epoch": 0.12168284789644013,
+      "grad_norm": 0.5772947072982788,
+      "learning_rate": 5.04941599281222e-05,
+      "loss": 1.038031816482544,
+      "step": 282
+    },
+    {
+      "epoch": 0.12254584681769148,
+      "grad_norm": 0.7293002009391785,
+      "learning_rate": 5.0853548966756516e-05,
+      "loss": 1.1063730716705322,
+      "step": 284
+    },
+    {
+      "epoch": 0.12340884573894283,
+      "grad_norm": 0.7937333583831787,
+      "learning_rate": 5.1212938005390846e-05,
+      "loss": 1.128495693206787,
+      "step": 286
+    },
+    {
+      "epoch": 0.12427184466019417,
+      "grad_norm": 0.48499324917793274,
+      "learning_rate": 5.157232704402516e-05,
+      "loss": 0.9438712000846863,
+      "step": 288
+    },
+    {
+      "epoch": 0.12513484358144553,
+      "grad_norm": 0.6010656952857971,
+      "learning_rate": 5.193171608265948e-05,
+      "loss": 1.0872881412506104,
+      "step": 290
+    },
+    {
+      "epoch": 0.12599784250269688,
+      "grad_norm": 0.6240811944007874,
+      "learning_rate": 5.22911051212938e-05,
+      "loss": 1.110992193222046,
+      "step": 292
+    },
+    {
+      "epoch": 0.1268608414239482,
+      "grad_norm": 0.7172768712043762,
+      "learning_rate": 5.265049415992812e-05,
+      "loss": 1.1109752655029297,
+      "step": 294
+    },
+    {
+      "epoch": 0.12772384034519957,
+      "grad_norm": 0.6442400217056274,
+      "learning_rate": 5.300988319856245e-05,
+      "loss": 1.05553138256073,
+      "step": 296
+    },
+    {
+      "epoch": 0.12858683926645093,
+      "grad_norm": 0.7074702382087708,
+      "learning_rate": 5.3369272237196765e-05,
+      "loss": 1.0717648267745972,
+      "step": 298
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "grad_norm": 0.5277591347694397,
+      "learning_rate": 5.3728661275831095e-05,
+      "loss": 0.9777541756629944,
+      "step": 300
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "eval_loss": 1.0977506637573242,
+      "eval_runtime": 662.1728,
+      "eval_samples_per_second": 3.111,
+      "eval_steps_per_second": 3.111,
+      "step": 300
+    },
+    {
+      "epoch": 0.1303128371089536,
+      "grad_norm": 0.7252246737480164,
+      "learning_rate": 5.408805031446541e-05,
+      "loss": 1.075905203819275,
+      "step": 302
+    },
+    {
+      "epoch": 0.13117583603020497,
+      "grad_norm": 0.7003294229507446,
+      "learning_rate": 5.444743935309974e-05,
+      "loss": 1.1117515563964844,
+      "step": 304
+    },
+    {
+      "epoch": 0.13203883495145632,
+      "grad_norm": 0.5878211259841919,
+      "learning_rate": 5.480682839173406e-05,
+      "loss": 1.0289191007614136,
+      "step": 306
+    },
+    {
+      "epoch": 0.13290183387270765,
+      "grad_norm": 0.7133644223213196,
+      "learning_rate": 5.5166217430368374e-05,
+      "loss": 1.0199183225631714,
+      "step": 308
+    },
+    {
+      "epoch": 0.133764832793959,
+      "grad_norm": 0.6098423600196838,
+      "learning_rate": 5.55256064690027e-05,
+      "loss": 1.0132375955581665,
+      "step": 310
+    },
+    {
+      "epoch": 0.13462783171521037,
+      "grad_norm": 0.6386916041374207,
+      "learning_rate": 5.5884995507637014e-05,
+      "loss": 1.1595754623413086,
+      "step": 312
+    },
+    {
+      "epoch": 0.1354908306364617,
+      "grad_norm": 0.6563469767570496,
+      "learning_rate": 5.6244384546271344e-05,
+      "loss": 1.0921307802200317,
+      "step": 314
+    },
+    {
+      "epoch": 0.13635382955771305,
+      "grad_norm": 0.6388015747070312,
+      "learning_rate": 5.660377358490566e-05,
+      "loss": 1.0200815200805664,
+      "step": 316
+    },
+    {
+      "epoch": 0.1372168284789644,
+      "grad_norm": 0.6026274561882019,
+      "learning_rate": 5.696316262353999e-05,
+      "loss": 0.9339485764503479,
+      "step": 318
+    },
+    {
+      "epoch": 0.13807982740021574,
+      "grad_norm": 0.619800865650177,
+      "learning_rate": 5.732255166217431e-05,
+      "loss": 1.0268478393554688,
+      "step": 320
+    },
+    {
+      "epoch": 0.1389428263214671,
+      "grad_norm": 0.5924715399742126,
+      "learning_rate": 5.768194070080862e-05,
+      "loss": 1.1394236087799072,
+      "step": 322
+    },
+    {
+      "epoch": 0.13980582524271845,
+      "grad_norm": 0.6829012036323547,
+      "learning_rate": 5.804132973944295e-05,
+      "loss": 1.002437949180603,
+      "step": 324
+    },
+    {
+      "epoch": 0.1406688241639698,
+      "grad_norm": 0.7012544274330139,
+      "learning_rate": 5.840071877807727e-05,
+      "loss": 1.132503628730774,
+      "step": 326
+    },
+    {
+      "epoch": 0.14153182308522114,
+      "grad_norm": 0.7921599745750427,
+      "learning_rate": 5.876010781671159e-05,
+      "loss": 1.1859129667282104,
+      "step": 328
+    },
+    {
+      "epoch": 0.1423948220064725,
+      "grad_norm": 0.6373353004455566,
+      "learning_rate": 5.9119496855345916e-05,
+      "loss": 1.0896776914596558,
+      "step": 330
+    },
+    {
+      "epoch": 0.14325782092772385,
+      "grad_norm": 0.6174030900001526,
+      "learning_rate": 5.947888589398024e-05,
+      "loss": 1.0691723823547363,
+      "step": 332
+    },
+    {
+      "epoch": 0.14412081984897518,
+      "grad_norm": 0.5110617280006409,
+      "learning_rate": 5.9838274932614556e-05,
+      "loss": 1.0144777297973633,
+      "step": 334
+    },
+    {
+      "epoch": 0.14498381877022654,
+      "grad_norm": 0.5580511093139648,
+      "learning_rate": 6.019766397124887e-05,
+      "loss": 0.9955101609230042,
+      "step": 336
+    },
+    {
+      "epoch": 0.1458468176914779,
+      "grad_norm": 0.6427345275878906,
+      "learning_rate": 6.05570530098832e-05,
+      "loss": 0.9863013625144958,
+      "step": 338
+    },
+    {
+      "epoch": 0.14670981661272922,
+      "grad_norm": 0.7464537024497986,
+      "learning_rate": 6.091644204851752e-05,
+      "loss": 1.0682255029678345,
+      "step": 340
+    },
+    {
+      "epoch": 0.14757281553398058,
+      "grad_norm": 0.599926769733429,
+      "learning_rate": 6.127583108715184e-05,
+      "loss": 1.034083366394043,
+      "step": 342
+    },
+    {
+      "epoch": 0.14843581445523193,
+      "grad_norm": 0.6320257186889648,
+      "learning_rate": 6.163522012578616e-05,
+      "loss": 1.0776089429855347,
+      "step": 344
+    },
+    {
+      "epoch": 0.1492988133764833,
+      "grad_norm": 0.6565091013908386,
+      "learning_rate": 6.199460916442049e-05,
+      "loss": 1.0493087768554688,
+      "step": 346
+    },
+    {
+      "epoch": 0.15016181229773462,
+      "grad_norm": 0.6512171626091003,
+      "learning_rate": 6.23539982030548e-05,
+      "loss": 1.0469218492507935,
+      "step": 348
+    },
+    {
+      "epoch": 0.15102481121898598,
+      "grad_norm": 0.8487282991409302,
+      "learning_rate": 6.271338724168913e-05,
+      "loss": 1.0985081195831299,
+      "step": 350
+    },
+    {
+      "epoch": 0.15188781014023733,
+      "grad_norm": 0.6718961596488953,
+      "learning_rate": 6.307277628032345e-05,
+      "loss": 1.0714176893234253,
+      "step": 352
+    },
+    {
+      "epoch": 0.15275080906148866,
+      "grad_norm": 0.8175088167190552,
+      "learning_rate": 6.343216531895777e-05,
+      "loss": 1.0599322319030762,
+      "step": 354
+    },
+    {
+      "epoch": 0.15361380798274002,
+      "grad_norm": 0.6359215378761292,
+      "learning_rate": 6.37915543575921e-05,
+      "loss": 0.9268131256103516,
+      "step": 356
+    },
+    {
+      "epoch": 0.15447680690399138,
+      "grad_norm": 0.6423866748809814,
+      "learning_rate": 6.415094339622641e-05,
+      "loss": 0.9838354587554932,
+      "step": 358
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "grad_norm": 0.6496716737747192,
+      "learning_rate": 6.451033243486074e-05,
+      "loss": 1.048566460609436,
+      "step": 360
+    },
+    {
+      "epoch": 0.15620280474649406,
+      "grad_norm": 0.6536920666694641,
+      "learning_rate": 6.486972147349506e-05,
+      "loss": 1.0910537242889404,
+      "step": 362
+    },
+    {
+      "epoch": 0.15706580366774542,
+      "grad_norm": 0.5832068920135498,
+      "learning_rate": 6.522911051212939e-05,
+      "loss": 0.9971448183059692,
+      "step": 364
+    },
+    {
+      "epoch": 0.15792880258899678,
+      "grad_norm": 0.6647719144821167,
+      "learning_rate": 6.558849955076371e-05,
+      "loss": 1.0496708154678345,
+      "step": 366
+    },
+    {
+      "epoch": 0.1587918015102481,
+      "grad_norm": 0.623252809047699,
+      "learning_rate": 6.594788858939802e-05,
+      "loss": 0.955894410610199,
+      "step": 368
+    },
+    {
+      "epoch": 0.15965480043149946,
+      "grad_norm": 0.6311860084533691,
+      "learning_rate": 6.630727762803235e-05,
+      "loss": 1.1304032802581787,
+      "step": 370
+    },
+    {
+      "epoch": 0.16051779935275082,
+      "grad_norm": 0.5306481122970581,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.8746405243873596,
+      "step": 372
+    },
+    {
+      "epoch": 0.16138079827400215,
+      "grad_norm": 0.6249631643295288,
+      "learning_rate": 6.7026055705301e-05,
+      "loss": 0.9104986786842346,
+      "step": 374
+    },
+    {
+      "epoch": 0.1622437971952535,
+      "grad_norm": 0.6243219971656799,
+      "learning_rate": 6.738544474393532e-05,
+      "loss": 1.043666124343872,
+      "step": 376
+    },
+    {
+      "epoch": 0.16310679611650486,
+      "grad_norm": 0.6833282113075256,
+      "learning_rate": 6.774483378256963e-05,
+      "loss": 1.0504906177520752,
+      "step": 378
+    },
+    {
+      "epoch": 0.16396979503775622,
+      "grad_norm": 0.7124452590942383,
+      "learning_rate": 6.810422282120395e-05,
+      "loss": 1.0608166456222534,
+      "step": 380
+    },
+    {
+      "epoch": 0.16483279395900755,
+      "grad_norm": 0.7520908117294312,
+      "learning_rate": 6.846361185983828e-05,
+      "loss": 1.1653732061386108,
+      "step": 382
+    },
+    {
+      "epoch": 0.1656957928802589,
+      "grad_norm": 0.7121814489364624,
+      "learning_rate": 6.88230008984726e-05,
+      "loss": 1.0626367330551147,
+      "step": 384
+    },
+    {
+      "epoch": 0.16655879180151026,
+      "grad_norm": 0.6825008988380432,
+      "learning_rate": 6.918238993710691e-05,
+      "loss": 1.012121319770813,
+      "step": 386
+    },
+    {
+      "epoch": 0.1674217907227616,
+      "grad_norm": 0.4922940135002136,
+      "learning_rate": 6.954177897574124e-05,
+      "loss": 1.0576211214065552,
+      "step": 388
+    },
+    {
+      "epoch": 0.16828478964401294,
+      "grad_norm": 0.6122089624404907,
+      "learning_rate": 6.990116801437556e-05,
+      "loss": 1.03916597366333,
+      "step": 390
+    },
+    {
+      "epoch": 0.1691477885652643,
+      "grad_norm": 0.6348981261253357,
+      "learning_rate": 7.026055705300989e-05,
+      "loss": 1.17647123336792,
+      "step": 392
+    },
+    {
+      "epoch": 0.17001078748651563,
+      "grad_norm": 0.6205878257751465,
+      "learning_rate": 7.06199460916442e-05,
+      "loss": 0.9095983505249023,
+      "step": 394
+    },
+    {
+      "epoch": 0.170873786407767,
+      "grad_norm": 0.61506187915802,
+      "learning_rate": 7.097933513027853e-05,
+      "loss": 1.082506775856018,
+      "step": 396
+    },
+    {
+      "epoch": 0.17173678532901834,
+      "grad_norm": 0.6481751799583435,
+      "learning_rate": 7.133872416891285e-05,
+      "loss": 1.0716280937194824,
+      "step": 398
+    },
+    {
+      "epoch": 0.1725997842502697,
+      "grad_norm": 0.4871014952659607,
+      "learning_rate": 7.169811320754717e-05,
+      "loss": 0.9616814851760864,
+      "step": 400
+    },
+    {
+      "epoch": 0.1725997842502697,
+      "eval_loss": 1.0649415254592896,
+      "eval_runtime": 668.6025,
+      "eval_samples_per_second": 3.081,
+      "eval_steps_per_second": 3.081,
+      "step": 400
+    },
+    {
+      "epoch": 0.17346278317152103,
+      "grad_norm": 0.5680040121078491,
+      "learning_rate": 7.20575022461815e-05,
+      "loss": 1.0475050210952759,
+      "step": 402
+    },
+    {
+      "epoch": 0.17432578209277239,
+      "grad_norm": 0.6417813897132874,
+      "learning_rate": 7.241689128481581e-05,
+      "loss": 0.9851161241531372,
+      "step": 404
+    },
+    {
+      "epoch": 0.17518878101402374,
+      "grad_norm": 0.6600468158721924,
+      "learning_rate": 7.277628032345014e-05,
+      "loss": 1.013339638710022,
+      "step": 406
+    },
+    {
+      "epoch": 0.17605177993527507,
+      "grad_norm": 0.6733932495117188,
+      "learning_rate": 7.313566936208446e-05,
+      "loss": 0.9346804022789001,
+      "step": 408
+    },
+    {
+      "epoch": 0.17691477885652643,
+      "grad_norm": 0.6812151074409485,
+      "learning_rate": 7.349505840071879e-05,
+      "loss": 0.9890368580818176,
+      "step": 410
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.6380394697189331,
+      "learning_rate": 7.385444743935311e-05,
+      "loss": 0.8787848949432373,
+      "step": 412
+    },
+    {
+      "epoch": 0.1786407766990291,
+      "grad_norm": 0.6004905700683594,
+      "learning_rate": 7.421383647798742e-05,
+      "loss": 1.0235728025436401,
+      "step": 414
+    },
+    {
+      "epoch": 0.17950377562028047,
+      "grad_norm": 0.6569193005561829,
+      "learning_rate": 7.457322551662175e-05,
+      "loss": 0.9972385168075562,
+      "step": 416
+    },
+    {
+      "epoch": 0.18036677454153183,
+      "grad_norm": 0.6761631369590759,
+      "learning_rate": 7.493261455525607e-05,
+      "loss": 0.9593698382377625,
+      "step": 418
+    },
+    {
+      "epoch": 0.18122977346278318,
+      "grad_norm": 0.7328561544418335,
+      "learning_rate": 7.529200359389039e-05,
+      "loss": 1.0426853895187378,
+      "step": 420
+    },
+    {
+      "epoch": 0.1820927723840345,
+      "grad_norm": 0.6256070137023926,
+      "learning_rate": 7.56513926325247e-05,
+      "loss": 0.9608182311058044,
+      "step": 422
+    },
+    {
+      "epoch": 0.18295577130528587,
+      "grad_norm": 1.2549844980239868,
+      "learning_rate": 7.601078167115903e-05,
+      "loss": 1.0162668228149414,
+      "step": 424
+    },
+    {
+      "epoch": 0.18381877022653723,
+      "grad_norm": 0.6751510500907898,
+      "learning_rate": 7.637017070979335e-05,
+      "loss": 1.130725383758545,
+      "step": 426
+    },
+    {
+      "epoch": 0.18468176914778855,
+      "grad_norm": 0.7029808163642883,
+      "learning_rate": 7.672955974842768e-05,
+      "loss": 1.0384817123413086,
+      "step": 428
+    },
+    {
+      "epoch": 0.1855447680690399,
+      "grad_norm": 0.644353449344635,
+      "learning_rate": 7.7088948787062e-05,
+      "loss": 1.017020344734192,
+      "step": 430
+    },
+    {
+      "epoch": 0.18640776699029127,
+      "grad_norm": 0.6784916520118713,
+      "learning_rate": 7.744833782569631e-05,
+      "loss": 1.005354404449463,
+      "step": 432
+    },
+    {
+      "epoch": 0.1872707659115426,
+      "grad_norm": 0.5989449620246887,
+      "learning_rate": 7.780772686433064e-05,
+      "loss": 1.026848316192627,
+      "step": 434
+    },
+    {
+      "epoch": 0.18813376483279395,
+      "grad_norm": 0.6502639651298523,
+      "learning_rate": 7.816711590296496e-05,
+      "loss": 0.9891080856323242,
+      "step": 436
+    },
+    {
+      "epoch": 0.1889967637540453,
+      "grad_norm": 0.6176205277442932,
+      "learning_rate": 7.852650494159929e-05,
+      "loss": 0.966316819190979,
+      "step": 438
+    },
+    {
+      "epoch": 0.18985976267529667,
+      "grad_norm": 0.6801626086235046,
+      "learning_rate": 7.88858939802336e-05,
+      "loss": 1.123063087463379,
+      "step": 440
+    },
+    {
+      "epoch": 0.190722761596548,
+      "grad_norm": 0.6718618273735046,
+      "learning_rate": 7.924528301886794e-05,
+      "loss": 1.0467073917388916,
+      "step": 442
+    },
+    {
+      "epoch": 0.19158576051779935,
+      "grad_norm": 0.6761009097099304,
+      "learning_rate": 7.960467205750225e-05,
+      "loss": 1.0952889919281006,
+      "step": 444
+    },
+    {
+      "epoch": 0.1924487594390507,
+      "grad_norm": 0.6356327533721924,
+      "learning_rate": 7.996406109613657e-05,
+      "loss": 0.954807698726654,
+      "step": 446
+    },
+    {
+      "epoch": 0.19331175836030204,
+      "grad_norm": 0.6798669695854187,
+      "learning_rate": 8.03234501347709e-05,
+      "loss": 0.9941422343254089,
+      "step": 448
+    },
+    {
+      "epoch": 0.1941747572815534,
+      "grad_norm": 0.6511302590370178,
+      "learning_rate": 8.068283917340521e-05,
+      "loss": 1.0351495742797852,
+      "step": 450
+    },
+    {
+      "epoch": 0.19503775620280475,
+      "grad_norm": 0.6061258912086487,
+      "learning_rate": 8.104222821203954e-05,
+      "loss": 1.00546133518219,
+      "step": 452
+    },
+    {
+      "epoch": 0.1959007551240561,
+      "grad_norm": 0.6278533935546875,
+      "learning_rate": 8.140161725067386e-05,
+      "loss": 1.0778460502624512,
+      "step": 454
+    },
+    {
+      "epoch": 0.19676375404530744,
+      "grad_norm": 0.6866298317909241,
+      "learning_rate": 8.176100628930818e-05,
+      "loss": 1.0344486236572266,
+      "step": 456
+    },
+    {
+      "epoch": 0.1976267529665588,
+      "grad_norm": 0.7338075041770935,
+      "learning_rate": 8.212039532794251e-05,
+      "loss": 1.0663033723831177,
+      "step": 458
+    },
+    {
+      "epoch": 0.19848975188781015,
+      "grad_norm": 0.6811459064483643,
+      "learning_rate": 8.247978436657682e-05,
+      "loss": 0.9665339589118958,
+      "step": 460
+    },
+    {
+      "epoch": 0.19935275080906148,
+      "grad_norm": 0.6779627799987793,
+      "learning_rate": 8.283917340521114e-05,
+      "loss": 1.024712324142456,
+      "step": 462
+    },
+    {
+      "epoch": 0.20021574973031284,
+      "grad_norm": 0.6486892700195312,
+      "learning_rate": 8.319856244384546e-05,
+      "loss": 0.9699305295944214,
+      "step": 464
+    },
+    {
+      "epoch": 0.2010787486515642,
+      "grad_norm": 0.7022278308868408,
+      "learning_rate": 8.355795148247979e-05,
+      "loss": 0.9540432095527649,
+      "step": 466
+    },
+    {
+      "epoch": 0.20194174757281552,
+      "grad_norm": 0.5922990441322327,
+      "learning_rate": 8.39173405211141e-05,
+      "loss": 0.9253339767456055,
+      "step": 468
+    },
+    {
+      "epoch": 0.20280474649406688,
+      "grad_norm": 0.7076792120933533,
+      "learning_rate": 8.427672955974843e-05,
+      "loss": 0.9987741112709045,
+      "step": 470
+    },
+    {
+      "epoch": 0.20366774541531824,
+      "grad_norm": 0.6491380333900452,
+      "learning_rate": 8.463611859838275e-05,
+      "loss": 1.0249329805374146,
+      "step": 472
+    },
+    {
+      "epoch": 0.2045307443365696,
+      "grad_norm": 0.6784211993217468,
+      "learning_rate": 8.499550763701708e-05,
+      "loss": 1.0577133893966675,
+      "step": 474
+    },
+    {
+      "epoch": 0.20539374325782092,
+      "grad_norm": 0.6453303694725037,
+      "learning_rate": 8.53548966756514e-05,
+      "loss": 1.1312458515167236,
+      "step": 476
+    },
+    {
+      "epoch": 0.20625674217907228,
+      "grad_norm": 0.7431377172470093,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 1.0592451095581055,
+      "step": 478
+    },
+    {
+      "epoch": 0.20711974110032363,
+      "grad_norm": 0.6097649931907654,
+      "learning_rate": 8.607367475292004e-05,
+      "loss": 0.9337235689163208,
+      "step": 480
+    },
+    {
+      "epoch": 0.20798274002157496,
+      "grad_norm": 0.5693124532699585,
+      "learning_rate": 8.643306379155436e-05,
+      "loss": 0.9088928699493408,
+      "step": 482
+    },
+    {
+      "epoch": 0.20884573894282632,
+      "grad_norm": 0.7377229332923889,
+      "learning_rate": 8.679245283018869e-05,
+      "loss": 1.0729358196258545,
+      "step": 484
+    },
+    {
+      "epoch": 0.20970873786407768,
+      "grad_norm": 0.7399470210075378,
+      "learning_rate": 8.7151841868823e-05,
+      "loss": 1.0428457260131836,
+      "step": 486
+    },
+    {
+      "epoch": 0.210571736785329,
+      "grad_norm": 0.677052915096283,
+      "learning_rate": 8.751123090745734e-05,
+      "loss": 0.9940266013145447,
+      "step": 488
+    },
+    {
+      "epoch": 0.21143473570658036,
+      "grad_norm": 0.7126721739768982,
+      "learning_rate": 8.787061994609165e-05,
+      "loss": 1.011808156967163,
+      "step": 490
+    },
+    {
+      "epoch": 0.21229773462783172,
+      "grad_norm": 0.6663792729377747,
+      "learning_rate": 8.823000898472597e-05,
+      "loss": 1.0054185390472412,
+      "step": 492
+    },
+    {
+      "epoch": 0.21316073354908308,
+      "grad_norm": 0.6661092042922974,
+      "learning_rate": 8.85893980233603e-05,
+      "loss": 1.0167138576507568,
+      "step": 494
+    },
+    {
+      "epoch": 0.2140237324703344,
+      "grad_norm": 0.6975740194320679,
+      "learning_rate": 8.894878706199461e-05,
+      "loss": 1.1470818519592285,
+      "step": 496
+    },
+    {
+      "epoch": 0.21488673139158576,
+      "grad_norm": 0.6594390869140625,
+      "learning_rate": 8.930817610062893e-05,
+      "loss": 0.9619631171226501,
+      "step": 498
+    },
+    {
+      "epoch": 0.21574973031283712,
+      "grad_norm": 0.7216679453849792,
+      "learning_rate": 8.966756513926325e-05,
+      "loss": 0.9971368312835693,
+      "step": 500
+    },
+    {
+      "epoch": 0.21574973031283712,
+      "eval_loss": 1.0417571067810059,
+      "eval_runtime": 659.3112,
+      "eval_samples_per_second": 3.124,
+      "eval_steps_per_second": 3.124,
+      "step": 500
+    },
+    {
+      "epoch": 0.21661272923408845,
+      "grad_norm": 0.6188210844993591,
+      "learning_rate": 9.002695417789758e-05,
+      "loss": 1.0307213068008423,
+      "step": 502
+    },
+    {
+      "epoch": 0.2174757281553398,
+      "grad_norm": 0.6716445088386536,
+      "learning_rate": 9.03863432165319e-05,
+      "loss": 1.0188794136047363,
+      "step": 504
+    },
+    {
+      "epoch": 0.21833872707659116,
+      "grad_norm": 0.6790863275527954,
+      "learning_rate": 9.074573225516622e-05,
+      "loss": 0.9764845967292786,
+      "step": 506
+    },
+    {
+      "epoch": 0.2192017259978425,
+      "grad_norm": 0.6764960289001465,
+      "learning_rate": 9.110512129380054e-05,
+      "loss": 0.948829174041748,
+      "step": 508
+    },
+    {
+      "epoch": 0.22006472491909385,
+      "grad_norm": 0.6210965514183044,
+      "learning_rate": 9.146451033243486e-05,
+      "loss": 1.008013129234314,
+      "step": 510
+    },
+    {
+      "epoch": 0.2209277238403452,
+      "grad_norm": 0.7739297747612,
+      "learning_rate": 9.182389937106919e-05,
+      "loss": 1.1662557125091553,
+      "step": 512
+    },
+    {
+      "epoch": 0.22179072276159656,
+      "grad_norm": 0.7055562138557434,
+      "learning_rate": 9.21832884097035e-05,
+      "loss": 1.0325161218643188,
+      "step": 514
+    },
+    {
+      "epoch": 0.2226537216828479,
+      "grad_norm": 0.6079210042953491,
+      "learning_rate": 9.254267744833783e-05,
+      "loss": 1.00056791305542,
+      "step": 516
+    },
+    {
+      "epoch": 0.22351672060409924,
+      "grad_norm": 0.5974318981170654,
+      "learning_rate": 9.290206648697215e-05,
+      "loss": 0.9422364234924316,
+      "step": 518
+    },
+    {
+      "epoch": 0.2243797195253506,
+      "grad_norm": 0.5963430404663086,
+      "learning_rate": 9.326145552560648e-05,
+      "loss": 0.936336100101471,
+      "step": 520
+    },
+    {
+      "epoch": 0.22524271844660193,
+      "grad_norm": 0.6823658347129822,
+      "learning_rate": 9.36208445642408e-05,
+      "loss": 1.0538607835769653,
+      "step": 522
+    },
+    {
+      "epoch": 0.2261057173678533,
+      "grad_norm": 0.6409855484962463,
+      "learning_rate": 9.398023360287511e-05,
+      "loss": 1.0483653545379639,
+      "step": 524
+    },
+    {
+      "epoch": 0.22696871628910464,
+      "grad_norm": 0.6867254376411438,
+      "learning_rate": 9.433962264150944e-05,
+      "loss": 0.9668049812316895,
+      "step": 526
+    },
+    {
+      "epoch": 0.227831715210356,
+      "grad_norm": 0.5690792798995972,
+      "learning_rate": 9.469901168014376e-05,
+      "loss": 1.008763313293457,
+      "step": 528
+    },
+    {
+      "epoch": 0.22869471413160733,
+      "grad_norm": 0.5964897274971008,
+      "learning_rate": 9.505840071877809e-05,
+      "loss": 1.0816441774368286,
+      "step": 530
+    },
+    {
+      "epoch": 0.2295577130528587,
+      "grad_norm": 0.627419114112854,
+      "learning_rate": 9.54177897574124e-05,
+      "loss": 0.9265700578689575,
+      "step": 532
+    },
+    {
+      "epoch": 0.23042071197411004,
+      "grad_norm": 0.5862151980400085,
+      "learning_rate": 9.577717879604674e-05,
+      "loss": 0.9804646372795105,
+      "step": 534
+    },
+    {
+      "epoch": 0.23128371089536137,
+      "grad_norm": 0.5573718547821045,
+      "learning_rate": 9.613656783468105e-05,
+      "loss": 0.9627988934516907,
+      "step": 536
+    },
+    {
+      "epoch": 0.23214670981661273,
+      "grad_norm": 0.6705166101455688,
+      "learning_rate": 9.649595687331537e-05,
+      "loss": 1.0012824535369873,
+      "step": 538
+    },
+    {
+      "epoch": 0.23300970873786409,
+      "grad_norm": 0.6251236796379089,
+      "learning_rate": 9.685534591194969e-05,
+      "loss": 0.9568162560462952,
+      "step": 540
+    },
+    {
+      "epoch": 0.23387270765911541,
+      "grad_norm": 0.6466493010520935,
+      "learning_rate": 9.7214734950584e-05,
+      "loss": 1.031549334526062,
+      "step": 542
+    },
+    {
+      "epoch": 0.23473570658036677,
+      "grad_norm": 0.5183866024017334,
+      "learning_rate": 9.757412398921833e-05,
+      "loss": 0.8603643774986267,
+      "step": 544
+    },
+    {
+      "epoch": 0.23559870550161813,
+      "grad_norm": 0.6725775599479675,
+      "learning_rate": 9.793351302785265e-05,
+      "loss": 1.0365077257156372,
+      "step": 546
+    },
+    {
+      "epoch": 0.23646170442286948,
+      "grad_norm": 0.5972357988357544,
+      "learning_rate": 9.829290206648698e-05,
+      "loss": 0.9304701089859009,
+      "step": 548
+    },
+    {
+      "epoch": 0.2373247033441208,
+      "grad_norm": 0.5319957733154297,
+      "learning_rate": 9.86522911051213e-05,
+      "loss": 0.9575805068016052,
+      "step": 550
+    },
+    {
+      "epoch": 0.23818770226537217,
+      "grad_norm": 0.6502835750579834,
+      "learning_rate": 9.901168014375562e-05,
+      "loss": 1.0307214260101318,
+      "step": 552
+    },
+    {
+      "epoch": 0.23905070118662353,
+      "grad_norm": 0.6734047532081604,
+      "learning_rate": 9.937106918238994e-05,
+      "loss": 1.05185067653656,
+      "step": 554
+    },
+    {
+      "epoch": 0.23991370010787486,
+      "grad_norm": 0.5667978525161743,
+      "learning_rate": 9.973045822102426e-05,
+      "loss": 1.0190176963806152,
+      "step": 556
+    },
+    {
+      "epoch": 0.2407766990291262,
+      "grad_norm": 0.6370418667793274,
+      "learning_rate": 0.00010008984725965857,
+      "loss": 1.076182246208191,
+      "step": 558
+    },
+    {
+      "epoch": 0.24163969795037757,
+      "grad_norm": 0.689719021320343,
+      "learning_rate": 0.0001004492362982929,
+      "loss": 1.0408724546432495,
+      "step": 560
+    },
+    {
+      "epoch": 0.2425026968716289,
+      "grad_norm": 0.6304254531860352,
+      "learning_rate": 0.00010080862533692723,
+      "loss": 0.9869902729988098,
+      "step": 562
+    },
+    {
+      "epoch": 0.24336569579288025,
+      "grad_norm": 0.6797420382499695,
+      "learning_rate": 0.00010116801437556156,
+      "loss": 1.0198370218276978,
+      "step": 564
+    },
+    {
+      "epoch": 0.2442286947141316,
+      "grad_norm": 0.5993657112121582,
+      "learning_rate": 0.00010152740341419587,
+      "loss": 0.9947441816329956,
+      "step": 566
+    },
+    {
+      "epoch": 0.24509169363538297,
+      "grad_norm": 0.6369836330413818,
+      "learning_rate": 0.0001018867924528302,
+      "loss": 0.9722896814346313,
+      "step": 568
+    },
+    {
+      "epoch": 0.2459546925566343,
+      "grad_norm": 0.6942457556724548,
+      "learning_rate": 0.00010224618149146453,
+      "loss": 0.9716570973396301,
+      "step": 570
+    },
+    {
+      "epoch": 0.24681769147788565,
+      "grad_norm": 0.5403370261192322,
+      "learning_rate": 0.00010260557053009883,
+      "loss": 0.9797524213790894,
+      "step": 572
+    },
+    {
+      "epoch": 0.247680690399137,
+      "grad_norm": 0.5207529067993164,
+      "learning_rate": 0.00010296495956873316,
+      "loss": 0.985367476940155,
+      "step": 574
+    },
+    {
+      "epoch": 0.24854368932038834,
+      "grad_norm": 0.6751103401184082,
+      "learning_rate": 0.00010332434860736748,
+      "loss": 1.075042724609375,
+      "step": 576
+    },
+    {
+      "epoch": 0.2494066882416397,
+      "grad_norm": 0.565331220626831,
+      "learning_rate": 0.0001036837376460018,
+      "loss": 0.9273878335952759,
+      "step": 578
+    },
+    {
+      "epoch": 0.25026968716289105,
+      "grad_norm": 0.6858948469161987,
+      "learning_rate": 0.00010404312668463612,
+      "loss": 0.9872279763221741,
+      "step": 580
+    },
+    {
+      "epoch": 0.2511326860841424,
+      "grad_norm": 0.7091426253318787,
+      "learning_rate": 0.00010440251572327044,
+      "loss": 1.0038671493530273,
+      "step": 582
+    },
+    {
+      "epoch": 0.25199568500539377,
+      "grad_norm": 0.6493771076202393,
+      "learning_rate": 0.00010476190476190477,
+      "loss": 1.0109868049621582,
+      "step": 584
+    },
+    {
+      "epoch": 0.25285868392664507,
+      "grad_norm": 0.6107586622238159,
+      "learning_rate": 0.00010512129380053907,
+      "loss": 1.0020402669906616,
+      "step": 586
+    },
+    {
+      "epoch": 0.2537216828478964,
+      "grad_norm": 0.6878048181533813,
+      "learning_rate": 0.0001054806828391734,
+      "loss": 0.961039662361145,
+      "step": 588
+    },
+    {
+      "epoch": 0.2545846817691478,
+      "grad_norm": 0.664034903049469,
+      "learning_rate": 0.00010584007187780773,
+      "loss": 0.9725209474563599,
+      "step": 590
+    },
+    {
+      "epoch": 0.25544768069039914,
+      "grad_norm": 0.6399680376052856,
+      "learning_rate": 0.00010619946091644206,
+      "loss": 0.9907437562942505,
+      "step": 592
+    },
+    {
+      "epoch": 0.2563106796116505,
+      "grad_norm": 0.6163286566734314,
+      "learning_rate": 0.00010655884995507636,
+      "loss": 0.9650095701217651,
+      "step": 594
+    },
+    {
+      "epoch": 0.25717367853290185,
+      "grad_norm": 0.6008322238922119,
+      "learning_rate": 0.0001069182389937107,
+      "loss": 1.0102758407592773,
+      "step": 596
+    },
+    {
+      "epoch": 0.2580366774541532,
+      "grad_norm": 0.6752071380615234,
+      "learning_rate": 0.00010727762803234502,
+      "loss": 0.9101885557174683,
+      "step": 598
+    },
+    {
+      "epoch": 0.2588996763754045,
+      "grad_norm": 0.6789175868034363,
+      "learning_rate": 0.00010763701707097935,
+      "loss": 1.0461398363113403,
+      "step": 600
+    },
+    {
+      "epoch": 0.2588996763754045,
+      "eval_loss": 1.021111011505127,
+      "eval_runtime": 648.1611,
+      "eval_samples_per_second": 3.178,
+      "eval_steps_per_second": 3.178,
+      "step": 600
+    },
+    {
+      "epoch": 0.25976267529665586,
+      "grad_norm": 0.5660730600357056,
+      "learning_rate": 0.00010799640610961366,
+      "loss": 0.9582418203353882,
+      "step": 602
+    },
+    {
+      "epoch": 0.2606256742179072,
+      "grad_norm": 0.6726544499397278,
+      "learning_rate": 0.00010835579514824799,
+      "loss": 1.0763746500015259,
+      "step": 604
+    },
+    {
+      "epoch": 0.2614886731391586,
+      "grad_norm": 0.6068508625030518,
+      "learning_rate": 0.00010871518418688232,
+      "loss": 1.0432032346725464,
+      "step": 606
+    },
+    {
+      "epoch": 0.26235167206040994,
+      "grad_norm": 0.5731637477874756,
+      "learning_rate": 0.00010907457322551662,
+      "loss": 0.9830516576766968,
+      "step": 608
+    },
+    {
+      "epoch": 0.2632146709816613,
+      "grad_norm": 0.6777567267417908,
+      "learning_rate": 0.00010943396226415095,
+      "loss": 1.0442042350769043,
+      "step": 610
+    },
+    {
+      "epoch": 0.26407766990291265,
+      "grad_norm": 0.6372506618499756,
+      "learning_rate": 0.00010979335130278528,
+      "loss": 1.0001944303512573,
+      "step": 612
+    },
+    {
+      "epoch": 0.26494066882416395,
+      "grad_norm": 0.6606221795082092,
+      "learning_rate": 0.0001101527403414196,
+      "loss": 1.035884141921997,
+      "step": 614
+    },
+    {
+      "epoch": 0.2658036677454153,
+      "grad_norm": 0.6083229780197144,
+      "learning_rate": 0.00011051212938005391,
+      "loss": 0.9403397440910339,
+      "step": 616
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.6318517923355103,
+      "learning_rate": 0.00011087151841868823,
+      "loss": 0.9274454116821289,
+      "step": 618
+    },
+    {
+      "epoch": 0.267529665587918,
+      "grad_norm": 0.628190279006958,
+      "learning_rate": 0.00011123090745732256,
+      "loss": 0.9883754253387451,
+      "step": 620
+    },
+    {
+      "epoch": 0.2683926645091694,
+      "grad_norm": 0.5961961150169373,
+      "learning_rate": 0.00011159029649595688,
+      "loss": 1.0317535400390625,
+      "step": 622
+    },
+    {
+      "epoch": 0.26925566343042073,
+      "grad_norm": 0.5995341539382935,
+      "learning_rate": 0.00011194968553459119,
+      "loss": 0.9776126742362976,
+      "step": 624
+    },
+    {
+      "epoch": 0.27011866235167203,
+      "grad_norm": 0.6639334559440613,
+      "learning_rate": 0.00011230907457322552,
+      "loss": 1.0112378597259521,
+      "step": 626
+    },
+    {
+      "epoch": 0.2709816612729234,
+      "grad_norm": 0.6348621249198914,
+      "learning_rate": 0.00011266846361185985,
+      "loss": 1.0553804636001587,
+      "step": 628
+    },
+    {
+      "epoch": 0.27184466019417475,
+      "grad_norm": 0.5929805040359497,
+      "learning_rate": 0.00011302785265049416,
+      "loss": 1.025888442993164,
+      "step": 630
+    },
+    {
+      "epoch": 0.2727076591154261,
+      "grad_norm": 0.6052366495132446,
+      "learning_rate": 0.00011338724168912849,
+      "loss": 1.02956223487854,
+      "step": 632
+    },
+    {
+      "epoch": 0.27357065803667746,
+      "grad_norm": 0.6494882106781006,
+      "learning_rate": 0.00011374663072776282,
+      "loss": 0.989752471446991,
+      "step": 634
+    },
+    {
+      "epoch": 0.2744336569579288,
+      "grad_norm": 0.6005767583847046,
+      "learning_rate": 0.00011410601976639712,
+      "loss": 1.0030683279037476,
+      "step": 636
+    },
+    {
+      "epoch": 0.2752966558791802,
+      "grad_norm": 0.6478356122970581,
+      "learning_rate": 0.00011446540880503145,
+      "loss": 1.002000093460083,
+      "step": 638
+    },
+    {
+      "epoch": 0.2761596548004315,
+      "grad_norm": 0.5804725289344788,
+      "learning_rate": 0.00011482479784366578,
+      "loss": 0.9807654023170471,
+      "step": 640
+    },
+    {
+      "epoch": 0.27702265372168283,
+      "grad_norm": 0.632530689239502,
+      "learning_rate": 0.00011518418688230011,
+      "loss": 0.9841892123222351,
+      "step": 642
+    },
+    {
+      "epoch": 0.2778856526429342,
+      "grad_norm": 0.5340113639831543,
+      "learning_rate": 0.00011554357592093441,
+      "loss": 0.8902478814125061,
+      "step": 644
+    },
+    {
+      "epoch": 0.27874865156418555,
+      "grad_norm": 0.5901665091514587,
+      "learning_rate": 0.00011590296495956874,
+      "loss": 0.9019404649734497,
+      "step": 646
+    },
+    {
+      "epoch": 0.2796116504854369,
+      "grad_norm": 0.666589617729187,
+      "learning_rate": 0.00011626235399820307,
+      "loss": 0.9384423494338989,
+      "step": 648
+    },
+    {
+      "epoch": 0.28047464940668826,
+      "grad_norm": 0.7000334858894348,
+      "learning_rate": 0.00011662174303683737,
+      "loss": 1.0666629076004028,
+      "step": 650
+    },
+    {
+      "epoch": 0.2813376483279396,
+      "grad_norm": 0.663663923740387,
+      "learning_rate": 0.0001169811320754717,
+      "loss": 1.000019907951355,
+      "step": 652
+    },
+    {
+      "epoch": 0.2822006472491909,
+      "grad_norm": 0.6097694039344788,
+      "learning_rate": 0.00011734052111410603,
+      "loss": 0.9450293183326721,
+      "step": 654
+    },
+    {
+      "epoch": 0.2830636461704423,
+      "grad_norm": 0.6130967140197754,
+      "learning_rate": 0.00011769991015274035,
+      "loss": 0.9480894207954407,
+      "step": 656
+    },
+    {
+      "epoch": 0.28392664509169363,
+      "grad_norm": 0.7091249227523804,
+      "learning_rate": 0.00011805929919137467,
+      "loss": 1.1377143859863281,
+      "step": 658
+    },
+    {
+      "epoch": 0.284789644012945,
+      "grad_norm": 0.6556766629219055,
+      "learning_rate": 0.00011841868823000898,
+      "loss": 0.9421243667602539,
+      "step": 660
+    },
+    {
+      "epoch": 0.28565264293419634,
+      "grad_norm": 0.6682968735694885,
+      "learning_rate": 0.00011877807726864331,
+      "loss": 0.9726828336715698,
+      "step": 662
+    },
+    {
+      "epoch": 0.2865156418554477,
+      "grad_norm": 0.5224708914756775,
+      "learning_rate": 0.00011913746630727762,
+      "loss": 0.8996511697769165,
+      "step": 664
+    },
+    {
+      "epoch": 0.287378640776699,
+      "grad_norm": 0.5914195775985718,
+      "learning_rate": 0.00011949685534591195,
+      "loss": 0.9679517149925232,
+      "step": 666
+    },
+    {
+      "epoch": 0.28824163969795036,
+      "grad_norm": 0.6175519824028015,
+      "learning_rate": 0.00011985624438454628,
+      "loss": 0.8743209838867188,
+      "step": 668
+    },
+    {
+      "epoch": 0.2891046386192017,
+      "grad_norm": 0.6019226312637329,
+      "learning_rate": 0.0001202156334231806,
+      "loss": 0.9741992354393005,
+      "step": 670
+    },
+    {
+      "epoch": 0.28996763754045307,
+      "grad_norm": 0.6080542206764221,
+      "learning_rate": 0.00012057502246181491,
+      "loss": 0.9516472816467285,
+      "step": 672
+    },
+    {
+      "epoch": 0.29083063646170443,
+      "grad_norm": 0.5885615944862366,
+      "learning_rate": 0.00012093441150044924,
+      "loss": 1.122761607170105,
+      "step": 674
+    },
+    {
+      "epoch": 0.2916936353829558,
+      "grad_norm": 0.6635209918022156,
+      "learning_rate": 0.00012129380053908357,
+      "loss": 1.0105189085006714,
+      "step": 676
+    },
+    {
+      "epoch": 0.29255663430420714,
+      "grad_norm": 0.5805009007453918,
+      "learning_rate": 0.0001216531895777179,
+      "loss": 0.906292200088501,
+      "step": 678
+    },
+    {
+      "epoch": 0.29341963322545844,
+      "grad_norm": 0.5980029702186584,
+      "learning_rate": 0.0001220125786163522,
+      "loss": 1.009568691253662,
+      "step": 680
+    },
+    {
+      "epoch": 0.2942826321467098,
+      "grad_norm": 0.6797705292701721,
+      "learning_rate": 0.00012237196765498652,
+      "loss": 1.0373667478561401,
+      "step": 682
+    },
+    {
+      "epoch": 0.29514563106796116,
+      "grad_norm": 0.6280547976493835,
+      "learning_rate": 0.00012273135669362085,
+      "loss": 0.9758188724517822,
+      "step": 684
+    },
+    {
+      "epoch": 0.2960086299892125,
+      "grad_norm": 0.511608898639679,
+      "learning_rate": 0.00012309074573225515,
+      "loss": 0.9111692905426025,
+      "step": 686
+    },
+    {
+      "epoch": 0.29687162891046387,
+      "grad_norm": 0.5781835317611694,
+      "learning_rate": 0.00012345013477088948,
+      "loss": 0.8865921497344971,
+      "step": 688
+    },
+    {
+      "epoch": 0.2977346278317152,
+      "grad_norm": 0.6514166593551636,
+      "learning_rate": 0.0001238095238095238,
+      "loss": 0.9768189191818237,
+      "step": 690
+    },
+    {
+      "epoch": 0.2985976267529666,
+      "grad_norm": 0.6109189987182617,
+      "learning_rate": 0.00012416891284815814,
+      "loss": 0.9991607069969177,
+      "step": 692
+    },
+    {
+      "epoch": 0.2994606256742179,
+      "grad_norm": 0.6598902344703674,
+      "learning_rate": 0.00012452830188679244,
+      "loss": 0.9548360705375671,
+      "step": 694
+    },
+    {
+      "epoch": 0.30032362459546924,
+      "grad_norm": 0.5633156895637512,
+      "learning_rate": 0.00012488769092542677,
+      "loss": 0.992988109588623,
+      "step": 696
+    },
+    {
+      "epoch": 0.3011866235167206,
+      "grad_norm": 0.6098802089691162,
+      "learning_rate": 0.0001252470799640611,
+      "loss": 0.9709890484809875,
+      "step": 698
+    },
+    {
+      "epoch": 0.30204962243797195,
+      "grad_norm": 0.6197102665901184,
+      "learning_rate": 0.0001256064690026954,
+      "loss": 1.018282175064087,
+      "step": 700
+    },
+    {
+      "epoch": 0.30204962243797195,
+      "eval_loss": 1.0030721426010132,
+      "eval_runtime": 655.4533,
+      "eval_samples_per_second": 3.143,
+      "eval_steps_per_second": 3.143,
+      "step": 700
+    },
+    {
+      "epoch": 0.3029126213592233,
+      "grad_norm": 0.5817480683326721,
+      "learning_rate": 0.00012596585804132974,
+      "loss": 0.9147283434867859,
+      "step": 702
+    },
+    {
+      "epoch": 0.30377562028047467,
+      "grad_norm": 0.5976696014404297,
+      "learning_rate": 0.00012632524707996407,
+      "loss": 0.9318362474441528,
+      "step": 704
+    },
+    {
+      "epoch": 0.304638619201726,
+      "grad_norm": 0.6389723420143127,
+      "learning_rate": 0.0001266846361185984,
+      "loss": 0.9500927925109863,
+      "step": 706
+    },
+    {
+      "epoch": 0.3055016181229773,
+      "grad_norm": 0.6485719084739685,
+      "learning_rate": 0.0001270440251572327,
+      "loss": 1.0271424055099487,
+      "step": 708
+    },
+    {
+      "epoch": 0.3063646170442287,
+      "grad_norm": 0.5802455544471741,
+      "learning_rate": 0.00012740341419586703,
+      "loss": 0.9781906008720398,
+      "step": 710
+    },
+    {
+      "epoch": 0.30722761596548004,
+      "grad_norm": 0.6359356641769409,
+      "learning_rate": 0.00012776280323450136,
+      "loss": 1.0195324420928955,
+      "step": 712
+    },
+    {
+      "epoch": 0.3080906148867314,
+      "grad_norm": 0.5975426435470581,
+      "learning_rate": 0.00012812219227313566,
+      "loss": 0.9250738024711609,
+      "step": 714
+    },
+    {
+      "epoch": 0.30895361380798275,
+      "grad_norm": 0.643110454082489,
+      "learning_rate": 0.00012848158131177,
+      "loss": 0.9888015985488892,
+      "step": 716
+    },
+    {
+      "epoch": 0.3098166127292341,
+      "grad_norm": 0.6043205261230469,
+      "learning_rate": 0.00012884097035040432,
+      "loss": 0.9709514379501343,
+      "step": 718
+    },
+    {
+      "epoch": 0.3106796116504854,
+      "grad_norm": 0.5687094926834106,
+      "learning_rate": 0.00012920035938903865,
+      "loss": 1.0272964239120483,
+      "step": 720
+    },
+    {
+      "epoch": 0.31154261057173677,
+      "grad_norm": 0.5688400864601135,
+      "learning_rate": 0.00012955974842767296,
+      "loss": 0.9370370507240295,
+      "step": 722
+    },
+    {
+      "epoch": 0.3124056094929881,
+      "grad_norm": 0.5610610246658325,
+      "learning_rate": 0.00012991913746630729,
+      "loss": 0.9535608291625977,
+      "step": 724
+    },
+    {
+      "epoch": 0.3132686084142395,
+      "grad_norm": 0.6338257193565369,
+      "learning_rate": 0.00013027852650494162,
+      "loss": 1.0188907384872437,
+      "step": 726
+    },
+    {
+      "epoch": 0.31413160733549084,
+      "grad_norm": 0.5365633368492126,
+      "learning_rate": 0.00013063791554357592,
+      "loss": 0.9253716468811035,
+      "step": 728
+    },
+    {
+      "epoch": 0.3149946062567422,
+      "grad_norm": 0.5599163174629211,
+      "learning_rate": 0.00013099730458221025,
+      "loss": 0.8941492438316345,
+      "step": 730
+    },
+    {
+      "epoch": 0.31585760517799355,
+      "grad_norm": 0.6059780716896057,
+      "learning_rate": 0.00013135669362084458,
+      "loss": 0.9831459522247314,
+      "step": 732
+    },
+    {
+      "epoch": 0.31672060409924485,
+      "grad_norm": 0.5596494078636169,
+      "learning_rate": 0.0001317160826594789,
+      "loss": 0.9332310557365417,
+      "step": 734
+    },
+    {
+      "epoch": 0.3175836030204962,
+      "grad_norm": 0.5618010759353638,
+      "learning_rate": 0.0001320754716981132,
+      "loss": 0.9082580208778381,
+      "step": 736
+    },
+    {
+      "epoch": 0.31844660194174756,
+      "grad_norm": 0.6412109732627869,
+      "learning_rate": 0.00013243486073674754,
+      "loss": 1.008690357208252,
+      "step": 738
+    },
+    {
+      "epoch": 0.3193096008629989,
+      "grad_norm": 0.5742355585098267,
+      "learning_rate": 0.00013279424977538187,
+      "loss": 0.9597798585891724,
+      "step": 740
+    },
+    {
+      "epoch": 0.3201725997842503,
+      "grad_norm": 0.6470226645469666,
+      "learning_rate": 0.00013315363881401617,
+      "loss": 0.989331841468811,
+      "step": 742
+    },
+    {
+      "epoch": 0.32103559870550163,
+      "grad_norm": 0.5598039031028748,
+      "learning_rate": 0.0001335130278526505,
+      "loss": 0.8677343130111694,
+      "step": 744
+    },
+    {
+      "epoch": 0.321898597626753,
+      "grad_norm": 0.5441372990608215,
+      "learning_rate": 0.00013387241689128483,
+      "loss": 0.9462730288505554,
+      "step": 746
+    },
+    {
+      "epoch": 0.3227615965480043,
+      "grad_norm": 0.5858626365661621,
+      "learning_rate": 0.00013423180592991916,
+      "loss": 0.994694173336029,
+      "step": 748
+    },
+    {
+      "epoch": 0.32362459546925565,
+      "grad_norm": 0.511372447013855,
+      "learning_rate": 0.00013459119496855347,
+      "loss": 0.9387269616127014,
+      "step": 750
+    },
+    {
+      "epoch": 0.324487594390507,
+      "grad_norm": 0.47798457741737366,
+      "learning_rate": 0.0001349505840071878,
+      "loss": 0.9473881721496582,
+      "step": 752
+    },
+    {
+      "epoch": 0.32535059331175836,
+      "grad_norm": 0.5907022953033447,
+      "learning_rate": 0.0001353099730458221,
+      "loss": 0.9375183582305908,
+      "step": 754
+    },
+    {
+      "epoch": 0.3262135922330097,
+      "grad_norm": 0.618733286857605,
+      "learning_rate": 0.00013566936208445643,
+      "loss": 1.028738260269165,
+      "step": 756
+    },
+    {
+      "epoch": 0.3270765911542611,
+      "grad_norm": 0.5234512090682983,
+      "learning_rate": 0.00013602875112309076,
+      "loss": 0.9420192241668701,
+      "step": 758
+    },
+    {
+      "epoch": 0.32793959007551243,
+      "grad_norm": 0.7036319971084595,
+      "learning_rate": 0.00013638814016172506,
+      "loss": 1.0252270698547363,
+      "step": 760
+    },
+    {
+      "epoch": 0.32880258899676373,
+      "grad_norm": 0.5543172359466553,
+      "learning_rate": 0.0001367475292003594,
+      "loss": 0.8453778028488159,
+      "step": 762
+    },
+    {
+      "epoch": 0.3296655879180151,
+      "grad_norm": 0.5438711643218994,
+      "learning_rate": 0.0001371069182389937,
+      "loss": 0.8659937977790833,
+      "step": 764
+    },
+    {
+      "epoch": 0.33052858683926645,
+      "grad_norm": 0.6390914916992188,
+      "learning_rate": 0.00013746630727762803,
+      "loss": 1.038142442703247,
+      "step": 766
+    },
+    {
+      "epoch": 0.3313915857605178,
+      "grad_norm": 0.50070720911026,
+      "learning_rate": 0.00013782569631626236,
+      "loss": 0.899932861328125,
+      "step": 768
+    },
+    {
+      "epoch": 0.33225458468176916,
+      "grad_norm": 0.5982286334037781,
+      "learning_rate": 0.00013818508535489669,
+      "loss": 0.9712884426116943,
+      "step": 770
+    },
+    {
+      "epoch": 0.3331175836030205,
+      "grad_norm": 0.6588822603225708,
+      "learning_rate": 0.000138544474393531,
+      "loss": 0.9427542686462402,
+      "step": 772
+    },
+    {
+      "epoch": 0.3339805825242718,
+      "grad_norm": 0.6022042632102966,
+      "learning_rate": 0.00013890386343216532,
+      "loss": 0.8961561918258667,
+      "step": 774
+    },
+    {
+      "epoch": 0.3348435814455232,
+      "grad_norm": 0.6595642566680908,
+      "learning_rate": 0.00013926325247079965,
+      "loss": 0.9525937438011169,
+      "step": 776
+    },
+    {
+      "epoch": 0.33570658036677453,
+      "grad_norm": 0.5210421681404114,
+      "learning_rate": 0.00013962264150943395,
+      "loss": 0.9218845367431641,
+      "step": 778
+    },
+    {
+      "epoch": 0.3365695792880259,
+      "grad_norm": 0.549669623374939,
+      "learning_rate": 0.00013998203054806828,
+      "loss": 0.877951443195343,
+      "step": 780
+    },
+    {
+      "epoch": 0.33743257820927725,
+      "grad_norm": 0.5360157489776611,
+      "learning_rate": 0.0001403414195867026,
+      "loss": 0.8670064210891724,
+      "step": 782
+    },
+    {
+      "epoch": 0.3382955771305286,
+      "grad_norm": 0.614734947681427,
+      "learning_rate": 0.00014070080862533694,
+      "loss": 0.9561367630958557,
+      "step": 784
+    },
+    {
+      "epoch": 0.33915857605177996,
+      "grad_norm": 0.5798251628875732,
+      "learning_rate": 0.00014106019766397124,
+      "loss": 0.9132505059242249,
+      "step": 786
+    },
+    {
+      "epoch": 0.34002157497303126,
+      "grad_norm": 0.6267077326774597,
+      "learning_rate": 0.00014141958670260557,
+      "loss": 0.9297707080841064,
+      "step": 788
+    },
+    {
+      "epoch": 0.3408845738942826,
+      "grad_norm": 0.6045349836349487,
+      "learning_rate": 0.0001417789757412399,
+      "loss": 0.9382412433624268,
+      "step": 790
+    },
+    {
+      "epoch": 0.341747572815534,
+      "grad_norm": 0.6125404834747314,
+      "learning_rate": 0.0001421383647798742,
+      "loss": 0.9078555107116699,
+      "step": 792
+    },
+    {
+      "epoch": 0.34261057173678533,
+      "grad_norm": 0.5927051901817322,
+      "learning_rate": 0.00014249775381850854,
+      "loss": 0.899101197719574,
+      "step": 794
+    },
+    {
+      "epoch": 0.3434735706580367,
+      "grad_norm": 0.6315743923187256,
+      "learning_rate": 0.00014285714285714287,
+      "loss": 1.028346300125122,
+      "step": 796
+    },
+    {
+      "epoch": 0.34433656957928804,
+      "grad_norm": 0.549271285533905,
+      "learning_rate": 0.0001432165318957772,
+      "loss": 0.8988189697265625,
+      "step": 798
+    },
+    {
+      "epoch": 0.3451995685005394,
+      "grad_norm": 0.6344245672225952,
+      "learning_rate": 0.0001435759209344115,
+      "loss": 1.0489003658294678,
+      "step": 800
+    },
+    {
+      "epoch": 0.3451995685005394,
+      "eval_loss": 0.9864639639854431,
+      "eval_runtime": 667.3516,
+      "eval_samples_per_second": 3.087,
+      "eval_steps_per_second": 3.087,
+      "step": 800
+    },
+    {
+      "epoch": 0.3460625674217907,
+      "grad_norm": 0.5625309348106384,
+      "learning_rate": 0.00014393530997304583,
+      "loss": 0.8773928284645081,
+      "step": 802
+    },
+    {
+      "epoch": 0.34692556634304206,
+      "grad_norm": 0.5931969285011292,
+      "learning_rate": 0.00014429469901168016,
+      "loss": 0.9116050004959106,
+      "step": 804
+    },
+    {
+      "epoch": 0.3477885652642934,
+      "grad_norm": 0.5189821720123291,
+      "learning_rate": 0.00014465408805031446,
+      "loss": 0.9124425649642944,
+      "step": 806
+    },
+    {
+      "epoch": 0.34865156418554477,
+      "grad_norm": 0.5392254590988159,
+      "learning_rate": 0.0001450134770889488,
+      "loss": 0.9517888426780701,
+      "step": 808
+    },
+    {
+      "epoch": 0.34951456310679613,
+      "grad_norm": 0.5584444999694824,
+      "learning_rate": 0.00014537286612758312,
+      "loss": 0.9947572350502014,
+      "step": 810
+    },
+    {
+      "epoch": 0.3503775620280475,
+      "grad_norm": 0.5188854932785034,
+      "learning_rate": 0.00014573225516621745,
+      "loss": 0.9314022660255432,
+      "step": 812
+    },
+    {
+      "epoch": 0.3512405609492988,
+      "grad_norm": 0.5783659815788269,
+      "learning_rate": 0.00014609164420485176,
+      "loss": 0.9135628938674927,
+      "step": 814
+    },
+    {
+      "epoch": 0.35210355987055014,
+      "grad_norm": 0.550959050655365,
+      "learning_rate": 0.0001464510332434861,
+      "loss": 0.9665075540542603,
+      "step": 816
+    },
+    {
+      "epoch": 0.3529665587918015,
+      "grad_norm": 0.6013346314430237,
+      "learning_rate": 0.00014681042228212042,
+      "loss": 0.9836555123329163,
+      "step": 818
+    },
+    {
+      "epoch": 0.35382955771305286,
+      "grad_norm": 0.49219194054603577,
+      "learning_rate": 0.00014716981132075472,
+      "loss": 0.8900108337402344,
+      "step": 820
+    },
+    {
+      "epoch": 0.3546925566343042,
+      "grad_norm": 0.5517411828041077,
+      "learning_rate": 0.00014752920035938905,
+      "loss": 0.8769304156303406,
+      "step": 822
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.6062695980072021,
+      "learning_rate": 0.00014788858939802338,
+      "loss": 0.9744759202003479,
+      "step": 824
+    },
+    {
+      "epoch": 0.3564185544768069,
+      "grad_norm": 0.5132041573524475,
+      "learning_rate": 0.0001482479784366577,
+      "loss": 0.8875447511672974,
+      "step": 826
+    },
+    {
+      "epoch": 0.3572815533980582,
+      "grad_norm": 0.551799476146698,
+      "learning_rate": 0.000148607367475292,
+      "loss": 0.962710440158844,
+      "step": 828
+    },
+    {
+      "epoch": 0.3581445523193096,
+      "grad_norm": 0.6046625971794128,
+      "learning_rate": 0.00014896675651392634,
+      "loss": 0.8997528553009033,
+      "step": 830
+    },
+    {
+      "epoch": 0.35900755124056094,
+      "grad_norm": 0.560025691986084,
+      "learning_rate": 0.00014932614555256067,
+      "loss": 0.9541417360305786,
+      "step": 832
+    },
+    {
+      "epoch": 0.3598705501618123,
+      "grad_norm": 0.6441047787666321,
+      "learning_rate": 0.00014968553459119498,
+      "loss": 0.907791018486023,
+      "step": 834
+    },
+    {
+      "epoch": 0.36073354908306365,
+      "grad_norm": 0.5636281967163086,
+      "learning_rate": 0.0001500449236298293,
+      "loss": 1.0295937061309814,
+      "step": 836
+    },
+    {
+      "epoch": 0.361596548004315,
+      "grad_norm": 0.5528303384780884,
+      "learning_rate": 0.0001504043126684636,
+      "loss": 0.8875265717506409,
+      "step": 838
+    },
+    {
+      "epoch": 0.36245954692556637,
+      "grad_norm": 0.5345163345336914,
+      "learning_rate": 0.00015076370170709794,
+      "loss": 0.9678915739059448,
+      "step": 840
+    },
+    {
+      "epoch": 0.36332254584681767,
+      "grad_norm": 0.5551225543022156,
+      "learning_rate": 0.00015112309074573224,
+      "loss": 0.9235162734985352,
+      "step": 842
+    },
+    {
+      "epoch": 0.364185544768069,
+      "grad_norm": 0.5131904482841492,
+      "learning_rate": 0.00015148247978436657,
+      "loss": 0.8624292016029358,
+      "step": 844
+    },
+    {
+      "epoch": 0.3650485436893204,
+      "grad_norm": 0.6811004281044006,
+      "learning_rate": 0.0001518418688230009,
+      "loss": 1.0360193252563477,
+      "step": 846
+    },
+    {
+      "epoch": 0.36591154261057174,
+      "grad_norm": 0.6409741640090942,
+      "learning_rate": 0.00015220125786163523,
+      "loss": 0.9254010915756226,
+      "step": 848
+    },
+    {
+      "epoch": 0.3667745415318231,
+      "grad_norm": 0.5534068942070007,
+      "learning_rate": 0.00015256064690026953,
+      "loss": 0.8900630474090576,
+      "step": 850
+    },
+    {
+      "epoch": 0.36763754045307445,
+      "grad_norm": 0.4999487102031708,
+      "learning_rate": 0.00015292003593890386,
+      "loss": 0.88521409034729,
+      "step": 852
+    },
+    {
+      "epoch": 0.3685005393743258,
+      "grad_norm": 0.5805923938751221,
+      "learning_rate": 0.0001532794249775382,
+      "loss": 0.9563921093940735,
+      "step": 854
+    },
+    {
+      "epoch": 0.3693635382955771,
+      "grad_norm": 0.5485470294952393,
+      "learning_rate": 0.0001536388140161725,
+      "loss": 0.8909372687339783,
+      "step": 856
+    },
+    {
+      "epoch": 0.37022653721682847,
+      "grad_norm": 0.5317923426628113,
+      "learning_rate": 0.00015399820305480683,
+      "loss": 0.9145731925964355,
+      "step": 858
+    },
+    {
+      "epoch": 0.3710895361380798,
+      "grad_norm": 0.6073495745658875,
+      "learning_rate": 0.00015435759209344116,
+      "loss": 1.01466965675354,
+      "step": 860
+    },
+    {
+      "epoch": 0.3719525350593312,
+      "grad_norm": 0.566655158996582,
+      "learning_rate": 0.0001547169811320755,
+      "loss": 0.9941825270652771,
+      "step": 862
+    },
+    {
+      "epoch": 0.37281553398058254,
+      "grad_norm": 0.5262459516525269,
+      "learning_rate": 0.0001550763701707098,
+      "loss": 1.0059782266616821,
+      "step": 864
+    },
+    {
+      "epoch": 0.3736785329018339,
+      "grad_norm": 0.6264083981513977,
+      "learning_rate": 0.00015543575920934412,
+      "loss": 1.0332856178283691,
+      "step": 866
+    },
+    {
+      "epoch": 0.3745415318230852,
+      "grad_norm": 0.6575480699539185,
+      "learning_rate": 0.00015579514824797845,
+      "loss": 1.022459626197815,
+      "step": 868
+    },
+    {
+      "epoch": 0.37540453074433655,
+      "grad_norm": 0.6291940212249756,
+      "learning_rate": 0.00015615453728661275,
+      "loss": 0.9550372362136841,
+      "step": 870
+    },
+    {
+      "epoch": 0.3762675296655879,
+      "grad_norm": 0.6710562109947205,
+      "learning_rate": 0.00015651392632524708,
+      "loss": 0.9861716628074646,
+      "step": 872
+    },
+    {
+      "epoch": 0.37713052858683926,
+      "grad_norm": 0.5505748987197876,
+      "learning_rate": 0.0001568733153638814,
+      "loss": 0.9719111919403076,
+      "step": 874
+    },
+    {
+      "epoch": 0.3779935275080906,
+      "grad_norm": 0.5055180788040161,
+      "learning_rate": 0.00015723270440251574,
+      "loss": 0.8698170185089111,
+      "step": 876
+    },
+    {
+      "epoch": 0.378856526429342,
+      "grad_norm": 0.5935947895050049,
+      "learning_rate": 0.00015759209344115005,
+      "loss": 1.029494285583496,
+      "step": 878
+    },
+    {
+      "epoch": 0.37971952535059333,
+      "grad_norm": 0.538325846195221,
+      "learning_rate": 0.00015795148247978438,
+      "loss": 0.923010528087616,
+      "step": 880
+    },
+    {
+      "epoch": 0.38058252427184464,
+      "grad_norm": 0.587297797203064,
+      "learning_rate": 0.0001583108715184187,
+      "loss": 0.9394056797027588,
+      "step": 882
+    },
+    {
+      "epoch": 0.381445523193096,
+      "grad_norm": 0.5910462737083435,
+      "learning_rate": 0.000158670260557053,
+      "loss": 0.9472483992576599,
+      "step": 884
+    },
+    {
+      "epoch": 0.38230852211434735,
+      "grad_norm": 0.629048764705658,
+      "learning_rate": 0.00015902964959568734,
+      "loss": 0.9028263688087463,
+      "step": 886
+    },
+    {
+      "epoch": 0.3831715210355987,
+      "grad_norm": 0.5028086304664612,
+      "learning_rate": 0.00015938903863432167,
+      "loss": 0.9579087495803833,
+      "step": 888
+    },
+    {
+      "epoch": 0.38403451995685006,
+      "grad_norm": 0.5372384190559387,
+      "learning_rate": 0.000159748427672956,
+      "loss": 0.8318673372268677,
+      "step": 890
+    },
+    {
+      "epoch": 0.3848975188781014,
+      "grad_norm": 0.6314184665679932,
+      "learning_rate": 0.0001601078167115903,
+      "loss": 0.9804943203926086,
+      "step": 892
+    },
+    {
+      "epoch": 0.3857605177993528,
+      "grad_norm": 0.5545229911804199,
+      "learning_rate": 0.00016046720575022463,
+      "loss": 1.0078438520431519,
+      "step": 894
+    },
+    {
+      "epoch": 0.3866235167206041,
+      "grad_norm": 0.4674014151096344,
+      "learning_rate": 0.00016082659478885896,
+      "loss": 0.9269036650657654,
+      "step": 896
+    },
+    {
+      "epoch": 0.38748651564185543,
+      "grad_norm": 1.5887153148651123,
+      "learning_rate": 0.00016118598382749326,
+      "loss": 0.8927953243255615,
+      "step": 898
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "grad_norm": 0.5217035412788391,
+      "learning_rate": 0.0001615453728661276,
+      "loss": 0.908074140548706,
+      "step": 900
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "eval_loss": 0.9741895794868469,
+      "eval_runtime": 667.2236,
+      "eval_samples_per_second": 3.087,
+      "eval_steps_per_second": 3.087,
+      "step": 900
+    },
+    {
+      "epoch": 0.38921251348435815,
+      "grad_norm": 0.470498651266098,
+      "learning_rate": 0.00016190476190476192,
+      "loss": 0.9660369157791138,
+      "step": 902
+    },
+    {
+      "epoch": 0.3900755124056095,
+      "grad_norm": 0.5111004114151001,
+      "learning_rate": 0.00016226415094339625,
+      "loss": 0.9236379265785217,
+      "step": 904
+    },
+    {
+      "epoch": 0.39093851132686086,
+      "grad_norm": 0.5872815251350403,
+      "learning_rate": 0.00016262353998203056,
+      "loss": 1.0061595439910889,
+      "step": 906
+    },
+    {
+      "epoch": 0.3918015102481122,
+      "grad_norm": 0.5150740742683411,
+      "learning_rate": 0.0001629829290206649,
+      "loss": 0.8347328901290894,
+      "step": 908
+    },
+    {
+      "epoch": 0.3926645091693635,
+      "grad_norm": 0.46554985642433167,
+      "learning_rate": 0.00016334231805929922,
+      "loss": 0.9091183543205261,
+      "step": 910
+    },
+    {
+      "epoch": 0.3935275080906149,
+      "grad_norm": 0.5292875170707703,
+      "learning_rate": 0.00016370170709793352,
+      "loss": 0.9299798011779785,
+      "step": 912
+    },
+    {
+      "epoch": 0.39439050701186623,
+      "grad_norm": 0.5177125930786133,
+      "learning_rate": 0.00016406109613656785,
+      "loss": 0.942286491394043,
+      "step": 914
+    },
+    {
+      "epoch": 0.3952535059331176,
+      "grad_norm": 0.5564161539077759,
+      "learning_rate": 0.00016442048517520215,
+      "loss": 0.825290858745575,
+      "step": 916
+    },
+    {
+      "epoch": 0.39611650485436894,
+      "grad_norm": 0.5572530031204224,
+      "learning_rate": 0.00016477987421383648,
+      "loss": 0.876898467540741,
+      "step": 918
+    },
+    {
+      "epoch": 0.3969795037756203,
+      "grad_norm": 0.7294673323631287,
+      "learning_rate": 0.0001651392632524708,
+      "loss": 0.8949798941612244,
+      "step": 920
+    },
+    {
+      "epoch": 0.3978425026968716,
+      "grad_norm": 0.5234251022338867,
+      "learning_rate": 0.00016549865229110512,
+      "loss": 0.8457819223403931,
+      "step": 922
+    },
+    {
+      "epoch": 0.39870550161812296,
+      "grad_norm": 0.5273709893226624,
+      "learning_rate": 0.00016585804132973945,
+      "loss": 0.9080174565315247,
+      "step": 924
+    },
+    {
+      "epoch": 0.3995685005393743,
+      "grad_norm": 0.5795063376426697,
+      "learning_rate": 0.00016621743036837378,
+      "loss": 1.0304023027420044,
+      "step": 926
+    },
+    {
+      "epoch": 0.4004314994606257,
+      "grad_norm": 0.6153313517570496,
+      "learning_rate": 0.00016657681940700808,
+      "loss": 0.8900477886199951,
+      "step": 928
+    },
+    {
+      "epoch": 0.40129449838187703,
+      "grad_norm": 0.6293173432350159,
+      "learning_rate": 0.0001669362084456424,
+      "loss": 1.0130009651184082,
+      "step": 930
+    },
+    {
+      "epoch": 0.4021574973031284,
+      "grad_norm": 0.5455223321914673,
+      "learning_rate": 0.00016729559748427674,
+      "loss": 0.9339282512664795,
+      "step": 932
+    },
+    {
+      "epoch": 0.40302049622437974,
+      "grad_norm": 0.5349094271659851,
+      "learning_rate": 0.00016765498652291104,
+      "loss": 0.9628980755805969,
+      "step": 934
+    },
+    {
+      "epoch": 0.40388349514563104,
+      "grad_norm": 0.491227924823761,
+      "learning_rate": 0.00016801437556154537,
+      "loss": 0.8922860026359558,
+      "step": 936
+    },
+    {
+      "epoch": 0.4047464940668824,
+      "grad_norm": 0.6331246495246887,
+      "learning_rate": 0.0001683737646001797,
+      "loss": 1.0470497608184814,
+      "step": 938
+    },
+    {
+      "epoch": 0.40560949298813376,
+      "grad_norm": 0.6079246401786804,
+      "learning_rate": 0.00016873315363881403,
+      "loss": 0.8868283629417419,
+      "step": 940
+    },
+    {
+      "epoch": 0.4064724919093851,
+      "grad_norm": 0.5326972603797913,
+      "learning_rate": 0.00016909254267744833,
+      "loss": 0.9938711524009705,
+      "step": 942
+    },
+    {
+      "epoch": 0.40733549083063647,
+      "grad_norm": 0.47754305601119995,
+      "learning_rate": 0.00016945193171608266,
+      "loss": 0.8280484676361084,
+      "step": 944
+    },
+    {
+      "epoch": 0.4081984897518878,
+      "grad_norm": 0.6683310270309448,
+      "learning_rate": 0.000169811320754717,
+      "loss": 1.089701533317566,
+      "step": 946
+    },
+    {
+      "epoch": 0.4090614886731392,
+      "grad_norm": 0.42798754572868347,
+      "learning_rate": 0.0001701707097933513,
+      "loss": 0.8535542488098145,
+      "step": 948
+    },
+    {
+      "epoch": 0.4099244875943905,
+      "grad_norm": 0.5999574065208435,
+      "learning_rate": 0.00017053009883198563,
+      "loss": 0.9039298295974731,
+      "step": 950
+    },
+    {
+      "epoch": 0.41078748651564184,
+      "grad_norm": 0.5752781629562378,
+      "learning_rate": 0.00017088948787061996,
+      "loss": 0.8786448240280151,
+      "step": 952
+    },
+    {
+      "epoch": 0.4116504854368932,
+      "grad_norm": 0.5121532678604126,
+      "learning_rate": 0.0001712488769092543,
+      "loss": 0.9206072688102722,
+      "step": 954
+    },
+    {
+      "epoch": 0.41251348435814456,
+      "grad_norm": 0.611078143119812,
+      "learning_rate": 0.0001716082659478886,
+      "loss": 0.9246986508369446,
+      "step": 956
+    },
+    {
+      "epoch": 0.4133764832793959,
+      "grad_norm": 0.5101020336151123,
+      "learning_rate": 0.00017196765498652292,
+      "loss": 0.9221894145011902,
+      "step": 958
+    },
+    {
+      "epoch": 0.41423948220064727,
+      "grad_norm": 0.5681450963020325,
+      "learning_rate": 0.00017232704402515725,
+      "loss": 0.9072799682617188,
+      "step": 960
+    },
+    {
+      "epoch": 0.41510248112189857,
+      "grad_norm": 0.47865498065948486,
+      "learning_rate": 0.00017268643306379155,
+      "loss": 0.9460896849632263,
+      "step": 962
+    },
+    {
+      "epoch": 0.4159654800431499,
+      "grad_norm": 0.49861401319503784,
+      "learning_rate": 0.00017304582210242588,
+      "loss": 0.9121519923210144,
+      "step": 964
+    },
+    {
+      "epoch": 0.4168284789644013,
+      "grad_norm": 0.43025892972946167,
+      "learning_rate": 0.0001734052111410602,
+      "loss": 0.8826848864555359,
+      "step": 966
+    },
+    {
+      "epoch": 0.41769147788565264,
+      "grad_norm": 0.4600491225719452,
+      "learning_rate": 0.00017376460017969454,
+      "loss": 0.8756251335144043,
+      "step": 968
+    },
+    {
+      "epoch": 0.418554476806904,
+      "grad_norm": 0.5297656059265137,
+      "learning_rate": 0.00017412398921832885,
+      "loss": 0.9171333312988281,
+      "step": 970
+    },
+    {
+      "epoch": 0.41941747572815535,
+      "grad_norm": 0.4906919002532959,
+      "learning_rate": 0.00017448337825696318,
+      "loss": 0.8887524008750916,
+      "step": 972
+    },
+    {
+      "epoch": 0.4202804746494067,
+      "grad_norm": 0.49263402819633484,
+      "learning_rate": 0.0001748427672955975,
+      "loss": 0.8345810174942017,
+      "step": 974
+    },
+    {
+      "epoch": 0.421143473570658,
+      "grad_norm": 0.5706565380096436,
+      "learning_rate": 0.0001752021563342318,
+      "loss": 0.968651294708252,
+      "step": 976
+    },
+    {
+      "epoch": 0.42200647249190937,
+      "grad_norm": 0.5269908308982849,
+      "learning_rate": 0.00017556154537286614,
+      "loss": 0.9729376435279846,
+      "step": 978
+    },
+    {
+      "epoch": 0.4228694714131607,
+      "grad_norm": 0.47058001160621643,
+      "learning_rate": 0.00017592093441150047,
+      "loss": 0.963884711265564,
+      "step": 980
+    },
+    {
+      "epoch": 0.4237324703344121,
+      "grad_norm": 0.5322962999343872,
+      "learning_rate": 0.0001762803234501348,
+      "loss": 0.8952447175979614,
+      "step": 982
+    },
+    {
+      "epoch": 0.42459546925566344,
+      "grad_norm": 0.5750975012779236,
+      "learning_rate": 0.0001766397124887691,
+      "loss": 0.8932783603668213,
+      "step": 984
+    },
+    {
+      "epoch": 0.4254584681769148,
+      "grad_norm": 0.5539655685424805,
+      "learning_rate": 0.00017699910152740343,
+      "loss": 0.916595458984375,
+      "step": 986
+    },
+    {
+      "epoch": 0.42632146709816615,
+      "grad_norm": 0.568000853061676,
+      "learning_rate": 0.00017735849056603776,
+      "loss": 0.9669626355171204,
+      "step": 988
+    },
+    {
+      "epoch": 0.42718446601941745,
+      "grad_norm": 0.6010684370994568,
+      "learning_rate": 0.00017771787960467206,
+      "loss": 1.0089105367660522,
+      "step": 990
+    },
+    {
+      "epoch": 0.4280474649406688,
+      "grad_norm": 0.6083462238311768,
+      "learning_rate": 0.0001780772686433064,
+      "loss": 0.9810921549797058,
+      "step": 992
+    },
+    {
+      "epoch": 0.42891046386192017,
+      "grad_norm": 0.5076655149459839,
+      "learning_rate": 0.0001784366576819407,
+      "loss": 0.9524372816085815,
+      "step": 994
+    },
+    {
+      "epoch": 0.4297734627831715,
+      "grad_norm": 0.5260922312736511,
+      "learning_rate": 0.00017879604672057503,
+      "loss": 0.881294846534729,
+      "step": 996
+    },
+    {
+      "epoch": 0.4306364617044229,
+      "grad_norm": 0.6130498051643372,
+      "learning_rate": 0.00017915543575920936,
+      "loss": 0.9138327836990356,
+      "step": 998
+    },
+    {
+      "epoch": 0.43149946062567424,
+      "grad_norm": 0.5346242785453796,
+      "learning_rate": 0.00017951482479784366,
+      "loss": 0.8861367106437683,
+      "step": 1000
+    },
+    {
+      "epoch": 0.43149946062567424,
+      "eval_loss": 0.9606748819351196,
+      "eval_runtime": 655.4358,
+      "eval_samples_per_second": 3.143,
+      "eval_steps_per_second": 3.143,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4323624595469256,
+      "grad_norm": 0.5977228879928589,
+      "learning_rate": 0.000179874213836478,
+      "loss": 0.8711628913879395,
+      "step": 1002
+    },
+    {
+      "epoch": 0.4332254584681769,
+      "grad_norm": 0.5547866821289062,
+      "learning_rate": 0.00018023360287511232,
+      "loss": 0.9393253326416016,
+      "step": 1004
+    },
+    {
+      "epoch": 0.43408845738942825,
+      "grad_norm": 0.536856472492218,
+      "learning_rate": 0.00018059299191374662,
+      "loss": 0.9486003518104553,
+      "step": 1006
+    },
+    {
+      "epoch": 0.4349514563106796,
+      "grad_norm": 0.4769814610481262,
+      "learning_rate": 0.00018095238095238095,
+      "loss": 0.9042052030563354,
+      "step": 1008
+    },
+    {
+      "epoch": 0.43581445523193096,
+      "grad_norm": 0.5554604530334473,
+      "learning_rate": 0.00018131176999101528,
+      "loss": 0.978546142578125,
+      "step": 1010
+    },
+    {
+      "epoch": 0.4366774541531823,
+      "grad_norm": 0.5112947225570679,
+      "learning_rate": 0.00018167115902964959,
+      "loss": 0.8382073640823364,
+      "step": 1012
+    },
+    {
+      "epoch": 0.4375404530744337,
+      "grad_norm": 0.45194941759109497,
+      "learning_rate": 0.00018203054806828392,
+      "loss": 0.8577026724815369,
+      "step": 1014
+    },
+    {
+      "epoch": 0.438403451995685,
+      "grad_norm": 0.5115043520927429,
+      "learning_rate": 0.00018238993710691825,
+      "loss": 0.8517863154411316,
+      "step": 1016
+    },
+    {
+      "epoch": 0.43926645091693634,
+      "grad_norm": 0.5485050082206726,
+      "learning_rate": 0.00018274932614555258,
+      "loss": 0.9597266912460327,
+      "step": 1018
+    },
+    {
+      "epoch": 0.4401294498381877,
+      "grad_norm": 0.5742959976196289,
+      "learning_rate": 0.00018310871518418688,
+      "loss": 1.0407187938690186,
+      "step": 1020
+    },
+    {
+      "epoch": 0.44099244875943905,
+      "grad_norm": 0.44870051741600037,
+      "learning_rate": 0.0001834681042228212,
+      "loss": 0.8696310520172119,
+      "step": 1022
+    },
+    {
+      "epoch": 0.4418554476806904,
+      "grad_norm": 0.5179623961448669,
+      "learning_rate": 0.00018382749326145554,
+      "loss": 0.9673634767532349,
+      "step": 1024
+    },
+    {
+      "epoch": 0.44271844660194176,
+      "grad_norm": 0.5404779314994812,
+      "learning_rate": 0.00018418688230008984,
+      "loss": 0.9596615433692932,
+      "step": 1026
+    },
+    {
+      "epoch": 0.4435814455231931,
+      "grad_norm": 0.47766315937042236,
+      "learning_rate": 0.00018454627133872417,
+      "loss": 0.8483878970146179,
+      "step": 1028
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.503380537033081,
+      "learning_rate": 0.0001849056603773585,
+      "loss": 0.9330979585647583,
+      "step": 1030
+    },
+    {
+      "epoch": 0.4453074433656958,
+      "grad_norm": 0.6129396557807922,
+      "learning_rate": 0.00018526504941599283,
+      "loss": 0.9341012239456177,
+      "step": 1032
+    },
+    {
+      "epoch": 0.44617044228694713,
+      "grad_norm": 0.4497876465320587,
+      "learning_rate": 0.00018562443845462713,
+      "loss": 0.9139068126678467,
+      "step": 1034
+    },
+    {
+      "epoch": 0.4470334412081985,
+      "grad_norm": 0.5369747281074524,
+      "learning_rate": 0.00018598382749326146,
+      "loss": 0.8874827027320862,
+      "step": 1036
+    },
+    {
+      "epoch": 0.44789644012944985,
+      "grad_norm": 0.5947322845458984,
+      "learning_rate": 0.0001863432165318958,
+      "loss": 0.9653725028038025,
+      "step": 1038
+    },
+    {
+      "epoch": 0.4487594390507012,
+      "grad_norm": 0.6649987101554871,
+      "learning_rate": 0.0001867026055705301,
+      "loss": 0.9553119540214539,
+      "step": 1040
+    },
+    {
+      "epoch": 0.44962243797195256,
+      "grad_norm": 0.5369387269020081,
+      "learning_rate": 0.00018706199460916443,
+      "loss": 0.904233992099762,
+      "step": 1042
+    },
+    {
+      "epoch": 0.45048543689320386,
+      "grad_norm": 0.4956842362880707,
+      "learning_rate": 0.00018742138364779876,
+      "loss": 0.8837952017784119,
+      "step": 1044
+    },
+    {
+      "epoch": 0.4513484358144552,
+      "grad_norm": 0.48045051097869873,
+      "learning_rate": 0.0001877807726864331,
+      "loss": 0.8964687585830688,
+      "step": 1046
+    },
+    {
+      "epoch": 0.4522114347357066,
+      "grad_norm": 0.4925530254840851,
+      "learning_rate": 0.0001881401617250674,
+      "loss": 0.9105878472328186,
+      "step": 1048
+    },
+    {
+      "epoch": 0.45307443365695793,
+      "grad_norm": 0.5131362080574036,
+      "learning_rate": 0.00018849955076370172,
+      "loss": 0.96272873878479,
+      "step": 1050
+    },
+    {
+      "epoch": 0.4539374325782093,
+      "grad_norm": 0.435739129781723,
+      "learning_rate": 0.00018885893980233605,
+      "loss": 0.8796783685684204,
+      "step": 1052
+    },
+    {
+      "epoch": 0.45480043149946064,
+      "grad_norm": 0.500938892364502,
+      "learning_rate": 0.00018921832884097035,
+      "loss": 0.9463814496994019,
+      "step": 1054
+    },
+    {
+      "epoch": 0.455663430420712,
+      "grad_norm": 0.4769900143146515,
+      "learning_rate": 0.00018957771787960468,
+      "loss": 0.9030335545539856,
+      "step": 1056
+    },
+    {
+      "epoch": 0.4565264293419633,
+      "grad_norm": 0.49585285782814026,
+      "learning_rate": 0.00018993710691823901,
+      "loss": 0.986995279788971,
+      "step": 1058
+    },
+    {
+      "epoch": 0.45738942826321466,
+      "grad_norm": 0.5875195264816284,
+      "learning_rate": 0.00019029649595687334,
+      "loss": 0.9297246932983398,
+      "step": 1060
+    },
+    {
+      "epoch": 0.458252427184466,
+      "grad_norm": 0.5552583932876587,
+      "learning_rate": 0.00019065588499550765,
+      "loss": 1.005869746208191,
+      "step": 1062
+    },
+    {
+      "epoch": 0.4591154261057174,
+      "grad_norm": 0.49282076954841614,
+      "learning_rate": 0.00019101527403414198,
+      "loss": 0.8949927091598511,
+      "step": 1064
+    },
+    {
+      "epoch": 0.45997842502696873,
+      "grad_norm": 0.4951777160167694,
+      "learning_rate": 0.0001913746630727763,
+      "loss": 0.9997886419296265,
+      "step": 1066
+    },
+    {
+      "epoch": 0.4608414239482201,
+      "grad_norm": 0.5154827237129211,
+      "learning_rate": 0.0001917340521114106,
+      "loss": 0.9532123804092407,
+      "step": 1068
+    },
+    {
+      "epoch": 0.4617044228694714,
+      "grad_norm": 0.5547500252723694,
+      "learning_rate": 0.00019209344115004494,
+      "loss": 0.8959843516349792,
+      "step": 1070
+    },
+    {
+      "epoch": 0.46256742179072274,
+      "grad_norm": 0.500188946723938,
+      "learning_rate": 0.00019245283018867927,
+      "loss": 0.8201484680175781,
+      "step": 1072
+    },
+    {
+      "epoch": 0.4634304207119741,
+      "grad_norm": 0.4181794822216034,
+      "learning_rate": 0.00019281221922731357,
+      "loss": 0.8255136609077454,
+      "step": 1074
+    },
+    {
+      "epoch": 0.46429341963322546,
+      "grad_norm": 0.5613874197006226,
+      "learning_rate": 0.0001931716082659479,
+      "loss": 0.896024763584137,
+      "step": 1076
+    },
+    {
+      "epoch": 0.4651564185544768,
+      "grad_norm": 0.5000972151756287,
+      "learning_rate": 0.0001935309973045822,
+      "loss": 0.8831873536109924,
+      "step": 1078
+    },
+    {
+      "epoch": 0.46601941747572817,
+      "grad_norm": 0.6321820616722107,
+      "learning_rate": 0.00019389038634321654,
+      "loss": 0.9787988662719727,
+      "step": 1080
+    },
+    {
+      "epoch": 0.4668824163969795,
+      "grad_norm": 0.4843652546405792,
+      "learning_rate": 0.00019424977538185087,
+      "loss": 0.933361828327179,
+      "step": 1082
+    },
+    {
+      "epoch": 0.46774541531823083,
+      "grad_norm": 0.537330150604248,
+      "learning_rate": 0.00019460916442048517,
+      "loss": 0.9046981334686279,
+      "step": 1084
+    },
+    {
+      "epoch": 0.4686084142394822,
+      "grad_norm": 0.5761371850967407,
+      "learning_rate": 0.0001949685534591195,
+      "loss": 0.9625781178474426,
+      "step": 1086
+    },
+    {
+      "epoch": 0.46947141316073354,
+      "grad_norm": 0.5209522843360901,
+      "learning_rate": 0.00019532794249775383,
+      "loss": 0.9280619025230408,
+      "step": 1088
+    },
+    {
+      "epoch": 0.4703344120819849,
+      "grad_norm": 0.5383933186531067,
+      "learning_rate": 0.00019568733153638813,
+      "loss": 0.8236247301101685,
+      "step": 1090
+    },
+    {
+      "epoch": 0.47119741100323626,
+      "grad_norm": 0.4994274377822876,
+      "learning_rate": 0.00019604672057502246,
+      "loss": 0.9404071569442749,
+      "step": 1092
+    },
+    {
+      "epoch": 0.4720604099244876,
+      "grad_norm": 0.5177807211875916,
+      "learning_rate": 0.0001964061096136568,
+      "loss": 0.8517536520957947,
+      "step": 1094
+    },
+    {
+      "epoch": 0.47292340884573897,
+      "grad_norm": 0.5374870896339417,
+      "learning_rate": 0.00019676549865229112,
+      "loss": 0.8214367032051086,
+      "step": 1096
+    },
+    {
+      "epoch": 0.47378640776699027,
+      "grad_norm": 0.5544074177742004,
+      "learning_rate": 0.00019712488769092542,
+      "loss": 1.016176700592041,
+      "step": 1098
+    },
+    {
+      "epoch": 0.4746494066882416,
+      "grad_norm": 0.5125867128372192,
+      "learning_rate": 0.00019748427672955975,
+      "loss": 0.8425421118736267,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4746494066882416,
+      "eval_loss": 0.944629430770874,
+      "eval_runtime": 649.9107,
+      "eval_samples_per_second": 3.17,
+      "eval_steps_per_second": 3.17,
+      "step": 1100
+    },
+    {
+      "epoch": 0.475512405609493,
+      "grad_norm": 0.5204418897628784,
+      "learning_rate": 0.00019784366576819408,
+      "loss": 0.9444556832313538,
+      "step": 1102
+    },
+    {
+      "epoch": 0.47637540453074434,
+      "grad_norm": 0.46085885167121887,
+      "learning_rate": 0.0001982030548068284,
+      "loss": 0.877082109451294,
+      "step": 1104
+    },
+    {
+      "epoch": 0.4772384034519957,
+      "grad_norm": 0.5269598960876465,
+      "learning_rate": 0.00019856244384546272,
+      "loss": 0.9214640259742737,
+      "step": 1106
+    },
+    {
+      "epoch": 0.47810140237324705,
+      "grad_norm": 0.4894753694534302,
+      "learning_rate": 0.00019892183288409705,
+      "loss": 0.8867175579071045,
+      "step": 1108
+    },
+    {
+      "epoch": 0.47896440129449835,
+      "grad_norm": 0.5204115509986877,
+      "learning_rate": 0.00019928122192273138,
+      "loss": 0.9641162753105164,
+      "step": 1110
+    },
+    {
+      "epoch": 0.4798274002157497,
+      "grad_norm": 0.6399031281471252,
+      "learning_rate": 0.00019964061096136568,
+      "loss": 1.0219199657440186,
+      "step": 1112
+    },
+    {
+      "epoch": 0.48069039913700107,
+      "grad_norm": 0.3979159891605377,
+      "learning_rate": 0.0002,
+      "loss": 0.8189998269081116,
+      "step": 1114
+    },
+    {
+      "epoch": 0.4815533980582524,
+      "grad_norm": 0.4782681465148926,
+      "learning_rate": 0.0001999999879427254,
+      "loss": 0.83241868019104,
+      "step": 1116
+    },
+    {
+      "epoch": 0.4824163969795038,
+      "grad_norm": 0.5235620141029358,
+      "learning_rate": 0.00019999995177090454,
+      "loss": 0.9371466636657715,
+      "step": 1118
+    },
+    {
+      "epoch": 0.48327939590075514,
+      "grad_norm": 0.4543023407459259,
+      "learning_rate": 0.00019999989148454606,
+      "loss": 0.7767758369445801,
+      "step": 1120
+    },
+    {
+      "epoch": 0.4841423948220065,
+      "grad_norm": 0.6191229820251465,
+      "learning_rate": 0.00019999980708366457,
+      "loss": 1.0103063583374023,
+      "step": 1122
+    },
+    {
+      "epoch": 0.4850053937432578,
+      "grad_norm": 0.45392486453056335,
+      "learning_rate": 0.00019999969856828042,
+      "loss": 0.8720875382423401,
+      "step": 1124
+    },
+    {
+      "epoch": 0.48586839266450915,
+      "grad_norm": 0.42748701572418213,
+      "learning_rate": 0.00019999956593841974,
+      "loss": 0.7859150171279907,
+      "step": 1126
+    },
+    {
+      "epoch": 0.4867313915857605,
+      "grad_norm": 0.4952569603919983,
+      "learning_rate": 0.00019999940919411454,
+      "loss": 0.9154419898986816,
+      "step": 1128
+    },
+    {
+      "epoch": 0.48759439050701187,
+      "grad_norm": 0.5522173047065735,
+      "learning_rate": 0.00019999922833540264,
+      "loss": 0.9076330065727234,
+      "step": 1130
+    },
+    {
+      "epoch": 0.4884573894282632,
+      "grad_norm": 0.5355855226516724,
+      "learning_rate": 0.00019999902336232758,
+      "loss": 0.8933543562889099,
+      "step": 1132
+    },
+    {
+      "epoch": 0.4893203883495146,
+      "grad_norm": 0.4613489508628845,
+      "learning_rate": 0.00019999879427493885,
+      "loss": 0.9160735607147217,
+      "step": 1134
+    },
+    {
+      "epoch": 0.49018338727076594,
+      "grad_norm": 0.4758962094783783,
+      "learning_rate": 0.0001999985410732917,
+      "loss": 0.8552446961402893,
+      "step": 1136
+    },
+    {
+      "epoch": 0.49104638619201724,
+      "grad_norm": 0.4549376964569092,
+      "learning_rate": 0.00019999826375744715,
+      "loss": 0.9979530572891235,
+      "step": 1138
+    },
+    {
+      "epoch": 0.4919093851132686,
+      "grad_norm": 0.4363284409046173,
+      "learning_rate": 0.0001999979623274721,
+      "loss": 0.9295380115509033,
+      "step": 1140
+    },
+    {
+      "epoch": 0.49277238403451995,
+      "grad_norm": 0.5090877413749695,
+      "learning_rate": 0.0001999976367834392,
+      "loss": 0.8737252950668335,
+      "step": 1142
+    },
+    {
+      "epoch": 0.4936353829557713,
+      "grad_norm": 0.45340779423713684,
+      "learning_rate": 0.000199997287125427,
+      "loss": 0.8312779068946838,
+      "step": 1144
+    },
+    {
+      "epoch": 0.49449838187702266,
+      "grad_norm": 0.4771472215652466,
+      "learning_rate": 0.0001999969133535198,
+      "loss": 0.9105207324028015,
+      "step": 1146
+    },
+    {
+      "epoch": 0.495361380798274,
+      "grad_norm": 0.5251384377479553,
+      "learning_rate": 0.00019999651546780773,
+      "loss": 0.8578172922134399,
+      "step": 1148
+    },
+    {
+      "epoch": 0.4962243797195254,
+      "grad_norm": 0.49128198623657227,
+      "learning_rate": 0.00019999609346838676,
+      "loss": 0.9193941950798035,
+      "step": 1150
+    },
+    {
+      "epoch": 0.4970873786407767,
+      "grad_norm": 0.5558596849441528,
+      "learning_rate": 0.0001999956473553586,
+      "loss": 0.9141314625740051,
+      "step": 1152
+    },
+    {
+      "epoch": 0.49795037756202803,
+      "grad_norm": 0.45872750878334045,
+      "learning_rate": 0.00019999517712883087,
+      "loss": 0.9058388471603394,
+      "step": 1154
+    },
+    {
+      "epoch": 0.4988133764832794,
+      "grad_norm": 0.4710173010826111,
+      "learning_rate": 0.00019999468278891698,
+      "loss": 0.8462487459182739,
+      "step": 1156
+    },
+    {
+      "epoch": 0.49967637540453075,
+      "grad_norm": 0.4805637001991272,
+      "learning_rate": 0.0001999941643357361,
+      "loss": 0.8960906863212585,
+      "step": 1158
+    },
+    {
+      "epoch": 0.5005393743257821,
+      "grad_norm": 0.5108052492141724,
+      "learning_rate": 0.00019999362176941325,
+      "loss": 0.9074980020523071,
+      "step": 1160
+    },
+    {
+      "epoch": 0.5014023732470334,
+      "grad_norm": 0.49572333693504333,
+      "learning_rate": 0.00019999305509007932,
+      "loss": 0.9710080623626709,
+      "step": 1162
+    },
+    {
+      "epoch": 0.5022653721682848,
+      "grad_norm": 0.5304561257362366,
+      "learning_rate": 0.0001999924642978709,
+      "loss": 0.8877825140953064,
+      "step": 1164
+    },
+    {
+      "epoch": 0.5031283710895361,
+      "grad_norm": 0.5007328391075134,
+      "learning_rate": 0.0001999918493929305,
+      "loss": 0.8955381512641907,
+      "step": 1166
+    },
+    {
+      "epoch": 0.5039913700107875,
+      "grad_norm": 0.569549024105072,
+      "learning_rate": 0.0001999912103754064,
+      "loss": 0.9478562474250793,
+      "step": 1168
+    },
+    {
+      "epoch": 0.5048543689320388,
+      "grad_norm": 0.5354957580566406,
+      "learning_rate": 0.00019999054724545264,
+      "loss": 0.9685383439064026,
+      "step": 1170
+    },
+    {
+      "epoch": 0.5057173678532901,
+      "grad_norm": 0.547788143157959,
+      "learning_rate": 0.00019998986000322917,
+      "loss": 0.9221975207328796,
+      "step": 1172
+    },
+    {
+      "epoch": 0.5065803667745415,
+      "grad_norm": 0.4919529855251312,
+      "learning_rate": 0.00019998914864890175,
+      "loss": 0.9104788303375244,
+      "step": 1174
+    },
+    {
+      "epoch": 0.5074433656957928,
+      "grad_norm": 0.5274141430854797,
+      "learning_rate": 0.00019998841318264187,
+      "loss": 0.9176050424575806,
+      "step": 1176
+    },
+    {
+      "epoch": 0.5083063646170443,
+      "grad_norm": 0.4257420301437378,
+      "learning_rate": 0.00019998765360462688,
+      "loss": 0.8389710187911987,
+      "step": 1178
+    },
+    {
+      "epoch": 0.5091693635382956,
+      "grad_norm": 0.4947778880596161,
+      "learning_rate": 0.00019998686991504002,
+      "loss": 1.0164397954940796,
+      "step": 1180
+    },
+    {
+      "epoch": 0.510032362459547,
+      "grad_norm": 0.5540821552276611,
+      "learning_rate": 0.00019998606211407016,
+      "loss": 0.9900994300842285,
+      "step": 1182
+    },
+    {
+      "epoch": 0.5108953613807983,
+      "grad_norm": 0.4793289601802826,
+      "learning_rate": 0.0001999852302019122,
+      "loss": 0.8797636032104492,
+      "step": 1184
+    },
+    {
+      "epoch": 0.5117583603020496,
+      "grad_norm": 0.47429659962654114,
+      "learning_rate": 0.00019998437417876672,
+      "loss": 0.96225905418396,
+      "step": 1186
+    },
+    {
+      "epoch": 0.512621359223301,
+      "grad_norm": 0.44918450713157654,
+      "learning_rate": 0.00019998349404484013,
+      "loss": 0.8604235649108887,
+      "step": 1188
+    },
+    {
+      "epoch": 0.5134843581445523,
+      "grad_norm": 0.566977858543396,
+      "learning_rate": 0.00019998258980034468,
+      "loss": 1.0325366258621216,
+      "step": 1190
+    },
+    {
+      "epoch": 0.5143473570658037,
+      "grad_norm": 0.4671999514102936,
+      "learning_rate": 0.00019998166144549843,
+      "loss": 0.7658900022506714,
+      "step": 1192
+    },
+    {
+      "epoch": 0.515210355987055,
+      "grad_norm": 0.42312702536582947,
+      "learning_rate": 0.00019998070898052521,
+      "loss": 0.9365432858467102,
+      "step": 1194
+    },
+    {
+      "epoch": 0.5160733549083064,
+      "grad_norm": 0.4652721881866455,
+      "learning_rate": 0.00019997973240565476,
+      "loss": 0.771016538143158,
+      "step": 1196
+    },
+    {
+      "epoch": 0.5169363538295577,
+      "grad_norm": 0.5048499703407288,
+      "learning_rate": 0.00019997873172112254,
+      "loss": 0.9123705625534058,
+      "step": 1198
+    },
+    {
+      "epoch": 0.517799352750809,
+      "grad_norm": 0.5446439981460571,
+      "learning_rate": 0.0001999777069271699,
+      "loss": 0.8975751399993896,
+      "step": 1200
+    },
+    {
+      "epoch": 0.517799352750809,
+      "eval_loss": 0.9344067573547363,
+      "eval_runtime": 658.6934,
+      "eval_samples_per_second": 3.127,
+      "eval_steps_per_second": 3.127,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5186623516720604,
+      "grad_norm": 0.5044088959693909,
+      "learning_rate": 0.0001999766580240439,
+      "loss": 0.89097660779953,
+      "step": 1202
+    },
+    {
+      "epoch": 0.5195253505933117,
+      "grad_norm": 0.4672294855117798,
+      "learning_rate": 0.00019997558501199753,
+      "loss": 0.9138525128364563,
+      "step": 1204
+    },
+    {
+      "epoch": 0.5203883495145631,
+      "grad_norm": 0.45749008655548096,
+      "learning_rate": 0.00019997448789128952,
+      "loss": 0.8946340680122375,
+      "step": 1206
+    },
+    {
+      "epoch": 0.5212513484358144,
+      "grad_norm": 0.4828707277774811,
+      "learning_rate": 0.00019997336666218447,
+      "loss": 0.8661436438560486,
+      "step": 1208
+    },
+    {
+      "epoch": 0.5221143473570659,
+      "grad_norm": 0.3975147008895874,
+      "learning_rate": 0.0001999722213249527,
+      "loss": 0.7684835195541382,
+      "step": 1210
+    },
+    {
+      "epoch": 0.5229773462783172,
+      "grad_norm": 0.5642077326774597,
+      "learning_rate": 0.00019997105187987045,
+      "loss": 0.9667536616325378,
+      "step": 1212
+    },
+    {
+      "epoch": 0.5238403451995685,
+      "grad_norm": 0.4907105565071106,
+      "learning_rate": 0.00019996985832721972,
+      "loss": 0.8679366707801819,
+      "step": 1214
+    },
+    {
+      "epoch": 0.5247033441208199,
+      "grad_norm": 0.46214789152145386,
+      "learning_rate": 0.0001999686406672883,
+      "loss": 0.8802784085273743,
+      "step": 1216
+    },
+    {
+      "epoch": 0.5255663430420712,
+      "grad_norm": 0.4355131685733795,
+      "learning_rate": 0.00019996739890036985,
+      "loss": 0.8493598103523254,
+      "step": 1218
+    },
+    {
+      "epoch": 0.5264293419633226,
+      "grad_norm": 0.4293915331363678,
+      "learning_rate": 0.0001999661330267638,
+      "loss": 0.8949980735778809,
+      "step": 1220
+    },
+    {
+      "epoch": 0.5272923408845739,
+      "grad_norm": 0.5452485680580139,
+      "learning_rate": 0.00019996484304677544,
+      "loss": 0.9497376680374146,
+      "step": 1222
+    },
+    {
+      "epoch": 0.5281553398058253,
+      "grad_norm": 0.45874500274658203,
+      "learning_rate": 0.00019996352896071583,
+      "loss": 0.9170818328857422,
+      "step": 1224
+    },
+    {
+      "epoch": 0.5290183387270766,
+      "grad_norm": 0.4414025843143463,
+      "learning_rate": 0.00019996219076890182,
+      "loss": 0.7557252645492554,
+      "step": 1226
+    },
+    {
+      "epoch": 0.5298813376483279,
+      "grad_norm": 0.4891829192638397,
+      "learning_rate": 0.0001999608284716562,
+      "loss": 0.848960816860199,
+      "step": 1228
+    },
+    {
+      "epoch": 0.5307443365695793,
+      "grad_norm": 0.5048345327377319,
+      "learning_rate": 0.00019995944206930734,
+      "loss": 0.9555954933166504,
+      "step": 1230
+    },
+    {
+      "epoch": 0.5316073354908306,
+      "grad_norm": 0.5006756782531738,
+      "learning_rate": 0.00019995803156218968,
+      "loss": 0.8080939054489136,
+      "step": 1232
+    },
+    {
+      "epoch": 0.532470334412082,
+      "grad_norm": 0.5422173738479614,
+      "learning_rate": 0.00019995659695064332,
+      "loss": 0.8638371825218201,
+      "step": 1234
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.4535163640975952,
+      "learning_rate": 0.0001999551382350142,
+      "loss": 0.889068067073822,
+      "step": 1236
+    },
+    {
+      "epoch": 0.5341963322545846,
+      "grad_norm": 0.4588642418384552,
+      "learning_rate": 0.00019995365541565412,
+      "loss": 0.8803121447563171,
+      "step": 1238
+    },
+    {
+      "epoch": 0.535059331175836,
+      "grad_norm": 0.49366191029548645,
+      "learning_rate": 0.00019995214849292064,
+      "loss": 0.9694926738739014,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5359223300970873,
+      "grad_norm": 0.41988301277160645,
+      "learning_rate": 0.0001999506174671771,
+      "loss": 0.8367960453033447,
+      "step": 1242
+    },
+    {
+      "epoch": 0.5367853290183388,
+      "grad_norm": 0.5242130160331726,
+      "learning_rate": 0.00019994906233879273,
+      "loss": 0.942340612411499,
+      "step": 1244
+    },
+    {
+      "epoch": 0.53764832793959,
+      "grad_norm": 0.4899834096431732,
+      "learning_rate": 0.00019994748310814256,
+      "loss": 0.8926790356636047,
+      "step": 1246
+    },
+    {
+      "epoch": 0.5385113268608415,
+      "grad_norm": 0.5496823787689209,
+      "learning_rate": 0.00019994587977560744,
+      "loss": 0.99891597032547,
+      "step": 1248
+    },
+    {
+      "epoch": 0.5393743257820928,
+      "grad_norm": 0.4497414231300354,
+      "learning_rate": 0.00019994425234157396,
+      "loss": 0.8873116970062256,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5402373247033441,
+      "grad_norm": 0.4256928563117981,
+      "learning_rate": 0.00019994260080643454,
+      "loss": 0.9041396975517273,
+      "step": 1252
+    },
+    {
+      "epoch": 0.5411003236245955,
+      "grad_norm": 0.36910608410835266,
+      "learning_rate": 0.00019994092517058753,
+      "loss": 0.7647561430931091,
+      "step": 1254
+    },
+    {
+      "epoch": 0.5419633225458468,
+      "grad_norm": 0.537584125995636,
+      "learning_rate": 0.0001999392254344369,
+      "loss": 0.8892287015914917,
+      "step": 1256
+    },
+    {
+      "epoch": 0.5428263214670982,
+      "grad_norm": 0.49463894963264465,
+      "learning_rate": 0.00019993750159839264,
+      "loss": 0.8638571500778198,
+      "step": 1258
+    },
+    {
+      "epoch": 0.5436893203883495,
+      "grad_norm": 0.5052056908607483,
+      "learning_rate": 0.00019993575366287036,
+      "loss": 0.8165372014045715,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5445523193096009,
+      "grad_norm": 0.47367510199546814,
+      "learning_rate": 0.0001999339816282916,
+      "loss": 0.9099977016448975,
+      "step": 1262
+    },
+    {
+      "epoch": 0.5454153182308522,
+      "grad_norm": 0.4600350558757782,
+      "learning_rate": 0.00019993218549508364,
+      "loss": 0.8557311296463013,
+      "step": 1264
+    },
+    {
+      "epoch": 0.5462783171521035,
+      "grad_norm": 0.5684534311294556,
+      "learning_rate": 0.0001999303652636797,
+      "loss": 0.9136497974395752,
+      "step": 1266
+    },
+    {
+      "epoch": 0.5471413160733549,
+      "grad_norm": 0.5151359438896179,
+      "learning_rate": 0.00019992852093451865,
+      "loss": 0.7906932830810547,
+      "step": 1268
+    },
+    {
+      "epoch": 0.5480043149946062,
+      "grad_norm": 0.48577409982681274,
+      "learning_rate": 0.00019992665250804525,
+      "loss": 0.9326766133308411,
+      "step": 1270
+    },
+    {
+      "epoch": 0.5488673139158576,
+      "grad_norm": 0.490531325340271,
+      "learning_rate": 0.00019992475998471004,
+      "loss": 0.9734495878219604,
+      "step": 1272
+    },
+    {
+      "epoch": 0.5497303128371089,
+      "grad_norm": 0.5092435479164124,
+      "learning_rate": 0.00019992284336496947,
+      "loss": 0.8728410005569458,
+      "step": 1274
+    },
+    {
+      "epoch": 0.5505933117583603,
+      "grad_norm": 0.3843296766281128,
+      "learning_rate": 0.00019992090264928566,
+      "loss": 0.7572637796401978,
+      "step": 1276
+    },
+    {
+      "epoch": 0.5514563106796116,
+      "grad_norm": 0.534304678440094,
+      "learning_rate": 0.00019991893783812662,
+      "loss": 0.8895323872566223,
+      "step": 1278
+    },
+    {
+      "epoch": 0.552319309600863,
+      "grad_norm": 0.4567227363586426,
+      "learning_rate": 0.00019991694893196614,
+      "loss": 0.9318088293075562,
+      "step": 1280
+    },
+    {
+      "epoch": 0.5531823085221144,
+      "grad_norm": 0.48464900255203247,
+      "learning_rate": 0.0001999149359312839,
+      "loss": 0.8541979789733887,
+      "step": 1282
+    },
+    {
+      "epoch": 0.5540453074433657,
+      "grad_norm": 0.5569567084312439,
+      "learning_rate": 0.00019991289883656524,
+      "loss": 0.977894127368927,
+      "step": 1284
+    },
+    {
+      "epoch": 0.5549083063646171,
+      "grad_norm": 0.4637227952480316,
+      "learning_rate": 0.00019991083764830145,
+      "loss": 0.8860608339309692,
+      "step": 1286
+    },
+    {
+      "epoch": 0.5557713052858684,
+      "grad_norm": 0.4096687436103821,
+      "learning_rate": 0.00019990875236698956,
+      "loss": 0.8429648876190186,
+      "step": 1288
+    },
+    {
+      "epoch": 0.5566343042071198,
+      "grad_norm": 0.5221695303916931,
+      "learning_rate": 0.00019990664299313242,
+      "loss": 0.8510909080505371,
+      "step": 1290
+    },
+    {
+      "epoch": 0.5574973031283711,
+      "grad_norm": 0.5155899524688721,
+      "learning_rate": 0.00019990450952723872,
+      "loss": 0.8971074223518372,
+      "step": 1292
+    },
+    {
+      "epoch": 0.5583603020496224,
+      "grad_norm": 0.5064809322357178,
+      "learning_rate": 0.0001999023519698229,
+      "loss": 0.9030373096466064,
+      "step": 1294
+    },
+    {
+      "epoch": 0.5592233009708738,
+      "grad_norm": 0.40551698207855225,
+      "learning_rate": 0.00019990017032140526,
+      "loss": 0.7866057753562927,
+      "step": 1296
+    },
+    {
+      "epoch": 0.5600862998921251,
+      "grad_norm": 0.5009430050849915,
+      "learning_rate": 0.00019989796458251194,
+      "loss": 0.9477730989456177,
+      "step": 1298
+    },
+    {
+      "epoch": 0.5609492988133765,
+      "grad_norm": 0.5192028880119324,
+      "learning_rate": 0.00019989573475367477,
+      "loss": 0.9206778407096863,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5609492988133765,
+      "eval_loss": 0.9177446365356445,
+      "eval_runtime": 665.3245,
+      "eval_samples_per_second": 3.096,
+      "eval_steps_per_second": 3.096,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5618122977346278,
+      "grad_norm": 0.5580230951309204,
+      "learning_rate": 0.00019989348083543148,
+      "loss": 0.9516512155532837,
+      "step": 1302
+    },
+    {
+      "epoch": 0.5626752966558792,
+      "grad_norm": 0.4151005744934082,
+      "learning_rate": 0.00019989120282832564,
+      "loss": 0.7725991606712341,
+      "step": 1304
+    },
+    {
+      "epoch": 0.5635382955771305,
+      "grad_norm": 0.56330406665802,
+      "learning_rate": 0.00019988890073290656,
+      "loss": 0.9241501688957214,
+      "step": 1306
+    },
+    {
+      "epoch": 0.5644012944983818,
+      "grad_norm": 0.44836440682411194,
+      "learning_rate": 0.00019988657454972936,
+      "loss": 0.8351686000823975,
+      "step": 1308
+    },
+    {
+      "epoch": 0.5652642934196332,
+      "grad_norm": 0.5414754152297974,
+      "learning_rate": 0.00019988422427935496,
+      "loss": 0.9033217430114746,
+      "step": 1310
+    },
+    {
+      "epoch": 0.5661272923408845,
+      "grad_norm": 0.5283750891685486,
+      "learning_rate": 0.0001998818499223502,
+      "loss": 0.8885331153869629,
+      "step": 1312
+    },
+    {
+      "epoch": 0.566990291262136,
+      "grad_norm": 0.45846256613731384,
+      "learning_rate": 0.00019987945147928758,
+      "loss": 0.8359912037849426,
+      "step": 1314
+    },
+    {
+      "epoch": 0.5678532901833873,
+      "grad_norm": 0.44439879059791565,
+      "learning_rate": 0.0001998770289507455,
+      "loss": 0.8327895402908325,
+      "step": 1316
+    },
+    {
+      "epoch": 0.5687162891046387,
+      "grad_norm": 0.5491341948509216,
+      "learning_rate": 0.00019987458233730813,
+      "loss": 0.9354757070541382,
+      "step": 1318
+    },
+    {
+      "epoch": 0.56957928802589,
+      "grad_norm": 0.5502263307571411,
+      "learning_rate": 0.00019987211163956548,
+      "loss": 0.944054901599884,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5704422869471413,
+      "grad_norm": 0.47165682911872864,
+      "learning_rate": 0.00019986961685811334,
+      "loss": 0.9515072107315063,
+      "step": 1322
+    },
+    {
+      "epoch": 0.5713052858683927,
+      "grad_norm": 0.5136987566947937,
+      "learning_rate": 0.0001998670979935533,
+      "loss": 0.9455493688583374,
+      "step": 1324
+    },
+    {
+      "epoch": 0.572168284789644,
+      "grad_norm": 0.4822693169116974,
+      "learning_rate": 0.00019986455504649277,
+      "loss": 0.8626728057861328,
+      "step": 1326
+    },
+    {
+      "epoch": 0.5730312837108954,
+      "grad_norm": 0.4639468193054199,
+      "learning_rate": 0.000199861988017545,
+      "loss": 0.8857194781303406,
+      "step": 1328
+    },
+    {
+      "epoch": 0.5738942826321467,
+      "grad_norm": 0.5224950313568115,
+      "learning_rate": 0.00019985939690732898,
+      "loss": 0.9198446273803711,
+      "step": 1330
+    },
+    {
+      "epoch": 0.574757281553398,
+      "grad_norm": 0.47504499554634094,
+      "learning_rate": 0.00019985678171646954,
+      "loss": 0.8785439133644104,
+      "step": 1332
+    },
+    {
+      "epoch": 0.5756202804746494,
+      "grad_norm": 0.5022051930427551,
+      "learning_rate": 0.0001998541424455974,
+      "loss": 0.9593754410743713,
+      "step": 1334
+    },
+    {
+      "epoch": 0.5764832793959007,
+      "grad_norm": 0.4572875201702118,
+      "learning_rate": 0.00019985147909534897,
+      "loss": 0.986197292804718,
+      "step": 1336
+    },
+    {
+      "epoch": 0.5773462783171521,
+      "grad_norm": 0.5153827667236328,
+      "learning_rate": 0.00019984879166636644,
+      "loss": 0.9163863658905029,
+      "step": 1338
+    },
+    {
+      "epoch": 0.5782092772384034,
+      "grad_norm": 0.4813650846481323,
+      "learning_rate": 0.00019984608015929792,
+      "loss": 0.8815995454788208,
+      "step": 1340
+    },
+    {
+      "epoch": 0.5790722761596548,
+      "grad_norm": 0.4319819211959839,
+      "learning_rate": 0.0001998433445747973,
+      "loss": 0.857044517993927,
+      "step": 1342
+    },
+    {
+      "epoch": 0.5799352750809061,
+      "grad_norm": 0.5128870010375977,
+      "learning_rate": 0.00019984058491352423,
+      "loss": 0.8939256072044373,
+      "step": 1344
+    },
+    {
+      "epoch": 0.5807982740021574,
+      "grad_norm": 0.41450315713882446,
+      "learning_rate": 0.0001998378011761442,
+      "loss": 0.9267327785491943,
+      "step": 1346
+    },
+    {
+      "epoch": 0.5816612729234089,
+      "grad_norm": 0.42916348576545715,
+      "learning_rate": 0.00019983499336332844,
+      "loss": 0.8494639992713928,
+      "step": 1348
+    },
+    {
+      "epoch": 0.5825242718446602,
+      "grad_norm": 0.43995746970176697,
+      "learning_rate": 0.00019983216147575412,
+      "loss": 0.9720427989959717,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5833872707659116,
+      "grad_norm": 0.5063773989677429,
+      "learning_rate": 0.00019982930551410411,
+      "loss": 0.9400854706764221,
+      "step": 1352
+    },
+    {
+      "epoch": 0.5842502696871629,
+      "grad_norm": 0.5029586553573608,
+      "learning_rate": 0.0001998264254790671,
+      "loss": 0.8657845258712769,
+      "step": 1354
+    },
+    {
+      "epoch": 0.5851132686084143,
+      "grad_norm": 0.45519232749938965,
+      "learning_rate": 0.00019982352137133764,
+      "loss": 0.8593506813049316,
+      "step": 1356
+    },
+    {
+      "epoch": 0.5859762675296656,
+      "grad_norm": 0.49116215109825134,
+      "learning_rate": 0.000199820593191616,
+      "loss": 0.8658114671707153,
+      "step": 1358
+    },
+    {
+      "epoch": 0.5868392664509169,
+      "grad_norm": 0.45347318053245544,
+      "learning_rate": 0.00019981764094060826,
+      "loss": 0.8044605255126953,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5877022653721683,
+      "grad_norm": 0.5191754698753357,
+      "learning_rate": 0.00019981466461902643,
+      "loss": 0.9176861047744751,
+      "step": 1362
+    },
+    {
+      "epoch": 0.5885652642934196,
+      "grad_norm": 0.4791528284549713,
+      "learning_rate": 0.00019981166422758818,
+      "loss": 0.8453370928764343,
+      "step": 1364
+    },
+    {
+      "epoch": 0.589428263214671,
+      "grad_norm": 0.5105116367340088,
+      "learning_rate": 0.00019980863976701705,
+      "loss": 0.9343777298927307,
+      "step": 1366
+    },
+    {
+      "epoch": 0.5902912621359223,
+      "grad_norm": 0.44593656063079834,
+      "learning_rate": 0.00019980559123804236,
+      "loss": 0.8950760960578918,
+      "step": 1368
+    },
+    {
+      "epoch": 0.5911542610571737,
+      "grad_norm": 0.4375658631324768,
+      "learning_rate": 0.0001998025186413993,
+      "loss": 0.8613521456718445,
+      "step": 1370
+    },
+    {
+      "epoch": 0.592017259978425,
+      "grad_norm": 0.5138815641403198,
+      "learning_rate": 0.00019979942197782878,
+      "loss": 0.8982083201408386,
+      "step": 1372
+    },
+    {
+      "epoch": 0.5928802588996763,
+      "grad_norm": 0.45473602414131165,
+      "learning_rate": 0.00019979630124807753,
+      "loss": 0.9372450709342957,
+      "step": 1374
+    },
+    {
+      "epoch": 0.5937432578209277,
+      "grad_norm": 0.4961191713809967,
+      "learning_rate": 0.00019979315645289814,
+      "loss": 0.8758652806282043,
+      "step": 1376
+    },
+    {
+      "epoch": 0.594606256742179,
+      "grad_norm": 0.5672827363014221,
+      "learning_rate": 0.00019978998759304895,
+      "loss": 0.9852207899093628,
+      "step": 1378
+    },
+    {
+      "epoch": 0.5954692556634305,
+      "grad_norm": 0.44907906651496887,
+      "learning_rate": 0.00019978679466929407,
+      "loss": 0.8451287746429443,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5963322545846818,
+      "grad_norm": 0.4759652316570282,
+      "learning_rate": 0.00019978357768240352,
+      "loss": 0.8381558656692505,
+      "step": 1382
+    },
+    {
+      "epoch": 0.5971952535059332,
+      "grad_norm": 0.4936048686504364,
+      "learning_rate": 0.00019978033663315304,
+      "loss": 0.8820816874504089,
+      "step": 1384
+    },
+    {
+      "epoch": 0.5980582524271845,
+      "grad_norm": 0.44983741641044617,
+      "learning_rate": 0.00019977707152232416,
+      "loss": 0.9156787991523743,
+      "step": 1386
+    },
+    {
+      "epoch": 0.5989212513484358,
+      "grad_norm": 0.45198705792427063,
+      "learning_rate": 0.0001997737823507043,
+      "loss": 0.8285194039344788,
+      "step": 1388
+    },
+    {
+      "epoch": 0.5997842502696872,
+      "grad_norm": 0.45788463950157166,
+      "learning_rate": 0.00019977046911908664,
+      "loss": 0.8109505772590637,
+      "step": 1390
+    },
+    {
+      "epoch": 0.6006472491909385,
+      "grad_norm": 0.4795142412185669,
+      "learning_rate": 0.0001997671318282701,
+      "loss": 0.8285947442054749,
+      "step": 1392
+    },
+    {
+      "epoch": 0.6015102481121899,
+      "grad_norm": 0.5026728510856628,
+      "learning_rate": 0.00019976377047905945,
+      "loss": 0.9497535228729248,
+      "step": 1394
+    },
+    {
+      "epoch": 0.6023732470334412,
+      "grad_norm": 0.4994853734970093,
+      "learning_rate": 0.0001997603850722653,
+      "loss": 0.9171916246414185,
+      "step": 1396
+    },
+    {
+      "epoch": 0.6032362459546926,
+      "grad_norm": 0.4789866507053375,
+      "learning_rate": 0.00019975697560870403,
+      "loss": 0.7894434928894043,
+      "step": 1398
+    },
+    {
+      "epoch": 0.6040992448759439,
+      "grad_norm": 0.42282742261886597,
+      "learning_rate": 0.0001997535420891978,
+      "loss": 0.8942429423332214,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6040992448759439,
+      "eval_loss": 0.9080492854118347,
+      "eval_runtime": 661.4597,
+      "eval_samples_per_second": 3.114,
+      "eval_steps_per_second": 3.114,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6049622437971952,
+      "grad_norm": 0.5789905190467834,
+      "learning_rate": 0.00019975008451457454,
+      "loss": 0.8938372731208801,
+      "step": 1402
+    },
+    {
+      "epoch": 0.6058252427184466,
+      "grad_norm": 0.46121683716773987,
+      "learning_rate": 0.00019974660288566814,
+      "loss": 0.8746235370635986,
+      "step": 1404
+    },
+    {
+      "epoch": 0.6066882416396979,
+      "grad_norm": 0.5195551514625549,
+      "learning_rate": 0.00019974309720331807,
+      "loss": 0.8650617003440857,
+      "step": 1406
+    },
+    {
+      "epoch": 0.6075512405609493,
+      "grad_norm": 0.46930259466171265,
+      "learning_rate": 0.00019973956746836976,
+      "loss": 0.8853039145469666,
+      "step": 1408
+    },
+    {
+      "epoch": 0.6084142394822006,
+      "grad_norm": 0.40869632363319397,
+      "learning_rate": 0.0001997360136816744,
+      "loss": 0.7865594029426575,
+      "step": 1410
+    },
+    {
+      "epoch": 0.609277238403452,
+      "grad_norm": 0.5398361086845398,
+      "learning_rate": 0.00019973243584408895,
+      "loss": 0.907535970211029,
+      "step": 1412
+    },
+    {
+      "epoch": 0.6101402373247033,
+      "grad_norm": 0.5110154747962952,
+      "learning_rate": 0.00019972883395647615,
+      "loss": 0.8682730197906494,
+      "step": 1414
+    },
+    {
+      "epoch": 0.6110032362459547,
+      "grad_norm": 0.44484639167785645,
+      "learning_rate": 0.00019972520801970467,
+      "loss": 0.8786011338233948,
+      "step": 1416
+    },
+    {
+      "epoch": 0.6118662351672061,
+      "grad_norm": 0.4768071472644806,
+      "learning_rate": 0.0001997215580346488,
+      "loss": 0.9021878242492676,
+      "step": 1418
+    },
+    {
+      "epoch": 0.6127292340884574,
+      "grad_norm": 0.43265241384506226,
+      "learning_rate": 0.0001997178840021888,
+      "loss": 0.7737482786178589,
+      "step": 1420
+    },
+    {
+      "epoch": 0.6135922330097088,
+      "grad_norm": 0.525692343711853,
+      "learning_rate": 0.0001997141859232106,
+      "loss": 0.876280665397644,
+      "step": 1422
+    },
+    {
+      "epoch": 0.6144552319309601,
+      "grad_norm": 0.48206865787506104,
+      "learning_rate": 0.00019971046379860594,
+      "loss": 0.8503577709197998,
+      "step": 1424
+    },
+    {
+      "epoch": 0.6153182308522115,
+      "grad_norm": 0.6032769680023193,
+      "learning_rate": 0.00019970671762927246,
+      "loss": 0.9459730982780457,
+      "step": 1426
+    },
+    {
+      "epoch": 0.6161812297734628,
+      "grad_norm": 0.4491981863975525,
+      "learning_rate": 0.0001997029474161135,
+      "loss": 0.8836647868156433,
+      "step": 1428
+    },
+    {
+      "epoch": 0.6170442286947141,
+      "grad_norm": 0.47503358125686646,
+      "learning_rate": 0.00019969915316003824,
+      "loss": 0.8614388108253479,
+      "step": 1430
+    },
+    {
+      "epoch": 0.6179072276159655,
+      "grad_norm": 0.44801047444343567,
+      "learning_rate": 0.00019969533486196162,
+      "loss": 0.8420360684394836,
+      "step": 1432
+    },
+    {
+      "epoch": 0.6187702265372168,
+      "grad_norm": 0.45057111978530884,
+      "learning_rate": 0.00019969149252280446,
+      "loss": 0.8256269693374634,
+      "step": 1434
+    },
+    {
+      "epoch": 0.6196332254584682,
+      "grad_norm": 0.4589645266532898,
+      "learning_rate": 0.00019968762614349327,
+      "loss": 0.9130199551582336,
+      "step": 1436
+    },
+    {
+      "epoch": 0.6204962243797195,
+      "grad_norm": 0.48914027214050293,
+      "learning_rate": 0.00019968373572496045,
+      "loss": 0.74083012342453,
+      "step": 1438
+    },
+    {
+      "epoch": 0.6213592233009708,
+      "grad_norm": 0.4582098424434662,
+      "learning_rate": 0.00019967982126814412,
+      "loss": 0.8538379669189453,
+      "step": 1440
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.48722779750823975,
+      "learning_rate": 0.00019967588277398823,
+      "loss": 0.8780114054679871,
+      "step": 1442
+    },
+    {
+      "epoch": 0.6230852211434735,
+      "grad_norm": 0.4291327893733978,
+      "learning_rate": 0.00019967192024344254,
+      "loss": 0.8341028690338135,
+      "step": 1444
+    },
+    {
+      "epoch": 0.623948220064725,
+      "grad_norm": 0.4773139953613281,
+      "learning_rate": 0.00019966793367746265,
+      "loss": 0.8651667237281799,
+      "step": 1446
+    },
+    {
+      "epoch": 0.6248112189859762,
+      "grad_norm": 0.45556166768074036,
+      "learning_rate": 0.00019966392307700986,
+      "loss": 0.8339929580688477,
+      "step": 1448
+    },
+    {
+      "epoch": 0.6256742179072277,
+      "grad_norm": 0.5126671195030212,
+      "learning_rate": 0.00019965988844305129,
+      "loss": 0.9129340052604675,
+      "step": 1450
+    },
+    {
+      "epoch": 0.626537216828479,
+      "grad_norm": 0.6067109704017639,
+      "learning_rate": 0.00019965582977655988,
+      "loss": 0.9057610034942627,
+      "step": 1452
+    },
+    {
+      "epoch": 0.6274002157497303,
+      "grad_norm": 0.46425968408584595,
+      "learning_rate": 0.00019965174707851438,
+      "loss": 0.874100387096405,
+      "step": 1454
+    },
+    {
+      "epoch": 0.6282632146709817,
+      "grad_norm": 0.481077641248703,
+      "learning_rate": 0.0001996476403498993,
+      "loss": 0.915635347366333,
+      "step": 1456
+    },
+    {
+      "epoch": 0.629126213592233,
+      "grad_norm": 0.47299909591674805,
+      "learning_rate": 0.000199643509591705,
+      "loss": 0.9059650301933289,
+      "step": 1458
+    },
+    {
+      "epoch": 0.6299892125134844,
+      "grad_norm": 0.48924630880355835,
+      "learning_rate": 0.00019963935480492753,
+      "loss": 0.9775188565254211,
+      "step": 1460
+    },
+    {
+      "epoch": 0.6308522114347357,
+      "grad_norm": 0.4407665431499481,
+      "learning_rate": 0.0001996351759905688,
+      "loss": 0.8950685858726501,
+      "step": 1462
+    },
+    {
+      "epoch": 0.6317152103559871,
+      "grad_norm": 0.5018318295478821,
+      "learning_rate": 0.00019963097314963657,
+      "loss": 0.8532119989395142,
+      "step": 1464
+    },
+    {
+      "epoch": 0.6325782092772384,
+      "grad_norm": 0.43245720863342285,
+      "learning_rate": 0.0001996267462831443,
+      "loss": 0.7775963544845581,
+      "step": 1466
+    },
+    {
+      "epoch": 0.6334412081984897,
+      "grad_norm": 0.5028865337371826,
+      "learning_rate": 0.00019962249539211125,
+      "loss": 0.8315839767456055,
+      "step": 1468
+    },
+    {
+      "epoch": 0.6343042071197411,
+      "grad_norm": 0.4697185754776001,
+      "learning_rate": 0.0001996182204775626,
+      "loss": 0.849076509475708,
+      "step": 1470
+    },
+    {
+      "epoch": 0.6351672060409924,
+      "grad_norm": 0.46725034713745117,
+      "learning_rate": 0.00019961392154052912,
+      "loss": 0.8828577995300293,
+      "step": 1472
+    },
+    {
+      "epoch": 0.6360302049622438,
+      "grad_norm": 0.4301203489303589,
+      "learning_rate": 0.00019960959858204754,
+      "loss": 0.850115954875946,
+      "step": 1474
+    },
+    {
+      "epoch": 0.6368932038834951,
+      "grad_norm": 0.46635881066322327,
+      "learning_rate": 0.0001996052516031603,
+      "loss": 0.7912618517875671,
+      "step": 1476
+    },
+    {
+      "epoch": 0.6377562028047465,
+      "grad_norm": 0.44143620133399963,
+      "learning_rate": 0.00019960088060491565,
+      "loss": 0.9072504639625549,
+      "step": 1478
+    },
+    {
+      "epoch": 0.6386192017259978,
+      "grad_norm": 0.47458893060684204,
+      "learning_rate": 0.00019959648558836763,
+      "loss": 0.8976638317108154,
+      "step": 1480
+    },
+    {
+      "epoch": 0.6394822006472491,
+      "grad_norm": 0.4596816897392273,
+      "learning_rate": 0.00019959206655457612,
+      "loss": 0.8142043352127075,
+      "step": 1482
+    },
+    {
+      "epoch": 0.6403451995685006,
+      "grad_norm": 0.4839977025985718,
+      "learning_rate": 0.0001995876235046067,
+      "loss": 0.860643744468689,
+      "step": 1484
+    },
+    {
+      "epoch": 0.6412081984897519,
+      "grad_norm": 0.3542814552783966,
+      "learning_rate": 0.00019958315643953085,
+      "loss": 0.7586524486541748,
+      "step": 1486
+    },
+    {
+      "epoch": 0.6420711974110033,
+      "grad_norm": 0.5423269271850586,
+      "learning_rate": 0.00019957866536042572,
+      "loss": 0.9353570342063904,
+      "step": 1488
+    },
+    {
+      "epoch": 0.6429341963322546,
+      "grad_norm": 0.4580909013748169,
+      "learning_rate": 0.00019957415026837437,
+      "loss": 0.9919291138648987,
+      "step": 1490
+    },
+    {
+      "epoch": 0.643797195253506,
+      "grad_norm": 0.4211732745170593,
+      "learning_rate": 0.00019956961116446555,
+      "loss": 0.8720914125442505,
+      "step": 1492
+    },
+    {
+      "epoch": 0.6446601941747573,
+      "grad_norm": 0.4583161175251007,
+      "learning_rate": 0.00019956504804979384,
+      "loss": 0.8661212921142578,
+      "step": 1494
+    },
+    {
+      "epoch": 0.6455231930960086,
+      "grad_norm": 0.4359884262084961,
+      "learning_rate": 0.00019956046092545966,
+      "loss": 0.8170996308326721,
+      "step": 1496
+    },
+    {
+      "epoch": 0.64638619201726,
+      "grad_norm": 0.4642556607723236,
+      "learning_rate": 0.00019955584979256913,
+      "loss": 0.8607422113418579,
+      "step": 1498
+    },
+    {
+      "epoch": 0.6472491909385113,
+      "grad_norm": 0.4496007561683655,
+      "learning_rate": 0.00019955121465223426,
+      "loss": 0.837529182434082,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6472491909385113,
+      "eval_loss": 0.8972997665405273,
+      "eval_runtime": 649.796,
+      "eval_samples_per_second": 3.17,
+      "eval_steps_per_second": 3.17,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6481121898597627,
+      "grad_norm": 0.48363205790519714,
+      "learning_rate": 0.0001995465555055727,
+      "loss": 0.9355250000953674,
+      "step": 1502
+    },
+    {
+      "epoch": 0.648975188781014,
+      "grad_norm": 0.44681695103645325,
+      "learning_rate": 0.0001995418723537081,
+      "loss": 0.8286949396133423,
+      "step": 1504
+    },
+    {
+      "epoch": 0.6498381877022654,
+      "grad_norm": 0.5110394358634949,
+      "learning_rate": 0.00019953716519776967,
+      "loss": 0.890398383140564,
+      "step": 1506
+    },
+    {
+      "epoch": 0.6507011866235167,
+      "grad_norm": 0.4353160262107849,
+      "learning_rate": 0.00019953243403889257,
+      "loss": 0.8117311000823975,
+      "step": 1508
+    },
+    {
+      "epoch": 0.651564185544768,
+      "grad_norm": 0.4731789231300354,
+      "learning_rate": 0.0001995276788782177,
+      "loss": 0.8255904316902161,
+      "step": 1510
+    },
+    {
+      "epoch": 0.6524271844660194,
+      "grad_norm": 0.5447185039520264,
+      "learning_rate": 0.00019952289971689177,
+      "loss": 0.9371263384819031,
+      "step": 1512
+    },
+    {
+      "epoch": 0.6532901833872707,
+      "grad_norm": 0.47616517543792725,
+      "learning_rate": 0.0001995180965560672,
+      "loss": 0.8532910943031311,
+      "step": 1514
+    },
+    {
+      "epoch": 0.6541531823085222,
+      "grad_norm": 0.4412213861942291,
+      "learning_rate": 0.0001995132693969023,
+      "loss": 0.8799141645431519,
+      "step": 1516
+    },
+    {
+      "epoch": 0.6550161812297735,
+      "grad_norm": 0.469911128282547,
+      "learning_rate": 0.00019950841824056107,
+      "loss": 0.8395764827728271,
+      "step": 1518
+    },
+    {
+      "epoch": 0.6558791801510249,
+      "grad_norm": 0.5236243009567261,
+      "learning_rate": 0.00019950354308821336,
+      "loss": 0.9556697010993958,
+      "step": 1520
+    },
+    {
+      "epoch": 0.6567421790722762,
+      "grad_norm": 0.4441990256309509,
+      "learning_rate": 0.00019949864394103482,
+      "loss": 0.8524283170700073,
+      "step": 1522
+    },
+    {
+      "epoch": 0.6576051779935275,
+      "grad_norm": 0.4173077940940857,
+      "learning_rate": 0.00019949372080020682,
+      "loss": 0.9213772416114807,
+      "step": 1524
+    },
+    {
+      "epoch": 0.6584681769147789,
+      "grad_norm": 0.4404120147228241,
+      "learning_rate": 0.00019948877366691658,
+      "loss": 0.9236897230148315,
+      "step": 1526
+    },
+    {
+      "epoch": 0.6593311758360302,
+      "grad_norm": 0.4586230516433716,
+      "learning_rate": 0.00019948380254235706,
+      "loss": 0.8373230695724487,
+      "step": 1528
+    },
+    {
+      "epoch": 0.6601941747572816,
+      "grad_norm": 0.4136028587818146,
+      "learning_rate": 0.00019947880742772703,
+      "loss": 0.8256528377532959,
+      "step": 1530
+    },
+    {
+      "epoch": 0.6610571736785329,
+      "grad_norm": 0.5007129907608032,
+      "learning_rate": 0.00019947378832423107,
+      "loss": 0.8580789566040039,
+      "step": 1532
+    },
+    {
+      "epoch": 0.6619201725997842,
+      "grad_norm": 0.39050203561782837,
+      "learning_rate": 0.00019946874523307947,
+      "loss": 0.7647744417190552,
+      "step": 1534
+    },
+    {
+      "epoch": 0.6627831715210356,
+      "grad_norm": 0.4640588164329529,
+      "learning_rate": 0.00019946367815548835,
+      "loss": 0.9042545557022095,
+      "step": 1536
+    },
+    {
+      "epoch": 0.6636461704422869,
+      "grad_norm": 0.5304957032203674,
+      "learning_rate": 0.00019945858709267963,
+      "loss": 0.9114110469818115,
+      "step": 1538
+    },
+    {
+      "epoch": 0.6645091693635383,
+      "grad_norm": 0.5426004528999329,
+      "learning_rate": 0.000199453472045881,
+      "loss": 0.8239460587501526,
+      "step": 1540
+    },
+    {
+      "epoch": 0.6653721682847896,
+      "grad_norm": 0.44893568754196167,
+      "learning_rate": 0.00019944833301632593,
+      "loss": 0.8091367483139038,
+      "step": 1542
+    },
+    {
+      "epoch": 0.666235167206041,
+      "grad_norm": 0.4294016361236572,
+      "learning_rate": 0.00019944317000525366,
+      "loss": 0.9202280640602112,
+      "step": 1544
+    },
+    {
+      "epoch": 0.6670981661272923,
+      "grad_norm": 0.449633926153183,
+      "learning_rate": 0.00019943798301390927,
+      "loss": 0.8884767889976501,
+      "step": 1546
+    },
+    {
+      "epoch": 0.6679611650485436,
+      "grad_norm": 0.4516827166080475,
+      "learning_rate": 0.0001994327720435435,
+      "loss": 0.8390879034996033,
+      "step": 1548
+    },
+    {
+      "epoch": 0.668824163969795,
+      "grad_norm": 0.422270268201828,
+      "learning_rate": 0.000199427537095413,
+      "loss": 0.7388033270835876,
+      "step": 1550
+    },
+    {
+      "epoch": 0.6696871628910464,
+      "grad_norm": 0.580563485622406,
+      "learning_rate": 0.00019942227817078015,
+      "loss": 0.9268350601196289,
+      "step": 1552
+    },
+    {
+      "epoch": 0.6705501618122978,
+      "grad_norm": 0.4436347782611847,
+      "learning_rate": 0.00019941699527091316,
+      "loss": 0.7978561520576477,
+      "step": 1554
+    },
+    {
+      "epoch": 0.6714131607335491,
+      "grad_norm": 0.4149787127971649,
+      "learning_rate": 0.0001994116883970859,
+      "loss": 0.8229286670684814,
+      "step": 1556
+    },
+    {
+      "epoch": 0.6722761596548005,
+      "grad_norm": 0.49915504455566406,
+      "learning_rate": 0.00019940635755057813,
+      "loss": 0.8554545640945435,
+      "step": 1558
+    },
+    {
+      "epoch": 0.6731391585760518,
+      "grad_norm": 0.45326656103134155,
+      "learning_rate": 0.00019940100273267537,
+      "loss": 0.9135572910308838,
+      "step": 1560
+    },
+    {
+      "epoch": 0.6740021574973031,
+      "grad_norm": 0.48639237880706787,
+      "learning_rate": 0.0001993956239446689,
+      "loss": 0.7769742012023926,
+      "step": 1562
+    },
+    {
+      "epoch": 0.6748651564185545,
+      "grad_norm": 0.5072791576385498,
+      "learning_rate": 0.0001993902211878558,
+      "loss": 0.9626237154006958,
+      "step": 1564
+    },
+    {
+      "epoch": 0.6757281553398058,
+      "grad_norm": 0.4646652638912201,
+      "learning_rate": 0.00019938479446353892,
+      "loss": 0.8506941199302673,
+      "step": 1566
+    },
+    {
+      "epoch": 0.6765911542610572,
+      "grad_norm": 0.4343051314353943,
+      "learning_rate": 0.00019937934377302688,
+      "loss": 0.8172947764396667,
+      "step": 1568
+    },
+    {
+      "epoch": 0.6774541531823085,
+      "grad_norm": 0.46890193223953247,
+      "learning_rate": 0.00019937386911763407,
+      "loss": 0.9215856790542603,
+      "step": 1570
+    },
+    {
+      "epoch": 0.6783171521035599,
+      "grad_norm": 0.5121113061904907,
+      "learning_rate": 0.0001993683704986807,
+      "loss": 0.8099892139434814,
+      "step": 1572
+    },
+    {
+      "epoch": 0.6791801510248112,
+      "grad_norm": 0.4652405083179474,
+      "learning_rate": 0.0001993628479174928,
+      "loss": 0.8675104975700378,
+      "step": 1574
+    },
+    {
+      "epoch": 0.6800431499460625,
+      "grad_norm": 0.4599422812461853,
+      "learning_rate": 0.00019935730137540198,
+      "loss": 0.7938929200172424,
+      "step": 1576
+    },
+    {
+      "epoch": 0.6809061488673139,
+      "grad_norm": 0.4738059937953949,
+      "learning_rate": 0.0001993517308737459,
+      "loss": 0.8610570430755615,
+      "step": 1578
+    },
+    {
+      "epoch": 0.6817691477885652,
+      "grad_norm": 0.5161214470863342,
+      "learning_rate": 0.00019934613641386776,
+      "loss": 0.9199413657188416,
+      "step": 1580
+    },
+    {
+      "epoch": 0.6826321467098166,
+      "grad_norm": 0.4284999370574951,
+      "learning_rate": 0.00019934051799711672,
+      "loss": 0.771649181842804,
+      "step": 1582
+    },
+    {
+      "epoch": 0.683495145631068,
+      "grad_norm": 0.5117548704147339,
+      "learning_rate": 0.00019933487562484757,
+      "loss": 0.8861327767372131,
+      "step": 1584
+    },
+    {
+      "epoch": 0.6843581445523194,
+      "grad_norm": 0.4964369833469391,
+      "learning_rate": 0.00019932920929842095,
+      "loss": 0.806983232498169,
+      "step": 1586
+    },
+    {
+      "epoch": 0.6852211434735707,
+      "grad_norm": 0.4699532091617584,
+      "learning_rate": 0.00019932351901920327,
+      "loss": 0.7963525652885437,
+      "step": 1588
+    },
+    {
+      "epoch": 0.686084142394822,
+      "grad_norm": 0.5329220294952393,
+      "learning_rate": 0.00019931780478856678,
+      "loss": 0.9406430721282959,
+      "step": 1590
+    },
+    {
+      "epoch": 0.6869471413160734,
+      "grad_norm": 0.49823835492134094,
+      "learning_rate": 0.00019931206660788936,
+      "loss": 0.8517770171165466,
+      "step": 1592
+    },
+    {
+      "epoch": 0.6878101402373247,
+      "grad_norm": 0.45245134830474854,
+      "learning_rate": 0.00019930630447855482,
+      "loss": 0.8703644275665283,
+      "step": 1594
+    },
+    {
+      "epoch": 0.6886731391585761,
+      "grad_norm": 0.47524577379226685,
+      "learning_rate": 0.0001993005184019526,
+      "loss": 0.9035283327102661,
+      "step": 1596
+    },
+    {
+      "epoch": 0.6895361380798274,
+      "grad_norm": 0.4537610411643982,
+      "learning_rate": 0.00019929470837947802,
+      "loss": 0.9173959493637085,
+      "step": 1598
+    },
+    {
+      "epoch": 0.6903991370010788,
+      "grad_norm": 0.42469722032546997,
+      "learning_rate": 0.00019928887441253212,
+      "loss": 0.8573579788208008,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6903991370010788,
+      "eval_loss": 0.8880587220191956,
+      "eval_runtime": 653.9515,
+      "eval_samples_per_second": 3.15,
+      "eval_steps_per_second": 3.15,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6912621359223301,
+      "grad_norm": 0.4388251304626465,
+      "learning_rate": 0.00019928301650252176,
+      "loss": 0.849348247051239,
+      "step": 1602
+    },
+    {
+      "epoch": 0.6921251348435814,
+      "grad_norm": 0.46086886525154114,
+      "learning_rate": 0.00019927713465085956,
+      "loss": 0.8298451900482178,
+      "step": 1604
+    },
+    {
+      "epoch": 0.6929881337648328,
+      "grad_norm": 0.42972785234451294,
+      "learning_rate": 0.00019927122885896387,
+      "loss": 0.8860712647438049,
+      "step": 1606
+    },
+    {
+      "epoch": 0.6938511326860841,
+      "grad_norm": 0.43009471893310547,
+      "learning_rate": 0.00019926529912825888,
+      "loss": 0.7972728610038757,
+      "step": 1608
+    },
+    {
+      "epoch": 0.6947141316073355,
+      "grad_norm": 0.3705308437347412,
+      "learning_rate": 0.00019925934546017446,
+      "loss": 0.8661653995513916,
+      "step": 1610
+    },
+    {
+      "epoch": 0.6955771305285868,
+      "grad_norm": 0.405208945274353,
+      "learning_rate": 0.00019925336785614635,
+      "loss": 0.8350111246109009,
+      "step": 1612
+    },
+    {
+      "epoch": 0.6964401294498382,
+      "grad_norm": 0.4773033857345581,
+      "learning_rate": 0.00019924736631761602,
+      "loss": 0.7920925617218018,
+      "step": 1614
+    },
+    {
+      "epoch": 0.6973031283710895,
+      "grad_norm": 0.4682428240776062,
+      "learning_rate": 0.00019924134084603075,
+      "loss": 0.8644304871559143,
+      "step": 1616
+    },
+    {
+      "epoch": 0.6981661272923408,
+      "grad_norm": 0.5694834589958191,
+      "learning_rate": 0.00019923529144284346,
+      "loss": 0.9897904992103577,
+      "step": 1618
+    },
+    {
+      "epoch": 0.6990291262135923,
+      "grad_norm": 0.40137484669685364,
+      "learning_rate": 0.00019922921810951302,
+      "loss": 0.6910083293914795,
+      "step": 1620
+    },
+    {
+      "epoch": 0.6998921251348436,
+      "grad_norm": 0.42076537013053894,
+      "learning_rate": 0.000199223120847504,
+      "loss": 0.8295826315879822,
+      "step": 1622
+    },
+    {
+      "epoch": 0.700755124056095,
+      "grad_norm": 0.4473017752170563,
+      "learning_rate": 0.00019921699965828662,
+      "loss": 0.820871889591217,
+      "step": 1624
+    },
+    {
+      "epoch": 0.7016181229773463,
+      "grad_norm": 0.43914029002189636,
+      "learning_rate": 0.00019921085454333706,
+      "loss": 0.8319019079208374,
+      "step": 1626
+    },
+    {
+      "epoch": 0.7024811218985976,
+      "grad_norm": 0.4758487939834595,
+      "learning_rate": 0.0001992046855041372,
+      "loss": 0.8589251041412354,
+      "step": 1628
+    },
+    {
+      "epoch": 0.703344120819849,
+      "grad_norm": 0.506401538848877,
+      "learning_rate": 0.00019919849254217465,
+      "loss": 0.9219205975532532,
+      "step": 1630
+    },
+    {
+      "epoch": 0.7042071197411003,
+      "grad_norm": 0.4397984445095062,
+      "learning_rate": 0.00019919227565894277,
+      "loss": 0.7824978232383728,
+      "step": 1632
+    },
+    {
+      "epoch": 0.7050701186623517,
+      "grad_norm": 0.3879252076148987,
+      "learning_rate": 0.0001991860348559408,
+      "loss": 0.8472069501876831,
+      "step": 1634
+    },
+    {
+      "epoch": 0.705933117583603,
+      "grad_norm": 0.42238810658454895,
+      "learning_rate": 0.00019917977013467368,
+      "loss": 0.824957013130188,
+      "step": 1636
+    },
+    {
+      "epoch": 0.7067961165048544,
+      "grad_norm": 0.5235037207603455,
+      "learning_rate": 0.00019917348149665206,
+      "loss": 0.9490993022918701,
+      "step": 1638
+    },
+    {
+      "epoch": 0.7076591154261057,
+      "grad_norm": 0.5195287466049194,
+      "learning_rate": 0.0001991671689433925,
+      "loss": 0.960905909538269,
+      "step": 1640
+    },
+    {
+      "epoch": 0.708522114347357,
+      "grad_norm": 0.5016481876373291,
+      "learning_rate": 0.00019916083247641716,
+      "loss": 0.8961218595504761,
+      "step": 1642
+    },
+    {
+      "epoch": 0.7093851132686084,
+      "grad_norm": 0.5510191321372986,
+      "learning_rate": 0.00019915447209725408,
+      "loss": 0.8883417844772339,
+      "step": 1644
+    },
+    {
+      "epoch": 0.7102481121898597,
+      "grad_norm": 0.4492250084877014,
+      "learning_rate": 0.0001991480878074371,
+      "loss": 0.7968636751174927,
+      "step": 1646
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.4189683496952057,
+      "learning_rate": 0.00019914167960850563,
+      "loss": 0.7869221568107605,
+      "step": 1648
+    },
+    {
+      "epoch": 0.7119741100323624,
+      "grad_norm": 0.4590536653995514,
+      "learning_rate": 0.0001991352475020051,
+      "loss": 0.8423646092414856,
+      "step": 1650
+    },
+    {
+      "epoch": 0.7128371089536139,
+      "grad_norm": 0.5058966875076294,
+      "learning_rate": 0.00019912879148948652,
+      "loss": 0.895459771156311,
+      "step": 1652
+    },
+    {
+      "epoch": 0.7137001078748652,
+      "grad_norm": 0.4904550313949585,
+      "learning_rate": 0.00019912231157250676,
+      "loss": 0.8737894296646118,
+      "step": 1654
+    },
+    {
+      "epoch": 0.7145631067961165,
+      "grad_norm": 0.4670710861682892,
+      "learning_rate": 0.0001991158077526284,
+      "loss": 0.8019732236862183,
+      "step": 1656
+    },
+    {
+      "epoch": 0.7154261057173679,
+      "grad_norm": 0.530343770980835,
+      "learning_rate": 0.00019910928003141984,
+      "loss": 0.9474499821662903,
+      "step": 1658
+    },
+    {
+      "epoch": 0.7162891046386192,
+      "grad_norm": 0.4250960052013397,
+      "learning_rate": 0.00019910272841045518,
+      "loss": 0.8738601803779602,
+      "step": 1660
+    },
+    {
+      "epoch": 0.7171521035598706,
+      "grad_norm": 0.4896513819694519,
+      "learning_rate": 0.0001990961528913143,
+      "loss": 0.9578261971473694,
+      "step": 1662
+    },
+    {
+      "epoch": 0.7180151024811219,
+      "grad_norm": 0.4999626576900482,
+      "learning_rate": 0.00019908955347558291,
+      "loss": 0.8116445541381836,
+      "step": 1664
+    },
+    {
+      "epoch": 0.7188781014023733,
+      "grad_norm": 0.4335242807865143,
+      "learning_rate": 0.00019908293016485237,
+      "loss": 0.8783043622970581,
+      "step": 1666
+    },
+    {
+      "epoch": 0.7197411003236246,
+      "grad_norm": 0.43542763590812683,
+      "learning_rate": 0.00019907628296071992,
+      "loss": 0.8223029375076294,
+      "step": 1668
+    },
+    {
+      "epoch": 0.7206040992448759,
+      "grad_norm": 0.4907461702823639,
+      "learning_rate": 0.00019906961186478842,
+      "loss": 1.0053197145462036,
+      "step": 1670
+    },
+    {
+      "epoch": 0.7214670981661273,
+      "grad_norm": 0.4054848253726959,
+      "learning_rate": 0.00019906291687866667,
+      "loss": 0.8107786178588867,
+      "step": 1672
+    },
+    {
+      "epoch": 0.7223300970873786,
+      "grad_norm": 0.3818599283695221,
+      "learning_rate": 0.0001990561980039691,
+      "loss": 0.780781626701355,
+      "step": 1674
+    },
+    {
+      "epoch": 0.72319309600863,
+      "grad_norm": 0.4128594994544983,
+      "learning_rate": 0.00019904945524231587,
+      "loss": 0.8189221620559692,
+      "step": 1676
+    },
+    {
+      "epoch": 0.7240560949298813,
+      "grad_norm": 0.46902593970298767,
+      "learning_rate": 0.0001990426885953331,
+      "loss": 0.83652263879776,
+      "step": 1678
+    },
+    {
+      "epoch": 0.7249190938511327,
+      "grad_norm": 0.49305564165115356,
+      "learning_rate": 0.00019903589806465242,
+      "loss": 0.8057956695556641,
+      "step": 1680
+    },
+    {
+      "epoch": 0.725782092772384,
+      "grad_norm": 0.44408300518989563,
+      "learning_rate": 0.0001990290836519114,
+      "loss": 0.8523716926574707,
+      "step": 1682
+    },
+    {
+      "epoch": 0.7266450916936353,
+      "grad_norm": 0.5211108922958374,
+      "learning_rate": 0.00019902224535875326,
+      "loss": 0.9179236888885498,
+      "step": 1684
+    },
+    {
+      "epoch": 0.7275080906148867,
+      "grad_norm": 0.4736526608467102,
+      "learning_rate": 0.00019901538318682705,
+      "loss": 0.8229476809501648,
+      "step": 1686
+    },
+    {
+      "epoch": 0.728371089536138,
+      "grad_norm": 0.541716992855072,
+      "learning_rate": 0.00019900849713778756,
+      "loss": 0.924200713634491,
+      "step": 1688
+    },
+    {
+      "epoch": 0.7292340884573895,
+      "grad_norm": 0.4524400532245636,
+      "learning_rate": 0.00019900158721329532,
+      "loss": 0.88961261510849,
+      "step": 1690
+    },
+    {
+      "epoch": 0.7300970873786408,
+      "grad_norm": 0.45256128907203674,
+      "learning_rate": 0.00019899465341501662,
+      "loss": 0.8491015434265137,
+      "step": 1692
+    },
+    {
+      "epoch": 0.7309600862998922,
+      "grad_norm": 0.5346773266792297,
+      "learning_rate": 0.0001989876957446235,
+      "loss": 0.8833339810371399,
+      "step": 1694
+    },
+    {
+      "epoch": 0.7318230852211435,
+      "grad_norm": 0.4696357846260071,
+      "learning_rate": 0.0001989807142037938,
+      "loss": 0.8535294532775879,
+      "step": 1696
+    },
+    {
+      "epoch": 0.7326860841423948,
+      "grad_norm": 0.4304637908935547,
+      "learning_rate": 0.0001989737087942111,
+      "loss": 0.8273076415061951,
+      "step": 1698
+    },
+    {
+      "epoch": 0.7335490830636462,
+      "grad_norm": 0.5085629224777222,
+      "learning_rate": 0.00019896667951756466,
+      "loss": 0.8759240508079529,
+      "step": 1700
+    },
+    {
+      "epoch": 0.7335490830636462,
+      "eval_loss": 0.879119336605072,
+      "eval_runtime": 663.0553,
+      "eval_samples_per_second": 3.107,
+      "eval_steps_per_second": 3.107,
+      "step": 1700
+    },
+    {
+      "epoch": 0.7344120819848975,
+      "grad_norm": 0.484223872423172,
+      "learning_rate": 0.00019895962637554964,
+      "loss": 0.852645218372345,
+      "step": 1702
+    },
+    {
+      "epoch": 0.7352750809061489,
+      "grad_norm": 0.4819294214248657,
+      "learning_rate": 0.0001989525493698668,
+      "loss": 0.878247857093811,
+      "step": 1704
+    },
+    {
+      "epoch": 0.7361380798274002,
+      "grad_norm": 0.4170311689376831,
+      "learning_rate": 0.00019894544850222276,
+      "loss": 0.8964285254478455,
+      "step": 1706
+    },
+    {
+      "epoch": 0.7370010787486516,
+      "grad_norm": 0.42712801694869995,
+      "learning_rate": 0.0001989383237743299,
+      "loss": 0.7479548454284668,
+      "step": 1708
+    },
+    {
+      "epoch": 0.7378640776699029,
+      "grad_norm": 0.5051686763763428,
+      "learning_rate": 0.00019893117518790624,
+      "loss": 0.8190052509307861,
+      "step": 1710
+    },
+    {
+      "epoch": 0.7387270765911542,
+      "grad_norm": 0.44053253531455994,
+      "learning_rate": 0.0001989240027446757,
+      "loss": 0.8646742105484009,
+      "step": 1712
+    },
+    {
+      "epoch": 0.7395900755124056,
+      "grad_norm": 0.4451025724411011,
+      "learning_rate": 0.00019891680644636782,
+      "loss": 0.874261736869812,
+      "step": 1714
+    },
+    {
+      "epoch": 0.7404530744336569,
+      "grad_norm": 0.4590521454811096,
+      "learning_rate": 0.00019890958629471798,
+      "loss": 0.8892465233802795,
+      "step": 1716
+    },
+    {
+      "epoch": 0.7413160733549083,
+      "grad_norm": 0.39169448614120483,
+      "learning_rate": 0.00019890234229146732,
+      "loss": 0.7031586766242981,
+      "step": 1718
+    },
+    {
+      "epoch": 0.7421790722761596,
+      "grad_norm": 0.46946024894714355,
+      "learning_rate": 0.00019889507443836266,
+      "loss": 0.8548433184623718,
+      "step": 1720
+    },
+    {
+      "epoch": 0.7430420711974111,
+      "grad_norm": 0.42404699325561523,
+      "learning_rate": 0.0001988877827371566,
+      "loss": 0.8231223821640015,
+      "step": 1722
+    },
+    {
+      "epoch": 0.7439050701186624,
+      "grad_norm": 0.40419483184814453,
+      "learning_rate": 0.00019888046718960755,
+      "loss": 0.8443762063980103,
+      "step": 1724
+    },
+    {
+      "epoch": 0.7447680690399137,
+      "grad_norm": 0.4550437927246094,
+      "learning_rate": 0.0001988731277974796,
+      "loss": 0.8787111639976501,
+      "step": 1726
+    },
+    {
+      "epoch": 0.7456310679611651,
+      "grad_norm": 0.42264053225517273,
+      "learning_rate": 0.0001988657645625426,
+      "loss": 0.8440850377082825,
+      "step": 1728
+    },
+    {
+      "epoch": 0.7464940668824164,
+      "grad_norm": 0.4638359844684601,
+      "learning_rate": 0.0001988583774865721,
+      "loss": 0.839216947555542,
+      "step": 1730
+    },
+    {
+      "epoch": 0.7473570658036678,
+      "grad_norm": 0.42644429206848145,
+      "learning_rate": 0.0001988509665713496,
+      "loss": 0.8011161684989929,
+      "step": 1732
+    },
+    {
+      "epoch": 0.7482200647249191,
+      "grad_norm": 0.36932024359703064,
+      "learning_rate": 0.0001988435318186621,
+      "loss": 0.850246787071228,
+      "step": 1734
+    },
+    {
+      "epoch": 0.7490830636461704,
+      "grad_norm": 0.4771935045719147,
+      "learning_rate": 0.00019883607323030252,
+      "loss": 0.7782483100891113,
+      "step": 1736
+    },
+    {
+      "epoch": 0.7499460625674218,
+      "grad_norm": 0.40007370710372925,
+      "learning_rate": 0.00019882859080806942,
+      "loss": 0.8337594866752625,
+      "step": 1738
+    },
+    {
+      "epoch": 0.7508090614886731,
+      "grad_norm": 0.5007418394088745,
+      "learning_rate": 0.00019882108455376716,
+      "loss": 0.8287386894226074,
+      "step": 1740
+    },
+    {
+      "epoch": 0.7516720604099245,
+      "grad_norm": 0.43999138474464417,
+      "learning_rate": 0.00019881355446920584,
+      "loss": 0.8655616044998169,
+      "step": 1742
+    },
+    {
+      "epoch": 0.7525350593311758,
+      "grad_norm": 0.5115824937820435,
+      "learning_rate": 0.00019880600055620135,
+      "loss": 0.8695262670516968,
+      "step": 1744
+    },
+    {
+      "epoch": 0.7533980582524272,
+      "grad_norm": 0.5035707950592041,
+      "learning_rate": 0.0001987984228165752,
+      "loss": 0.9207013845443726,
+      "step": 1746
+    },
+    {
+      "epoch": 0.7542610571736785,
+      "grad_norm": 0.4689575731754303,
+      "learning_rate": 0.0001987908212521548,
+      "loss": 0.8798729777336121,
+      "step": 1748
+    },
+    {
+      "epoch": 0.7551240560949298,
+      "grad_norm": 0.4730616509914398,
+      "learning_rate": 0.00019878319586477322,
+      "loss": 0.7737767696380615,
+      "step": 1750
+    },
+    {
+      "epoch": 0.7559870550161812,
+      "grad_norm": 0.49012845754623413,
+      "learning_rate": 0.00019877554665626926,
+      "loss": 0.929466187953949,
+      "step": 1752
+    },
+    {
+      "epoch": 0.7568500539374325,
+      "grad_norm": 0.43468761444091797,
+      "learning_rate": 0.0001987678736284875,
+      "loss": 0.8155670166015625,
+      "step": 1754
+    },
+    {
+      "epoch": 0.757713052858684,
+      "grad_norm": 0.507399320602417,
+      "learning_rate": 0.00019876017678327826,
+      "loss": 0.8082395195960999,
+      "step": 1756
+    },
+    {
+      "epoch": 0.7585760517799353,
+      "grad_norm": 0.4733552634716034,
+      "learning_rate": 0.0001987524561224976,
+      "loss": 0.8905934691429138,
+      "step": 1758
+    },
+    {
+      "epoch": 0.7594390507011867,
+      "grad_norm": 0.4670012891292572,
+      "learning_rate": 0.00019874471164800733,
+      "loss": 0.8794633746147156,
+      "step": 1760
+    },
+    {
+      "epoch": 0.760302049622438,
+      "grad_norm": 0.4951624572277069,
+      "learning_rate": 0.000198736943361675,
+      "loss": 0.8413973450660706,
+      "step": 1762
+    },
+    {
+      "epoch": 0.7611650485436893,
+      "grad_norm": 0.5478648543357849,
+      "learning_rate": 0.00019872915126537387,
+      "loss": 0.9067897200584412,
+      "step": 1764
+    },
+    {
+      "epoch": 0.7620280474649407,
+      "grad_norm": 0.48215776681900024,
+      "learning_rate": 0.000198721335360983,
+      "loss": 0.8932394981384277,
+      "step": 1766
+    },
+    {
+      "epoch": 0.762891046386192,
+      "grad_norm": 0.4688864052295685,
+      "learning_rate": 0.00019871349565038715,
+      "loss": 0.8496726751327515,
+      "step": 1768
+    },
+    {
+      "epoch": 0.7637540453074434,
+      "grad_norm": 0.4728260636329651,
+      "learning_rate": 0.0001987056321354768,
+      "loss": 0.9232800602912903,
+      "step": 1770
+    },
+    {
+      "epoch": 0.7646170442286947,
+      "grad_norm": 0.44501692056655884,
+      "learning_rate": 0.00019869774481814828,
+      "loss": 0.849755585193634,
+      "step": 1772
+    },
+    {
+      "epoch": 0.7654800431499461,
+      "grad_norm": 0.4189201593399048,
+      "learning_rate": 0.00019868983370030348,
+      "loss": 0.8258485794067383,
+      "step": 1774
+    },
+    {
+      "epoch": 0.7663430420711974,
+      "grad_norm": 0.5144591927528381,
+      "learning_rate": 0.00019868189878385016,
+      "loss": 0.8762873411178589,
+      "step": 1776
+    },
+    {
+      "epoch": 0.7672060409924487,
+      "grad_norm": 0.5048011541366577,
+      "learning_rate": 0.00019867394007070188,
+      "loss": 0.8732464909553528,
+      "step": 1778
+    },
+    {
+      "epoch": 0.7680690399137001,
+      "grad_norm": 0.41639819741249084,
+      "learning_rate": 0.00019866595756277774,
+      "loss": 0.8732751607894897,
+      "step": 1780
+    },
+    {
+      "epoch": 0.7689320388349514,
+      "grad_norm": 0.526757538318634,
+      "learning_rate": 0.00019865795126200271,
+      "loss": 0.8453729748725891,
+      "step": 1782
+    },
+    {
+      "epoch": 0.7697950377562028,
+      "grad_norm": 0.47041091322898865,
+      "learning_rate": 0.0001986499211703075,
+      "loss": 0.8780192732810974,
+      "step": 1784
+    },
+    {
+      "epoch": 0.7706580366774541,
+      "grad_norm": 0.4535890221595764,
+      "learning_rate": 0.0001986418672896285,
+      "loss": 0.8508450388908386,
+      "step": 1786
+    },
+    {
+      "epoch": 0.7715210355987056,
+      "grad_norm": 0.4608050286769867,
+      "learning_rate": 0.00019863378962190788,
+      "loss": 0.822467565536499,
+      "step": 1788
+    },
+    {
+      "epoch": 0.7723840345199569,
+      "grad_norm": 0.5190523862838745,
+      "learning_rate": 0.00019862568816909356,
+      "loss": 0.844614565372467,
+      "step": 1790
+    },
+    {
+      "epoch": 0.7732470334412082,
+      "grad_norm": 0.42502254247665405,
+      "learning_rate": 0.00019861756293313912,
+      "loss": 0.8144394755363464,
+      "step": 1792
+    },
+    {
+      "epoch": 0.7741100323624596,
+      "grad_norm": 0.47112616896629333,
+      "learning_rate": 0.000198609413916004,
+      "loss": 0.8836341500282288,
+      "step": 1794
+    },
+    {
+      "epoch": 0.7749730312837109,
+      "grad_norm": 0.48414838314056396,
+      "learning_rate": 0.0001986012411196532,
+      "loss": 0.8846262693405151,
+      "step": 1796
+    },
+    {
+      "epoch": 0.7758360302049623,
+      "grad_norm": 0.4670039415359497,
+      "learning_rate": 0.00019859304454605763,
+      "loss": 0.7993118762969971,
+      "step": 1798
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "grad_norm": 0.41939061880111694,
+      "learning_rate": 0.0001985848241971938,
+      "loss": 0.8389407396316528,
+      "step": 1800
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "eval_loss": 0.8727664947509766,
+      "eval_runtime": 668.2062,
+      "eval_samples_per_second": 3.083,
+      "eval_steps_per_second": 3.083,
+      "step": 1800
+    },
+    {
+      "epoch": 0.777562028047465,
+      "grad_norm": 0.4566517174243927,
+      "learning_rate": 0.00019857658007504405,
+      "loss": 0.8824291825294495,
+      "step": 1802
+    },
+    {
+      "epoch": 0.7784250269687163,
+      "grad_norm": 0.4798925518989563,
+      "learning_rate": 0.0001985683121815964,
+      "loss": 0.808982789516449,
+      "step": 1804
+    },
+    {
+      "epoch": 0.7792880258899676,
+      "grad_norm": 0.4659746587276459,
+      "learning_rate": 0.00019856002051884462,
+      "loss": 0.955269992351532,
+      "step": 1806
+    },
+    {
+      "epoch": 0.780151024811219,
+      "grad_norm": 0.48573991656303406,
+      "learning_rate": 0.00019855170508878818,
+      "loss": 0.8142994046211243,
+      "step": 1808
+    },
+    {
+      "epoch": 0.7810140237324703,
+      "grad_norm": 0.4700213670730591,
+      "learning_rate": 0.00019854336589343236,
+      "loss": 0.8755695819854736,
+      "step": 1810
+    },
+    {
+      "epoch": 0.7818770226537217,
+      "grad_norm": 0.42113450169563293,
+      "learning_rate": 0.00019853500293478806,
+      "loss": 0.8098483681678772,
+      "step": 1812
+    },
+    {
+      "epoch": 0.782740021574973,
+      "grad_norm": 0.4218153655529022,
+      "learning_rate": 0.00019852661621487205,
+      "loss": 0.8219783306121826,
+      "step": 1814
+    },
+    {
+      "epoch": 0.7836030204962244,
+      "grad_norm": 0.499052494764328,
+      "learning_rate": 0.00019851820573570664,
+      "loss": 0.8314159512519836,
+      "step": 1816
+    },
+    {
+      "epoch": 0.7844660194174757,
+      "grad_norm": 0.42420193552970886,
+      "learning_rate": 0.00019850977149932008,
+      "loss": 0.7985323071479797,
+      "step": 1818
+    },
+    {
+      "epoch": 0.785329018338727,
+      "grad_norm": 0.46345841884613037,
+      "learning_rate": 0.0001985013135077462,
+      "loss": 0.8528217077255249,
+      "step": 1820
+    },
+    {
+      "epoch": 0.7861920172599784,
+      "grad_norm": 0.4433307945728302,
+      "learning_rate": 0.00019849283176302462,
+      "loss": 0.8659319877624512,
+      "step": 1822
+    },
+    {
+      "epoch": 0.7870550161812297,
+      "grad_norm": 0.48279091715812683,
+      "learning_rate": 0.00019848432626720067,
+      "loss": 0.8675655126571655,
+      "step": 1824
+    },
+    {
+      "epoch": 0.7879180151024812,
+      "grad_norm": 0.5439180731773376,
+      "learning_rate": 0.0001984757970223254,
+      "loss": 0.8550227284431458,
+      "step": 1826
+    },
+    {
+      "epoch": 0.7887810140237325,
+      "grad_norm": 0.45749521255493164,
+      "learning_rate": 0.0001984672440304556,
+      "loss": 0.7290607690811157,
+      "step": 1828
+    },
+    {
+      "epoch": 0.7896440129449838,
+      "grad_norm": 0.4654783606529236,
+      "learning_rate": 0.00019845866729365378,
+      "loss": 0.8619251251220703,
+      "step": 1830
+    },
+    {
+      "epoch": 0.7905070118662352,
+      "grad_norm": 0.42632243037223816,
+      "learning_rate": 0.00019845006681398823,
+      "loss": 0.8249601125717163,
+      "step": 1832
+    },
+    {
+      "epoch": 0.7913700107874865,
+      "grad_norm": 0.4747186005115509,
+      "learning_rate": 0.0001984414425935329,
+      "loss": 0.7138552069664001,
+      "step": 1834
+    },
+    {
+      "epoch": 0.7922330097087379,
+      "grad_norm": 0.4462338387966156,
+      "learning_rate": 0.0001984327946343674,
+      "loss": 0.903292715549469,
+      "step": 1836
+    },
+    {
+      "epoch": 0.7930960086299892,
+      "grad_norm": 0.4581359922885895,
+      "learning_rate": 0.00019842412293857726,
+      "loss": 0.7569618225097656,
+      "step": 1838
+    },
+    {
+      "epoch": 0.7939590075512406,
+      "grad_norm": 0.4183015525341034,
+      "learning_rate": 0.00019841542750825356,
+      "loss": 0.8063036203384399,
+      "step": 1840
+    },
+    {
+      "epoch": 0.7948220064724919,
+      "grad_norm": 0.3954181373119354,
+      "learning_rate": 0.0001984067083454932,
+      "loss": 0.81150221824646,
+      "step": 1842
+    },
+    {
+      "epoch": 0.7956850053937432,
+      "grad_norm": 0.46220019459724426,
+      "learning_rate": 0.0001983979654523987,
+      "loss": 0.841649055480957,
+      "step": 1844
+    },
+    {
+      "epoch": 0.7965480043149946,
+      "grad_norm": 0.47807541489601135,
+      "learning_rate": 0.00019838919883107843,
+      "loss": 0.8019483685493469,
+      "step": 1846
+    },
+    {
+      "epoch": 0.7974110032362459,
+      "grad_norm": 0.48015692830085754,
+      "learning_rate": 0.0001983804084836464,
+      "loss": 0.9343363046646118,
+      "step": 1848
+    },
+    {
+      "epoch": 0.7982740021574973,
+      "grad_norm": 0.4906708896160126,
+      "learning_rate": 0.00019837159441222238,
+      "loss": 0.9163194894790649,
+      "step": 1850
+    },
+    {
+      "epoch": 0.7991370010787486,
+      "grad_norm": 0.4856911599636078,
+      "learning_rate": 0.0001983627566189318,
+      "loss": 0.8017736077308655,
+      "step": 1852
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.49403145909309387,
+      "learning_rate": 0.0001983538951059059,
+      "loss": 0.8375223875045776,
+      "step": 1854
+    },
+    {
+      "epoch": 0.8008629989212513,
+      "grad_norm": 0.4237985908985138,
+      "learning_rate": 0.00019834500987528158,
+      "loss": 0.8213951587677002,
+      "step": 1856
+    },
+    {
+      "epoch": 0.8017259978425026,
+      "grad_norm": 0.3977980315685272,
+      "learning_rate": 0.00019833610092920149,
+      "loss": 0.8086028099060059,
+      "step": 1858
+    },
+    {
+      "epoch": 0.8025889967637541,
+      "grad_norm": 0.435253381729126,
+      "learning_rate": 0.00019832716826981392,
+      "loss": 0.9402202367782593,
+      "step": 1860
+    },
+    {
+      "epoch": 0.8034519956850054,
+      "grad_norm": 0.4074764847755432,
+      "learning_rate": 0.000198318211899273,
+      "loss": 0.7730796933174133,
+      "step": 1862
+    },
+    {
+      "epoch": 0.8043149946062568,
+      "grad_norm": 0.48804348707199097,
+      "learning_rate": 0.0001983092318197385,
+      "loss": 0.9185802936553955,
+      "step": 1864
+    },
+    {
+      "epoch": 0.8051779935275081,
+      "grad_norm": 0.44363343715667725,
+      "learning_rate": 0.00019830022803337592,
+      "loss": 0.8578243851661682,
+      "step": 1866
+    },
+    {
+      "epoch": 0.8060409924487595,
+      "grad_norm": 0.46645957231521606,
+      "learning_rate": 0.00019829120054235653,
+      "loss": 0.8682060241699219,
+      "step": 1868
+    },
+    {
+      "epoch": 0.8069039913700108,
+      "grad_norm": 0.4527221620082855,
+      "learning_rate": 0.00019828214934885718,
+      "loss": 0.7845040559768677,
+      "step": 1870
+    },
+    {
+      "epoch": 0.8077669902912621,
+      "grad_norm": 0.4103536307811737,
+      "learning_rate": 0.0001982730744550606,
+      "loss": 0.8768247961997986,
+      "step": 1872
+    },
+    {
+      "epoch": 0.8086299892125135,
+      "grad_norm": 0.5257515907287598,
+      "learning_rate": 0.00019826397586315513,
+      "loss": 0.850267231464386,
+      "step": 1874
+    },
+    {
+      "epoch": 0.8094929881337648,
+      "grad_norm": 0.46675893664360046,
+      "learning_rate": 0.00019825485357533485,
+      "loss": 0.8234293460845947,
+      "step": 1876
+    },
+    {
+      "epoch": 0.8103559870550162,
+      "grad_norm": 0.46315401792526245,
+      "learning_rate": 0.00019824570759379958,
+      "loss": 0.8131387829780579,
+      "step": 1878
+    },
+    {
+      "epoch": 0.8112189859762675,
+      "grad_norm": 0.4766870439052582,
+      "learning_rate": 0.00019823653792075478,
+      "loss": 0.7680494785308838,
+      "step": 1880
+    },
+    {
+      "epoch": 0.8120819848975189,
+      "grad_norm": 0.39025625586509705,
+      "learning_rate": 0.00019822734455841173,
+      "loss": 0.7891425490379333,
+      "step": 1882
+    },
+    {
+      "epoch": 0.8129449838187702,
+      "grad_norm": 0.4672441780567169,
+      "learning_rate": 0.0001982181275089874,
+      "loss": 0.7990400791168213,
+      "step": 1884
+    },
+    {
+      "epoch": 0.8138079827400215,
+      "grad_norm": 0.44310975074768066,
+      "learning_rate": 0.00019820888677470432,
+      "loss": 0.7828341722488403,
+      "step": 1886
+    },
+    {
+      "epoch": 0.8146709816612729,
+      "grad_norm": 0.45098716020584106,
+      "learning_rate": 0.00019819962235779096,
+      "loss": 0.897715151309967,
+      "step": 1888
+    },
+    {
+      "epoch": 0.8155339805825242,
+      "grad_norm": 0.466805100440979,
+      "learning_rate": 0.00019819033426048135,
+      "loss": 0.7987668514251709,
+      "step": 1890
+    },
+    {
+      "epoch": 0.8163969795037757,
+      "grad_norm": 0.4438319206237793,
+      "learning_rate": 0.00019818102248501528,
+      "loss": 0.7950236201286316,
+      "step": 1892
+    },
+    {
+      "epoch": 0.817259978425027,
+      "grad_norm": 0.42012497782707214,
+      "learning_rate": 0.00019817168703363823,
+      "loss": 0.8789975643157959,
+      "step": 1894
+    },
+    {
+      "epoch": 0.8181229773462784,
+      "grad_norm": 0.4359394311904907,
+      "learning_rate": 0.0001981623279086014,
+      "loss": 0.8159777522087097,
+      "step": 1896
+    },
+    {
+      "epoch": 0.8189859762675297,
+      "grad_norm": 0.44709593057632446,
+      "learning_rate": 0.00019815294511216173,
+      "loss": 0.84877610206604,
+      "step": 1898
+    },
+    {
+      "epoch": 0.819848975188781,
+      "grad_norm": 0.4315306544303894,
+      "learning_rate": 0.00019814353864658184,
+      "loss": 0.8467556834220886,
+      "step": 1900
+    },
+    {
+      "epoch": 0.819848975188781,
+      "eval_loss": 0.8643407821655273,
+      "eval_runtime": 658.6942,
+      "eval_samples_per_second": 3.127,
+      "eval_steps_per_second": 3.127,
+      "step": 1900
+    },
+    {
+      "epoch": 0.8207119741100324,
+      "grad_norm": 0.35530397295951843,
+      "learning_rate": 0.00019813410851412998,
+      "loss": 0.7398589849472046,
+      "step": 1902
+    },
+    {
+      "epoch": 0.8215749730312837,
+      "grad_norm": 0.46949300169944763,
+      "learning_rate": 0.00019812465471708032,
+      "loss": 0.8544237613677979,
+      "step": 1904
+    },
+    {
+      "epoch": 0.8224379719525351,
+      "grad_norm": 0.4961565434932709,
+      "learning_rate": 0.00019811517725771248,
+      "loss": 0.8242526054382324,
+      "step": 1906
+    },
+    {
+      "epoch": 0.8233009708737864,
+      "grad_norm": 0.45835059881210327,
+      "learning_rate": 0.00019810567613831194,
+      "loss": 0.7856690287590027,
+      "step": 1908
+    },
+    {
+      "epoch": 0.8241639697950378,
+      "grad_norm": 0.4446084797382355,
+      "learning_rate": 0.0001980961513611699,
+      "loss": 0.8361829519271851,
+      "step": 1910
+    },
+    {
+      "epoch": 0.8250269687162891,
+      "grad_norm": 0.4470907747745514,
+      "learning_rate": 0.00019808660292858313,
+      "loss": 0.8993050456047058,
+      "step": 1912
+    },
+    {
+      "epoch": 0.8258899676375404,
+      "grad_norm": 0.44883644580841064,
+      "learning_rate": 0.0001980770308428543,
+      "loss": 0.8702824711799622,
+      "step": 1914
+    },
+    {
+      "epoch": 0.8267529665587918,
+      "grad_norm": 0.43215686082839966,
+      "learning_rate": 0.00019806743510629159,
+      "loss": 0.8454389572143555,
+      "step": 1916
+    },
+    {
+      "epoch": 0.8276159654800431,
+      "grad_norm": 0.4525185823440552,
+      "learning_rate": 0.00019805781572120897,
+      "loss": 0.8621824383735657,
+      "step": 1918
+    },
+    {
+      "epoch": 0.8284789644012945,
+      "grad_norm": 0.4616840183734894,
+      "learning_rate": 0.00019804817268992615,
+      "loss": 0.8661681413650513,
+      "step": 1920
+    },
+    {
+      "epoch": 0.8293419633225458,
+      "grad_norm": 0.4252975583076477,
+      "learning_rate": 0.0001980385060147685,
+      "loss": 0.8376660346984863,
+      "step": 1922
+    },
+    {
+      "epoch": 0.8302049622437971,
+      "grad_norm": 0.44600266218185425,
+      "learning_rate": 0.00019802881569806706,
+      "loss": 0.9258401393890381,
+      "step": 1924
+    },
+    {
+      "epoch": 0.8310679611650486,
+      "grad_norm": 0.48872479796409607,
+      "learning_rate": 0.00019801910174215866,
+      "loss": 0.8804965615272522,
+      "step": 1926
+    },
+    {
+      "epoch": 0.8319309600862999,
+      "grad_norm": 0.5357037782669067,
+      "learning_rate": 0.00019800936414938574,
+      "loss": 0.8561494946479797,
+      "step": 1928
+    },
+    {
+      "epoch": 0.8327939590075513,
+      "grad_norm": 0.39637291431427,
+      "learning_rate": 0.00019799960292209647,
+      "loss": 0.782166063785553,
+      "step": 1930
+    },
+    {
+      "epoch": 0.8336569579288026,
+      "grad_norm": 0.521138072013855,
+      "learning_rate": 0.00019798981806264476,
+      "loss": 0.9048293232917786,
+      "step": 1932
+    },
+    {
+      "epoch": 0.834519956850054,
+      "grad_norm": 0.4723529815673828,
+      "learning_rate": 0.00019798000957339015,
+      "loss": 0.9269952774047852,
+      "step": 1934
+    },
+    {
+      "epoch": 0.8353829557713053,
+      "grad_norm": 0.42827340960502625,
+      "learning_rate": 0.0001979701774566979,
+      "loss": 0.8620670437812805,
+      "step": 1936
+    },
+    {
+      "epoch": 0.8362459546925566,
+      "grad_norm": 0.4305116534233093,
+      "learning_rate": 0.00019796032171493907,
+      "loss": 0.8016669750213623,
+      "step": 1938
+    },
+    {
+      "epoch": 0.837108953613808,
+      "grad_norm": 0.4995502233505249,
+      "learning_rate": 0.00019795044235049024,
+      "loss": 0.879247784614563,
+      "step": 1940
+    },
+    {
+      "epoch": 0.8379719525350593,
+      "grad_norm": 0.49229878187179565,
+      "learning_rate": 0.0001979405393657338,
+      "loss": 0.9476580023765564,
+      "step": 1942
+    },
+    {
+      "epoch": 0.8388349514563107,
+      "grad_norm": 0.45756596326828003,
+      "learning_rate": 0.0001979306127630578,
+      "loss": 0.8654064536094666,
+      "step": 1944
+    },
+    {
+      "epoch": 0.839697950377562,
+      "grad_norm": 0.4855344891548157,
+      "learning_rate": 0.00019792066254485603,
+      "loss": 0.7792956829071045,
+      "step": 1946
+    },
+    {
+      "epoch": 0.8405609492988134,
+      "grad_norm": 0.4358632266521454,
+      "learning_rate": 0.00019791068871352787,
+      "loss": 0.8000320792198181,
+      "step": 1948
+    },
+    {
+      "epoch": 0.8414239482200647,
+      "grad_norm": 0.4225342273712158,
+      "learning_rate": 0.00019790069127147852,
+      "loss": 0.818372368812561,
+      "step": 1950
+    },
+    {
+      "epoch": 0.842286947141316,
+      "grad_norm": 0.3894529938697815,
+      "learning_rate": 0.00019789067022111886,
+      "loss": 0.727220892906189,
+      "step": 1952
+    },
+    {
+      "epoch": 0.8431499460625674,
+      "grad_norm": 0.5060731768608093,
+      "learning_rate": 0.0001978806255648653,
+      "loss": 0.894101083278656,
+      "step": 1954
+    },
+    {
+      "epoch": 0.8440129449838187,
+      "grad_norm": 0.4165003001689911,
+      "learning_rate": 0.0001978705573051402,
+      "loss": 0.878365695476532,
+      "step": 1956
+    },
+    {
+      "epoch": 0.8448759439050701,
+      "grad_norm": 0.48767927289009094,
+      "learning_rate": 0.0001978604654443714,
+      "loss": 0.8390909433364868,
+      "step": 1958
+    },
+    {
+      "epoch": 0.8457389428263214,
+      "grad_norm": 0.43019410967826843,
+      "learning_rate": 0.00019785034998499247,
+      "loss": 0.8807769417762756,
+      "step": 1960
+    },
+    {
+      "epoch": 0.8466019417475729,
+      "grad_norm": 0.4430403709411621,
+      "learning_rate": 0.0001978402109294428,
+      "loss": 0.8037779331207275,
+      "step": 1962
+    },
+    {
+      "epoch": 0.8474649406688242,
+      "grad_norm": 0.41642463207244873,
+      "learning_rate": 0.0001978300482801673,
+      "loss": 0.8341337442398071,
+      "step": 1964
+    },
+    {
+      "epoch": 0.8483279395900755,
+      "grad_norm": 0.45358774065971375,
+      "learning_rate": 0.00019781986203961668,
+      "loss": 0.854821503162384,
+      "step": 1966
+    },
+    {
+      "epoch": 0.8491909385113269,
+      "grad_norm": 0.4316342771053314,
+      "learning_rate": 0.00019780965221024728,
+      "loss": 0.8527678847312927,
+      "step": 1968
+    },
+    {
+      "epoch": 0.8500539374325782,
+      "grad_norm": 0.4581106901168823,
+      "learning_rate": 0.00019779941879452122,
+      "loss": 0.7461717128753662,
+      "step": 1970
+    },
+    {
+      "epoch": 0.8509169363538296,
+      "grad_norm": 0.49578142166137695,
+      "learning_rate": 0.0001977891617949062,
+      "loss": 0.884441077709198,
+      "step": 1972
+    },
+    {
+      "epoch": 0.8517799352750809,
+      "grad_norm": 0.4366011917591095,
+      "learning_rate": 0.00019777888121387562,
+      "loss": 0.855915904045105,
+      "step": 1974
+    },
+    {
+      "epoch": 0.8526429341963323,
+      "grad_norm": 0.486162930727005,
+      "learning_rate": 0.00019776857705390864,
+      "loss": 0.7563765645027161,
+      "step": 1976
+    },
+    {
+      "epoch": 0.8535059331175836,
+      "grad_norm": 0.5162674784660339,
+      "learning_rate": 0.00019775824931749005,
+      "loss": 0.8346326947212219,
+      "step": 1978
+    },
+    {
+      "epoch": 0.8543689320388349,
+      "grad_norm": 0.5824693441390991,
+      "learning_rate": 0.0001977478980071103,
+      "loss": 0.8701820969581604,
+      "step": 1980
+    },
+    {
+      "epoch": 0.8552319309600863,
+      "grad_norm": 0.4297148883342743,
+      "learning_rate": 0.00019773752312526565,
+      "loss": 0.893528938293457,
+      "step": 1982
+    },
+    {
+      "epoch": 0.8560949298813376,
+      "grad_norm": 0.42978280782699585,
+      "learning_rate": 0.00019772712467445788,
+      "loss": 0.8201018571853638,
+      "step": 1984
+    },
+    {
+      "epoch": 0.856957928802589,
+      "grad_norm": 0.5192655324935913,
+      "learning_rate": 0.00019771670265719454,
+      "loss": 0.9080212116241455,
+      "step": 1986
+    },
+    {
+      "epoch": 0.8578209277238403,
+      "grad_norm": 0.452690452337265,
+      "learning_rate": 0.00019770625707598885,
+      "loss": 0.8518272638320923,
+      "step": 1988
+    },
+    {
+      "epoch": 0.8586839266450917,
+      "grad_norm": 0.4371768832206726,
+      "learning_rate": 0.00019769578793335976,
+      "loss": 0.9426717758178711,
+      "step": 1990
+    },
+    {
+      "epoch": 0.859546925566343,
+      "grad_norm": 0.44595038890838623,
+      "learning_rate": 0.0001976852952318318,
+      "loss": 0.8065400123596191,
+      "step": 1992
+    },
+    {
+      "epoch": 0.8604099244875943,
+      "grad_norm": 0.4355090260505676,
+      "learning_rate": 0.0001976747789739353,
+      "loss": 0.7674415707588196,
+      "step": 1994
+    },
+    {
+      "epoch": 0.8612729234088458,
+      "grad_norm": 0.43745186924934387,
+      "learning_rate": 0.00019766423916220616,
+      "loss": 0.813849925994873,
+      "step": 1996
+    },
+    {
+      "epoch": 0.8621359223300971,
+      "grad_norm": 0.4588927924633026,
+      "learning_rate": 0.00019765367579918598,
+      "loss": 0.7870585322380066,
+      "step": 1998
+    },
+    {
+      "epoch": 0.8629989212513485,
+      "grad_norm": 0.4170977473258972,
+      "learning_rate": 0.00019764308888742214,
+      "loss": 0.8383269309997559,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8629989212513485,
+      "eval_loss": 0.8567262887954712,
+      "eval_runtime": 646.6443,
+      "eval_samples_per_second": 3.186,
+      "eval_steps_per_second": 3.186,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8638619201725998,
+      "grad_norm": 0.4819261431694031,
+      "learning_rate": 0.0001976324784294676,
+      "loss": 0.8261714577674866,
+      "step": 2002
+    },
+    {
+      "epoch": 0.8647249190938512,
+      "grad_norm": 0.4215400218963623,
+      "learning_rate": 0.00019762184442788098,
+      "loss": 0.8493392467498779,
+      "step": 2004
+    },
+    {
+      "epoch": 0.8655879180151025,
+      "grad_norm": 0.45448991656303406,
+      "learning_rate": 0.00019761118688522668,
+      "loss": 0.8645208477973938,
+      "step": 2006
+    },
+    {
+      "epoch": 0.8664509169363538,
+      "grad_norm": 0.4436458349227905,
+      "learning_rate": 0.0001976005058040747,
+      "loss": 0.8816449046134949,
+      "step": 2008
+    },
+    {
+      "epoch": 0.8673139158576052,
+      "grad_norm": 0.42662230134010315,
+      "learning_rate": 0.00019758980118700072,
+      "loss": 0.7622330784797668,
+      "step": 2010
+    },
+    {
+      "epoch": 0.8681769147788565,
+      "grad_norm": 0.3936038613319397,
+      "learning_rate": 0.0001975790730365861,
+      "loss": 0.7843833565711975,
+      "step": 2012
+    },
+    {
+      "epoch": 0.8690399137001079,
+      "grad_norm": 0.4460368752479553,
+      "learning_rate": 0.00019756832135541796,
+      "loss": 0.8294675946235657,
+      "step": 2014
+    },
+    {
+      "epoch": 0.8699029126213592,
+      "grad_norm": 0.47043702006340027,
+      "learning_rate": 0.00019755754614608892,
+      "loss": 0.851332426071167,
+      "step": 2016
+    },
+    {
+      "epoch": 0.8707659115426106,
+      "grad_norm": 0.4579448401927948,
+      "learning_rate": 0.00019754674741119746,
+      "loss": 0.8450362682342529,
+      "step": 2018
+    },
+    {
+      "epoch": 0.8716289104638619,
+      "grad_norm": 0.44362813234329224,
+      "learning_rate": 0.00019753592515334758,
+      "loss": 0.8585519194602966,
+      "step": 2020
+    },
+    {
+      "epoch": 0.8724919093851132,
+      "grad_norm": 0.4500923156738281,
+      "learning_rate": 0.00019752507937514905,
+      "loss": 0.8300179243087769,
+      "step": 2022
+    },
+    {
+      "epoch": 0.8733549083063646,
+      "grad_norm": 0.4330301582813263,
+      "learning_rate": 0.00019751421007921724,
+      "loss": 0.805014431476593,
+      "step": 2024
+    },
+    {
+      "epoch": 0.8742179072276159,
+      "grad_norm": 0.43873998522758484,
+      "learning_rate": 0.00019750331726817332,
+      "loss": 0.8228020071983337,
+      "step": 2026
+    },
+    {
+      "epoch": 0.8750809061488674,
+      "grad_norm": 0.47558829188346863,
+      "learning_rate": 0.00019749240094464395,
+      "loss": 0.8490906357765198,
+      "step": 2028
+    },
+    {
+      "epoch": 0.8759439050701187,
+      "grad_norm": 0.4285199046134949,
+      "learning_rate": 0.0001974814611112616,
+      "loss": 0.816324770450592,
+      "step": 2030
+    },
+    {
+      "epoch": 0.87680690399137,
+      "grad_norm": 0.4762725532054901,
+      "learning_rate": 0.0001974704977706644,
+      "loss": 0.9229121208190918,
+      "step": 2032
+    },
+    {
+      "epoch": 0.8776699029126214,
+      "grad_norm": 0.49856793880462646,
+      "learning_rate": 0.00019745951092549598,
+      "loss": 0.9847140908241272,
+      "step": 2034
+    },
+    {
+      "epoch": 0.8785329018338727,
+      "grad_norm": 0.5163881182670593,
+      "learning_rate": 0.00019744850057840587,
+      "loss": 0.8305321335792542,
+      "step": 2036
+    },
+    {
+      "epoch": 0.8793959007551241,
+      "grad_norm": 0.47826042771339417,
+      "learning_rate": 0.00019743746673204918,
+      "loss": 0.7909449934959412,
+      "step": 2038
+    },
+    {
+      "epoch": 0.8802588996763754,
+      "grad_norm": 0.44080349802970886,
+      "learning_rate": 0.0001974264093890866,
+      "loss": 0.809201180934906,
+      "step": 2040
+    },
+    {
+      "epoch": 0.8811218985976268,
+      "grad_norm": 0.46925660967826843,
+      "learning_rate": 0.00019741532855218464,
+      "loss": 0.8064218163490295,
+      "step": 2042
+    },
+    {
+      "epoch": 0.8819848975188781,
+      "grad_norm": 0.4223597049713135,
+      "learning_rate": 0.00019740422422401531,
+      "loss": 0.8135121464729309,
+      "step": 2044
+    },
+    {
+      "epoch": 0.8828478964401294,
+      "grad_norm": 0.46334266662597656,
+      "learning_rate": 0.00019739309640725642,
+      "loss": 0.8047984838485718,
+      "step": 2046
+    },
+    {
+      "epoch": 0.8837108953613808,
+      "grad_norm": 0.413682222366333,
+      "learning_rate": 0.0001973819451045914,
+      "loss": 0.7897430658340454,
+      "step": 2048
+    },
+    {
+      "epoch": 0.8845738942826321,
+      "grad_norm": 0.4276670515537262,
+      "learning_rate": 0.0001973707703187093,
+      "loss": 0.8411629796028137,
+      "step": 2050
+    },
+    {
+      "epoch": 0.8854368932038835,
+      "grad_norm": 0.4199331998825073,
+      "learning_rate": 0.0001973595720523049,
+      "loss": 0.7906913161277771,
+      "step": 2052
+    },
+    {
+      "epoch": 0.8862998921251348,
+      "grad_norm": 0.43233853578567505,
+      "learning_rate": 0.0001973483503080786,
+      "loss": 0.9042854309082031,
+      "step": 2054
+    },
+    {
+      "epoch": 0.8871628910463862,
+      "grad_norm": 0.41147297620773315,
+      "learning_rate": 0.00019733710508873647,
+      "loss": 0.8177635073661804,
+      "step": 2056
+    },
+    {
+      "epoch": 0.8880258899676375,
+      "grad_norm": 0.45957690477371216,
+      "learning_rate": 0.00019732583639699023,
+      "loss": 0.8867166042327881,
+      "step": 2058
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.3979831635951996,
+      "learning_rate": 0.00019731454423555728,
+      "loss": 0.7208530902862549,
+      "step": 2060
+    },
+    {
+      "epoch": 0.8897518878101403,
+      "grad_norm": 0.4434017837047577,
+      "learning_rate": 0.00019730322860716073,
+      "loss": 0.9158181548118591,
+      "step": 2062
+    },
+    {
+      "epoch": 0.8906148867313916,
+      "grad_norm": 0.40012025833129883,
+      "learning_rate": 0.00019729188951452922,
+      "loss": 0.8103255033493042,
+      "step": 2064
+    },
+    {
+      "epoch": 0.891477885652643,
+      "grad_norm": 0.41914620995521545,
+      "learning_rate": 0.00019728052696039715,
+      "loss": 0.7780100703239441,
+      "step": 2066
+    },
+    {
+      "epoch": 0.8923408845738943,
+      "grad_norm": 0.48365312814712524,
+      "learning_rate": 0.00019726914094750453,
+      "loss": 0.7105780839920044,
+      "step": 2068
+    },
+    {
+      "epoch": 0.8932038834951457,
+      "grad_norm": 0.4272058308124542,
+      "learning_rate": 0.0001972577314785971,
+      "loss": 0.7529635429382324,
+      "step": 2070
+    },
+    {
+      "epoch": 0.894066882416397,
+      "grad_norm": 0.48760271072387695,
+      "learning_rate": 0.00019724629855642612,
+      "loss": 0.836787223815918,
+      "step": 2072
+    },
+    {
+      "epoch": 0.8949298813376483,
+      "grad_norm": 0.47811925411224365,
+      "learning_rate": 0.00019723484218374865,
+      "loss": 0.8773119449615479,
+      "step": 2074
+    },
+    {
+      "epoch": 0.8957928802588997,
+      "grad_norm": 0.40109625458717346,
+      "learning_rate": 0.0001972233623633273,
+      "loss": 0.7151904106140137,
+      "step": 2076
+    },
+    {
+      "epoch": 0.896655879180151,
+      "grad_norm": 0.48640304803848267,
+      "learning_rate": 0.00019721185909793047,
+      "loss": 0.8348540663719177,
+      "step": 2078
+    },
+    {
+      "epoch": 0.8975188781014024,
+      "grad_norm": 0.45748841762542725,
+      "learning_rate": 0.000197200332390332,
+      "loss": 0.845246434211731,
+      "step": 2080
+    },
+    {
+      "epoch": 0.8983818770226537,
+      "grad_norm": 0.41650277376174927,
+      "learning_rate": 0.00019718878224331157,
+      "loss": 0.8746084570884705,
+      "step": 2082
+    },
+    {
+      "epoch": 0.8992448759439051,
+      "grad_norm": 0.45878589153289795,
+      "learning_rate": 0.00019717720865965443,
+      "loss": 0.8252862691879272,
+      "step": 2084
+    },
+    {
+      "epoch": 0.9001078748651564,
+      "grad_norm": 0.3710020184516907,
+      "learning_rate": 0.0001971656116421515,
+      "loss": 0.7056596875190735,
+      "step": 2086
+    },
+    {
+      "epoch": 0.9009708737864077,
+      "grad_norm": 0.4251181185245514,
+      "learning_rate": 0.00019715399119359935,
+      "loss": 0.8305537700653076,
+      "step": 2088
+    },
+    {
+      "epoch": 0.9018338727076591,
+      "grad_norm": 0.48429808020591736,
+      "learning_rate": 0.0001971423473168002,
+      "loss": 0.8431704044342041,
+      "step": 2090
+    },
+    {
+      "epoch": 0.9026968716289104,
+      "grad_norm": 0.5384030342102051,
+      "learning_rate": 0.00019713068001456186,
+      "loss": 0.8311790227890015,
+      "step": 2092
+    },
+    {
+      "epoch": 0.9035598705501618,
+      "grad_norm": 0.452029287815094,
+      "learning_rate": 0.00019711898928969796,
+      "loss": 0.8077114224433899,
+      "step": 2094
+    },
+    {
+      "epoch": 0.9044228694714131,
+      "grad_norm": 0.4427074193954468,
+      "learning_rate": 0.0001971072751450276,
+      "loss": 0.8454164266586304,
+      "step": 2096
+    },
+    {
+      "epoch": 0.9052858683926646,
+      "grad_norm": 0.4895693063735962,
+      "learning_rate": 0.00019709553758337557,
+      "loss": 0.8551414608955383,
+      "step": 2098
+    },
+    {
+      "epoch": 0.9061488673139159,
+      "grad_norm": 0.47199201583862305,
+      "learning_rate": 0.00019708377660757244,
+      "loss": 0.9158598184585571,
+      "step": 2100
+    },
+    {
+      "epoch": 0.9061488673139159,
+      "eval_loss": 0.8524587750434875,
+      "eval_runtime": 655.7682,
+      "eval_samples_per_second": 3.141,
+      "eval_steps_per_second": 3.141,
+      "step": 2100
+    },
+    {
+      "epoch": 0.9070118662351672,
+      "grad_norm": 0.45380064845085144,
+      "learning_rate": 0.00019707199222045415,
+      "loss": 0.8301376700401306,
+      "step": 2102
+    },
+    {
+      "epoch": 0.9078748651564186,
+      "grad_norm": 0.4775148034095764,
+      "learning_rate": 0.00019706018442486255,
+      "loss": 0.8191117644309998,
+      "step": 2104
+    },
+    {
+      "epoch": 0.9087378640776699,
+      "grad_norm": 0.40894538164138794,
+      "learning_rate": 0.00019704835322364506,
+      "loss": 0.8333686590194702,
+      "step": 2106
+    },
+    {
+      "epoch": 0.9096008629989213,
+      "grad_norm": 0.4202065169811249,
+      "learning_rate": 0.00019703649861965467,
+      "loss": 0.7916508913040161,
+      "step": 2108
+    },
+    {
+      "epoch": 0.9104638619201726,
+      "grad_norm": 0.39157143235206604,
+      "learning_rate": 0.00019702462061575008,
+      "loss": 0.8018013834953308,
+      "step": 2110
+    },
+    {
+      "epoch": 0.911326860841424,
+      "grad_norm": 0.4623039662837982,
+      "learning_rate": 0.00019701271921479565,
+      "loss": 0.8819739818572998,
+      "step": 2112
+    },
+    {
+      "epoch": 0.9121898597626753,
+      "grad_norm": 0.45183128118515015,
+      "learning_rate": 0.00019700079441966128,
+      "loss": 0.7652842402458191,
+      "step": 2114
+    },
+    {
+      "epoch": 0.9130528586839266,
+      "grad_norm": 0.4562322795391083,
+      "learning_rate": 0.00019698884623322262,
+      "loss": 0.817150890827179,
+      "step": 2116
+    },
+    {
+      "epoch": 0.913915857605178,
+      "grad_norm": 0.45955994725227356,
+      "learning_rate": 0.00019697687465836095,
+      "loss": 0.8223007917404175,
+      "step": 2118
+    },
+    {
+      "epoch": 0.9147788565264293,
+      "grad_norm": 0.44595572352409363,
+      "learning_rate": 0.00019696487969796307,
+      "loss": 0.7716509699821472,
+      "step": 2120
+    },
+    {
+      "epoch": 0.9156418554476807,
+      "grad_norm": 0.4380198121070862,
+      "learning_rate": 0.00019695286135492163,
+      "loss": 0.8205068111419678,
+      "step": 2122
+    },
+    {
+      "epoch": 0.916504854368932,
+      "grad_norm": 0.4025624692440033,
+      "learning_rate": 0.0001969408196321347,
+      "loss": 0.8126305341720581,
+      "step": 2124
+    },
+    {
+      "epoch": 0.9173678532901833,
+      "grad_norm": 0.424277663230896,
+      "learning_rate": 0.00019692875453250616,
+      "loss": 0.7840806841850281,
+      "step": 2126
+    },
+    {
+      "epoch": 0.9182308522114347,
+      "grad_norm": 0.4683000445365906,
+      "learning_rate": 0.00019691666605894538,
+      "loss": 0.9391030669212341,
+      "step": 2128
+    },
+    {
+      "epoch": 0.919093851132686,
+      "grad_norm": 0.47679048776626587,
+      "learning_rate": 0.00019690455421436754,
+      "loss": 0.8336083889007568,
+      "step": 2130
+    },
+    {
+      "epoch": 0.9199568500539375,
+      "grad_norm": 0.45669928193092346,
+      "learning_rate": 0.00019689241900169323,
+      "loss": 0.917514443397522,
+      "step": 2132
+    },
+    {
+      "epoch": 0.9208198489751888,
+      "grad_norm": 0.4372829794883728,
+      "learning_rate": 0.00019688026042384893,
+      "loss": 0.7798282504081726,
+      "step": 2134
+    },
+    {
+      "epoch": 0.9216828478964402,
+      "grad_norm": 0.4497234523296356,
+      "learning_rate": 0.00019686807848376655,
+      "loss": 0.7415590286254883,
+      "step": 2136
+    },
+    {
+      "epoch": 0.9225458468176915,
+      "grad_norm": 0.4892704486846924,
+      "learning_rate": 0.00019685587318438372,
+      "loss": 0.7713689208030701,
+      "step": 2138
+    },
+    {
+      "epoch": 0.9234088457389428,
+      "grad_norm": 0.490495502948761,
+      "learning_rate": 0.0001968436445286437,
+      "loss": 0.821044385433197,
+      "step": 2140
+    },
+    {
+      "epoch": 0.9242718446601942,
+      "grad_norm": 0.43616363406181335,
+      "learning_rate": 0.00019683139251949538,
+      "loss": 0.796081006526947,
+      "step": 2142
+    },
+    {
+      "epoch": 0.9251348435814455,
+      "grad_norm": 0.4199701249599457,
+      "learning_rate": 0.00019681911715989326,
+      "loss": 0.737835705280304,
+      "step": 2144
+    },
+    {
+      "epoch": 0.9259978425026969,
+      "grad_norm": 0.45367109775543213,
+      "learning_rate": 0.0001968068184527975,
+      "loss": 0.8224935531616211,
+      "step": 2146
+    },
+    {
+      "epoch": 0.9268608414239482,
+      "grad_norm": 0.43349263072013855,
+      "learning_rate": 0.0001967944964011739,
+      "loss": 0.826752245426178,
+      "step": 2148
+    },
+    {
+      "epoch": 0.9277238403451996,
+      "grad_norm": 0.4693690538406372,
+      "learning_rate": 0.00019678215100799384,
+      "loss": 0.8527786731719971,
+      "step": 2150
+    },
+    {
+      "epoch": 0.9285868392664509,
+      "grad_norm": 0.4281991124153137,
+      "learning_rate": 0.00019676978227623434,
+      "loss": 0.8101436495780945,
+      "step": 2152
+    },
+    {
+      "epoch": 0.9294498381877022,
+      "grad_norm": 0.4662301540374756,
+      "learning_rate": 0.0001967573902088781,
+      "loss": 0.8997542262077332,
+      "step": 2154
+    },
+    {
+      "epoch": 0.9303128371089536,
+      "grad_norm": 0.41807958483695984,
+      "learning_rate": 0.0001967449748089134,
+      "loss": 0.8378244638442993,
+      "step": 2156
+    },
+    {
+      "epoch": 0.9311758360302049,
+      "grad_norm": 0.4789344072341919,
+      "learning_rate": 0.00019673253607933416,
+      "loss": 0.8562051057815552,
+      "step": 2158
+    },
+    {
+      "epoch": 0.9320388349514563,
+      "grad_norm": 0.43706783652305603,
+      "learning_rate": 0.0001967200740231399,
+      "loss": 0.78457111120224,
+      "step": 2160
+    },
+    {
+      "epoch": 0.9329018338727076,
+      "grad_norm": 0.4441883862018585,
+      "learning_rate": 0.0001967075886433358,
+      "loss": 0.8058217763900757,
+      "step": 2162
+    },
+    {
+      "epoch": 0.933764832793959,
+      "grad_norm": 0.48960480093955994,
+      "learning_rate": 0.00019669507994293266,
+      "loss": 0.916145384311676,
+      "step": 2164
+    },
+    {
+      "epoch": 0.9346278317152104,
+      "grad_norm": 0.3990147113800049,
+      "learning_rate": 0.00019668254792494692,
+      "loss": 0.8805235028266907,
+      "step": 2166
+    },
+    {
+      "epoch": 0.9354908306364617,
+      "grad_norm": 0.4299201965332031,
+      "learning_rate": 0.00019666999259240056,
+      "loss": 0.8611101508140564,
+      "step": 2168
+    },
+    {
+      "epoch": 0.9363538295577131,
+      "grad_norm": 0.5267254114151001,
+      "learning_rate": 0.00019665741394832132,
+      "loss": 0.8429995179176331,
+      "step": 2170
+    },
+    {
+      "epoch": 0.9372168284789644,
+      "grad_norm": 0.46667975187301636,
+      "learning_rate": 0.0001966448119957424,
+      "loss": 0.8057775497436523,
+      "step": 2172
+    },
+    {
+      "epoch": 0.9380798274002158,
+      "grad_norm": 0.4140365421772003,
+      "learning_rate": 0.00019663218673770277,
+      "loss": 0.7456767559051514,
+      "step": 2174
+    },
+    {
+      "epoch": 0.9389428263214671,
+      "grad_norm": 0.4236559569835663,
+      "learning_rate": 0.00019661953817724692,
+      "loss": 0.7320394515991211,
+      "step": 2176
+    },
+    {
+      "epoch": 0.9398058252427185,
+      "grad_norm": 0.4075721800327301,
+      "learning_rate": 0.000196606866317425,
+      "loss": 0.7850301265716553,
+      "step": 2178
+    },
+    {
+      "epoch": 0.9406688241639698,
+      "grad_norm": 0.4638446271419525,
+      "learning_rate": 0.00019659417116129276,
+      "loss": 0.8228051662445068,
+      "step": 2180
+    },
+    {
+      "epoch": 0.9415318230852211,
+      "grad_norm": 0.4641942083835602,
+      "learning_rate": 0.00019658145271191164,
+      "loss": 0.8458912372589111,
+      "step": 2182
+    },
+    {
+      "epoch": 0.9423948220064725,
+      "grad_norm": 0.42868348956108093,
+      "learning_rate": 0.00019656871097234856,
+      "loss": 0.8002372980117798,
+      "step": 2184
+    },
+    {
+      "epoch": 0.9432578209277238,
+      "grad_norm": 0.4726828336715698,
+      "learning_rate": 0.00019655594594567615,
+      "loss": 0.9096182584762573,
+      "step": 2186
+    },
+    {
+      "epoch": 0.9441208198489752,
+      "grad_norm": 0.40363940596580505,
+      "learning_rate": 0.00019654315763497265,
+      "loss": 0.7508110404014587,
+      "step": 2188
+    },
+    {
+      "epoch": 0.9449838187702265,
+      "grad_norm": 0.46951010823249817,
+      "learning_rate": 0.00019653034604332192,
+      "loss": 0.8898510932922363,
+      "step": 2190
+    },
+    {
+      "epoch": 0.9458468176914779,
+      "grad_norm": 0.4564061164855957,
+      "learning_rate": 0.0001965175111738134,
+      "loss": 0.8604891896247864,
+      "step": 2192
+    },
+    {
+      "epoch": 0.9467098166127292,
+      "grad_norm": 0.4366895854473114,
+      "learning_rate": 0.00019650465302954219,
+      "loss": 0.8314935564994812,
+      "step": 2194
+    },
+    {
+      "epoch": 0.9475728155339805,
+      "grad_norm": 0.541490375995636,
+      "learning_rate": 0.0001964917716136089,
+      "loss": 0.851138174533844,
+      "step": 2196
+    },
+    {
+      "epoch": 0.948435814455232,
+      "grad_norm": 0.45251160860061646,
+      "learning_rate": 0.0001964788669291199,
+      "loss": 0.9248369336128235,
+      "step": 2198
+    },
+    {
+      "epoch": 0.9492988133764833,
+      "grad_norm": 0.46237683296203613,
+      "learning_rate": 0.00019646593897918707,
+      "loss": 0.8113608956336975,
+      "step": 2200
+    },
+    {
+      "epoch": 0.9492988133764833,
+      "eval_loss": 0.8443478941917419,
+      "eval_runtime": 666.5866,
+      "eval_samples_per_second": 3.09,
+      "eval_steps_per_second": 3.09,
+      "step": 2200
+    },
+    {
+      "epoch": 0.9501618122977347,
+      "grad_norm": 0.4506337344646454,
+      "learning_rate": 0.0001964529877669279,
+      "loss": 0.8151772618293762,
+      "step": 2202
+    },
+    {
+      "epoch": 0.951024811218986,
+      "grad_norm": 0.42866984009742737,
+      "learning_rate": 0.00019644001329546557,
+      "loss": 0.920696496963501,
+      "step": 2204
+    },
+    {
+      "epoch": 0.9518878101402374,
+      "grad_norm": 0.3899093270301819,
+      "learning_rate": 0.00019642701556792878,
+      "loss": 0.8228384256362915,
+      "step": 2206
+    },
+    {
+      "epoch": 0.9527508090614887,
+      "grad_norm": 0.42472460865974426,
+      "learning_rate": 0.00019641399458745186,
+      "loss": 0.7483987808227539,
+      "step": 2208
+    },
+    {
+      "epoch": 0.95361380798274,
+      "grad_norm": 0.4046783447265625,
+      "learning_rate": 0.00019640095035717482,
+      "loss": 0.7356619834899902,
+      "step": 2210
+    },
+    {
+      "epoch": 0.9544768069039914,
+      "grad_norm": 0.4608006179332733,
+      "learning_rate": 0.00019638788288024316,
+      "loss": 0.7374731302261353,
+      "step": 2212
+    },
+    {
+      "epoch": 0.9553398058252427,
+      "grad_norm": 0.448503315448761,
+      "learning_rate": 0.00019637479215980807,
+      "loss": 0.9128687977790833,
+      "step": 2214
+    },
+    {
+      "epoch": 0.9562028047464941,
+      "grad_norm": 0.4477374851703644,
+      "learning_rate": 0.0001963616781990263,
+      "loss": 0.6983766555786133,
+      "step": 2216
+    },
+    {
+      "epoch": 0.9570658036677454,
+      "grad_norm": 0.41463667154312134,
+      "learning_rate": 0.00019634854100106025,
+      "loss": 0.8543318510055542,
+      "step": 2218
+    },
+    {
+      "epoch": 0.9579288025889967,
+      "grad_norm": 0.5271132588386536,
+      "learning_rate": 0.00019633538056907786,
+      "loss": 0.8866401314735413,
+      "step": 2220
+    },
+    {
+      "epoch": 0.9587918015102481,
+      "grad_norm": 0.4496590495109558,
+      "learning_rate": 0.00019632219690625272,
+      "loss": 0.8414724469184875,
+      "step": 2222
+    },
+    {
+      "epoch": 0.9596548004314994,
+      "grad_norm": 0.4772113263607025,
+      "learning_rate": 0.00019630899001576405,
+      "loss": 0.8859618902206421,
+      "step": 2224
+    },
+    {
+      "epoch": 0.9605177993527508,
+      "grad_norm": 0.5249642729759216,
+      "learning_rate": 0.0001962957599007966,
+      "loss": 0.8347851037979126,
+      "step": 2226
+    },
+    {
+      "epoch": 0.9613807982740021,
+      "grad_norm": 0.4931469261646271,
+      "learning_rate": 0.0001962825065645407,
+      "loss": 0.7893235087394714,
+      "step": 2228
+    },
+    {
+      "epoch": 0.9622437971952535,
+      "grad_norm": 0.45010602474212646,
+      "learning_rate": 0.00019626923001019245,
+      "loss": 0.815602719783783,
+      "step": 2230
+    },
+    {
+      "epoch": 0.9631067961165048,
+      "grad_norm": 0.42947128415107727,
+      "learning_rate": 0.00019625593024095333,
+      "loss": 0.807309627532959,
+      "step": 2232
+    },
+    {
+      "epoch": 0.9639697950377561,
+      "grad_norm": 0.43500378727912903,
+      "learning_rate": 0.00019624260726003057,
+      "loss": 0.8135440945625305,
+      "step": 2234
+    },
+    {
+      "epoch": 0.9648327939590076,
+      "grad_norm": 0.41840270161628723,
+      "learning_rate": 0.00019622926107063692,
+      "loss": 0.802107036113739,
+      "step": 2236
+    },
+    {
+      "epoch": 0.9656957928802589,
+      "grad_norm": 0.4580598771572113,
+      "learning_rate": 0.00019621589167599077,
+      "loss": 0.7596800923347473,
+      "step": 2238
+    },
+    {
+      "epoch": 0.9665587918015103,
+      "grad_norm": 0.38064274191856384,
+      "learning_rate": 0.0001962024990793161,
+      "loss": 0.7609489560127258,
+      "step": 2240
+    },
+    {
+      "epoch": 0.9674217907227616,
+      "grad_norm": 0.39098140597343445,
+      "learning_rate": 0.00019618908328384246,
+      "loss": 0.7829734086990356,
+      "step": 2242
+    },
+    {
+      "epoch": 0.968284789644013,
+      "grad_norm": 0.38412022590637207,
+      "learning_rate": 0.00019617564429280502,
+      "loss": 0.7570722699165344,
+      "step": 2244
+    },
+    {
+      "epoch": 0.9691477885652643,
+      "grad_norm": 0.41451776027679443,
+      "learning_rate": 0.0001961621821094445,
+      "loss": 0.8634825348854065,
+      "step": 2246
+    },
+    {
+      "epoch": 0.9700107874865156,
+      "grad_norm": 0.4989950954914093,
+      "learning_rate": 0.00019614869673700725,
+      "loss": 0.9002810120582581,
+      "step": 2248
+    },
+    {
+      "epoch": 0.970873786407767,
+      "grad_norm": 0.4316846430301666,
+      "learning_rate": 0.00019613518817874524,
+      "loss": 0.7587819695472717,
+      "step": 2250
+    },
+    {
+      "epoch": 0.9717367853290183,
+      "grad_norm": 0.41293349862098694,
+      "learning_rate": 0.000196121656437916,
+      "loss": 0.686238706111908,
+      "step": 2252
+    },
+    {
+      "epoch": 0.9725997842502697,
+      "grad_norm": 0.40252262353897095,
+      "learning_rate": 0.00019610810151778258,
+      "loss": 0.7895162105560303,
+      "step": 2254
+    },
+    {
+      "epoch": 0.973462783171521,
+      "grad_norm": 0.42973560094833374,
+      "learning_rate": 0.0001960945234216138,
+      "loss": 0.8360300064086914,
+      "step": 2256
+    },
+    {
+      "epoch": 0.9743257820927724,
+      "grad_norm": 0.40562206506729126,
+      "learning_rate": 0.00019608092215268386,
+      "loss": 0.7624704241752625,
+      "step": 2258
+    },
+    {
+      "epoch": 0.9751887810140237,
+      "grad_norm": 0.4486660063266754,
+      "learning_rate": 0.00019606729771427266,
+      "loss": 0.8285008072853088,
+      "step": 2260
+    },
+    {
+      "epoch": 0.976051779935275,
+      "grad_norm": 0.37069520354270935,
+      "learning_rate": 0.0001960536501096657,
+      "loss": 0.7951943278312683,
+      "step": 2262
+    },
+    {
+      "epoch": 0.9769147788565264,
+      "grad_norm": 0.43367981910705566,
+      "learning_rate": 0.00019603997934215404,
+      "loss": 0.7641335129737854,
+      "step": 2264
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.42540937662124634,
+      "learning_rate": 0.00019602628541503432,
+      "loss": 0.8449530601501465,
+      "step": 2266
+    },
+    {
+      "epoch": 0.9786407766990292,
+      "grad_norm": 0.46175941824913025,
+      "learning_rate": 0.00019601256833160874,
+      "loss": 0.8207030296325684,
+      "step": 2268
+    },
+    {
+      "epoch": 0.9795037756202805,
+      "grad_norm": 0.3834969103336334,
+      "learning_rate": 0.00019599882809518513,
+      "loss": 0.7753700017929077,
+      "step": 2270
+    },
+    {
+      "epoch": 0.9803667745415319,
+      "grad_norm": 0.43960243463516235,
+      "learning_rate": 0.0001959850647090769,
+      "loss": 0.8844934701919556,
+      "step": 2272
+    },
+    {
+      "epoch": 0.9812297734627832,
+      "grad_norm": 0.4240610897541046,
+      "learning_rate": 0.00019597127817660303,
+      "loss": 0.7795814275741577,
+      "step": 2274
+    },
+    {
+      "epoch": 0.9820927723840345,
+      "grad_norm": 0.41870981454849243,
+      "learning_rate": 0.00019595746850108807,
+      "loss": 0.6960644721984863,
+      "step": 2276
+    },
+    {
+      "epoch": 0.9829557713052859,
+      "grad_norm": 0.43871861696243286,
+      "learning_rate": 0.00019594363568586215,
+      "loss": 0.7709649205207825,
+      "step": 2278
+    },
+    {
+      "epoch": 0.9838187702265372,
+      "grad_norm": 0.45331820845603943,
+      "learning_rate": 0.00019592977973426098,
+      "loss": 0.7324449419975281,
+      "step": 2280
+    },
+    {
+      "epoch": 0.9846817691477886,
+      "grad_norm": 0.4300173223018646,
+      "learning_rate": 0.00019591590064962593,
+      "loss": 0.8720724582672119,
+      "step": 2282
+    },
+    {
+      "epoch": 0.9855447680690399,
+      "grad_norm": 0.4478892982006073,
+      "learning_rate": 0.0001959019984353038,
+      "loss": 0.7396156191825867,
+      "step": 2284
+    },
+    {
+      "epoch": 0.9864077669902913,
+      "grad_norm": 0.4391026198863983,
+      "learning_rate": 0.00019588807309464708,
+      "loss": 0.8303509950637817,
+      "step": 2286
+    },
+    {
+      "epoch": 0.9872707659115426,
+      "grad_norm": 0.4046599268913269,
+      "learning_rate": 0.00019587412463101378,
+      "loss": 0.739641010761261,
+      "step": 2288
+    },
+    {
+      "epoch": 0.9881337648327939,
+      "grad_norm": 0.4619915187358856,
+      "learning_rate": 0.00019586015304776756,
+      "loss": 0.7448247671127319,
+      "step": 2290
+    },
+    {
+      "epoch": 0.9889967637540453,
+      "grad_norm": 0.4603526294231415,
+      "learning_rate": 0.00019584615834827753,
+      "loss": 0.8184107542037964,
+      "step": 2292
+    },
+    {
+      "epoch": 0.9898597626752966,
+      "grad_norm": 0.4828874170780182,
+      "learning_rate": 0.00019583214053591852,
+      "loss": 0.9069648385047913,
+      "step": 2294
+    },
+    {
+      "epoch": 0.990722761596548,
+      "grad_norm": 0.37467876076698303,
+      "learning_rate": 0.00019581809961407082,
+      "loss": 0.6628880500793457,
+      "step": 2296
+    },
+    {
+      "epoch": 0.9915857605177993,
+      "grad_norm": 0.4300445318222046,
+      "learning_rate": 0.00019580403558612037,
+      "loss": 0.7712231278419495,
+      "step": 2298
+    },
+    {
+      "epoch": 0.9924487594390508,
+      "grad_norm": 0.4368257522583008,
+      "learning_rate": 0.00019578994845545863,
+      "loss": 0.7796293497085571,
+      "step": 2300
+    },
+    {
+      "epoch": 0.9924487594390508,
+      "eval_loss": 0.839731752872467,
+      "eval_runtime": 666.2332,
+      "eval_samples_per_second": 3.092,
+      "eval_steps_per_second": 3.092,
+      "step": 2300
+    },
+    {
+      "epoch": 0.993311758360302,
+      "grad_norm": 0.4383920729160309,
+      "learning_rate": 0.00019577583822548262,
+      "loss": 0.7504367232322693,
+      "step": 2302
+    },
+    {
+      "epoch": 0.9941747572815534,
+      "grad_norm": 0.3895981013774872,
+      "learning_rate": 0.00019576170489959496,
+      "loss": 0.7298936247825623,
+      "step": 2304
+    },
+    {
+      "epoch": 0.9950377562028048,
+      "grad_norm": 0.4950196444988251,
+      "learning_rate": 0.00019574754848120392,
+      "loss": 0.9137371778488159,
+      "step": 2306
+    },
+    {
+      "epoch": 0.9959007551240561,
+      "grad_norm": 0.5115531086921692,
+      "learning_rate": 0.00019573336897372318,
+      "loss": 0.9203279614448547,
+      "step": 2308
+    },
+    {
+      "epoch": 0.9967637540453075,
+      "grad_norm": 0.43145665526390076,
+      "learning_rate": 0.000195719166380572,
+      "loss": 0.7708958387374878,
+      "step": 2310
+    },
+    {
+      "epoch": 0.9976267529665588,
+      "grad_norm": 0.39575520157814026,
+      "learning_rate": 0.00019570494070517545,
+      "loss": 0.7911062836647034,
+      "step": 2312
+    },
+    {
+      "epoch": 0.9984897518878102,
+      "grad_norm": 0.45690420269966125,
+      "learning_rate": 0.00019569069195096386,
+      "loss": 0.8282244205474854,
+      "step": 2314
+    },
+    {
+      "epoch": 0.9993527508090615,
+      "grad_norm": 0.43362128734588623,
+      "learning_rate": 0.00019567642012137325,
+      "loss": 0.8658884763717651,
+      "step": 2316
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6889842748641968,
+      "learning_rate": 0.00019566212521984527,
+      "loss": 0.7823468446731567,
+      "step": 2318
+    },
+    {
+      "epoch": 1.0008629989212514,
+      "grad_norm": 0.3945363759994507,
+      "learning_rate": 0.00019564780724982706,
+      "loss": 0.8244057297706604,
+      "step": 2320
+    },
+    {
+      "epoch": 1.0017259978425026,
+      "grad_norm": 0.5313655734062195,
+      "learning_rate": 0.00019563346621477129,
+      "loss": 0.8228418827056885,
+      "step": 2322
+    },
+    {
+      "epoch": 1.002588996763754,
+      "grad_norm": 0.47728294134140015,
+      "learning_rate": 0.00019561910211813625,
+      "loss": 0.8627800941467285,
+      "step": 2324
+    },
+    {
+      "epoch": 1.0034519956850054,
+      "grad_norm": 0.4706253111362457,
+      "learning_rate": 0.00019560471496338582,
+      "loss": 0.8810665011405945,
+      "step": 2326
+    },
+    {
+      "epoch": 1.0043149946062568,
+      "grad_norm": 0.4333725571632385,
+      "learning_rate": 0.0001955903047539893,
+      "loss": 0.7736411094665527,
+      "step": 2328
+    },
+    {
+      "epoch": 1.005177993527508,
+      "grad_norm": 0.49580323696136475,
+      "learning_rate": 0.00019557587149342178,
+      "loss": 0.9185295104980469,
+      "step": 2330
+    },
+    {
+      "epoch": 1.0060409924487594,
+      "grad_norm": 0.4362829029560089,
+      "learning_rate": 0.0001955614151851637,
+      "loss": 0.7387797832489014,
+      "step": 2332
+    },
+    {
+      "epoch": 1.0069039913700109,
+      "grad_norm": 0.42584139108657837,
+      "learning_rate": 0.00019554693583270113,
+      "loss": 0.672156810760498,
+      "step": 2334
+    },
+    {
+      "epoch": 1.007766990291262,
+      "grad_norm": 0.40073466300964355,
+      "learning_rate": 0.0001955324334395257,
+      "loss": 0.7638119459152222,
+      "step": 2336
+    },
+    {
+      "epoch": 1.0086299892125135,
+      "grad_norm": 0.49992597103118896,
+      "learning_rate": 0.00019551790800913458,
+      "loss": 0.7930200695991516,
+      "step": 2338
+    },
+    {
+      "epoch": 1.0094929881337649,
+      "grad_norm": 0.3825504779815674,
+      "learning_rate": 0.00019550335954503058,
+      "loss": 0.7128595113754272,
+      "step": 2340
+    },
+    {
+      "epoch": 1.0103559870550163,
+      "grad_norm": 0.4654180705547333,
+      "learning_rate": 0.00019548878805072196,
+      "loss": 0.7130335569381714,
+      "step": 2342
+    },
+    {
+      "epoch": 1.0112189859762675,
+      "grad_norm": 0.4199283719062805,
+      "learning_rate": 0.00019547419352972258,
+      "loss": 0.7843249440193176,
+      "step": 2344
+    },
+    {
+      "epoch": 1.0120819848975189,
+      "grad_norm": 0.43597257137298584,
+      "learning_rate": 0.0001954595759855518,
+      "loss": 0.676262617111206,
+      "step": 2346
+    },
+    {
+      "epoch": 1.0129449838187703,
+      "grad_norm": 0.47415891289711,
+      "learning_rate": 0.0001954449354217346,
+      "loss": 0.742564857006073,
+      "step": 2348
+    },
+    {
+      "epoch": 1.0138079827400215,
+      "grad_norm": 0.44753482937812805,
+      "learning_rate": 0.00019543027184180153,
+      "loss": 0.7419085502624512,
+      "step": 2350
+    },
+    {
+      "epoch": 1.014670981661273,
+      "grad_norm": 0.4175751209259033,
+      "learning_rate": 0.0001954155852492886,
+      "loss": 0.7373939752578735,
+      "step": 2352
+    },
+    {
+      "epoch": 1.0155339805825243,
+      "grad_norm": 0.40376800298690796,
+      "learning_rate": 0.00019540087564773738,
+      "loss": 0.7639825344085693,
+      "step": 2354
+    },
+    {
+      "epoch": 1.0163969795037757,
+      "grad_norm": 0.4166127145290375,
+      "learning_rate": 0.0001953861430406951,
+      "loss": 0.7797452211380005,
+      "step": 2356
+    },
+    {
+      "epoch": 1.017259978425027,
+      "grad_norm": 0.4340934753417969,
+      "learning_rate": 0.0001953713874317144,
+      "loss": 0.8258501887321472,
+      "step": 2358
+    },
+    {
+      "epoch": 1.0181229773462783,
+      "grad_norm": 0.47081413865089417,
+      "learning_rate": 0.0001953566088243536,
+      "loss": 0.7664495706558228,
+      "step": 2360
+    },
+    {
+      "epoch": 1.0189859762675297,
+      "grad_norm": 0.4126851260662079,
+      "learning_rate": 0.00019534180722217644,
+      "loss": 0.7411028742790222,
+      "step": 2362
+    },
+    {
+      "epoch": 1.019848975188781,
+      "grad_norm": 0.45279955863952637,
+      "learning_rate": 0.00019532698262875227,
+      "loss": 0.7514335513114929,
+      "step": 2364
+    },
+    {
+      "epoch": 1.0207119741100323,
+      "grad_norm": 0.4857143461704254,
+      "learning_rate": 0.00019531213504765595,
+      "loss": 0.7544763088226318,
+      "step": 2366
+    },
+    {
+      "epoch": 1.0215749730312838,
+      "grad_norm": 0.5232970714569092,
+      "learning_rate": 0.00019529726448246795,
+      "loss": 0.7246702313423157,
+      "step": 2368
+    },
+    {
+      "epoch": 1.0224379719525352,
+      "grad_norm": 0.4434663653373718,
+      "learning_rate": 0.00019528237093677424,
+      "loss": 0.7399187684059143,
+      "step": 2370
+    },
+    {
+      "epoch": 1.0233009708737864,
+      "grad_norm": 0.44713014364242554,
+      "learning_rate": 0.0001952674544141663,
+      "loss": 0.7208506464958191,
+      "step": 2372
+    },
+    {
+      "epoch": 1.0241639697950378,
+      "grad_norm": 0.43205446004867554,
+      "learning_rate": 0.0001952525149182412,
+      "loss": 0.761768639087677,
+      "step": 2374
+    },
+    {
+      "epoch": 1.0250269687162892,
+      "grad_norm": 0.4322265386581421,
+      "learning_rate": 0.0001952375524526015,
+      "loss": 0.6573513746261597,
+      "step": 2376
+    },
+    {
+      "epoch": 1.0258899676375404,
+      "grad_norm": 0.4776996970176697,
+      "learning_rate": 0.0001952225670208554,
+      "loss": 0.8118118047714233,
+      "step": 2378
+    },
+    {
+      "epoch": 1.0267529665587918,
+      "grad_norm": 0.5014623403549194,
+      "learning_rate": 0.00019520755862661648,
+      "loss": 0.781197190284729,
+      "step": 2380
+    },
+    {
+      "epoch": 1.0276159654800432,
+      "grad_norm": 0.5164223313331604,
+      "learning_rate": 0.00019519252727350403,
+      "loss": 0.8399010896682739,
+      "step": 2382
+    },
+    {
+      "epoch": 1.0284789644012946,
+      "grad_norm": 0.47874927520751953,
+      "learning_rate": 0.00019517747296514276,
+      "loss": 0.786519467830658,
+      "step": 2384
+    },
+    {
+      "epoch": 1.0293419633225458,
+      "grad_norm": 0.48447099328041077,
+      "learning_rate": 0.00019516239570516292,
+      "loss": 0.7837404012680054,
+      "step": 2386
+    },
+    {
+      "epoch": 1.0302049622437972,
+      "grad_norm": 0.4762440323829651,
+      "learning_rate": 0.0001951472954972004,
+      "loss": 0.833958625793457,
+      "step": 2388
+    },
+    {
+      "epoch": 1.0310679611650486,
+      "grad_norm": 0.42814165353775024,
+      "learning_rate": 0.00019513217234489645,
+      "loss": 0.7688734531402588,
+      "step": 2390
+    },
+    {
+      "epoch": 1.0319309600862998,
+      "grad_norm": 0.4784977436065674,
+      "learning_rate": 0.00019511702625189803,
+      "loss": 0.814251720905304,
+      "step": 2392
+    },
+    {
+      "epoch": 1.0327939590075512,
+      "grad_norm": 0.44989243149757385,
+      "learning_rate": 0.00019510185722185748,
+      "loss": 0.7277538180351257,
+      "step": 2394
+    },
+    {
+      "epoch": 1.0336569579288026,
+      "grad_norm": 0.5141931772232056,
+      "learning_rate": 0.0001950866652584328,
+      "loss": 0.844467282295227,
+      "step": 2396
+    },
+    {
+      "epoch": 1.0345199568500538,
+      "grad_norm": 0.48569414019584656,
+      "learning_rate": 0.00019507145036528747,
+      "loss": 0.7662147879600525,
+      "step": 2398
+    },
+    {
+      "epoch": 1.0353829557713052,
+      "grad_norm": 0.5075576901435852,
+      "learning_rate": 0.00019505621254609047,
+      "loss": 0.7628200054168701,
+      "step": 2400
+    },
+    {
+      "epoch": 1.0353829557713052,
+      "eval_loss": 0.8369861245155334,
+      "eval_runtime": 653.1661,
+      "eval_samples_per_second": 3.154,
+      "eval_steps_per_second": 3.154,
+      "step": 2400
+    },
+    {
+      "epoch": 1.0362459546925566,
+      "grad_norm": 0.49423643946647644,
+      "learning_rate": 0.00019504095180451628,
+      "loss": 0.8225719332695007,
+      "step": 2402
+    },
+    {
+      "epoch": 1.037108953613808,
+      "grad_norm": 0.4558854401111603,
+      "learning_rate": 0.00019502566814424505,
+      "loss": 0.8239169120788574,
+      "step": 2404
+    },
+    {
+      "epoch": 1.0379719525350593,
+      "grad_norm": 0.4864993691444397,
+      "learning_rate": 0.00019501036156896232,
+      "loss": 0.7805002331733704,
+      "step": 2406
+    },
+    {
+      "epoch": 1.0388349514563107,
+      "grad_norm": 0.44108837842941284,
+      "learning_rate": 0.00019499503208235918,
+      "loss": 0.866910994052887,
+      "step": 2408
+    },
+    {
+      "epoch": 1.039697950377562,
+      "grad_norm": 0.4616626799106598,
+      "learning_rate": 0.00019497967968813232,
+      "loss": 0.7601662874221802,
+      "step": 2410
+    },
+    {
+      "epoch": 1.0405609492988135,
+      "grad_norm": 0.4792969524860382,
+      "learning_rate": 0.00019496430438998387,
+      "loss": 0.8155668377876282,
+      "step": 2412
+    },
+    {
+      "epoch": 1.0414239482200647,
+      "grad_norm": 0.45400261878967285,
+      "learning_rate": 0.00019494890619162152,
+      "loss": 0.7879545092582703,
+      "step": 2414
+    },
+    {
+      "epoch": 1.042286947141316,
+      "grad_norm": 0.44541165232658386,
+      "learning_rate": 0.0001949334850967585,
+      "loss": 0.7196864485740662,
+      "step": 2416
+    },
+    {
+      "epoch": 1.0431499460625675,
+      "grad_norm": 0.44515085220336914,
+      "learning_rate": 0.00019491804110911343,
+      "loss": 0.7288097739219666,
+      "step": 2418
+    },
+    {
+      "epoch": 1.0440129449838187,
+      "grad_norm": 0.43586596846580505,
+      "learning_rate": 0.0001949025742324107,
+      "loss": 0.7182422280311584,
+      "step": 2420
+    },
+    {
+      "epoch": 1.04487594390507,
+      "grad_norm": 0.44399815797805786,
+      "learning_rate": 0.00019488708447038002,
+      "loss": 0.7005030512809753,
+      "step": 2422
+    },
+    {
+      "epoch": 1.0457389428263215,
+      "grad_norm": 0.4658401310443878,
+      "learning_rate": 0.00019487157182675665,
+      "loss": 0.715505063533783,
+      "step": 2424
+    },
+    {
+      "epoch": 1.0466019417475727,
+      "grad_norm": 0.4468056261539459,
+      "learning_rate": 0.00019485603630528143,
+      "loss": 0.7170135974884033,
+      "step": 2426
+    },
+    {
+      "epoch": 1.0474649406688241,
+      "grad_norm": 0.5302334427833557,
+      "learning_rate": 0.00019484047790970066,
+      "loss": 0.83464115858078,
+      "step": 2428
+    },
+    {
+      "epoch": 1.0483279395900755,
+      "grad_norm": 0.46583443880081177,
+      "learning_rate": 0.0001948248966437662,
+      "loss": 0.7129145264625549,
+      "step": 2430
+    },
+    {
+      "epoch": 1.049190938511327,
+      "grad_norm": 0.38922831416130066,
+      "learning_rate": 0.0001948092925112354,
+      "loss": 0.7990599870681763,
+      "step": 2432
+    },
+    {
+      "epoch": 1.0500539374325781,
+      "grad_norm": 0.4599211513996124,
+      "learning_rate": 0.00019479366551587108,
+      "loss": 0.8572773933410645,
+      "step": 2434
+    },
+    {
+      "epoch": 1.0509169363538295,
+      "grad_norm": 0.47514498233795166,
+      "learning_rate": 0.00019477801566144165,
+      "loss": 0.8107781410217285,
+      "step": 2436
+    },
+    {
+      "epoch": 1.051779935275081,
+      "grad_norm": 0.41368064284324646,
+      "learning_rate": 0.00019476234295172102,
+      "loss": 0.7433347702026367,
+      "step": 2438
+    },
+    {
+      "epoch": 1.0526429341963321,
+      "grad_norm": 0.4666398763656616,
+      "learning_rate": 0.00019474664739048858,
+      "loss": 0.8033983111381531,
+      "step": 2440
+    },
+    {
+      "epoch": 1.0535059331175836,
+      "grad_norm": 0.41621699929237366,
+      "learning_rate": 0.00019473092898152924,
+      "loss": 0.7320330142974854,
+      "step": 2442
+    },
+    {
+      "epoch": 1.054368932038835,
+      "grad_norm": 0.43523117899894714,
+      "learning_rate": 0.00019471518772863343,
+      "loss": 0.7742927074432373,
+      "step": 2444
+    },
+    {
+      "epoch": 1.0552319309600864,
+      "grad_norm": 0.5151914358139038,
+      "learning_rate": 0.0001946994236355971,
+      "loss": 0.8301699161529541,
+      "step": 2446
+    },
+    {
+      "epoch": 1.0560949298813376,
+      "grad_norm": 0.566112756729126,
+      "learning_rate": 0.0001946836367062216,
+      "loss": 0.837057888507843,
+      "step": 2448
+    },
+    {
+      "epoch": 1.056957928802589,
+      "grad_norm": 0.4257231652736664,
+      "learning_rate": 0.00019466782694431398,
+      "loss": 0.7323788404464722,
+      "step": 2450
+    },
+    {
+      "epoch": 1.0578209277238404,
+      "grad_norm": 0.5477433800697327,
+      "learning_rate": 0.0001946519943536867,
+      "loss": 0.7410078048706055,
+      "step": 2452
+    },
+    {
+      "epoch": 1.0586839266450916,
+      "grad_norm": 0.37357097864151,
+      "learning_rate": 0.00019463613893815762,
+      "loss": 0.6646532416343689,
+      "step": 2454
+    },
+    {
+      "epoch": 1.059546925566343,
+      "grad_norm": 0.438048779964447,
+      "learning_rate": 0.00019462026070155028,
+      "loss": 0.7773549556732178,
+      "step": 2456
+    },
+    {
+      "epoch": 1.0604099244875944,
+      "grad_norm": 0.5114307999610901,
+      "learning_rate": 0.0001946043596476936,
+      "loss": 0.8977773785591125,
+      "step": 2458
+    },
+    {
+      "epoch": 1.0612729234088458,
+      "grad_norm": 0.4340408146381378,
+      "learning_rate": 0.0001945884357804221,
+      "loss": 0.8128405809402466,
+      "step": 2460
+    },
+    {
+      "epoch": 1.062135922330097,
+      "grad_norm": 0.4922826290130615,
+      "learning_rate": 0.0001945724891035757,
+      "loss": 0.8096795678138733,
+      "step": 2462
+    },
+    {
+      "epoch": 1.0629989212513484,
+      "grad_norm": 0.47231894731521606,
+      "learning_rate": 0.00019455651962099987,
+      "loss": 0.7965760231018066,
+      "step": 2464
+    },
+    {
+      "epoch": 1.0638619201725998,
+      "grad_norm": 0.4519463777542114,
+      "learning_rate": 0.00019454052733654565,
+      "loss": 0.7136726975440979,
+      "step": 2466
+    },
+    {
+      "epoch": 1.064724919093851,
+      "grad_norm": 0.44883614778518677,
+      "learning_rate": 0.0001945245122540694,
+      "loss": 0.8136170506477356,
+      "step": 2468
+    },
+    {
+      "epoch": 1.0655879180151024,
+      "grad_norm": 0.4224080741405487,
+      "learning_rate": 0.00019450847437743317,
+      "loss": 0.7840399146080017,
+      "step": 2470
+    },
+    {
+      "epoch": 1.0664509169363539,
+      "grad_norm": 0.4979367256164551,
+      "learning_rate": 0.00019449241371050438,
+      "loss": 0.8202947378158569,
+      "step": 2472
+    },
+    {
+      "epoch": 1.0673139158576053,
+      "grad_norm": 0.5551356673240662,
+      "learning_rate": 0.000194476330257156,
+      "loss": 0.8608070611953735,
+      "step": 2474
+    },
+    {
+      "epoch": 1.0681769147788565,
+      "grad_norm": 0.3980900049209595,
+      "learning_rate": 0.00019446022402126647,
+      "loss": 0.7202636003494263,
+      "step": 2476
+    },
+    {
+      "epoch": 1.0690399137001079,
+      "grad_norm": 0.5393417477607727,
+      "learning_rate": 0.00019444409500671977,
+      "loss": 0.8301891684532166,
+      "step": 2478
+    },
+    {
+      "epoch": 1.0699029126213593,
+      "grad_norm": 0.47717350721359253,
+      "learning_rate": 0.0001944279432174053,
+      "loss": 0.700567901134491,
+      "step": 2480
+    },
+    {
+      "epoch": 1.0707659115426105,
+      "grad_norm": 0.5197957158088684,
+      "learning_rate": 0.000194411768657218,
+      "loss": 0.794978141784668,
+      "step": 2482
+    },
+    {
+      "epoch": 1.0716289104638619,
+      "grad_norm": 0.5289306044578552,
+      "learning_rate": 0.0001943955713300583,
+      "loss": 0.8052116632461548,
+      "step": 2484
+    },
+    {
+      "epoch": 1.0724919093851133,
+      "grad_norm": 0.4360409080982208,
+      "learning_rate": 0.00019437935123983212,
+      "loss": 0.750991702079773,
+      "step": 2486
+    },
+    {
+      "epoch": 1.0733549083063647,
+      "grad_norm": 0.38651731610298157,
+      "learning_rate": 0.00019436310839045085,
+      "loss": 0.6631898880004883,
+      "step": 2488
+    },
+    {
+      "epoch": 1.074217907227616,
+      "grad_norm": 0.4376210868358612,
+      "learning_rate": 0.00019434684278583138,
+      "loss": 0.7995471358299255,
+      "step": 2490
+    },
+    {
+      "epoch": 1.0750809061488673,
+      "grad_norm": 0.46636906266212463,
+      "learning_rate": 0.0001943305544298961,
+      "loss": 0.7633864879608154,
+      "step": 2492
+    },
+    {
+      "epoch": 1.0759439050701187,
+      "grad_norm": 0.43499618768692017,
+      "learning_rate": 0.00019431424332657288,
+      "loss": 0.7281562089920044,
+      "step": 2494
+    },
+    {
+      "epoch": 1.07680690399137,
+      "grad_norm": 0.39683374762535095,
+      "learning_rate": 0.000194297909479795,
+      "loss": 0.7313723564147949,
+      "step": 2496
+    },
+    {
+      "epoch": 1.0776699029126213,
+      "grad_norm": 0.4545603096485138,
+      "learning_rate": 0.0001942815528935014,
+      "loss": 0.7120141983032227,
+      "step": 2498
+    },
+    {
+      "epoch": 1.0785329018338727,
+      "grad_norm": 0.5040699243545532,
+      "learning_rate": 0.0001942651735716363,
+      "loss": 0.752600908279419,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0785329018338727,
+      "eval_loss": 0.8323014378547668,
+      "eval_runtime": 652.3791,
+      "eval_samples_per_second": 3.158,
+      "eval_steps_per_second": 3.158,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0793959007551241,
+      "grad_norm": 0.48951438069343567,
+      "learning_rate": 0.00019424877151814958,
+      "loss": 0.7719982266426086,
+      "step": 2502
+    },
+    {
+      "epoch": 1.0802588996763753,
+      "grad_norm": 0.5009822845458984,
+      "learning_rate": 0.00019423234673699648,
+      "loss": 0.7921367883682251,
+      "step": 2504
+    },
+    {
+      "epoch": 1.0811218985976268,
+      "grad_norm": 0.4699440896511078,
+      "learning_rate": 0.00019421589923213772,
+      "loss": 0.7714369297027588,
+      "step": 2506
+    },
+    {
+      "epoch": 1.0819848975188782,
+      "grad_norm": 0.4438663125038147,
+      "learning_rate": 0.00019419942900753963,
+      "loss": 0.6981601119041443,
+      "step": 2508
+    },
+    {
+      "epoch": 1.0828478964401294,
+      "grad_norm": 0.49927031993865967,
+      "learning_rate": 0.00019418293606717385,
+      "loss": 0.7822043895721436,
+      "step": 2510
+    },
+    {
+      "epoch": 1.0837108953613808,
+      "grad_norm": 0.395433634519577,
+      "learning_rate": 0.00019416642041501767,
+      "loss": 0.7166627049446106,
+      "step": 2512
+    },
+    {
+      "epoch": 1.0845738942826322,
+      "grad_norm": 0.47293251752853394,
+      "learning_rate": 0.00019414988205505366,
+      "loss": 0.7287489771842957,
+      "step": 2514
+    },
+    {
+      "epoch": 1.0854368932038836,
+      "grad_norm": 0.43168675899505615,
+      "learning_rate": 0.00019413332099127008,
+      "loss": 0.7672322988510132,
+      "step": 2516
+    },
+    {
+      "epoch": 1.0862998921251348,
+      "grad_norm": 0.4542049765586853,
+      "learning_rate": 0.00019411673722766044,
+      "loss": 0.7427115440368652,
+      "step": 2518
+    },
+    {
+      "epoch": 1.0871628910463862,
+      "grad_norm": 0.4920838177204132,
+      "learning_rate": 0.00019410013076822394,
+      "loss": 0.742889404296875,
+      "step": 2520
+    },
+    {
+      "epoch": 1.0880258899676376,
+      "grad_norm": 0.5404410362243652,
+      "learning_rate": 0.0001940835016169651,
+      "loss": 0.767113208770752,
+      "step": 2522
+    },
+    {
+      "epoch": 1.0888888888888888,
+      "grad_norm": 0.4543033540248871,
+      "learning_rate": 0.00019406684977789395,
+      "loss": 0.6729961037635803,
+      "step": 2524
+    },
+    {
+      "epoch": 1.0897518878101402,
+      "grad_norm": 0.49171510338783264,
+      "learning_rate": 0.00019405017525502607,
+      "loss": 0.6907814145088196,
+      "step": 2526
+    },
+    {
+      "epoch": 1.0906148867313916,
+      "grad_norm": 0.491252601146698,
+      "learning_rate": 0.00019403347805238238,
+      "loss": 0.7643960118293762,
+      "step": 2528
+    },
+    {
+      "epoch": 1.091477885652643,
+      "grad_norm": 0.527920663356781,
+      "learning_rate": 0.0001940167581739894,
+      "loss": 0.8070526123046875,
+      "step": 2530
+    },
+    {
+      "epoch": 1.0923408845738942,
+      "grad_norm": 0.4318726658821106,
+      "learning_rate": 0.00019400001562387898,
+      "loss": 0.7900120615959167,
+      "step": 2532
+    },
+    {
+      "epoch": 1.0932038834951456,
+      "grad_norm": 0.4903397560119629,
+      "learning_rate": 0.00019398325040608855,
+      "loss": 0.7778371572494507,
+      "step": 2534
+    },
+    {
+      "epoch": 1.094066882416397,
+      "grad_norm": 0.4835105240345001,
+      "learning_rate": 0.00019396646252466097,
+      "loss": 0.7758864164352417,
+      "step": 2536
+    },
+    {
+      "epoch": 1.0949298813376482,
+      "grad_norm": 0.47125598788261414,
+      "learning_rate": 0.00019394965198364455,
+      "loss": 0.7927643656730652,
+      "step": 2538
+    },
+    {
+      "epoch": 1.0957928802588996,
+      "grad_norm": 0.46723976731300354,
+      "learning_rate": 0.0001939328187870931,
+      "loss": 0.7884714007377625,
+      "step": 2540
+    },
+    {
+      "epoch": 1.096655879180151,
+      "grad_norm": 0.46274980902671814,
+      "learning_rate": 0.00019391596293906582,
+      "loss": 0.7663765549659729,
+      "step": 2542
+    },
+    {
+      "epoch": 1.0975188781014025,
+      "grad_norm": 0.431887149810791,
+      "learning_rate": 0.00019389908444362747,
+      "loss": 0.6656131744384766,
+      "step": 2544
+    },
+    {
+      "epoch": 1.0983818770226537,
+      "grad_norm": 0.5138527750968933,
+      "learning_rate": 0.00019388218330484823,
+      "loss": 0.795498788356781,
+      "step": 2546
+    },
+    {
+      "epoch": 1.099244875943905,
+      "grad_norm": 0.4679732024669647,
+      "learning_rate": 0.00019386525952680365,
+      "loss": 0.807344377040863,
+      "step": 2548
+    },
+    {
+      "epoch": 1.1001078748651565,
+      "grad_norm": 0.473088800907135,
+      "learning_rate": 0.0001938483131135749,
+      "loss": 0.6828449368476868,
+      "step": 2550
+    },
+    {
+      "epoch": 1.1009708737864077,
+      "grad_norm": 0.49941009283065796,
+      "learning_rate": 0.00019383134406924856,
+      "loss": 0.8669595122337341,
+      "step": 2552
+    },
+    {
+      "epoch": 1.101833872707659,
+      "grad_norm": 0.47401952743530273,
+      "learning_rate": 0.00019381435239791656,
+      "loss": 0.7382985949516296,
+      "step": 2554
+    },
+    {
+      "epoch": 1.1026968716289105,
+      "grad_norm": 0.47803637385368347,
+      "learning_rate": 0.0001937973381036764,
+      "loss": 0.7240811586380005,
+      "step": 2556
+    },
+    {
+      "epoch": 1.103559870550162,
+      "grad_norm": 0.4534960985183716,
+      "learning_rate": 0.000193780301190631,
+      "loss": 0.736165463924408,
+      "step": 2558
+    },
+    {
+      "epoch": 1.104422869471413,
+      "grad_norm": 0.4594196677207947,
+      "learning_rate": 0.0001937632416628887,
+      "loss": 0.7364692091941833,
+      "step": 2560
+    },
+    {
+      "epoch": 1.1052858683926645,
+      "grad_norm": 0.45354577898979187,
+      "learning_rate": 0.0001937461595245634,
+      "loss": 0.803584635257721,
+      "step": 2562
+    },
+    {
+      "epoch": 1.106148867313916,
+      "grad_norm": 0.47314611077308655,
+      "learning_rate": 0.00019372905477977432,
+      "loss": 0.7224286794662476,
+      "step": 2564
+    },
+    {
+      "epoch": 1.1070118662351671,
+      "grad_norm": 0.4453343451023102,
+      "learning_rate": 0.0001937119274326462,
+      "loss": 0.7446297407150269,
+      "step": 2566
+    },
+    {
+      "epoch": 1.1078748651564185,
+      "grad_norm": 0.5266496539115906,
+      "learning_rate": 0.0001936947774873093,
+      "loss": 0.7666438817977905,
+      "step": 2568
+    },
+    {
+      "epoch": 1.10873786407767,
+      "grad_norm": 0.44142624735832214,
+      "learning_rate": 0.00019367760494789913,
+      "loss": 0.8593260049819946,
+      "step": 2570
+    },
+    {
+      "epoch": 1.1096008629989211,
+      "grad_norm": 0.552436888217926,
+      "learning_rate": 0.00019366040981855682,
+      "loss": 0.7768570184707642,
+      "step": 2572
+    },
+    {
+      "epoch": 1.1104638619201725,
+      "grad_norm": 0.4223164916038513,
+      "learning_rate": 0.0001936431921034289,
+      "loss": 0.7356681823730469,
+      "step": 2574
+    },
+    {
+      "epoch": 1.111326860841424,
+      "grad_norm": 0.5104808211326599,
+      "learning_rate": 0.0001936259518066674,
+      "loss": 0.7693892121315002,
+      "step": 2576
+    },
+    {
+      "epoch": 1.1121898597626754,
+      "grad_norm": 0.40713393688201904,
+      "learning_rate": 0.00019360868893242967,
+      "loss": 0.7651313543319702,
+      "step": 2578
+    },
+    {
+      "epoch": 1.1130528586839266,
+      "grad_norm": 0.4819444417953491,
+      "learning_rate": 0.00019359140348487858,
+      "loss": 0.8427110314369202,
+      "step": 2580
+    },
+    {
+      "epoch": 1.113915857605178,
+      "grad_norm": 0.45872536301612854,
+      "learning_rate": 0.00019357409546818247,
+      "loss": 0.7783478498458862,
+      "step": 2582
+    },
+    {
+      "epoch": 1.1147788565264294,
+      "grad_norm": 0.43954113125801086,
+      "learning_rate": 0.00019355676488651508,
+      "loss": 0.6625193357467651,
+      "step": 2584
+    },
+    {
+      "epoch": 1.1156418554476808,
+      "grad_norm": 0.4524446725845337,
+      "learning_rate": 0.00019353941174405558,
+      "loss": 0.7208001613616943,
+      "step": 2586
+    },
+    {
+      "epoch": 1.116504854368932,
+      "grad_norm": 0.4748269021511078,
+      "learning_rate": 0.0001935220360449886,
+      "loss": 0.7567161917686462,
+      "step": 2588
+    },
+    {
+      "epoch": 1.1173678532901834,
+      "grad_norm": 0.4493826925754547,
+      "learning_rate": 0.00019350463779350423,
+      "loss": 0.7631603479385376,
+      "step": 2590
+    },
+    {
+      "epoch": 1.1182308522114348,
+      "grad_norm": 0.45398685336112976,
+      "learning_rate": 0.00019348721699379798,
+      "loss": 0.7756917476654053,
+      "step": 2592
+    },
+    {
+      "epoch": 1.119093851132686,
+      "grad_norm": 0.4246262311935425,
+      "learning_rate": 0.0001934697736500708,
+      "loss": 0.7516605854034424,
+      "step": 2594
+    },
+    {
+      "epoch": 1.1199568500539374,
+      "grad_norm": 0.44801613688468933,
+      "learning_rate": 0.00019345230776652908,
+      "loss": 0.7058185338973999,
+      "step": 2596
+    },
+    {
+      "epoch": 1.1208198489751888,
+      "grad_norm": 0.4591200649738312,
+      "learning_rate": 0.00019343481934738462,
+      "loss": 0.8071328997612,
+      "step": 2598
+    },
+    {
+      "epoch": 1.12168284789644,
+      "grad_norm": 0.39467594027519226,
+      "learning_rate": 0.0001934173083968547,
+      "loss": 0.6992195844650269,
+      "step": 2600
+    },
+    {
+      "epoch": 1.12168284789644,
+      "eval_loss": 0.8300262093544006,
+      "eval_runtime": 658.9488,
+      "eval_samples_per_second": 3.126,
+      "eval_steps_per_second": 3.126,
+      "step": 2600
+    },
+    {
+      "epoch": 1.1225458468176914,
+      "grad_norm": 0.40905407071113586,
+      "learning_rate": 0.00019339977491916196,
+      "loss": 0.7683232426643372,
+      "step": 2602
+    },
+    {
+      "epoch": 1.1234088457389428,
+      "grad_norm": 0.42742034792900085,
+      "learning_rate": 0.00019338221891853453,
+      "loss": 0.7048685550689697,
+      "step": 2604
+    },
+    {
+      "epoch": 1.1242718446601943,
+      "grad_norm": 0.4435581564903259,
+      "learning_rate": 0.000193364640399206,
+      "loss": 0.7206799983978271,
+      "step": 2606
+    },
+    {
+      "epoch": 1.1251348435814454,
+      "grad_norm": 0.48409897089004517,
+      "learning_rate": 0.00019334703936541535,
+      "loss": 0.8230411410331726,
+      "step": 2608
+    },
+    {
+      "epoch": 1.1259978425026969,
+      "grad_norm": 0.5060800909996033,
+      "learning_rate": 0.00019332941582140693,
+      "loss": 0.7833203077316284,
+      "step": 2610
+    },
+    {
+      "epoch": 1.1268608414239483,
+      "grad_norm": 0.48900339007377625,
+      "learning_rate": 0.00019331176977143062,
+      "loss": 0.7785601615905762,
+      "step": 2612
+    },
+    {
+      "epoch": 1.1277238403451997,
+      "grad_norm": 0.46176961064338684,
+      "learning_rate": 0.0001932941012197417,
+      "loss": 0.800255537033081,
+      "step": 2614
+    },
+    {
+      "epoch": 1.1285868392664509,
+      "grad_norm": 0.4946233332157135,
+      "learning_rate": 0.00019327641017060084,
+      "loss": 0.7647190690040588,
+      "step": 2616
+    },
+    {
+      "epoch": 1.1294498381877023,
+      "grad_norm": 0.4153730571269989,
+      "learning_rate": 0.00019325869662827416,
+      "loss": 0.7271775007247925,
+      "step": 2618
+    },
+    {
+      "epoch": 1.1303128371089537,
+      "grad_norm": 0.46707460284233093,
+      "learning_rate": 0.0001932409605970332,
+      "loss": 0.7926952838897705,
+      "step": 2620
+    },
+    {
+      "epoch": 1.1311758360302049,
+      "grad_norm": 0.4980720579624176,
+      "learning_rate": 0.00019322320208115489,
+      "loss": 0.8106555938720703,
+      "step": 2622
+    },
+    {
+      "epoch": 1.1320388349514563,
+      "grad_norm": 0.4300958514213562,
+      "learning_rate": 0.0001932054210849217,
+      "loss": 0.7208700776100159,
+      "step": 2624
+    },
+    {
+      "epoch": 1.1329018338727077,
+      "grad_norm": 0.4756612479686737,
+      "learning_rate": 0.00019318761761262136,
+      "loss": 0.7212259769439697,
+      "step": 2626
+    },
+    {
+      "epoch": 1.133764832793959,
+      "grad_norm": 0.4502181112766266,
+      "learning_rate": 0.00019316979166854713,
+      "loss": 0.6725794672966003,
+      "step": 2628
+    },
+    {
+      "epoch": 1.1346278317152103,
+      "grad_norm": 0.4845540523529053,
+      "learning_rate": 0.00019315194325699765,
+      "loss": 0.7582959532737732,
+      "step": 2630
+    },
+    {
+      "epoch": 1.1354908306364617,
+      "grad_norm": 0.45892953872680664,
+      "learning_rate": 0.00019313407238227698,
+      "loss": 0.7707560062408447,
+      "step": 2632
+    },
+    {
+      "epoch": 1.1363538295577131,
+      "grad_norm": 0.4707877039909363,
+      "learning_rate": 0.00019311617904869464,
+      "loss": 0.7824680209159851,
+      "step": 2634
+    },
+    {
+      "epoch": 1.1372168284789643,
+      "grad_norm": 0.5212311744689941,
+      "learning_rate": 0.00019309826326056545,
+      "loss": 0.7750257253646851,
+      "step": 2636
+    },
+    {
+      "epoch": 1.1380798274002157,
+      "grad_norm": 0.4952082633972168,
+      "learning_rate": 0.0001930803250222098,
+      "loss": 0.7691953182220459,
+      "step": 2638
+    },
+    {
+      "epoch": 1.1389428263214671,
+      "grad_norm": 0.4428424835205078,
+      "learning_rate": 0.00019306236433795334,
+      "loss": 0.737209141254425,
+      "step": 2640
+    },
+    {
+      "epoch": 1.1398058252427186,
+      "grad_norm": 0.5063129663467407,
+      "learning_rate": 0.00019304438121212728,
+      "loss": 0.7487695813179016,
+      "step": 2642
+    },
+    {
+      "epoch": 1.1406688241639698,
+      "grad_norm": 0.4571828246116638,
+      "learning_rate": 0.00019302637564906814,
+      "loss": 0.7647218704223633,
+      "step": 2644
+    },
+    {
+      "epoch": 1.1415318230852212,
+      "grad_norm": 0.4918457567691803,
+      "learning_rate": 0.00019300834765311785,
+      "loss": 0.8173171877861023,
+      "step": 2646
+    },
+    {
+      "epoch": 1.1423948220064726,
+      "grad_norm": 0.40057408809661865,
+      "learning_rate": 0.0001929902972286238,
+      "loss": 0.6472562551498413,
+      "step": 2648
+    },
+    {
+      "epoch": 1.1432578209277238,
+      "grad_norm": 0.432763934135437,
+      "learning_rate": 0.0001929722243799388,
+      "loss": 0.8462889194488525,
+      "step": 2650
+    },
+    {
+      "epoch": 1.1441208198489752,
+      "grad_norm": 0.36540713906288147,
+      "learning_rate": 0.000192954129111421,
+      "loss": 0.808388352394104,
+      "step": 2652
+    },
+    {
+      "epoch": 1.1449838187702266,
+      "grad_norm": 0.4236038029193878,
+      "learning_rate": 0.00019293601142743403,
+      "loss": 0.7144365906715393,
+      "step": 2654
+    },
+    {
+      "epoch": 1.1458468176914778,
+      "grad_norm": 0.4316163957118988,
+      "learning_rate": 0.00019291787133234682,
+      "loss": 0.693168580532074,
+      "step": 2656
+    },
+    {
+      "epoch": 1.1467098166127292,
+      "grad_norm": 0.43088117241859436,
+      "learning_rate": 0.00019289970883053386,
+      "loss": 0.7981953024864197,
+      "step": 2658
+    },
+    {
+      "epoch": 1.1475728155339806,
+      "grad_norm": 0.4200972318649292,
+      "learning_rate": 0.00019288152392637486,
+      "loss": 0.7342561483383179,
+      "step": 2660
+    },
+    {
+      "epoch": 1.148435814455232,
+      "grad_norm": 0.4461527466773987,
+      "learning_rate": 0.00019286331662425512,
+      "loss": 0.7239733934402466,
+      "step": 2662
+    },
+    {
+      "epoch": 1.1492988133764832,
+      "grad_norm": 0.3945358097553253,
+      "learning_rate": 0.00019284508692856518,
+      "loss": 0.6575030088424683,
+      "step": 2664
+    },
+    {
+      "epoch": 1.1501618122977346,
+      "grad_norm": 0.4653085470199585,
+      "learning_rate": 0.0001928268348437011,
+      "loss": 0.7754159569740295,
+      "step": 2666
+    },
+    {
+      "epoch": 1.151024811218986,
+      "grad_norm": 0.47542640566825867,
+      "learning_rate": 0.00019280856037406422,
+      "loss": 0.683927595615387,
+      "step": 2668
+    },
+    {
+      "epoch": 1.1518878101402374,
+      "grad_norm": 0.4191996455192566,
+      "learning_rate": 0.00019279026352406143,
+      "loss": 0.6907603144645691,
+      "step": 2670
+    },
+    {
+      "epoch": 1.1527508090614886,
+      "grad_norm": 0.4643108546733856,
+      "learning_rate": 0.00019277194429810488,
+      "loss": 0.8362683653831482,
+      "step": 2672
+    },
+    {
+      "epoch": 1.15361380798274,
+      "grad_norm": 0.4213605225086212,
+      "learning_rate": 0.00019275360270061217,
+      "loss": 0.737736701965332,
+      "step": 2674
+    },
+    {
+      "epoch": 1.1544768069039915,
+      "grad_norm": 0.537070095539093,
+      "learning_rate": 0.0001927352387360063,
+      "loss": 0.7617850303649902,
+      "step": 2676
+    },
+    {
+      "epoch": 1.1553398058252426,
+      "grad_norm": 0.47798195481300354,
+      "learning_rate": 0.0001927168524087157,
+      "loss": 0.7252766489982605,
+      "step": 2678
+    },
+    {
+      "epoch": 1.156202804746494,
+      "grad_norm": 0.48654067516326904,
+      "learning_rate": 0.00019269844372317408,
+      "loss": 0.7671495676040649,
+      "step": 2680
+    },
+    {
+      "epoch": 1.1570658036677455,
+      "grad_norm": 0.5374535322189331,
+      "learning_rate": 0.00019268001268382066,
+      "loss": 0.8648670315742493,
+      "step": 2682
+    },
+    {
+      "epoch": 1.1579288025889967,
+      "grad_norm": 0.42167672514915466,
+      "learning_rate": 0.00019266155929509996,
+      "loss": 0.6848083138465881,
+      "step": 2684
+    },
+    {
+      "epoch": 1.158791801510248,
+      "grad_norm": 0.38867753744125366,
+      "learning_rate": 0.00019264308356146197,
+      "loss": 0.6890886425971985,
+      "step": 2686
+    },
+    {
+      "epoch": 1.1596548004314995,
+      "grad_norm": 0.42711013555526733,
+      "learning_rate": 0.000192624585487362,
+      "loss": 0.7399795651435852,
+      "step": 2688
+    },
+    {
+      "epoch": 1.160517799352751,
+      "grad_norm": 0.48802322149276733,
+      "learning_rate": 0.00019260606507726083,
+      "loss": 0.8026465773582458,
+      "step": 2690
+    },
+    {
+      "epoch": 1.161380798274002,
+      "grad_norm": 0.47166478633880615,
+      "learning_rate": 0.00019258752233562452,
+      "loss": 0.7589768171310425,
+      "step": 2692
+    },
+    {
+      "epoch": 1.1622437971952535,
+      "grad_norm": 0.47413256764411926,
+      "learning_rate": 0.00019256895726692459,
+      "loss": 0.7620571851730347,
+      "step": 2694
+    },
+    {
+      "epoch": 1.163106796116505,
+      "grad_norm": 0.5377517342567444,
+      "learning_rate": 0.0001925503698756379,
+      "loss": 0.798933207988739,
+      "step": 2696
+    },
+    {
+      "epoch": 1.1639697950377563,
+      "grad_norm": 0.44990095496177673,
+      "learning_rate": 0.00019253176016624678,
+      "loss": 0.7550637125968933,
+      "step": 2698
+    },
+    {
+      "epoch": 1.1648327939590075,
+      "grad_norm": 0.4633009433746338,
+      "learning_rate": 0.00019251312814323876,
+      "loss": 0.7919567227363586,
+      "step": 2700
+    },
+    {
+      "epoch": 1.1648327939590075,
+      "eval_loss": 0.8251468539237976,
+      "eval_runtime": 667.0436,
+      "eval_samples_per_second": 3.088,
+      "eval_steps_per_second": 3.088,
+      "step": 2700
+    },
+    {
+      "epoch": 1.165695792880259,
+      "grad_norm": 0.4339669942855835,
+      "learning_rate": 0.000192494473811107,
+      "loss": 0.8140546083450317,
+      "step": 2702
+    },
+    {
+      "epoch": 1.1665587918015103,
+      "grad_norm": 0.5794349312782288,
+      "learning_rate": 0.00019247579717434984,
+      "loss": 0.8462281823158264,
+      "step": 2704
+    },
+    {
+      "epoch": 1.1674217907227615,
+      "grad_norm": 0.41820067167282104,
+      "learning_rate": 0.00019245709823747102,
+      "loss": 0.7468760013580322,
+      "step": 2706
+    },
+    {
+      "epoch": 1.168284789644013,
+      "grad_norm": 0.4002464711666107,
+      "learning_rate": 0.0001924383770049798,
+      "loss": 0.694807767868042,
+      "step": 2708
+    },
+    {
+      "epoch": 1.1691477885652644,
+      "grad_norm": 0.47752025723457336,
+      "learning_rate": 0.00019241963348139068,
+      "loss": 0.7512534856796265,
+      "step": 2710
+    },
+    {
+      "epoch": 1.1700107874865155,
+      "grad_norm": 0.45852312445640564,
+      "learning_rate": 0.0001924008676712236,
+      "loss": 0.8069711923599243,
+      "step": 2712
+    },
+    {
+      "epoch": 1.170873786407767,
+      "grad_norm": 0.4336509108543396,
+      "learning_rate": 0.0001923820795790038,
+      "loss": 0.7022751569747925,
+      "step": 2714
+    },
+    {
+      "epoch": 1.1717367853290184,
+      "grad_norm": 0.40044888854026794,
+      "learning_rate": 0.00019236326920926193,
+      "loss": 0.6904252767562866,
+      "step": 2716
+    },
+    {
+      "epoch": 1.1725997842502698,
+      "grad_norm": 0.48451852798461914,
+      "learning_rate": 0.00019234443656653412,
+      "loss": 0.7924585938453674,
+      "step": 2718
+    },
+    {
+      "epoch": 1.173462783171521,
+      "grad_norm": 0.49168315529823303,
+      "learning_rate": 0.0001923255816553617,
+      "loss": 0.7383922338485718,
+      "step": 2720
+    },
+    {
+      "epoch": 1.1743257820927724,
+      "grad_norm": 0.4363260269165039,
+      "learning_rate": 0.00019230670448029148,
+      "loss": 0.7508589029312134,
+      "step": 2722
+    },
+    {
+      "epoch": 1.1751887810140238,
+      "grad_norm": 0.4520082175731659,
+      "learning_rate": 0.0001922878050458756,
+      "loss": 0.7814584970474243,
+      "step": 2724
+    },
+    {
+      "epoch": 1.176051779935275,
+      "grad_norm": 0.4675535559654236,
+      "learning_rate": 0.00019226888335667158,
+      "loss": 0.7011970281600952,
+      "step": 2726
+    },
+    {
+      "epoch": 1.1769147788565264,
+      "grad_norm": 0.47536277770996094,
+      "learning_rate": 0.00019224993941724226,
+      "loss": 0.7414659857749939,
+      "step": 2728
+    },
+    {
+      "epoch": 1.1777777777777778,
+      "grad_norm": 0.5455507040023804,
+      "learning_rate": 0.00019223097323215594,
+      "loss": 0.7949363589286804,
+      "step": 2730
+    },
+    {
+      "epoch": 1.1786407766990292,
+      "grad_norm": 0.4897938370704651,
+      "learning_rate": 0.00019221198480598616,
+      "loss": 0.813949465751648,
+      "step": 2732
+    },
+    {
+      "epoch": 1.1795037756202804,
+      "grad_norm": 0.46766766905784607,
+      "learning_rate": 0.000192192974143312,
+      "loss": 0.7444795966148376,
+      "step": 2734
+    },
+    {
+      "epoch": 1.1803667745415318,
+      "grad_norm": 0.41503575444221497,
+      "learning_rate": 0.00019217394124871768,
+      "loss": 0.7937621474266052,
+      "step": 2736
+    },
+    {
+      "epoch": 1.1812297734627832,
+      "grad_norm": 0.41906169056892395,
+      "learning_rate": 0.00019215488612679295,
+      "loss": 0.7342435717582703,
+      "step": 2738
+    },
+    {
+      "epoch": 1.1820927723840344,
+      "grad_norm": 0.47820931673049927,
+      "learning_rate": 0.00019213580878213292,
+      "loss": 0.7533642053604126,
+      "step": 2740
+    },
+    {
+      "epoch": 1.1829557713052858,
+      "grad_norm": 0.44907891750335693,
+      "learning_rate": 0.00019211670921933792,
+      "loss": 0.799866795539856,
+      "step": 2742
+    },
+    {
+      "epoch": 1.1838187702265373,
+      "grad_norm": 0.48050498962402344,
+      "learning_rate": 0.00019209758744301376,
+      "loss": 0.7468855381011963,
+      "step": 2744
+    },
+    {
+      "epoch": 1.1846817691477884,
+      "grad_norm": 0.4311312437057495,
+      "learning_rate": 0.00019207844345777155,
+      "loss": 0.7423141002655029,
+      "step": 2746
+    },
+    {
+      "epoch": 1.1855447680690399,
+      "grad_norm": 0.439386248588562,
+      "learning_rate": 0.0001920592772682278,
+      "loss": 0.7046169638633728,
+      "step": 2748
+    },
+    {
+      "epoch": 1.1864077669902913,
+      "grad_norm": 0.4230091869831085,
+      "learning_rate": 0.00019204008887900435,
+      "loss": 0.7284982204437256,
+      "step": 2750
+    },
+    {
+      "epoch": 1.1872707659115427,
+      "grad_norm": 0.4583308696746826,
+      "learning_rate": 0.0001920208782947284,
+      "loss": 0.7297943234443665,
+      "step": 2752
+    },
+    {
+      "epoch": 1.1881337648327939,
+      "grad_norm": 0.44526317715644836,
+      "learning_rate": 0.00019200164552003247,
+      "loss": 0.7170902490615845,
+      "step": 2754
+    },
+    {
+      "epoch": 1.1889967637540453,
+      "grad_norm": 0.46664097905158997,
+      "learning_rate": 0.00019198239055955444,
+      "loss": 0.7746089696884155,
+      "step": 2756
+    },
+    {
+      "epoch": 1.1898597626752967,
+      "grad_norm": 0.4023241102695465,
+      "learning_rate": 0.0001919631134179376,
+      "loss": 0.7381687760353088,
+      "step": 2758
+    },
+    {
+      "epoch": 1.190722761596548,
+      "grad_norm": 0.5126422047615051,
+      "learning_rate": 0.00019194381409983055,
+      "loss": 0.7951313853263855,
+      "step": 2760
+    },
+    {
+      "epoch": 1.1915857605177993,
+      "grad_norm": 0.4056018590927124,
+      "learning_rate": 0.0001919244926098872,
+      "loss": 0.692834198474884,
+      "step": 2762
+    },
+    {
+      "epoch": 1.1924487594390507,
+      "grad_norm": 0.49225106835365295,
+      "learning_rate": 0.00019190514895276687,
+      "loss": 0.7494171857833862,
+      "step": 2764
+    },
+    {
+      "epoch": 1.1933117583603021,
+      "grad_norm": 0.47823601961135864,
+      "learning_rate": 0.00019188578313313417,
+      "loss": 0.8541221022605896,
+      "step": 2766
+    },
+    {
+      "epoch": 1.1941747572815533,
+      "grad_norm": 0.461773544549942,
+      "learning_rate": 0.0001918663951556591,
+      "loss": 0.8017639517784119,
+      "step": 2768
+    },
+    {
+      "epoch": 1.1950377562028047,
+      "grad_norm": 0.48888009786605835,
+      "learning_rate": 0.00019184698502501695,
+      "loss": 0.7509341835975647,
+      "step": 2770
+    },
+    {
+      "epoch": 1.1959007551240561,
+      "grad_norm": 0.4140535295009613,
+      "learning_rate": 0.0001918275527458884,
+      "loss": 0.7123914361000061,
+      "step": 2772
+    },
+    {
+      "epoch": 1.1967637540453073,
+      "grad_norm": 0.4918449819087982,
+      "learning_rate": 0.00019180809832295952,
+      "loss": 0.73713219165802,
+      "step": 2774
+    },
+    {
+      "epoch": 1.1976267529665587,
+      "grad_norm": 0.48218831419944763,
+      "learning_rate": 0.00019178862176092159,
+      "loss": 0.708644688129425,
+      "step": 2776
+    },
+    {
+      "epoch": 1.1984897518878102,
+      "grad_norm": 0.45588797330856323,
+      "learning_rate": 0.0001917691230644713,
+      "loss": 0.7277385592460632,
+      "step": 2778
+    },
+    {
+      "epoch": 1.1993527508090616,
+      "grad_norm": 0.3959250748157501,
+      "learning_rate": 0.00019174960223831064,
+      "loss": 0.7501665949821472,
+      "step": 2780
+    },
+    {
+      "epoch": 1.2002157497303128,
+      "grad_norm": 0.6228574514389038,
+      "learning_rate": 0.00019173005928714703,
+      "loss": 0.8842931389808655,
+      "step": 2782
+    },
+    {
+      "epoch": 1.2010787486515642,
+      "grad_norm": 0.4346935749053955,
+      "learning_rate": 0.00019171049421569318,
+      "loss": 0.7008639574050903,
+      "step": 2784
+    },
+    {
+      "epoch": 1.2019417475728156,
+      "grad_norm": 0.691254198551178,
+      "learning_rate": 0.00019169090702866705,
+      "loss": 0.7203702330589294,
+      "step": 2786
+    },
+    {
+      "epoch": 1.202804746494067,
+      "grad_norm": 0.4219740331172943,
+      "learning_rate": 0.00019167129773079203,
+      "loss": 0.7170791029930115,
+      "step": 2788
+    },
+    {
+      "epoch": 1.2036677454153182,
+      "grad_norm": 0.4639855921268463,
+      "learning_rate": 0.00019165166632679686,
+      "loss": 0.7895086407661438,
+      "step": 2790
+    },
+    {
+      "epoch": 1.2045307443365696,
+      "grad_norm": 0.44938549399375916,
+      "learning_rate": 0.00019163201282141546,
+      "loss": 0.7323113679885864,
+      "step": 2792
+    },
+    {
+      "epoch": 1.205393743257821,
+      "grad_norm": 0.43633413314819336,
+      "learning_rate": 0.00019161233721938728,
+      "loss": 0.7486892342567444,
+      "step": 2794
+    },
+    {
+      "epoch": 1.2062567421790722,
+      "grad_norm": 0.42983385920524597,
+      "learning_rate": 0.00019159263952545698,
+      "loss": 0.777079701423645,
+      "step": 2796
+    },
+    {
+      "epoch": 1.2071197411003236,
+      "grad_norm": 0.4630664587020874,
+      "learning_rate": 0.00019157291974437456,
+      "loss": 0.800602912902832,
+      "step": 2798
+    },
+    {
+      "epoch": 1.207982740021575,
+      "grad_norm": 0.43607378005981445,
+      "learning_rate": 0.00019155317788089536,
+      "loss": 0.6763592958450317,
+      "step": 2800
+    },
+    {
+      "epoch": 1.207982740021575,
+      "eval_loss": 0.8219058513641357,
+      "eval_runtime": 661.5144,
+      "eval_samples_per_second": 3.114,
+      "eval_steps_per_second": 3.114,
+      "step": 2800
+    },
+    {
+      "epoch": 1.2088457389428262,
+      "grad_norm": 0.4910019338130951,
+      "learning_rate": 0.00019153341393978002,
+      "loss": 0.7569329738616943,
+      "step": 2802
+    },
+    {
+      "epoch": 1.2097087378640776,
+      "grad_norm": 0.4993135631084442,
+      "learning_rate": 0.00019151362792579457,
+      "loss": 0.734387218952179,
+      "step": 2804
+    },
+    {
+      "epoch": 1.210571736785329,
+      "grad_norm": 0.48742055892944336,
+      "learning_rate": 0.00019149381984371027,
+      "loss": 0.719099223613739,
+      "step": 2806
+    },
+    {
+      "epoch": 1.2114347357065804,
+      "grad_norm": 0.4083765149116516,
+      "learning_rate": 0.00019147398969830378,
+      "loss": 0.8490580320358276,
+      "step": 2808
+    },
+    {
+      "epoch": 1.2122977346278316,
+      "grad_norm": 0.4316021502017975,
+      "learning_rate": 0.00019145413749435702,
+      "loss": 0.7604904770851135,
+      "step": 2810
+    },
+    {
+      "epoch": 1.213160733549083,
+      "grad_norm": 0.4294895529747009,
+      "learning_rate": 0.0001914342632366573,
+      "loss": 0.7739580869674683,
+      "step": 2812
+    },
+    {
+      "epoch": 1.2140237324703345,
+      "grad_norm": 0.4773736000061035,
+      "learning_rate": 0.00019141436692999718,
+      "loss": 0.7625397443771362,
+      "step": 2814
+    },
+    {
+      "epoch": 1.2148867313915859,
+      "grad_norm": 0.46148404479026794,
+      "learning_rate": 0.00019139444857917457,
+      "loss": 0.7224686741828918,
+      "step": 2816
+    },
+    {
+      "epoch": 1.215749730312837,
+      "grad_norm": 0.436300128698349,
+      "learning_rate": 0.0001913745081889927,
+      "loss": 0.7708583474159241,
+      "step": 2818
+    },
+    {
+      "epoch": 1.2166127292340885,
+      "grad_norm": 0.4959073066711426,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.8550406098365784,
+      "step": 2820
+    },
+    {
+      "epoch": 1.2174757281553399,
+      "grad_norm": 0.4672411382198334,
+      "learning_rate": 0.00019133456130979062,
+      "loss": 0.781597912311554,
+      "step": 2822
+    },
+    {
+      "epoch": 1.218338727076591,
+      "grad_norm": 0.5249256491661072,
+      "learning_rate": 0.0001913145548304034,
+      "loss": 0.860835075378418,
+      "step": 2824
+    },
+    {
+      "epoch": 1.2192017259978425,
+      "grad_norm": 0.5132579207420349,
+      "learning_rate": 0.00019129452633092294,
+      "loss": 0.715717613697052,
+      "step": 2826
+    },
+    {
+      "epoch": 1.220064724919094,
+      "grad_norm": 0.4291874170303345,
+      "learning_rate": 0.00019127447581617903,
+      "loss": 0.727998673915863,
+      "step": 2828
+    },
+    {
+      "epoch": 1.220927723840345,
+      "grad_norm": 0.3698529005050659,
+      "learning_rate": 0.00019125440329100673,
+      "loss": 0.7164589762687683,
+      "step": 2830
+    },
+    {
+      "epoch": 1.2217907227615965,
+      "grad_norm": 0.5034273266792297,
+      "learning_rate": 0.00019123430876024646,
+      "loss": 0.8113957643508911,
+      "step": 2832
+    },
+    {
+      "epoch": 1.222653721682848,
+      "grad_norm": 0.4612481892108917,
+      "learning_rate": 0.0001912141922287439,
+      "loss": 0.7350133061408997,
+      "step": 2834
+    },
+    {
+      "epoch": 1.2235167206040993,
+      "grad_norm": 0.4433611035346985,
+      "learning_rate": 0.00019119405370135012,
+      "loss": 0.8156216144561768,
+      "step": 2836
+    },
+    {
+      "epoch": 1.2243797195253505,
+      "grad_norm": 0.4700625240802765,
+      "learning_rate": 0.00019117389318292136,
+      "loss": 0.7824334502220154,
+      "step": 2838
+    },
+    {
+      "epoch": 1.225242718446602,
+      "grad_norm": 0.4854332208633423,
+      "learning_rate": 0.00019115371067831928,
+      "loss": 0.8136369585990906,
+      "step": 2840
+    },
+    {
+      "epoch": 1.2261057173678533,
+      "grad_norm": 0.4403935372829437,
+      "learning_rate": 0.00019113350619241078,
+      "loss": 0.7042210102081299,
+      "step": 2842
+    },
+    {
+      "epoch": 1.2269687162891048,
+      "grad_norm": 0.4311469793319702,
+      "learning_rate": 0.00019111327973006813,
+      "loss": 0.7598573565483093,
+      "step": 2844
+    },
+    {
+      "epoch": 1.227831715210356,
+      "grad_norm": 0.5551521182060242,
+      "learning_rate": 0.0001910930312961688,
+      "loss": 0.8001043796539307,
+      "step": 2846
+    },
+    {
+      "epoch": 1.2286947141316074,
+      "grad_norm": 0.44149601459503174,
+      "learning_rate": 0.0001910727608955956,
+      "loss": 0.6874746084213257,
+      "step": 2848
+    },
+    {
+      "epoch": 1.2295577130528588,
+      "grad_norm": 0.44726014137268066,
+      "learning_rate": 0.00019105246853323672,
+      "loss": 0.7484437823295593,
+      "step": 2850
+    },
+    {
+      "epoch": 1.23042071197411,
+      "grad_norm": 0.4710492193698883,
+      "learning_rate": 0.00019103215421398546,
+      "loss": 0.7512558102607727,
+      "step": 2852
+    },
+    {
+      "epoch": 1.2312837108953614,
+      "grad_norm": 0.4304901957511902,
+      "learning_rate": 0.0001910118179427406,
+      "loss": 0.7161203622817993,
+      "step": 2854
+    },
+    {
+      "epoch": 1.2321467098166128,
+      "grad_norm": 0.4651104509830475,
+      "learning_rate": 0.00019099145972440614,
+      "loss": 0.722236156463623,
+      "step": 2856
+    },
+    {
+      "epoch": 1.233009708737864,
+      "grad_norm": 0.5231161117553711,
+      "learning_rate": 0.00019097107956389135,
+      "loss": 0.8200751543045044,
+      "step": 2858
+    },
+    {
+      "epoch": 1.2338727076591154,
+      "grad_norm": 0.45574283599853516,
+      "learning_rate": 0.00019095067746611083,
+      "loss": 0.7529966235160828,
+      "step": 2860
+    },
+    {
+      "epoch": 1.2347357065803668,
+      "grad_norm": 0.4451949894428253,
+      "learning_rate": 0.00019093025343598448,
+      "loss": 0.7574380040168762,
+      "step": 2862
+    },
+    {
+      "epoch": 1.2355987055016182,
+      "grad_norm": 0.4557603597640991,
+      "learning_rate": 0.00019090980747843737,
+      "loss": 0.8461237549781799,
+      "step": 2864
+    },
+    {
+      "epoch": 1.2364617044228694,
+      "grad_norm": 0.41115859150886536,
+      "learning_rate": 0.00019088933959840004,
+      "loss": 0.7910104990005493,
+      "step": 2866
+    },
+    {
+      "epoch": 1.2373247033441208,
+      "grad_norm": 0.5087599158287048,
+      "learning_rate": 0.0001908688498008082,
+      "loss": 0.8318688273429871,
+      "step": 2868
+    },
+    {
+      "epoch": 1.2381877022653722,
+      "grad_norm": 0.4243653118610382,
+      "learning_rate": 0.00019084833809060285,
+      "loss": 0.713392436504364,
+      "step": 2870
+    },
+    {
+      "epoch": 1.2390507011866236,
+      "grad_norm": 0.3965010344982147,
+      "learning_rate": 0.00019082780447273034,
+      "loss": 0.7697778344154358,
+      "step": 2872
+    },
+    {
+      "epoch": 1.2399137001078748,
+      "grad_norm": 0.4493406116962433,
+      "learning_rate": 0.00019080724895214222,
+      "loss": 0.7437527179718018,
+      "step": 2874
+    },
+    {
+      "epoch": 1.2407766990291262,
+      "grad_norm": 0.5189685821533203,
+      "learning_rate": 0.00019078667153379537,
+      "loss": 0.858138918876648,
+      "step": 2876
+    },
+    {
+      "epoch": 1.2416396979503777,
+      "grad_norm": 0.39455580711364746,
+      "learning_rate": 0.00019076607222265197,
+      "loss": 0.7235360145568848,
+      "step": 2878
+    },
+    {
+      "epoch": 1.2425026968716288,
+      "grad_norm": 0.524804413318634,
+      "learning_rate": 0.00019074545102367943,
+      "loss": 0.7995675206184387,
+      "step": 2880
+    },
+    {
+      "epoch": 1.2433656957928803,
+      "grad_norm": 0.4873242974281311,
+      "learning_rate": 0.00019072480794185044,
+      "loss": 0.8404105305671692,
+      "step": 2882
+    },
+    {
+      "epoch": 1.2442286947141317,
+      "grad_norm": 0.4591716527938843,
+      "learning_rate": 0.000190704142982143,
+      "loss": 0.7540513277053833,
+      "step": 2884
+    },
+    {
+      "epoch": 1.2450916936353829,
+      "grad_norm": 0.48403632640838623,
+      "learning_rate": 0.0001906834561495404,
+      "loss": 0.7566621899604797,
+      "step": 2886
+    },
+    {
+      "epoch": 1.2459546925566343,
+      "grad_norm": 0.4854280948638916,
+      "learning_rate": 0.00019066274744903113,
+      "loss": 0.7141375541687012,
+      "step": 2888
+    },
+    {
+      "epoch": 1.2468176914778857,
+      "grad_norm": 0.45851001143455505,
+      "learning_rate": 0.00019064201688560902,
+      "loss": 0.7798115611076355,
+      "step": 2890
+    },
+    {
+      "epoch": 1.247680690399137,
+      "grad_norm": 0.4584810435771942,
+      "learning_rate": 0.00019062126446427318,
+      "loss": 0.7212263941764832,
+      "step": 2892
+    },
+    {
+      "epoch": 1.2485436893203883,
+      "grad_norm": 0.5282798409461975,
+      "learning_rate": 0.00019060049019002792,
+      "loss": 0.8268418312072754,
+      "step": 2894
+    },
+    {
+      "epoch": 1.2494066882416397,
+      "grad_norm": 0.40996623039245605,
+      "learning_rate": 0.00019057969406788289,
+      "loss": 0.7512726783752441,
+      "step": 2896
+    },
+    {
+      "epoch": 1.250269687162891,
+      "grad_norm": 0.39559319615364075,
+      "learning_rate": 0.00019055887610285296,
+      "loss": 0.6680556535720825,
+      "step": 2898
+    },
+    {
+      "epoch": 1.2511326860841425,
+      "grad_norm": 0.42002710700035095,
+      "learning_rate": 0.0001905380362999583,
+      "loss": 0.7307850122451782,
+      "step": 2900
+    },
+    {
+      "epoch": 1.2511326860841425,
+      "eval_loss": 0.8155517578125,
+      "eval_runtime": 650.62,
+      "eval_samples_per_second": 3.166,
+      "eval_steps_per_second": 3.166,
+      "step": 2900
+    },
+    {
+      "epoch": 1.2519956850053937,
+      "grad_norm": 0.3914625644683838,
+      "learning_rate": 0.00019051717466422435,
+      "loss": 0.7316054701805115,
+      "step": 2902
+    },
+    {
+      "epoch": 1.2528586839266451,
+      "grad_norm": 0.48939383029937744,
+      "learning_rate": 0.00019049629120068175,
+      "loss": 0.8977305889129639,
+      "step": 2904
+    },
+    {
+      "epoch": 1.2537216828478965,
+      "grad_norm": 0.4892135262489319,
+      "learning_rate": 0.0001904753859143665,
+      "loss": 0.7962324619293213,
+      "step": 2906
+    },
+    {
+      "epoch": 1.2545846817691477,
+      "grad_norm": 0.5323660969734192,
+      "learning_rate": 0.00019045445881031982,
+      "loss": 0.791375458240509,
+      "step": 2908
+    },
+    {
+      "epoch": 1.2554476806903991,
+      "grad_norm": 0.44778114557266235,
+      "learning_rate": 0.00019043350989358818,
+      "loss": 0.7218163013458252,
+      "step": 2910
+    },
+    {
+      "epoch": 1.2563106796116505,
+      "grad_norm": 0.4763379991054535,
+      "learning_rate": 0.00019041253916922326,
+      "loss": 0.7380548119544983,
+      "step": 2912
+    },
+    {
+      "epoch": 1.2571736785329017,
+      "grad_norm": 0.4979628026485443,
+      "learning_rate": 0.00019039154664228213,
+      "loss": 0.7586072683334351,
+      "step": 2914
+    },
+    {
+      "epoch": 1.2580366774541532,
+      "grad_norm": 0.46175920963287354,
+      "learning_rate": 0.000190370532317827,
+      "loss": 0.763477623462677,
+      "step": 2916
+    },
+    {
+      "epoch": 1.2588996763754046,
+      "grad_norm": 0.43192169070243835,
+      "learning_rate": 0.0001903494962009254,
+      "loss": 0.7479409575462341,
+      "step": 2918
+    },
+    {
+      "epoch": 1.2597626752966558,
+      "grad_norm": 0.42883434891700745,
+      "learning_rate": 0.0001903284382966501,
+      "loss": 0.7355074882507324,
+      "step": 2920
+    },
+    {
+      "epoch": 1.2606256742179072,
+      "grad_norm": 0.47708168625831604,
+      "learning_rate": 0.00019030735861007912,
+      "loss": 0.7762811183929443,
+      "step": 2922
+    },
+    {
+      "epoch": 1.2614886731391586,
+      "grad_norm": 0.4478151500225067,
+      "learning_rate": 0.0001902862571462957,
+      "loss": 0.6964467763900757,
+      "step": 2924
+    },
+    {
+      "epoch": 1.26235167206041,
+      "grad_norm": 0.4531081020832062,
+      "learning_rate": 0.00019026513391038837,
+      "loss": 0.7414857745170593,
+      "step": 2926
+    },
+    {
+      "epoch": 1.2632146709816614,
+      "grad_norm": 0.4623842239379883,
+      "learning_rate": 0.00019024398890745092,
+      "loss": 0.7639371156692505,
+      "step": 2928
+    },
+    {
+      "epoch": 1.2640776699029126,
+      "grad_norm": 0.4362739622592926,
+      "learning_rate": 0.00019022282214258238,
+      "loss": 0.800457239151001,
+      "step": 2930
+    },
+    {
+      "epoch": 1.264940668824164,
+      "grad_norm": 0.42854052782058716,
+      "learning_rate": 0.000190201633620887,
+      "loss": 0.7960386872291565,
+      "step": 2932
+    },
+    {
+      "epoch": 1.2658036677454154,
+      "grad_norm": 0.47477999329566956,
+      "learning_rate": 0.0001901804233474743,
+      "loss": 0.7544003129005432,
+      "step": 2934
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 0.4584832191467285,
+      "learning_rate": 0.00019015919132745905,
+      "loss": 0.7819825410842896,
+      "step": 2936
+    },
+    {
+      "epoch": 1.267529665587918,
+      "grad_norm": 0.5465012192726135,
+      "learning_rate": 0.00019013793756596123,
+      "loss": 0.7719182372093201,
+      "step": 2938
+    },
+    {
+      "epoch": 1.2683926645091694,
+      "grad_norm": 0.42024123668670654,
+      "learning_rate": 0.00019011666206810614,
+      "loss": 0.7442063093185425,
+      "step": 2940
+    },
+    {
+      "epoch": 1.2692556634304206,
+      "grad_norm": 0.4374787211418152,
+      "learning_rate": 0.00019009536483902424,
+      "loss": 0.6696176528930664,
+      "step": 2942
+    },
+    {
+      "epoch": 1.270118662351672,
+      "grad_norm": 0.4136449992656708,
+      "learning_rate": 0.00019007404588385125,
+      "loss": 0.7048487663269043,
+      "step": 2944
+    },
+    {
+      "epoch": 1.2709816612729234,
+      "grad_norm": 0.4463474452495575,
+      "learning_rate": 0.00019005270520772817,
+      "loss": 0.7587971687316895,
+      "step": 2946
+    },
+    {
+      "epoch": 1.2718446601941746,
+      "grad_norm": 0.43167322874069214,
+      "learning_rate": 0.00019003134281580115,
+      "loss": 0.7741286754608154,
+      "step": 2948
+    },
+    {
+      "epoch": 1.272707659115426,
+      "grad_norm": 0.5189676284790039,
+      "learning_rate": 0.0001900099587132217,
+      "loss": 0.7572245597839355,
+      "step": 2950
+    },
+    {
+      "epoch": 1.2735706580366775,
+      "grad_norm": 0.4256224036216736,
+      "learning_rate": 0.00018998855290514646,
+      "loss": 0.7743186354637146,
+      "step": 2952
+    },
+    {
+      "epoch": 1.2744336569579289,
+      "grad_norm": 0.4304806888103485,
+      "learning_rate": 0.00018996712539673735,
+      "loss": 0.7287778854370117,
+      "step": 2954
+    },
+    {
+      "epoch": 1.2752966558791803,
+      "grad_norm": 0.489372193813324,
+      "learning_rate": 0.00018994567619316156,
+      "loss": 0.7930773496627808,
+      "step": 2956
+    },
+    {
+      "epoch": 1.2761596548004315,
+      "grad_norm": 0.3855830430984497,
+      "learning_rate": 0.0001899242052995914,
+      "loss": 0.7283111214637756,
+      "step": 2958
+    },
+    {
+      "epoch": 1.2770226537216829,
+      "grad_norm": 0.46708667278289795,
+      "learning_rate": 0.00018990271272120452,
+      "loss": 0.721849262714386,
+      "step": 2960
+    },
+    {
+      "epoch": 1.2778856526429343,
+      "grad_norm": 0.3663526773452759,
+      "learning_rate": 0.00018988119846318377,
+      "loss": 0.6678964495658875,
+      "step": 2962
+    },
+    {
+      "epoch": 1.2787486515641855,
+      "grad_norm": 0.5074638724327087,
+      "learning_rate": 0.00018985966253071718,
+      "loss": 0.8021678924560547,
+      "step": 2964
+    },
+    {
+      "epoch": 1.279611650485437,
+      "grad_norm": 0.4902975857257843,
+      "learning_rate": 0.00018983810492899806,
+      "loss": 0.8313384056091309,
+      "step": 2966
+    },
+    {
+      "epoch": 1.2804746494066883,
+      "grad_norm": 0.5023161768913269,
+      "learning_rate": 0.00018981652566322493,
+      "loss": 0.8330302834510803,
+      "step": 2968
+    },
+    {
+      "epoch": 1.2813376483279395,
+      "grad_norm": 0.48227089643478394,
+      "learning_rate": 0.00018979492473860155,
+      "loss": 0.8806158304214478,
+      "step": 2970
+    },
+    {
+      "epoch": 1.282200647249191,
+      "grad_norm": 0.40143465995788574,
+      "learning_rate": 0.00018977330216033683,
+      "loss": 0.6835185885429382,
+      "step": 2972
+    },
+    {
+      "epoch": 1.2830636461704423,
+      "grad_norm": 0.4368304908275604,
+      "learning_rate": 0.00018975165793364503,
+      "loss": 0.7207706570625305,
+      "step": 2974
+    },
+    {
+      "epoch": 1.2839266450916935,
+      "grad_norm": 0.39989250898361206,
+      "learning_rate": 0.0001897299920637455,
+      "loss": 0.6909692883491516,
+      "step": 2976
+    },
+    {
+      "epoch": 1.284789644012945,
+      "grad_norm": 0.4826473593711853,
+      "learning_rate": 0.0001897083045558629,
+      "loss": 0.838360071182251,
+      "step": 2978
+    },
+    {
+      "epoch": 1.2856526429341963,
+      "grad_norm": 0.4860877990722656,
+      "learning_rate": 0.00018968659541522705,
+      "loss": 0.7693317532539368,
+      "step": 2980
+    },
+    {
+      "epoch": 1.2865156418554478,
+      "grad_norm": 0.4361511170864105,
+      "learning_rate": 0.00018966486464707305,
+      "loss": 0.7662015557289124,
+      "step": 2982
+    },
+    {
+      "epoch": 1.287378640776699,
+      "grad_norm": 0.45333993434906006,
+      "learning_rate": 0.00018964311225664113,
+      "loss": 0.752369225025177,
+      "step": 2984
+    },
+    {
+      "epoch": 1.2882416396979504,
+      "grad_norm": 0.4825304448604584,
+      "learning_rate": 0.0001896213382491768,
+      "loss": 0.7524476051330566,
+      "step": 2986
+    },
+    {
+      "epoch": 1.2891046386192018,
+      "grad_norm": 0.5303854942321777,
+      "learning_rate": 0.00018959954262993077,
+      "loss": 0.8564903736114502,
+      "step": 2988
+    },
+    {
+      "epoch": 1.2899676375404532,
+      "grad_norm": 0.43856459856033325,
+      "learning_rate": 0.00018957772540415896,
+      "loss": 0.7839077711105347,
+      "step": 2990
+    },
+    {
+      "epoch": 1.2908306364617044,
+      "grad_norm": 0.438041627407074,
+      "learning_rate": 0.00018955588657712248,
+      "loss": 0.7580918669700623,
+      "step": 2992
+    },
+    {
+      "epoch": 1.2916936353829558,
+      "grad_norm": 0.4497842490673065,
+      "learning_rate": 0.00018953402615408768,
+      "loss": 0.7014032602310181,
+      "step": 2994
+    },
+    {
+      "epoch": 1.2925566343042072,
+      "grad_norm": 0.5659869313240051,
+      "learning_rate": 0.0001895121441403261,
+      "loss": 0.8220269083976746,
+      "step": 2996
+    },
+    {
+      "epoch": 1.2934196332254584,
+      "grad_norm": 0.4850102961063385,
+      "learning_rate": 0.00018949024054111448,
+      "loss": 0.6880294680595398,
+      "step": 2998
+    },
+    {
+      "epoch": 1.2942826321467098,
+      "grad_norm": 0.4253626763820648,
+      "learning_rate": 0.00018946831536173476,
+      "loss": 0.7443753480911255,
+      "step": 3000
+    },
+    {
+      "epoch": 1.2942826321467098,
+      "eval_loss": 0.8127614259719849,
+      "eval_runtime": 650.4396,
+      "eval_samples_per_second": 3.167,
+      "eval_steps_per_second": 3.167,
+      "step": 3000
+    },
+    {
+      "epoch": 1.2951456310679612,
+      "grad_norm": 0.3746396005153656,
+      "learning_rate": 0.00018944636860747412,
+      "loss": 0.6588667631149292,
+      "step": 3002
+    },
+    {
+      "epoch": 1.2960086299892124,
+      "grad_norm": 0.4039393663406372,
+      "learning_rate": 0.00018942440028362493,
+      "loss": 0.7135416865348816,
+      "step": 3004
+    },
+    {
+      "epoch": 1.2968716289104638,
+      "grad_norm": 0.457533061504364,
+      "learning_rate": 0.00018940241039548474,
+      "loss": 0.7895556688308716,
+      "step": 3006
+    },
+    {
+      "epoch": 1.2977346278317152,
+      "grad_norm": 0.4989747107028961,
+      "learning_rate": 0.0001893803989483563,
+      "loss": 0.7863595485687256,
+      "step": 3008
+    },
+    {
+      "epoch": 1.2985976267529666,
+      "grad_norm": 0.470002681016922,
+      "learning_rate": 0.00018935836594754756,
+      "loss": 0.795306921005249,
+      "step": 3010
+    },
+    {
+      "epoch": 1.2994606256742178,
+      "grad_norm": 0.43668872117996216,
+      "learning_rate": 0.00018933631139837176,
+      "loss": 0.7313401699066162,
+      "step": 3012
+    },
+    {
+      "epoch": 1.3003236245954692,
+      "grad_norm": 0.4843446910381317,
+      "learning_rate": 0.00018931423530614715,
+      "loss": 0.7331582903862,
+      "step": 3014
+    },
+    {
+      "epoch": 1.3011866235167207,
+      "grad_norm": 0.4233832359313965,
+      "learning_rate": 0.00018929213767619735,
+      "loss": 0.7046043872833252,
+      "step": 3016
+    },
+    {
+      "epoch": 1.302049622437972,
+      "grad_norm": 0.6326188445091248,
+      "learning_rate": 0.00018927001851385108,
+      "loss": 0.8217260241508484,
+      "step": 3018
+    },
+    {
+      "epoch": 1.3029126213592233,
+      "grad_norm": 0.409653902053833,
+      "learning_rate": 0.00018924787782444223,
+      "loss": 0.6477662324905396,
+      "step": 3020
+    },
+    {
+      "epoch": 1.3037756202804747,
+      "grad_norm": 0.3869863748550415,
+      "learning_rate": 0.00018922571561331004,
+      "loss": 0.6408766508102417,
+      "step": 3022
+    },
+    {
+      "epoch": 1.304638619201726,
+      "grad_norm": 0.4400722086429596,
+      "learning_rate": 0.00018920353188579874,
+      "loss": 0.7396708726882935,
+      "step": 3024
+    },
+    {
+      "epoch": 1.3055016181229773,
+      "grad_norm": 0.39694252610206604,
+      "learning_rate": 0.00018918132664725784,
+      "loss": 0.6409308314323425,
+      "step": 3026
+    },
+    {
+      "epoch": 1.3063646170442287,
+      "grad_norm": 0.49937903881073,
+      "learning_rate": 0.00018915909990304205,
+      "loss": 0.7825533151626587,
+      "step": 3028
+    },
+    {
+      "epoch": 1.30722761596548,
+      "grad_norm": 0.43940550088882446,
+      "learning_rate": 0.0001891368516585113,
+      "loss": 0.7182250022888184,
+      "step": 3030
+    },
+    {
+      "epoch": 1.3080906148867313,
+      "grad_norm": 0.43905356526374817,
+      "learning_rate": 0.00018911458191903053,
+      "loss": 0.7602632641792297,
+      "step": 3032
+    },
+    {
+      "epoch": 1.3089536138079827,
+      "grad_norm": 0.4172695279121399,
+      "learning_rate": 0.0001890922906899701,
+      "loss": 0.7307555675506592,
+      "step": 3034
+    },
+    {
+      "epoch": 1.309816612729234,
+      "grad_norm": 0.49642932415008545,
+      "learning_rate": 0.00018906997797670544,
+      "loss": 0.782136857509613,
+      "step": 3036
+    },
+    {
+      "epoch": 1.3106796116504853,
+      "grad_norm": 0.49893322587013245,
+      "learning_rate": 0.00018904764378461705,
+      "loss": 0.787925124168396,
+      "step": 3038
+    },
+    {
+      "epoch": 1.3115426105717367,
+      "grad_norm": 0.42691150307655334,
+      "learning_rate": 0.00018902528811909081,
+      "loss": 0.6731302738189697,
+      "step": 3040
+    },
+    {
+      "epoch": 1.3124056094929881,
+      "grad_norm": 0.4961661696434021,
+      "learning_rate": 0.00018900291098551767,
+      "loss": 0.7211409211158752,
+      "step": 3042
+    },
+    {
+      "epoch": 1.3132686084142395,
+      "grad_norm": 0.45150521397590637,
+      "learning_rate": 0.00018898051238929378,
+      "loss": 0.7317034602165222,
+      "step": 3044
+    },
+    {
+      "epoch": 1.314131607335491,
+      "grad_norm": 0.5012714266777039,
+      "learning_rate": 0.00018895809233582047,
+      "loss": 0.7838613390922546,
+      "step": 3046
+    },
+    {
+      "epoch": 1.3149946062567421,
+      "grad_norm": 0.5605086088180542,
+      "learning_rate": 0.0001889356508305042,
+      "loss": 0.8206616640090942,
+      "step": 3048
+    },
+    {
+      "epoch": 1.3158576051779936,
+      "grad_norm": 0.4337491989135742,
+      "learning_rate": 0.00018891318787875666,
+      "loss": 0.7460386753082275,
+      "step": 3050
+    },
+    {
+      "epoch": 1.316720604099245,
+      "grad_norm": 0.4392184913158417,
+      "learning_rate": 0.00018889070348599468,
+      "loss": 0.7973155379295349,
+      "step": 3052
+    },
+    {
+      "epoch": 1.3175836030204962,
+      "grad_norm": 0.4550181031227112,
+      "learning_rate": 0.00018886819765764028,
+      "loss": 0.6951689720153809,
+      "step": 3054
+    },
+    {
+      "epoch": 1.3184466019417476,
+      "grad_norm": 0.4058854877948761,
+      "learning_rate": 0.00018884567039912062,
+      "loss": 0.7353226542472839,
+      "step": 3056
+    },
+    {
+      "epoch": 1.319309600862999,
+      "grad_norm": 0.4157969057559967,
+      "learning_rate": 0.00018882312171586806,
+      "loss": 0.7758772969245911,
+      "step": 3058
+    },
+    {
+      "epoch": 1.3201725997842502,
+      "grad_norm": 0.44122767448425293,
+      "learning_rate": 0.00018880055161332016,
+      "loss": 0.6808486580848694,
+      "step": 3060
+    },
+    {
+      "epoch": 1.3210355987055016,
+      "grad_norm": 0.4674125015735626,
+      "learning_rate": 0.0001887779600969195,
+      "loss": 0.7781010270118713,
+      "step": 3062
+    },
+    {
+      "epoch": 1.321898597626753,
+      "grad_norm": 0.4414712190628052,
+      "learning_rate": 0.000188755347172114,
+      "loss": 0.7759971022605896,
+      "step": 3064
+    },
+    {
+      "epoch": 1.3227615965480042,
+      "grad_norm": 0.4804554283618927,
+      "learning_rate": 0.00018873271284435664,
+      "loss": 0.7430314421653748,
+      "step": 3066
+    },
+    {
+      "epoch": 1.3236245954692556,
+      "grad_norm": 0.4891934096813202,
+      "learning_rate": 0.00018871005711910562,
+      "loss": 0.6974785923957825,
+      "step": 3068
+    },
+    {
+      "epoch": 1.324487594390507,
+      "grad_norm": 0.4103528559207916,
+      "learning_rate": 0.0001886873800018242,
+      "loss": 0.6832907199859619,
+      "step": 3070
+    },
+    {
+      "epoch": 1.3253505933117584,
+      "grad_norm": 0.45092564821243286,
+      "learning_rate": 0.00018866468149798089,
+      "loss": 0.7700413465499878,
+      "step": 3072
+    },
+    {
+      "epoch": 1.3262135922330098,
+      "grad_norm": 0.47934943437576294,
+      "learning_rate": 0.00018864196161304933,
+      "loss": 0.7441738843917847,
+      "step": 3074
+    },
+    {
+      "epoch": 1.327076591154261,
+      "grad_norm": 0.756400465965271,
+      "learning_rate": 0.00018861922035250835,
+      "loss": 0.7195783853530884,
+      "step": 3076
+    },
+    {
+      "epoch": 1.3279395900755124,
+      "grad_norm": 0.47899410128593445,
+      "learning_rate": 0.00018859645772184187,
+      "loss": 0.6692811846733093,
+      "step": 3078
+    },
+    {
+      "epoch": 1.3288025889967638,
+      "grad_norm": 0.43265631794929504,
+      "learning_rate": 0.000188573673726539,
+      "loss": 0.6882596611976624,
+      "step": 3080
+    },
+    {
+      "epoch": 1.329665587918015,
+      "grad_norm": 0.4955349266529083,
+      "learning_rate": 0.00018855086837209401,
+      "loss": 0.9300010204315186,
+      "step": 3082
+    },
+    {
+      "epoch": 1.3305285868392664,
+      "grad_norm": 0.4638696312904358,
+      "learning_rate": 0.0001885280416640063,
+      "loss": 0.8391118049621582,
+      "step": 3084
+    },
+    {
+      "epoch": 1.3313915857605179,
+      "grad_norm": 0.4086083471775055,
+      "learning_rate": 0.00018850519360778044,
+      "loss": 0.7136397957801819,
+      "step": 3086
+    },
+    {
+      "epoch": 1.332254584681769,
+      "grad_norm": 0.4455646574497223,
+      "learning_rate": 0.0001884823242089261,
+      "loss": 0.6886621117591858,
+      "step": 3088
+    },
+    {
+      "epoch": 1.3331175836030205,
+      "grad_norm": 0.43355703353881836,
+      "learning_rate": 0.0001884594334729582,
+      "loss": 0.7261496782302856,
+      "step": 3090
+    },
+    {
+      "epoch": 1.3339805825242719,
+      "grad_norm": 0.5322562456130981,
+      "learning_rate": 0.00018843652140539664,
+      "loss": 0.8529927134513855,
+      "step": 3092
+    },
+    {
+      "epoch": 1.334843581445523,
+      "grad_norm": 0.4504645764827728,
+      "learning_rate": 0.00018841358801176668,
+      "loss": 0.8131585121154785,
+      "step": 3094
+    },
+    {
+      "epoch": 1.3357065803667745,
+      "grad_norm": 0.44101089239120483,
+      "learning_rate": 0.0001883906332975985,
+      "loss": 0.800965428352356,
+      "step": 3096
+    },
+    {
+      "epoch": 1.3365695792880259,
+      "grad_norm": 0.46587181091308594,
+      "learning_rate": 0.00018836765726842759,
+      "loss": 0.711025059223175,
+      "step": 3098
+    },
+    {
+      "epoch": 1.3374325782092773,
+      "grad_norm": 0.4656004011631012,
+      "learning_rate": 0.00018834465992979447,
+      "loss": 0.7824587225914001,
+      "step": 3100
+    },
+    {
+      "epoch": 1.3374325782092773,
+      "eval_loss": 0.8109187483787537,
+      "eval_runtime": 662.5843,
+      "eval_samples_per_second": 3.109,
+      "eval_steps_per_second": 3.109,
+      "step": 3100
+    },
+    {
+      "epoch": 1.3382955771305287,
+      "grad_norm": 0.4942762851715088,
+      "learning_rate": 0.00018832164128724488,
+      "loss": 0.7444300651550293,
+      "step": 3102
+    },
+    {
+      "epoch": 1.33915857605178,
+      "grad_norm": 0.5280060172080994,
+      "learning_rate": 0.00018829860134632963,
+      "loss": 0.8248856067657471,
+      "step": 3104
+    },
+    {
+      "epoch": 1.3400215749730313,
+      "grad_norm": 0.4131146967411041,
+      "learning_rate": 0.00018827554011260474,
+      "loss": 0.7753435373306274,
+      "step": 3106
+    },
+    {
+      "epoch": 1.3408845738942827,
+      "grad_norm": 0.38460803031921387,
+      "learning_rate": 0.0001882524575916313,
+      "loss": 0.7512242197990417,
+      "step": 3108
+    },
+    {
+      "epoch": 1.341747572815534,
+      "grad_norm": 0.4719627797603607,
+      "learning_rate": 0.00018822935378897554,
+      "loss": 0.7760549783706665,
+      "step": 3110
+    },
+    {
+      "epoch": 1.3426105717367853,
+      "grad_norm": 0.47593894600868225,
+      "learning_rate": 0.00018820622871020887,
+      "loss": 0.7802333831787109,
+      "step": 3112
+    },
+    {
+      "epoch": 1.3434735706580367,
+      "grad_norm": 0.46464505791664124,
+      "learning_rate": 0.00018818308236090778,
+      "loss": 0.7037042379379272,
+      "step": 3114
+    },
+    {
+      "epoch": 1.344336569579288,
+      "grad_norm": 0.4358392059803009,
+      "learning_rate": 0.0001881599147466539,
+      "loss": 0.7476377487182617,
+      "step": 3116
+    },
+    {
+      "epoch": 1.3451995685005393,
+      "grad_norm": 0.5236833095550537,
+      "learning_rate": 0.000188136725873034,
+      "loss": 0.8273758292198181,
+      "step": 3118
+    },
+    {
+      "epoch": 1.3460625674217908,
+      "grad_norm": 0.5240068435668945,
+      "learning_rate": 0.00018811351574564,
+      "loss": 0.7407519817352295,
+      "step": 3120
+    },
+    {
+      "epoch": 1.346925566343042,
+      "grad_norm": 0.44454488158226013,
+      "learning_rate": 0.00018809028437006888,
+      "loss": 0.708732008934021,
+      "step": 3122
+    },
+    {
+      "epoch": 1.3477885652642934,
+      "grad_norm": 0.43769216537475586,
+      "learning_rate": 0.00018806703175192283,
+      "loss": 0.7243810296058655,
+      "step": 3124
+    },
+    {
+      "epoch": 1.3486515641855448,
+      "grad_norm": 0.4477781355381012,
+      "learning_rate": 0.00018804375789680905,
+      "loss": 0.7603667974472046,
+      "step": 3126
+    },
+    {
+      "epoch": 1.3495145631067962,
+      "grad_norm": 0.4425322115421295,
+      "learning_rate": 0.00018802046281033997,
+      "loss": 0.7545933127403259,
+      "step": 3128
+    },
+    {
+      "epoch": 1.3503775620280476,
+      "grad_norm": 0.458310604095459,
+      "learning_rate": 0.00018799714649813304,
+      "loss": 0.7925270795822144,
+      "step": 3130
+    },
+    {
+      "epoch": 1.3512405609492988,
+      "grad_norm": 0.4328557848930359,
+      "learning_rate": 0.00018797380896581095,
+      "loss": 0.7392709851264954,
+      "step": 3132
+    },
+    {
+      "epoch": 1.3521035598705502,
+      "grad_norm": 0.4476810693740845,
+      "learning_rate": 0.00018795045021900144,
+      "loss": 0.7340229153633118,
+      "step": 3134
+    },
+    {
+      "epoch": 1.3529665587918016,
+      "grad_norm": 0.3931216895580292,
+      "learning_rate": 0.00018792707026333734,
+      "loss": 0.6678531765937805,
+      "step": 3136
+    },
+    {
+      "epoch": 1.3538295577130528,
+      "grad_norm": 0.4768988788127899,
+      "learning_rate": 0.0001879036691044566,
+      "loss": 0.8059957027435303,
+      "step": 3138
+    },
+    {
+      "epoch": 1.3546925566343042,
+      "grad_norm": 0.4464127719402313,
+      "learning_rate": 0.00018788024674800234,
+      "loss": 0.7618262767791748,
+      "step": 3140
+    },
+    {
+      "epoch": 1.3555555555555556,
+      "grad_norm": 0.4115859866142273,
+      "learning_rate": 0.00018785680319962272,
+      "loss": 0.7277366518974304,
+      "step": 3142
+    },
+    {
+      "epoch": 1.3564185544768068,
+      "grad_norm": 0.40479758381843567,
+      "learning_rate": 0.0001878333384649711,
+      "loss": 0.7587567567825317,
+      "step": 3144
+    },
+    {
+      "epoch": 1.3572815533980582,
+      "grad_norm": 0.5233479738235474,
+      "learning_rate": 0.00018780985254970584,
+      "loss": 0.7896765470504761,
+      "step": 3146
+    },
+    {
+      "epoch": 1.3581445523193096,
+      "grad_norm": 0.5604038834571838,
+      "learning_rate": 0.00018778634545949053,
+      "loss": 0.8300224542617798,
+      "step": 3148
+    },
+    {
+      "epoch": 1.3590075512405608,
+      "grad_norm": 0.48418891429901123,
+      "learning_rate": 0.00018776281719999372,
+      "loss": 0.8129078149795532,
+      "step": 3150
+    },
+    {
+      "epoch": 1.3598705501618122,
+      "grad_norm": 0.4338721036911011,
+      "learning_rate": 0.00018773926777688918,
+      "loss": 0.72742760181427,
+      "step": 3152
+    },
+    {
+      "epoch": 1.3607335490830637,
+      "grad_norm": 0.48870885372161865,
+      "learning_rate": 0.00018771569719585576,
+      "loss": 0.8129846453666687,
+      "step": 3154
+    },
+    {
+      "epoch": 1.361596548004315,
+      "grad_norm": 0.5070347785949707,
+      "learning_rate": 0.00018769210546257736,
+      "loss": 0.7692790031433105,
+      "step": 3156
+    },
+    {
+      "epoch": 1.3624595469255665,
+      "grad_norm": 0.4609982669353485,
+      "learning_rate": 0.0001876684925827431,
+      "loss": 0.6610854864120483,
+      "step": 3158
+    },
+    {
+      "epoch": 1.3633225458468177,
+      "grad_norm": 0.4481177031993866,
+      "learning_rate": 0.000187644858562047,
+      "loss": 0.7724031805992126,
+      "step": 3160
+    },
+    {
+      "epoch": 1.364185544768069,
+      "grad_norm": 0.38047513365745544,
+      "learning_rate": 0.0001876212034061884,
+      "loss": 0.7166935801506042,
+      "step": 3162
+    },
+    {
+      "epoch": 1.3650485436893205,
+      "grad_norm": 0.4010603427886963,
+      "learning_rate": 0.00018759752712087157,
+      "loss": 0.7535263299942017,
+      "step": 3164
+    },
+    {
+      "epoch": 1.3659115426105717,
+      "grad_norm": 0.411430299282074,
+      "learning_rate": 0.00018757382971180598,
+      "loss": 0.7471357583999634,
+      "step": 3166
+    },
+    {
+      "epoch": 1.366774541531823,
+      "grad_norm": 0.36775025725364685,
+      "learning_rate": 0.00018755011118470617,
+      "loss": 0.6910786032676697,
+      "step": 3168
+    },
+    {
+      "epoch": 1.3676375404530745,
+      "grad_norm": 0.5100153684616089,
+      "learning_rate": 0.0001875263715452917,
+      "loss": 0.7566528916358948,
+      "step": 3170
+    },
+    {
+      "epoch": 1.3685005393743257,
+      "grad_norm": 0.43466782569885254,
+      "learning_rate": 0.00018750261079928727,
+      "loss": 0.722017765045166,
+      "step": 3172
+    },
+    {
+      "epoch": 1.369363538295577,
+      "grad_norm": 0.4221585988998413,
+      "learning_rate": 0.00018747882895242275,
+      "loss": 0.7369917035102844,
+      "step": 3174
+    },
+    {
+      "epoch": 1.3702265372168285,
+      "grad_norm": 0.4663652777671814,
+      "learning_rate": 0.00018745502601043298,
+      "loss": 0.7522714138031006,
+      "step": 3176
+    },
+    {
+      "epoch": 1.3710895361380797,
+      "grad_norm": 0.4493909478187561,
+      "learning_rate": 0.0001874312019790579,
+      "loss": 0.7403551340103149,
+      "step": 3178
+    },
+    {
+      "epoch": 1.3719525350593311,
+      "grad_norm": 0.4245595932006836,
+      "learning_rate": 0.00018740735686404266,
+      "loss": 0.6998772025108337,
+      "step": 3180
+    },
+    {
+      "epoch": 1.3728155339805825,
+      "grad_norm": 0.4703865051269531,
+      "learning_rate": 0.00018738349067113735,
+      "loss": 0.6735976934432983,
+      "step": 3182
+    },
+    {
+      "epoch": 1.373678532901834,
+      "grad_norm": 0.5369067788124084,
+      "learning_rate": 0.00018735960340609715,
+      "loss": 0.764581561088562,
+      "step": 3184
+    },
+    {
+      "epoch": 1.3745415318230851,
+      "grad_norm": 0.4964922368526459,
+      "learning_rate": 0.00018733569507468242,
+      "loss": 0.7491477131843567,
+      "step": 3186
+    },
+    {
+      "epoch": 1.3754045307443366,
+      "grad_norm": 0.4167616665363312,
+      "learning_rate": 0.00018731176568265854,
+      "loss": 0.687139093875885,
+      "step": 3188
+    },
+    {
+      "epoch": 1.376267529665588,
+      "grad_norm": 0.4885561764240265,
+      "learning_rate": 0.00018728781523579598,
+      "loss": 0.76422518491745,
+      "step": 3190
+    },
+    {
+      "epoch": 1.3771305285868394,
+      "grad_norm": 0.45865342020988464,
+      "learning_rate": 0.00018726384373987025,
+      "loss": 0.7054057121276855,
+      "step": 3192
+    },
+    {
+      "epoch": 1.3779935275080906,
+      "grad_norm": 0.4557322561740875,
+      "learning_rate": 0.000187239851200662,
+      "loss": 0.7476370334625244,
+      "step": 3194
+    },
+    {
+      "epoch": 1.378856526429342,
+      "grad_norm": 0.4359823763370514,
+      "learning_rate": 0.00018721583762395692,
+      "loss": 0.7450100183486938,
+      "step": 3196
+    },
+    {
+      "epoch": 1.3797195253505934,
+      "grad_norm": 0.45140165090560913,
+      "learning_rate": 0.00018719180301554576,
+      "loss": 0.6332225799560547,
+      "step": 3198
+    },
+    {
+      "epoch": 1.3805825242718446,
+      "grad_norm": 0.4051663875579834,
+      "learning_rate": 0.00018716774738122436,
+      "loss": 0.6999903917312622,
+      "step": 3200
+    },
+    {
+      "epoch": 1.3805825242718446,
+      "eval_loss": 0.8053163290023804,
+      "eval_runtime": 668.3288,
+      "eval_samples_per_second": 3.082,
+      "eval_steps_per_second": 3.082,
+      "step": 3200
+    },
+    {
+      "epoch": 1.381445523193096,
+      "grad_norm": 0.43624332547187805,
+      "learning_rate": 0.00018714367072679365,
+      "loss": 0.675305962562561,
+      "step": 3202
+    },
+    {
+      "epoch": 1.3823085221143474,
+      "grad_norm": 0.5163410902023315,
+      "learning_rate": 0.00018711957305805955,
+      "loss": 0.8098652958869934,
+      "step": 3204
+    },
+    {
+      "epoch": 1.3831715210355986,
+      "grad_norm": 0.5261862277984619,
+      "learning_rate": 0.00018709545438083317,
+      "loss": 0.7265567779541016,
+      "step": 3206
+    },
+    {
+      "epoch": 1.38403451995685,
+      "grad_norm": 0.5289353728294373,
+      "learning_rate": 0.0001870713147009306,
+      "loss": 0.8171496987342834,
+      "step": 3208
+    },
+    {
+      "epoch": 1.3848975188781014,
+      "grad_norm": 0.45589691400527954,
+      "learning_rate": 0.000187047154024173,
+      "loss": 0.800773024559021,
+      "step": 3210
+    },
+    {
+      "epoch": 1.3857605177993528,
+      "grad_norm": 0.4709073603153229,
+      "learning_rate": 0.00018702297235638664,
+      "loss": 0.7034035921096802,
+      "step": 3212
+    },
+    {
+      "epoch": 1.386623516720604,
+      "grad_norm": 0.41431429982185364,
+      "learning_rate": 0.00018699876970340278,
+      "loss": 0.6707210540771484,
+      "step": 3214
+    },
+    {
+      "epoch": 1.3874865156418554,
+      "grad_norm": 0.4663850963115692,
+      "learning_rate": 0.0001869745460710578,
+      "loss": 0.7554471492767334,
+      "step": 3216
+    },
+    {
+      "epoch": 1.3883495145631068,
+      "grad_norm": 0.3720403015613556,
+      "learning_rate": 0.00018695030146519313,
+      "loss": 0.6852688193321228,
+      "step": 3218
+    },
+    {
+      "epoch": 1.3892125134843583,
+      "grad_norm": 0.46755164861679077,
+      "learning_rate": 0.00018692603589165523,
+      "loss": 0.7974506616592407,
+      "step": 3220
+    },
+    {
+      "epoch": 1.3900755124056094,
+      "grad_norm": 0.4087965786457062,
+      "learning_rate": 0.00018690174935629563,
+      "loss": 0.6643959283828735,
+      "step": 3222
+    },
+    {
+      "epoch": 1.3909385113268609,
+      "grad_norm": 0.43572601675987244,
+      "learning_rate": 0.00018687744186497092,
+      "loss": 0.6455117464065552,
+      "step": 3224
+    },
+    {
+      "epoch": 1.3918015102481123,
+      "grad_norm": 0.4832928776741028,
+      "learning_rate": 0.00018685311342354276,
+      "loss": 0.7152265310287476,
+      "step": 3226
+    },
+    {
+      "epoch": 1.3926645091693635,
+      "grad_norm": 0.44429874420166016,
+      "learning_rate": 0.00018682876403787783,
+      "loss": 0.714832067489624,
+      "step": 3228
+    },
+    {
+      "epoch": 1.3935275080906149,
+      "grad_norm": 0.4570554494857788,
+      "learning_rate": 0.0001868043937138479,
+      "loss": 0.7785174250602722,
+      "step": 3230
+    },
+    {
+      "epoch": 1.3943905070118663,
+      "grad_norm": 0.4618188738822937,
+      "learning_rate": 0.00018678000245732972,
+      "loss": 0.7226384878158569,
+      "step": 3232
+    },
+    {
+      "epoch": 1.3952535059331175,
+      "grad_norm": 0.5473061203956604,
+      "learning_rate": 0.00018675559027420515,
+      "loss": 0.741666316986084,
+      "step": 3234
+    },
+    {
+      "epoch": 1.396116504854369,
+      "grad_norm": 0.45633625984191895,
+      "learning_rate": 0.0001867311571703611,
+      "loss": 0.7774195671081543,
+      "step": 3236
+    },
+    {
+      "epoch": 1.3969795037756203,
+      "grad_norm": 0.4549288749694824,
+      "learning_rate": 0.00018670670315168946,
+      "loss": 0.7062699794769287,
+      "step": 3238
+    },
+    {
+      "epoch": 1.3978425026968715,
+      "grad_norm": 0.4530162513256073,
+      "learning_rate": 0.00018668222822408725,
+      "loss": 0.7901433110237122,
+      "step": 3240
+    },
+    {
+      "epoch": 1.398705501618123,
+      "grad_norm": 0.4526861608028412,
+      "learning_rate": 0.00018665773239345647,
+      "loss": 0.7321763038635254,
+      "step": 3242
+    },
+    {
+      "epoch": 1.3995685005393743,
+      "grad_norm": 0.471683531999588,
+      "learning_rate": 0.00018663321566570417,
+      "loss": 0.780885636806488,
+      "step": 3244
+    },
+    {
+      "epoch": 1.4004314994606257,
+      "grad_norm": 0.4421135187149048,
+      "learning_rate": 0.00018660867804674248,
+      "loss": 0.7124532461166382,
+      "step": 3246
+    },
+    {
+      "epoch": 1.4012944983818771,
+      "grad_norm": 0.45071855187416077,
+      "learning_rate": 0.00018658411954248849,
+      "loss": 0.7868198156356812,
+      "step": 3248
+    },
+    {
+      "epoch": 1.4021574973031283,
+      "grad_norm": 0.45456045866012573,
+      "learning_rate": 0.0001865595401588644,
+      "loss": 0.7364398837089539,
+      "step": 3250
+    },
+    {
+      "epoch": 1.4030204962243797,
+      "grad_norm": 0.4487321972846985,
+      "learning_rate": 0.0001865349399017974,
+      "loss": 0.7381253838539124,
+      "step": 3252
+    },
+    {
+      "epoch": 1.4038834951456312,
+      "grad_norm": 0.433517724275589,
+      "learning_rate": 0.00018651031877721976,
+      "loss": 0.6974755525588989,
+      "step": 3254
+    },
+    {
+      "epoch": 1.4047464940668823,
+      "grad_norm": 0.45759329199790955,
+      "learning_rate": 0.00018648567679106873,
+      "loss": 0.7638785243034363,
+      "step": 3256
+    },
+    {
+      "epoch": 1.4056094929881338,
+      "grad_norm": 0.4451565742492676,
+      "learning_rate": 0.00018646101394928662,
+      "loss": 0.7301747798919678,
+      "step": 3258
+    },
+    {
+      "epoch": 1.4064724919093852,
+      "grad_norm": 0.5451349020004272,
+      "learning_rate": 0.0001864363302578208,
+      "loss": 0.770787239074707,
+      "step": 3260
+    },
+    {
+      "epoch": 1.4073354908306364,
+      "grad_norm": 0.47335579991340637,
+      "learning_rate": 0.00018641162572262355,
+      "loss": 0.7637011408805847,
+      "step": 3262
+    },
+    {
+      "epoch": 1.4081984897518878,
+      "grad_norm": 0.480887234210968,
+      "learning_rate": 0.0001863869003496523,
+      "loss": 0.7140913009643555,
+      "step": 3264
+    },
+    {
+      "epoch": 1.4090614886731392,
+      "grad_norm": 0.4122021496295929,
+      "learning_rate": 0.0001863621541448695,
+      "loss": 0.6538959741592407,
+      "step": 3266
+    },
+    {
+      "epoch": 1.4099244875943904,
+      "grad_norm": 0.4456968605518341,
+      "learning_rate": 0.00018633738711424253,
+      "loss": 0.7153927087783813,
+      "step": 3268
+    },
+    {
+      "epoch": 1.4107874865156418,
+      "grad_norm": 0.4152887761592865,
+      "learning_rate": 0.00018631259926374388,
+      "loss": 0.7140036821365356,
+      "step": 3270
+    },
+    {
+      "epoch": 1.4116504854368932,
+      "grad_norm": 0.47110119462013245,
+      "learning_rate": 0.00018628779059935103,
+      "loss": 0.7193810939788818,
+      "step": 3272
+    },
+    {
+      "epoch": 1.4125134843581446,
+      "grad_norm": 0.39739692211151123,
+      "learning_rate": 0.0001862629611270464,
+      "loss": 0.7133702039718628,
+      "step": 3274
+    },
+    {
+      "epoch": 1.413376483279396,
+      "grad_norm": 0.4808974862098694,
+      "learning_rate": 0.00018623811085281765,
+      "loss": 0.811927855014801,
+      "step": 3276
+    },
+    {
+      "epoch": 1.4142394822006472,
+      "grad_norm": 0.4607976973056793,
+      "learning_rate": 0.00018621323978265718,
+      "loss": 0.8125779032707214,
+      "step": 3278
+    },
+    {
+      "epoch": 1.4151024811218986,
+      "grad_norm": 0.41523823142051697,
+      "learning_rate": 0.00018618834792256261,
+      "loss": 0.7065606117248535,
+      "step": 3280
+    },
+    {
+      "epoch": 1.41596548004315,
+      "grad_norm": 0.46665191650390625,
+      "learning_rate": 0.00018616343527853645,
+      "loss": 0.7346477508544922,
+      "step": 3282
+    },
+    {
+      "epoch": 1.4168284789644012,
+      "grad_norm": 0.4744371473789215,
+      "learning_rate": 0.00018613850185658634,
+      "loss": 0.7590131759643555,
+      "step": 3284
+    },
+    {
+      "epoch": 1.4176914778856526,
+      "grad_norm": 0.4905717074871063,
+      "learning_rate": 0.0001861135476627248,
+      "loss": 0.786243200302124,
+      "step": 3286
+    },
+    {
+      "epoch": 1.418554476806904,
+      "grad_norm": 0.45114004611968994,
+      "learning_rate": 0.00018608857270296944,
+      "loss": 0.6855072379112244,
+      "step": 3288
+    },
+    {
+      "epoch": 1.4194174757281552,
+      "grad_norm": 0.5547319054603577,
+      "learning_rate": 0.00018606357698334284,
+      "loss": 0.8294073343276978,
+      "step": 3290
+    },
+    {
+      "epoch": 1.4202804746494067,
+      "grad_norm": 0.4100660979747772,
+      "learning_rate": 0.00018603856050987267,
+      "loss": 0.6352306604385376,
+      "step": 3292
+    },
+    {
+      "epoch": 1.421143473570658,
+      "grad_norm": 0.47723907232284546,
+      "learning_rate": 0.00018601352328859148,
+      "loss": 0.7822797298431396,
+      "step": 3294
+    },
+    {
+      "epoch": 1.4220064724919093,
+      "grad_norm": 0.45811668038368225,
+      "learning_rate": 0.00018598846532553691,
+      "loss": 0.7675215601921082,
+      "step": 3296
+    },
+    {
+      "epoch": 1.4228694714131607,
+      "grad_norm": 0.4794461131095886,
+      "learning_rate": 0.00018596338662675154,
+      "loss": 0.7994555234909058,
+      "step": 3298
+    },
+    {
+      "epoch": 1.423732470334412,
+      "grad_norm": 0.458723783493042,
+      "learning_rate": 0.00018593828719828303,
+      "loss": 0.7676554918289185,
+      "step": 3300
+    },
+    {
+      "epoch": 1.423732470334412,
+      "eval_loss": 0.8030428886413574,
+      "eval_runtime": 658.5495,
+      "eval_samples_per_second": 3.128,
+      "eval_steps_per_second": 3.128,
+      "step": 3300
+    },
+    {
+      "epoch": 1.4245954692556635,
+      "grad_norm": 0.4599555432796478,
+      "learning_rate": 0.00018591316704618397,
+      "loss": 0.7642499804496765,
+      "step": 3302
+    },
+    {
+      "epoch": 1.425458468176915,
+      "grad_norm": 0.5012795925140381,
+      "learning_rate": 0.000185888026176512,
+      "loss": 0.7753090262413025,
+      "step": 3304
+    },
+    {
+      "epoch": 1.426321467098166,
+      "grad_norm": 0.4497458040714264,
+      "learning_rate": 0.00018586286459532967,
+      "loss": 0.7226543426513672,
+      "step": 3306
+    },
+    {
+      "epoch": 1.4271844660194175,
+      "grad_norm": 0.47314873337745667,
+      "learning_rate": 0.0001858376823087046,
+      "loss": 0.752973735332489,
+      "step": 3308
+    },
+    {
+      "epoch": 1.428047464940669,
+      "grad_norm": 0.45765072107315063,
+      "learning_rate": 0.00018581247932270944,
+      "loss": 0.7653468251228333,
+      "step": 3310
+    },
+    {
+      "epoch": 1.42891046386192,
+      "grad_norm": 0.4725930392742157,
+      "learning_rate": 0.0001857872556434217,
+      "loss": 0.8080248832702637,
+      "step": 3312
+    },
+    {
+      "epoch": 1.4297734627831715,
+      "grad_norm": 0.4430061876773834,
+      "learning_rate": 0.00018576201127692402,
+      "loss": 0.8083968162536621,
+      "step": 3314
+    },
+    {
+      "epoch": 1.430636461704423,
+      "grad_norm": 0.4197101294994354,
+      "learning_rate": 0.00018573674622930392,
+      "loss": 0.7861490249633789,
+      "step": 3316
+    },
+    {
+      "epoch": 1.4314994606256741,
+      "grad_norm": 0.4047538936138153,
+      "learning_rate": 0.00018571146050665397,
+      "loss": 0.8125455379486084,
+      "step": 3318
+    },
+    {
+      "epoch": 1.4323624595469255,
+      "grad_norm": 0.5689038634300232,
+      "learning_rate": 0.00018568615411507174,
+      "loss": 0.779180645942688,
+      "step": 3320
+    },
+    {
+      "epoch": 1.433225458468177,
+      "grad_norm": 0.47798338532447815,
+      "learning_rate": 0.00018566082706065969,
+      "loss": 0.7555606961250305,
+      "step": 3322
+    },
+    {
+      "epoch": 1.4340884573894281,
+      "grad_norm": 0.4296347200870514,
+      "learning_rate": 0.00018563547934952537,
+      "loss": 0.6761099696159363,
+      "step": 3324
+    },
+    {
+      "epoch": 1.4349514563106796,
+      "grad_norm": 0.4605977237224579,
+      "learning_rate": 0.00018561011098778126,
+      "loss": 0.7465946078300476,
+      "step": 3326
+    },
+    {
+      "epoch": 1.435814455231931,
+      "grad_norm": 0.48226889967918396,
+      "learning_rate": 0.00018558472198154478,
+      "loss": 0.7459924817085266,
+      "step": 3328
+    },
+    {
+      "epoch": 1.4366774541531824,
+      "grad_norm": 0.4655393362045288,
+      "learning_rate": 0.00018555931233693845,
+      "loss": 0.6451191306114197,
+      "step": 3330
+    },
+    {
+      "epoch": 1.4375404530744338,
+      "grad_norm": 0.4614768922328949,
+      "learning_rate": 0.00018553388206008961,
+      "loss": 0.764894962310791,
+      "step": 3332
+    },
+    {
+      "epoch": 1.438403451995685,
+      "grad_norm": 0.47503674030303955,
+      "learning_rate": 0.00018550843115713072,
+      "loss": 0.7709850072860718,
+      "step": 3334
+    },
+    {
+      "epoch": 1.4392664509169364,
+      "grad_norm": 0.5408021807670593,
+      "learning_rate": 0.00018548295963419914,
+      "loss": 0.8470542430877686,
+      "step": 3336
+    },
+    {
+      "epoch": 1.4401294498381878,
+      "grad_norm": 0.44747427105903625,
+      "learning_rate": 0.0001854574674974372,
+      "loss": 0.770861804485321,
+      "step": 3338
+    },
+    {
+      "epoch": 1.440992448759439,
+      "grad_norm": 0.3823722004890442,
+      "learning_rate": 0.00018543195475299222,
+      "loss": 0.6909842491149902,
+      "step": 3340
+    },
+    {
+      "epoch": 1.4418554476806904,
+      "grad_norm": 0.42207640409469604,
+      "learning_rate": 0.0001854064214070165,
+      "loss": 0.7684979438781738,
+      "step": 3342
+    },
+    {
+      "epoch": 1.4427184466019418,
+      "grad_norm": 0.4514349400997162,
+      "learning_rate": 0.00018538086746566724,
+      "loss": 0.754643440246582,
+      "step": 3344
+    },
+    {
+      "epoch": 1.443581445523193,
+      "grad_norm": 0.4289906620979309,
+      "learning_rate": 0.0001853552929351067,
+      "loss": 0.7302715182304382,
+      "step": 3346
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 0.4458511173725128,
+      "learning_rate": 0.00018532969782150205,
+      "loss": 0.7611445188522339,
+      "step": 3348
+    },
+    {
+      "epoch": 1.4453074433656958,
+      "grad_norm": 0.4370715022087097,
+      "learning_rate": 0.00018530408213102546,
+      "loss": 0.7713651061058044,
+      "step": 3350
+    },
+    {
+      "epoch": 1.446170442286947,
+      "grad_norm": 0.40230461955070496,
+      "learning_rate": 0.000185278445869854,
+      "loss": 0.6728963851928711,
+      "step": 3352
+    },
+    {
+      "epoch": 1.4470334412081984,
+      "grad_norm": 0.43601900339126587,
+      "learning_rate": 0.00018525278904416975,
+      "loss": 0.7662684321403503,
+      "step": 3354
+    },
+    {
+      "epoch": 1.4478964401294498,
+      "grad_norm": 0.45813488960266113,
+      "learning_rate": 0.00018522711166015974,
+      "loss": 0.8269308805465698,
+      "step": 3356
+    },
+    {
+      "epoch": 1.4487594390507013,
+      "grad_norm": 0.48386695981025696,
+      "learning_rate": 0.00018520141372401595,
+      "loss": 0.8171968460083008,
+      "step": 3358
+    },
+    {
+      "epoch": 1.4496224379719527,
+      "grad_norm": 0.41737180948257446,
+      "learning_rate": 0.00018517569524193535,
+      "loss": 0.8057414889335632,
+      "step": 3360
+    },
+    {
+      "epoch": 1.4504854368932039,
+      "grad_norm": 0.41048938035964966,
+      "learning_rate": 0.0001851499562201198,
+      "loss": 0.7350438833236694,
+      "step": 3362
+    },
+    {
+      "epoch": 1.4513484358144553,
+      "grad_norm": 0.49414724111557007,
+      "learning_rate": 0.0001851241966647762,
+      "loss": 0.7771334052085876,
+      "step": 3364
+    },
+    {
+      "epoch": 1.4522114347357067,
+      "grad_norm": 0.48357486724853516,
+      "learning_rate": 0.00018509841658211632,
+      "loss": 0.8041897416114807,
+      "step": 3366
+    },
+    {
+      "epoch": 1.4530744336569579,
+      "grad_norm": 0.44553041458129883,
+      "learning_rate": 0.00018507261597835686,
+      "loss": 0.7079073786735535,
+      "step": 3368
+    },
+    {
+      "epoch": 1.4539374325782093,
+      "grad_norm": 0.4198709726333618,
+      "learning_rate": 0.0001850467948597196,
+      "loss": 0.7564307451248169,
+      "step": 3370
+    },
+    {
+      "epoch": 1.4548004314994607,
+      "grad_norm": 0.4005102217197418,
+      "learning_rate": 0.00018502095323243113,
+      "loss": 0.6955130696296692,
+      "step": 3372
+    },
+    {
+      "epoch": 1.455663430420712,
+      "grad_norm": 0.43197157979011536,
+      "learning_rate": 0.00018499509110272308,
+      "loss": 0.6564432978630066,
+      "step": 3374
+    },
+    {
+      "epoch": 1.4565264293419633,
+      "grad_norm": 0.4266451299190521,
+      "learning_rate": 0.00018496920847683196,
+      "loss": 0.6715503931045532,
+      "step": 3376
+    },
+    {
+      "epoch": 1.4573894282632147,
+      "grad_norm": 0.4835279583930969,
+      "learning_rate": 0.00018494330536099926,
+      "loss": 0.7800700068473816,
+      "step": 3378
+    },
+    {
+      "epoch": 1.458252427184466,
+      "grad_norm": 0.5084423422813416,
+      "learning_rate": 0.00018491738176147139,
+      "loss": 0.7650374174118042,
+      "step": 3380
+    },
+    {
+      "epoch": 1.4591154261057173,
+      "grad_norm": 0.41681453585624695,
+      "learning_rate": 0.00018489143768449974,
+      "loss": 0.7307957410812378,
+      "step": 3382
+    },
+    {
+      "epoch": 1.4599784250269687,
+      "grad_norm": 0.4184363782405853,
+      "learning_rate": 0.00018486547313634058,
+      "loss": 0.7257798910140991,
+      "step": 3384
+    },
+    {
+      "epoch": 1.4608414239482201,
+      "grad_norm": 0.5055010318756104,
+      "learning_rate": 0.00018483948812325512,
+      "loss": 0.7981155514717102,
+      "step": 3386
+    },
+    {
+      "epoch": 1.4617044228694713,
+      "grad_norm": 0.4449431300163269,
+      "learning_rate": 0.00018481348265150961,
+      "loss": 0.7802942395210266,
+      "step": 3388
+    },
+    {
+      "epoch": 1.4625674217907227,
+      "grad_norm": 0.3826743960380554,
+      "learning_rate": 0.00018478745672737508,
+      "loss": 0.6799795031547546,
+      "step": 3390
+    },
+    {
+      "epoch": 1.4634304207119742,
+      "grad_norm": 0.4156678318977356,
+      "learning_rate": 0.00018476141035712757,
+      "loss": 0.7275620698928833,
+      "step": 3392
+    },
+    {
+      "epoch": 1.4642934196332256,
+      "grad_norm": 0.47241929173469543,
+      "learning_rate": 0.00018473534354704807,
+      "loss": 0.6979914903640747,
+      "step": 3394
+    },
+    {
+      "epoch": 1.4651564185544768,
+      "grad_norm": 0.4340677261352539,
+      "learning_rate": 0.00018470925630342247,
+      "loss": 0.7208709120750427,
+      "step": 3396
+    },
+    {
+      "epoch": 1.4660194174757282,
+      "grad_norm": 0.39896467328071594,
+      "learning_rate": 0.00018468314863254154,
+      "loss": 0.6596860885620117,
+      "step": 3398
+    },
+    {
+      "epoch": 1.4668824163969796,
+      "grad_norm": 0.4282037317752838,
+      "learning_rate": 0.00018465702054070113,
+      "loss": 0.7703273892402649,
+      "step": 3400
+    },
+    {
+      "epoch": 1.4668824163969796,
+      "eval_loss": 0.8002338409423828,
+      "eval_runtime": 649.7427,
+      "eval_samples_per_second": 3.17,
+      "eval_steps_per_second": 3.17,
+      "step": 3400
+    },
+    {
+      "epoch": 1.4677454153182308,
+      "grad_norm": 0.39301496744155884,
+      "learning_rate": 0.00018463087203420182,
+      "loss": 0.740729033946991,
+      "step": 3402
+    },
+    {
+      "epoch": 1.4686084142394822,
+      "grad_norm": 0.4466440677642822,
+      "learning_rate": 0.00018460470311934923,
+      "loss": 0.6625239253044128,
+      "step": 3404
+    },
+    {
+      "epoch": 1.4694714131607336,
+      "grad_norm": 0.48659050464630127,
+      "learning_rate": 0.00018457851380245392,
+      "loss": 0.7232626080513,
+      "step": 3406
+    },
+    {
+      "epoch": 1.4703344120819848,
+      "grad_norm": 0.44322678446769714,
+      "learning_rate": 0.00018455230408983124,
+      "loss": 0.6909189224243164,
+      "step": 3408
+    },
+    {
+      "epoch": 1.4711974110032362,
+      "grad_norm": 0.4537222683429718,
+      "learning_rate": 0.0001845260739878016,
+      "loss": 0.728760302066803,
+      "step": 3410
+    },
+    {
+      "epoch": 1.4720604099244876,
+      "grad_norm": 0.426753968000412,
+      "learning_rate": 0.0001844998235026903,
+      "loss": 0.6631523966789246,
+      "step": 3412
+    },
+    {
+      "epoch": 1.472923408845739,
+      "grad_norm": 0.46893343329429626,
+      "learning_rate": 0.0001844735526408275,
+      "loss": 0.7257310748100281,
+      "step": 3414
+    },
+    {
+      "epoch": 1.4737864077669902,
+      "grad_norm": 0.41580045223236084,
+      "learning_rate": 0.00018444726140854823,
+      "loss": 0.7732333540916443,
+      "step": 3416
+    },
+    {
+      "epoch": 1.4746494066882416,
+      "grad_norm": 0.42891791462898254,
+      "learning_rate": 0.00018442094981219257,
+      "loss": 0.6602647304534912,
+      "step": 3418
+    },
+    {
+      "epoch": 1.475512405609493,
+      "grad_norm": 0.45967262983322144,
+      "learning_rate": 0.00018439461785810547,
+      "loss": 0.7164129018783569,
+      "step": 3420
+    },
+    {
+      "epoch": 1.4763754045307445,
+      "grad_norm": 0.4251352846622467,
+      "learning_rate": 0.0001843682655526367,
+      "loss": 0.7289180755615234,
+      "step": 3422
+    },
+    {
+      "epoch": 1.4772384034519956,
+      "grad_norm": 0.3898853361606598,
+      "learning_rate": 0.00018434189290214106,
+      "loss": 0.7455880641937256,
+      "step": 3424
+    },
+    {
+      "epoch": 1.478101402373247,
+      "grad_norm": 0.4341840445995331,
+      "learning_rate": 0.00018431549991297815,
+      "loss": 0.7042546272277832,
+      "step": 3426
+    },
+    {
+      "epoch": 1.4789644012944985,
+      "grad_norm": 0.41306495666503906,
+      "learning_rate": 0.00018428908659151252,
+      "loss": 0.7600736021995544,
+      "step": 3428
+    },
+    {
+      "epoch": 1.4798274002157497,
+      "grad_norm": 0.41544052958488464,
+      "learning_rate": 0.00018426265294411363,
+      "loss": 0.7219595909118652,
+      "step": 3430
+    },
+    {
+      "epoch": 1.480690399137001,
+      "grad_norm": 0.45290282368659973,
+      "learning_rate": 0.00018423619897715585,
+      "loss": 0.8417305946350098,
+      "step": 3432
+    },
+    {
+      "epoch": 1.4815533980582525,
+      "grad_norm": 0.4438819885253906,
+      "learning_rate": 0.00018420972469701842,
+      "loss": 0.7625543475151062,
+      "step": 3434
+    },
+    {
+      "epoch": 1.4824163969795037,
+      "grad_norm": 0.49848470091819763,
+      "learning_rate": 0.00018418323011008548,
+      "loss": 0.7759302258491516,
+      "step": 3436
+    },
+    {
+      "epoch": 1.483279395900755,
+      "grad_norm": 0.3774218261241913,
+      "learning_rate": 0.00018415671522274614,
+      "loss": 0.6921430826187134,
+      "step": 3438
+    },
+    {
+      "epoch": 1.4841423948220065,
+      "grad_norm": 0.4494822919368744,
+      "learning_rate": 0.0001841301800413943,
+      "loss": 0.6789629459381104,
+      "step": 3440
+    },
+    {
+      "epoch": 1.4850053937432577,
+      "grad_norm": 0.4084416329860687,
+      "learning_rate": 0.00018410362457242876,
+      "loss": 0.6904259324073792,
+      "step": 3442
+    },
+    {
+      "epoch": 1.485868392664509,
+      "grad_norm": 0.4472881257534027,
+      "learning_rate": 0.0001840770488222533,
+      "loss": 0.7037150263786316,
+      "step": 3444
+    },
+    {
+      "epoch": 1.4867313915857605,
+      "grad_norm": 0.4696385860443115,
+      "learning_rate": 0.0001840504527972766,
+      "loss": 0.7732300758361816,
+      "step": 3446
+    },
+    {
+      "epoch": 1.487594390507012,
+      "grad_norm": 0.4683626592159271,
+      "learning_rate": 0.00018402383650391207,
+      "loss": 0.767594039440155,
+      "step": 3448
+    },
+    {
+      "epoch": 1.4884573894282633,
+      "grad_norm": 0.47404953837394714,
+      "learning_rate": 0.00018399719994857816,
+      "loss": 0.8145772218704224,
+      "step": 3450
+    },
+    {
+      "epoch": 1.4893203883495145,
+      "grad_norm": 0.5147852897644043,
+      "learning_rate": 0.00018397054313769814,
+      "loss": 0.784772515296936,
+      "step": 3452
+    },
+    {
+      "epoch": 1.490183387270766,
+      "grad_norm": 0.5376461744308472,
+      "learning_rate": 0.00018394386607770017,
+      "loss": 0.7849431037902832,
+      "step": 3454
+    },
+    {
+      "epoch": 1.4910463861920173,
+      "grad_norm": 0.4688630700111389,
+      "learning_rate": 0.0001839171687750173,
+      "loss": 0.7196945548057556,
+      "step": 3456
+    },
+    {
+      "epoch": 1.4919093851132685,
+      "grad_norm": 0.5115576386451721,
+      "learning_rate": 0.00018389045123608753,
+      "loss": 0.8277292251586914,
+      "step": 3458
+    },
+    {
+      "epoch": 1.49277238403452,
+      "grad_norm": 0.3999786674976349,
+      "learning_rate": 0.0001838637134673536,
+      "loss": 0.7628065943717957,
+      "step": 3460
+    },
+    {
+      "epoch": 1.4936353829557714,
+      "grad_norm": 0.4474492371082306,
+      "learning_rate": 0.00018383695547526322,
+      "loss": 0.717315673828125,
+      "step": 3462
+    },
+    {
+      "epoch": 1.4944983818770226,
+      "grad_norm": 0.4175044596195221,
+      "learning_rate": 0.00018381017726626896,
+      "loss": 0.7365549206733704,
+      "step": 3464
+    },
+    {
+      "epoch": 1.495361380798274,
+      "grad_norm": 0.4938793480396271,
+      "learning_rate": 0.0001837833788468283,
+      "loss": 0.7562727928161621,
+      "step": 3466
+    },
+    {
+      "epoch": 1.4962243797195254,
+      "grad_norm": 0.4369599521160126,
+      "learning_rate": 0.0001837565602234035,
+      "loss": 0.82245272397995,
+      "step": 3468
+    },
+    {
+      "epoch": 1.4970873786407766,
+      "grad_norm": 0.4824387729167938,
+      "learning_rate": 0.00018372972140246182,
+      "loss": 0.7570599913597107,
+      "step": 3470
+    },
+    {
+      "epoch": 1.497950377562028,
+      "grad_norm": 0.46261459589004517,
+      "learning_rate": 0.00018370286239047522,
+      "loss": 0.7152431607246399,
+      "step": 3472
+    },
+    {
+      "epoch": 1.4988133764832794,
+      "grad_norm": 0.4452435076236725,
+      "learning_rate": 0.0001836759831939207,
+      "loss": 0.6635003089904785,
+      "step": 3474
+    },
+    {
+      "epoch": 1.4996763754045308,
+      "grad_norm": 0.4698450267314911,
+      "learning_rate": 0.0001836490838192801,
+      "loss": 0.7814362645149231,
+      "step": 3476
+    },
+    {
+      "epoch": 1.5005393743257822,
+      "grad_norm": 0.44320493936538696,
+      "learning_rate": 0.00018362216427303998,
+      "loss": 0.6941080689430237,
+      "step": 3478
+    },
+    {
+      "epoch": 1.5014023732470334,
+      "grad_norm": 0.467252254486084,
+      "learning_rate": 0.00018359522456169193,
+      "loss": 0.7583049535751343,
+      "step": 3480
+    },
+    {
+      "epoch": 1.5022653721682848,
+      "grad_norm": 0.5454360842704773,
+      "learning_rate": 0.00018356826469173232,
+      "loss": 0.9017908573150635,
+      "step": 3482
+    },
+    {
+      "epoch": 1.5031283710895362,
+      "grad_norm": 0.5124768614768982,
+      "learning_rate": 0.00018354128466966242,
+      "loss": 0.8088064789772034,
+      "step": 3484
+    },
+    {
+      "epoch": 1.5039913700107874,
+      "grad_norm": 0.4634758234024048,
+      "learning_rate": 0.00018351428450198834,
+      "loss": 0.7869967222213745,
+      "step": 3486
+    },
+    {
+      "epoch": 1.5048543689320388,
+      "grad_norm": 0.39626801013946533,
+      "learning_rate": 0.00018348726419522098,
+      "loss": 0.7509294152259827,
+      "step": 3488
+    },
+    {
+      "epoch": 1.5057173678532902,
+      "grad_norm": 0.48879387974739075,
+      "learning_rate": 0.00018346022375587628,
+      "loss": 0.710981011390686,
+      "step": 3490
+    },
+    {
+      "epoch": 1.5065803667745414,
+      "grad_norm": 0.4784195125102997,
+      "learning_rate": 0.00018343316319047482,
+      "loss": 0.7631853222846985,
+      "step": 3492
+    },
+    {
+      "epoch": 1.5074433656957928,
+      "grad_norm": 0.45802050828933716,
+      "learning_rate": 0.00018340608250554222,
+      "loss": 0.7416844964027405,
+      "step": 3494
+    },
+    {
+      "epoch": 1.5083063646170443,
+      "grad_norm": 0.42670297622680664,
+      "learning_rate": 0.0001833789817076088,
+      "loss": 0.8117082715034485,
+      "step": 3496
+    },
+    {
+      "epoch": 1.5091693635382954,
+      "grad_norm": 0.48401451110839844,
+      "learning_rate": 0.00018335186080320983,
+      "loss": 0.724604606628418,
+      "step": 3498
+    },
+    {
+      "epoch": 1.510032362459547,
+      "grad_norm": 0.5217538475990295,
+      "learning_rate": 0.00018332471979888535,
+      "loss": 0.8395941257476807,
+      "step": 3500
+    },
+    {
+      "epoch": 1.510032362459547,
+      "eval_loss": 0.7970634698867798,
+      "eval_runtime": 655.3078,
+      "eval_samples_per_second": 3.144,
+      "eval_steps_per_second": 3.144,
+      "step": 3500
+    },
+    {
+      "epoch": 1.5108953613807983,
+      "grad_norm": 0.4357616901397705,
+      "learning_rate": 0.00018329755870118033,
+      "loss": 0.7151007056236267,
+      "step": 3502
+    },
+    {
+      "epoch": 1.5117583603020495,
+      "grad_norm": 0.4224613606929779,
+      "learning_rate": 0.00018327037751664454,
+      "loss": 0.6745702028274536,
+      "step": 3504
+    },
+    {
+      "epoch": 1.512621359223301,
+      "grad_norm": 0.4674745500087738,
+      "learning_rate": 0.0001832431762518326,
+      "loss": 0.7870205640792847,
+      "step": 3506
+    },
+    {
+      "epoch": 1.5134843581445523,
+      "grad_norm": 0.44136863946914673,
+      "learning_rate": 0.00018321595491330397,
+      "loss": 0.777145504951477,
+      "step": 3508
+    },
+    {
+      "epoch": 1.5143473570658037,
+      "grad_norm": 0.5091800093650818,
+      "learning_rate": 0.00018318871350762295,
+      "loss": 0.7991534471511841,
+      "step": 3510
+    },
+    {
+      "epoch": 1.5152103559870551,
+      "grad_norm": 0.42728134989738464,
+      "learning_rate": 0.00018316145204135865,
+      "loss": 0.7678582072257996,
+      "step": 3512
+    },
+    {
+      "epoch": 1.5160733549083063,
+      "grad_norm": 0.47067728638648987,
+      "learning_rate": 0.00018313417052108513,
+      "loss": 0.7971519231796265,
+      "step": 3514
+    },
+    {
+      "epoch": 1.5169363538295577,
+      "grad_norm": 0.4250936210155487,
+      "learning_rate": 0.00018310686895338117,
+      "loss": 0.7281476259231567,
+      "step": 3516
+    },
+    {
+      "epoch": 1.5177993527508091,
+      "grad_norm": 0.4261043667793274,
+      "learning_rate": 0.00018307954734483038,
+      "loss": 0.7346498966217041,
+      "step": 3518
+    },
+    {
+      "epoch": 1.5186623516720603,
+      "grad_norm": 0.4935494363307953,
+      "learning_rate": 0.0001830522057020213,
+      "loss": 0.765254557132721,
+      "step": 3520
+    },
+    {
+      "epoch": 1.5195253505933117,
+      "grad_norm": 0.4546700119972229,
+      "learning_rate": 0.00018302484403154718,
+      "loss": 0.7073609828948975,
+      "step": 3522
+    },
+    {
+      "epoch": 1.5203883495145631,
+      "grad_norm": 0.4881356656551361,
+      "learning_rate": 0.0001829974623400062,
+      "loss": 0.681342363357544,
+      "step": 3524
+    },
+    {
+      "epoch": 1.5212513484358143,
+      "grad_norm": 0.4397423565387726,
+      "learning_rate": 0.00018297006063400134,
+      "loss": 0.6735935211181641,
+      "step": 3526
+    },
+    {
+      "epoch": 1.522114347357066,
+      "grad_norm": 0.4426570236682892,
+      "learning_rate": 0.00018294263892014038,
+      "loss": 0.721441924571991,
+      "step": 3528
+    },
+    {
+      "epoch": 1.5229773462783172,
+      "grad_norm": 0.5235413908958435,
+      "learning_rate": 0.00018291519720503599,
+      "loss": 0.8269463777542114,
+      "step": 3530
+    },
+    {
+      "epoch": 1.5238403451995683,
+      "grad_norm": 0.4708006978034973,
+      "learning_rate": 0.00018288773549530557,
+      "loss": 0.7080397605895996,
+      "step": 3532
+    },
+    {
+      "epoch": 1.52470334412082,
+      "grad_norm": 0.47188836336135864,
+      "learning_rate": 0.00018286025379757136,
+      "loss": 0.7505635023117065,
+      "step": 3534
+    },
+    {
+      "epoch": 1.5255663430420712,
+      "grad_norm": 0.4706624746322632,
+      "learning_rate": 0.00018283275211846052,
+      "loss": 0.743853747844696,
+      "step": 3536
+    },
+    {
+      "epoch": 1.5264293419633226,
+      "grad_norm": 0.42075470089912415,
+      "learning_rate": 0.0001828052304646049,
+      "loss": 0.7527500987052917,
+      "step": 3538
+    },
+    {
+      "epoch": 1.527292340884574,
+      "grad_norm": 0.47468745708465576,
+      "learning_rate": 0.00018277768884264123,
+      "loss": 0.7295951247215271,
+      "step": 3540
+    },
+    {
+      "epoch": 1.5281553398058252,
+      "grad_norm": 0.49890658259391785,
+      "learning_rate": 0.00018275012725921106,
+      "loss": 0.7707282900810242,
+      "step": 3542
+    },
+    {
+      "epoch": 1.5290183387270766,
+      "grad_norm": 0.44301101565361023,
+      "learning_rate": 0.00018272254572096076,
+      "loss": 0.7032204270362854,
+      "step": 3544
+    },
+    {
+      "epoch": 1.529881337648328,
+      "grad_norm": 0.4144493043422699,
+      "learning_rate": 0.00018269494423454148,
+      "loss": 0.6652095317840576,
+      "step": 3546
+    },
+    {
+      "epoch": 1.5307443365695792,
+      "grad_norm": 0.41546186804771423,
+      "learning_rate": 0.00018266732280660915,
+      "loss": 0.7446690797805786,
+      "step": 3548
+    },
+    {
+      "epoch": 1.5316073354908306,
+      "grad_norm": 0.46266189217567444,
+      "learning_rate": 0.00018263968144382464,
+      "loss": 0.800329327583313,
+      "step": 3550
+    },
+    {
+      "epoch": 1.532470334412082,
+      "grad_norm": 0.46991246938705444,
+      "learning_rate": 0.00018261202015285347,
+      "loss": 0.8398324251174927,
+      "step": 3552
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.45873361825942993,
+      "learning_rate": 0.00018258433894036605,
+      "loss": 0.7080168724060059,
+      "step": 3554
+    },
+    {
+      "epoch": 1.5341963322545846,
+      "grad_norm": 0.4650769531726837,
+      "learning_rate": 0.00018255663781303758,
+      "loss": 0.7790565490722656,
+      "step": 3556
+    },
+    {
+      "epoch": 1.535059331175836,
+      "grad_norm": 0.4353472590446472,
+      "learning_rate": 0.00018252891677754808,
+      "loss": 0.7548949122428894,
+      "step": 3558
+    },
+    {
+      "epoch": 1.5359223300970872,
+      "grad_norm": 0.4259464740753174,
+      "learning_rate": 0.00018250117584058236,
+      "loss": 0.7493187189102173,
+      "step": 3560
+    },
+    {
+      "epoch": 1.5367853290183389,
+      "grad_norm": 0.4781721234321594,
+      "learning_rate": 0.00018247341500883,
+      "loss": 0.8031244277954102,
+      "step": 3562
+    },
+    {
+      "epoch": 1.53764832793959,
+      "grad_norm": 0.4471439719200134,
+      "learning_rate": 0.00018244563428898537,
+      "loss": 0.74393630027771,
+      "step": 3564
+    },
+    {
+      "epoch": 1.5385113268608415,
+      "grad_norm": 0.4181448519229889,
+      "learning_rate": 0.00018241783368774773,
+      "loss": 0.8052780628204346,
+      "step": 3566
+    },
+    {
+      "epoch": 1.5393743257820929,
+      "grad_norm": 0.5136722326278687,
+      "learning_rate": 0.000182390013211821,
+      "loss": 0.825944721698761,
+      "step": 3568
+    },
+    {
+      "epoch": 1.540237324703344,
+      "grad_norm": 0.43782681226730347,
+      "learning_rate": 0.00018236217286791403,
+      "loss": 0.70372474193573,
+      "step": 3570
+    },
+    {
+      "epoch": 1.5411003236245955,
+      "grad_norm": 0.44272729754447937,
+      "learning_rate": 0.00018233431266274038,
+      "loss": 0.7298035621643066,
+      "step": 3572
+    },
+    {
+      "epoch": 1.541963322545847,
+      "grad_norm": 0.44322386384010315,
+      "learning_rate": 0.00018230643260301838,
+      "loss": 0.7507740259170532,
+      "step": 3574
+    },
+    {
+      "epoch": 1.542826321467098,
+      "grad_norm": 0.48743686079978943,
+      "learning_rate": 0.00018227853269547117,
+      "loss": 0.7720011472702026,
+      "step": 3576
+    },
+    {
+      "epoch": 1.5436893203883495,
+      "grad_norm": 0.4608381390571594,
+      "learning_rate": 0.00018225061294682674,
+      "loss": 0.8001248240470886,
+      "step": 3578
+    },
+    {
+      "epoch": 1.544552319309601,
+      "grad_norm": 0.45625007152557373,
+      "learning_rate": 0.00018222267336381778,
+      "loss": 0.7971346378326416,
+      "step": 3580
+    },
+    {
+      "epoch": 1.545415318230852,
+      "grad_norm": 0.4687005579471588,
+      "learning_rate": 0.00018219471395318178,
+      "loss": 0.7254680395126343,
+      "step": 3582
+    },
+    {
+      "epoch": 1.5462783171521035,
+      "grad_norm": 0.48081183433532715,
+      "learning_rate": 0.00018216673472166108,
+      "loss": 0.7372352480888367,
+      "step": 3584
+    },
+    {
+      "epoch": 1.547141316073355,
+      "grad_norm": 0.42272305488586426,
+      "learning_rate": 0.0001821387356760027,
+      "loss": 0.6276986598968506,
+      "step": 3586
+    },
+    {
+      "epoch": 1.5480043149946061,
+      "grad_norm": 0.42225342988967896,
+      "learning_rate": 0.0001821107168229585,
+      "loss": 0.7299351692199707,
+      "step": 3588
+    },
+    {
+      "epoch": 1.5488673139158577,
+      "grad_norm": 0.4649020731449127,
+      "learning_rate": 0.00018208267816928507,
+      "loss": 0.6684783101081848,
+      "step": 3590
+    },
+    {
+      "epoch": 1.549730312837109,
+      "grad_norm": 0.3961552679538727,
+      "learning_rate": 0.00018205461972174388,
+      "loss": 0.6579244136810303,
+      "step": 3592
+    },
+    {
+      "epoch": 1.5505933117583603,
+      "grad_norm": 0.500170111656189,
+      "learning_rate": 0.00018202654148710102,
+      "loss": 0.6955749988555908,
+      "step": 3594
+    },
+    {
+      "epoch": 1.5514563106796118,
+      "grad_norm": 0.5200181603431702,
+      "learning_rate": 0.00018199844347212746,
+      "loss": 0.6725539565086365,
+      "step": 3596
+    },
+    {
+      "epoch": 1.552319309600863,
+      "grad_norm": 0.4894106984138489,
+      "learning_rate": 0.0001819703256835989,
+      "loss": 0.7726914882659912,
+      "step": 3598
+    },
+    {
+      "epoch": 1.5531823085221144,
+      "grad_norm": 0.487623006105423,
+      "learning_rate": 0.00018194218812829583,
+      "loss": 0.8290923833847046,
+      "step": 3600
+    },
+    {
+      "epoch": 1.5531823085221144,
+      "eval_loss": 0.7935511469841003,
+      "eval_runtime": 666.5283,
+      "eval_samples_per_second": 3.091,
+      "eval_steps_per_second": 3.091,
+      "step": 3600
+    },
+    {
+      "epoch": 1.5540453074433658,
+      "grad_norm": 0.4056689441204071,
+      "learning_rate": 0.0001819140308130035,
+      "loss": 0.6819650530815125,
+      "step": 3602
+    },
+    {
+      "epoch": 1.554908306364617,
+      "grad_norm": 0.4337533712387085,
+      "learning_rate": 0.0001818858537445119,
+      "loss": 0.6709993481636047,
+      "step": 3604
+    },
+    {
+      "epoch": 1.5557713052858684,
+      "grad_norm": 0.4365732967853546,
+      "learning_rate": 0.0001818576569296158,
+      "loss": 0.6784732937812805,
+      "step": 3606
+    },
+    {
+      "epoch": 1.5566343042071198,
+      "grad_norm": 0.4632627069950104,
+      "learning_rate": 0.00018182944037511476,
+      "loss": 0.7771052718162537,
+      "step": 3608
+    },
+    {
+      "epoch": 1.557497303128371,
+      "grad_norm": 0.45411452651023865,
+      "learning_rate": 0.00018180120408781305,
+      "loss": 0.8117473125457764,
+      "step": 3610
+    },
+    {
+      "epoch": 1.5583603020496224,
+      "grad_norm": 0.4931472837924957,
+      "learning_rate": 0.00018177294807451974,
+      "loss": 0.7268829941749573,
+      "step": 3612
+    },
+    {
+      "epoch": 1.5592233009708738,
+      "grad_norm": 0.4711272418498993,
+      "learning_rate": 0.00018174467234204867,
+      "loss": 0.7986008524894714,
+      "step": 3614
+    },
+    {
+      "epoch": 1.560086299892125,
+      "grad_norm": 0.47048646211624146,
+      "learning_rate": 0.00018171637689721833,
+      "loss": 0.7606064081192017,
+      "step": 3616
+    },
+    {
+      "epoch": 1.5609492988133766,
+      "grad_norm": 0.4612944424152374,
+      "learning_rate": 0.00018168806174685212,
+      "loss": 0.7444906234741211,
+      "step": 3618
+    },
+    {
+      "epoch": 1.5618122977346278,
+      "grad_norm": 0.4275529980659485,
+      "learning_rate": 0.00018165972689777803,
+      "loss": 0.7393948435783386,
+      "step": 3620
+    },
+    {
+      "epoch": 1.5626752966558792,
+      "grad_norm": 0.5759958028793335,
+      "learning_rate": 0.00018163137235682893,
+      "loss": 0.7669101357460022,
+      "step": 3622
+    },
+    {
+      "epoch": 1.5635382955771306,
+      "grad_norm": 0.41767528653144836,
+      "learning_rate": 0.00018160299813084238,
+      "loss": 0.7250568270683289,
+      "step": 3624
+    },
+    {
+      "epoch": 1.5644012944983818,
+      "grad_norm": 0.40168496966362,
+      "learning_rate": 0.00018157460422666075,
+      "loss": 0.7880772352218628,
+      "step": 3626
+    },
+    {
+      "epoch": 1.5652642934196332,
+      "grad_norm": 0.4270237386226654,
+      "learning_rate": 0.00018154619065113102,
+      "loss": 0.7754803895950317,
+      "step": 3628
+    },
+    {
+      "epoch": 1.5661272923408847,
+      "grad_norm": 0.46184200048446655,
+      "learning_rate": 0.000181517757411105,
+      "loss": 0.701246976852417,
+      "step": 3630
+    },
+    {
+      "epoch": 1.5669902912621358,
+      "grad_norm": 0.39403679966926575,
+      "learning_rate": 0.0001814893045134393,
+      "loss": 0.7201641201972961,
+      "step": 3632
+    },
+    {
+      "epoch": 1.5678532901833873,
+      "grad_norm": 0.4320994019508362,
+      "learning_rate": 0.00018146083196499512,
+      "loss": 0.6649395823478699,
+      "step": 3634
+    },
+    {
+      "epoch": 1.5687162891046387,
+      "grad_norm": 0.46719890832901,
+      "learning_rate": 0.0001814323397726386,
+      "loss": 0.7596995234489441,
+      "step": 3636
+    },
+    {
+      "epoch": 1.5695792880258899,
+      "grad_norm": 0.49942320585250854,
+      "learning_rate": 0.0001814038279432404,
+      "loss": 0.7265456914901733,
+      "step": 3638
+    },
+    {
+      "epoch": 1.5704422869471413,
+      "grad_norm": 0.41604548692703247,
+      "learning_rate": 0.00018137529648367607,
+      "loss": 0.6903387308120728,
+      "step": 3640
+    },
+    {
+      "epoch": 1.5713052858683927,
+      "grad_norm": 0.4712325930595398,
+      "learning_rate": 0.00018134674540082587,
+      "loss": 0.7590459585189819,
+      "step": 3642
+    },
+    {
+      "epoch": 1.5721682847896439,
+      "grad_norm": 0.5137260556221008,
+      "learning_rate": 0.00018131817470157471,
+      "loss": 0.7304242253303528,
+      "step": 3644
+    },
+    {
+      "epoch": 1.5730312837108955,
+      "grad_norm": 0.459363728761673,
+      "learning_rate": 0.0001812895843928123,
+      "loss": 0.6472513675689697,
+      "step": 3646
+    },
+    {
+      "epoch": 1.5738942826321467,
+      "grad_norm": 0.518924355506897,
+      "learning_rate": 0.00018126097448143306,
+      "loss": 0.7312461733818054,
+      "step": 3648
+    },
+    {
+      "epoch": 1.574757281553398,
+      "grad_norm": 0.491247296333313,
+      "learning_rate": 0.00018123234497433615,
+      "loss": 0.7790979146957397,
+      "step": 3650
+    },
+    {
+      "epoch": 1.5756202804746495,
+      "grad_norm": 0.4290984570980072,
+      "learning_rate": 0.00018120369587842547,
+      "loss": 0.7140002846717834,
+      "step": 3652
+    },
+    {
+      "epoch": 1.5764832793959007,
+      "grad_norm": 0.4229796528816223,
+      "learning_rate": 0.0001811750272006096,
+      "loss": 0.7497822046279907,
+      "step": 3654
+    },
+    {
+      "epoch": 1.5773462783171521,
+      "grad_norm": 0.444733589887619,
+      "learning_rate": 0.00018114633894780182,
+      "loss": 0.769322395324707,
+      "step": 3656
+    },
+    {
+      "epoch": 1.5782092772384035,
+      "grad_norm": 0.4415557384490967,
+      "learning_rate": 0.00018111763112692024,
+      "loss": 0.7770668268203735,
+      "step": 3658
+    },
+    {
+      "epoch": 1.5790722761596547,
+      "grad_norm": 0.42115989327430725,
+      "learning_rate": 0.00018108890374488759,
+      "loss": 0.7666043639183044,
+      "step": 3660
+    },
+    {
+      "epoch": 1.5799352750809061,
+      "grad_norm": 0.4013395607471466,
+      "learning_rate": 0.00018106015680863132,
+      "loss": 0.7253396511077881,
+      "step": 3662
+    },
+    {
+      "epoch": 1.5807982740021576,
+      "grad_norm": 0.37566566467285156,
+      "learning_rate": 0.0001810313903250837,
+      "loss": 0.6983510255813599,
+      "step": 3664
+    },
+    {
+      "epoch": 1.5816612729234087,
+      "grad_norm": 0.4788576364517212,
+      "learning_rate": 0.00018100260430118162,
+      "loss": 0.7309481501579285,
+      "step": 3666
+    },
+    {
+      "epoch": 1.5825242718446602,
+      "grad_norm": 0.43960556387901306,
+      "learning_rate": 0.0001809737987438666,
+      "loss": 0.7518695592880249,
+      "step": 3668
+    },
+    {
+      "epoch": 1.5833872707659116,
+      "grad_norm": 0.4018779993057251,
+      "learning_rate": 0.0001809449736600851,
+      "loss": 0.6877766251564026,
+      "step": 3670
+    },
+    {
+      "epoch": 1.5842502696871628,
+      "grad_norm": 0.43951910734176636,
+      "learning_rate": 0.00018091612905678808,
+      "loss": 0.7189319729804993,
+      "step": 3672
+    },
+    {
+      "epoch": 1.5851132686084144,
+      "grad_norm": 0.42398321628570557,
+      "learning_rate": 0.0001808872649409313,
+      "loss": 0.6966261863708496,
+      "step": 3674
+    },
+    {
+      "epoch": 1.5859762675296656,
+      "grad_norm": 0.4551796019077301,
+      "learning_rate": 0.00018085838131947526,
+      "loss": 0.6944435834884644,
+      "step": 3676
+    },
+    {
+      "epoch": 1.5868392664509168,
+      "grad_norm": 0.487661212682724,
+      "learning_rate": 0.00018082947819938504,
+      "loss": 0.7711076736450195,
+      "step": 3678
+    },
+    {
+      "epoch": 1.5877022653721684,
+      "grad_norm": 0.45423412322998047,
+      "learning_rate": 0.00018080055558763057,
+      "loss": 0.7488799691200256,
+      "step": 3680
+    },
+    {
+      "epoch": 1.5885652642934196,
+      "grad_norm": 0.40377750992774963,
+      "learning_rate": 0.00018077161349118633,
+      "loss": 0.6809216737747192,
+      "step": 3682
+    },
+    {
+      "epoch": 1.589428263214671,
+      "grad_norm": 0.5005835294723511,
+      "learning_rate": 0.00018074265191703163,
+      "loss": 0.7147122621536255,
+      "step": 3684
+    },
+    {
+      "epoch": 1.5902912621359224,
+      "grad_norm": 0.5540063381195068,
+      "learning_rate": 0.00018071367087215044,
+      "loss": 0.7934401035308838,
+      "step": 3686
+    },
+    {
+      "epoch": 1.5911542610571736,
+      "grad_norm": 0.41316506266593933,
+      "learning_rate": 0.00018068467036353133,
+      "loss": 0.6978628039360046,
+      "step": 3688
+    },
+    {
+      "epoch": 1.592017259978425,
+      "grad_norm": 0.5138319134712219,
+      "learning_rate": 0.00018065565039816772,
+      "loss": 0.8193445205688477,
+      "step": 3690
+    },
+    {
+      "epoch": 1.5928802588996764,
+      "grad_norm": 0.4598786234855652,
+      "learning_rate": 0.00018062661098305763,
+      "loss": 0.7386526465415955,
+      "step": 3692
+    },
+    {
+      "epoch": 1.5937432578209276,
+      "grad_norm": 0.446444034576416,
+      "learning_rate": 0.00018059755212520372,
+      "loss": 0.7734212875366211,
+      "step": 3694
+    },
+    {
+      "epoch": 1.594606256742179,
+      "grad_norm": 0.41883963346481323,
+      "learning_rate": 0.0001805684738316135,
+      "loss": 0.718011200428009,
+      "step": 3696
+    },
+    {
+      "epoch": 1.5954692556634305,
+      "grad_norm": 0.4579313397407532,
+      "learning_rate": 0.00018053937610929897,
+      "loss": 0.7522324919700623,
+      "step": 3698
+    },
+    {
+      "epoch": 1.5963322545846816,
+      "grad_norm": 0.43380051851272583,
+      "learning_rate": 0.000180510258965277,
+      "loss": 0.6498246788978577,
+      "step": 3700
+    },
+    {
+      "epoch": 1.5963322545846816,
+      "eval_loss": 0.7914894223213196,
+      "eval_runtime": 668.9887,
+      "eval_samples_per_second": 3.079,
+      "eval_steps_per_second": 3.079,
+      "step": 3700
+    },
+    {
+      "epoch": 1.5971952535059333,
+      "grad_norm": 0.39354878664016724,
+      "learning_rate": 0.000180481122406569,
+      "loss": 0.7064145803451538,
+      "step": 3702
+    },
+    {
+      "epoch": 1.5980582524271845,
+      "grad_norm": 0.3876212239265442,
+      "learning_rate": 0.00018045196644020118,
+      "loss": 0.6859980821609497,
+      "step": 3704
+    },
+    {
+      "epoch": 1.5989212513484357,
+      "grad_norm": 0.48381999135017395,
+      "learning_rate": 0.00018042279107320427,
+      "loss": 0.8459084630012512,
+      "step": 3706
+    },
+    {
+      "epoch": 1.5997842502696873,
+      "grad_norm": 0.4688359797000885,
+      "learning_rate": 0.0001803935963126139,
+      "loss": 0.6574559211730957,
+      "step": 3708
+    },
+    {
+      "epoch": 1.6006472491909385,
+      "grad_norm": 0.537028968334198,
+      "learning_rate": 0.0001803643821654702,
+      "loss": 0.8127812147140503,
+      "step": 3710
+    },
+    {
+      "epoch": 1.60151024811219,
+      "grad_norm": 0.3990524113178253,
+      "learning_rate": 0.00018033514863881797,
+      "loss": 0.7411133050918579,
+      "step": 3712
+    },
+    {
+      "epoch": 1.6023732470334413,
+      "grad_norm": 0.38037553429603577,
+      "learning_rate": 0.00018030589573970684,
+      "loss": 0.7164896130561829,
+      "step": 3714
+    },
+    {
+      "epoch": 1.6032362459546925,
+      "grad_norm": 0.45911267399787903,
+      "learning_rate": 0.00018027662347519096,
+      "loss": 0.7164638638496399,
+      "step": 3716
+    },
+    {
+      "epoch": 1.604099244875944,
+      "grad_norm": 0.37456580996513367,
+      "learning_rate": 0.00018024733185232922,
+      "loss": 0.6928568482398987,
+      "step": 3718
+    },
+    {
+      "epoch": 1.6049622437971953,
+      "grad_norm": 0.4336542785167694,
+      "learning_rate": 0.00018021802087818517,
+      "loss": 0.6571218371391296,
+      "step": 3720
+    },
+    {
+      "epoch": 1.6058252427184465,
+      "grad_norm": 0.41265374422073364,
+      "learning_rate": 0.00018018869055982698,
+      "loss": 0.6813036203384399,
+      "step": 3722
+    },
+    {
+      "epoch": 1.606688241639698,
+      "grad_norm": 0.4339812695980072,
+      "learning_rate": 0.00018015934090432757,
+      "loss": 0.753751277923584,
+      "step": 3724
+    },
+    {
+      "epoch": 1.6075512405609493,
+      "grad_norm": 0.41123342514038086,
+      "learning_rate": 0.00018012997191876447,
+      "loss": 0.676802396774292,
+      "step": 3726
+    },
+    {
+      "epoch": 1.6084142394822005,
+      "grad_norm": 0.4282870292663574,
+      "learning_rate": 0.00018010058361021987,
+      "loss": 0.7151802778244019,
+      "step": 3728
+    },
+    {
+      "epoch": 1.6092772384034522,
+      "grad_norm": 0.44637587666511536,
+      "learning_rate": 0.00018007117598578063,
+      "loss": 0.815374493598938,
+      "step": 3730
+    },
+    {
+      "epoch": 1.6101402373247033,
+      "grad_norm": 0.41761815547943115,
+      "learning_rate": 0.00018004174905253826,
+      "loss": 0.7119425535202026,
+      "step": 3732
+    },
+    {
+      "epoch": 1.6110032362459545,
+      "grad_norm": 0.4224661886692047,
+      "learning_rate": 0.0001800123028175889,
+      "loss": 0.7779671549797058,
+      "step": 3734
+    },
+    {
+      "epoch": 1.6118662351672062,
+      "grad_norm": 0.476329505443573,
+      "learning_rate": 0.00017998283728803345,
+      "loss": 0.5716424584388733,
+      "step": 3736
+    },
+    {
+      "epoch": 1.6127292340884574,
+      "grad_norm": 0.4721233546733856,
+      "learning_rate": 0.00017995335247097738,
+      "loss": 0.7326773405075073,
+      "step": 3738
+    },
+    {
+      "epoch": 1.6135922330097088,
+      "grad_norm": 0.38915106654167175,
+      "learning_rate": 0.00017992384837353073,
+      "loss": 0.7872865200042725,
+      "step": 3740
+    },
+    {
+      "epoch": 1.6144552319309602,
+      "grad_norm": 0.4306866526603699,
+      "learning_rate": 0.00017989432500280838,
+      "loss": 0.8006538152694702,
+      "step": 3742
+    },
+    {
+      "epoch": 1.6153182308522114,
+      "grad_norm": 0.3983909487724304,
+      "learning_rate": 0.00017986478236592973,
+      "loss": 0.7693750858306885,
+      "step": 3744
+    },
+    {
+      "epoch": 1.6161812297734628,
+      "grad_norm": 0.4322768747806549,
+      "learning_rate": 0.00017983522047001883,
+      "loss": 0.7483386993408203,
+      "step": 3746
+    },
+    {
+      "epoch": 1.6170442286947142,
+      "grad_norm": 0.5202714204788208,
+      "learning_rate": 0.00017980563932220442,
+      "loss": 0.7642959356307983,
+      "step": 3748
+    },
+    {
+      "epoch": 1.6179072276159654,
+      "grad_norm": 0.4318627119064331,
+      "learning_rate": 0.00017977603892961982,
+      "loss": 0.741479754447937,
+      "step": 3750
+    },
+    {
+      "epoch": 1.6187702265372168,
+      "grad_norm": 0.4942893981933594,
+      "learning_rate": 0.0001797464192994031,
+      "loss": 0.7392295598983765,
+      "step": 3752
+    },
+    {
+      "epoch": 1.6196332254584682,
+      "grad_norm": 0.46874746680259705,
+      "learning_rate": 0.00017971678043869686,
+      "loss": 0.7523542046546936,
+      "step": 3754
+    },
+    {
+      "epoch": 1.6204962243797194,
+      "grad_norm": 0.47045233845710754,
+      "learning_rate": 0.00017968712235464837,
+      "loss": 0.6766729950904846,
+      "step": 3756
+    },
+    {
+      "epoch": 1.6213592233009708,
+      "grad_norm": 0.43984928727149963,
+      "learning_rate": 0.00017965744505440956,
+      "loss": 0.7277816534042358,
+      "step": 3758
+    },
+    {
+      "epoch": 1.6222222222222222,
+      "grad_norm": 0.41389113664627075,
+      "learning_rate": 0.00017962774854513697,
+      "loss": 0.7649447917938232,
+      "step": 3760
+    },
+    {
+      "epoch": 1.6230852211434734,
+      "grad_norm": 0.461200475692749,
+      "learning_rate": 0.00017959803283399182,
+      "loss": 0.7033944129943848,
+      "step": 3762
+    },
+    {
+      "epoch": 1.623948220064725,
+      "grad_norm": 0.4776712954044342,
+      "learning_rate": 0.00017956829792813985,
+      "loss": 0.8075087070465088,
+      "step": 3764
+    },
+    {
+      "epoch": 1.6248112189859762,
+      "grad_norm": 0.5021974444389343,
+      "learning_rate": 0.00017953854383475154,
+      "loss": 0.7541269063949585,
+      "step": 3766
+    },
+    {
+      "epoch": 1.6256742179072277,
+      "grad_norm": 0.46222755312919617,
+      "learning_rate": 0.0001795087705610019,
+      "loss": 0.703751266002655,
+      "step": 3768
+    },
+    {
+      "epoch": 1.626537216828479,
+      "grad_norm": 0.34487178921699524,
+      "learning_rate": 0.0001794789781140707,
+      "loss": 0.6657921671867371,
+      "step": 3770
+    },
+    {
+      "epoch": 1.6274002157497303,
+      "grad_norm": 0.38064146041870117,
+      "learning_rate": 0.00017944916650114223,
+      "loss": 0.7999282479286194,
+      "step": 3772
+    },
+    {
+      "epoch": 1.6282632146709817,
+      "grad_norm": 0.48815488815307617,
+      "learning_rate": 0.00017941933572940543,
+      "loss": 0.7157361507415771,
+      "step": 3774
+    },
+    {
+      "epoch": 1.629126213592233,
+      "grad_norm": 0.42136189341545105,
+      "learning_rate": 0.00017938948580605382,
+      "loss": 0.6897950768470764,
+      "step": 3776
+    },
+    {
+      "epoch": 1.6299892125134843,
+      "grad_norm": 0.388630747795105,
+      "learning_rate": 0.0001793596167382856,
+      "loss": 0.6738383173942566,
+      "step": 3778
+    },
+    {
+      "epoch": 1.6308522114347357,
+      "grad_norm": 0.4050692617893219,
+      "learning_rate": 0.00017932972853330355,
+      "loss": 0.6531928777694702,
+      "step": 3780
+    },
+    {
+      "epoch": 1.631715210355987,
+      "grad_norm": 0.542385995388031,
+      "learning_rate": 0.0001792998211983151,
+      "loss": 0.8739076256752014,
+      "step": 3782
+    },
+    {
+      "epoch": 1.6325782092772383,
+      "grad_norm": 0.4323846995830536,
+      "learning_rate": 0.00017926989474053223,
+      "loss": 0.7771362662315369,
+      "step": 3784
+    },
+    {
+      "epoch": 1.6334412081984897,
+      "grad_norm": 0.47487086057662964,
+      "learning_rate": 0.00017923994916717163,
+      "loss": 0.7664928436279297,
+      "step": 3786
+    },
+    {
+      "epoch": 1.6343042071197411,
+      "grad_norm": 0.3801349401473999,
+      "learning_rate": 0.0001792099844854545,
+      "loss": 0.6508067846298218,
+      "step": 3788
+    },
+    {
+      "epoch": 1.6351672060409923,
+      "grad_norm": 0.38995426893234253,
+      "learning_rate": 0.00017918000070260668,
+      "loss": 0.6948919892311096,
+      "step": 3790
+    },
+    {
+      "epoch": 1.636030204962244,
+      "grad_norm": 0.4038735628128052,
+      "learning_rate": 0.00017914999782585862,
+      "loss": 0.7225003242492676,
+      "step": 3792
+    },
+    {
+      "epoch": 1.6368932038834951,
+      "grad_norm": 0.45372122526168823,
+      "learning_rate": 0.00017911997586244542,
+      "loss": 0.7177075147628784,
+      "step": 3794
+    },
+    {
+      "epoch": 1.6377562028047465,
+      "grad_norm": 0.5123688578605652,
+      "learning_rate": 0.00017908993481960669,
+      "loss": 0.8427615165710449,
+      "step": 3796
+    },
+    {
+      "epoch": 1.638619201725998,
+      "grad_norm": 0.505483865737915,
+      "learning_rate": 0.00017905987470458675,
+      "loss": 0.7884581089019775,
+      "step": 3798
+    },
+    {
+      "epoch": 1.6394822006472491,
+      "grad_norm": 0.5441710948944092,
+      "learning_rate": 0.0001790297955246344,
+      "loss": 0.8026853799819946,
+      "step": 3800
+    },
+    {
+      "epoch": 1.6394822006472491,
+      "eval_loss": 0.7887746691703796,
+      "eval_runtime": 655.8201,
+      "eval_samples_per_second": 3.141,
+      "eval_steps_per_second": 3.141,
+      "step": 3800
+    },
+    {
+      "epoch": 1.6403451995685006,
+      "grad_norm": 0.3747040033340454,
+      "learning_rate": 0.00017899969728700315,
+      "loss": 0.6836490035057068,
+      "step": 3802
+    },
+    {
+      "epoch": 1.641208198489752,
+      "grad_norm": 0.4163338243961334,
+      "learning_rate": 0.000178969579998951,
+      "loss": 0.748136579990387,
+      "step": 3804
+    },
+    {
+      "epoch": 1.6420711974110032,
+      "grad_norm": 0.4737973213195801,
+      "learning_rate": 0.00017893944366774065,
+      "loss": 0.7534400224685669,
+      "step": 3806
+    },
+    {
+      "epoch": 1.6429341963322546,
+      "grad_norm": 0.4687727093696594,
+      "learning_rate": 0.00017890928830063932,
+      "loss": 0.7779349088668823,
+      "step": 3808
+    },
+    {
+      "epoch": 1.643797195253506,
+      "grad_norm": 0.43674737215042114,
+      "learning_rate": 0.00017887911390491884,
+      "loss": 0.6942368149757385,
+      "step": 3810
+    },
+    {
+      "epoch": 1.6446601941747572,
+      "grad_norm": 0.43343719840049744,
+      "learning_rate": 0.00017884892048785565,
+      "loss": 0.7554087042808533,
+      "step": 3812
+    },
+    {
+      "epoch": 1.6455231930960086,
+      "grad_norm": 0.4790881276130676,
+      "learning_rate": 0.0001788187080567307,
+      "loss": 0.7387835383415222,
+      "step": 3814
+    },
+    {
+      "epoch": 1.64638619201726,
+      "grad_norm": 0.4524185061454773,
+      "learning_rate": 0.00017878847661882965,
+      "loss": 0.7229949235916138,
+      "step": 3816
+    },
+    {
+      "epoch": 1.6472491909385112,
+      "grad_norm": 0.4563996195793152,
+      "learning_rate": 0.00017875822618144263,
+      "loss": 0.6808197498321533,
+      "step": 3818
+    },
+    {
+      "epoch": 1.6481121898597628,
+      "grad_norm": 0.452282190322876,
+      "learning_rate": 0.00017872795675186442,
+      "loss": 0.6958807110786438,
+      "step": 3820
+    },
+    {
+      "epoch": 1.648975188781014,
+      "grad_norm": 0.5677687525749207,
+      "learning_rate": 0.00017869766833739434,
+      "loss": 0.7347233295440674,
+      "step": 3822
+    },
+    {
+      "epoch": 1.6498381877022654,
+      "grad_norm": 0.5028979778289795,
+      "learning_rate": 0.00017866736094533628,
+      "loss": 0.7279980182647705,
+      "step": 3824
+    },
+    {
+      "epoch": 1.6507011866235168,
+      "grad_norm": 0.4216834604740143,
+      "learning_rate": 0.0001786370345829988,
+      "loss": 0.7350833415985107,
+      "step": 3826
+    },
+    {
+      "epoch": 1.651564185544768,
+      "grad_norm": 0.4700584411621094,
+      "learning_rate": 0.00017860668925769494,
+      "loss": 0.8165807127952576,
+      "step": 3828
+    },
+    {
+      "epoch": 1.6524271844660194,
+      "grad_norm": 0.41511070728302,
+      "learning_rate": 0.0001785763249767423,
+      "loss": 0.7146443128585815,
+      "step": 3830
+    },
+    {
+      "epoch": 1.6532901833872709,
+      "grad_norm": 0.5240047574043274,
+      "learning_rate": 0.00017854594174746314,
+      "loss": 0.7849907875061035,
+      "step": 3832
+    },
+    {
+      "epoch": 1.654153182308522,
+      "grad_norm": 0.4594099223613739,
+      "learning_rate": 0.0001785155395771842,
+      "loss": 0.6815205812454224,
+      "step": 3834
+    },
+    {
+      "epoch": 1.6550161812297735,
+      "grad_norm": 0.41762664914131165,
+      "learning_rate": 0.00017848511847323682,
+      "loss": 0.7110051512718201,
+      "step": 3836
+    },
+    {
+      "epoch": 1.6558791801510249,
+      "grad_norm": 0.4596463143825531,
+      "learning_rate": 0.00017845467844295696,
+      "loss": 0.7868525981903076,
+      "step": 3838
+    },
+    {
+      "epoch": 1.656742179072276,
+      "grad_norm": 0.3694678246974945,
+      "learning_rate": 0.00017842421949368505,
+      "loss": 0.7308529615402222,
+      "step": 3840
+    },
+    {
+      "epoch": 1.6576051779935275,
+      "grad_norm": 0.4251806139945984,
+      "learning_rate": 0.00017839374163276616,
+      "loss": 0.6846014857292175,
+      "step": 3842
+    },
+    {
+      "epoch": 1.6584681769147789,
+      "grad_norm": 0.4015883207321167,
+      "learning_rate": 0.00017836324486754986,
+      "loss": 0.7137831449508667,
+      "step": 3844
+    },
+    {
+      "epoch": 1.65933117583603,
+      "grad_norm": 0.4787199795246124,
+      "learning_rate": 0.00017833272920539034,
+      "loss": 0.7908329367637634,
+      "step": 3846
+    },
+    {
+      "epoch": 1.6601941747572817,
+      "grad_norm": 0.4505045711994171,
+      "learning_rate": 0.0001783021946536463,
+      "loss": 0.6918519139289856,
+      "step": 3848
+    },
+    {
+      "epoch": 1.661057173678533,
+      "grad_norm": 0.43013763427734375,
+      "learning_rate": 0.00017827164121968103,
+      "loss": 0.7223191857337952,
+      "step": 3850
+    },
+    {
+      "epoch": 1.661920172599784,
+      "grad_norm": 0.47614169120788574,
+      "learning_rate": 0.00017824106891086228,
+      "loss": 0.8076598644256592,
+      "step": 3852
+    },
+    {
+      "epoch": 1.6627831715210357,
+      "grad_norm": 0.48056647181510925,
+      "learning_rate": 0.0001782104777345625,
+      "loss": 0.7656319737434387,
+      "step": 3854
+    },
+    {
+      "epoch": 1.663646170442287,
+      "grad_norm": 0.38120999932289124,
+      "learning_rate": 0.00017817986769815857,
+      "loss": 0.7252323031425476,
+      "step": 3856
+    },
+    {
+      "epoch": 1.6645091693635383,
+      "grad_norm": 0.478983074426651,
+      "learning_rate": 0.00017814923880903202,
+      "loss": 0.747683048248291,
+      "step": 3858
+    },
+    {
+      "epoch": 1.6653721682847897,
+      "grad_norm": 0.4553819000720978,
+      "learning_rate": 0.0001781185910745688,
+      "loss": 0.69855135679245,
+      "step": 3860
+    },
+    {
+      "epoch": 1.666235167206041,
+      "grad_norm": 0.49657294154167175,
+      "learning_rate": 0.0001780879245021595,
+      "loss": 0.8340141773223877,
+      "step": 3862
+    },
+    {
+      "epoch": 1.6670981661272923,
+      "grad_norm": 0.40509313344955444,
+      "learning_rate": 0.00017805723909919925,
+      "loss": 0.7290753722190857,
+      "step": 3864
+    },
+    {
+      "epoch": 1.6679611650485437,
+      "grad_norm": 0.4422856271266937,
+      "learning_rate": 0.00017802653487308768,
+      "loss": 0.7971621751785278,
+      "step": 3866
+    },
+    {
+      "epoch": 1.668824163969795,
+      "grad_norm": 0.4734835624694824,
+      "learning_rate": 0.00017799581183122894,
+      "loss": 0.7099016904830933,
+      "step": 3868
+    },
+    {
+      "epoch": 1.6696871628910464,
+      "grad_norm": 0.3835538625717163,
+      "learning_rate": 0.0001779650699810318,
+      "loss": 0.7210022211074829,
+      "step": 3870
+    },
+    {
+      "epoch": 1.6705501618122978,
+      "grad_norm": 0.3696903884410858,
+      "learning_rate": 0.00017793430932990951,
+      "loss": 0.6639223694801331,
+      "step": 3872
+    },
+    {
+      "epoch": 1.671413160733549,
+      "grad_norm": 0.4560008645057678,
+      "learning_rate": 0.00017790352988527984,
+      "loss": 0.8337125182151794,
+      "step": 3874
+    },
+    {
+      "epoch": 1.6722761596548006,
+      "grad_norm": 0.43672001361846924,
+      "learning_rate": 0.00017787273165456515,
+      "loss": 0.6761727929115295,
+      "step": 3876
+    },
+    {
+      "epoch": 1.6731391585760518,
+      "grad_norm": 0.37448835372924805,
+      "learning_rate": 0.00017784191464519225,
+      "loss": 0.6976995468139648,
+      "step": 3878
+    },
+    {
+      "epoch": 1.674002157497303,
+      "grad_norm": 0.37624600529670715,
+      "learning_rate": 0.00017781107886459253,
+      "loss": 0.6759265661239624,
+      "step": 3880
+    },
+    {
+      "epoch": 1.6748651564185546,
+      "grad_norm": 0.4134359359741211,
+      "learning_rate": 0.00017778022432020198,
+      "loss": 0.6577118039131165,
+      "step": 3882
+    },
+    {
+      "epoch": 1.6757281553398058,
+      "grad_norm": 0.41737261414527893,
+      "learning_rate": 0.00017774935101946092,
+      "loss": 0.7117277979850769,
+      "step": 3884
+    },
+    {
+      "epoch": 1.6765911542610572,
+      "grad_norm": 0.41871723532676697,
+      "learning_rate": 0.00017771845896981438,
+      "loss": 0.6871168613433838,
+      "step": 3886
+    },
+    {
+      "epoch": 1.6774541531823086,
+      "grad_norm": 0.4778793156147003,
+      "learning_rate": 0.00017768754817871178,
+      "loss": 0.7382785677909851,
+      "step": 3888
+    },
+    {
+      "epoch": 1.6783171521035598,
+      "grad_norm": 0.4502207338809967,
+      "learning_rate": 0.00017765661865360718,
+      "loss": 0.6783252358436584,
+      "step": 3890
+    },
+    {
+      "epoch": 1.6791801510248112,
+      "grad_norm": 0.4124210774898529,
+      "learning_rate": 0.00017762567040195907,
+      "loss": 0.7115309238433838,
+      "step": 3892
+    },
+    {
+      "epoch": 1.6800431499460626,
+      "grad_norm": 0.45017218589782715,
+      "learning_rate": 0.0001775947034312305,
+      "loss": 0.6698686480522156,
+      "step": 3894
+    },
+    {
+      "epoch": 1.6809061488673138,
+      "grad_norm": 0.4965505301952362,
+      "learning_rate": 0.00017756371774888896,
+      "loss": 0.7978704571723938,
+      "step": 3896
+    },
+    {
+      "epoch": 1.6817691477885652,
+      "grad_norm": 0.44287896156311035,
+      "learning_rate": 0.00017753271336240655,
+      "loss": 0.7991471290588379,
+      "step": 3898
+    },
+    {
+      "epoch": 1.6826321467098166,
+      "grad_norm": 0.4569724500179291,
+      "learning_rate": 0.00017750169027925985,
+      "loss": 0.7351664900779724,
+      "step": 3900
+    },
+    {
+      "epoch": 1.6826321467098166,
+      "eval_loss": 0.7847991585731506,
+      "eval_runtime": 648.2009,
+      "eval_samples_per_second": 3.178,
+      "eval_steps_per_second": 3.178,
+      "step": 3900
+    },
+    {
+      "epoch": 1.6834951456310678,
+      "grad_norm": 0.39483416080474854,
+      "learning_rate": 0.00017747064850692993,
+      "loss": 0.744560182094574,
+      "step": 3902
+    },
+    {
+      "epoch": 1.6843581445523195,
+      "grad_norm": 0.4636281430721283,
+      "learning_rate": 0.00017743958805290232,
+      "loss": 0.7506792545318604,
+      "step": 3904
+    },
+    {
+      "epoch": 1.6852211434735707,
+      "grad_norm": 0.43549975752830505,
+      "learning_rate": 0.00017740850892466719,
+      "loss": 0.7190370559692383,
+      "step": 3906
+    },
+    {
+      "epoch": 1.6860841423948218,
+      "grad_norm": 0.4514775276184082,
+      "learning_rate": 0.00017737741112971907,
+      "loss": 0.7768138647079468,
+      "step": 3908
+    },
+    {
+      "epoch": 1.6869471413160735,
+      "grad_norm": 0.45857131481170654,
+      "learning_rate": 0.0001773462946755571,
+      "loss": 0.7726560831069946,
+      "step": 3910
+    },
+    {
+      "epoch": 1.6878101402373247,
+      "grad_norm": 0.4479610323905945,
+      "learning_rate": 0.00017731515956968482,
+      "loss": 0.6987468600273132,
+      "step": 3912
+    },
+    {
+      "epoch": 1.688673139158576,
+      "grad_norm": 0.489849716424942,
+      "learning_rate": 0.00017728400581961036,
+      "loss": 0.6895362734794617,
+      "step": 3914
+    },
+    {
+      "epoch": 1.6895361380798275,
+      "grad_norm": 0.48648950457572937,
+      "learning_rate": 0.00017725283343284629,
+      "loss": 0.7460364699363708,
+      "step": 3916
+    },
+    {
+      "epoch": 1.6903991370010787,
+      "grad_norm": 0.5052891969680786,
+      "learning_rate": 0.0001772216424169097,
+      "loss": 0.7300586104393005,
+      "step": 3918
+    },
+    {
+      "epoch": 1.69126213592233,
+      "grad_norm": 0.48179247975349426,
+      "learning_rate": 0.00017719043277932215,
+      "loss": 0.7635855674743652,
+      "step": 3920
+    },
+    {
+      "epoch": 1.6921251348435815,
+      "grad_norm": 0.5296869277954102,
+      "learning_rate": 0.00017715920452760972,
+      "loss": 0.7760766744613647,
+      "step": 3922
+    },
+    {
+      "epoch": 1.6929881337648327,
+      "grad_norm": 0.5226309895515442,
+      "learning_rate": 0.00017712795766930298,
+      "loss": 0.798885703086853,
+      "step": 3924
+    },
+    {
+      "epoch": 1.6938511326860841,
+      "grad_norm": 0.3812384605407715,
+      "learning_rate": 0.0001770966922119369,
+      "loss": 0.7614596486091614,
+      "step": 3926
+    },
+    {
+      "epoch": 1.6947141316073355,
+      "grad_norm": 0.4084458649158478,
+      "learning_rate": 0.00017706540816305103,
+      "loss": 0.7634122967720032,
+      "step": 3928
+    },
+    {
+      "epoch": 1.6955771305285867,
+      "grad_norm": 0.49413034319877625,
+      "learning_rate": 0.00017703410553018944,
+      "loss": 0.7364476323127747,
+      "step": 3930
+    },
+    {
+      "epoch": 1.6964401294498384,
+      "grad_norm": 0.4119735658168793,
+      "learning_rate": 0.00017700278432090057,
+      "loss": 0.6874673366546631,
+      "step": 3932
+    },
+    {
+      "epoch": 1.6973031283710895,
+      "grad_norm": 0.5013890266418457,
+      "learning_rate": 0.00017697144454273736,
+      "loss": 0.7503598928451538,
+      "step": 3934
+    },
+    {
+      "epoch": 1.6981661272923407,
+      "grad_norm": 0.4563339054584503,
+      "learning_rate": 0.0001769400862032573,
+      "loss": 0.7193819880485535,
+      "step": 3936
+    },
+    {
+      "epoch": 1.6990291262135924,
+      "grad_norm": 0.4373779892921448,
+      "learning_rate": 0.00017690870931002232,
+      "loss": 0.7516534328460693,
+      "step": 3938
+    },
+    {
+      "epoch": 1.6998921251348436,
+      "grad_norm": 0.40220266580581665,
+      "learning_rate": 0.0001768773138705988,
+      "loss": 0.7319802045822144,
+      "step": 3940
+    },
+    {
+      "epoch": 1.700755124056095,
+      "grad_norm": 0.42924389243125916,
+      "learning_rate": 0.00017684589989255757,
+      "loss": 0.6950404644012451,
+      "step": 3942
+    },
+    {
+      "epoch": 1.7016181229773464,
+      "grad_norm": 0.4453158378601074,
+      "learning_rate": 0.00017681446738347404,
+      "loss": 0.697744607925415,
+      "step": 3944
+    },
+    {
+      "epoch": 1.7024811218985976,
+      "grad_norm": 0.4532380998134613,
+      "learning_rate": 0.00017678301635092795,
+      "loss": 0.6951707601547241,
+      "step": 3946
+    },
+    {
+      "epoch": 1.703344120819849,
+      "grad_norm": 0.4668843448162079,
+      "learning_rate": 0.00017675154680250361,
+      "loss": 0.781558096408844,
+      "step": 3948
+    },
+    {
+      "epoch": 1.7042071197411004,
+      "grad_norm": 0.48179176449775696,
+      "learning_rate": 0.00017672005874578978,
+      "loss": 0.7811654806137085,
+      "step": 3950
+    },
+    {
+      "epoch": 1.7050701186623516,
+      "grad_norm": 0.40447115898132324,
+      "learning_rate": 0.00017668855218837962,
+      "loss": 0.7350773215293884,
+      "step": 3952
+    },
+    {
+      "epoch": 1.705933117583603,
+      "grad_norm": 0.45968949794769287,
+      "learning_rate": 0.00017665702713787082,
+      "loss": 0.7492660284042358,
+      "step": 3954
+    },
+    {
+      "epoch": 1.7067961165048544,
+      "grad_norm": 0.5223715901374817,
+      "learning_rate": 0.0001766254836018655,
+      "loss": 0.7472123503684998,
+      "step": 3956
+    },
+    {
+      "epoch": 1.7076591154261056,
+      "grad_norm": 0.4571165144443512,
+      "learning_rate": 0.00017659392158797023,
+      "loss": 0.7836515307426453,
+      "step": 3958
+    },
+    {
+      "epoch": 1.708522114347357,
+      "grad_norm": 0.4370459318161011,
+      "learning_rate": 0.00017656234110379607,
+      "loss": 0.7453757524490356,
+      "step": 3960
+    },
+    {
+      "epoch": 1.7093851132686084,
+      "grad_norm": 0.4259219467639923,
+      "learning_rate": 0.0001765307421569585,
+      "loss": 0.7094024419784546,
+      "step": 3962
+    },
+    {
+      "epoch": 1.7102481121898596,
+      "grad_norm": 0.41195449233055115,
+      "learning_rate": 0.00017649912475507744,
+      "loss": 0.7037264108657837,
+      "step": 3964
+    },
+    {
+      "epoch": 1.7111111111111112,
+      "grad_norm": 0.40624237060546875,
+      "learning_rate": 0.0001764674889057773,
+      "loss": 0.7216715216636658,
+      "step": 3966
+    },
+    {
+      "epoch": 1.7119741100323624,
+      "grad_norm": 0.46490001678466797,
+      "learning_rate": 0.00017643583461668695,
+      "loss": 0.7317749261856079,
+      "step": 3968
+    },
+    {
+      "epoch": 1.7128371089536139,
+      "grad_norm": 0.4935937821865082,
+      "learning_rate": 0.00017640416189543964,
+      "loss": 0.7064663767814636,
+      "step": 3970
+    },
+    {
+      "epoch": 1.7137001078748653,
+      "grad_norm": 0.454501211643219,
+      "learning_rate": 0.00017637247074967315,
+      "loss": 0.6983333826065063,
+      "step": 3972
+    },
+    {
+      "epoch": 1.7145631067961165,
+      "grad_norm": 0.4357846975326538,
+      "learning_rate": 0.00017634076118702962,
+      "loss": 0.7516914010047913,
+      "step": 3974
+    },
+    {
+      "epoch": 1.7154261057173679,
+      "grad_norm": 0.421758234500885,
+      "learning_rate": 0.00017630903321515565,
+      "loss": 0.7914417386054993,
+      "step": 3976
+    },
+    {
+      "epoch": 1.7162891046386193,
+      "grad_norm": 0.4549725353717804,
+      "learning_rate": 0.00017627728684170235,
+      "loss": 0.7100850343704224,
+      "step": 3978
+    },
+    {
+      "epoch": 1.7171521035598705,
+      "grad_norm": 0.4313303530216217,
+      "learning_rate": 0.00017624552207432518,
+      "loss": 0.7711127400398254,
+      "step": 3980
+    },
+    {
+      "epoch": 1.7180151024811219,
+      "grad_norm": 0.46351364254951477,
+      "learning_rate": 0.00017621373892068407,
+      "loss": 0.681434690952301,
+      "step": 3982
+    },
+    {
+      "epoch": 1.7188781014023733,
+      "grad_norm": 0.5010084509849548,
+      "learning_rate": 0.0001761819373884434,
+      "loss": 0.7418093681335449,
+      "step": 3984
+    },
+    {
+      "epoch": 1.7197411003236245,
+      "grad_norm": 0.4252820909023285,
+      "learning_rate": 0.00017615011748527194,
+      "loss": 0.7767686247825623,
+      "step": 3986
+    },
+    {
+      "epoch": 1.720604099244876,
+      "grad_norm": 0.48956605792045593,
+      "learning_rate": 0.00017611827921884296,
+      "loss": 0.7049045562744141,
+      "step": 3988
+    },
+    {
+      "epoch": 1.7214670981661273,
+      "grad_norm": 0.42927032709121704,
+      "learning_rate": 0.00017608642259683407,
+      "loss": 0.7224108576774597,
+      "step": 3990
+    },
+    {
+      "epoch": 1.7223300970873785,
+      "grad_norm": 0.49601903557777405,
+      "learning_rate": 0.0001760545476269274,
+      "loss": 0.7203757166862488,
+      "step": 3992
+    },
+    {
+      "epoch": 1.7231930960086301,
+      "grad_norm": 0.38675686717033386,
+      "learning_rate": 0.0001760226543168094,
+      "loss": 0.6614230871200562,
+      "step": 3994
+    },
+    {
+      "epoch": 1.7240560949298813,
+      "grad_norm": 0.4299238622188568,
+      "learning_rate": 0.00017599074267417105,
+      "loss": 0.7201424837112427,
+      "step": 3996
+    },
+    {
+      "epoch": 1.7249190938511327,
+      "grad_norm": 0.43249231576919556,
+      "learning_rate": 0.00017595881270670763,
+      "loss": 0.7156208753585815,
+      "step": 3998
+    },
+    {
+      "epoch": 1.7257820927723841,
+      "grad_norm": 0.426278680562973,
+      "learning_rate": 0.00017592686442211898,
+      "loss": 0.7258728742599487,
+      "step": 4000
+    },
+    {
+      "epoch": 1.7257820927723841,
+      "eval_loss": 0.7843562960624695,
+      "eval_runtime": 657.9206,
+      "eval_samples_per_second": 3.131,
+      "eval_steps_per_second": 3.131,
+      "step": 4000
+    },
+    {
+      "epoch": 1.7266450916936353,
+      "grad_norm": 0.4646218419075012,
+      "learning_rate": 0.00017589489782810923,
+      "loss": 0.7290486097335815,
+      "step": 4002
+    },
+    {
+      "epoch": 1.7275080906148867,
+      "grad_norm": 0.4184021055698395,
+      "learning_rate": 0.00017586291293238704,
+      "loss": 0.7124513387680054,
+      "step": 4004
+    },
+    {
+      "epoch": 1.7283710895361382,
+      "grad_norm": 0.4271237850189209,
+      "learning_rate": 0.00017583090974266537,
+      "loss": 0.74180006980896,
+      "step": 4006
+    },
+    {
+      "epoch": 1.7292340884573894,
+      "grad_norm": 0.41022035479545593,
+      "learning_rate": 0.00017579888826666165,
+      "loss": 0.6774834394454956,
+      "step": 4008
+    },
+    {
+      "epoch": 1.7300970873786408,
+      "grad_norm": 0.5100602507591248,
+      "learning_rate": 0.00017576684851209774,
+      "loss": 0.7206428050994873,
+      "step": 4010
+    },
+    {
+      "epoch": 1.7309600862998922,
+      "grad_norm": 0.43499550223350525,
+      "learning_rate": 0.00017573479048669987,
+      "loss": 0.6632843613624573,
+      "step": 4012
+    },
+    {
+      "epoch": 1.7318230852211434,
+      "grad_norm": 0.4398936927318573,
+      "learning_rate": 0.0001757027141981987,
+      "loss": 0.7945244312286377,
+      "step": 4014
+    },
+    {
+      "epoch": 1.7326860841423948,
+      "grad_norm": 0.5156806111335754,
+      "learning_rate": 0.00017567061965432926,
+      "loss": 0.7410688996315002,
+      "step": 4016
+    },
+    {
+      "epoch": 1.7335490830636462,
+      "grad_norm": 0.45140013098716736,
+      "learning_rate": 0.00017563850686283102,
+      "loss": 0.7249122858047485,
+      "step": 4018
+    },
+    {
+      "epoch": 1.7344120819848974,
+      "grad_norm": 0.4980209469795227,
+      "learning_rate": 0.0001756063758314478,
+      "loss": 0.7548064589500427,
+      "step": 4020
+    },
+    {
+      "epoch": 1.735275080906149,
+      "grad_norm": 0.426337867975235,
+      "learning_rate": 0.00017557422656792792,
+      "loss": 0.6763073205947876,
+      "step": 4022
+    },
+    {
+      "epoch": 1.7361380798274002,
+      "grad_norm": 0.4775279760360718,
+      "learning_rate": 0.000175542059080024,
+      "loss": 0.8444951176643372,
+      "step": 4024
+    },
+    {
+      "epoch": 1.7370010787486516,
+      "grad_norm": 0.4614261984825134,
+      "learning_rate": 0.00017550987337549304,
+      "loss": 0.7031195163726807,
+      "step": 4026
+    },
+    {
+      "epoch": 1.737864077669903,
+      "grad_norm": 0.4657931327819824,
+      "learning_rate": 0.00017547766946209654,
+      "loss": 0.7708158493041992,
+      "step": 4028
+    },
+    {
+      "epoch": 1.7387270765911542,
+      "grad_norm": 0.4373331665992737,
+      "learning_rate": 0.0001754454473476003,
+      "loss": 0.7013334035873413,
+      "step": 4030
+    },
+    {
+      "epoch": 1.7395900755124056,
+      "grad_norm": 0.5230216383934021,
+      "learning_rate": 0.00017541320703977453,
+      "loss": 0.7644510865211487,
+      "step": 4032
+    },
+    {
+      "epoch": 1.740453074433657,
+      "grad_norm": 0.4254145920276642,
+      "learning_rate": 0.00017538094854639387,
+      "loss": 0.7311883568763733,
+      "step": 4034
+    },
+    {
+      "epoch": 1.7413160733549082,
+      "grad_norm": 0.40677928924560547,
+      "learning_rate": 0.00017534867187523728,
+      "loss": 0.8042954802513123,
+      "step": 4036
+    },
+    {
+      "epoch": 1.7421790722761596,
+      "grad_norm": 0.4729449450969696,
+      "learning_rate": 0.00017531637703408815,
+      "loss": 0.7260869741439819,
+      "step": 4038
+    },
+    {
+      "epoch": 1.743042071197411,
+      "grad_norm": 0.5013999342918396,
+      "learning_rate": 0.0001752840640307342,
+      "loss": 0.7968364953994751,
+      "step": 4040
+    },
+    {
+      "epoch": 1.7439050701186622,
+      "grad_norm": 0.50171959400177,
+      "learning_rate": 0.0001752517328729676,
+      "loss": 0.6834843754768372,
+      "step": 4042
+    },
+    {
+      "epoch": 1.7447680690399137,
+      "grad_norm": 0.45370912551879883,
+      "learning_rate": 0.00017521938356858488,
+      "loss": 0.7420654296875,
+      "step": 4044
+    },
+    {
+      "epoch": 1.745631067961165,
+      "grad_norm": 0.43417057394981384,
+      "learning_rate": 0.00017518701612538685,
+      "loss": 0.721342921257019,
+      "step": 4046
+    },
+    {
+      "epoch": 1.7464940668824163,
+      "grad_norm": 0.3888097405433655,
+      "learning_rate": 0.00017515463055117885,
+      "loss": 0.6757205128669739,
+      "step": 4048
+    },
+    {
+      "epoch": 1.747357065803668,
+      "grad_norm": 0.3910084068775177,
+      "learning_rate": 0.00017512222685377055,
+      "loss": 0.682235062122345,
+      "step": 4050
+    },
+    {
+      "epoch": 1.748220064724919,
+      "grad_norm": 0.4092451333999634,
+      "learning_rate": 0.0001750898050409758,
+      "loss": 0.6801605224609375,
+      "step": 4052
+    },
+    {
+      "epoch": 1.7490830636461703,
+      "grad_norm": 0.464478075504303,
+      "learning_rate": 0.00017505736512061316,
+      "loss": 0.7368552684783936,
+      "step": 4054
+    },
+    {
+      "epoch": 1.749946062567422,
+      "grad_norm": 0.47949129343032837,
+      "learning_rate": 0.00017502490710050522,
+      "loss": 0.7422438263893127,
+      "step": 4056
+    },
+    {
+      "epoch": 1.750809061488673,
+      "grad_norm": 0.47410422563552856,
+      "learning_rate": 0.00017499243098847918,
+      "loss": 0.7370736598968506,
+      "step": 4058
+    },
+    {
+      "epoch": 1.7516720604099245,
+      "grad_norm": 0.3986700177192688,
+      "learning_rate": 0.00017495993679236645,
+      "loss": 0.6773675680160522,
+      "step": 4060
+    },
+    {
+      "epoch": 1.752535059331176,
+      "grad_norm": 0.41113027930259705,
+      "learning_rate": 0.0001749274245200029,
+      "loss": 0.7170975208282471,
+      "step": 4062
+    },
+    {
+      "epoch": 1.7533980582524271,
+      "grad_norm": 0.43275657296180725,
+      "learning_rate": 0.0001748948941792287,
+      "loss": 0.6957781314849854,
+      "step": 4064
+    },
+    {
+      "epoch": 1.7542610571736785,
+      "grad_norm": 0.4488718509674072,
+      "learning_rate": 0.00017486234577788838,
+      "loss": 0.7540420889854431,
+      "step": 4066
+    },
+    {
+      "epoch": 1.75512405609493,
+      "grad_norm": 0.44178634881973267,
+      "learning_rate": 0.00017482977932383088,
+      "loss": 0.7581563591957092,
+      "step": 4068
+    },
+    {
+      "epoch": 1.7559870550161811,
+      "grad_norm": 0.4245910942554474,
+      "learning_rate": 0.0001747971948249094,
+      "loss": 0.7012783885002136,
+      "step": 4070
+    },
+    {
+      "epoch": 1.7568500539374325,
+      "grad_norm": 0.4418242573738098,
+      "learning_rate": 0.0001747645922889816,
+      "loss": 0.6657902002334595,
+      "step": 4072
+    },
+    {
+      "epoch": 1.757713052858684,
+      "grad_norm": 0.4621461033821106,
+      "learning_rate": 0.00017473197172390942,
+      "loss": 0.6813042163848877,
+      "step": 4074
+    },
+    {
+      "epoch": 1.7585760517799351,
+      "grad_norm": 0.47244367003440857,
+      "learning_rate": 0.00017469933313755913,
+      "loss": 0.7490677237510681,
+      "step": 4076
+    },
+    {
+      "epoch": 1.7594390507011868,
+      "grad_norm": 0.43918749690055847,
+      "learning_rate": 0.00017466667653780142,
+      "loss": 0.7485169172286987,
+      "step": 4078
+    },
+    {
+      "epoch": 1.760302049622438,
+      "grad_norm": 0.45456430315971375,
+      "learning_rate": 0.00017463400193251126,
+      "loss": 0.8234745264053345,
+      "step": 4080
+    },
+    {
+      "epoch": 1.7611650485436892,
+      "grad_norm": 0.47970378398895264,
+      "learning_rate": 0.000174601309329568,
+      "loss": 0.8200880289077759,
+      "step": 4082
+    },
+    {
+      "epoch": 1.7620280474649408,
+      "grad_norm": 0.4489441215991974,
+      "learning_rate": 0.00017456859873685523,
+      "loss": 0.7460210919380188,
+      "step": 4084
+    },
+    {
+      "epoch": 1.762891046386192,
+      "grad_norm": 0.44073280692100525,
+      "learning_rate": 0.0001745358701622611,
+      "loss": 0.7544209957122803,
+      "step": 4086
+    },
+    {
+      "epoch": 1.7637540453074434,
+      "grad_norm": 0.5178254842758179,
+      "learning_rate": 0.00017450312361367787,
+      "loss": 0.7942423820495605,
+      "step": 4088
+    },
+    {
+      "epoch": 1.7646170442286948,
+      "grad_norm": 0.4069359600543976,
+      "learning_rate": 0.00017447035909900222,
+      "loss": 0.6761540174484253,
+      "step": 4090
+    },
+    {
+      "epoch": 1.765480043149946,
+      "grad_norm": 0.42108529806137085,
+      "learning_rate": 0.0001744375766261352,
+      "loss": 0.6959407329559326,
+      "step": 4092
+    },
+    {
+      "epoch": 1.7663430420711974,
+      "grad_norm": 0.4824271500110626,
+      "learning_rate": 0.00017440477620298217,
+      "loss": 0.8067643642425537,
+      "step": 4094
+    },
+    {
+      "epoch": 1.7672060409924488,
+      "grad_norm": 0.4846031367778778,
+      "learning_rate": 0.00017437195783745276,
+      "loss": 0.8048238754272461,
+      "step": 4096
+    },
+    {
+      "epoch": 1.7680690399137,
+      "grad_norm": 0.47893181443214417,
+      "learning_rate": 0.00017433912153746098,
+      "loss": 0.7465305328369141,
+      "step": 4098
+    },
+    {
+      "epoch": 1.7689320388349514,
+      "grad_norm": 0.4115507900714874,
+      "learning_rate": 0.00017430626731092515,
+      "loss": 0.7086948752403259,
+      "step": 4100
+    },
+    {
+      "epoch": 1.7689320388349514,
+      "eval_loss": 0.7808024883270264,
+      "eval_runtime": 666.5954,
+      "eval_samples_per_second": 3.09,
+      "eval_steps_per_second": 3.09,
+      "step": 4100
+    },
+    {
+      "epoch": 1.7697950377562028,
+      "grad_norm": 0.40175846219062805,
+      "learning_rate": 0.00017427339516576796,
+      "loss": 0.6837684512138367,
+      "step": 4102
+    },
+    {
+      "epoch": 1.770658036677454,
+      "grad_norm": 0.4699510633945465,
+      "learning_rate": 0.00017424050510991634,
+      "loss": 0.7253594994544983,
+      "step": 4104
+    },
+    {
+      "epoch": 1.7715210355987057,
+      "grad_norm": 0.5029735565185547,
+      "learning_rate": 0.0001742075971513016,
+      "loss": 0.7273471355438232,
+      "step": 4106
+    },
+    {
+      "epoch": 1.7723840345199569,
+      "grad_norm": 0.46295008063316345,
+      "learning_rate": 0.00017417467129785937,
+      "loss": 0.7040302157402039,
+      "step": 4108
+    },
+    {
+      "epoch": 1.773247033441208,
+      "grad_norm": 0.43181541562080383,
+      "learning_rate": 0.0001741417275575295,
+      "loss": 0.72527015209198,
+      "step": 4110
+    },
+    {
+      "epoch": 1.7741100323624597,
+      "grad_norm": 0.40259307622909546,
+      "learning_rate": 0.00017410876593825625,
+      "loss": 0.6736238598823547,
+      "step": 4112
+    },
+    {
+      "epoch": 1.7749730312837109,
+      "grad_norm": 0.44186654686927795,
+      "learning_rate": 0.00017407578644798818,
+      "loss": 0.6924970746040344,
+      "step": 4114
+    },
+    {
+      "epoch": 1.7758360302049623,
+      "grad_norm": 0.5186018347740173,
+      "learning_rate": 0.00017404278909467815,
+      "loss": 0.7088955640792847,
+      "step": 4116
+    },
+    {
+      "epoch": 1.7766990291262137,
+      "grad_norm": 0.45042574405670166,
+      "learning_rate": 0.00017400977388628332,
+      "loss": 0.6548104286193848,
+      "step": 4118
+    },
+    {
+      "epoch": 1.7775620280474649,
+      "grad_norm": 0.4164215326309204,
+      "learning_rate": 0.00017397674083076517,
+      "loss": 0.6818945407867432,
+      "step": 4120
+    },
+    {
+      "epoch": 1.7784250269687163,
+      "grad_norm": 0.4045083522796631,
+      "learning_rate": 0.00017394368993608943,
+      "loss": 0.7920825481414795,
+      "step": 4122
+    },
+    {
+      "epoch": 1.7792880258899677,
+      "grad_norm": 0.4170040190219879,
+      "learning_rate": 0.0001739106212102262,
+      "loss": 0.7774871587753296,
+      "step": 4124
+    },
+    {
+      "epoch": 1.780151024811219,
+      "grad_norm": 0.4969266653060913,
+      "learning_rate": 0.00017387753466114987,
+      "loss": 0.7776943445205688,
+      "step": 4126
+    },
+    {
+      "epoch": 1.7810140237324703,
+      "grad_norm": 0.36906328797340393,
+      "learning_rate": 0.00017384443029683913,
+      "loss": 0.6679043769836426,
+      "step": 4128
+    },
+    {
+      "epoch": 1.7818770226537217,
+      "grad_norm": 0.476610392332077,
+      "learning_rate": 0.00017381130812527687,
+      "loss": 0.7691782712936401,
+      "step": 4130
+    },
+    {
+      "epoch": 1.782740021574973,
+      "grad_norm": 0.45970338582992554,
+      "learning_rate": 0.0001737781681544504,
+      "loss": 0.7127588987350464,
+      "step": 4132
+    },
+    {
+      "epoch": 1.7836030204962245,
+      "grad_norm": 0.47383829951286316,
+      "learning_rate": 0.00017374501039235128,
+      "loss": 0.7561655044555664,
+      "step": 4134
+    },
+    {
+      "epoch": 1.7844660194174757,
+      "grad_norm": 0.40685102343559265,
+      "learning_rate": 0.00017371183484697538,
+      "loss": 0.739709734916687,
+      "step": 4136
+    },
+    {
+      "epoch": 1.785329018338727,
+      "grad_norm": 0.4961703419685364,
+      "learning_rate": 0.0001736786415263228,
+      "loss": 0.8365469574928284,
+      "step": 4138
+    },
+    {
+      "epoch": 1.7861920172599786,
+      "grad_norm": 0.44277071952819824,
+      "learning_rate": 0.00017364543043839792,
+      "loss": 0.758213996887207,
+      "step": 4140
+    },
+    {
+      "epoch": 1.7870550161812297,
+      "grad_norm": 0.4293559491634369,
+      "learning_rate": 0.00017361220159120948,
+      "loss": 0.6730729341506958,
+      "step": 4142
+    },
+    {
+      "epoch": 1.7879180151024812,
+      "grad_norm": 0.4188339114189148,
+      "learning_rate": 0.00017357895499277052,
+      "loss": 0.8141124248504639,
+      "step": 4144
+    },
+    {
+      "epoch": 1.7887810140237326,
+      "grad_norm": 0.41425400972366333,
+      "learning_rate": 0.0001735456906510982,
+      "loss": 0.7831918597221375,
+      "step": 4146
+    },
+    {
+      "epoch": 1.7896440129449838,
+      "grad_norm": 0.4522942304611206,
+      "learning_rate": 0.0001735124085742142,
+      "loss": 0.6969084739685059,
+      "step": 4148
+    },
+    {
+      "epoch": 1.7905070118662352,
+      "grad_norm": 0.5915003418922424,
+      "learning_rate": 0.00017347910877014422,
+      "loss": 0.6732504963874817,
+      "step": 4150
+    },
+    {
+      "epoch": 1.7913700107874866,
+      "grad_norm": 0.41376325488090515,
+      "learning_rate": 0.0001734457912469184,
+      "loss": 0.7403483390808105,
+      "step": 4152
+    },
+    {
+      "epoch": 1.7922330097087378,
+      "grad_norm": 0.3962151110172272,
+      "learning_rate": 0.00017341245601257111,
+      "loss": 0.6874727606773376,
+      "step": 4154
+    },
+    {
+      "epoch": 1.7930960086299892,
+      "grad_norm": 0.4639807939529419,
+      "learning_rate": 0.00017337910307514101,
+      "loss": 0.6919097900390625,
+      "step": 4156
+    },
+    {
+      "epoch": 1.7939590075512406,
+      "grad_norm": 0.40313324332237244,
+      "learning_rate": 0.000173345732442671,
+      "loss": 0.7562543749809265,
+      "step": 4158
+    },
+    {
+      "epoch": 1.7948220064724918,
+      "grad_norm": 0.4477533996105194,
+      "learning_rate": 0.0001733123441232083,
+      "loss": 0.729914128780365,
+      "step": 4160
+    },
+    {
+      "epoch": 1.7956850053937432,
+      "grad_norm": 0.5002303123474121,
+      "learning_rate": 0.00017327893812480426,
+      "loss": 0.8119242787361145,
+      "step": 4162
+    },
+    {
+      "epoch": 1.7965480043149946,
+      "grad_norm": 0.464579313993454,
+      "learning_rate": 0.00017324551445551466,
+      "loss": 0.6835103034973145,
+      "step": 4164
+    },
+    {
+      "epoch": 1.7974110032362458,
+      "grad_norm": 0.3973700702190399,
+      "learning_rate": 0.0001732120731233994,
+      "loss": 0.7308543920516968,
+      "step": 4166
+    },
+    {
+      "epoch": 1.7982740021574974,
+      "grad_norm": 0.3675004839897156,
+      "learning_rate": 0.00017317861413652277,
+      "loss": 0.6357728838920593,
+      "step": 4168
+    },
+    {
+      "epoch": 1.7991370010787486,
+      "grad_norm": 0.5020666718482971,
+      "learning_rate": 0.00017314513750295323,
+      "loss": 0.7257087230682373,
+      "step": 4170
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.43989744782447815,
+      "learning_rate": 0.00017311164323076354,
+      "loss": 0.6529711484909058,
+      "step": 4172
+    },
+    {
+      "epoch": 1.8008629989212515,
+      "grad_norm": 0.4717860221862793,
+      "learning_rate": 0.00017307813132803066,
+      "loss": 0.740652859210968,
+      "step": 4174
+    },
+    {
+      "epoch": 1.8017259978425026,
+      "grad_norm": 0.42297297716140747,
+      "learning_rate": 0.00017304460180283583,
+      "loss": 0.7142172455787659,
+      "step": 4176
+    },
+    {
+      "epoch": 1.802588996763754,
+      "grad_norm": 0.4779362976551056,
+      "learning_rate": 0.0001730110546632646,
+      "loss": 0.7233486175537109,
+      "step": 4178
+    },
+    {
+      "epoch": 1.8034519956850055,
+      "grad_norm": 0.38539960980415344,
+      "learning_rate": 0.00017297748991740663,
+      "loss": 0.7120639681816101,
+      "step": 4180
+    },
+    {
+      "epoch": 1.8043149946062567,
+      "grad_norm": 0.43327030539512634,
+      "learning_rate": 0.000172943907573356,
+      "loss": 0.7120950818061829,
+      "step": 4182
+    },
+    {
+      "epoch": 1.805177993527508,
+      "grad_norm": 0.48741552233695984,
+      "learning_rate": 0.00017291030763921087,
+      "loss": 0.7957805395126343,
+      "step": 4184
+    },
+    {
+      "epoch": 1.8060409924487595,
+      "grad_norm": 0.4763964116573334,
+      "learning_rate": 0.0001728766901230737,
+      "loss": 0.6962721943855286,
+      "step": 4186
+    },
+    {
+      "epoch": 1.8069039913700107,
+      "grad_norm": 0.4499688744544983,
+      "learning_rate": 0.00017284305503305128,
+      "loss": 0.6778126955032349,
+      "step": 4188
+    },
+    {
+      "epoch": 1.807766990291262,
+      "grad_norm": 0.46147263050079346,
+      "learning_rate": 0.00017280940237725451,
+      "loss": 0.7177738547325134,
+      "step": 4190
+    },
+    {
+      "epoch": 1.8086299892125135,
+      "grad_norm": 0.39121973514556885,
+      "learning_rate": 0.00017277573216379857,
+      "loss": 0.6445587277412415,
+      "step": 4192
+    },
+    {
+      "epoch": 1.8094929881337647,
+      "grad_norm": 0.44156384468078613,
+      "learning_rate": 0.0001727420444008029,
+      "loss": 0.8183205723762512,
+      "step": 4194
+    },
+    {
+      "epoch": 1.8103559870550163,
+      "grad_norm": 0.45122894644737244,
+      "learning_rate": 0.00017270833909639114,
+      "loss": 0.708315908908844,
+      "step": 4196
+    },
+    {
+      "epoch": 1.8112189859762675,
+      "grad_norm": 0.5312398672103882,
+      "learning_rate": 0.00017267461625869118,
+      "loss": 0.7654728293418884,
+      "step": 4198
+    },
+    {
+      "epoch": 1.812081984897519,
+      "grad_norm": 0.4401609003543854,
+      "learning_rate": 0.00017264087589583516,
+      "loss": 0.8182219862937927,
+      "step": 4200
+    },
+    {
+      "epoch": 1.812081984897519,
+      "eval_loss": 0.7768770456314087,
+      "eval_runtime": 664.5255,
+      "eval_samples_per_second": 3.1,
+      "eval_steps_per_second": 3.1,
+      "step": 4200
+    },
+    {
+      "epoch": 1.8129449838187703,
+      "grad_norm": 0.40371671319007874,
+      "learning_rate": 0.00017260711801595933,
+      "loss": 0.6492214202880859,
+      "step": 4202
+    },
+    {
+      "epoch": 1.8138079827400215,
+      "grad_norm": 0.4950125813484192,
+      "learning_rate": 0.00017257334262720436,
+      "loss": 0.7230119705200195,
+      "step": 4204
+    },
+    {
+      "epoch": 1.814670981661273,
+      "grad_norm": 0.4659440517425537,
+      "learning_rate": 0.00017253954973771494,
+      "loss": 0.7157304883003235,
+      "step": 4206
+    },
+    {
+      "epoch": 1.8155339805825244,
+      "grad_norm": 0.4222276508808136,
+      "learning_rate": 0.00017250573935564012,
+      "loss": 0.7163988351821899,
+      "step": 4208
+    },
+    {
+      "epoch": 1.8163969795037755,
+      "grad_norm": 0.4653847813606262,
+      "learning_rate": 0.0001724719114891331,
+      "loss": 0.8364236950874329,
+      "step": 4210
+    },
+    {
+      "epoch": 1.817259978425027,
+      "grad_norm": 0.42004603147506714,
+      "learning_rate": 0.00017243806614635133,
+      "loss": 0.7096951007843018,
+      "step": 4212
+    },
+    {
+      "epoch": 1.8181229773462784,
+      "grad_norm": 0.4078772962093353,
+      "learning_rate": 0.0001724042033354565,
+      "loss": 0.7669811248779297,
+      "step": 4214
+    },
+    {
+      "epoch": 1.8189859762675296,
+      "grad_norm": 0.540237307548523,
+      "learning_rate": 0.0001723703230646144,
+      "loss": 0.8241565823554993,
+      "step": 4216
+    },
+    {
+      "epoch": 1.819848975188781,
+      "grad_norm": 0.5155133008956909,
+      "learning_rate": 0.00017233642534199514,
+      "loss": 0.7156816720962524,
+      "step": 4218
+    },
+    {
+      "epoch": 1.8207119741100324,
+      "grad_norm": 0.41354167461395264,
+      "learning_rate": 0.000172302510175773,
+      "loss": 0.6945502161979675,
+      "step": 4220
+    },
+    {
+      "epoch": 1.8215749730312836,
+      "grad_norm": 0.4960228502750397,
+      "learning_rate": 0.00017226857757412652,
+      "loss": 0.790353536605835,
+      "step": 4222
+    },
+    {
+      "epoch": 1.8224379719525352,
+      "grad_norm": 0.4391328990459442,
+      "learning_rate": 0.00017223462754523833,
+      "loss": 0.7331936955451965,
+      "step": 4224
+    },
+    {
+      "epoch": 1.8233009708737864,
+      "grad_norm": 0.4315200448036194,
+      "learning_rate": 0.0001722006600972953,
+      "loss": 0.7099514603614807,
+      "step": 4226
+    },
+    {
+      "epoch": 1.8241639697950378,
+      "grad_norm": 0.4148513674736023,
+      "learning_rate": 0.0001721666752384886,
+      "loss": 0.7503170967102051,
+      "step": 4228
+    },
+    {
+      "epoch": 1.8250269687162892,
+      "grad_norm": 0.39631742238998413,
+      "learning_rate": 0.00017213267297701347,
+      "loss": 0.7042041420936584,
+      "step": 4230
+    },
+    {
+      "epoch": 1.8258899676375404,
+      "grad_norm": 0.4037681221961975,
+      "learning_rate": 0.00017209865332106948,
+      "loss": 0.6457626819610596,
+      "step": 4232
+    },
+    {
+      "epoch": 1.8267529665587918,
+      "grad_norm": 0.4731367230415344,
+      "learning_rate": 0.0001720646162788602,
+      "loss": 0.7379142045974731,
+      "step": 4234
+    },
+    {
+      "epoch": 1.8276159654800432,
+      "grad_norm": 0.48663607239723206,
+      "learning_rate": 0.0001720305618585936,
+      "loss": 0.7307448387145996,
+      "step": 4236
+    },
+    {
+      "epoch": 1.8284789644012944,
+      "grad_norm": 0.42846018075942993,
+      "learning_rate": 0.00017199649006848172,
+      "loss": 0.7429580688476562,
+      "step": 4238
+    },
+    {
+      "epoch": 1.8293419633225458,
+      "grad_norm": 0.4572913348674774,
+      "learning_rate": 0.00017196240091674086,
+      "loss": 0.8380557298660278,
+      "step": 4240
+    },
+    {
+      "epoch": 1.8302049622437973,
+      "grad_norm": 0.4150466322898865,
+      "learning_rate": 0.00017192829441159136,
+      "loss": 0.7590726613998413,
+      "step": 4242
+    },
+    {
+      "epoch": 1.8310679611650484,
+      "grad_norm": 0.5212832689285278,
+      "learning_rate": 0.00017189417056125795,
+      "loss": 0.6875066161155701,
+      "step": 4244
+    },
+    {
+      "epoch": 1.8319309600862999,
+      "grad_norm": 0.39897283911705017,
+      "learning_rate": 0.00017186002937396943,
+      "loss": 0.6904876828193665,
+      "step": 4246
+    },
+    {
+      "epoch": 1.8327939590075513,
+      "grad_norm": 0.47237759828567505,
+      "learning_rate": 0.00017182587085795876,
+      "loss": 0.729841947555542,
+      "step": 4248
+    },
+    {
+      "epoch": 1.8336569579288025,
+      "grad_norm": 0.3762347102165222,
+      "learning_rate": 0.00017179169502146312,
+      "loss": 0.6299530267715454,
+      "step": 4250
+    },
+    {
+      "epoch": 1.834519956850054,
+      "grad_norm": 0.47408151626586914,
+      "learning_rate": 0.00017175750187272386,
+      "loss": 0.7029539942741394,
+      "step": 4252
+    },
+    {
+      "epoch": 1.8353829557713053,
+      "grad_norm": 0.3598722219467163,
+      "learning_rate": 0.00017172329141998654,
+      "loss": 0.6389845609664917,
+      "step": 4254
+    },
+    {
+      "epoch": 1.8362459546925565,
+      "grad_norm": 0.4635334312915802,
+      "learning_rate": 0.00017168906367150076,
+      "loss": 0.687628984451294,
+      "step": 4256
+    },
+    {
+      "epoch": 1.837108953613808,
+      "grad_norm": 0.4610443115234375,
+      "learning_rate": 0.00017165481863552052,
+      "loss": 0.7720530033111572,
+      "step": 4258
+    },
+    {
+      "epoch": 1.8379719525350593,
+      "grad_norm": 0.4014928340911865,
+      "learning_rate": 0.00017162055632030375,
+      "loss": 0.7185879349708557,
+      "step": 4260
+    },
+    {
+      "epoch": 1.8388349514563107,
+      "grad_norm": 0.4805688261985779,
+      "learning_rate": 0.0001715862767341127,
+      "loss": 0.7026579976081848,
+      "step": 4262
+    },
+    {
+      "epoch": 1.8396979503775621,
+      "grad_norm": 0.42337459325790405,
+      "learning_rate": 0.00017155197988521375,
+      "loss": 0.698957622051239,
+      "step": 4264
+    },
+    {
+      "epoch": 1.8405609492988133,
+      "grad_norm": 0.41200968623161316,
+      "learning_rate": 0.00017151766578187737,
+      "loss": 0.6705408096313477,
+      "step": 4266
+    },
+    {
+      "epoch": 1.8414239482200647,
+      "grad_norm": 0.4329065978527069,
+      "learning_rate": 0.0001714833344323783,
+      "loss": 0.6862514615058899,
+      "step": 4268
+    },
+    {
+      "epoch": 1.8422869471413161,
+      "grad_norm": 0.5093284845352173,
+      "learning_rate": 0.0001714489858449954,
+      "loss": 0.7468723654747009,
+      "step": 4270
+    },
+    {
+      "epoch": 1.8431499460625673,
+      "grad_norm": 0.4891190230846405,
+      "learning_rate": 0.00017141462002801162,
+      "loss": 0.7447264194488525,
+      "step": 4272
+    },
+    {
+      "epoch": 1.8440129449838187,
+      "grad_norm": 0.4578206241130829,
+      "learning_rate": 0.0001713802369897142,
+      "loss": 0.6918519735336304,
+      "step": 4274
+    },
+    {
+      "epoch": 1.8448759439050701,
+      "grad_norm": 0.46908026933670044,
+      "learning_rate": 0.00017134583673839439,
+      "loss": 0.6955613493919373,
+      "step": 4276
+    },
+    {
+      "epoch": 1.8457389428263213,
+      "grad_norm": 0.48165956139564514,
+      "learning_rate": 0.0001713114192823477,
+      "loss": 0.7485507130622864,
+      "step": 4278
+    },
+    {
+      "epoch": 1.846601941747573,
+      "grad_norm": 0.4701056480407715,
+      "learning_rate": 0.00017127698462987367,
+      "loss": 0.799237847328186,
+      "step": 4280
+    },
+    {
+      "epoch": 1.8474649406688242,
+      "grad_norm": 0.3776571452617645,
+      "learning_rate": 0.00017124253278927616,
+      "loss": 0.6577883958816528,
+      "step": 4282
+    },
+    {
+      "epoch": 1.8483279395900754,
+      "grad_norm": 0.4055720567703247,
+      "learning_rate": 0.00017120806376886302,
+      "loss": 0.7250326871871948,
+      "step": 4284
+    },
+    {
+      "epoch": 1.849190938511327,
+      "grad_norm": 0.4074631333351135,
+      "learning_rate": 0.00017117357757694634,
+      "loss": 0.7517069578170776,
+      "step": 4286
+    },
+    {
+      "epoch": 1.8500539374325782,
+      "grad_norm": 0.4045642614364624,
+      "learning_rate": 0.00017113907422184224,
+      "loss": 0.6158990859985352,
+      "step": 4288
+    },
+    {
+      "epoch": 1.8509169363538296,
+      "grad_norm": 0.4492259621620178,
+      "learning_rate": 0.0001711045537118711,
+      "loss": 0.7236425876617432,
+      "step": 4290
+    },
+    {
+      "epoch": 1.851779935275081,
+      "grad_norm": 0.4565478265285492,
+      "learning_rate": 0.00017107001605535737,
+      "loss": 0.7718945741653442,
+      "step": 4292
+    },
+    {
+      "epoch": 1.8526429341963322,
+      "grad_norm": 0.42028820514678955,
+      "learning_rate": 0.00017103546126062967,
+      "loss": 0.7165213227272034,
+      "step": 4294
+    },
+    {
+      "epoch": 1.8535059331175836,
+      "grad_norm": 0.43695729970932007,
+      "learning_rate": 0.0001710008893360207,
+      "loss": 0.6750491857528687,
+      "step": 4296
+    },
+    {
+      "epoch": 1.854368932038835,
+      "grad_norm": 0.4253435730934143,
+      "learning_rate": 0.00017096630028986734,
+      "loss": 0.7486634850502014,
+      "step": 4298
+    },
+    {
+      "epoch": 1.8552319309600862,
+      "grad_norm": 0.4334436058998108,
+      "learning_rate": 0.0001709316941305106,
+      "loss": 0.6766000986099243,
+      "step": 4300
+    },
+    {
+      "epoch": 1.8552319309600862,
+      "eval_loss": 0.7747175693511963,
+      "eval_runtime": 654.7294,
+      "eval_samples_per_second": 3.146,
+      "eval_steps_per_second": 3.146,
+      "step": 4300
+    },
+    {
+      "epoch": 1.8560949298813376,
+      "grad_norm": 0.4382997453212738,
+      "learning_rate": 0.00017089707086629557,
+      "loss": 0.6958843469619751,
+      "step": 4302
+    },
+    {
+      "epoch": 1.856957928802589,
+      "grad_norm": 0.4810338616371155,
+      "learning_rate": 0.0001708624305055715,
+      "loss": 0.7561178803443909,
+      "step": 4304
+    },
+    {
+      "epoch": 1.8578209277238402,
+      "grad_norm": 0.47984233498573303,
+      "learning_rate": 0.00017082777305669176,
+      "loss": 0.8058216571807861,
+      "step": 4306
+    },
+    {
+      "epoch": 1.8586839266450919,
+      "grad_norm": 0.4484567642211914,
+      "learning_rate": 0.00017079309852801385,
+      "loss": 0.7262290120124817,
+      "step": 4308
+    },
+    {
+      "epoch": 1.859546925566343,
+      "grad_norm": 0.41116195917129517,
+      "learning_rate": 0.00017075840692789938,
+      "loss": 0.7000281810760498,
+      "step": 4310
+    },
+    {
+      "epoch": 1.8604099244875942,
+      "grad_norm": 0.4403190016746521,
+      "learning_rate": 0.00017072369826471407,
+      "loss": 0.7535883188247681,
+      "step": 4312
+    },
+    {
+      "epoch": 1.8612729234088459,
+      "grad_norm": 0.43298110365867615,
+      "learning_rate": 0.0001706889725468277,
+      "loss": 0.792589008808136,
+      "step": 4314
+    },
+    {
+      "epoch": 1.862135922330097,
+      "grad_norm": 0.5362349152565002,
+      "learning_rate": 0.0001706542297826143,
+      "loss": 0.7327062487602234,
+      "step": 4316
+    },
+    {
+      "epoch": 1.8629989212513485,
+      "grad_norm": 0.5060083270072937,
+      "learning_rate": 0.00017061946998045188,
+      "loss": 0.7859953045845032,
+      "step": 4318
+    },
+    {
+      "epoch": 1.8638619201725999,
+      "grad_norm": 0.4489237368106842,
+      "learning_rate": 0.00017058469314872266,
+      "loss": 0.702696681022644,
+      "step": 4320
+    },
+    {
+      "epoch": 1.864724919093851,
+      "grad_norm": 0.4355533719062805,
+      "learning_rate": 0.00017054989929581288,
+      "loss": 0.7487955093383789,
+      "step": 4322
+    },
+    {
+      "epoch": 1.8655879180151025,
+      "grad_norm": 0.413460910320282,
+      "learning_rate": 0.0001705150884301129,
+      "loss": 0.6919105648994446,
+      "step": 4324
+    },
+    {
+      "epoch": 1.866450916936354,
+      "grad_norm": 0.4663568139076233,
+      "learning_rate": 0.00017048026056001723,
+      "loss": 0.6864221096038818,
+      "step": 4326
+    },
+    {
+      "epoch": 1.867313915857605,
+      "grad_norm": 0.36837631464004517,
+      "learning_rate": 0.00017044541569392446,
+      "loss": 0.6459081172943115,
+      "step": 4328
+    },
+    {
+      "epoch": 1.8681769147788565,
+      "grad_norm": 0.386055052280426,
+      "learning_rate": 0.00017041055384023728,
+      "loss": 0.7037135362625122,
+      "step": 4330
+    },
+    {
+      "epoch": 1.869039913700108,
+      "grad_norm": 0.500342607498169,
+      "learning_rate": 0.00017037567500736246,
+      "loss": 0.7065625190734863,
+      "step": 4332
+    },
+    {
+      "epoch": 1.869902912621359,
+      "grad_norm": 0.543442964553833,
+      "learning_rate": 0.00017034077920371083,
+      "loss": 0.7432923316955566,
+      "step": 4334
+    },
+    {
+      "epoch": 1.8707659115426107,
+      "grad_norm": 0.4365047812461853,
+      "learning_rate": 0.0001703058664376974,
+      "loss": 0.6966627240180969,
+      "step": 4336
+    },
+    {
+      "epoch": 1.871628910463862,
+      "grad_norm": 0.43488597869873047,
+      "learning_rate": 0.00017027093671774122,
+      "loss": 0.7880892753601074,
+      "step": 4338
+    },
+    {
+      "epoch": 1.8724919093851131,
+      "grad_norm": 0.4579373896121979,
+      "learning_rate": 0.00017023599005226546,
+      "loss": 0.7417665123939514,
+      "step": 4340
+    },
+    {
+      "epoch": 1.8733549083063648,
+      "grad_norm": 0.4457826316356659,
+      "learning_rate": 0.00017020102644969728,
+      "loss": 0.7073261141777039,
+      "step": 4342
+    },
+    {
+      "epoch": 1.874217907227616,
+      "grad_norm": 0.47289299964904785,
+      "learning_rate": 0.0001701660459184681,
+      "loss": 0.7597265243530273,
+      "step": 4344
+    },
+    {
+      "epoch": 1.8750809061488674,
+      "grad_norm": 0.4678288996219635,
+      "learning_rate": 0.0001701310484670132,
+      "loss": 0.703773021697998,
+      "step": 4346
+    },
+    {
+      "epoch": 1.8759439050701188,
+      "grad_norm": 0.4159858226776123,
+      "learning_rate": 0.00017009603410377214,
+      "loss": 0.7227264046669006,
+      "step": 4348
+    },
+    {
+      "epoch": 1.87680690399137,
+      "grad_norm": 0.42966076731681824,
+      "learning_rate": 0.00017006100283718846,
+      "loss": 0.7137405872344971,
+      "step": 4350
+    },
+    {
+      "epoch": 1.8776699029126214,
+      "grad_norm": 0.4697307050228119,
+      "learning_rate": 0.0001700259546757098,
+      "loss": 0.835712730884552,
+      "step": 4352
+    },
+    {
+      "epoch": 1.8785329018338728,
+      "grad_norm": 0.4686335027217865,
+      "learning_rate": 0.0001699908896277878,
+      "loss": 0.720323383808136,
+      "step": 4354
+    },
+    {
+      "epoch": 1.879395900755124,
+      "grad_norm": 0.4535554051399231,
+      "learning_rate": 0.00016995580770187832,
+      "loss": 0.7081778645515442,
+      "step": 4356
+    },
+    {
+      "epoch": 1.8802588996763754,
+      "grad_norm": 0.42280903458595276,
+      "learning_rate": 0.00016992070890644114,
+      "loss": 0.6428251266479492,
+      "step": 4358
+    },
+    {
+      "epoch": 1.8811218985976268,
+      "grad_norm": 0.46084120869636536,
+      "learning_rate": 0.0001698855932499402,
+      "loss": 0.7378063201904297,
+      "step": 4360
+    },
+    {
+      "epoch": 1.881984897518878,
+      "grad_norm": 0.4233613610267639,
+      "learning_rate": 0.00016985046074084357,
+      "loss": 0.745130717754364,
+      "step": 4362
+    },
+    {
+      "epoch": 1.8828478964401294,
+      "grad_norm": 0.43696120381355286,
+      "learning_rate": 0.00016981531138762318,
+      "loss": 0.7285540103912354,
+      "step": 4364
+    },
+    {
+      "epoch": 1.8837108953613808,
+      "grad_norm": 0.458446204662323,
+      "learning_rate": 0.00016978014519875516,
+      "loss": 0.7078036069869995,
+      "step": 4366
+    },
+    {
+      "epoch": 1.884573894282632,
+      "grad_norm": 0.41318631172180176,
+      "learning_rate": 0.00016974496218271972,
+      "loss": 0.6465590596199036,
+      "step": 4368
+    },
+    {
+      "epoch": 1.8854368932038836,
+      "grad_norm": 0.43945857882499695,
+      "learning_rate": 0.00016970976234800104,
+      "loss": 0.6374526023864746,
+      "step": 4370
+    },
+    {
+      "epoch": 1.8862998921251348,
+      "grad_norm": 0.4725545048713684,
+      "learning_rate": 0.00016967454570308746,
+      "loss": 0.7523587346076965,
+      "step": 4372
+    },
+    {
+      "epoch": 1.8871628910463862,
+      "grad_norm": 0.44840991497039795,
+      "learning_rate": 0.00016963931225647124,
+      "loss": 0.764968991279602,
+      "step": 4374
+    },
+    {
+      "epoch": 1.8880258899676376,
+      "grad_norm": 0.40001222491264343,
+      "learning_rate": 0.00016960406201664883,
+      "loss": 0.7077135443687439,
+      "step": 4376
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 0.4679710268974304,
+      "learning_rate": 0.00016956879499212062,
+      "loss": 0.7109629511833191,
+      "step": 4378
+    },
+    {
+      "epoch": 1.8897518878101403,
+      "grad_norm": 0.4309675991535187,
+      "learning_rate": 0.00016953351119139114,
+      "loss": 0.6676799654960632,
+      "step": 4380
+    },
+    {
+      "epoch": 1.8906148867313917,
+      "grad_norm": 0.4097946882247925,
+      "learning_rate": 0.00016949821062296888,
+      "loss": 0.7011449337005615,
+      "step": 4382
+    },
+    {
+      "epoch": 1.8914778856526429,
+      "grad_norm": 0.4526914060115814,
+      "learning_rate": 0.00016946289329536641,
+      "loss": 0.7500543594360352,
+      "step": 4384
+    },
+    {
+      "epoch": 1.8923408845738943,
+      "grad_norm": 0.448703408241272,
+      "learning_rate": 0.0001694275592171004,
+      "loss": 0.8412749767303467,
+      "step": 4386
+    },
+    {
+      "epoch": 1.8932038834951457,
+      "grad_norm": 0.3906726539134979,
+      "learning_rate": 0.00016939220839669143,
+      "loss": 0.7479212284088135,
+      "step": 4388
+    },
+    {
+      "epoch": 1.8940668824163969,
+      "grad_norm": 0.44968852400779724,
+      "learning_rate": 0.00016935684084266425,
+      "loss": 0.7404555082321167,
+      "step": 4390
+    },
+    {
+      "epoch": 1.8949298813376483,
+      "grad_norm": 0.4262198805809021,
+      "learning_rate": 0.00016932145656354758,
+      "loss": 0.7160722017288208,
+      "step": 4392
+    },
+    {
+      "epoch": 1.8957928802588997,
+      "grad_norm": 0.4741004705429077,
+      "learning_rate": 0.00016928605556787413,
+      "loss": 0.6597195863723755,
+      "step": 4394
+    },
+    {
+      "epoch": 1.8966558791801509,
+      "grad_norm": 0.4941152334213257,
+      "learning_rate": 0.0001692506378641807,
+      "loss": 0.7020326852798462,
+      "step": 4396
+    },
+    {
+      "epoch": 1.8975188781014025,
+      "grad_norm": 0.4449406564235687,
+      "learning_rate": 0.0001692152034610082,
+      "loss": 0.6817783713340759,
+      "step": 4398
+    },
+    {
+      "epoch": 1.8983818770226537,
+      "grad_norm": 0.4189581274986267,
+      "learning_rate": 0.00016917975236690138,
+      "loss": 0.6696207523345947,
+      "step": 4400
+    },
+    {
+      "epoch": 1.8983818770226537,
+      "eval_loss": 0.7715606689453125,
+      "eval_runtime": 648.4164,
+      "eval_samples_per_second": 3.177,
+      "eval_steps_per_second": 3.177,
+      "step": 4400
+    },
+    {
+      "epoch": 1.8992448759439051,
+      "grad_norm": 0.4761787950992584,
+      "learning_rate": 0.0001691442845904091,
+      "loss": 0.6992137432098389,
+      "step": 4402
+    },
+    {
+      "epoch": 1.9001078748651565,
+      "grad_norm": 0.438167542219162,
+      "learning_rate": 0.00016910880014008438,
+      "loss": 0.6070076823234558,
+      "step": 4404
+    },
+    {
+      "epoch": 1.9009708737864077,
+      "grad_norm": 0.4941405653953552,
+      "learning_rate": 0.00016907329902448397,
+      "loss": 0.6767536401748657,
+      "step": 4406
+    },
+    {
+      "epoch": 1.9018338727076591,
+      "grad_norm": 0.39704009890556335,
+      "learning_rate": 0.00016903778125216892,
+      "loss": 0.6732425093650818,
+      "step": 4408
+    },
+    {
+      "epoch": 1.9026968716289105,
+      "grad_norm": 0.4666280448436737,
+      "learning_rate": 0.00016900224683170413,
+      "loss": 0.7694390416145325,
+      "step": 4410
+    },
+    {
+      "epoch": 1.9035598705501617,
+      "grad_norm": 0.3905762732028961,
+      "learning_rate": 0.0001689666957716586,
+      "loss": 0.8102390170097351,
+      "step": 4412
+    },
+    {
+      "epoch": 1.9044228694714131,
+      "grad_norm": 0.45140960812568665,
+      "learning_rate": 0.00016893112808060527,
+      "loss": 0.6950157284736633,
+      "step": 4414
+    },
+    {
+      "epoch": 1.9052858683926646,
+      "grad_norm": 0.36071425676345825,
+      "learning_rate": 0.0001688955437671212,
+      "loss": 0.6316207051277161,
+      "step": 4416
+    },
+    {
+      "epoch": 1.9061488673139158,
+      "grad_norm": 0.4559943974018097,
+      "learning_rate": 0.00016885994283978725,
+      "loss": 0.736228883266449,
+      "step": 4418
+    },
+    {
+      "epoch": 1.9070118662351672,
+      "grad_norm": 0.42006543278694153,
+      "learning_rate": 0.00016882432530718856,
+      "loss": 0.663848876953125,
+      "step": 4420
+    },
+    {
+      "epoch": 1.9078748651564186,
+      "grad_norm": 0.4335814118385315,
+      "learning_rate": 0.00016878869117791404,
+      "loss": 0.7144405841827393,
+      "step": 4422
+    },
+    {
+      "epoch": 1.9087378640776698,
+      "grad_norm": 0.454925537109375,
+      "learning_rate": 0.0001687530404605568,
+      "loss": 0.7918539643287659,
+      "step": 4424
+    },
+    {
+      "epoch": 1.9096008629989214,
+      "grad_norm": 0.4195649325847626,
+      "learning_rate": 0.00016871737316371375,
+      "loss": 0.7775250673294067,
+      "step": 4426
+    },
+    {
+      "epoch": 1.9104638619201726,
+      "grad_norm": 0.40194037556648254,
+      "learning_rate": 0.00016868168929598596,
+      "loss": 0.7011466026306152,
+      "step": 4428
+    },
+    {
+      "epoch": 1.911326860841424,
+      "grad_norm": 0.4803355932235718,
+      "learning_rate": 0.0001686459888659784,
+      "loss": 0.7481483817100525,
+      "step": 4430
+    },
+    {
+      "epoch": 1.9121898597626754,
+      "grad_norm": 0.4976218342781067,
+      "learning_rate": 0.00016861027188230012,
+      "loss": 0.7103830575942993,
+      "step": 4432
+    },
+    {
+      "epoch": 1.9130528586839266,
+      "grad_norm": 0.4329865276813507,
+      "learning_rate": 0.00016857453835356401,
+      "loss": 0.6993346810340881,
+      "step": 4434
+    },
+    {
+      "epoch": 1.913915857605178,
+      "grad_norm": 0.39290672540664673,
+      "learning_rate": 0.00016853878828838718,
+      "loss": 0.7064663171768188,
+      "step": 4436
+    },
+    {
+      "epoch": 1.9147788565264294,
+      "grad_norm": 0.4755532741546631,
+      "learning_rate": 0.0001685030216953905,
+      "loss": 0.7383471727371216,
+      "step": 4438
+    },
+    {
+      "epoch": 1.9156418554476806,
+      "grad_norm": 0.4168999195098877,
+      "learning_rate": 0.00016846723858319896,
+      "loss": 0.6742298603057861,
+      "step": 4440
+    },
+    {
+      "epoch": 1.916504854368932,
+      "grad_norm": 0.4728643000125885,
+      "learning_rate": 0.00016843143896044146,
+      "loss": 0.7861196994781494,
+      "step": 4442
+    },
+    {
+      "epoch": 1.9173678532901834,
+      "grad_norm": 0.4734310209751129,
+      "learning_rate": 0.00016839562283575097,
+      "loss": 0.7680529952049255,
+      "step": 4444
+    },
+    {
+      "epoch": 1.9182308522114346,
+      "grad_norm": 0.44408535957336426,
+      "learning_rate": 0.00016835979021776433,
+      "loss": 0.7587183713912964,
+      "step": 4446
+    },
+    {
+      "epoch": 1.919093851132686,
+      "grad_norm": 0.4441621005535126,
+      "learning_rate": 0.00016832394111512247,
+      "loss": 0.6908396482467651,
+      "step": 4448
+    },
+    {
+      "epoch": 1.9199568500539375,
+      "grad_norm": 0.4286157488822937,
+      "learning_rate": 0.00016828807553647023,
+      "loss": 0.7139167189598083,
+      "step": 4450
+    },
+    {
+      "epoch": 1.9208198489751886,
+      "grad_norm": 0.46225154399871826,
+      "learning_rate": 0.0001682521934904564,
+      "loss": 0.7594030499458313,
+      "step": 4452
+    },
+    {
+      "epoch": 1.9216828478964403,
+      "grad_norm": 0.46970534324645996,
+      "learning_rate": 0.0001682162949857338,
+      "loss": 0.7202461957931519,
+      "step": 4454
+    },
+    {
+      "epoch": 1.9225458468176915,
+      "grad_norm": 0.5053386092185974,
+      "learning_rate": 0.00016818038003095918,
+      "loss": 0.7119565606117249,
+      "step": 4456
+    },
+    {
+      "epoch": 1.9234088457389427,
+      "grad_norm": 0.4012000560760498,
+      "learning_rate": 0.00016814444863479325,
+      "loss": 0.6812665462493896,
+      "step": 4458
+    },
+    {
+      "epoch": 1.9242718446601943,
+      "grad_norm": 0.47809499502182007,
+      "learning_rate": 0.00016810850080590077,
+      "loss": 0.7549154758453369,
+      "step": 4460
+    },
+    {
+      "epoch": 1.9251348435814455,
+      "grad_norm": 0.42006292939186096,
+      "learning_rate": 0.00016807253655295033,
+      "loss": 0.6555595993995667,
+      "step": 4462
+    },
+    {
+      "epoch": 1.925997842502697,
+      "grad_norm": 0.39846277236938477,
+      "learning_rate": 0.00016803655588461459,
+      "loss": 0.688592255115509,
+      "step": 4464
+    },
+    {
+      "epoch": 1.9268608414239483,
+      "grad_norm": 0.4685076177120209,
+      "learning_rate": 0.00016800055880957011,
+      "loss": 0.7375786900520325,
+      "step": 4466
+    },
+    {
+      "epoch": 1.9277238403451995,
+      "grad_norm": 0.4540894031524658,
+      "learning_rate": 0.00016796454533649742,
+      "loss": 0.7663659453392029,
+      "step": 4468
+    },
+    {
+      "epoch": 1.928586839266451,
+      "grad_norm": 0.3871139585971832,
+      "learning_rate": 0.000167928515474081,
+      "loss": 0.7322548031806946,
+      "step": 4470
+    },
+    {
+      "epoch": 1.9294498381877023,
+      "grad_norm": 0.5056940317153931,
+      "learning_rate": 0.0001678924692310093,
+      "loss": 0.7807921767234802,
+      "step": 4472
+    },
+    {
+      "epoch": 1.9303128371089535,
+      "grad_norm": 0.5218532681465149,
+      "learning_rate": 0.00016785640661597467,
+      "loss": 0.7619108557701111,
+      "step": 4474
+    },
+    {
+      "epoch": 1.931175836030205,
+      "grad_norm": 0.49141281843185425,
+      "learning_rate": 0.00016782032763767356,
+      "loss": 0.7600476741790771,
+      "step": 4476
+    },
+    {
+      "epoch": 1.9320388349514563,
+      "grad_norm": 0.44819942116737366,
+      "learning_rate": 0.00016778423230480612,
+      "loss": 0.724636971950531,
+      "step": 4478
+    },
+    {
+      "epoch": 1.9329018338727075,
+      "grad_norm": 0.4031332731246948,
+      "learning_rate": 0.00016774812062607665,
+      "loss": 0.7845118045806885,
+      "step": 4480
+    },
+    {
+      "epoch": 1.9337648327939592,
+      "grad_norm": 0.45330920815467834,
+      "learning_rate": 0.00016771199261019328,
+      "loss": 0.6626143455505371,
+      "step": 4482
+    },
+    {
+      "epoch": 1.9346278317152104,
+      "grad_norm": 0.42102664709091187,
+      "learning_rate": 0.00016767584826586816,
+      "loss": 0.7041512727737427,
+      "step": 4484
+    },
+    {
+      "epoch": 1.9354908306364615,
+      "grad_norm": 0.44634684920310974,
+      "learning_rate": 0.0001676396876018173,
+      "loss": 0.6547129154205322,
+      "step": 4486
+    },
+    {
+      "epoch": 1.9363538295577132,
+      "grad_norm": 0.4141015410423279,
+      "learning_rate": 0.00016760351062676074,
+      "loss": 0.7318123579025269,
+      "step": 4488
+    },
+    {
+      "epoch": 1.9372168284789644,
+      "grad_norm": 0.42240142822265625,
+      "learning_rate": 0.0001675673173494223,
+      "loss": 0.7246537208557129,
+      "step": 4490
+    },
+    {
+      "epoch": 1.9380798274002158,
+      "grad_norm": 0.4295092225074768,
+      "learning_rate": 0.0001675311077785299,
+      "loss": 0.6859333515167236,
+      "step": 4492
+    },
+    {
+      "epoch": 1.9389428263214672,
+      "grad_norm": 0.4344942569732666,
+      "learning_rate": 0.0001674948819228153,
+      "loss": 0.6654847264289856,
+      "step": 4494
+    },
+    {
+      "epoch": 1.9398058252427184,
+      "grad_norm": 0.48967039585113525,
+      "learning_rate": 0.00016745863979101416,
+      "loss": 0.7616198658943176,
+      "step": 4496
+    },
+    {
+      "epoch": 1.9406688241639698,
+      "grad_norm": 0.5314980745315552,
+      "learning_rate": 0.00016742238139186617,
+      "loss": 0.7908874154090881,
+      "step": 4498
+    },
+    {
+      "epoch": 1.9415318230852212,
+      "grad_norm": 0.4205719530582428,
+      "learning_rate": 0.00016738610673411485,
+      "loss": 0.7347621917724609,
+      "step": 4500
+    },
+    {
+      "epoch": 1.9415318230852212,
+      "eval_loss": 0.771009087562561,
+      "eval_runtime": 660.4659,
+      "eval_samples_per_second": 3.119,
+      "eval_steps_per_second": 3.119,
+      "step": 4500
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 13908,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.001
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 1
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.698195119322841e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/sft_qwen_14B/checkpoints/checkpoint-4500/training_args.bin b/sft_qwen_14B/checkpoints/checkpoint-4500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b023888140f1fb107e8d5ebbfbcb9d9558b09d43
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-4500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4200830b23d19bc86049c280236c4a6b18c26d7061b5a57cc024888ec760920f
+size 5201
diff --git a/sft_qwen_14B/checkpoints/checkpoint-500/README.md b/sft_qwen_14B/checkpoints/checkpoint-500/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..779b6406e547b32301fef1d181301a873befe542
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-500/README.md
@@ -0,0 +1,207 @@
+---
+base_model: runs/cpt_run_14b/merged_14b_cpt_lora
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:runs/cpt_run_14b/merged_14b_cpt_lora
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0
\ No newline at end of file
diff --git a/sft_qwen_14B/checkpoints/checkpoint-500/adapter_config.json b/sft_qwen_14B/checkpoints/checkpoint-500/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8ea271115c141fb10c6d899b06f46f21800e1ad6
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-500/adapter_config.json
@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "runs/cpt_run_14b/merged_14b_cpt_lora",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/sft_qwen_14B/checkpoints/checkpoint-500/adapter_model.safetensors b/sft_qwen_14B/checkpoints/checkpoint-500/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..508ad487699afadd7038197f5d15ae6c2fcfb385
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-500/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c959a7e022b51ccc9262a8d2c3e57eae65d8f558b98dcf2307fc69eaff487c91
+size 100715016
diff --git a/sft_qwen_14B/checkpoints/checkpoint-500/optimizer.pt b/sft_qwen_14B/checkpoints/checkpoint-500/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5aeca0b0dd3d247c4737c90199e3cfdc272097bb
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-500/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f62a6229cf6af2b0f3ac23252419f7bc1c177eb27f64c93376440e3b9adf9178
+size 201650659
diff --git a/sft_qwen_14B/checkpoints/checkpoint-500/rng_state.pth b/sft_qwen_14B/checkpoints/checkpoint-500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8193aefb3fd13d959867cd21be2447bcaa671c7c
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c60e613d74be8f44226a909df50066c143816dfba1e6c3e47239463e1d1460d
+size 14645
diff --git a/sft_qwen_14B/checkpoints/checkpoint-500/scheduler.pt b/sft_qwen_14B/checkpoints/checkpoint-500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6713d13e01895c6ca3fc525b8cacc733bbc3bcea
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fb6272e5daaf9216a1be187448628e809e0c7037bb715d746050c217b2355de
+size 1465
diff --git a/sft_qwen_14B/checkpoints/checkpoint-500/trainer_state.json b/sft_qwen_14B/checkpoints/checkpoint-500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..1622195f23dd648993b0e9f51d7179097279ee85
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-500/trainer_state.json
@@ -0,0 +1,1833 @@
+{
+  "best_global_step": 500,
+  "best_metric": 1.0417571067810059,
+  "best_model_checkpoint": "runs/instruct_run_14b_v1/checkpoints/checkpoint-500",
+  "epoch": 0.21574973031283712,
+  "eval_steps": 100,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008629989212513484,
+      "grad_norm": 0.36567428708076477,
+      "learning_rate": 1.7969451931716084e-07,
+      "loss": 1.6794371604919434,
+      "step": 2
+    },
+    {
+      "epoch": 0.001725997842502697,
+      "grad_norm": 0.4024646580219269,
+      "learning_rate": 5.390835579514825e-07,
+      "loss": 1.6853073835372925,
+      "step": 4
+    },
+    {
+      "epoch": 0.0025889967637540453,
+      "grad_norm": 0.40199393033981323,
+      "learning_rate": 8.984725965858042e-07,
+      "loss": 1.7621158361434937,
+      "step": 6
+    },
+    {
+      "epoch": 0.003451995685005394,
+      "grad_norm": 0.35409677028656006,
+      "learning_rate": 1.257861635220126e-06,
+      "loss": 1.633257269859314,
+      "step": 8
+    },
+    {
+      "epoch": 0.004314994606256742,
+      "grad_norm": 0.39087551832199097,
+      "learning_rate": 1.6172506738544475e-06,
+      "loss": 1.7374768257141113,
+      "step": 10
+    },
+    {
+      "epoch": 0.005177993527508091,
+      "grad_norm": 0.3586857318878174,
+      "learning_rate": 1.9766397124887693e-06,
+      "loss": 1.6955714225769043,
+      "step": 12
+    },
+    {
+      "epoch": 0.006040992448759439,
+      "grad_norm": 0.32755669951438904,
+      "learning_rate": 2.3360287511230908e-06,
+      "loss": 1.720664381980896,
+      "step": 14
+    },
+    {
+      "epoch": 0.006903991370010788,
+      "grad_norm": 0.4054872691631317,
+      "learning_rate": 2.6954177897574127e-06,
+      "loss": 1.6957035064697266,
+      "step": 16
+    },
+    {
+      "epoch": 0.007766990291262136,
+      "grad_norm": 0.37593814730644226,
+      "learning_rate": 3.0548068283917343e-06,
+      "loss": 1.7286947965621948,
+      "step": 18
+    },
+    {
+      "epoch": 0.008629989212513484,
+      "grad_norm": 0.3344813287258148,
+      "learning_rate": 3.414195867026056e-06,
+      "loss": 1.727295994758606,
+      "step": 20
+    },
+    {
+      "epoch": 0.009492988133764833,
+      "grad_norm": 0.357474148273468,
+      "learning_rate": 3.7735849056603773e-06,
+      "loss": 1.6727914810180664,
+      "step": 22
+    },
+    {
+      "epoch": 0.010355987055016181,
+      "grad_norm": 0.39115726947784424,
+      "learning_rate": 4.132973944294699e-06,
+      "loss": 1.6518884897232056,
+      "step": 24
+    },
+    {
+      "epoch": 0.01121898597626753,
+      "grad_norm": 0.4711727201938629,
+      "learning_rate": 4.492362982929021e-06,
+      "loss": 1.7868088483810425,
+      "step": 26
+    },
+    {
+      "epoch": 0.012081984897518877,
+      "grad_norm": 0.34112176299095154,
+      "learning_rate": 4.851752021563342e-06,
+      "loss": 1.6127634048461914,
+      "step": 28
+    },
+    {
+      "epoch": 0.012944983818770227,
+      "grad_norm": 0.5071991682052612,
+      "learning_rate": 5.211141060197664e-06,
+      "loss": 1.7858378887176514,
+      "step": 30
+    },
+    {
+      "epoch": 0.013807982740021575,
+      "grad_norm": 0.42048847675323486,
+      "learning_rate": 5.570530098831986e-06,
+      "loss": 1.7123326063156128,
+      "step": 32
+    },
+    {
+      "epoch": 0.014670981661272923,
+      "grad_norm": 0.48883870244026184,
+      "learning_rate": 5.929919137466308e-06,
+      "loss": 1.737749695777893,
+      "step": 34
+    },
+    {
+      "epoch": 0.015533980582524271,
+      "grad_norm": 0.3311465084552765,
+      "learning_rate": 6.289308176100629e-06,
+      "loss": 1.5578981637954712,
+      "step": 36
+    },
+    {
+      "epoch": 0.01639697950377562,
+      "grad_norm": 0.5178973078727722,
+      "learning_rate": 6.64869721473495e-06,
+      "loss": 1.719806432723999,
+      "step": 38
+    },
+    {
+      "epoch": 0.017259978425026967,
+      "grad_norm": 0.47097742557525635,
+      "learning_rate": 7.008086253369272e-06,
+      "loss": 1.728212833404541,
+      "step": 40
+    },
+    {
+      "epoch": 0.018122977346278317,
+      "grad_norm": 0.5051584243774414,
+      "learning_rate": 7.367475292003594e-06,
+      "loss": 1.6542466878890991,
+      "step": 42
+    },
+    {
+      "epoch": 0.018985976267529667,
+      "grad_norm": 0.4645111560821533,
+      "learning_rate": 7.726864330637915e-06,
+      "loss": 1.7087690830230713,
+      "step": 44
+    },
+    {
+      "epoch": 0.019848975188781013,
+      "grad_norm": 0.5184999704360962,
+      "learning_rate": 8.086253369272237e-06,
+      "loss": 1.7018946409225464,
+      "step": 46
+    },
+    {
+      "epoch": 0.020711974110032363,
+      "grad_norm": 0.4543815851211548,
+      "learning_rate": 8.44564240790656e-06,
+      "loss": 1.6818269491195679,
+      "step": 48
+    },
+    {
+      "epoch": 0.021574973031283712,
+      "grad_norm": 0.44411996006965637,
+      "learning_rate": 8.80503144654088e-06,
+      "loss": 1.5772877931594849,
+      "step": 50
+    },
+    {
+      "epoch": 0.02243797195253506,
+      "grad_norm": 0.3409404158592224,
+      "learning_rate": 9.164420485175203e-06,
+      "loss": 1.498152732849121,
+      "step": 52
+    },
+    {
+      "epoch": 0.02330097087378641,
+      "grad_norm": 0.42104434967041016,
+      "learning_rate": 9.523809523809523e-06,
+      "loss": 1.6189048290252686,
+      "step": 54
+    },
+    {
+      "epoch": 0.024163969795037755,
+      "grad_norm": 0.3756246268749237,
+      "learning_rate": 9.883198562443846e-06,
+      "loss": 1.4596441984176636,
+      "step": 56
+    },
+    {
+      "epoch": 0.025026968716289105,
+      "grad_norm": 0.36214128136634827,
+      "learning_rate": 1.0242587601078168e-05,
+      "loss": 1.503880500793457,
+      "step": 58
+    },
+    {
+      "epoch": 0.025889967637540454,
+      "grad_norm": 0.40893009305000305,
+      "learning_rate": 1.060197663971249e-05,
+      "loss": 1.5912823677062988,
+      "step": 60
+    },
+    {
+      "epoch": 0.0267529665587918,
+      "grad_norm": 0.28710272908210754,
+      "learning_rate": 1.0961365678346811e-05,
+      "loss": 1.2956721782684326,
+      "step": 62
+    },
+    {
+      "epoch": 0.02761596548004315,
+      "grad_norm": 0.304573118686676,
+      "learning_rate": 1.1320754716981132e-05,
+      "loss": 1.4648056030273438,
+      "step": 64
+    },
+    {
+      "epoch": 0.0284789644012945,
+      "grad_norm": 0.36523914337158203,
+      "learning_rate": 1.1680143755615454e-05,
+      "loss": 1.6078968048095703,
+      "step": 66
+    },
+    {
+      "epoch": 0.029341963322545846,
+      "grad_norm": 0.37929031252861023,
+      "learning_rate": 1.2039532794249775e-05,
+      "loss": 1.5969421863555908,
+      "step": 68
+    },
+    {
+      "epoch": 0.030204962243797196,
+      "grad_norm": 0.3053947389125824,
+      "learning_rate": 1.2398921832884097e-05,
+      "loss": 1.4312325716018677,
+      "step": 70
+    },
+    {
+      "epoch": 0.031067961165048542,
+      "grad_norm": 0.3028779923915863,
+      "learning_rate": 1.275831087151842e-05,
+      "loss": 1.4101300239562988,
+      "step": 72
+    },
+    {
+      "epoch": 0.03193096008629989,
+      "grad_norm": 0.29649803042411804,
+      "learning_rate": 1.3117699910152742e-05,
+      "loss": 1.4553817510604858,
+      "step": 74
+    },
+    {
+      "epoch": 0.03279395900755124,
+      "grad_norm": 0.26032644510269165,
+      "learning_rate": 1.3477088948787062e-05,
+      "loss": 1.4623000621795654,
+      "step": 76
+    },
+    {
+      "epoch": 0.03365695792880259,
+      "grad_norm": 0.33558446168899536,
+      "learning_rate": 1.3836477987421385e-05,
+      "loss": 1.5181745290756226,
+      "step": 78
+    },
+    {
+      "epoch": 0.034519956850053934,
+      "grad_norm": 0.28307804465293884,
+      "learning_rate": 1.4195867026055706e-05,
+      "loss": 1.4397861957550049,
+      "step": 80
+    },
+    {
+      "epoch": 0.035382955771305284,
+      "grad_norm": 0.3451690673828125,
+      "learning_rate": 1.455525606469003e-05,
+      "loss": 1.463841199874878,
+      "step": 82
+    },
+    {
+      "epoch": 0.036245954692556634,
+      "grad_norm": 0.3248669505119324,
+      "learning_rate": 1.4914645103324348e-05,
+      "loss": 1.3554227352142334,
+      "step": 84
+    },
+    {
+      "epoch": 0.037108953613807984,
+      "grad_norm": 0.2855011224746704,
+      "learning_rate": 1.527403414195867e-05,
+      "loss": 1.2810425758361816,
+      "step": 86
+    },
+    {
+      "epoch": 0.03797195253505933,
+      "grad_norm": 0.33365535736083984,
+      "learning_rate": 1.5633423180592992e-05,
+      "loss": 1.428163766860962,
+      "step": 88
+    },
+    {
+      "epoch": 0.038834951456310676,
+      "grad_norm": 0.34099438786506653,
+      "learning_rate": 1.5992812219227316e-05,
+      "loss": 1.3487578630447388,
+      "step": 90
+    },
+    {
+      "epoch": 0.039697950377562026,
+      "grad_norm": 0.39247506856918335,
+      "learning_rate": 1.6352201257861635e-05,
+      "loss": 1.30057954788208,
+      "step": 92
+    },
+    {
+      "epoch": 0.040560949298813376,
+      "grad_norm": 0.32692041993141174,
+      "learning_rate": 1.671159029649596e-05,
+      "loss": 1.2923580408096313,
+      "step": 94
+    },
+    {
+      "epoch": 0.041423948220064725,
+      "grad_norm": 0.43452519178390503,
+      "learning_rate": 1.707097933513028e-05,
+      "loss": 1.5002273321151733,
+      "step": 96
+    },
+    {
+      "epoch": 0.042286947141316075,
+      "grad_norm": 0.3251534402370453,
+      "learning_rate": 1.7430368373764602e-05,
+      "loss": 1.330254077911377,
+      "step": 98
+    },
+    {
+      "epoch": 0.043149946062567425,
+      "grad_norm": 0.3198273479938507,
+      "learning_rate": 1.778975741239892e-05,
+      "loss": 1.3054943084716797,
+      "step": 100
+    },
+    {
+      "epoch": 0.043149946062567425,
+      "eval_loss": 1.366738200187683,
+      "eval_runtime": 651.8198,
+      "eval_samples_per_second": 3.16,
+      "eval_steps_per_second": 3.16,
+      "step": 100
+    },
+    {
+      "epoch": 0.04401294498381877,
+      "grad_norm": 0.37364065647125244,
+      "learning_rate": 1.8149146451033245e-05,
+      "loss": 1.314281940460205,
+      "step": 102
+    },
+    {
+      "epoch": 0.04487594390507012,
+      "grad_norm": 0.39384758472442627,
+      "learning_rate": 1.8508535489667568e-05,
+      "loss": 1.2737246751785278,
+      "step": 104
+    },
+    {
+      "epoch": 0.04573894282632147,
+      "grad_norm": 0.3521905541419983,
+      "learning_rate": 1.8867924528301888e-05,
+      "loss": 1.3113226890563965,
+      "step": 106
+    },
+    {
+      "epoch": 0.04660194174757282,
+      "grad_norm": 0.33531463146209717,
+      "learning_rate": 1.9227313566936208e-05,
+      "loss": 1.3253653049468994,
+      "step": 108
+    },
+    {
+      "epoch": 0.04746494066882417,
+      "grad_norm": 0.35596340894699097,
+      "learning_rate": 1.958670260557053e-05,
+      "loss": 1.3236849308013916,
+      "step": 110
+    },
+    {
+      "epoch": 0.04832793959007551,
+      "grad_norm": 0.36028242111206055,
+      "learning_rate": 1.9946091644204854e-05,
+      "loss": 1.183128833770752,
+      "step": 112
+    },
+    {
+      "epoch": 0.04919093851132686,
+      "grad_norm": 0.42109814286231995,
+      "learning_rate": 2.0305480682839174e-05,
+      "loss": 1.2741888761520386,
+      "step": 114
+    },
+    {
+      "epoch": 0.05005393743257821,
+      "grad_norm": 0.39675939083099365,
+      "learning_rate": 2.0664869721473494e-05,
+      "loss": 1.3050109148025513,
+      "step": 116
+    },
+    {
+      "epoch": 0.05091693635382956,
+      "grad_norm": 0.4414141774177551,
+      "learning_rate": 2.1024258760107817e-05,
+      "loss": 1.2472094297409058,
+      "step": 118
+    },
+    {
+      "epoch": 0.05177993527508091,
+      "grad_norm": 0.42872729897499084,
+      "learning_rate": 2.138364779874214e-05,
+      "loss": 1.3338921070098877,
+      "step": 120
+    },
+    {
+      "epoch": 0.05264293419633225,
+      "grad_norm": 0.38336244225502014,
+      "learning_rate": 2.174303683737646e-05,
+      "loss": 1.322908878326416,
+      "step": 122
+    },
+    {
+      "epoch": 0.0535059331175836,
+      "grad_norm": 0.41046878695487976,
+      "learning_rate": 2.2102425876010783e-05,
+      "loss": 1.2169240713119507,
+      "step": 124
+    },
+    {
+      "epoch": 0.05436893203883495,
+      "grad_norm": 0.39460113644599915,
+      "learning_rate": 2.2461814914645103e-05,
+      "loss": 1.2085309028625488,
+      "step": 126
+    },
+    {
+      "epoch": 0.0552319309600863,
+      "grad_norm": 0.42829909920692444,
+      "learning_rate": 2.2821203953279426e-05,
+      "loss": 1.2969133853912354,
+      "step": 128
+    },
+    {
+      "epoch": 0.05609492988133765,
+      "grad_norm": 0.3940851390361786,
+      "learning_rate": 2.3180592991913746e-05,
+      "loss": 1.1892330646514893,
+      "step": 130
+    },
+    {
+      "epoch": 0.056957928802589,
+      "grad_norm": 0.45011839270591736,
+      "learning_rate": 2.353998203054807e-05,
+      "loss": 1.2082979679107666,
+      "step": 132
+    },
+    {
+      "epoch": 0.05782092772384034,
+      "grad_norm": 0.46059420704841614,
+      "learning_rate": 2.3899371069182393e-05,
+      "loss": 1.2388817071914673,
+      "step": 134
+    },
+    {
+      "epoch": 0.05868392664509169,
+      "grad_norm": 0.41085872054100037,
+      "learning_rate": 2.4258760107816713e-05,
+      "loss": 1.193917155265808,
+      "step": 136
+    },
+    {
+      "epoch": 0.05954692556634304,
+      "grad_norm": 0.4024205207824707,
+      "learning_rate": 2.4618149146451032e-05,
+      "loss": 1.1514034271240234,
+      "step": 138
+    },
+    {
+      "epoch": 0.06040992448759439,
+      "grad_norm": 0.3893793523311615,
+      "learning_rate": 2.4977538185085356e-05,
+      "loss": 1.1626157760620117,
+      "step": 140
+    },
+    {
+      "epoch": 0.06127292340884574,
+      "grad_norm": 0.4456317126750946,
+      "learning_rate": 2.5336927223719675e-05,
+      "loss": 1.1627076864242554,
+      "step": 142
+    },
+    {
+      "epoch": 0.062135922330097085,
+      "grad_norm": 0.5050215125083923,
+      "learning_rate": 2.5696316262354e-05,
+      "loss": 1.3038755655288696,
+      "step": 144
+    },
+    {
+      "epoch": 0.06299892125134844,
+      "grad_norm": 0.4071207642555237,
+      "learning_rate": 2.605570530098832e-05,
+      "loss": 1.1708844900131226,
+      "step": 146
+    },
+    {
+      "epoch": 0.06386192017259978,
+      "grad_norm": 0.4363228678703308,
+      "learning_rate": 2.641509433962264e-05,
+      "loss": 1.2149070501327515,
+      "step": 148
+    },
+    {
+      "epoch": 0.06472491909385113,
+      "grad_norm": 0.4436556398868561,
+      "learning_rate": 2.6774483378256965e-05,
+      "loss": 1.1942368745803833,
+      "step": 150
+    },
+    {
+      "epoch": 0.06558791801510248,
+      "grad_norm": 0.4068629741668701,
+      "learning_rate": 2.7133872416891288e-05,
+      "loss": 1.1799161434173584,
+      "step": 152
+    },
+    {
+      "epoch": 0.06645091693635383,
+      "grad_norm": 0.5291106700897217,
+      "learning_rate": 2.7493261455525608e-05,
+      "loss": 1.1832845211029053,
+      "step": 154
+    },
+    {
+      "epoch": 0.06731391585760518,
+      "grad_norm": 0.4410109221935272,
+      "learning_rate": 2.785265049415993e-05,
+      "loss": 1.1696993112564087,
+      "step": 156
+    },
+    {
+      "epoch": 0.06817691477885653,
+      "grad_norm": 0.4858371913433075,
+      "learning_rate": 2.8212039532794248e-05,
+      "loss": 1.2036973237991333,
+      "step": 158
+    },
+    {
+      "epoch": 0.06903991370010787,
+      "grad_norm": 0.45373693108558655,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 1.1145079135894775,
+      "step": 160
+    },
+    {
+      "epoch": 0.06990291262135923,
+      "grad_norm": 0.4881038963794708,
+      "learning_rate": 2.8930817610062894e-05,
+      "loss": 1.173502802848816,
+      "step": 162
+    },
+    {
+      "epoch": 0.07076591154261057,
+      "grad_norm": 0.576934814453125,
+      "learning_rate": 2.9290206648697217e-05,
+      "loss": 1.250414490699768,
+      "step": 164
+    },
+    {
+      "epoch": 0.07162891046386193,
+      "grad_norm": 0.4900001287460327,
+      "learning_rate": 2.9649595687331537e-05,
+      "loss": 1.0721495151519775,
+      "step": 166
+    },
+    {
+      "epoch": 0.07249190938511327,
+      "grad_norm": 0.4440019726753235,
+      "learning_rate": 3.000898472596586e-05,
+      "loss": 1.0689374208450317,
+      "step": 168
+    },
+    {
+      "epoch": 0.07335490830636461,
+      "grad_norm": 0.4267268180847168,
+      "learning_rate": 3.0368373764600184e-05,
+      "loss": 1.2095128297805786,
+      "step": 170
+    },
+    {
+      "epoch": 0.07421790722761597,
+      "grad_norm": 0.6062787771224976,
+      "learning_rate": 3.0727762803234503e-05,
+      "loss": 1.077776551246643,
+      "step": 172
+    },
+    {
+      "epoch": 0.07508090614886731,
+      "grad_norm": 0.49510180950164795,
+      "learning_rate": 3.108715184186882e-05,
+      "loss": 1.144006371498108,
+      "step": 174
+    },
+    {
+      "epoch": 0.07594390507011867,
+      "grad_norm": 0.4670701026916504,
+      "learning_rate": 3.144654088050314e-05,
+      "loss": 1.1663392782211304,
+      "step": 176
+    },
+    {
+      "epoch": 0.07680690399137001,
+      "grad_norm": 0.5615383386611938,
+      "learning_rate": 3.1805929919137466e-05,
+      "loss": 1.1665973663330078,
+      "step": 178
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "grad_norm": 0.47305551171302795,
+      "learning_rate": 3.216531895777179e-05,
+      "loss": 1.1337063312530518,
+      "step": 180
+    },
+    {
+      "epoch": 0.07853290183387271,
+      "grad_norm": 0.5127068758010864,
+      "learning_rate": 3.252470799640611e-05,
+      "loss": 1.072874903678894,
+      "step": 182
+    },
+    {
+      "epoch": 0.07939590075512405,
+      "grad_norm": 0.632448136806488,
+      "learning_rate": 3.2884097035040436e-05,
+      "loss": 1.1577240228652954,
+      "step": 184
+    },
+    {
+      "epoch": 0.08025889967637541,
+      "grad_norm": 0.4041025638580322,
+      "learning_rate": 3.324348607367476e-05,
+      "loss": 1.1186822652816772,
+      "step": 186
+    },
+    {
+      "epoch": 0.08112189859762675,
+      "grad_norm": 0.5239102244377136,
+      "learning_rate": 3.3602875112309076e-05,
+      "loss": 1.1468429565429688,
+      "step": 188
+    },
+    {
+      "epoch": 0.08198489751887811,
+      "grad_norm": 0.4486575424671173,
+      "learning_rate": 3.39622641509434e-05,
+      "loss": 1.0017019510269165,
+      "step": 190
+    },
+    {
+      "epoch": 0.08284789644012945,
+      "grad_norm": 0.4994317293167114,
+      "learning_rate": 3.4321653189577715e-05,
+      "loss": 1.1901532411575317,
+      "step": 192
+    },
+    {
+      "epoch": 0.0837108953613808,
+      "grad_norm": 0.5023699998855591,
+      "learning_rate": 3.468104222821204e-05,
+      "loss": 1.1398564577102661,
+      "step": 194
+    },
+    {
+      "epoch": 0.08457389428263215,
+      "grad_norm": 0.5077701807022095,
+      "learning_rate": 3.504043126684636e-05,
+      "loss": 1.1390413045883179,
+      "step": 196
+    },
+    {
+      "epoch": 0.0854368932038835,
+      "grad_norm": 0.5527892112731934,
+      "learning_rate": 3.5399820305480685e-05,
+      "loss": 1.1411432027816772,
+      "step": 198
+    },
+    {
+      "epoch": 0.08629989212513485,
+      "grad_norm": 0.5572488903999329,
+      "learning_rate": 3.575920934411501e-05,
+      "loss": 1.071260690689087,
+      "step": 200
+    },
+    {
+      "epoch": 0.08629989212513485,
+      "eval_loss": 1.1519012451171875,
+      "eval_runtime": 654.6055,
+      "eval_samples_per_second": 3.147,
+      "eval_steps_per_second": 3.147,
+      "step": 200
+    },
+    {
+      "epoch": 0.08716289104638619,
+      "grad_norm": 0.5134095549583435,
+      "learning_rate": 3.611859838274933e-05,
+      "loss": 1.138135552406311,
+      "step": 202
+    },
+    {
+      "epoch": 0.08802588996763754,
+      "grad_norm": 0.5166040658950806,
+      "learning_rate": 3.647798742138365e-05,
+      "loss": 1.111999273300171,
+      "step": 204
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.5336993336677551,
+      "learning_rate": 3.683737646001797e-05,
+      "loss": 1.1031352281570435,
+      "step": 206
+    },
+    {
+      "epoch": 0.08975188781014024,
+      "grad_norm": 0.8289600014686584,
+      "learning_rate": 3.7196765498652294e-05,
+      "loss": 1.0388667583465576,
+      "step": 208
+    },
+    {
+      "epoch": 0.09061488673139159,
+      "grad_norm": 0.47992637753486633,
+      "learning_rate": 3.755615453728661e-05,
+      "loss": 1.0950241088867188,
+      "step": 210
+    },
+    {
+      "epoch": 0.09147788565264293,
+      "grad_norm": 0.5629691481590271,
+      "learning_rate": 3.7915543575920934e-05,
+      "loss": 1.0361733436584473,
+      "step": 212
+    },
+    {
+      "epoch": 0.09234088457389428,
+      "grad_norm": 0.5515111684799194,
+      "learning_rate": 3.827493261455526e-05,
+      "loss": 1.0922447443008423,
+      "step": 214
+    },
+    {
+      "epoch": 0.09320388349514563,
+      "grad_norm": 0.5078643560409546,
+      "learning_rate": 3.863432165318958e-05,
+      "loss": 1.0866856575012207,
+      "step": 216
+    },
+    {
+      "epoch": 0.09406688241639698,
+      "grad_norm": 0.6046127676963806,
+      "learning_rate": 3.8993710691823904e-05,
+      "loss": 1.1231595277786255,
+      "step": 218
+    },
+    {
+      "epoch": 0.09492988133764833,
+      "grad_norm": 0.6255762577056885,
+      "learning_rate": 3.935309973045822e-05,
+      "loss": 1.099171757698059,
+      "step": 220
+    },
+    {
+      "epoch": 0.09579288025889968,
+      "grad_norm": 0.6036638021469116,
+      "learning_rate": 3.971248876909254e-05,
+      "loss": 1.0557761192321777,
+      "step": 222
+    },
+    {
+      "epoch": 0.09665587918015102,
+      "grad_norm": 0.5520529747009277,
+      "learning_rate": 4.0071877807726867e-05,
+      "loss": 1.0467877388000488,
+      "step": 224
+    },
+    {
+      "epoch": 0.09751887810140238,
+      "grad_norm": 0.5958684682846069,
+      "learning_rate": 4.043126684636119e-05,
+      "loss": 1.17941153049469,
+      "step": 226
+    },
+    {
+      "epoch": 0.09838187702265372,
+      "grad_norm": 0.5283281803131104,
+      "learning_rate": 4.079065588499551e-05,
+      "loss": 1.104217767715454,
+      "step": 228
+    },
+    {
+      "epoch": 0.09924487594390508,
+      "grad_norm": 0.5608792901039124,
+      "learning_rate": 4.115004492362983e-05,
+      "loss": 1.0900640487670898,
+      "step": 230
+    },
+    {
+      "epoch": 0.10010787486515642,
+      "grad_norm": 0.555964469909668,
+      "learning_rate": 4.150943396226415e-05,
+      "loss": 0.9887422323226929,
+      "step": 232
+    },
+    {
+      "epoch": 0.10097087378640776,
+      "grad_norm": 0.5875785946846008,
+      "learning_rate": 4.1868823000898476e-05,
+      "loss": 1.1298567056655884,
+      "step": 234
+    },
+    {
+      "epoch": 0.10183387270765912,
+      "grad_norm": 0.4544795751571655,
+      "learning_rate": 4.222821203953279e-05,
+      "loss": 1.0957067012786865,
+      "step": 236
+    },
+    {
+      "epoch": 0.10269687162891046,
+      "grad_norm": 0.564145565032959,
+      "learning_rate": 4.2587601078167116e-05,
+      "loss": 1.0328738689422607,
+      "step": 238
+    },
+    {
+      "epoch": 0.10355987055016182,
+      "grad_norm": 0.6285979747772217,
+      "learning_rate": 4.294699011680144e-05,
+      "loss": 1.1085515022277832,
+      "step": 240
+    },
+    {
+      "epoch": 0.10442286947141316,
+      "grad_norm": 0.6442288756370544,
+      "learning_rate": 4.330637915543576e-05,
+      "loss": 1.1291271448135376,
+      "step": 242
+    },
+    {
+      "epoch": 0.1052858683926645,
+      "grad_norm": 0.6137154698371887,
+      "learning_rate": 4.3665768194070085e-05,
+      "loss": 1.1759567260742188,
+      "step": 244
+    },
+    {
+      "epoch": 0.10614886731391586,
+      "grad_norm": 0.5906805992126465,
+      "learning_rate": 4.402515723270441e-05,
+      "loss": 1.148414969444275,
+      "step": 246
+    },
+    {
+      "epoch": 0.1070118662351672,
+      "grad_norm": 0.5382888913154602,
+      "learning_rate": 4.438454627133873e-05,
+      "loss": 1.0749616622924805,
+      "step": 248
+    },
+    {
+      "epoch": 0.10787486515641856,
+      "grad_norm": 0.6185492873191833,
+      "learning_rate": 4.474393530997305e-05,
+      "loss": 1.2235801219940186,
+      "step": 250
+    },
+    {
+      "epoch": 0.1087378640776699,
+      "grad_norm": 0.5981597900390625,
+      "learning_rate": 4.5103324348607365e-05,
+      "loss": 1.1390639543533325,
+      "step": 252
+    },
+    {
+      "epoch": 0.10960086299892124,
+      "grad_norm": 0.5664694905281067,
+      "learning_rate": 4.546271338724169e-05,
+      "loss": 1.171774983406067,
+      "step": 254
+    },
+    {
+      "epoch": 0.1104638619201726,
+      "grad_norm": 0.7071851491928101,
+      "learning_rate": 4.582210242587601e-05,
+      "loss": 1.1704237461090088,
+      "step": 256
+    },
+    {
+      "epoch": 0.11132686084142394,
+      "grad_norm": 0.5815614461898804,
+      "learning_rate": 4.6181491464510334e-05,
+      "loss": 1.0619677305221558,
+      "step": 258
+    },
+    {
+      "epoch": 0.1121898597626753,
+      "grad_norm": 0.6481915712356567,
+      "learning_rate": 4.654088050314466e-05,
+      "loss": 1.0824390649795532,
+      "step": 260
+    },
+    {
+      "epoch": 0.11305285868392664,
+      "grad_norm": 0.5988591313362122,
+      "learning_rate": 4.690026954177898e-05,
+      "loss": 1.087929606437683,
+      "step": 262
+    },
+    {
+      "epoch": 0.113915857605178,
+      "grad_norm": 0.6545296311378479,
+      "learning_rate": 4.7259658580413304e-05,
+      "loss": 1.0936195850372314,
+      "step": 264
+    },
+    {
+      "epoch": 0.11477885652642934,
+      "grad_norm": 0.5826204419136047,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 1.0433681011199951,
+      "step": 266
+    },
+    {
+      "epoch": 0.11564185544768069,
+      "grad_norm": 0.5907514095306396,
+      "learning_rate": 4.7978436657681944e-05,
+      "loss": 1.0719536542892456,
+      "step": 268
+    },
+    {
+      "epoch": 0.11650485436893204,
+      "grad_norm": 0.524394154548645,
+      "learning_rate": 4.833782569631627e-05,
+      "loss": 1.0231504440307617,
+      "step": 270
+    },
+    {
+      "epoch": 0.11736785329018339,
+      "grad_norm": 0.5472846031188965,
+      "learning_rate": 4.869721473495058e-05,
+      "loss": 0.9905915260314941,
+      "step": 272
+    },
+    {
+      "epoch": 0.11823085221143474,
+      "grad_norm": 0.727922260761261,
+      "learning_rate": 4.9056603773584906e-05,
+      "loss": 1.213677167892456,
+      "step": 274
+    },
+    {
+      "epoch": 0.11909385113268608,
+      "grad_norm": 0.6009684801101685,
+      "learning_rate": 4.941599281221923e-05,
+      "loss": 1.0052144527435303,
+      "step": 276
+    },
+    {
+      "epoch": 0.11995685005393743,
+      "grad_norm": 0.6564669013023376,
+      "learning_rate": 4.977538185085355e-05,
+      "loss": 1.108136773109436,
+      "step": 278
+    },
+    {
+      "epoch": 0.12081984897518878,
+      "grad_norm": 0.650074303150177,
+      "learning_rate": 5.013477088948787e-05,
+      "loss": 0.9700815677642822,
+      "step": 280
+    },
+    {
+      "epoch": 0.12168284789644013,
+      "grad_norm": 0.5772947072982788,
+      "learning_rate": 5.04941599281222e-05,
+      "loss": 1.038031816482544,
+      "step": 282
+    },
+    {
+      "epoch": 0.12254584681769148,
+      "grad_norm": 0.7293002009391785,
+      "learning_rate": 5.0853548966756516e-05,
+      "loss": 1.1063730716705322,
+      "step": 284
+    },
+    {
+      "epoch": 0.12340884573894283,
+      "grad_norm": 0.7937333583831787,
+      "learning_rate": 5.1212938005390846e-05,
+      "loss": 1.128495693206787,
+      "step": 286
+    },
+    {
+      "epoch": 0.12427184466019417,
+      "grad_norm": 0.48499324917793274,
+      "learning_rate": 5.157232704402516e-05,
+      "loss": 0.9438712000846863,
+      "step": 288
+    },
+    {
+      "epoch": 0.12513484358144553,
+      "grad_norm": 0.6010656952857971,
+      "learning_rate": 5.193171608265948e-05,
+      "loss": 1.0872881412506104,
+      "step": 290
+    },
+    {
+      "epoch": 0.12599784250269688,
+      "grad_norm": 0.6240811944007874,
+      "learning_rate": 5.22911051212938e-05,
+      "loss": 1.110992193222046,
+      "step": 292
+    },
+    {
+      "epoch": 0.1268608414239482,
+      "grad_norm": 0.7172768712043762,
+      "learning_rate": 5.265049415992812e-05,
+      "loss": 1.1109752655029297,
+      "step": 294
+    },
+    {
+      "epoch": 0.12772384034519957,
+      "grad_norm": 0.6442400217056274,
+      "learning_rate": 5.300988319856245e-05,
+      "loss": 1.05553138256073,
+      "step": 296
+    },
+    {
+      "epoch": 0.12858683926645093,
+      "grad_norm": 0.7074702382087708,
+      "learning_rate": 5.3369272237196765e-05,
+      "loss": 1.0717648267745972,
+      "step": 298
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "grad_norm": 0.5277591347694397,
+      "learning_rate": 5.3728661275831095e-05,
+      "loss": 0.9777541756629944,
+      "step": 300
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "eval_loss": 1.0977506637573242,
+      "eval_runtime": 662.1728,
+      "eval_samples_per_second": 3.111,
+      "eval_steps_per_second": 3.111,
+      "step": 300
+    },
+    {
+      "epoch": 0.1303128371089536,
+      "grad_norm": 0.7252246737480164,
+      "learning_rate": 5.408805031446541e-05,
+      "loss": 1.075905203819275,
+      "step": 302
+    },
+    {
+      "epoch": 0.13117583603020497,
+      "grad_norm": 0.7003294229507446,
+      "learning_rate": 5.444743935309974e-05,
+      "loss": 1.1117515563964844,
+      "step": 304
+    },
+    {
+      "epoch": 0.13203883495145632,
+      "grad_norm": 0.5878211259841919,
+      "learning_rate": 5.480682839173406e-05,
+      "loss": 1.0289191007614136,
+      "step": 306
+    },
+    {
+      "epoch": 0.13290183387270765,
+      "grad_norm": 0.7133644223213196,
+      "learning_rate": 5.5166217430368374e-05,
+      "loss": 1.0199183225631714,
+      "step": 308
+    },
+    {
+      "epoch": 0.133764832793959,
+      "grad_norm": 0.6098423600196838,
+      "learning_rate": 5.55256064690027e-05,
+      "loss": 1.0132375955581665,
+      "step": 310
+    },
+    {
+      "epoch": 0.13462783171521037,
+      "grad_norm": 0.6386916041374207,
+      "learning_rate": 5.5884995507637014e-05,
+      "loss": 1.1595754623413086,
+      "step": 312
+    },
+    {
+      "epoch": 0.1354908306364617,
+      "grad_norm": 0.6563469767570496,
+      "learning_rate": 5.6244384546271344e-05,
+      "loss": 1.0921307802200317,
+      "step": 314
+    },
+    {
+      "epoch": 0.13635382955771305,
+      "grad_norm": 0.6388015747070312,
+      "learning_rate": 5.660377358490566e-05,
+      "loss": 1.0200815200805664,
+      "step": 316
+    },
+    {
+      "epoch": 0.1372168284789644,
+      "grad_norm": 0.6026274561882019,
+      "learning_rate": 5.696316262353999e-05,
+      "loss": 0.9339485764503479,
+      "step": 318
+    },
+    {
+      "epoch": 0.13807982740021574,
+      "grad_norm": 0.619800865650177,
+      "learning_rate": 5.732255166217431e-05,
+      "loss": 1.0268478393554688,
+      "step": 320
+    },
+    {
+      "epoch": 0.1389428263214671,
+      "grad_norm": 0.5924715399742126,
+      "learning_rate": 5.768194070080862e-05,
+      "loss": 1.1394236087799072,
+      "step": 322
+    },
+    {
+      "epoch": 0.13980582524271845,
+      "grad_norm": 0.6829012036323547,
+      "learning_rate": 5.804132973944295e-05,
+      "loss": 1.002437949180603,
+      "step": 324
+    },
+    {
+      "epoch": 0.1406688241639698,
+      "grad_norm": 0.7012544274330139,
+      "learning_rate": 5.840071877807727e-05,
+      "loss": 1.132503628730774,
+      "step": 326
+    },
+    {
+      "epoch": 0.14153182308522114,
+      "grad_norm": 0.7921599745750427,
+      "learning_rate": 5.876010781671159e-05,
+      "loss": 1.1859129667282104,
+      "step": 328
+    },
+    {
+      "epoch": 0.1423948220064725,
+      "grad_norm": 0.6373353004455566,
+      "learning_rate": 5.9119496855345916e-05,
+      "loss": 1.0896776914596558,
+      "step": 330
+    },
+    {
+      "epoch": 0.14325782092772385,
+      "grad_norm": 0.6174030900001526,
+      "learning_rate": 5.947888589398024e-05,
+      "loss": 1.0691723823547363,
+      "step": 332
+    },
+    {
+      "epoch": 0.14412081984897518,
+      "grad_norm": 0.5110617280006409,
+      "learning_rate": 5.9838274932614556e-05,
+      "loss": 1.0144777297973633,
+      "step": 334
+    },
+    {
+      "epoch": 0.14498381877022654,
+      "grad_norm": 0.5580511093139648,
+      "learning_rate": 6.019766397124887e-05,
+      "loss": 0.9955101609230042,
+      "step": 336
+    },
+    {
+      "epoch": 0.1458468176914779,
+      "grad_norm": 0.6427345275878906,
+      "learning_rate": 6.05570530098832e-05,
+      "loss": 0.9863013625144958,
+      "step": 338
+    },
+    {
+      "epoch": 0.14670981661272922,
+      "grad_norm": 0.7464537024497986,
+      "learning_rate": 6.091644204851752e-05,
+      "loss": 1.0682255029678345,
+      "step": 340
+    },
+    {
+      "epoch": 0.14757281553398058,
+      "grad_norm": 0.599926769733429,
+      "learning_rate": 6.127583108715184e-05,
+      "loss": 1.034083366394043,
+      "step": 342
+    },
+    {
+      "epoch": 0.14843581445523193,
+      "grad_norm": 0.6320257186889648,
+      "learning_rate": 6.163522012578616e-05,
+      "loss": 1.0776089429855347,
+      "step": 344
+    },
+    {
+      "epoch": 0.1492988133764833,
+      "grad_norm": 0.6565091013908386,
+      "learning_rate": 6.199460916442049e-05,
+      "loss": 1.0493087768554688,
+      "step": 346
+    },
+    {
+      "epoch": 0.15016181229773462,
+      "grad_norm": 0.6512171626091003,
+      "learning_rate": 6.23539982030548e-05,
+      "loss": 1.0469218492507935,
+      "step": 348
+    },
+    {
+      "epoch": 0.15102481121898598,
+      "grad_norm": 0.8487282991409302,
+      "learning_rate": 6.271338724168913e-05,
+      "loss": 1.0985081195831299,
+      "step": 350
+    },
+    {
+      "epoch": 0.15188781014023733,
+      "grad_norm": 0.6718961596488953,
+      "learning_rate": 6.307277628032345e-05,
+      "loss": 1.0714176893234253,
+      "step": 352
+    },
+    {
+      "epoch": 0.15275080906148866,
+      "grad_norm": 0.8175088167190552,
+      "learning_rate": 6.343216531895777e-05,
+      "loss": 1.0599322319030762,
+      "step": 354
+    },
+    {
+      "epoch": 0.15361380798274002,
+      "grad_norm": 0.6359215378761292,
+      "learning_rate": 6.37915543575921e-05,
+      "loss": 0.9268131256103516,
+      "step": 356
+    },
+    {
+      "epoch": 0.15447680690399138,
+      "grad_norm": 0.6423866748809814,
+      "learning_rate": 6.415094339622641e-05,
+      "loss": 0.9838354587554932,
+      "step": 358
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "grad_norm": 0.6496716737747192,
+      "learning_rate": 6.451033243486074e-05,
+      "loss": 1.048566460609436,
+      "step": 360
+    },
+    {
+      "epoch": 0.15620280474649406,
+      "grad_norm": 0.6536920666694641,
+      "learning_rate": 6.486972147349506e-05,
+      "loss": 1.0910537242889404,
+      "step": 362
+    },
+    {
+      "epoch": 0.15706580366774542,
+      "grad_norm": 0.5832068920135498,
+      "learning_rate": 6.522911051212939e-05,
+      "loss": 0.9971448183059692,
+      "step": 364
+    },
+    {
+      "epoch": 0.15792880258899678,
+      "grad_norm": 0.6647719144821167,
+      "learning_rate": 6.558849955076371e-05,
+      "loss": 1.0496708154678345,
+      "step": 366
+    },
+    {
+      "epoch": 0.1587918015102481,
+      "grad_norm": 0.623252809047699,
+      "learning_rate": 6.594788858939802e-05,
+      "loss": 0.955894410610199,
+      "step": 368
+    },
+    {
+      "epoch": 0.15965480043149946,
+      "grad_norm": 0.6311860084533691,
+      "learning_rate": 6.630727762803235e-05,
+      "loss": 1.1304032802581787,
+      "step": 370
+    },
+    {
+      "epoch": 0.16051779935275082,
+      "grad_norm": 0.5306481122970581,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.8746405243873596,
+      "step": 372
+    },
+    {
+      "epoch": 0.16138079827400215,
+      "grad_norm": 0.6249631643295288,
+      "learning_rate": 6.7026055705301e-05,
+      "loss": 0.9104986786842346,
+      "step": 374
+    },
+    {
+      "epoch": 0.1622437971952535,
+      "grad_norm": 0.6243219971656799,
+      "learning_rate": 6.738544474393532e-05,
+      "loss": 1.043666124343872,
+      "step": 376
+    },
+    {
+      "epoch": 0.16310679611650486,
+      "grad_norm": 0.6833282113075256,
+      "learning_rate": 6.774483378256963e-05,
+      "loss": 1.0504906177520752,
+      "step": 378
+    },
+    {
+      "epoch": 0.16396979503775622,
+      "grad_norm": 0.7124452590942383,
+      "learning_rate": 6.810422282120395e-05,
+      "loss": 1.0608166456222534,
+      "step": 380
+    },
+    {
+      "epoch": 0.16483279395900755,
+      "grad_norm": 0.7520908117294312,
+      "learning_rate": 6.846361185983828e-05,
+      "loss": 1.1653732061386108,
+      "step": 382
+    },
+    {
+      "epoch": 0.1656957928802589,
+      "grad_norm": 0.7121814489364624,
+      "learning_rate": 6.88230008984726e-05,
+      "loss": 1.0626367330551147,
+      "step": 384
+    },
+    {
+      "epoch": 0.16655879180151026,
+      "grad_norm": 0.6825008988380432,
+      "learning_rate": 6.918238993710691e-05,
+      "loss": 1.012121319770813,
+      "step": 386
+    },
+    {
+      "epoch": 0.1674217907227616,
+      "grad_norm": 0.4922940135002136,
+      "learning_rate": 6.954177897574124e-05,
+      "loss": 1.0576211214065552,
+      "step": 388
+    },
+    {
+      "epoch": 0.16828478964401294,
+      "grad_norm": 0.6122089624404907,
+      "learning_rate": 6.990116801437556e-05,
+      "loss": 1.03916597366333,
+      "step": 390
+    },
+    {
+      "epoch": 0.1691477885652643,
+      "grad_norm": 0.6348981261253357,
+      "learning_rate": 7.026055705300989e-05,
+      "loss": 1.17647123336792,
+      "step": 392
+    },
+    {
+      "epoch": 0.17001078748651563,
+      "grad_norm": 0.6205878257751465,
+      "learning_rate": 7.06199460916442e-05,
+      "loss": 0.9095983505249023,
+      "step": 394
+    },
+    {
+      "epoch": 0.170873786407767,
+      "grad_norm": 0.61506187915802,
+      "learning_rate": 7.097933513027853e-05,
+      "loss": 1.082506775856018,
+      "step": 396
+    },
+    {
+      "epoch": 0.17173678532901834,
+      "grad_norm": 0.6481751799583435,
+      "learning_rate": 7.133872416891285e-05,
+      "loss": 1.0716280937194824,
+      "step": 398
+    },
+    {
+      "epoch": 0.1725997842502697,
+      "grad_norm": 0.4871014952659607,
+      "learning_rate": 7.169811320754717e-05,
+      "loss": 0.9616814851760864,
+      "step": 400
+    },
+    {
+      "epoch": 0.1725997842502697,
+      "eval_loss": 1.0649415254592896,
+      "eval_runtime": 668.6025,
+      "eval_samples_per_second": 3.081,
+      "eval_steps_per_second": 3.081,
+      "step": 400
+    },
+    {
+      "epoch": 0.17346278317152103,
+      "grad_norm": 0.5680040121078491,
+      "learning_rate": 7.20575022461815e-05,
+      "loss": 1.0475050210952759,
+      "step": 402
+    },
+    {
+      "epoch": 0.17432578209277239,
+      "grad_norm": 0.6417813897132874,
+      "learning_rate": 7.241689128481581e-05,
+      "loss": 0.9851161241531372,
+      "step": 404
+    },
+    {
+      "epoch": 0.17518878101402374,
+      "grad_norm": 0.6600468158721924,
+      "learning_rate": 7.277628032345014e-05,
+      "loss": 1.013339638710022,
+      "step": 406
+    },
+    {
+      "epoch": 0.17605177993527507,
+      "grad_norm": 0.6733932495117188,
+      "learning_rate": 7.313566936208446e-05,
+      "loss": 0.9346804022789001,
+      "step": 408
+    },
+    {
+      "epoch": 0.17691477885652643,
+      "grad_norm": 0.6812151074409485,
+      "learning_rate": 7.349505840071879e-05,
+      "loss": 0.9890368580818176,
+      "step": 410
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.6380394697189331,
+      "learning_rate": 7.385444743935311e-05,
+      "loss": 0.8787848949432373,
+      "step": 412
+    },
+    {
+      "epoch": 0.1786407766990291,
+      "grad_norm": 0.6004905700683594,
+      "learning_rate": 7.421383647798742e-05,
+      "loss": 1.0235728025436401,
+      "step": 414
+    },
+    {
+      "epoch": 0.17950377562028047,
+      "grad_norm": 0.6569193005561829,
+      "learning_rate": 7.457322551662175e-05,
+      "loss": 0.9972385168075562,
+      "step": 416
+    },
+    {
+      "epoch": 0.18036677454153183,
+      "grad_norm": 0.6761631369590759,
+      "learning_rate": 7.493261455525607e-05,
+      "loss": 0.9593698382377625,
+      "step": 418
+    },
+    {
+      "epoch": 0.18122977346278318,
+      "grad_norm": 0.7328561544418335,
+      "learning_rate": 7.529200359389039e-05,
+      "loss": 1.0426853895187378,
+      "step": 420
+    },
+    {
+      "epoch": 0.1820927723840345,
+      "grad_norm": 0.6256070137023926,
+      "learning_rate": 7.56513926325247e-05,
+      "loss": 0.9608182311058044,
+      "step": 422
+    },
+    {
+      "epoch": 0.18295577130528587,
+      "grad_norm": 1.2549844980239868,
+      "learning_rate": 7.601078167115903e-05,
+      "loss": 1.0162668228149414,
+      "step": 424
+    },
+    {
+      "epoch": 0.18381877022653723,
+      "grad_norm": 0.6751510500907898,
+      "learning_rate": 7.637017070979335e-05,
+      "loss": 1.130725383758545,
+      "step": 426
+    },
+    {
+      "epoch": 0.18468176914778855,
+      "grad_norm": 0.7029808163642883,
+      "learning_rate": 7.672955974842768e-05,
+      "loss": 1.0384817123413086,
+      "step": 428
+    },
+    {
+      "epoch": 0.1855447680690399,
+      "grad_norm": 0.644353449344635,
+      "learning_rate": 7.7088948787062e-05,
+      "loss": 1.017020344734192,
+      "step": 430
+    },
+    {
+      "epoch": 0.18640776699029127,
+      "grad_norm": 0.6784916520118713,
+      "learning_rate": 7.744833782569631e-05,
+      "loss": 1.005354404449463,
+      "step": 432
+    },
+    {
+      "epoch": 0.1872707659115426,
+      "grad_norm": 0.5989449620246887,
+      "learning_rate": 7.780772686433064e-05,
+      "loss": 1.026848316192627,
+      "step": 434
+    },
+    {
+      "epoch": 0.18813376483279395,
+      "grad_norm": 0.6502639651298523,
+      "learning_rate": 7.816711590296496e-05,
+      "loss": 0.9891080856323242,
+      "step": 436
+    },
+    {
+      "epoch": 0.1889967637540453,
+      "grad_norm": 0.6176205277442932,
+      "learning_rate": 7.852650494159929e-05,
+      "loss": 0.966316819190979,
+      "step": 438
+    },
+    {
+      "epoch": 0.18985976267529667,
+      "grad_norm": 0.6801626086235046,
+      "learning_rate": 7.88858939802336e-05,
+      "loss": 1.123063087463379,
+      "step": 440
+    },
+    {
+      "epoch": 0.190722761596548,
+      "grad_norm": 0.6718618273735046,
+      "learning_rate": 7.924528301886794e-05,
+      "loss": 1.0467073917388916,
+      "step": 442
+    },
+    {
+      "epoch": 0.19158576051779935,
+      "grad_norm": 0.6761009097099304,
+      "learning_rate": 7.960467205750225e-05,
+      "loss": 1.0952889919281006,
+      "step": 444
+    },
+    {
+      "epoch": 0.1924487594390507,
+      "grad_norm": 0.6356327533721924,
+      "learning_rate": 7.996406109613657e-05,
+      "loss": 0.954807698726654,
+      "step": 446
+    },
+    {
+      "epoch": 0.19331175836030204,
+      "grad_norm": 0.6798669695854187,
+      "learning_rate": 8.03234501347709e-05,
+      "loss": 0.9941422343254089,
+      "step": 448
+    },
+    {
+      "epoch": 0.1941747572815534,
+      "grad_norm": 0.6511302590370178,
+      "learning_rate": 8.068283917340521e-05,
+      "loss": 1.0351495742797852,
+      "step": 450
+    },
+    {
+      "epoch": 0.19503775620280475,
+      "grad_norm": 0.6061258912086487,
+      "learning_rate": 8.104222821203954e-05,
+      "loss": 1.00546133518219,
+      "step": 452
+    },
+    {
+      "epoch": 0.1959007551240561,
+      "grad_norm": 0.6278533935546875,
+      "learning_rate": 8.140161725067386e-05,
+      "loss": 1.0778460502624512,
+      "step": 454
+    },
+    {
+      "epoch": 0.19676375404530744,
+      "grad_norm": 0.6866298317909241,
+      "learning_rate": 8.176100628930818e-05,
+      "loss": 1.0344486236572266,
+      "step": 456
+    },
+    {
+      "epoch": 0.1976267529665588,
+      "grad_norm": 0.7338075041770935,
+      "learning_rate": 8.212039532794251e-05,
+      "loss": 1.0663033723831177,
+      "step": 458
+    },
+    {
+      "epoch": 0.19848975188781015,
+      "grad_norm": 0.6811459064483643,
+      "learning_rate": 8.247978436657682e-05,
+      "loss": 0.9665339589118958,
+      "step": 460
+    },
+    {
+      "epoch": 0.19935275080906148,
+      "grad_norm": 0.6779627799987793,
+      "learning_rate": 8.283917340521114e-05,
+      "loss": 1.024712324142456,
+      "step": 462
+    },
+    {
+      "epoch": 0.20021574973031284,
+      "grad_norm": 0.6486892700195312,
+      "learning_rate": 8.319856244384546e-05,
+      "loss": 0.9699305295944214,
+      "step": 464
+    },
+    {
+      "epoch": 0.2010787486515642,
+      "grad_norm": 0.7022278308868408,
+      "learning_rate": 8.355795148247979e-05,
+      "loss": 0.9540432095527649,
+      "step": 466
+    },
+    {
+      "epoch": 0.20194174757281552,
+      "grad_norm": 0.5922990441322327,
+      "learning_rate": 8.39173405211141e-05,
+      "loss": 0.9253339767456055,
+      "step": 468
+    },
+    {
+      "epoch": 0.20280474649406688,
+      "grad_norm": 0.7076792120933533,
+      "learning_rate": 8.427672955974843e-05,
+      "loss": 0.9987741112709045,
+      "step": 470
+    },
+    {
+      "epoch": 0.20366774541531824,
+      "grad_norm": 0.6491380333900452,
+      "learning_rate": 8.463611859838275e-05,
+      "loss": 1.0249329805374146,
+      "step": 472
+    },
+    {
+      "epoch": 0.2045307443365696,
+      "grad_norm": 0.6784211993217468,
+      "learning_rate": 8.499550763701708e-05,
+      "loss": 1.0577133893966675,
+      "step": 474
+    },
+    {
+      "epoch": 0.20539374325782092,
+      "grad_norm": 0.6453303694725037,
+      "learning_rate": 8.53548966756514e-05,
+      "loss": 1.1312458515167236,
+      "step": 476
+    },
+    {
+      "epoch": 0.20625674217907228,
+      "grad_norm": 0.7431377172470093,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 1.0592451095581055,
+      "step": 478
+    },
+    {
+      "epoch": 0.20711974110032363,
+      "grad_norm": 0.6097649931907654,
+      "learning_rate": 8.607367475292004e-05,
+      "loss": 0.9337235689163208,
+      "step": 480
+    },
+    {
+      "epoch": 0.20798274002157496,
+      "grad_norm": 0.5693124532699585,
+      "learning_rate": 8.643306379155436e-05,
+      "loss": 0.9088928699493408,
+      "step": 482
+    },
+    {
+      "epoch": 0.20884573894282632,
+      "grad_norm": 0.7377229332923889,
+      "learning_rate": 8.679245283018869e-05,
+      "loss": 1.0729358196258545,
+      "step": 484
+    },
+    {
+      "epoch": 0.20970873786407768,
+      "grad_norm": 0.7399470210075378,
+      "learning_rate": 8.7151841868823e-05,
+      "loss": 1.0428457260131836,
+      "step": 486
+    },
+    {
+      "epoch": 0.210571736785329,
+      "grad_norm": 0.677052915096283,
+      "learning_rate": 8.751123090745734e-05,
+      "loss": 0.9940266013145447,
+      "step": 488
+    },
+    {
+      "epoch": 0.21143473570658036,
+      "grad_norm": 0.7126721739768982,
+      "learning_rate": 8.787061994609165e-05,
+      "loss": 1.011808156967163,
+      "step": 490
+    },
+    {
+      "epoch": 0.21229773462783172,
+      "grad_norm": 0.6663792729377747,
+      "learning_rate": 8.823000898472597e-05,
+      "loss": 1.0054185390472412,
+      "step": 492
+    },
+    {
+      "epoch": 0.21316073354908308,
+      "grad_norm": 0.6661092042922974,
+      "learning_rate": 8.85893980233603e-05,
+      "loss": 1.0167138576507568,
+      "step": 494
+    },
+    {
+      "epoch": 0.2140237324703344,
+      "grad_norm": 0.6975740194320679,
+      "learning_rate": 8.894878706199461e-05,
+      "loss": 1.1470818519592285,
+      "step": 496
+    },
+    {
+      "epoch": 0.21488673139158576,
+      "grad_norm": 0.6594390869140625,
+      "learning_rate": 8.930817610062893e-05,
+      "loss": 0.9619631171226501,
+      "step": 498
+    },
+    {
+      "epoch": 0.21574973031283712,
+      "grad_norm": 0.7216679453849792,
+      "learning_rate": 8.966756513926325e-05,
+      "loss": 0.9971368312835693,
+      "step": 500
+    },
+    {
+      "epoch": 0.21574973031283712,
+      "eval_loss": 1.0417571067810059,
+      "eval_runtime": 659.3112,
+      "eval_samples_per_second": 3.124,
+      "eval_steps_per_second": 3.124,
+      "step": 500
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 13908,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.001
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.99279618206464e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/sft_qwen_14B/checkpoints/checkpoint-500/training_args.bin b/sft_qwen_14B/checkpoints/checkpoint-500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b023888140f1fb107e8d5ebbfbcb9d9558b09d43
--- /dev/null
+++ b/sft_qwen_14B/checkpoints/checkpoint-500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4200830b23d19bc86049c280236c4a6b18c26d7061b5a57cc024888ec760920f
+size 5201
diff --git a/sft_qwen_14B/config_resolved.yaml b/sft_qwen_14B/config_resolved.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..f1367dbb9e283198f3daf4c4263eae04e1a6e24a
--- /dev/null
+++ b/sft_qwen_14B/config_resolved.yaml
@@ -0,0 +1,106 @@
+run:
+  run_dir: ./runs/instruct_run_14b_v1
+  seed: 42
+wandb:
+  enabled: true
+  project: sft-training
+  entity: null
+  name: null
+  tags:
+  - sft-lora
+  - instruction-tuning
+  notes: null
+model:
+  repo_id: ./runs/cpt_run_14b/merged_14b_cpt_lora
+  revision: null
+  base_local_dir: base_model
+  trust_remote_code: true
+  tokenizer_use_fast: true
+  device_map: auto
+  torch_dtype: bfloat16
+  use_4bit: false
+  bnb_4bit_quant_type: nf4
+  bnb_4bit_use_double_quant: false
+  bnb_4bit_compute_dtype: bfloat16
+  attn_implementation: null
+data:
+  train_jsonl: sft_dataset.jsonl
+  eval_jsonl: null
+  eval_split_ratio: 0.1
+  instruction_field: instruction
+  input_field: input
+  output_field: output
+  format_type: custom
+  system_prompt: "You are a Hyperswitch Rust code analyzer. Identify functions/structs\
+    \ that need modification for a given task.\n\n## Output Format\n\n##OUTPUT\nExplain\
+    \ the data flow and why each component must change:\n- Flow: [Input \u2192 Processing\
+    \ \u2192 Output with arrows]\n- For each component: \"The [ComponentName] ([path])\
+    \ must [action] because [reason]\u2014without this, [consequence]\"\n- Explain\
+    \ coupling between components\n\n##SELECT\nmodify::crates/path/to/file.rs::impl::ComponentName\n\
+    add::crates/another/file.rs::function::AnotherComponent\n<EOS>\n\n## Rules\n\n\
+    1. Use full paths: `remove::crates/folder/file.rs::Type::Name`\n2. Use `::` for\
+    \ nested items: `status::StructName::Type::Name`\n3. Always explain \"must change\
+    \ because\" and \"without this\"\n3. Types of components: function, struct, enum,\
+    \ impl, trait\n4. If there is extra information (e.g., enum variants), include\
+    \ that too.\n5. Start with ##OUTPUT, end with ##SELECT, terminate with <EOS>\n\
+    \n## Example\n\n##TASK\nAdd webhook subscription support\n\n##OUTPUT\nThe webhook\
+    \ system routes events via EventClass enum. Flow: webhook \u2192 EventClass \u2192\
+    \ handler \u2192 processing. The EventClass enum (crates/common_enums/src/enums.rs::EventClass)\
+    \ must add Subscriptions variant because it defines event routing\u2014without\
+    \ this, subscription events cannot be processed. The SubscriptionStatus impl (crates/common_enums/src/transformers.rs::SubscriptionStatus)\
+    \ must map to EventType because it converts status to events\u2014without this,\
+    \ status changes don't trigger webhooks. These are coupled: EventClass routes\
+    \ to handlers that use SubscriptionStatus mappings.\n\n##SELECT\ncrates/common_enums/src/enums.rs::EventClass\n\
+    crates/common_enums/src/transformers.rs::SubscriptionStatus\n<EOS>\n"
+  custom_template: '##INSTRUCTION
+
+    {instruction}<|im_end|>
+
+    ##TASK
+
+    {input}<|im_end|>
+
+    ##OUTPUT
+
+    {output}<|im_end|>'
+  max_length: 2048
+  shuffle: true
+  num_proc: 4
+peft:
+  enabled: true
+  r: 16
+  lora_alpha: 32
+  lora_dropout: 0.05
+  bias: none
+  target_modules: auto
+train:
+  num_train_epochs: 6
+  per_device_train_batch_size: 1
+  per_device_eval_batch_size: 1
+  gradient_accumulation_steps: 8
+  learning_rate: 2e-4
+  weight_decay: 0.0
+  warmup_ratio: 0.08
+  lr_scheduler_type: cosine
+  optim: adamw_torch
+  max_grad_norm: 1.0
+  gradient_checkpointing: true
+  logging_steps: 2
+  save_strategy: steps
+  save_steps: 500
+  save_total_limit: 20
+  evaluation_strategy: steps
+  eval_steps: 100
+  load_best_model_at_end: true
+  early_stopping:
+    enabled: true
+    patience: 3
+    min_delta: 0.001
+    metric: eval_loss
+    mode: min
+  resume_from_checkpoint: auto
+merge:
+  enabled: true
+  merged_dtype: float16
+  max_shard_size: 2GB
+  output_dir: ./merged_14b_instruct_lora
diff --git a/sft_qwen_14B/eval_final.json b/sft_qwen_14B/eval_final.json
new file mode 100644
index 0000000000000000000000000000000000000000..72407c488467158d111d9ca298cd26bf0783d23c
--- /dev/null
+++ b/sft_qwen_14B/eval_final.json
@@ -0,0 +1,8 @@
+{
+  "eval_loss": 0.771009087562561,
+  "eval_runtime": 660.1524,
+  "eval_samples_per_second": 3.12,
+  "eval_steps_per_second": 3.12,
+  "epoch": 2.113915857605178,
+  "perplexity": 2.1619467470189244
+}
\ No newline at end of file
diff --git a/sft_qwen_14B/logs/eval.jsonl b/sft_qwen_14B/logs/eval.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..bcd2b8af8bf9d077d17f9311c55724191f9d678b
--- /dev/null
+++ b/sft_qwen_14B/logs/eval.jsonl
@@ -0,0 +1,50 @@
+{"ts": "2025-12-23T14:51:59", "event": "eval", "step": 100, "epoch": 0.043149946062567425, "eval_loss": 1.366738200187683, "eval_runtime": 651.8198, "eval_samples_per_second": 3.16, "eval_steps_per_second": 3.16, "perplexity": 3.922535281330596}
+{"ts": "2025-12-23T15:15:42", "event": "eval", "step": 200, "epoch": 0.08629989212513485, "eval_loss": 1.1519012451171875, "eval_runtime": 654.6055, "eval_samples_per_second": 3.147, "eval_steps_per_second": 3.147, "perplexity": 3.1642031201696734}
+{"ts": "2025-12-23T15:39:12", "event": "eval", "step": 300, "epoch": 0.12944983818770225, "eval_loss": 1.0977506637573242, "eval_runtime": 662.1728, "eval_samples_per_second": 3.111, "eval_steps_per_second": 3.111, "perplexity": 2.9974162385441088}
+{"ts": "2025-12-23T16:02:45", "event": "eval", "step": 400, "epoch": 0.1725997842502697, "eval_loss": 1.0649415254592896, "eval_runtime": 668.6025, "eval_samples_per_second": 3.081, "eval_steps_per_second": 3.081, "perplexity": 2.900669363791648}
+{"ts": "2025-12-23T16:26:21", "event": "eval", "step": 500, "epoch": 0.21574973031283712, "eval_loss": 1.0417571067810059, "eval_runtime": 659.3112, "eval_samples_per_second": 3.124, "eval_steps_per_second": 3.124, "perplexity": 2.8341926208081856}
+{"ts": "2025-12-23T16:49:58", "event": "eval", "step": 600, "epoch": 0.2588996763754045, "eval_loss": 1.021111011505127, "eval_runtime": 648.1611, "eval_samples_per_second": 3.178, "eval_steps_per_second": 3.178, "perplexity": 2.7762775274287583}
+{"ts": "2025-12-23T17:13:39", "event": "eval", "step": 700, "epoch": 0.30204962243797195, "eval_loss": 1.0030721426010132, "eval_runtime": 655.4533, "eval_samples_per_second": 3.143, "eval_steps_per_second": 3.143, "perplexity": 2.7266456186657524}
+{"ts": "2025-12-23T17:37:26", "event": "eval", "step": 800, "epoch": 0.3451995685005394, "eval_loss": 0.9864639639854431, "eval_runtime": 667.3516, "eval_samples_per_second": 3.087, "eval_steps_per_second": 3.087, "perplexity": 2.6817349755110063}
+{"ts": "2025-12-23T18:00:50", "event": "eval", "step": 900, "epoch": 0.3883495145631068, "eval_loss": 0.9741895794868469, "eval_runtime": 667.2236, "eval_samples_per_second": 3.087, "eval_steps_per_second": 3.087, "perplexity": 2.6490195210745533}
+{"ts": "2025-12-23T18:24:24", "event": "eval", "step": 1000, "epoch": 0.43149946062567424, "eval_loss": 0.9606748819351196, "eval_runtime": 655.4358, "eval_samples_per_second": 3.143, "eval_steps_per_second": 3.143, "perplexity": 2.6134596550958538}
+{"ts": "2025-12-23T18:48:06", "event": "eval", "step": 1100, "epoch": 0.4746494066882416, "eval_loss": 0.944629430770874, "eval_runtime": 649.9107, "eval_samples_per_second": 3.17, "eval_steps_per_second": 3.17, "perplexity": 2.5718601497474842}
+{"ts": "2025-12-23T19:12:00", "event": "eval", "step": 1200, "epoch": 0.517799352750809, "eval_loss": 0.9344067573547363, "eval_runtime": 658.6934, "eval_samples_per_second": 3.127, "eval_steps_per_second": 3.127, "perplexity": 2.545702790229787}
+{"ts": "2025-12-23T19:35:41", "event": "eval", "step": 1300, "epoch": 0.5609492988133765, "eval_loss": 0.9177446365356445, "eval_runtime": 665.3245, "eval_samples_per_second": 3.096, "eval_steps_per_second": 3.096, "perplexity": 2.5036374052331953}
+{"ts": "2025-12-23T19:58:55", "event": "eval", "step": 1400, "epoch": 0.6040992448759439, "eval_loss": 0.9080492854118347, "eval_runtime": 661.4597, "eval_samples_per_second": 3.114, "eval_steps_per_second": 3.114, "perplexity": 2.4794810528858227}
+{"ts": "2025-12-23T20:22:23", "event": "eval", "step": 1500, "epoch": 0.6472491909385113, "eval_loss": 0.8972997665405273, "eval_runtime": 649.796, "eval_samples_per_second": 3.17, "eval_steps_per_second": 3.17, "perplexity": 2.4529705672775997}
+{"ts": "2025-12-23T20:46:12", "event": "eval", "step": 1600, "epoch": 0.6903991370010788, "eval_loss": 0.8880587220191956, "eval_runtime": 653.9515, "eval_samples_per_second": 3.15, "eval_steps_per_second": 3.15, "perplexity": 2.4304069732160403}
+{"ts": "2025-12-23T21:09:45", "event": "eval", "step": 1700, "epoch": 0.7335490830636462, "eval_loss": 0.879119336605072, "eval_runtime": 663.0553, "eval_samples_per_second": 3.107, "eval_steps_per_second": 3.107, "perplexity": 2.4087774499308896}
+{"ts": "2025-12-23T21:33:12", "event": "eval", "step": 1800, "epoch": 0.7766990291262136, "eval_loss": 0.8727664947509766, "eval_runtime": 668.2062, "eval_samples_per_second": 3.083, "eval_steps_per_second": 3.083, "perplexity": 2.3935233724035805}
+{"ts": "2025-12-23T21:56:42", "event": "eval", "step": 1900, "epoch": 0.819848975188781, "eval_loss": 0.8643407821655273, "eval_runtime": 658.6942, "eval_samples_per_second": 3.127, "eval_steps_per_second": 3.127, "perplexity": 2.373440955545881}
+{"ts": "2025-12-23T22:20:12", "event": "eval", "step": 2000, "epoch": 0.8629989212513485, "eval_loss": 0.8567262887954712, "eval_runtime": 646.6443, "eval_samples_per_second": 3.186, "eval_steps_per_second": 3.186, "perplexity": 2.35543703747267}
+{"ts": "2025-12-23T22:44:04", "event": "eval", "step": 2100, "epoch": 0.9061488673139159, "eval_loss": 0.8524587750434875, "eval_runtime": 655.7682, "eval_samples_per_second": 3.141, "eval_steps_per_second": 3.141, "perplexity": 2.3454065952709313}
+{"ts": "2025-12-23T23:07:42", "event": "eval", "step": 2200, "epoch": 0.9492988133764833, "eval_loss": 0.8443478941917419, "eval_runtime": 666.5866, "eval_samples_per_second": 3.09, "eval_steps_per_second": 3.09, "perplexity": 2.3264602215852364}
+{"ts": "2025-12-23T23:31:07", "event": "eval", "step": 2300, "epoch": 0.9924487594390508, "eval_loss": 0.839731752872467, "eval_runtime": 666.2332, "eval_samples_per_second": 3.092, "eval_steps_per_second": 3.092, "perplexity": 2.3157457013246616}
+{"ts": "2025-12-23T23:54:35", "event": "eval", "step": 2400, "epoch": 1.0353829557713052, "eval_loss": 0.8369861245155334, "eval_runtime": 653.1661, "eval_samples_per_second": 3.154, "eval_steps_per_second": 3.154, "perplexity": 2.3093962448722687}
+{"ts": "2025-12-24T00:18:15", "event": "eval", "step": 2500, "epoch": 1.0785329018338727, "eval_loss": 0.8323014378547668, "eval_runtime": 652.3791, "eval_samples_per_second": 3.158, "eval_steps_per_second": 3.158, "perplexity": 2.2986027489025456}
+{"ts": "2025-12-24T00:41:59", "event": "eval", "step": 2600, "epoch": 1.12168284789644, "eval_loss": 0.8300262093544006, "eval_runtime": 658.9488, "eval_samples_per_second": 3.126, "eval_steps_per_second": 3.126, "perplexity": 2.293378847455482}
+{"ts": "2025-12-24T01:05:34", "event": "eval", "step": 2700, "epoch": 1.1648327939590075, "eval_loss": 0.8251468539237976, "eval_runtime": 667.0436, "eval_samples_per_second": 3.088, "eval_steps_per_second": 3.088, "perplexity": 2.282215893080141}
+{"ts": "2025-12-24T01:28:55", "event": "eval", "step": 2800, "epoch": 1.207982740021575, "eval_loss": 0.8219058513641357, "eval_runtime": 661.5144, "eval_samples_per_second": 3.114, "eval_steps_per_second": 3.114, "perplexity": 2.274831198899466}
+{"ts": "2025-12-24T01:52:27", "event": "eval", "step": 2900, "epoch": 1.2511326860841425, "eval_loss": 0.8155517578125, "eval_runtime": 650.62, "eval_samples_per_second": 3.166, "eval_steps_per_second": 3.166, "perplexity": 2.2604225341279616}
+{"ts": "2025-12-24T02:16:12", "event": "eval", "step": 3000, "epoch": 1.2942826321467098, "eval_loss": 0.8127614259719849, "eval_runtime": 650.4396, "eval_samples_per_second": 3.167, "eval_steps_per_second": 3.167, "perplexity": 2.2541239967493394}
+{"ts": "2025-12-24T02:40:03", "event": "eval", "step": 3100, "epoch": 1.3374325782092773, "eval_loss": 0.8109187483787537, "eval_runtime": 662.5843, "eval_samples_per_second": 3.109, "eval_steps_per_second": 3.109, "perplexity": 2.2499741975134055}
+{"ts": "2025-12-24T03:03:33", "event": "eval", "step": 3200, "epoch": 1.3805825242718446, "eval_loss": 0.8053163290023804, "eval_runtime": 668.3288, "eval_samples_per_second": 3.082, "eval_steps_per_second": 3.082, "perplexity": 2.2374041427103286}
+{"ts": "2025-12-24T03:26:53", "event": "eval", "step": 3300, "epoch": 1.423732470334412, "eval_loss": 0.8030428886413574, "eval_runtime": 658.5495, "eval_samples_per_second": 3.128, "eval_steps_per_second": 3.128, "perplexity": 2.232323315495567}
+{"ts": "2025-12-24T03:50:25", "event": "eval", "step": 3400, "epoch": 1.4668824163969796, "eval_loss": 0.8002338409423828, "eval_runtime": 649.7427, "eval_samples_per_second": 3.17, "eval_steps_per_second": 3.17, "perplexity": 2.226061411933295}
+{"ts": "2025-12-24T04:14:11", "event": "eval", "step": 3500, "epoch": 1.510032362459547, "eval_loss": 0.7970634698867798, "eval_runtime": 655.3078, "eval_samples_per_second": 3.144, "eval_steps_per_second": 3.144, "perplexity": 2.219015146804396}
+{"ts": "2025-12-24T04:37:57", "event": "eval", "step": 3600, "epoch": 1.5531823085221144, "eval_loss": 0.7935511469841003, "eval_runtime": 666.5283, "eval_samples_per_second": 3.091, "eval_steps_per_second": 3.091, "perplexity": 2.2112349204148884}
+{"ts": "2025-12-24T05:01:26", "event": "eval", "step": 3700, "epoch": 1.5963322545846816, "eval_loss": 0.7914894223213196, "eval_runtime": 668.9887, "eval_samples_per_second": 3.079, "eval_steps_per_second": 3.079, "perplexity": 2.2066806592737613}
+{"ts": "2025-12-24T05:24:59", "event": "eval", "step": 3800, "epoch": 1.6394822006472491, "eval_loss": 0.7887746691703796, "eval_runtime": 655.8201, "eval_samples_per_second": 3.141, "eval_steps_per_second": 3.141, "perplexity": 2.2006981901385223}
+{"ts": "2025-12-24T05:48:36", "event": "eval", "step": 3900, "epoch": 1.6826321467098166, "eval_loss": 0.7847991585731506, "eval_runtime": 648.2009, "eval_samples_per_second": 3.178, "eval_steps_per_second": 3.178, "perplexity": 2.191966658809909}
+{"ts": "2025-12-24T06:12:24", "event": "eval", "step": 4000, "epoch": 1.7257820927723841, "eval_loss": 0.7843562960624695, "eval_runtime": 657.9206, "eval_samples_per_second": 3.131, "eval_steps_per_second": 3.131, "perplexity": 2.190996133872477}
+{"ts": "2025-12-24T06:36:02", "event": "eval", "step": 4100, "epoch": 1.7689320388349514, "eval_loss": 0.7808024883270264, "eval_runtime": 666.5954, "eval_samples_per_second": 3.09, "eval_steps_per_second": 3.09, "perplexity": 2.183223574135379}
+{"ts": "2025-12-24T06:59:21", "event": "eval", "step": 4200, "epoch": 1.812081984897519, "eval_loss": 0.7768770456314087, "eval_runtime": 664.5255, "eval_samples_per_second": 3.1, "eval_steps_per_second": 3.1, "perplexity": 2.1746702538709117}
+{"ts": "2025-12-24T07:22:55", "event": "eval", "step": 4300, "epoch": 1.8552319309600862, "eval_loss": 0.7747175693511963, "eval_runtime": 654.7294, "eval_samples_per_second": 3.146, "eval_steps_per_second": 3.146, "perplexity": 2.169979172003413}
+{"ts": "2025-12-24T07:46:41", "event": "eval", "step": 4400, "epoch": 1.8983818770226537, "eval_loss": 0.7715606689453125, "eval_runtime": 648.4164, "eval_samples_per_second": 3.177, "eval_steps_per_second": 3.177, "perplexity": 2.1631395655330805}
+{"ts": "2025-12-24T08:10:25", "event": "eval", "step": 4500, "epoch": 1.9415318230852212, "eval_loss": 0.771009087562561, "eval_runtime": 660.4659, "eval_samples_per_second": 3.119, "eval_steps_per_second": 3.119, "perplexity": 2.1619467470189244}
+{"ts": "2025-12-24T08:34:04", "event": "eval", "step": 4600, "epoch": 1.9846817691477887, "eval_loss": 0.7693634033203125, "eval_runtime": 666.3969, "eval_samples_per_second": 3.091, "eval_steps_per_second": 3.091, "perplexity": 2.1583917912944006}
+{"ts": "2025-12-24T08:57:23", "event": "eval", "step": 4700, "epoch": 2.027615965480043, "eval_loss": 0.7736310362815857, "eval_runtime": 661.1886, "eval_samples_per_second": 3.116, "eval_steps_per_second": 3.116, "perplexity": 2.167622698297798}
+{"ts": "2025-12-24T09:20:58", "event": "eval", "step": 4800, "epoch": 2.0707659115426105, "eval_loss": 0.7749598026275635, "eval_runtime": 651.5576, "eval_samples_per_second": 3.162, "eval_steps_per_second": 3.162, "perplexity": 2.1705048768369273}
+{"ts": "2025-12-24T09:44:37", "event": "eval", "step": 4900, "epoch": 2.113915857605178, "eval_loss": 0.7710265517234802, "eval_runtime": 649.6739, "eval_samples_per_second": 3.171, "eval_steps_per_second": 3.171, "perplexity": 2.1619845039345087}
+{"ts": "2025-12-24T09:55:38", "event": "eval", "step": 4900, "epoch": 2.113915857605178, "eval_loss": 0.771009087562561, "eval_runtime": 660.1524, "eval_samples_per_second": 3.12, "eval_steps_per_second": 3.12, "perplexity": 2.1619467470189244}
diff --git a/sft_qwen_14B/logs/train.jsonl b/sft_qwen_14B/logs/train.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..180b76852694583635b5e7836de67ccbbdfb44ab
--- /dev/null
+++ b/sft_qwen_14B/logs/train.jsonl
@@ -0,0 +1,2501 @@
+{"ts": "2025-12-23T14:28:44", "event": "train_log", "step": 2, "epoch": 0.0008629989212513484, "progress_pct": 0.01, "epoch_pct": 0.01, "eta": "31:57:28", "max_grad_norm": 1.0, "loss": 1.6794371604919434, "grad_norm": 0.36567428708076477, "learning_rate": 1.7969451931716084e-07}
+{"ts": "2025-12-23T14:28:59", "event": "train_log", "step": 4, "epoch": 0.001725997842502697, "progress_pct": 0.03, "epoch_pct": 0.03, "eta": "30:49:58", "max_grad_norm": 1.0, "loss": 1.6853073835372925, "grad_norm": 0.4024646580219269, "learning_rate": 5.390835579514825e-07}
+{"ts": "2025-12-23T14:29:14", "event": "train_log", "step": 6, "epoch": 0.0025889967637540453, "progress_pct": 0.04, "epoch_pct": 0.04, "eta": "29:55:34", "max_grad_norm": 1.0, "loss": 1.7621158361434937, "grad_norm": 0.40199393033981323, "learning_rate": 8.984725965858042e-07}
+{"ts": "2025-12-23T14:29:30", "event": "train_log", "step": 8, "epoch": 0.003451995685005394, "progress_pct": 0.06, "epoch_pct": 0.06, "eta": "30:12:32", "max_grad_norm": 1.0, "loss": 1.633257269859314, "grad_norm": 0.35409677028656006, "learning_rate": 1.257861635220126e-06}
+{"ts": "2025-12-23T14:29:44", "event": "train_log", "step": 10, "epoch": 0.004314994606256742, "progress_pct": 0.07, "epoch_pct": 0.07, "eta": "29:48:45", "max_grad_norm": 1.0, "loss": 1.7374768257141113, "grad_norm": 0.39087551832199097, "learning_rate": 1.6172506738544475e-06}
+{"ts": "2025-12-23T14:30:01", "event": "train_log", "step": 12, "epoch": 0.005177993527508091, "progress_pct": 0.09, "epoch_pct": 0.09, "eta": "30:03:29", "max_grad_norm": 1.0, "loss": 1.6955714225769043, "grad_norm": 0.3586857318878174, "learning_rate": 1.9766397124887693e-06}
+{"ts": "2025-12-23T14:30:16", "event": "train_log", "step": 14, "epoch": 0.006040992448759439, "progress_pct": 0.1, "epoch_pct": 0.1, "eta": "29:52:00", "max_grad_norm": 1.0, "loss": 1.720664381980896, "grad_norm": 0.32755669951438904, "learning_rate": 2.3360287511230908e-06}
+{"ts": "2025-12-23T14:30:31", "event": "train_log", "step": 16, "epoch": 0.006903991370010788, "progress_pct": 0.12, "epoch_pct": 0.12, "eta": "29:53:28", "max_grad_norm": 1.0, "loss": 1.6957035064697266, "grad_norm": 0.4054872691631317, "learning_rate": 2.6954177897574127e-06}
+{"ts": "2025-12-23T14:30:46", "event": "train_log", "step": 18, "epoch": 0.007766990291262136, "progress_pct": 0.13, "epoch_pct": 0.13, "eta": "29:40:19", "max_grad_norm": 1.0, "loss": 1.7286947965621948, "grad_norm": 0.37593814730644226, "learning_rate": 3.0548068283917343e-06}
+{"ts": "2025-12-23T14:31:02", "event": "train_log", "step": 20, "epoch": 0.008629989212513484, "progress_pct": 0.14, "epoch_pct": 0.14, "eta": "29:46:52", "max_grad_norm": 1.0, "loss": 1.727295994758606, "grad_norm": 0.3344813287258148, "learning_rate": 3.414195867026056e-06}
+{"ts": "2025-12-23T14:31:16", "event": "train_log", "step": 22, "epoch": 0.009492988133764833, "progress_pct": 0.16, "epoch_pct": 0.16, "eta": "29:39:56", "max_grad_norm": 1.0, "loss": 1.6727914810180664, "grad_norm": 0.357474148273468, "learning_rate": 3.7735849056603773e-06}
+{"ts": "2025-12-23T14:31:32", "event": "train_log", "step": 24, "epoch": 0.010355987055016181, "progress_pct": 0.17, "epoch_pct": 0.17, "eta": "29:45:54", "max_grad_norm": 1.0, "loss": 1.6518884897232056, "grad_norm": 0.39115726947784424, "learning_rate": 4.132973944294699e-06}
+{"ts": "2025-12-23T14:31:47", "event": "train_log", "step": 26, "epoch": 0.01121898597626753, "progress_pct": 0.19, "epoch_pct": 0.19, "eta": "29:40:12", "max_grad_norm": 1.0, "loss": 1.7868088483810425, "grad_norm": 0.4711727201938629, "learning_rate": 4.492362982929021e-06}
+{"ts": "2025-12-23T14:32:02", "event": "train_log", "step": 28, "epoch": 0.012081984897518877, "progress_pct": 0.2, "epoch_pct": 0.2, "eta": "29:32:21", "max_grad_norm": 1.0, "loss": 1.6127634048461914, "grad_norm": 0.34112176299095154, "learning_rate": 4.851752021563342e-06}
+{"ts": "2025-12-23T14:32:17", "event": "train_log", "step": 30, "epoch": 0.012944983818770227, "progress_pct": 0.22, "epoch_pct": 0.22, "eta": "29:29:25", "max_grad_norm": 1.0, "loss": 1.7858378887176514, "grad_norm": 0.5071991682052612, "learning_rate": 5.211141060197664e-06}
+{"ts": "2025-12-23T14:32:31", "event": "train_log", "step": 32, "epoch": 0.013807982740021575, "progress_pct": 0.23, "epoch_pct": 0.23, "eta": "29:25:06", "max_grad_norm": 1.0, "loss": 1.7123326063156128, "grad_norm": 0.42048847675323486, "learning_rate": 5.570530098831986e-06}
+{"ts": "2025-12-23T14:32:47", "event": "train_log", "step": 34, "epoch": 0.014670981661272923, "progress_pct": 0.24, "epoch_pct": 0.24, "eta": "29:27:13", "max_grad_norm": 1.0, "loss": 1.737749695777893, "grad_norm": 0.48883870244026184, "learning_rate": 5.929919137466308e-06}
+{"ts": "2025-12-23T14:33:03", "event": "train_log", "step": 36, "epoch": 0.015533980582524271, "progress_pct": 0.26, "epoch_pct": 0.26, "eta": "29:29:37", "max_grad_norm": 1.0, "loss": 1.5578981637954712, "grad_norm": 0.3311465084552765, "learning_rate": 6.289308176100629e-06}
+{"ts": "2025-12-23T14:33:18", "event": "train_log", "step": 38, "epoch": 0.01639697950377562, "progress_pct": 0.27, "epoch_pct": 0.27, "eta": "29:29:33", "max_grad_norm": 1.0, "loss": 1.719806432723999, "grad_norm": 0.5178973078727722, "learning_rate": 6.64869721473495e-06}
+{"ts": "2025-12-23T14:33:33", "event": "train_log", "step": 40, "epoch": 0.017259978425026967, "progress_pct": 0.29, "epoch_pct": 0.29, "eta": "29:25:16", "max_grad_norm": 1.0, "loss": 1.728212833404541, "grad_norm": 0.47097742557525635, "learning_rate": 7.008086253369272e-06}
+{"ts": "2025-12-23T14:33:48", "event": "train_log", "step": 42, "epoch": 0.018122977346278317, "progress_pct": 0.3, "epoch_pct": 0.3, "eta": "29:23:52", "max_grad_norm": 1.0, "loss": 1.6542466878890991, "grad_norm": 0.5051584243774414, "learning_rate": 7.367475292003594e-06}
+{"ts": "2025-12-23T14:34:03", "event": "train_log", "step": 44, "epoch": 0.018985976267529667, "progress_pct": 0.32, "epoch_pct": 0.32, "eta": "29:24:59", "max_grad_norm": 1.0, "loss": 1.7087690830230713, "grad_norm": 0.4645111560821533, "learning_rate": 7.726864330637915e-06}
+{"ts": "2025-12-23T14:34:18", "event": "train_log", "step": 46, "epoch": 0.019848975188781013, "progress_pct": 0.33, "epoch_pct": 0.33, "eta": "29:22:55", "max_grad_norm": 1.0, "loss": 1.7018946409225464, "grad_norm": 0.5184999704360962, "learning_rate": 8.086253369272237e-06}
+{"ts": "2025-12-23T14:34:34", "event": "train_log", "step": 48, "epoch": 0.020711974110032363, "progress_pct": 0.35, "epoch_pct": 0.35, "eta": "29:24:45", "max_grad_norm": 1.0, "loss": 1.6818269491195679, "grad_norm": 0.4543815851211548, "learning_rate": 8.44564240790656e-06}
+{"ts": "2025-12-23T14:34:50", "event": "train_log", "step": 50, "epoch": 0.021574973031283712, "progress_pct": 0.36, "epoch_pct": 0.36, "eta": "29:26:33", "max_grad_norm": 1.0, "loss": 1.5772877931594849, "grad_norm": 0.44411996006965637, "learning_rate": 8.80503144654088e-06}
+{"ts": "2025-12-23T14:35:06", "event": "train_log", "step": 52, "epoch": 0.02243797195253506, "progress_pct": 0.37, "epoch_pct": 0.37, "eta": "29:31:12", "max_grad_norm": 1.0, "loss": 1.498152732849121, "grad_norm": 0.3409404158592224, "learning_rate": 9.164420485175203e-06}
+{"ts": "2025-12-23T14:35:21", "event": "train_log", "step": 54, "epoch": 0.02330097087378641, "progress_pct": 0.39, "epoch_pct": 0.39, "eta": "29:30:48", "max_grad_norm": 1.0, "loss": 1.6189048290252686, "grad_norm": 0.42104434967041016, "learning_rate": 9.523809523809523e-06}
+{"ts": "2025-12-23T14:35:36", "event": "train_log", "step": 56, "epoch": 0.024163969795037755, "progress_pct": 0.4, "epoch_pct": 0.4, "eta": "29:28:33", "max_grad_norm": 1.0, "loss": 1.4596441984176636, "grad_norm": 0.3756246268749237, "learning_rate": 9.883198562443846e-06}
+{"ts": "2025-12-23T14:35:51", "event": "train_log", "step": 58, "epoch": 0.025026968716289105, "progress_pct": 0.42, "epoch_pct": 0.42, "eta": "29:27:21", "max_grad_norm": 1.0, "loss": 1.503880500793457, "grad_norm": 0.36214128136634827, "learning_rate": 1.0242587601078168e-05}
+{"ts": "2025-12-23T14:36:06", "event": "train_log", "step": 60, "epoch": 0.025889967637540454, "progress_pct": 0.43, "epoch_pct": 0.43, "eta": "29:26:19", "max_grad_norm": 1.0, "loss": 1.5912823677062988, "grad_norm": 0.40893009305000305, "learning_rate": 1.060197663971249e-05}
+{"ts": "2025-12-23T14:36:23", "event": "train_log", "step": 62, "epoch": 0.0267529665587918, "progress_pct": 0.45, "epoch_pct": 0.45, "eta": "29:30:37", "max_grad_norm": 1.0, "loss": 1.2956721782684326, "grad_norm": 0.28710272908210754, "learning_rate": 1.0961365678346811e-05}
+{"ts": "2025-12-23T14:36:40", "event": "train_log", "step": 64, "epoch": 0.02761596548004315, "progress_pct": 0.46, "epoch_pct": 0.46, "eta": "29:36:22", "max_grad_norm": 1.0, "loss": 1.4648056030273438, "grad_norm": 0.304573118686676, "learning_rate": 1.1320754716981132e-05}
+{"ts": "2025-12-23T14:36:56", "event": "train_log", "step": 66, "epoch": 0.0284789644012945, "progress_pct": 0.47, "epoch_pct": 0.47, "eta": "29:37:53", "max_grad_norm": 1.0, "loss": 1.6078968048095703, "grad_norm": 0.36523914337158203, "learning_rate": 1.1680143755615454e-05}
+{"ts": "2025-12-23T14:37:10", "event": "train_log", "step": 68, "epoch": 0.029341963322545846, "progress_pct": 0.49, "epoch_pct": 0.49, "eta": "29:31:53", "max_grad_norm": 1.0, "loss": 1.5969421863555908, "grad_norm": 0.37929031252861023, "learning_rate": 1.2039532794249775e-05}
+{"ts": "2025-12-23T14:37:25", "event": "train_log", "step": 70, "epoch": 0.030204962243797196, "progress_pct": 0.5, "epoch_pct": 0.5, "eta": "29:30:10", "max_grad_norm": 1.0, "loss": 1.4312325716018677, "grad_norm": 0.3053947389125824, "learning_rate": 1.2398921832884097e-05}
+{"ts": "2025-12-23T14:37:39", "event": "train_log", "step": 72, "epoch": 0.031067961165048542, "progress_pct": 0.52, "epoch_pct": 0.52, "eta": "29:28:23", "max_grad_norm": 1.0, "loss": 1.4101300239562988, "grad_norm": 0.3028779923915863, "learning_rate": 1.275831087151842e-05}
+{"ts": "2025-12-23T14:37:54", "event": "train_log", "step": 74, "epoch": 0.03193096008629989, "progress_pct": 0.53, "epoch_pct": 0.53, "eta": "29:26:19", "max_grad_norm": 1.0, "loss": 1.4553817510604858, "grad_norm": 0.29649803042411804, "learning_rate": 1.3117699910152742e-05}
+{"ts": "2025-12-23T14:38:09", "event": "train_log", "step": 76, "epoch": 0.03279395900755124, "progress_pct": 0.55, "epoch_pct": 0.55, "eta": "29:24:41", "max_grad_norm": 1.0, "loss": 1.4623000621795654, "grad_norm": 0.26032644510269165, "learning_rate": 1.3477088948787062e-05}
+{"ts": "2025-12-23T14:38:23", "event": "train_log", "step": 78, "epoch": 0.03365695792880259, "progress_pct": 0.56, "epoch_pct": 0.56, "eta": "29:21:31", "max_grad_norm": 1.0, "loss": 1.5181745290756226, "grad_norm": 0.33558446168899536, "learning_rate": 1.3836477987421385e-05}
+{"ts": "2025-12-23T14:38:38", "event": "train_log", "step": 80, "epoch": 0.034519956850053934, "progress_pct": 0.58, "epoch_pct": 0.58, "eta": "29:20:21", "max_grad_norm": 1.0, "loss": 1.4397861957550049, "grad_norm": 0.28307804465293884, "learning_rate": 1.4195867026055706e-05}
+{"ts": "2025-12-23T14:38:53", "event": "train_log", "step": 82, "epoch": 0.035382955771305284, "progress_pct": 0.59, "epoch_pct": 0.59, "eta": "29:17:20", "max_grad_norm": 1.0, "loss": 1.463841199874878, "grad_norm": 0.3451690673828125, "learning_rate": 1.455525606469003e-05}
+{"ts": "2025-12-23T14:39:07", "event": "train_log", "step": 84, "epoch": 0.036245954692556634, "progress_pct": 0.6, "epoch_pct": 0.6, "eta": "29:16:01", "max_grad_norm": 1.0, "loss": 1.3554227352142334, "grad_norm": 0.3248669505119324, "learning_rate": 1.4914645103324348e-05}
+{"ts": "2025-12-23T14:39:23", "event": "train_log", "step": 86, "epoch": 0.037108953613807984, "progress_pct": 0.62, "epoch_pct": 0.62, "eta": "29:17:17", "max_grad_norm": 1.0, "loss": 1.2810425758361816, "grad_norm": 0.2855011224746704, "learning_rate": 1.527403414195867e-05}
+{"ts": "2025-12-23T14:39:38", "event": "train_log", "step": 88, "epoch": 0.03797195253505933, "progress_pct": 0.63, "epoch_pct": 0.63, "eta": "29:16:28", "max_grad_norm": 1.0, "loss": 1.428163766860962, "grad_norm": 0.33365535736083984, "learning_rate": 1.5633423180592992e-05}
+{"ts": "2025-12-23T14:39:53", "event": "train_log", "step": 90, "epoch": 0.038834951456310676, "progress_pct": 0.65, "epoch_pct": 0.65, "eta": "29:14:24", "max_grad_norm": 1.0, "loss": 1.3487578630447388, "grad_norm": 0.34099438786506653, "learning_rate": 1.5992812219227316e-05}
+{"ts": "2025-12-23T14:40:08", "event": "train_log", "step": 92, "epoch": 0.039697950377562026, "progress_pct": 0.66, "epoch_pct": 0.66, "eta": "29:13:51", "max_grad_norm": 1.0, "loss": 1.30057954788208, "grad_norm": 0.39247506856918335, "learning_rate": 1.6352201257861635e-05}
+{"ts": "2025-12-23T14:40:23", "event": "train_log", "step": 94, "epoch": 0.040560949298813376, "progress_pct": 0.68, "epoch_pct": 0.68, "eta": "29:13:27", "max_grad_norm": 1.0, "loss": 1.2923580408096313, "grad_norm": 0.32692041993141174, "learning_rate": 1.671159029649596e-05}
+{"ts": "2025-12-23T14:40:37", "event": "train_log", "step": 96, "epoch": 0.041423948220064725, "progress_pct": 0.69, "epoch_pct": 0.69, "eta": "29:09:49", "max_grad_norm": 1.0, "loss": 1.5002273321151733, "grad_norm": 0.43452519178390503, "learning_rate": 1.707097933513028e-05}
+{"ts": "2025-12-23T14:40:52", "event": "train_log", "step": 98, "epoch": 0.042286947141316075, "progress_pct": 0.7, "epoch_pct": 0.7, "eta": "29:08:44", "max_grad_norm": 1.0, "loss": 1.330254077911377, "grad_norm": 0.3251534402370453, "learning_rate": 1.7430368373764602e-05}
+{"ts": "2025-12-23T14:41:07", "event": "train_log", "step": 100, "epoch": 0.043149946062567425, "progress_pct": 0.72, "epoch_pct": 0.72, "eta": "29:08:23", "max_grad_norm": 1.0, "loss": 1.3054943084716797, "grad_norm": 0.3198273479938507, "learning_rate": 1.778975741239892e-05}
+{"ts": "2025-12-23T14:51:59", "event": "train_log", "step": 100, "epoch": 0.043149946062567425, "progress_pct": 0.72, "epoch_pct": 0.72, "eta": "54:08:27", "max_grad_norm": 1.0, "eval_loss": 1.366738200187683, "eval_runtime": 651.8198, "eval_samples_per_second": 3.16, "eval_steps_per_second": 3.16}
+{"ts": "2025-12-23T14:52:15", "event": "train_log", "step": 102, "epoch": 0.04401294498381877, "progress_pct": 0.73, "epoch_pct": 0.73, "eta": "53:39:52", "max_grad_norm": 1.0, "loss": 1.314281940460205, "grad_norm": 0.37364065647125244, "learning_rate": 1.8149146451033245e-05}
+{"ts": "2025-12-23T14:52:31", "event": "train_log", "step": 104, "epoch": 0.04487594390507012, "progress_pct": 0.75, "epoch_pct": 0.75, "eta": "53:13:25", "max_grad_norm": 1.0, "loss": 1.2737246751785278, "grad_norm": 0.39384758472442627, "learning_rate": 1.8508535489667568e-05}
+{"ts": "2025-12-23T14:52:47", "event": "train_log", "step": 106, "epoch": 0.04573894282632147, "progress_pct": 0.76, "epoch_pct": 0.76, "eta": "52:47:00", "max_grad_norm": 1.0, "loss": 1.3113226890563965, "grad_norm": 0.3521905541419983, "learning_rate": 1.8867924528301888e-05}
+{"ts": "2025-12-23T14:53:03", "event": "train_log", "step": 108, "epoch": 0.04660194174757282, "progress_pct": 0.78, "epoch_pct": 0.78, "eta": "52:22:46", "max_grad_norm": 1.0, "loss": 1.3253653049468994, "grad_norm": 0.33531463146209717, "learning_rate": 1.9227313566936208e-05}
+{"ts": "2025-12-23T14:53:20", "event": "train_log", "step": 110, "epoch": 0.04746494066882417, "progress_pct": 0.79, "epoch_pct": 0.79, "eta": "52:00:36", "max_grad_norm": 1.0, "loss": 1.3236849308013916, "grad_norm": 0.35596340894699097, "learning_rate": 1.958670260557053e-05}
+{"ts": "2025-12-23T14:53:35", "event": "train_log", "step": 112, "epoch": 0.04832793959007551, "progress_pct": 0.81, "epoch_pct": 0.81, "eta": "51:36:20", "max_grad_norm": 1.0, "loss": 1.183128833770752, "grad_norm": 0.36028242111206055, "learning_rate": 1.9946091644204854e-05}
+{"ts": "2025-12-23T14:53:50", "event": "train_log", "step": 114, "epoch": 0.04919093851132686, "progress_pct": 0.82, "epoch_pct": 0.82, "eta": "51:11:23", "max_grad_norm": 1.0, "loss": 1.2741888761520386, "grad_norm": 0.42109814286231995, "learning_rate": 2.0305480682839174e-05}
+{"ts": "2025-12-23T14:54:05", "event": "train_log", "step": 116, "epoch": 0.05005393743257821, "progress_pct": 0.83, "epoch_pct": 0.83, "eta": "50:47:21", "max_grad_norm": 1.0, "loss": 1.3050109148025513, "grad_norm": 0.39675939083099365, "learning_rate": 2.0664869721473494e-05}
+{"ts": "2025-12-23T14:54:21", "event": "train_log", "step": 118, "epoch": 0.05091693635382956, "progress_pct": 0.85, "epoch_pct": 0.85, "eta": "50:25:19", "max_grad_norm": 1.0, "loss": 1.2472094297409058, "grad_norm": 0.4414141774177551, "learning_rate": 2.1024258760107817e-05}
+{"ts": "2025-12-23T14:54:36", "event": "train_log", "step": 120, "epoch": 0.05177993527508091, "progress_pct": 0.86, "epoch_pct": 0.86, "eta": "50:04:17", "max_grad_norm": 1.0, "loss": 1.3338921070098877, "grad_norm": 0.42872729897499084, "learning_rate": 2.138364779874214e-05}
+{"ts": "2025-12-23T14:54:50", "event": "train_log", "step": 122, "epoch": 0.05264293419633225, "progress_pct": 0.88, "epoch_pct": 0.88, "eta": "49:40:23", "max_grad_norm": 1.0, "loss": 1.322908878326416, "grad_norm": 0.38336244225502014, "learning_rate": 2.174303683737646e-05}
+{"ts": "2025-12-23T14:55:06", "event": "train_log", "step": 124, "epoch": 0.0535059331175836, "progress_pct": 0.89, "epoch_pct": 0.89, "eta": "49:21:26", "max_grad_norm": 1.0, "loss": 1.2169240713119507, "grad_norm": 0.41046878695487976, "learning_rate": 2.2102425876010783e-05}
+{"ts": "2025-12-23T14:55:21", "event": "train_log", "step": 126, "epoch": 0.05436893203883495, "progress_pct": 0.91, "epoch_pct": 0.91, "eta": "49:02:21", "max_grad_norm": 1.0, "loss": 1.2085309028625488, "grad_norm": 0.39460113644599915, "learning_rate": 2.2461814914645103e-05}
+{"ts": "2025-12-23T14:55:35", "event": "train_log", "step": 128, "epoch": 0.0552319309600863, "progress_pct": 0.92, "epoch_pct": 0.92, "eta": "48:40:54", "max_grad_norm": 1.0, "loss": 1.2969133853912354, "grad_norm": 0.42829909920692444, "learning_rate": 2.2821203953279426e-05}
+{"ts": "2025-12-23T14:55:50", "event": "train_log", "step": 130, "epoch": 0.05609492988133765, "progress_pct": 0.93, "epoch_pct": 0.93, "eta": "48:21:20", "max_grad_norm": 1.0, "loss": 1.1892330646514893, "grad_norm": 0.3940851390361786, "learning_rate": 2.3180592991913746e-05}
+{"ts": "2025-12-23T14:56:06", "event": "train_log", "step": 132, "epoch": 0.056957928802589, "progress_pct": 0.95, "epoch_pct": 0.95, "eta": "48:04:31", "max_grad_norm": 1.0, "loss": 1.2082979679107666, "grad_norm": 0.45011839270591736, "learning_rate": 2.353998203054807e-05}
+{"ts": "2025-12-23T14:56:20", "event": "train_log", "step": 134, "epoch": 0.05782092772384034, "progress_pct": 0.96, "epoch_pct": 0.96, "eta": "47:46:10", "max_grad_norm": 1.0, "loss": 1.2388817071914673, "grad_norm": 0.46059420704841614, "learning_rate": 2.3899371069182393e-05}
+{"ts": "2025-12-23T14:56:36", "event": "train_log", "step": 136, "epoch": 0.05868392664509169, "progress_pct": 0.98, "epoch_pct": 0.98, "eta": "47:29:25", "max_grad_norm": 1.0, "loss": 1.193917155265808, "grad_norm": 0.41085872054100037, "learning_rate": 2.4258760107816713e-05}
+{"ts": "2025-12-23T14:56:51", "event": "train_log", "step": 138, "epoch": 0.05954692556634304, "progress_pct": 0.99, "epoch_pct": 0.99, "eta": "47:12:59", "max_grad_norm": 1.0, "loss": 1.1514034271240234, "grad_norm": 0.4024205207824707, "learning_rate": 2.4618149146451032e-05}
+{"ts": "2025-12-23T14:57:07", "event": "train_log", "step": 140, "epoch": 0.06040992448759439, "progress_pct": 1.01, "epoch_pct": 1.01, "eta": "46:58:19", "max_grad_norm": 1.0, "loss": 1.1626157760620117, "grad_norm": 0.3893793523311615, "learning_rate": 2.4977538185085356e-05}
+{"ts": "2025-12-23T14:57:22", "event": "train_log", "step": 142, "epoch": 0.06127292340884574, "progress_pct": 1.02, "epoch_pct": 1.02, "eta": "46:43:10", "max_grad_norm": 1.0, "loss": 1.1627076864242554, "grad_norm": 0.4456317126750946, "learning_rate": 2.5336927223719675e-05}
+{"ts": "2025-12-23T14:57:38", "event": "train_log", "step": 144, "epoch": 0.062135922330097085, "progress_pct": 1.04, "epoch_pct": 1.04, "eta": "46:29:05", "max_grad_norm": 1.0, "loss": 1.3038755655288696, "grad_norm": 0.5050215125083923, "learning_rate": 2.5696316262354e-05}
+{"ts": "2025-12-23T14:57:53", "event": "train_log", "step": 146, "epoch": 0.06299892125134844, "progress_pct": 1.05, "epoch_pct": 1.05, "eta": "46:14:25", "max_grad_norm": 1.0, "loss": 1.1708844900131226, "grad_norm": 0.4071207642555237, "learning_rate": 2.605570530098832e-05}
+{"ts": "2025-12-23T14:58:09", "event": "train_log", "step": 148, "epoch": 0.06386192017259978, "progress_pct": 1.06, "epoch_pct": 1.06, "eta": "46:01:10", "max_grad_norm": 1.0, "loss": 1.2149070501327515, "grad_norm": 0.4363228678703308, "learning_rate": 2.641509433962264e-05}
+{"ts": "2025-12-23T14:58:25", "event": "train_log", "step": 150, "epoch": 0.06472491909385113, "progress_pct": 1.08, "epoch_pct": 1.08, "eta": "45:47:41", "max_grad_norm": 1.0, "loss": 1.1942368745803833, "grad_norm": 0.4436556398868561, "learning_rate": 2.6774483378256965e-05}
+{"ts": "2025-12-23T14:58:40", "event": "train_log", "step": 152, "epoch": 0.06558791801510248, "progress_pct": 1.09, "epoch_pct": 1.09, "eta": "45:34:19", "max_grad_norm": 1.0, "loss": 1.1799161434173584, "grad_norm": 0.4068629741668701, "learning_rate": 2.7133872416891288e-05}
+{"ts": "2025-12-23T14:58:54", "event": "train_log", "step": 154, "epoch": 0.06645091693635383, "progress_pct": 1.11, "epoch_pct": 1.11, "eta": "45:19:38", "max_grad_norm": 1.0, "loss": 1.1832845211029053, "grad_norm": 0.5291106700897217, "learning_rate": 2.7493261455525608e-05}
+{"ts": "2025-12-23T14:59:10", "event": "train_log", "step": 156, "epoch": 0.06731391585760518, "progress_pct": 1.12, "epoch_pct": 1.12, "eta": "45:07:21", "max_grad_norm": 1.0, "loss": 1.1696993112564087, "grad_norm": 0.4410109221935272, "learning_rate": 2.785265049415993e-05}
+{"ts": "2025-12-23T14:59:25", "event": "train_log", "step": 158, "epoch": 0.06817691477885653, "progress_pct": 1.14, "epoch_pct": 1.14, "eta": "44:53:46", "max_grad_norm": 1.0, "loss": 1.2036973237991333, "grad_norm": 0.4858371913433075, "learning_rate": 2.8212039532794248e-05}
+{"ts": "2025-12-23T14:59:40", "event": "train_log", "step": 160, "epoch": 0.06903991370010787, "progress_pct": 1.15, "epoch_pct": 1.15, "eta": "44:41:32", "max_grad_norm": 1.0, "loss": 1.1145079135894775, "grad_norm": 0.45373693108558655, "learning_rate": 2.857142857142857e-05}
+{"ts": "2025-12-23T14:59:55", "event": "train_log", "step": 162, "epoch": 0.06990291262135923, "progress_pct": 1.16, "epoch_pct": 1.17, "eta": "44:29:57", "max_grad_norm": 1.0, "loss": 1.173502802848816, "grad_norm": 0.4881038963794708, "learning_rate": 2.8930817610062894e-05}
+{"ts": "2025-12-23T15:00:10", "event": "train_log", "step": 164, "epoch": 0.07076591154261057, "progress_pct": 1.18, "epoch_pct": 1.18, "eta": "44:18:03", "max_grad_norm": 1.0, "loss": 1.250414490699768, "grad_norm": 0.576934814453125, "learning_rate": 2.9290206648697217e-05}
+{"ts": "2025-12-23T15:00:26", "event": "train_log", "step": 166, "epoch": 0.07162891046386193, "progress_pct": 1.19, "epoch_pct": 1.19, "eta": "44:07:43", "max_grad_norm": 1.0, "loss": 1.0721495151519775, "grad_norm": 0.4900001287460327, "learning_rate": 2.9649595687331537e-05}
+{"ts": "2025-12-23T15:00:41", "event": "train_log", "step": 168, "epoch": 0.07249190938511327, "progress_pct": 1.21, "epoch_pct": 1.21, "eta": "43:56:13", "max_grad_norm": 1.0, "loss": 1.0689374208450317, "grad_norm": 0.4440019726753235, "learning_rate": 3.000898472596586e-05}
+{"ts": "2025-12-23T15:00:56", "event": "train_log", "step": 170, "epoch": 0.07335490830636461, "progress_pct": 1.22, "epoch_pct": 1.22, "eta": "43:45:12", "max_grad_norm": 1.0, "loss": 1.2095128297805786, "grad_norm": 0.4267268180847168, "learning_rate": 3.0368373764600184e-05}
+{"ts": "2025-12-23T15:01:12", "event": "train_log", "step": 172, "epoch": 0.07421790722761597, "progress_pct": 1.24, "epoch_pct": 1.24, "eta": "43:34:39", "max_grad_norm": 1.0, "loss": 1.077776551246643, "grad_norm": 0.6062787771224976, "learning_rate": 3.0727762803234503e-05}
+{"ts": "2025-12-23T15:01:27", "event": "train_log", "step": 174, "epoch": 0.07508090614886731, "progress_pct": 1.25, "epoch_pct": 1.25, "eta": "43:24:41", "max_grad_norm": 1.0, "loss": 1.144006371498108, "grad_norm": 0.49510180950164795, "learning_rate": 3.108715184186882e-05}
+{"ts": "2025-12-23T15:01:43", "event": "train_log", "step": 176, "epoch": 0.07594390507011867, "progress_pct": 1.27, "epoch_pct": 1.27, "eta": "43:15:46", "max_grad_norm": 1.0, "loss": 1.1663392782211304, "grad_norm": 0.4670701026916504, "learning_rate": 3.144654088050314e-05}
+{"ts": "2025-12-23T15:01:58", "event": "train_log", "step": 178, "epoch": 0.07680690399137001, "progress_pct": 1.28, "epoch_pct": 1.28, "eta": "43:05:08", "max_grad_norm": 1.0, "loss": 1.1665973663330078, "grad_norm": 0.5615383386611938, "learning_rate": 3.1805929919137466e-05}
+{"ts": "2025-12-23T15:02:14", "event": "train_log", "step": 180, "epoch": 0.07766990291262135, "progress_pct": 1.29, "epoch_pct": 1.29, "eta": "42:56:33", "max_grad_norm": 1.0, "loss": 1.1337063312530518, "grad_norm": 0.47305551171302795, "learning_rate": 3.216531895777179e-05}
+{"ts": "2025-12-23T15:02:29", "event": "train_log", "step": 182, "epoch": 0.07853290183387271, "progress_pct": 1.31, "epoch_pct": 1.31, "eta": "42:46:49", "max_grad_norm": 1.0, "loss": 1.072874903678894, "grad_norm": 0.5127068758010864, "learning_rate": 3.252470799640611e-05}
+{"ts": "2025-12-23T15:02:44", "event": "train_log", "step": 184, "epoch": 0.07939590075512405, "progress_pct": 1.32, "epoch_pct": 1.32, "eta": "42:37:07", "max_grad_norm": 1.0, "loss": 1.1577240228652954, "grad_norm": 0.632448136806488, "learning_rate": 3.2884097035040436e-05}
+{"ts": "2025-12-23T15:03:00", "event": "train_log", "step": 186, "epoch": 0.08025889967637541, "progress_pct": 1.34, "epoch_pct": 1.34, "eta": "42:28:32", "max_grad_norm": 1.0, "loss": 1.1186822652816772, "grad_norm": 0.4041025638580322, "learning_rate": 3.324348607367476e-05}
+{"ts": "2025-12-23T15:03:15", "event": "train_log", "step": 188, "epoch": 0.08112189859762675, "progress_pct": 1.35, "epoch_pct": 1.35, "eta": "42:18:58", "max_grad_norm": 1.0, "loss": 1.1468429565429688, "grad_norm": 0.5239102244377136, "learning_rate": 3.3602875112309076e-05}
+{"ts": "2025-12-23T15:03:30", "event": "train_log", "step": 190, "epoch": 0.08198489751887811, "progress_pct": 1.37, "epoch_pct": 1.37, "eta": "42:10:05", "max_grad_norm": 1.0, "loss": 1.0017019510269165, "grad_norm": 0.4486575424671173, "learning_rate": 3.39622641509434e-05}
+{"ts": "2025-12-23T15:03:45", "event": "train_log", "step": 192, "epoch": 0.08284789644012945, "progress_pct": 1.38, "epoch_pct": 1.38, "eta": "42:00:58", "max_grad_norm": 1.0, "loss": 1.1901532411575317, "grad_norm": 0.4994317293167114, "learning_rate": 3.4321653189577715e-05}
+{"ts": "2025-12-23T15:04:01", "event": "train_log", "step": 194, "epoch": 0.0837108953613808, "progress_pct": 1.39, "epoch_pct": 1.4, "eta": "41:54:02", "max_grad_norm": 1.0, "loss": 1.1398564577102661, "grad_norm": 0.5023699998855591, "learning_rate": 3.468104222821204e-05}
+{"ts": "2025-12-23T15:04:16", "event": "train_log", "step": 196, "epoch": 0.08457389428263215, "progress_pct": 1.41, "epoch_pct": 1.41, "eta": "41:45:53", "max_grad_norm": 1.0, "loss": 1.1390413045883179, "grad_norm": 0.5077701807022095, "learning_rate": 3.504043126684636e-05}
+{"ts": "2025-12-23T15:04:31", "event": "train_log", "step": 198, "epoch": 0.0854368932038835, "progress_pct": 1.42, "epoch_pct": 1.42, "eta": "41:37:03", "max_grad_norm": 1.0, "loss": 1.1411432027816772, "grad_norm": 0.5527892112731934, "learning_rate": 3.5399820305480685e-05}
+{"ts": "2025-12-23T15:04:47", "event": "train_log", "step": 200, "epoch": 0.08629989212513485, "progress_pct": 1.44, "epoch_pct": 1.44, "eta": "41:30:16", "max_grad_norm": 1.0, "loss": 1.071260690689087, "grad_norm": 0.5572488903999329, "learning_rate": 3.575920934411501e-05}
+{"ts": "2025-12-23T15:15:42", "event": "train_log", "step": 200, "epoch": 0.08629989212513485, "progress_pct": 1.44, "epoch_pct": 1.44, "eta": "53:58:03", "max_grad_norm": 1.0, "eval_loss": 1.1519012451171875, "eval_runtime": 654.6055, "eval_samples_per_second": 3.147, "eval_steps_per_second": 3.147}
+{"ts": "2025-12-23T15:15:56", "event": "train_log", "step": 202, "epoch": 0.08716289104638619, "progress_pct": 1.45, "epoch_pct": 1.45, "eta": "53:41:57", "max_grad_norm": 1.0, "loss": 1.138135552406311, "grad_norm": 0.5134095549583435, "learning_rate": 3.611859838274933e-05}
+{"ts": "2025-12-23T15:16:11", "event": "train_log", "step": 204, "epoch": 0.08802588996763754, "progress_pct": 1.47, "epoch_pct": 1.47, "eta": "53:26:11", "max_grad_norm": 1.0, "loss": 1.111999273300171, "grad_norm": 0.5166040658950806, "learning_rate": 3.647798742138365e-05}
+{"ts": "2025-12-23T15:16:26", "event": "train_log", "step": 206, "epoch": 0.08888888888888889, "progress_pct": 1.48, "epoch_pct": 1.48, "eta": "53:11:24", "max_grad_norm": 1.0, "loss": 1.1031352281570435, "grad_norm": 0.5336993336677551, "learning_rate": 3.683737646001797e-05}
+{"ts": "2025-12-23T15:16:41", "event": "train_log", "step": 208, "epoch": 0.08975188781014024, "progress_pct": 1.5, "epoch_pct": 1.5, "eta": "52:57:00", "max_grad_norm": 1.0, "loss": 1.0388667583465576, "grad_norm": 0.8289600014686584, "learning_rate": 3.7196765498652294e-05}
+{"ts": "2025-12-23T15:16:56", "event": "train_log", "step": 210, "epoch": 0.09061488673139159, "progress_pct": 1.51, "epoch_pct": 1.51, "eta": "52:42:25", "max_grad_norm": 1.0, "loss": 1.0950241088867188, "grad_norm": 0.47992637753486633, "learning_rate": 3.755615453728661e-05}
+{"ts": "2025-12-23T15:17:11", "event": "train_log", "step": 212, "epoch": 0.09147788565264293, "progress_pct": 1.52, "epoch_pct": 1.52, "eta": "52:28:31", "max_grad_norm": 1.0, "loss": 1.0361733436584473, "grad_norm": 0.5629691481590271, "learning_rate": 3.7915543575920934e-05}
+{"ts": "2025-12-23T15:17:26", "event": "train_log", "step": 214, "epoch": 0.09234088457389428, "progress_pct": 1.54, "epoch_pct": 1.54, "eta": "52:14:21", "max_grad_norm": 1.0, "loss": 1.0922447443008423, "grad_norm": 0.5515111684799194, "learning_rate": 3.827493261455526e-05}
+{"ts": "2025-12-23T15:17:41", "event": "train_log", "step": 216, "epoch": 0.09320388349514563, "progress_pct": 1.55, "epoch_pct": 1.55, "eta": "52:00:25", "max_grad_norm": 1.0, "loss": 1.0866856575012207, "grad_norm": 0.5078643560409546, "learning_rate": 3.863432165318958e-05}
+{"ts": "2025-12-23T15:17:55", "event": "train_log", "step": 218, "epoch": 0.09406688241639698, "progress_pct": 1.57, "epoch_pct": 1.57, "eta": "51:46:07", "max_grad_norm": 1.0, "loss": 1.1231595277786255, "grad_norm": 0.6046127676963806, "learning_rate": 3.8993710691823904e-05}
+{"ts": "2025-12-23T15:18:09", "event": "train_log", "step": 220, "epoch": 0.09492988133764833, "progress_pct": 1.58, "epoch_pct": 1.58, "eta": "51:31:51", "max_grad_norm": 1.0, "loss": 1.099171757698059, "grad_norm": 0.6255762577056885, "learning_rate": 3.935309973045822e-05}
+{"ts": "2025-12-23T15:18:23", "event": "train_log", "step": 222, "epoch": 0.09579288025889968, "progress_pct": 1.6, "epoch_pct": 1.6, "eta": "51:18:20", "max_grad_norm": 1.0, "loss": 1.0557761192321777, "grad_norm": 0.6036638021469116, "learning_rate": 3.971248876909254e-05}
+{"ts": "2025-12-23T15:18:39", "event": "train_log", "step": 224, "epoch": 0.09665587918015102, "progress_pct": 1.61, "epoch_pct": 1.61, "eta": "51:06:10", "max_grad_norm": 1.0, "loss": 1.0467877388000488, "grad_norm": 0.5520529747009277, "learning_rate": 4.0071877807726867e-05}
+{"ts": "2025-12-23T15:18:53", "event": "train_log", "step": 226, "epoch": 0.09751887810140238, "progress_pct": 1.62, "epoch_pct": 1.63, "eta": "50:52:43", "max_grad_norm": 1.0, "loss": 1.17941153049469, "grad_norm": 0.5958684682846069, "learning_rate": 4.043126684636119e-05}
+{"ts": "2025-12-23T15:19:07", "event": "train_log", "step": 228, "epoch": 0.09838187702265372, "progress_pct": 1.64, "epoch_pct": 1.64, "eta": "50:39:35", "max_grad_norm": 1.0, "loss": 1.104217767715454, "grad_norm": 0.5283281803131104, "learning_rate": 4.079065588499551e-05}
+{"ts": "2025-12-23T15:19:22", "event": "train_log", "step": 230, "epoch": 0.09924487594390508, "progress_pct": 1.65, "epoch_pct": 1.65, "eta": "50:27:35", "max_grad_norm": 1.0, "loss": 1.0900640487670898, "grad_norm": 0.5608792901039124, "learning_rate": 4.115004492362983e-05}
+{"ts": "2025-12-23T15:19:37", "event": "train_log", "step": 232, "epoch": 0.10010787486515642, "progress_pct": 1.67, "epoch_pct": 1.67, "eta": "50:15:36", "max_grad_norm": 1.0, "loss": 0.9887422323226929, "grad_norm": 0.555964469909668, "learning_rate": 4.150943396226415e-05}
+{"ts": "2025-12-23T15:19:51", "event": "train_log", "step": 234, "epoch": 0.10097087378640776, "progress_pct": 1.68, "epoch_pct": 1.68, "eta": "50:03:26", "max_grad_norm": 1.0, "loss": 1.1298567056655884, "grad_norm": 0.5875785946846008, "learning_rate": 4.1868823000898476e-05}
+{"ts": "2025-12-23T15:20:06", "event": "train_log", "step": 236, "epoch": 0.10183387270765912, "progress_pct": 1.7, "epoch_pct": 1.7, "eta": "49:51:40", "max_grad_norm": 1.0, "loss": 1.0957067012786865, "grad_norm": 0.4544795751571655, "learning_rate": 4.222821203953279e-05}
+{"ts": "2025-12-23T15:20:21", "event": "train_log", "step": 238, "epoch": 0.10269687162891046, "progress_pct": 1.71, "epoch_pct": 1.71, "eta": "49:40:18", "max_grad_norm": 1.0, "loss": 1.0328738689422607, "grad_norm": 0.564145565032959, "learning_rate": 4.2587601078167116e-05}
+{"ts": "2025-12-23T15:20:35", "event": "train_log", "step": 240, "epoch": 0.10355987055016182, "progress_pct": 1.73, "epoch_pct": 1.73, "eta": "49:28:54", "max_grad_norm": 1.0, "loss": 1.1085515022277832, "grad_norm": 0.6285979747772217, "learning_rate": 4.294699011680144e-05}
+{"ts": "2025-12-23T15:20:49", "event": "train_log", "step": 242, "epoch": 0.10442286947141316, "progress_pct": 1.74, "epoch_pct": 1.74, "eta": "49:17:08", "max_grad_norm": 1.0, "loss": 1.1291271448135376, "grad_norm": 0.6442288756370544, "learning_rate": 4.330637915543576e-05}
+{"ts": "2025-12-23T15:21:03", "event": "train_log", "step": 244, "epoch": 0.1052858683926645, "progress_pct": 1.75, "epoch_pct": 1.75, "eta": "49:05:36", "max_grad_norm": 1.0, "loss": 1.1759567260742188, "grad_norm": 0.6137154698371887, "learning_rate": 4.3665768194070085e-05}
+{"ts": "2025-12-23T15:21:18", "event": "train_log", "step": 246, "epoch": 0.10614886731391586, "progress_pct": 1.77, "epoch_pct": 1.77, "eta": "48:55:19", "max_grad_norm": 1.0, "loss": 1.148414969444275, "grad_norm": 0.5906805992126465, "learning_rate": 4.402515723270441e-05}
+{"ts": "2025-12-23T15:21:35", "event": "train_log", "step": 248, "epoch": 0.1070118662351672, "progress_pct": 1.78, "epoch_pct": 1.78, "eta": "48:45:57", "max_grad_norm": 1.0, "loss": 1.0749616622924805, "grad_norm": 0.5382888913154602, "learning_rate": 4.438454627133873e-05}
+{"ts": "2025-12-23T15:21:49", "event": "train_log", "step": 250, "epoch": 0.10787486515641856, "progress_pct": 1.8, "epoch_pct": 1.8, "eta": "48:35:27", "max_grad_norm": 1.0, "loss": 1.2235801219940186, "grad_norm": 0.6185492873191833, "learning_rate": 4.474393530997305e-05}
+{"ts": "2025-12-23T15:22:04", "event": "train_log", "step": 252, "epoch": 0.1087378640776699, "progress_pct": 1.81, "epoch_pct": 1.81, "eta": "48:25:39", "max_grad_norm": 1.0, "loss": 1.1390639543533325, "grad_norm": 0.5981597900390625, "learning_rate": 4.5103324348607365e-05}
+{"ts": "2025-12-23T15:22:20", "event": "train_log", "step": 254, "epoch": 0.10960086299892124, "progress_pct": 1.83, "epoch_pct": 1.83, "eta": "48:16:04", "max_grad_norm": 1.0, "loss": 1.171774983406067, "grad_norm": 0.5664694905281067, "learning_rate": 4.546271338724169e-05}
+{"ts": "2025-12-23T15:22:35", "event": "train_log", "step": 256, "epoch": 0.1104638619201726, "progress_pct": 1.84, "epoch_pct": 1.84, "eta": "48:06:47", "max_grad_norm": 1.0, "loss": 1.1704237461090088, "grad_norm": 0.7071851491928101, "learning_rate": 4.582210242587601e-05}
+{"ts": "2025-12-23T15:22:50", "event": "train_log", "step": 258, "epoch": 0.11132686084142394, "progress_pct": 1.86, "epoch_pct": 1.86, "eta": "47:57:13", "max_grad_norm": 1.0, "loss": 1.0619677305221558, "grad_norm": 0.5815614461898804, "learning_rate": 4.6181491464510334e-05}
+{"ts": "2025-12-23T15:23:05", "event": "train_log", "step": 260, "epoch": 0.1121898597626753, "progress_pct": 1.87, "epoch_pct": 1.87, "eta": "47:47:38", "max_grad_norm": 1.0, "loss": 1.0824390649795532, "grad_norm": 0.6481915712356567, "learning_rate": 4.654088050314466e-05}
+{"ts": "2025-12-23T15:23:20", "event": "train_log", "step": 262, "epoch": 0.11305285868392664, "progress_pct": 1.88, "epoch_pct": 1.88, "eta": "47:38:33", "max_grad_norm": 1.0, "loss": 1.087929606437683, "grad_norm": 0.5988591313362122, "learning_rate": 4.690026954177898e-05}
+{"ts": "2025-12-23T15:23:35", "event": "train_log", "step": 264, "epoch": 0.113915857605178, "progress_pct": 1.9, "epoch_pct": 1.9, "eta": "47:29:21", "max_grad_norm": 1.0, "loss": 1.0936195850372314, "grad_norm": 0.6545296311378479, "learning_rate": 4.7259658580413304e-05}
+{"ts": "2025-12-23T15:23:50", "event": "train_log", "step": 266, "epoch": 0.11477885652642934, "progress_pct": 1.91, "epoch_pct": 1.91, "eta": "47:19:58", "max_grad_norm": 1.0, "loss": 1.0433681011199951, "grad_norm": 0.5826204419136047, "learning_rate": 4.761904761904762e-05}
+{"ts": "2025-12-23T15:24:04", "event": "train_log", "step": 268, "epoch": 0.11564185544768069, "progress_pct": 1.93, "epoch_pct": 1.93, "eta": "47:10:23", "max_grad_norm": 1.0, "loss": 1.0719536542892456, "grad_norm": 0.5907514095306396, "learning_rate": 4.7978436657681944e-05}
+{"ts": "2025-12-23T15:24:20", "event": "train_log", "step": 270, "epoch": 0.11650485436893204, "progress_pct": 1.94, "epoch_pct": 1.94, "eta": "47:02:19", "max_grad_norm": 1.0, "loss": 1.0231504440307617, "grad_norm": 0.524394154548645, "learning_rate": 4.833782569631627e-05}
+{"ts": "2025-12-23T15:24:35", "event": "train_log", "step": 272, "epoch": 0.11736785329018339, "progress_pct": 1.96, "epoch_pct": 1.96, "eta": "46:54:12", "max_grad_norm": 1.0, "loss": 0.9905915260314941, "grad_norm": 0.5472846031188965, "learning_rate": 4.869721473495058e-05}
+{"ts": "2025-12-23T15:24:49", "event": "train_log", "step": 274, "epoch": 0.11823085221143474, "progress_pct": 1.97, "epoch_pct": 1.97, "eta": "46:44:56", "max_grad_norm": 1.0, "loss": 1.213677167892456, "grad_norm": 0.727922260761261, "learning_rate": 4.9056603773584906e-05}
+{"ts": "2025-12-23T15:25:07", "event": "train_log", "step": 276, "epoch": 0.11909385113268608, "progress_pct": 1.98, "epoch_pct": 1.98, "eta": "46:38:35", "max_grad_norm": 1.0, "loss": 1.0052144527435303, "grad_norm": 0.6009684801101685, "learning_rate": 4.941599281221923e-05}
+{"ts": "2025-12-23T15:25:22", "event": "train_log", "step": 278, "epoch": 0.11995685005393743, "progress_pct": 2.0, "epoch_pct": 2.0, "eta": "46:30:17", "max_grad_norm": 1.0, "loss": 1.108136773109436, "grad_norm": 0.6564669013023376, "learning_rate": 4.977538185085355e-05}
+{"ts": "2025-12-23T15:25:39", "event": "train_log", "step": 280, "epoch": 0.12081984897518878, "progress_pct": 2.01, "epoch_pct": 2.01, "eta": "46:23:44", "max_grad_norm": 1.0, "loss": 0.9700815677642822, "grad_norm": 0.650074303150177, "learning_rate": 5.013477088948787e-05}
+{"ts": "2025-12-23T15:25:54", "event": "train_log", "step": 282, "epoch": 0.12168284789644013, "progress_pct": 2.03, "epoch_pct": 2.03, "eta": "46:15:42", "max_grad_norm": 1.0, "loss": 1.038031816482544, "grad_norm": 0.5772947072982788, "learning_rate": 5.04941599281222e-05}
+{"ts": "2025-12-23T15:26:09", "event": "train_log", "step": 284, "epoch": 0.12254584681769148, "progress_pct": 2.04, "epoch_pct": 2.04, "eta": "46:07:54", "max_grad_norm": 1.0, "loss": 1.1063730716705322, "grad_norm": 0.7293002009391785, "learning_rate": 5.0853548966756516e-05}
+{"ts": "2025-12-23T15:26:24", "event": "train_log", "step": 286, "epoch": 0.12340884573894283, "progress_pct": 2.06, "epoch_pct": 2.06, "eta": "45:59:50", "max_grad_norm": 1.0, "loss": 1.128495693206787, "grad_norm": 0.7937333583831787, "learning_rate": 5.1212938005390846e-05}
+{"ts": "2025-12-23T15:26:39", "event": "train_log", "step": 288, "epoch": 0.12427184466019417, "progress_pct": 2.07, "epoch_pct": 2.07, "eta": "45:52:23", "max_grad_norm": 1.0, "loss": 0.9438712000846863, "grad_norm": 0.48499324917793274, "learning_rate": 5.157232704402516e-05}
+{"ts": "2025-12-23T15:26:55", "event": "train_log", "step": 290, "epoch": 0.12513484358144553, "progress_pct": 2.09, "epoch_pct": 2.09, "eta": "45:45:35", "max_grad_norm": 1.0, "loss": 1.0872881412506104, "grad_norm": 0.6010656952857971, "learning_rate": 5.193171608265948e-05}
+{"ts": "2025-12-23T15:27:10", "event": "train_log", "step": 292, "epoch": 0.12599784250269688, "progress_pct": 2.1, "epoch_pct": 2.1, "eta": "45:37:43", "max_grad_norm": 1.0, "loss": 1.110992193222046, "grad_norm": 0.6240811944007874, "learning_rate": 5.22911051212938e-05}
+{"ts": "2025-12-23T15:27:24", "event": "train_log", "step": 294, "epoch": 0.1268608414239482, "progress_pct": 2.11, "epoch_pct": 2.11, "eta": "45:29:46", "max_grad_norm": 1.0, "loss": 1.1109752655029297, "grad_norm": 0.7172768712043762, "learning_rate": 5.265049415992812e-05}
+{"ts": "2025-12-23T15:27:40", "event": "train_log", "step": 296, "epoch": 0.12772384034519957, "progress_pct": 2.13, "epoch_pct": 2.13, "eta": "45:22:58", "max_grad_norm": 1.0, "loss": 1.05553138256073, "grad_norm": 0.6442400217056274, "learning_rate": 5.300988319856245e-05}
+{"ts": "2025-12-23T15:27:54", "event": "train_log", "step": 298, "epoch": 0.12858683926645093, "progress_pct": 2.14, "epoch_pct": 2.14, "eta": "45:15:08", "max_grad_norm": 1.0, "loss": 1.0717648267745972, "grad_norm": 0.7074702382087708, "learning_rate": 5.3369272237196765e-05}
+{"ts": "2025-12-23T15:28:10", "event": "train_log", "step": 300, "epoch": 0.12944983818770225, "progress_pct": 2.16, "epoch_pct": 2.16, "eta": "45:08:28", "max_grad_norm": 1.0, "loss": 0.9777541756629944, "grad_norm": 0.5277591347694397, "learning_rate": 5.3728661275831095e-05}
+{"ts": "2025-12-23T15:39:12", "event": "train_log", "step": 300, "epoch": 0.12944983818770225, "progress_pct": 2.16, "epoch_pct": 2.16, "eta": "53:29:04", "max_grad_norm": 1.0, "eval_loss": 1.0977506637573242, "eval_runtime": 662.1728, "eval_samples_per_second": 3.111, "eval_steps_per_second": 3.111}
+{"ts": "2025-12-23T15:39:26", "event": "train_log", "step": 302, "epoch": 0.1303128371089536, "progress_pct": 2.17, "epoch_pct": 2.17, "eta": "53:18:00", "max_grad_norm": 1.0, "loss": 1.075905203819275, "grad_norm": 0.7252246737480164, "learning_rate": 5.408805031446541e-05}
+{"ts": "2025-12-23T15:39:40", "event": "train_log", "step": 304, "epoch": 0.13117583603020497, "progress_pct": 2.19, "epoch_pct": 2.19, "eta": "53:07:00", "max_grad_norm": 1.0, "loss": 1.1117515563964844, "grad_norm": 0.7003294229507446, "learning_rate": 5.444743935309974e-05}
+{"ts": "2025-12-23T15:39:55", "event": "train_log", "step": 306, "epoch": 0.13203883495145632, "progress_pct": 2.2, "epoch_pct": 2.2, "eta": "52:56:51", "max_grad_norm": 1.0, "loss": 1.0289191007614136, "grad_norm": 0.5878211259841919, "learning_rate": 5.480682839173406e-05}
+{"ts": "2025-12-23T15:40:10", "event": "train_log", "step": 308, "epoch": 0.13290183387270765, "progress_pct": 2.21, "epoch_pct": 2.22, "eta": "52:46:52", "max_grad_norm": 1.0, "loss": 1.0199183225631714, "grad_norm": 0.7133644223213196, "learning_rate": 5.5166217430368374e-05}
+{"ts": "2025-12-23T15:40:25", "event": "train_log", "step": 310, "epoch": 0.133764832793959, "progress_pct": 2.23, "epoch_pct": 2.23, "eta": "52:36:44", "max_grad_norm": 1.0, "loss": 1.0132375955581665, "grad_norm": 0.6098423600196838, "learning_rate": 5.55256064690027e-05}
+{"ts": "2025-12-23T15:40:40", "event": "train_log", "step": 312, "epoch": 0.13462783171521037, "progress_pct": 2.24, "epoch_pct": 2.24, "eta": "52:26:34", "max_grad_norm": 1.0, "loss": 1.1595754623413086, "grad_norm": 0.6386916041374207, "learning_rate": 5.5884995507637014e-05}
+{"ts": "2025-12-23T15:40:54", "event": "train_log", "step": 314, "epoch": 0.1354908306364617, "progress_pct": 2.26, "epoch_pct": 2.26, "eta": "52:16:29", "max_grad_norm": 1.0, "loss": 1.0921307802200317, "grad_norm": 0.6563469767570496, "learning_rate": 5.6244384546271344e-05}
+{"ts": "2025-12-23T15:41:09", "event": "train_log", "step": 316, "epoch": 0.13635382955771305, "progress_pct": 2.27, "epoch_pct": 2.27, "eta": "52:06:41", "max_grad_norm": 1.0, "loss": 1.0200815200805664, "grad_norm": 0.6388015747070312, "learning_rate": 5.660377358490566e-05}
+{"ts": "2025-12-23T15:41:25", "event": "train_log", "step": 318, "epoch": 0.1372168284789644, "progress_pct": 2.29, "epoch_pct": 2.29, "eta": "51:57:59", "max_grad_norm": 1.0, "loss": 0.9339485764503479, "grad_norm": 0.6026274561882019, "learning_rate": 5.696316262353999e-05}
+{"ts": "2025-12-23T15:41:39", "event": "train_log", "step": 320, "epoch": 0.13807982740021574, "progress_pct": 2.3, "epoch_pct": 2.3, "eta": "51:48:21", "max_grad_norm": 1.0, "loss": 1.0268478393554688, "grad_norm": 0.619800865650177, "learning_rate": 5.732255166217431e-05}
+{"ts": "2025-12-23T15:41:54", "event": "train_log", "step": 322, "epoch": 0.1389428263214671, "progress_pct": 2.32, "epoch_pct": 2.32, "eta": "51:38:47", "max_grad_norm": 1.0, "loss": 1.1394236087799072, "grad_norm": 0.5924715399742126, "learning_rate": 5.768194070080862e-05}
+{"ts": "2025-12-23T15:42:09", "event": "train_log", "step": 324, "epoch": 0.13980582524271845, "progress_pct": 2.33, "epoch_pct": 2.33, "eta": "51:29:44", "max_grad_norm": 1.0, "loss": 1.002437949180603, "grad_norm": 0.6829012036323547, "learning_rate": 5.804132973944295e-05}
+{"ts": "2025-12-23T15:42:23", "event": "train_log", "step": 326, "epoch": 0.1406688241639698, "progress_pct": 2.34, "epoch_pct": 2.34, "eta": "51:20:16", "max_grad_norm": 1.0, "loss": 1.132503628730774, "grad_norm": 0.7012544274330139, "learning_rate": 5.840071877807727e-05}
+{"ts": "2025-12-23T15:42:37", "event": "train_log", "step": 328, "epoch": 0.14153182308522114, "progress_pct": 2.36, "epoch_pct": 2.36, "eta": "51:10:39", "max_grad_norm": 1.0, "loss": 1.1859129667282104, "grad_norm": 0.7921599745750427, "learning_rate": 5.876010781671159e-05}
+{"ts": "2025-12-23T15:42:52", "event": "train_log", "step": 330, "epoch": 0.1423948220064725, "progress_pct": 2.37, "epoch_pct": 2.37, "eta": "51:01:40", "max_grad_norm": 1.0, "loss": 1.0896776914596558, "grad_norm": 0.6373353004455566, "learning_rate": 5.9119496855345916e-05}
+{"ts": "2025-12-23T15:43:06", "event": "train_log", "step": 332, "epoch": 0.14325782092772385, "progress_pct": 2.39, "epoch_pct": 2.39, "eta": "50:52:33", "max_grad_norm": 1.0, "loss": 1.0691723823547363, "grad_norm": 0.6174030900001526, "learning_rate": 5.947888589398024e-05}
+{"ts": "2025-12-23T15:43:21", "event": "train_log", "step": 334, "epoch": 0.14412081984897518, "progress_pct": 2.4, "epoch_pct": 2.4, "eta": "50:44:02", "max_grad_norm": 1.0, "loss": 1.0144777297973633, "grad_norm": 0.5110617280006409, "learning_rate": 5.9838274932614556e-05}
+{"ts": "2025-12-23T15:43:37", "event": "train_log", "step": 336, "epoch": 0.14498381877022654, "progress_pct": 2.42, "epoch_pct": 2.42, "eta": "50:35:41", "max_grad_norm": 1.0, "loss": 0.9955101609230042, "grad_norm": 0.5580511093139648, "learning_rate": 6.019766397124887e-05}
+{"ts": "2025-12-23T15:43:52", "event": "train_log", "step": 338, "epoch": 0.1458468176914779, "progress_pct": 2.43, "epoch_pct": 2.43, "eta": "50:27:48", "max_grad_norm": 1.0, "loss": 0.9863013625144958, "grad_norm": 0.6427345275878906, "learning_rate": 6.05570530098832e-05}
+{"ts": "2025-12-23T15:44:07", "event": "train_log", "step": 340, "epoch": 0.14670981661272922, "progress_pct": 2.44, "epoch_pct": 2.45, "eta": "50:19:12", "max_grad_norm": 1.0, "loss": 1.0682255029678345, "grad_norm": 0.7464537024497986, "learning_rate": 6.091644204851752e-05}
+{"ts": "2025-12-23T15:44:21", "event": "train_log", "step": 342, "epoch": 0.14757281553398058, "progress_pct": 2.46, "epoch_pct": 2.46, "eta": "50:10:31", "max_grad_norm": 1.0, "loss": 1.034083366394043, "grad_norm": 0.599926769733429, "learning_rate": 6.127583108715184e-05}
+{"ts": "2025-12-23T15:44:36", "event": "train_log", "step": 344, "epoch": 0.14843581445523193, "progress_pct": 2.47, "epoch_pct": 2.47, "eta": "50:02:16", "max_grad_norm": 1.0, "loss": 1.0776089429855347, "grad_norm": 0.6320257186889648, "learning_rate": 6.163522012578616e-05}
+{"ts": "2025-12-23T15:44:51", "event": "train_log", "step": 346, "epoch": 0.1492988133764833, "progress_pct": 2.49, "epoch_pct": 2.49, "eta": "49:54:23", "max_grad_norm": 1.0, "loss": 1.0493087768554688, "grad_norm": 0.6565091013908386, "learning_rate": 6.199460916442049e-05}
+{"ts": "2025-12-23T15:45:06", "event": "train_log", "step": 348, "epoch": 0.15016181229773462, "progress_pct": 2.5, "epoch_pct": 2.5, "eta": "49:46:32", "max_grad_norm": 1.0, "loss": 1.0469218492507935, "grad_norm": 0.6512171626091003, "learning_rate": 6.23539982030548e-05}
+{"ts": "2025-12-23T15:45:20", "event": "train_log", "step": 350, "epoch": 0.15102481121898598, "progress_pct": 2.52, "epoch_pct": 2.52, "eta": "49:37:53", "max_grad_norm": 1.0, "loss": 1.0985081195831299, "grad_norm": 0.8487282991409302, "learning_rate": 6.271338724168913e-05}
+{"ts": "2025-12-23T15:45:34", "event": "train_log", "step": 352, "epoch": 0.15188781014023733, "progress_pct": 2.53, "epoch_pct": 2.53, "eta": "49:29:34", "max_grad_norm": 1.0, "loss": 1.0714176893234253, "grad_norm": 0.6718961596488953, "learning_rate": 6.307277628032345e-05}
+{"ts": "2025-12-23T15:45:48", "event": "train_log", "step": 354, "epoch": 0.15275080906148866, "progress_pct": 2.55, "epoch_pct": 2.55, "eta": "49:21:31", "max_grad_norm": 1.0, "loss": 1.0599322319030762, "grad_norm": 0.8175088167190552, "learning_rate": 6.343216531895777e-05}
+{"ts": "2025-12-23T15:46:04", "event": "train_log", "step": 356, "epoch": 0.15361380798274002, "progress_pct": 2.56, "epoch_pct": 2.56, "eta": "49:14:23", "max_grad_norm": 1.0, "loss": 0.9268131256103516, "grad_norm": 0.6359215378761292, "learning_rate": 6.37915543575921e-05}
+{"ts": "2025-12-23T15:46:19", "event": "train_log", "step": 358, "epoch": 0.15447680690399138, "progress_pct": 2.57, "epoch_pct": 2.57, "eta": "49:07:10", "max_grad_norm": 1.0, "loss": 0.9838354587554932, "grad_norm": 0.6423866748809814, "learning_rate": 6.415094339622641e-05}
+{"ts": "2025-12-23T15:46:33", "event": "train_log", "step": 360, "epoch": 0.1553398058252427, "progress_pct": 2.59, "epoch_pct": 2.59, "eta": "48:59:17", "max_grad_norm": 1.0, "loss": 1.048566460609436, "grad_norm": 0.6496716737747192, "learning_rate": 6.451033243486074e-05}
+{"ts": "2025-12-23T15:46:49", "event": "train_log", "step": 362, "epoch": 0.15620280474649406, "progress_pct": 2.6, "epoch_pct": 2.6, "eta": "48:52:03", "max_grad_norm": 1.0, "loss": 1.0910537242889404, "grad_norm": 0.6536920666694641, "learning_rate": 6.486972147349506e-05}
+{"ts": "2025-12-23T15:47:04", "event": "train_log", "step": 364, "epoch": 0.15706580366774542, "progress_pct": 2.62, "epoch_pct": 2.62, "eta": "48:44:57", "max_grad_norm": 1.0, "loss": 0.9971448183059692, "grad_norm": 0.5832068920135498, "learning_rate": 6.522911051212939e-05}
+{"ts": "2025-12-23T15:47:18", "event": "train_log", "step": 366, "epoch": 0.15792880258899678, "progress_pct": 2.63, "epoch_pct": 2.63, "eta": "48:37:22", "max_grad_norm": 1.0, "loss": 1.0496708154678345, "grad_norm": 0.6647719144821167, "learning_rate": 6.558849955076371e-05}
+{"ts": "2025-12-23T15:47:33", "event": "train_log", "step": 368, "epoch": 0.1587918015102481, "progress_pct": 2.65, "epoch_pct": 2.65, "eta": "48:30:09", "max_grad_norm": 1.0, "loss": 0.955894410610199, "grad_norm": 0.623252809047699, "learning_rate": 6.594788858939802e-05}
+{"ts": "2025-12-23T15:47:48", "event": "train_log", "step": 370, "epoch": 0.15965480043149946, "progress_pct": 2.66, "epoch_pct": 2.66, "eta": "48:23:07", "max_grad_norm": 1.0, "loss": 1.1304032802581787, "grad_norm": 0.6311860084533691, "learning_rate": 6.630727762803235e-05}
+{"ts": "2025-12-23T15:48:05", "event": "train_log", "step": 372, "epoch": 0.16051779935275082, "progress_pct": 2.67, "epoch_pct": 2.68, "eta": "48:17:09", "max_grad_norm": 1.0, "loss": 0.8746405243873596, "grad_norm": 0.5306481122970581, "learning_rate": 6.666666666666667e-05}
+{"ts": "2025-12-23T15:48:19", "event": "train_log", "step": 374, "epoch": 0.16138079827400215, "progress_pct": 2.69, "epoch_pct": 2.69, "eta": "48:10:10", "max_grad_norm": 1.0, "loss": 0.9104986786842346, "grad_norm": 0.6249631643295288, "learning_rate": 6.7026055705301e-05}
+{"ts": "2025-12-23T15:48:35", "event": "train_log", "step": 376, "epoch": 0.1622437971952535, "progress_pct": 2.7, "epoch_pct": 2.7, "eta": "48:03:37", "max_grad_norm": 1.0, "loss": 1.043666124343872, "grad_norm": 0.6243219971656799, "learning_rate": 6.738544474393532e-05}
+{"ts": "2025-12-23T15:48:49", "event": "train_log", "step": 378, "epoch": 0.16310679611650486, "progress_pct": 2.72, "epoch_pct": 2.72, "eta": "47:56:34", "max_grad_norm": 1.0, "loss": 1.0504906177520752, "grad_norm": 0.6833282113075256, "learning_rate": 6.774483378256963e-05}
+{"ts": "2025-12-23T15:49:03", "event": "train_log", "step": 380, "epoch": 0.16396979503775622, "progress_pct": 2.73, "epoch_pct": 2.73, "eta": "47:49:20", "max_grad_norm": 1.0, "loss": 1.0608166456222534, "grad_norm": 0.7124452590942383, "learning_rate": 6.810422282120395e-05}
+{"ts": "2025-12-23T15:49:17", "event": "train_log", "step": 382, "epoch": 0.16483279395900755, "progress_pct": 2.75, "epoch_pct": 2.75, "eta": "47:42:14", "max_grad_norm": 1.0, "loss": 1.1653732061386108, "grad_norm": 0.7520908117294312, "learning_rate": 6.846361185983828e-05}
+{"ts": "2025-12-23T15:49:33", "event": "train_log", "step": 384, "epoch": 0.1656957928802589, "progress_pct": 2.76, "epoch_pct": 2.76, "eta": "47:36:09", "max_grad_norm": 1.0, "loss": 1.0626367330551147, "grad_norm": 0.7121814489364624, "learning_rate": 6.88230008984726e-05}
+{"ts": "2025-12-23T15:49:48", "event": "train_log", "step": 386, "epoch": 0.16655879180151026, "progress_pct": 2.78, "epoch_pct": 2.78, "eta": "47:29:53", "max_grad_norm": 1.0, "loss": 1.012121319770813, "grad_norm": 0.6825008988380432, "learning_rate": 6.918238993710691e-05}
+{"ts": "2025-12-23T15:50:04", "event": "train_log", "step": 388, "epoch": 0.1674217907227616, "progress_pct": 2.79, "epoch_pct": 2.79, "eta": "47:23:38", "max_grad_norm": 1.0, "loss": 1.0576211214065552, "grad_norm": 0.4922940135002136, "learning_rate": 6.954177897574124e-05}
+{"ts": "2025-12-23T15:50:19", "event": "train_log", "step": 390, "epoch": 0.16828478964401294, "progress_pct": 2.8, "epoch_pct": 2.8, "eta": "47:17:19", "max_grad_norm": 1.0, "loss": 1.03916597366333, "grad_norm": 0.6122089624404907, "learning_rate": 6.990116801437556e-05}
+{"ts": "2025-12-23T15:50:33", "event": "train_log", "step": 392, "epoch": 0.1691477885652643, "progress_pct": 2.82, "epoch_pct": 2.82, "eta": "47:10:46", "max_grad_norm": 1.0, "loss": 1.17647123336792, "grad_norm": 0.6348981261253357, "learning_rate": 7.026055705300989e-05}
+{"ts": "2025-12-23T15:50:49", "event": "train_log", "step": 394, "epoch": 0.17001078748651563, "progress_pct": 2.83, "epoch_pct": 2.83, "eta": "47:04:44", "max_grad_norm": 1.0, "loss": 0.9095983505249023, "grad_norm": 0.6205878257751465, "learning_rate": 7.06199460916442e-05}
+{"ts": "2025-12-23T15:51:03", "event": "train_log", "step": 396, "epoch": 0.170873786407767, "progress_pct": 2.85, "epoch_pct": 2.85, "eta": "46:57:59", "max_grad_norm": 1.0, "loss": 1.082506775856018, "grad_norm": 0.61506187915802, "learning_rate": 7.097933513027853e-05}
+{"ts": "2025-12-23T15:51:18", "event": "train_log", "step": 398, "epoch": 0.17173678532901834, "progress_pct": 2.86, "epoch_pct": 2.86, "eta": "46:52:07", "max_grad_norm": 1.0, "loss": 1.0716280937194824, "grad_norm": 0.6481751799583435, "learning_rate": 7.133872416891285e-05}
+{"ts": "2025-12-23T15:51:36", "event": "train_log", "step": 400, "epoch": 0.1725997842502697, "progress_pct": 2.88, "epoch_pct": 2.88, "eta": "46:48:04", "max_grad_norm": 1.0, "loss": 0.9616814851760864, "grad_norm": 0.4871014952659607, "learning_rate": 7.169811320754717e-05}
+{"ts": "2025-12-23T16:02:45", "event": "train_log", "step": 400, "epoch": 0.1725997842502697, "progress_pct": 2.88, "epoch_pct": 2.88, "eta": "53:04:22", "max_grad_norm": 1.0, "eval_loss": 1.0649415254592896, "eval_runtime": 668.6025, "eval_samples_per_second": 3.081, "eval_steps_per_second": 3.081}
+{"ts": "2025-12-23T16:03:01", "event": "train_log", "step": 402, "epoch": 0.17346278317152103, "progress_pct": 2.89, "epoch_pct": 2.89, "eta": "52:56:52", "max_grad_norm": 1.0, "loss": 1.0475050210952759, "grad_norm": 0.5680040121078491, "learning_rate": 7.20575022461815e-05}
+{"ts": "2025-12-23T16:03:17", "event": "train_log", "step": 404, "epoch": 0.17432578209277239, "progress_pct": 2.9, "epoch_pct": 2.91, "eta": "52:49:29", "max_grad_norm": 1.0, "loss": 0.9851161241531372, "grad_norm": 0.6417813897132874, "learning_rate": 7.241689128481581e-05}
+{"ts": "2025-12-23T16:03:32", "event": "train_log", "step": 406, "epoch": 0.17518878101402374, "progress_pct": 2.92, "epoch_pct": 2.92, "eta": "52:41:57", "max_grad_norm": 1.0, "loss": 1.013339638710022, "grad_norm": 0.6600468158721924, "learning_rate": 7.277628032345014e-05}
+{"ts": "2025-12-23T16:03:48", "event": "train_log", "step": 408, "epoch": 0.17605177993527507, "progress_pct": 2.93, "epoch_pct": 2.93, "eta": "52:34:45", "max_grad_norm": 1.0, "loss": 0.9346804022789001, "grad_norm": 0.6733932495117188, "learning_rate": 7.313566936208446e-05}
+{"ts": "2025-12-23T16:04:03", "event": "train_log", "step": 410, "epoch": 0.17691477885652643, "progress_pct": 2.95, "epoch_pct": 2.95, "eta": "52:27:24", "max_grad_norm": 1.0, "loss": 0.9890368580818176, "grad_norm": 0.6812151074409485, "learning_rate": 7.349505840071879e-05}
+{"ts": "2025-12-23T16:04:19", "event": "train_log", "step": 412, "epoch": 0.17777777777777778, "progress_pct": 2.96, "epoch_pct": 2.96, "eta": "52:20:13", "max_grad_norm": 1.0, "loss": 0.8787848949432373, "grad_norm": 0.6380394697189331, "learning_rate": 7.385444743935311e-05}
+{"ts": "2025-12-23T16:04:35", "event": "train_log", "step": 414, "epoch": 0.1786407766990291, "progress_pct": 2.98, "epoch_pct": 2.98, "eta": "52:13:14", "max_grad_norm": 1.0, "loss": 1.0235728025436401, "grad_norm": 0.6004905700683594, "learning_rate": 7.421383647798742e-05}
+{"ts": "2025-12-23T16:04:50", "event": "train_log", "step": 416, "epoch": 0.17950377562028047, "progress_pct": 2.99, "epoch_pct": 2.99, "eta": "52:05:59", "max_grad_norm": 1.0, "loss": 0.9972385168075562, "grad_norm": 0.6569193005561829, "learning_rate": 7.457322551662175e-05}
+{"ts": "2025-12-23T16:05:07", "event": "train_log", "step": 418, "epoch": 0.18036677454153183, "progress_pct": 3.01, "epoch_pct": 3.01, "eta": "51:59:27", "max_grad_norm": 1.0, "loss": 0.9593698382377625, "grad_norm": 0.6761631369590759, "learning_rate": 7.493261455525607e-05}
+{"ts": "2025-12-23T16:05:22", "event": "train_log", "step": 420, "epoch": 0.18122977346278318, "progress_pct": 3.02, "epoch_pct": 3.02, "eta": "51:52:13", "max_grad_norm": 1.0, "loss": 1.0426853895187378, "grad_norm": 0.7328561544418335, "learning_rate": 7.529200359389039e-05}
+{"ts": "2025-12-23T16:05:38", "event": "train_log", "step": 422, "epoch": 0.1820927723840345, "progress_pct": 3.03, "epoch_pct": 3.03, "eta": "51:45:34", "max_grad_norm": 1.0, "loss": 0.9608182311058044, "grad_norm": 0.6256070137023926, "learning_rate": 7.56513926325247e-05}
+{"ts": "2025-12-23T16:05:54", "event": "train_log", "step": 424, "epoch": 0.18295577130528587, "progress_pct": 3.05, "epoch_pct": 3.05, "eta": "51:39:04", "max_grad_norm": 1.0, "loss": 1.0162668228149414, "grad_norm": 1.2549844980239868, "learning_rate": 7.601078167115903e-05}
+{"ts": "2025-12-23T16:06:10", "event": "train_log", "step": 426, "epoch": 0.18381877022653723, "progress_pct": 3.06, "epoch_pct": 3.06, "eta": "51:32:10", "max_grad_norm": 1.0, "loss": 1.130725383758545, "grad_norm": 0.6751510500907898, "learning_rate": 7.637017070979335e-05}
+{"ts": "2025-12-23T16:06:26", "event": "train_log", "step": 428, "epoch": 0.18468176914778855, "progress_pct": 3.08, "epoch_pct": 3.08, "eta": "51:25:44", "max_grad_norm": 1.0, "loss": 1.0384817123413086, "grad_norm": 0.7029808163642883, "learning_rate": 7.672955974842768e-05}
+{"ts": "2025-12-23T16:06:40", "event": "train_log", "step": 430, "epoch": 0.1855447680690399, "progress_pct": 3.09, "epoch_pct": 3.09, "eta": "51:18:17", "max_grad_norm": 1.0, "loss": 1.017020344734192, "grad_norm": 0.644353449344635, "learning_rate": 7.7088948787062e-05}
+{"ts": "2025-12-23T16:06:55", "event": "train_log", "step": 432, "epoch": 0.18640776699029127, "progress_pct": 3.11, "epoch_pct": 3.11, "eta": "51:11:42", "max_grad_norm": 1.0, "loss": 1.005354404449463, "grad_norm": 0.6784916520118713, "learning_rate": 7.744833782569631e-05}
+{"ts": "2025-12-23T16:07:11", "event": "train_log", "step": 434, "epoch": 0.1872707659115426, "progress_pct": 3.12, "epoch_pct": 3.12, "eta": "51:05:09", "max_grad_norm": 1.0, "loss": 1.026848316192627, "grad_norm": 0.5989449620246887, "learning_rate": 7.780772686433064e-05}
+{"ts": "2025-12-23T16:07:26", "event": "train_log", "step": 436, "epoch": 0.18813376483279395, "progress_pct": 3.13, "epoch_pct": 3.14, "eta": "50:58:09", "max_grad_norm": 1.0, "loss": 0.9891080856323242, "grad_norm": 0.6502639651298523, "learning_rate": 7.816711590296496e-05}
+{"ts": "2025-12-23T16:07:42", "event": "train_log", "step": 438, "epoch": 0.1889967637540453, "progress_pct": 3.15, "epoch_pct": 3.15, "eta": "50:51:59", "max_grad_norm": 1.0, "loss": 0.966316819190979, "grad_norm": 0.6176205277442932, "learning_rate": 7.852650494159929e-05}
+{"ts": "2025-12-23T16:07:56", "event": "train_log", "step": 440, "epoch": 0.18985976267529667, "progress_pct": 3.16, "epoch_pct": 3.16, "eta": "50:45:01", "max_grad_norm": 1.0, "loss": 1.123063087463379, "grad_norm": 0.6801626086235046, "learning_rate": 7.88858939802336e-05}
+{"ts": "2025-12-23T16:08:12", "event": "train_log", "step": 442, "epoch": 0.190722761596548, "progress_pct": 3.18, "epoch_pct": 3.18, "eta": "50:38:37", "max_grad_norm": 1.0, "loss": 1.0467073917388916, "grad_norm": 0.6718618273735046, "learning_rate": 7.924528301886794e-05}
+{"ts": "2025-12-23T16:08:26", "event": "train_log", "step": 444, "epoch": 0.19158576051779935, "progress_pct": 3.19, "epoch_pct": 3.19, "eta": "50:31:51", "max_grad_norm": 1.0, "loss": 1.0952889919281006, "grad_norm": 0.6761009097099304, "learning_rate": 7.960467205750225e-05}
+{"ts": "2025-12-23T16:08:41", "event": "train_log", "step": 446, "epoch": 0.1924487594390507, "progress_pct": 3.21, "epoch_pct": 3.21, "eta": "50:25:09", "max_grad_norm": 1.0, "loss": 0.954807698726654, "grad_norm": 0.6356327533721924, "learning_rate": 7.996406109613657e-05}
+{"ts": "2025-12-23T16:08:56", "event": "train_log", "step": 448, "epoch": 0.19331175836030204, "progress_pct": 3.22, "epoch_pct": 3.22, "eta": "50:18:54", "max_grad_norm": 1.0, "loss": 0.9941422343254089, "grad_norm": 0.6798669695854187, "learning_rate": 8.03234501347709e-05}
+{"ts": "2025-12-23T16:09:10", "event": "train_log", "step": 450, "epoch": 0.1941747572815534, "progress_pct": 3.24, "epoch_pct": 3.24, "eta": "50:12:11", "max_grad_norm": 1.0, "loss": 1.0351495742797852, "grad_norm": 0.6511302590370178, "learning_rate": 8.068283917340521e-05}
+{"ts": "2025-12-23T16:09:26", "event": "train_log", "step": 452, "epoch": 0.19503775620280475, "progress_pct": 3.25, "epoch_pct": 3.25, "eta": "50:05:53", "max_grad_norm": 1.0, "loss": 1.00546133518219, "grad_norm": 0.6061258912086487, "learning_rate": 8.104222821203954e-05}
+{"ts": "2025-12-23T16:09:40", "event": "train_log", "step": 454, "epoch": 0.1959007551240561, "progress_pct": 3.26, "epoch_pct": 3.27, "eta": "49:59:32", "max_grad_norm": 1.0, "loss": 1.0778460502624512, "grad_norm": 0.6278533935546875, "learning_rate": 8.140161725067386e-05}
+{"ts": "2025-12-23T16:09:55", "event": "train_log", "step": 456, "epoch": 0.19676375404530744, "progress_pct": 3.28, "epoch_pct": 3.28, "eta": "49:52:56", "max_grad_norm": 1.0, "loss": 1.0344486236572266, "grad_norm": 0.6866298317909241, "learning_rate": 8.176100628930818e-05}
+{"ts": "2025-12-23T16:10:09", "event": "train_log", "step": 458, "epoch": 0.1976267529665588, "progress_pct": 3.29, "epoch_pct": 3.29, "eta": "49:46:35", "max_grad_norm": 1.0, "loss": 1.0663033723831177, "grad_norm": 0.7338075041770935, "learning_rate": 8.212039532794251e-05}
+{"ts": "2025-12-23T16:10:24", "event": "train_log", "step": 460, "epoch": 0.19848975188781015, "progress_pct": 3.31, "epoch_pct": 3.31, "eta": "49:40:18", "max_grad_norm": 1.0, "loss": 0.9665339589118958, "grad_norm": 0.6811459064483643, "learning_rate": 8.247978436657682e-05}
+{"ts": "2025-12-23T16:10:39", "event": "train_log", "step": 462, "epoch": 0.19935275080906148, "progress_pct": 3.32, "epoch_pct": 3.32, "eta": "49:34:08", "max_grad_norm": 1.0, "loss": 1.024712324142456, "grad_norm": 0.6779627799987793, "learning_rate": 8.283917340521114e-05}
+{"ts": "2025-12-23T16:10:55", "event": "train_log", "step": 464, "epoch": 0.20021574973031284, "progress_pct": 3.34, "epoch_pct": 3.34, "eta": "49:28:44", "max_grad_norm": 1.0, "loss": 0.9699305295944214, "grad_norm": 0.6486892700195312, "learning_rate": 8.319856244384546e-05}
+{"ts": "2025-12-23T16:11:10", "event": "train_log", "step": 466, "epoch": 0.2010787486515642, "progress_pct": 3.35, "epoch_pct": 3.35, "eta": "49:22:45", "max_grad_norm": 1.0, "loss": 0.9540432095527649, "grad_norm": 0.7022278308868408, "learning_rate": 8.355795148247979e-05}
+{"ts": "2025-12-23T16:11:25", "event": "train_log", "step": 468, "epoch": 0.20194174757281552, "progress_pct": 3.36, "epoch_pct": 3.37, "eta": "49:16:57", "max_grad_norm": 1.0, "loss": 0.9253339767456055, "grad_norm": 0.5922990441322327, "learning_rate": 8.39173405211141e-05}
+{"ts": "2025-12-23T16:11:40", "event": "train_log", "step": 470, "epoch": 0.20280474649406688, "progress_pct": 3.38, "epoch_pct": 3.38, "eta": "49:10:57", "max_grad_norm": 1.0, "loss": 0.9987741112709045, "grad_norm": 0.7076792120933533, "learning_rate": 8.427672955974843e-05}
+{"ts": "2025-12-23T16:11:55", "event": "train_log", "step": 472, "epoch": 0.20366774541531824, "progress_pct": 3.39, "epoch_pct": 3.39, "eta": "49:05:17", "max_grad_norm": 1.0, "loss": 1.0249329805374146, "grad_norm": 0.6491380333900452, "learning_rate": 8.463611859838275e-05}
+{"ts": "2025-12-23T16:12:10", "event": "train_log", "step": 474, "epoch": 0.2045307443365696, "progress_pct": 3.41, "epoch_pct": 3.41, "eta": "48:59:18", "max_grad_norm": 1.0, "loss": 1.0577133893966675, "grad_norm": 0.6784211993217468, "learning_rate": 8.499550763701708e-05}
+{"ts": "2025-12-23T16:12:24", "event": "train_log", "step": 476, "epoch": 0.20539374325782092, "progress_pct": 3.42, "epoch_pct": 3.42, "eta": "48:53:15", "max_grad_norm": 1.0, "loss": 1.1312458515167236, "grad_norm": 0.6453303694725037, "learning_rate": 8.53548966756514e-05}
+{"ts": "2025-12-23T16:12:39", "event": "train_log", "step": 478, "epoch": 0.20625674217907228, "progress_pct": 3.44, "epoch_pct": 3.44, "eta": "48:47:20", "max_grad_norm": 1.0, "loss": 1.0592451095581055, "grad_norm": 0.7431377172470093, "learning_rate": 8.571428571428571e-05}
+{"ts": "2025-12-23T16:12:54", "event": "train_log", "step": 480, "epoch": 0.20711974110032363, "progress_pct": 3.45, "epoch_pct": 3.45, "eta": "48:41:48", "max_grad_norm": 1.0, "loss": 0.9337235689163208, "grad_norm": 0.6097649931907654, "learning_rate": 8.607367475292004e-05}
+{"ts": "2025-12-23T16:13:10", "event": "train_log", "step": 482, "epoch": 0.20798274002157496, "progress_pct": 3.47, "epoch_pct": 3.47, "eta": "48:36:43", "max_grad_norm": 1.0, "loss": 0.9088928699493408, "grad_norm": 0.5693124532699585, "learning_rate": 8.643306379155436e-05}
+{"ts": "2025-12-23T16:13:25", "event": "train_log", "step": 484, "epoch": 0.20884573894282632, "progress_pct": 3.48, "epoch_pct": 3.48, "eta": "48:31:03", "max_grad_norm": 1.0, "loss": 1.0729358196258545, "grad_norm": 0.7377229332923889, "learning_rate": 8.679245283018869e-05}
+{"ts": "2025-12-23T16:13:39", "event": "train_log", "step": 486, "epoch": 0.20970873786407768, "progress_pct": 3.49, "epoch_pct": 3.5, "eta": "48:25:14", "max_grad_norm": 1.0, "loss": 1.0428457260131836, "grad_norm": 0.7399470210075378, "learning_rate": 8.7151841868823e-05}
+{"ts": "2025-12-23T16:13:54", "event": "train_log", "step": 488, "epoch": 0.210571736785329, "progress_pct": 3.51, "epoch_pct": 3.51, "eta": "48:19:38", "max_grad_norm": 1.0, "loss": 0.9940266013145447, "grad_norm": 0.677052915096283, "learning_rate": 8.751123090745734e-05}
+{"ts": "2025-12-23T16:14:09", "event": "train_log", "step": 490, "epoch": 0.21143473570658036, "progress_pct": 3.52, "epoch_pct": 3.52, "eta": "48:14:16", "max_grad_norm": 1.0, "loss": 1.011808156967163, "grad_norm": 0.7126721739768982, "learning_rate": 8.787061994609165e-05}
+{"ts": "2025-12-23T16:14:23", "event": "train_log", "step": 492, "epoch": 0.21229773462783172, "progress_pct": 3.54, "epoch_pct": 3.54, "eta": "48:08:38", "max_grad_norm": 1.0, "loss": 1.0054185390472412, "grad_norm": 0.6663792729377747, "learning_rate": 8.823000898472597e-05}
+{"ts": "2025-12-23T16:14:38", "event": "train_log", "step": 494, "epoch": 0.21316073354908308, "progress_pct": 3.55, "epoch_pct": 3.55, "eta": "48:03:04", "max_grad_norm": 1.0, "loss": 1.0167138576507568, "grad_norm": 0.6661092042922974, "learning_rate": 8.85893980233603e-05}
+{"ts": "2025-12-23T16:14:52", "event": "train_log", "step": 496, "epoch": 0.2140237324703344, "progress_pct": 3.57, "epoch_pct": 3.57, "eta": "47:57:26", "max_grad_norm": 1.0, "loss": 1.1470818519592285, "grad_norm": 0.6975740194320679, "learning_rate": 8.894878706199461e-05}
+{"ts": "2025-12-23T16:15:07", "event": "train_log", "step": 498, "epoch": 0.21488673139158576, "progress_pct": 3.58, "epoch_pct": 3.58, "eta": "47:52:20", "max_grad_norm": 1.0, "loss": 0.9619631171226501, "grad_norm": 0.6594390869140625, "learning_rate": 8.930817610062893e-05}
+{"ts": "2025-12-23T16:15:21", "event": "train_log", "step": 500, "epoch": 0.21574973031283712, "progress_pct": 3.6, "epoch_pct": 3.6, "eta": "47:46:41", "max_grad_norm": 1.0, "loss": 0.9971368312835693, "grad_norm": 0.7216679453849792, "learning_rate": 8.966756513926325e-05}
+{"ts": "2025-12-23T16:26:21", "event": "train_log", "step": 500, "epoch": 0.21574973031283712, "progress_pct": 3.6, "epoch_pct": 3.6, "eta": "52:41:21", "max_grad_norm": 1.0, "eval_loss": 1.0417571067810059, "eval_runtime": 659.3112, "eval_samples_per_second": 3.124, "eval_steps_per_second": 3.124}
+{"ts": "2025-12-23T16:26:36", "event": "train_log", "step": 502, "epoch": 0.21661272923408845, "progress_pct": 3.61, "epoch_pct": 3.61, "eta": "52:34:54", "max_grad_norm": 1.0, "loss": 1.0307213068008423, "grad_norm": 0.6188210844993591, "learning_rate": 9.002695417789758e-05}
+{"ts": "2025-12-23T16:26:51", "event": "train_log", "step": 504, "epoch": 0.2174757281553398, "progress_pct": 3.62, "epoch_pct": 3.62, "eta": "52:28:57", "max_grad_norm": 1.0, "loss": 1.0188794136047363, "grad_norm": 0.6716445088386536, "learning_rate": 9.03863432165319e-05}
+{"ts": "2025-12-23T16:27:07", "event": "train_log", "step": 506, "epoch": 0.21833872707659116, "progress_pct": 3.64, "epoch_pct": 3.64, "eta": "52:22:45", "max_grad_norm": 1.0, "loss": 0.9764845967292786, "grad_norm": 0.6790863275527954, "learning_rate": 9.074573225516622e-05}
+{"ts": "2025-12-23T16:27:22", "event": "train_log", "step": 508, "epoch": 0.2192017259978425, "progress_pct": 3.65, "epoch_pct": 3.65, "eta": "52:16:47", "max_grad_norm": 1.0, "loss": 0.948829174041748, "grad_norm": 0.6764960289001465, "learning_rate": 9.110512129380054e-05}
+{"ts": "2025-12-23T16:27:38", "event": "train_log", "step": 510, "epoch": 0.22006472491909385, "progress_pct": 3.67, "epoch_pct": 3.67, "eta": "52:10:51", "max_grad_norm": 1.0, "loss": 1.008013129234314, "grad_norm": 0.6210965514183044, "learning_rate": 9.146451033243486e-05}
+{"ts": "2025-12-23T16:27:53", "event": "train_log", "step": 512, "epoch": 0.2209277238403452, "progress_pct": 3.68, "epoch_pct": 3.68, "eta": "52:04:32", "max_grad_norm": 1.0, "loss": 1.1662557125091553, "grad_norm": 0.7739297747612, "learning_rate": 9.182389937106919e-05}
+{"ts": "2025-12-23T16:28:08", "event": "train_log", "step": 514, "epoch": 0.22179072276159656, "progress_pct": 3.7, "epoch_pct": 3.7, "eta": "51:58:42", "max_grad_norm": 1.0, "loss": 1.0325161218643188, "grad_norm": 0.7055562138557434, "learning_rate": 9.21832884097035e-05}
+{"ts": "2025-12-23T16:28:25", "event": "train_log", "step": 516, "epoch": 0.2226537216828479, "progress_pct": 3.71, "epoch_pct": 3.71, "eta": "51:53:19", "max_grad_norm": 1.0, "loss": 1.00056791305542, "grad_norm": 0.6079210042953491, "learning_rate": 9.254267744833783e-05}
+{"ts": "2025-12-23T16:28:41", "event": "train_log", "step": 518, "epoch": 0.22351672060409924, "progress_pct": 3.72, "epoch_pct": 3.73, "eta": "51:47:59", "max_grad_norm": 1.0, "loss": 0.9422364234924316, "grad_norm": 0.5974318981170654, "learning_rate": 9.290206648697215e-05}
+{"ts": "2025-12-23T16:28:57", "event": "train_log", "step": 520, "epoch": 0.2243797195253506, "progress_pct": 3.74, "epoch_pct": 3.74, "eta": "51:42:16", "max_grad_norm": 1.0, "loss": 0.936336100101471, "grad_norm": 0.5963430404663086, "learning_rate": 9.326145552560648e-05}
+{"ts": "2025-12-23T16:29:13", "event": "train_log", "step": 522, "epoch": 0.22524271844660193, "progress_pct": 3.75, "epoch_pct": 3.75, "eta": "51:36:57", "max_grad_norm": 1.0, "loss": 1.0538607835769653, "grad_norm": 0.6823658347129822, "learning_rate": 9.36208445642408e-05}
+{"ts": "2025-12-23T16:29:29", "event": "train_log", "step": 524, "epoch": 0.2261057173678533, "progress_pct": 3.77, "epoch_pct": 3.77, "eta": "51:31:27", "max_grad_norm": 1.0, "loss": 1.0483653545379639, "grad_norm": 0.6409855484962463, "learning_rate": 9.398023360287511e-05}
+{"ts": "2025-12-23T16:29:44", "event": "train_log", "step": 526, "epoch": 0.22696871628910464, "progress_pct": 3.78, "epoch_pct": 3.78, "eta": "51:25:29", "max_grad_norm": 1.0, "loss": 0.9668049812316895, "grad_norm": 0.6867254376411438, "learning_rate": 9.433962264150944e-05}
+{"ts": "2025-12-23T16:30:00", "event": "train_log", "step": 528, "epoch": 0.227831715210356, "progress_pct": 3.8, "epoch_pct": 3.8, "eta": "51:19:55", "max_grad_norm": 1.0, "loss": 1.008763313293457, "grad_norm": 0.5690792798995972, "learning_rate": 9.469901168014376e-05}
+{"ts": "2025-12-23T16:30:15", "event": "train_log", "step": 530, "epoch": 0.22869471413160733, "progress_pct": 3.81, "epoch_pct": 3.81, "eta": "51:14:16", "max_grad_norm": 1.0, "loss": 1.0816441774368286, "grad_norm": 0.5964897274971008, "learning_rate": 9.505840071877809e-05}
+{"ts": "2025-12-23T16:30:31", "event": "train_log", "step": 532, "epoch": 0.2295577130528587, "progress_pct": 3.83, "epoch_pct": 3.83, "eta": "51:08:58", "max_grad_norm": 1.0, "loss": 0.9265700578689575, "grad_norm": 0.627419114112854, "learning_rate": 9.54177897574124e-05}
+{"ts": "2025-12-23T16:30:46", "event": "train_log", "step": 534, "epoch": 0.23042071197411004, "progress_pct": 3.84, "epoch_pct": 3.84, "eta": "51:03:17", "max_grad_norm": 1.0, "loss": 0.9804646372795105, "grad_norm": 0.5862151980400085, "learning_rate": 9.577717879604674e-05}
+{"ts": "2025-12-23T16:31:03", "event": "train_log", "step": 536, "epoch": 0.23128371089536137, "progress_pct": 3.85, "epoch_pct": 3.85, "eta": "50:58:18", "max_grad_norm": 1.0, "loss": 0.9627988934516907, "grad_norm": 0.5573718547821045, "learning_rate": 9.613656783468105e-05}
+{"ts": "2025-12-23T16:31:18", "event": "train_log", "step": 538, "epoch": 0.23214670981661273, "progress_pct": 3.87, "epoch_pct": 3.87, "eta": "50:53:03", "max_grad_norm": 1.0, "loss": 1.0012824535369873, "grad_norm": 0.6705166101455688, "learning_rate": 9.649595687331537e-05}
+{"ts": "2025-12-23T16:31:33", "event": "train_log", "step": 540, "epoch": 0.23300970873786409, "progress_pct": 3.88, "epoch_pct": 3.88, "eta": "50:47:28", "max_grad_norm": 1.0, "loss": 0.9568162560462952, "grad_norm": 0.6251236796379089, "learning_rate": 9.685534591194969e-05}
+{"ts": "2025-12-23T16:31:48", "event": "train_log", "step": 542, "epoch": 0.23387270765911541, "progress_pct": 3.9, "epoch_pct": 3.9, "eta": "50:41:48", "max_grad_norm": 1.0, "loss": 1.031549334526062, "grad_norm": 0.6466493010520935, "learning_rate": 9.7214734950584e-05}
+{"ts": "2025-12-23T16:32:03", "event": "train_log", "step": 544, "epoch": 0.23473570658036677, "progress_pct": 3.91, "epoch_pct": 3.91, "eta": "50:36:21", "max_grad_norm": 1.0, "loss": 0.8603643774986267, "grad_norm": 0.5183866024017334, "learning_rate": 9.757412398921833e-05}
+{"ts": "2025-12-23T16:32:18", "event": "train_log", "step": 546, "epoch": 0.23559870550161813, "progress_pct": 3.93, "epoch_pct": 3.93, "eta": "50:30:59", "max_grad_norm": 1.0, "loss": 1.0365077257156372, "grad_norm": 0.6725775599479675, "learning_rate": 9.793351302785265e-05}
+{"ts": "2025-12-23T16:32:34", "event": "train_log", "step": 548, "epoch": 0.23646170442286948, "progress_pct": 3.94, "epoch_pct": 3.94, "eta": "50:25:45", "max_grad_norm": 1.0, "loss": 0.9304701089859009, "grad_norm": 0.5972357988357544, "learning_rate": 9.829290206648698e-05}
+{"ts": "2025-12-23T16:32:50", "event": "train_log", "step": 550, "epoch": 0.2373247033441208, "progress_pct": 3.95, "epoch_pct": 3.96, "eta": "50:20:43", "max_grad_norm": 1.0, "loss": 0.9575805068016052, "grad_norm": 0.5319957733154297, "learning_rate": 9.86522911051213e-05}
+{"ts": "2025-12-23T16:33:05", "event": "train_log", "step": 552, "epoch": 0.23818770226537217, "progress_pct": 3.97, "epoch_pct": 3.97, "eta": "50:15:19", "max_grad_norm": 1.0, "loss": 1.0307214260101318, "grad_norm": 0.6502835750579834, "learning_rate": 9.901168014375562e-05}
+{"ts": "2025-12-23T16:33:18", "event": "train_log", "step": 554, "epoch": 0.23905070118662353, "progress_pct": 3.98, "epoch_pct": 3.98, "eta": "50:09:33", "max_grad_norm": 1.0, "loss": 1.05185067653656, "grad_norm": 0.6734047532081604, "learning_rate": 9.937106918238994e-05}
+{"ts": "2025-12-23T16:33:35", "event": "train_log", "step": 556, "epoch": 0.23991370010787486, "progress_pct": 4.0, "epoch_pct": 4.0, "eta": "50:04:46", "max_grad_norm": 1.0, "loss": 1.0190176963806152, "grad_norm": 0.5667978525161743, "learning_rate": 9.973045822102426e-05}
+{"ts": "2025-12-23T16:33:50", "event": "train_log", "step": 558, "epoch": 0.2407766990291262, "progress_pct": 4.01, "epoch_pct": 4.01, "eta": "49:59:40", "max_grad_norm": 1.0, "loss": 1.076182246208191, "grad_norm": 0.6370418667793274, "learning_rate": 0.00010008984725965857}
+{"ts": "2025-12-23T16:34:05", "event": "train_log", "step": 560, "epoch": 0.24163969795037757, "progress_pct": 4.03, "epoch_pct": 4.03, "eta": "49:54:25", "max_grad_norm": 1.0, "loss": 1.0408724546432495, "grad_norm": 0.689719021320343, "learning_rate": 0.0001004492362982929}
+{"ts": "2025-12-23T16:34:21", "event": "train_log", "step": 562, "epoch": 0.2425026968716289, "progress_pct": 4.04, "epoch_pct": 4.04, "eta": "49:49:51", "max_grad_norm": 1.0, "loss": 0.9869902729988098, "grad_norm": 0.6304254531860352, "learning_rate": 0.00010080862533692723}
+{"ts": "2025-12-23T16:34:37", "event": "train_log", "step": 564, "epoch": 0.24336569579288025, "progress_pct": 4.06, "epoch_pct": 4.06, "eta": "49:44:53", "max_grad_norm": 1.0, "loss": 1.0198370218276978, "grad_norm": 0.6797420382499695, "learning_rate": 0.00010116801437556156}
+{"ts": "2025-12-23T16:34:52", "event": "train_log", "step": 566, "epoch": 0.2442286947141316, "progress_pct": 4.07, "epoch_pct": 4.07, "eta": "49:39:54", "max_grad_norm": 1.0, "loss": 0.9947441816329956, "grad_norm": 0.5993657112121582, "learning_rate": 0.00010152740341419587}
+{"ts": "2025-12-23T16:35:08", "event": "train_log", "step": 568, "epoch": 0.24509169363538297, "progress_pct": 4.08, "epoch_pct": 4.08, "eta": "49:35:07", "max_grad_norm": 1.0, "loss": 0.9722896814346313, "grad_norm": 0.6369836330413818, "learning_rate": 0.0001018867924528302}
+{"ts": "2025-12-23T16:35:23", "event": "train_log", "step": 570, "epoch": 0.2459546925566343, "progress_pct": 4.1, "epoch_pct": 4.1, "eta": "49:30:12", "max_grad_norm": 1.0, "loss": 0.9716570973396301, "grad_norm": 0.6942457556724548, "learning_rate": 0.00010224618149146453}
+{"ts": "2025-12-23T16:35:39", "event": "train_log", "step": 572, "epoch": 0.24681769147788565, "progress_pct": 4.11, "epoch_pct": 4.11, "eta": "49:25:34", "max_grad_norm": 1.0, "loss": 0.9797524213790894, "grad_norm": 0.5403370261192322, "learning_rate": 0.00010260557053009883}
+{"ts": "2025-12-23T16:35:55", "event": "train_log", "step": 574, "epoch": 0.247680690399137, "progress_pct": 4.13, "epoch_pct": 4.13, "eta": "49:20:49", "max_grad_norm": 1.0, "loss": 0.985367476940155, "grad_norm": 0.5207529067993164, "learning_rate": 0.00010296495956873316}
+{"ts": "2025-12-23T16:36:09", "event": "train_log", "step": 576, "epoch": 0.24854368932038834, "progress_pct": 4.14, "epoch_pct": 4.14, "eta": "49:15:41", "max_grad_norm": 1.0, "loss": 1.075042724609375, "grad_norm": 0.6751103401184082, "learning_rate": 0.00010332434860736748}
+{"ts": "2025-12-23T16:36:24", "event": "train_log", "step": 578, "epoch": 0.2494066882416397, "progress_pct": 4.16, "epoch_pct": 4.16, "eta": "49:10:43", "max_grad_norm": 1.0, "loss": 0.9273878335952759, "grad_norm": 0.565331220626831, "learning_rate": 0.0001036837376460018}
+{"ts": "2025-12-23T16:36:40", "event": "train_log", "step": 580, "epoch": 0.25026968716289105, "progress_pct": 4.17, "epoch_pct": 4.17, "eta": "49:06:13", "max_grad_norm": 1.0, "loss": 0.9872279763221741, "grad_norm": 0.6858948469161987, "learning_rate": 0.00010404312668463612}
+{"ts": "2025-12-23T16:36:55", "event": "train_log", "step": 582, "epoch": 0.2511326860841424, "progress_pct": 4.18, "epoch_pct": 4.19, "eta": "49:01:15", "max_grad_norm": 1.0, "loss": 1.0038671493530273, "grad_norm": 0.7091426253318787, "learning_rate": 0.00010440251572327044}
+{"ts": "2025-12-23T16:37:10", "event": "train_log", "step": 584, "epoch": 0.25199568500539377, "progress_pct": 4.2, "epoch_pct": 4.2, "eta": "48:56:27", "max_grad_norm": 1.0, "loss": 1.0109868049621582, "grad_norm": 0.6493771076202393, "learning_rate": 0.00010476190476190477}
+{"ts": "2025-12-23T16:37:25", "event": "train_log", "step": 586, "epoch": 0.25285868392664507, "progress_pct": 4.21, "epoch_pct": 4.21, "eta": "48:51:45", "max_grad_norm": 1.0, "loss": 1.0020402669906616, "grad_norm": 0.6107586622238159, "learning_rate": 0.00010512129380053907}
+{"ts": "2025-12-23T16:37:40", "event": "train_log", "step": 588, "epoch": 0.2537216828478964, "progress_pct": 4.23, "epoch_pct": 4.23, "eta": "48:46:52", "max_grad_norm": 1.0, "loss": 0.961039662361145, "grad_norm": 0.6878048181533813, "learning_rate": 0.0001054806828391734}
+{"ts": "2025-12-23T16:37:54", "event": "train_log", "step": 590, "epoch": 0.2545846817691478, "progress_pct": 4.24, "epoch_pct": 4.24, "eta": "48:41:55", "max_grad_norm": 1.0, "loss": 0.9725209474563599, "grad_norm": 0.664034903049469, "learning_rate": 0.00010584007187780773}
+{"ts": "2025-12-23T16:38:09", "event": "train_log", "step": 592, "epoch": 0.25544768069039914, "progress_pct": 4.26, "epoch_pct": 4.26, "eta": "48:37:11", "max_grad_norm": 1.0, "loss": 0.9907437562942505, "grad_norm": 0.6399680376052856, "learning_rate": 0.00010619946091644206}
+{"ts": "2025-12-23T16:38:25", "event": "train_log", "step": 594, "epoch": 0.2563106796116505, "progress_pct": 4.27, "epoch_pct": 4.27, "eta": "48:32:55", "max_grad_norm": 1.0, "loss": 0.9650095701217651, "grad_norm": 0.6163286566734314, "learning_rate": 0.00010655884995507636}
+{"ts": "2025-12-23T16:38:40", "event": "train_log", "step": 596, "epoch": 0.25717367853290185, "progress_pct": 4.29, "epoch_pct": 4.29, "eta": "48:28:26", "max_grad_norm": 1.0, "loss": 1.0102758407592773, "grad_norm": 0.6008322238922119, "learning_rate": 0.0001069182389937107}
+{"ts": "2025-12-23T16:38:55", "event": "train_log", "step": 598, "epoch": 0.2580366774541532, "progress_pct": 4.3, "epoch_pct": 4.3, "eta": "48:23:48", "max_grad_norm": 1.0, "loss": 0.9101885557174683, "grad_norm": 0.6752071380615234, "learning_rate": 0.00010727762803234502}
+{"ts": "2025-12-23T16:39:10", "event": "train_log", "step": 600, "epoch": 0.2588996763754045, "progress_pct": 4.31, "epoch_pct": 4.31, "eta": "48:19:16", "max_grad_norm": 1.0, "loss": 1.0461398363113403, "grad_norm": 0.6789175868034363, "learning_rate": 0.00010763701707097935}
+{"ts": "2025-12-23T16:49:58", "event": "train_log", "step": 600, "epoch": 0.2588996763754045, "progress_pct": 4.31, "epoch_pct": 4.31, "eta": "52:18:52", "max_grad_norm": 1.0, "eval_loss": 1.021111011505127, "eval_runtime": 648.1611, "eval_samples_per_second": 3.178, "eval_steps_per_second": 3.178}
+{"ts": "2025-12-23T16:50:13", "event": "train_log", "step": 602, "epoch": 0.25976267529665586, "progress_pct": 4.33, "epoch_pct": 4.33, "eta": "52:13:25", "max_grad_norm": 1.0, "loss": 0.9582418203353882, "grad_norm": 0.5660730600357056, "learning_rate": 0.00010799640610961366}
+{"ts": "2025-12-23T16:50:28", "event": "train_log", "step": 604, "epoch": 0.2606256742179072, "progress_pct": 4.34, "epoch_pct": 4.34, "eta": "52:07:52", "max_grad_norm": 1.0, "loss": 1.0763746500015259, "grad_norm": 0.6726544499397278, "learning_rate": 0.00010835579514824799}
+{"ts": "2025-12-23T16:50:42", "event": "train_log", "step": 606, "epoch": 0.2614886731391586, "progress_pct": 4.36, "epoch_pct": 4.36, "eta": "52:02:31", "max_grad_norm": 1.0, "loss": 1.0432032346725464, "grad_norm": 0.6068508625030518, "learning_rate": 0.00010871518418688232}
+{"ts": "2025-12-23T16:50:58", "event": "train_log", "step": 608, "epoch": 0.26235167206040994, "progress_pct": 4.37, "epoch_pct": 4.37, "eta": "51:57:18", "max_grad_norm": 1.0, "loss": 0.9830516576766968, "grad_norm": 0.5731637477874756, "learning_rate": 0.00010907457322551662}
+{"ts": "2025-12-23T16:51:13", "event": "train_log", "step": 610, "epoch": 0.2632146709816613, "progress_pct": 4.39, "epoch_pct": 4.39, "eta": "51:52:03", "max_grad_norm": 1.0, "loss": 1.0442042350769043, "grad_norm": 0.6777567267417908, "learning_rate": 0.00010943396226415095}
+{"ts": "2025-12-23T16:51:28", "event": "train_log", "step": 612, "epoch": 0.26407766990291265, "progress_pct": 4.4, "epoch_pct": 4.4, "eta": "51:46:58", "max_grad_norm": 1.0, "loss": 1.0001944303512573, "grad_norm": 0.6372506618499756, "learning_rate": 0.00010979335130278528}
+{"ts": "2025-12-23T16:51:43", "event": "train_log", "step": 614, "epoch": 0.26494066882416395, "progress_pct": 4.41, "epoch_pct": 4.42, "eta": "51:41:44", "max_grad_norm": 1.0, "loss": 1.035884141921997, "grad_norm": 0.6606221795082092, "learning_rate": 0.0001101527403414196}
+{"ts": "2025-12-23T16:51:59", "event": "train_log", "step": 616, "epoch": 0.2658036677454153, "progress_pct": 4.43, "epoch_pct": 4.43, "eta": "51:36:54", "max_grad_norm": 1.0, "loss": 0.9403397440910339, "grad_norm": 0.6083229780197144, "learning_rate": 0.00011051212938005391}
+{"ts": "2025-12-23T16:52:14", "event": "train_log", "step": 618, "epoch": 0.26666666666666666, "progress_pct": 4.44, "epoch_pct": 4.44, "eta": "51:32:04", "max_grad_norm": 1.0, "loss": 0.9274454116821289, "grad_norm": 0.6318517923355103, "learning_rate": 0.00011087151841868823}
+{"ts": "2025-12-23T16:52:30", "event": "train_log", "step": 620, "epoch": 0.267529665587918, "progress_pct": 4.46, "epoch_pct": 4.46, "eta": "51:27:16", "max_grad_norm": 1.0, "loss": 0.9883754253387451, "grad_norm": 0.628190279006958, "learning_rate": 0.00011123090745732256}
+{"ts": "2025-12-23T16:52:45", "event": "train_log", "step": 622, "epoch": 0.2683926645091694, "progress_pct": 4.47, "epoch_pct": 4.47, "eta": "51:22:10", "max_grad_norm": 1.0, "loss": 1.0317535400390625, "grad_norm": 0.5961961150169373, "learning_rate": 0.00011159029649595688}
+{"ts": "2025-12-23T16:53:00", "event": "train_log", "step": 624, "epoch": 0.26925566343042073, "progress_pct": 4.49, "epoch_pct": 4.49, "eta": "51:17:18", "max_grad_norm": 1.0, "loss": 0.9776126742362976, "grad_norm": 0.5995341539382935, "learning_rate": 0.00011194968553459119}
+{"ts": "2025-12-23T16:53:16", "event": "train_log", "step": 626, "epoch": 0.27011866235167203, "progress_pct": 4.5, "epoch_pct": 4.5, "eta": "51:12:26", "max_grad_norm": 1.0, "loss": 1.0112378597259521, "grad_norm": 0.6639334559440613, "learning_rate": 0.00011230907457322552}
+{"ts": "2025-12-23T16:53:31", "event": "train_log", "step": 628, "epoch": 0.2709816612729234, "progress_pct": 4.52, "epoch_pct": 4.52, "eta": "51:07:29", "max_grad_norm": 1.0, "loss": 1.0553804636001587, "grad_norm": 0.6348621249198914, "learning_rate": 0.00011266846361185985}
+{"ts": "2025-12-23T16:53:47", "event": "train_log", "step": 630, "epoch": 0.27184466019417475, "progress_pct": 4.53, "epoch_pct": 4.53, "eta": "51:02:56", "max_grad_norm": 1.0, "loss": 1.025888442993164, "grad_norm": 0.5929805040359497, "learning_rate": 0.00011302785265049416}
+{"ts": "2025-12-23T16:54:02", "event": "train_log", "step": 632, "epoch": 0.2727076591154261, "progress_pct": 4.54, "epoch_pct": 4.55, "eta": "50:58:11", "max_grad_norm": 1.0, "loss": 1.02956223487854, "grad_norm": 0.6052366495132446, "learning_rate": 0.00011338724168912849}
+{"ts": "2025-12-23T16:54:17", "event": "train_log", "step": 634, "epoch": 0.27357065803667746, "progress_pct": 4.56, "epoch_pct": 4.56, "eta": "50:53:17", "max_grad_norm": 1.0, "loss": 0.989752471446991, "grad_norm": 0.6494882106781006, "learning_rate": 0.00011374663072776282}
+{"ts": "2025-12-23T16:54:33", "event": "train_log", "step": 636, "epoch": 0.2744336569579288, "progress_pct": 4.57, "epoch_pct": 4.57, "eta": "50:48:40", "max_grad_norm": 1.0, "loss": 1.0030683279037476, "grad_norm": 0.6005767583847046, "learning_rate": 0.00011410601976639712}
+{"ts": "2025-12-23T16:54:48", "event": "train_log", "step": 638, "epoch": 0.2752966558791802, "progress_pct": 4.59, "epoch_pct": 4.59, "eta": "50:43:59", "max_grad_norm": 1.0, "loss": 1.002000093460083, "grad_norm": 0.6478356122970581, "learning_rate": 0.00011446540880503145}
+{"ts": "2025-12-23T16:55:03", "event": "train_log", "step": 640, "epoch": 0.2761596548004315, "progress_pct": 4.6, "epoch_pct": 4.6, "eta": "50:38:57", "max_grad_norm": 1.0, "loss": 0.9807654023170471, "grad_norm": 0.5804725289344788, "learning_rate": 0.00011482479784366578}
+{"ts": "2025-12-23T16:55:18", "event": "train_log", "step": 642, "epoch": 0.27702265372168283, "progress_pct": 4.62, "epoch_pct": 4.62, "eta": "50:34:26", "max_grad_norm": 1.0, "loss": 0.9841892123222351, "grad_norm": 0.632530689239502, "learning_rate": 0.00011518418688230011}
+{"ts": "2025-12-23T16:55:35", "event": "train_log", "step": 644, "epoch": 0.2778856526429342, "progress_pct": 4.63, "epoch_pct": 4.63, "eta": "50:30:19", "max_grad_norm": 1.0, "loss": 0.8902478814125061, "grad_norm": 0.5340113639831543, "learning_rate": 0.00011554357592093441}
+{"ts": "2025-12-23T16:55:51", "event": "train_log", "step": 646, "epoch": 0.27874865156418555, "progress_pct": 4.64, "epoch_pct": 4.65, "eta": "50:25:52", "max_grad_norm": 1.0, "loss": 0.9019404649734497, "grad_norm": 0.5901665091514587, "learning_rate": 0.00011590296495956874}
+{"ts": "2025-12-23T16:56:05", "event": "train_log", "step": 648, "epoch": 0.2796116504854369, "progress_pct": 4.66, "epoch_pct": 4.66, "eta": "50:20:58", "max_grad_norm": 1.0, "loss": 0.9384423494338989, "grad_norm": 0.666589617729187, "learning_rate": 0.00011626235399820307}
+{"ts": "2025-12-23T16:56:20", "event": "train_log", "step": 650, "epoch": 0.28047464940668826, "progress_pct": 4.67, "epoch_pct": 4.67, "eta": "50:16:16", "max_grad_norm": 1.0, "loss": 1.0666629076004028, "grad_norm": 0.7000334858894348, "learning_rate": 0.00011662174303683737}
+{"ts": "2025-12-23T16:56:36", "event": "train_log", "step": 652, "epoch": 0.2813376483279396, "progress_pct": 4.69, "epoch_pct": 4.69, "eta": "50:11:55", "max_grad_norm": 1.0, "loss": 1.000019907951355, "grad_norm": 0.663663923740387, "learning_rate": 0.0001169811320754717}
+{"ts": "2025-12-23T16:56:51", "event": "train_log", "step": 654, "epoch": 0.2822006472491909, "progress_pct": 4.7, "epoch_pct": 4.7, "eta": "50:07:28", "max_grad_norm": 1.0, "loss": 0.9450293183326721, "grad_norm": 0.6097694039344788, "learning_rate": 0.00011734052111410603}
+{"ts": "2025-12-23T16:57:08", "event": "train_log", "step": 656, "epoch": 0.2830636461704423, "progress_pct": 4.72, "epoch_pct": 4.72, "eta": "50:03:24", "max_grad_norm": 1.0, "loss": 0.9480894207954407, "grad_norm": 0.6130967140197754, "learning_rate": 0.00011769991015274035}
+{"ts": "2025-12-23T16:57:22", "event": "train_log", "step": 658, "epoch": 0.28392664509169363, "progress_pct": 4.73, "epoch_pct": 4.73, "eta": "49:58:33", "max_grad_norm": 1.0, "loss": 1.1377143859863281, "grad_norm": 0.7091249227523804, "learning_rate": 0.00011805929919137467}
+{"ts": "2025-12-23T16:57:37", "event": "train_log", "step": 660, "epoch": 0.284789644012945, "progress_pct": 4.75, "epoch_pct": 4.75, "eta": "49:54:08", "max_grad_norm": 1.0, "loss": 0.9421243667602539, "grad_norm": 0.6556766629219055, "learning_rate": 0.00011841868823000898}
+{"ts": "2025-12-23T16:57:53", "event": "train_log", "step": 662, "epoch": 0.28565264293419634, "progress_pct": 4.76, "epoch_pct": 4.76, "eta": "49:50:04", "max_grad_norm": 1.0, "loss": 0.9726828336715698, "grad_norm": 0.6682968735694885, "learning_rate": 0.00011877807726864331}
+{"ts": "2025-12-23T16:58:09", "event": "train_log", "step": 664, "epoch": 0.2865156418554477, "progress_pct": 4.77, "epoch_pct": 4.78, "eta": "49:45:47", "max_grad_norm": 1.0, "loss": 0.8996511697769165, "grad_norm": 0.5224708914756775, "learning_rate": 0.00011913746630727762}
+{"ts": "2025-12-23T16:58:24", "event": "train_log", "step": 666, "epoch": 0.287378640776699, "progress_pct": 4.79, "epoch_pct": 4.79, "eta": "49:41:16", "max_grad_norm": 1.0, "loss": 0.9679517149925232, "grad_norm": 0.5914195775985718, "learning_rate": 0.00011949685534591195}
+{"ts": "2025-12-23T16:58:39", "event": "train_log", "step": 668, "epoch": 0.28824163969795036, "progress_pct": 4.8, "epoch_pct": 4.8, "eta": "49:36:46", "max_grad_norm": 1.0, "loss": 0.8743209838867188, "grad_norm": 0.6175519824028015, "learning_rate": 0.00011985624438454628}
+{"ts": "2025-12-23T16:58:55", "event": "train_log", "step": 670, "epoch": 0.2891046386192017, "progress_pct": 4.82, "epoch_pct": 4.82, "eta": "49:32:53", "max_grad_norm": 1.0, "loss": 0.9741992354393005, "grad_norm": 0.6019226312637329, "learning_rate": 0.0001202156334231806}
+{"ts": "2025-12-23T16:59:09", "event": "train_log", "step": 672, "epoch": 0.28996763754045307, "progress_pct": 4.83, "epoch_pct": 4.83, "eta": "49:28:15", "max_grad_norm": 1.0, "loss": 0.9516472816467285, "grad_norm": 0.6080542206764221, "learning_rate": 0.00012057502246181491}
+{"ts": "2025-12-23T16:59:23", "event": "train_log", "step": 674, "epoch": 0.29083063646170443, "progress_pct": 4.85, "epoch_pct": 4.85, "eta": "49:23:37", "max_grad_norm": 1.0, "loss": 1.122761607170105, "grad_norm": 0.5885615944862366, "learning_rate": 0.00012093441150044924}
+{"ts": "2025-12-23T16:59:39", "event": "train_log", "step": 676, "epoch": 0.2916936353829558, "progress_pct": 4.86, "epoch_pct": 4.86, "eta": "49:19:20", "max_grad_norm": 1.0, "loss": 1.0105189085006714, "grad_norm": 0.6635209918022156, "learning_rate": 0.00012129380053908357}
+{"ts": "2025-12-23T16:59:54", "event": "train_log", "step": 678, "epoch": 0.29255663430420714, "progress_pct": 4.87, "epoch_pct": 4.88, "eta": "49:15:05", "max_grad_norm": 1.0, "loss": 0.906292200088501, "grad_norm": 0.5805009007453918, "learning_rate": 0.0001216531895777179}
+{"ts": "2025-12-23T17:00:09", "event": "train_log", "step": 680, "epoch": 0.29341963322545844, "progress_pct": 4.89, "epoch_pct": 4.89, "eta": "49:10:55", "max_grad_norm": 1.0, "loss": 1.009568691253662, "grad_norm": 0.5980029702186584, "learning_rate": 0.0001220125786163522}
+{"ts": "2025-12-23T17:00:24", "event": "train_log", "step": 682, "epoch": 0.2942826321467098, "progress_pct": 4.9, "epoch_pct": 4.9, "eta": "49:06:48", "max_grad_norm": 1.0, "loss": 1.0373667478561401, "grad_norm": 0.6797705292701721, "learning_rate": 0.00012237196765498652}
+{"ts": "2025-12-23T17:00:39", "event": "train_log", "step": 684, "epoch": 0.29514563106796116, "progress_pct": 4.92, "epoch_pct": 4.92, "eta": "49:02:34", "max_grad_norm": 1.0, "loss": 0.9758188724517822, "grad_norm": 0.6280547976493835, "learning_rate": 0.00012273135669362085}
+{"ts": "2025-12-23T17:00:55", "event": "train_log", "step": 686, "epoch": 0.2960086299892125, "progress_pct": 4.93, "epoch_pct": 4.93, "eta": "48:58:43", "max_grad_norm": 1.0, "loss": 0.9111692905426025, "grad_norm": 0.511608898639679, "learning_rate": 0.00012309074573225515}
+{"ts": "2025-12-23T17:01:11", "event": "train_log", "step": 688, "epoch": 0.29687162891046387, "progress_pct": 4.95, "epoch_pct": 4.95, "eta": "48:54:42", "max_grad_norm": 1.0, "loss": 0.8865921497344971, "grad_norm": 0.5781835317611694, "learning_rate": 0.00012345013477088948}
+{"ts": "2025-12-23T17:01:27", "event": "train_log", "step": 690, "epoch": 0.2977346278317152, "progress_pct": 4.96, "epoch_pct": 4.96, "eta": "48:50:46", "max_grad_norm": 1.0, "loss": 0.9768189191818237, "grad_norm": 0.6514166593551636, "learning_rate": 0.0001238095238095238}
+{"ts": "2025-12-23T17:01:42", "event": "train_log", "step": 692, "epoch": 0.2985976267529666, "progress_pct": 4.98, "epoch_pct": 4.98, "eta": "48:46:45", "max_grad_norm": 1.0, "loss": 0.9991607069969177, "grad_norm": 0.6109189987182617, "learning_rate": 0.00012416891284815814}
+{"ts": "2025-12-23T17:01:58", "event": "train_log", "step": 694, "epoch": 0.2994606256742179, "progress_pct": 4.99, "epoch_pct": 4.99, "eta": "48:42:52", "max_grad_norm": 1.0, "loss": 0.9548360705375671, "grad_norm": 0.6598902344703674, "learning_rate": 0.00012452830188679244}
+{"ts": "2025-12-23T17:02:13", "event": "train_log", "step": 696, "epoch": 0.30032362459546924, "progress_pct": 5.0, "epoch_pct": 5.01, "eta": "48:38:49", "max_grad_norm": 1.0, "loss": 0.992988109588623, "grad_norm": 0.5633156895637512, "learning_rate": 0.00012488769092542677}
+{"ts": "2025-12-23T17:02:28", "event": "train_log", "step": 698, "epoch": 0.3011866235167206, "progress_pct": 5.02, "epoch_pct": 5.02, "eta": "48:34:50", "max_grad_norm": 1.0, "loss": 0.9709890484809875, "grad_norm": 0.6098802089691162, "learning_rate": 0.0001252470799640611}
+{"ts": "2025-12-23T17:02:44", "event": "train_log", "step": 700, "epoch": 0.30204962243797195, "progress_pct": 5.03, "epoch_pct": 5.03, "eta": "48:30:54", "max_grad_norm": 1.0, "loss": 1.018282175064087, "grad_norm": 0.6197102665901184, "learning_rate": 0.0001256064690026954}
+{"ts": "2025-12-23T17:13:39", "event": "train_log", "step": 700, "epoch": 0.30204962243797195, "progress_pct": 5.03, "epoch_pct": 5.03, "eta": "51:57:01", "max_grad_norm": 1.0, "eval_loss": 1.0030721426010132, "eval_runtime": 655.4533, "eval_samples_per_second": 3.143, "eval_steps_per_second": 3.143}
+{"ts": "2025-12-23T17:13:53", "event": "train_log", "step": 702, "epoch": 0.3029126213592233, "progress_pct": 5.05, "epoch_pct": 5.05, "eta": "51:52:04", "max_grad_norm": 1.0, "loss": 0.9147283434867859, "grad_norm": 0.5817480683326721, "learning_rate": 0.00012596585804132974}
+{"ts": "2025-12-23T17:14:07", "event": "train_log", "step": 704, "epoch": 0.30377562028047467, "progress_pct": 5.06, "epoch_pct": 5.06, "eta": "51:47:15", "max_grad_norm": 1.0, "loss": 0.9318362474441528, "grad_norm": 0.5976696014404297, "learning_rate": 0.00012632524707996407}
+{"ts": "2025-12-23T17:14:22", "event": "train_log", "step": 706, "epoch": 0.304638619201726, "progress_pct": 5.08, "epoch_pct": 5.08, "eta": "51:42:36", "max_grad_norm": 1.0, "loss": 0.9500927925109863, "grad_norm": 0.6389723420143127, "learning_rate": 0.0001266846361185984}
+{"ts": "2025-12-23T17:14:37", "event": "train_log", "step": 708, "epoch": 0.3055016181229773, "progress_pct": 5.09, "epoch_pct": 5.09, "eta": "51:37:54", "max_grad_norm": 1.0, "loss": 1.0271424055099487, "grad_norm": 0.6485719084739685, "learning_rate": 0.0001270440251572327}
+{"ts": "2025-12-23T17:14:51", "event": "train_log", "step": 710, "epoch": 0.3063646170442287, "progress_pct": 5.1, "epoch_pct": 5.11, "eta": "51:33:09", "max_grad_norm": 1.0, "loss": 0.9781906008720398, "grad_norm": 0.5802455544471741, "learning_rate": 0.00012740341419586703}
+{"ts": "2025-12-23T17:15:06", "event": "train_log", "step": 712, "epoch": 0.30722761596548004, "progress_pct": 5.12, "epoch_pct": 5.12, "eta": "51:28:34", "max_grad_norm": 1.0, "loss": 1.0195324420928955, "grad_norm": 0.6359356641769409, "learning_rate": 0.00012776280323450136}
+{"ts": "2025-12-23T17:15:21", "event": "train_log", "step": 714, "epoch": 0.3080906148867314, "progress_pct": 5.13, "epoch_pct": 5.13, "eta": "51:24:02", "max_grad_norm": 1.0, "loss": 0.9250738024711609, "grad_norm": 0.5975426435470581, "learning_rate": 0.00012812219227313566}
+{"ts": "2025-12-23T17:15:36", "event": "train_log", "step": 716, "epoch": 0.30895361380798275, "progress_pct": 5.15, "epoch_pct": 5.15, "eta": "51:19:30", "max_grad_norm": 1.0, "loss": 0.9888015985488892, "grad_norm": 0.643110454082489, "learning_rate": 0.00012848158131177}
+{"ts": "2025-12-23T17:15:50", "event": "train_log", "step": 718, "epoch": 0.3098166127292341, "progress_pct": 5.16, "epoch_pct": 5.16, "eta": "51:14:58", "max_grad_norm": 1.0, "loss": 0.9709514379501343, "grad_norm": 0.6043205261230469, "learning_rate": 0.00012884097035040432}
+{"ts": "2025-12-23T17:16:06", "event": "train_log", "step": 720, "epoch": 0.3106796116504854, "progress_pct": 5.18, "epoch_pct": 5.18, "eta": "51:10:41", "max_grad_norm": 1.0, "loss": 1.0272964239120483, "grad_norm": 0.5687094926834106, "learning_rate": 0.00012920035938903865}
+{"ts": "2025-12-23T17:16:21", "event": "train_log", "step": 722, "epoch": 0.31154261057173677, "progress_pct": 5.19, "epoch_pct": 5.19, "eta": "51:06:21", "max_grad_norm": 1.0, "loss": 0.9370370507240295, "grad_norm": 0.5688400864601135, "learning_rate": 0.00012955974842767296}
+{"ts": "2025-12-23T17:16:37", "event": "train_log", "step": 724, "epoch": 0.3124056094929881, "progress_pct": 5.21, "epoch_pct": 5.21, "eta": "51:02:04", "max_grad_norm": 1.0, "loss": 0.9535608291625977, "grad_norm": 0.5610610246658325, "learning_rate": 0.00012991913746630729}
+{"ts": "2025-12-23T17:16:51", "event": "train_log", "step": 726, "epoch": 0.3132686084142395, "progress_pct": 5.22, "epoch_pct": 5.22, "eta": "50:57:28", "max_grad_norm": 1.0, "loss": 1.0188907384872437, "grad_norm": 0.6338257193565369, "learning_rate": 0.00013027852650494162}
+{"ts": "2025-12-23T17:17:06", "event": "train_log", "step": 728, "epoch": 0.31413160733549084, "progress_pct": 5.23, "epoch_pct": 5.24, "eta": "50:53:06", "max_grad_norm": 1.0, "loss": 0.9253716468811035, "grad_norm": 0.5365633368492126, "learning_rate": 0.00013063791554357592}
+{"ts": "2025-12-23T17:17:21", "event": "train_log", "step": 730, "epoch": 0.3149946062567422, "progress_pct": 5.25, "epoch_pct": 5.25, "eta": "50:48:47", "max_grad_norm": 1.0, "loss": 0.8941492438316345, "grad_norm": 0.5599163174629211, "learning_rate": 0.00013099730458221025}
+{"ts": "2025-12-23T17:17:35", "event": "train_log", "step": 732, "epoch": 0.31585760517799355, "progress_pct": 5.26, "epoch_pct": 5.26, "eta": "50:44:20", "max_grad_norm": 1.0, "loss": 0.9831459522247314, "grad_norm": 0.6059780716896057, "learning_rate": 0.00013135669362084458}
+{"ts": "2025-12-23T17:17:50", "event": "train_log", "step": 734, "epoch": 0.31672060409924485, "progress_pct": 5.28, "epoch_pct": 5.28, "eta": "50:40:06", "max_grad_norm": 1.0, "loss": 0.9332310557365417, "grad_norm": 0.5596494078636169, "learning_rate": 0.0001317160826594789}
+{"ts": "2025-12-23T17:18:05", "event": "train_log", "step": 736, "epoch": 0.3175836030204962, "progress_pct": 5.29, "epoch_pct": 5.29, "eta": "50:35:54", "max_grad_norm": 1.0, "loss": 0.9082580208778381, "grad_norm": 0.5618010759353638, "learning_rate": 0.0001320754716981132}
+{"ts": "2025-12-23T17:18:19", "event": "train_log", "step": 738, "epoch": 0.31844660194174756, "progress_pct": 5.31, "epoch_pct": 5.31, "eta": "50:31:22", "max_grad_norm": 1.0, "loss": 1.008690357208252, "grad_norm": 0.6412109732627869, "learning_rate": 0.00013243486073674754}
+{"ts": "2025-12-23T17:18:34", "event": "train_log", "step": 740, "epoch": 0.3193096008629989, "progress_pct": 5.32, "epoch_pct": 5.32, "eta": "50:27:09", "max_grad_norm": 1.0, "loss": 0.9597798585891724, "grad_norm": 0.5742355585098267, "learning_rate": 0.00013279424977538187}
+{"ts": "2025-12-23T17:18:49", "event": "train_log", "step": 742, "epoch": 0.3201725997842503, "progress_pct": 5.34, "epoch_pct": 5.34, "eta": "50:22:46", "max_grad_norm": 1.0, "loss": 0.989331841468811, "grad_norm": 0.6470226645469666, "learning_rate": 0.00013315363881401617}
+{"ts": "2025-12-23T17:19:03", "event": "train_log", "step": 744, "epoch": 0.32103559870550163, "progress_pct": 5.35, "epoch_pct": 5.35, "eta": "50:18:30", "max_grad_norm": 1.0, "loss": 0.8677343130111694, "grad_norm": 0.5598039031028748, "learning_rate": 0.0001335130278526505}
+{"ts": "2025-12-23T17:19:18", "event": "train_log", "step": 746, "epoch": 0.321898597626753, "progress_pct": 5.36, "epoch_pct": 5.36, "eta": "50:14:23", "max_grad_norm": 1.0, "loss": 0.9462730288505554, "grad_norm": 0.5441372990608215, "learning_rate": 0.00013387241689128483}
+{"ts": "2025-12-23T17:19:33", "event": "train_log", "step": 748, "epoch": 0.3227615965480043, "progress_pct": 5.38, "epoch_pct": 5.38, "eta": "50:10:16", "max_grad_norm": 1.0, "loss": 0.994694173336029, "grad_norm": 0.5858626365661621, "learning_rate": 0.00013423180592991916}
+{"ts": "2025-12-23T17:19:49", "event": "train_log", "step": 750, "epoch": 0.32362459546925565, "progress_pct": 5.39, "epoch_pct": 5.39, "eta": "50:06:14", "max_grad_norm": 1.0, "loss": 0.9387269616127014, "grad_norm": 0.511372447013855, "learning_rate": 0.00013459119496855347}
+{"ts": "2025-12-23T17:20:04", "event": "train_log", "step": 752, "epoch": 0.324487594390507, "progress_pct": 5.41, "epoch_pct": 5.41, "eta": "50:02:19", "max_grad_norm": 1.0, "loss": 0.9473881721496582, "grad_norm": 0.47798457741737366, "learning_rate": 0.0001349505840071878}
+{"ts": "2025-12-23T17:20:19", "event": "train_log", "step": 754, "epoch": 0.32535059331175836, "progress_pct": 5.42, "epoch_pct": 5.42, "eta": "49:58:17", "max_grad_norm": 1.0, "loss": 0.9375183582305908, "grad_norm": 0.5907022953033447, "learning_rate": 0.0001353099730458221}
+{"ts": "2025-12-23T17:20:34", "event": "train_log", "step": 756, "epoch": 0.3262135922330097, "progress_pct": 5.44, "epoch_pct": 5.44, "eta": "49:54:07", "max_grad_norm": 1.0, "loss": 1.028738260269165, "grad_norm": 0.618733286857605, "learning_rate": 0.00013566936208445643}
+{"ts": "2025-12-23T17:20:49", "event": "train_log", "step": 758, "epoch": 0.3270765911542611, "progress_pct": 5.45, "epoch_pct": 5.45, "eta": "49:50:19", "max_grad_norm": 1.0, "loss": 0.9420192241668701, "grad_norm": 0.5234512090682983, "learning_rate": 0.00013602875112309076}
+{"ts": "2025-12-23T17:21:05", "event": "train_log", "step": 760, "epoch": 0.32793959007551243, "progress_pct": 5.46, "epoch_pct": 5.47, "eta": "49:46:33", "max_grad_norm": 1.0, "loss": 1.0252270698547363, "grad_norm": 0.7036319971084595, "learning_rate": 0.00013638814016172506}
+{"ts": "2025-12-23T17:21:20", "event": "train_log", "step": 762, "epoch": 0.32880258899676373, "progress_pct": 5.48, "epoch_pct": 5.48, "eta": "49:42:37", "max_grad_norm": 1.0, "loss": 0.8453778028488159, "grad_norm": 0.5543172359466553, "learning_rate": 0.0001367475292003594}
+{"ts": "2025-12-23T17:21:36", "event": "train_log", "step": 764, "epoch": 0.3296655879180151, "progress_pct": 5.49, "epoch_pct": 5.49, "eta": "49:38:48", "max_grad_norm": 1.0, "loss": 0.8659937977790833, "grad_norm": 0.5438711643218994, "learning_rate": 0.0001371069182389937}
+{"ts": "2025-12-23T17:21:51", "event": "train_log", "step": 766, "epoch": 0.33052858683926645, "progress_pct": 5.51, "epoch_pct": 5.51, "eta": "49:34:57", "max_grad_norm": 1.0, "loss": 1.038142442703247, "grad_norm": 0.6390914916992188, "learning_rate": 0.00013746630727762803}
+{"ts": "2025-12-23T17:22:07", "event": "train_log", "step": 768, "epoch": 0.3313915857605178, "progress_pct": 5.52, "epoch_pct": 5.52, "eta": "49:31:22", "max_grad_norm": 1.0, "loss": 0.899932861328125, "grad_norm": 0.50070720911026, "learning_rate": 0.00013782569631626236}
+{"ts": "2025-12-23T17:22:24", "event": "train_log", "step": 770, "epoch": 0.33225458468176916, "progress_pct": 5.54, "epoch_pct": 5.54, "eta": "49:27:51", "max_grad_norm": 1.0, "loss": 0.9712884426116943, "grad_norm": 0.5982286334037781, "learning_rate": 0.00013818508535489669}
+{"ts": "2025-12-23T17:22:39", "event": "train_log", "step": 772, "epoch": 0.3331175836030205, "progress_pct": 5.55, "epoch_pct": 5.55, "eta": "49:24:06", "max_grad_norm": 1.0, "loss": 0.9427542686462402, "grad_norm": 0.6588822603225708, "learning_rate": 0.000138544474393531}
+{"ts": "2025-12-23T17:22:55", "event": "train_log", "step": 774, "epoch": 0.3339805825242718, "progress_pct": 5.57, "epoch_pct": 5.57, "eta": "49:20:23", "max_grad_norm": 1.0, "loss": 0.8961561918258667, "grad_norm": 0.6022042632102966, "learning_rate": 0.00013890386343216532}
+{"ts": "2025-12-23T17:23:11", "event": "train_log", "step": 776, "epoch": 0.3348435814455232, "progress_pct": 5.58, "epoch_pct": 5.58, "eta": "49:16:50", "max_grad_norm": 1.0, "loss": 0.9525937438011169, "grad_norm": 0.6595642566680908, "learning_rate": 0.00013926325247079965}
+{"ts": "2025-12-23T17:23:26", "event": "train_log", "step": 778, "epoch": 0.33570658036677453, "progress_pct": 5.59, "epoch_pct": 5.6, "eta": "49:13:05", "max_grad_norm": 1.0, "loss": 0.9218845367431641, "grad_norm": 0.5210421681404114, "learning_rate": 0.00013962264150943395}
+{"ts": "2025-12-23T17:23:42", "event": "train_log", "step": 780, "epoch": 0.3365695792880259, "progress_pct": 5.61, "epoch_pct": 5.61, "eta": "49:09:31", "max_grad_norm": 1.0, "loss": 0.877951443195343, "grad_norm": 0.549669623374939, "learning_rate": 0.00013998203054806828}
+{"ts": "2025-12-23T17:23:58", "event": "train_log", "step": 782, "epoch": 0.33743257820927725, "progress_pct": 5.62, "epoch_pct": 5.62, "eta": "49:05:55", "max_grad_norm": 1.0, "loss": 0.8670064210891724, "grad_norm": 0.5360157489776611, "learning_rate": 0.0001403414195867026}
+{"ts": "2025-12-23T17:24:14", "event": "train_log", "step": 784, "epoch": 0.3382955771305286, "progress_pct": 5.64, "epoch_pct": 5.64, "eta": "49:02:32", "max_grad_norm": 1.0, "loss": 0.9561367630958557, "grad_norm": 0.614734947681427, "learning_rate": 0.00014070080862533694}
+{"ts": "2025-12-23T17:24:30", "event": "train_log", "step": 786, "epoch": 0.33915857605177996, "progress_pct": 5.65, "epoch_pct": 5.65, "eta": "48:59:03", "max_grad_norm": 1.0, "loss": 0.9132505059242249, "grad_norm": 0.5798251628875732, "learning_rate": 0.00014106019766397124}
+{"ts": "2025-12-23T17:24:46", "event": "train_log", "step": 788, "epoch": 0.34002157497303126, "progress_pct": 5.67, "epoch_pct": 5.67, "eta": "48:55:28", "max_grad_norm": 1.0, "loss": 0.9297707080841064, "grad_norm": 0.6267077326774597, "learning_rate": 0.00014141958670260557}
+{"ts": "2025-12-23T17:25:01", "event": "train_log", "step": 790, "epoch": 0.3408845738942826, "progress_pct": 5.68, "epoch_pct": 5.68, "eta": "48:51:56", "max_grad_norm": 1.0, "loss": 0.9382412433624268, "grad_norm": 0.6045349836349487, "learning_rate": 0.0001417789757412399}
+{"ts": "2025-12-23T17:25:17", "event": "train_log", "step": 792, "epoch": 0.341747572815534, "progress_pct": 5.69, "epoch_pct": 5.7, "eta": "48:48:28", "max_grad_norm": 1.0, "loss": 0.9078555107116699, "grad_norm": 0.6125404834747314, "learning_rate": 0.0001421383647798742}
+{"ts": "2025-12-23T17:25:34", "event": "train_log", "step": 794, "epoch": 0.34261057173678533, "progress_pct": 5.71, "epoch_pct": 5.71, "eta": "48:45:07", "max_grad_norm": 1.0, "loss": 0.899101197719574, "grad_norm": 0.5927051901817322, "learning_rate": 0.00014249775381850854}
+{"ts": "2025-12-23T17:25:49", "event": "train_log", "step": 796, "epoch": 0.3434735706580367, "progress_pct": 5.72, "epoch_pct": 5.72, "eta": "48:41:35", "max_grad_norm": 1.0, "loss": 1.028346300125122, "grad_norm": 0.6315743923187256, "learning_rate": 0.00014285714285714287}
+{"ts": "2025-12-23T17:26:04", "event": "train_log", "step": 798, "epoch": 0.34433656957928804, "progress_pct": 5.74, "epoch_pct": 5.74, "eta": "48:38:02", "max_grad_norm": 1.0, "loss": 0.8988189697265625, "grad_norm": 0.549271285533905, "learning_rate": 0.0001432165318957772}
+{"ts": "2025-12-23T17:26:19", "event": "train_log", "step": 800, "epoch": 0.3451995685005394, "progress_pct": 5.75, "epoch_pct": 5.75, "eta": "48:34:10", "max_grad_norm": 1.0, "loss": 1.0489003658294678, "grad_norm": 0.6344245672225952, "learning_rate": 0.0001435759209344115}
+{"ts": "2025-12-23T17:37:26", "event": "train_log", "step": 800, "epoch": 0.3451995685005394, "progress_pct": 5.75, "epoch_pct": 5.75, "eta": "51:36:24", "max_grad_norm": 1.0, "eval_loss": 0.9864639639854431, "eval_runtime": 667.3516, "eval_samples_per_second": 3.087, "eval_steps_per_second": 3.087}
+{"ts": "2025-12-23T17:37:41", "event": "train_log", "step": 802, "epoch": 0.3460625674217907, "progress_pct": 5.77, "epoch_pct": 5.77, "eta": "51:32:13", "max_grad_norm": 1.0, "loss": 0.8773928284645081, "grad_norm": 0.5625309348106384, "learning_rate": 0.00014393530997304583}
+{"ts": "2025-12-23T17:37:55", "event": "train_log", "step": 804, "epoch": 0.34692556634304206, "progress_pct": 5.78, "epoch_pct": 5.78, "eta": "51:28:01", "max_grad_norm": 1.0, "loss": 0.9116050004959106, "grad_norm": 0.5931969285011292, "learning_rate": 0.00014429469901168016}
+{"ts": "2025-12-23T17:38:11", "event": "train_log", "step": 806, "epoch": 0.3477885652642934, "progress_pct": 5.8, "epoch_pct": 5.8, "eta": "51:24:06", "max_grad_norm": 1.0, "loss": 0.9124425649642944, "grad_norm": 0.5189821720123291, "learning_rate": 0.00014465408805031446}
+{"ts": "2025-12-23T17:38:26", "event": "train_log", "step": 808, "epoch": 0.34865156418554477, "progress_pct": 5.81, "epoch_pct": 5.81, "eta": "51:20:07", "max_grad_norm": 1.0, "loss": 0.9517888426780701, "grad_norm": 0.5392254590988159, "learning_rate": 0.0001450134770889488}
+{"ts": "2025-12-23T17:38:41", "event": "train_log", "step": 810, "epoch": 0.34951456310679613, "progress_pct": 5.82, "epoch_pct": 5.83, "eta": "51:15:59", "max_grad_norm": 1.0, "loss": 0.9947572350502014, "grad_norm": 0.5584444999694824, "learning_rate": 0.00014537286612758312}
+{"ts": "2025-12-23T17:38:55", "event": "train_log", "step": 812, "epoch": 0.3503775620280475, "progress_pct": 5.84, "epoch_pct": 5.84, "eta": "51:11:47", "max_grad_norm": 1.0, "loss": 0.9314022660255432, "grad_norm": 0.5188854932785034, "learning_rate": 0.00014573225516621745}
+{"ts": "2025-12-23T17:39:10", "event": "train_log", "step": 814, "epoch": 0.3512405609492988, "progress_pct": 5.85, "epoch_pct": 5.85, "eta": "51:07:43", "max_grad_norm": 1.0, "loss": 0.9135628938674927, "grad_norm": 0.5783659815788269, "learning_rate": 0.00014609164420485176}
+{"ts": "2025-12-23T17:39:24", "event": "train_log", "step": 816, "epoch": 0.35210355987055014, "progress_pct": 5.87, "epoch_pct": 5.87, "eta": "51:03:39", "max_grad_norm": 1.0, "loss": 0.9665075540542603, "grad_norm": 0.550959050655365, "learning_rate": 0.0001464510332434861}
+{"ts": "2025-12-23T17:39:39", "event": "train_log", "step": 818, "epoch": 0.3529665587918015, "progress_pct": 5.88, "epoch_pct": 5.88, "eta": "50:59:37", "max_grad_norm": 1.0, "loss": 0.9836555123329163, "grad_norm": 0.6013346314430237, "learning_rate": 0.00014681042228212042}
+{"ts": "2025-12-23T17:39:55", "event": "train_log", "step": 820, "epoch": 0.35382955771305286, "progress_pct": 5.9, "epoch_pct": 5.9, "eta": "50:55:57", "max_grad_norm": 1.0, "loss": 0.8900108337402344, "grad_norm": 0.49219194054603577, "learning_rate": 0.00014716981132075472}
+{"ts": "2025-12-23T17:40:10", "event": "train_log", "step": 822, "epoch": 0.3546925566343042, "progress_pct": 5.91, "epoch_pct": 5.91, "eta": "50:52:04", "max_grad_norm": 1.0, "loss": 0.8769304156303406, "grad_norm": 0.5517411828041077, "learning_rate": 0.00014752920035938905}
+{"ts": "2025-12-23T17:40:24", "event": "train_log", "step": 824, "epoch": 0.35555555555555557, "progress_pct": 5.92, "epoch_pct": 5.93, "eta": "50:47:57", "max_grad_norm": 1.0, "loss": 0.9744759202003479, "grad_norm": 0.6062695980072021, "learning_rate": 0.00014788858939802338}
+{"ts": "2025-12-23T17:40:40", "event": "train_log", "step": 826, "epoch": 0.3564185544768069, "progress_pct": 5.94, "epoch_pct": 5.94, "eta": "50:44:08", "max_grad_norm": 1.0, "loss": 0.8875447511672974, "grad_norm": 0.5132041573524475, "learning_rate": 0.0001482479784366577}
+{"ts": "2025-12-23T17:40:54", "event": "train_log", "step": 828, "epoch": 0.3572815533980582, "progress_pct": 5.95, "epoch_pct": 5.95, "eta": "50:40:04", "max_grad_norm": 1.0, "loss": 0.962710440158844, "grad_norm": 0.551799476146698, "learning_rate": 0.000148607367475292}
+{"ts": "2025-12-23T17:41:09", "event": "train_log", "step": 830, "epoch": 0.3581445523193096, "progress_pct": 5.97, "epoch_pct": 5.97, "eta": "50:36:20", "max_grad_norm": 1.0, "loss": 0.8997528553009033, "grad_norm": 0.6046625971794128, "learning_rate": 0.00014896675651392634}
+{"ts": "2025-12-23T17:41:25", "event": "train_log", "step": 832, "epoch": 0.35900755124056094, "progress_pct": 5.98, "epoch_pct": 5.98, "eta": "50:32:38", "max_grad_norm": 1.0, "loss": 0.9541417360305786, "grad_norm": 0.560025691986084, "learning_rate": 0.00014932614555256067}
+{"ts": "2025-12-23T17:41:40", "event": "train_log", "step": 834, "epoch": 0.3598705501618123, "progress_pct": 6.0, "epoch_pct": 6.0, "eta": "50:28:47", "max_grad_norm": 1.0, "loss": 0.907791018486023, "grad_norm": 0.6441047787666321, "learning_rate": 0.00014968553459119498}
+{"ts": "2025-12-23T17:41:54", "event": "train_log", "step": 836, "epoch": 0.36073354908306365, "progress_pct": 6.01, "epoch_pct": 6.01, "eta": "50:24:48", "max_grad_norm": 1.0, "loss": 1.0295937061309814, "grad_norm": 0.5636281967163086, "learning_rate": 0.0001500449236298293}
+{"ts": "2025-12-23T17:42:09", "event": "train_log", "step": 838, "epoch": 0.361596548004315, "progress_pct": 6.03, "epoch_pct": 6.03, "eta": "50:21:00", "max_grad_norm": 1.0, "loss": 0.8875265717506409, "grad_norm": 0.5528303384780884, "learning_rate": 0.0001504043126684636}
+{"ts": "2025-12-23T17:42:23", "event": "train_log", "step": 840, "epoch": 0.36245954692556637, "progress_pct": 6.04, "epoch_pct": 6.04, "eta": "50:17:05", "max_grad_norm": 1.0, "loss": 0.9678915739059448, "grad_norm": 0.5345163345336914, "learning_rate": 0.00015076370170709794}
+{"ts": "2025-12-23T17:42:38", "event": "train_log", "step": 842, "epoch": 0.36332254584681767, "progress_pct": 6.05, "epoch_pct": 6.06, "eta": "50:13:14", "max_grad_norm": 1.0, "loss": 0.9235162734985352, "grad_norm": 0.5551225543022156, "learning_rate": 0.00015112309074573224}
+{"ts": "2025-12-23T17:42:53", "event": "train_log", "step": 844, "epoch": 0.364185544768069, "progress_pct": 6.07, "epoch_pct": 6.07, "eta": "50:09:34", "max_grad_norm": 1.0, "loss": 0.8624292016029358, "grad_norm": 0.5131904482841492, "learning_rate": 0.00015148247978436657}
+{"ts": "2025-12-23T17:43:08", "event": "train_log", "step": 846, "epoch": 0.3650485436893204, "progress_pct": 6.08, "epoch_pct": 6.08, "eta": "50:05:51", "max_grad_norm": 1.0, "loss": 1.0360193252563477, "grad_norm": 0.6811004281044006, "learning_rate": 0.0001518418688230009}
+{"ts": "2025-12-23T17:43:22", "event": "train_log", "step": 848, "epoch": 0.36591154261057174, "progress_pct": 6.1, "epoch_pct": 6.1, "eta": "50:01:50", "max_grad_norm": 1.0, "loss": 0.9254010915756226, "grad_norm": 0.6409741640090942, "learning_rate": 0.00015220125786163523}
+{"ts": "2025-12-23T17:43:38", "event": "train_log", "step": 850, "epoch": 0.3667745415318231, "progress_pct": 6.11, "epoch_pct": 6.11, "eta": "49:58:23", "max_grad_norm": 1.0, "loss": 0.8900630474090576, "grad_norm": 0.5534068942070007, "learning_rate": 0.00015256064690026953}
+{"ts": "2025-12-23T17:43:53", "event": "train_log", "step": 852, "epoch": 0.36763754045307445, "progress_pct": 6.13, "epoch_pct": 6.13, "eta": "49:54:42", "max_grad_norm": 1.0, "loss": 0.88521409034729, "grad_norm": 0.4999487102031708, "learning_rate": 0.00015292003593890386}
+{"ts": "2025-12-23T17:44:07", "event": "train_log", "step": 854, "epoch": 0.3685005393743258, "progress_pct": 6.14, "epoch_pct": 6.14, "eta": "49:50:53", "max_grad_norm": 1.0, "loss": 0.9563921093940735, "grad_norm": 0.5805923938751221, "learning_rate": 0.0001532794249775382}
+{"ts": "2025-12-23T17:44:22", "event": "train_log", "step": 856, "epoch": 0.3693635382955771, "progress_pct": 6.15, "epoch_pct": 6.16, "eta": "49:47:13", "max_grad_norm": 1.0, "loss": 0.8909372687339783, "grad_norm": 0.5485470294952393, "learning_rate": 0.0001536388140161725}
+{"ts": "2025-12-23T17:44:37", "event": "train_log", "step": 858, "epoch": 0.37022653721682847, "progress_pct": 6.17, "epoch_pct": 6.17, "eta": "49:43:31", "max_grad_norm": 1.0, "loss": 0.9145731925964355, "grad_norm": 0.5317923426628113, "learning_rate": 0.00015399820305480683}
+{"ts": "2025-12-23T17:44:50", "event": "train_log", "step": 860, "epoch": 0.3710895361380798, "progress_pct": 6.18, "epoch_pct": 6.18, "eta": "49:39:35", "max_grad_norm": 1.0, "loss": 1.01466965675354, "grad_norm": 0.6073495745658875, "learning_rate": 0.00015435759209344116}
+{"ts": "2025-12-23T17:45:05", "event": "train_log", "step": 862, "epoch": 0.3719525350593312, "progress_pct": 6.2, "epoch_pct": 6.2, "eta": "49:35:52", "max_grad_norm": 1.0, "loss": 0.9941825270652771, "grad_norm": 0.566655158996582, "learning_rate": 0.0001547169811320755}
+{"ts": "2025-12-23T17:45:19", "event": "train_log", "step": 864, "epoch": 0.37281553398058254, "progress_pct": 6.21, "epoch_pct": 6.21, "eta": "49:32:06", "max_grad_norm": 1.0, "loss": 1.0059782266616821, "grad_norm": 0.5262459516525269, "learning_rate": 0.0001550763701707098}
+{"ts": "2025-12-23T17:45:34", "event": "train_log", "step": 866, "epoch": 0.3736785329018339, "progress_pct": 6.23, "epoch_pct": 6.23, "eta": "49:28:31", "max_grad_norm": 1.0, "loss": 1.0332856178283691, "grad_norm": 0.6264083981513977, "learning_rate": 0.00015543575920934412}
+{"ts": "2025-12-23T17:45:48", "event": "train_log", "step": 868, "epoch": 0.3745415318230852, "progress_pct": 6.24, "epoch_pct": 6.24, "eta": "49:24:40", "max_grad_norm": 1.0, "loss": 1.022459626197815, "grad_norm": 0.6575480699539185, "learning_rate": 0.00015579514824797845}
+{"ts": "2025-12-23T17:46:01", "event": "train_log", "step": 870, "epoch": 0.37540453074433655, "progress_pct": 6.26, "epoch_pct": 6.26, "eta": "49:20:50", "max_grad_norm": 1.0, "loss": 0.9550372362136841, "grad_norm": 0.6291940212249756, "learning_rate": 0.00015615453728661275}
+{"ts": "2025-12-23T17:46:16", "event": "train_log", "step": 872, "epoch": 0.3762675296655879, "progress_pct": 6.27, "epoch_pct": 6.27, "eta": "49:17:08", "max_grad_norm": 1.0, "loss": 0.9861716628074646, "grad_norm": 0.6710562109947205, "learning_rate": 0.00015651392632524708}
+{"ts": "2025-12-23T17:46:31", "event": "train_log", "step": 874, "epoch": 0.37713052858683926, "progress_pct": 6.28, "epoch_pct": 6.29, "eta": "49:13:44", "max_grad_norm": 1.0, "loss": 0.9719111919403076, "grad_norm": 0.5505748987197876, "learning_rate": 0.0001568733153638814}
+{"ts": "2025-12-23T17:46:47", "event": "train_log", "step": 876, "epoch": 0.3779935275080906, "progress_pct": 6.3, "epoch_pct": 6.3, "eta": "49:10:21", "max_grad_norm": 1.0, "loss": 0.8698170185089111, "grad_norm": 0.5055180788040161, "learning_rate": 0.00015723270440251574}
+{"ts": "2025-12-23T17:47:01", "event": "train_log", "step": 878, "epoch": 0.378856526429342, "progress_pct": 6.31, "epoch_pct": 6.31, "eta": "49:06:44", "max_grad_norm": 1.0, "loss": 1.029494285583496, "grad_norm": 0.5935947895050049, "learning_rate": 0.00015759209344115005}
+{"ts": "2025-12-23T17:47:15", "event": "train_log", "step": 880, "epoch": 0.37971952535059333, "progress_pct": 6.33, "epoch_pct": 6.33, "eta": "49:03:10", "max_grad_norm": 1.0, "loss": 0.923010528087616, "grad_norm": 0.538325846195221, "learning_rate": 0.00015795148247978438}
+{"ts": "2025-12-23T17:47:29", "event": "train_log", "step": 882, "epoch": 0.38058252427184464, "progress_pct": 6.34, "epoch_pct": 6.34, "eta": "48:59:27", "max_grad_norm": 1.0, "loss": 0.9394056797027588, "grad_norm": 0.587297797203064, "learning_rate": 0.0001583108715184187}
+{"ts": "2025-12-23T17:47:43", "event": "train_log", "step": 884, "epoch": 0.381445523193096, "progress_pct": 6.36, "epoch_pct": 6.36, "eta": "48:55:49", "max_grad_norm": 1.0, "loss": 0.9472483992576599, "grad_norm": 0.5910462737083435, "learning_rate": 0.000158670260557053}
+{"ts": "2025-12-23T17:47:58", "event": "train_log", "step": 886, "epoch": 0.38230852211434735, "progress_pct": 6.37, "epoch_pct": 6.37, "eta": "48:52:20", "max_grad_norm": 1.0, "loss": 0.9028263688087463, "grad_norm": 0.629048764705658, "learning_rate": 0.00015902964959568734}
+{"ts": "2025-12-23T17:48:13", "event": "train_log", "step": 888, "epoch": 0.3831715210355987, "progress_pct": 6.38, "epoch_pct": 6.39, "eta": "48:48:57", "max_grad_norm": 1.0, "loss": 0.9579087495803833, "grad_norm": 0.5028086304664612, "learning_rate": 0.00015938903863432167}
+{"ts": "2025-12-23T17:48:29", "event": "train_log", "step": 890, "epoch": 0.38403451995685006, "progress_pct": 6.4, "epoch_pct": 6.4, "eta": "48:45:43", "max_grad_norm": 1.0, "loss": 0.8318673372268677, "grad_norm": 0.5372384190559387, "learning_rate": 0.000159748427672956}
+{"ts": "2025-12-23T17:48:43", "event": "train_log", "step": 892, "epoch": 0.3848975188781014, "progress_pct": 6.41, "epoch_pct": 6.41, "eta": "48:42:10", "max_grad_norm": 1.0, "loss": 0.9804943203926086, "grad_norm": 0.6314184665679932, "learning_rate": 0.0001601078167115903}
+{"ts": "2025-12-23T17:48:58", "event": "train_log", "step": 894, "epoch": 0.3857605177993528, "progress_pct": 6.43, "epoch_pct": 6.43, "eta": "48:38:46", "max_grad_norm": 1.0, "loss": 1.0078438520431519, "grad_norm": 0.5545229911804199, "learning_rate": 0.00016046720575022463}
+{"ts": "2025-12-23T17:49:14", "event": "train_log", "step": 896, "epoch": 0.3866235167206041, "progress_pct": 6.44, "epoch_pct": 6.44, "eta": "48:35:44", "max_grad_norm": 1.0, "loss": 0.9269036650657654, "grad_norm": 0.4674014151096344, "learning_rate": 0.00016082659478885896}
+{"ts": "2025-12-23T17:49:29", "event": "train_log", "step": 898, "epoch": 0.38748651564185543, "progress_pct": 6.46, "epoch_pct": 6.46, "eta": "48:32:21", "max_grad_norm": 1.0, "loss": 0.8927953243255615, "grad_norm": 1.5887153148651123, "learning_rate": 0.00016118598382749326}
+{"ts": "2025-12-23T17:49:43", "event": "train_log", "step": 900, "epoch": 0.3883495145631068, "progress_pct": 6.47, "epoch_pct": 6.47, "eta": "48:28:53", "max_grad_norm": 1.0, "loss": 0.908074140548706, "grad_norm": 0.5217035412788391, "learning_rate": 0.0001615453728661276}
+{"ts": "2025-12-23T18:00:50", "event": "train_log", "step": 900, "epoch": 0.3883495145631068, "progress_pct": 6.47, "epoch_pct": 6.47, "eta": "51:09:37", "max_grad_norm": 1.0, "eval_loss": 0.9741895794868469, "eval_runtime": 667.2236, "eval_samples_per_second": 3.087, "eval_steps_per_second": 3.087}
+{"ts": "2025-12-23T18:01:05", "event": "train_log", "step": 902, "epoch": 0.38921251348435815, "progress_pct": 6.49, "epoch_pct": 6.49, "eta": "51:06:01", "max_grad_norm": 1.0, "loss": 0.9660369157791138, "grad_norm": 0.470498651266098, "learning_rate": 0.00016190476190476192}
+{"ts": "2025-12-23T18:01:22", "event": "train_log", "step": 904, "epoch": 0.3900755124056095, "progress_pct": 6.5, "epoch_pct": 6.5, "eta": "51:02:38", "max_grad_norm": 1.0, "loss": 0.9236379265785217, "grad_norm": 0.5111004114151001, "learning_rate": 0.00016226415094339625}
+{"ts": "2025-12-23T18:01:37", "event": "train_log", "step": 906, "epoch": 0.39093851132686086, "progress_pct": 6.51, "epoch_pct": 6.52, "eta": "50:59:11", "max_grad_norm": 1.0, "loss": 1.0061595439910889, "grad_norm": 0.5872815251350403, "learning_rate": 0.00016262353998203056}
+{"ts": "2025-12-23T18:01:53", "event": "train_log", "step": 908, "epoch": 0.3918015102481122, "progress_pct": 6.53, "epoch_pct": 6.53, "eta": "50:55:46", "max_grad_norm": 1.0, "loss": 0.8347328901290894, "grad_norm": 0.5150740742683411, "learning_rate": 0.0001629829290206649}
+{"ts": "2025-12-23T18:02:10", "event": "train_log", "step": 910, "epoch": 0.3926645091693635, "progress_pct": 6.54, "epoch_pct": 6.54, "eta": "50:52:27", "max_grad_norm": 1.0, "loss": 0.9091183543205261, "grad_norm": 0.46554985642433167, "learning_rate": 0.00016334231805929922}
+{"ts": "2025-12-23T18:02:26", "event": "train_log", "step": 912, "epoch": 0.3935275080906149, "progress_pct": 6.56, "epoch_pct": 6.56, "eta": "50:49:15", "max_grad_norm": 1.0, "loss": 0.9299798011779785, "grad_norm": 0.5292875170707703, "learning_rate": 0.00016370170709793352}
+{"ts": "2025-12-23T18:02:41", "event": "train_log", "step": 914, "epoch": 0.39439050701186623, "progress_pct": 6.57, "epoch_pct": 6.57, "eta": "50:45:39", "max_grad_norm": 1.0, "loss": 0.942286491394043, "grad_norm": 0.5177125930786133, "learning_rate": 0.00016406109613656785}
+{"ts": "2025-12-23T18:02:56", "event": "train_log", "step": 916, "epoch": 0.3952535059331176, "progress_pct": 6.59, "epoch_pct": 6.59, "eta": "50:42:05", "max_grad_norm": 1.0, "loss": 0.825290858745575, "grad_norm": 0.5564161539077759, "learning_rate": 0.00016442048517520215}
+{"ts": "2025-12-23T18:03:10", "event": "train_log", "step": 918, "epoch": 0.39611650485436894, "progress_pct": 6.6, "epoch_pct": 6.6, "eta": "50:38:20", "max_grad_norm": 1.0, "loss": 0.876898467540741, "grad_norm": 0.5572530031204224, "learning_rate": 0.00016477987421383648}
+{"ts": "2025-12-23T18:03:26", "event": "train_log", "step": 920, "epoch": 0.3969795037756203, "progress_pct": 6.61, "epoch_pct": 6.62, "eta": "50:34:54", "max_grad_norm": 1.0, "loss": 0.8949798941612244, "grad_norm": 0.7294673323631287, "learning_rate": 0.0001651392632524708}
+{"ts": "2025-12-23T18:03:42", "event": "train_log", "step": 922, "epoch": 0.3978425026968716, "progress_pct": 6.63, "epoch_pct": 6.63, "eta": "50:31:40", "max_grad_norm": 1.0, "loss": 0.8457819223403931, "grad_norm": 0.5234251022338867, "learning_rate": 0.00016549865229110512}
+{"ts": "2025-12-23T18:03:59", "event": "train_log", "step": 924, "epoch": 0.39870550161812296, "progress_pct": 6.64, "epoch_pct": 6.65, "eta": "50:28:32", "max_grad_norm": 1.0, "loss": 0.9080174565315247, "grad_norm": 0.5273709893226624, "learning_rate": 0.00016585804132973945}
+{"ts": "2025-12-23T18:04:14", "event": "train_log", "step": 926, "epoch": 0.3995685005393743, "progress_pct": 6.66, "epoch_pct": 6.66, "eta": "50:25:11", "max_grad_norm": 1.0, "loss": 1.0304023027420044, "grad_norm": 0.5795063376426697, "learning_rate": 0.00016621743036837378}
+{"ts": "2025-12-23T18:04:30", "event": "train_log", "step": 928, "epoch": 0.4004314994606257, "progress_pct": 6.67, "epoch_pct": 6.67, "eta": "50:21:57", "max_grad_norm": 1.0, "loss": 0.8900477886199951, "grad_norm": 0.6153313517570496, "learning_rate": 0.00016657681940700808}
+{"ts": "2025-12-23T18:04:45", "event": "train_log", "step": 930, "epoch": 0.40129449838187703, "progress_pct": 6.69, "epoch_pct": 6.69, "eta": "50:18:17", "max_grad_norm": 1.0, "loss": 1.0130009651184082, "grad_norm": 0.6293173432350159, "learning_rate": 0.0001669362084456424}
+{"ts": "2025-12-23T18:05:00", "event": "train_log", "step": 932, "epoch": 0.4021574973031284, "progress_pct": 6.7, "epoch_pct": 6.7, "eta": "50:14:50", "max_grad_norm": 1.0, "loss": 0.9339282512664795, "grad_norm": 0.5455223321914673, "learning_rate": 0.00016729559748427674}
+{"ts": "2025-12-23T18:05:15", "event": "train_log", "step": 934, "epoch": 0.40302049622437974, "progress_pct": 6.72, "epoch_pct": 6.72, "eta": "50:11:32", "max_grad_norm": 1.0, "loss": 0.9628980755805969, "grad_norm": 0.5349094271659851, "learning_rate": 0.00016765498652291104}
+{"ts": "2025-12-23T18:05:31", "event": "train_log", "step": 936, "epoch": 0.40388349514563104, "progress_pct": 6.73, "epoch_pct": 6.73, "eta": "50:08:18", "max_grad_norm": 1.0, "loss": 0.8922860026359558, "grad_norm": 0.491227924823761, "learning_rate": 0.00016801437556154537}
+{"ts": "2025-12-23T18:05:47", "event": "train_log", "step": 938, "epoch": 0.4047464940668824, "progress_pct": 6.74, "epoch_pct": 6.75, "eta": "50:05:04", "max_grad_norm": 1.0, "loss": 1.0470497608184814, "grad_norm": 0.6331246495246887, "learning_rate": 0.0001683737646001797}
+{"ts": "2025-12-23T18:06:03", "event": "train_log", "step": 940, "epoch": 0.40560949298813376, "progress_pct": 6.76, "epoch_pct": 6.76, "eta": "50:01:49", "max_grad_norm": 1.0, "loss": 0.8868283629417419, "grad_norm": 0.6079246401786804, "learning_rate": 0.00016873315363881403}
+{"ts": "2025-12-23T18:06:18", "event": "train_log", "step": 942, "epoch": 0.4064724919093851, "progress_pct": 6.77, "epoch_pct": 6.77, "eta": "49:58:25", "max_grad_norm": 1.0, "loss": 0.9938711524009705, "grad_norm": 0.5326972603797913, "learning_rate": 0.00016909254267744833}
+{"ts": "2025-12-23T18:06:33", "event": "train_log", "step": 944, "epoch": 0.40733549083063647, "progress_pct": 6.79, "epoch_pct": 6.79, "eta": "49:55:04", "max_grad_norm": 1.0, "loss": 0.8280484676361084, "grad_norm": 0.47754305601119995, "learning_rate": 0.00016945193171608266}
+{"ts": "2025-12-23T18:06:48", "event": "train_log", "step": 946, "epoch": 0.4081984897518878, "progress_pct": 6.8, "epoch_pct": 6.8, "eta": "49:51:41", "max_grad_norm": 1.0, "loss": 1.089701533317566, "grad_norm": 0.6683310270309448, "learning_rate": 0.000169811320754717}
+{"ts": "2025-12-23T18:07:03", "event": "train_log", "step": 948, "epoch": 0.4090614886731392, "progress_pct": 6.82, "epoch_pct": 6.82, "eta": "49:48:28", "max_grad_norm": 1.0, "loss": 0.8535542488098145, "grad_norm": 0.42798754572868347, "learning_rate": 0.0001701707097933513}
+{"ts": "2025-12-23T18:07:18", "event": "train_log", "step": 950, "epoch": 0.4099244875943905, "progress_pct": 6.83, "epoch_pct": 6.83, "eta": "49:45:03", "max_grad_norm": 1.0, "loss": 0.9039298295974731, "grad_norm": 0.5999574065208435, "learning_rate": 0.00017053009883198563}
+{"ts": "2025-12-23T18:07:33", "event": "train_log", "step": 952, "epoch": 0.41078748651564184, "progress_pct": 6.84, "epoch_pct": 6.85, "eta": "49:41:49", "max_grad_norm": 1.0, "loss": 0.8786448240280151, "grad_norm": 0.5752781629562378, "learning_rate": 0.00017088948787061996}
+{"ts": "2025-12-23T18:07:49", "event": "train_log", "step": 954, "epoch": 0.4116504854368932, "progress_pct": 6.86, "epoch_pct": 6.86, "eta": "49:38:33", "max_grad_norm": 1.0, "loss": 0.9206072688102722, "grad_norm": 0.5121532678604126, "learning_rate": 0.0001712488769092543}
+{"ts": "2025-12-23T18:08:04", "event": "train_log", "step": 956, "epoch": 0.41251348435814456, "progress_pct": 6.87, "epoch_pct": 6.88, "eta": "49:35:17", "max_grad_norm": 1.0, "loss": 0.9246986508369446, "grad_norm": 0.611078143119812, "learning_rate": 0.0001716082659478886}
+{"ts": "2025-12-23T18:08:18", "event": "train_log", "step": 958, "epoch": 0.4133764832793959, "progress_pct": 6.89, "epoch_pct": 6.89, "eta": "49:31:46", "max_grad_norm": 1.0, "loss": 0.9221894145011902, "grad_norm": 0.5101020336151123, "learning_rate": 0.00017196765498652292}
+{"ts": "2025-12-23T18:08:33", "event": "train_log", "step": 960, "epoch": 0.41423948220064727, "progress_pct": 6.9, "epoch_pct": 6.9, "eta": "49:28:29", "max_grad_norm": 1.0, "loss": 0.9072799682617188, "grad_norm": 0.5681450963020325, "learning_rate": 0.00017232704402515725}
+{"ts": "2025-12-23T18:08:48", "event": "train_log", "step": 962, "epoch": 0.41510248112189857, "progress_pct": 6.92, "epoch_pct": 6.92, "eta": "49:25:13", "max_grad_norm": 1.0, "loss": 0.9460896849632263, "grad_norm": 0.47865498065948486, "learning_rate": 0.00017268643306379155}
+{"ts": "2025-12-23T18:09:02", "event": "train_log", "step": 964, "epoch": 0.4159654800431499, "progress_pct": 6.93, "epoch_pct": 6.93, "eta": "49:21:53", "max_grad_norm": 1.0, "loss": 0.9121519923210144, "grad_norm": 0.49861401319503784, "learning_rate": 0.00017304582210242588}
+{"ts": "2025-12-23T18:09:18", "event": "train_log", "step": 966, "epoch": 0.4168284789644013, "progress_pct": 6.95, "epoch_pct": 6.95, "eta": "49:18:42", "max_grad_norm": 1.0, "loss": 0.8826848864555359, "grad_norm": 0.43025892972946167, "learning_rate": 0.0001734052111410602}
+{"ts": "2025-12-23T18:09:34", "event": "train_log", "step": 968, "epoch": 0.41769147788565264, "progress_pct": 6.96, "epoch_pct": 6.96, "eta": "49:15:40", "max_grad_norm": 1.0, "loss": 0.8756251335144043, "grad_norm": 0.4600491225719452, "learning_rate": 0.00017376460017969454}
+{"ts": "2025-12-23T18:09:48", "event": "train_log", "step": 970, "epoch": 0.418554476806904, "progress_pct": 6.97, "epoch_pct": 6.98, "eta": "49:12:19", "max_grad_norm": 1.0, "loss": 0.9171333312988281, "grad_norm": 0.5297656059265137, "learning_rate": 0.00017412398921832885}
+{"ts": "2025-12-23T18:10:03", "event": "train_log", "step": 972, "epoch": 0.41941747572815535, "progress_pct": 6.99, "epoch_pct": 6.99, "eta": "49:09:02", "max_grad_norm": 1.0, "loss": 0.8887524008750916, "grad_norm": 0.4906919002532959, "learning_rate": 0.00017448337825696318}
+{"ts": "2025-12-23T18:10:19", "event": "train_log", "step": 974, "epoch": 0.4202804746494067, "progress_pct": 7.0, "epoch_pct": 7.0, "eta": "49:06:07", "max_grad_norm": 1.0, "loss": 0.8345810174942017, "grad_norm": 0.49263402819633484, "learning_rate": 0.0001748427672955975}
+{"ts": "2025-12-23T18:10:33", "event": "train_log", "step": 976, "epoch": 0.421143473570658, "progress_pct": 7.02, "epoch_pct": 7.02, "eta": "49:02:47", "max_grad_norm": 1.0, "loss": 0.968651294708252, "grad_norm": 0.5706565380096436, "learning_rate": 0.0001752021563342318}
+{"ts": "2025-12-23T18:10:48", "event": "train_log", "step": 978, "epoch": 0.42200647249190937, "progress_pct": 7.03, "epoch_pct": 7.03, "eta": "48:59:32", "max_grad_norm": 1.0, "loss": 0.9729376435279846, "grad_norm": 0.5269908308982849, "learning_rate": 0.00017556154537286614}
+{"ts": "2025-12-23T18:11:02", "event": "train_log", "step": 980, "epoch": 0.4228694714131607, "progress_pct": 7.05, "epoch_pct": 7.05, "eta": "48:56:12", "max_grad_norm": 1.0, "loss": 0.963884711265564, "grad_norm": 0.47058001160621643, "learning_rate": 0.00017592093441150047}
+{"ts": "2025-12-23T18:11:16", "event": "train_log", "step": 982, "epoch": 0.4237324703344121, "progress_pct": 7.06, "epoch_pct": 7.06, "eta": "48:52:56", "max_grad_norm": 1.0, "loss": 0.8952447175979614, "grad_norm": 0.5322962999343872, "learning_rate": 0.0001762803234501348}
+{"ts": "2025-12-23T18:11:31", "event": "train_log", "step": 984, "epoch": 0.42459546925566344, "progress_pct": 7.08, "epoch_pct": 7.08, "eta": "48:49:49", "max_grad_norm": 1.0, "loss": 0.8932783603668213, "grad_norm": 0.5750975012779236, "learning_rate": 0.0001766397124887691}
+{"ts": "2025-12-23T18:11:46", "event": "train_log", "step": 986, "epoch": 0.4254584681769148, "progress_pct": 7.09, "epoch_pct": 7.09, "eta": "48:46:39", "max_grad_norm": 1.0, "loss": 0.916595458984375, "grad_norm": 0.5539655685424805, "learning_rate": 0.00017699910152740343}
+{"ts": "2025-12-23T18:12:01", "event": "train_log", "step": 988, "epoch": 0.42632146709816615, "progress_pct": 7.1, "epoch_pct": 7.11, "eta": "48:43:25", "max_grad_norm": 1.0, "loss": 0.9669626355171204, "grad_norm": 0.568000853061676, "learning_rate": 0.00017735849056603776}
+{"ts": "2025-12-23T18:12:15", "event": "train_log", "step": 990, "epoch": 0.42718446601941745, "progress_pct": 7.12, "epoch_pct": 7.12, "eta": "48:40:07", "max_grad_norm": 1.0, "loss": 1.0089105367660522, "grad_norm": 0.6010684370994568, "learning_rate": 0.00017771787960467206}
+{"ts": "2025-12-23T18:12:29", "event": "train_log", "step": 992, "epoch": 0.4280474649406688, "progress_pct": 7.13, "epoch_pct": 7.13, "eta": "48:36:49", "max_grad_norm": 1.0, "loss": 0.9810921549797058, "grad_norm": 0.6083462238311768, "learning_rate": 0.0001780772686433064}
+{"ts": "2025-12-23T18:12:44", "event": "train_log", "step": 994, "epoch": 0.42891046386192017, "progress_pct": 7.15, "epoch_pct": 7.15, "eta": "48:33:43", "max_grad_norm": 1.0, "loss": 0.9524372816085815, "grad_norm": 0.5076655149459839, "learning_rate": 0.0001784366576819407}
+{"ts": "2025-12-23T18:12:59", "event": "train_log", "step": 996, "epoch": 0.4297734627831715, "progress_pct": 7.16, "epoch_pct": 7.16, "eta": "48:30:41", "max_grad_norm": 1.0, "loss": 0.881294846534729, "grad_norm": 0.5260922312736511, "learning_rate": 0.00017879604672057503}
+{"ts": "2025-12-23T18:13:14", "event": "train_log", "step": 998, "epoch": 0.4306364617044229, "progress_pct": 7.18, "epoch_pct": 7.18, "eta": "48:27:40", "max_grad_norm": 1.0, "loss": 0.9138327836990356, "grad_norm": 0.6130498051643372, "learning_rate": 0.00017915543575920936}
+{"ts": "2025-12-23T18:13:29", "event": "train_log", "step": 1000, "epoch": 0.43149946062567424, "progress_pct": 7.19, "epoch_pct": 7.19, "eta": "48:24:39", "max_grad_norm": 1.0, "loss": 0.8861367106437683, "grad_norm": 0.5346242785453796, "learning_rate": 0.00017951482479784366}
+{"ts": "2025-12-23T18:24:24", "event": "train_log", "step": 1000, "epoch": 0.43149946062567424, "progress_pct": 7.19, "epoch_pct": 7.19, "eta": "50:45:40", "max_grad_norm": 1.0, "eval_loss": 0.9606748819351196, "eval_runtime": 655.4358, "eval_samples_per_second": 3.143, "eval_steps_per_second": 3.143}
+{"ts": "2025-12-23T18:24:40", "event": "train_log", "step": 1002, "epoch": 0.4323624595469256, "progress_pct": 7.2, "epoch_pct": 7.21, "eta": "50:42:31", "max_grad_norm": 1.0, "loss": 0.8711628913879395, "grad_norm": 0.5977228879928589, "learning_rate": 0.000179874213836478}
+{"ts": "2025-12-23T18:24:56", "event": "train_log", "step": 1004, "epoch": 0.4332254584681769, "progress_pct": 7.22, "epoch_pct": 7.22, "eta": "50:39:23", "max_grad_norm": 1.0, "loss": 0.9393253326416016, "grad_norm": 0.5547866821289062, "learning_rate": 0.00018023360287511232}
+{"ts": "2025-12-23T18:25:11", "event": "train_log", "step": 1006, "epoch": 0.43408845738942825, "progress_pct": 7.23, "epoch_pct": 7.23, "eta": "50:36:08", "max_grad_norm": 1.0, "loss": 0.9486003518104553, "grad_norm": 0.536856472492218, "learning_rate": 0.00018059299191374662}
+{"ts": "2025-12-23T18:25:28", "event": "train_log", "step": 1008, "epoch": 0.4349514563106796, "progress_pct": 7.25, "epoch_pct": 7.25, "eta": "50:33:14", "max_grad_norm": 1.0, "loss": 0.9042052030563354, "grad_norm": 0.4769814610481262, "learning_rate": 0.00018095238095238095}
+{"ts": "2025-12-23T18:25:44", "event": "train_log", "step": 1010, "epoch": 0.43581445523193096, "progress_pct": 7.26, "epoch_pct": 7.26, "eta": "50:30:02", "max_grad_norm": 1.0, "loss": 0.978546142578125, "grad_norm": 0.5554604530334473, "learning_rate": 0.00018131176999101528}
+{"ts": "2025-12-23T18:25:59", "event": "train_log", "step": 1012, "epoch": 0.4366774541531823, "progress_pct": 7.28, "epoch_pct": 7.28, "eta": "50:26:51", "max_grad_norm": 1.0, "loss": 0.8382073640823364, "grad_norm": 0.5112947225570679, "learning_rate": 0.00018167115902964959}
+{"ts": "2025-12-23T18:26:16", "event": "train_log", "step": 1014, "epoch": 0.4375404530744337, "progress_pct": 7.29, "epoch_pct": 7.29, "eta": "50:23:55", "max_grad_norm": 1.0, "loss": 0.8577026724815369, "grad_norm": 0.45194941759109497, "learning_rate": 0.00018203054806828392}
+{"ts": "2025-12-23T18:26:33", "event": "train_log", "step": 1016, "epoch": 0.438403451995685, "progress_pct": 7.31, "epoch_pct": 7.31, "eta": "50:21:06", "max_grad_norm": 1.0, "loss": 0.8517863154411316, "grad_norm": 0.5115043520927429, "learning_rate": 0.00018238993710691825}
+{"ts": "2025-12-23T18:26:47", "event": "train_log", "step": 1018, "epoch": 0.43926645091693634, "progress_pct": 7.32, "epoch_pct": 7.32, "eta": "50:17:47", "max_grad_norm": 1.0, "loss": 0.9597266912460327, "grad_norm": 0.5485050082206726, "learning_rate": 0.00018274932614555258}
+{"ts": "2025-12-23T18:27:02", "event": "train_log", "step": 1020, "epoch": 0.4401294498381877, "progress_pct": 7.33, "epoch_pct": 7.34, "eta": "50:14:30", "max_grad_norm": 1.0, "loss": 1.0407187938690186, "grad_norm": 0.5742959976196289, "learning_rate": 0.00018310871518418688}
+{"ts": "2025-12-23T18:27:17", "event": "train_log", "step": 1022, "epoch": 0.44099244875943905, "progress_pct": 7.35, "epoch_pct": 7.35, "eta": "50:11:19", "max_grad_norm": 1.0, "loss": 0.8696310520172119, "grad_norm": 0.44870051741600037, "learning_rate": 0.0001834681042228212}
+{"ts": "2025-12-23T18:27:33", "event": "train_log", "step": 1024, "epoch": 0.4418554476806904, "progress_pct": 7.36, "epoch_pct": 7.36, "eta": "50:08:14", "max_grad_norm": 1.0, "loss": 0.9673634767532349, "grad_norm": 0.5179623961448669, "learning_rate": 0.00018382749326145554}
+{"ts": "2025-12-23T18:27:48", "event": "train_log", "step": 1026, "epoch": 0.44271844660194176, "progress_pct": 7.38, "epoch_pct": 7.38, "eta": "50:05:01", "max_grad_norm": 1.0, "loss": 0.9596615433692932, "grad_norm": 0.5404779314994812, "learning_rate": 0.00018418688230008984}
+{"ts": "2025-12-23T18:28:03", "event": "train_log", "step": 1028, "epoch": 0.4435814455231931, "progress_pct": 7.39, "epoch_pct": 7.39, "eta": "50:01:54", "max_grad_norm": 1.0, "loss": 0.8483878970146179, "grad_norm": 0.47766315937042236, "learning_rate": 0.00018454627133872417}
+{"ts": "2025-12-23T18:28:19", "event": "train_log", "step": 1030, "epoch": 0.4444444444444444, "progress_pct": 7.41, "epoch_pct": 7.41, "eta": "49:59:00", "max_grad_norm": 1.0, "loss": 0.9330979585647583, "grad_norm": 0.503380537033081, "learning_rate": 0.0001849056603773585}
+{"ts": "2025-12-23T18:28:35", "event": "train_log", "step": 1032, "epoch": 0.4453074433656958, "progress_pct": 7.42, "epoch_pct": 7.42, "eta": "49:55:58", "max_grad_norm": 1.0, "loss": 0.9341012239456177, "grad_norm": 0.6129396557807922, "learning_rate": 0.00018526504941599283}
+{"ts": "2025-12-23T18:28:50", "event": "train_log", "step": 1034, "epoch": 0.44617044228694713, "progress_pct": 7.43, "epoch_pct": 7.44, "eta": "49:52:58", "max_grad_norm": 1.0, "loss": 0.9139068126678467, "grad_norm": 0.4497876465320587, "learning_rate": 0.00018562443845462713}
+{"ts": "2025-12-23T18:29:07", "event": "train_log", "step": 1036, "epoch": 0.4470334412081985, "progress_pct": 7.45, "epoch_pct": 7.45, "eta": "49:50:04", "max_grad_norm": 1.0, "loss": 0.8874827027320862, "grad_norm": 0.5369747281074524, "learning_rate": 0.00018598382749326146}
+{"ts": "2025-12-23T18:29:22", "event": "train_log", "step": 1038, "epoch": 0.44789644012944985, "progress_pct": 7.46, "epoch_pct": 7.46, "eta": "49:46:56", "max_grad_norm": 1.0, "loss": 0.9653725028038025, "grad_norm": 0.5947322845458984, "learning_rate": 0.0001863432165318958}
+{"ts": "2025-12-23T18:29:37", "event": "train_log", "step": 1040, "epoch": 0.4487594390507012, "progress_pct": 7.48, "epoch_pct": 7.48, "eta": "49:43:58", "max_grad_norm": 1.0, "loss": 0.9553119540214539, "grad_norm": 0.6649987101554871, "learning_rate": 0.0001867026055705301}
+{"ts": "2025-12-23T18:29:52", "event": "train_log", "step": 1042, "epoch": 0.44962243797195256, "progress_pct": 7.49, "epoch_pct": 7.49, "eta": "49:40:43", "max_grad_norm": 1.0, "loss": 0.904233992099762, "grad_norm": 0.5369387269020081, "learning_rate": 0.00018706199460916443}
+{"ts": "2025-12-23T18:30:06", "event": "train_log", "step": 1044, "epoch": 0.45048543689320386, "progress_pct": 7.51, "epoch_pct": 7.51, "eta": "49:37:31", "max_grad_norm": 1.0, "loss": 0.8837952017784119, "grad_norm": 0.4956842362880707, "learning_rate": 0.00018742138364779876}
+{"ts": "2025-12-23T18:30:20", "event": "train_log", "step": 1046, "epoch": 0.4513484358144552, "progress_pct": 7.52, "epoch_pct": 7.52, "eta": "49:34:18", "max_grad_norm": 1.0, "loss": 0.8964687585830688, "grad_norm": 0.48045051097869873, "learning_rate": 0.0001877807726864331}
+{"ts": "2025-12-23T18:30:37", "event": "train_log", "step": 1048, "epoch": 0.4522114347357066, "progress_pct": 7.54, "epoch_pct": 7.54, "eta": "49:31:34", "max_grad_norm": 1.0, "loss": 0.9105878472328186, "grad_norm": 0.4925530254840851, "learning_rate": 0.0001881401617250674}
+{"ts": "2025-12-23T18:30:52", "event": "train_log", "step": 1050, "epoch": 0.45307443365695793, "progress_pct": 7.55, "epoch_pct": 7.55, "eta": "49:28:29", "max_grad_norm": 1.0, "loss": 0.96272873878479, "grad_norm": 0.5131362080574036, "learning_rate": 0.00018849955076370172}
+{"ts": "2025-12-23T18:31:08", "event": "train_log", "step": 1052, "epoch": 0.4539374325782093, "progress_pct": 7.56, "epoch_pct": 7.57, "eta": "49:25:36", "max_grad_norm": 1.0, "loss": 0.8796783685684204, "grad_norm": 0.435739129781723, "learning_rate": 0.00018885893980233605}
+{"ts": "2025-12-23T18:31:23", "event": "train_log", "step": 1054, "epoch": 0.45480043149946064, "progress_pct": 7.58, "epoch_pct": 7.58, "eta": "49:22:38", "max_grad_norm": 1.0, "loss": 0.9463814496994019, "grad_norm": 0.500938892364502, "learning_rate": 0.00018921832884097035}
+{"ts": "2025-12-23T18:31:38", "event": "train_log", "step": 1056, "epoch": 0.455663430420712, "progress_pct": 7.59, "epoch_pct": 7.59, "eta": "49:19:32", "max_grad_norm": 1.0, "loss": 0.9030335545539856, "grad_norm": 0.4769900143146515, "learning_rate": 0.00018957771787960468}
+{"ts": "2025-12-23T18:31:53", "event": "train_log", "step": 1058, "epoch": 0.4565264293419633, "progress_pct": 7.61, "epoch_pct": 7.61, "eta": "49:16:30", "max_grad_norm": 1.0, "loss": 0.986995279788971, "grad_norm": 0.49585285782814026, "learning_rate": 0.00018993710691823901}
+{"ts": "2025-12-23T18:32:09", "event": "train_log", "step": 1060, "epoch": 0.45738942826321466, "progress_pct": 7.62, "epoch_pct": 7.62, "eta": "49:13:40", "max_grad_norm": 1.0, "loss": 0.9297246932983398, "grad_norm": 0.5875195264816284, "learning_rate": 0.00019029649595687334}
+{"ts": "2025-12-23T18:32:24", "event": "train_log", "step": 1062, "epoch": 0.458252427184466, "progress_pct": 7.64, "epoch_pct": 7.64, "eta": "49:10:41", "max_grad_norm": 1.0, "loss": 1.005869746208191, "grad_norm": 0.5552583932876587, "learning_rate": 0.00019065588499550765}
+{"ts": "2025-12-23T18:32:40", "event": "train_log", "step": 1064, "epoch": 0.4591154261057174, "progress_pct": 7.65, "epoch_pct": 7.65, "eta": "49:07:57", "max_grad_norm": 1.0, "loss": 0.8949927091598511, "grad_norm": 0.49282076954841614, "learning_rate": 0.00019101527403414198}
+{"ts": "2025-12-23T18:32:55", "event": "train_log", "step": 1066, "epoch": 0.45997842502696873, "progress_pct": 7.66, "epoch_pct": 7.67, "eta": "49:04:59", "max_grad_norm": 1.0, "loss": 0.9997886419296265, "grad_norm": 0.4951777160167694, "learning_rate": 0.0001913746630727763}
+{"ts": "2025-12-23T18:33:10", "event": "train_log", "step": 1068, "epoch": 0.4608414239482201, "progress_pct": 7.68, "epoch_pct": 7.68, "eta": "49:02:00", "max_grad_norm": 1.0, "loss": 0.9532123804092407, "grad_norm": 0.5154827237129211, "learning_rate": 0.0001917340521114106}
+{"ts": "2025-12-23T18:33:26", "event": "train_log", "step": 1070, "epoch": 0.4617044228694714, "progress_pct": 7.69, "epoch_pct": 7.7, "eta": "48:59:14", "max_grad_norm": 1.0, "loss": 0.8959843516349792, "grad_norm": 0.5547500252723694, "learning_rate": 0.00019209344115004494}
+{"ts": "2025-12-23T18:33:41", "event": "train_log", "step": 1072, "epoch": 0.46256742179072274, "progress_pct": 7.71, "epoch_pct": 7.71, "eta": "48:56:16", "max_grad_norm": 1.0, "loss": 0.8201484680175781, "grad_norm": 0.500188946723938, "learning_rate": 0.00019245283018867927}
+{"ts": "2025-12-23T18:33:56", "event": "train_log", "step": 1074, "epoch": 0.4634304207119741, "progress_pct": 7.72, "epoch_pct": 7.72, "eta": "48:53:27", "max_grad_norm": 1.0, "loss": 0.8255136609077454, "grad_norm": 0.4181794822216034, "learning_rate": 0.00019281221922731357}
+{"ts": "2025-12-23T18:34:12", "event": "train_log", "step": 1076, "epoch": 0.46429341963322546, "progress_pct": 7.74, "epoch_pct": 7.74, "eta": "48:50:34", "max_grad_norm": 1.0, "loss": 0.896024763584137, "grad_norm": 0.5613874197006226, "learning_rate": 0.0001931716082659479}
+{"ts": "2025-12-23T18:34:28", "event": "train_log", "step": 1078, "epoch": 0.4651564185544768, "progress_pct": 7.75, "epoch_pct": 7.75, "eta": "48:48:01", "max_grad_norm": 1.0, "loss": 0.8831873536109924, "grad_norm": 0.5000972151756287, "learning_rate": 0.0001935309973045822}
+{"ts": "2025-12-23T18:34:42", "event": "train_log", "step": 1080, "epoch": 0.46601941747572817, "progress_pct": 7.77, "epoch_pct": 7.77, "eta": "48:44:49", "max_grad_norm": 1.0, "loss": 0.9787988662719727, "grad_norm": 0.6321820616722107, "learning_rate": 0.00019389038634321654}
+{"ts": "2025-12-23T18:34:58", "event": "train_log", "step": 1082, "epoch": 0.4668824163969795, "progress_pct": 7.78, "epoch_pct": 7.78, "eta": "48:42:07", "max_grad_norm": 1.0, "loss": 0.933361828327179, "grad_norm": 0.4843652546405792, "learning_rate": 0.00019424977538185087}
+{"ts": "2025-12-23T18:35:12", "event": "train_log", "step": 1084, "epoch": 0.46774541531823083, "progress_pct": 7.79, "epoch_pct": 7.8, "eta": "48:39:08", "max_grad_norm": 1.0, "loss": 0.9046981334686279, "grad_norm": 0.537330150604248, "learning_rate": 0.00019460916442048517}
+{"ts": "2025-12-23T18:35:29", "event": "train_log", "step": 1086, "epoch": 0.4686084142394822, "progress_pct": 7.81, "epoch_pct": 7.81, "eta": "48:36:30", "max_grad_norm": 1.0, "loss": 0.9625781178474426, "grad_norm": 0.5761371850967407, "learning_rate": 0.0001949685534591195}
+{"ts": "2025-12-23T18:35:44", "event": "train_log", "step": 1088, "epoch": 0.46947141316073354, "progress_pct": 7.82, "epoch_pct": 7.82, "eta": "48:33:40", "max_grad_norm": 1.0, "loss": 0.9280619025230408, "grad_norm": 0.5209522843360901, "learning_rate": 0.00019532794249775383}
+{"ts": "2025-12-23T18:36:00", "event": "train_log", "step": 1090, "epoch": 0.4703344120819849, "progress_pct": 7.84, "epoch_pct": 7.84, "eta": "48:31:01", "max_grad_norm": 1.0, "loss": 0.8236247301101685, "grad_norm": 0.5383933186531067, "learning_rate": 0.00019568733153638813}
+{"ts": "2025-12-23T18:36:17", "event": "train_log", "step": 1092, "epoch": 0.47119741100323626, "progress_pct": 7.85, "epoch_pct": 7.85, "eta": "48:28:30", "max_grad_norm": 1.0, "loss": 0.9404071569442749, "grad_norm": 0.4994274377822876, "learning_rate": 0.00019604672057502246}
+{"ts": "2025-12-23T18:36:31", "event": "train_log", "step": 1094, "epoch": 0.4720604099244876, "progress_pct": 7.87, "epoch_pct": 7.87, "eta": "48:25:38", "max_grad_norm": 1.0, "loss": 0.8517536520957947, "grad_norm": 0.5177807211875916, "learning_rate": 0.0001964061096136568}
+{"ts": "2025-12-23T18:36:48", "event": "train_log", "step": 1096, "epoch": 0.47292340884573897, "progress_pct": 7.88, "epoch_pct": 7.88, "eta": "48:23:05", "max_grad_norm": 1.0, "loss": 0.8214367032051086, "grad_norm": 0.5374870896339417, "learning_rate": 0.00019676549865229112}
+{"ts": "2025-12-23T18:37:02", "event": "train_log", "step": 1098, "epoch": 0.47378640776699027, "progress_pct": 7.89, "epoch_pct": 7.9, "eta": "48:20:05", "max_grad_norm": 1.0, "loss": 1.016176700592041, "grad_norm": 0.5544074177742004, "learning_rate": 0.00019712488769092542}
+{"ts": "2025-12-23T18:37:16", "event": "train_log", "step": 1100, "epoch": 0.4746494066882416, "progress_pct": 7.91, "epoch_pct": 7.91, "eta": "48:17:08", "max_grad_norm": 1.0, "loss": 0.8425421118736267, "grad_norm": 0.5125867128372192, "learning_rate": 0.00019748427672955975}
+{"ts": "2025-12-23T18:48:06", "event": "train_log", "step": 1100, "epoch": 0.4746494066882416, "progress_pct": 7.91, "epoch_pct": 7.91, "eta": "50:23:15", "max_grad_norm": 1.0, "eval_loss": 0.944629430770874, "eval_runtime": 649.9107, "eval_samples_per_second": 3.17, "eval_steps_per_second": 3.17}
+{"ts": "2025-12-23T18:48:21", "event": "train_log", "step": 1102, "epoch": 0.475512405609493, "progress_pct": 7.92, "epoch_pct": 7.93, "eta": "50:20:12", "max_grad_norm": 1.0, "loss": 0.9444556832313538, "grad_norm": 0.5204418897628784, "learning_rate": 0.00019784366576819408}
+{"ts": "2025-12-23T18:48:36", "event": "train_log", "step": 1104, "epoch": 0.47637540453074434, "progress_pct": 7.94, "epoch_pct": 7.94, "eta": "50:17:10", "max_grad_norm": 1.0, "loss": 0.877082109451294, "grad_norm": 0.46085885167121887, "learning_rate": 0.0001982030548068284}
+{"ts": "2025-12-23T18:48:50", "event": "train_log", "step": 1106, "epoch": 0.4772384034519957, "progress_pct": 7.95, "epoch_pct": 7.95, "eta": "50:13:57", "max_grad_norm": 1.0, "loss": 0.9214640259742737, "grad_norm": 0.5269598960876465, "learning_rate": 0.00019856244384546272}
+{"ts": "2025-12-23T18:49:05", "event": "train_log", "step": 1108, "epoch": 0.47810140237324705, "progress_pct": 7.97, "epoch_pct": 7.97, "eta": "50:10:48", "max_grad_norm": 1.0, "loss": 0.8867175579071045, "grad_norm": 0.4894753694534302, "learning_rate": 0.00019892183288409705}
+{"ts": "2025-12-23T18:49:20", "event": "train_log", "step": 1110, "epoch": 0.47896440129449835, "progress_pct": 7.98, "epoch_pct": 7.98, "eta": "50:07:46", "max_grad_norm": 1.0, "loss": 0.9641162753105164, "grad_norm": 0.5204115509986877, "learning_rate": 0.00019928122192273138}
+{"ts": "2025-12-23T18:49:33", "event": "train_log", "step": 1112, "epoch": 0.4798274002157497, "progress_pct": 8.0, "epoch_pct": 8.0, "eta": "50:04:33", "max_grad_norm": 1.0, "loss": 1.0219199657440186, "grad_norm": 0.6399031281471252, "learning_rate": 0.00019964061096136568}
+{"ts": "2025-12-23T18:49:49", "event": "train_log", "step": 1114, "epoch": 0.48069039913700107, "progress_pct": 8.01, "epoch_pct": 8.01, "eta": "50:01:35", "max_grad_norm": 1.0, "loss": 0.8189998269081116, "grad_norm": 0.3979159891605377, "learning_rate": 0.0002}
+{"ts": "2025-12-23T18:50:04", "event": "train_log", "step": 1116, "epoch": 0.4815533980582524, "progress_pct": 8.02, "epoch_pct": 8.03, "eta": "49:58:38", "max_grad_norm": 1.0, "loss": 0.83241868019104, "grad_norm": 0.4782681465148926, "learning_rate": 0.0001999999879427254}
+{"ts": "2025-12-23T18:50:18", "event": "train_log", "step": 1118, "epoch": 0.4824163969795038, "progress_pct": 8.04, "epoch_pct": 8.04, "eta": "49:55:37", "max_grad_norm": 1.0, "loss": 0.9371466636657715, "grad_norm": 0.5235620141029358, "learning_rate": 0.00019999995177090454}
+{"ts": "2025-12-23T18:50:35", "event": "train_log", "step": 1120, "epoch": 0.48327939590075514, "progress_pct": 8.05, "epoch_pct": 8.05, "eta": "49:52:53", "max_grad_norm": 1.0, "loss": 0.7767758369445801, "grad_norm": 0.4543023407459259, "learning_rate": 0.00019999989148454606}
+{"ts": "2025-12-23T18:50:49", "event": "train_log", "step": 1122, "epoch": 0.4841423948220065, "progress_pct": 8.07, "epoch_pct": 8.07, "eta": "49:49:48", "max_grad_norm": 1.0, "loss": 1.0103063583374023, "grad_norm": 0.6191229820251465, "learning_rate": 0.00019999980708366457}
+{"ts": "2025-12-23T18:51:05", "event": "train_log", "step": 1124, "epoch": 0.4850053937432578, "progress_pct": 8.08, "epoch_pct": 8.08, "eta": "49:46:59", "max_grad_norm": 1.0, "loss": 0.8720875382423401, "grad_norm": 0.45392486453056335, "learning_rate": 0.00019999969856828042}
+{"ts": "2025-12-23T18:51:22", "event": "train_log", "step": 1126, "epoch": 0.48586839266450915, "progress_pct": 8.1, "epoch_pct": 8.1, "eta": "49:44:31", "max_grad_norm": 1.0, "loss": 0.7859150171279907, "grad_norm": 0.42748701572418213, "learning_rate": 0.00019999956593841974}
+{"ts": "2025-12-23T18:51:37", "event": "train_log", "step": 1128, "epoch": 0.4867313915857605, "progress_pct": 8.11, "epoch_pct": 8.11, "eta": "49:41:38", "max_grad_norm": 1.0, "loss": 0.9154419898986816, "grad_norm": 0.4952569603919983, "learning_rate": 0.00019999940919411454}
+{"ts": "2025-12-23T18:51:52", "event": "train_log", "step": 1130, "epoch": 0.48759439050701187, "progress_pct": 8.12, "epoch_pct": 8.13, "eta": "49:38:36", "max_grad_norm": 1.0, "loss": 0.9076330065727234, "grad_norm": 0.5522173047065735, "learning_rate": 0.00019999922833540264}
+{"ts": "2025-12-23T18:52:07", "event": "train_log", "step": 1132, "epoch": 0.4884573894282632, "progress_pct": 8.14, "epoch_pct": 8.14, "eta": "49:35:39", "max_grad_norm": 1.0, "loss": 0.8933543562889099, "grad_norm": 0.5355855226516724, "learning_rate": 0.00019999902336232758}
+{"ts": "2025-12-23T18:52:24", "event": "train_log", "step": 1134, "epoch": 0.4893203883495146, "progress_pct": 8.15, "epoch_pct": 8.16, "eta": "49:33:16", "max_grad_norm": 1.0, "loss": 0.9160735607147217, "grad_norm": 0.4613489508628845, "learning_rate": 0.00019999879427493885}
+{"ts": "2025-12-23T18:52:41", "event": "train_log", "step": 1136, "epoch": 0.49018338727076594, "progress_pct": 8.17, "epoch_pct": 8.17, "eta": "49:30:38", "max_grad_norm": 1.0, "loss": 0.8552446961402893, "grad_norm": 0.4758962094783783, "learning_rate": 0.0001999985410732917}
+{"ts": "2025-12-23T18:52:56", "event": "train_log", "step": 1138, "epoch": 0.49104638619201724, "progress_pct": 8.18, "epoch_pct": 8.18, "eta": "49:27:51", "max_grad_norm": 1.0, "loss": 0.9979530572891235, "grad_norm": 0.4549376964569092, "learning_rate": 0.00019999826375744715}
+{"ts": "2025-12-23T18:53:12", "event": "train_log", "step": 1140, "epoch": 0.4919093851132686, "progress_pct": 8.2, "epoch_pct": 8.2, "eta": "49:25:10", "max_grad_norm": 1.0, "loss": 0.9295380115509033, "grad_norm": 0.4363284409046173, "learning_rate": 0.0001999979623274721}
+{"ts": "2025-12-23T18:53:29", "event": "train_log", "step": 1142, "epoch": 0.49277238403451995, "progress_pct": 8.21, "epoch_pct": 8.21, "eta": "49:22:40", "max_grad_norm": 1.0, "loss": 0.8737252950668335, "grad_norm": 0.5090877413749695, "learning_rate": 0.0001999976367834392}
+{"ts": "2025-12-23T18:53:44", "event": "train_log", "step": 1144, "epoch": 0.4936353829557713, "progress_pct": 8.23, "epoch_pct": 8.23, "eta": "49:19:51", "max_grad_norm": 1.0, "loss": 0.8312779068946838, "grad_norm": 0.45340779423713684, "learning_rate": 0.000199997287125427}
+{"ts": "2025-12-23T18:53:59", "event": "train_log", "step": 1146, "epoch": 0.49449838187702266, "progress_pct": 8.24, "epoch_pct": 8.24, "eta": "49:17:02", "max_grad_norm": 1.0, "loss": 0.9105207324028015, "grad_norm": 0.4771472215652466, "learning_rate": 0.0001999969133535198}
+{"ts": "2025-12-23T18:54:15", "event": "train_log", "step": 1148, "epoch": 0.495361380798274, "progress_pct": 8.25, "epoch_pct": 8.26, "eta": "49:14:20", "max_grad_norm": 1.0, "loss": 0.8578172922134399, "grad_norm": 0.5251384377479553, "learning_rate": 0.00019999651546780773}
+{"ts": "2025-12-23T18:54:31", "event": "train_log", "step": 1150, "epoch": 0.4962243797195254, "progress_pct": 8.27, "epoch_pct": 8.27, "eta": "49:11:38", "max_grad_norm": 1.0, "loss": 0.9193941950798035, "grad_norm": 0.49128198623657227, "learning_rate": 0.00019999609346838676}
+{"ts": "2025-12-23T18:54:47", "event": "train_log", "step": 1152, "epoch": 0.4970873786407767, "progress_pct": 8.28, "epoch_pct": 8.28, "eta": "49:09:01", "max_grad_norm": 1.0, "loss": 0.9141314625740051, "grad_norm": 0.5558596849441528, "learning_rate": 0.0001999956473553586}
+{"ts": "2025-12-23T18:55:03", "event": "train_log", "step": 1154, "epoch": 0.49795037756202803, "progress_pct": 8.3, "epoch_pct": 8.3, "eta": "49:06:19", "max_grad_norm": 1.0, "loss": 0.9058388471603394, "grad_norm": 0.45872750878334045, "learning_rate": 0.00019999517712883087}
+{"ts": "2025-12-23T18:55:18", "event": "train_log", "step": 1156, "epoch": 0.4988133764832794, "progress_pct": 8.31, "epoch_pct": 8.31, "eta": "49:03:42", "max_grad_norm": 1.0, "loss": 0.8462487459182739, "grad_norm": 0.4710173010826111, "learning_rate": 0.00019999468278891698}
+{"ts": "2025-12-23T18:55:34", "event": "train_log", "step": 1158, "epoch": 0.49967637540453075, "progress_pct": 8.33, "epoch_pct": 8.33, "eta": "49:00:59", "max_grad_norm": 1.0, "loss": 0.8960906863212585, "grad_norm": 0.4805637001991272, "learning_rate": 0.0001999941643357361}
+{"ts": "2025-12-23T18:55:49", "event": "train_log", "step": 1160, "epoch": 0.5005393743257821, "progress_pct": 8.34, "epoch_pct": 8.34, "eta": "48:58:15", "max_grad_norm": 1.0, "loss": 0.9074980020523071, "grad_norm": 0.5108052492141724, "learning_rate": 0.00019999362176941325}
+{"ts": "2025-12-23T18:56:03", "event": "train_log", "step": 1162, "epoch": 0.5014023732470334, "progress_pct": 8.35, "epoch_pct": 8.36, "eta": "48:55:18", "max_grad_norm": 1.0, "loss": 0.9710080623626709, "grad_norm": 0.49572333693504333, "learning_rate": 0.00019999305509007932}
+{"ts": "2025-12-23T18:56:19", "event": "train_log", "step": 1164, "epoch": 0.5022653721682848, "progress_pct": 8.37, "epoch_pct": 8.37, "eta": "48:52:35", "max_grad_norm": 1.0, "loss": 0.8877825140953064, "grad_norm": 0.5304561257362366, "learning_rate": 0.0001999924642978709}
+{"ts": "2025-12-23T18:56:36", "event": "train_log", "step": 1166, "epoch": 0.5031283710895361, "progress_pct": 8.38, "epoch_pct": 8.39, "eta": "48:50:13", "max_grad_norm": 1.0, "loss": 0.8955381512641907, "grad_norm": 0.5007328391075134, "learning_rate": 0.0001999918493929305}
+{"ts": "2025-12-23T18:56:51", "event": "train_log", "step": 1168, "epoch": 0.5039913700107875, "progress_pct": 8.4, "epoch_pct": 8.4, "eta": "48:47:28", "max_grad_norm": 1.0, "loss": 0.9478562474250793, "grad_norm": 0.569549024105072, "learning_rate": 0.0001999912103754064}
+{"ts": "2025-12-23T18:57:06", "event": "train_log", "step": 1170, "epoch": 0.5048543689320388, "progress_pct": 8.41, "epoch_pct": 8.41, "eta": "48:44:46", "max_grad_norm": 1.0, "loss": 0.9685383439064026, "grad_norm": 0.5354957580566406, "learning_rate": 0.00019999054724545264}
+{"ts": "2025-12-23T18:57:20", "event": "train_log", "step": 1172, "epoch": 0.5057173678532901, "progress_pct": 8.43, "epoch_pct": 8.43, "eta": "48:41:47", "max_grad_norm": 1.0, "loss": 0.9221975207328796, "grad_norm": 0.547788143157959, "learning_rate": 0.00019998986000322917}
+{"ts": "2025-12-23T18:57:36", "event": "train_log", "step": 1174, "epoch": 0.5065803667745415, "progress_pct": 8.44, "epoch_pct": 8.44, "eta": "48:39:16", "max_grad_norm": 1.0, "loss": 0.9104788303375244, "grad_norm": 0.4919529855251312, "learning_rate": 0.00019998914864890175}
+{"ts": "2025-12-23T18:57:51", "event": "train_log", "step": 1176, "epoch": 0.5074433656957928, "progress_pct": 8.46, "epoch_pct": 8.46, "eta": "48:36:34", "max_grad_norm": 1.0, "loss": 0.9176050424575806, "grad_norm": 0.5274141430854797, "learning_rate": 0.00019998841318264187}
+{"ts": "2025-12-23T18:58:07", "event": "train_log", "step": 1178, "epoch": 0.5083063646170443, "progress_pct": 8.47, "epoch_pct": 8.47, "eta": "48:34:09", "max_grad_norm": 1.0, "loss": 0.8389710187911987, "grad_norm": 0.4257420301437378, "learning_rate": 0.00019998765360462688}
+{"ts": "2025-12-23T18:58:23", "event": "train_log", "step": 1180, "epoch": 0.5091693635382956, "progress_pct": 8.48, "epoch_pct": 8.49, "eta": "48:31:35", "max_grad_norm": 1.0, "loss": 1.0164397954940796, "grad_norm": 0.4947778880596161, "learning_rate": 0.00019998686991504002}
+{"ts": "2025-12-23T18:58:38", "event": "train_log", "step": 1182, "epoch": 0.510032362459547, "progress_pct": 8.5, "epoch_pct": 8.5, "eta": "48:28:48", "max_grad_norm": 1.0, "loss": 0.9900994300842285, "grad_norm": 0.5540821552276611, "learning_rate": 0.00019998606211407016}
+{"ts": "2025-12-23T18:58:54", "event": "train_log", "step": 1184, "epoch": 0.5108953613807983, "progress_pct": 8.51, "epoch_pct": 8.51, "eta": "48:26:18", "max_grad_norm": 1.0, "loss": 0.8797636032104492, "grad_norm": 0.4793289601802826, "learning_rate": 0.0001999852302019122}
+{"ts": "2025-12-23T18:59:09", "event": "train_log", "step": 1186, "epoch": 0.5117583603020496, "progress_pct": 8.53, "epoch_pct": 8.53, "eta": "48:23:44", "max_grad_norm": 1.0, "loss": 0.96225905418396, "grad_norm": 0.47429659962654114, "learning_rate": 0.00019998437417876672}
+{"ts": "2025-12-23T18:59:25", "event": "train_log", "step": 1188, "epoch": 0.512621359223301, "progress_pct": 8.54, "epoch_pct": 8.54, "eta": "48:21:08", "max_grad_norm": 1.0, "loss": 0.8604235649108887, "grad_norm": 0.44918450713157654, "learning_rate": 0.00019998349404484013}
+{"ts": "2025-12-23T18:59:40", "event": "train_log", "step": 1190, "epoch": 0.5134843581445523, "progress_pct": 8.56, "epoch_pct": 8.56, "eta": "48:18:31", "max_grad_norm": 1.0, "loss": 1.0325366258621216, "grad_norm": 0.566977858543396, "learning_rate": 0.00019998258980034468}
+{"ts": "2025-12-23T18:59:56", "event": "train_log", "step": 1192, "epoch": 0.5143473570658037, "progress_pct": 8.57, "epoch_pct": 8.57, "eta": "48:16:09", "max_grad_norm": 1.0, "loss": 0.7658900022506714, "grad_norm": 0.4671999514102936, "learning_rate": 0.00019998166144549843}
+{"ts": "2025-12-23T19:00:13", "event": "train_log", "step": 1194, "epoch": 0.515210355987055, "progress_pct": 8.58, "epoch_pct": 8.59, "eta": "48:13:49", "max_grad_norm": 1.0, "loss": 0.9365432858467102, "grad_norm": 0.42312702536582947, "learning_rate": 0.00019998070898052521}
+{"ts": "2025-12-23T19:00:29", "event": "train_log", "step": 1196, "epoch": 0.5160733549083064, "progress_pct": 8.6, "epoch_pct": 8.6, "eta": "48:11:24", "max_grad_norm": 1.0, "loss": 0.771016538143158, "grad_norm": 0.4652721881866455, "learning_rate": 0.00019997973240565476}
+{"ts": "2025-12-23T19:00:46", "event": "train_log", "step": 1198, "epoch": 0.5169363538295577, "progress_pct": 8.61, "epoch_pct": 8.62, "eta": "48:09:05", "max_grad_norm": 1.0, "loss": 0.9123705625534058, "grad_norm": 0.5048499703407288, "learning_rate": 0.00019997873172112254}
+{"ts": "2025-12-23T19:01:01", "event": "train_log", "step": 1200, "epoch": 0.517799352750809, "progress_pct": 8.63, "epoch_pct": 8.63, "eta": "48:06:26", "max_grad_norm": 1.0, "loss": 0.8975751399993896, "grad_norm": 0.5446439981460571, "learning_rate": 0.0001999777069271699}
+{"ts": "2025-12-23T19:12:00", "event": "train_log", "step": 1200, "epoch": 0.517799352750809, "progress_pct": 8.63, "epoch_pct": 8.63, "eta": "50:02:42", "max_grad_norm": 1.0, "eval_loss": 0.9344067573547363, "eval_runtime": 658.6934, "eval_samples_per_second": 3.127, "eval_steps_per_second": 3.127}
+{"ts": "2025-12-23T19:12:14", "event": "train_log", "step": 1202, "epoch": 0.5186623516720604, "progress_pct": 8.64, "epoch_pct": 8.64, "eta": "49:59:46", "max_grad_norm": 1.0, "loss": 0.89097660779953, "grad_norm": 0.5044088959693909, "learning_rate": 0.0001999766580240439}
+{"ts": "2025-12-23T19:12:29", "event": "train_log", "step": 1204, "epoch": 0.5195253505933117, "progress_pct": 8.66, "epoch_pct": 8.66, "eta": "49:56:52", "max_grad_norm": 1.0, "loss": 0.9138525128364563, "grad_norm": 0.4672294855117798, "learning_rate": 0.00019997558501199753}
+{"ts": "2025-12-23T19:12:45", "event": "train_log", "step": 1206, "epoch": 0.5203883495145631, "progress_pct": 8.67, "epoch_pct": 8.67, "eta": "49:54:12", "max_grad_norm": 1.0, "loss": 0.8946340680122375, "grad_norm": 0.45749008655548096, "learning_rate": 0.00019997448789128952}
+{"ts": "2025-12-23T19:13:00", "event": "train_log", "step": 1208, "epoch": 0.5212513484358144, "progress_pct": 8.69, "epoch_pct": 8.69, "eta": "49:51:26", "max_grad_norm": 1.0, "loss": 0.8661436438560486, "grad_norm": 0.4828707277774811, "learning_rate": 0.00019997336666218447}
+{"ts": "2025-12-23T19:13:16", "event": "train_log", "step": 1210, "epoch": 0.5221143473570659, "progress_pct": 8.7, "epoch_pct": 8.7, "eta": "49:48:56", "max_grad_norm": 1.0, "loss": 0.7684835195541382, "grad_norm": 0.3975147008895874, "learning_rate": 0.0001999722213249527}
+{"ts": "2025-12-23T19:13:31", "event": "train_log", "step": 1212, "epoch": 0.5229773462783172, "progress_pct": 8.71, "epoch_pct": 8.72, "eta": "49:46:05", "max_grad_norm": 1.0, "loss": 0.9667536616325378, "grad_norm": 0.5642077326774597, "learning_rate": 0.00019997105187987045}
+{"ts": "2025-12-23T19:13:46", "event": "train_log", "step": 1214, "epoch": 0.5238403451995685, "progress_pct": 8.73, "epoch_pct": 8.73, "eta": "49:43:15", "max_grad_norm": 1.0, "loss": 0.8679366707801819, "grad_norm": 0.4907105565071106, "learning_rate": 0.00019996985832721972}
+{"ts": "2025-12-23T19:14:01", "event": "train_log", "step": 1216, "epoch": 0.5247033441208199, "progress_pct": 8.74, "epoch_pct": 8.75, "eta": "49:40:32", "max_grad_norm": 1.0, "loss": 0.8802784085273743, "grad_norm": 0.46214789152145386, "learning_rate": 0.0001999686406672883}
+{"ts": "2025-12-23T19:14:16", "event": "train_log", "step": 1218, "epoch": 0.5255663430420712, "progress_pct": 8.76, "epoch_pct": 8.76, "eta": "49:37:49", "max_grad_norm": 1.0, "loss": 0.8493598103523254, "grad_norm": 0.4355131685733795, "learning_rate": 0.00019996739890036985}
+{"ts": "2025-12-23T19:14:32", "event": "train_log", "step": 1220, "epoch": 0.5264293419633226, "progress_pct": 8.77, "epoch_pct": 8.77, "eta": "49:35:10", "max_grad_norm": 1.0, "loss": 0.8949980735778809, "grad_norm": 0.4293915331363678, "learning_rate": 0.0001999661330267638}
+{"ts": "2025-12-23T19:14:47", "event": "train_log", "step": 1222, "epoch": 0.5272923408845739, "progress_pct": 8.79, "epoch_pct": 8.79, "eta": "49:32:24", "max_grad_norm": 1.0, "loss": 0.9497376680374146, "grad_norm": 0.5452485680580139, "learning_rate": 0.00019996484304677544}
+{"ts": "2025-12-23T19:15:01", "event": "train_log", "step": 1224, "epoch": 0.5281553398058253, "progress_pct": 8.8, "epoch_pct": 8.8, "eta": "49:29:37", "max_grad_norm": 1.0, "loss": 0.9170818328857422, "grad_norm": 0.45874500274658203, "learning_rate": 0.00019996352896071583}
+{"ts": "2025-12-23T19:15:17", "event": "train_log", "step": 1226, "epoch": 0.5290183387270766, "progress_pct": 8.82, "epoch_pct": 8.82, "eta": "49:26:59", "max_grad_norm": 1.0, "loss": 0.7557252645492554, "grad_norm": 0.4414025843143463, "learning_rate": 0.00019996219076890182}
+{"ts": "2025-12-23T19:15:32", "event": "train_log", "step": 1228, "epoch": 0.5298813376483279, "progress_pct": 8.83, "epoch_pct": 8.83, "eta": "49:24:18", "max_grad_norm": 1.0, "loss": 0.848960816860199, "grad_norm": 0.4891829192638397, "learning_rate": 0.0001999608284716562}
+{"ts": "2025-12-23T19:15:47", "event": "train_log", "step": 1230, "epoch": 0.5307443365695793, "progress_pct": 8.84, "epoch_pct": 8.85, "eta": "49:21:32", "max_grad_norm": 1.0, "loss": 0.9555954933166504, "grad_norm": 0.5048345327377319, "learning_rate": 0.00019995944206930734}
+{"ts": "2025-12-23T19:16:02", "event": "train_log", "step": 1232, "epoch": 0.5316073354908306, "progress_pct": 8.86, "epoch_pct": 8.86, "eta": "49:18:54", "max_grad_norm": 1.0, "loss": 0.8080939054489136, "grad_norm": 0.5006756782531738, "learning_rate": 0.00019995803156218968}
+{"ts": "2025-12-23T19:16:17", "event": "train_log", "step": 1234, "epoch": 0.532470334412082, "progress_pct": 8.87, "epoch_pct": 8.87, "eta": "49:16:10", "max_grad_norm": 1.0, "loss": 0.8638371825218201, "grad_norm": 0.5422173738479614, "learning_rate": 0.00019995659695064332}
+{"ts": "2025-12-23T19:16:31", "event": "train_log", "step": 1236, "epoch": 0.5333333333333333, "progress_pct": 8.89, "epoch_pct": 8.89, "eta": "49:13:25", "max_grad_norm": 1.0, "loss": 0.889068067073822, "grad_norm": 0.4535163640975952, "learning_rate": 0.0001999551382350142}
+{"ts": "2025-12-23T19:16:46", "event": "train_log", "step": 1238, "epoch": 0.5341963322545846, "progress_pct": 8.9, "epoch_pct": 8.9, "eta": "49:10:39", "max_grad_norm": 1.0, "loss": 0.8803121447563171, "grad_norm": 0.4588642418384552, "learning_rate": 0.00019995365541565412}
+{"ts": "2025-12-23T19:17:01", "event": "train_log", "step": 1240, "epoch": 0.535059331175836, "progress_pct": 8.92, "epoch_pct": 8.92, "eta": "49:07:58", "max_grad_norm": 1.0, "loss": 0.9694926738739014, "grad_norm": 0.49366191029548645, "learning_rate": 0.00019995214849292064}
+{"ts": "2025-12-23T19:17:16", "event": "train_log", "step": 1242, "epoch": 0.5359223300970873, "progress_pct": 8.93, "epoch_pct": 8.93, "eta": "49:05:15", "max_grad_norm": 1.0, "loss": 0.8367960453033447, "grad_norm": 0.41988301277160645, "learning_rate": 0.0001999506174671771}
+{"ts": "2025-12-23T19:17:30", "event": "train_log", "step": 1244, "epoch": 0.5367853290183388, "progress_pct": 8.94, "epoch_pct": 8.95, "eta": "49:02:29", "max_grad_norm": 1.0, "loss": 0.942340612411499, "grad_norm": 0.5242130160331726, "learning_rate": 0.00019994906233879273}
+{"ts": "2025-12-23T19:17:44", "event": "train_log", "step": 1246, "epoch": 0.53764832793959, "progress_pct": 8.96, "epoch_pct": 8.96, "eta": "48:59:45", "max_grad_norm": 1.0, "loss": 0.8926790356636047, "grad_norm": 0.4899834096431732, "learning_rate": 0.00019994748310814256}
+{"ts": "2025-12-23T19:17:59", "event": "train_log", "step": 1248, "epoch": 0.5385113268608415, "progress_pct": 8.97, "epoch_pct": 8.98, "eta": "48:57:01", "max_grad_norm": 1.0, "loss": 0.99891597032547, "grad_norm": 0.5496823787689209, "learning_rate": 0.00019994587977560744}
+{"ts": "2025-12-23T19:18:14", "event": "train_log", "step": 1250, "epoch": 0.5393743257820928, "progress_pct": 8.99, "epoch_pct": 8.99, "eta": "48:54:23", "max_grad_norm": 1.0, "loss": 0.8873116970062256, "grad_norm": 0.4497414231300354, "learning_rate": 0.00019994425234157396}
+{"ts": "2025-12-23T19:18:30", "event": "train_log", "step": 1252, "epoch": 0.5402373247033441, "progress_pct": 9.0, "epoch_pct": 9.0, "eta": "48:51:54", "max_grad_norm": 1.0, "loss": 0.9041396975517273, "grad_norm": 0.4256928563117981, "learning_rate": 0.00019994260080643454}
+{"ts": "2025-12-23T19:18:46", "event": "train_log", "step": 1254, "epoch": 0.5411003236245955, "progress_pct": 9.02, "epoch_pct": 9.02, "eta": "48:49:33", "max_grad_norm": 1.0, "loss": 0.7647561430931091, "grad_norm": 0.36910608410835266, "learning_rate": 0.00019994092517058753}
+{"ts": "2025-12-23T19:19:00", "event": "train_log", "step": 1256, "epoch": 0.5419633225458468, "progress_pct": 9.03, "epoch_pct": 9.03, "eta": "48:46:46", "max_grad_norm": 1.0, "loss": 0.8892287015914917, "grad_norm": 0.537584125995636, "learning_rate": 0.0001999392254344369}
+{"ts": "2025-12-23T19:19:15", "event": "train_log", "step": 1258, "epoch": 0.5428263214670982, "progress_pct": 9.05, "epoch_pct": 9.05, "eta": "48:44:06", "max_grad_norm": 1.0, "loss": 0.8638571500778198, "grad_norm": 0.49463894963264465, "learning_rate": 0.00019993750159839264}
+{"ts": "2025-12-23T19:19:29", "event": "train_log", "step": 1260, "epoch": 0.5436893203883495, "progress_pct": 9.06, "epoch_pct": 9.06, "eta": "48:41:21", "max_grad_norm": 1.0, "loss": 0.8165372014045715, "grad_norm": 0.5052056908607483, "learning_rate": 0.00019993575366287036}
+{"ts": "2025-12-23T19:19:44", "event": "train_log", "step": 1262, "epoch": 0.5445523193096009, "progress_pct": 9.07, "epoch_pct": 9.08, "eta": "48:38:44", "max_grad_norm": 1.0, "loss": 0.9099977016448975, "grad_norm": 0.47367510199546814, "learning_rate": 0.0001999339816282916}
+{"ts": "2025-12-23T19:19:58", "event": "train_log", "step": 1264, "epoch": 0.5454153182308522, "progress_pct": 9.09, "epoch_pct": 9.09, "eta": "48:36:05", "max_grad_norm": 1.0, "loss": 0.8557311296463013, "grad_norm": 0.4600350558757782, "learning_rate": 0.00019993218549508364}
+{"ts": "2025-12-23T19:20:12", "event": "train_log", "step": 1266, "epoch": 0.5462783171521035, "progress_pct": 9.1, "epoch_pct": 9.1, "eta": "48:33:20", "max_grad_norm": 1.0, "loss": 0.9136497974395752, "grad_norm": 0.5684534311294556, "learning_rate": 0.0001999303652636797}
+{"ts": "2025-12-23T19:20:26", "event": "train_log", "step": 1268, "epoch": 0.5471413160733549, "progress_pct": 9.12, "epoch_pct": 9.12, "eta": "48:30:36", "max_grad_norm": 1.0, "loss": 0.7906932830810547, "grad_norm": 0.5151359438896179, "learning_rate": 0.00019992852093451865}
+{"ts": "2025-12-23T19:20:41", "event": "train_log", "step": 1270, "epoch": 0.5480043149946062, "progress_pct": 9.13, "epoch_pct": 9.13, "eta": "48:27:57", "max_grad_norm": 1.0, "loss": 0.9326766133308411, "grad_norm": 0.48577409982681274, "learning_rate": 0.00019992665250804525}
+{"ts": "2025-12-23T19:20:56", "event": "train_log", "step": 1272, "epoch": 0.5488673139158576, "progress_pct": 9.15, "epoch_pct": 9.15, "eta": "48:25:31", "max_grad_norm": 1.0, "loss": 0.9734495878219604, "grad_norm": 0.490531325340271, "learning_rate": 0.00019992475998471004}
+{"ts": "2025-12-23T19:21:12", "event": "train_log", "step": 1274, "epoch": 0.5497303128371089, "progress_pct": 9.16, "epoch_pct": 9.16, "eta": "48:23:10", "max_grad_norm": 1.0, "loss": 0.8728410005569458, "grad_norm": 0.5092435479164124, "learning_rate": 0.00019992284336496947}
+{"ts": "2025-12-23T19:21:28", "event": "train_log", "step": 1276, "epoch": 0.5505933117583603, "progress_pct": 9.17, "epoch_pct": 9.18, "eta": "48:20:42", "max_grad_norm": 1.0, "loss": 0.7572637796401978, "grad_norm": 0.3843296766281128, "learning_rate": 0.00019992090264928566}
+{"ts": "2025-12-23T19:21:44", "event": "train_log", "step": 1278, "epoch": 0.5514563106796116, "progress_pct": 9.19, "epoch_pct": 9.19, "eta": "48:18:22", "max_grad_norm": 1.0, "loss": 0.8895323872566223, "grad_norm": 0.534304678440094, "learning_rate": 0.00019991893783812662}
+{"ts": "2025-12-23T19:22:00", "event": "train_log", "step": 1280, "epoch": 0.552319309600863, "progress_pct": 9.2, "epoch_pct": 9.21, "eta": "48:16:00", "max_grad_norm": 1.0, "loss": 0.9318088293075562, "grad_norm": 0.4567227363586426, "learning_rate": 0.00019991694893196614}
+{"ts": "2025-12-23T19:22:16", "event": "train_log", "step": 1282, "epoch": 0.5531823085221144, "progress_pct": 9.22, "epoch_pct": 9.22, "eta": "48:13:43", "max_grad_norm": 1.0, "loss": 0.8541979789733887, "grad_norm": 0.48464900255203247, "learning_rate": 0.0001999149359312839}
+{"ts": "2025-12-23T19:22:31", "event": "train_log", "step": 1284, "epoch": 0.5540453074433657, "progress_pct": 9.23, "epoch_pct": 9.23, "eta": "48:11:10", "max_grad_norm": 1.0, "loss": 0.977894127368927, "grad_norm": 0.5569567084312439, "learning_rate": 0.00019991289883656524}
+{"ts": "2025-12-23T19:22:46", "event": "train_log", "step": 1286, "epoch": 0.5549083063646171, "progress_pct": 9.25, "epoch_pct": 9.25, "eta": "48:08:43", "max_grad_norm": 1.0, "loss": 0.8860608339309692, "grad_norm": 0.4637227952480316, "learning_rate": 0.00019991083764830145}
+{"ts": "2025-12-23T19:23:03", "event": "train_log", "step": 1288, "epoch": 0.5557713052858684, "progress_pct": 9.26, "epoch_pct": 9.26, "eta": "48:06:29", "max_grad_norm": 1.0, "loss": 0.8429648876190186, "grad_norm": 0.4096687436103821, "learning_rate": 0.00019990875236698956}
+{"ts": "2025-12-23T19:23:19", "event": "train_log", "step": 1290, "epoch": 0.5566343042071198, "progress_pct": 9.28, "epoch_pct": 9.28, "eta": "48:04:09", "max_grad_norm": 1.0, "loss": 0.8510909080505371, "grad_norm": 0.5221695303916931, "learning_rate": 0.00019990664299313242}
+{"ts": "2025-12-23T19:23:34", "event": "train_log", "step": 1292, "epoch": 0.5574973031283711, "progress_pct": 9.29, "epoch_pct": 9.29, "eta": "48:01:43", "max_grad_norm": 1.0, "loss": 0.8971074223518372, "grad_norm": 0.5155899524688721, "learning_rate": 0.00019990450952723872}
+{"ts": "2025-12-23T19:23:51", "event": "train_log", "step": 1294, "epoch": 0.5583603020496224, "progress_pct": 9.3, "epoch_pct": 9.31, "eta": "47:59:31", "max_grad_norm": 1.0, "loss": 0.9030373096466064, "grad_norm": 0.5064809322357178, "learning_rate": 0.0001999023519698229}
+{"ts": "2025-12-23T19:24:06", "event": "train_log", "step": 1296, "epoch": 0.5592233009708738, "progress_pct": 9.32, "epoch_pct": 9.32, "eta": "47:57:00", "max_grad_norm": 1.0, "loss": 0.7866057753562927, "grad_norm": 0.40551698207855225, "learning_rate": 0.00019990017032140526}
+{"ts": "2025-12-23T19:24:21", "event": "train_log", "step": 1298, "epoch": 0.5600862998921251, "progress_pct": 9.33, "epoch_pct": 9.33, "eta": "47:54:33", "max_grad_norm": 1.0, "loss": 0.9477730989456177, "grad_norm": 0.5009430050849915, "learning_rate": 0.00019989796458251194}
+{"ts": "2025-12-23T19:24:35", "event": "train_log", "step": 1300, "epoch": 0.5609492988133765, "progress_pct": 9.35, "epoch_pct": 9.35, "eta": "47:52:03", "max_grad_norm": 1.0, "loss": 0.9206778407096863, "grad_norm": 0.5192028880119324, "learning_rate": 0.00019989573475367477}
+{"ts": "2025-12-23T19:35:41", "event": "train_log", "step": 1300, "epoch": 0.5609492988133765, "progress_pct": 9.35, "epoch_pct": 9.35, "eta": "49:39:36", "max_grad_norm": 1.0, "eval_loss": 0.9177446365356445, "eval_runtime": 665.3245, "eval_samples_per_second": 3.096, "eval_steps_per_second": 3.096}
+{"ts": "2025-12-23T19:35:56", "event": "train_log", "step": 1302, "epoch": 0.5618122977346278, "progress_pct": 9.36, "epoch_pct": 9.36, "eta": "49:37:00", "max_grad_norm": 1.0, "loss": 0.9516512155532837, "grad_norm": 0.5580230951309204, "learning_rate": 0.00019989348083543148}
+{"ts": "2025-12-23T19:36:11", "event": "train_log", "step": 1304, "epoch": 0.5626752966558792, "progress_pct": 9.38, "epoch_pct": 9.38, "eta": "49:34:19", "max_grad_norm": 1.0, "loss": 0.7725991606712341, "grad_norm": 0.4151005744934082, "learning_rate": 0.00019989120282832564}
+{"ts": "2025-12-23T19:36:25", "event": "train_log", "step": 1306, "epoch": 0.5635382955771305, "progress_pct": 9.39, "epoch_pct": 9.39, "eta": "49:31:41", "max_grad_norm": 1.0, "loss": 0.9241501688957214, "grad_norm": 0.56330406665802, "learning_rate": 0.00019988890073290656}
+{"ts": "2025-12-23T19:36:41", "event": "train_log", "step": 1308, "epoch": 0.5644012944983818, "progress_pct": 9.4, "epoch_pct": 9.41, "eta": "49:29:13", "max_grad_norm": 1.0, "loss": 0.8351686000823975, "grad_norm": 0.44836440682411194, "learning_rate": 0.00019988657454972936}
+{"ts": "2025-12-23T19:36:56", "event": "train_log", "step": 1310, "epoch": 0.5652642934196332, "progress_pct": 9.42, "epoch_pct": 9.42, "eta": "49:26:30", "max_grad_norm": 1.0, "loss": 0.9033217430114746, "grad_norm": 0.5414754152297974, "learning_rate": 0.00019988422427935496}
+{"ts": "2025-12-23T19:37:09", "event": "train_log", "step": 1312, "epoch": 0.5661272923408845, "progress_pct": 9.43, "epoch_pct": 9.44, "eta": "49:23:43", "max_grad_norm": 1.0, "loss": 0.8885331153869629, "grad_norm": 0.5283750891685486, "learning_rate": 0.0001998818499223502}
+{"ts": "2025-12-23T19:37:24", "event": "train_log", "step": 1314, "epoch": 0.566990291262136, "progress_pct": 9.45, "epoch_pct": 9.45, "eta": "49:21:04", "max_grad_norm": 1.0, "loss": 0.8359912037849426, "grad_norm": 0.45846256613731384, "learning_rate": 0.00019987945147928758}
+{"ts": "2025-12-23T19:37:39", "event": "train_log", "step": 1316, "epoch": 0.5678532901833873, "progress_pct": 9.46, "epoch_pct": 9.46, "eta": "49:18:28", "max_grad_norm": 1.0, "loss": 0.8327895402908325, "grad_norm": 0.44439879059791565, "learning_rate": 0.0001998770289507455}
+{"ts": "2025-12-23T19:37:53", "event": "train_log", "step": 1318, "epoch": 0.5687162891046387, "progress_pct": 9.48, "epoch_pct": 9.48, "eta": "49:15:43", "max_grad_norm": 1.0, "loss": 0.9354757070541382, "grad_norm": 0.5491341948509216, "learning_rate": 0.00019987458233730813}
+{"ts": "2025-12-23T19:38:06", "event": "train_log", "step": 1320, "epoch": 0.56957928802589, "progress_pct": 9.49, "epoch_pct": 9.49, "eta": "49:12:57", "max_grad_norm": 1.0, "loss": 0.944054901599884, "grad_norm": 0.5502263307571411, "learning_rate": 0.00019987211163956548}
+{"ts": "2025-12-23T19:38:21", "event": "train_log", "step": 1322, "epoch": 0.5704422869471413, "progress_pct": 9.51, "epoch_pct": 9.51, "eta": "49:10:19", "max_grad_norm": 1.0, "loss": 0.9515072107315063, "grad_norm": 0.47165682911872864, "learning_rate": 0.00019986961685811334}
+{"ts": "2025-12-23T19:38:34", "event": "train_log", "step": 1324, "epoch": 0.5713052858683927, "progress_pct": 9.52, "epoch_pct": 9.52, "eta": "49:07:33", "max_grad_norm": 1.0, "loss": 0.9455493688583374, "grad_norm": 0.5136987566947937, "learning_rate": 0.0001998670979935533}
+{"ts": "2025-12-23T19:38:49", "event": "train_log", "step": 1326, "epoch": 0.572168284789644, "progress_pct": 9.53, "epoch_pct": 9.54, "eta": "49:04:59", "max_grad_norm": 1.0, "loss": 0.8626728057861328, "grad_norm": 0.4822693169116974, "learning_rate": 0.00019986455504649277}
+{"ts": "2025-12-23T19:39:05", "event": "train_log", "step": 1328, "epoch": 0.5730312837108954, "progress_pct": 9.55, "epoch_pct": 9.55, "eta": "49:02:32", "max_grad_norm": 1.0, "loss": 0.8857194781303406, "grad_norm": 0.4639468193054199, "learning_rate": 0.000199861988017545}
+{"ts": "2025-12-23T19:39:19", "event": "train_log", "step": 1330, "epoch": 0.5738942826321467, "progress_pct": 9.56, "epoch_pct": 9.56, "eta": "48:59:51", "max_grad_norm": 1.0, "loss": 0.9198446273803711, "grad_norm": 0.5224950313568115, "learning_rate": 0.00019985939690732898}
+{"ts": "2025-12-23T19:39:34", "event": "train_log", "step": 1332, "epoch": 0.574757281553398, "progress_pct": 9.58, "epoch_pct": 9.58, "eta": "48:57:18", "max_grad_norm": 1.0, "loss": 0.8785439133644104, "grad_norm": 0.47504499554634094, "learning_rate": 0.00019985678171646954}
+{"ts": "2025-12-23T19:39:48", "event": "train_log", "step": 1334, "epoch": 0.5756202804746494, "progress_pct": 9.59, "epoch_pct": 9.59, "eta": "48:54:36", "max_grad_norm": 1.0, "loss": 0.9593754410743713, "grad_norm": 0.5022051930427551, "learning_rate": 0.0001998541424455974}
+{"ts": "2025-12-23T19:40:02", "event": "train_log", "step": 1336, "epoch": 0.5764832793959007, "progress_pct": 9.61, "epoch_pct": 9.61, "eta": "48:52:02", "max_grad_norm": 1.0, "loss": 0.986197292804718, "grad_norm": 0.4572875201702118, "learning_rate": 0.00019985147909534897}
+{"ts": "2025-12-23T19:40:18", "event": "train_log", "step": 1338, "epoch": 0.5773462783171521, "progress_pct": 9.62, "epoch_pct": 9.62, "eta": "48:49:35", "max_grad_norm": 1.0, "loss": 0.9163863658905029, "grad_norm": 0.5153827667236328, "learning_rate": 0.00019984879166636644}
+{"ts": "2025-12-23T19:40:32", "event": "train_log", "step": 1340, "epoch": 0.5782092772384034, "progress_pct": 9.63, "epoch_pct": 9.64, "eta": "48:46:59", "max_grad_norm": 1.0, "loss": 0.8815995454788208, "grad_norm": 0.4813650846481323, "learning_rate": 0.00019984608015929792}
+{"ts": "2025-12-23T19:40:47", "event": "train_log", "step": 1342, "epoch": 0.5790722761596548, "progress_pct": 9.65, "epoch_pct": 9.65, "eta": "48:44:31", "max_grad_norm": 1.0, "loss": 0.857044517993927, "grad_norm": 0.4319819211959839, "learning_rate": 0.0001998433445747973}
+{"ts": "2025-12-23T19:41:01", "event": "train_log", "step": 1344, "epoch": 0.5799352750809061, "progress_pct": 9.66, "epoch_pct": 9.67, "eta": "48:41:56", "max_grad_norm": 1.0, "loss": 0.8939256072044373, "grad_norm": 0.5128870010375977, "learning_rate": 0.00019984058491352423}
+{"ts": "2025-12-23T19:41:16", "event": "train_log", "step": 1346, "epoch": 0.5807982740021574, "progress_pct": 9.68, "epoch_pct": 9.68, "eta": "48:39:26", "max_grad_norm": 1.0, "loss": 0.9267327785491943, "grad_norm": 0.41450315713882446, "learning_rate": 0.0001998378011761442}
+{"ts": "2025-12-23T19:41:31", "event": "train_log", "step": 1348, "epoch": 0.5816612729234089, "progress_pct": 9.69, "epoch_pct": 9.69, "eta": "48:37:01", "max_grad_norm": 1.0, "loss": 0.8494639992713928, "grad_norm": 0.42916348576545715, "learning_rate": 0.00019983499336332844}
+{"ts": "2025-12-23T19:41:46", "event": "train_log", "step": 1350, "epoch": 0.5825242718446602, "progress_pct": 9.71, "epoch_pct": 9.71, "eta": "48:34:25", "max_grad_norm": 1.0, "loss": 0.9720427989959717, "grad_norm": 0.43995746970176697, "learning_rate": 0.00019983216147575412}
+{"ts": "2025-12-23T19:42:00", "event": "train_log", "step": 1352, "epoch": 0.5833872707659116, "progress_pct": 9.72, "epoch_pct": 9.72, "eta": "48:31:54", "max_grad_norm": 1.0, "loss": 0.9400854706764221, "grad_norm": 0.5063773989677429, "learning_rate": 0.00019982930551410411}
+{"ts": "2025-12-23T19:42:14", "event": "train_log", "step": 1354, "epoch": 0.5842502696871629, "progress_pct": 9.74, "epoch_pct": 9.74, "eta": "48:29:17", "max_grad_norm": 1.0, "loss": 0.8657845258712769, "grad_norm": 0.5029586553573608, "learning_rate": 0.0001998264254790671}
+{"ts": "2025-12-23T19:42:29", "event": "train_log", "step": 1356, "epoch": 0.5851132686084143, "progress_pct": 9.75, "epoch_pct": 9.75, "eta": "48:26:52", "max_grad_norm": 1.0, "loss": 0.8593506813049316, "grad_norm": 0.45519232749938965, "learning_rate": 0.00019982352137133764}
+{"ts": "2025-12-23T19:42:45", "event": "train_log", "step": 1358, "epoch": 0.5859762675296656, "progress_pct": 9.76, "epoch_pct": 9.77, "eta": "48:24:31", "max_grad_norm": 1.0, "loss": 0.8658114671707153, "grad_norm": 0.49116215109825134, "learning_rate": 0.000199820593191616}
+{"ts": "2025-12-23T19:43:00", "event": "train_log", "step": 1360, "epoch": 0.5868392664509169, "progress_pct": 9.78, "epoch_pct": 9.78, "eta": "48:22:04", "max_grad_norm": 1.0, "loss": 0.8044605255126953, "grad_norm": 0.45347318053245544, "learning_rate": 0.00019981764094060826}
+{"ts": "2025-12-23T19:43:13", "event": "train_log", "step": 1362, "epoch": 0.5877022653721683, "progress_pct": 9.79, "epoch_pct": 9.8, "eta": "48:19:29", "max_grad_norm": 1.0, "loss": 0.9176861047744751, "grad_norm": 0.5191754698753357, "learning_rate": 0.00019981466461902643}
+{"ts": "2025-12-23T19:43:29", "event": "train_log", "step": 1364, "epoch": 0.5885652642934196, "progress_pct": 9.81, "epoch_pct": 9.81, "eta": "48:17:06", "max_grad_norm": 1.0, "loss": 0.8453370928764343, "grad_norm": 0.4791528284549713, "learning_rate": 0.00019981166422758818}
+{"ts": "2025-12-23T19:43:43", "event": "train_log", "step": 1366, "epoch": 0.589428263214671, "progress_pct": 9.82, "epoch_pct": 9.82, "eta": "48:14:37", "max_grad_norm": 1.0, "loss": 0.9343777298927307, "grad_norm": 0.5105116367340088, "learning_rate": 0.00019980863976701705}
+{"ts": "2025-12-23T19:43:58", "event": "train_log", "step": 1368, "epoch": 0.5902912621359223, "progress_pct": 9.84, "epoch_pct": 9.84, "eta": "48:12:11", "max_grad_norm": 1.0, "loss": 0.8950760960578918, "grad_norm": 0.44593656063079834, "learning_rate": 0.00019980559123804236}
+{"ts": "2025-12-23T19:44:13", "event": "train_log", "step": 1370, "epoch": 0.5911542610571737, "progress_pct": 9.85, "epoch_pct": 9.85, "eta": "48:09:50", "max_grad_norm": 1.0, "loss": 0.8613521456718445, "grad_norm": 0.4375658631324768, "learning_rate": 0.0001998025186413993}
+{"ts": "2025-12-23T19:44:28", "event": "train_log", "step": 1372, "epoch": 0.592017259978425, "progress_pct": 9.86, "epoch_pct": 9.87, "eta": "48:07:25", "max_grad_norm": 1.0, "loss": 0.8982083201408386, "grad_norm": 0.5138815641403198, "learning_rate": 0.00019979942197782878}
+{"ts": "2025-12-23T19:44:43", "event": "train_log", "step": 1374, "epoch": 0.5928802588996763, "progress_pct": 9.88, "epoch_pct": 9.88, "eta": "48:04:59", "max_grad_norm": 1.0, "loss": 0.9372450709342957, "grad_norm": 0.45473602414131165, "learning_rate": 0.00019979630124807753}
+{"ts": "2025-12-23T19:44:57", "event": "train_log", "step": 1376, "epoch": 0.5937432578209277, "progress_pct": 9.89, "epoch_pct": 9.9, "eta": "48:02:31", "max_grad_norm": 1.0, "loss": 0.8758652806282043, "grad_norm": 0.4961191713809967, "learning_rate": 0.00019979315645289814}
+{"ts": "2025-12-23T19:45:11", "event": "train_log", "step": 1378, "epoch": 0.594606256742179, "progress_pct": 9.91, "epoch_pct": 9.91, "eta": "47:59:59", "max_grad_norm": 1.0, "loss": 0.9852207899093628, "grad_norm": 0.5672827363014221, "learning_rate": 0.00019978998759304895}
+{"ts": "2025-12-23T19:45:27", "event": "train_log", "step": 1380, "epoch": 0.5954692556634305, "progress_pct": 9.92, "epoch_pct": 9.92, "eta": "47:57:42", "max_grad_norm": 1.0, "loss": 0.8451287746429443, "grad_norm": 0.44907906651496887, "learning_rate": 0.00019978679466929407}
+{"ts": "2025-12-23T19:45:41", "event": "train_log", "step": 1382, "epoch": 0.5963322545846818, "progress_pct": 9.94, "epoch_pct": 9.94, "eta": "47:55:16", "max_grad_norm": 1.0, "loss": 0.8381558656692505, "grad_norm": 0.4759652316570282, "learning_rate": 0.00019978357768240352}
+{"ts": "2025-12-23T19:45:55", "event": "train_log", "step": 1384, "epoch": 0.5971952535059332, "progress_pct": 9.95, "epoch_pct": 9.95, "eta": "47:52:46", "max_grad_norm": 1.0, "loss": 0.8820816874504089, "grad_norm": 0.4936048686504364, "learning_rate": 0.00019978033663315304}
+{"ts": "2025-12-23T19:46:10", "event": "train_log", "step": 1386, "epoch": 0.5980582524271845, "progress_pct": 9.97, "epoch_pct": 9.97, "eta": "47:50:22", "max_grad_norm": 1.0, "loss": 0.9156787991523743, "grad_norm": 0.44983741641044617, "learning_rate": 0.00019977707152232416}
+{"ts": "2025-12-23T19:46:25", "event": "train_log", "step": 1388, "epoch": 0.5989212513484358, "progress_pct": 9.98, "epoch_pct": 9.98, "eta": "47:48:01", "max_grad_norm": 1.0, "loss": 0.8285194039344788, "grad_norm": 0.45198705792427063, "learning_rate": 0.0001997737823507043}
+{"ts": "2025-12-23T19:46:40", "event": "train_log", "step": 1390, "epoch": 0.5997842502696872, "progress_pct": 9.99, "epoch_pct": 10.0, "eta": "47:45:41", "max_grad_norm": 1.0, "loss": 0.8109505772590637, "grad_norm": 0.45788463950157166, "learning_rate": 0.00019977046911908664}
+{"ts": "2025-12-23T19:46:55", "event": "train_log", "step": 1392, "epoch": 0.6006472491909385, "progress_pct": 10.01, "epoch_pct": 10.01, "eta": "47:43:21", "max_grad_norm": 1.0, "loss": 0.8285947442054749, "grad_norm": 0.4795142412185669, "learning_rate": 0.0001997671318282701}
+{"ts": "2025-12-23T19:47:09", "event": "train_log", "step": 1394, "epoch": 0.6015102481121899, "progress_pct": 10.02, "epoch_pct": 10.03, "eta": "47:40:55", "max_grad_norm": 1.0, "loss": 0.9497535228729248, "grad_norm": 0.5026728510856628, "learning_rate": 0.00019976377047905945}
+{"ts": "2025-12-23T19:47:23", "event": "train_log", "step": 1396, "epoch": 0.6023732470334412, "progress_pct": 10.04, "epoch_pct": 10.04, "eta": "47:38:27", "max_grad_norm": 1.0, "loss": 0.9171916246414185, "grad_norm": 0.4994853734970093, "learning_rate": 0.0001997603850722653}
+{"ts": "2025-12-23T19:47:38", "event": "train_log", "step": 1398, "epoch": 0.6032362459546926, "progress_pct": 10.05, "epoch_pct": 10.05, "eta": "47:36:14", "max_grad_norm": 1.0, "loss": 0.7894434928894043, "grad_norm": 0.4789866507053375, "learning_rate": 0.00019975697560870403}
+{"ts": "2025-12-23T19:47:54", "event": "train_log", "step": 1400, "epoch": 0.6040992448759439, "progress_pct": 10.07, "epoch_pct": 10.07, "eta": "47:33:59", "max_grad_norm": 1.0, "loss": 0.8942429423332214, "grad_norm": 0.42282742261886597, "learning_rate": 0.0001997535420891978}
+{"ts": "2025-12-23T19:58:55", "event": "train_log", "step": 1400, "epoch": 0.6040992448759439, "progress_pct": 10.07, "epoch_pct": 10.07, "eta": "49:12:29", "max_grad_norm": 1.0, "eval_loss": 0.9080492854118347, "eval_runtime": 661.4597, "eval_samples_per_second": 3.114, "eval_steps_per_second": 3.114}
+{"ts": "2025-12-23T19:59:10", "event": "train_log", "step": 1402, "epoch": 0.6049622437971952, "progress_pct": 10.08, "epoch_pct": 10.08, "eta": "49:09:58", "max_grad_norm": 1.0, "loss": 0.8938372731208801, "grad_norm": 0.5789905190467834, "learning_rate": 0.00019975008451457454}
+{"ts": "2025-12-23T19:59:26", "event": "train_log", "step": 1404, "epoch": 0.6058252427184466, "progress_pct": 10.09, "epoch_pct": 10.1, "eta": "49:07:39", "max_grad_norm": 1.0, "loss": 0.8746235370635986, "grad_norm": 0.46121683716773987, "learning_rate": 0.00019974660288566814}
+{"ts": "2025-12-23T19:59:41", "event": "train_log", "step": 1406, "epoch": 0.6066882416396979, "progress_pct": 10.11, "epoch_pct": 10.11, "eta": "49:05:17", "max_grad_norm": 1.0, "loss": 0.8650617003440857, "grad_norm": 0.5195551514625549, "learning_rate": 0.00019974309720331807}
+{"ts": "2025-12-23T19:59:56", "event": "train_log", "step": 1408, "epoch": 0.6075512405609493, "progress_pct": 10.12, "epoch_pct": 10.13, "eta": "49:02:52", "max_grad_norm": 1.0, "loss": 0.8853039145469666, "grad_norm": 0.46930259466171265, "learning_rate": 0.00019973956746836976}
+{"ts": "2025-12-23T20:00:13", "event": "train_log", "step": 1410, "epoch": 0.6084142394822006, "progress_pct": 10.14, "epoch_pct": 10.14, "eta": "49:00:40", "max_grad_norm": 1.0, "loss": 0.7865594029426575, "grad_norm": 0.40869632363319397, "learning_rate": 0.0001997360136816744}
+{"ts": "2025-12-23T20:00:29", "event": "train_log", "step": 1412, "epoch": 0.609277238403452, "progress_pct": 10.15, "epoch_pct": 10.15, "eta": "48:58:23", "max_grad_norm": 1.0, "loss": 0.907535970211029, "grad_norm": 0.5398361086845398, "learning_rate": 0.00019973243584408895}
+{"ts": "2025-12-23T20:00:45", "event": "train_log", "step": 1414, "epoch": 0.6101402373247033, "progress_pct": 10.17, "epoch_pct": 10.17, "eta": "48:56:05", "max_grad_norm": 1.0, "loss": 0.8682730197906494, "grad_norm": 0.5110154747962952, "learning_rate": 0.00019972883395647615}
+{"ts": "2025-12-23T20:01:01", "event": "train_log", "step": 1416, "epoch": 0.6110032362459547, "progress_pct": 10.18, "epoch_pct": 10.18, "eta": "48:53:48", "max_grad_norm": 1.0, "loss": 0.8786011338233948, "grad_norm": 0.44484639167785645, "learning_rate": 0.00019972520801970467}
+{"ts": "2025-12-23T20:01:16", "event": "train_log", "step": 1418, "epoch": 0.6118662351672061, "progress_pct": 10.2, "epoch_pct": 10.2, "eta": "48:51:29", "max_grad_norm": 1.0, "loss": 0.9021878242492676, "grad_norm": 0.4768071472644806, "learning_rate": 0.0001997215580346488}
+{"ts": "2025-12-23T20:01:31", "event": "train_log", "step": 1420, "epoch": 0.6127292340884574, "progress_pct": 10.21, "epoch_pct": 10.21, "eta": "48:49:05", "max_grad_norm": 1.0, "loss": 0.7737482786178589, "grad_norm": 0.43265241384506226, "learning_rate": 0.0001997178840021888}
+{"ts": "2025-12-23T20:01:46", "event": "train_log", "step": 1422, "epoch": 0.6135922330097088, "progress_pct": 10.22, "epoch_pct": 10.23, "eta": "48:46:39", "max_grad_norm": 1.0, "loss": 0.876280665397644, "grad_norm": 0.525692343711853, "learning_rate": 0.0001997141859232106}
+{"ts": "2025-12-23T20:02:02", "event": "train_log", "step": 1424, "epoch": 0.6144552319309601, "progress_pct": 10.24, "epoch_pct": 10.24, "eta": "48:44:25", "max_grad_norm": 1.0, "loss": 0.8503577709197998, "grad_norm": 0.48206865787506104, "learning_rate": 0.00019971046379860594}
+{"ts": "2025-12-23T20:02:16", "event": "train_log", "step": 1426, "epoch": 0.6153182308522115, "progress_pct": 10.25, "epoch_pct": 10.26, "eta": "48:41:57", "max_grad_norm": 1.0, "loss": 0.9459730982780457, "grad_norm": 0.6032769680023193, "learning_rate": 0.00019970671762927246}
+{"ts": "2025-12-23T20:02:31", "event": "train_log", "step": 1428, "epoch": 0.6161812297734628, "progress_pct": 10.27, "epoch_pct": 10.27, "eta": "48:39:31", "max_grad_norm": 1.0, "loss": 0.8836647868156433, "grad_norm": 0.4491981863975525, "learning_rate": 0.0001997029474161135}
+{"ts": "2025-12-23T20:02:46", "event": "train_log", "step": 1430, "epoch": 0.6170442286947141, "progress_pct": 10.28, "epoch_pct": 10.28, "eta": "48:37:09", "max_grad_norm": 1.0, "loss": 0.8614388108253479, "grad_norm": 0.47503358125686646, "learning_rate": 0.00019969915316003824}
+{"ts": "2025-12-23T20:03:00", "event": "train_log", "step": 1432, "epoch": 0.6179072276159655, "progress_pct": 10.3, "epoch_pct": 10.3, "eta": "48:34:39", "max_grad_norm": 1.0, "loss": 0.8420360684394836, "grad_norm": 0.44801047444343567, "learning_rate": 0.00019969533486196162}
+{"ts": "2025-12-23T20:03:15", "event": "train_log", "step": 1434, "epoch": 0.6187702265372168, "progress_pct": 10.31, "epoch_pct": 10.31, "eta": "48:32:17", "max_grad_norm": 1.0, "loss": 0.8256269693374634, "grad_norm": 0.45057111978530884, "learning_rate": 0.00019969149252280446}
+{"ts": "2025-12-23T20:03:30", "event": "train_log", "step": 1436, "epoch": 0.6196332254584682, "progress_pct": 10.32, "epoch_pct": 10.33, "eta": "48:30:01", "max_grad_norm": 1.0, "loss": 0.9130199551582336, "grad_norm": 0.4589645266532898, "learning_rate": 0.00019968762614349327}
+{"ts": "2025-12-23T20:03:45", "event": "train_log", "step": 1438, "epoch": 0.6204962243797195, "progress_pct": 10.34, "epoch_pct": 10.34, "eta": "48:27:39", "max_grad_norm": 1.0, "loss": 0.74083012342453, "grad_norm": 0.48914027214050293, "learning_rate": 0.00019968373572496045}
+{"ts": "2025-12-23T20:04:00", "event": "train_log", "step": 1440, "epoch": 0.6213592233009708, "progress_pct": 10.35, "epoch_pct": 10.36, "eta": "48:25:12", "max_grad_norm": 1.0, "loss": 0.8538379669189453, "grad_norm": 0.4582098424434662, "learning_rate": 0.00019967982126814412}
+{"ts": "2025-12-23T20:04:16", "event": "train_log", "step": 1442, "epoch": 0.6222222222222222, "progress_pct": 10.37, "epoch_pct": 10.37, "eta": "48:23:01", "max_grad_norm": 1.0, "loss": 0.8780114054679871, "grad_norm": 0.48722779750823975, "learning_rate": 0.00019967588277398823}
+{"ts": "2025-12-23T20:04:31", "event": "train_log", "step": 1444, "epoch": 0.6230852211434735, "progress_pct": 10.38, "epoch_pct": 10.38, "eta": "48:20:48", "max_grad_norm": 1.0, "loss": 0.8341028690338135, "grad_norm": 0.4291327893733978, "learning_rate": 0.00019967192024344254}
+{"ts": "2025-12-23T20:04:48", "event": "train_log", "step": 1446, "epoch": 0.623948220064725, "progress_pct": 10.4, "epoch_pct": 10.4, "eta": "48:18:41", "max_grad_norm": 1.0, "loss": 0.8651667237281799, "grad_norm": 0.4773139953613281, "learning_rate": 0.00019966793367746265}
+{"ts": "2025-12-23T20:05:04", "event": "train_log", "step": 1448, "epoch": 0.6248112189859762, "progress_pct": 10.41, "epoch_pct": 10.41, "eta": "48:16:28", "max_grad_norm": 1.0, "loss": 0.8339929580688477, "grad_norm": 0.45556166768074036, "learning_rate": 0.00019966392307700986}
+{"ts": "2025-12-23T20:05:19", "event": "train_log", "step": 1450, "epoch": 0.6256742179072277, "progress_pct": 10.43, "epoch_pct": 10.43, "eta": "48:14:15", "max_grad_norm": 1.0, "loss": 0.9129340052604675, "grad_norm": 0.5126671195030212, "learning_rate": 0.00019965988844305129}
+{"ts": "2025-12-23T20:05:35", "event": "train_log", "step": 1452, "epoch": 0.626537216828479, "progress_pct": 10.44, "epoch_pct": 10.44, "eta": "48:12:01", "max_grad_norm": 1.0, "loss": 0.9057610034942627, "grad_norm": 0.6067109704017639, "learning_rate": 0.00019965582977655988}
+{"ts": "2025-12-23T20:05:49", "event": "train_log", "step": 1454, "epoch": 0.6274002157497303, "progress_pct": 10.45, "epoch_pct": 10.46, "eta": "48:09:36", "max_grad_norm": 1.0, "loss": 0.874100387096405, "grad_norm": 0.46425968408584595, "learning_rate": 0.00019965174707851438}
+{"ts": "2025-12-23T20:06:04", "event": "train_log", "step": 1456, "epoch": 0.6282632146709817, "progress_pct": 10.47, "epoch_pct": 10.47, "eta": "48:07:19", "max_grad_norm": 1.0, "loss": 0.915635347366333, "grad_norm": 0.481077641248703, "learning_rate": 0.0001996476403498993}
+{"ts": "2025-12-23T20:06:19", "event": "train_log", "step": 1458, "epoch": 0.629126213592233, "progress_pct": 10.48, "epoch_pct": 10.49, "eta": "48:05:03", "max_grad_norm": 1.0, "loss": 0.9059650301933289, "grad_norm": 0.47299909591674805, "learning_rate": 0.000199643509591705}
+{"ts": "2025-12-23T20:06:35", "event": "train_log", "step": 1460, "epoch": 0.6299892125134844, "progress_pct": 10.5, "epoch_pct": 10.5, "eta": "48:02:57", "max_grad_norm": 1.0, "loss": 0.9775188565254211, "grad_norm": 0.48924630880355835, "learning_rate": 0.00019963935480492753}
+{"ts": "2025-12-23T20:06:51", "event": "train_log", "step": 1462, "epoch": 0.6308522114347357, "progress_pct": 10.51, "epoch_pct": 10.51, "eta": "48:00:48", "max_grad_norm": 1.0, "loss": 0.8950685858726501, "grad_norm": 0.4407665431499481, "learning_rate": 0.0001996351759905688}
+{"ts": "2025-12-23T20:07:06", "event": "train_log", "step": 1464, "epoch": 0.6317152103559871, "progress_pct": 10.53, "epoch_pct": 10.53, "eta": "47:58:32", "max_grad_norm": 1.0, "loss": 0.8532119989395142, "grad_norm": 0.5018318295478821, "learning_rate": 0.00019963097314963657}
+{"ts": "2025-12-23T20:07:22", "event": "train_log", "step": 1466, "epoch": 0.6325782092772384, "progress_pct": 10.54, "epoch_pct": 10.54, "eta": "47:56:18", "max_grad_norm": 1.0, "loss": 0.7775963544845581, "grad_norm": 0.43245720863342285, "learning_rate": 0.0001996267462831443}
+{"ts": "2025-12-23T20:07:37", "event": "train_log", "step": 1468, "epoch": 0.6334412081984897, "progress_pct": 10.56, "epoch_pct": 10.56, "eta": "47:54:06", "max_grad_norm": 1.0, "loss": 0.8315839767456055, "grad_norm": 0.5028865337371826, "learning_rate": 0.00019962249539211125}
+{"ts": "2025-12-23T20:07:52", "event": "train_log", "step": 1470, "epoch": 0.6343042071197411, "progress_pct": 10.57, "epoch_pct": 10.57, "eta": "47:51:54", "max_grad_norm": 1.0, "loss": 0.849076509475708, "grad_norm": 0.4697185754776001, "learning_rate": 0.0001996182204775626}
+{"ts": "2025-12-23T20:08:07", "event": "train_log", "step": 1472, "epoch": 0.6351672060409924, "progress_pct": 10.58, "epoch_pct": 10.59, "eta": "47:49:37", "max_grad_norm": 1.0, "loss": 0.8828577995300293, "grad_norm": 0.46725034713745117, "learning_rate": 0.00019961392154052912}
+{"ts": "2025-12-23T20:08:23", "event": "train_log", "step": 1474, "epoch": 0.6360302049622438, "progress_pct": 10.6, "epoch_pct": 10.6, "eta": "47:47:25", "max_grad_norm": 1.0, "loss": 0.850115954875946, "grad_norm": 0.4301203489303589, "learning_rate": 0.00019960959858204754}
+{"ts": "2025-12-23T20:08:38", "event": "train_log", "step": 1476, "epoch": 0.6368932038834951, "progress_pct": 10.61, "epoch_pct": 10.61, "eta": "47:45:11", "max_grad_norm": 1.0, "loss": 0.7912618517875671, "grad_norm": 0.46635881066322327, "learning_rate": 0.0001996052516031603}
+{"ts": "2025-12-23T20:08:53", "event": "train_log", "step": 1478, "epoch": 0.6377562028047465, "progress_pct": 10.63, "epoch_pct": 10.63, "eta": "47:42:57", "max_grad_norm": 1.0, "loss": 0.9072504639625549, "grad_norm": 0.44143620133399963, "learning_rate": 0.00019960088060491565}
+{"ts": "2025-12-23T20:09:07", "event": "train_log", "step": 1480, "epoch": 0.6386192017259978, "progress_pct": 10.64, "epoch_pct": 10.64, "eta": "47:40:34", "max_grad_norm": 1.0, "loss": 0.8976638317108154, "grad_norm": 0.47458893060684204, "learning_rate": 0.00019959648558836763}
+{"ts": "2025-12-23T20:09:21", "event": "train_log", "step": 1482, "epoch": 0.6394822006472491, "progress_pct": 10.66, "epoch_pct": 10.66, "eta": "47:38:18", "max_grad_norm": 1.0, "loss": 0.8142043352127075, "grad_norm": 0.4596816897392273, "learning_rate": 0.00019959206655457612}
+{"ts": "2025-12-23T20:09:35", "event": "train_log", "step": 1484, "epoch": 0.6403451995685006, "progress_pct": 10.67, "epoch_pct": 10.67, "eta": "47:35:56", "max_grad_norm": 1.0, "loss": 0.860643744468689, "grad_norm": 0.4839977025985718, "learning_rate": 0.0001995876235046067}
+{"ts": "2025-12-23T20:09:50", "event": "train_log", "step": 1486, "epoch": 0.6412081984897519, "progress_pct": 10.68, "epoch_pct": 10.69, "eta": "47:33:45", "max_grad_norm": 1.0, "loss": 0.7586524486541748, "grad_norm": 0.3542814552783966, "learning_rate": 0.00019958315643953085}
+{"ts": "2025-12-23T20:10:05", "event": "train_log", "step": 1488, "epoch": 0.6420711974110033, "progress_pct": 10.7, "epoch_pct": 10.7, "eta": "47:31:26", "max_grad_norm": 1.0, "loss": 0.9353570342063904, "grad_norm": 0.5423269271850586, "learning_rate": 0.00019957866536042572}
+{"ts": "2025-12-23T20:10:18", "event": "train_log", "step": 1490, "epoch": 0.6429341963322546, "progress_pct": 10.71, "epoch_pct": 10.72, "eta": "47:29:04", "max_grad_norm": 1.0, "loss": 0.9919291138648987, "grad_norm": 0.4580909013748169, "learning_rate": 0.00019957415026837437}
+{"ts": "2025-12-23T20:10:34", "event": "train_log", "step": 1492, "epoch": 0.643797195253506, "progress_pct": 10.73, "epoch_pct": 10.73, "eta": "47:26:56", "max_grad_norm": 1.0, "loss": 0.8720914125442505, "grad_norm": 0.4211732745170593, "learning_rate": 0.00019956961116446555}
+{"ts": "2025-12-23T20:10:49", "event": "train_log", "step": 1494, "epoch": 0.6446601941747573, "progress_pct": 10.74, "epoch_pct": 10.74, "eta": "47:24:42", "max_grad_norm": 1.0, "loss": 0.8661212921142578, "grad_norm": 0.4583161175251007, "learning_rate": 0.00019956504804979384}
+{"ts": "2025-12-23T20:11:04", "event": "train_log", "step": 1496, "epoch": 0.6455231930960086, "progress_pct": 10.76, "epoch_pct": 10.76, "eta": "47:22:33", "max_grad_norm": 1.0, "loss": 0.8170996308326721, "grad_norm": 0.4359884262084961, "learning_rate": 0.00019956046092545966}
+{"ts": "2025-12-23T20:11:19", "event": "train_log", "step": 1498, "epoch": 0.64638619201726, "progress_pct": 10.77, "epoch_pct": 10.77, "eta": "47:20:20", "max_grad_norm": 1.0, "loss": 0.8607422113418579, "grad_norm": 0.4642556607723236, "learning_rate": 0.00019955584979256913}
+{"ts": "2025-12-23T20:11:33", "event": "train_log", "step": 1500, "epoch": 0.6472491909385113, "progress_pct": 10.79, "epoch_pct": 10.79, "eta": "47:18:04", "max_grad_norm": 1.0, "loss": 0.837529182434082, "grad_norm": 0.4496007561683655, "learning_rate": 0.00019955121465223426}
+{"ts": "2025-12-23T20:22:23", "event": "train_log", "step": 1500, "epoch": 0.6472491909385113, "progress_pct": 10.79, "epoch_pct": 10.79, "eta": "48:47:39", "max_grad_norm": 1.0, "eval_loss": 0.8972997665405273, "eval_runtime": 649.796, "eval_samples_per_second": 3.17, "eval_steps_per_second": 3.17}
+{"ts": "2025-12-23T20:22:39", "event": "train_log", "step": 1502, "epoch": 0.6481121898597627, "progress_pct": 10.8, "epoch_pct": 10.8, "eta": "48:45:29", "max_grad_norm": 1.0, "loss": 0.9355250000953674, "grad_norm": 0.48363205790519714, "learning_rate": 0.0001995465555055727}
+{"ts": "2025-12-23T20:22:54", "event": "train_log", "step": 1504, "epoch": 0.648975188781014, "progress_pct": 10.81, "epoch_pct": 10.82, "eta": "48:43:11", "max_grad_norm": 1.0, "loss": 0.8286949396133423, "grad_norm": 0.44681695103645325, "learning_rate": 0.0001995418723537081}
+{"ts": "2025-12-23T20:23:09", "event": "train_log", "step": 1506, "epoch": 0.6498381877022654, "progress_pct": 10.83, "epoch_pct": 10.83, "eta": "48:40:54", "max_grad_norm": 1.0, "loss": 0.890398383140564, "grad_norm": 0.5110394358634949, "learning_rate": 0.00019953716519776967}
+{"ts": "2025-12-23T20:23:25", "event": "train_log", "step": 1508, "epoch": 0.6507011866235167, "progress_pct": 10.84, "epoch_pct": 10.85, "eta": "48:38:43", "max_grad_norm": 1.0, "loss": 0.8117311000823975, "grad_norm": 0.4353160262107849, "learning_rate": 0.00019953243403889257}
+{"ts": "2025-12-23T20:23:40", "event": "train_log", "step": 1510, "epoch": 0.651564185544768, "progress_pct": 10.86, "epoch_pct": 10.86, "eta": "48:36:30", "max_grad_norm": 1.0, "loss": 0.8255904316902161, "grad_norm": 0.4731789231300354, "learning_rate": 0.0001995276788782177}
+{"ts": "2025-12-23T20:23:55", "event": "train_log", "step": 1512, "epoch": 0.6524271844660194, "progress_pct": 10.87, "epoch_pct": 10.87, "eta": "48:34:16", "max_grad_norm": 1.0, "loss": 0.9371263384819031, "grad_norm": 0.5447185039520264, "learning_rate": 0.00019952289971689177}
+{"ts": "2025-12-23T20:24:11", "event": "train_log", "step": 1514, "epoch": 0.6532901833872707, "progress_pct": 10.89, "epoch_pct": 10.89, "eta": "48:32:02", "max_grad_norm": 1.0, "loss": 0.8532910943031311, "grad_norm": 0.47616517543792725, "learning_rate": 0.0001995180965560672}
+{"ts": "2025-12-23T20:24:27", "event": "train_log", "step": 1516, "epoch": 0.6541531823085222, "progress_pct": 10.9, "epoch_pct": 10.9, "eta": "48:29:59", "max_grad_norm": 1.0, "loss": 0.8799141645431519, "grad_norm": 0.4412213861942291, "learning_rate": 0.0001995132693969023}
+{"ts": "2025-12-23T20:24:43", "event": "train_log", "step": 1518, "epoch": 0.6550161812297735, "progress_pct": 10.91, "epoch_pct": 10.92, "eta": "48:27:48", "max_grad_norm": 1.0, "loss": 0.8395764827728271, "grad_norm": 0.469911128282547, "learning_rate": 0.00019950841824056107}
+{"ts": "2025-12-23T20:24:59", "event": "train_log", "step": 1520, "epoch": 0.6558791801510249, "progress_pct": 10.93, "epoch_pct": 10.93, "eta": "48:25:39", "max_grad_norm": 1.0, "loss": 0.9556697010993958, "grad_norm": 0.5236243009567261, "learning_rate": 0.00019950354308821336}
+{"ts": "2025-12-23T20:25:14", "event": "train_log", "step": 1522, "epoch": 0.6567421790722762, "progress_pct": 10.94, "epoch_pct": 10.95, "eta": "48:23:27", "max_grad_norm": 1.0, "loss": 0.8524283170700073, "grad_norm": 0.4441990256309509, "learning_rate": 0.00019949864394103482}
+{"ts": "2025-12-23T20:25:31", "event": "train_log", "step": 1524, "epoch": 0.6576051779935275, "progress_pct": 10.96, "epoch_pct": 10.96, "eta": "48:21:31", "max_grad_norm": 1.0, "loss": 0.9213772416114807, "grad_norm": 0.4173077940940857, "learning_rate": 0.00019949372080020682}
+{"ts": "2025-12-23T20:25:46", "event": "train_log", "step": 1526, "epoch": 0.6584681769147789, "progress_pct": 10.97, "epoch_pct": 10.97, "eta": "48:19:17", "max_grad_norm": 1.0, "loss": 0.9236897230148315, "grad_norm": 0.4404120147228241, "learning_rate": 0.00019948877366691658}
+{"ts": "2025-12-23T20:26:01", "event": "train_log", "step": 1528, "epoch": 0.6593311758360302, "progress_pct": 10.99, "epoch_pct": 10.99, "eta": "48:16:59", "max_grad_norm": 1.0, "loss": 0.8373230695724487, "grad_norm": 0.4586230516433716, "learning_rate": 0.00019948380254235706}
+{"ts": "2025-12-23T20:26:17", "event": "train_log", "step": 1530, "epoch": 0.6601941747572816, "progress_pct": 11.0, "epoch_pct": 11.0, "eta": "48:14:53", "max_grad_norm": 1.0, "loss": 0.8256528377532959, "grad_norm": 0.4136028587818146, "learning_rate": 0.00019947880742772703}
+{"ts": "2025-12-23T20:26:32", "event": "train_log", "step": 1532, "epoch": 0.6610571736785329, "progress_pct": 11.02, "epoch_pct": 11.02, "eta": "48:12:43", "max_grad_norm": 1.0, "loss": 0.8580789566040039, "grad_norm": 0.5007129907608032, "learning_rate": 0.00019947378832423107}
+{"ts": "2025-12-23T20:26:49", "event": "train_log", "step": 1534, "epoch": 0.6619201725997842, "progress_pct": 11.03, "epoch_pct": 11.03, "eta": "48:10:41", "max_grad_norm": 1.0, "loss": 0.7647744417190552, "grad_norm": 0.39050203561782837, "learning_rate": 0.00019946874523307947}
+{"ts": "2025-12-23T20:27:04", "event": "train_log", "step": 1536, "epoch": 0.6627831715210356, "progress_pct": 11.04, "epoch_pct": 11.05, "eta": "48:08:34", "max_grad_norm": 1.0, "loss": 0.9042545557022095, "grad_norm": 0.4640588164329529, "learning_rate": 0.00019946367815548835}
+{"ts": "2025-12-23T20:27:20", "event": "train_log", "step": 1538, "epoch": 0.6636461704422869, "progress_pct": 11.06, "epoch_pct": 11.06, "eta": "48:06:22", "max_grad_norm": 1.0, "loss": 0.9114110469818115, "grad_norm": 0.5304957032203674, "learning_rate": 0.00019945858709267963}
+{"ts": "2025-12-23T20:27:34", "event": "train_log", "step": 1540, "epoch": 0.6645091693635383, "progress_pct": 11.07, "epoch_pct": 11.08, "eta": "48:04:07", "max_grad_norm": 1.0, "loss": 0.8239460587501526, "grad_norm": 0.5426004528999329, "learning_rate": 0.000199453472045881}
+{"ts": "2025-12-23T20:27:49", "event": "train_log", "step": 1542, "epoch": 0.6653721682847896, "progress_pct": 11.09, "epoch_pct": 11.09, "eta": "48:01:52", "max_grad_norm": 1.0, "loss": 0.8091367483139038, "grad_norm": 0.44893568754196167, "learning_rate": 0.00019944833301632593}
+{"ts": "2025-12-23T20:28:04", "event": "train_log", "step": 1544, "epoch": 0.666235167206041, "progress_pct": 11.1, "epoch_pct": 11.1, "eta": "47:59:41", "max_grad_norm": 1.0, "loss": 0.9202280640602112, "grad_norm": 0.4294016361236572, "learning_rate": 0.00019944317000525366}
+{"ts": "2025-12-23T20:28:20", "event": "train_log", "step": 1546, "epoch": 0.6670981661272923, "progress_pct": 11.12, "epoch_pct": 11.12, "eta": "47:57:34", "max_grad_norm": 1.0, "loss": 0.8884767889976501, "grad_norm": 0.449633926153183, "learning_rate": 0.00019943798301390927}
+{"ts": "2025-12-23T20:28:34", "event": "train_log", "step": 1548, "epoch": 0.6679611650485436, "progress_pct": 11.13, "epoch_pct": 11.13, "eta": "47:55:22", "max_grad_norm": 1.0, "loss": 0.8390879034996033, "grad_norm": 0.4516827166080475, "learning_rate": 0.0001994327720435435}
+{"ts": "2025-12-23T20:28:49", "event": "train_log", "step": 1550, "epoch": 0.668824163969795, "progress_pct": 11.14, "epoch_pct": 11.15, "eta": "47:53:08", "max_grad_norm": 1.0, "loss": 0.7388033270835876, "grad_norm": 0.422270268201828, "learning_rate": 0.000199427537095413}
+{"ts": "2025-12-23T20:29:04", "event": "train_log", "step": 1552, "epoch": 0.6696871628910464, "progress_pct": 11.16, "epoch_pct": 11.16, "eta": "47:50:55", "max_grad_norm": 1.0, "loss": 0.9268350601196289, "grad_norm": 0.580563485622406, "learning_rate": 0.00019942227817078015}
+{"ts": "2025-12-23T20:29:20", "event": "train_log", "step": 1554, "epoch": 0.6705501618122978, "progress_pct": 11.17, "epoch_pct": 11.18, "eta": "47:48:53", "max_grad_norm": 1.0, "loss": 0.7978561520576477, "grad_norm": 0.4436347782611847, "learning_rate": 0.00019941699527091316}
+{"ts": "2025-12-23T20:29:35", "event": "train_log", "step": 1556, "epoch": 0.6714131607335491, "progress_pct": 11.19, "epoch_pct": 11.19, "eta": "47:46:45", "max_grad_norm": 1.0, "loss": 0.8229286670684814, "grad_norm": 0.4149787127971649, "learning_rate": 0.0001994116883970859}
+{"ts": "2025-12-23T20:29:50", "event": "train_log", "step": 1558, "epoch": 0.6722761596548005, "progress_pct": 11.2, "epoch_pct": 11.2, "eta": "47:44:35", "max_grad_norm": 1.0, "loss": 0.8554545640945435, "grad_norm": 0.49915504455566406, "learning_rate": 0.00019940635755057813}
+{"ts": "2025-12-23T20:30:05", "event": "train_log", "step": 1560, "epoch": 0.6731391585760518, "progress_pct": 11.22, "epoch_pct": 11.22, "eta": "47:42:26", "max_grad_norm": 1.0, "loss": 0.9135572910308838, "grad_norm": 0.45326656103134155, "learning_rate": 0.00019940100273267537}
+{"ts": "2025-12-23T20:30:21", "event": "train_log", "step": 1562, "epoch": 0.6740021574973031, "progress_pct": 11.23, "epoch_pct": 11.23, "eta": "47:40:26", "max_grad_norm": 1.0, "loss": 0.7769742012023926, "grad_norm": 0.48639237880706787, "learning_rate": 0.0001993956239446689}
+{"ts": "2025-12-23T20:30:35", "event": "train_log", "step": 1564, "epoch": 0.6748651564185545, "progress_pct": 11.25, "epoch_pct": 11.25, "eta": "47:38:10", "max_grad_norm": 1.0, "loss": 0.9626237154006958, "grad_norm": 0.5072791576385498, "learning_rate": 0.0001993902211878558}
+{"ts": "2025-12-23T20:30:51", "event": "train_log", "step": 1566, "epoch": 0.6757281553398058, "progress_pct": 11.26, "epoch_pct": 11.26, "eta": "47:36:08", "max_grad_norm": 1.0, "loss": 0.8506941199302673, "grad_norm": 0.4646652638912201, "learning_rate": 0.00019938479446353892}
+{"ts": "2025-12-23T20:31:07", "event": "train_log", "step": 1568, "epoch": 0.6765911542610572, "progress_pct": 11.27, "epoch_pct": 11.28, "eta": "47:34:07", "max_grad_norm": 1.0, "loss": 0.8172947764396667, "grad_norm": 0.4343051314353943, "learning_rate": 0.00019937934377302688}
+{"ts": "2025-12-23T20:31:22", "event": "train_log", "step": 1570, "epoch": 0.6774541531823085, "progress_pct": 11.29, "epoch_pct": 11.29, "eta": "47:31:57", "max_grad_norm": 1.0, "loss": 0.9215856790542603, "grad_norm": 0.46890193223953247, "learning_rate": 0.00019937386911763407}
+{"ts": "2025-12-23T20:31:37", "event": "train_log", "step": 1572, "epoch": 0.6783171521035599, "progress_pct": 11.3, "epoch_pct": 11.31, "eta": "47:29:50", "max_grad_norm": 1.0, "loss": 0.8099892139434814, "grad_norm": 0.5121113061904907, "learning_rate": 0.0001993683704986807}
+{"ts": "2025-12-23T20:31:53", "event": "train_log", "step": 1574, "epoch": 0.6791801510248112, "progress_pct": 11.32, "epoch_pct": 11.32, "eta": "47:27:47", "max_grad_norm": 1.0, "loss": 0.8675104975700378, "grad_norm": 0.4652405083179474, "learning_rate": 0.0001993628479174928}
+{"ts": "2025-12-23T20:32:08", "event": "train_log", "step": 1576, "epoch": 0.6800431499460625, "progress_pct": 11.33, "epoch_pct": 11.33, "eta": "47:25:47", "max_grad_norm": 1.0, "loss": 0.7938929200172424, "grad_norm": 0.4599422812461853, "learning_rate": 0.00019935730137540198}
+{"ts": "2025-12-23T20:32:25", "event": "train_log", "step": 1578, "epoch": 0.6809061488673139, "progress_pct": 11.35, "epoch_pct": 11.35, "eta": "47:23:53", "max_grad_norm": 1.0, "loss": 0.8610570430755615, "grad_norm": 0.4738059937953949, "learning_rate": 0.0001993517308737459}
+{"ts": "2025-12-23T20:32:39", "event": "train_log", "step": 1580, "epoch": 0.6817691477885652, "progress_pct": 11.36, "epoch_pct": 11.36, "eta": "47:21:40", "max_grad_norm": 1.0, "loss": 0.9199413657188416, "grad_norm": 0.5161214470863342, "learning_rate": 0.00019934613641386776}
+{"ts": "2025-12-23T20:32:54", "event": "train_log", "step": 1582, "epoch": 0.6826321467098166, "progress_pct": 11.37, "epoch_pct": 11.38, "eta": "47:19:35", "max_grad_norm": 1.0, "loss": 0.771649181842804, "grad_norm": 0.4284999370574951, "learning_rate": 0.00019934051799711672}
+{"ts": "2025-12-23T20:33:10", "event": "train_log", "step": 1584, "epoch": 0.683495145631068, "progress_pct": 11.39, "epoch_pct": 11.39, "eta": "47:17:35", "max_grad_norm": 1.0, "loss": 0.8861327767372131, "grad_norm": 0.5117548704147339, "learning_rate": 0.00019933487562484757}
+{"ts": "2025-12-23T20:33:26", "event": "train_log", "step": 1586, "epoch": 0.6843581445523194, "progress_pct": 11.4, "epoch_pct": 11.41, "eta": "47:15:34", "max_grad_norm": 1.0, "loss": 0.806983232498169, "grad_norm": 0.4964369833469391, "learning_rate": 0.00019932920929842095}
+{"ts": "2025-12-23T20:33:42", "event": "train_log", "step": 1588, "epoch": 0.6852211434735707, "progress_pct": 11.42, "epoch_pct": 11.42, "eta": "47:13:35", "max_grad_norm": 1.0, "loss": 0.7963525652885437, "grad_norm": 0.4699532091617584, "learning_rate": 0.00019932351901920327}
+{"ts": "2025-12-23T20:33:59", "event": "train_log", "step": 1590, "epoch": 0.686084142394822, "progress_pct": 11.43, "epoch_pct": 11.43, "eta": "47:11:48", "max_grad_norm": 1.0, "loss": 0.9406430721282959, "grad_norm": 0.5329220294952393, "learning_rate": 0.00019931780478856678}
+{"ts": "2025-12-23T20:34:14", "event": "train_log", "step": 1592, "epoch": 0.6869471413160734, "progress_pct": 11.45, "epoch_pct": 11.45, "eta": "47:09:47", "max_grad_norm": 1.0, "loss": 0.8517770171165466, "grad_norm": 0.49823835492134094, "learning_rate": 0.00019931206660788936}
+{"ts": "2025-12-23T20:34:30", "event": "train_log", "step": 1594, "epoch": 0.6878101402373247, "progress_pct": 11.46, "epoch_pct": 11.46, "eta": "47:07:45", "max_grad_norm": 1.0, "loss": 0.8703644275665283, "grad_norm": 0.45245134830474854, "learning_rate": 0.00019930630447855482}
+{"ts": "2025-12-23T20:34:46", "event": "train_log", "step": 1596, "epoch": 0.6886731391585761, "progress_pct": 11.48, "epoch_pct": 11.48, "eta": "47:05:48", "max_grad_norm": 1.0, "loss": 0.9035283327102661, "grad_norm": 0.47524577379226685, "learning_rate": 0.0001993005184019526}
+{"ts": "2025-12-23T20:35:01", "event": "train_log", "step": 1598, "epoch": 0.6895361380798274, "progress_pct": 11.49, "epoch_pct": 11.49, "eta": "47:03:46", "max_grad_norm": 1.0, "loss": 0.9173959493637085, "grad_norm": 0.4537610411643982, "learning_rate": 0.00019929470837947802}
+{"ts": "2025-12-23T20:35:18", "event": "train_log", "step": 1600, "epoch": 0.6903991370010788, "progress_pct": 11.5, "epoch_pct": 11.51, "eta": "47:01:54", "max_grad_norm": 1.0, "loss": 0.8573579788208008, "grad_norm": 0.42469722032546997, "learning_rate": 0.00019928887441253212}
+{"ts": "2025-12-23T20:46:12", "event": "train_log", "step": 1600, "epoch": 0.6903991370010788, "progress_pct": 11.5, "epoch_pct": 11.51, "eta": "48:25:45", "max_grad_norm": 1.0, "eval_loss": 0.8880587220191956, "eval_runtime": 653.9515, "eval_samples_per_second": 3.15, "eval_steps_per_second": 3.15}
+{"ts": "2025-12-23T20:46:27", "event": "train_log", "step": 1602, "epoch": 0.6912621359223301, "progress_pct": 11.52, "epoch_pct": 11.52, "eta": "48:23:37", "max_grad_norm": 1.0, "loss": 0.849348247051239, "grad_norm": 0.4388251304626465, "learning_rate": 0.00019928301650252176}
+{"ts": "2025-12-23T20:46:42", "event": "train_log", "step": 1604, "epoch": 0.6921251348435814, "progress_pct": 11.53, "epoch_pct": 11.54, "eta": "48:21:25", "max_grad_norm": 1.0, "loss": 0.8298451900482178, "grad_norm": 0.46086886525154114, "learning_rate": 0.00019927713465085956}
+{"ts": "2025-12-23T20:46:56", "event": "train_log", "step": 1606, "epoch": 0.6929881337648328, "progress_pct": 11.55, "epoch_pct": 11.55, "eta": "48:19:13", "max_grad_norm": 1.0, "loss": 0.8860712647438049, "grad_norm": 0.42972785234451294, "learning_rate": 0.00019927122885896387}
+{"ts": "2025-12-23T20:47:11", "event": "train_log", "step": 1608, "epoch": 0.6938511326860841, "progress_pct": 11.56, "epoch_pct": 11.56, "eta": "48:17:02", "max_grad_norm": 1.0, "loss": 0.7972728610038757, "grad_norm": 0.43009471893310547, "learning_rate": 0.00019926529912825888}
+{"ts": "2025-12-23T20:47:26", "event": "train_log", "step": 1610, "epoch": 0.6947141316073355, "progress_pct": 11.58, "epoch_pct": 11.58, "eta": "48:14:53", "max_grad_norm": 1.0, "loss": 0.8661653995513916, "grad_norm": 0.3705308437347412, "learning_rate": 0.00019925934546017446}
+{"ts": "2025-12-23T20:47:42", "event": "train_log", "step": 1612, "epoch": 0.6955771305285868, "progress_pct": 11.59, "epoch_pct": 11.59, "eta": "48:12:49", "max_grad_norm": 1.0, "loss": 0.8350111246109009, "grad_norm": 0.405208945274353, "learning_rate": 0.00019925336785614635}
+{"ts": "2025-12-23T20:47:57", "event": "train_log", "step": 1614, "epoch": 0.6964401294498382, "progress_pct": 11.6, "epoch_pct": 11.61, "eta": "48:10:40", "max_grad_norm": 1.0, "loss": 0.7920925617218018, "grad_norm": 0.4773033857345581, "learning_rate": 0.00019924736631761602}
+{"ts": "2025-12-23T20:48:12", "event": "train_log", "step": 1616, "epoch": 0.6973031283710895, "progress_pct": 11.62, "epoch_pct": 11.62, "eta": "48:08:31", "max_grad_norm": 1.0, "loss": 0.8644304871559143, "grad_norm": 0.4682428240776062, "learning_rate": 0.00019924134084603075}
+{"ts": "2025-12-23T20:48:26", "event": "train_log", "step": 1618, "epoch": 0.6981661272923408, "progress_pct": 11.63, "epoch_pct": 11.64, "eta": "48:06:17", "max_grad_norm": 1.0, "loss": 0.9897904992103577, "grad_norm": 0.5694834589958191, "learning_rate": 0.00019923529144284346}
+{"ts": "2025-12-23T20:48:42", "event": "train_log", "step": 1620, "epoch": 0.6990291262135923, "progress_pct": 11.65, "epoch_pct": 11.65, "eta": "48:04:13", "max_grad_norm": 1.0, "loss": 0.6910083293914795, "grad_norm": 0.40137484669685364, "learning_rate": 0.00019922921810951302}
+{"ts": "2025-12-23T20:48:58", "event": "train_log", "step": 1622, "epoch": 0.6998921251348436, "progress_pct": 11.66, "epoch_pct": 11.66, "eta": "48:02:11", "max_grad_norm": 1.0, "loss": 0.8295826315879822, "grad_norm": 0.42076537013053894, "learning_rate": 0.000199223120847504}
+{"ts": "2025-12-23T20:49:12", "event": "train_log", "step": 1624, "epoch": 0.700755124056095, "progress_pct": 11.68, "epoch_pct": 11.68, "eta": "47:59:57", "max_grad_norm": 1.0, "loss": 0.820871889591217, "grad_norm": 0.4473017752170563, "learning_rate": 0.00019921699965828662}
+{"ts": "2025-12-23T20:49:26", "event": "train_log", "step": 1626, "epoch": 0.7016181229773463, "progress_pct": 11.69, "epoch_pct": 11.69, "eta": "47:57:45", "max_grad_norm": 1.0, "loss": 0.8319019079208374, "grad_norm": 0.43914029002189636, "learning_rate": 0.00019921085454333706}
+{"ts": "2025-12-23T20:49:41", "event": "train_log", "step": 1628, "epoch": 0.7024811218985976, "progress_pct": 11.71, "epoch_pct": 11.71, "eta": "47:55:39", "max_grad_norm": 1.0, "loss": 0.8589251041412354, "grad_norm": 0.4758487939834595, "learning_rate": 0.0001992046855041372}
+{"ts": "2025-12-23T20:49:55", "event": "train_log", "step": 1630, "epoch": 0.703344120819849, "progress_pct": 11.72, "epoch_pct": 11.72, "eta": "47:53:25", "max_grad_norm": 1.0, "loss": 0.9219205975532532, "grad_norm": 0.506401538848877, "learning_rate": 0.00019919849254217465}
+{"ts": "2025-12-23T20:50:09", "event": "train_log", "step": 1632, "epoch": 0.7042071197411003, "progress_pct": 11.73, "epoch_pct": 11.74, "eta": "47:51:11", "max_grad_norm": 1.0, "loss": 0.7824978232383728, "grad_norm": 0.4397984445095062, "learning_rate": 0.00019919227565894277}
+{"ts": "2025-12-23T20:50:24", "event": "train_log", "step": 1634, "epoch": 0.7050701186623517, "progress_pct": 11.75, "epoch_pct": 11.75, "eta": "47:49:02", "max_grad_norm": 1.0, "loss": 0.8472069501876831, "grad_norm": 0.3879252076148987, "learning_rate": 0.0001991860348559408}
+{"ts": "2025-12-23T20:50:39", "event": "train_log", "step": 1636, "epoch": 0.705933117583603, "progress_pct": 11.76, "epoch_pct": 11.77, "eta": "47:46:57", "max_grad_norm": 1.0, "loss": 0.824957013130188, "grad_norm": 0.42238810658454895, "learning_rate": 0.00019917977013467368}
+{"ts": "2025-12-23T20:50:54", "event": "train_log", "step": 1638, "epoch": 0.7067961165048544, "progress_pct": 11.78, "epoch_pct": 11.78, "eta": "47:44:47", "max_grad_norm": 1.0, "loss": 0.9490993022918701, "grad_norm": 0.5235037207603455, "learning_rate": 0.00019917348149665206}
+{"ts": "2025-12-23T20:51:09", "event": "train_log", "step": 1640, "epoch": 0.7076591154261057, "progress_pct": 11.79, "epoch_pct": 11.79, "eta": "47:42:43", "max_grad_norm": 1.0, "loss": 0.960905909538269, "grad_norm": 0.5195287466049194, "learning_rate": 0.0001991671689433925}
+{"ts": "2025-12-23T20:51:23", "event": "train_log", "step": 1642, "epoch": 0.708522114347357, "progress_pct": 11.81, "epoch_pct": 11.81, "eta": "47:40:35", "max_grad_norm": 1.0, "loss": 0.8961218595504761, "grad_norm": 0.5016481876373291, "learning_rate": 0.00019916083247641716}
+{"ts": "2025-12-23T20:51:38", "event": "train_log", "step": 1644, "epoch": 0.7093851132686084, "progress_pct": 11.82, "epoch_pct": 11.82, "eta": "47:38:27", "max_grad_norm": 1.0, "loss": 0.8883417844772339, "grad_norm": 0.5510191321372986, "learning_rate": 0.00019915447209725408}
+{"ts": "2025-12-23T20:51:53", "event": "train_log", "step": 1646, "epoch": 0.7102481121898597, "progress_pct": 11.83, "epoch_pct": 11.84, "eta": "47:36:23", "max_grad_norm": 1.0, "loss": 0.7968636751174927, "grad_norm": 0.4492250084877014, "learning_rate": 0.0001991480878074371}
+{"ts": "2025-12-23T20:52:10", "event": "train_log", "step": 1648, "epoch": 0.7111111111111111, "progress_pct": 11.85, "epoch_pct": 11.85, "eta": "47:34:30", "max_grad_norm": 1.0, "loss": 0.7869221568107605, "grad_norm": 0.4189683496952057, "learning_rate": 0.00019914167960850563}
+{"ts": "2025-12-23T20:52:24", "event": "train_log", "step": 1650, "epoch": 0.7119741100323624, "progress_pct": 11.86, "epoch_pct": 11.87, "eta": "47:32:19", "max_grad_norm": 1.0, "loss": 0.8423646092414856, "grad_norm": 0.4590536653995514, "learning_rate": 0.0001991352475020051}
+{"ts": "2025-12-23T20:52:39", "event": "train_log", "step": 1652, "epoch": 0.7128371089536139, "progress_pct": 11.88, "epoch_pct": 11.88, "eta": "47:30:15", "max_grad_norm": 1.0, "loss": 0.895459771156311, "grad_norm": 0.5058966875076294, "learning_rate": 0.00019912879148948652}
+{"ts": "2025-12-23T20:52:54", "event": "train_log", "step": 1654, "epoch": 0.7137001078748652, "progress_pct": 11.89, "epoch_pct": 11.9, "eta": "47:28:13", "max_grad_norm": 1.0, "loss": 0.8737894296646118, "grad_norm": 0.4904550313949585, "learning_rate": 0.00019912231157250676}
+{"ts": "2025-12-23T20:53:09", "event": "train_log", "step": 1656, "epoch": 0.7145631067961165, "progress_pct": 11.91, "epoch_pct": 11.91, "eta": "47:26:07", "max_grad_norm": 1.0, "loss": 0.8019732236862183, "grad_norm": 0.4670710861682892, "learning_rate": 0.0001991158077526284}
+{"ts": "2025-12-23T20:53:23", "event": "train_log", "step": 1658, "epoch": 0.7154261057173679, "progress_pct": 11.92, "epoch_pct": 11.92, "eta": "47:23:59", "max_grad_norm": 1.0, "loss": 0.9474499821662903, "grad_norm": 0.530343770980835, "learning_rate": 0.00019910928003141984}
+{"ts": "2025-12-23T20:53:38", "event": "train_log", "step": 1660, "epoch": 0.7162891046386192, "progress_pct": 11.94, "epoch_pct": 11.94, "eta": "47:21:56", "max_grad_norm": 1.0, "loss": 0.8738601803779602, "grad_norm": 0.4250960052013397, "learning_rate": 0.00019910272841045518}
+{"ts": "2025-12-23T20:53:53", "event": "train_log", "step": 1662, "epoch": 0.7171521035598706, "progress_pct": 11.95, "epoch_pct": 11.95, "eta": "47:19:55", "max_grad_norm": 1.0, "loss": 0.9578261971473694, "grad_norm": 0.4896513819694519, "learning_rate": 0.0001990961528913143}
+{"ts": "2025-12-23T20:54:08", "event": "train_log", "step": 1664, "epoch": 0.7180151024811219, "progress_pct": 11.96, "epoch_pct": 11.97, "eta": "47:17:51", "max_grad_norm": 1.0, "loss": 0.8116445541381836, "grad_norm": 0.4999626576900482, "learning_rate": 0.00019908955347558291}
+{"ts": "2025-12-23T20:54:23", "event": "train_log", "step": 1666, "epoch": 0.7188781014023733, "progress_pct": 11.98, "epoch_pct": 11.98, "eta": "47:15:47", "max_grad_norm": 1.0, "loss": 0.8783043622970581, "grad_norm": 0.4335242807865143, "learning_rate": 0.00019908293016485237}
+{"ts": "2025-12-23T20:54:39", "event": "train_log", "step": 1668, "epoch": 0.7197411003236246, "progress_pct": 11.99, "epoch_pct": 12.0, "eta": "47:13:59", "max_grad_norm": 1.0, "loss": 0.8223029375076294, "grad_norm": 0.43542763590812683, "learning_rate": 0.00019907628296071992}
+{"ts": "2025-12-23T20:54:54", "event": "train_log", "step": 1670, "epoch": 0.7206040992448759, "progress_pct": 12.01, "epoch_pct": 12.01, "eta": "47:11:57", "max_grad_norm": 1.0, "loss": 1.0053197145462036, "grad_norm": 0.4907461702823639, "learning_rate": 0.00019906961186478842}
+{"ts": "2025-12-23T20:55:10", "event": "train_log", "step": 1672, "epoch": 0.7214670981661273, "progress_pct": 12.02, "epoch_pct": 12.02, "eta": "47:10:04", "max_grad_norm": 1.0, "loss": 0.8107786178588867, "grad_norm": 0.4054848253726959, "learning_rate": 0.00019906291687866667}
+{"ts": "2025-12-23T20:55:26", "event": "train_log", "step": 1674, "epoch": 0.7223300970873786, "progress_pct": 12.04, "epoch_pct": 12.04, "eta": "47:08:09", "max_grad_norm": 1.0, "loss": 0.780781626701355, "grad_norm": 0.3818599283695221, "learning_rate": 0.0001990561980039691}
+{"ts": "2025-12-23T20:55:41", "event": "train_log", "step": 1676, "epoch": 0.72319309600863, "progress_pct": 12.05, "epoch_pct": 12.05, "eta": "47:06:08", "max_grad_norm": 1.0, "loss": 0.8189221620559692, "grad_norm": 0.4128594994544983, "learning_rate": 0.00019904945524231587}
+{"ts": "2025-12-23T20:55:56", "event": "train_log", "step": 1678, "epoch": 0.7240560949298813, "progress_pct": 12.06, "epoch_pct": 12.07, "eta": "47:04:05", "max_grad_norm": 1.0, "loss": 0.83652263879776, "grad_norm": 0.46902593970298767, "learning_rate": 0.0001990426885953331}
+{"ts": "2025-12-23T20:56:10", "event": "train_log", "step": 1680, "epoch": 0.7249190938511327, "progress_pct": 12.08, "epoch_pct": 12.08, "eta": "47:01:58", "max_grad_norm": 1.0, "loss": 0.8057956695556641, "grad_norm": 0.49305564165115356, "learning_rate": 0.00019903589806465242}
+{"ts": "2025-12-23T20:56:25", "event": "train_log", "step": 1682, "epoch": 0.725782092772384, "progress_pct": 12.09, "epoch_pct": 12.1, "eta": "47:00:02", "max_grad_norm": 1.0, "loss": 0.8523716926574707, "grad_norm": 0.44408300518989563, "learning_rate": 0.0001990290836519114}
+{"ts": "2025-12-23T20:56:39", "event": "train_log", "step": 1684, "epoch": 0.7266450916936353, "progress_pct": 12.11, "epoch_pct": 12.11, "eta": "46:57:55", "max_grad_norm": 1.0, "loss": 0.9179236888885498, "grad_norm": 0.5211108922958374, "learning_rate": 0.00019902224535875326}
+{"ts": "2025-12-23T20:56:55", "event": "train_log", "step": 1686, "epoch": 0.7275080906148867, "progress_pct": 12.12, "epoch_pct": 12.13, "eta": "46:55:56", "max_grad_norm": 1.0, "loss": 0.8229476809501648, "grad_norm": 0.4736526608467102, "learning_rate": 0.00019901538318682705}
+{"ts": "2025-12-23T20:57:09", "event": "train_log", "step": 1688, "epoch": 0.728371089536138, "progress_pct": 12.14, "epoch_pct": 12.14, "eta": "46:53:52", "max_grad_norm": 1.0, "loss": 0.924200713634491, "grad_norm": 0.541716992855072, "learning_rate": 0.00019900849713778756}
+{"ts": "2025-12-23T20:57:24", "event": "train_log", "step": 1690, "epoch": 0.7292340884573895, "progress_pct": 12.15, "epoch_pct": 12.15, "eta": "46:51:53", "max_grad_norm": 1.0, "loss": 0.88961261510849, "grad_norm": 0.4524400532245636, "learning_rate": 0.00019900158721329532}
+{"ts": "2025-12-23T20:57:39", "event": "train_log", "step": 1692, "epoch": 0.7300970873786408, "progress_pct": 12.17, "epoch_pct": 12.17, "eta": "46:49:56", "max_grad_norm": 1.0, "loss": 0.8491015434265137, "grad_norm": 0.45256128907203674, "learning_rate": 0.00019899465341501662}
+{"ts": "2025-12-23T20:57:54", "event": "train_log", "step": 1694, "epoch": 0.7309600862998922, "progress_pct": 12.18, "epoch_pct": 12.18, "eta": "46:47:59", "max_grad_norm": 1.0, "loss": 0.8833339810371399, "grad_norm": 0.5346773266792297, "learning_rate": 0.0001989876957446235}
+{"ts": "2025-12-23T20:58:11", "event": "train_log", "step": 1696, "epoch": 0.7318230852211435, "progress_pct": 12.19, "epoch_pct": 12.2, "eta": "46:46:10", "max_grad_norm": 1.0, "loss": 0.8535294532775879, "grad_norm": 0.4696357846260071, "learning_rate": 0.0001989807142037938}
+{"ts": "2025-12-23T20:58:27", "event": "train_log", "step": 1698, "epoch": 0.7326860841423948, "progress_pct": 12.21, "epoch_pct": 12.21, "eta": "46:44:21", "max_grad_norm": 1.0, "loss": 0.8273076415061951, "grad_norm": 0.4304637908935547, "learning_rate": 0.0001989737087942111}
+{"ts": "2025-12-23T20:58:42", "event": "train_log", "step": 1700, "epoch": 0.7335490830636462, "progress_pct": 12.22, "epoch_pct": 12.23, "eta": "46:42:24", "max_grad_norm": 1.0, "loss": 0.8759240508079529, "grad_norm": 0.5085629224777222, "learning_rate": 0.00019896667951756466}
+{"ts": "2025-12-23T21:09:45", "event": "train_log", "step": 1700, "epoch": 0.7335490830636462, "progress_pct": 12.22, "epoch_pct": 12.23, "eta": "48:01:46", "max_grad_norm": 1.0, "eval_loss": 0.879119336605072, "eval_runtime": 663.0553, "eval_samples_per_second": 3.107, "eval_steps_per_second": 3.107}
+{"ts": "2025-12-23T21:09:59", "event": "train_log", "step": 1702, "epoch": 0.7344120819848975, "progress_pct": 12.24, "epoch_pct": 12.24, "eta": "47:59:36", "max_grad_norm": 1.0, "loss": 0.852645218372345, "grad_norm": 0.484223872423172, "learning_rate": 0.00019895962637554964}
+{"ts": "2025-12-23T21:10:13", "event": "train_log", "step": 1704, "epoch": 0.7352750809061489, "progress_pct": 12.25, "epoch_pct": 12.25, "eta": "47:57:27", "max_grad_norm": 1.0, "loss": 0.878247857093811, "grad_norm": 0.4819294214248657, "learning_rate": 0.0001989525493698668}
+{"ts": "2025-12-23T21:10:28", "event": "train_log", "step": 1706, "epoch": 0.7361380798274002, "progress_pct": 12.27, "epoch_pct": 12.27, "eta": "47:55:24", "max_grad_norm": 1.0, "loss": 0.8964285254478455, "grad_norm": 0.4170311689376831, "learning_rate": 0.00019894544850222276}
+{"ts": "2025-12-23T21:10:44", "event": "train_log", "step": 1708, "epoch": 0.7370010787486516, "progress_pct": 12.28, "epoch_pct": 12.28, "eta": "47:53:21", "max_grad_norm": 1.0, "loss": 0.7479548454284668, "grad_norm": 0.42712801694869995, "learning_rate": 0.0001989383237743299}
+{"ts": "2025-12-23T21:10:59", "event": "train_log", "step": 1710, "epoch": 0.7378640776699029, "progress_pct": 12.3, "epoch_pct": 12.3, "eta": "47:51:20", "max_grad_norm": 1.0, "loss": 0.8190052509307861, "grad_norm": 0.5051686763763428, "learning_rate": 0.00019893117518790624}
+{"ts": "2025-12-23T21:11:13", "event": "train_log", "step": 1712, "epoch": 0.7387270765911542, "progress_pct": 12.31, "epoch_pct": 12.31, "eta": "47:49:16", "max_grad_norm": 1.0, "loss": 0.8646742105484009, "grad_norm": 0.44053253531455994, "learning_rate": 0.0001989240027446757}
+{"ts": "2025-12-23T21:11:28", "event": "train_log", "step": 1714, "epoch": 0.7395900755124056, "progress_pct": 12.32, "epoch_pct": 12.33, "eta": "47:47:12", "max_grad_norm": 1.0, "loss": 0.874261736869812, "grad_norm": 0.4451025724411011, "learning_rate": 0.00019891680644636782}
+{"ts": "2025-12-23T21:11:43", "event": "train_log", "step": 1716, "epoch": 0.7404530744336569, "progress_pct": 12.34, "epoch_pct": 12.34, "eta": "47:45:05", "max_grad_norm": 1.0, "loss": 0.8892465233802795, "grad_norm": 0.4590521454811096, "learning_rate": 0.00019890958629471798}
+{"ts": "2025-12-23T21:11:58", "event": "train_log", "step": 1718, "epoch": 0.7413160733549083, "progress_pct": 12.35, "epoch_pct": 12.36, "eta": "47:43:09", "max_grad_norm": 1.0, "loss": 0.7031586766242981, "grad_norm": 0.39169448614120483, "learning_rate": 0.00019890234229146732}
+{"ts": "2025-12-23T21:12:13", "event": "train_log", "step": 1720, "epoch": 0.7421790722761596, "progress_pct": 12.37, "epoch_pct": 12.37, "eta": "47:41:05", "max_grad_norm": 1.0, "loss": 0.8548433184623718, "grad_norm": 0.46946024894714355, "learning_rate": 0.00019889507443836266}
+{"ts": "2025-12-23T21:12:28", "event": "train_log", "step": 1722, "epoch": 0.7430420711974111, "progress_pct": 12.38, "epoch_pct": 12.38, "eta": "47:39:02", "max_grad_norm": 1.0, "loss": 0.8231223821640015, "grad_norm": 0.42404699325561523, "learning_rate": 0.0001988877827371566}
+{"ts": "2025-12-23T21:12:44", "event": "train_log", "step": 1724, "epoch": 0.7439050701186624, "progress_pct": 12.4, "epoch_pct": 12.4, "eta": "47:37:09", "max_grad_norm": 1.0, "loss": 0.8443762063980103, "grad_norm": 0.40419483184814453, "learning_rate": 0.00019888046718960755}
+{"ts": "2025-12-23T21:12:58", "event": "train_log", "step": 1726, "epoch": 0.7447680690399137, "progress_pct": 12.41, "epoch_pct": 12.41, "eta": "47:35:04", "max_grad_norm": 1.0, "loss": 0.8787111639976501, "grad_norm": 0.4550437927246094, "learning_rate": 0.0001988731277974796}
+{"ts": "2025-12-23T21:13:13", "event": "train_log", "step": 1728, "epoch": 0.7456310679611651, "progress_pct": 12.42, "epoch_pct": 12.43, "eta": "47:33:02", "max_grad_norm": 1.0, "loss": 0.8440850377082825, "grad_norm": 0.42264053225517273, "learning_rate": 0.0001988657645625426}
+{"ts": "2025-12-23T21:13:28", "event": "train_log", "step": 1730, "epoch": 0.7464940668824164, "progress_pct": 12.44, "epoch_pct": 12.44, "eta": "47:30:57", "max_grad_norm": 1.0, "loss": 0.839216947555542, "grad_norm": 0.4638359844684601, "learning_rate": 0.0001988583774865721}
+{"ts": "2025-12-23T21:13:42", "event": "train_log", "step": 1732, "epoch": 0.7473570658036678, "progress_pct": 12.45, "epoch_pct": 12.46, "eta": "47:28:54", "max_grad_norm": 1.0, "loss": 0.8011161684989929, "grad_norm": 0.42644429206848145, "learning_rate": 0.0001988509665713496}
+{"ts": "2025-12-23T21:13:58", "event": "train_log", "step": 1734, "epoch": 0.7482200647249191, "progress_pct": 12.47, "epoch_pct": 12.47, "eta": "47:26:58", "max_grad_norm": 1.0, "loss": 0.850246787071228, "grad_norm": 0.36932024359703064, "learning_rate": 0.0001988435318186621}
+{"ts": "2025-12-23T21:14:12", "event": "train_log", "step": 1736, "epoch": 0.7490830636461704, "progress_pct": 12.48, "epoch_pct": 12.48, "eta": "47:24:55", "max_grad_norm": 1.0, "loss": 0.7782483100891113, "grad_norm": 0.4771935045719147, "learning_rate": 0.00019883607323030252}
+{"ts": "2025-12-23T21:14:27", "event": "train_log", "step": 1738, "epoch": 0.7499460625674218, "progress_pct": 12.5, "epoch_pct": 12.5, "eta": "47:22:56", "max_grad_norm": 1.0, "loss": 0.8337594866752625, "grad_norm": 0.40007370710372925, "learning_rate": 0.00019882859080806942}
+{"ts": "2025-12-23T21:14:42", "event": "train_log", "step": 1740, "epoch": 0.7508090614886731, "progress_pct": 12.51, "epoch_pct": 12.51, "eta": "47:20:58", "max_grad_norm": 1.0, "loss": 0.8287386894226074, "grad_norm": 0.5007418394088745, "learning_rate": 0.00019882108455376716}
+{"ts": "2025-12-23T21:14:57", "event": "train_log", "step": 1742, "epoch": 0.7516720604099245, "progress_pct": 12.53, "epoch_pct": 12.53, "eta": "47:18:57", "max_grad_norm": 1.0, "loss": 0.8655616044998169, "grad_norm": 0.43999138474464417, "learning_rate": 0.00019881355446920584}
+{"ts": "2025-12-23T21:15:12", "event": "train_log", "step": 1744, "epoch": 0.7525350593311758, "progress_pct": 12.54, "epoch_pct": 12.54, "eta": "47:16:54", "max_grad_norm": 1.0, "loss": 0.8695262670516968, "grad_norm": 0.5115824937820435, "learning_rate": 0.00019880600055620135}
+{"ts": "2025-12-23T21:15:26", "event": "train_log", "step": 1746, "epoch": 0.7533980582524272, "progress_pct": 12.55, "epoch_pct": 12.56, "eta": "47:14:50", "max_grad_norm": 1.0, "loss": 0.9207013845443726, "grad_norm": 0.5035707950592041, "learning_rate": 0.0001987984228165752}
+{"ts": "2025-12-23T21:15:40", "event": "train_log", "step": 1748, "epoch": 0.7542610571736785, "progress_pct": 12.57, "epoch_pct": 12.57, "eta": "47:12:50", "max_grad_norm": 1.0, "loss": 0.8798729777336121, "grad_norm": 0.4689575731754303, "learning_rate": 0.0001987908212521548}
+{"ts": "2025-12-23T21:15:56", "event": "train_log", "step": 1750, "epoch": 0.7551240560949298, "progress_pct": 12.58, "epoch_pct": 12.59, "eta": "47:10:56", "max_grad_norm": 1.0, "loss": 0.7737767696380615, "grad_norm": 0.4730616509914398, "learning_rate": 0.00019878319586477322}
+{"ts": "2025-12-23T21:16:11", "event": "train_log", "step": 1752, "epoch": 0.7559870550161812, "progress_pct": 12.6, "epoch_pct": 12.6, "eta": "47:08:55", "max_grad_norm": 1.0, "loss": 0.929466187953949, "grad_norm": 0.49012845754623413, "learning_rate": 0.00019877554665626926}
+{"ts": "2025-12-23T21:16:26", "event": "train_log", "step": 1754, "epoch": 0.7568500539374325, "progress_pct": 12.61, "epoch_pct": 12.61, "eta": "47:07:01", "max_grad_norm": 1.0, "loss": 0.8155670166015625, "grad_norm": 0.43468761444091797, "learning_rate": 0.0001987678736284875}
+{"ts": "2025-12-23T21:16:41", "event": "train_log", "step": 1756, "epoch": 0.757713052858684, "progress_pct": 12.63, "epoch_pct": 12.63, "eta": "47:05:02", "max_grad_norm": 1.0, "loss": 0.8082395195960999, "grad_norm": 0.507399320602417, "learning_rate": 0.00019876017678327826}
+{"ts": "2025-12-23T21:16:56", "event": "train_log", "step": 1758, "epoch": 0.7585760517799353, "progress_pct": 12.64, "epoch_pct": 12.64, "eta": "47:03:03", "max_grad_norm": 1.0, "loss": 0.8905934691429138, "grad_norm": 0.4733552634716034, "learning_rate": 0.0001987524561224976}
+{"ts": "2025-12-23T21:17:11", "event": "train_log", "step": 1760, "epoch": 0.7594390507011867, "progress_pct": 12.65, "epoch_pct": 12.66, "eta": "47:01:07", "max_grad_norm": 1.0, "loss": 0.8794633746147156, "grad_norm": 0.4670012891292572, "learning_rate": 0.00019874471164800733}
+{"ts": "2025-12-23T21:17:25", "event": "train_log", "step": 1762, "epoch": 0.760302049622438, "progress_pct": 12.67, "epoch_pct": 12.67, "eta": "46:59:07", "max_grad_norm": 1.0, "loss": 0.8413973450660706, "grad_norm": 0.4951624572277069, "learning_rate": 0.000198736943361675}
+{"ts": "2025-12-23T21:17:39", "event": "train_log", "step": 1764, "epoch": 0.7611650485436893, "progress_pct": 12.68, "epoch_pct": 12.69, "eta": "46:57:03", "max_grad_norm": 1.0, "loss": 0.9067897200584412, "grad_norm": 0.5478648543357849, "learning_rate": 0.00019872915126537387}
+{"ts": "2025-12-23T21:17:54", "event": "train_log", "step": 1766, "epoch": 0.7620280474649407, "progress_pct": 12.7, "epoch_pct": 12.7, "eta": "46:55:03", "max_grad_norm": 1.0, "loss": 0.8932394981384277, "grad_norm": 0.48215776681900024, "learning_rate": 0.000198721335360983}
+{"ts": "2025-12-23T21:18:08", "event": "train_log", "step": 1768, "epoch": 0.762891046386192, "progress_pct": 12.71, "epoch_pct": 12.71, "eta": "46:53:02", "max_grad_norm": 1.0, "loss": 0.8496726751327515, "grad_norm": 0.4688864052295685, "learning_rate": 0.00019871349565038715}
+{"ts": "2025-12-23T21:18:22", "event": "train_log", "step": 1770, "epoch": 0.7637540453074434, "progress_pct": 12.73, "epoch_pct": 12.73, "eta": "46:51:03", "max_grad_norm": 1.0, "loss": 0.9232800602912903, "grad_norm": 0.4728260636329651, "learning_rate": 0.0001987056321354768}
+{"ts": "2025-12-23T21:18:37", "event": "train_log", "step": 1772, "epoch": 0.7646170442286947, "progress_pct": 12.74, "epoch_pct": 12.74, "eta": "46:49:06", "max_grad_norm": 1.0, "loss": 0.849755585193634, "grad_norm": 0.44501692056655884, "learning_rate": 0.00019869774481814828}
+{"ts": "2025-12-23T21:18:52", "event": "train_log", "step": 1774, "epoch": 0.7654800431499461, "progress_pct": 12.76, "epoch_pct": 12.76, "eta": "46:47:09", "max_grad_norm": 1.0, "loss": 0.8258485794067383, "grad_norm": 0.4189201593399048, "learning_rate": 0.00019868983370030348}
+{"ts": "2025-12-23T21:19:06", "event": "train_log", "step": 1776, "epoch": 0.7663430420711974, "progress_pct": 12.77, "epoch_pct": 12.77, "eta": "46:45:09", "max_grad_norm": 1.0, "loss": 0.8762873411178589, "grad_norm": 0.5144591927528381, "learning_rate": 0.00019868189878385016}
+{"ts": "2025-12-23T21:19:20", "event": "train_log", "step": 1778, "epoch": 0.7672060409924487, "progress_pct": 12.78, "epoch_pct": 12.79, "eta": "46:43:09", "max_grad_norm": 1.0, "loss": 0.8732464909553528, "grad_norm": 0.5048011541366577, "learning_rate": 0.00019867394007070188}
+{"ts": "2025-12-23T21:19:36", "event": "train_log", "step": 1780, "epoch": 0.7680690399137001, "progress_pct": 12.8, "epoch_pct": 12.8, "eta": "46:41:21", "max_grad_norm": 1.0, "loss": 0.8732751607894897, "grad_norm": 0.41639819741249084, "learning_rate": 0.00019866595756277774}
+{"ts": "2025-12-23T21:19:50", "event": "train_log", "step": 1782, "epoch": 0.7689320388349514, "progress_pct": 12.81, "epoch_pct": 12.82, "eta": "46:39:20", "max_grad_norm": 1.0, "loss": 0.8453729748725891, "grad_norm": 0.526757538318634, "learning_rate": 0.00019865795126200271}
+{"ts": "2025-12-23T21:20:04", "event": "train_log", "step": 1784, "epoch": 0.7697950377562028, "progress_pct": 12.83, "epoch_pct": 12.83, "eta": "46:37:19", "max_grad_norm": 1.0, "loss": 0.8780192732810974, "grad_norm": 0.47041091322898865, "learning_rate": 0.0001986499211703075}
+{"ts": "2025-12-23T21:20:18", "event": "train_log", "step": 1786, "epoch": 0.7706580366774541, "progress_pct": 12.84, "epoch_pct": 12.84, "eta": "46:35:20", "max_grad_norm": 1.0, "loss": 0.8508450388908386, "grad_norm": 0.4535890221595764, "learning_rate": 0.0001986418672896285}
+{"ts": "2025-12-23T21:20:33", "event": "train_log", "step": 1788, "epoch": 0.7715210355987056, "progress_pct": 12.86, "epoch_pct": 12.86, "eta": "46:33:23", "max_grad_norm": 1.0, "loss": 0.822467565536499, "grad_norm": 0.4608050286769867, "learning_rate": 0.00019863378962190788}
+{"ts": "2025-12-23T21:20:48", "event": "train_log", "step": 1790, "epoch": 0.7723840345199569, "progress_pct": 12.87, "epoch_pct": 12.87, "eta": "46:31:29", "max_grad_norm": 1.0, "loss": 0.844614565372467, "grad_norm": 0.5190523862838745, "learning_rate": 0.00019862568816909356}
+{"ts": "2025-12-23T21:21:03", "event": "train_log", "step": 1792, "epoch": 0.7732470334412082, "progress_pct": 12.88, "epoch_pct": 12.89, "eta": "46:29:34", "max_grad_norm": 1.0, "loss": 0.8144394755363464, "grad_norm": 0.42502254247665405, "learning_rate": 0.00019861756293313912}
+{"ts": "2025-12-23T21:21:17", "event": "train_log", "step": 1794, "epoch": 0.7741100323624596, "progress_pct": 12.9, "epoch_pct": 12.9, "eta": "46:27:36", "max_grad_norm": 1.0, "loss": 0.8836341500282288, "grad_norm": 0.47112616896629333, "learning_rate": 0.000198609413916004}
+{"ts": "2025-12-23T21:21:32", "event": "train_log", "step": 1796, "epoch": 0.7749730312837109, "progress_pct": 12.91, "epoch_pct": 12.92, "eta": "46:25:46", "max_grad_norm": 1.0, "loss": 0.8846262693405151, "grad_norm": 0.48414838314056396, "learning_rate": 0.0001986012411196532}
+{"ts": "2025-12-23T21:21:47", "event": "train_log", "step": 1798, "epoch": 0.7758360302049623, "progress_pct": 12.93, "epoch_pct": 12.93, "eta": "46:23:54", "max_grad_norm": 1.0, "loss": 0.7993118762969971, "grad_norm": 0.4670039415359497, "learning_rate": 0.00019859304454605763}
+{"ts": "2025-12-23T21:22:04", "event": "train_log", "step": 1800, "epoch": 0.7766990291262136, "progress_pct": 12.94, "epoch_pct": 12.94, "eta": "46:22:14", "max_grad_norm": 1.0, "loss": 0.8389407396316528, "grad_norm": 0.41939061880111694, "learning_rate": 0.0001985848241971938}
+{"ts": "2025-12-23T21:33:12", "event": "train_log", "step": 1800, "epoch": 0.7766990291262136, "progress_pct": 12.94, "epoch_pct": 12.94, "eta": "47:37:09", "max_grad_norm": 1.0, "eval_loss": 0.8727664947509766, "eval_runtime": 668.2062, "eval_samples_per_second": 3.083, "eval_steps_per_second": 3.083}
+{"ts": "2025-12-23T21:33:27", "event": "train_log", "step": 1802, "epoch": 0.777562028047465, "progress_pct": 12.96, "epoch_pct": 12.96, "eta": "47:35:12", "max_grad_norm": 1.0, "loss": 0.8824291825294495, "grad_norm": 0.4566517174243927, "learning_rate": 0.00019857658007504405}
+{"ts": "2025-12-23T21:33:43", "event": "train_log", "step": 1804, "epoch": 0.7784250269687163, "progress_pct": 12.97, "epoch_pct": 12.97, "eta": "47:33:17", "max_grad_norm": 1.0, "loss": 0.808982789516449, "grad_norm": 0.4798925518989563, "learning_rate": 0.0001985683121815964}
+{"ts": "2025-12-23T21:33:59", "event": "train_log", "step": 1806, "epoch": 0.7792880258899676, "progress_pct": 12.99, "epoch_pct": 12.99, "eta": "47:31:25", "max_grad_norm": 1.0, "loss": 0.955269992351532, "grad_norm": 0.4659746587276459, "learning_rate": 0.00019856002051884462}
+{"ts": "2025-12-23T21:34:14", "event": "train_log", "step": 1808, "epoch": 0.780151024811219, "progress_pct": 13.0, "epoch_pct": 13.0, "eta": "47:29:31", "max_grad_norm": 1.0, "loss": 0.8142994046211243, "grad_norm": 0.48573991656303406, "learning_rate": 0.00019855170508878818}
+{"ts": "2025-12-23T21:34:29", "event": "train_log", "step": 1810, "epoch": 0.7810140237324703, "progress_pct": 13.01, "epoch_pct": 13.02, "eta": "47:27:36", "max_grad_norm": 1.0, "loss": 0.8755695819854736, "grad_norm": 0.4700213670730591, "learning_rate": 0.00019854336589343236}
+{"ts": "2025-12-23T21:34:45", "event": "train_log", "step": 1812, "epoch": 0.7818770226537217, "progress_pct": 13.03, "epoch_pct": 13.03, "eta": "47:25:46", "max_grad_norm": 1.0, "loss": 0.8098483681678772, "grad_norm": 0.42113450169563293, "learning_rate": 0.00019853500293478806}
+{"ts": "2025-12-23T21:35:02", "event": "train_log", "step": 1814, "epoch": 0.782740021574973, "progress_pct": 13.04, "epoch_pct": 13.05, "eta": "47:23:59", "max_grad_norm": 1.0, "loss": 0.8219783306121826, "grad_norm": 0.4218153655529022, "learning_rate": 0.00019852661621487205}
+{"ts": "2025-12-23T21:35:17", "event": "train_log", "step": 1816, "epoch": 0.7836030204962244, "progress_pct": 13.06, "epoch_pct": 13.06, "eta": "47:22:06", "max_grad_norm": 1.0, "loss": 0.8314159512519836, "grad_norm": 0.499052494764328, "learning_rate": 0.00019851820573570664}
+{"ts": "2025-12-23T21:35:32", "event": "train_log", "step": 1818, "epoch": 0.7844660194174757, "progress_pct": 13.07, "epoch_pct": 13.07, "eta": "47:20:09", "max_grad_norm": 1.0, "loss": 0.7985323071479797, "grad_norm": 0.42420193552970886, "learning_rate": 0.00019850977149932008}
+{"ts": "2025-12-23T21:35:47", "event": "train_log", "step": 1820, "epoch": 0.785329018338727, "progress_pct": 13.09, "epoch_pct": 13.09, "eta": "47:18:16", "max_grad_norm": 1.0, "loss": 0.8528217077255249, "grad_norm": 0.46345841884613037, "learning_rate": 0.0001985013135077462}
+{"ts": "2025-12-23T21:36:03", "event": "train_log", "step": 1822, "epoch": 0.7861920172599784, "progress_pct": 13.1, "epoch_pct": 13.1, "eta": "47:16:21", "max_grad_norm": 1.0, "loss": 0.8659319877624512, "grad_norm": 0.4433307945728302, "learning_rate": 0.00019849283176302462}
+{"ts": "2025-12-23T21:36:17", "event": "train_log", "step": 1824, "epoch": 0.7870550161812297, "progress_pct": 13.11, "epoch_pct": 13.12, "eta": "47:14:24", "max_grad_norm": 1.0, "loss": 0.8675655126571655, "grad_norm": 0.48279091715812683, "learning_rate": 0.00019848432626720067}
+{"ts": "2025-12-23T21:36:32", "event": "train_log", "step": 1826, "epoch": 0.7879180151024812, "progress_pct": 13.13, "epoch_pct": 13.13, "eta": "47:12:30", "max_grad_norm": 1.0, "loss": 0.8550227284431458, "grad_norm": 0.5439180731773376, "learning_rate": 0.0001984757970223254}
+{"ts": "2025-12-23T21:36:47", "event": "train_log", "step": 1828, "epoch": 0.7887810140237325, "progress_pct": 13.14, "epoch_pct": 13.15, "eta": "47:10:34", "max_grad_norm": 1.0, "loss": 0.7290607690811157, "grad_norm": 0.45749521255493164, "learning_rate": 0.0001984672440304556}
+{"ts": "2025-12-23T21:37:02", "event": "train_log", "step": 1830, "epoch": 0.7896440129449838, "progress_pct": 13.16, "epoch_pct": 13.16, "eta": "47:08:40", "max_grad_norm": 1.0, "loss": 0.8619251251220703, "grad_norm": 0.4654783606529236, "learning_rate": 0.00019845866729365378}
+{"ts": "2025-12-23T21:37:17", "event": "train_log", "step": 1832, "epoch": 0.7905070118662352, "progress_pct": 13.17, "epoch_pct": 13.18, "eta": "47:06:43", "max_grad_norm": 1.0, "loss": 0.8249601125717163, "grad_norm": 0.42632243037223816, "learning_rate": 0.00019845006681398823}
+{"ts": "2025-12-23T21:37:32", "event": "train_log", "step": 1834, "epoch": 0.7913700107874865, "progress_pct": 13.19, "epoch_pct": 13.19, "eta": "47:04:50", "max_grad_norm": 1.0, "loss": 0.7138552069664001, "grad_norm": 0.4747186005115509, "learning_rate": 0.0001984414425935329}
+{"ts": "2025-12-23T21:37:46", "event": "train_log", "step": 1836, "epoch": 0.7922330097087379, "progress_pct": 13.2, "epoch_pct": 13.2, "eta": "47:02:48", "max_grad_norm": 1.0, "loss": 0.903292715549469, "grad_norm": 0.4462338387966156, "learning_rate": 0.0001984327946343674}
+{"ts": "2025-12-23T21:38:01", "event": "train_log", "step": 1838, "epoch": 0.7930960086299892, "progress_pct": 13.22, "epoch_pct": 13.22, "eta": "47:00:53", "max_grad_norm": 1.0, "loss": 0.7569618225097656, "grad_norm": 0.4581359922885895, "learning_rate": 0.00019842412293857726}
+{"ts": "2025-12-23T21:38:17", "event": "train_log", "step": 1840, "epoch": 0.7939590075512406, "progress_pct": 13.23, "epoch_pct": 13.23, "eta": "46:59:06", "max_grad_norm": 1.0, "loss": 0.8063036203384399, "grad_norm": 0.4183015525341034, "learning_rate": 0.00019841542750825356}
+{"ts": "2025-12-23T21:38:33", "event": "train_log", "step": 1842, "epoch": 0.7948220064724919, "progress_pct": 13.24, "epoch_pct": 13.25, "eta": "46:57:20", "max_grad_norm": 1.0, "loss": 0.81150221824646, "grad_norm": 0.3954181373119354, "learning_rate": 0.0001984067083454932}
+{"ts": "2025-12-23T21:38:48", "event": "train_log", "step": 1844, "epoch": 0.7956850053937432, "progress_pct": 13.26, "epoch_pct": 13.26, "eta": "46:55:26", "max_grad_norm": 1.0, "loss": 0.841649055480957, "grad_norm": 0.46220019459724426, "learning_rate": 0.0001983979654523987}
+{"ts": "2025-12-23T21:39:02", "event": "train_log", "step": 1846, "epoch": 0.7965480043149946, "progress_pct": 13.27, "epoch_pct": 13.28, "eta": "46:53:29", "max_grad_norm": 1.0, "loss": 0.8019483685493469, "grad_norm": 0.47807541489601135, "learning_rate": 0.00019838919883107843}
+{"ts": "2025-12-23T21:39:17", "event": "train_log", "step": 1848, "epoch": 0.7974110032362459, "progress_pct": 13.29, "epoch_pct": 13.29, "eta": "46:51:32", "max_grad_norm": 1.0, "loss": 0.9343363046646118, "grad_norm": 0.48015692830085754, "learning_rate": 0.0001983804084836464}
+{"ts": "2025-12-23T21:39:32", "event": "train_log", "step": 1850, "epoch": 0.7982740021574973, "progress_pct": 13.3, "epoch_pct": 13.3, "eta": "46:49:39", "max_grad_norm": 1.0, "loss": 0.9163194894790649, "grad_norm": 0.4906708896160126, "learning_rate": 0.00019837159441222238}
+{"ts": "2025-12-23T21:39:47", "event": "train_log", "step": 1852, "epoch": 0.7991370010787486, "progress_pct": 13.32, "epoch_pct": 13.32, "eta": "46:47:49", "max_grad_norm": 1.0, "loss": 0.8017736077308655, "grad_norm": 0.4856911599636078, "learning_rate": 0.0001983627566189318}
+{"ts": "2025-12-23T21:40:01", "event": "train_log", "step": 1854, "epoch": 0.8, "progress_pct": 13.33, "epoch_pct": 13.33, "eta": "46:45:53", "max_grad_norm": 1.0, "loss": 0.8375223875045776, "grad_norm": 0.49403145909309387, "learning_rate": 0.0001983538951059059}
+{"ts": "2025-12-23T21:40:16", "event": "train_log", "step": 1856, "epoch": 0.8008629989212513, "progress_pct": 13.34, "epoch_pct": 13.35, "eta": "46:44:01", "max_grad_norm": 1.0, "loss": 0.8213951587677002, "grad_norm": 0.4237985908985138, "learning_rate": 0.00019834500987528158}
+{"ts": "2025-12-23T21:40:32", "event": "train_log", "step": 1858, "epoch": 0.8017259978425026, "progress_pct": 13.36, "epoch_pct": 13.36, "eta": "46:42:14", "max_grad_norm": 1.0, "loss": 0.8086028099060059, "grad_norm": 0.3977980315685272, "learning_rate": 0.00019833610092920149}
+{"ts": "2025-12-23T21:40:47", "event": "train_log", "step": 1860, "epoch": 0.8025889967637541, "progress_pct": 13.37, "epoch_pct": 13.38, "eta": "46:40:20", "max_grad_norm": 1.0, "loss": 0.9402202367782593, "grad_norm": 0.435253381729126, "learning_rate": 0.00019832716826981392}
+{"ts": "2025-12-23T21:41:02", "event": "train_log", "step": 1862, "epoch": 0.8034519956850054, "progress_pct": 13.39, "epoch_pct": 13.39, "eta": "46:38:32", "max_grad_norm": 1.0, "loss": 0.7730796933174133, "grad_norm": 0.4074764847755432, "learning_rate": 0.000198318211899273}
+{"ts": "2025-12-23T21:41:18", "event": "train_log", "step": 1864, "epoch": 0.8043149946062568, "progress_pct": 13.4, "epoch_pct": 13.41, "eta": "46:36:44", "max_grad_norm": 1.0, "loss": 0.9185802936553955, "grad_norm": 0.48804348707199097, "learning_rate": 0.0001983092318197385}
+{"ts": "2025-12-23T21:41:32", "event": "train_log", "step": 1866, "epoch": 0.8051779935275081, "progress_pct": 13.42, "epoch_pct": 13.42, "eta": "46:34:51", "max_grad_norm": 1.0, "loss": 0.8578243851661682, "grad_norm": 0.44363343715667725, "learning_rate": 0.00019830022803337592}
+{"ts": "2025-12-23T21:41:47", "event": "train_log", "step": 1868, "epoch": 0.8060409924487595, "progress_pct": 13.43, "epoch_pct": 13.43, "eta": "46:32:57", "max_grad_norm": 1.0, "loss": 0.8682060241699219, "grad_norm": 0.46645957231521606, "learning_rate": 0.00019829120054235653}
+{"ts": "2025-12-23T21:42:02", "event": "train_log", "step": 1870, "epoch": 0.8069039913700108, "progress_pct": 13.45, "epoch_pct": 13.45, "eta": "46:31:08", "max_grad_norm": 1.0, "loss": 0.7845040559768677, "grad_norm": 0.4527221620082855, "learning_rate": 0.00019828214934885718}
+{"ts": "2025-12-23T21:42:17", "event": "train_log", "step": 1872, "epoch": 0.8077669902912621, "progress_pct": 13.46, "epoch_pct": 13.46, "eta": "46:29:19", "max_grad_norm": 1.0, "loss": 0.8768247961997986, "grad_norm": 0.4103536307811737, "learning_rate": 0.0001982730744550606}
+{"ts": "2025-12-23T21:42:31", "event": "train_log", "step": 1874, "epoch": 0.8086299892125135, "progress_pct": 13.47, "epoch_pct": 13.48, "eta": "46:27:22", "max_grad_norm": 1.0, "loss": 0.850267231464386, "grad_norm": 0.5257515907287598, "learning_rate": 0.00019826397586315513}
+{"ts": "2025-12-23T21:42:47", "event": "train_log", "step": 1876, "epoch": 0.8094929881337648, "progress_pct": 13.49, "epoch_pct": 13.49, "eta": "46:25:36", "max_grad_norm": 1.0, "loss": 0.8234293460845947, "grad_norm": 0.46675893664360046, "learning_rate": 0.00019825485357533485}
+{"ts": "2025-12-23T21:43:01", "event": "train_log", "step": 1878, "epoch": 0.8103559870550162, "progress_pct": 13.5, "epoch_pct": 13.51, "eta": "46:23:41", "max_grad_norm": 1.0, "loss": 0.8131387829780579, "grad_norm": 0.46315401792526245, "learning_rate": 0.00019824570759379958}
+{"ts": "2025-12-23T21:43:16", "event": "train_log", "step": 1880, "epoch": 0.8112189859762675, "progress_pct": 13.52, "epoch_pct": 13.52, "eta": "46:21:51", "max_grad_norm": 1.0, "loss": 0.7680494785308838, "grad_norm": 0.4766870439052582, "learning_rate": 0.00019823653792075478}
+{"ts": "2025-12-23T21:43:31", "event": "train_log", "step": 1882, "epoch": 0.8120819848975189, "progress_pct": 13.53, "epoch_pct": 13.53, "eta": "46:20:02", "max_grad_norm": 1.0, "loss": 0.7891425490379333, "grad_norm": 0.39025625586509705, "learning_rate": 0.00019822734455841173}
+{"ts": "2025-12-23T21:43:45", "event": "train_log", "step": 1884, "epoch": 0.8129449838187702, "progress_pct": 13.55, "epoch_pct": 13.55, "eta": "46:18:08", "max_grad_norm": 1.0, "loss": 0.7990400791168213, "grad_norm": 0.4672441780567169, "learning_rate": 0.0001982181275089874}
+{"ts": "2025-12-23T21:44:01", "event": "train_log", "step": 1886, "epoch": 0.8138079827400215, "progress_pct": 13.56, "epoch_pct": 13.56, "eta": "46:16:24", "max_grad_norm": 1.0, "loss": 0.7828341722488403, "grad_norm": 0.44310975074768066, "learning_rate": 0.00019820888677470432}
+{"ts": "2025-12-23T21:44:15", "event": "train_log", "step": 1888, "epoch": 0.8146709816612729, "progress_pct": 13.57, "epoch_pct": 13.58, "eta": "46:14:31", "max_grad_norm": 1.0, "loss": 0.897715151309967, "grad_norm": 0.45098716020584106, "learning_rate": 0.00019819962235779096}
+{"ts": "2025-12-23T21:44:30", "event": "train_log", "step": 1890, "epoch": 0.8155339805825242, "progress_pct": 13.59, "epoch_pct": 13.59, "eta": "46:12:44", "max_grad_norm": 1.0, "loss": 0.7987668514251709, "grad_norm": 0.466805100440979, "learning_rate": 0.00019819033426048135}
+{"ts": "2025-12-23T21:44:45", "event": "train_log", "step": 1892, "epoch": 0.8163969795037757, "progress_pct": 13.6, "epoch_pct": 13.61, "eta": "46:10:55", "max_grad_norm": 1.0, "loss": 0.7950236201286316, "grad_norm": 0.4438319206237793, "learning_rate": 0.00019818102248501528}
+{"ts": "2025-12-23T21:45:00", "event": "train_log", "step": 1894, "epoch": 0.817259978425027, "progress_pct": 13.62, "epoch_pct": 13.62, "eta": "46:09:04", "max_grad_norm": 1.0, "loss": 0.8789975643157959, "grad_norm": 0.42012497782707214, "learning_rate": 0.00019817168703363823}
+{"ts": "2025-12-23T21:45:14", "event": "train_log", "step": 1896, "epoch": 0.8181229773462784, "progress_pct": 13.63, "epoch_pct": 13.64, "eta": "46:07:12", "max_grad_norm": 1.0, "loss": 0.8159777522087097, "grad_norm": 0.4359394311904907, "learning_rate": 0.0001981623279086014}
+{"ts": "2025-12-23T21:45:29", "event": "train_log", "step": 1898, "epoch": 0.8189859762675297, "progress_pct": 13.65, "epoch_pct": 13.65, "eta": "46:05:23", "max_grad_norm": 1.0, "loss": 0.84877610206604, "grad_norm": 0.44709593057632446, "learning_rate": 0.00019815294511216173}
+{"ts": "2025-12-23T21:45:43", "event": "train_log", "step": 1900, "epoch": 0.819848975188781, "progress_pct": 13.66, "epoch_pct": 13.66, "eta": "46:03:28", "max_grad_norm": 1.0, "loss": 0.8467556834220886, "grad_norm": 0.4315306544303894, "learning_rate": 0.00019814353864658184}
+{"ts": "2025-12-23T21:56:42", "event": "train_log", "step": 1900, "epoch": 0.819848975188781, "progress_pct": 13.66, "epoch_pct": 13.66, "eta": "47:12:51", "max_grad_norm": 1.0, "eval_loss": 0.8643407821655273, "eval_runtime": 658.6942, "eval_samples_per_second": 3.127, "eval_steps_per_second": 3.127}
+{"ts": "2025-12-23T21:56:58", "event": "train_log", "step": 1902, "epoch": 0.8207119741100324, "progress_pct": 13.68, "epoch_pct": 13.68, "eta": "47:11:06", "max_grad_norm": 1.0, "loss": 0.7398589849472046, "grad_norm": 0.35530397295951843, "learning_rate": 0.00019813410851412998}
+{"ts": "2025-12-23T21:57:13", "event": "train_log", "step": 1904, "epoch": 0.8215749730312837, "progress_pct": 13.69, "epoch_pct": 13.69, "eta": "47:09:13", "max_grad_norm": 1.0, "loss": 0.8544237613677979, "grad_norm": 0.46949300169944763, "learning_rate": 0.00019812465471708032}
+{"ts": "2025-12-23T21:57:27", "event": "train_log", "step": 1906, "epoch": 0.8224379719525351, "progress_pct": 13.7, "epoch_pct": 13.71, "eta": "47:07:19", "max_grad_norm": 1.0, "loss": 0.8242526054382324, "grad_norm": 0.4961565434932709, "learning_rate": 0.00019811517725771248}
+{"ts": "2025-12-23T21:57:43", "event": "train_log", "step": 1908, "epoch": 0.8233009708737864, "progress_pct": 13.72, "epoch_pct": 13.72, "eta": "47:05:32", "max_grad_norm": 1.0, "loss": 0.7856690287590027, "grad_norm": 0.45835059881210327, "learning_rate": 0.00019810567613831194}
+{"ts": "2025-12-23T21:57:59", "event": "train_log", "step": 1910, "epoch": 0.8241639697950378, "progress_pct": 13.73, "epoch_pct": 13.74, "eta": "47:03:47", "max_grad_norm": 1.0, "loss": 0.8361829519271851, "grad_norm": 0.4446084797382355, "learning_rate": 0.0001980961513611699}
+{"ts": "2025-12-23T21:58:14", "event": "train_log", "step": 1912, "epoch": 0.8250269687162891, "progress_pct": 13.75, "epoch_pct": 13.75, "eta": "47:01:54", "max_grad_norm": 1.0, "loss": 0.8993050456047058, "grad_norm": 0.4470907747745514, "learning_rate": 0.00019808660292858313}
+{"ts": "2025-12-23T21:58:29", "event": "train_log", "step": 1914, "epoch": 0.8258899676375404, "progress_pct": 13.76, "epoch_pct": 13.76, "eta": "47:00:07", "max_grad_norm": 1.0, "loss": 0.8702824711799622, "grad_norm": 0.44883644580841064, "learning_rate": 0.0001980770308428543}
+{"ts": "2025-12-23T21:58:45", "event": "train_log", "step": 1916, "epoch": 0.8267529665587918, "progress_pct": 13.78, "epoch_pct": 13.78, "eta": "46:58:21", "max_grad_norm": 1.0, "loss": 0.8454389572143555, "grad_norm": 0.43215686082839966, "learning_rate": 0.00019806743510629159}
+{"ts": "2025-12-23T21:59:00", "event": "train_log", "step": 1918, "epoch": 0.8276159654800431, "progress_pct": 13.79, "epoch_pct": 13.79, "eta": "46:56:27", "max_grad_norm": 1.0, "loss": 0.8621824383735657, "grad_norm": 0.4525185823440552, "learning_rate": 0.00019805781572120897}
+{"ts": "2025-12-23T21:59:16", "event": "train_log", "step": 1920, "epoch": 0.8284789644012945, "progress_pct": 13.81, "epoch_pct": 13.81, "eta": "46:54:45", "max_grad_norm": 1.0, "loss": 0.8661681413650513, "grad_norm": 0.4616840183734894, "learning_rate": 0.00019804817268992615}
+{"ts": "2025-12-23T21:59:31", "event": "train_log", "step": 1922, "epoch": 0.8293419633225458, "progress_pct": 13.82, "epoch_pct": 13.82, "eta": "46:52:55", "max_grad_norm": 1.0, "loss": 0.8376660346984863, "grad_norm": 0.4252975583076477, "learning_rate": 0.0001980385060147685}
+{"ts": "2025-12-23T21:59:45", "event": "train_log", "step": 1924, "epoch": 0.8302049622437971, "progress_pct": 13.83, "epoch_pct": 13.84, "eta": "46:51:00", "max_grad_norm": 1.0, "loss": 0.9258401393890381, "grad_norm": 0.44600266218185425, "learning_rate": 0.00019802881569806706}
+{"ts": "2025-12-23T22:00:00", "event": "train_log", "step": 1926, "epoch": 0.8310679611650486, "progress_pct": 13.85, "epoch_pct": 13.85, "eta": "46:49:09", "max_grad_norm": 1.0, "loss": 0.8804965615272522, "grad_norm": 0.48872479796409607, "learning_rate": 0.00019801910174215866}
+{"ts": "2025-12-23T22:00:15", "event": "train_log", "step": 1928, "epoch": 0.8319309600862999, "progress_pct": 13.86, "epoch_pct": 13.87, "eta": "46:47:16", "max_grad_norm": 1.0, "loss": 0.8561494946479797, "grad_norm": 0.5357037782669067, "learning_rate": 0.00019800936414938574}
+{"ts": "2025-12-23T22:00:30", "event": "train_log", "step": 1930, "epoch": 0.8327939590075513, "progress_pct": 13.88, "epoch_pct": 13.88, "eta": "46:45:31", "max_grad_norm": 1.0, "loss": 0.782166063785553, "grad_norm": 0.39637291431427, "learning_rate": 0.00019799960292209647}
+{"ts": "2025-12-23T22:00:46", "event": "train_log", "step": 1932, "epoch": 0.8336569579288026, "progress_pct": 13.89, "epoch_pct": 13.89, "eta": "46:43:43", "max_grad_norm": 1.0, "loss": 0.9048293232917786, "grad_norm": 0.521138072013855, "learning_rate": 0.00019798981806264476}
+{"ts": "2025-12-23T22:01:01", "event": "train_log", "step": 1934, "epoch": 0.834519956850054, "progress_pct": 13.91, "epoch_pct": 13.91, "eta": "46:41:55", "max_grad_norm": 1.0, "loss": 0.9269952774047852, "grad_norm": 0.4723529815673828, "learning_rate": 0.00019798000957339015}
+{"ts": "2025-12-23T22:01:17", "event": "train_log", "step": 1936, "epoch": 0.8353829557713053, "progress_pct": 13.92, "epoch_pct": 13.92, "eta": "46:40:14", "max_grad_norm": 1.0, "loss": 0.8620670437812805, "grad_norm": 0.42827340960502625, "learning_rate": 0.0001979701774566979}
+{"ts": "2025-12-23T22:01:32", "event": "train_log", "step": 1938, "epoch": 0.8362459546925566, "progress_pct": 13.93, "epoch_pct": 13.94, "eta": "46:38:25", "max_grad_norm": 1.0, "loss": 0.8016669750213623, "grad_norm": 0.4305116534233093, "learning_rate": 0.00019796032171493907}
+{"ts": "2025-12-23T22:01:47", "event": "train_log", "step": 1940, "epoch": 0.837108953613808, "progress_pct": 13.95, "epoch_pct": 13.95, "eta": "46:36:36", "max_grad_norm": 1.0, "loss": 0.879247784614563, "grad_norm": 0.4995502233505249, "learning_rate": 0.00019795044235049024}
+{"ts": "2025-12-23T22:02:02", "event": "train_log", "step": 1942, "epoch": 0.8379719525350593, "progress_pct": 13.96, "epoch_pct": 13.97, "eta": "46:34:45", "max_grad_norm": 1.0, "loss": 0.9476580023765564, "grad_norm": 0.49229878187179565, "learning_rate": 0.0001979405393657338}
+{"ts": "2025-12-23T22:02:17", "event": "train_log", "step": 1944, "epoch": 0.8388349514563107, "progress_pct": 13.98, "epoch_pct": 13.98, "eta": "46:33:01", "max_grad_norm": 1.0, "loss": 0.8654064536094666, "grad_norm": 0.45756596326828003, "learning_rate": 0.0001979306127630578}
+{"ts": "2025-12-23T22:02:33", "event": "train_log", "step": 1946, "epoch": 0.839697950377562, "progress_pct": 13.99, "epoch_pct": 13.99, "eta": "46:31:15", "max_grad_norm": 1.0, "loss": 0.7792956829071045, "grad_norm": 0.4855344891548157, "learning_rate": 0.00019792066254485603}
+{"ts": "2025-12-23T22:02:48", "event": "train_log", "step": 1948, "epoch": 0.8405609492988134, "progress_pct": 14.01, "epoch_pct": 14.01, "eta": "46:29:33", "max_grad_norm": 1.0, "loss": 0.8000320792198181, "grad_norm": 0.4358632266521454, "learning_rate": 0.00019791068871352787}
+{"ts": "2025-12-23T22:03:03", "event": "train_log", "step": 1950, "epoch": 0.8414239482200647, "progress_pct": 14.02, "epoch_pct": 14.02, "eta": "46:27:44", "max_grad_norm": 1.0, "loss": 0.818372368812561, "grad_norm": 0.4225342273712158, "learning_rate": 0.00019790069127147852}
+{"ts": "2025-12-23T22:03:20", "event": "train_log", "step": 1952, "epoch": 0.842286947141316, "progress_pct": 14.04, "epoch_pct": 14.04, "eta": "46:26:05", "max_grad_norm": 1.0, "loss": 0.727220892906189, "grad_norm": 0.3894529938697815, "learning_rate": 0.00019789067022111886}
+{"ts": "2025-12-23T22:03:34", "event": "train_log", "step": 1954, "epoch": 0.8431499460625674, "progress_pct": 14.05, "epoch_pct": 14.05, "eta": "46:24:17", "max_grad_norm": 1.0, "loss": 0.894101083278656, "grad_norm": 0.5060731768608093, "learning_rate": 0.0001978806255648653}
+{"ts": "2025-12-23T22:03:51", "event": "train_log", "step": 1956, "epoch": 0.8440129449838187, "progress_pct": 14.06, "epoch_pct": 14.07, "eta": "46:22:36", "max_grad_norm": 1.0, "loss": 0.878365695476532, "grad_norm": 0.4165003001689911, "learning_rate": 0.0001978705573051402}
+{"ts": "2025-12-23T22:04:07", "event": "train_log", "step": 1958, "epoch": 0.8448759439050701, "progress_pct": 14.08, "epoch_pct": 14.08, "eta": "46:20:57", "max_grad_norm": 1.0, "loss": 0.8390909433364868, "grad_norm": 0.48767927289009094, "learning_rate": 0.0001978604654443714}
+{"ts": "2025-12-23T22:04:22", "event": "train_log", "step": 1960, "epoch": 0.8457389428263214, "progress_pct": 14.09, "epoch_pct": 14.1, "eta": "46:19:14", "max_grad_norm": 1.0, "loss": 0.8807769417762756, "grad_norm": 0.43019410967826843, "learning_rate": 0.00019785034998499247}
+{"ts": "2025-12-23T22:04:37", "event": "train_log", "step": 1962, "epoch": 0.8466019417475729, "progress_pct": 14.11, "epoch_pct": 14.11, "eta": "46:17:27", "max_grad_norm": 1.0, "loss": 0.8037779331207275, "grad_norm": 0.4430403709411621, "learning_rate": 0.0001978402109294428}
+{"ts": "2025-12-23T22:04:53", "event": "train_log", "step": 1964, "epoch": 0.8474649406688242, "progress_pct": 14.12, "epoch_pct": 14.12, "eta": "46:15:45", "max_grad_norm": 1.0, "loss": 0.8341337442398071, "grad_norm": 0.41642463207244873, "learning_rate": 0.0001978300482801673}
+{"ts": "2025-12-23T22:05:08", "event": "train_log", "step": 1966, "epoch": 0.8483279395900755, "progress_pct": 14.14, "epoch_pct": 14.14, "eta": "46:14:00", "max_grad_norm": 1.0, "loss": 0.854821503162384, "grad_norm": 0.45358774065971375, "learning_rate": 0.00019781986203961668}
+{"ts": "2025-12-23T22:05:24", "event": "train_log", "step": 1968, "epoch": 0.8491909385113269, "progress_pct": 14.15, "epoch_pct": 14.15, "eta": "46:12:20", "max_grad_norm": 1.0, "loss": 0.8527678847312927, "grad_norm": 0.4316342771053314, "learning_rate": 0.00019780965221024728}
+{"ts": "2025-12-23T22:05:41", "event": "train_log", "step": 1970, "epoch": 0.8500539374325782, "progress_pct": 14.16, "epoch_pct": 14.17, "eta": "46:10:46", "max_grad_norm": 1.0, "loss": 0.7461717128753662, "grad_norm": 0.4581106901168823, "learning_rate": 0.00019779941879452122}
+{"ts": "2025-12-23T22:05:56", "event": "train_log", "step": 1972, "epoch": 0.8509169363538296, "progress_pct": 14.18, "epoch_pct": 14.18, "eta": "46:08:57", "max_grad_norm": 1.0, "loss": 0.884441077709198, "grad_norm": 0.49578142166137695, "learning_rate": 0.0001977891617949062}
+{"ts": "2025-12-23T22:06:11", "event": "train_log", "step": 1974, "epoch": 0.8517799352750809, "progress_pct": 14.19, "epoch_pct": 14.2, "eta": "46:07:14", "max_grad_norm": 1.0, "loss": 0.855915904045105, "grad_norm": 0.4366011917591095, "learning_rate": 0.00019777888121387562}
+{"ts": "2025-12-23T22:06:26", "event": "train_log", "step": 1976, "epoch": 0.8526429341963323, "progress_pct": 14.21, "epoch_pct": 14.21, "eta": "46:05:29", "max_grad_norm": 1.0, "loss": 0.7563765645027161, "grad_norm": 0.486162930727005, "learning_rate": 0.00019776857705390864}
+{"ts": "2025-12-23T22:06:43", "event": "train_log", "step": 1978, "epoch": 0.8535059331175836, "progress_pct": 14.22, "epoch_pct": 14.23, "eta": "46:03:55", "max_grad_norm": 1.0, "loss": 0.8346326947212219, "grad_norm": 0.5162674784660339, "learning_rate": 0.00019775824931749005}
+{"ts": "2025-12-23T22:06:58", "event": "train_log", "step": 1980, "epoch": 0.8543689320388349, "progress_pct": 14.24, "epoch_pct": 14.24, "eta": "46:02:11", "max_grad_norm": 1.0, "loss": 0.8701820969581604, "grad_norm": 0.5824693441390991, "learning_rate": 0.0001977478980071103}
+{"ts": "2025-12-23T22:07:13", "event": "train_log", "step": 1982, "epoch": 0.8552319309600863, "progress_pct": 14.25, "epoch_pct": 14.25, "eta": "46:00:24", "max_grad_norm": 1.0, "loss": 0.893528938293457, "grad_norm": 0.4297148883342743, "learning_rate": 0.00019773752312526565}
+{"ts": "2025-12-23T22:07:27", "event": "train_log", "step": 1984, "epoch": 0.8560949298813376, "progress_pct": 14.27, "epoch_pct": 14.27, "eta": "45:58:38", "max_grad_norm": 1.0, "loss": 0.8201018571853638, "grad_norm": 0.42978280782699585, "learning_rate": 0.00019772712467445788}
+{"ts": "2025-12-23T22:07:42", "event": "train_log", "step": 1986, "epoch": 0.856957928802589, "progress_pct": 14.28, "epoch_pct": 14.28, "eta": "45:56:49", "max_grad_norm": 1.0, "loss": 0.9080212116241455, "grad_norm": 0.5192655324935913, "learning_rate": 0.00019771670265719454}
+{"ts": "2025-12-23T22:07:56", "event": "train_log", "step": 1988, "epoch": 0.8578209277238403, "progress_pct": 14.29, "epoch_pct": 14.3, "eta": "45:55:02", "max_grad_norm": 1.0, "loss": 0.8518272638320923, "grad_norm": 0.452690452337265, "learning_rate": 0.00019770625707598885}
+{"ts": "2025-12-23T22:08:10", "event": "train_log", "step": 1990, "epoch": 0.8586839266450917, "progress_pct": 14.31, "epoch_pct": 14.31, "eta": "45:53:12", "max_grad_norm": 1.0, "loss": 0.9426717758178711, "grad_norm": 0.4371768832206726, "learning_rate": 0.00019769578793335976}
+{"ts": "2025-12-23T22:08:25", "event": "train_log", "step": 1992, "epoch": 0.859546925566343, "progress_pct": 14.32, "epoch_pct": 14.33, "eta": "45:51:29", "max_grad_norm": 1.0, "loss": 0.8065400123596191, "grad_norm": 0.44595038890838623, "learning_rate": 0.0001976852952318318}
+{"ts": "2025-12-23T22:08:40", "event": "train_log", "step": 1994, "epoch": 0.8604099244875943, "progress_pct": 14.34, "epoch_pct": 14.34, "eta": "45:49:44", "max_grad_norm": 1.0, "loss": 0.7674415707588196, "grad_norm": 0.4355090260505676, "learning_rate": 0.0001976747789739353}
+{"ts": "2025-12-23T22:08:56", "event": "train_log", "step": 1996, "epoch": 0.8612729234088458, "progress_pct": 14.35, "epoch_pct": 14.35, "eta": "45:48:03", "max_grad_norm": 1.0, "loss": 0.813849925994873, "grad_norm": 0.43745186924934387, "learning_rate": 0.00019766423916220616}
+{"ts": "2025-12-23T22:09:10", "event": "train_log", "step": 1998, "epoch": 0.8621359223300971, "progress_pct": 14.37, "epoch_pct": 14.37, "eta": "45:46:19", "max_grad_norm": 1.0, "loss": 0.7870585322380066, "grad_norm": 0.4588927924633026, "learning_rate": 0.00019765367579918598}
+{"ts": "2025-12-23T22:09:25", "event": "train_log", "step": 2000, "epoch": 0.8629989212513485, "progress_pct": 14.38, "epoch_pct": 14.38, "eta": "45:44:34", "max_grad_norm": 1.0, "loss": 0.8383269309997559, "grad_norm": 0.4170977473258972, "learning_rate": 0.00019764308888742214}
+{"ts": "2025-12-23T22:20:12", "event": "train_log", "step": 2000, "epoch": 0.8629989212513485, "progress_pct": 14.38, "epoch_pct": 14.38, "eta": "46:48:44", "max_grad_norm": 1.0, "eval_loss": 0.8567262887954712, "eval_runtime": 646.6443, "eval_samples_per_second": 3.186, "eval_steps_per_second": 3.186}
+{"ts": "2025-12-23T22:20:27", "event": "train_log", "step": 2002, "epoch": 0.8638619201725998, "progress_pct": 14.39, "epoch_pct": 14.4, "eta": "46:46:59", "max_grad_norm": 1.0, "loss": 0.8261714577674866, "grad_norm": 0.4819261431694031, "learning_rate": 0.0001976324784294676}
+{"ts": "2025-12-23T22:20:42", "event": "train_log", "step": 2004, "epoch": 0.8647249190938512, "progress_pct": 14.41, "epoch_pct": 14.41, "eta": "46:45:09", "max_grad_norm": 1.0, "loss": 0.8493392467498779, "grad_norm": 0.4215400218963623, "learning_rate": 0.00019762184442788098}
+{"ts": "2025-12-23T22:20:57", "event": "train_log", "step": 2006, "epoch": 0.8655879180151025, "progress_pct": 14.42, "epoch_pct": 14.43, "eta": "46:43:22", "max_grad_norm": 1.0, "loss": 0.8645208477973938, "grad_norm": 0.45448991656303406, "learning_rate": 0.00019761118688522668}
+{"ts": "2025-12-23T22:21:12", "event": "train_log", "step": 2008, "epoch": 0.8664509169363538, "progress_pct": 14.44, "epoch_pct": 14.44, "eta": "46:41:39", "max_grad_norm": 1.0, "loss": 0.8816449046134949, "grad_norm": 0.4436458349227905, "learning_rate": 0.0001976005058040747}
+{"ts": "2025-12-23T22:21:27", "event": "train_log", "step": 2010, "epoch": 0.8673139158576052, "progress_pct": 14.45, "epoch_pct": 14.46, "eta": "46:39:52", "max_grad_norm": 1.0, "loss": 0.7622330784797668, "grad_norm": 0.42662230134010315, "learning_rate": 0.00019758980118700072}
+{"ts": "2025-12-23T22:21:43", "event": "train_log", "step": 2012, "epoch": 0.8681769147788565, "progress_pct": 14.47, "epoch_pct": 14.47, "eta": "46:38:12", "max_grad_norm": 1.0, "loss": 0.7843833565711975, "grad_norm": 0.3936038613319397, "learning_rate": 0.0001975790730365861}
+{"ts": "2025-12-23T22:22:00", "event": "train_log", "step": 2014, "epoch": 0.8690399137001079, "progress_pct": 14.48, "epoch_pct": 14.48, "eta": "46:36:34", "max_grad_norm": 1.0, "loss": 0.8294675946235657, "grad_norm": 0.4460368752479553, "learning_rate": 0.00019756832135541796}
+{"ts": "2025-12-23T22:22:15", "event": "train_log", "step": 2016, "epoch": 0.8699029126213592, "progress_pct": 14.5, "epoch_pct": 14.5, "eta": "46:34:51", "max_grad_norm": 1.0, "loss": 0.851332426071167, "grad_norm": 0.47043702006340027, "learning_rate": 0.00019755754614608892}
+{"ts": "2025-12-23T22:22:31", "event": "train_log", "step": 2018, "epoch": 0.8707659115426106, "progress_pct": 14.51, "epoch_pct": 14.51, "eta": "46:33:08", "max_grad_norm": 1.0, "loss": 0.8450362682342529, "grad_norm": 0.4579448401927948, "learning_rate": 0.00019754674741119746}
+{"ts": "2025-12-23T22:22:46", "event": "train_log", "step": 2020, "epoch": 0.8716289104638619, "progress_pct": 14.52, "epoch_pct": 14.53, "eta": "46:31:25", "max_grad_norm": 1.0, "loss": 0.8585519194602966, "grad_norm": 0.44362813234329224, "learning_rate": 0.00019753592515334758}
+{"ts": "2025-12-23T22:23:01", "event": "train_log", "step": 2022, "epoch": 0.8724919093851132, "progress_pct": 14.54, "epoch_pct": 14.54, "eta": "46:29:38", "max_grad_norm": 1.0, "loss": 0.8300179243087769, "grad_norm": 0.4500923156738281, "learning_rate": 0.00019752507937514905}
+{"ts": "2025-12-23T22:23:16", "event": "train_log", "step": 2024, "epoch": 0.8733549083063646, "progress_pct": 14.55, "epoch_pct": 14.56, "eta": "46:27:54", "max_grad_norm": 1.0, "loss": 0.805014431476593, "grad_norm": 0.4330301582813263, "learning_rate": 0.00019751421007921724}
+{"ts": "2025-12-23T22:23:33", "event": "train_log", "step": 2026, "epoch": 0.8742179072276159, "progress_pct": 14.57, "epoch_pct": 14.57, "eta": "46:26:16", "max_grad_norm": 1.0, "loss": 0.8228020071983337, "grad_norm": 0.43873998522758484, "learning_rate": 0.00019750331726817332}
+{"ts": "2025-12-23T22:23:48", "event": "train_log", "step": 2028, "epoch": 0.8750809061488674, "progress_pct": 14.58, "epoch_pct": 14.58, "eta": "46:24:33", "max_grad_norm": 1.0, "loss": 0.8490906357765198, "grad_norm": 0.47558829188346863, "learning_rate": 0.00019749240094464395}
+{"ts": "2025-12-23T22:24:04", "event": "train_log", "step": 2030, "epoch": 0.8759439050701187, "progress_pct": 14.6, "epoch_pct": 14.6, "eta": "46:22:53", "max_grad_norm": 1.0, "loss": 0.816324770450592, "grad_norm": 0.4285199046134949, "learning_rate": 0.0001974814611112616}
+{"ts": "2025-12-23T22:24:19", "event": "train_log", "step": 2032, "epoch": 0.87680690399137, "progress_pct": 14.61, "epoch_pct": 14.61, "eta": "46:21:10", "max_grad_norm": 1.0, "loss": 0.9229121208190918, "grad_norm": 0.4762725532054901, "learning_rate": 0.0001974704977706644}
+{"ts": "2025-12-23T22:24:34", "event": "train_log", "step": 2034, "epoch": 0.8776699029126214, "progress_pct": 14.62, "epoch_pct": 14.63, "eta": "46:19:24", "max_grad_norm": 1.0, "loss": 0.9847140908241272, "grad_norm": 0.49856793880462646, "learning_rate": 0.00019745951092549598}
+{"ts": "2025-12-23T22:24:49", "event": "train_log", "step": 2036, "epoch": 0.8785329018338727, "progress_pct": 14.64, "epoch_pct": 14.64, "eta": "46:17:39", "max_grad_norm": 1.0, "loss": 0.8305321335792542, "grad_norm": 0.5163881182670593, "learning_rate": 0.00019744850057840587}
+{"ts": "2025-12-23T22:25:05", "event": "train_log", "step": 2038, "epoch": 0.8793959007551241, "progress_pct": 14.65, "epoch_pct": 14.66, "eta": "46:16:01", "max_grad_norm": 1.0, "loss": 0.7909449934959412, "grad_norm": 0.47826042771339417, "learning_rate": 0.00019743746673204918}
+{"ts": "2025-12-23T22:25:20", "event": "train_log", "step": 2040, "epoch": 0.8802588996763754, "progress_pct": 14.67, "epoch_pct": 14.67, "eta": "46:14:19", "max_grad_norm": 1.0, "loss": 0.809201180934906, "grad_norm": 0.44080349802970886, "learning_rate": 0.0001974264093890866}
+{"ts": "2025-12-23T22:25:35", "event": "train_log", "step": 2042, "epoch": 0.8811218985976268, "progress_pct": 14.68, "epoch_pct": 14.69, "eta": "46:12:33", "max_grad_norm": 1.0, "loss": 0.8064218163490295, "grad_norm": 0.46925660967826843, "learning_rate": 0.00019741532855218464}
+{"ts": "2025-12-23T22:25:51", "event": "train_log", "step": 2044, "epoch": 0.8819848975188781, "progress_pct": 14.7, "epoch_pct": 14.7, "eta": "46:10:56", "max_grad_norm": 1.0, "loss": 0.8135121464729309, "grad_norm": 0.4223597049713135, "learning_rate": 0.00019740422422401531}
+{"ts": "2025-12-23T22:26:06", "event": "train_log", "step": 2046, "epoch": 0.8828478964401294, "progress_pct": 14.71, "epoch_pct": 14.71, "eta": "46:09:15", "max_grad_norm": 1.0, "loss": 0.8047984838485718, "grad_norm": 0.46334266662597656, "learning_rate": 0.00019739309640725642}
+{"ts": "2025-12-23T22:26:23", "event": "train_log", "step": 2048, "epoch": 0.8837108953613808, "progress_pct": 14.73, "epoch_pct": 14.73, "eta": "46:07:38", "max_grad_norm": 1.0, "loss": 0.7897430658340454, "grad_norm": 0.413682222366333, "learning_rate": 0.0001973819451045914}
+{"ts": "2025-12-23T22:26:39", "event": "train_log", "step": 2050, "epoch": 0.8845738942826321, "progress_pct": 14.74, "epoch_pct": 14.74, "eta": "46:06:04", "max_grad_norm": 1.0, "loss": 0.8411629796028137, "grad_norm": 0.4276670515537262, "learning_rate": 0.0001973707703187093}
+{"ts": "2025-12-23T22:26:55", "event": "train_log", "step": 2052, "epoch": 0.8854368932038835, "progress_pct": 14.75, "epoch_pct": 14.76, "eta": "46:04:25", "max_grad_norm": 1.0, "loss": 0.7906913161277771, "grad_norm": 0.4199331998825073, "learning_rate": 0.0001973595720523049}
+{"ts": "2025-12-23T22:27:09", "event": "train_log", "step": 2054, "epoch": 0.8862998921251348, "progress_pct": 14.77, "epoch_pct": 14.77, "eta": "46:02:38", "max_grad_norm": 1.0, "loss": 0.9042854309082031, "grad_norm": 0.43233853578567505, "learning_rate": 0.0001973483503080786}
+{"ts": "2025-12-23T22:27:25", "event": "train_log", "step": 2056, "epoch": 0.8871628910463862, "progress_pct": 14.78, "epoch_pct": 14.79, "eta": "46:00:58", "max_grad_norm": 1.0, "loss": 0.8177635073661804, "grad_norm": 0.41147297620773315, "learning_rate": 0.00019733710508873647}
+{"ts": "2025-12-23T22:27:40", "event": "train_log", "step": 2058, "epoch": 0.8880258899676375, "progress_pct": 14.8, "epoch_pct": 14.8, "eta": "45:59:17", "max_grad_norm": 1.0, "loss": 0.8867166042327881, "grad_norm": 0.45957690477371216, "learning_rate": 0.00019732583639699023}
+{"ts": "2025-12-23T22:27:55", "event": "train_log", "step": 2060, "epoch": 0.8888888888888888, "progress_pct": 14.81, "epoch_pct": 14.81, "eta": "45:57:37", "max_grad_norm": 1.0, "loss": 0.7208530902862549, "grad_norm": 0.3979831635951996, "learning_rate": 0.00019731454423555728}
+{"ts": "2025-12-23T22:28:10", "event": "train_log", "step": 2062, "epoch": 0.8897518878101403, "progress_pct": 14.83, "epoch_pct": 14.83, "eta": "45:55:56", "max_grad_norm": 1.0, "loss": 0.9158181548118591, "grad_norm": 0.4434017837047577, "learning_rate": 0.00019730322860716073}
+{"ts": "2025-12-23T22:28:27", "event": "train_log", "step": 2064, "epoch": 0.8906148867313916, "progress_pct": 14.84, "epoch_pct": 14.84, "eta": "45:54:20", "max_grad_norm": 1.0, "loss": 0.8103255033493042, "grad_norm": 0.40012025833129883, "learning_rate": 0.00019729188951452922}
+{"ts": "2025-12-23T22:28:43", "event": "train_log", "step": 2066, "epoch": 0.891477885652643, "progress_pct": 14.85, "epoch_pct": 14.86, "eta": "45:52:46", "max_grad_norm": 1.0, "loss": 0.7780100703239441, "grad_norm": 0.41914620995521545, "learning_rate": 0.00019728052696039715}
+{"ts": "2025-12-23T22:28:58", "event": "train_log", "step": 2068, "epoch": 0.8923408845738943, "progress_pct": 14.87, "epoch_pct": 14.87, "eta": "45:51:05", "max_grad_norm": 1.0, "loss": 0.7105780839920044, "grad_norm": 0.48365312814712524, "learning_rate": 0.00019726914094750453}
+{"ts": "2025-12-23T22:29:14", "event": "train_log", "step": 2070, "epoch": 0.8932038834951457, "progress_pct": 14.88, "epoch_pct": 14.89, "eta": "45:49:29", "max_grad_norm": 1.0, "loss": 0.7529635429382324, "grad_norm": 0.4272058308124542, "learning_rate": 0.0001972577314785971}
+{"ts": "2025-12-23T22:29:28", "event": "train_log", "step": 2072, "epoch": 0.894066882416397, "progress_pct": 14.9, "epoch_pct": 14.9, "eta": "45:47:41", "max_grad_norm": 1.0, "loss": 0.836787223815918, "grad_norm": 0.48760271072387695, "learning_rate": 0.00019724629855642612}
+{"ts": "2025-12-23T22:29:44", "event": "train_log", "step": 2074, "epoch": 0.8949298813376483, "progress_pct": 14.91, "epoch_pct": 14.92, "eta": "45:46:04", "max_grad_norm": 1.0, "loss": 0.8773119449615479, "grad_norm": 0.47811925411224365, "learning_rate": 0.00019723484218374865}
+{"ts": "2025-12-23T22:30:00", "event": "train_log", "step": 2076, "epoch": 0.8957928802588997, "progress_pct": 14.93, "epoch_pct": 14.93, "eta": "45:44:29", "max_grad_norm": 1.0, "loss": 0.7151904106140137, "grad_norm": 0.40109625458717346, "learning_rate": 0.0001972233623633273}
+{"ts": "2025-12-23T22:30:15", "event": "train_log", "step": 2078, "epoch": 0.896655879180151, "progress_pct": 14.94, "epoch_pct": 14.94, "eta": "45:42:51", "max_grad_norm": 1.0, "loss": 0.8348540663719177, "grad_norm": 0.48640304803848267, "learning_rate": 0.00019721185909793047}
+{"ts": "2025-12-23T22:30:30", "event": "train_log", "step": 2080, "epoch": 0.8975188781014024, "progress_pct": 14.96, "epoch_pct": 14.96, "eta": "45:41:08", "max_grad_norm": 1.0, "loss": 0.845246434211731, "grad_norm": 0.45748841762542725, "learning_rate": 0.000197200332390332}
+{"ts": "2025-12-23T22:30:45", "event": "train_log", "step": 2082, "epoch": 0.8983818770226537, "progress_pct": 14.97, "epoch_pct": 14.97, "eta": "45:39:30", "max_grad_norm": 1.0, "loss": 0.8746084570884705, "grad_norm": 0.41650277376174927, "learning_rate": 0.00019718878224331157}
+{"ts": "2025-12-23T22:31:00", "event": "train_log", "step": 2084, "epoch": 0.8992448759439051, "progress_pct": 14.98, "epoch_pct": 14.99, "eta": "45:37:48", "max_grad_norm": 1.0, "loss": 0.8252862691879272, "grad_norm": 0.45878589153289795, "learning_rate": 0.00019717720865965443}
+{"ts": "2025-12-23T22:31:18", "event": "train_log", "step": 2086, "epoch": 0.9001078748651564, "progress_pct": 15.0, "epoch_pct": 15.0, "eta": "45:36:27", "max_grad_norm": 1.0, "loss": 0.7056596875190735, "grad_norm": 0.3710020184516907, "learning_rate": 0.0001971656116421515}
+{"ts": "2025-12-23T22:31:34", "event": "train_log", "step": 2088, "epoch": 0.9009708737864077, "progress_pct": 15.01, "epoch_pct": 15.02, "eta": "45:34:51", "max_grad_norm": 1.0, "loss": 0.8305537700653076, "grad_norm": 0.4251181185245514, "learning_rate": 0.00019715399119359935}
+{"ts": "2025-12-23T22:31:49", "event": "train_log", "step": 2090, "epoch": 0.9018338727076591, "progress_pct": 15.03, "epoch_pct": 15.03, "eta": "45:33:11", "max_grad_norm": 1.0, "loss": 0.8431704044342041, "grad_norm": 0.48429808020591736, "learning_rate": 0.0001971423473168002}
+{"ts": "2025-12-23T22:32:05", "event": "train_log", "step": 2092, "epoch": 0.9026968716289104, "progress_pct": 15.04, "epoch_pct": 15.04, "eta": "45:31:34", "max_grad_norm": 1.0, "loss": 0.8311790227890015, "grad_norm": 0.5384030342102051, "learning_rate": 0.00019713068001456186}
+{"ts": "2025-12-23T22:32:21", "event": "train_log", "step": 2094, "epoch": 0.9035598705501618, "progress_pct": 15.06, "epoch_pct": 15.06, "eta": "45:30:05", "max_grad_norm": 1.0, "loss": 0.8077114224433899, "grad_norm": 0.452029287815094, "learning_rate": 0.00019711898928969796}
+{"ts": "2025-12-23T22:32:37", "event": "train_log", "step": 2096, "epoch": 0.9044228694714131, "progress_pct": 15.07, "epoch_pct": 15.07, "eta": "45:28:31", "max_grad_norm": 1.0, "loss": 0.8454164266586304, "grad_norm": 0.4427074193954468, "learning_rate": 0.0001971072751450276}
+{"ts": "2025-12-23T22:32:53", "event": "train_log", "step": 2098, "epoch": 0.9052858683926646, "progress_pct": 15.08, "epoch_pct": 15.09, "eta": "45:26:54", "max_grad_norm": 1.0, "loss": 0.8551414608955383, "grad_norm": 0.4895693063735962, "learning_rate": 0.00019709553758337557}
+{"ts": "2025-12-23T22:33:08", "event": "train_log", "step": 2100, "epoch": 0.9061488673139159, "progress_pct": 15.1, "epoch_pct": 15.1, "eta": "45:25:16", "max_grad_norm": 1.0, "loss": 0.9158598184585571, "grad_norm": 0.47199201583862305, "learning_rate": 0.00019708377660757244}
+{"ts": "2025-12-23T22:44:04", "event": "train_log", "step": 2100, "epoch": 0.9061488673139159, "progress_pct": 15.1, "epoch_pct": 15.1, "eta": "46:26:44", "max_grad_norm": 1.0, "eval_loss": 0.8524587750434875, "eval_runtime": 655.7682, "eval_samples_per_second": 3.141, "eval_steps_per_second": 3.141}
+{"ts": "2025-12-23T22:44:19", "event": "train_log", "step": 2102, "epoch": 0.9070118662351672, "progress_pct": 15.11, "epoch_pct": 15.12, "eta": "46:24:59", "max_grad_norm": 1.0, "loss": 0.8301376700401306, "grad_norm": 0.45380064845085144, "learning_rate": 0.00019707199222045415}
+{"ts": "2025-12-23T22:44:33", "event": "train_log", "step": 2104, "epoch": 0.9078748651564186, "progress_pct": 15.13, "epoch_pct": 15.13, "eta": "46:23:16", "max_grad_norm": 1.0, "loss": 0.8191117644309998, "grad_norm": 0.4775148034095764, "learning_rate": 0.00019706018442486255}
+{"ts": "2025-12-23T22:44:49", "event": "train_log", "step": 2106, "epoch": 0.9087378640776699, "progress_pct": 15.14, "epoch_pct": 15.15, "eta": "46:21:37", "max_grad_norm": 1.0, "loss": 0.8333686590194702, "grad_norm": 0.40894538164138794, "learning_rate": 0.00019704835322364506}
+{"ts": "2025-12-23T22:45:03", "event": "train_log", "step": 2108, "epoch": 0.9096008629989213, "progress_pct": 15.16, "epoch_pct": 15.16, "eta": "46:19:50", "max_grad_norm": 1.0, "loss": 0.7916508913040161, "grad_norm": 0.4202065169811249, "learning_rate": 0.00019703649861965467}
+{"ts": "2025-12-23T22:45:18", "event": "train_log", "step": 2110, "epoch": 0.9104638619201726, "progress_pct": 15.17, "epoch_pct": 15.17, "eta": "46:18:03", "max_grad_norm": 1.0, "loss": 0.8018013834953308, "grad_norm": 0.39157143235206604, "learning_rate": 0.00019702462061575008}
+{"ts": "2025-12-23T22:45:32", "event": "train_log", "step": 2112, "epoch": 0.911326860841424, "progress_pct": 15.19, "epoch_pct": 15.19, "eta": "46:16:15", "max_grad_norm": 1.0, "loss": 0.8819739818572998, "grad_norm": 0.4623039662837982, "learning_rate": 0.00019701271921479565}
+{"ts": "2025-12-23T22:45:46", "event": "train_log", "step": 2114, "epoch": 0.9121898597626753, "progress_pct": 15.2, "epoch_pct": 15.2, "eta": "46:14:32", "max_grad_norm": 1.0, "loss": 0.7652842402458191, "grad_norm": 0.45183128118515015, "learning_rate": 0.00019700079441966128}
+{"ts": "2025-12-23T22:46:01", "event": "train_log", "step": 2116, "epoch": 0.9130528586839266, "progress_pct": 15.21, "epoch_pct": 15.22, "eta": "46:12:48", "max_grad_norm": 1.0, "loss": 0.817150890827179, "grad_norm": 0.4562322795391083, "learning_rate": 0.00019698884623322262}
+{"ts": "2025-12-23T22:46:16", "event": "train_log", "step": 2118, "epoch": 0.913915857605178, "progress_pct": 15.23, "epoch_pct": 15.23, "eta": "46:11:04", "max_grad_norm": 1.0, "loss": 0.8223007917404175, "grad_norm": 0.45955994725227356, "learning_rate": 0.00019697687465836095}
+{"ts": "2025-12-23T22:46:30", "event": "train_log", "step": 2120, "epoch": 0.9147788565264293, "progress_pct": 15.24, "epoch_pct": 15.25, "eta": "46:09:18", "max_grad_norm": 1.0, "loss": 0.7716509699821472, "grad_norm": 0.44595572352409363, "learning_rate": 0.00019696487969796307}
+{"ts": "2025-12-23T22:46:45", "event": "train_log", "step": 2122, "epoch": 0.9156418554476807, "progress_pct": 15.26, "epoch_pct": 15.26, "eta": "46:07:36", "max_grad_norm": 1.0, "loss": 0.8205068111419678, "grad_norm": 0.4380198121070862, "learning_rate": 0.00019695286135492163}
+{"ts": "2025-12-23T22:46:59", "event": "train_log", "step": 2124, "epoch": 0.916504854368932, "progress_pct": 15.27, "epoch_pct": 15.28, "eta": "46:05:53", "max_grad_norm": 1.0, "loss": 0.8126305341720581, "grad_norm": 0.4025624692440033, "learning_rate": 0.0001969408196321347}
+{"ts": "2025-12-23T22:47:14", "event": "train_log", "step": 2126, "epoch": 0.9173678532901833, "progress_pct": 15.29, "epoch_pct": 15.29, "eta": "46:04:09", "max_grad_norm": 1.0, "loss": 0.7840806841850281, "grad_norm": 0.424277663230896, "learning_rate": 0.00019692875453250616}
+{"ts": "2025-12-23T22:47:29", "event": "train_log", "step": 2128, "epoch": 0.9182308522114347, "progress_pct": 15.3, "epoch_pct": 15.3, "eta": "46:02:26", "max_grad_norm": 1.0, "loss": 0.9391030669212341, "grad_norm": 0.4683000445365906, "learning_rate": 0.00019691666605894538}
+{"ts": "2025-12-23T22:47:43", "event": "train_log", "step": 2130, "epoch": 0.919093851132686, "progress_pct": 15.31, "epoch_pct": 15.32, "eta": "46:00:44", "max_grad_norm": 1.0, "loss": 0.8336083889007568, "grad_norm": 0.47679048776626587, "learning_rate": 0.00019690455421436754}
+{"ts": "2025-12-23T22:47:58", "event": "train_log", "step": 2132, "epoch": 0.9199568500539375, "progress_pct": 15.33, "epoch_pct": 15.33, "eta": "45:59:00", "max_grad_norm": 1.0, "loss": 0.917514443397522, "grad_norm": 0.45669928193092346, "learning_rate": 0.00019689241900169323}
+{"ts": "2025-12-23T22:48:13", "event": "train_log", "step": 2134, "epoch": 0.9208198489751888, "progress_pct": 15.34, "epoch_pct": 15.35, "eta": "45:57:23", "max_grad_norm": 1.0, "loss": 0.7798282504081726, "grad_norm": 0.4372829794883728, "learning_rate": 0.00019688026042384893}
+{"ts": "2025-12-23T22:48:29", "event": "train_log", "step": 2136, "epoch": 0.9216828478964402, "progress_pct": 15.36, "epoch_pct": 15.36, "eta": "45:55:44", "max_grad_norm": 1.0, "loss": 0.7415590286254883, "grad_norm": 0.4497234523296356, "learning_rate": 0.00019686807848376655}
+{"ts": "2025-12-23T22:48:43", "event": "train_log", "step": 2138, "epoch": 0.9225458468176915, "progress_pct": 15.37, "epoch_pct": 15.38, "eta": "45:54:01", "max_grad_norm": 1.0, "loss": 0.7713689208030701, "grad_norm": 0.4892704486846924, "learning_rate": 0.00019685587318438372}
+{"ts": "2025-12-23T22:48:58", "event": "train_log", "step": 2140, "epoch": 0.9234088457389428, "progress_pct": 15.39, "epoch_pct": 15.39, "eta": "45:52:20", "max_grad_norm": 1.0, "loss": 0.821044385433197, "grad_norm": 0.490495502948761, "learning_rate": 0.0001968436445286437}
+{"ts": "2025-12-23T22:49:14", "event": "train_log", "step": 2142, "epoch": 0.9242718446601942, "progress_pct": 15.4, "epoch_pct": 15.4, "eta": "45:50:46", "max_grad_norm": 1.0, "loss": 0.796081006526947, "grad_norm": 0.43616363406181335, "learning_rate": 0.00019683139251949538}
+{"ts": "2025-12-23T22:49:28", "event": "train_log", "step": 2144, "epoch": 0.9251348435814455, "progress_pct": 15.42, "epoch_pct": 15.42, "eta": "45:49:04", "max_grad_norm": 1.0, "loss": 0.737835705280304, "grad_norm": 0.4199701249599457, "learning_rate": 0.00019681911715989326}
+{"ts": "2025-12-23T22:49:43", "event": "train_log", "step": 2146, "epoch": 0.9259978425026969, "progress_pct": 15.43, "epoch_pct": 15.43, "eta": "45:47:21", "max_grad_norm": 1.0, "loss": 0.8224935531616211, "grad_norm": 0.45367109775543213, "learning_rate": 0.0001968068184527975}
+{"ts": "2025-12-23T22:49:58", "event": "train_log", "step": 2148, "epoch": 0.9268608414239482, "progress_pct": 15.44, "epoch_pct": 15.45, "eta": "45:45:42", "max_grad_norm": 1.0, "loss": 0.826752245426178, "grad_norm": 0.43349263072013855, "learning_rate": 0.0001967944964011739}
+{"ts": "2025-12-23T22:50:13", "event": "train_log", "step": 2150, "epoch": 0.9277238403451996, "progress_pct": 15.46, "epoch_pct": 15.46, "eta": "45:44:03", "max_grad_norm": 1.0, "loss": 0.8527786731719971, "grad_norm": 0.4693690538406372, "learning_rate": 0.00019678215100799384}
+{"ts": "2025-12-23T22:50:27", "event": "train_log", "step": 2152, "epoch": 0.9285868392664509, "progress_pct": 15.47, "epoch_pct": 15.48, "eta": "45:42:20", "max_grad_norm": 1.0, "loss": 0.8101436495780945, "grad_norm": 0.4281991124153137, "learning_rate": 0.00019676978227623434}
+{"ts": "2025-12-23T22:50:42", "event": "train_log", "step": 2154, "epoch": 0.9294498381877022, "progress_pct": 15.49, "epoch_pct": 15.49, "eta": "45:40:39", "max_grad_norm": 1.0, "loss": 0.8997542262077332, "grad_norm": 0.4662301540374756, "learning_rate": 0.0001967573902088781}
+{"ts": "2025-12-23T22:50:56", "event": "train_log", "step": 2156, "epoch": 0.9303128371089536, "progress_pct": 15.5, "epoch_pct": 15.51, "eta": "45:38:58", "max_grad_norm": 1.0, "loss": 0.8378244638442993, "grad_norm": 0.41807958483695984, "learning_rate": 0.0001967449748089134}
+{"ts": "2025-12-23T22:51:11", "event": "train_log", "step": 2158, "epoch": 0.9311758360302049, "progress_pct": 15.52, "epoch_pct": 15.52, "eta": "45:37:19", "max_grad_norm": 1.0, "loss": 0.8562051057815552, "grad_norm": 0.4789344072341919, "learning_rate": 0.00019673253607933416}
+{"ts": "2025-12-23T22:51:27", "event": "train_log", "step": 2160, "epoch": 0.9320388349514563, "progress_pct": 15.53, "epoch_pct": 15.53, "eta": "45:35:44", "max_grad_norm": 1.0, "loss": 0.78457111120224, "grad_norm": 0.43706783652305603, "learning_rate": 0.0001967200740231399}
+{"ts": "2025-12-23T22:51:43", "event": "train_log", "step": 2162, "epoch": 0.9329018338727076, "progress_pct": 15.55, "epoch_pct": 15.55, "eta": "45:34:13", "max_grad_norm": 1.0, "loss": 0.8058217763900757, "grad_norm": 0.4441883862018585, "learning_rate": 0.0001967075886433358}
+{"ts": "2025-12-23T22:51:59", "event": "train_log", "step": 2164, "epoch": 0.933764832793959, "progress_pct": 15.56, "epoch_pct": 15.56, "eta": "45:32:36", "max_grad_norm": 1.0, "loss": 0.916145384311676, "grad_norm": 0.48960480093955994, "learning_rate": 0.00019669507994293266}
+{"ts": "2025-12-23T22:52:14", "event": "train_log", "step": 2166, "epoch": 0.9346278317152104, "progress_pct": 15.57, "epoch_pct": 15.58, "eta": "45:31:00", "max_grad_norm": 1.0, "loss": 0.8805235028266907, "grad_norm": 0.3990147113800049, "learning_rate": 0.00019668254792494692}
+{"ts": "2025-12-23T22:52:29", "event": "train_log", "step": 2168, "epoch": 0.9354908306364617, "progress_pct": 15.59, "epoch_pct": 15.59, "eta": "45:29:24", "max_grad_norm": 1.0, "loss": 0.8611101508140564, "grad_norm": 0.4299201965332031, "learning_rate": 0.00019666999259240056}
+{"ts": "2025-12-23T22:52:44", "event": "train_log", "step": 2170, "epoch": 0.9363538295577131, "progress_pct": 15.6, "epoch_pct": 15.61, "eta": "45:27:45", "max_grad_norm": 1.0, "loss": 0.8429995179176331, "grad_norm": 0.5267254114151001, "learning_rate": 0.00019665741394832132}
+{"ts": "2025-12-23T22:53:00", "event": "train_log", "step": 2172, "epoch": 0.9372168284789644, "progress_pct": 15.62, "epoch_pct": 15.62, "eta": "45:26:14", "max_grad_norm": 1.0, "loss": 0.8057775497436523, "grad_norm": 0.46667975187301636, "learning_rate": 0.0001966448119957424}
+{"ts": "2025-12-23T22:53:16", "event": "train_log", "step": 2174, "epoch": 0.9380798274002158, "progress_pct": 15.63, "epoch_pct": 15.63, "eta": "45:24:41", "max_grad_norm": 1.0, "loss": 0.7456767559051514, "grad_norm": 0.4140365421772003, "learning_rate": 0.00019663218673770277}
+{"ts": "2025-12-23T22:53:32", "event": "train_log", "step": 2176, "epoch": 0.9389428263214671, "progress_pct": 15.65, "epoch_pct": 15.65, "eta": "45:23:10", "max_grad_norm": 1.0, "loss": 0.7320394515991211, "grad_norm": 0.4236559569835663, "learning_rate": 0.00019661953817724692}
+{"ts": "2025-12-23T22:53:49", "event": "train_log", "step": 2178, "epoch": 0.9398058252427185, "progress_pct": 15.66, "epoch_pct": 15.66, "eta": "45:21:42", "max_grad_norm": 1.0, "loss": 0.7850301265716553, "grad_norm": 0.4075721800327301, "learning_rate": 0.000196606866317425}
+{"ts": "2025-12-23T22:54:03", "event": "train_log", "step": 2180, "epoch": 0.9406688241639698, "progress_pct": 15.67, "epoch_pct": 15.68, "eta": "45:20:01", "max_grad_norm": 1.0, "loss": 0.8228051662445068, "grad_norm": 0.4638446271419525, "learning_rate": 0.00019659417116129276}
+{"ts": "2025-12-23T22:54:19", "event": "train_log", "step": 2182, "epoch": 0.9415318230852211, "progress_pct": 15.69, "epoch_pct": 15.69, "eta": "45:18:27", "max_grad_norm": 1.0, "loss": 0.8458912372589111, "grad_norm": 0.4641942083835602, "learning_rate": 0.00019658145271191164}
+{"ts": "2025-12-23T22:54:33", "event": "train_log", "step": 2184, "epoch": 0.9423948220064725, "progress_pct": 15.7, "epoch_pct": 15.71, "eta": "45:16:49", "max_grad_norm": 1.0, "loss": 0.8002372980117798, "grad_norm": 0.42868348956108093, "learning_rate": 0.00019656871097234856}
+{"ts": "2025-12-23T22:54:48", "event": "train_log", "step": 2186, "epoch": 0.9432578209277238, "progress_pct": 15.72, "epoch_pct": 15.72, "eta": "45:15:11", "max_grad_norm": 1.0, "loss": 0.9096182584762573, "grad_norm": 0.4726828336715698, "learning_rate": 0.00019655594594567615}
+{"ts": "2025-12-23T22:55:04", "event": "train_log", "step": 2188, "epoch": 0.9441208198489752, "progress_pct": 15.73, "epoch_pct": 15.74, "eta": "45:13:41", "max_grad_norm": 1.0, "loss": 0.7508110404014587, "grad_norm": 0.40363940596580505, "learning_rate": 0.00019654315763497265}
+{"ts": "2025-12-23T22:55:19", "event": "train_log", "step": 2190, "epoch": 0.9449838187702265, "progress_pct": 15.75, "epoch_pct": 15.75, "eta": "45:12:04", "max_grad_norm": 1.0, "loss": 0.8898510932922363, "grad_norm": 0.46951010823249817, "learning_rate": 0.00019653034604332192}
+{"ts": "2025-12-23T22:55:35", "event": "train_log", "step": 2192, "epoch": 0.9458468176914779, "progress_pct": 15.76, "epoch_pct": 15.76, "eta": "45:10:30", "max_grad_norm": 1.0, "loss": 0.8604891896247864, "grad_norm": 0.4564061164855957, "learning_rate": 0.0001965175111738134}
+{"ts": "2025-12-23T22:55:50", "event": "train_log", "step": 2194, "epoch": 0.9467098166127292, "progress_pct": 15.78, "epoch_pct": 15.78, "eta": "45:08:56", "max_grad_norm": 1.0, "loss": 0.8314935564994812, "grad_norm": 0.4366895854473114, "learning_rate": 0.00019650465302954219}
+{"ts": "2025-12-23T22:56:05", "event": "train_log", "step": 2196, "epoch": 0.9475728155339805, "progress_pct": 15.79, "epoch_pct": 15.79, "eta": "45:07:19", "max_grad_norm": 1.0, "loss": 0.851138174533844, "grad_norm": 0.541490375995636, "learning_rate": 0.0001964917716136089}
+{"ts": "2025-12-23T22:56:19", "event": "train_log", "step": 2198, "epoch": 0.948435814455232, "progress_pct": 15.8, "epoch_pct": 15.81, "eta": "45:05:42", "max_grad_norm": 1.0, "loss": 0.9248369336128235, "grad_norm": 0.45251160860061646, "learning_rate": 0.0001964788669291199}
+{"ts": "2025-12-23T22:56:35", "event": "train_log", "step": 2200, "epoch": 0.9492988133764833, "progress_pct": 15.82, "epoch_pct": 15.82, "eta": "45:04:11", "max_grad_norm": 1.0, "loss": 0.8113608956336975, "grad_norm": 0.46237683296203613, "learning_rate": 0.00019646593897918707}
+{"ts": "2025-12-23T23:07:42", "event": "train_log", "step": 2200, "epoch": 0.9492988133764833, "progress_pct": 15.82, "epoch_pct": 15.82, "eta": "46:03:18", "max_grad_norm": 1.0, "eval_loss": 0.8443478941917419, "eval_runtime": 666.5866, "eval_samples_per_second": 3.09, "eval_steps_per_second": 3.09}
+{"ts": "2025-12-23T23:07:57", "event": "train_log", "step": 2202, "epoch": 0.9501618122977347, "progress_pct": 15.83, "epoch_pct": 15.84, "eta": "46:01:39", "max_grad_norm": 1.0, "loss": 0.8151772618293762, "grad_norm": 0.4506337344646454, "learning_rate": 0.0001964529877669279}
+{"ts": "2025-12-23T23:08:11", "event": "train_log", "step": 2204, "epoch": 0.951024811218986, "progress_pct": 15.85, "epoch_pct": 15.85, "eta": "45:59:56", "max_grad_norm": 1.0, "loss": 0.920696496963501, "grad_norm": 0.42866984009742737, "learning_rate": 0.00019644001329546557}
+{"ts": "2025-12-23T23:08:25", "event": "train_log", "step": 2206, "epoch": 0.9518878101402374, "progress_pct": 15.86, "epoch_pct": 15.86, "eta": "45:58:14", "max_grad_norm": 1.0, "loss": 0.8228384256362915, "grad_norm": 0.3899093270301819, "learning_rate": 0.00019642701556792878}
+{"ts": "2025-12-23T23:08:40", "event": "train_log", "step": 2208, "epoch": 0.9527508090614887, "progress_pct": 15.88, "epoch_pct": 15.88, "eta": "45:56:35", "max_grad_norm": 1.0, "loss": 0.7483987808227539, "grad_norm": 0.42472460865974426, "learning_rate": 0.00019641399458745186}
+{"ts": "2025-12-23T23:08:56", "event": "train_log", "step": 2210, "epoch": 0.95361380798274, "progress_pct": 15.89, "epoch_pct": 15.89, "eta": "45:54:59", "max_grad_norm": 1.0, "loss": 0.7356619834899902, "grad_norm": 0.4046783447265625, "learning_rate": 0.00019640095035717482}
+{"ts": "2025-12-23T23:09:10", "event": "train_log", "step": 2212, "epoch": 0.9544768069039914, "progress_pct": 15.9, "epoch_pct": 15.91, "eta": "45:53:19", "max_grad_norm": 1.0, "loss": 0.7374731302261353, "grad_norm": 0.4608006179332733, "learning_rate": 0.00019638788288024316}
+{"ts": "2025-12-23T23:09:25", "event": "train_log", "step": 2214, "epoch": 0.9553398058252427, "progress_pct": 15.92, "epoch_pct": 15.92, "eta": "45:51:36", "max_grad_norm": 1.0, "loss": 0.9128687977790833, "grad_norm": 0.448503315448761, "learning_rate": 0.00019637479215980807}
+{"ts": "2025-12-23T23:09:39", "event": "train_log", "step": 2216, "epoch": 0.9562028047464941, "progress_pct": 15.93, "epoch_pct": 15.94, "eta": "45:49:57", "max_grad_norm": 1.0, "loss": 0.6983766555786133, "grad_norm": 0.4477374851703644, "learning_rate": 0.0001963616781990263}
+{"ts": "2025-12-23T23:09:54", "event": "train_log", "step": 2218, "epoch": 0.9570658036677454, "progress_pct": 15.95, "epoch_pct": 15.95, "eta": "45:48:18", "max_grad_norm": 1.0, "loss": 0.8543318510055542, "grad_norm": 0.41463667154312134, "learning_rate": 0.00019634854100106025}
+{"ts": "2025-12-23T23:10:09", "event": "train_log", "step": 2220, "epoch": 0.9579288025889967, "progress_pct": 15.96, "epoch_pct": 15.97, "eta": "45:46:40", "max_grad_norm": 1.0, "loss": 0.8866401314735413, "grad_norm": 0.5271132588386536, "learning_rate": 0.00019633538056907786}
+{"ts": "2025-12-23T23:10:23", "event": "train_log", "step": 2222, "epoch": 0.9587918015102481, "progress_pct": 15.98, "epoch_pct": 15.98, "eta": "45:44:57", "max_grad_norm": 1.0, "loss": 0.8414724469184875, "grad_norm": 0.4496590495109558, "learning_rate": 0.00019632219690625272}
+{"ts": "2025-12-23T23:10:38", "event": "train_log", "step": 2224, "epoch": 0.9596548004314994, "progress_pct": 15.99, "epoch_pct": 15.99, "eta": "45:43:18", "max_grad_norm": 1.0, "loss": 0.8859618902206421, "grad_norm": 0.4772113263607025, "learning_rate": 0.00019630899001576405}
+{"ts": "2025-12-23T23:10:52", "event": "train_log", "step": 2226, "epoch": 0.9605177993527508, "progress_pct": 16.01, "epoch_pct": 16.01, "eta": "45:41:36", "max_grad_norm": 1.0, "loss": 0.8347851037979126, "grad_norm": 0.5249642729759216, "learning_rate": 0.0001962957599007966}
+{"ts": "2025-12-23T23:11:06", "event": "train_log", "step": 2228, "epoch": 0.9613807982740021, "progress_pct": 16.02, "epoch_pct": 16.02, "eta": "45:39:54", "max_grad_norm": 1.0, "loss": 0.7893235087394714, "grad_norm": 0.4931469261646271, "learning_rate": 0.0001962825065645407}
+{"ts": "2025-12-23T23:11:21", "event": "train_log", "step": 2230, "epoch": 0.9622437971952535, "progress_pct": 16.03, "epoch_pct": 16.04, "eta": "45:38:15", "max_grad_norm": 1.0, "loss": 0.815602719783783, "grad_norm": 0.45010602474212646, "learning_rate": 0.00019626923001019245}
+{"ts": "2025-12-23T23:11:35", "event": "train_log", "step": 2232, "epoch": 0.9631067961165048, "progress_pct": 16.05, "epoch_pct": 16.05, "eta": "45:36:37", "max_grad_norm": 1.0, "loss": 0.807309627532959, "grad_norm": 0.42947128415107727, "learning_rate": 0.00019625593024095333}
+{"ts": "2025-12-23T23:11:50", "event": "train_log", "step": 2234, "epoch": 0.9639697950377561, "progress_pct": 16.06, "epoch_pct": 16.07, "eta": "45:35:00", "max_grad_norm": 1.0, "loss": 0.8135440945625305, "grad_norm": 0.43500378727912903, "learning_rate": 0.00019624260726003057}
+{"ts": "2025-12-23T23:12:05", "event": "train_log", "step": 2236, "epoch": 0.9648327939590076, "progress_pct": 16.08, "epoch_pct": 16.08, "eta": "45:33:24", "max_grad_norm": 1.0, "loss": 0.802107036113739, "grad_norm": 0.41840270161628723, "learning_rate": 0.00019622926107063692}
+{"ts": "2025-12-23T23:12:20", "event": "train_log", "step": 2238, "epoch": 0.9656957928802589, "progress_pct": 16.09, "epoch_pct": 16.09, "eta": "45:31:45", "max_grad_norm": 1.0, "loss": 0.7596800923347473, "grad_norm": 0.4580598771572113, "learning_rate": 0.00019621589167599077}
+{"ts": "2025-12-23T23:12:35", "event": "train_log", "step": 2240, "epoch": 0.9665587918015103, "progress_pct": 16.11, "epoch_pct": 16.11, "eta": "45:30:06", "max_grad_norm": 1.0, "loss": 0.7609489560127258, "grad_norm": 0.38064274191856384, "learning_rate": 0.0001962024990793161}
+{"ts": "2025-12-23T23:12:50", "event": "train_log", "step": 2242, "epoch": 0.9674217907227616, "progress_pct": 16.12, "epoch_pct": 16.12, "eta": "45:28:33", "max_grad_norm": 1.0, "loss": 0.7829734086990356, "grad_norm": 0.39098140597343445, "learning_rate": 0.00019618908328384246}
+{"ts": "2025-12-23T23:13:06", "event": "train_log", "step": 2244, "epoch": 0.968284789644013, "progress_pct": 16.13, "epoch_pct": 16.14, "eta": "45:26:59", "max_grad_norm": 1.0, "loss": 0.7570722699165344, "grad_norm": 0.38412022590637207, "learning_rate": 0.00019617564429280502}
+{"ts": "2025-12-23T23:13:21", "event": "train_log", "step": 2246, "epoch": 0.9691477885652643, "progress_pct": 16.15, "epoch_pct": 16.15, "eta": "45:25:23", "max_grad_norm": 1.0, "loss": 0.8634825348854065, "grad_norm": 0.41451776027679443, "learning_rate": 0.0001961621821094445}
+{"ts": "2025-12-23T23:13:35", "event": "train_log", "step": 2248, "epoch": 0.9700107874865156, "progress_pct": 16.16, "epoch_pct": 16.17, "eta": "45:23:44", "max_grad_norm": 1.0, "loss": 0.9002810120582581, "grad_norm": 0.4989950954914093, "learning_rate": 0.00019614869673700725}
+{"ts": "2025-12-23T23:13:50", "event": "train_log", "step": 2250, "epoch": 0.970873786407767, "progress_pct": 16.18, "epoch_pct": 16.18, "eta": "45:22:07", "max_grad_norm": 1.0, "loss": 0.7587819695472717, "grad_norm": 0.4316846430301666, "learning_rate": 0.00019613518817874524}
+{"ts": "2025-12-23T23:14:05", "event": "train_log", "step": 2252, "epoch": 0.9717367853290183, "progress_pct": 16.19, "epoch_pct": 16.2, "eta": "45:20:34", "max_grad_norm": 1.0, "loss": 0.686238706111908, "grad_norm": 0.41293349862098694, "learning_rate": 0.000196121656437916}
+{"ts": "2025-12-23T23:14:19", "event": "train_log", "step": 2254, "epoch": 0.9725997842502697, "progress_pct": 16.21, "epoch_pct": 16.21, "eta": "45:18:54", "max_grad_norm": 1.0, "loss": 0.7895162105560303, "grad_norm": 0.40252262353897095, "learning_rate": 0.00019610810151778258}
+{"ts": "2025-12-23T23:14:34", "event": "train_log", "step": 2256, "epoch": 0.973462783171521, "progress_pct": 16.22, "epoch_pct": 16.22, "eta": "45:17:18", "max_grad_norm": 1.0, "loss": 0.8360300064086914, "grad_norm": 0.42973560094833374, "learning_rate": 0.0001960945234216138}
+{"ts": "2025-12-23T23:14:49", "event": "train_log", "step": 2258, "epoch": 0.9743257820927724, "progress_pct": 16.24, "epoch_pct": 16.24, "eta": "45:15:44", "max_grad_norm": 1.0, "loss": 0.7624704241752625, "grad_norm": 0.40562206506729126, "learning_rate": 0.00019608092215268386}
+{"ts": "2025-12-23T23:15:04", "event": "train_log", "step": 2260, "epoch": 0.9751887810140237, "progress_pct": 16.25, "epoch_pct": 16.25, "eta": "45:14:10", "max_grad_norm": 1.0, "loss": 0.8285008072853088, "grad_norm": 0.4486660063266754, "learning_rate": 0.00019606729771427266}
+{"ts": "2025-12-23T23:15:20", "event": "train_log", "step": 2262, "epoch": 0.976051779935275, "progress_pct": 16.26, "epoch_pct": 16.27, "eta": "45:12:38", "max_grad_norm": 1.0, "loss": 0.7951943278312683, "grad_norm": 0.37069520354270935, "learning_rate": 0.0001960536501096657}
+{"ts": "2025-12-23T23:15:35", "event": "train_log", "step": 2264, "epoch": 0.9769147788565264, "progress_pct": 16.28, "epoch_pct": 16.28, "eta": "45:11:06", "max_grad_norm": 1.0, "loss": 0.7641335129737854, "grad_norm": 0.43367981910705566, "learning_rate": 0.00019603997934215404}
+{"ts": "2025-12-23T23:15:50", "event": "train_log", "step": 2266, "epoch": 0.9777777777777777, "progress_pct": 16.29, "epoch_pct": 16.3, "eta": "45:09:30", "max_grad_norm": 1.0, "loss": 0.8449530601501465, "grad_norm": 0.42540937662124634, "learning_rate": 0.00019602628541503432}
+{"ts": "2025-12-23T23:16:04", "event": "train_log", "step": 2268, "epoch": 0.9786407766990292, "progress_pct": 16.31, "epoch_pct": 16.31, "eta": "45:07:52", "max_grad_norm": 1.0, "loss": 0.8207030296325684, "grad_norm": 0.46175941824913025, "learning_rate": 0.00019601256833160874}
+{"ts": "2025-12-23T23:16:20", "event": "train_log", "step": 2270, "epoch": 0.9795037756202805, "progress_pct": 16.32, "epoch_pct": 16.33, "eta": "45:06:21", "max_grad_norm": 1.0, "loss": 0.7753700017929077, "grad_norm": 0.3834969103336334, "learning_rate": 0.00019599882809518513}
+{"ts": "2025-12-23T23:16:35", "event": "train_log", "step": 2272, "epoch": 0.9803667745415319, "progress_pct": 16.34, "epoch_pct": 16.34, "eta": "45:04:45", "max_grad_norm": 1.0, "loss": 0.8844934701919556, "grad_norm": 0.43960243463516235, "learning_rate": 0.0001959850647090769}
+{"ts": "2025-12-23T23:16:49", "event": "train_log", "step": 2274, "epoch": 0.9812297734627832, "progress_pct": 16.35, "epoch_pct": 16.35, "eta": "45:03:06", "max_grad_norm": 1.0, "loss": 0.7795814275741577, "grad_norm": 0.4240610897541046, "learning_rate": 0.00019597127817660303}
+{"ts": "2025-12-23T23:17:04", "event": "train_log", "step": 2276, "epoch": 0.9820927723840345, "progress_pct": 16.36, "epoch_pct": 16.37, "eta": "45:01:35", "max_grad_norm": 1.0, "loss": 0.6960644721984863, "grad_norm": 0.41870981454849243, "learning_rate": 0.00019595746850108807}
+{"ts": "2025-12-23T23:17:18", "event": "train_log", "step": 2278, "epoch": 0.9829557713052859, "progress_pct": 16.38, "epoch_pct": 16.38, "eta": "44:59:56", "max_grad_norm": 1.0, "loss": 0.7709649205207825, "grad_norm": 0.43871861696243286, "learning_rate": 0.00019594363568586215}
+{"ts": "2025-12-23T23:17:33", "event": "train_log", "step": 2280, "epoch": 0.9838187702265372, "progress_pct": 16.39, "epoch_pct": 16.4, "eta": "44:58:22", "max_grad_norm": 1.0, "loss": 0.7324449419975281, "grad_norm": 0.45331820845603943, "learning_rate": 0.00019592977973426098}
+{"ts": "2025-12-23T23:17:48", "event": "train_log", "step": 2282, "epoch": 0.9846817691477886, "progress_pct": 16.41, "epoch_pct": 16.41, "eta": "44:56:52", "max_grad_norm": 1.0, "loss": 0.8720724582672119, "grad_norm": 0.4300173223018646, "learning_rate": 0.00019591590064962593}
+{"ts": "2025-12-23T23:18:03", "event": "train_log", "step": 2284, "epoch": 0.9855447680690399, "progress_pct": 16.42, "epoch_pct": 16.43, "eta": "44:55:15", "max_grad_norm": 1.0, "loss": 0.7396156191825867, "grad_norm": 0.4478892982006073, "learning_rate": 0.0001959019984353038}
+{"ts": "2025-12-23T23:18:17", "event": "train_log", "step": 2286, "epoch": 0.9864077669902913, "progress_pct": 16.44, "epoch_pct": 16.44, "eta": "44:53:37", "max_grad_norm": 1.0, "loss": 0.8303509950637817, "grad_norm": 0.4391026198863983, "learning_rate": 0.00019588807309464708}
+{"ts": "2025-12-23T23:18:32", "event": "train_log", "step": 2288, "epoch": 0.9872707659115426, "progress_pct": 16.45, "epoch_pct": 16.45, "eta": "44:52:03", "max_grad_norm": 1.0, "loss": 0.739641010761261, "grad_norm": 0.4046599268913269, "learning_rate": 0.00019587412463101378}
+{"ts": "2025-12-23T23:18:46", "event": "train_log", "step": 2290, "epoch": 0.9881337648327939, "progress_pct": 16.47, "epoch_pct": 16.47, "eta": "44:50:28", "max_grad_norm": 1.0, "loss": 0.7448247671127319, "grad_norm": 0.4619915187358856, "learning_rate": 0.00019586015304776756}
+{"ts": "2025-12-23T23:19:00", "event": "train_log", "step": 2292, "epoch": 0.9889967637540453, "progress_pct": 16.48, "epoch_pct": 16.48, "eta": "44:48:51", "max_grad_norm": 1.0, "loss": 0.8184107542037964, "grad_norm": 0.4603526294231415, "learning_rate": 0.00019584615834827753}
+{"ts": "2025-12-23T23:19:15", "event": "train_log", "step": 2294, "epoch": 0.9898597626752966, "progress_pct": 16.49, "epoch_pct": 16.5, "eta": "44:47:15", "max_grad_norm": 1.0, "loss": 0.9069648385047913, "grad_norm": 0.4828874170780182, "learning_rate": 0.00019583214053591852}
+{"ts": "2025-12-23T23:19:31", "event": "train_log", "step": 2296, "epoch": 0.990722761596548, "progress_pct": 16.51, "epoch_pct": 16.51, "eta": "44:45:50", "max_grad_norm": 1.0, "loss": 0.6628880500793457, "grad_norm": 0.37467876076698303, "learning_rate": 0.00019581809961407082}
+{"ts": "2025-12-23T23:19:46", "event": "train_log", "step": 2298, "epoch": 0.9915857605177993, "progress_pct": 16.52, "epoch_pct": 16.53, "eta": "44:44:19", "max_grad_norm": 1.0, "loss": 0.7712231278419495, "grad_norm": 0.4300445318222046, "learning_rate": 0.00019580403558612037}
+{"ts": "2025-12-23T23:20:01", "event": "train_log", "step": 2300, "epoch": 0.9924487594390508, "progress_pct": 16.54, "epoch_pct": 16.54, "eta": "44:42:44", "max_grad_norm": 1.0, "loss": 0.7796293497085571, "grad_norm": 0.4368257522583008, "learning_rate": 0.00019578994845545863}
+{"ts": "2025-12-23T23:31:07", "event": "train_log", "step": 2300, "epoch": 0.9924487594390508, "progress_pct": 16.54, "epoch_pct": 16.54, "eta": "45:38:47", "max_grad_norm": 1.0, "eval_loss": 0.839731752872467, "eval_runtime": 666.2332, "eval_samples_per_second": 3.092, "eval_steps_per_second": 3.092}
+{"ts": "2025-12-23T23:31:22", "event": "train_log", "step": 2302, "epoch": 0.993311758360302, "progress_pct": 16.55, "epoch_pct": 16.56, "eta": "45:37:13", "max_grad_norm": 1.0, "loss": 0.7504367232322693, "grad_norm": 0.4383920729160309, "learning_rate": 0.00019577583822548262}
+{"ts": "2025-12-23T23:31:40", "event": "train_log", "step": 2304, "epoch": 0.9941747572815534, "progress_pct": 16.57, "epoch_pct": 16.57, "eta": "45:35:50", "max_grad_norm": 1.0, "loss": 0.7298936247825623, "grad_norm": 0.3895981013774872, "learning_rate": 0.00019576170489959496}
+{"ts": "2025-12-23T23:31:55", "event": "train_log", "step": 2306, "epoch": 0.9950377562028048, "progress_pct": 16.58, "epoch_pct": 16.58, "eta": "45:34:15", "max_grad_norm": 1.0, "loss": 0.9137371778488159, "grad_norm": 0.4950196444988251, "learning_rate": 0.00019574754848120392}
+{"ts": "2025-12-23T23:32:09", "event": "train_log", "step": 2308, "epoch": 0.9959007551240561, "progress_pct": 16.59, "epoch_pct": 16.6, "eta": "45:32:38", "max_grad_norm": 1.0, "loss": 0.9203279614448547, "grad_norm": 0.5115531086921692, "learning_rate": 0.00019573336897372318}
+{"ts": "2025-12-23T23:32:24", "event": "train_log", "step": 2310, "epoch": 0.9967637540453075, "progress_pct": 16.61, "epoch_pct": 16.61, "eta": "45:31:02", "max_grad_norm": 1.0, "loss": 0.7708958387374878, "grad_norm": 0.43145665526390076, "learning_rate": 0.000195719166380572}
+{"ts": "2025-12-23T23:32:40", "event": "train_log", "step": 2312, "epoch": 0.9976267529665588, "progress_pct": 16.62, "epoch_pct": 16.63, "eta": "45:29:34", "max_grad_norm": 1.0, "loss": 0.7911062836647034, "grad_norm": 0.39575520157814026, "learning_rate": 0.00019570494070517545}
+{"ts": "2025-12-23T23:32:56", "event": "train_log", "step": 2314, "epoch": 0.9984897518878102, "progress_pct": 16.64, "epoch_pct": 16.64, "eta": "45:28:02", "max_grad_norm": 1.0, "loss": 0.8282244205474854, "grad_norm": 0.45690420269966125, "learning_rate": 0.00019569069195096386}
+{"ts": "2025-12-23T23:33:11", "event": "train_log", "step": 2316, "epoch": 0.9993527508090615, "progress_pct": 16.65, "epoch_pct": 16.66, "eta": "45:26:30", "max_grad_norm": 1.0, "loss": 0.8658884763717651, "grad_norm": 0.43362128734588623, "learning_rate": 0.00019567642012137325}
+{"ts": "2025-12-23T23:33:23", "event": "train_log", "step": 2318, "epoch": 1.0, "progress_pct": 16.67, "epoch_pct": 16.67, "eta": "45:24:40", "max_grad_norm": 1.0, "loss": 0.7823468446731567, "grad_norm": 0.6889842748641968, "learning_rate": 0.00019566212521984527}
+{"ts": "2025-12-23T23:33:39", "event": "train_log", "step": 2320, "epoch": 1.0008629989212514, "progress_pct": 16.68, "epoch_pct": 16.68, "eta": "45:23:10", "max_grad_norm": 1.0, "loss": 0.8244057297706604, "grad_norm": 0.3945363759994507, "learning_rate": 0.00019564780724982706}
+{"ts": "2025-12-23T23:33:54", "event": "train_log", "step": 2322, "epoch": 1.0017259978425026, "progress_pct": 16.7, "epoch_pct": 16.7, "eta": "45:21:34", "max_grad_norm": 1.0, "loss": 0.8228418827056885, "grad_norm": 0.5313655734062195, "learning_rate": 0.00019563346621477129}
+{"ts": "2025-12-23T23:34:10", "event": "train_log", "step": 2324, "epoch": 1.002588996763754, "progress_pct": 16.71, "epoch_pct": 16.71, "eta": "45:20:04", "max_grad_norm": 1.0, "loss": 0.8627800941467285, "grad_norm": 0.47728294134140015, "learning_rate": 0.00019561910211813625}
+{"ts": "2025-12-23T23:34:25", "event": "train_log", "step": 2326, "epoch": 1.0034519956850054, "progress_pct": 16.72, "epoch_pct": 16.72, "eta": "45:18:33", "max_grad_norm": 1.0, "loss": 0.8810665011405945, "grad_norm": 0.4706253111362457, "learning_rate": 0.00019560471496338582}
+{"ts": "2025-12-23T23:34:40", "event": "train_log", "step": 2328, "epoch": 1.0043149946062568, "progress_pct": 16.74, "epoch_pct": 16.74, "eta": "45:16:59", "max_grad_norm": 1.0, "loss": 0.7736411094665527, "grad_norm": 0.4333725571632385, "learning_rate": 0.0001955903047539893}
+{"ts": "2025-12-23T23:34:56", "event": "train_log", "step": 2330, "epoch": 1.005177993527508, "progress_pct": 16.75, "epoch_pct": 16.75, "eta": "45:15:28", "max_grad_norm": 1.0, "loss": 0.9185295104980469, "grad_norm": 0.49580323696136475, "learning_rate": 0.00019557587149342178}
+{"ts": "2025-12-23T23:35:12", "event": "train_log", "step": 2332, "epoch": 1.0060409924487594, "progress_pct": 16.77, "epoch_pct": 16.77, "eta": "45:14:03", "max_grad_norm": 1.0, "loss": 0.7387797832489014, "grad_norm": 0.4362829029560089, "learning_rate": 0.0001955614151851637}
+{"ts": "2025-12-23T23:35:30", "event": "train_log", "step": 2334, "epoch": 1.0069039913700109, "progress_pct": 16.78, "epoch_pct": 16.78, "eta": "45:12:41", "max_grad_norm": 1.0, "loss": 0.672156810760498, "grad_norm": 0.42584139108657837, "learning_rate": 0.00019554693583270113}
+{"ts": "2025-12-23T23:35:45", "event": "train_log", "step": 2336, "epoch": 1.007766990291262, "progress_pct": 16.8, "epoch_pct": 16.8, "eta": "45:11:10", "max_grad_norm": 1.0, "loss": 0.7638119459152222, "grad_norm": 0.40073466300964355, "learning_rate": 0.0001955324334395257}
+{"ts": "2025-12-23T23:36:00", "event": "train_log", "step": 2338, "epoch": 1.0086299892125135, "progress_pct": 16.81, "epoch_pct": 16.81, "eta": "45:09:38", "max_grad_norm": 1.0, "loss": 0.7930200695991516, "grad_norm": 0.49992597103118896, "learning_rate": 0.00019551790800913458}
+{"ts": "2025-12-23T23:36:16", "event": "train_log", "step": 2340, "epoch": 1.0094929881337649, "progress_pct": 16.82, "epoch_pct": 16.82, "eta": "45:08:07", "max_grad_norm": 1.0, "loss": 0.7128595113754272, "grad_norm": 0.3825504779815674, "learning_rate": 0.00019550335954503058}
+{"ts": "2025-12-23T23:36:32", "event": "train_log", "step": 2342, "epoch": 1.0103559870550163, "progress_pct": 16.84, "epoch_pct": 16.84, "eta": "45:06:42", "max_grad_norm": 1.0, "loss": 0.7130335569381714, "grad_norm": 0.4654180705547333, "learning_rate": 0.00019548878805072196}
+{"ts": "2025-12-23T23:36:48", "event": "train_log", "step": 2344, "epoch": 1.0112189859762675, "progress_pct": 16.85, "epoch_pct": 16.85, "eta": "45:05:13", "max_grad_norm": 1.0, "loss": 0.7843249440193176, "grad_norm": 0.4199283719062805, "learning_rate": 0.00019547419352972258}
+{"ts": "2025-12-23T23:37:03", "event": "train_log", "step": 2346, "epoch": 1.0120819848975189, "progress_pct": 16.87, "epoch_pct": 16.87, "eta": "45:03:42", "max_grad_norm": 1.0, "loss": 0.676262617111206, "grad_norm": 0.43597257137298584, "learning_rate": 0.0001954595759855518}
+{"ts": "2025-12-23T23:37:18", "event": "train_log", "step": 2348, "epoch": 1.0129449838187703, "progress_pct": 16.88, "epoch_pct": 16.88, "eta": "45:02:08", "max_grad_norm": 1.0, "loss": 0.742564857006073, "grad_norm": 0.47415891289711, "learning_rate": 0.0001954449354217346}
+{"ts": "2025-12-23T23:37:33", "event": "train_log", "step": 2350, "epoch": 1.0138079827400215, "progress_pct": 16.9, "epoch_pct": 16.9, "eta": "45:00:34", "max_grad_norm": 1.0, "loss": 0.7419085502624512, "grad_norm": 0.44753482937812805, "learning_rate": 0.00019543027184180153}
+{"ts": "2025-12-23T23:37:48", "event": "train_log", "step": 2352, "epoch": 1.014670981661273, "progress_pct": 16.91, "epoch_pct": 16.91, "eta": "44:59:06", "max_grad_norm": 1.0, "loss": 0.7373939752578735, "grad_norm": 0.4175751209259033, "learning_rate": 0.0001954155852492886}
+{"ts": "2025-12-23T23:38:03", "event": "train_log", "step": 2354, "epoch": 1.0155339805825243, "progress_pct": 16.93, "epoch_pct": 16.93, "eta": "44:57:34", "max_grad_norm": 1.0, "loss": 0.7639825344085693, "grad_norm": 0.40376800298690796, "learning_rate": 0.00019540087564773738}
+{"ts": "2025-12-23T23:38:19", "event": "train_log", "step": 2356, "epoch": 1.0163969795037757, "progress_pct": 16.94, "epoch_pct": 16.94, "eta": "44:56:05", "max_grad_norm": 1.0, "loss": 0.7797452211380005, "grad_norm": 0.4166127145290375, "learning_rate": 0.0001953861430406951}
+{"ts": "2025-12-23T23:38:33", "event": "train_log", "step": 2358, "epoch": 1.017259978425027, "progress_pct": 16.95, "epoch_pct": 16.95, "eta": "44:54:28", "max_grad_norm": 1.0, "loss": 0.8258501887321472, "grad_norm": 0.4340934753417969, "learning_rate": 0.0001953713874317144}
+{"ts": "2025-12-23T23:38:47", "event": "train_log", "step": 2360, "epoch": 1.0181229773462783, "progress_pct": 16.97, "epoch_pct": 16.97, "eta": "44:52:54", "max_grad_norm": 1.0, "loss": 0.7664495706558228, "grad_norm": 0.47081413865089417, "learning_rate": 0.0001953566088243536}
+{"ts": "2025-12-23T23:39:02", "event": "train_log", "step": 2362, "epoch": 1.0189859762675297, "progress_pct": 16.98, "epoch_pct": 16.98, "eta": "44:51:22", "max_grad_norm": 1.0, "loss": 0.7411028742790222, "grad_norm": 0.4126851260662079, "learning_rate": 0.00019534180722217644}
+{"ts": "2025-12-23T23:39:16", "event": "train_log", "step": 2364, "epoch": 1.019848975188781, "progress_pct": 17.0, "epoch_pct": 17.0, "eta": "44:49:47", "max_grad_norm": 1.0, "loss": 0.7514335513114929, "grad_norm": 0.45279955863952637, "learning_rate": 0.00019532698262875227}
+{"ts": "2025-12-23T23:39:31", "event": "train_log", "step": 2366, "epoch": 1.0207119741100323, "progress_pct": 17.01, "epoch_pct": 17.01, "eta": "44:48:14", "max_grad_norm": 1.0, "loss": 0.7544763088226318, "grad_norm": 0.4857143461704254, "learning_rate": 0.00019531213504765595}
+{"ts": "2025-12-23T23:39:46", "event": "train_log", "step": 2368, "epoch": 1.0215749730312838, "progress_pct": 17.03, "epoch_pct": 17.03, "eta": "44:46:44", "max_grad_norm": 1.0, "loss": 0.7246702313423157, "grad_norm": 0.5232970714569092, "learning_rate": 0.00019529726448246795}
+{"ts": "2025-12-23T23:40:01", "event": "train_log", "step": 2370, "epoch": 1.0224379719525352, "progress_pct": 17.04, "epoch_pct": 17.04, "eta": "44:45:12", "max_grad_norm": 1.0, "loss": 0.7399187684059143, "grad_norm": 0.4434663653373718, "learning_rate": 0.00019528237093677424}
+{"ts": "2025-12-23T23:40:16", "event": "train_log", "step": 2372, "epoch": 1.0233009708737864, "progress_pct": 17.05, "epoch_pct": 17.06, "eta": "44:43:39", "max_grad_norm": 1.0, "loss": 0.7208506464958191, "grad_norm": 0.44713014364242554, "learning_rate": 0.0001952674544141663}
+{"ts": "2025-12-23T23:40:30", "event": "train_log", "step": 2374, "epoch": 1.0241639697950378, "progress_pct": 17.07, "epoch_pct": 17.07, "eta": "44:42:07", "max_grad_norm": 1.0, "loss": 0.761768639087677, "grad_norm": 0.43205446004867554, "learning_rate": 0.0001952525149182412}
+{"ts": "2025-12-23T23:40:46", "event": "train_log", "step": 2376, "epoch": 1.0250269687162892, "progress_pct": 17.08, "epoch_pct": 17.08, "eta": "44:40:38", "max_grad_norm": 1.0, "loss": 0.6573513746261597, "grad_norm": 0.4322265386581421, "learning_rate": 0.0001952375524526015}
+{"ts": "2025-12-23T23:41:00", "event": "train_log", "step": 2378, "epoch": 1.0258899676375404, "progress_pct": 17.1, "epoch_pct": 17.1, "eta": "44:39:05", "max_grad_norm": 1.0, "loss": 0.8118118047714233, "grad_norm": 0.4776996970176697, "learning_rate": 0.0001952225670208554}
+{"ts": "2025-12-23T23:41:15", "event": "train_log", "step": 2380, "epoch": 1.0267529665587918, "progress_pct": 17.11, "epoch_pct": 17.11, "eta": "44:37:35", "max_grad_norm": 1.0, "loss": 0.781197190284729, "grad_norm": 0.5014623403549194, "learning_rate": 0.00019520755862661648}
+{"ts": "2025-12-23T23:41:29", "event": "train_log", "step": 2382, "epoch": 1.0276159654800432, "progress_pct": 17.13, "epoch_pct": 17.13, "eta": "44:36:01", "max_grad_norm": 1.0, "loss": 0.8399010896682739, "grad_norm": 0.5164223313331604, "learning_rate": 0.00019519252727350403}
+{"ts": "2025-12-23T23:41:44", "event": "train_log", "step": 2384, "epoch": 1.0284789644012946, "progress_pct": 17.14, "epoch_pct": 17.14, "eta": "44:34:31", "max_grad_norm": 1.0, "loss": 0.786519467830658, "grad_norm": 0.47874927520751953, "learning_rate": 0.00019517747296514276}
+{"ts": "2025-12-23T23:42:00", "event": "train_log", "step": 2386, "epoch": 1.0293419633225458, "progress_pct": 17.16, "epoch_pct": 17.16, "eta": "44:33:03", "max_grad_norm": 1.0, "loss": 0.7837404012680054, "grad_norm": 0.48447099328041077, "learning_rate": 0.00019516239570516292}
+{"ts": "2025-12-23T23:42:14", "event": "train_log", "step": 2388, "epoch": 1.0302049622437972, "progress_pct": 17.17, "epoch_pct": 17.17, "eta": "44:31:30", "max_grad_norm": 1.0, "loss": 0.833958625793457, "grad_norm": 0.4762440323829651, "learning_rate": 0.0001951472954972004}
+{"ts": "2025-12-23T23:42:29", "event": "train_log", "step": 2390, "epoch": 1.0310679611650486, "progress_pct": 17.18, "epoch_pct": 17.18, "eta": "44:29:59", "max_grad_norm": 1.0, "loss": 0.7688734531402588, "grad_norm": 0.42814165353775024, "learning_rate": 0.00019513217234489645}
+{"ts": "2025-12-23T23:42:43", "event": "train_log", "step": 2392, "epoch": 1.0319309600862998, "progress_pct": 17.2, "epoch_pct": 17.2, "eta": "44:28:27", "max_grad_norm": 1.0, "loss": 0.814251720905304, "grad_norm": 0.4784977436065674, "learning_rate": 0.00019511702625189803}
+{"ts": "2025-12-23T23:42:58", "event": "train_log", "step": 2394, "epoch": 1.0327939590075512, "progress_pct": 17.21, "epoch_pct": 17.21, "eta": "44:26:57", "max_grad_norm": 1.0, "loss": 0.7277538180351257, "grad_norm": 0.44989243149757385, "learning_rate": 0.00019510185722185748}
+{"ts": "2025-12-23T23:43:13", "event": "train_log", "step": 2396, "epoch": 1.0336569579288026, "progress_pct": 17.23, "epoch_pct": 17.23, "eta": "44:25:25", "max_grad_norm": 1.0, "loss": 0.844467282295227, "grad_norm": 0.5141931772232056, "learning_rate": 0.0001950866652584328}
+{"ts": "2025-12-23T23:43:28", "event": "train_log", "step": 2398, "epoch": 1.0345199568500538, "progress_pct": 17.24, "epoch_pct": 17.24, "eta": "44:23:55", "max_grad_norm": 1.0, "loss": 0.7662147879600525, "grad_norm": 0.48569414019584656, "learning_rate": 0.00019507145036528747}
+{"ts": "2025-12-23T23:43:42", "event": "train_log", "step": 2400, "epoch": 1.0353829557713052, "progress_pct": 17.26, "epoch_pct": 17.26, "eta": "44:22:23", "max_grad_norm": 1.0, "loss": 0.7628200054168701, "grad_norm": 0.5075576901435852, "learning_rate": 0.00019505621254609047}
+{"ts": "2025-12-23T23:54:35", "event": "train_log", "step": 2400, "epoch": 1.0353829557713052, "progress_pct": 17.26, "epoch_pct": 17.26, "eta": "45:14:35", "max_grad_norm": 1.0, "eval_loss": 0.8369861245155334, "eval_runtime": 653.1661, "eval_samples_per_second": 3.154, "eval_steps_per_second": 3.154}
+{"ts": "2025-12-23T23:54:50", "event": "train_log", "step": 2402, "epoch": 1.0362459546925566, "progress_pct": 17.27, "epoch_pct": 17.27, "eta": "45:13:03", "max_grad_norm": 1.0, "loss": 0.8225719332695007, "grad_norm": 0.49423643946647644, "learning_rate": 0.00019504095180451628}
+{"ts": "2025-12-23T23:55:05", "event": "train_log", "step": 2404, "epoch": 1.037108953613808, "progress_pct": 17.29, "epoch_pct": 17.29, "eta": "45:11:30", "max_grad_norm": 1.0, "loss": 0.8239169120788574, "grad_norm": 0.4558854401111603, "learning_rate": 0.00019502566814424505}
+{"ts": "2025-12-23T23:55:20", "event": "train_log", "step": 2406, "epoch": 1.0379719525350593, "progress_pct": 17.3, "epoch_pct": 17.3, "eta": "45:10:00", "max_grad_norm": 1.0, "loss": 0.7805002331733704, "grad_norm": 0.4864993691444397, "learning_rate": 0.00019501036156896232}
+{"ts": "2025-12-23T23:55:36", "event": "train_log", "step": 2408, "epoch": 1.0388349514563107, "progress_pct": 17.31, "epoch_pct": 17.31, "eta": "45:08:33", "max_grad_norm": 1.0, "loss": 0.866910994052887, "grad_norm": 0.44108837842941284, "learning_rate": 0.00019499503208235918}
+{"ts": "2025-12-23T23:55:51", "event": "train_log", "step": 2410, "epoch": 1.039697950377562, "progress_pct": 17.33, "epoch_pct": 17.33, "eta": "45:07:00", "max_grad_norm": 1.0, "loss": 0.7601662874221802, "grad_norm": 0.4616626799106598, "learning_rate": 0.00019497967968813232}
+{"ts": "2025-12-23T23:56:07", "event": "train_log", "step": 2412, "epoch": 1.0405609492988135, "progress_pct": 17.34, "epoch_pct": 17.34, "eta": "45:05:32", "max_grad_norm": 1.0, "loss": 0.8155668377876282, "grad_norm": 0.4792969524860382, "learning_rate": 0.00019496430438998387}
+{"ts": "2025-12-23T23:56:21", "event": "train_log", "step": 2414, "epoch": 1.0414239482200647, "progress_pct": 17.36, "epoch_pct": 17.36, "eta": "45:04:00", "max_grad_norm": 1.0, "loss": 0.7879545092582703, "grad_norm": 0.45400261878967285, "learning_rate": 0.00019494890619162152}
+{"ts": "2025-12-23T23:56:37", "event": "train_log", "step": 2416, "epoch": 1.042286947141316, "progress_pct": 17.37, "epoch_pct": 17.37, "eta": "45:02:29", "max_grad_norm": 1.0, "loss": 0.7196864485740662, "grad_norm": 0.44541165232658386, "learning_rate": 0.0001949334850967585}
+{"ts": "2025-12-23T23:56:53", "event": "train_log", "step": 2418, "epoch": 1.0431499460625675, "progress_pct": 17.39, "epoch_pct": 17.39, "eta": "45:01:05", "max_grad_norm": 1.0, "loss": 0.7288097739219666, "grad_norm": 0.44515085220336914, "learning_rate": 0.00019491804110911343}
+{"ts": "2025-12-23T23:57:08", "event": "train_log", "step": 2420, "epoch": 1.0440129449838187, "progress_pct": 17.4, "epoch_pct": 17.4, "eta": "44:59:37", "max_grad_norm": 1.0, "loss": 0.7182422280311584, "grad_norm": 0.43586596846580505, "learning_rate": 0.0001949025742324107}
+{"ts": "2025-12-23T23:57:24", "event": "train_log", "step": 2422, "epoch": 1.04487594390507, "progress_pct": 17.41, "epoch_pct": 17.41, "eta": "44:58:10", "max_grad_norm": 1.0, "loss": 0.7005030512809753, "grad_norm": 0.44399815797805786, "learning_rate": 0.00019488708447038002}
+{"ts": "2025-12-23T23:57:40", "event": "train_log", "step": 2424, "epoch": 1.0457389428263215, "progress_pct": 17.43, "epoch_pct": 17.43, "eta": "44:56:43", "max_grad_norm": 1.0, "loss": 0.715505063533783, "grad_norm": 0.4658401310443878, "learning_rate": 0.00019487157182675665}
+{"ts": "2025-12-23T23:57:56", "event": "train_log", "step": 2426, "epoch": 1.0466019417475727, "progress_pct": 17.44, "epoch_pct": 17.44, "eta": "44:55:17", "max_grad_norm": 1.0, "loss": 0.7170135974884033, "grad_norm": 0.4468056261539459, "learning_rate": 0.00019485603630528143}
+{"ts": "2025-12-23T23:58:11", "event": "train_log", "step": 2428, "epoch": 1.0474649406688241, "progress_pct": 17.46, "epoch_pct": 17.46, "eta": "44:53:47", "max_grad_norm": 1.0, "loss": 0.83464115858078, "grad_norm": 0.5302334427833557, "learning_rate": 0.00019484047790970066}
+{"ts": "2025-12-23T23:58:26", "event": "train_log", "step": 2430, "epoch": 1.0483279395900755, "progress_pct": 17.47, "epoch_pct": 17.47, "eta": "44:52:17", "max_grad_norm": 1.0, "loss": 0.7129145264625549, "grad_norm": 0.46583443880081177, "learning_rate": 0.0001948248966437662}
+{"ts": "2025-12-23T23:58:42", "event": "train_log", "step": 2432, "epoch": 1.049190938511327, "progress_pct": 17.49, "epoch_pct": 17.49, "eta": "44:50:50", "max_grad_norm": 1.0, "loss": 0.7990599870681763, "grad_norm": 0.38922831416130066, "learning_rate": 0.0001948092925112354}
+{"ts": "2025-12-23T23:58:56", "event": "train_log", "step": 2434, "epoch": 1.0500539374325781, "progress_pct": 17.5, "epoch_pct": 17.5, "eta": "44:49:17", "max_grad_norm": 1.0, "loss": 0.8572773933410645, "grad_norm": 0.4599211513996124, "learning_rate": 0.00019479366551587108}
+{"ts": "2025-12-23T23:59:11", "event": "train_log", "step": 2436, "epoch": 1.0509169363538295, "progress_pct": 17.52, "epoch_pct": 17.52, "eta": "44:47:47", "max_grad_norm": 1.0, "loss": 0.8107781410217285, "grad_norm": 0.47514498233795166, "learning_rate": 0.00019477801566144165}
+{"ts": "2025-12-23T23:59:28", "event": "train_log", "step": 2438, "epoch": 1.051779935275081, "progress_pct": 17.53, "epoch_pct": 17.53, "eta": "44:46:26", "max_grad_norm": 1.0, "loss": 0.7433347702026367, "grad_norm": 0.41368064284324646, "learning_rate": 0.00019476234295172102}
+{"ts": "2025-12-23T23:59:43", "event": "train_log", "step": 2440, "epoch": 1.0526429341963321, "progress_pct": 17.54, "epoch_pct": 17.54, "eta": "44:44:56", "max_grad_norm": 1.0, "loss": 0.8033983111381531, "grad_norm": 0.4666398763656616, "learning_rate": 0.00019474664739048858}
+{"ts": "2025-12-24T00:00:00", "event": "train_log", "step": 2442, "epoch": 1.0535059331175836, "progress_pct": 17.56, "epoch_pct": 17.56, "eta": "44:43:33", "max_grad_norm": 1.0, "loss": 0.7320330142974854, "grad_norm": 0.41621699929237366, "learning_rate": 0.00019473092898152924}
+{"ts": "2025-12-24T00:00:16", "event": "train_log", "step": 2444, "epoch": 1.054368932038835, "progress_pct": 17.57, "epoch_pct": 17.57, "eta": "44:42:10", "max_grad_norm": 1.0, "loss": 0.7742927074432373, "grad_norm": 0.43523117899894714, "learning_rate": 0.00019471518772863343}
+{"ts": "2025-12-24T00:00:32", "event": "train_log", "step": 2446, "epoch": 1.0552319309600864, "progress_pct": 17.59, "epoch_pct": 17.59, "eta": "44:40:44", "max_grad_norm": 1.0, "loss": 0.8301699161529541, "grad_norm": 0.5151914358139038, "learning_rate": 0.0001946994236355971}
+{"ts": "2025-12-24T00:00:48", "event": "train_log", "step": 2448, "epoch": 1.0560949298813376, "progress_pct": 17.6, "epoch_pct": 17.6, "eta": "44:39:22", "max_grad_norm": 1.0, "loss": 0.837057888507843, "grad_norm": 0.566112756729126, "learning_rate": 0.0001946836367062216}
+{"ts": "2025-12-24T00:01:05", "event": "train_log", "step": 2450, "epoch": 1.056957928802589, "progress_pct": 17.62, "epoch_pct": 17.62, "eta": "44:38:01", "max_grad_norm": 1.0, "loss": 0.7323788404464722, "grad_norm": 0.4257231652736664, "learning_rate": 0.00019466782694431398}
+{"ts": "2025-12-24T00:01:19", "event": "train_log", "step": 2452, "epoch": 1.0578209277238404, "progress_pct": 17.63, "epoch_pct": 17.63, "eta": "44:36:30", "max_grad_norm": 1.0, "loss": 0.7410078048706055, "grad_norm": 0.5477433800697327, "learning_rate": 0.0001946519943536867}
+{"ts": "2025-12-24T00:01:36", "event": "train_log", "step": 2454, "epoch": 1.0586839266450916, "progress_pct": 17.64, "epoch_pct": 17.64, "eta": "44:35:07", "max_grad_norm": 1.0, "loss": 0.6646532416343689, "grad_norm": 0.37357097864151, "learning_rate": 0.00019463613893815762}
+{"ts": "2025-12-24T00:01:51", "event": "train_log", "step": 2456, "epoch": 1.059546925566343, "progress_pct": 17.66, "epoch_pct": 17.66, "eta": "44:33:38", "max_grad_norm": 1.0, "loss": 0.7773549556732178, "grad_norm": 0.438048779964447, "learning_rate": 0.00019462026070155028}
+{"ts": "2025-12-24T00:02:06", "event": "train_log", "step": 2458, "epoch": 1.0604099244875944, "progress_pct": 17.67, "epoch_pct": 17.67, "eta": "44:32:11", "max_grad_norm": 1.0, "loss": 0.8977773785591125, "grad_norm": 0.5114307999610901, "learning_rate": 0.0001946043596476936}
+{"ts": "2025-12-24T00:02:20", "event": "train_log", "step": 2460, "epoch": 1.0612729234088458, "progress_pct": 17.69, "epoch_pct": 17.69, "eta": "44:30:36", "max_grad_norm": 1.0, "loss": 0.8128405809402466, "grad_norm": 0.4340408146381378, "learning_rate": 0.0001945884357804221}
+{"ts": "2025-12-24T00:02:35", "event": "train_log", "step": 2462, "epoch": 1.062135922330097, "progress_pct": 17.7, "epoch_pct": 17.7, "eta": "44:29:09", "max_grad_norm": 1.0, "loss": 0.8096795678138733, "grad_norm": 0.4922826290130615, "learning_rate": 0.0001945724891035757}
+{"ts": "2025-12-24T00:02:50", "event": "train_log", "step": 2464, "epoch": 1.0629989212513484, "progress_pct": 17.72, "epoch_pct": 17.72, "eta": "44:27:40", "max_grad_norm": 1.0, "loss": 0.7965760231018066, "grad_norm": 0.47231894731521606, "learning_rate": 0.00019455651962099987}
+{"ts": "2025-12-24T00:03:05", "event": "train_log", "step": 2466, "epoch": 1.0638619201725998, "progress_pct": 17.73, "epoch_pct": 17.73, "eta": "44:26:14", "max_grad_norm": 1.0, "loss": 0.7136726975440979, "grad_norm": 0.4519463777542114, "learning_rate": 0.00019454052733654565}
+{"ts": "2025-12-24T00:03:20", "event": "train_log", "step": 2468, "epoch": 1.064724919093851, "progress_pct": 17.75, "epoch_pct": 17.75, "eta": "44:24:44", "max_grad_norm": 1.0, "loss": 0.8136170506477356, "grad_norm": 0.44883614778518677, "learning_rate": 0.0001945245122540694}
+{"ts": "2025-12-24T00:03:35", "event": "train_log", "step": 2470, "epoch": 1.0655879180151024, "progress_pct": 17.76, "epoch_pct": 17.76, "eta": "44:23:19", "max_grad_norm": 1.0, "loss": 0.7840399146080017, "grad_norm": 0.4224080741405487, "learning_rate": 0.00019450847437743317}
+{"ts": "2025-12-24T00:03:51", "event": "train_log", "step": 2472, "epoch": 1.0664509169363539, "progress_pct": 17.77, "epoch_pct": 17.77, "eta": "44:21:51", "max_grad_norm": 1.0, "loss": 0.8202947378158569, "grad_norm": 0.4979367256164551, "learning_rate": 0.00019449241371050438}
+{"ts": "2025-12-24T00:04:05", "event": "train_log", "step": 2474, "epoch": 1.0673139158576053, "progress_pct": 17.79, "epoch_pct": 17.79, "eta": "44:20:23", "max_grad_norm": 1.0, "loss": 0.8608070611953735, "grad_norm": 0.5551356673240662, "learning_rate": 0.000194476330257156}
+{"ts": "2025-12-24T00:04:21", "event": "train_log", "step": 2476, "epoch": 1.0681769147788565, "progress_pct": 17.8, "epoch_pct": 17.8, "eta": "44:19:00", "max_grad_norm": 1.0, "loss": 0.7202636003494263, "grad_norm": 0.3980900049209595, "learning_rate": 0.00019446022402126647}
+{"ts": "2025-12-24T00:04:35", "event": "train_log", "step": 2478, "epoch": 1.0690399137001079, "progress_pct": 17.82, "epoch_pct": 17.82, "eta": "44:17:28", "max_grad_norm": 1.0, "loss": 0.8301891684532166, "grad_norm": 0.5393417477607727, "learning_rate": 0.00019444409500671977}
+{"ts": "2025-12-24T00:04:51", "event": "train_log", "step": 2480, "epoch": 1.0699029126213593, "progress_pct": 17.83, "epoch_pct": 17.83, "eta": "44:16:05", "max_grad_norm": 1.0, "loss": 0.700567901134491, "grad_norm": 0.47717350721359253, "learning_rate": 0.0001944279432174053}
+{"ts": "2025-12-24T00:05:06", "event": "train_log", "step": 2482, "epoch": 1.0707659115426105, "progress_pct": 17.85, "epoch_pct": 17.85, "eta": "44:14:35", "max_grad_norm": 1.0, "loss": 0.794978141784668, "grad_norm": 0.5197957158088684, "learning_rate": 0.000194411768657218}
+{"ts": "2025-12-24T00:05:20", "event": "train_log", "step": 2484, "epoch": 1.0716289104638619, "progress_pct": 17.86, "epoch_pct": 17.86, "eta": "44:13:06", "max_grad_norm": 1.0, "loss": 0.8052116632461548, "grad_norm": 0.5289306044578552, "learning_rate": 0.0001943955713300583}
+{"ts": "2025-12-24T00:05:36", "event": "train_log", "step": 2486, "epoch": 1.0724919093851133, "progress_pct": 17.87, "epoch_pct": 17.87, "eta": "44:11:41", "max_grad_norm": 1.0, "loss": 0.750991702079773, "grad_norm": 0.4360409080982208, "learning_rate": 0.00019437935123983212}
+{"ts": "2025-12-24T00:05:52", "event": "train_log", "step": 2488, "epoch": 1.0733549083063647, "progress_pct": 17.89, "epoch_pct": 17.89, "eta": "44:10:20", "max_grad_norm": 1.0, "loss": 0.6631898880004883, "grad_norm": 0.38651731610298157, "learning_rate": 0.00019436310839045085}
+{"ts": "2025-12-24T00:06:08", "event": "train_log", "step": 2490, "epoch": 1.074217907227616, "progress_pct": 17.9, "epoch_pct": 17.9, "eta": "44:08:55", "max_grad_norm": 1.0, "loss": 0.7995471358299255, "grad_norm": 0.4376210868358612, "learning_rate": 0.00019434684278583138}
+{"ts": "2025-12-24T00:06:22", "event": "train_log", "step": 2492, "epoch": 1.0750809061488673, "progress_pct": 17.92, "epoch_pct": 17.92, "eta": "44:07:26", "max_grad_norm": 1.0, "loss": 0.7633864879608154, "grad_norm": 0.46636906266212463, "learning_rate": 0.0001943305544298961}
+{"ts": "2025-12-24T00:06:37", "event": "train_log", "step": 2494, "epoch": 1.0759439050701187, "progress_pct": 17.93, "epoch_pct": 17.93, "eta": "44:06:00", "max_grad_norm": 1.0, "loss": 0.7281562089920044, "grad_norm": 0.43499618768692017, "learning_rate": 0.00019431424332657288}
+{"ts": "2025-12-24T00:06:53", "event": "train_log", "step": 2496, "epoch": 1.07680690399137, "progress_pct": 17.95, "epoch_pct": 17.95, "eta": "44:04:38", "max_grad_norm": 1.0, "loss": 0.7313723564147949, "grad_norm": 0.39683374762535095, "learning_rate": 0.000194297909479795}
+{"ts": "2025-12-24T00:07:08", "event": "train_log", "step": 2498, "epoch": 1.0776699029126213, "progress_pct": 17.96, "epoch_pct": 17.96, "eta": "44:03:13", "max_grad_norm": 1.0, "loss": 0.7120141983032227, "grad_norm": 0.4545603096485138, "learning_rate": 0.0001942815528935014}
+{"ts": "2025-12-24T00:07:23", "event": "train_log", "step": 2500, "epoch": 1.0785329018338727, "progress_pct": 17.98, "epoch_pct": 17.98, "eta": "44:01:44", "max_grad_norm": 1.0, "loss": 0.752600908279419, "grad_norm": 0.5040699243545532, "learning_rate": 0.0001942651735716363}
+{"ts": "2025-12-24T00:18:15", "event": "train_log", "step": 2500, "epoch": 1.0785329018338727, "progress_pct": 17.98, "epoch_pct": 17.98, "eta": "44:51:21", "max_grad_norm": 1.0, "eval_loss": 0.8323014378547668, "eval_runtime": 652.3791, "eval_samples_per_second": 3.158, "eval_steps_per_second": 3.158}
+{"ts": "2025-12-24T00:18:30", "event": "train_log", "step": 2502, "epoch": 1.0793959007551241, "progress_pct": 17.99, "epoch_pct": 17.99, "eta": "44:49:53", "max_grad_norm": 1.0, "loss": 0.7719982266426086, "grad_norm": 0.48951438069343567, "learning_rate": 0.00019424877151814958}
+{"ts": "2025-12-24T00:18:44", "event": "train_log", "step": 2504, "epoch": 1.0802588996763753, "progress_pct": 18.0, "epoch_pct": 18.0, "eta": "44:48:20", "max_grad_norm": 1.0, "loss": 0.7921367883682251, "grad_norm": 0.5009822845458984, "learning_rate": 0.00019423234673699648}
+{"ts": "2025-12-24T00:18:59", "event": "train_log", "step": 2506, "epoch": 1.0811218985976268, "progress_pct": 18.02, "epoch_pct": 18.02, "eta": "44:46:50", "max_grad_norm": 1.0, "loss": 0.7714369297027588, "grad_norm": 0.4699440896511078, "learning_rate": 0.00019421589923213772}
+{"ts": "2025-12-24T00:19:14", "event": "train_log", "step": 2508, "epoch": 1.0819848975188782, "progress_pct": 18.03, "epoch_pct": 18.03, "eta": "44:45:20", "max_grad_norm": 1.0, "loss": 0.6981601119041443, "grad_norm": 0.4438663125038147, "learning_rate": 0.00019419942900753963}
+{"ts": "2025-12-24T00:19:29", "event": "train_log", "step": 2510, "epoch": 1.0828478964401294, "progress_pct": 18.05, "epoch_pct": 18.05, "eta": "44:43:51", "max_grad_norm": 1.0, "loss": 0.7822043895721436, "grad_norm": 0.49927031993865967, "learning_rate": 0.00019418293606717385}
+{"ts": "2025-12-24T00:19:43", "event": "train_log", "step": 2512, "epoch": 1.0837108953613808, "progress_pct": 18.06, "epoch_pct": 18.06, "eta": "44:42:22", "max_grad_norm": 1.0, "loss": 0.7166627049446106, "grad_norm": 0.395433634519577, "learning_rate": 0.00019416642041501767}
+{"ts": "2025-12-24T00:19:58", "event": "train_log", "step": 2514, "epoch": 1.0845738942826322, "progress_pct": 18.08, "epoch_pct": 18.08, "eta": "44:40:52", "max_grad_norm": 1.0, "loss": 0.7287489771842957, "grad_norm": 0.47293251752853394, "learning_rate": 0.00019414988205505366}
+{"ts": "2025-12-24T00:20:13", "event": "train_log", "step": 2516, "epoch": 1.0854368932038836, "progress_pct": 18.09, "epoch_pct": 18.09, "eta": "44:39:24", "max_grad_norm": 1.0, "loss": 0.7672322988510132, "grad_norm": 0.43168675899505615, "learning_rate": 0.00019413332099127008}
+{"ts": "2025-12-24T00:20:28", "event": "train_log", "step": 2518, "epoch": 1.0862998921251348, "progress_pct": 18.1, "epoch_pct": 18.1, "eta": "44:37:53", "max_grad_norm": 1.0, "loss": 0.7427115440368652, "grad_norm": 0.4542049765586853, "learning_rate": 0.00019411673722766044}
+{"ts": "2025-12-24T00:20:43", "event": "train_log", "step": 2520, "epoch": 1.0871628910463862, "progress_pct": 18.12, "epoch_pct": 18.12, "eta": "44:36:25", "max_grad_norm": 1.0, "loss": 0.742889404296875, "grad_norm": 0.4920838177204132, "learning_rate": 0.00019410013076822394}
+{"ts": "2025-12-24T00:20:57", "event": "train_log", "step": 2522, "epoch": 1.0880258899676376, "progress_pct": 18.13, "epoch_pct": 18.13, "eta": "44:34:55", "max_grad_norm": 1.0, "loss": 0.767113208770752, "grad_norm": 0.5404410362243652, "learning_rate": 0.0001940835016169651}
+{"ts": "2025-12-24T00:21:13", "event": "train_log", "step": 2524, "epoch": 1.0888888888888888, "progress_pct": 18.15, "epoch_pct": 18.15, "eta": "44:33:30", "max_grad_norm": 1.0, "loss": 0.6729961037635803, "grad_norm": 0.4543033540248871, "learning_rate": 0.00019406684977789395}
+{"ts": "2025-12-24T00:21:28", "event": "train_log", "step": 2526, "epoch": 1.0897518878101402, "progress_pct": 18.16, "epoch_pct": 18.16, "eta": "44:32:04", "max_grad_norm": 1.0, "loss": 0.6907814145088196, "grad_norm": 0.49171510338783264, "learning_rate": 0.00019405017525502607}
+{"ts": "2025-12-24T00:21:44", "event": "train_log", "step": 2528, "epoch": 1.0906148867313916, "progress_pct": 18.18, "epoch_pct": 18.18, "eta": "44:30:40", "max_grad_norm": 1.0, "loss": 0.7643960118293762, "grad_norm": 0.491252601146698, "learning_rate": 0.00019403347805238238}
+{"ts": "2025-12-24T00:21:59", "event": "train_log", "step": 2530, "epoch": 1.091477885652643, "progress_pct": 18.19, "epoch_pct": 18.19, "eta": "44:29:14", "max_grad_norm": 1.0, "loss": 0.8070526123046875, "grad_norm": 0.527920663356781, "learning_rate": 0.0001940167581739894}
+{"ts": "2025-12-24T00:22:14", "event": "train_log", "step": 2532, "epoch": 1.0923408845738942, "progress_pct": 18.21, "epoch_pct": 18.21, "eta": "44:27:47", "max_grad_norm": 1.0, "loss": 0.7900120615959167, "grad_norm": 0.4318726658821106, "learning_rate": 0.00019400001562387898}
+{"ts": "2025-12-24T00:22:29", "event": "train_log", "step": 2534, "epoch": 1.0932038834951456, "progress_pct": 18.22, "epoch_pct": 18.22, "eta": "44:26:18", "max_grad_norm": 1.0, "loss": 0.7778371572494507, "grad_norm": 0.4903397560119629, "learning_rate": 0.00019398325040608855}
+{"ts": "2025-12-24T00:22:44", "event": "train_log", "step": 2536, "epoch": 1.094066882416397, "progress_pct": 18.23, "epoch_pct": 18.23, "eta": "44:24:53", "max_grad_norm": 1.0, "loss": 0.7758864164352417, "grad_norm": 0.4835105240345001, "learning_rate": 0.00019396646252466097}
+{"ts": "2025-12-24T00:22:59", "event": "train_log", "step": 2538, "epoch": 1.0949298813376482, "progress_pct": 18.25, "epoch_pct": 18.25, "eta": "44:23:24", "max_grad_norm": 1.0, "loss": 0.7927643656730652, "grad_norm": 0.47125598788261414, "learning_rate": 0.00019394965198364455}
+{"ts": "2025-12-24T00:23:14", "event": "train_log", "step": 2540, "epoch": 1.0957928802588996, "progress_pct": 18.26, "epoch_pct": 18.26, "eta": "44:22:00", "max_grad_norm": 1.0, "loss": 0.7884714007377625, "grad_norm": 0.46723976731300354, "learning_rate": 0.0001939328187870931}
+{"ts": "2025-12-24T00:23:30", "event": "train_log", "step": 2542, "epoch": 1.096655879180151, "progress_pct": 18.28, "epoch_pct": 18.28, "eta": "44:20:38", "max_grad_norm": 1.0, "loss": 0.7663765549659729, "grad_norm": 0.46274980902671814, "learning_rate": 0.00019391596293906582}
+{"ts": "2025-12-24T00:23:47", "event": "train_log", "step": 2544, "epoch": 1.0975188781014025, "progress_pct": 18.29, "epoch_pct": 18.29, "eta": "44:19:20", "max_grad_norm": 1.0, "loss": 0.6656131744384766, "grad_norm": 0.431887149810791, "learning_rate": 0.00019389908444362747}
+{"ts": "2025-12-24T00:24:03", "event": "train_log", "step": 2546, "epoch": 1.0983818770226537, "progress_pct": 18.31, "epoch_pct": 18.31, "eta": "44:17:55", "max_grad_norm": 1.0, "loss": 0.795498788356781, "grad_norm": 0.5138527750968933, "learning_rate": 0.00019388218330484823}
+{"ts": "2025-12-24T00:24:17", "event": "train_log", "step": 2548, "epoch": 1.099244875943905, "progress_pct": 18.32, "epoch_pct": 18.32, "eta": "44:16:28", "max_grad_norm": 1.0, "loss": 0.807344377040863, "grad_norm": 0.4679732024669647, "learning_rate": 0.00019386525952680365}
+{"ts": "2025-12-24T00:24:33", "event": "train_log", "step": 2550, "epoch": 1.1001078748651565, "progress_pct": 18.33, "epoch_pct": 18.34, "eta": "44:15:04", "max_grad_norm": 1.0, "loss": 0.6828449368476868, "grad_norm": 0.473088800907135, "learning_rate": 0.0001938483131135749}
+{"ts": "2025-12-24T00:24:49", "event": "train_log", "step": 2552, "epoch": 1.1009708737864077, "progress_pct": 18.35, "epoch_pct": 18.35, "eta": "44:13:41", "max_grad_norm": 1.0, "loss": 0.8669595122337341, "grad_norm": 0.49941009283065796, "learning_rate": 0.00019383134406924856}
+{"ts": "2025-12-24T00:25:04", "event": "train_log", "step": 2554, "epoch": 1.101833872707659, "progress_pct": 18.36, "epoch_pct": 18.36, "eta": "44:12:16", "max_grad_norm": 1.0, "loss": 0.7382985949516296, "grad_norm": 0.47401952743530273, "learning_rate": 0.00019381435239791656}
+{"ts": "2025-12-24T00:25:19", "event": "train_log", "step": 2556, "epoch": 1.1026968716289105, "progress_pct": 18.38, "epoch_pct": 18.38, "eta": "44:10:52", "max_grad_norm": 1.0, "loss": 0.7240811586380005, "grad_norm": 0.47803637385368347, "learning_rate": 0.0001937973381036764}
+{"ts": "2025-12-24T00:25:34", "event": "train_log", "step": 2558, "epoch": 1.103559870550162, "progress_pct": 18.39, "epoch_pct": 18.39, "eta": "44:09:25", "max_grad_norm": 1.0, "loss": 0.736165463924408, "grad_norm": 0.4534960985183716, "learning_rate": 0.000193780301190631}
+{"ts": "2025-12-24T00:25:50", "event": "train_log", "step": 2560, "epoch": 1.104422869471413, "progress_pct": 18.41, "epoch_pct": 18.41, "eta": "44:08:03", "max_grad_norm": 1.0, "loss": 0.7364692091941833, "grad_norm": 0.4594196677207947, "learning_rate": 0.0001937632416628887}
+{"ts": "2025-12-24T00:26:05", "event": "train_log", "step": 2562, "epoch": 1.1052858683926645, "progress_pct": 18.42, "epoch_pct": 18.42, "eta": "44:06:37", "max_grad_norm": 1.0, "loss": 0.803584635257721, "grad_norm": 0.45354577898979187, "learning_rate": 0.0001937461595245634}
+{"ts": "2025-12-24T00:26:19", "event": "train_log", "step": 2564, "epoch": 1.106148867313916, "progress_pct": 18.44, "epoch_pct": 18.44, "eta": "44:05:07", "max_grad_norm": 1.0, "loss": 0.7224286794662476, "grad_norm": 0.47314611077308655, "learning_rate": 0.00019372905477977432}
+{"ts": "2025-12-24T00:26:35", "event": "train_log", "step": 2566, "epoch": 1.1070118662351671, "progress_pct": 18.45, "epoch_pct": 18.45, "eta": "44:03:46", "max_grad_norm": 1.0, "loss": 0.7446297407150269, "grad_norm": 0.4453343451023102, "learning_rate": 0.0001937119274326462}
+{"ts": "2025-12-24T00:26:50", "event": "train_log", "step": 2568, "epoch": 1.1078748651564185, "progress_pct": 18.46, "epoch_pct": 18.46, "eta": "44:02:20", "max_grad_norm": 1.0, "loss": 0.7666438817977905, "grad_norm": 0.5266496539115906, "learning_rate": 0.0001936947774873093}
+{"ts": "2025-12-24T00:27:05", "event": "train_log", "step": 2570, "epoch": 1.10873786407767, "progress_pct": 18.48, "epoch_pct": 18.48, "eta": "44:00:58", "max_grad_norm": 1.0, "loss": 0.8593260049819946, "grad_norm": 0.44142624735832214, "learning_rate": 0.00019367760494789913}
+{"ts": "2025-12-24T00:27:20", "event": "train_log", "step": 2572, "epoch": 1.1096008629989211, "progress_pct": 18.49, "epoch_pct": 18.49, "eta": "43:59:31", "max_grad_norm": 1.0, "loss": 0.7768570184707642, "grad_norm": 0.552436888217926, "learning_rate": 0.00019366040981855682}
+{"ts": "2025-12-24T00:27:35", "event": "train_log", "step": 2574, "epoch": 1.1104638619201725, "progress_pct": 18.51, "epoch_pct": 18.51, "eta": "43:58:09", "max_grad_norm": 1.0, "loss": 0.7356681823730469, "grad_norm": 0.4223164916038513, "learning_rate": 0.0001936431921034289}
+{"ts": "2025-12-24T00:27:50", "event": "train_log", "step": 2576, "epoch": 1.111326860841424, "progress_pct": 18.52, "epoch_pct": 18.52, "eta": "43:56:43", "max_grad_norm": 1.0, "loss": 0.7693892121315002, "grad_norm": 0.5104808211326599, "learning_rate": 0.0001936259518066674}
+{"ts": "2025-12-24T00:28:06", "event": "train_log", "step": 2578, "epoch": 1.1121898597626754, "progress_pct": 18.54, "epoch_pct": 18.54, "eta": "43:55:20", "max_grad_norm": 1.0, "loss": 0.7651313543319702, "grad_norm": 0.40713393688201904, "learning_rate": 0.00019360868893242967}
+{"ts": "2025-12-24T00:28:21", "event": "train_log", "step": 2580, "epoch": 1.1130528586839266, "progress_pct": 18.55, "epoch_pct": 18.55, "eta": "43:53:56", "max_grad_norm": 1.0, "loss": 0.8427110314369202, "grad_norm": 0.4819444417953491, "learning_rate": 0.00019359140348487858}
+{"ts": "2025-12-24T00:28:37", "event": "train_log", "step": 2582, "epoch": 1.113915857605178, "progress_pct": 18.56, "epoch_pct": 18.57, "eta": "43:52:37", "max_grad_norm": 1.0, "loss": 0.7783478498458862, "grad_norm": 0.45872536301612854, "learning_rate": 0.00019357409546818247}
+{"ts": "2025-12-24T00:28:53", "event": "train_log", "step": 2584, "epoch": 1.1147788565264294, "progress_pct": 18.58, "epoch_pct": 18.58, "eta": "43:51:18", "max_grad_norm": 1.0, "loss": 0.6625193357467651, "grad_norm": 0.43954113125801086, "learning_rate": 0.00019355676488651508}
+{"ts": "2025-12-24T00:29:09", "event": "train_log", "step": 2586, "epoch": 1.1156418554476808, "progress_pct": 18.59, "epoch_pct": 18.59, "eta": "43:49:56", "max_grad_norm": 1.0, "loss": 0.7208001613616943, "grad_norm": 0.4524446725845337, "learning_rate": 0.00019353941174405558}
+{"ts": "2025-12-24T00:29:24", "event": "train_log", "step": 2588, "epoch": 1.116504854368932, "progress_pct": 18.61, "epoch_pct": 18.61, "eta": "43:48:35", "max_grad_norm": 1.0, "loss": 0.7567161917686462, "grad_norm": 0.4748269021511078, "learning_rate": 0.0001935220360449886}
+{"ts": "2025-12-24T00:29:40", "event": "train_log", "step": 2590, "epoch": 1.1173678532901834, "progress_pct": 18.62, "epoch_pct": 18.62, "eta": "43:47:13", "max_grad_norm": 1.0, "loss": 0.7631603479385376, "grad_norm": 0.4493826925754547, "learning_rate": 0.00019350463779350423}
+{"ts": "2025-12-24T00:29:56", "event": "train_log", "step": 2592, "epoch": 1.1182308522114348, "progress_pct": 18.64, "epoch_pct": 18.64, "eta": "43:45:54", "max_grad_norm": 1.0, "loss": 0.7756917476654053, "grad_norm": 0.45398685336112976, "learning_rate": 0.00019348721699379798}
+{"ts": "2025-12-24T00:30:12", "event": "train_log", "step": 2594, "epoch": 1.119093851132686, "progress_pct": 18.65, "epoch_pct": 18.65, "eta": "43:44:34", "max_grad_norm": 1.0, "loss": 0.7516605854034424, "grad_norm": 0.4246262311935425, "learning_rate": 0.0001934697736500708}
+{"ts": "2025-12-24T00:30:28", "event": "train_log", "step": 2596, "epoch": 1.1199568500539374, "progress_pct": 18.67, "epoch_pct": 18.67, "eta": "43:43:16", "max_grad_norm": 1.0, "loss": 0.7058185338973999, "grad_norm": 0.44801613688468933, "learning_rate": 0.00019345230776652908}
+{"ts": "2025-12-24T00:30:42", "event": "train_log", "step": 2598, "epoch": 1.1208198489751888, "progress_pct": 18.68, "epoch_pct": 18.68, "eta": "43:41:48", "max_grad_norm": 1.0, "loss": 0.8071328997612, "grad_norm": 0.4591200649738312, "learning_rate": 0.00019343481934738462}
+{"ts": "2025-12-24T00:31:00", "event": "train_log", "step": 2600, "epoch": 1.12168284789644, "progress_pct": 18.69, "epoch_pct": 18.69, "eta": "43:40:35", "max_grad_norm": 1.0, "loss": 0.6992195844650269, "grad_norm": 0.39467594027519226, "learning_rate": 0.0001934173083968547}
+{"ts": "2025-12-24T00:41:59", "event": "train_log", "step": 2600, "epoch": 1.12168284789644, "progress_pct": 18.69, "epoch_pct": 18.69, "eta": "44:28:21", "max_grad_norm": 1.0, "eval_loss": 0.8300262093544006, "eval_runtime": 658.9488, "eval_samples_per_second": 3.126, "eval_steps_per_second": 3.126}
+{"ts": "2025-12-24T00:42:14", "event": "train_log", "step": 2602, "epoch": 1.1225458468176914, "progress_pct": 18.71, "epoch_pct": 18.71, "eta": "44:26:55", "max_grad_norm": 1.0, "loss": 0.7683232426643372, "grad_norm": 0.40905407071113586, "learning_rate": 0.00019339977491916196}
+{"ts": "2025-12-24T00:42:29", "event": "train_log", "step": 2604, "epoch": 1.1234088457389428, "progress_pct": 18.72, "epoch_pct": 18.72, "eta": "44:25:31", "max_grad_norm": 1.0, "loss": 0.7048685550689697, "grad_norm": 0.42742034792900085, "learning_rate": 0.00019338221891853453}
+{"ts": "2025-12-24T00:42:44", "event": "train_log", "step": 2606, "epoch": 1.1242718446601943, "progress_pct": 18.74, "epoch_pct": 18.74, "eta": "44:24:03", "max_grad_norm": 1.0, "loss": 0.7206799983978271, "grad_norm": 0.4435581564903259, "learning_rate": 0.000193364640399206}
+{"ts": "2025-12-24T00:42:58", "event": "train_log", "step": 2608, "epoch": 1.1251348435814454, "progress_pct": 18.75, "epoch_pct": 18.75, "eta": "44:22:34", "max_grad_norm": 1.0, "loss": 0.8230411410331726, "grad_norm": 0.48409897089004517, "learning_rate": 0.00019334703936541535}
+{"ts": "2025-12-24T00:43:13", "event": "train_log", "step": 2610, "epoch": 1.1259978425026969, "progress_pct": 18.77, "epoch_pct": 18.77, "eta": "44:21:06", "max_grad_norm": 1.0, "loss": 0.7833203077316284, "grad_norm": 0.5060800909996033, "learning_rate": 0.00019332941582140693}
+{"ts": "2025-12-24T00:43:27", "event": "train_log", "step": 2612, "epoch": 1.1268608414239483, "progress_pct": 18.78, "epoch_pct": 18.78, "eta": "44:19:38", "max_grad_norm": 1.0, "loss": 0.7785601615905762, "grad_norm": 0.48900339007377625, "learning_rate": 0.00019331176977143062}
+{"ts": "2025-12-24T00:43:41", "event": "train_log", "step": 2614, "epoch": 1.1277238403451997, "progress_pct": 18.79, "epoch_pct": 18.8, "eta": "44:18:09", "max_grad_norm": 1.0, "loss": 0.800255537033081, "grad_norm": 0.46176961064338684, "learning_rate": 0.0001932941012197417}
+{"ts": "2025-12-24T00:43:55", "event": "train_log", "step": 2616, "epoch": 1.1285868392664509, "progress_pct": 18.81, "epoch_pct": 18.81, "eta": "44:16:38", "max_grad_norm": 1.0, "loss": 0.7647190690040588, "grad_norm": 0.4946233332157135, "learning_rate": 0.00019327641017060084}
+{"ts": "2025-12-24T00:44:10", "event": "train_log", "step": 2618, "epoch": 1.1294498381877023, "progress_pct": 18.82, "epoch_pct": 18.82, "eta": "44:15:14", "max_grad_norm": 1.0, "loss": 0.7271775007247925, "grad_norm": 0.4153730571269989, "learning_rate": 0.00019325869662827416}
+{"ts": "2025-12-24T00:44:25", "event": "train_log", "step": 2620, "epoch": 1.1303128371089537, "progress_pct": 18.84, "epoch_pct": 18.84, "eta": "44:13:47", "max_grad_norm": 1.0, "loss": 0.7926952838897705, "grad_norm": 0.46707460284233093, "learning_rate": 0.0001932409605970332}
+{"ts": "2025-12-24T00:44:40", "event": "train_log", "step": 2622, "epoch": 1.1311758360302049, "progress_pct": 18.85, "epoch_pct": 18.85, "eta": "44:12:21", "max_grad_norm": 1.0, "loss": 0.8106555938720703, "grad_norm": 0.4980720579624176, "learning_rate": 0.00019322320208115489}
+{"ts": "2025-12-24T00:44:55", "event": "train_log", "step": 2624, "epoch": 1.1320388349514563, "progress_pct": 18.87, "epoch_pct": 18.87, "eta": "44:10:56", "max_grad_norm": 1.0, "loss": 0.7208700776100159, "grad_norm": 0.4300958514213562, "learning_rate": 0.0001932054210849217}
+{"ts": "2025-12-24T00:45:09", "event": "train_log", "step": 2626, "epoch": 1.1329018338727077, "progress_pct": 18.88, "epoch_pct": 18.88, "eta": "44:09:28", "max_grad_norm": 1.0, "loss": 0.7212259769439697, "grad_norm": 0.4756612479686737, "learning_rate": 0.00019318761761262136}
+{"ts": "2025-12-24T00:45:24", "event": "train_log", "step": 2628, "epoch": 1.133764832793959, "progress_pct": 18.9, "epoch_pct": 18.9, "eta": "44:08:03", "max_grad_norm": 1.0, "loss": 0.6725794672966003, "grad_norm": 0.4502181112766266, "learning_rate": 0.00019316979166854713}
+{"ts": "2025-12-24T00:45:39", "event": "train_log", "step": 2630, "epoch": 1.1346278317152103, "progress_pct": 18.91, "epoch_pct": 18.91, "eta": "44:06:39", "max_grad_norm": 1.0, "loss": 0.7582959532737732, "grad_norm": 0.4845540523529053, "learning_rate": 0.00019315194325699765}
+{"ts": "2025-12-24T00:45:54", "event": "train_log", "step": 2632, "epoch": 1.1354908306364617, "progress_pct": 18.92, "epoch_pct": 18.92, "eta": "44:05:14", "max_grad_norm": 1.0, "loss": 0.7707560062408447, "grad_norm": 0.45892953872680664, "learning_rate": 0.00019313407238227698}
+{"ts": "2025-12-24T00:46:08", "event": "train_log", "step": 2634, "epoch": 1.1363538295577131, "progress_pct": 18.94, "epoch_pct": 18.94, "eta": "44:03:44", "max_grad_norm": 1.0, "loss": 0.7824680209159851, "grad_norm": 0.4707877039909363, "learning_rate": 0.00019311617904869464}
+{"ts": "2025-12-24T00:46:22", "event": "train_log", "step": 2636, "epoch": 1.1372168284789643, "progress_pct": 18.95, "epoch_pct": 18.95, "eta": "44:02:18", "max_grad_norm": 1.0, "loss": 0.7750257253646851, "grad_norm": 0.5212311744689941, "learning_rate": 0.00019309826326056545}
+{"ts": "2025-12-24T00:46:37", "event": "train_log", "step": 2638, "epoch": 1.1380798274002157, "progress_pct": 18.97, "epoch_pct": 18.97, "eta": "44:00:51", "max_grad_norm": 1.0, "loss": 0.7691953182220459, "grad_norm": 0.4952082633972168, "learning_rate": 0.0001930803250222098}
+{"ts": "2025-12-24T00:46:51", "event": "train_log", "step": 2640, "epoch": 1.1389428263214671, "progress_pct": 18.98, "epoch_pct": 18.98, "eta": "43:59:23", "max_grad_norm": 1.0, "loss": 0.737209141254425, "grad_norm": 0.4428424835205078, "learning_rate": 0.00019306236433795334}
+{"ts": "2025-12-24T00:47:05", "event": "train_log", "step": 2642, "epoch": 1.1398058252427186, "progress_pct": 19.0, "epoch_pct": 19.0, "eta": "43:57:56", "max_grad_norm": 1.0, "loss": 0.7487695813179016, "grad_norm": 0.5063129663467407, "learning_rate": 0.00019304438121212728}
+{"ts": "2025-12-24T00:47:19", "event": "train_log", "step": 2644, "epoch": 1.1406688241639698, "progress_pct": 19.01, "epoch_pct": 19.01, "eta": "43:56:30", "max_grad_norm": 1.0, "loss": 0.7647218704223633, "grad_norm": 0.4571828246116638, "learning_rate": 0.00019302637564906814}
+{"ts": "2025-12-24T00:47:34", "event": "train_log", "step": 2646, "epoch": 1.1415318230852212, "progress_pct": 19.03, "epoch_pct": 19.03, "eta": "43:55:03", "max_grad_norm": 1.0, "loss": 0.8173171877861023, "grad_norm": 0.4918457567691803, "learning_rate": 0.00019300834765311785}
+{"ts": "2025-12-24T00:47:49", "event": "train_log", "step": 2648, "epoch": 1.1423948220064726, "progress_pct": 19.04, "epoch_pct": 19.04, "eta": "43:53:43", "max_grad_norm": 1.0, "loss": 0.6472562551498413, "grad_norm": 0.40057408809661865, "learning_rate": 0.0001929902972286238}
+{"ts": "2025-12-24T00:48:04", "event": "train_log", "step": 2650, "epoch": 1.1432578209277238, "progress_pct": 19.05, "epoch_pct": 19.05, "eta": "43:52:17", "max_grad_norm": 1.0, "loss": 0.8462889194488525, "grad_norm": 0.432763934135437, "learning_rate": 0.0001929722243799388}
+{"ts": "2025-12-24T00:48:20", "event": "train_log", "step": 2652, "epoch": 1.1441208198489752, "progress_pct": 19.07, "epoch_pct": 19.07, "eta": "43:50:56", "max_grad_norm": 1.0, "loss": 0.808388352394104, "grad_norm": 0.36540713906288147, "learning_rate": 0.000192954129111421}
+{"ts": "2025-12-24T00:48:34", "event": "train_log", "step": 2654, "epoch": 1.1449838187702266, "progress_pct": 19.08, "epoch_pct": 19.08, "eta": "43:49:32", "max_grad_norm": 1.0, "loss": 0.7144365906715393, "grad_norm": 0.4236038029193878, "learning_rate": 0.00019293601142743403}
+{"ts": "2025-12-24T00:48:49", "event": "train_log", "step": 2656, "epoch": 1.1458468176914778, "progress_pct": 19.1, "epoch_pct": 19.1, "eta": "43:48:07", "max_grad_norm": 1.0, "loss": 0.693168580532074, "grad_norm": 0.4316163957118988, "learning_rate": 0.00019291787133234682}
+{"ts": "2025-12-24T00:49:03", "event": "train_log", "step": 2658, "epoch": 1.1467098166127292, "progress_pct": 19.11, "epoch_pct": 19.11, "eta": "43:46:42", "max_grad_norm": 1.0, "loss": 0.7981953024864197, "grad_norm": 0.43088117241859436, "learning_rate": 0.00019289970883053386}
+{"ts": "2025-12-24T00:49:19", "event": "train_log", "step": 2660, "epoch": 1.1475728155339806, "progress_pct": 19.13, "epoch_pct": 19.13, "eta": "43:45:21", "max_grad_norm": 1.0, "loss": 0.7342561483383179, "grad_norm": 0.4200972318649292, "learning_rate": 0.00019288152392637486}
+{"ts": "2025-12-24T00:49:34", "event": "train_log", "step": 2662, "epoch": 1.148435814455232, "progress_pct": 19.14, "epoch_pct": 19.14, "eta": "43:43:59", "max_grad_norm": 1.0, "loss": 0.7239733934402466, "grad_norm": 0.4461527466773987, "learning_rate": 0.00019286331662425512}
+{"ts": "2025-12-24T00:49:49", "event": "train_log", "step": 2664, "epoch": 1.1492988133764832, "progress_pct": 19.15, "epoch_pct": 19.15, "eta": "43:42:36", "max_grad_norm": 1.0, "loss": 0.6575030088424683, "grad_norm": 0.3945358097553253, "learning_rate": 0.00019284508692856518}
+{"ts": "2025-12-24T00:50:03", "event": "train_log", "step": 2666, "epoch": 1.1501618122977346, "progress_pct": 19.17, "epoch_pct": 19.17, "eta": "43:41:06", "max_grad_norm": 1.0, "loss": 0.7754159569740295, "grad_norm": 0.4653085470199585, "learning_rate": 0.0001928268348437011}
+{"ts": "2025-12-24T00:50:18", "event": "train_log", "step": 2668, "epoch": 1.151024811218986, "progress_pct": 19.18, "epoch_pct": 19.18, "eta": "43:39:45", "max_grad_norm": 1.0, "loss": 0.683927595615387, "grad_norm": 0.47542640566825867, "learning_rate": 0.00019280856037406422}
+{"ts": "2025-12-24T00:50:33", "event": "train_log", "step": 2670, "epoch": 1.1518878101402374, "progress_pct": 19.2, "epoch_pct": 19.2, "eta": "43:38:24", "max_grad_norm": 1.0, "loss": 0.6907603144645691, "grad_norm": 0.4191996455192566, "learning_rate": 0.00019279026352406143}
+{"ts": "2025-12-24T00:50:49", "event": "train_log", "step": 2672, "epoch": 1.1527508090614886, "progress_pct": 19.21, "epoch_pct": 19.21, "eta": "43:37:05", "max_grad_norm": 1.0, "loss": 0.8362683653831482, "grad_norm": 0.4643108546733856, "learning_rate": 0.00019277194429810488}
+{"ts": "2025-12-24T00:51:04", "event": "train_log", "step": 2674, "epoch": 1.15361380798274, "progress_pct": 19.23, "epoch_pct": 19.23, "eta": "43:35:44", "max_grad_norm": 1.0, "loss": 0.737736701965332, "grad_norm": 0.4213605225086212, "learning_rate": 0.00019275360270061217}
+{"ts": "2025-12-24T00:51:20", "event": "train_log", "step": 2676, "epoch": 1.1544768069039915, "progress_pct": 19.24, "epoch_pct": 19.24, "eta": "43:34:24", "max_grad_norm": 1.0, "loss": 0.7617850303649902, "grad_norm": 0.537070095539093, "learning_rate": 0.0001927352387360063}
+{"ts": "2025-12-24T00:51:35", "event": "train_log", "step": 2678, "epoch": 1.1553398058252426, "progress_pct": 19.26, "epoch_pct": 19.26, "eta": "43:33:03", "max_grad_norm": 1.0, "loss": 0.7252766489982605, "grad_norm": 0.47798195481300354, "learning_rate": 0.0001927168524087157}
+{"ts": "2025-12-24T00:51:51", "event": "train_log", "step": 2680, "epoch": 1.156202804746494, "progress_pct": 19.27, "epoch_pct": 19.27, "eta": "43:31:46", "max_grad_norm": 1.0, "loss": 0.7671495676040649, "grad_norm": 0.48654067516326904, "learning_rate": 0.00019269844372317408}
+{"ts": "2025-12-24T00:52:06", "event": "train_log", "step": 2682, "epoch": 1.1570658036677455, "progress_pct": 19.28, "epoch_pct": 19.28, "eta": "43:30:23", "max_grad_norm": 1.0, "loss": 0.8648670315742493, "grad_norm": 0.5374535322189331, "learning_rate": 0.00019268001268382066}
+{"ts": "2025-12-24T00:52:23", "event": "train_log", "step": 2684, "epoch": 1.1579288025889967, "progress_pct": 19.3, "epoch_pct": 19.3, "eta": "43:29:09", "max_grad_norm": 1.0, "loss": 0.6848083138465881, "grad_norm": 0.42167672514915466, "learning_rate": 0.00019266155929509996}
+{"ts": "2025-12-24T00:52:39", "event": "train_log", "step": 2686, "epoch": 1.158791801510248, "progress_pct": 19.31, "epoch_pct": 19.31, "eta": "43:27:52", "max_grad_norm": 1.0, "loss": 0.6890886425971985, "grad_norm": 0.38867753744125366, "learning_rate": 0.00019264308356146197}
+{"ts": "2025-12-24T00:52:56", "event": "train_log", "step": 2688, "epoch": 1.1596548004314995, "progress_pct": 19.33, "epoch_pct": 19.33, "eta": "43:26:39", "max_grad_norm": 1.0, "loss": 0.7399795651435852, "grad_norm": 0.42711013555526733, "learning_rate": 0.000192624585487362}
+{"ts": "2025-12-24T00:53:12", "event": "train_log", "step": 2690, "epoch": 1.160517799352751, "progress_pct": 19.34, "epoch_pct": 19.34, "eta": "43:25:19", "max_grad_norm": 1.0, "loss": 0.8026465773582458, "grad_norm": 0.48802322149276733, "learning_rate": 0.00019260606507726083}
+{"ts": "2025-12-24T00:53:26", "event": "train_log", "step": 2692, "epoch": 1.161380798274002, "progress_pct": 19.36, "epoch_pct": 19.36, "eta": "43:23:54", "max_grad_norm": 1.0, "loss": 0.7589768171310425, "grad_norm": 0.47166478633880615, "learning_rate": 0.00019258752233562452}
+{"ts": "2025-12-24T00:53:41", "event": "train_log", "step": 2694, "epoch": 1.1622437971952535, "progress_pct": 19.37, "epoch_pct": 19.37, "eta": "43:22:32", "max_grad_norm": 1.0, "loss": 0.7620571851730347, "grad_norm": 0.47413256764411926, "learning_rate": 0.00019256895726692459}
+{"ts": "2025-12-24T00:53:55", "event": "train_log", "step": 2696, "epoch": 1.163106796116505, "progress_pct": 19.38, "epoch_pct": 19.39, "eta": "43:21:09", "max_grad_norm": 1.0, "loss": 0.798933207988739, "grad_norm": 0.5377517342567444, "learning_rate": 0.0001925503698756379}
+{"ts": "2025-12-24T00:54:11", "event": "train_log", "step": 2698, "epoch": 1.1639697950377563, "progress_pct": 19.4, "epoch_pct": 19.4, "eta": "43:19:50", "max_grad_norm": 1.0, "loss": 0.7550637125968933, "grad_norm": 0.44990095496177673, "learning_rate": 0.00019253176016624678}
+{"ts": "2025-12-24T00:54:26", "event": "train_log", "step": 2700, "epoch": 1.1648327939590075, "progress_pct": 19.41, "epoch_pct": 19.41, "eta": "43:18:32", "max_grad_norm": 1.0, "loss": 0.7919567227363586, "grad_norm": 0.4633009433746338, "learning_rate": 0.00019251312814323876}
+{"ts": "2025-12-24T01:05:34", "event": "train_log", "step": 2700, "epoch": 1.1648327939590075, "progress_pct": 19.41, "epoch_pct": 19.41, "eta": "44:04:41", "max_grad_norm": 1.0, "eval_loss": 0.8251468539237976, "eval_runtime": 667.0436, "eval_samples_per_second": 3.088, "eval_steps_per_second": 3.088}
+{"ts": "2025-12-24T01:05:48", "event": "train_log", "step": 2702, "epoch": 1.165695792880259, "progress_pct": 19.43, "epoch_pct": 19.43, "eta": "44:03:16", "max_grad_norm": 1.0, "loss": 0.8140546083450317, "grad_norm": 0.4339669942855835, "learning_rate": 0.000192494473811107}
+{"ts": "2025-12-24T01:06:02", "event": "train_log", "step": 2704, "epoch": 1.1665587918015103, "progress_pct": 19.44, "epoch_pct": 19.44, "eta": "44:01:50", "max_grad_norm": 1.0, "loss": 0.8462281823158264, "grad_norm": 0.5794349312782288, "learning_rate": 0.00019247579717434984}
+{"ts": "2025-12-24T01:06:19", "event": "train_log", "step": 2706, "epoch": 1.1674217907227615, "progress_pct": 19.46, "epoch_pct": 19.46, "eta": "44:00:33", "max_grad_norm": 1.0, "loss": 0.7468760013580322, "grad_norm": 0.41820067167282104, "learning_rate": 0.00019245709823747102}
+{"ts": "2025-12-24T01:06:35", "event": "train_log", "step": 2708, "epoch": 1.168284789644013, "progress_pct": 19.47, "epoch_pct": 19.47, "eta": "43:59:12", "max_grad_norm": 1.0, "loss": 0.694807767868042, "grad_norm": 0.4002464711666107, "learning_rate": 0.0001924383770049798}
+{"ts": "2025-12-24T01:06:49", "event": "train_log", "step": 2710, "epoch": 1.1691477885652644, "progress_pct": 19.49, "epoch_pct": 19.49, "eta": "43:57:48", "max_grad_norm": 1.0, "loss": 0.7512534856796265, "grad_norm": 0.47752025723457336, "learning_rate": 0.00019241963348139068}
+{"ts": "2025-12-24T01:07:04", "event": "train_log", "step": 2712, "epoch": 1.1700107874865155, "progress_pct": 19.5, "epoch_pct": 19.5, "eta": "43:56:22", "max_grad_norm": 1.0, "loss": 0.8069711923599243, "grad_norm": 0.45852312445640564, "learning_rate": 0.0001924008676712236}
+{"ts": "2025-12-24T01:07:19", "event": "train_log", "step": 2714, "epoch": 1.170873786407767, "progress_pct": 19.51, "epoch_pct": 19.51, "eta": "43:55:00", "max_grad_norm": 1.0, "loss": 0.7022751569747925, "grad_norm": 0.4336509108543396, "learning_rate": 0.0001923820795790038}
+{"ts": "2025-12-24T01:07:35", "event": "train_log", "step": 2716, "epoch": 1.1717367853290184, "progress_pct": 19.53, "epoch_pct": 19.53, "eta": "43:53:40", "max_grad_norm": 1.0, "loss": 0.6904252767562866, "grad_norm": 0.40044888854026794, "learning_rate": 0.00019236326920926193}
+{"ts": "2025-12-24T01:07:49", "event": "train_log", "step": 2718, "epoch": 1.1725997842502698, "progress_pct": 19.54, "epoch_pct": 19.54, "eta": "43:52:14", "max_grad_norm": 1.0, "loss": 0.7924585938453674, "grad_norm": 0.48451852798461914, "learning_rate": 0.00019234443656653412}
+{"ts": "2025-12-24T01:08:04", "event": "train_log", "step": 2720, "epoch": 1.173462783171521, "progress_pct": 19.56, "epoch_pct": 19.56, "eta": "43:50:54", "max_grad_norm": 1.0, "loss": 0.7383922338485718, "grad_norm": 0.49168315529823303, "learning_rate": 0.0001923255816553617}
+{"ts": "2025-12-24T01:08:20", "event": "train_log", "step": 2722, "epoch": 1.1743257820927724, "progress_pct": 19.57, "epoch_pct": 19.57, "eta": "43:49:32", "max_grad_norm": 1.0, "loss": 0.7508589029312134, "grad_norm": 0.4363260269165039, "learning_rate": 0.00019230670448029148}
+{"ts": "2025-12-24T01:08:35", "event": "train_log", "step": 2724, "epoch": 1.1751887810140238, "progress_pct": 19.59, "epoch_pct": 19.59, "eta": "43:48:11", "max_grad_norm": 1.0, "loss": 0.7814584970474243, "grad_norm": 0.4520082175731659, "learning_rate": 0.0001922878050458756}
+{"ts": "2025-12-24T01:08:49", "event": "train_log", "step": 2726, "epoch": 1.176051779935275, "progress_pct": 19.6, "epoch_pct": 19.6, "eta": "43:46:44", "max_grad_norm": 1.0, "loss": 0.7011970281600952, "grad_norm": 0.4675535559654236, "learning_rate": 0.00019226888335667158}
+{"ts": "2025-12-24T01:09:04", "event": "train_log", "step": 2728, "epoch": 1.1769147788565264, "progress_pct": 19.61, "epoch_pct": 19.62, "eta": "43:45:21", "max_grad_norm": 1.0, "loss": 0.7414659857749939, "grad_norm": 0.47536277770996094, "learning_rate": 0.00019224993941724226}
+{"ts": "2025-12-24T01:09:18", "event": "train_log", "step": 2730, "epoch": 1.1777777777777778, "progress_pct": 19.63, "epoch_pct": 19.63, "eta": "43:43:55", "max_grad_norm": 1.0, "loss": 0.7949363589286804, "grad_norm": 0.5455507040023804, "learning_rate": 0.00019223097323215594}
+{"ts": "2025-12-24T01:09:32", "event": "train_log", "step": 2732, "epoch": 1.1786407766990292, "progress_pct": 19.64, "epoch_pct": 19.64, "eta": "43:42:29", "max_grad_norm": 1.0, "loss": 0.813949465751648, "grad_norm": 0.4897938370704651, "learning_rate": 0.00019221198480598616}
+{"ts": "2025-12-24T01:09:46", "event": "train_log", "step": 2734, "epoch": 1.1795037756202804, "progress_pct": 19.66, "epoch_pct": 19.66, "eta": "43:41:05", "max_grad_norm": 1.0, "loss": 0.7444795966148376, "grad_norm": 0.46766766905784607, "learning_rate": 0.000192192974143312}
+{"ts": "2025-12-24T01:10:01", "event": "train_log", "step": 2736, "epoch": 1.1803667745415318, "progress_pct": 19.67, "epoch_pct": 19.67, "eta": "43:39:42", "max_grad_norm": 1.0, "loss": 0.7937621474266052, "grad_norm": 0.41503575444221497, "learning_rate": 0.00019217394124871768}
+{"ts": "2025-12-24T01:10:16", "event": "train_log", "step": 2738, "epoch": 1.1812297734627832, "progress_pct": 19.69, "epoch_pct": 19.69, "eta": "43:38:21", "max_grad_norm": 1.0, "loss": 0.7342435717582703, "grad_norm": 0.41906169056892395, "learning_rate": 0.00019215488612679295}
+{"ts": "2025-12-24T01:10:31", "event": "train_log", "step": 2740, "epoch": 1.1820927723840344, "progress_pct": 19.7, "epoch_pct": 19.7, "eta": "43:36:59", "max_grad_norm": 1.0, "loss": 0.7533642053604126, "grad_norm": 0.47820931673049927, "learning_rate": 0.00019213580878213292}
+{"ts": "2025-12-24T01:10:46", "event": "train_log", "step": 2742, "epoch": 1.1829557713052858, "progress_pct": 19.72, "epoch_pct": 19.72, "eta": "43:35:37", "max_grad_norm": 1.0, "loss": 0.799866795539856, "grad_norm": 0.44907891750335693, "learning_rate": 0.00019211670921933792}
+{"ts": "2025-12-24T01:11:01", "event": "train_log", "step": 2744, "epoch": 1.1838187702265373, "progress_pct": 19.73, "epoch_pct": 19.73, "eta": "43:34:15", "max_grad_norm": 1.0, "loss": 0.7468855381011963, "grad_norm": 0.48050498962402344, "learning_rate": 0.00019209758744301376}
+{"ts": "2025-12-24T01:11:16", "event": "train_log", "step": 2746, "epoch": 1.1846817691477884, "progress_pct": 19.74, "epoch_pct": 19.74, "eta": "43:32:53", "max_grad_norm": 1.0, "loss": 0.7423141002655029, "grad_norm": 0.4311312437057495, "learning_rate": 0.00019207844345777155}
+{"ts": "2025-12-24T01:11:30", "event": "train_log", "step": 2748, "epoch": 1.1855447680690399, "progress_pct": 19.76, "epoch_pct": 19.76, "eta": "43:31:31", "max_grad_norm": 1.0, "loss": 0.7046169638633728, "grad_norm": 0.439386248588562, "learning_rate": 0.0001920592772682278}
+{"ts": "2025-12-24T01:11:45", "event": "train_log", "step": 2750, "epoch": 1.1864077669902913, "progress_pct": 19.77, "epoch_pct": 19.77, "eta": "43:30:10", "max_grad_norm": 1.0, "loss": 0.7284982204437256, "grad_norm": 0.4230091869831085, "learning_rate": 0.00019204008887900435}
+{"ts": "2025-12-24T01:12:00", "event": "train_log", "step": 2752, "epoch": 1.1872707659115427, "progress_pct": 19.79, "epoch_pct": 19.79, "eta": "43:28:46", "max_grad_norm": 1.0, "loss": 0.7297943234443665, "grad_norm": 0.4583308696746826, "learning_rate": 0.0001920208782947284}
+{"ts": "2025-12-24T01:12:15", "event": "train_log", "step": 2754, "epoch": 1.1881337648327939, "progress_pct": 19.8, "epoch_pct": 19.8, "eta": "43:27:25", "max_grad_norm": 1.0, "loss": 0.7170902490615845, "grad_norm": 0.44526317715644836, "learning_rate": 0.00019200164552003247}
+{"ts": "2025-12-24T01:12:30", "event": "train_log", "step": 2756, "epoch": 1.1889967637540453, "progress_pct": 19.82, "epoch_pct": 19.82, "eta": "43:26:05", "max_grad_norm": 1.0, "loss": 0.7746089696884155, "grad_norm": 0.46664097905158997, "learning_rate": 0.00019198239055955444}
+{"ts": "2025-12-24T01:12:45", "event": "train_log", "step": 2758, "epoch": 1.1898597626752967, "progress_pct": 19.83, "epoch_pct": 19.83, "eta": "43:24:43", "max_grad_norm": 1.0, "loss": 0.7381687760353088, "grad_norm": 0.4023241102695465, "learning_rate": 0.0001919631134179376}
+{"ts": "2025-12-24T01:12:59", "event": "train_log", "step": 2760, "epoch": 1.190722761596548, "progress_pct": 19.84, "epoch_pct": 19.85, "eta": "43:23:19", "max_grad_norm": 1.0, "loss": 0.7951313853263855, "grad_norm": 0.5126422047615051, "learning_rate": 0.00019194381409983055}
+{"ts": "2025-12-24T01:13:14", "event": "train_log", "step": 2762, "epoch": 1.1915857605177993, "progress_pct": 19.86, "epoch_pct": 19.86, "eta": "43:21:58", "max_grad_norm": 1.0, "loss": 0.692834198474884, "grad_norm": 0.4056018590927124, "learning_rate": 0.0001919244926098872}
+{"ts": "2025-12-24T01:13:28", "event": "train_log", "step": 2764, "epoch": 1.1924487594390507, "progress_pct": 19.87, "epoch_pct": 19.87, "eta": "43:20:35", "max_grad_norm": 1.0, "loss": 0.7494171857833862, "grad_norm": 0.49225106835365295, "learning_rate": 0.00019190514895276687}
+{"ts": "2025-12-24T01:13:43", "event": "train_log", "step": 2766, "epoch": 1.1933117583603021, "progress_pct": 19.89, "epoch_pct": 19.89, "eta": "43:19:13", "max_grad_norm": 1.0, "loss": 0.8541221022605896, "grad_norm": 0.47823601961135864, "learning_rate": 0.00019188578313313417}
+{"ts": "2025-12-24T01:13:58", "event": "train_log", "step": 2768, "epoch": 1.1941747572815533, "progress_pct": 19.9, "epoch_pct": 19.9, "eta": "43:17:54", "max_grad_norm": 1.0, "loss": 0.8017639517784119, "grad_norm": 0.461773544549942, "learning_rate": 0.0001918663951556591}
+{"ts": "2025-12-24T01:14:13", "event": "train_log", "step": 2770, "epoch": 1.1950377562028047, "progress_pct": 19.92, "epoch_pct": 19.92, "eta": "43:16:34", "max_grad_norm": 1.0, "loss": 0.7509341835975647, "grad_norm": 0.48888009786605835, "learning_rate": 0.00019184698502501695}
+{"ts": "2025-12-24T01:14:28", "event": "train_log", "step": 2772, "epoch": 1.1959007551240561, "progress_pct": 19.93, "epoch_pct": 19.93, "eta": "43:15:14", "max_grad_norm": 1.0, "loss": 0.7123914361000061, "grad_norm": 0.4140535295009613, "learning_rate": 0.0001918275527458884}
+{"ts": "2025-12-24T01:14:43", "event": "train_log", "step": 2774, "epoch": 1.1967637540453073, "progress_pct": 19.95, "epoch_pct": 19.95, "eta": "43:13:53", "max_grad_norm": 1.0, "loss": 0.73713219165802, "grad_norm": 0.4918449819087982, "learning_rate": 0.00019180809832295952}
+{"ts": "2025-12-24T01:14:57", "event": "train_log", "step": 2776, "epoch": 1.1976267529665587, "progress_pct": 19.96, "epoch_pct": 19.96, "eta": "43:12:31", "max_grad_norm": 1.0, "loss": 0.708644688129425, "grad_norm": 0.48218831419944763, "learning_rate": 0.00019178862176092159}
+{"ts": "2025-12-24T01:15:12", "event": "train_log", "step": 2778, "epoch": 1.1984897518878102, "progress_pct": 19.97, "epoch_pct": 19.97, "eta": "43:11:11", "max_grad_norm": 1.0, "loss": 0.7277385592460632, "grad_norm": 0.45588797330856323, "learning_rate": 0.0001917691230644713}
+{"ts": "2025-12-24T01:15:27", "event": "train_log", "step": 2780, "epoch": 1.1993527508090616, "progress_pct": 19.99, "epoch_pct": 19.99, "eta": "43:09:51", "max_grad_norm": 1.0, "loss": 0.7501665949821472, "grad_norm": 0.3959250748157501, "learning_rate": 0.00019174960223831064}
+{"ts": "2025-12-24T01:15:41", "event": "train_log", "step": 2782, "epoch": 1.2002157497303128, "progress_pct": 20.0, "epoch_pct": 20.0, "eta": "43:08:26", "max_grad_norm": 1.0, "loss": 0.8842931389808655, "grad_norm": 0.6228574514389038, "learning_rate": 0.00019173005928714703}
+{"ts": "2025-12-24T01:15:56", "event": "train_log", "step": 2784, "epoch": 1.2010787486515642, "progress_pct": 20.02, "epoch_pct": 20.02, "eta": "43:07:05", "max_grad_norm": 1.0, "loss": 0.7008639574050903, "grad_norm": 0.4346935749053955, "learning_rate": 0.00019171049421569318}
+{"ts": "2025-12-24T01:16:10", "event": "train_log", "step": 2786, "epoch": 1.2019417475728156, "progress_pct": 20.03, "epoch_pct": 20.03, "eta": "43:05:44", "max_grad_norm": 1.0, "loss": 0.7203702330589294, "grad_norm": 0.691254198551178, "learning_rate": 0.00019169090702866705}
+{"ts": "2025-12-24T01:16:25", "event": "train_log", "step": 2788, "epoch": 1.202804746494067, "progress_pct": 20.05, "epoch_pct": 20.05, "eta": "43:04:25", "max_grad_norm": 1.0, "loss": 0.7170791029930115, "grad_norm": 0.4219740331172943, "learning_rate": 0.00019167129773079203}
+{"ts": "2025-12-24T01:16:40", "event": "train_log", "step": 2790, "epoch": 1.2036677454153182, "progress_pct": 20.06, "epoch_pct": 20.06, "eta": "43:03:05", "max_grad_norm": 1.0, "loss": 0.7895086407661438, "grad_norm": 0.4639855921268463, "learning_rate": 0.00019165166632679686}
+{"ts": "2025-12-24T01:16:54", "event": "train_log", "step": 2792, "epoch": 1.2045307443365696, "progress_pct": 20.07, "epoch_pct": 20.08, "eta": "43:01:44", "max_grad_norm": 1.0, "loss": 0.7323113679885864, "grad_norm": 0.44938549399375916, "learning_rate": 0.00019163201282141546}
+{"ts": "2025-12-24T01:17:09", "event": "train_log", "step": 2794, "epoch": 1.205393743257821, "progress_pct": 20.09, "epoch_pct": 20.09, "eta": "43:00:24", "max_grad_norm": 1.0, "loss": 0.7486892342567444, "grad_norm": 0.43633413314819336, "learning_rate": 0.00019161233721938728}
+{"ts": "2025-12-24T01:17:24", "event": "train_log", "step": 2796, "epoch": 1.2062567421790722, "progress_pct": 20.1, "epoch_pct": 20.1, "eta": "42:59:04", "max_grad_norm": 1.0, "loss": 0.777079701423645, "grad_norm": 0.42983385920524597, "learning_rate": 0.00019159263952545698}
+{"ts": "2025-12-24T01:17:38", "event": "train_log", "step": 2798, "epoch": 1.2071197411003236, "progress_pct": 20.12, "epoch_pct": 20.12, "eta": "42:57:42", "max_grad_norm": 1.0, "loss": 0.800602912902832, "grad_norm": 0.4630664587020874, "learning_rate": 0.00019157291974437456}
+{"ts": "2025-12-24T01:17:53", "event": "train_log", "step": 2800, "epoch": 1.207982740021575, "progress_pct": 20.13, "epoch_pct": 20.13, "eta": "42:56:22", "max_grad_norm": 1.0, "loss": 0.6763592958450317, "grad_norm": 0.43607378005981445, "learning_rate": 0.00019155317788089536}
+{"ts": "2025-12-24T01:28:55", "event": "train_log", "step": 2800, "epoch": 1.207982740021575, "progress_pct": 20.13, "epoch_pct": 20.13, "eta": "43:40:06", "max_grad_norm": 1.0, "eval_loss": 0.8219058513641357, "eval_runtime": 661.5144, "eval_samples_per_second": 3.114, "eval_steps_per_second": 3.114}
+{"ts": "2025-12-24T01:29:11", "event": "train_log", "step": 2802, "epoch": 1.2088457389428262, "progress_pct": 20.15, "epoch_pct": 20.15, "eta": "43:38:51", "max_grad_norm": 1.0, "loss": 0.7569329738616943, "grad_norm": 0.4910019338130951, "learning_rate": 0.00019153341393978002}
+{"ts": "2025-12-24T01:29:26", "event": "train_log", "step": 2804, "epoch": 1.2097087378640776, "progress_pct": 20.16, "epoch_pct": 20.16, "eta": "43:37:30", "max_grad_norm": 1.0, "loss": 0.734387218952179, "grad_norm": 0.4993135631084442, "learning_rate": 0.00019151362792579457}
+{"ts": "2025-12-24T01:29:42", "event": "train_log", "step": 2806, "epoch": 1.210571736785329, "progress_pct": 20.18, "epoch_pct": 20.18, "eta": "43:36:14", "max_grad_norm": 1.0, "loss": 0.719099223613739, "grad_norm": 0.48742055892944336, "learning_rate": 0.00019149381984371027}
+{"ts": "2025-12-24T01:29:58", "event": "train_log", "step": 2808, "epoch": 1.2114347357065804, "progress_pct": 20.19, "epoch_pct": 20.19, "eta": "43:34:55", "max_grad_norm": 1.0, "loss": 0.8490580320358276, "grad_norm": 0.4083765149116516, "learning_rate": 0.00019147398969830378}
+{"ts": "2025-12-24T01:30:14", "event": "train_log", "step": 2810, "epoch": 1.2122977346278316, "progress_pct": 20.2, "epoch_pct": 20.2, "eta": "43:33:41", "max_grad_norm": 1.0, "loss": 0.7604904770851135, "grad_norm": 0.4316021502017975, "learning_rate": 0.00019145413749435702}
+{"ts": "2025-12-24T01:30:30", "event": "train_log", "step": 2812, "epoch": 1.213160733549083, "progress_pct": 20.22, "epoch_pct": 20.22, "eta": "43:32:23", "max_grad_norm": 1.0, "loss": 0.7739580869674683, "grad_norm": 0.4294895529747009, "learning_rate": 0.0001914342632366573}
+{"ts": "2025-12-24T01:30:44", "event": "train_log", "step": 2814, "epoch": 1.2140237324703345, "progress_pct": 20.23, "epoch_pct": 20.23, "eta": "43:31:00", "max_grad_norm": 1.0, "loss": 0.7625397443771362, "grad_norm": 0.4773736000061035, "learning_rate": 0.00019141436692999718}
+{"ts": "2025-12-24T01:31:00", "event": "train_log", "step": 2816, "epoch": 1.2148867313915859, "progress_pct": 20.25, "epoch_pct": 20.25, "eta": "43:29:42", "max_grad_norm": 1.0, "loss": 0.7224686741828918, "grad_norm": 0.46148404479026794, "learning_rate": 0.00019139444857917457}
+{"ts": "2025-12-24T01:31:15", "event": "train_log", "step": 2818, "epoch": 1.215749730312837, "progress_pct": 20.26, "epoch_pct": 20.26, "eta": "43:28:21", "max_grad_norm": 1.0, "loss": 0.7708583474159241, "grad_norm": 0.436300128698349, "learning_rate": 0.0001913745081889927}
+{"ts": "2025-12-24T01:31:31", "event": "train_log", "step": 2820, "epoch": 1.2166127292340885, "progress_pct": 20.28, "epoch_pct": 20.28, "eta": "43:27:06", "max_grad_norm": 1.0, "loss": 0.8550406098365784, "grad_norm": 0.4959073066711426, "learning_rate": 0.0001913545457642601}
+{"ts": "2025-12-24T01:31:45", "event": "train_log", "step": 2822, "epoch": 1.2174757281553399, "progress_pct": 20.29, "epoch_pct": 20.29, "eta": "43:25:44", "max_grad_norm": 1.0, "loss": 0.781597912311554, "grad_norm": 0.4672411382198334, "learning_rate": 0.00019133456130979062}
+{"ts": "2025-12-24T01:32:00", "event": "train_log", "step": 2824, "epoch": 1.218338727076591, "progress_pct": 20.3, "epoch_pct": 20.31, "eta": "43:24:22", "max_grad_norm": 1.0, "loss": 0.860835075378418, "grad_norm": 0.5249256491661072, "learning_rate": 0.0001913145548304034}
+{"ts": "2025-12-24T01:32:16", "event": "train_log", "step": 2826, "epoch": 1.2192017259978425, "progress_pct": 20.32, "epoch_pct": 20.32, "eta": "43:23:06", "max_grad_norm": 1.0, "loss": 0.715717613697052, "grad_norm": 0.5132579207420349, "learning_rate": 0.00019129452633092294}
+{"ts": "2025-12-24T01:32:31", "event": "train_log", "step": 2828, "epoch": 1.220064724919094, "progress_pct": 20.33, "epoch_pct": 20.33, "eta": "43:21:47", "max_grad_norm": 1.0, "loss": 0.727998673915863, "grad_norm": 0.4291874170303345, "learning_rate": 0.00019127447581617903}
+{"ts": "2025-12-24T01:32:47", "event": "train_log", "step": 2830, "epoch": 1.220927723840345, "progress_pct": 20.35, "epoch_pct": 20.35, "eta": "43:20:31", "max_grad_norm": 1.0, "loss": 0.7164589762687683, "grad_norm": 0.3698529005050659, "learning_rate": 0.00019125440329100673}
+{"ts": "2025-12-24T01:33:02", "event": "train_log", "step": 2832, "epoch": 1.2217907227615965, "progress_pct": 20.36, "epoch_pct": 20.36, "eta": "43:19:11", "max_grad_norm": 1.0, "loss": 0.8113957643508911, "grad_norm": 0.5034273266792297, "learning_rate": 0.00019123430876024646}
+{"ts": "2025-12-24T01:33:18", "event": "train_log", "step": 2834, "epoch": 1.222653721682848, "progress_pct": 20.38, "epoch_pct": 20.38, "eta": "43:17:54", "max_grad_norm": 1.0, "loss": 0.7350133061408997, "grad_norm": 0.4612481892108917, "learning_rate": 0.0001912141922287439}
+{"ts": "2025-12-24T01:33:33", "event": "train_log", "step": 2836, "epoch": 1.2235167206040993, "progress_pct": 20.39, "epoch_pct": 20.39, "eta": "43:16:33", "max_grad_norm": 1.0, "loss": 0.8156216144561768, "grad_norm": 0.4433611035346985, "learning_rate": 0.00019119405370135012}
+{"ts": "2025-12-24T01:33:48", "event": "train_log", "step": 2838, "epoch": 1.2243797195253505, "progress_pct": 20.41, "epoch_pct": 20.41, "eta": "43:15:17", "max_grad_norm": 1.0, "loss": 0.7824334502220154, "grad_norm": 0.4700625240802765, "learning_rate": 0.00019117389318292136}
+{"ts": "2025-12-24T01:34:04", "event": "train_log", "step": 2840, "epoch": 1.225242718446602, "progress_pct": 20.42, "epoch_pct": 20.42, "eta": "43:13:58", "max_grad_norm": 1.0, "loss": 0.8136369585990906, "grad_norm": 0.4854332208633423, "learning_rate": 0.00019115371067831928}
+{"ts": "2025-12-24T01:34:19", "event": "train_log", "step": 2842, "epoch": 1.2261057173678533, "progress_pct": 20.43, "epoch_pct": 20.44, "eta": "43:12:40", "max_grad_norm": 1.0, "loss": 0.7042210102081299, "grad_norm": 0.4403935372829437, "learning_rate": 0.00019113350619241078}
+{"ts": "2025-12-24T01:34:35", "event": "train_log", "step": 2844, "epoch": 1.2269687162891048, "progress_pct": 20.45, "epoch_pct": 20.45, "eta": "43:11:25", "max_grad_norm": 1.0, "loss": 0.7598573565483093, "grad_norm": 0.4311469793319702, "learning_rate": 0.00019111327973006813}
+{"ts": "2025-12-24T01:34:48", "event": "train_log", "step": 2846, "epoch": 1.227831715210356, "progress_pct": 20.46, "epoch_pct": 20.46, "eta": "43:10:00", "max_grad_norm": 1.0, "loss": 0.8001043796539307, "grad_norm": 0.5551521182060242, "learning_rate": 0.0001910930312961688}
+{"ts": "2025-12-24T01:35:04", "event": "train_log", "step": 2848, "epoch": 1.2286947141316074, "progress_pct": 20.48, "epoch_pct": 20.48, "eta": "43:08:43", "max_grad_norm": 1.0, "loss": 0.6874746084213257, "grad_norm": 0.44149601459503174, "learning_rate": 0.0001910727608955956}
+{"ts": "2025-12-24T01:35:19", "event": "train_log", "step": 2850, "epoch": 1.2295577130528588, "progress_pct": 20.49, "epoch_pct": 20.49, "eta": "43:07:27", "max_grad_norm": 1.0, "loss": 0.7484437823295593, "grad_norm": 0.44726014137268066, "learning_rate": 0.00019105246853323672}
+{"ts": "2025-12-24T01:35:36", "event": "train_log", "step": 2852, "epoch": 1.23042071197411, "progress_pct": 20.51, "epoch_pct": 20.51, "eta": "43:06:12", "max_grad_norm": 1.0, "loss": 0.7512558102607727, "grad_norm": 0.4710492193698883, "learning_rate": 0.00019103215421398546}
+{"ts": "2025-12-24T01:35:52", "event": "train_log", "step": 2854, "epoch": 1.2312837108953614, "progress_pct": 20.52, "epoch_pct": 20.52, "eta": "43:04:58", "max_grad_norm": 1.0, "loss": 0.7161203622817993, "grad_norm": 0.4304901957511902, "learning_rate": 0.0001910118179427406}
+{"ts": "2025-12-24T01:36:07", "event": "train_log", "step": 2856, "epoch": 1.2321467098166128, "progress_pct": 20.53, "epoch_pct": 20.54, "eta": "43:03:41", "max_grad_norm": 1.0, "loss": 0.722236156463623, "grad_norm": 0.4651104509830475, "learning_rate": 0.00019099145972440614}
+{"ts": "2025-12-24T01:36:23", "event": "train_log", "step": 2858, "epoch": 1.233009708737864, "progress_pct": 20.55, "epoch_pct": 20.55, "eta": "43:02:27", "max_grad_norm": 1.0, "loss": 0.8200751543045044, "grad_norm": 0.5231161117553711, "learning_rate": 0.00019097107956389135}
+{"ts": "2025-12-24T01:36:39", "event": "train_log", "step": 2860, "epoch": 1.2338727076591154, "progress_pct": 20.56, "epoch_pct": 20.56, "eta": "43:01:11", "max_grad_norm": 1.0, "loss": 0.7529966235160828, "grad_norm": 0.45574283599853516, "learning_rate": 0.00019095067746611083}
+{"ts": "2025-12-24T01:36:54", "event": "train_log", "step": 2862, "epoch": 1.2347357065803668, "progress_pct": 20.58, "epoch_pct": 20.58, "eta": "42:59:52", "max_grad_norm": 1.0, "loss": 0.7574380040168762, "grad_norm": 0.4451949894428253, "learning_rate": 0.00019093025343598448}
+{"ts": "2025-12-24T01:37:09", "event": "train_log", "step": 2864, "epoch": 1.2355987055016182, "progress_pct": 20.59, "epoch_pct": 20.59, "eta": "42:58:33", "max_grad_norm": 1.0, "loss": 0.8461237549781799, "grad_norm": 0.4557603597640991, "learning_rate": 0.00019090980747843737}
+{"ts": "2025-12-24T01:37:24", "event": "train_log", "step": 2866, "epoch": 1.2364617044228694, "progress_pct": 20.61, "epoch_pct": 20.61, "eta": "42:57:15", "max_grad_norm": 1.0, "loss": 0.7910104990005493, "grad_norm": 0.41115859150886536, "learning_rate": 0.00019088933959840004}
+{"ts": "2025-12-24T01:37:38", "event": "train_log", "step": 2868, "epoch": 1.2373247033441208, "progress_pct": 20.62, "epoch_pct": 20.62, "eta": "42:55:53", "max_grad_norm": 1.0, "loss": 0.8318688273429871, "grad_norm": 0.5087599158287048, "learning_rate": 0.0001908688498008082}
+{"ts": "2025-12-24T01:37:53", "event": "train_log", "step": 2870, "epoch": 1.2381877022653722, "progress_pct": 20.64, "epoch_pct": 20.64, "eta": "42:54:35", "max_grad_norm": 1.0, "loss": 0.713392436504364, "grad_norm": 0.4243653118610382, "learning_rate": 0.00019084833809060285}
+{"ts": "2025-12-24T01:38:08", "event": "train_log", "step": 2872, "epoch": 1.2390507011866236, "progress_pct": 20.65, "epoch_pct": 20.65, "eta": "42:53:19", "max_grad_norm": 1.0, "loss": 0.7697778344154358, "grad_norm": 0.3965010344982147, "learning_rate": 0.00019082780447273034}
+{"ts": "2025-12-24T01:38:23", "event": "train_log", "step": 2874, "epoch": 1.2399137001078748, "progress_pct": 20.66, "epoch_pct": 20.67, "eta": "42:52:00", "max_grad_norm": 1.0, "loss": 0.7437527179718018, "grad_norm": 0.4493406116962433, "learning_rate": 0.00019080724895214222}
+{"ts": "2025-12-24T01:38:37", "event": "train_log", "step": 2876, "epoch": 1.2407766990291262, "progress_pct": 20.68, "epoch_pct": 20.68, "eta": "42:50:40", "max_grad_norm": 1.0, "loss": 0.858138918876648, "grad_norm": 0.5189685821533203, "learning_rate": 0.00019078667153379537}
+{"ts": "2025-12-24T01:38:53", "event": "train_log", "step": 2878, "epoch": 1.2416396979503777, "progress_pct": 20.69, "epoch_pct": 20.69, "eta": "42:49:26", "max_grad_norm": 1.0, "loss": 0.7235360145568848, "grad_norm": 0.39455580711364746, "learning_rate": 0.00019076607222265197}
+{"ts": "2025-12-24T01:39:07", "event": "train_log", "step": 2880, "epoch": 1.2425026968716288, "progress_pct": 20.71, "epoch_pct": 20.71, "eta": "42:48:06", "max_grad_norm": 1.0, "loss": 0.7995675206184387, "grad_norm": 0.524804413318634, "learning_rate": 0.00019074545102367943}
+{"ts": "2025-12-24T01:39:23", "event": "train_log", "step": 2882, "epoch": 1.2433656957928803, "progress_pct": 20.72, "epoch_pct": 20.72, "eta": "42:46:49", "max_grad_norm": 1.0, "loss": 0.8404105305671692, "grad_norm": 0.4873242974281311, "learning_rate": 0.00019072480794185044}
+{"ts": "2025-12-24T01:39:37", "event": "train_log", "step": 2884, "epoch": 1.2442286947141317, "progress_pct": 20.74, "epoch_pct": 20.74, "eta": "42:45:31", "max_grad_norm": 1.0, "loss": 0.7540513277053833, "grad_norm": 0.4591716527938843, "learning_rate": 0.000190704142982143}
+{"ts": "2025-12-24T01:39:53", "event": "train_log", "step": 2886, "epoch": 1.2450916936353829, "progress_pct": 20.75, "epoch_pct": 20.75, "eta": "42:44:14", "max_grad_norm": 1.0, "loss": 0.7566621899604797, "grad_norm": 0.48403632640838623, "learning_rate": 0.0001906834561495404}
+{"ts": "2025-12-24T01:40:08", "event": "train_log", "step": 2888, "epoch": 1.2459546925566343, "progress_pct": 20.77, "epoch_pct": 20.77, "eta": "42:42:58", "max_grad_norm": 1.0, "loss": 0.7141375541687012, "grad_norm": 0.4854280948638916, "learning_rate": 0.00019066274744903113}
+{"ts": "2025-12-24T01:40:22", "event": "train_log", "step": 2890, "epoch": 1.2468176914778857, "progress_pct": 20.78, "epoch_pct": 20.78, "eta": "42:41:39", "max_grad_norm": 1.0, "loss": 0.7798115611076355, "grad_norm": 0.45851001143455505, "learning_rate": 0.00019064201688560902}
+{"ts": "2025-12-24T01:40:37", "event": "train_log", "step": 2892, "epoch": 1.247680690399137, "progress_pct": 20.79, "epoch_pct": 20.79, "eta": "42:40:22", "max_grad_norm": 1.0, "loss": 0.7212263941764832, "grad_norm": 0.4584810435771942, "learning_rate": 0.00019062126446427318}
+{"ts": "2025-12-24T01:40:51", "event": "train_log", "step": 2894, "epoch": 1.2485436893203883, "progress_pct": 20.81, "epoch_pct": 20.81, "eta": "42:39:00", "max_grad_norm": 1.0, "loss": 0.8268418312072754, "grad_norm": 0.5282798409461975, "learning_rate": 0.00019060049019002792}
+{"ts": "2025-12-24T01:41:06", "event": "train_log", "step": 2896, "epoch": 1.2494066882416397, "progress_pct": 20.82, "epoch_pct": 20.82, "eta": "42:37:43", "max_grad_norm": 1.0, "loss": 0.7512726783752441, "grad_norm": 0.40996623039245605, "learning_rate": 0.00019057969406788289}
+{"ts": "2025-12-24T01:41:22", "event": "train_log", "step": 2898, "epoch": 1.250269687162891, "progress_pct": 20.84, "epoch_pct": 20.84, "eta": "42:36:29", "max_grad_norm": 1.0, "loss": 0.6680556535720825, "grad_norm": 0.39559319615364075, "learning_rate": 0.00019055887610285296}
+{"ts": "2025-12-24T01:41:37", "event": "train_log", "step": 2900, "epoch": 1.2511326860841425, "progress_pct": 20.85, "epoch_pct": 20.85, "eta": "42:35:12", "max_grad_norm": 1.0, "loss": 0.7307850122451782, "grad_norm": 0.42002710700035095, "learning_rate": 0.0001905380362999583}
+{"ts": "2025-12-24T01:52:27", "event": "train_log", "step": 2900, "epoch": 1.2511326860841425, "progress_pct": 20.85, "epoch_pct": 20.85, "eta": "43:16:21", "max_grad_norm": 1.0, "eval_loss": 0.8155517578125, "eval_runtime": 650.62, "eval_samples_per_second": 3.166, "eval_steps_per_second": 3.166}
+{"ts": "2025-12-24T01:52:43", "event": "train_log", "step": 2902, "epoch": 1.2519956850053937, "progress_pct": 20.87, "epoch_pct": 20.87, "eta": "43:15:06", "max_grad_norm": 1.0, "loss": 0.7316054701805115, "grad_norm": 0.3914625644683838, "learning_rate": 0.00019051717466422435}
+{"ts": "2025-12-24T01:52:57", "event": "train_log", "step": 2904, "epoch": 1.2528586839266451, "progress_pct": 20.88, "epoch_pct": 20.88, "eta": "43:13:44", "max_grad_norm": 1.0, "loss": 0.8977305889129639, "grad_norm": 0.48939383029937744, "learning_rate": 0.00019049629120068175}
+{"ts": "2025-12-24T01:53:13", "event": "train_log", "step": 2906, "epoch": 1.2537216828478965, "progress_pct": 20.89, "epoch_pct": 20.9, "eta": "43:12:30", "max_grad_norm": 1.0, "loss": 0.7962324619293213, "grad_norm": 0.4892135262489319, "learning_rate": 0.0001904753859143665}
+{"ts": "2025-12-24T01:53:29", "event": "train_log", "step": 2908, "epoch": 1.2545846817691477, "progress_pct": 20.91, "epoch_pct": 20.91, "eta": "43:11:13", "max_grad_norm": 1.0, "loss": 0.791375458240509, "grad_norm": 0.5323660969734192, "learning_rate": 0.00019045445881031982}
+{"ts": "2025-12-24T01:53:45", "event": "train_log", "step": 2910, "epoch": 1.2554476806903991, "progress_pct": 20.92, "epoch_pct": 20.92, "eta": "43:09:58", "max_grad_norm": 1.0, "loss": 0.7218163013458252, "grad_norm": 0.44778114557266235, "learning_rate": 0.00019043350989358818}
+{"ts": "2025-12-24T01:54:00", "event": "train_log", "step": 2912, "epoch": 1.2563106796116505, "progress_pct": 20.94, "epoch_pct": 20.94, "eta": "43:08:41", "max_grad_norm": 1.0, "loss": 0.7380548119544983, "grad_norm": 0.4763379991054535, "learning_rate": 0.00019041253916922326}
+{"ts": "2025-12-24T01:54:15", "event": "train_log", "step": 2914, "epoch": 1.2571736785329017, "progress_pct": 20.95, "epoch_pct": 20.95, "eta": "43:07:24", "max_grad_norm": 1.0, "loss": 0.7586072683334351, "grad_norm": 0.4979628026485443, "learning_rate": 0.00019039154664228213}
+{"ts": "2025-12-24T01:54:31", "event": "train_log", "step": 2916, "epoch": 1.2580366774541532, "progress_pct": 20.97, "epoch_pct": 20.97, "eta": "43:06:10", "max_grad_norm": 1.0, "loss": 0.763477623462677, "grad_norm": 0.46175920963287354, "learning_rate": 0.000190370532317827}
+{"ts": "2025-12-24T01:54:48", "event": "train_log", "step": 2918, "epoch": 1.2588996763754046, "progress_pct": 20.98, "epoch_pct": 20.98, "eta": "43:04:56", "max_grad_norm": 1.0, "loss": 0.7479409575462341, "grad_norm": 0.43192169070243835, "learning_rate": 0.0001903494962009254}
+{"ts": "2025-12-24T01:55:04", "event": "train_log", "step": 2920, "epoch": 1.2597626752966558, "progress_pct": 21.0, "epoch_pct": 21.0, "eta": "43:03:43", "max_grad_norm": 1.0, "loss": 0.7355074882507324, "grad_norm": 0.42883434891700745, "learning_rate": 0.0001903284382966501}
+{"ts": "2025-12-24T01:55:20", "event": "train_log", "step": 2922, "epoch": 1.2606256742179072, "progress_pct": 21.01, "epoch_pct": 21.01, "eta": "43:02:28", "max_grad_norm": 1.0, "loss": 0.7762811183929443, "grad_norm": 0.47708168625831604, "learning_rate": 0.00019030735861007912}
+{"ts": "2025-12-24T01:55:36", "event": "train_log", "step": 2924, "epoch": 1.2614886731391586, "progress_pct": 21.02, "epoch_pct": 21.02, "eta": "43:01:14", "max_grad_norm": 1.0, "loss": 0.6964467763900757, "grad_norm": 0.4478151500225067, "learning_rate": 0.0001902862571462957}
+{"ts": "2025-12-24T01:55:50", "event": "train_log", "step": 2926, "epoch": 1.26235167206041, "progress_pct": 21.04, "epoch_pct": 21.04, "eta": "42:59:55", "max_grad_norm": 1.0, "loss": 0.7414857745170593, "grad_norm": 0.4531081020832062, "learning_rate": 0.00019026513391038837}
+{"ts": "2025-12-24T01:56:07", "event": "train_log", "step": 2928, "epoch": 1.2632146709816614, "progress_pct": 21.05, "epoch_pct": 21.05, "eta": "42:58:45", "max_grad_norm": 1.0, "loss": 0.7639371156692505, "grad_norm": 0.4623842239379883, "learning_rate": 0.00019024398890745092}
+{"ts": "2025-12-24T01:56:24", "event": "train_log", "step": 2930, "epoch": 1.2640776699029126, "progress_pct": 21.07, "epoch_pct": 21.07, "eta": "42:57:33", "max_grad_norm": 1.0, "loss": 0.800457239151001, "grad_norm": 0.4362739622592926, "learning_rate": 0.00019022282214258238}
+{"ts": "2025-12-24T01:56:39", "event": "train_log", "step": 2932, "epoch": 1.264940668824164, "progress_pct": 21.08, "epoch_pct": 21.08, "eta": "42:56:17", "max_grad_norm": 1.0, "loss": 0.7960386872291565, "grad_norm": 0.42854052782058716, "learning_rate": 0.000190201633620887}
+{"ts": "2025-12-24T01:56:55", "event": "train_log", "step": 2934, "epoch": 1.2658036677454154, "progress_pct": 21.1, "epoch_pct": 21.1, "eta": "42:55:01", "max_grad_norm": 1.0, "loss": 0.7544003129005432, "grad_norm": 0.47477999329566956, "learning_rate": 0.0001901804233474743}
+{"ts": "2025-12-24T01:57:10", "event": "train_log", "step": 2936, "epoch": 1.2666666666666666, "progress_pct": 21.11, "epoch_pct": 21.11, "eta": "42:53:44", "max_grad_norm": 1.0, "loss": 0.7819825410842896, "grad_norm": 0.4584832191467285, "learning_rate": 0.00019015919132745905}
+{"ts": "2025-12-24T01:57:26", "event": "train_log", "step": 2938, "epoch": 1.267529665587918, "progress_pct": 21.12, "epoch_pct": 21.13, "eta": "42:52:30", "max_grad_norm": 1.0, "loss": 0.7719182372093201, "grad_norm": 0.5465012192726135, "learning_rate": 0.00019013793756596123}
+{"ts": "2025-12-24T01:57:42", "event": "train_log", "step": 2940, "epoch": 1.2683926645091694, "progress_pct": 21.14, "epoch_pct": 21.14, "eta": "42:51:17", "max_grad_norm": 1.0, "loss": 0.7442063093185425, "grad_norm": 0.42024123668670654, "learning_rate": 0.00019011666206810614}
+{"ts": "2025-12-24T01:57:57", "event": "train_log", "step": 2942, "epoch": 1.2692556634304206, "progress_pct": 21.15, "epoch_pct": 21.15, "eta": "42:50:03", "max_grad_norm": 1.0, "loss": 0.6696176528930664, "grad_norm": 0.4374787211418152, "learning_rate": 0.00019009536483902424}
+{"ts": "2025-12-24T01:58:13", "event": "train_log", "step": 2944, "epoch": 1.270118662351672, "progress_pct": 21.17, "epoch_pct": 21.17, "eta": "42:48:48", "max_grad_norm": 1.0, "loss": 0.7048487663269043, "grad_norm": 0.4136449992656708, "learning_rate": 0.00019007404588385125}
+{"ts": "2025-12-24T01:58:28", "event": "train_log", "step": 2946, "epoch": 1.2709816612729234, "progress_pct": 21.18, "epoch_pct": 21.18, "eta": "42:47:30", "max_grad_norm": 1.0, "loss": 0.7587971687316895, "grad_norm": 0.4463474452495575, "learning_rate": 0.00019005270520772817}
+{"ts": "2025-12-24T01:58:43", "event": "train_log", "step": 2948, "epoch": 1.2718446601941746, "progress_pct": 21.2, "epoch_pct": 21.2, "eta": "42:46:16", "max_grad_norm": 1.0, "loss": 0.7741286754608154, "grad_norm": 0.43167322874069214, "learning_rate": 0.00019003134281580115}
+{"ts": "2025-12-24T01:58:59", "event": "train_log", "step": 2950, "epoch": 1.272707659115426, "progress_pct": 21.21, "epoch_pct": 21.21, "eta": "42:45:00", "max_grad_norm": 1.0, "loss": 0.7572245597839355, "grad_norm": 0.5189676284790039, "learning_rate": 0.0001900099587132217}
+{"ts": "2025-12-24T01:59:14", "event": "train_log", "step": 2952, "epoch": 1.2735706580366775, "progress_pct": 21.23, "epoch_pct": 21.23, "eta": "42:43:44", "max_grad_norm": 1.0, "loss": 0.7743186354637146, "grad_norm": 0.4256224036216736, "learning_rate": 0.00018998855290514646}
+{"ts": "2025-12-24T01:59:29", "event": "train_log", "step": 2954, "epoch": 1.2744336569579289, "progress_pct": 21.24, "epoch_pct": 21.24, "eta": "42:42:26", "max_grad_norm": 1.0, "loss": 0.7287778854370117, "grad_norm": 0.4304806888103485, "learning_rate": 0.00018996712539673735}
+{"ts": "2025-12-24T01:59:44", "event": "train_log", "step": 2956, "epoch": 1.2752966558791803, "progress_pct": 21.25, "epoch_pct": 21.25, "eta": "42:41:10", "max_grad_norm": 1.0, "loss": 0.7930773496627808, "grad_norm": 0.489372193813324, "learning_rate": 0.00018994567619316156}
+{"ts": "2025-12-24T01:59:59", "event": "train_log", "step": 2958, "epoch": 1.2761596548004315, "progress_pct": 21.27, "epoch_pct": 21.27, "eta": "42:39:54", "max_grad_norm": 1.0, "loss": 0.7283111214637756, "grad_norm": 0.3855830430984497, "learning_rate": 0.0001899242052995914}
+{"ts": "2025-12-24T02:00:14", "event": "train_log", "step": 2960, "epoch": 1.2770226537216829, "progress_pct": 21.28, "epoch_pct": 21.28, "eta": "42:38:37", "max_grad_norm": 1.0, "loss": 0.721849262714386, "grad_norm": 0.46708667278289795, "learning_rate": 0.00018990271272120452}
+{"ts": "2025-12-24T02:00:30", "event": "train_log", "step": 2962, "epoch": 1.2778856526429343, "progress_pct": 21.3, "epoch_pct": 21.3, "eta": "42:37:27", "max_grad_norm": 1.0, "loss": 0.6678964495658875, "grad_norm": 0.3663526773452759, "learning_rate": 0.00018988119846318377}
+{"ts": "2025-12-24T02:00:45", "event": "train_log", "step": 2964, "epoch": 1.2787486515641855, "progress_pct": 21.31, "epoch_pct": 21.31, "eta": "42:36:11", "max_grad_norm": 1.0, "loss": 0.8021678924560547, "grad_norm": 0.5074638724327087, "learning_rate": 0.00018985966253071718}
+{"ts": "2025-12-24T02:01:00", "event": "train_log", "step": 2966, "epoch": 1.279611650485437, "progress_pct": 21.33, "epoch_pct": 21.33, "eta": "42:34:55", "max_grad_norm": 1.0, "loss": 0.8313384056091309, "grad_norm": 0.4902975857257843, "learning_rate": 0.00018983810492899806}
+{"ts": "2025-12-24T02:01:15", "event": "train_log", "step": 2968, "epoch": 1.2804746494066883, "progress_pct": 21.34, "epoch_pct": 21.34, "eta": "42:33:37", "max_grad_norm": 1.0, "loss": 0.8330302834510803, "grad_norm": 0.5023161768913269, "learning_rate": 0.00018981652566322493}
+{"ts": "2025-12-24T02:01:30", "event": "train_log", "step": 2970, "epoch": 1.2813376483279395, "progress_pct": 21.35, "epoch_pct": 21.36, "eta": "42:32:22", "max_grad_norm": 1.0, "loss": 0.8806158304214478, "grad_norm": 0.48227089643478394, "learning_rate": 0.00018979492473860155}
+{"ts": "2025-12-24T02:01:46", "event": "train_log", "step": 2972, "epoch": 1.282200647249191, "progress_pct": 21.37, "epoch_pct": 21.37, "eta": "42:31:11", "max_grad_norm": 1.0, "loss": 0.6835185885429382, "grad_norm": 0.40143465995788574, "learning_rate": 0.00018977330216033683}
+{"ts": "2025-12-24T02:02:01", "event": "train_log", "step": 2974, "epoch": 1.2830636461704423, "progress_pct": 21.38, "epoch_pct": 21.38, "eta": "42:29:54", "max_grad_norm": 1.0, "loss": 0.7207706570625305, "grad_norm": 0.4368304908275604, "learning_rate": 0.00018975165793364503}
+{"ts": "2025-12-24T02:02:18", "event": "train_log", "step": 2976, "epoch": 1.2839266450916935, "progress_pct": 21.4, "epoch_pct": 21.4, "eta": "42:28:43", "max_grad_norm": 1.0, "loss": 0.6909692883491516, "grad_norm": 0.39989250898361206, "learning_rate": 0.0001897299920637455}
+{"ts": "2025-12-24T02:02:32", "event": "train_log", "step": 2978, "epoch": 1.284789644012945, "progress_pct": 21.41, "epoch_pct": 21.41, "eta": "42:27:28", "max_grad_norm": 1.0, "loss": 0.838360071182251, "grad_norm": 0.4826473593711853, "learning_rate": 0.0001897083045558629}
+{"ts": "2025-12-24T02:02:47", "event": "train_log", "step": 2980, "epoch": 1.2856526429341963, "progress_pct": 21.43, "epoch_pct": 21.43, "eta": "42:26:10", "max_grad_norm": 1.0, "loss": 0.7693317532539368, "grad_norm": 0.4860877990722656, "learning_rate": 0.00018968659541522705}
+{"ts": "2025-12-24T02:03:02", "event": "train_log", "step": 2982, "epoch": 1.2865156418554478, "progress_pct": 21.44, "epoch_pct": 21.44, "eta": "42:24:57", "max_grad_norm": 1.0, "loss": 0.7662015557289124, "grad_norm": 0.4361511170864105, "learning_rate": 0.00018966486464707305}
+{"ts": "2025-12-24T02:03:18", "event": "train_log", "step": 2984, "epoch": 1.287378640776699, "progress_pct": 21.46, "epoch_pct": 21.46, "eta": "42:23:44", "max_grad_norm": 1.0, "loss": 0.752369225025177, "grad_norm": 0.45333993434906006, "learning_rate": 0.00018964311225664113}
+{"ts": "2025-12-24T02:03:34", "event": "train_log", "step": 2986, "epoch": 1.2882416396979504, "progress_pct": 21.47, "epoch_pct": 21.47, "eta": "42:22:33", "max_grad_norm": 1.0, "loss": 0.7524476051330566, "grad_norm": 0.4825304448604584, "learning_rate": 0.0001896213382491768}
+{"ts": "2025-12-24T02:03:49", "event": "train_log", "step": 2988, "epoch": 1.2891046386192018, "progress_pct": 21.48, "epoch_pct": 21.49, "eta": "42:21:15", "max_grad_norm": 1.0, "loss": 0.8564903736114502, "grad_norm": 0.5303854942321777, "learning_rate": 0.00018959954262993077}
+{"ts": "2025-12-24T02:04:04", "event": "train_log", "step": 2990, "epoch": 1.2899676375404532, "progress_pct": 21.5, "epoch_pct": 21.5, "eta": "42:20:02", "max_grad_norm": 1.0, "loss": 0.7839077711105347, "grad_norm": 0.43856459856033325, "learning_rate": 0.00018957772540415896}
+{"ts": "2025-12-24T02:04:20", "event": "train_log", "step": 2992, "epoch": 1.2908306364617044, "progress_pct": 21.51, "epoch_pct": 21.51, "eta": "42:18:50", "max_grad_norm": 1.0, "loss": 0.7580918669700623, "grad_norm": 0.438041627407074, "learning_rate": 0.00018955588657712248}
+{"ts": "2025-12-24T02:04:36", "event": "train_log", "step": 2994, "epoch": 1.2916936353829558, "progress_pct": 21.53, "epoch_pct": 21.53, "eta": "42:17:39", "max_grad_norm": 1.0, "loss": 0.7014032602310181, "grad_norm": 0.4497842490673065, "learning_rate": 0.00018953402615408768}
+{"ts": "2025-12-24T02:04:51", "event": "train_log", "step": 2996, "epoch": 1.2925566343042072, "progress_pct": 21.54, "epoch_pct": 21.54, "eta": "42:16:24", "max_grad_norm": 1.0, "loss": 0.8220269083976746, "grad_norm": 0.5659869313240051, "learning_rate": 0.0001895121441403261}
+{"ts": "2025-12-24T02:05:06", "event": "train_log", "step": 2998, "epoch": 1.2934196332254584, "progress_pct": 21.56, "epoch_pct": 21.56, "eta": "42:15:09", "max_grad_norm": 1.0, "loss": 0.6880294680595398, "grad_norm": 0.4850102961063385, "learning_rate": 0.00018949024054111448}
+{"ts": "2025-12-24T02:05:22", "event": "train_log", "step": 3000, "epoch": 1.2942826321467098, "progress_pct": 21.57, "epoch_pct": 21.57, "eta": "42:13:57", "max_grad_norm": 1.0, "loss": 0.7443753480911255, "grad_norm": 0.4253626763820648, "learning_rate": 0.00018946831536173476}
+{"ts": "2025-12-24T02:16:12", "event": "train_log", "step": 3000, "epoch": 1.2942826321467098, "progress_pct": 21.57, "epoch_pct": 21.57, "eta": "42:53:22", "max_grad_norm": 1.0, "eval_loss": 0.8127614259719849, "eval_runtime": 650.4396, "eval_samples_per_second": 3.167, "eval_steps_per_second": 3.167}
+{"ts": "2025-12-24T02:16:28", "event": "train_log", "step": 3002, "epoch": 1.2951456310679612, "progress_pct": 21.58, "epoch_pct": 21.59, "eta": "42:52:10", "max_grad_norm": 1.0, "loss": 0.6588667631149292, "grad_norm": 0.3746396005153656, "learning_rate": 0.00018944636860747412}
+{"ts": "2025-12-24T02:16:43", "event": "train_log", "step": 3004, "epoch": 1.2960086299892124, "progress_pct": 21.6, "epoch_pct": 21.6, "eta": "42:50:52", "max_grad_norm": 1.0, "loss": 0.7135416865348816, "grad_norm": 0.4039393663406372, "learning_rate": 0.00018942440028362493}
+{"ts": "2025-12-24T02:16:58", "event": "train_log", "step": 3006, "epoch": 1.2968716289104638, "progress_pct": 21.61, "epoch_pct": 21.61, "eta": "42:49:34", "max_grad_norm": 1.0, "loss": 0.7895556688308716, "grad_norm": 0.457533061504364, "learning_rate": 0.00018940241039548474}
+{"ts": "2025-12-24T02:17:13", "event": "train_log", "step": 3008, "epoch": 1.2977346278317152, "progress_pct": 21.63, "epoch_pct": 21.63, "eta": "42:48:18", "max_grad_norm": 1.0, "loss": 0.7863595485687256, "grad_norm": 0.4989747107028961, "learning_rate": 0.0001893803989483563}
+{"ts": "2025-12-24T02:17:27", "event": "train_log", "step": 3010, "epoch": 1.2985976267529666, "progress_pct": 21.64, "epoch_pct": 21.64, "eta": "42:46:59", "max_grad_norm": 1.0, "loss": 0.795306921005249, "grad_norm": 0.470002681016922, "learning_rate": 0.00018935836594754756}
+{"ts": "2025-12-24T02:17:42", "event": "train_log", "step": 3012, "epoch": 1.2994606256742178, "progress_pct": 21.66, "epoch_pct": 21.66, "eta": "42:45:43", "max_grad_norm": 1.0, "loss": 0.7313401699066162, "grad_norm": 0.43668872117996216, "learning_rate": 0.00018933631139837176}
+{"ts": "2025-12-24T02:17:57", "event": "train_log", "step": 3014, "epoch": 1.3003236245954692, "progress_pct": 21.67, "epoch_pct": 21.67, "eta": "42:44:25", "max_grad_norm": 1.0, "loss": 0.7331582903862, "grad_norm": 0.4843446910381317, "learning_rate": 0.00018931423530614715}
+{"ts": "2025-12-24T02:18:12", "event": "train_log", "step": 3016, "epoch": 1.3011866235167207, "progress_pct": 21.69, "epoch_pct": 21.69, "eta": "42:43:09", "max_grad_norm": 1.0, "loss": 0.7046043872833252, "grad_norm": 0.4233832359313965, "learning_rate": 0.00018929213767619735}
+{"ts": "2025-12-24T02:18:26", "event": "train_log", "step": 3018, "epoch": 1.302049622437972, "progress_pct": 21.7, "epoch_pct": 21.7, "eta": "42:41:51", "max_grad_norm": 1.0, "loss": 0.8217260241508484, "grad_norm": 0.6326188445091248, "learning_rate": 0.00018927001851385108}
+{"ts": "2025-12-24T02:18:41", "event": "train_log", "step": 3020, "epoch": 1.3029126213592233, "progress_pct": 21.71, "epoch_pct": 21.72, "eta": "42:40:36", "max_grad_norm": 1.0, "loss": 0.6477662324905396, "grad_norm": 0.409653902053833, "learning_rate": 0.00018924787782444223}
+{"ts": "2025-12-24T02:18:56", "event": "train_log", "step": 3022, "epoch": 1.3037756202804747, "progress_pct": 21.73, "epoch_pct": 21.73, "eta": "42:39:19", "max_grad_norm": 1.0, "loss": 0.6408766508102417, "grad_norm": 0.3869863748550415, "learning_rate": 0.00018922571561331004}
+{"ts": "2025-12-24T02:19:11", "event": "train_log", "step": 3024, "epoch": 1.304638619201726, "progress_pct": 21.74, "epoch_pct": 21.74, "eta": "42:38:03", "max_grad_norm": 1.0, "loss": 0.7396708726882935, "grad_norm": 0.4400722086429596, "learning_rate": 0.00018920353188579874}
+{"ts": "2025-12-24T02:19:26", "event": "train_log", "step": 3026, "epoch": 1.3055016181229773, "progress_pct": 21.76, "epoch_pct": 21.76, "eta": "42:36:47", "max_grad_norm": 1.0, "loss": 0.6409308314323425, "grad_norm": 0.39694252610206604, "learning_rate": 0.00018918132664725784}
+{"ts": "2025-12-24T02:19:40", "event": "train_log", "step": 3028, "epoch": 1.3063646170442287, "progress_pct": 21.77, "epoch_pct": 21.77, "eta": "42:35:28", "max_grad_norm": 1.0, "loss": 0.7825533151626587, "grad_norm": 0.49937903881073, "learning_rate": 0.00018915909990304205}
+{"ts": "2025-12-24T02:19:55", "event": "train_log", "step": 3030, "epoch": 1.30722761596548, "progress_pct": 21.79, "epoch_pct": 21.79, "eta": "42:34:12", "max_grad_norm": 1.0, "loss": 0.7182250022888184, "grad_norm": 0.43940550088882446, "learning_rate": 0.0001891368516585113}
+{"ts": "2025-12-24T02:20:10", "event": "train_log", "step": 3032, "epoch": 1.3080906148867313, "progress_pct": 21.8, "epoch_pct": 21.8, "eta": "42:32:57", "max_grad_norm": 1.0, "loss": 0.7602632641792297, "grad_norm": 0.43905356526374817, "learning_rate": 0.00018911458191903053}
+{"ts": "2025-12-24T02:20:25", "event": "train_log", "step": 3034, "epoch": 1.3089536138079827, "progress_pct": 21.81, "epoch_pct": 21.82, "eta": "42:31:40", "max_grad_norm": 1.0, "loss": 0.7307555675506592, "grad_norm": 0.4172695279121399, "learning_rate": 0.0001890922906899701}
+{"ts": "2025-12-24T02:20:40", "event": "train_log", "step": 3036, "epoch": 1.309816612729234, "progress_pct": 21.83, "epoch_pct": 21.83, "eta": "42:30:27", "max_grad_norm": 1.0, "loss": 0.782136857509613, "grad_norm": 0.49642932415008545, "learning_rate": 0.00018906997797670544}
+{"ts": "2025-12-24T02:20:55", "event": "train_log", "step": 3038, "epoch": 1.3106796116504853, "progress_pct": 21.84, "epoch_pct": 21.84, "eta": "42:29:13", "max_grad_norm": 1.0, "loss": 0.787925124168396, "grad_norm": 0.49893322587013245, "learning_rate": 0.00018904764378461705}
+{"ts": "2025-12-24T02:21:11", "event": "train_log", "step": 3040, "epoch": 1.3115426105717367, "progress_pct": 21.86, "epoch_pct": 21.86, "eta": "42:28:00", "max_grad_norm": 1.0, "loss": 0.6731302738189697, "grad_norm": 0.42691150307655334, "learning_rate": 0.00018902528811909081}
+{"ts": "2025-12-24T02:21:27", "event": "train_log", "step": 3042, "epoch": 1.3124056094929881, "progress_pct": 21.87, "epoch_pct": 21.87, "eta": "42:26:48", "max_grad_norm": 1.0, "loss": 0.7211409211158752, "grad_norm": 0.4961661696434021, "learning_rate": 0.00018900291098551767}
+{"ts": "2025-12-24T02:21:43", "event": "train_log", "step": 3044, "epoch": 1.3132686084142395, "progress_pct": 21.89, "epoch_pct": 21.89, "eta": "42:25:36", "max_grad_norm": 1.0, "loss": 0.7317034602165222, "grad_norm": 0.45150521397590637, "learning_rate": 0.00018898051238929378}
+{"ts": "2025-12-24T02:21:58", "event": "train_log", "step": 3046, "epoch": 1.314131607335491, "progress_pct": 21.9, "epoch_pct": 21.9, "eta": "42:24:22", "max_grad_norm": 1.0, "loss": 0.7838613390922546, "grad_norm": 0.5012714266777039, "learning_rate": 0.00018895809233582047}
+{"ts": "2025-12-24T02:22:13", "event": "train_log", "step": 3048, "epoch": 1.3149946062567421, "progress_pct": 21.92, "epoch_pct": 21.92, "eta": "42:23:08", "max_grad_norm": 1.0, "loss": 0.8206616640090942, "grad_norm": 0.5605086088180542, "learning_rate": 0.0001889356508305042}
+{"ts": "2025-12-24T02:22:28", "event": "train_log", "step": 3050, "epoch": 1.3158576051779936, "progress_pct": 21.93, "epoch_pct": 21.93, "eta": "42:21:53", "max_grad_norm": 1.0, "loss": 0.7460386753082275, "grad_norm": 0.4337491989135742, "learning_rate": 0.00018891318787875666}
+{"ts": "2025-12-24T02:22:42", "event": "train_log", "step": 3052, "epoch": 1.316720604099245, "progress_pct": 21.94, "epoch_pct": 21.95, "eta": "42:20:34", "max_grad_norm": 1.0, "loss": 0.7973155379295349, "grad_norm": 0.4392184913158417, "learning_rate": 0.00018889070348599468}
+{"ts": "2025-12-24T02:22:58", "event": "train_log", "step": 3054, "epoch": 1.3175836030204962, "progress_pct": 21.96, "epoch_pct": 21.96, "eta": "42:19:22", "max_grad_norm": 1.0, "loss": 0.6951689720153809, "grad_norm": 0.4550181031227112, "learning_rate": 0.00018886819765764028}
+{"ts": "2025-12-24T02:23:13", "event": "train_log", "step": 3056, "epoch": 1.3184466019417476, "progress_pct": 21.97, "epoch_pct": 21.97, "eta": "42:18:09", "max_grad_norm": 1.0, "loss": 0.7353226542472839, "grad_norm": 0.4058854877948761, "learning_rate": 0.00018884567039912062}
+{"ts": "2025-12-24T02:23:29", "event": "train_log", "step": 3058, "epoch": 1.319309600862999, "progress_pct": 21.99, "epoch_pct": 21.99, "eta": "42:16:59", "max_grad_norm": 1.0, "loss": 0.7758772969245911, "grad_norm": 0.4157969057559967, "learning_rate": 0.00018882312171586806}
+{"ts": "2025-12-24T02:23:45", "event": "train_log", "step": 3060, "epoch": 1.3201725997842502, "progress_pct": 22.0, "epoch_pct": 22.0, "eta": "42:15:47", "max_grad_norm": 1.0, "loss": 0.6808486580848694, "grad_norm": 0.44122767448425293, "learning_rate": 0.00018880055161332016}
+{"ts": "2025-12-24T02:24:00", "event": "train_log", "step": 3062, "epoch": 1.3210355987055016, "progress_pct": 22.02, "epoch_pct": 22.02, "eta": "42:14:33", "max_grad_norm": 1.0, "loss": 0.7781010270118713, "grad_norm": 0.4674125015735626, "learning_rate": 0.0001887779600969195}
+{"ts": "2025-12-24T02:24:16", "event": "train_log", "step": 3064, "epoch": 1.321898597626753, "progress_pct": 22.03, "epoch_pct": 22.03, "eta": "42:13:22", "max_grad_norm": 1.0, "loss": 0.7759971022605896, "grad_norm": 0.4414712190628052, "learning_rate": 0.000188755347172114}
+{"ts": "2025-12-24T02:24:32", "event": "train_log", "step": 3066, "epoch": 1.3227615965480042, "progress_pct": 22.04, "epoch_pct": 22.05, "eta": "42:12:11", "max_grad_norm": 1.0, "loss": 0.7430314421653748, "grad_norm": 0.4804554283618927, "learning_rate": 0.00018873271284435664}
+{"ts": "2025-12-24T02:24:48", "event": "train_log", "step": 3068, "epoch": 1.3236245954692556, "progress_pct": 22.06, "epoch_pct": 22.06, "eta": "42:11:00", "max_grad_norm": 1.0, "loss": 0.6974785923957825, "grad_norm": 0.4891934096813202, "learning_rate": 0.00018871005711910562}
+{"ts": "2025-12-24T02:25:04", "event": "train_log", "step": 3070, "epoch": 1.324487594390507, "progress_pct": 22.07, "epoch_pct": 22.07, "eta": "42:09:51", "max_grad_norm": 1.0, "loss": 0.6832907199859619, "grad_norm": 0.4103528559207916, "learning_rate": 0.0001886873800018242}
+{"ts": "2025-12-24T02:25:21", "event": "train_log", "step": 3072, "epoch": 1.3253505933117584, "progress_pct": 22.09, "epoch_pct": 22.09, "eta": "42:08:42", "max_grad_norm": 1.0, "loss": 0.7700413465499878, "grad_norm": 0.45092564821243286, "learning_rate": 0.00018866468149798089}
+{"ts": "2025-12-24T02:25:37", "event": "train_log", "step": 3074, "epoch": 1.3262135922330098, "progress_pct": 22.1, "epoch_pct": 22.1, "eta": "42:07:32", "max_grad_norm": 1.0, "loss": 0.7441738843917847, "grad_norm": 0.47934943437576294, "learning_rate": 0.00018864196161304933}
+{"ts": "2025-12-24T02:25:51", "event": "train_log", "step": 3076, "epoch": 1.327076591154261, "progress_pct": 22.12, "epoch_pct": 22.12, "eta": "42:06:18", "max_grad_norm": 1.0, "loss": 0.7195783853530884, "grad_norm": 0.756400465965271, "learning_rate": 0.00018861922035250835}
+{"ts": "2025-12-24T02:26:08", "event": "train_log", "step": 3078, "epoch": 1.3279395900755124, "progress_pct": 22.13, "epoch_pct": 22.13, "eta": "42:05:08", "max_grad_norm": 1.0, "loss": 0.6692811846733093, "grad_norm": 0.47899410128593445, "learning_rate": 0.00018859645772184187}
+{"ts": "2025-12-24T02:26:23", "event": "train_log", "step": 3080, "epoch": 1.3288025889967638, "progress_pct": 22.15, "epoch_pct": 22.15, "eta": "42:03:57", "max_grad_norm": 1.0, "loss": 0.6882596611976624, "grad_norm": 0.43265631794929504, "learning_rate": 0.000188573673726539}
+{"ts": "2025-12-24T02:26:38", "event": "train_log", "step": 3082, "epoch": 1.329665587918015, "progress_pct": 22.16, "epoch_pct": 22.16, "eta": "42:02:43", "max_grad_norm": 1.0, "loss": 0.9300010204315186, "grad_norm": 0.4955349266529083, "learning_rate": 0.00018855086837209401}
+{"ts": "2025-12-24T02:26:53", "event": "train_log", "step": 3084, "epoch": 1.3305285868392664, "progress_pct": 22.17, "epoch_pct": 22.18, "eta": "42:01:29", "max_grad_norm": 1.0, "loss": 0.8391118049621582, "grad_norm": 0.4638696312904358, "learning_rate": 0.0001885280416640063}
+{"ts": "2025-12-24T02:27:11", "event": "train_log", "step": 3086, "epoch": 1.3313915857605179, "progress_pct": 22.19, "epoch_pct": 22.19, "eta": "42:00:26", "max_grad_norm": 1.0, "loss": 0.7136397957801819, "grad_norm": 0.4086083471775055, "learning_rate": 0.00018850519360778044}
+{"ts": "2025-12-24T02:27:27", "event": "train_log", "step": 3088, "epoch": 1.332254584681769, "progress_pct": 22.2, "epoch_pct": 22.2, "eta": "41:59:17", "max_grad_norm": 1.0, "loss": 0.6886621117591858, "grad_norm": 0.4455646574497223, "learning_rate": 0.0001884823242089261}
+{"ts": "2025-12-24T02:27:44", "event": "train_log", "step": 3090, "epoch": 1.3331175836030205, "progress_pct": 22.22, "epoch_pct": 22.22, "eta": "41:58:09", "max_grad_norm": 1.0, "loss": 0.7261496782302856, "grad_norm": 0.43355703353881836, "learning_rate": 0.0001884594334729582}
+{"ts": "2025-12-24T02:27:58", "event": "train_log", "step": 3092, "epoch": 1.3339805825242719, "progress_pct": 22.23, "epoch_pct": 22.23, "eta": "41:56:55", "max_grad_norm": 1.0, "loss": 0.8529927134513855, "grad_norm": 0.5322562456130981, "learning_rate": 0.00018843652140539664}
+{"ts": "2025-12-24T02:28:13", "event": "train_log", "step": 3094, "epoch": 1.334843581445523, "progress_pct": 22.25, "epoch_pct": 22.25, "eta": "41:55:41", "max_grad_norm": 1.0, "loss": 0.8131585121154785, "grad_norm": 0.4504645764827728, "learning_rate": 0.00018841358801176668}
+{"ts": "2025-12-24T02:28:29", "event": "train_log", "step": 3096, "epoch": 1.3357065803667745, "progress_pct": 22.26, "epoch_pct": 22.26, "eta": "41:54:32", "max_grad_norm": 1.0, "loss": 0.800965428352356, "grad_norm": 0.44101089239120483, "learning_rate": 0.0001883906332975985}
+{"ts": "2025-12-24T02:28:45", "event": "train_log", "step": 3098, "epoch": 1.3365695792880259, "progress_pct": 22.27, "epoch_pct": 22.28, "eta": "41:53:21", "max_grad_norm": 1.0, "loss": 0.711025059223175, "grad_norm": 0.46587181091308594, "learning_rate": 0.00018836765726842759}
+{"ts": "2025-12-24T02:29:01", "event": "train_log", "step": 3100, "epoch": 1.3374325782092773, "progress_pct": 22.29, "epoch_pct": 22.29, "eta": "41:52:10", "max_grad_norm": 1.0, "loss": 0.7824587225914001, "grad_norm": 0.4656004011631012, "learning_rate": 0.00018834465992979447}
+{"ts": "2025-12-24T02:40:03", "event": "train_log", "step": 3100, "epoch": 1.3374325782092773, "progress_pct": 22.29, "epoch_pct": 22.29, "eta": "42:30:41", "max_grad_norm": 1.0, "eval_loss": 0.8109187483787537, "eval_runtime": 662.5843, "eval_samples_per_second": 3.109, "eval_steps_per_second": 3.109}
+{"ts": "2025-12-24T02:40:18", "event": "train_log", "step": 3102, "epoch": 1.3382955771305287, "progress_pct": 22.3, "epoch_pct": 22.3, "eta": "42:29:24", "max_grad_norm": 1.0, "loss": 0.7444300651550293, "grad_norm": 0.4942762851715088, "learning_rate": 0.00018832164128724488}
+{"ts": "2025-12-24T02:40:32", "event": "train_log", "step": 3104, "epoch": 1.33915857605178, "progress_pct": 22.32, "epoch_pct": 22.32, "eta": "42:28:07", "max_grad_norm": 1.0, "loss": 0.8248856067657471, "grad_norm": 0.5280060172080994, "learning_rate": 0.00018829860134632963}
+{"ts": "2025-12-24T02:40:47", "event": "train_log", "step": 3106, "epoch": 1.3400215749730313, "progress_pct": 22.33, "epoch_pct": 22.33, "eta": "42:26:52", "max_grad_norm": 1.0, "loss": 0.7753435373306274, "grad_norm": 0.4131146967411041, "learning_rate": 0.00018827554011260474}
+{"ts": "2025-12-24T02:41:02", "event": "train_log", "step": 3108, "epoch": 1.3408845738942827, "progress_pct": 22.35, "epoch_pct": 22.35, "eta": "42:25:37", "max_grad_norm": 1.0, "loss": 0.7512242197990417, "grad_norm": 0.38460803031921387, "learning_rate": 0.0001882524575916313}
+{"ts": "2025-12-24T02:41:17", "event": "train_log", "step": 3110, "epoch": 1.341747572815534, "progress_pct": 22.36, "epoch_pct": 22.36, "eta": "42:24:23", "max_grad_norm": 1.0, "loss": 0.7760549783706665, "grad_norm": 0.4719627797603607, "learning_rate": 0.00018822935378897554}
+{"ts": "2025-12-24T02:41:31", "event": "train_log", "step": 3112, "epoch": 1.3426105717367853, "progress_pct": 22.38, "epoch_pct": 22.38, "eta": "42:23:07", "max_grad_norm": 1.0, "loss": 0.7802333831787109, "grad_norm": 0.47593894600868225, "learning_rate": 0.00018820622871020887}
+{"ts": "2025-12-24T02:41:46", "event": "train_log", "step": 3114, "epoch": 1.3434735706580367, "progress_pct": 22.39, "epoch_pct": 22.39, "eta": "42:21:52", "max_grad_norm": 1.0, "loss": 0.7037042379379272, "grad_norm": 0.46464505791664124, "learning_rate": 0.00018818308236090778}
+{"ts": "2025-12-24T02:42:01", "event": "train_log", "step": 3116, "epoch": 1.344336569579288, "progress_pct": 22.4, "epoch_pct": 22.41, "eta": "42:20:36", "max_grad_norm": 1.0, "loss": 0.7476377487182617, "grad_norm": 0.4358392059803009, "learning_rate": 0.0001881599147466539}
+{"ts": "2025-12-24T02:42:15", "event": "train_log", "step": 3118, "epoch": 1.3451995685005393, "progress_pct": 22.42, "epoch_pct": 22.42, "eta": "42:19:18", "max_grad_norm": 1.0, "loss": 0.8273758292198181, "grad_norm": 0.5236833095550537, "learning_rate": 0.000188136725873034}
+{"ts": "2025-12-24T02:42:29", "event": "train_log", "step": 3120, "epoch": 1.3460625674217908, "progress_pct": 22.43, "epoch_pct": 22.43, "eta": "42:18:01", "max_grad_norm": 1.0, "loss": 0.7407519817352295, "grad_norm": 0.5240068435668945, "learning_rate": 0.00018811351574564}
+{"ts": "2025-12-24T02:42:44", "event": "train_log", "step": 3122, "epoch": 1.346925566343042, "progress_pct": 22.45, "epoch_pct": 22.45, "eta": "42:16:47", "max_grad_norm": 1.0, "loss": 0.708732008934021, "grad_norm": 0.44454488158226013, "learning_rate": 0.00018809028437006888}
+{"ts": "2025-12-24T02:42:58", "event": "train_log", "step": 3124, "epoch": 1.3477885652642934, "progress_pct": 22.46, "epoch_pct": 22.46, "eta": "42:15:32", "max_grad_norm": 1.0, "loss": 0.7243810296058655, "grad_norm": 0.43769216537475586, "learning_rate": 0.00018806703175192283}
+{"ts": "2025-12-24T02:43:12", "event": "train_log", "step": 3126, "epoch": 1.3486515641855448, "progress_pct": 22.48, "epoch_pct": 22.48, "eta": "42:14:15", "max_grad_norm": 1.0, "loss": 0.7603667974472046, "grad_norm": 0.4477781355381012, "learning_rate": 0.00018804375789680905}
+{"ts": "2025-12-24T02:43:27", "event": "train_log", "step": 3128, "epoch": 1.3495145631067962, "progress_pct": 22.49, "epoch_pct": 22.49, "eta": "42:13:01", "max_grad_norm": 1.0, "loss": 0.7545933127403259, "grad_norm": 0.4425322115421295, "learning_rate": 0.00018802046281033997}
+{"ts": "2025-12-24T02:43:43", "event": "train_log", "step": 3130, "epoch": 1.3503775620280476, "progress_pct": 22.51, "epoch_pct": 22.51, "eta": "42:11:49", "max_grad_norm": 1.0, "loss": 0.7925270795822144, "grad_norm": 0.458310604095459, "learning_rate": 0.00018799714649813304}
+{"ts": "2025-12-24T02:43:57", "event": "train_log", "step": 3132, "epoch": 1.3512405609492988, "progress_pct": 22.52, "epoch_pct": 22.52, "eta": "42:10:34", "max_grad_norm": 1.0, "loss": 0.7392709851264954, "grad_norm": 0.4328557848930359, "learning_rate": 0.00018797380896581095}
+{"ts": "2025-12-24T02:44:12", "event": "train_log", "step": 3134, "epoch": 1.3521035598705502, "progress_pct": 22.53, "epoch_pct": 22.54, "eta": "42:09:20", "max_grad_norm": 1.0, "loss": 0.7340229153633118, "grad_norm": 0.4476810693740845, "learning_rate": 0.00018795045021900144}
+{"ts": "2025-12-24T02:44:28", "event": "train_log", "step": 3136, "epoch": 1.3529665587918016, "progress_pct": 22.55, "epoch_pct": 22.55, "eta": "42:08:08", "max_grad_norm": 1.0, "loss": 0.6678531765937805, "grad_norm": 0.3931216895580292, "learning_rate": 0.00018792707026333734}
+{"ts": "2025-12-24T02:44:42", "event": "train_log", "step": 3138, "epoch": 1.3538295577130528, "progress_pct": 22.56, "epoch_pct": 22.56, "eta": "42:06:53", "max_grad_norm": 1.0, "loss": 0.8059957027435303, "grad_norm": 0.4768988788127899, "learning_rate": 0.0001879036691044566}
+{"ts": "2025-12-24T02:44:56", "event": "train_log", "step": 3140, "epoch": 1.3546925566343042, "progress_pct": 22.58, "epoch_pct": 22.58, "eta": "42:05:37", "max_grad_norm": 1.0, "loss": 0.7618262767791748, "grad_norm": 0.4464127719402313, "learning_rate": 0.00018788024674800234}
+{"ts": "2025-12-24T02:45:11", "event": "train_log", "step": 3142, "epoch": 1.3555555555555556, "progress_pct": 22.59, "epoch_pct": 22.59, "eta": "42:04:23", "max_grad_norm": 1.0, "loss": 0.7277366518974304, "grad_norm": 0.4115859866142273, "learning_rate": 0.00018785680319962272}
+{"ts": "2025-12-24T02:45:27", "event": "train_log", "step": 3144, "epoch": 1.3564185544768068, "progress_pct": 22.61, "epoch_pct": 22.61, "eta": "42:03:12", "max_grad_norm": 1.0, "loss": 0.7587567567825317, "grad_norm": 0.40479758381843567, "learning_rate": 0.0001878333384649711}
+{"ts": "2025-12-24T02:45:41", "event": "train_log", "step": 3146, "epoch": 1.3572815533980582, "progress_pct": 22.62, "epoch_pct": 22.62, "eta": "42:01:55", "max_grad_norm": 1.0, "loss": 0.7896765470504761, "grad_norm": 0.5233479738235474, "learning_rate": 0.00018780985254970584}
+{"ts": "2025-12-24T02:45:55", "event": "train_log", "step": 3148, "epoch": 1.3581445523193096, "progress_pct": 22.63, "epoch_pct": 22.64, "eta": "42:00:40", "max_grad_norm": 1.0, "loss": 0.8300224542617798, "grad_norm": 0.5604038834571838, "learning_rate": 0.00018778634545949053}
+{"ts": "2025-12-24T02:46:09", "event": "train_log", "step": 3150, "epoch": 1.3590075512405608, "progress_pct": 22.65, "epoch_pct": 22.65, "eta": "41:59:24", "max_grad_norm": 1.0, "loss": 0.8129078149795532, "grad_norm": 0.48418891429901123, "learning_rate": 0.00018776281719999372}
+{"ts": "2025-12-24T02:46:23", "event": "train_log", "step": 3152, "epoch": 1.3598705501618122, "progress_pct": 22.66, "epoch_pct": 22.66, "eta": "41:58:09", "max_grad_norm": 1.0, "loss": 0.72742760181427, "grad_norm": 0.4338721036911011, "learning_rate": 0.00018773926777688918}
+{"ts": "2025-12-24T02:46:38", "event": "train_log", "step": 3154, "epoch": 1.3607335490830637, "progress_pct": 22.68, "epoch_pct": 22.68, "eta": "41:56:54", "max_grad_norm": 1.0, "loss": 0.8129846453666687, "grad_norm": 0.48870885372161865, "learning_rate": 0.00018771569719585576}
+{"ts": "2025-12-24T02:46:53", "event": "train_log", "step": 3156, "epoch": 1.361596548004315, "progress_pct": 22.69, "epoch_pct": 22.69, "eta": "41:55:42", "max_grad_norm": 1.0, "loss": 0.7692790031433105, "grad_norm": 0.5070347785949707, "learning_rate": 0.00018769210546257736}
+{"ts": "2025-12-24T02:47:08", "event": "train_log", "step": 3158, "epoch": 1.3624595469255665, "progress_pct": 22.71, "epoch_pct": 22.71, "eta": "41:54:29", "max_grad_norm": 1.0, "loss": 0.6610854864120483, "grad_norm": 0.4609982669353485, "learning_rate": 0.0001876684925827431}
+{"ts": "2025-12-24T02:47:23", "event": "train_log", "step": 3160, "epoch": 1.3633225458468177, "progress_pct": 22.72, "epoch_pct": 22.72, "eta": "41:53:17", "max_grad_norm": 1.0, "loss": 0.7724031805992126, "grad_norm": 0.4481177031993866, "learning_rate": 0.000187644858562047}
+{"ts": "2025-12-24T02:47:39", "event": "train_log", "step": 3162, "epoch": 1.364185544768069, "progress_pct": 22.74, "epoch_pct": 22.74, "eta": "41:52:07", "max_grad_norm": 1.0, "loss": 0.7166935801506042, "grad_norm": 0.38047513365745544, "learning_rate": 0.0001876212034061884}
+{"ts": "2025-12-24T02:47:54", "event": "train_log", "step": 3164, "epoch": 1.3650485436893205, "progress_pct": 22.75, "epoch_pct": 22.75, "eta": "41:50:55", "max_grad_norm": 1.0, "loss": 0.7535263299942017, "grad_norm": 0.4010603427886963, "learning_rate": 0.00018759752712087157}
+{"ts": "2025-12-24T02:48:08", "event": "train_log", "step": 3166, "epoch": 1.3659115426105717, "progress_pct": 22.76, "epoch_pct": 22.77, "eta": "41:49:41", "max_grad_norm": 1.0, "loss": 0.7471357583999634, "grad_norm": 0.411430299282074, "learning_rate": 0.00018757382971180598}
+{"ts": "2025-12-24T02:48:23", "event": "train_log", "step": 3168, "epoch": 1.366774541531823, "progress_pct": 22.78, "epoch_pct": 22.78, "eta": "41:48:29", "max_grad_norm": 1.0, "loss": 0.6910786032676697, "grad_norm": 0.36775025725364685, "learning_rate": 0.00018755011118470617}
+{"ts": "2025-12-24T02:48:38", "event": "train_log", "step": 3170, "epoch": 1.3676375404530745, "progress_pct": 22.79, "epoch_pct": 22.79, "eta": "41:47:15", "max_grad_norm": 1.0, "loss": 0.7566528916358948, "grad_norm": 0.5100153684616089, "learning_rate": 0.0001875263715452917}
+{"ts": "2025-12-24T02:48:53", "event": "train_log", "step": 3172, "epoch": 1.3685005393743257, "progress_pct": 22.81, "epoch_pct": 22.81, "eta": "41:46:02", "max_grad_norm": 1.0, "loss": 0.722017765045166, "grad_norm": 0.43466782569885254, "learning_rate": 0.00018750261079928727}
+{"ts": "2025-12-24T02:49:08", "event": "train_log", "step": 3174, "epoch": 1.369363538295577, "progress_pct": 22.82, "epoch_pct": 22.82, "eta": "41:44:50", "max_grad_norm": 1.0, "loss": 0.7369917035102844, "grad_norm": 0.4221585988998413, "learning_rate": 0.00018747882895242275}
+{"ts": "2025-12-24T02:49:22", "event": "train_log", "step": 3176, "epoch": 1.3702265372168285, "progress_pct": 22.84, "epoch_pct": 22.84, "eta": "41:43:38", "max_grad_norm": 1.0, "loss": 0.7522714138031006, "grad_norm": 0.4663652777671814, "learning_rate": 0.00018745502601043298}
+{"ts": "2025-12-24T02:49:37", "event": "train_log", "step": 3178, "epoch": 1.3710895361380797, "progress_pct": 22.85, "epoch_pct": 22.85, "eta": "41:42:24", "max_grad_norm": 1.0, "loss": 0.7403551340103149, "grad_norm": 0.4493909478187561, "learning_rate": 0.0001874312019790579}
+{"ts": "2025-12-24T02:49:52", "event": "train_log", "step": 3180, "epoch": 1.3719525350593311, "progress_pct": 22.86, "epoch_pct": 22.87, "eta": "41:41:13", "max_grad_norm": 1.0, "loss": 0.6998772025108337, "grad_norm": 0.4245595932006836, "learning_rate": 0.00018740735686404266}
+{"ts": "2025-12-24T02:50:07", "event": "train_log", "step": 3182, "epoch": 1.3728155339805825, "progress_pct": 22.88, "epoch_pct": 22.88, "eta": "41:40:02", "max_grad_norm": 1.0, "loss": 0.6735976934432983, "grad_norm": 0.4703865051269531, "learning_rate": 0.00018738349067113735}
+{"ts": "2025-12-24T02:50:22", "event": "train_log", "step": 3184, "epoch": 1.373678532901834, "progress_pct": 22.89, "epoch_pct": 22.89, "eta": "41:38:49", "max_grad_norm": 1.0, "loss": 0.764581561088562, "grad_norm": 0.5369067788124084, "learning_rate": 0.00018735960340609715}
+{"ts": "2025-12-24T02:50:38", "event": "train_log", "step": 3186, "epoch": 1.3745415318230851, "progress_pct": 22.91, "epoch_pct": 22.91, "eta": "41:37:42", "max_grad_norm": 1.0, "loss": 0.7491477131843567, "grad_norm": 0.4964922368526459, "learning_rate": 0.00018733569507468242}
+{"ts": "2025-12-24T02:50:54", "event": "train_log", "step": 3188, "epoch": 1.3754045307443366, "progress_pct": 22.92, "epoch_pct": 22.92, "eta": "41:36:32", "max_grad_norm": 1.0, "loss": 0.687139093875885, "grad_norm": 0.4167616665363312, "learning_rate": 0.00018731176568265854}
+{"ts": "2025-12-24T02:51:09", "event": "train_log", "step": 3190, "epoch": 1.376267529665588, "progress_pct": 22.94, "epoch_pct": 22.94, "eta": "41:35:20", "max_grad_norm": 1.0, "loss": 0.76422518491745, "grad_norm": 0.4885561764240265, "learning_rate": 0.00018728781523579598}
+{"ts": "2025-12-24T02:51:24", "event": "train_log", "step": 3192, "epoch": 1.3771305285868394, "progress_pct": 22.95, "epoch_pct": 22.95, "eta": "41:34:10", "max_grad_norm": 1.0, "loss": 0.7054057121276855, "grad_norm": 0.45865342020988464, "learning_rate": 0.00018726384373987025}
+{"ts": "2025-12-24T02:51:39", "event": "train_log", "step": 3194, "epoch": 1.3779935275080906, "progress_pct": 22.97, "epoch_pct": 22.97, "eta": "41:32:59", "max_grad_norm": 1.0, "loss": 0.7476370334625244, "grad_norm": 0.4557322561740875, "learning_rate": 0.000187239851200662}
+{"ts": "2025-12-24T02:51:55", "event": "train_log", "step": 3196, "epoch": 1.378856526429342, "progress_pct": 22.98, "epoch_pct": 22.98, "eta": "41:31:49", "max_grad_norm": 1.0, "loss": 0.7450100183486938, "grad_norm": 0.4359823763370514, "learning_rate": 0.00018721583762395692}
+{"ts": "2025-12-24T02:52:09", "event": "train_log", "step": 3198, "epoch": 1.3797195253505934, "progress_pct": 22.99, "epoch_pct": 23.0, "eta": "41:30:37", "max_grad_norm": 1.0, "loss": 0.6332225799560547, "grad_norm": 0.45140165090560913, "learning_rate": 0.00018719180301554576}
+{"ts": "2025-12-24T02:52:25", "event": "train_log", "step": 3200, "epoch": 1.3805825242718446, "progress_pct": 23.01, "epoch_pct": 23.01, "eta": "41:29:28", "max_grad_norm": 1.0, "loss": 0.6999903917312622, "grad_norm": 0.4051663875579834, "learning_rate": 0.00018716774738122436}
+{"ts": "2025-12-24T03:03:33", "event": "train_log", "step": 3200, "epoch": 1.3805825242718446, "progress_pct": 23.01, "epoch_pct": 23.01, "eta": "42:06:45", "max_grad_norm": 1.0, "eval_loss": 0.8053163290023804, "eval_runtime": 668.3288, "eval_samples_per_second": 3.082, "eval_steps_per_second": 3.082}
+{"ts": "2025-12-24T03:03:49", "event": "train_log", "step": 3202, "epoch": 1.381445523193096, "progress_pct": 23.02, "epoch_pct": 23.02, "eta": "42:05:34", "max_grad_norm": 1.0, "loss": 0.675305962562561, "grad_norm": 0.43624332547187805, "learning_rate": 0.00018714367072679365}
+{"ts": "2025-12-24T03:04:04", "event": "train_log", "step": 3204, "epoch": 1.3823085221143474, "progress_pct": 23.04, "epoch_pct": 23.04, "eta": "42:04:21", "max_grad_norm": 1.0, "loss": 0.8098652958869934, "grad_norm": 0.5163410902023315, "learning_rate": 0.00018711957305805955}
+{"ts": "2025-12-24T03:04:20", "event": "train_log", "step": 3206, "epoch": 1.3831715210355986, "progress_pct": 23.05, "epoch_pct": 23.05, "eta": "42:03:11", "max_grad_norm": 1.0, "loss": 0.7265567779541016, "grad_norm": 0.5261862277984619, "learning_rate": 0.00018709545438083317}
+{"ts": "2025-12-24T03:04:35", "event": "train_log", "step": 3208, "epoch": 1.38403451995685, "progress_pct": 23.07, "epoch_pct": 23.07, "eta": "42:01:58", "max_grad_norm": 1.0, "loss": 0.8171496987342834, "grad_norm": 0.5289353728294373, "learning_rate": 0.0001870713147009306}
+{"ts": "2025-12-24T03:04:51", "event": "train_log", "step": 3210, "epoch": 1.3848975188781014, "progress_pct": 23.08, "epoch_pct": 23.08, "eta": "42:00:50", "max_grad_norm": 1.0, "loss": 0.800773024559021, "grad_norm": 0.45589691400527954, "learning_rate": 0.000187047154024173}
+{"ts": "2025-12-24T03:05:05", "event": "train_log", "step": 3212, "epoch": 1.3857605177993528, "progress_pct": 23.09, "epoch_pct": 23.1, "eta": "41:59:36", "max_grad_norm": 1.0, "loss": 0.7034035921096802, "grad_norm": 0.4709073603153229, "learning_rate": 0.00018702297235638664}
+{"ts": "2025-12-24T03:05:22", "event": "train_log", "step": 3214, "epoch": 1.386623516720604, "progress_pct": 23.11, "epoch_pct": 23.11, "eta": "41:58:27", "max_grad_norm": 1.0, "loss": 0.6707210540771484, "grad_norm": 0.41431429982185364, "learning_rate": 0.00018699876970340278}
+{"ts": "2025-12-24T03:05:36", "event": "train_log", "step": 3216, "epoch": 1.3874865156418554, "progress_pct": 23.12, "epoch_pct": 23.12, "eta": "41:57:14", "max_grad_norm": 1.0, "loss": 0.7554471492767334, "grad_norm": 0.4663850963115692, "learning_rate": 0.0001869745460710578}
+{"ts": "2025-12-24T03:05:51", "event": "train_log", "step": 3218, "epoch": 1.3883495145631068, "progress_pct": 23.14, "epoch_pct": 23.14, "eta": "41:56:02", "max_grad_norm": 1.0, "loss": 0.6852688193321228, "grad_norm": 0.3720403015613556, "learning_rate": 0.00018695030146519313}
+{"ts": "2025-12-24T03:06:06", "event": "train_log", "step": 3220, "epoch": 1.3892125134843583, "progress_pct": 23.15, "epoch_pct": 23.15, "eta": "41:54:50", "max_grad_norm": 1.0, "loss": 0.7974506616592407, "grad_norm": 0.46755164861679077, "learning_rate": 0.00018692603589165523}
+{"ts": "2025-12-24T03:06:23", "event": "train_log", "step": 3222, "epoch": 1.3900755124056094, "progress_pct": 23.17, "epoch_pct": 23.17, "eta": "41:53:42", "max_grad_norm": 1.0, "loss": 0.6643959283828735, "grad_norm": 0.4087965786457062, "learning_rate": 0.00018690174935629563}
+{"ts": "2025-12-24T03:06:38", "event": "train_log", "step": 3224, "epoch": 1.3909385113268609, "progress_pct": 23.18, "epoch_pct": 23.18, "eta": "41:52:30", "max_grad_norm": 1.0, "loss": 0.6455117464065552, "grad_norm": 0.43572601675987244, "learning_rate": 0.00018687744186497092}
+{"ts": "2025-12-24T03:06:52", "event": "train_log", "step": 3226, "epoch": 1.3918015102481123, "progress_pct": 23.2, "epoch_pct": 23.2, "eta": "41:51:17", "max_grad_norm": 1.0, "loss": 0.7152265310287476, "grad_norm": 0.4832928776741028, "learning_rate": 0.00018685311342354276}
+{"ts": "2025-12-24T03:07:07", "event": "train_log", "step": 3228, "epoch": 1.3926645091693635, "progress_pct": 23.21, "epoch_pct": 23.21, "eta": "41:50:05", "max_grad_norm": 1.0, "loss": 0.714832067489624, "grad_norm": 0.44429874420166016, "learning_rate": 0.00018682876403787783}
+{"ts": "2025-12-24T03:07:22", "event": "train_log", "step": 3230, "epoch": 1.3935275080906149, "progress_pct": 23.22, "epoch_pct": 23.23, "eta": "41:48:51", "max_grad_norm": 1.0, "loss": 0.7785174250602722, "grad_norm": 0.4570554494857788, "learning_rate": 0.0001868043937138479}
+{"ts": "2025-12-24T03:07:37", "event": "train_log", "step": 3232, "epoch": 1.3943905070118663, "progress_pct": 23.24, "epoch_pct": 23.24, "eta": "41:47:40", "max_grad_norm": 1.0, "loss": 0.7226384878158569, "grad_norm": 0.4618188738822937, "learning_rate": 0.00018678000245732972}
+{"ts": "2025-12-24T03:07:52", "event": "train_log", "step": 3234, "epoch": 1.3952535059331175, "progress_pct": 23.25, "epoch_pct": 23.25, "eta": "41:46:27", "max_grad_norm": 1.0, "loss": 0.741666316986084, "grad_norm": 0.5473061203956604, "learning_rate": 0.00018675559027420515}
+{"ts": "2025-12-24T03:08:07", "event": "train_log", "step": 3236, "epoch": 1.396116504854369, "progress_pct": 23.27, "epoch_pct": 23.27, "eta": "41:45:15", "max_grad_norm": 1.0, "loss": 0.7774195671081543, "grad_norm": 0.45633625984191895, "learning_rate": 0.0001867311571703611}
+{"ts": "2025-12-24T03:08:21", "event": "train_log", "step": 3238, "epoch": 1.3969795037756203, "progress_pct": 23.28, "epoch_pct": 23.28, "eta": "41:44:03", "max_grad_norm": 1.0, "loss": 0.7062699794769287, "grad_norm": 0.4549288749694824, "learning_rate": 0.00018670670315168946}
+{"ts": "2025-12-24T03:08:35", "event": "train_log", "step": 3240, "epoch": 1.3978425026968715, "progress_pct": 23.3, "epoch_pct": 23.3, "eta": "41:42:49", "max_grad_norm": 1.0, "loss": 0.7901433110237122, "grad_norm": 0.4530162513256073, "learning_rate": 0.00018668222822408725}
+{"ts": "2025-12-24T03:08:50", "event": "train_log", "step": 3242, "epoch": 1.398705501618123, "progress_pct": 23.31, "epoch_pct": 23.31, "eta": "41:41:35", "max_grad_norm": 1.0, "loss": 0.7321763038635254, "grad_norm": 0.4526861608028412, "learning_rate": 0.00018665773239345647}
+{"ts": "2025-12-24T03:09:04", "event": "train_log", "step": 3244, "epoch": 1.3995685005393743, "progress_pct": 23.32, "epoch_pct": 23.33, "eta": "41:40:21", "max_grad_norm": 1.0, "loss": 0.780885636806488, "grad_norm": 0.471683531999588, "learning_rate": 0.00018663321566570417}
+{"ts": "2025-12-24T03:09:18", "event": "train_log", "step": 3246, "epoch": 1.4004314994606257, "progress_pct": 23.34, "epoch_pct": 23.34, "eta": "41:39:08", "max_grad_norm": 1.0, "loss": 0.7124532461166382, "grad_norm": 0.4421135187149048, "learning_rate": 0.00018660867804674248}
+{"ts": "2025-12-24T03:09:33", "event": "train_log", "step": 3248, "epoch": 1.4012944983818771, "progress_pct": 23.35, "epoch_pct": 23.35, "eta": "41:37:57", "max_grad_norm": 1.0, "loss": 0.7868198156356812, "grad_norm": 0.45071855187416077, "learning_rate": 0.00018658411954248849}
+{"ts": "2025-12-24T03:09:48", "event": "train_log", "step": 3250, "epoch": 1.4021574973031283, "progress_pct": 23.37, "epoch_pct": 23.37, "eta": "41:36:45", "max_grad_norm": 1.0, "loss": 0.7364398837089539, "grad_norm": 0.45456045866012573, "learning_rate": 0.0001865595401588644}
+{"ts": "2025-12-24T03:10:03", "event": "train_log", "step": 3252, "epoch": 1.4030204962243797, "progress_pct": 23.38, "epoch_pct": 23.38, "eta": "41:35:34", "max_grad_norm": 1.0, "loss": 0.7381253838539124, "grad_norm": 0.4487321972846985, "learning_rate": 0.0001865349399017974}
+{"ts": "2025-12-24T03:10:18", "event": "train_log", "step": 3254, "epoch": 1.4038834951456312, "progress_pct": 23.4, "epoch_pct": 23.4, "eta": "41:34:22", "max_grad_norm": 1.0, "loss": 0.6974755525588989, "grad_norm": 0.433517724275589, "learning_rate": 0.00018651031877721976}
+{"ts": "2025-12-24T03:10:33", "event": "train_log", "step": 3256, "epoch": 1.4047464940668823, "progress_pct": 23.41, "epoch_pct": 23.41, "eta": "41:33:10", "max_grad_norm": 1.0, "loss": 0.7638785243034363, "grad_norm": 0.45759329199790955, "learning_rate": 0.00018648567679106873}
+{"ts": "2025-12-24T03:10:48", "event": "train_log", "step": 3258, "epoch": 1.4056094929881338, "progress_pct": 23.43, "epoch_pct": 23.43, "eta": "41:31:59", "max_grad_norm": 1.0, "loss": 0.7301747798919678, "grad_norm": 0.4451565742492676, "learning_rate": 0.00018646101394928662}
+{"ts": "2025-12-24T03:11:02", "event": "train_log", "step": 3260, "epoch": 1.4064724919093852, "progress_pct": 23.44, "epoch_pct": 23.44, "eta": "41:30:46", "max_grad_norm": 1.0, "loss": 0.770787239074707, "grad_norm": 0.5451349020004272, "learning_rate": 0.0001864363302578208}
+{"ts": "2025-12-24T03:11:16", "event": "train_log", "step": 3262, "epoch": 1.4073354908306364, "progress_pct": 23.45, "epoch_pct": 23.46, "eta": "41:29:31", "max_grad_norm": 1.0, "loss": 0.7637011408805847, "grad_norm": 0.47335579991340637, "learning_rate": 0.00018641162572262355}
+{"ts": "2025-12-24T03:11:30", "event": "train_log", "step": 3264, "epoch": 1.4081984897518878, "progress_pct": 23.47, "epoch_pct": 23.47, "eta": "41:28:19", "max_grad_norm": 1.0, "loss": 0.7140913009643555, "grad_norm": 0.480887234210968, "learning_rate": 0.0001863869003496523}
+{"ts": "2025-12-24T03:11:45", "event": "train_log", "step": 3266, "epoch": 1.4090614886731392, "progress_pct": 23.48, "epoch_pct": 23.48, "eta": "41:27:08", "max_grad_norm": 1.0, "loss": 0.6538959741592407, "grad_norm": 0.4122021496295929, "learning_rate": 0.0001863621541448695}
+{"ts": "2025-12-24T03:12:00", "event": "train_log", "step": 3268, "epoch": 1.4099244875943904, "progress_pct": 23.5, "epoch_pct": 23.5, "eta": "41:25:57", "max_grad_norm": 1.0, "loss": 0.7153927087783813, "grad_norm": 0.4456968605518341, "learning_rate": 0.00018633738711424253}
+{"ts": "2025-12-24T03:12:15", "event": "train_log", "step": 3270, "epoch": 1.4107874865156418, "progress_pct": 23.51, "epoch_pct": 23.51, "eta": "41:24:48", "max_grad_norm": 1.0, "loss": 0.7140036821365356, "grad_norm": 0.4152887761592865, "learning_rate": 0.00018631259926374388}
+{"ts": "2025-12-24T03:12:31", "event": "train_log", "step": 3272, "epoch": 1.4116504854368932, "progress_pct": 23.53, "epoch_pct": 23.53, "eta": "41:23:39", "max_grad_norm": 1.0, "loss": 0.7193810939788818, "grad_norm": 0.47110119462013245, "learning_rate": 0.00018628779059935103}
+{"ts": "2025-12-24T03:12:45", "event": "train_log", "step": 3274, "epoch": 1.4125134843581446, "progress_pct": 23.54, "epoch_pct": 23.54, "eta": "41:22:28", "max_grad_norm": 1.0, "loss": 0.7133702039718628, "grad_norm": 0.39739692211151123, "learning_rate": 0.0001862629611270464}
+{"ts": "2025-12-24T03:12:59", "event": "train_log", "step": 3276, "epoch": 1.413376483279396, "progress_pct": 23.55, "epoch_pct": 23.56, "eta": "41:21:13", "max_grad_norm": 1.0, "loss": 0.811927855014801, "grad_norm": 0.4808974862098694, "learning_rate": 0.00018623811085281765}
+{"ts": "2025-12-24T03:13:13", "event": "train_log", "step": 3278, "epoch": 1.4142394822006472, "progress_pct": 23.57, "epoch_pct": 23.57, "eta": "41:19:59", "max_grad_norm": 1.0, "loss": 0.8125779032707214, "grad_norm": 0.4607976973056793, "learning_rate": 0.00018621323978265718}
+{"ts": "2025-12-24T03:13:28", "event": "train_log", "step": 3280, "epoch": 1.4151024811218986, "progress_pct": 23.58, "epoch_pct": 23.59, "eta": "41:18:49", "max_grad_norm": 1.0, "loss": 0.7065606117248535, "grad_norm": 0.41523823142051697, "learning_rate": 0.00018618834792256261}
+{"ts": "2025-12-24T03:13:43", "event": "train_log", "step": 3282, "epoch": 1.41596548004315, "progress_pct": 23.6, "epoch_pct": 23.6, "eta": "41:17:38", "max_grad_norm": 1.0, "loss": 0.7346477508544922, "grad_norm": 0.46665191650390625, "learning_rate": 0.00018616343527853645}
+{"ts": "2025-12-24T03:13:57", "event": "train_log", "step": 3284, "epoch": 1.4168284789644012, "progress_pct": 23.61, "epoch_pct": 23.61, "eta": "41:16:25", "max_grad_norm": 1.0, "loss": 0.7590131759643555, "grad_norm": 0.4744371473789215, "learning_rate": 0.00018613850185658634}
+{"ts": "2025-12-24T03:14:12", "event": "train_log", "step": 3286, "epoch": 1.4176914778856526, "progress_pct": 23.63, "epoch_pct": 23.63, "eta": "41:15:14", "max_grad_norm": 1.0, "loss": 0.786243200302124, "grad_norm": 0.4905717074871063, "learning_rate": 0.0001861135476627248}
+{"ts": "2025-12-24T03:14:27", "event": "train_log", "step": 3288, "epoch": 1.418554476806904, "progress_pct": 23.64, "epoch_pct": 23.64, "eta": "41:14:06", "max_grad_norm": 1.0, "loss": 0.6855072379112244, "grad_norm": 0.45114004611968994, "learning_rate": 0.00018608857270296944}
+{"ts": "2025-12-24T03:14:41", "event": "train_log", "step": 3290, "epoch": 1.4194174757281552, "progress_pct": 23.66, "epoch_pct": 23.66, "eta": "41:12:54", "max_grad_norm": 1.0, "loss": 0.8294073343276978, "grad_norm": 0.5547319054603577, "learning_rate": 0.00018606357698334284}
+{"ts": "2025-12-24T03:14:56", "event": "train_log", "step": 3292, "epoch": 1.4202804746494067, "progress_pct": 23.67, "epoch_pct": 23.67, "eta": "41:11:45", "max_grad_norm": 1.0, "loss": 0.6352306604385376, "grad_norm": 0.4100660979747772, "learning_rate": 0.00018603856050987267}
+{"ts": "2025-12-24T03:15:10", "event": "train_log", "step": 3294, "epoch": 1.421143473570658, "progress_pct": 23.68, "epoch_pct": 23.69, "eta": "41:10:32", "max_grad_norm": 1.0, "loss": 0.7822797298431396, "grad_norm": 0.47723907232284546, "learning_rate": 0.00018601352328859148}
+{"ts": "2025-12-24T03:15:25", "event": "train_log", "step": 3296, "epoch": 1.4220064724919093, "progress_pct": 23.7, "epoch_pct": 23.7, "eta": "41:09:21", "max_grad_norm": 1.0, "loss": 0.7675215601921082, "grad_norm": 0.45811668038368225, "learning_rate": 0.00018598846532553691}
+{"ts": "2025-12-24T03:15:40", "event": "train_log", "step": 3298, "epoch": 1.4228694714131607, "progress_pct": 23.71, "epoch_pct": 23.71, "eta": "41:08:12", "max_grad_norm": 1.0, "loss": 0.7994555234909058, "grad_norm": 0.4794461131095886, "learning_rate": 0.00018596338662675154}
+{"ts": "2025-12-24T03:15:54", "event": "train_log", "step": 3300, "epoch": 1.423732470334412, "progress_pct": 23.73, "epoch_pct": 23.73, "eta": "41:07:00", "max_grad_norm": 1.0, "loss": 0.7676554918289185, "grad_norm": 0.458723783493042, "learning_rate": 0.00018593828719828303}
+{"ts": "2025-12-24T03:26:53", "event": "train_log", "step": 3300, "epoch": 1.423732470334412, "progress_pct": 23.73, "epoch_pct": 23.73, "eta": "41:42:17", "max_grad_norm": 1.0, "eval_loss": 0.8030428886413574, "eval_runtime": 658.5495, "eval_samples_per_second": 3.128, "eval_steps_per_second": 3.128}
+{"ts": "2025-12-24T03:27:08", "event": "train_log", "step": 3302, "epoch": 1.4245954692556635, "progress_pct": 23.74, "epoch_pct": 23.74, "eta": "41:41:06", "max_grad_norm": 1.0, "loss": 0.7642499804496765, "grad_norm": 0.4599555432796478, "learning_rate": 0.00018591316704618397}
+{"ts": "2025-12-24T03:27:23", "event": "train_log", "step": 3304, "epoch": 1.425458468176915, "progress_pct": 23.76, "epoch_pct": 23.76, "eta": "41:39:54", "max_grad_norm": 1.0, "loss": 0.7753090262413025, "grad_norm": 0.5012795925140381, "learning_rate": 0.000185888026176512}
+{"ts": "2025-12-24T03:27:39", "event": "train_log", "step": 3306, "epoch": 1.426321467098166, "progress_pct": 23.77, "epoch_pct": 23.77, "eta": "41:38:47", "max_grad_norm": 1.0, "loss": 0.7226543426513672, "grad_norm": 0.4497458040714264, "learning_rate": 0.00018586286459532967}
+{"ts": "2025-12-24T03:27:54", "event": "train_log", "step": 3308, "epoch": 1.4271844660194175, "progress_pct": 23.78, "epoch_pct": 23.79, "eta": "41:37:37", "max_grad_norm": 1.0, "loss": 0.752973735332489, "grad_norm": 0.47314873337745667, "learning_rate": 0.0001858376823087046}
+{"ts": "2025-12-24T03:28:11", "event": "train_log", "step": 3310, "epoch": 1.428047464940669, "progress_pct": 23.8, "epoch_pct": 23.8, "eta": "41:36:33", "max_grad_norm": 1.0, "loss": 0.7653468251228333, "grad_norm": 0.45765072107315063, "learning_rate": 0.00018581247932270944}
+{"ts": "2025-12-24T03:28:26", "event": "train_log", "step": 3312, "epoch": 1.42891046386192, "progress_pct": 23.81, "epoch_pct": 23.82, "eta": "41:35:21", "max_grad_norm": 1.0, "loss": 0.8080248832702637, "grad_norm": 0.4725930392742157, "learning_rate": 0.0001857872556434217}
+{"ts": "2025-12-24T03:28:42", "event": "train_log", "step": 3314, "epoch": 1.4297734627831715, "progress_pct": 23.83, "epoch_pct": 23.83, "eta": "41:34:15", "max_grad_norm": 1.0, "loss": 0.8083968162536621, "grad_norm": 0.4430061876773834, "learning_rate": 0.00018576201127692402}
+{"ts": "2025-12-24T03:28:58", "event": "train_log", "step": 3316, "epoch": 1.430636461704423, "progress_pct": 23.84, "epoch_pct": 23.84, "eta": "41:33:06", "max_grad_norm": 1.0, "loss": 0.7861490249633789, "grad_norm": 0.4197101294994354, "learning_rate": 0.00018573674622930392}
+{"ts": "2025-12-24T03:29:14", "event": "train_log", "step": 3318, "epoch": 1.4314994606256741, "progress_pct": 23.86, "epoch_pct": 23.86, "eta": "41:31:59", "max_grad_norm": 1.0, "loss": 0.8125455379486084, "grad_norm": 0.4047538936138153, "learning_rate": 0.00018571146050665397}
+{"ts": "2025-12-24T03:29:28", "event": "train_log", "step": 3320, "epoch": 1.4323624595469255, "progress_pct": 23.87, "epoch_pct": 23.87, "eta": "41:30:45", "max_grad_norm": 1.0, "loss": 0.779180645942688, "grad_norm": 0.5689038634300232, "learning_rate": 0.00018568615411507174}
+{"ts": "2025-12-24T03:29:44", "event": "train_log", "step": 3322, "epoch": 1.433225458468177, "progress_pct": 23.89, "epoch_pct": 23.89, "eta": "41:29:38", "max_grad_norm": 1.0, "loss": 0.7555606961250305, "grad_norm": 0.47798338532447815, "learning_rate": 0.00018566082706065969}
+{"ts": "2025-12-24T03:30:00", "event": "train_log", "step": 3324, "epoch": 1.4340884573894281, "progress_pct": 23.9, "epoch_pct": 23.9, "eta": "41:28:31", "max_grad_norm": 1.0, "loss": 0.6761099696159363, "grad_norm": 0.4296347200870514, "learning_rate": 0.00018563547934952537}
+{"ts": "2025-12-24T03:30:16", "event": "train_log", "step": 3326, "epoch": 1.4349514563106796, "progress_pct": 23.91, "epoch_pct": 23.92, "eta": "41:27:24", "max_grad_norm": 1.0, "loss": 0.7465946078300476, "grad_norm": 0.4605977237224579, "learning_rate": 0.00018561011098778126}
+{"ts": "2025-12-24T03:30:31", "event": "train_log", "step": 3328, "epoch": 1.435814455231931, "progress_pct": 23.93, "epoch_pct": 23.93, "eta": "41:26:13", "max_grad_norm": 1.0, "loss": 0.7459924817085266, "grad_norm": 0.48226889967918396, "learning_rate": 0.00018558472198154478}
+{"ts": "2025-12-24T03:30:47", "event": "train_log", "step": 3330, "epoch": 1.4366774541531824, "progress_pct": 23.94, "epoch_pct": 23.94, "eta": "41:25:06", "max_grad_norm": 1.0, "loss": 0.6451191306114197, "grad_norm": 0.4655393362045288, "learning_rate": 0.00018555931233693845}
+{"ts": "2025-12-24T03:31:02", "event": "train_log", "step": 3332, "epoch": 1.4375404530744338, "progress_pct": 23.96, "epoch_pct": 23.96, "eta": "41:23:58", "max_grad_norm": 1.0, "loss": 0.764894962310791, "grad_norm": 0.4614768922328949, "learning_rate": 0.00018553388206008961}
+{"ts": "2025-12-24T03:31:17", "event": "train_log", "step": 3334, "epoch": 1.438403451995685, "progress_pct": 23.97, "epoch_pct": 23.97, "eta": "41:22:48", "max_grad_norm": 1.0, "loss": 0.7709850072860718, "grad_norm": 0.47503674030303955, "learning_rate": 0.00018550843115713072}
+{"ts": "2025-12-24T03:31:32", "event": "train_log", "step": 3336, "epoch": 1.4392664509169364, "progress_pct": 23.99, "epoch_pct": 23.99, "eta": "41:21:38", "max_grad_norm": 1.0, "loss": 0.8470542430877686, "grad_norm": 0.5408021807670593, "learning_rate": 0.00018548295963419914}
+{"ts": "2025-12-24T03:31:46", "event": "train_log", "step": 3338, "epoch": 1.4401294498381878, "progress_pct": 24.0, "epoch_pct": 24.0, "eta": "41:20:26", "max_grad_norm": 1.0, "loss": 0.770861804485321, "grad_norm": 0.44747427105903625, "learning_rate": 0.0001854574674974372}
+{"ts": "2025-12-24T03:32:03", "event": "train_log", "step": 3340, "epoch": 1.440992448759439, "progress_pct": 24.01, "epoch_pct": 24.02, "eta": "41:19:20", "max_grad_norm": 1.0, "loss": 0.6909842491149902, "grad_norm": 0.3823722004890442, "learning_rate": 0.00018543195475299222}
+{"ts": "2025-12-24T03:32:19", "event": "train_log", "step": 3342, "epoch": 1.4418554476806904, "progress_pct": 24.03, "epoch_pct": 24.03, "eta": "41:18:15", "max_grad_norm": 1.0, "loss": 0.7684979438781738, "grad_norm": 0.42207640409469604, "learning_rate": 0.0001854064214070165}
+{"ts": "2025-12-24T03:32:34", "event": "train_log", "step": 3344, "epoch": 1.4427184466019418, "progress_pct": 24.04, "epoch_pct": 24.05, "eta": "41:17:04", "max_grad_norm": 1.0, "loss": 0.754643440246582, "grad_norm": 0.4514349400997162, "learning_rate": 0.00018538086746566724}
+{"ts": "2025-12-24T03:32:49", "event": "train_log", "step": 3346, "epoch": 1.443581445523193, "progress_pct": 24.06, "epoch_pct": 24.06, "eta": "41:15:55", "max_grad_norm": 1.0, "loss": 0.7302715182304382, "grad_norm": 0.4289906620979309, "learning_rate": 0.0001853552929351067}
+{"ts": "2025-12-24T03:33:04", "event": "train_log", "step": 3348, "epoch": 1.4444444444444444, "progress_pct": 24.07, "epoch_pct": 24.07, "eta": "41:14:46", "max_grad_norm": 1.0, "loss": 0.7611445188522339, "grad_norm": 0.4458511173725128, "learning_rate": 0.00018532969782150205}
+{"ts": "2025-12-24T03:33:19", "event": "train_log", "step": 3350, "epoch": 1.4453074433656958, "progress_pct": 24.09, "epoch_pct": 24.09, "eta": "41:13:37", "max_grad_norm": 1.0, "loss": 0.7713651061058044, "grad_norm": 0.4370715022087097, "learning_rate": 0.00018530408213102546}
+{"ts": "2025-12-24T03:33:35", "event": "train_log", "step": 3352, "epoch": 1.446170442286947, "progress_pct": 24.1, "epoch_pct": 24.1, "eta": "41:12:29", "max_grad_norm": 1.0, "loss": 0.6728963851928711, "grad_norm": 0.40230461955070496, "learning_rate": 0.000185278445869854}
+{"ts": "2025-12-24T03:33:50", "event": "train_log", "step": 3354, "epoch": 1.4470334412081984, "progress_pct": 24.12, "epoch_pct": 24.12, "eta": "41:11:19", "max_grad_norm": 1.0, "loss": 0.7662684321403503, "grad_norm": 0.43601900339126587, "learning_rate": 0.00018525278904416975}
+{"ts": "2025-12-24T03:34:05", "event": "train_log", "step": 3356, "epoch": 1.4478964401294498, "progress_pct": 24.13, "epoch_pct": 24.13, "eta": "41:10:10", "max_grad_norm": 1.0, "loss": 0.8269308805465698, "grad_norm": 0.45813488960266113, "learning_rate": 0.00018522711166015974}
+{"ts": "2025-12-24T03:34:20", "event": "train_log", "step": 3358, "epoch": 1.4487594390507013, "progress_pct": 24.14, "epoch_pct": 24.15, "eta": "41:09:03", "max_grad_norm": 1.0, "loss": 0.8171968460083008, "grad_norm": 0.48386695981025696, "learning_rate": 0.00018520141372401595}
+{"ts": "2025-12-24T03:34:37", "event": "train_log", "step": 3360, "epoch": 1.4496224379719527, "progress_pct": 24.16, "epoch_pct": 24.16, "eta": "41:07:58", "max_grad_norm": 1.0, "loss": 0.8057414889335632, "grad_norm": 0.41737180948257446, "learning_rate": 0.00018517569524193535}
+{"ts": "2025-12-24T03:34:51", "event": "train_log", "step": 3362, "epoch": 1.4504854368932039, "progress_pct": 24.17, "epoch_pct": 24.17, "eta": "41:06:47", "max_grad_norm": 1.0, "loss": 0.7350438833236694, "grad_norm": 0.41048938035964966, "learning_rate": 0.0001851499562201198}
+{"ts": "2025-12-24T03:35:06", "event": "train_log", "step": 3364, "epoch": 1.4513484358144553, "progress_pct": 24.19, "epoch_pct": 24.19, "eta": "41:05:37", "max_grad_norm": 1.0, "loss": 0.7771334052085876, "grad_norm": 0.49414724111557007, "learning_rate": 0.0001851241966647762}
+{"ts": "2025-12-24T03:35:21", "event": "train_log", "step": 3366, "epoch": 1.4522114347357067, "progress_pct": 24.2, "epoch_pct": 24.2, "eta": "41:04:28", "max_grad_norm": 1.0, "loss": 0.8041897416114807, "grad_norm": 0.48357486724853516, "learning_rate": 0.00018509841658211632}
+{"ts": "2025-12-24T03:35:36", "event": "train_log", "step": 3368, "epoch": 1.4530744336569579, "progress_pct": 24.22, "epoch_pct": 24.22, "eta": "41:03:20", "max_grad_norm": 1.0, "loss": 0.7079073786735535, "grad_norm": 0.44553041458129883, "learning_rate": 0.00018507261597835686}
+{"ts": "2025-12-24T03:35:52", "event": "train_log", "step": 3370, "epoch": 1.4539374325782093, "progress_pct": 24.23, "epoch_pct": 24.23, "eta": "41:02:13", "max_grad_norm": 1.0, "loss": 0.7564307451248169, "grad_norm": 0.4198709726333618, "learning_rate": 0.0001850467948597196}
+{"ts": "2025-12-24T03:36:08", "event": "train_log", "step": 3372, "epoch": 1.4548004314994607, "progress_pct": 24.25, "epoch_pct": 24.25, "eta": "41:01:08", "max_grad_norm": 1.0, "loss": 0.6955130696296692, "grad_norm": 0.4005102217197418, "learning_rate": 0.00018502095323243113}
+{"ts": "2025-12-24T03:36:23", "event": "train_log", "step": 3374, "epoch": 1.455663430420712, "progress_pct": 24.26, "epoch_pct": 24.26, "eta": "40:59:59", "max_grad_norm": 1.0, "loss": 0.6564432978630066, "grad_norm": 0.43197157979011536, "learning_rate": 0.00018499509110272308}
+{"ts": "2025-12-24T03:36:39", "event": "train_log", "step": 3376, "epoch": 1.4565264293419633, "progress_pct": 24.27, "epoch_pct": 24.28, "eta": "40:58:54", "max_grad_norm": 1.0, "loss": 0.6715503931045532, "grad_norm": 0.4266451299190521, "learning_rate": 0.00018496920847683196}
+{"ts": "2025-12-24T03:36:53", "event": "train_log", "step": 3378, "epoch": 1.4573894282632147, "progress_pct": 24.29, "epoch_pct": 24.29, "eta": "40:57:43", "max_grad_norm": 1.0, "loss": 0.7800700068473816, "grad_norm": 0.4835279583930969, "learning_rate": 0.00018494330536099926}
+{"ts": "2025-12-24T03:37:07", "event": "train_log", "step": 3380, "epoch": 1.458252427184466, "progress_pct": 24.3, "epoch_pct": 24.3, "eta": "40:56:30", "max_grad_norm": 1.0, "loss": 0.7650374174118042, "grad_norm": 0.5084423422813416, "learning_rate": 0.00018491738176147139}
+{"ts": "2025-12-24T03:37:23", "event": "train_log", "step": 3382, "epoch": 1.4591154261057173, "progress_pct": 24.32, "epoch_pct": 24.32, "eta": "40:55:24", "max_grad_norm": 1.0, "loss": 0.7307957410812378, "grad_norm": 0.41681453585624695, "learning_rate": 0.00018489143768449974}
+{"ts": "2025-12-24T03:37:37", "event": "train_log", "step": 3384, "epoch": 1.4599784250269687, "progress_pct": 24.33, "epoch_pct": 24.33, "eta": "40:54:15", "max_grad_norm": 1.0, "loss": 0.7257798910140991, "grad_norm": 0.4184363782405853, "learning_rate": 0.00018486547313634058}
+{"ts": "2025-12-24T03:37:51", "event": "train_log", "step": 3386, "epoch": 1.4608414239482201, "progress_pct": 24.35, "epoch_pct": 24.35, "eta": "40:53:02", "max_grad_norm": 1.0, "loss": 0.7981155514717102, "grad_norm": 0.5055010318756104, "learning_rate": 0.00018483948812325512}
+{"ts": "2025-12-24T03:38:06", "event": "train_log", "step": 3388, "epoch": 1.4617044228694713, "progress_pct": 24.36, "epoch_pct": 24.36, "eta": "40:51:55", "max_grad_norm": 1.0, "loss": 0.7802942395210266, "grad_norm": 0.4449431300163269, "learning_rate": 0.00018481348265150961}
+{"ts": "2025-12-24T03:38:21", "event": "train_log", "step": 3390, "epoch": 1.4625674217907227, "progress_pct": 24.37, "epoch_pct": 24.38, "eta": "40:50:46", "max_grad_norm": 1.0, "loss": 0.6799795031547546, "grad_norm": 0.3826743960380554, "learning_rate": 0.00018478745672737508}
+{"ts": "2025-12-24T03:38:37", "event": "train_log", "step": 3392, "epoch": 1.4634304207119742, "progress_pct": 24.39, "epoch_pct": 24.39, "eta": "40:49:41", "max_grad_norm": 1.0, "loss": 0.7275620698928833, "grad_norm": 0.4156678318977356, "learning_rate": 0.00018476141035712757}
+{"ts": "2025-12-24T03:38:52", "event": "train_log", "step": 3394, "epoch": 1.4642934196332256, "progress_pct": 24.4, "epoch_pct": 24.4, "eta": "40:48:32", "max_grad_norm": 1.0, "loss": 0.6979914903640747, "grad_norm": 0.47241929173469543, "learning_rate": 0.00018473534354704807}
+{"ts": "2025-12-24T03:39:07", "event": "train_log", "step": 3396, "epoch": 1.4651564185544768, "progress_pct": 24.42, "epoch_pct": 24.42, "eta": "40:47:24", "max_grad_norm": 1.0, "loss": 0.7208709120750427, "grad_norm": 0.4340677261352539, "learning_rate": 0.00018470925630342247}
+{"ts": "2025-12-24T03:39:21", "event": "train_log", "step": 3398, "epoch": 1.4660194174757282, "progress_pct": 24.43, "epoch_pct": 24.43, "eta": "40:46:15", "max_grad_norm": 1.0, "loss": 0.6596860885620117, "grad_norm": 0.39896467328071594, "learning_rate": 0.00018468314863254154}
+{"ts": "2025-12-24T03:39:36", "event": "train_log", "step": 3400, "epoch": 1.4668824163969796, "progress_pct": 24.45, "epoch_pct": 24.45, "eta": "40:45:04", "max_grad_norm": 1.0, "loss": 0.7703273892402649, "grad_norm": 0.4282037317752838, "learning_rate": 0.00018465702054070113}
+{"ts": "2025-12-24T03:50:25", "event": "train_log", "step": 3400, "epoch": 1.4668824163969796, "progress_pct": 24.45, "epoch_pct": 24.45, "eta": "41:18:33", "max_grad_norm": 1.0, "eval_loss": 0.8002338409423828, "eval_runtime": 649.7427, "eval_samples_per_second": 3.17, "eval_steps_per_second": 3.17}
+{"ts": "2025-12-24T03:50:40", "event": "train_log", "step": 3402, "epoch": 1.4677454153182308, "progress_pct": 24.46, "epoch_pct": 24.46, "eta": "41:17:24", "max_grad_norm": 1.0, "loss": 0.740729033946991, "grad_norm": 0.39301496744155884, "learning_rate": 0.00018463087203420182}
+{"ts": "2025-12-24T03:50:55", "event": "train_log", "step": 3404, "epoch": 1.4686084142394822, "progress_pct": 24.48, "epoch_pct": 24.48, "eta": "41:16:14", "max_grad_norm": 1.0, "loss": 0.6625239253044128, "grad_norm": 0.4466440677642822, "learning_rate": 0.00018460470311934923}
+{"ts": "2025-12-24T03:51:13", "event": "train_log", "step": 3406, "epoch": 1.4694714131607336, "progress_pct": 24.49, "epoch_pct": 24.49, "eta": "41:15:13", "max_grad_norm": 1.0, "loss": 0.7232626080513, "grad_norm": 0.48659050464630127, "learning_rate": 0.00018457851380245392}
+{"ts": "2025-12-24T03:51:28", "event": "train_log", "step": 3408, "epoch": 1.4703344120819848, "progress_pct": 24.5, "epoch_pct": 24.51, "eta": "41:14:04", "max_grad_norm": 1.0, "loss": 0.6909189224243164, "grad_norm": 0.44322678446769714, "learning_rate": 0.00018455230408983124}
+{"ts": "2025-12-24T03:51:42", "event": "train_log", "step": 3410, "epoch": 1.4711974110032362, "progress_pct": 24.52, "epoch_pct": 24.52, "eta": "41:12:52", "max_grad_norm": 1.0, "loss": 0.728760302066803, "grad_norm": 0.4537222683429718, "learning_rate": 0.0001845260739878016}
+{"ts": "2025-12-24T03:51:58", "event": "train_log", "step": 3412, "epoch": 1.4720604099244876, "progress_pct": 24.53, "epoch_pct": 24.53, "eta": "41:11:45", "max_grad_norm": 1.0, "loss": 0.6631523966789246, "grad_norm": 0.426753968000412, "learning_rate": 0.0001844998235026903}
+{"ts": "2025-12-24T03:52:13", "event": "train_log", "step": 3414, "epoch": 1.472923408845739, "progress_pct": 24.55, "epoch_pct": 24.55, "eta": "41:10:38", "max_grad_norm": 1.0, "loss": 0.7257310748100281, "grad_norm": 0.46893343329429626, "learning_rate": 0.0001844735526408275}
+{"ts": "2025-12-24T03:52:29", "event": "train_log", "step": 3416, "epoch": 1.4737864077669902, "progress_pct": 24.56, "epoch_pct": 24.56, "eta": "41:09:31", "max_grad_norm": 1.0, "loss": 0.7732333540916443, "grad_norm": 0.41580045223236084, "learning_rate": 0.00018444726140854823}
+{"ts": "2025-12-24T03:52:46", "event": "train_log", "step": 3418, "epoch": 1.4746494066882416, "progress_pct": 24.58, "epoch_pct": 24.58, "eta": "41:08:26", "max_grad_norm": 1.0, "loss": 0.6602647304534912, "grad_norm": 0.42891791462898254, "learning_rate": 0.00018442094981219257}
+{"ts": "2025-12-24T03:53:02", "event": "train_log", "step": 3420, "epoch": 1.475512405609493, "progress_pct": 24.59, "epoch_pct": 24.59, "eta": "41:07:22", "max_grad_norm": 1.0, "loss": 0.7164129018783569, "grad_norm": 0.45967262983322144, "learning_rate": 0.00018439461785810547}
+{"ts": "2025-12-24T03:53:17", "event": "train_log", "step": 3422, "epoch": 1.4763754045307445, "progress_pct": 24.6, "epoch_pct": 24.61, "eta": "41:06:12", "max_grad_norm": 1.0, "loss": 0.7289180755615234, "grad_norm": 0.4251352846622467, "learning_rate": 0.0001843682655526367}
+{"ts": "2025-12-24T03:53:33", "event": "train_log", "step": 3424, "epoch": 1.4772384034519956, "progress_pct": 24.62, "epoch_pct": 24.62, "eta": "41:05:08", "max_grad_norm": 1.0, "loss": 0.7455880641937256, "grad_norm": 0.3898853361606598, "learning_rate": 0.00018434189290214106}
+{"ts": "2025-12-24T03:53:49", "event": "train_log", "step": 3426, "epoch": 1.478101402373247, "progress_pct": 24.63, "epoch_pct": 24.64, "eta": "41:04:02", "max_grad_norm": 1.0, "loss": 0.7042546272277832, "grad_norm": 0.4341840445995331, "learning_rate": 0.00018431549991297815}
+{"ts": "2025-12-24T03:54:04", "event": "train_log", "step": 3428, "epoch": 1.4789644012944985, "progress_pct": 24.65, "epoch_pct": 24.65, "eta": "41:02:54", "max_grad_norm": 1.0, "loss": 0.7600736021995544, "grad_norm": 0.41306495666503906, "learning_rate": 0.00018428908659151252}
+{"ts": "2025-12-24T03:54:20", "event": "train_log", "step": 3430, "epoch": 1.4798274002157497, "progress_pct": 24.66, "epoch_pct": 24.66, "eta": "41:01:48", "max_grad_norm": 1.0, "loss": 0.7219595909118652, "grad_norm": 0.41544052958488464, "learning_rate": 0.00018426265294411363}
+{"ts": "2025-12-24T03:54:35", "event": "train_log", "step": 3432, "epoch": 1.480690399137001, "progress_pct": 24.68, "epoch_pct": 24.68, "eta": "41:00:40", "max_grad_norm": 1.0, "loss": 0.8417305946350098, "grad_norm": 0.45290282368659973, "learning_rate": 0.00018423619897715585}
+{"ts": "2025-12-24T03:54:51", "event": "train_log", "step": 3434, "epoch": 1.4815533980582525, "progress_pct": 24.69, "epoch_pct": 24.69, "eta": "40:59:35", "max_grad_norm": 1.0, "loss": 0.7625543475151062, "grad_norm": 0.4438819885253906, "learning_rate": 0.00018420972469701842}
+{"ts": "2025-12-24T03:55:05", "event": "train_log", "step": 3436, "epoch": 1.4824163969795037, "progress_pct": 24.71, "epoch_pct": 24.71, "eta": "40:58:23", "max_grad_norm": 1.0, "loss": 0.7759302258491516, "grad_norm": 0.49848470091819763, "learning_rate": 0.00018418323011008548}
+{"ts": "2025-12-24T03:55:21", "event": "train_log", "step": 3438, "epoch": 1.483279395900755, "progress_pct": 24.72, "epoch_pct": 24.72, "eta": "40:57:17", "max_grad_norm": 1.0, "loss": 0.6921430826187134, "grad_norm": 0.3774218261241913, "learning_rate": 0.00018415671522274614}
+{"ts": "2025-12-24T03:55:37", "event": "train_log", "step": 3440, "epoch": 1.4841423948220065, "progress_pct": 24.73, "epoch_pct": 24.74, "eta": "40:56:12", "max_grad_norm": 1.0, "loss": 0.6789629459381104, "grad_norm": 0.4494822919368744, "learning_rate": 0.0001841301800413943}
+{"ts": "2025-12-24T03:55:52", "event": "train_log", "step": 3442, "epoch": 1.4850053937432577, "progress_pct": 24.75, "epoch_pct": 24.75, "eta": "40:55:03", "max_grad_norm": 1.0, "loss": 0.6904259324073792, "grad_norm": 0.4084416329860687, "learning_rate": 0.00018410362457242876}
+{"ts": "2025-12-24T03:56:06", "event": "train_log", "step": 3444, "epoch": 1.485868392664509, "progress_pct": 24.76, "epoch_pct": 24.76, "eta": "40:53:53", "max_grad_norm": 1.0, "loss": 0.7037150263786316, "grad_norm": 0.4472881257534027, "learning_rate": 0.0001840770488222533}
+{"ts": "2025-12-24T03:56:21", "event": "train_log", "step": 3446, "epoch": 1.4867313915857605, "progress_pct": 24.78, "epoch_pct": 24.78, "eta": "40:52:46", "max_grad_norm": 1.0, "loss": 0.7732300758361816, "grad_norm": 0.4696385860443115, "learning_rate": 0.0001840504527972766}
+{"ts": "2025-12-24T03:56:38", "event": "train_log", "step": 3448, "epoch": 1.487594390507012, "progress_pct": 24.79, "epoch_pct": 24.79, "eta": "40:51:42", "max_grad_norm": 1.0, "loss": 0.767594039440155, "grad_norm": 0.4683626592159271, "learning_rate": 0.00018402383650391207}
+{"ts": "2025-12-24T03:56:54", "event": "train_log", "step": 3450, "epoch": 1.4884573894282633, "progress_pct": 24.81, "epoch_pct": 24.81, "eta": "40:50:37", "max_grad_norm": 1.0, "loss": 0.8145772218704224, "grad_norm": 0.47404953837394714, "learning_rate": 0.00018399719994857816}
+{"ts": "2025-12-24T03:57:10", "event": "train_log", "step": 3452, "epoch": 1.4893203883495145, "progress_pct": 24.82, "epoch_pct": 24.82, "eta": "40:49:32", "max_grad_norm": 1.0, "loss": 0.784772515296936, "grad_norm": 0.5147852897644043, "learning_rate": 0.00018397054313769814}
+{"ts": "2025-12-24T03:57:25", "event": "train_log", "step": 3454, "epoch": 1.490183387270766, "progress_pct": 24.83, "epoch_pct": 24.84, "eta": "40:48:25", "max_grad_norm": 1.0, "loss": 0.7849431037902832, "grad_norm": 0.5376461744308472, "learning_rate": 0.00018394386607770017}
+{"ts": "2025-12-24T03:57:40", "event": "train_log", "step": 3456, "epoch": 1.4910463861920173, "progress_pct": 24.85, "epoch_pct": 24.85, "eta": "40:47:18", "max_grad_norm": 1.0, "loss": 0.7196945548057556, "grad_norm": 0.4688630700111389, "learning_rate": 0.0001839171687750173}
+{"ts": "2025-12-24T03:57:55", "event": "train_log", "step": 3458, "epoch": 1.4919093851132685, "progress_pct": 24.86, "epoch_pct": 24.87, "eta": "40:46:09", "max_grad_norm": 1.0, "loss": 0.8277292251586914, "grad_norm": 0.5115576386451721, "learning_rate": 0.00018389045123608753}
+{"ts": "2025-12-24T03:58:11", "event": "train_log", "step": 3460, "epoch": 1.49277238403452, "progress_pct": 24.88, "epoch_pct": 24.88, "eta": "40:45:07", "max_grad_norm": 1.0, "loss": 0.7628065943717957, "grad_norm": 0.3999786674976349, "learning_rate": 0.0001838637134673536}
+{"ts": "2025-12-24T03:58:26", "event": "train_log", "step": 3462, "epoch": 1.4936353829557714, "progress_pct": 24.89, "epoch_pct": 24.89, "eta": "40:43:58", "max_grad_norm": 1.0, "loss": 0.717315673828125, "grad_norm": 0.4474492371082306, "learning_rate": 0.00018383695547526322}
+{"ts": "2025-12-24T03:58:42", "event": "train_log", "step": 3464, "epoch": 1.4944983818770226, "progress_pct": 24.91, "epoch_pct": 24.91, "eta": "40:42:53", "max_grad_norm": 1.0, "loss": 0.7365549206733704, "grad_norm": 0.4175044596195221, "learning_rate": 0.00018381017726626896}
+{"ts": "2025-12-24T03:58:57", "event": "train_log", "step": 3466, "epoch": 1.495361380798274, "progress_pct": 24.92, "epoch_pct": 24.92, "eta": "40:41:47", "max_grad_norm": 1.0, "loss": 0.7562727928161621, "grad_norm": 0.4938793480396271, "learning_rate": 0.0001837833788468283}
+{"ts": "2025-12-24T03:59:12", "event": "train_log", "step": 3468, "epoch": 1.4962243797195254, "progress_pct": 24.94, "epoch_pct": 24.94, "eta": "40:40:38", "max_grad_norm": 1.0, "loss": 0.82245272397995, "grad_norm": 0.4369599521160126, "learning_rate": 0.0001837565602234035}
+{"ts": "2025-12-24T03:59:27", "event": "train_log", "step": 3470, "epoch": 1.4970873786407766, "progress_pct": 24.95, "epoch_pct": 24.95, "eta": "40:39:31", "max_grad_norm": 1.0, "loss": 0.7570599913597107, "grad_norm": 0.4824387729167938, "learning_rate": 0.00018372972140246182}
+{"ts": "2025-12-24T03:59:43", "event": "train_log", "step": 3472, "epoch": 1.497950377562028, "progress_pct": 24.96, "epoch_pct": 24.97, "eta": "40:38:27", "max_grad_norm": 1.0, "loss": 0.7152431607246399, "grad_norm": 0.46261459589004517, "learning_rate": 0.00018370286239047522}
+{"ts": "2025-12-24T03:59:59", "event": "train_log", "step": 3474, "epoch": 1.4988133764832794, "progress_pct": 24.98, "epoch_pct": 24.98, "eta": "40:37:24", "max_grad_norm": 1.0, "loss": 0.6635003089904785, "grad_norm": 0.4452435076236725, "learning_rate": 0.0001836759831939207}
+{"ts": "2025-12-24T04:00:15", "event": "train_log", "step": 3476, "epoch": 1.4996763754045308, "progress_pct": 24.99, "epoch_pct": 24.99, "eta": "40:36:18", "max_grad_norm": 1.0, "loss": 0.7814362645149231, "grad_norm": 0.4698450267314911, "learning_rate": 0.0001836490838192801}
+{"ts": "2025-12-24T04:00:30", "event": "train_log", "step": 3478, "epoch": 1.5005393743257822, "progress_pct": 25.01, "epoch_pct": 25.01, "eta": "40:35:12", "max_grad_norm": 1.0, "loss": 0.6941080689430237, "grad_norm": 0.44320493936538696, "learning_rate": 0.00018362216427303998}
+{"ts": "2025-12-24T04:00:45", "event": "train_log", "step": 3480, "epoch": 1.5014023732470334, "progress_pct": 25.02, "epoch_pct": 25.02, "eta": "40:34:05", "max_grad_norm": 1.0, "loss": 0.7583049535751343, "grad_norm": 0.467252254486084, "learning_rate": 0.00018359522456169193}
+{"ts": "2025-12-24T04:01:00", "event": "train_log", "step": 3482, "epoch": 1.5022653721682848, "progress_pct": 25.04, "epoch_pct": 25.04, "eta": "40:32:57", "max_grad_norm": 1.0, "loss": 0.9017908573150635, "grad_norm": 0.5454360842704773, "learning_rate": 0.00018356826469173232}
+{"ts": "2025-12-24T04:01:15", "event": "train_log", "step": 3484, "epoch": 1.5031283710895362, "progress_pct": 25.05, "epoch_pct": 25.05, "eta": "40:31:49", "max_grad_norm": 1.0, "loss": 0.8088064789772034, "grad_norm": 0.5124768614768982, "learning_rate": 0.00018354128466966242}
+{"ts": "2025-12-24T04:01:30", "event": "train_log", "step": 3486, "epoch": 1.5039913700107874, "progress_pct": 25.06, "epoch_pct": 25.07, "eta": "40:30:42", "max_grad_norm": 1.0, "loss": 0.7869967222213745, "grad_norm": 0.4634758234024048, "learning_rate": 0.00018351428450198834}
+{"ts": "2025-12-24T04:01:44", "event": "train_log", "step": 3488, "epoch": 1.5048543689320388, "progress_pct": 25.08, "epoch_pct": 25.08, "eta": "40:29:33", "max_grad_norm": 1.0, "loss": 0.7509294152259827, "grad_norm": 0.39626801013946533, "learning_rate": 0.00018348726419522098}
+{"ts": "2025-12-24T04:02:00", "event": "train_log", "step": 3490, "epoch": 1.5057173678532902, "progress_pct": 25.09, "epoch_pct": 25.1, "eta": "40:28:30", "max_grad_norm": 1.0, "loss": 0.710981011390686, "grad_norm": 0.48879387974739075, "learning_rate": 0.00018346022375587628}
+{"ts": "2025-12-24T04:02:15", "event": "train_log", "step": 3492, "epoch": 1.5065803667745414, "progress_pct": 25.11, "epoch_pct": 25.11, "eta": "40:27:25", "max_grad_norm": 1.0, "loss": 0.7631853222846985, "grad_norm": 0.4784195125102997, "learning_rate": 0.00018343316319047482}
+{"ts": "2025-12-24T04:02:32", "event": "train_log", "step": 3494, "epoch": 1.5074433656957928, "progress_pct": 25.12, "epoch_pct": 25.12, "eta": "40:26:22", "max_grad_norm": 1.0, "loss": 0.7416844964027405, "grad_norm": 0.45802050828933716, "learning_rate": 0.00018340608250554222}
+{"ts": "2025-12-24T04:02:47", "event": "train_log", "step": 3496, "epoch": 1.5083063646170443, "progress_pct": 25.14, "epoch_pct": 25.14, "eta": "40:25:16", "max_grad_norm": 1.0, "loss": 0.8117082715034485, "grad_norm": 0.42670297622680664, "learning_rate": 0.0001833789817076088}
+{"ts": "2025-12-24T04:03:01", "event": "train_log", "step": 3498, "epoch": 1.5091693635382954, "progress_pct": 25.15, "epoch_pct": 25.15, "eta": "40:24:08", "max_grad_norm": 1.0, "loss": 0.724604606628418, "grad_norm": 0.48401451110839844, "learning_rate": 0.00018335186080320983}
+{"ts": "2025-12-24T04:03:16", "event": "train_log", "step": 3500, "epoch": 1.510032362459547, "progress_pct": 25.17, "epoch_pct": 25.17, "eta": "40:23:00", "max_grad_norm": 1.0, "loss": 0.8395941257476807, "grad_norm": 0.5217538475990295, "learning_rate": 0.00018332471979888535}
+{"ts": "2025-12-24T04:14:11", "event": "train_log", "step": 3500, "epoch": 1.510032362459547, "progress_pct": 25.17, "epoch_pct": 25.17, "eta": "40:55:29", "max_grad_norm": 1.0, "eval_loss": 0.7970634698867798, "eval_runtime": 655.3078, "eval_samples_per_second": 3.144, "eval_steps_per_second": 3.144}
+{"ts": "2025-12-24T04:14:27", "event": "train_log", "step": 3502, "epoch": 1.5108953613807983, "progress_pct": 25.18, "epoch_pct": 25.18, "eta": "40:54:23", "max_grad_norm": 1.0, "loss": 0.7151007056236267, "grad_norm": 0.4357616901397705, "learning_rate": 0.00018329755870118033}
+{"ts": "2025-12-24T04:14:41", "event": "train_log", "step": 3504, "epoch": 1.5117583603020495, "progress_pct": 25.19, "epoch_pct": 25.2, "eta": "40:53:14", "max_grad_norm": 1.0, "loss": 0.6745702028274536, "grad_norm": 0.4224613606929779, "learning_rate": 0.00018327037751664454}
+{"ts": "2025-12-24T04:14:56", "event": "train_log", "step": 3506, "epoch": 1.512621359223301, "progress_pct": 25.21, "epoch_pct": 25.21, "eta": "40:52:04", "max_grad_norm": 1.0, "loss": 0.7870205640792847, "grad_norm": 0.4674745500087738, "learning_rate": 0.0001832431762518326}
+{"ts": "2025-12-24T04:15:11", "event": "train_log", "step": 3508, "epoch": 1.5134843581445523, "progress_pct": 25.22, "epoch_pct": 25.22, "eta": "40:50:57", "max_grad_norm": 1.0, "loss": 0.777145504951477, "grad_norm": 0.44136863946914673, "learning_rate": 0.00018321595491330397}
+{"ts": "2025-12-24T04:15:25", "event": "train_log", "step": 3510, "epoch": 1.5143473570658037, "progress_pct": 25.24, "epoch_pct": 25.24, "eta": "40:49:48", "max_grad_norm": 1.0, "loss": 0.7991534471511841, "grad_norm": 0.5091800093650818, "learning_rate": 0.00018318871350762295}
+{"ts": "2025-12-24T04:15:40", "event": "train_log", "step": 3512, "epoch": 1.5152103559870551, "progress_pct": 25.25, "epoch_pct": 25.25, "eta": "40:48:39", "max_grad_norm": 1.0, "loss": 0.7678582072257996, "grad_norm": 0.42728134989738464, "learning_rate": 0.00018316145204135865}
+{"ts": "2025-12-24T04:15:55", "event": "train_log", "step": 3514, "epoch": 1.5160733549083063, "progress_pct": 25.27, "epoch_pct": 25.27, "eta": "40:47:33", "max_grad_norm": 1.0, "loss": 0.7971519231796265, "grad_norm": 0.47067728638648987, "learning_rate": 0.00018313417052108513}
+{"ts": "2025-12-24T04:16:11", "event": "train_log", "step": 3516, "epoch": 1.5169363538295577, "progress_pct": 25.28, "epoch_pct": 25.28, "eta": "40:46:28", "max_grad_norm": 1.0, "loss": 0.7281476259231567, "grad_norm": 0.4250936210155487, "learning_rate": 0.00018310686895338117}
+{"ts": "2025-12-24T04:16:26", "event": "train_log", "step": 3518, "epoch": 1.5177993527508091, "progress_pct": 25.29, "epoch_pct": 25.3, "eta": "40:45:21", "max_grad_norm": 1.0, "loss": 0.7346498966217041, "grad_norm": 0.4261043667793274, "learning_rate": 0.00018307954734483038}
+{"ts": "2025-12-24T04:16:41", "event": "train_log", "step": 3520, "epoch": 1.5186623516720603, "progress_pct": 25.31, "epoch_pct": 25.31, "eta": "40:44:12", "max_grad_norm": 1.0, "loss": 0.765254557132721, "grad_norm": 0.4935494363307953, "learning_rate": 0.0001830522057020213}
+{"ts": "2025-12-24T04:16:56", "event": "train_log", "step": 3522, "epoch": 1.5195253505933117, "progress_pct": 25.32, "epoch_pct": 25.33, "eta": "40:43:05", "max_grad_norm": 1.0, "loss": 0.7073609828948975, "grad_norm": 0.4546700119972229, "learning_rate": 0.00018302484403154718}
+{"ts": "2025-12-24T04:17:11", "event": "train_log", "step": 3524, "epoch": 1.5203883495145631, "progress_pct": 25.34, "epoch_pct": 25.34, "eta": "40:41:59", "max_grad_norm": 1.0, "loss": 0.681342363357544, "grad_norm": 0.4881356656551361, "learning_rate": 0.0001829974623400062}
+{"ts": "2025-12-24T04:17:26", "event": "train_log", "step": 3526, "epoch": 1.5212513484358143, "progress_pct": 25.35, "epoch_pct": 25.35, "eta": "40:40:52", "max_grad_norm": 1.0, "loss": 0.6735935211181641, "grad_norm": 0.4397423565387726, "learning_rate": 0.00018297006063400134}
+{"ts": "2025-12-24T04:17:41", "event": "train_log", "step": 3528, "epoch": 1.522114347357066, "progress_pct": 25.37, "epoch_pct": 25.37, "eta": "40:39:43", "max_grad_norm": 1.0, "loss": 0.721441924571991, "grad_norm": 0.4426570236682892, "learning_rate": 0.00018294263892014038}
+{"ts": "2025-12-24T04:17:55", "event": "train_log", "step": 3530, "epoch": 1.5229773462783172, "progress_pct": 25.38, "epoch_pct": 25.38, "eta": "40:38:34", "max_grad_norm": 1.0, "loss": 0.8269463777542114, "grad_norm": 0.5235413908958435, "learning_rate": 0.00018291519720503599}
+{"ts": "2025-12-24T04:18:10", "event": "train_log", "step": 3532, "epoch": 1.5238403451995683, "progress_pct": 25.4, "epoch_pct": 25.4, "eta": "40:37:27", "max_grad_norm": 1.0, "loss": 0.7080397605895996, "grad_norm": 0.4708006978034973, "learning_rate": 0.00018288773549530557}
+{"ts": "2025-12-24T04:18:24", "event": "train_log", "step": 3534, "epoch": 1.52470334412082, "progress_pct": 25.41, "epoch_pct": 25.41, "eta": "40:36:18", "max_grad_norm": 1.0, "loss": 0.7505635023117065, "grad_norm": 0.47188836336135864, "learning_rate": 0.00018286025379757136}
+{"ts": "2025-12-24T04:18:39", "event": "train_log", "step": 3536, "epoch": 1.5255663430420712, "progress_pct": 25.42, "epoch_pct": 25.43, "eta": "40:35:09", "max_grad_norm": 1.0, "loss": 0.743853747844696, "grad_norm": 0.4706624746322632, "learning_rate": 0.00018283275211846052}
+{"ts": "2025-12-24T04:18:53", "event": "train_log", "step": 3538, "epoch": 1.5264293419633226, "progress_pct": 25.44, "epoch_pct": 25.44, "eta": "40:34:00", "max_grad_norm": 1.0, "loss": 0.7527500987052917, "grad_norm": 0.42075470089912415, "learning_rate": 0.0001828052304646049}
+{"ts": "2025-12-24T04:19:07", "event": "train_log", "step": 3540, "epoch": 1.527292340884574, "progress_pct": 25.45, "epoch_pct": 25.45, "eta": "40:32:51", "max_grad_norm": 1.0, "loss": 0.7295951247215271, "grad_norm": 0.47468745708465576, "learning_rate": 0.00018277768884264123}
+{"ts": "2025-12-24T04:19:21", "event": "train_log", "step": 3542, "epoch": 1.5281553398058252, "progress_pct": 25.47, "epoch_pct": 25.47, "eta": "40:31:42", "max_grad_norm": 1.0, "loss": 0.7707282900810242, "grad_norm": 0.49890658259391785, "learning_rate": 0.00018275012725921106}
+{"ts": "2025-12-24T04:19:36", "event": "train_log", "step": 3544, "epoch": 1.5290183387270766, "progress_pct": 25.48, "epoch_pct": 25.48, "eta": "40:30:35", "max_grad_norm": 1.0, "loss": 0.7032204270362854, "grad_norm": 0.44301101565361023, "learning_rate": 0.00018272254572096076}
+{"ts": "2025-12-24T04:19:52", "event": "train_log", "step": 3546, "epoch": 1.529881337648328, "progress_pct": 25.5, "epoch_pct": 25.5, "eta": "40:29:30", "max_grad_norm": 1.0, "loss": 0.6652095317840576, "grad_norm": 0.4144493043422699, "learning_rate": 0.00018269494423454148}
+{"ts": "2025-12-24T04:20:06", "event": "train_log", "step": 3548, "epoch": 1.5307443365695792, "progress_pct": 25.51, "epoch_pct": 25.51, "eta": "40:28:21", "max_grad_norm": 1.0, "loss": 0.7446690797805786, "grad_norm": 0.41546186804771423, "learning_rate": 0.00018266732280660915}
+{"ts": "2025-12-24T04:20:21", "event": "train_log", "step": 3550, "epoch": 1.5316073354908306, "progress_pct": 25.52, "epoch_pct": 25.53, "eta": "40:27:16", "max_grad_norm": 1.0, "loss": 0.800329327583313, "grad_norm": 0.46266189217567444, "learning_rate": 0.00018263968144382464}
+{"ts": "2025-12-24T04:20:37", "event": "train_log", "step": 3552, "epoch": 1.532470334412082, "progress_pct": 25.54, "epoch_pct": 25.54, "eta": "40:26:12", "max_grad_norm": 1.0, "loss": 0.8398324251174927, "grad_norm": 0.46991246938705444, "learning_rate": 0.00018261202015285347}
+{"ts": "2025-12-24T04:20:54", "event": "train_log", "step": 3554, "epoch": 1.5333333333333332, "progress_pct": 25.55, "epoch_pct": 25.56, "eta": "40:25:10", "max_grad_norm": 1.0, "loss": 0.7080168724060059, "grad_norm": 0.45873361825942993, "learning_rate": 0.00018258433894036605}
+{"ts": "2025-12-24T04:21:08", "event": "train_log", "step": 3556, "epoch": 1.5341963322545846, "progress_pct": 25.57, "epoch_pct": 25.57, "eta": "40:24:01", "max_grad_norm": 1.0, "loss": 0.7790565490722656, "grad_norm": 0.4650769531726837, "learning_rate": 0.00018255663781303758}
+{"ts": "2025-12-24T04:21:24", "event": "train_log", "step": 3558, "epoch": 1.535059331175836, "progress_pct": 25.58, "epoch_pct": 25.58, "eta": "40:22:58", "max_grad_norm": 1.0, "loss": 0.7548949122428894, "grad_norm": 0.4353472590446472, "learning_rate": 0.00018252891677754808}
+{"ts": "2025-12-24T04:21:39", "event": "train_log", "step": 3560, "epoch": 1.5359223300970872, "progress_pct": 25.6, "epoch_pct": 25.6, "eta": "40:21:53", "max_grad_norm": 1.0, "loss": 0.7493187189102173, "grad_norm": 0.4259464740753174, "learning_rate": 0.00018250117584058236}
+{"ts": "2025-12-24T04:21:55", "event": "train_log", "step": 3562, "epoch": 1.5367853290183389, "progress_pct": 25.61, "epoch_pct": 25.61, "eta": "40:20:51", "max_grad_norm": 1.0, "loss": 0.8031244277954102, "grad_norm": 0.4781721234321594, "learning_rate": 0.00018247341500883}
+{"ts": "2025-12-24T04:22:11", "event": "train_log", "step": 3564, "epoch": 1.53764832793959, "progress_pct": 25.63, "epoch_pct": 25.63, "eta": "40:19:47", "max_grad_norm": 1.0, "loss": 0.74393630027771, "grad_norm": 0.4471439719200134, "learning_rate": 0.00018244563428898537}
+{"ts": "2025-12-24T04:22:26", "event": "train_log", "step": 3566, "epoch": 1.5385113268608415, "progress_pct": 25.64, "epoch_pct": 25.64, "eta": "40:18:40", "max_grad_norm": 1.0, "loss": 0.8052780628204346, "grad_norm": 0.4181448519229889, "learning_rate": 0.00018241783368774773}
+{"ts": "2025-12-24T04:22:41", "event": "train_log", "step": 3568, "epoch": 1.5393743257820929, "progress_pct": 25.65, "epoch_pct": 25.66, "eta": "40:17:34", "max_grad_norm": 1.0, "loss": 0.825944721698761, "grad_norm": 0.5136722326278687, "learning_rate": 0.000182390013211821}
+{"ts": "2025-12-24T04:22:56", "event": "train_log", "step": 3570, "epoch": 1.540237324703344, "progress_pct": 25.67, "epoch_pct": 25.67, "eta": "40:16:29", "max_grad_norm": 1.0, "loss": 0.70372474193573, "grad_norm": 0.43782681226730347, "learning_rate": 0.00018236217286791403}
+{"ts": "2025-12-24T04:23:13", "event": "train_log", "step": 3572, "epoch": 1.5411003236245955, "progress_pct": 25.68, "epoch_pct": 25.69, "eta": "40:15:29", "max_grad_norm": 1.0, "loss": 0.7298035621643066, "grad_norm": 0.44272729754447937, "learning_rate": 0.00018233431266274038}
+{"ts": "2025-12-24T04:23:29", "event": "train_log", "step": 3574, "epoch": 1.541963322545847, "progress_pct": 25.7, "epoch_pct": 25.7, "eta": "40:14:26", "max_grad_norm": 1.0, "loss": 0.7507740259170532, "grad_norm": 0.44322386384010315, "learning_rate": 0.00018230643260301838}
+{"ts": "2025-12-24T04:23:44", "event": "train_log", "step": 3576, "epoch": 1.542826321467098, "progress_pct": 25.71, "epoch_pct": 25.71, "eta": "40:13:20", "max_grad_norm": 1.0, "loss": 0.7720011472702026, "grad_norm": 0.48743686079978943, "learning_rate": 0.00018227853269547117}
+{"ts": "2025-12-24T04:23:59", "event": "train_log", "step": 3578, "epoch": 1.5436893203883495, "progress_pct": 25.73, "epoch_pct": 25.73, "eta": "40:12:15", "max_grad_norm": 1.0, "loss": 0.8001248240470886, "grad_norm": 0.4608381390571594, "learning_rate": 0.00018225061294682674}
+{"ts": "2025-12-24T04:24:15", "event": "train_log", "step": 3580, "epoch": 1.544552319309601, "progress_pct": 25.74, "epoch_pct": 25.74, "eta": "40:11:13", "max_grad_norm": 1.0, "loss": 0.7971346378326416, "grad_norm": 0.45625007152557373, "learning_rate": 0.00018222267336381778}
+{"ts": "2025-12-24T04:24:30", "event": "train_log", "step": 3582, "epoch": 1.545415318230852, "progress_pct": 25.75, "epoch_pct": 25.76, "eta": "40:10:07", "max_grad_norm": 1.0, "loss": 0.7254680395126343, "grad_norm": 0.4687005579471588, "learning_rate": 0.00018219471395318178}
+{"ts": "2025-12-24T04:24:47", "event": "train_log", "step": 3584, "epoch": 1.5462783171521035, "progress_pct": 25.77, "epoch_pct": 25.77, "eta": "40:09:05", "max_grad_norm": 1.0, "loss": 0.7372352480888367, "grad_norm": 0.48081183433532715, "learning_rate": 0.00018216673472166108}
+{"ts": "2025-12-24T04:25:03", "event": "train_log", "step": 3586, "epoch": 1.547141316073355, "progress_pct": 25.78, "epoch_pct": 25.79, "eta": "40:08:03", "max_grad_norm": 1.0, "loss": 0.6276986598968506, "grad_norm": 0.42272305488586426, "learning_rate": 0.0001821387356760027}
+{"ts": "2025-12-24T04:25:17", "event": "train_log", "step": 3588, "epoch": 1.5480043149946061, "progress_pct": 25.8, "epoch_pct": 25.8, "eta": "40:06:56", "max_grad_norm": 1.0, "loss": 0.7299351692199707, "grad_norm": 0.42225342988967896, "learning_rate": 0.0001821107168229585}
+{"ts": "2025-12-24T04:25:32", "event": "train_log", "step": 3590, "epoch": 1.5488673139158577, "progress_pct": 25.81, "epoch_pct": 25.81, "eta": "40:05:50", "max_grad_norm": 1.0, "loss": 0.6684783101081848, "grad_norm": 0.4649020731449127, "learning_rate": 0.00018208267816928507}
+{"ts": "2025-12-24T04:25:49", "event": "train_log", "step": 3592, "epoch": 1.549730312837109, "progress_pct": 25.83, "epoch_pct": 25.83, "eta": "40:04:52", "max_grad_norm": 1.0, "loss": 0.6579244136810303, "grad_norm": 0.3961552679538727, "learning_rate": 0.00018205461972174388}
+{"ts": "2025-12-24T04:26:05", "event": "train_log", "step": 3594, "epoch": 1.5505933117583603, "progress_pct": 25.84, "epoch_pct": 25.84, "eta": "40:03:48", "max_grad_norm": 1.0, "loss": 0.6955749988555908, "grad_norm": 0.500170111656189, "learning_rate": 0.00018202654148710102}
+{"ts": "2025-12-24T04:26:21", "event": "train_log", "step": 3596, "epoch": 1.5514563106796118, "progress_pct": 25.86, "epoch_pct": 25.86, "eta": "40:02:46", "max_grad_norm": 1.0, "loss": 0.6725539565086365, "grad_norm": 0.5200181603431702, "learning_rate": 0.00018199844347212746}
+{"ts": "2025-12-24T04:26:36", "event": "train_log", "step": 3598, "epoch": 1.552319309600863, "progress_pct": 25.87, "epoch_pct": 25.87, "eta": "40:01:40", "max_grad_norm": 1.0, "loss": 0.7726914882659912, "grad_norm": 0.4894106984138489, "learning_rate": 0.0001819703256835989}
+{"ts": "2025-12-24T04:26:51", "event": "train_log", "step": 3600, "epoch": 1.5531823085221144, "progress_pct": 25.88, "epoch_pct": 25.89, "eta": "40:00:35", "max_grad_norm": 1.0, "loss": 0.8290923833847046, "grad_norm": 0.487623006105423, "learning_rate": 0.00018194218812829583}
+{"ts": "2025-12-24T04:37:57", "event": "train_log", "step": 3600, "epoch": 1.5531823085221144, "progress_pct": 25.88, "epoch_pct": 25.89, "eta": "40:32:24", "max_grad_norm": 1.0, "eval_loss": 0.7935511469841003, "eval_runtime": 666.5283, "eval_samples_per_second": 3.091, "eval_steps_per_second": 3.091}
+{"ts": "2025-12-24T04:38:13", "event": "train_log", "step": 3602, "epoch": 1.5540453074433658, "progress_pct": 25.9, "epoch_pct": 25.9, "eta": "40:31:18", "max_grad_norm": 1.0, "loss": 0.6819650530815125, "grad_norm": 0.4056689441204071, "learning_rate": 0.0001819140308130035}
+{"ts": "2025-12-24T04:38:28", "event": "train_log", "step": 3604, "epoch": 1.554908306364617, "progress_pct": 25.91, "epoch_pct": 25.92, "eta": "40:30:13", "max_grad_norm": 1.0, "loss": 0.6709993481636047, "grad_norm": 0.4337533712387085, "learning_rate": 0.0001818858537445119}
+{"ts": "2025-12-24T04:38:44", "event": "train_log", "step": 3606, "epoch": 1.5557713052858684, "progress_pct": 25.93, "epoch_pct": 25.93, "eta": "40:29:08", "max_grad_norm": 1.0, "loss": 0.6784732937812805, "grad_norm": 0.4365732967853546, "learning_rate": 0.0001818576569296158}
+{"ts": "2025-12-24T04:38:58", "event": "train_log", "step": 3608, "epoch": 1.5566343042071198, "progress_pct": 25.94, "epoch_pct": 25.94, "eta": "40:28:00", "max_grad_norm": 1.0, "loss": 0.7771052718162537, "grad_norm": 0.4632627069950104, "learning_rate": 0.00018182944037511476}
+{"ts": "2025-12-24T04:39:13", "event": "train_log", "step": 3610, "epoch": 1.557497303128371, "progress_pct": 25.96, "epoch_pct": 25.96, "eta": "40:26:53", "max_grad_norm": 1.0, "loss": 0.8117473125457764, "grad_norm": 0.45411452651023865, "learning_rate": 0.00018180120408781305}
+{"ts": "2025-12-24T04:39:27", "event": "train_log", "step": 3612, "epoch": 1.5583603020496224, "progress_pct": 25.97, "epoch_pct": 25.97, "eta": "40:25:46", "max_grad_norm": 1.0, "loss": 0.7268829941749573, "grad_norm": 0.4931472837924957, "learning_rate": 0.00018177294807451974}
+{"ts": "2025-12-24T04:39:41", "event": "train_log", "step": 3614, "epoch": 1.5592233009708738, "progress_pct": 25.99, "epoch_pct": 25.99, "eta": "40:24:37", "max_grad_norm": 1.0, "loss": 0.7986008524894714, "grad_norm": 0.4711272418498993, "learning_rate": 0.00018174467234204867}
+{"ts": "2025-12-24T04:39:56", "event": "train_log", "step": 3616, "epoch": 1.560086299892125, "progress_pct": 26.0, "epoch_pct": 26.0, "eta": "40:23:30", "max_grad_norm": 1.0, "loss": 0.7606064081192017, "grad_norm": 0.47048646211624146, "learning_rate": 0.00018171637689721833}
+{"ts": "2025-12-24T04:40:11", "event": "train_log", "step": 3618, "epoch": 1.5609492988133766, "progress_pct": 26.01, "epoch_pct": 26.02, "eta": "40:22:24", "max_grad_norm": 1.0, "loss": 0.7444906234741211, "grad_norm": 0.4612944424152374, "learning_rate": 0.00018168806174685212}
+{"ts": "2025-12-24T04:40:26", "event": "train_log", "step": 3620, "epoch": 1.5618122977346278, "progress_pct": 26.03, "epoch_pct": 26.03, "eta": "40:21:17", "max_grad_norm": 1.0, "loss": 0.7393948435783386, "grad_norm": 0.4275529980659485, "learning_rate": 0.00018165972689777803}
+{"ts": "2025-12-24T04:40:40", "event": "train_log", "step": 3622, "epoch": 1.5626752966558792, "progress_pct": 26.04, "epoch_pct": 26.04, "eta": "40:20:09", "max_grad_norm": 1.0, "loss": 0.7669101357460022, "grad_norm": 0.5759958028793335, "learning_rate": 0.00018163137235682893}
+{"ts": "2025-12-24T04:40:55", "event": "train_log", "step": 3624, "epoch": 1.5635382955771306, "progress_pct": 26.06, "epoch_pct": 26.06, "eta": "40:19:03", "max_grad_norm": 1.0, "loss": 0.7250568270683289, "grad_norm": 0.41767528653144836, "learning_rate": 0.00018160299813084238}
+{"ts": "2025-12-24T04:41:10", "event": "train_log", "step": 3626, "epoch": 1.5644012944983818, "progress_pct": 26.07, "epoch_pct": 26.07, "eta": "40:17:58", "max_grad_norm": 1.0, "loss": 0.7880772352218628, "grad_norm": 0.40168496966362, "learning_rate": 0.00018157460422666075}
+{"ts": "2025-12-24T04:41:25", "event": "train_log", "step": 3628, "epoch": 1.5652642934196332, "progress_pct": 26.09, "epoch_pct": 26.09, "eta": "40:16:51", "max_grad_norm": 1.0, "loss": 0.7754803895950317, "grad_norm": 0.4270237386226654, "learning_rate": 0.00018154619065113102}
+{"ts": "2025-12-24T04:41:40", "event": "train_log", "step": 3630, "epoch": 1.5661272923408847, "progress_pct": 26.1, "epoch_pct": 26.1, "eta": "40:15:48", "max_grad_norm": 1.0, "loss": 0.701246976852417, "grad_norm": 0.46184200048446655, "learning_rate": 0.000181517757411105}
+{"ts": "2025-12-24T04:41:55", "event": "train_log", "step": 3632, "epoch": 1.5669902912621358, "progress_pct": 26.11, "epoch_pct": 26.12, "eta": "40:14:43", "max_grad_norm": 1.0, "loss": 0.7201641201972961, "grad_norm": 0.39403679966926575, "learning_rate": 0.0001814893045134393}
+{"ts": "2025-12-24T04:42:11", "event": "train_log", "step": 3634, "epoch": 1.5678532901833873, "progress_pct": 26.13, "epoch_pct": 26.13, "eta": "40:13:37", "max_grad_norm": 1.0, "loss": 0.6649395823478699, "grad_norm": 0.4320994019508362, "learning_rate": 0.00018146083196499512}
+{"ts": "2025-12-24T04:42:26", "event": "train_log", "step": 3636, "epoch": 1.5687162891046387, "progress_pct": 26.14, "epoch_pct": 26.15, "eta": "40:12:32", "max_grad_norm": 1.0, "loss": 0.7596995234489441, "grad_norm": 0.46719890832901, "learning_rate": 0.0001814323397726386}
+{"ts": "2025-12-24T04:42:40", "event": "train_log", "step": 3638, "epoch": 1.5695792880258899, "progress_pct": 26.16, "epoch_pct": 26.16, "eta": "40:11:25", "max_grad_norm": 1.0, "loss": 0.7265456914901733, "grad_norm": 0.49942320585250854, "learning_rate": 0.0001814038279432404}
+{"ts": "2025-12-24T04:42:55", "event": "train_log", "step": 3640, "epoch": 1.5704422869471413, "progress_pct": 26.17, "epoch_pct": 26.17, "eta": "40:10:19", "max_grad_norm": 1.0, "loss": 0.6903387308120728, "grad_norm": 0.41604548692703247, "learning_rate": 0.00018137529648367607}
+{"ts": "2025-12-24T04:43:10", "event": "train_log", "step": 3642, "epoch": 1.5713052858683927, "progress_pct": 26.19, "epoch_pct": 26.19, "eta": "40:09:13", "max_grad_norm": 1.0, "loss": 0.7590459585189819, "grad_norm": 0.4712325930595398, "learning_rate": 0.00018134674540082587}
+{"ts": "2025-12-24T04:43:24", "event": "train_log", "step": 3644, "epoch": 1.5721682847896439, "progress_pct": 26.2, "epoch_pct": 26.2, "eta": "40:08:05", "max_grad_norm": 1.0, "loss": 0.7304242253303528, "grad_norm": 0.5137260556221008, "learning_rate": 0.00018131817470157471}
+{"ts": "2025-12-24T04:43:39", "event": "train_log", "step": 3646, "epoch": 1.5730312837108955, "progress_pct": 26.22, "epoch_pct": 26.22, "eta": "40:07:00", "max_grad_norm": 1.0, "loss": 0.6472513675689697, "grad_norm": 0.459363728761673, "learning_rate": 0.0001812895843928123}
+{"ts": "2025-12-24T04:43:52", "event": "train_log", "step": 3648, "epoch": 1.5738942826321467, "progress_pct": 26.23, "epoch_pct": 26.23, "eta": "40:05:51", "max_grad_norm": 1.0, "loss": 0.7312461733818054, "grad_norm": 0.518924355506897, "learning_rate": 0.00018126097448143306}
+{"ts": "2025-12-24T04:44:07", "event": "train_log", "step": 3650, "epoch": 1.574757281553398, "progress_pct": 26.24, "epoch_pct": 26.25, "eta": "40:04:44", "max_grad_norm": 1.0, "loss": 0.7790979146957397, "grad_norm": 0.491247296333313, "learning_rate": 0.00018123234497433615}
+{"ts": "2025-12-24T04:44:22", "event": "train_log", "step": 3652, "epoch": 1.5756202804746495, "progress_pct": 26.26, "epoch_pct": 26.26, "eta": "40:03:39", "max_grad_norm": 1.0, "loss": 0.7140002846717834, "grad_norm": 0.4290984570980072, "learning_rate": 0.00018120369587842547}
+{"ts": "2025-12-24T04:44:37", "event": "train_log", "step": 3654, "epoch": 1.5764832793959007, "progress_pct": 26.27, "epoch_pct": 26.27, "eta": "40:02:35", "max_grad_norm": 1.0, "loss": 0.7497822046279907, "grad_norm": 0.4229796528816223, "learning_rate": 0.0001811750272006096}
+{"ts": "2025-12-24T04:44:51", "event": "train_log", "step": 3656, "epoch": 1.5773462783171521, "progress_pct": 26.29, "epoch_pct": 26.29, "eta": "40:01:28", "max_grad_norm": 1.0, "loss": 0.769322395324707, "grad_norm": 0.444733589887619, "learning_rate": 0.00018114633894780182}
+{"ts": "2025-12-24T04:45:06", "event": "train_log", "step": 3658, "epoch": 1.5782092772384035, "progress_pct": 26.3, "epoch_pct": 26.3, "eta": "40:00:24", "max_grad_norm": 1.0, "loss": 0.7770668268203735, "grad_norm": 0.4415557384490967, "learning_rate": 0.00018111763112692024}
+{"ts": "2025-12-24T04:45:22", "event": "train_log", "step": 3660, "epoch": 1.5790722761596547, "progress_pct": 26.32, "epoch_pct": 26.32, "eta": "39:59:20", "max_grad_norm": 1.0, "loss": 0.7666043639183044, "grad_norm": 0.42115989327430725, "learning_rate": 0.00018108890374488759}
+{"ts": "2025-12-24T04:45:36", "event": "train_log", "step": 3662, "epoch": 1.5799352750809061, "progress_pct": 26.33, "epoch_pct": 26.33, "eta": "39:58:13", "max_grad_norm": 1.0, "loss": 0.7253396511077881, "grad_norm": 0.4013395607471466, "learning_rate": 0.00018106015680863132}
+{"ts": "2025-12-24T04:45:51", "event": "train_log", "step": 3664, "epoch": 1.5807982740021576, "progress_pct": 26.34, "epoch_pct": 26.35, "eta": "39:57:09", "max_grad_norm": 1.0, "loss": 0.6983510255813599, "grad_norm": 0.37566566467285156, "learning_rate": 0.0001810313903250837}
+{"ts": "2025-12-24T04:46:05", "event": "train_log", "step": 3666, "epoch": 1.5816612729234087, "progress_pct": 26.36, "epoch_pct": 26.36, "eta": "39:56:02", "max_grad_norm": 1.0, "loss": 0.7309481501579285, "grad_norm": 0.4788576364517212, "learning_rate": 0.00018100260430118162}
+{"ts": "2025-12-24T04:46:20", "event": "train_log", "step": 3668, "epoch": 1.5825242718446602, "progress_pct": 26.37, "epoch_pct": 26.38, "eta": "39:54:57", "max_grad_norm": 1.0, "loss": 0.7518695592880249, "grad_norm": 0.43960556387901306, "learning_rate": 0.0001809737987438666}
+{"ts": "2025-12-24T04:46:35", "event": "train_log", "step": 3670, "epoch": 1.5833872707659116, "progress_pct": 26.39, "epoch_pct": 26.39, "eta": "39:53:53", "max_grad_norm": 1.0, "loss": 0.6877766251564026, "grad_norm": 0.4018779993057251, "learning_rate": 0.0001809449736600851}
+{"ts": "2025-12-24T04:46:50", "event": "train_log", "step": 3672, "epoch": 1.5842502696871628, "progress_pct": 26.4, "epoch_pct": 26.4, "eta": "39:52:47", "max_grad_norm": 1.0, "loss": 0.7189319729804993, "grad_norm": 0.43951910734176636, "learning_rate": 0.00018091612905678808}
+{"ts": "2025-12-24T04:47:05", "event": "train_log", "step": 3674, "epoch": 1.5851132686084144, "progress_pct": 26.42, "epoch_pct": 26.42, "eta": "39:51:43", "max_grad_norm": 1.0, "loss": 0.6966261863708496, "grad_norm": 0.42398321628570557, "learning_rate": 0.0001808872649409313}
+{"ts": "2025-12-24T04:47:20", "event": "train_log", "step": 3676, "epoch": 1.5859762675296656, "progress_pct": 26.43, "epoch_pct": 26.43, "eta": "39:50:39", "max_grad_norm": 1.0, "loss": 0.6944435834884644, "grad_norm": 0.4551796019077301, "learning_rate": 0.00018085838131947526}
+{"ts": "2025-12-24T04:47:34", "event": "train_log", "step": 3678, "epoch": 1.5868392664509168, "progress_pct": 26.45, "epoch_pct": 26.45, "eta": "39:49:32", "max_grad_norm": 1.0, "loss": 0.7711076736450195, "grad_norm": 0.487661212682724, "learning_rate": 0.00018082947819938504}
+{"ts": "2025-12-24T04:47:48", "event": "train_log", "step": 3680, "epoch": 1.5877022653721684, "progress_pct": 26.46, "epoch_pct": 26.46, "eta": "39:48:26", "max_grad_norm": 1.0, "loss": 0.7488799691200256, "grad_norm": 0.45423412322998047, "learning_rate": 0.00018080055558763057}
+{"ts": "2025-12-24T04:48:03", "event": "train_log", "step": 3682, "epoch": 1.5885652642934196, "progress_pct": 26.47, "epoch_pct": 26.48, "eta": "39:47:20", "max_grad_norm": 1.0, "loss": 0.6809216737747192, "grad_norm": 0.40377750992774963, "learning_rate": 0.00018077161349118633}
+{"ts": "2025-12-24T04:48:18", "event": "train_log", "step": 3684, "epoch": 1.589428263214671, "progress_pct": 26.49, "epoch_pct": 26.49, "eta": "39:46:17", "max_grad_norm": 1.0, "loss": 0.7147122621536255, "grad_norm": 0.5005835294723511, "learning_rate": 0.00018074265191703163}
+{"ts": "2025-12-24T04:48:33", "event": "train_log", "step": 3686, "epoch": 1.5902912621359224, "progress_pct": 26.5, "epoch_pct": 26.5, "eta": "39:45:12", "max_grad_norm": 1.0, "loss": 0.7934401035308838, "grad_norm": 0.5540063381195068, "learning_rate": 0.00018071367087215044}
+{"ts": "2025-12-24T04:48:49", "event": "train_log", "step": 3688, "epoch": 1.5911542610571736, "progress_pct": 26.52, "epoch_pct": 26.52, "eta": "39:44:10", "max_grad_norm": 1.0, "loss": 0.6978628039360046, "grad_norm": 0.41316506266593933, "learning_rate": 0.00018068467036353133}
+{"ts": "2025-12-24T04:49:03", "event": "train_log", "step": 3690, "epoch": 1.592017259978425, "progress_pct": 26.53, "epoch_pct": 26.53, "eta": "39:43:04", "max_grad_norm": 1.0, "loss": 0.8193445205688477, "grad_norm": 0.5138319134712219, "learning_rate": 0.00018065565039816772}
+{"ts": "2025-12-24T04:49:17", "event": "train_log", "step": 3692, "epoch": 1.5928802588996764, "progress_pct": 26.55, "epoch_pct": 26.55, "eta": "39:41:57", "max_grad_norm": 1.0, "loss": 0.7386526465415955, "grad_norm": 0.4598786234855652, "learning_rate": 0.00018062661098305763}
+{"ts": "2025-12-24T04:49:31", "event": "train_log", "step": 3694, "epoch": 1.5937432578209276, "progress_pct": 26.56, "epoch_pct": 26.56, "eta": "39:40:52", "max_grad_norm": 1.0, "loss": 0.7734212875366211, "grad_norm": 0.446444034576416, "learning_rate": 0.00018059755212520372}
+{"ts": "2025-12-24T04:49:46", "event": "train_log", "step": 3696, "epoch": 1.594606256742179, "progress_pct": 26.57, "epoch_pct": 26.58, "eta": "39:39:48", "max_grad_norm": 1.0, "loss": 0.718011200428009, "grad_norm": 0.41883963346481323, "learning_rate": 0.0001805684738316135}
+{"ts": "2025-12-24T04:50:01", "event": "train_log", "step": 3698, "epoch": 1.5954692556634305, "progress_pct": 26.59, "epoch_pct": 26.59, "eta": "39:38:44", "max_grad_norm": 1.0, "loss": 0.7522324919700623, "grad_norm": 0.4579313397407532, "learning_rate": 0.00018053937610929897}
+{"ts": "2025-12-24T04:50:17", "event": "train_log", "step": 3700, "epoch": 1.5963322545846816, "progress_pct": 26.6, "epoch_pct": 26.61, "eta": "39:37:42", "max_grad_norm": 1.0, "loss": 0.6498246788978577, "grad_norm": 0.43380051851272583, "learning_rate": 0.000180510258965277}
+{"ts": "2025-12-24T05:01:26", "event": "train_log", "step": 3700, "epoch": 1.5963322545846816, "progress_pct": 26.6, "epoch_pct": 26.61, "eta": "40:08:28", "max_grad_norm": 1.0, "eval_loss": 0.7914894223213196, "eval_runtime": 668.9887, "eval_samples_per_second": 3.079, "eval_steps_per_second": 3.079}
+{"ts": "2025-12-24T05:01:40", "event": "train_log", "step": 3702, "epoch": 1.5971952535059333, "progress_pct": 26.62, "epoch_pct": 26.62, "eta": "40:07:22", "max_grad_norm": 1.0, "loss": 0.7064145803451538, "grad_norm": 0.39354878664016724, "learning_rate": 0.000180481122406569}
+{"ts": "2025-12-24T05:01:57", "event": "train_log", "step": 3704, "epoch": 1.5980582524271845, "progress_pct": 26.63, "epoch_pct": 26.63, "eta": "40:06:22", "max_grad_norm": 1.0, "loss": 0.6859980821609497, "grad_norm": 0.3876212239265442, "learning_rate": 0.00018045196644020118}
+{"ts": "2025-12-24T05:02:12", "event": "train_log", "step": 3706, "epoch": 1.5989212513484357, "progress_pct": 26.65, "epoch_pct": 26.65, "eta": "40:05:16", "max_grad_norm": 1.0, "loss": 0.8459084630012512, "grad_norm": 0.48381999135017395, "learning_rate": 0.00018042279107320427}
+{"ts": "2025-12-24T05:02:29", "event": "train_log", "step": 3708, "epoch": 1.5997842502696873, "progress_pct": 26.66, "epoch_pct": 26.66, "eta": "40:04:16", "max_grad_norm": 1.0, "loss": 0.6574559211730957, "grad_norm": 0.4688359797000885, "learning_rate": 0.0001803935963126139}
+{"ts": "2025-12-24T05:02:43", "event": "train_log", "step": 3710, "epoch": 1.6006472491909385, "progress_pct": 26.68, "epoch_pct": 26.68, "eta": "40:03:10", "max_grad_norm": 1.0, "loss": 0.8127812147140503, "grad_norm": 0.537028968334198, "learning_rate": 0.0001803643821654702}
+{"ts": "2025-12-24T05:02:58", "event": "train_log", "step": 3712, "epoch": 1.60151024811219, "progress_pct": 26.69, "epoch_pct": 26.69, "eta": "40:02:06", "max_grad_norm": 1.0, "loss": 0.7411133050918579, "grad_norm": 0.3990524113178253, "learning_rate": 0.00018033514863881797}
+{"ts": "2025-12-24T05:03:14", "event": "train_log", "step": 3714, "epoch": 1.6023732470334413, "progress_pct": 26.7, "epoch_pct": 26.71, "eta": "40:01:03", "max_grad_norm": 1.0, "loss": 0.7164896130561829, "grad_norm": 0.38037553429603577, "learning_rate": 0.00018030589573970684}
+{"ts": "2025-12-24T05:03:29", "event": "train_log", "step": 3716, "epoch": 1.6032362459546925, "progress_pct": 26.72, "epoch_pct": 26.72, "eta": "39:59:58", "max_grad_norm": 1.0, "loss": 0.7164638638496399, "grad_norm": 0.45911267399787903, "learning_rate": 0.00018027662347519096}
+{"ts": "2025-12-24T05:03:46", "event": "train_log", "step": 3718, "epoch": 1.604099244875944, "progress_pct": 26.73, "epoch_pct": 26.73, "eta": "39:58:58", "max_grad_norm": 1.0, "loss": 0.6928568482398987, "grad_norm": 0.37456580996513367, "learning_rate": 0.00018024733185232922}
+{"ts": "2025-12-24T05:04:01", "event": "train_log", "step": 3720, "epoch": 1.6049622437971953, "progress_pct": 26.75, "epoch_pct": 26.75, "eta": "39:57:55", "max_grad_norm": 1.0, "loss": 0.6571218371391296, "grad_norm": 0.4336542785167694, "learning_rate": 0.00018021802087818517}
+{"ts": "2025-12-24T05:04:17", "event": "train_log", "step": 3722, "epoch": 1.6058252427184465, "progress_pct": 26.76, "epoch_pct": 26.76, "eta": "39:56:53", "max_grad_norm": 1.0, "loss": 0.6813036203384399, "grad_norm": 0.41265374422073364, "learning_rate": 0.00018018869055982698}
+{"ts": "2025-12-24T05:04:33", "event": "train_log", "step": 3724, "epoch": 1.606688241639698, "progress_pct": 26.78, "epoch_pct": 26.78, "eta": "39:55:50", "max_grad_norm": 1.0, "loss": 0.753751277923584, "grad_norm": 0.4339812695980072, "learning_rate": 0.00018015934090432757}
+{"ts": "2025-12-24T05:04:49", "event": "train_log", "step": 3726, "epoch": 1.6075512405609493, "progress_pct": 26.79, "epoch_pct": 26.79, "eta": "39:54:49", "max_grad_norm": 1.0, "loss": 0.676802396774292, "grad_norm": 0.41123342514038086, "learning_rate": 0.00018012997191876447}
+{"ts": "2025-12-24T05:05:05", "event": "train_log", "step": 3728, "epoch": 1.6084142394822005, "progress_pct": 26.8, "epoch_pct": 26.81, "eta": "39:53:46", "max_grad_norm": 1.0, "loss": 0.7151802778244019, "grad_norm": 0.4282870292663574, "learning_rate": 0.00018010058361021987}
+{"ts": "2025-12-24T05:05:20", "event": "train_log", "step": 3730, "epoch": 1.6092772384034522, "progress_pct": 26.82, "epoch_pct": 26.82, "eta": "39:52:44", "max_grad_norm": 1.0, "loss": 0.815374493598938, "grad_norm": 0.44637587666511536, "learning_rate": 0.00018007117598578063}
+{"ts": "2025-12-24T05:05:38", "event": "train_log", "step": 3732, "epoch": 1.6101402373247033, "progress_pct": 26.83, "epoch_pct": 26.84, "eta": "39:51:46", "max_grad_norm": 1.0, "loss": 0.7119425535202026, "grad_norm": 0.41761815547943115, "learning_rate": 0.00018004174905253826}
+{"ts": "2025-12-24T05:05:52", "event": "train_log", "step": 3734, "epoch": 1.6110032362459545, "progress_pct": 26.85, "epoch_pct": 26.85, "eta": "39:50:40", "max_grad_norm": 1.0, "loss": 0.7779671549797058, "grad_norm": 0.4224661886692047, "learning_rate": 0.0001800123028175889}
+{"ts": "2025-12-24T05:06:09", "event": "train_log", "step": 3736, "epoch": 1.6118662351672062, "progress_pct": 26.86, "epoch_pct": 26.86, "eta": "39:49:42", "max_grad_norm": 1.0, "loss": 0.5716424584388733, "grad_norm": 0.476329505443573, "learning_rate": 0.00017998283728803345}
+{"ts": "2025-12-24T05:06:23", "event": "train_log", "step": 3738, "epoch": 1.6127292340884574, "progress_pct": 26.88, "epoch_pct": 26.88, "eta": "39:48:35", "max_grad_norm": 1.0, "loss": 0.7326773405075073, "grad_norm": 0.4721233546733856, "learning_rate": 0.00017995335247097738}
+{"ts": "2025-12-24T05:06:38", "event": "train_log", "step": 3740, "epoch": 1.6135922330097088, "progress_pct": 26.89, "epoch_pct": 26.89, "eta": "39:47:31", "max_grad_norm": 1.0, "loss": 0.7872865200042725, "grad_norm": 0.38915106654167175, "learning_rate": 0.00017992384837353073}
+{"ts": "2025-12-24T05:06:53", "event": "train_log", "step": 3742, "epoch": 1.6144552319309602, "progress_pct": 26.91, "epoch_pct": 26.91, "eta": "39:46:27", "max_grad_norm": 1.0, "loss": 0.8006538152694702, "grad_norm": 0.4306866526603699, "learning_rate": 0.00017989432500280838}
+{"ts": "2025-12-24T05:07:08", "event": "train_log", "step": 3744, "epoch": 1.6153182308522114, "progress_pct": 26.92, "epoch_pct": 26.92, "eta": "39:45:22", "max_grad_norm": 1.0, "loss": 0.7693750858306885, "grad_norm": 0.3983909487724304, "learning_rate": 0.00017986478236592973}
+{"ts": "2025-12-24T05:07:22", "event": "train_log", "step": 3746, "epoch": 1.6161812297734628, "progress_pct": 26.93, "epoch_pct": 26.94, "eta": "39:44:17", "max_grad_norm": 1.0, "loss": 0.7483386993408203, "grad_norm": 0.4322768747806549, "learning_rate": 0.00017983522047001883}
+{"ts": "2025-12-24T05:07:37", "event": "train_log", "step": 3748, "epoch": 1.6170442286947142, "progress_pct": 26.95, "epoch_pct": 26.95, "eta": "39:43:12", "max_grad_norm": 1.0, "loss": 0.7642959356307983, "grad_norm": 0.5202714204788208, "learning_rate": 0.00017980563932220442}
+{"ts": "2025-12-24T05:07:52", "event": "train_log", "step": 3750, "epoch": 1.6179072276159654, "progress_pct": 26.96, "epoch_pct": 26.97, "eta": "39:42:10", "max_grad_norm": 1.0, "loss": 0.741479754447937, "grad_norm": 0.4318627119064331, "learning_rate": 0.00017977603892961982}
+{"ts": "2025-12-24T05:08:07", "event": "train_log", "step": 3752, "epoch": 1.6187702265372168, "progress_pct": 26.98, "epoch_pct": 26.98, "eta": "39:41:05", "max_grad_norm": 1.0, "loss": 0.7392295598983765, "grad_norm": 0.4942893981933594, "learning_rate": 0.0001797464192994031}
+{"ts": "2025-12-24T05:08:21", "event": "train_log", "step": 3754, "epoch": 1.6196332254584682, "progress_pct": 26.99, "epoch_pct": 26.99, "eta": "39:40:00", "max_grad_norm": 1.0, "loss": 0.7523542046546936, "grad_norm": 0.46874746680259705, "learning_rate": 0.00017971678043869686}
+{"ts": "2025-12-24T05:08:36", "event": "train_log", "step": 3756, "epoch": 1.6204962243797194, "progress_pct": 27.01, "epoch_pct": 27.01, "eta": "39:38:55", "max_grad_norm": 1.0, "loss": 0.6766729950904846, "grad_norm": 0.47045233845710754, "learning_rate": 0.00017968712235464837}
+{"ts": "2025-12-24T05:08:52", "event": "train_log", "step": 3758, "epoch": 1.6213592233009708, "progress_pct": 27.02, "epoch_pct": 27.02, "eta": "39:37:53", "max_grad_norm": 1.0, "loss": 0.7277816534042358, "grad_norm": 0.43984928727149963, "learning_rate": 0.00017965744505440956}
+{"ts": "2025-12-24T05:09:07", "event": "train_log", "step": 3760, "epoch": 1.6222222222222222, "progress_pct": 27.03, "epoch_pct": 27.04, "eta": "39:36:49", "max_grad_norm": 1.0, "loss": 0.7649447917938232, "grad_norm": 0.41389113664627075, "learning_rate": 0.00017962774854513697}
+{"ts": "2025-12-24T05:09:21", "event": "train_log", "step": 3762, "epoch": 1.6230852211434734, "progress_pct": 27.05, "epoch_pct": 27.05, "eta": "39:35:45", "max_grad_norm": 1.0, "loss": 0.7033944129943848, "grad_norm": 0.461200475692749, "learning_rate": 0.00017959803283399182}
+{"ts": "2025-12-24T05:09:36", "event": "train_log", "step": 3764, "epoch": 1.623948220064725, "progress_pct": 27.06, "epoch_pct": 27.07, "eta": "39:34:42", "max_grad_norm": 1.0, "loss": 0.8075087070465088, "grad_norm": 0.4776712954044342, "learning_rate": 0.00017956829792813985}
+{"ts": "2025-12-24T05:09:50", "event": "train_log", "step": 3766, "epoch": 1.6248112189859762, "progress_pct": 27.08, "epoch_pct": 27.08, "eta": "39:33:34", "max_grad_norm": 1.0, "loss": 0.7541269063949585, "grad_norm": 0.5021974444389343, "learning_rate": 0.00017953854383475154}
+{"ts": "2025-12-24T05:10:04", "event": "train_log", "step": 3768, "epoch": 1.6256742179072277, "progress_pct": 27.09, "epoch_pct": 27.09, "eta": "39:32:30", "max_grad_norm": 1.0, "loss": 0.703751266002655, "grad_norm": 0.46222755312919617, "learning_rate": 0.0001795087705610019}
+{"ts": "2025-12-24T05:10:20", "event": "train_log", "step": 3770, "epoch": 1.626537216828479, "progress_pct": 27.11, "epoch_pct": 27.11, "eta": "39:31:30", "max_grad_norm": 1.0, "loss": 0.6657921671867371, "grad_norm": 0.34487178921699524, "learning_rate": 0.0001794789781140707}
+{"ts": "2025-12-24T05:10:36", "event": "train_log", "step": 3772, "epoch": 1.6274002157497303, "progress_pct": 27.12, "epoch_pct": 27.12, "eta": "39:30:28", "max_grad_norm": 1.0, "loss": 0.7999282479286194, "grad_norm": 0.38064146041870117, "learning_rate": 0.00017944916650114223}
+{"ts": "2025-12-24T05:10:50", "event": "train_log", "step": 3774, "epoch": 1.6282632146709817, "progress_pct": 27.14, "epoch_pct": 27.14, "eta": "39:29:23", "max_grad_norm": 1.0, "loss": 0.7157361507415771, "grad_norm": 0.48815488815307617, "learning_rate": 0.00017941933572940543}
+{"ts": "2025-12-24T05:11:06", "event": "train_log", "step": 3776, "epoch": 1.629126213592233, "progress_pct": 27.15, "epoch_pct": 27.15, "eta": "39:28:21", "max_grad_norm": 1.0, "loss": 0.6897950768470764, "grad_norm": 0.42136189341545105, "learning_rate": 0.00017938948580605382}
+{"ts": "2025-12-24T05:11:21", "event": "train_log", "step": 3778, "epoch": 1.6299892125134843, "progress_pct": 27.16, "epoch_pct": 27.17, "eta": "39:27:17", "max_grad_norm": 1.0, "loss": 0.6738383173942566, "grad_norm": 0.388630747795105, "learning_rate": 0.0001793596167382856}
+{"ts": "2025-12-24T05:11:36", "event": "train_log", "step": 3780, "epoch": 1.6308522114347357, "progress_pct": 27.18, "epoch_pct": 27.18, "eta": "39:26:14", "max_grad_norm": 1.0, "loss": 0.6531928777694702, "grad_norm": 0.4050692617893219, "learning_rate": 0.00017932972853330355}
+{"ts": "2025-12-24T05:11:49", "event": "train_log", "step": 3782, "epoch": 1.631715210355987, "progress_pct": 27.19, "epoch_pct": 27.2, "eta": "39:25:07", "max_grad_norm": 1.0, "loss": 0.8739076256752014, "grad_norm": 0.542385995388031, "learning_rate": 0.0001792998211983151}
+{"ts": "2025-12-24T05:12:04", "event": "train_log", "step": 3784, "epoch": 1.6325782092772383, "progress_pct": 27.21, "epoch_pct": 27.21, "eta": "39:24:04", "max_grad_norm": 1.0, "loss": 0.7771362662315369, "grad_norm": 0.4323846995830536, "learning_rate": 0.00017926989474053223}
+{"ts": "2025-12-24T05:12:19", "event": "train_log", "step": 3786, "epoch": 1.6334412081984897, "progress_pct": 27.22, "epoch_pct": 27.22, "eta": "39:23:01", "max_grad_norm": 1.0, "loss": 0.7664928436279297, "grad_norm": 0.47487086057662964, "learning_rate": 0.00017923994916717163}
+{"ts": "2025-12-24T05:12:35", "event": "train_log", "step": 3788, "epoch": 1.6343042071197411, "progress_pct": 27.24, "epoch_pct": 27.24, "eta": "39:22:01", "max_grad_norm": 1.0, "loss": 0.6508067846298218, "grad_norm": 0.3801349401473999, "learning_rate": 0.0001792099844854545}
+{"ts": "2025-12-24T05:12:51", "event": "train_log", "step": 3790, "epoch": 1.6351672060409923, "progress_pct": 27.25, "epoch_pct": 27.25, "eta": "39:21:00", "max_grad_norm": 1.0, "loss": 0.6948919892311096, "grad_norm": 0.38995426893234253, "learning_rate": 0.00017918000070260668}
+{"ts": "2025-12-24T05:13:07", "event": "train_log", "step": 3792, "epoch": 1.636030204962244, "progress_pct": 27.26, "epoch_pct": 27.27, "eta": "39:20:01", "max_grad_norm": 1.0, "loss": 0.7225003242492676, "grad_norm": 0.4038735628128052, "learning_rate": 0.00017914999782585862}
+{"ts": "2025-12-24T05:13:21", "event": "train_log", "step": 3794, "epoch": 1.6368932038834951, "progress_pct": 27.28, "epoch_pct": 27.28, "eta": "39:18:56", "max_grad_norm": 1.0, "loss": 0.7177075147628784, "grad_norm": 0.45372122526168823, "learning_rate": 0.00017911997586244542}
+{"ts": "2025-12-24T05:13:35", "event": "train_log", "step": 3796, "epoch": 1.6377562028047465, "progress_pct": 27.29, "epoch_pct": 27.3, "eta": "39:17:51", "max_grad_norm": 1.0, "loss": 0.8427615165710449, "grad_norm": 0.5123688578605652, "learning_rate": 0.00017908993481960669}
+{"ts": "2025-12-24T05:13:50", "event": "train_log", "step": 3798, "epoch": 1.638619201725998, "progress_pct": 27.31, "epoch_pct": 27.31, "eta": "39:16:47", "max_grad_norm": 1.0, "loss": 0.7884581089019775, "grad_norm": 0.505483865737915, "learning_rate": 0.00017905987470458675}
+{"ts": "2025-12-24T05:14:04", "event": "train_log", "step": 3800, "epoch": 1.6394822006472491, "progress_pct": 27.32, "epoch_pct": 27.32, "eta": "39:15:42", "max_grad_norm": 1.0, "loss": 0.8026853799819946, "grad_norm": 0.5441710948944092, "learning_rate": 0.0001790297955246344}
+{"ts": "2025-12-24T05:24:59", "event": "train_log", "step": 3800, "epoch": 1.6394822006472491, "progress_pct": 27.32, "epoch_pct": 27.32, "eta": "39:44:47", "max_grad_norm": 1.0, "eval_loss": 0.7887746691703796, "eval_runtime": 655.8201, "eval_samples_per_second": 3.141, "eval_steps_per_second": 3.141}
+{"ts": "2025-12-24T05:25:15", "event": "train_log", "step": 3802, "epoch": 1.6403451995685006, "progress_pct": 27.34, "epoch_pct": 27.34, "eta": "39:43:44", "max_grad_norm": 1.0, "loss": 0.6836490035057068, "grad_norm": 0.3747040033340454, "learning_rate": 0.00017899969728700315}
+{"ts": "2025-12-24T05:25:31", "event": "train_log", "step": 3804, "epoch": 1.641208198489752, "progress_pct": 27.35, "epoch_pct": 27.35, "eta": "39:42:43", "max_grad_norm": 1.0, "loss": 0.748136579990387, "grad_norm": 0.4163338243961334, "learning_rate": 0.000178969579998951}
+{"ts": "2025-12-24T05:25:45", "event": "train_log", "step": 3806, "epoch": 1.6420711974110032, "progress_pct": 27.37, "epoch_pct": 27.37, "eta": "39:41:37", "max_grad_norm": 1.0, "loss": 0.7534400224685669, "grad_norm": 0.4737973213195801, "learning_rate": 0.00017893944366774065}
+{"ts": "2025-12-24T05:26:00", "event": "train_log", "step": 3808, "epoch": 1.6429341963322546, "progress_pct": 27.38, "epoch_pct": 27.38, "eta": "39:40:32", "max_grad_norm": 1.0, "loss": 0.7779349088668823, "grad_norm": 0.4687727093696594, "learning_rate": 0.00017890928830063932}
+{"ts": "2025-12-24T05:26:16", "event": "train_log", "step": 3810, "epoch": 1.643797195253506, "progress_pct": 27.39, "epoch_pct": 27.4, "eta": "39:39:32", "max_grad_norm": 1.0, "loss": 0.6942368149757385, "grad_norm": 0.43674737215042114, "learning_rate": 0.00017887911390491884}
+{"ts": "2025-12-24T05:26:30", "event": "train_log", "step": 3812, "epoch": 1.6446601941747572, "progress_pct": 27.41, "epoch_pct": 27.41, "eta": "39:38:28", "max_grad_norm": 1.0, "loss": 0.7554087042808533, "grad_norm": 0.43343719840049744, "learning_rate": 0.00017884892048785565}
+{"ts": "2025-12-24T05:26:46", "event": "train_log", "step": 3814, "epoch": 1.6455231930960086, "progress_pct": 27.42, "epoch_pct": 27.43, "eta": "39:37:27", "max_grad_norm": 1.0, "loss": 0.7387835383415222, "grad_norm": 0.4790881276130676, "learning_rate": 0.0001788187080567307}
+{"ts": "2025-12-24T05:27:02", "event": "train_log", "step": 3816, "epoch": 1.64638619201726, "progress_pct": 27.44, "epoch_pct": 27.44, "eta": "39:36:27", "max_grad_norm": 1.0, "loss": 0.7229949235916138, "grad_norm": 0.4524185061454773, "learning_rate": 0.00017878847661882965}
+{"ts": "2025-12-24T05:27:17", "event": "train_log", "step": 3818, "epoch": 1.6472491909385112, "progress_pct": 27.45, "epoch_pct": 27.45, "eta": "39:35:22", "max_grad_norm": 1.0, "loss": 0.6808197498321533, "grad_norm": 0.4563996195793152, "learning_rate": 0.00017875822618144263}
+{"ts": "2025-12-24T05:27:33", "event": "train_log", "step": 3820, "epoch": 1.6481121898597628, "progress_pct": 27.47, "epoch_pct": 27.47, "eta": "39:34:20", "max_grad_norm": 1.0, "loss": 0.6958807110786438, "grad_norm": 0.452282190322876, "learning_rate": 0.00017872795675186442}
+{"ts": "2025-12-24T05:27:47", "event": "train_log", "step": 3822, "epoch": 1.648975188781014, "progress_pct": 27.48, "epoch_pct": 27.48, "eta": "39:33:15", "max_grad_norm": 1.0, "loss": 0.7347233295440674, "grad_norm": 0.5677687525749207, "learning_rate": 0.00017869766833739434}
+{"ts": "2025-12-24T05:28:02", "event": "train_log", "step": 3824, "epoch": 1.6498381877022654, "progress_pct": 27.49, "epoch_pct": 27.5, "eta": "39:32:13", "max_grad_norm": 1.0, "loss": 0.7279980182647705, "grad_norm": 0.5028979778289795, "learning_rate": 0.00017866736094533628}
+{"ts": "2025-12-24T05:28:18", "event": "train_log", "step": 3826, "epoch": 1.6507011866235168, "progress_pct": 27.51, "epoch_pct": 27.51, "eta": "39:31:12", "max_grad_norm": 1.0, "loss": 0.7350833415985107, "grad_norm": 0.4216834604740143, "learning_rate": 0.0001786370345829988}
+{"ts": "2025-12-24T05:28:32", "event": "train_log", "step": 3828, "epoch": 1.651564185544768, "progress_pct": 27.52, "epoch_pct": 27.53, "eta": "39:30:07", "max_grad_norm": 1.0, "loss": 0.8165807127952576, "grad_norm": 0.4700584411621094, "learning_rate": 0.00017860668925769494}
+{"ts": "2025-12-24T05:28:49", "event": "train_log", "step": 3830, "epoch": 1.6524271844660194, "progress_pct": 27.54, "epoch_pct": 27.54, "eta": "39:29:08", "max_grad_norm": 1.0, "loss": 0.7146443128585815, "grad_norm": 0.41511070728302, "learning_rate": 0.0001785763249767423}
+{"ts": "2025-12-24T05:29:04", "event": "train_log", "step": 3832, "epoch": 1.6532901833872709, "progress_pct": 27.55, "epoch_pct": 27.55, "eta": "39:28:05", "max_grad_norm": 1.0, "loss": 0.7849907875061035, "grad_norm": 0.5240047574043274, "learning_rate": 0.00017854594174746314}
+{"ts": "2025-12-24T05:29:19", "event": "train_log", "step": 3834, "epoch": 1.654153182308522, "progress_pct": 27.57, "epoch_pct": 27.57, "eta": "39:27:03", "max_grad_norm": 1.0, "loss": 0.6815205812454224, "grad_norm": 0.4594099223613739, "learning_rate": 0.0001785155395771842}
+{"ts": "2025-12-24T05:29:35", "event": "train_log", "step": 3836, "epoch": 1.6550161812297735, "progress_pct": 27.58, "epoch_pct": 27.58, "eta": "39:26:02", "max_grad_norm": 1.0, "loss": 0.7110051512718201, "grad_norm": 0.41762664914131165, "learning_rate": 0.00017848511847323682}
+{"ts": "2025-12-24T05:29:50", "event": "train_log", "step": 3838, "epoch": 1.6558791801510249, "progress_pct": 27.6, "epoch_pct": 27.6, "eta": "39:25:00", "max_grad_norm": 1.0, "loss": 0.7868525981903076, "grad_norm": 0.4596463143825531, "learning_rate": 0.00017845467844295696}
+{"ts": "2025-12-24T05:30:06", "event": "train_log", "step": 3840, "epoch": 1.656742179072276, "progress_pct": 27.61, "epoch_pct": 27.61, "eta": "39:23:59", "max_grad_norm": 1.0, "loss": 0.7308529615402222, "grad_norm": 0.3694678246974945, "learning_rate": 0.00017842421949368505}
+{"ts": "2025-12-24T05:30:21", "event": "train_log", "step": 3842, "epoch": 1.6576051779935275, "progress_pct": 27.62, "epoch_pct": 27.63, "eta": "39:22:56", "max_grad_norm": 1.0, "loss": 0.6846014857292175, "grad_norm": 0.4251806139945984, "learning_rate": 0.00017839374163276616}
+{"ts": "2025-12-24T05:30:37", "event": "train_log", "step": 3844, "epoch": 1.6584681769147789, "progress_pct": 27.64, "epoch_pct": 27.64, "eta": "39:21:56", "max_grad_norm": 1.0, "loss": 0.7137831449508667, "grad_norm": 0.4015883207321167, "learning_rate": 0.00017836324486754986}
+{"ts": "2025-12-24T05:30:51", "event": "train_log", "step": 3846, "epoch": 1.65933117583603, "progress_pct": 27.65, "epoch_pct": 27.66, "eta": "39:20:53", "max_grad_norm": 1.0, "loss": 0.7908329367637634, "grad_norm": 0.4787199795246124, "learning_rate": 0.00017833272920539034}
+{"ts": "2025-12-24T05:31:08", "event": "train_log", "step": 3848, "epoch": 1.6601941747572817, "progress_pct": 27.67, "epoch_pct": 27.67, "eta": "39:19:55", "max_grad_norm": 1.0, "loss": 0.6918519139289856, "grad_norm": 0.4505045711994171, "learning_rate": 0.0001783021946536463}
+{"ts": "2025-12-24T05:31:25", "event": "train_log", "step": 3850, "epoch": 1.661057173678533, "progress_pct": 27.68, "epoch_pct": 27.68, "eta": "39:18:56", "max_grad_norm": 1.0, "loss": 0.7223191857337952, "grad_norm": 0.43013763427734375, "learning_rate": 0.00017827164121968103}
+{"ts": "2025-12-24T05:31:40", "event": "train_log", "step": 3852, "epoch": 1.661920172599784, "progress_pct": 27.7, "epoch_pct": 27.7, "eta": "39:17:56", "max_grad_norm": 1.0, "loss": 0.8076598644256592, "grad_norm": 0.47614169120788574, "learning_rate": 0.00017824106891086228}
+{"ts": "2025-12-24T05:31:55", "event": "train_log", "step": 3854, "epoch": 1.6627831715210357, "progress_pct": 27.71, "epoch_pct": 27.71, "eta": "39:16:51", "max_grad_norm": 1.0, "loss": 0.7656319737434387, "grad_norm": 0.48056647181510925, "learning_rate": 0.0001782104777345625}
+{"ts": "2025-12-24T05:32:11", "event": "train_log", "step": 3856, "epoch": 1.663646170442287, "progress_pct": 27.73, "epoch_pct": 27.73, "eta": "39:15:54", "max_grad_norm": 1.0, "loss": 0.7252323031425476, "grad_norm": 0.38120999932289124, "learning_rate": 0.00017817986769815857}
+{"ts": "2025-12-24T05:32:27", "event": "train_log", "step": 3858, "epoch": 1.6645091693635383, "progress_pct": 27.74, "epoch_pct": 27.74, "eta": "39:14:52", "max_grad_norm": 1.0, "loss": 0.747683048248291, "grad_norm": 0.478983074426651, "learning_rate": 0.00017814923880903202}
+{"ts": "2025-12-24T05:32:42", "event": "train_log", "step": 3860, "epoch": 1.6653721682847897, "progress_pct": 27.75, "epoch_pct": 27.76, "eta": "39:13:51", "max_grad_norm": 1.0, "loss": 0.69855135679245, "grad_norm": 0.4553819000720978, "learning_rate": 0.0001781185910745688}
+{"ts": "2025-12-24T05:32:58", "event": "train_log", "step": 3862, "epoch": 1.666235167206041, "progress_pct": 27.77, "epoch_pct": 27.77, "eta": "39:12:52", "max_grad_norm": 1.0, "loss": 0.8340141773223877, "grad_norm": 0.49657294154167175, "learning_rate": 0.0001780879245021595}
+{"ts": "2025-12-24T05:33:14", "event": "train_log", "step": 3864, "epoch": 1.6670981661272923, "progress_pct": 27.78, "epoch_pct": 27.78, "eta": "39:11:51", "max_grad_norm": 1.0, "loss": 0.7290753722190857, "grad_norm": 0.40509313344955444, "learning_rate": 0.00017805723909919925}
+{"ts": "2025-12-24T05:33:29", "event": "train_log", "step": 3866, "epoch": 1.6679611650485437, "progress_pct": 27.8, "epoch_pct": 27.8, "eta": "39:10:49", "max_grad_norm": 1.0, "loss": 0.7971621751785278, "grad_norm": 0.4422856271266937, "learning_rate": 0.00017802653487308768}
+{"ts": "2025-12-24T05:33:46", "event": "train_log", "step": 3868, "epoch": 1.668824163969795, "progress_pct": 27.81, "epoch_pct": 27.81, "eta": "39:09:52", "max_grad_norm": 1.0, "loss": 0.7099016904830933, "grad_norm": 0.4734835624694824, "learning_rate": 0.00017799581183122894}
+{"ts": "2025-12-24T05:34:01", "event": "train_log", "step": 3870, "epoch": 1.6696871628910464, "progress_pct": 27.83, "epoch_pct": 27.83, "eta": "39:08:51", "max_grad_norm": 1.0, "loss": 0.7210022211074829, "grad_norm": 0.3835538625717163, "learning_rate": 0.0001779650699810318}
+{"ts": "2025-12-24T05:34:18", "event": "train_log", "step": 3872, "epoch": 1.6705501618122978, "progress_pct": 27.84, "epoch_pct": 27.84, "eta": "39:07:52", "max_grad_norm": 1.0, "loss": 0.6639223694801331, "grad_norm": 0.3696903884410858, "learning_rate": 0.00017793430932990951}
+{"ts": "2025-12-24T05:34:32", "event": "train_log", "step": 3874, "epoch": 1.671413160733549, "progress_pct": 27.85, "epoch_pct": 27.86, "eta": "39:06:50", "max_grad_norm": 1.0, "loss": 0.8337125182151794, "grad_norm": 0.4560008645057678, "learning_rate": 0.00017790352988527984}
+{"ts": "2025-12-24T05:34:47", "event": "train_log", "step": 3876, "epoch": 1.6722761596548006, "progress_pct": 27.87, "epoch_pct": 27.87, "eta": "39:05:47", "max_grad_norm": 1.0, "loss": 0.6761727929115295, "grad_norm": 0.43672001361846924, "learning_rate": 0.00017787273165456515}
+{"ts": "2025-12-24T05:35:02", "event": "train_log", "step": 3878, "epoch": 1.6731391585760518, "progress_pct": 27.88, "epoch_pct": 27.89, "eta": "39:04:46", "max_grad_norm": 1.0, "loss": 0.6976995468139648, "grad_norm": 0.37448835372924805, "learning_rate": 0.00017784191464519225}
+{"ts": "2025-12-24T05:35:19", "event": "train_log", "step": 3880, "epoch": 1.674002157497303, "progress_pct": 27.9, "epoch_pct": 27.9, "eta": "39:03:47", "max_grad_norm": 1.0, "loss": 0.6759265661239624, "grad_norm": 0.37624600529670715, "learning_rate": 0.00017781107886459253}
+{"ts": "2025-12-24T05:35:33", "event": "train_log", "step": 3882, "epoch": 1.6748651564185546, "progress_pct": 27.91, "epoch_pct": 27.91, "eta": "39:02:45", "max_grad_norm": 1.0, "loss": 0.6577118039131165, "grad_norm": 0.4134359359741211, "learning_rate": 0.00017778022432020198}
+{"ts": "2025-12-24T05:35:49", "event": "train_log", "step": 3884, "epoch": 1.6757281553398058, "progress_pct": 27.93, "epoch_pct": 27.93, "eta": "39:01:45", "max_grad_norm": 1.0, "loss": 0.7117277979850769, "grad_norm": 0.41737261414527893, "learning_rate": 0.00017774935101946092}
+{"ts": "2025-12-24T05:36:05", "event": "train_log", "step": 3886, "epoch": 1.6765911542610572, "progress_pct": 27.94, "epoch_pct": 27.94, "eta": "39:00:47", "max_grad_norm": 1.0, "loss": 0.6871168613433838, "grad_norm": 0.41871723532676697, "learning_rate": 0.00017771845896981438}
+{"ts": "2025-12-24T05:36:21", "event": "train_log", "step": 3888, "epoch": 1.6774541531823086, "progress_pct": 27.96, "epoch_pct": 27.96, "eta": "38:59:46", "max_grad_norm": 1.0, "loss": 0.7382785677909851, "grad_norm": 0.4778793156147003, "learning_rate": 0.00017768754817871178}
+{"ts": "2025-12-24T05:36:35", "event": "train_log", "step": 3890, "epoch": 1.6783171521035598, "progress_pct": 27.97, "epoch_pct": 27.97, "eta": "38:58:43", "max_grad_norm": 1.0, "loss": 0.6783252358436584, "grad_norm": 0.4502207338809967, "learning_rate": 0.00017765661865360718}
+{"ts": "2025-12-24T05:36:50", "event": "train_log", "step": 3892, "epoch": 1.6791801510248112, "progress_pct": 27.98, "epoch_pct": 27.99, "eta": "38:57:40", "max_grad_norm": 1.0, "loss": 0.7115309238433838, "grad_norm": 0.4124210774898529, "learning_rate": 0.00017762567040195907}
+{"ts": "2025-12-24T05:37:05", "event": "train_log", "step": 3894, "epoch": 1.6800431499460626, "progress_pct": 28.0, "epoch_pct": 28.0, "eta": "38:56:40", "max_grad_norm": 1.0, "loss": 0.6698686480522156, "grad_norm": 0.45017218589782715, "learning_rate": 0.0001775947034312305}
+{"ts": "2025-12-24T05:37:19", "event": "train_log", "step": 3896, "epoch": 1.6809061488673138, "progress_pct": 28.01, "epoch_pct": 28.02, "eta": "38:55:37", "max_grad_norm": 1.0, "loss": 0.7978704571723938, "grad_norm": 0.4965505301952362, "learning_rate": 0.00017756371774888896}
+{"ts": "2025-12-24T05:37:34", "event": "train_log", "step": 3898, "epoch": 1.6817691477885652, "progress_pct": 28.03, "epoch_pct": 28.03, "eta": "38:54:34", "max_grad_norm": 1.0, "loss": 0.7991471290588379, "grad_norm": 0.44287896156311035, "learning_rate": 0.00017753271336240655}
+{"ts": "2025-12-24T05:37:48", "event": "train_log", "step": 3900, "epoch": 1.6826321467098166, "progress_pct": 28.04, "epoch_pct": 28.04, "eta": "38:53:31", "max_grad_norm": 1.0, "loss": 0.7351664900779724, "grad_norm": 0.4569724500179291, "learning_rate": 0.00017750169027925985}
+{"ts": "2025-12-24T05:48:36", "event": "train_log", "step": 3900, "epoch": 1.6826321467098166, "progress_pct": 28.04, "epoch_pct": 28.04, "eta": "39:21:14", "max_grad_norm": 1.0, "eval_loss": 0.7847991585731506, "eval_runtime": 648.2009, "eval_samples_per_second": 3.178, "eval_steps_per_second": 3.178}
+{"ts": "2025-12-24T05:48:51", "event": "train_log", "step": 3902, "epoch": 1.6834951456310678, "progress_pct": 28.06, "epoch_pct": 28.06, "eta": "39:20:12", "max_grad_norm": 1.0, "loss": 0.744560182094574, "grad_norm": 0.39483416080474854, "learning_rate": 0.00017747064850692993}
+{"ts": "2025-12-24T05:49:05", "event": "train_log", "step": 3904, "epoch": 1.6843581445523195, "progress_pct": 28.07, "epoch_pct": 28.07, "eta": "39:19:06", "max_grad_norm": 1.0, "loss": 0.7506792545318604, "grad_norm": 0.4636281430721283, "learning_rate": 0.00017743958805290232}
+{"ts": "2025-12-24T05:49:20", "event": "train_log", "step": 3906, "epoch": 1.6852211434735707, "progress_pct": 28.08, "epoch_pct": 28.09, "eta": "39:18:03", "max_grad_norm": 1.0, "loss": 0.7190370559692383, "grad_norm": 0.43549975752830505, "learning_rate": 0.00017740850892466719}
+{"ts": "2025-12-24T05:49:34", "event": "train_log", "step": 3908, "epoch": 1.6860841423948218, "progress_pct": 28.1, "epoch_pct": 28.1, "eta": "39:17:00", "max_grad_norm": 1.0, "loss": 0.7768138647079468, "grad_norm": 0.4514775276184082, "learning_rate": 0.00017737741112971907}
+{"ts": "2025-12-24T05:49:49", "event": "train_log", "step": 3910, "epoch": 1.6869471413160735, "progress_pct": 28.11, "epoch_pct": 28.12, "eta": "39:15:56", "max_grad_norm": 1.0, "loss": 0.7726560831069946, "grad_norm": 0.45857131481170654, "learning_rate": 0.0001773462946755571}
+{"ts": "2025-12-24T05:50:04", "event": "train_log", "step": 3912, "epoch": 1.6878101402373247, "progress_pct": 28.13, "epoch_pct": 28.13, "eta": "39:14:55", "max_grad_norm": 1.0, "loss": 0.6987468600273132, "grad_norm": 0.4479610323905945, "learning_rate": 0.00017731515956968482}
+{"ts": "2025-12-24T05:50:20", "event": "train_log", "step": 3914, "epoch": 1.688673139158576, "progress_pct": 28.14, "epoch_pct": 28.14, "eta": "39:13:55", "max_grad_norm": 1.0, "loss": 0.6895362734794617, "grad_norm": 0.489849716424942, "learning_rate": 0.00017728400581961036}
+{"ts": "2025-12-24T05:50:35", "event": "train_log", "step": 3916, "epoch": 1.6895361380798275, "progress_pct": 28.16, "epoch_pct": 28.16, "eta": "39:12:53", "max_grad_norm": 1.0, "loss": 0.7460364699363708, "grad_norm": 0.48648950457572937, "learning_rate": 0.00017725283343284629}
+{"ts": "2025-12-24T05:50:51", "event": "train_log", "step": 3918, "epoch": 1.6903991370010787, "progress_pct": 28.17, "epoch_pct": 28.17, "eta": "39:11:53", "max_grad_norm": 1.0, "loss": 0.7300586104393005, "grad_norm": 0.5052891969680786, "learning_rate": 0.0001772216424169097}
+{"ts": "2025-12-24T05:51:05", "event": "train_log", "step": 3920, "epoch": 1.69126213592233, "progress_pct": 28.19, "epoch_pct": 28.19, "eta": "39:10:50", "max_grad_norm": 1.0, "loss": 0.7635855674743652, "grad_norm": 0.48179247975349426, "learning_rate": 0.00017719043277932215}
+{"ts": "2025-12-24T05:51:21", "event": "train_log", "step": 3922, "epoch": 1.6921251348435815, "progress_pct": 28.2, "epoch_pct": 28.2, "eta": "39:09:49", "max_grad_norm": 1.0, "loss": 0.7760766744613647, "grad_norm": 0.5296869277954102, "learning_rate": 0.00017715920452760972}
+{"ts": "2025-12-24T05:51:35", "event": "train_log", "step": 3924, "epoch": 1.6929881337648327, "progress_pct": 28.21, "epoch_pct": 28.22, "eta": "39:08:46", "max_grad_norm": 1.0, "loss": 0.798885703086853, "grad_norm": 0.5226309895515442, "learning_rate": 0.00017712795766930298}
+{"ts": "2025-12-24T05:51:51", "event": "train_log", "step": 3926, "epoch": 1.6938511326860841, "progress_pct": 28.23, "epoch_pct": 28.23, "eta": "39:07:46", "max_grad_norm": 1.0, "loss": 0.7614596486091614, "grad_norm": 0.3812384605407715, "learning_rate": 0.0001770966922119369}
+{"ts": "2025-12-24T05:52:07", "event": "train_log", "step": 3928, "epoch": 1.6947141316073355, "progress_pct": 28.24, "epoch_pct": 28.25, "eta": "39:06:46", "max_grad_norm": 1.0, "loss": 0.7634122967720032, "grad_norm": 0.4084458649158478, "learning_rate": 0.00017706540816305103}
+{"ts": "2025-12-24T05:52:23", "event": "train_log", "step": 3930, "epoch": 1.6955771305285867, "progress_pct": 28.26, "epoch_pct": 28.26, "eta": "39:05:47", "max_grad_norm": 1.0, "loss": 0.7364476323127747, "grad_norm": 0.49413034319877625, "learning_rate": 0.00017703410553018944}
+{"ts": "2025-12-24T05:52:38", "event": "train_log", "step": 3932, "epoch": 1.6964401294498384, "progress_pct": 28.27, "epoch_pct": 28.27, "eta": "39:04:46", "max_grad_norm": 1.0, "loss": 0.6874673366546631, "grad_norm": 0.4119735658168793, "learning_rate": 0.00017700278432090057}
+{"ts": "2025-12-24T05:52:53", "event": "train_log", "step": 3934, "epoch": 1.6973031283710895, "progress_pct": 28.29, "epoch_pct": 28.29, "eta": "39:03:44", "max_grad_norm": 1.0, "loss": 0.7503598928451538, "grad_norm": 0.5013890266418457, "learning_rate": 0.00017697144454273736}
+{"ts": "2025-12-24T05:53:09", "event": "train_log", "step": 3936, "epoch": 1.6981661272923407, "progress_pct": 28.3, "epoch_pct": 28.3, "eta": "39:02:44", "max_grad_norm": 1.0, "loss": 0.7193819880485535, "grad_norm": 0.4563339054584503, "learning_rate": 0.0001769400862032573}
+{"ts": "2025-12-24T05:53:24", "event": "train_log", "step": 3938, "epoch": 1.6990291262135924, "progress_pct": 28.31, "epoch_pct": 28.32, "eta": "39:01:43", "max_grad_norm": 1.0, "loss": 0.7516534328460693, "grad_norm": 0.4373779892921448, "learning_rate": 0.00017690870931002232}
+{"ts": "2025-12-24T05:53:40", "event": "train_log", "step": 3940, "epoch": 1.6998921251348436, "progress_pct": 28.33, "epoch_pct": 28.33, "eta": "39:00:44", "max_grad_norm": 1.0, "loss": 0.7319802045822144, "grad_norm": 0.40220266580581665, "learning_rate": 0.0001768773138705988}
+{"ts": "2025-12-24T05:53:56", "event": "train_log", "step": 3942, "epoch": 1.700755124056095, "progress_pct": 28.34, "epoch_pct": 28.35, "eta": "38:59:46", "max_grad_norm": 1.0, "loss": 0.6950404644012451, "grad_norm": 0.42924389243125916, "learning_rate": 0.00017684589989255757}
+{"ts": "2025-12-24T05:54:11", "event": "train_log", "step": 3944, "epoch": 1.7016181229773464, "progress_pct": 28.36, "epoch_pct": 28.36, "eta": "38:58:44", "max_grad_norm": 1.0, "loss": 0.697744607925415, "grad_norm": 0.4453158378601074, "learning_rate": 0.00017681446738347404}
+{"ts": "2025-12-24T05:54:27", "event": "train_log", "step": 3946, "epoch": 1.7024811218985976, "progress_pct": 28.37, "epoch_pct": 28.37, "eta": "38:57:45", "max_grad_norm": 1.0, "loss": 0.6951707601547241, "grad_norm": 0.4532380998134613, "learning_rate": 0.00017678301635092795}
+{"ts": "2025-12-24T05:54:41", "event": "train_log", "step": 3948, "epoch": 1.703344120819849, "progress_pct": 28.39, "epoch_pct": 28.39, "eta": "38:56:42", "max_grad_norm": 1.0, "loss": 0.781558096408844, "grad_norm": 0.4668843448162079, "learning_rate": 0.00017675154680250361}
+{"ts": "2025-12-24T05:54:56", "event": "train_log", "step": 3950, "epoch": 1.7042071197411004, "progress_pct": 28.4, "epoch_pct": 28.4, "eta": "38:55:40", "max_grad_norm": 1.0, "loss": 0.7811654806137085, "grad_norm": 0.48179176449775696, "learning_rate": 0.00017672005874578978}
+{"ts": "2025-12-24T05:55:12", "event": "train_log", "step": 3952, "epoch": 1.7050701186623516, "progress_pct": 28.42, "epoch_pct": 28.42, "eta": "38:54:39", "max_grad_norm": 1.0, "loss": 0.7350773215293884, "grad_norm": 0.40447115898132324, "learning_rate": 0.00017668855218837962}
+{"ts": "2025-12-24T05:55:27", "event": "train_log", "step": 3954, "epoch": 1.705933117583603, "progress_pct": 28.43, "epoch_pct": 28.43, "eta": "38:53:40", "max_grad_norm": 1.0, "loss": 0.7492660284042358, "grad_norm": 0.45968949794769287, "learning_rate": 0.00017665702713787082}
+{"ts": "2025-12-24T05:55:42", "event": "train_log", "step": 3956, "epoch": 1.7067961165048544, "progress_pct": 28.44, "epoch_pct": 28.45, "eta": "38:52:39", "max_grad_norm": 1.0, "loss": 0.7472123503684998, "grad_norm": 0.5223715901374817, "learning_rate": 0.0001766254836018655}
+{"ts": "2025-12-24T05:55:57", "event": "train_log", "step": 3958, "epoch": 1.7076591154261056, "progress_pct": 28.46, "epoch_pct": 28.46, "eta": "38:51:38", "max_grad_norm": 1.0, "loss": 0.7836515307426453, "grad_norm": 0.4571165144443512, "learning_rate": 0.00017659392158797023}
+{"ts": "2025-12-24T05:56:12", "event": "train_log", "step": 3960, "epoch": 1.708522114347357, "progress_pct": 28.47, "epoch_pct": 28.48, "eta": "38:50:36", "max_grad_norm": 1.0, "loss": 0.7453757524490356, "grad_norm": 0.4370459318161011, "learning_rate": 0.00017656234110379607}
+{"ts": "2025-12-24T05:56:27", "event": "train_log", "step": 3962, "epoch": 1.7093851132686084, "progress_pct": 28.49, "epoch_pct": 28.49, "eta": "38:49:34", "max_grad_norm": 1.0, "loss": 0.7094024419784546, "grad_norm": 0.4259219467639923, "learning_rate": 0.0001765307421569585}
+{"ts": "2025-12-24T05:56:43", "event": "train_log", "step": 3964, "epoch": 1.7102481121898596, "progress_pct": 28.5, "epoch_pct": 28.5, "eta": "38:48:37", "max_grad_norm": 1.0, "loss": 0.7037264108657837, "grad_norm": 0.41195449233055115, "learning_rate": 0.00017649912475507744}
+{"ts": "2025-12-24T05:56:58", "event": "train_log", "step": 3966, "epoch": 1.7111111111111112, "progress_pct": 28.52, "epoch_pct": 28.52, "eta": "38:47:37", "max_grad_norm": 1.0, "loss": 0.7216715216636658, "grad_norm": 0.40624237060546875, "learning_rate": 0.0001764674889057773}
+{"ts": "2025-12-24T05:57:13", "event": "train_log", "step": 3968, "epoch": 1.7119741100323624, "progress_pct": 28.53, "epoch_pct": 28.53, "eta": "38:46:35", "max_grad_norm": 1.0, "loss": 0.7317749261856079, "grad_norm": 0.46490001678466797, "learning_rate": 0.00017643583461668695}
+{"ts": "2025-12-24T05:57:29", "event": "train_log", "step": 3970, "epoch": 1.7128371089536139, "progress_pct": 28.54, "epoch_pct": 28.55, "eta": "38:45:37", "max_grad_norm": 1.0, "loss": 0.7064663767814636, "grad_norm": 0.4935937821865082, "learning_rate": 0.00017640416189543964}
+{"ts": "2025-12-24T05:57:46", "event": "train_log", "step": 3972, "epoch": 1.7137001078748653, "progress_pct": 28.56, "epoch_pct": 28.56, "eta": "38:44:39", "max_grad_norm": 1.0, "loss": 0.6983333826065063, "grad_norm": 0.454501211643219, "learning_rate": 0.00017637247074967315}
+{"ts": "2025-12-24T05:58:00", "event": "train_log", "step": 3974, "epoch": 1.7145631067961165, "progress_pct": 28.57, "epoch_pct": 28.58, "eta": "38:43:38", "max_grad_norm": 1.0, "loss": 0.7516914010047913, "grad_norm": 0.4357846975326538, "learning_rate": 0.00017634076118702962}
+{"ts": "2025-12-24T05:58:16", "event": "train_log", "step": 3976, "epoch": 1.7154261057173679, "progress_pct": 28.59, "epoch_pct": 28.59, "eta": "38:42:39", "max_grad_norm": 1.0, "loss": 0.7914417386054993, "grad_norm": 0.421758234500885, "learning_rate": 0.00017630903321515565}
+{"ts": "2025-12-24T05:58:32", "event": "train_log", "step": 3978, "epoch": 1.7162891046386193, "progress_pct": 28.6, "epoch_pct": 28.6, "eta": "38:41:40", "max_grad_norm": 1.0, "loss": 0.7100850343704224, "grad_norm": 0.4549725353717804, "learning_rate": 0.00017627728684170235}
+{"ts": "2025-12-24T05:58:47", "event": "train_log", "step": 3980, "epoch": 1.7171521035598705, "progress_pct": 28.62, "epoch_pct": 28.62, "eta": "38:40:41", "max_grad_norm": 1.0, "loss": 0.7711127400398254, "grad_norm": 0.4313303530216217, "learning_rate": 0.00017624552207432518}
+{"ts": "2025-12-24T05:59:02", "event": "train_log", "step": 3982, "epoch": 1.7180151024811219, "progress_pct": 28.63, "epoch_pct": 28.63, "eta": "38:39:41", "max_grad_norm": 1.0, "loss": 0.681434690952301, "grad_norm": 0.46351364254951477, "learning_rate": 0.00017621373892068407}
+{"ts": "2025-12-24T05:59:17", "event": "train_log", "step": 3984, "epoch": 1.7188781014023733, "progress_pct": 28.65, "epoch_pct": 28.65, "eta": "38:38:39", "max_grad_norm": 1.0, "loss": 0.7418093681335449, "grad_norm": 0.5010084509849548, "learning_rate": 0.0001761819373884434}
+{"ts": "2025-12-24T05:59:33", "event": "train_log", "step": 3986, "epoch": 1.7197411003236245, "progress_pct": 28.66, "epoch_pct": 28.66, "eta": "38:37:41", "max_grad_norm": 1.0, "loss": 0.7767686247825623, "grad_norm": 0.4252820909023285, "learning_rate": 0.00017615011748527194}
+{"ts": "2025-12-24T05:59:49", "event": "train_log", "step": 3988, "epoch": 1.720604099244876, "progress_pct": 28.67, "epoch_pct": 28.68, "eta": "38:36:42", "max_grad_norm": 1.0, "loss": 0.7049045562744141, "grad_norm": 0.48956605792045593, "learning_rate": 0.00017611827921884296}
+{"ts": "2025-12-24T06:00:05", "event": "train_log", "step": 3990, "epoch": 1.7214670981661273, "progress_pct": 28.69, "epoch_pct": 28.69, "eta": "38:35:46", "max_grad_norm": 1.0, "loss": 0.7224108576774597, "grad_norm": 0.42927032709121704, "learning_rate": 0.00017608642259683407}
+{"ts": "2025-12-24T06:00:20", "event": "train_log", "step": 3992, "epoch": 1.7223300970873785, "progress_pct": 28.7, "epoch_pct": 28.71, "eta": "38:34:44", "max_grad_norm": 1.0, "loss": 0.7203757166862488, "grad_norm": 0.49601903557777405, "learning_rate": 0.0001760545476269274}
+{"ts": "2025-12-24T06:00:36", "event": "train_log", "step": 3994, "epoch": 1.7231930960086301, "progress_pct": 28.72, "epoch_pct": 28.72, "eta": "38:33:47", "max_grad_norm": 1.0, "loss": 0.6614230871200562, "grad_norm": 0.38675686717033386, "learning_rate": 0.0001760226543168094}
+{"ts": "2025-12-24T06:00:52", "event": "train_log", "step": 3996, "epoch": 1.7240560949298813, "progress_pct": 28.73, "epoch_pct": 28.73, "eta": "38:32:49", "max_grad_norm": 1.0, "loss": 0.7201424837112427, "grad_norm": 0.4299238622188568, "learning_rate": 0.00017599074267417105}
+{"ts": "2025-12-24T06:01:09", "event": "train_log", "step": 3998, "epoch": 1.7249190938511327, "progress_pct": 28.75, "epoch_pct": 28.75, "eta": "38:31:55", "max_grad_norm": 1.0, "loss": 0.7156208753585815, "grad_norm": 0.43249231576919556, "learning_rate": 0.00017595881270670763}
+{"ts": "2025-12-24T06:01:26", "event": "train_log", "step": 4000, "epoch": 1.7257820927723841, "progress_pct": 28.76, "epoch_pct": 28.76, "eta": "38:30:59", "max_grad_norm": 1.0, "loss": 0.7258728742599487, "grad_norm": 0.426278680562973, "learning_rate": 0.00017592686442211898}
+{"ts": "2025-12-24T06:12:24", "event": "train_log", "step": 4000, "epoch": 1.7257820927723841, "progress_pct": 28.76, "epoch_pct": 28.76, "eta": "38:58:09", "max_grad_norm": 1.0, "eval_loss": 0.7843562960624695, "eval_runtime": 657.9206, "eval_samples_per_second": 3.131, "eval_steps_per_second": 3.131}
+{"ts": "2025-12-24T06:12:39", "event": "train_log", "step": 4002, "epoch": 1.7266450916936353, "progress_pct": 28.77, "epoch_pct": 28.78, "eta": "38:57:07", "max_grad_norm": 1.0, "loss": 0.7290486097335815, "grad_norm": 0.4646218419075012, "learning_rate": 0.00017589489782810923}
+{"ts": "2025-12-24T06:12:54", "event": "train_log", "step": 4004, "epoch": 1.7275080906148867, "progress_pct": 28.79, "epoch_pct": 28.79, "eta": "38:56:07", "max_grad_norm": 1.0, "loss": 0.7124513387680054, "grad_norm": 0.4184021055698395, "learning_rate": 0.00017586291293238704}
+{"ts": "2025-12-24T06:13:09", "event": "train_log", "step": 4006, "epoch": 1.7283710895361382, "progress_pct": 28.8, "epoch_pct": 28.81, "eta": "38:55:06", "max_grad_norm": 1.0, "loss": 0.74180006980896, "grad_norm": 0.4271237850189209, "learning_rate": 0.00017583090974266537}
+{"ts": "2025-12-24T06:13:25", "event": "train_log", "step": 4008, "epoch": 1.7292340884573894, "progress_pct": 28.82, "epoch_pct": 28.82, "eta": "38:54:05", "max_grad_norm": 1.0, "loss": 0.6774834394454956, "grad_norm": 0.41022035479545593, "learning_rate": 0.00017579888826666165}
+{"ts": "2025-12-24T06:13:39", "event": "train_log", "step": 4010, "epoch": 1.7300970873786408, "progress_pct": 28.83, "epoch_pct": 28.83, "eta": "38:53:03", "max_grad_norm": 1.0, "loss": 0.7206428050994873, "grad_norm": 0.5100602507591248, "learning_rate": 0.00017576684851209774}
+{"ts": "2025-12-24T06:13:54", "event": "train_log", "step": 4012, "epoch": 1.7309600862998922, "progress_pct": 28.85, "epoch_pct": 28.85, "eta": "38:52:02", "max_grad_norm": 1.0, "loss": 0.6632843613624573, "grad_norm": 0.43499550223350525, "learning_rate": 0.00017573479048669987}
+{"ts": "2025-12-24T06:14:09", "event": "train_log", "step": 4014, "epoch": 1.7318230852211434, "progress_pct": 28.86, "epoch_pct": 28.86, "eta": "38:51:00", "max_grad_norm": 1.0, "loss": 0.7945244312286377, "grad_norm": 0.4398936927318573, "learning_rate": 0.0001757027141981987}
+{"ts": "2025-12-24T06:14:23", "event": "train_log", "step": 4016, "epoch": 1.7326860841423948, "progress_pct": 28.88, "epoch_pct": 28.88, "eta": "38:49:57", "max_grad_norm": 1.0, "loss": 0.7410688996315002, "grad_norm": 0.5156806111335754, "learning_rate": 0.00017567061965432926}
+{"ts": "2025-12-24T06:14:38", "event": "train_log", "step": 4018, "epoch": 1.7335490830636462, "progress_pct": 28.89, "epoch_pct": 28.89, "eta": "38:48:56", "max_grad_norm": 1.0, "loss": 0.7249122858047485, "grad_norm": 0.45140013098716736, "learning_rate": 0.00017563850686283102}
+{"ts": "2025-12-24T06:14:52", "event": "train_log", "step": 4020, "epoch": 1.7344120819848974, "progress_pct": 28.9, "epoch_pct": 28.91, "eta": "38:47:54", "max_grad_norm": 1.0, "loss": 0.7548064589500427, "grad_norm": 0.4980209469795227, "learning_rate": 0.0001756063758314478}
+{"ts": "2025-12-24T06:15:08", "event": "train_log", "step": 4022, "epoch": 1.735275080906149, "progress_pct": 28.92, "epoch_pct": 28.92, "eta": "38:46:54", "max_grad_norm": 1.0, "loss": 0.6763073205947876, "grad_norm": 0.426337867975235, "learning_rate": 0.00017557422656792792}
+{"ts": "2025-12-24T06:15:22", "event": "train_log", "step": 4024, "epoch": 1.7361380798274002, "progress_pct": 28.93, "epoch_pct": 28.94, "eta": "38:45:52", "max_grad_norm": 1.0, "loss": 0.8444951176643372, "grad_norm": 0.4775279760360718, "learning_rate": 0.000175542059080024}
+{"ts": "2025-12-24T06:15:37", "event": "train_log", "step": 4026, "epoch": 1.7370010787486516, "progress_pct": 28.95, "epoch_pct": 28.95, "eta": "38:44:51", "max_grad_norm": 1.0, "loss": 0.7031195163726807, "grad_norm": 0.4614261984825134, "learning_rate": 0.00017550987337549304}
+{"ts": "2025-12-24T06:15:51", "event": "train_log", "step": 4028, "epoch": 1.737864077669903, "progress_pct": 28.96, "epoch_pct": 28.96, "eta": "38:43:48", "max_grad_norm": 1.0, "loss": 0.7708158493041992, "grad_norm": 0.4657931327819824, "learning_rate": 0.00017547766946209654}
+{"ts": "2025-12-24T06:16:07", "event": "train_log", "step": 4030, "epoch": 1.7387270765911542, "progress_pct": 28.98, "epoch_pct": 28.98, "eta": "38:42:48", "max_grad_norm": 1.0, "loss": 0.7013334035873413, "grad_norm": 0.4373331665992737, "learning_rate": 0.0001754454473476003}
+{"ts": "2025-12-24T06:16:20", "event": "train_log", "step": 4032, "epoch": 1.7395900755124056, "progress_pct": 28.99, "epoch_pct": 28.99, "eta": "38:41:45", "max_grad_norm": 1.0, "loss": 0.7644510865211487, "grad_norm": 0.5230216383934021, "learning_rate": 0.00017541320703977453}
+{"ts": "2025-12-24T06:16:36", "event": "train_log", "step": 4034, "epoch": 1.740453074433657, "progress_pct": 29.0, "epoch_pct": 29.01, "eta": "38:40:45", "max_grad_norm": 1.0, "loss": 0.7311883568763733, "grad_norm": 0.4254145920276642, "learning_rate": 0.00017538094854639387}
+{"ts": "2025-12-24T06:16:51", "event": "train_log", "step": 4036, "epoch": 1.7413160733549082, "progress_pct": 29.02, "epoch_pct": 29.02, "eta": "38:39:44", "max_grad_norm": 1.0, "loss": 0.8042954802513123, "grad_norm": 0.40677928924560547, "learning_rate": 0.00017534867187523728}
+{"ts": "2025-12-24T06:17:05", "event": "train_log", "step": 4038, "epoch": 1.7421790722761596, "progress_pct": 29.03, "epoch_pct": 29.04, "eta": "38:38:42", "max_grad_norm": 1.0, "loss": 0.7260869741439819, "grad_norm": 0.4729449450969696, "learning_rate": 0.00017531637703408815}
+{"ts": "2025-12-24T06:17:20", "event": "train_log", "step": 4040, "epoch": 1.743042071197411, "progress_pct": 29.05, "epoch_pct": 29.05, "eta": "38:37:41", "max_grad_norm": 1.0, "loss": 0.7968364953994751, "grad_norm": 0.5013999342918396, "learning_rate": 0.0001752840640307342}
+{"ts": "2025-12-24T06:17:34", "event": "train_log", "step": 4042, "epoch": 1.7439050701186622, "progress_pct": 29.06, "epoch_pct": 29.07, "eta": "38:36:38", "max_grad_norm": 1.0, "loss": 0.6834843754768372, "grad_norm": 0.50171959400177, "learning_rate": 0.0001752517328729676}
+{"ts": "2025-12-24T06:17:48", "event": "train_log", "step": 4044, "epoch": 1.7447680690399137, "progress_pct": 29.08, "epoch_pct": 29.08, "eta": "38:35:37", "max_grad_norm": 1.0, "loss": 0.7420654296875, "grad_norm": 0.45370912551879883, "learning_rate": 0.00017521938356858488}
+{"ts": "2025-12-24T06:18:03", "event": "train_log", "step": 4046, "epoch": 1.745631067961165, "progress_pct": 29.09, "epoch_pct": 29.09, "eta": "38:34:36", "max_grad_norm": 1.0, "loss": 0.721342921257019, "grad_norm": 0.43417057394981384, "learning_rate": 0.00017518701612538685}
+{"ts": "2025-12-24T06:18:19", "event": "train_log", "step": 4048, "epoch": 1.7464940668824163, "progress_pct": 29.11, "epoch_pct": 29.11, "eta": "38:33:38", "max_grad_norm": 1.0, "loss": 0.6757205128669739, "grad_norm": 0.3888097405433655, "learning_rate": 0.00017515463055117885}
+{"ts": "2025-12-24T06:18:34", "event": "train_log", "step": 4050, "epoch": 1.747357065803668, "progress_pct": 29.12, "epoch_pct": 29.12, "eta": "38:32:39", "max_grad_norm": 1.0, "loss": 0.682235062122345, "grad_norm": 0.3910084068775177, "learning_rate": 0.00017512222685377055}
+{"ts": "2025-12-24T06:18:49", "event": "train_log", "step": 4052, "epoch": 1.748220064724919, "progress_pct": 29.13, "epoch_pct": 29.14, "eta": "38:31:38", "max_grad_norm": 1.0, "loss": 0.6801605224609375, "grad_norm": 0.4092451333999634, "learning_rate": 0.0001750898050409758}
+{"ts": "2025-12-24T06:19:04", "event": "train_log", "step": 4054, "epoch": 1.7490830636461703, "progress_pct": 29.15, "epoch_pct": 29.15, "eta": "38:30:38", "max_grad_norm": 1.0, "loss": 0.7368552684783936, "grad_norm": 0.464478075504303, "learning_rate": 0.00017505736512061316}
+{"ts": "2025-12-24T06:19:18", "event": "train_log", "step": 4056, "epoch": 1.749946062567422, "progress_pct": 29.16, "epoch_pct": 29.17, "eta": "38:29:35", "max_grad_norm": 1.0, "loss": 0.7422438263893127, "grad_norm": 0.47949129343032837, "learning_rate": 0.00017502490710050522}
+{"ts": "2025-12-24T06:19:32", "event": "train_log", "step": 4058, "epoch": 1.750809061488673, "progress_pct": 29.18, "epoch_pct": 29.18, "eta": "38:28:33", "max_grad_norm": 1.0, "loss": 0.7370736598968506, "grad_norm": 0.47410422563552856, "learning_rate": 0.00017499243098847918}
+{"ts": "2025-12-24T06:19:47", "event": "train_log", "step": 4060, "epoch": 1.7516720604099245, "progress_pct": 29.19, "epoch_pct": 29.19, "eta": "38:27:33", "max_grad_norm": 1.0, "loss": 0.6773675680160522, "grad_norm": 0.3986700177192688, "learning_rate": 0.00017495993679236645}
+{"ts": "2025-12-24T06:20:03", "event": "train_log", "step": 4062, "epoch": 1.752535059331176, "progress_pct": 29.21, "epoch_pct": 29.21, "eta": "38:26:35", "max_grad_norm": 1.0, "loss": 0.7170975208282471, "grad_norm": 0.41113027930259705, "learning_rate": 0.0001749274245200029}
+{"ts": "2025-12-24T06:20:18", "event": "train_log", "step": 4064, "epoch": 1.7533980582524271, "progress_pct": 29.22, "epoch_pct": 29.22, "eta": "38:25:37", "max_grad_norm": 1.0, "loss": 0.6957781314849854, "grad_norm": 0.43275657296180725, "learning_rate": 0.0001748948941792287}
+{"ts": "2025-12-24T06:20:33", "event": "train_log", "step": 4066, "epoch": 1.7542610571736785, "progress_pct": 29.23, "epoch_pct": 29.24, "eta": "38:24:36", "max_grad_norm": 1.0, "loss": 0.7540420889854431, "grad_norm": 0.4488718509674072, "learning_rate": 0.00017486234577788838}
+{"ts": "2025-12-24T06:20:49", "event": "train_log", "step": 4068, "epoch": 1.75512405609493, "progress_pct": 29.25, "epoch_pct": 29.25, "eta": "38:23:40", "max_grad_norm": 1.0, "loss": 0.7581563591957092, "grad_norm": 0.44178634881973267, "learning_rate": 0.00017482977932383088}
+{"ts": "2025-12-24T06:21:04", "event": "train_log", "step": 4070, "epoch": 1.7559870550161811, "progress_pct": 29.26, "epoch_pct": 29.27, "eta": "38:22:40", "max_grad_norm": 1.0, "loss": 0.7012783885002136, "grad_norm": 0.4245910942554474, "learning_rate": 0.0001747971948249094}
+{"ts": "2025-12-24T06:21:19", "event": "train_log", "step": 4072, "epoch": 1.7568500539374325, "progress_pct": 29.28, "epoch_pct": 29.28, "eta": "38:21:40", "max_grad_norm": 1.0, "loss": 0.6657902002334595, "grad_norm": 0.4418242573738098, "learning_rate": 0.0001747645922889816}
+{"ts": "2025-12-24T06:21:34", "event": "train_log", "step": 4074, "epoch": 1.757713052858684, "progress_pct": 29.29, "epoch_pct": 29.3, "eta": "38:20:39", "max_grad_norm": 1.0, "loss": 0.6813042163848877, "grad_norm": 0.4621461033821106, "learning_rate": 0.00017473197172390942}
+{"ts": "2025-12-24T06:21:49", "event": "train_log", "step": 4076, "epoch": 1.7585760517799351, "progress_pct": 29.31, "epoch_pct": 29.31, "eta": "38:19:41", "max_grad_norm": 1.0, "loss": 0.7490677237510681, "grad_norm": 0.47244367003440857, "learning_rate": 0.00017469933313755913}
+{"ts": "2025-12-24T06:22:05", "event": "train_log", "step": 4078, "epoch": 1.7594390507011868, "progress_pct": 29.32, "epoch_pct": 29.32, "eta": "38:18:42", "max_grad_norm": 1.0, "loss": 0.7485169172286987, "grad_norm": 0.43918749690055847, "learning_rate": 0.00017466667653780142}
+{"ts": "2025-12-24T06:22:20", "event": "train_log", "step": 4080, "epoch": 1.760302049622438, "progress_pct": 29.34, "epoch_pct": 29.34, "eta": "38:17:42", "max_grad_norm": 1.0, "loss": 0.8234745264053345, "grad_norm": 0.45456430315971375, "learning_rate": 0.00017463400193251126}
+{"ts": "2025-12-24T06:22:35", "event": "train_log", "step": 4082, "epoch": 1.7611650485436892, "progress_pct": 29.35, "epoch_pct": 29.35, "eta": "38:16:44", "max_grad_norm": 1.0, "loss": 0.8200880289077759, "grad_norm": 0.47970378398895264, "learning_rate": 0.000174601309329568}
+{"ts": "2025-12-24T06:22:52", "event": "train_log", "step": 4084, "epoch": 1.7620280474649408, "progress_pct": 29.36, "epoch_pct": 29.37, "eta": "38:15:48", "max_grad_norm": 1.0, "loss": 0.7460210919380188, "grad_norm": 0.4489441215991974, "learning_rate": 0.00017456859873685523}
+{"ts": "2025-12-24T06:23:07", "event": "train_log", "step": 4086, "epoch": 1.762891046386192, "progress_pct": 29.38, "epoch_pct": 29.38, "eta": "38:14:50", "max_grad_norm": 1.0, "loss": 0.7544209957122803, "grad_norm": 0.44073280692100525, "learning_rate": 0.0001745358701622611}
+{"ts": "2025-12-24T06:23:21", "event": "train_log", "step": 4088, "epoch": 1.7637540453074434, "progress_pct": 29.39, "epoch_pct": 29.4, "eta": "38:13:49", "max_grad_norm": 1.0, "loss": 0.7942423820495605, "grad_norm": 0.5178254842758179, "learning_rate": 0.00017450312361367787}
+{"ts": "2025-12-24T06:23:38", "event": "train_log", "step": 4090, "epoch": 1.7646170442286948, "progress_pct": 29.41, "epoch_pct": 29.41, "eta": "38:12:54", "max_grad_norm": 1.0, "loss": 0.6761540174484253, "grad_norm": 0.4069359600543976, "learning_rate": 0.00017447035909900222}
+{"ts": "2025-12-24T06:23:54", "event": "train_log", "step": 4092, "epoch": 1.765480043149946, "progress_pct": 29.42, "epoch_pct": 29.42, "eta": "38:11:56", "max_grad_norm": 1.0, "loss": 0.6959407329559326, "grad_norm": 0.42108529806137085, "learning_rate": 0.0001744375766261352}
+{"ts": "2025-12-24T06:24:09", "event": "train_log", "step": 4094, "epoch": 1.7663430420711974, "progress_pct": 29.44, "epoch_pct": 29.44, "eta": "38:10:58", "max_grad_norm": 1.0, "loss": 0.8067643642425537, "grad_norm": 0.4824271500110626, "learning_rate": 0.00017440477620298217}
+{"ts": "2025-12-24T06:24:25", "event": "train_log", "step": 4096, "epoch": 1.7672060409924488, "progress_pct": 29.45, "epoch_pct": 29.45, "eta": "38:10:01", "max_grad_norm": 1.0, "loss": 0.8048238754272461, "grad_norm": 0.4846031367778778, "learning_rate": 0.00017437195783745276}
+{"ts": "2025-12-24T06:24:40", "event": "train_log", "step": 4098, "epoch": 1.7680690399137, "progress_pct": 29.47, "epoch_pct": 29.47, "eta": "38:09:02", "max_grad_norm": 1.0, "loss": 0.7465305328369141, "grad_norm": 0.47893181443214417, "learning_rate": 0.00017433912153746098}
+{"ts": "2025-12-24T06:24:56", "event": "train_log", "step": 4100, "epoch": 1.7689320388349514, "progress_pct": 29.48, "epoch_pct": 29.48, "eta": "38:08:04", "max_grad_norm": 1.0, "loss": 0.7086948752403259, "grad_norm": 0.4115507900714874, "learning_rate": 0.00017430626731092515}
+{"ts": "2025-12-24T06:36:02", "event": "train_log", "step": 4100, "epoch": 1.7689320388349514, "progress_pct": 29.48, "epoch_pct": 29.48, "eta": "38:34:39", "max_grad_norm": 1.0, "eval_loss": 0.7808024883270264, "eval_runtime": 666.5954, "eval_samples_per_second": 3.09, "eval_steps_per_second": 3.09}
+{"ts": "2025-12-24T06:36:18", "event": "train_log", "step": 4102, "epoch": 1.7697950377562028, "progress_pct": 29.49, "epoch_pct": 29.5, "eta": "38:33:39", "max_grad_norm": 1.0, "loss": 0.6837684512138367, "grad_norm": 0.40175846219062805, "learning_rate": 0.00017427339516576796}
+{"ts": "2025-12-24T06:36:32", "event": "train_log", "step": 4104, "epoch": 1.770658036677454, "progress_pct": 29.51, "epoch_pct": 29.51, "eta": "38:32:38", "max_grad_norm": 1.0, "loss": 0.7253594994544983, "grad_norm": 0.4699510633945465, "learning_rate": 0.00017424050510991634}
+{"ts": "2025-12-24T06:36:47", "event": "train_log", "step": 4106, "epoch": 1.7715210355987057, "progress_pct": 29.52, "epoch_pct": 29.53, "eta": "38:31:37", "max_grad_norm": 1.0, "loss": 0.7273471355438232, "grad_norm": 0.5029735565185547, "learning_rate": 0.0001742075971513016}
+{"ts": "2025-12-24T06:37:01", "event": "train_log", "step": 4108, "epoch": 1.7723840345199569, "progress_pct": 29.54, "epoch_pct": 29.54, "eta": "38:30:35", "max_grad_norm": 1.0, "loss": 0.7040302157402039, "grad_norm": 0.46295008063316345, "learning_rate": 0.00017417467129785937}
+{"ts": "2025-12-24T06:37:15", "event": "train_log", "step": 4110, "epoch": 1.773247033441208, "progress_pct": 29.55, "epoch_pct": 29.55, "eta": "38:29:33", "max_grad_norm": 1.0, "loss": 0.72527015209198, "grad_norm": 0.43181541562080383, "learning_rate": 0.0001741417275575295}
+{"ts": "2025-12-24T06:37:30", "event": "train_log", "step": 4112, "epoch": 1.7741100323624597, "progress_pct": 29.57, "epoch_pct": 29.57, "eta": "38:28:32", "max_grad_norm": 1.0, "loss": 0.6736238598823547, "grad_norm": 0.40259307622909546, "learning_rate": 0.00017410876593825625}
+{"ts": "2025-12-24T06:37:44", "event": "train_log", "step": 4114, "epoch": 1.7749730312837109, "progress_pct": 29.58, "epoch_pct": 29.58, "eta": "38:27:31", "max_grad_norm": 1.0, "loss": 0.6924970746040344, "grad_norm": 0.44186654686927795, "learning_rate": 0.00017407578644798818}
+{"ts": "2025-12-24T06:37:59", "event": "train_log", "step": 4116, "epoch": 1.7758360302049623, "progress_pct": 29.59, "epoch_pct": 29.6, "eta": "38:26:30", "max_grad_norm": 1.0, "loss": 0.7088955640792847, "grad_norm": 0.5186018347740173, "learning_rate": 0.00017404278909467815}
+{"ts": "2025-12-24T06:38:13", "event": "train_log", "step": 4118, "epoch": 1.7766990291262137, "progress_pct": 29.61, "epoch_pct": 29.61, "eta": "38:25:29", "max_grad_norm": 1.0, "loss": 0.6548104286193848, "grad_norm": 0.45042574405670166, "learning_rate": 0.00017400977388628332}
+{"ts": "2025-12-24T06:38:28", "event": "train_log", "step": 4120, "epoch": 1.7775620280474649, "progress_pct": 29.62, "epoch_pct": 29.63, "eta": "38:24:28", "max_grad_norm": 1.0, "loss": 0.6818945407867432, "grad_norm": 0.4164215326309204, "learning_rate": 0.00017397674083076517}
+{"ts": "2025-12-24T06:38:43", "event": "train_log", "step": 4122, "epoch": 1.7784250269687163, "progress_pct": 29.64, "epoch_pct": 29.64, "eta": "38:23:29", "max_grad_norm": 1.0, "loss": 0.7920825481414795, "grad_norm": 0.4045083522796631, "learning_rate": 0.00017394368993608943}
+{"ts": "2025-12-24T06:38:57", "event": "train_log", "step": 4124, "epoch": 1.7792880258899677, "progress_pct": 29.65, "epoch_pct": 29.65, "eta": "38:22:28", "max_grad_norm": 1.0, "loss": 0.7774871587753296, "grad_norm": 0.4170040190219879, "learning_rate": 0.0001739106212102262}
+{"ts": "2025-12-24T06:39:12", "event": "train_log", "step": 4126, "epoch": 1.780151024811219, "progress_pct": 29.67, "epoch_pct": 29.67, "eta": "38:21:27", "max_grad_norm": 1.0, "loss": 0.7776943445205688, "grad_norm": 0.4969266653060913, "learning_rate": 0.00017387753466114987}
+{"ts": "2025-12-24T06:39:27", "event": "train_log", "step": 4128, "epoch": 1.7810140237324703, "progress_pct": 29.68, "epoch_pct": 29.68, "eta": "38:20:28", "max_grad_norm": 1.0, "loss": 0.6679043769836426, "grad_norm": 0.36906328797340393, "learning_rate": 0.00017384443029683913}
+{"ts": "2025-12-24T06:39:42", "event": "train_log", "step": 4130, "epoch": 1.7818770226537217, "progress_pct": 29.7, "epoch_pct": 29.7, "eta": "38:19:27", "max_grad_norm": 1.0, "loss": 0.7691782712936401, "grad_norm": 0.476610392332077, "learning_rate": 0.00017381130812527687}
+{"ts": "2025-12-24T06:39:56", "event": "train_log", "step": 4132, "epoch": 1.782740021574973, "progress_pct": 29.71, "epoch_pct": 29.71, "eta": "38:18:26", "max_grad_norm": 1.0, "loss": 0.7127588987350464, "grad_norm": 0.45970338582992554, "learning_rate": 0.0001737781681544504}
+{"ts": "2025-12-24T06:40:11", "event": "train_log", "step": 4134, "epoch": 1.7836030204962245, "progress_pct": 29.72, "epoch_pct": 29.73, "eta": "38:17:26", "max_grad_norm": 1.0, "loss": 0.7561655044555664, "grad_norm": 0.47383829951286316, "learning_rate": 0.00017374501039235128}
+{"ts": "2025-12-24T06:40:25", "event": "train_log", "step": 4136, "epoch": 1.7844660194174757, "progress_pct": 29.74, "epoch_pct": 29.74, "eta": "38:16:26", "max_grad_norm": 1.0, "loss": 0.739709734916687, "grad_norm": 0.40685102343559265, "learning_rate": 0.00017371183484697538}
+{"ts": "2025-12-24T06:40:40", "event": "train_log", "step": 4138, "epoch": 1.785329018338727, "progress_pct": 29.75, "epoch_pct": 29.76, "eta": "38:15:25", "max_grad_norm": 1.0, "loss": 0.8365469574928284, "grad_norm": 0.4961703419685364, "learning_rate": 0.0001736786415263228}
+{"ts": "2025-12-24T06:40:54", "event": "train_log", "step": 4140, "epoch": 1.7861920172599786, "progress_pct": 29.77, "epoch_pct": 29.77, "eta": "38:14:25", "max_grad_norm": 1.0, "loss": 0.758213996887207, "grad_norm": 0.44277071952819824, "learning_rate": 0.00017364543043839792}
+{"ts": "2025-12-24T06:41:10", "event": "train_log", "step": 4142, "epoch": 1.7870550161812297, "progress_pct": 29.78, "epoch_pct": 29.78, "eta": "38:13:26", "max_grad_norm": 1.0, "loss": 0.6730729341506958, "grad_norm": 0.4293559491634369, "learning_rate": 0.00017361220159120948}
+{"ts": "2025-12-24T06:41:24", "event": "train_log", "step": 4144, "epoch": 1.7879180151024812, "progress_pct": 29.8, "epoch_pct": 29.8, "eta": "38:12:25", "max_grad_norm": 1.0, "loss": 0.8141124248504639, "grad_norm": 0.4188339114189148, "learning_rate": 0.00017357895499277052}
+{"ts": "2025-12-24T06:41:38", "event": "train_log", "step": 4146, "epoch": 1.7887810140237326, "progress_pct": 29.81, "epoch_pct": 29.81, "eta": "38:11:25", "max_grad_norm": 1.0, "loss": 0.7831918597221375, "grad_norm": 0.41425400972366333, "learning_rate": 0.0001735456906510982}
+{"ts": "2025-12-24T06:41:53", "event": "train_log", "step": 4148, "epoch": 1.7896440129449838, "progress_pct": 29.82, "epoch_pct": 29.83, "eta": "38:10:25", "max_grad_norm": 1.0, "loss": 0.6969084739685059, "grad_norm": 0.4522942304611206, "learning_rate": 0.0001735124085742142}
+{"ts": "2025-12-24T06:42:08", "event": "train_log", "step": 4150, "epoch": 1.7905070118662352, "progress_pct": 29.84, "epoch_pct": 29.84, "eta": "38:09:26", "max_grad_norm": 1.0, "loss": 0.6732504963874817, "grad_norm": 0.5915003418922424, "learning_rate": 0.00017347910877014422}
+{"ts": "2025-12-24T06:42:24", "event": "train_log", "step": 4152, "epoch": 1.7913700107874866, "progress_pct": 29.85, "epoch_pct": 29.86, "eta": "38:08:28", "max_grad_norm": 1.0, "loss": 0.7403483390808105, "grad_norm": 0.41376325488090515, "learning_rate": 0.0001734457912469184}
+{"ts": "2025-12-24T06:42:39", "event": "train_log", "step": 4154, "epoch": 1.7922330097087378, "progress_pct": 29.87, "epoch_pct": 29.87, "eta": "38:07:29", "max_grad_norm": 1.0, "loss": 0.6874727606773376, "grad_norm": 0.3962151110172272, "learning_rate": 0.00017341245601257111}
+{"ts": "2025-12-24T06:42:53", "event": "train_log", "step": 4156, "epoch": 1.7930960086299892, "progress_pct": 29.88, "epoch_pct": 29.88, "eta": "38:06:30", "max_grad_norm": 1.0, "loss": 0.6919097900390625, "grad_norm": 0.4639807939529419, "learning_rate": 0.00017337910307514101}
+{"ts": "2025-12-24T06:43:08", "event": "train_log", "step": 4158, "epoch": 1.7939590075512406, "progress_pct": 29.9, "epoch_pct": 29.9, "eta": "38:05:30", "max_grad_norm": 1.0, "loss": 0.7562543749809265, "grad_norm": 0.40313324332237244, "learning_rate": 0.000173345732442671}
+{"ts": "2025-12-24T06:43:23", "event": "train_log", "step": 4160, "epoch": 1.7948220064724918, "progress_pct": 29.91, "epoch_pct": 29.91, "eta": "38:04:30", "max_grad_norm": 1.0, "loss": 0.729914128780365, "grad_norm": 0.4477533996105194, "learning_rate": 0.0001733123441232083}
+{"ts": "2025-12-24T06:43:36", "event": "train_log", "step": 4162, "epoch": 1.7956850053937432, "progress_pct": 29.93, "epoch_pct": 29.93, "eta": "38:03:28", "max_grad_norm": 1.0, "loss": 0.8119242787361145, "grad_norm": 0.5002303123474121, "learning_rate": 0.00017327893812480426}
+{"ts": "2025-12-24T06:43:51", "event": "train_log", "step": 4164, "epoch": 1.7965480043149946, "progress_pct": 29.94, "epoch_pct": 29.94, "eta": "38:02:29", "max_grad_norm": 1.0, "loss": 0.6835103034973145, "grad_norm": 0.464579313993454, "learning_rate": 0.00017324551445551466}
+{"ts": "2025-12-24T06:44:07", "event": "train_log", "step": 4166, "epoch": 1.7974110032362458, "progress_pct": 29.95, "epoch_pct": 29.96, "eta": "38:01:32", "max_grad_norm": 1.0, "loss": 0.7308543920516968, "grad_norm": 0.3973700702190399, "learning_rate": 0.0001732120731233994}
+{"ts": "2025-12-24T06:44:23", "event": "train_log", "step": 4168, "epoch": 1.7982740021574974, "progress_pct": 29.97, "epoch_pct": 29.97, "eta": "38:00:35", "max_grad_norm": 1.0, "loss": 0.6357728838920593, "grad_norm": 0.3675004839897156, "learning_rate": 0.00017317861413652277}
+{"ts": "2025-12-24T06:44:38", "event": "train_log", "step": 4170, "epoch": 1.7991370010787486, "progress_pct": 29.98, "epoch_pct": 29.99, "eta": "37:59:37", "max_grad_norm": 1.0, "loss": 0.7257087230682373, "grad_norm": 0.5020666718482971, "learning_rate": 0.00017314513750295323}
+{"ts": "2025-12-24T06:44:54", "event": "train_log", "step": 4172, "epoch": 1.8, "progress_pct": 30.0, "epoch_pct": 30.0, "eta": "37:58:42", "max_grad_norm": 1.0, "loss": 0.6529711484909058, "grad_norm": 0.43989744782447815, "learning_rate": 0.00017311164323076354}
+{"ts": "2025-12-24T06:45:09", "event": "train_log", "step": 4174, "epoch": 1.8008629989212515, "progress_pct": 30.01, "epoch_pct": 30.01, "eta": "37:57:42", "max_grad_norm": 1.0, "loss": 0.740652859210968, "grad_norm": 0.4717860221862793, "learning_rate": 0.00017307813132803066}
+{"ts": "2025-12-24T06:45:24", "event": "train_log", "step": 4176, "epoch": 1.8017259978425026, "progress_pct": 30.03, "epoch_pct": 30.03, "eta": "37:56:43", "max_grad_norm": 1.0, "loss": 0.7142172455787659, "grad_norm": 0.42297297716140747, "learning_rate": 0.00017304460180283583}
+{"ts": "2025-12-24T06:45:38", "event": "train_log", "step": 4178, "epoch": 1.802588996763754, "progress_pct": 30.04, "epoch_pct": 30.04, "eta": "37:55:43", "max_grad_norm": 1.0, "loss": 0.7233486175537109, "grad_norm": 0.4779362976551056, "learning_rate": 0.0001730110546632646}
+{"ts": "2025-12-24T06:45:53", "event": "train_log", "step": 4180, "epoch": 1.8034519956850055, "progress_pct": 30.05, "epoch_pct": 30.06, "eta": "37:54:45", "max_grad_norm": 1.0, "loss": 0.7120639681816101, "grad_norm": 0.38539960980415344, "learning_rate": 0.00017297748991740663}
+{"ts": "2025-12-24T06:46:08", "event": "train_log", "step": 4182, "epoch": 1.8043149946062567, "progress_pct": 30.07, "epoch_pct": 30.07, "eta": "37:53:45", "max_grad_norm": 1.0, "loss": 0.7120950818061829, "grad_norm": 0.43327030539512634, "learning_rate": 0.000172943907573356}
+{"ts": "2025-12-24T06:46:22", "event": "train_log", "step": 4184, "epoch": 1.805177993527508, "progress_pct": 30.08, "epoch_pct": 30.09, "eta": "37:52:45", "max_grad_norm": 1.0, "loss": 0.7957805395126343, "grad_norm": 0.48741552233695984, "learning_rate": 0.00017291030763921087}
+{"ts": "2025-12-24T06:46:36", "event": "train_log", "step": 4186, "epoch": 1.8060409924487595, "progress_pct": 30.1, "epoch_pct": 30.1, "eta": "37:51:43", "max_grad_norm": 1.0, "loss": 0.6962721943855286, "grad_norm": 0.4763964116573334, "learning_rate": 0.0001728766901230737}
+{"ts": "2025-12-24T06:46:50", "event": "train_log", "step": 4188, "epoch": 1.8069039913700107, "progress_pct": 30.11, "epoch_pct": 30.12, "eta": "37:50:44", "max_grad_norm": 1.0, "loss": 0.6778126955032349, "grad_norm": 0.4499688744544983, "learning_rate": 0.00017284305503305128}
+{"ts": "2025-12-24T06:47:05", "event": "train_log", "step": 4190, "epoch": 1.807766990291262, "progress_pct": 30.13, "epoch_pct": 30.13, "eta": "37:49:45", "max_grad_norm": 1.0, "loss": 0.7177738547325134, "grad_norm": 0.46147263050079346, "learning_rate": 0.00017280940237725451}
+{"ts": "2025-12-24T06:47:20", "event": "train_log", "step": 4192, "epoch": 1.8086299892125135, "progress_pct": 30.14, "epoch_pct": 30.14, "eta": "37:48:47", "max_grad_norm": 1.0, "loss": 0.6445587277412415, "grad_norm": 0.39121973514556885, "learning_rate": 0.00017277573216379857}
+{"ts": "2025-12-24T06:47:34", "event": "train_log", "step": 4194, "epoch": 1.8094929881337647, "progress_pct": 30.16, "epoch_pct": 30.16, "eta": "37:47:47", "max_grad_norm": 1.0, "loss": 0.8183205723762512, "grad_norm": 0.44156384468078613, "learning_rate": 0.0001727420444008029}
+{"ts": "2025-12-24T06:47:48", "event": "train_log", "step": 4196, "epoch": 1.8103559870550163, "progress_pct": 30.17, "epoch_pct": 30.17, "eta": "37:46:47", "max_grad_norm": 1.0, "loss": 0.708315908908844, "grad_norm": 0.45122894644737244, "learning_rate": 0.00017270833909639114}
+{"ts": "2025-12-24T06:48:02", "event": "train_log", "step": 4198, "epoch": 1.8112189859762675, "progress_pct": 30.18, "epoch_pct": 30.19, "eta": "37:45:46", "max_grad_norm": 1.0, "loss": 0.7654728293418884, "grad_norm": 0.5312398672103882, "learning_rate": 0.00017267461625869118}
+{"ts": "2025-12-24T06:48:17", "event": "train_log", "step": 4200, "epoch": 1.812081984897519, "progress_pct": 30.2, "epoch_pct": 30.2, "eta": "37:44:47", "max_grad_norm": 1.0, "loss": 0.8182219862937927, "grad_norm": 0.4401609003543854, "learning_rate": 0.00017264087589583516}
+{"ts": "2025-12-24T06:59:21", "event": "train_log", "step": 4200, "epoch": 1.812081984897519, "progress_pct": 30.2, "epoch_pct": 30.2, "eta": "38:10:23", "max_grad_norm": 1.0, "eval_loss": 0.7768770456314087, "eval_runtime": 664.5255, "eval_samples_per_second": 3.1, "eval_steps_per_second": 3.1}
+{"ts": "2025-12-24T06:59:36", "event": "train_log", "step": 4202, "epoch": 1.8129449838187703, "progress_pct": 30.21, "epoch_pct": 30.22, "eta": "38:09:24", "max_grad_norm": 1.0, "loss": 0.6492214202880859, "grad_norm": 0.40371671319007874, "learning_rate": 0.00017260711801595933}
+{"ts": "2025-12-24T06:59:54", "event": "train_log", "step": 4204, "epoch": 1.8138079827400215, "progress_pct": 30.23, "epoch_pct": 30.23, "eta": "38:08:31", "max_grad_norm": 1.0, "loss": 0.7230119705200195, "grad_norm": 0.4950125813484192, "learning_rate": 0.00017257334262720436}
+{"ts": "2025-12-24T07:00:08", "event": "train_log", "step": 4206, "epoch": 1.814670981661273, "progress_pct": 30.24, "epoch_pct": 30.24, "eta": "38:07:31", "max_grad_norm": 1.0, "loss": 0.7157304883003235, "grad_norm": 0.4659440517425537, "learning_rate": 0.00017253954973771494}
+{"ts": "2025-12-24T07:00:24", "event": "train_log", "step": 4208, "epoch": 1.8155339805825244, "progress_pct": 30.26, "epoch_pct": 30.26, "eta": "38:06:33", "max_grad_norm": 1.0, "loss": 0.7163988351821899, "grad_norm": 0.4222276508808136, "learning_rate": 0.00017250573935564012}
+{"ts": "2025-12-24T07:00:39", "event": "train_log", "step": 4210, "epoch": 1.8163969795037755, "progress_pct": 30.27, "epoch_pct": 30.27, "eta": "38:05:35", "max_grad_norm": 1.0, "loss": 0.8364236950874329, "grad_norm": 0.4653847813606262, "learning_rate": 0.0001724719114891331}
+{"ts": "2025-12-24T07:00:55", "event": "train_log", "step": 4212, "epoch": 1.817259978425027, "progress_pct": 30.28, "epoch_pct": 30.29, "eta": "38:04:37", "max_grad_norm": 1.0, "loss": 0.7096951007843018, "grad_norm": 0.42004603147506714, "learning_rate": 0.00017243806614635133}
+{"ts": "2025-12-24T07:01:10", "event": "train_log", "step": 4214, "epoch": 1.8181229773462784, "progress_pct": 30.3, "epoch_pct": 30.3, "eta": "38:03:39", "max_grad_norm": 1.0, "loss": 0.7669811248779297, "grad_norm": 0.4078772962093353, "learning_rate": 0.0001724042033354565}
+{"ts": "2025-12-24T07:01:26", "event": "train_log", "step": 4216, "epoch": 1.8189859762675296, "progress_pct": 30.31, "epoch_pct": 30.32, "eta": "38:02:42", "max_grad_norm": 1.0, "loss": 0.8241565823554993, "grad_norm": 0.540237307548523, "learning_rate": 0.0001723703230646144}
+{"ts": "2025-12-24T07:01:41", "event": "train_log", "step": 4218, "epoch": 1.819848975188781, "progress_pct": 30.33, "epoch_pct": 30.33, "eta": "38:01:43", "max_grad_norm": 1.0, "loss": 0.7156816720962524, "grad_norm": 0.5155133008956909, "learning_rate": 0.00017233642534199514}
+{"ts": "2025-12-24T07:01:57", "event": "train_log", "step": 4220, "epoch": 1.8207119741100324, "progress_pct": 30.34, "epoch_pct": 30.35, "eta": "38:00:47", "max_grad_norm": 1.0, "loss": 0.6945502161979675, "grad_norm": 0.41354167461395264, "learning_rate": 0.000172302510175773}
+{"ts": "2025-12-24T07:02:12", "event": "train_log", "step": 4222, "epoch": 1.8215749730312836, "progress_pct": 30.36, "epoch_pct": 30.36, "eta": "37:59:48", "max_grad_norm": 1.0, "loss": 0.790353536605835, "grad_norm": 0.4960228502750397, "learning_rate": 0.00017226857757412652}
+{"ts": "2025-12-24T07:02:28", "event": "train_log", "step": 4224, "epoch": 1.8224379719525352, "progress_pct": 30.37, "epoch_pct": 30.37, "eta": "37:58:53", "max_grad_norm": 1.0, "loss": 0.7331936955451965, "grad_norm": 0.4391328990459442, "learning_rate": 0.00017223462754523833}
+{"ts": "2025-12-24T07:02:44", "event": "train_log", "step": 4226, "epoch": 1.8233009708737864, "progress_pct": 30.39, "epoch_pct": 30.39, "eta": "37:57:57", "max_grad_norm": 1.0, "loss": 0.7099514603614807, "grad_norm": 0.4315200448036194, "learning_rate": 0.0001722006600972953}
+{"ts": "2025-12-24T07:03:01", "event": "train_log", "step": 4228, "epoch": 1.8241639697950378, "progress_pct": 30.4, "epoch_pct": 30.4, "eta": "37:57:02", "max_grad_norm": 1.0, "loss": 0.7503170967102051, "grad_norm": 0.4148513674736023, "learning_rate": 0.0001721666752384886}
+{"ts": "2025-12-24T07:03:16", "event": "train_log", "step": 4230, "epoch": 1.8250269687162892, "progress_pct": 30.41, "epoch_pct": 30.42, "eta": "37:56:04", "max_grad_norm": 1.0, "loss": 0.7042041420936584, "grad_norm": 0.39631742238998413, "learning_rate": 0.00017213267297701347}
+{"ts": "2025-12-24T07:03:30", "event": "train_log", "step": 4232, "epoch": 1.8258899676375404, "progress_pct": 30.43, "epoch_pct": 30.43, "eta": "37:55:04", "max_grad_norm": 1.0, "loss": 0.6457626819610596, "grad_norm": 0.4037681221961975, "learning_rate": 0.00017209865332106948}
+{"ts": "2025-12-24T07:03:45", "event": "train_log", "step": 4234, "epoch": 1.8267529665587918, "progress_pct": 30.44, "epoch_pct": 30.45, "eta": "37:54:04", "max_grad_norm": 1.0, "loss": 0.7379142045974731, "grad_norm": 0.4731367230415344, "learning_rate": 0.0001720646162788602}
+{"ts": "2025-12-24T07:04:00", "event": "train_log", "step": 4236, "epoch": 1.8276159654800432, "progress_pct": 30.46, "epoch_pct": 30.46, "eta": "37:53:07", "max_grad_norm": 1.0, "loss": 0.7307448387145996, "grad_norm": 0.48663607239723206, "learning_rate": 0.0001720305618585936}
+{"ts": "2025-12-24T07:04:14", "event": "train_log", "step": 4238, "epoch": 1.8284789644012944, "progress_pct": 30.47, "epoch_pct": 30.47, "eta": "37:52:07", "max_grad_norm": 1.0, "loss": 0.7429580688476562, "grad_norm": 0.42846018075942993, "learning_rate": 0.00017199649006848172}
+{"ts": "2025-12-24T07:04:29", "event": "train_log", "step": 4240, "epoch": 1.8293419633225458, "progress_pct": 30.49, "epoch_pct": 30.49, "eta": "37:51:08", "max_grad_norm": 1.0, "loss": 0.8380557298660278, "grad_norm": 0.4572913348674774, "learning_rate": 0.00017196240091674086}
+{"ts": "2025-12-24T07:04:44", "event": "train_log", "step": 4242, "epoch": 1.8302049622437973, "progress_pct": 30.5, "epoch_pct": 30.5, "eta": "37:50:09", "max_grad_norm": 1.0, "loss": 0.7590726613998413, "grad_norm": 0.4150466322898865, "learning_rate": 0.00017192829441159136}
+{"ts": "2025-12-24T07:04:59", "event": "train_log", "step": 4244, "epoch": 1.8310679611650484, "progress_pct": 30.51, "epoch_pct": 30.52, "eta": "37:49:11", "max_grad_norm": 1.0, "loss": 0.6875066161155701, "grad_norm": 0.5212832689285278, "learning_rate": 0.00017189417056125795}
+{"ts": "2025-12-24T07:05:16", "event": "train_log", "step": 4246, "epoch": 1.8319309600862999, "progress_pct": 30.53, "epoch_pct": 30.53, "eta": "37:48:18", "max_grad_norm": 1.0, "loss": 0.6904876828193665, "grad_norm": 0.39897283911705017, "learning_rate": 0.00017186002937396943}
+{"ts": "2025-12-24T07:05:33", "event": "train_log", "step": 4248, "epoch": 1.8327939590075513, "progress_pct": 30.54, "epoch_pct": 30.55, "eta": "37:47:24", "max_grad_norm": 1.0, "loss": 0.729841947555542, "grad_norm": 0.47237759828567505, "learning_rate": 0.00017182587085795876}
+{"ts": "2025-12-24T07:05:51", "event": "train_log", "step": 4250, "epoch": 1.8336569579288025, "progress_pct": 30.56, "epoch_pct": 30.56, "eta": "37:46:33", "max_grad_norm": 1.0, "loss": 0.6299530267715454, "grad_norm": 0.3762347102165222, "learning_rate": 0.00017179169502146312}
+{"ts": "2025-12-24T07:06:07", "event": "train_log", "step": 4252, "epoch": 1.834519956850054, "progress_pct": 30.57, "epoch_pct": 30.58, "eta": "37:45:36", "max_grad_norm": 1.0, "loss": 0.7029539942741394, "grad_norm": 0.47408151626586914, "learning_rate": 0.00017175750187272386}
+{"ts": "2025-12-24T07:06:22", "event": "train_log", "step": 4254, "epoch": 1.8353829557713053, "progress_pct": 30.59, "epoch_pct": 30.59, "eta": "37:44:39", "max_grad_norm": 1.0, "loss": 0.6389845609664917, "grad_norm": 0.3598722219467163, "learning_rate": 0.00017172329141998654}
+{"ts": "2025-12-24T07:06:37", "event": "train_log", "step": 4256, "epoch": 1.8362459546925565, "progress_pct": 30.6, "epoch_pct": 30.6, "eta": "37:43:41", "max_grad_norm": 1.0, "loss": 0.687628984451294, "grad_norm": 0.4635334312915802, "learning_rate": 0.00017168906367150076}
+{"ts": "2025-12-24T07:06:51", "event": "train_log", "step": 4258, "epoch": 1.837108953613808, "progress_pct": 30.62, "epoch_pct": 30.62, "eta": "37:42:41", "max_grad_norm": 1.0, "loss": 0.7720530033111572, "grad_norm": 0.4610443115234375, "learning_rate": 0.00017165481863552052}
+{"ts": "2025-12-24T07:07:05", "event": "train_log", "step": 4260, "epoch": 1.8379719525350593, "progress_pct": 30.63, "epoch_pct": 30.63, "eta": "37:41:42", "max_grad_norm": 1.0, "loss": 0.7185879349708557, "grad_norm": 0.4014928340911865, "learning_rate": 0.00017162055632030375}
+{"ts": "2025-12-24T07:07:19", "event": "train_log", "step": 4262, "epoch": 1.8388349514563107, "progress_pct": 30.64, "epoch_pct": 30.65, "eta": "37:40:41", "max_grad_norm": 1.0, "loss": 0.7026579976081848, "grad_norm": 0.4805688261985779, "learning_rate": 0.0001715862767341127}
+{"ts": "2025-12-24T07:07:35", "event": "train_log", "step": 4264, "epoch": 1.8396979503775621, "progress_pct": 30.66, "epoch_pct": 30.66, "eta": "37:39:44", "max_grad_norm": 1.0, "loss": 0.698957622051239, "grad_norm": 0.42337459325790405, "learning_rate": 0.00017155197988521375}
+{"ts": "2025-12-24T07:07:50", "event": "train_log", "step": 4266, "epoch": 1.8405609492988133, "progress_pct": 30.67, "epoch_pct": 30.68, "eta": "37:38:47", "max_grad_norm": 1.0, "loss": 0.6705408096313477, "grad_norm": 0.41200968623161316, "learning_rate": 0.00017151766578187737}
+{"ts": "2025-12-24T07:08:05", "event": "train_log", "step": 4268, "epoch": 1.8414239482200647, "progress_pct": 30.69, "epoch_pct": 30.69, "eta": "37:37:49", "max_grad_norm": 1.0, "loss": 0.6862514615058899, "grad_norm": 0.4329065978527069, "learning_rate": 0.0001714833344323783}
+{"ts": "2025-12-24T07:08:20", "event": "train_log", "step": 4270, "epoch": 1.8422869471413161, "progress_pct": 30.7, "epoch_pct": 30.7, "eta": "37:36:51", "max_grad_norm": 1.0, "loss": 0.7468723654747009, "grad_norm": 0.5093284845352173, "learning_rate": 0.0001714489858449954}
+{"ts": "2025-12-24T07:08:34", "event": "train_log", "step": 4272, "epoch": 1.8431499460625673, "progress_pct": 30.72, "epoch_pct": 30.72, "eta": "37:35:52", "max_grad_norm": 1.0, "loss": 0.7447264194488525, "grad_norm": 0.4891190230846405, "learning_rate": 0.00017141462002801162}
+{"ts": "2025-12-24T07:08:49", "event": "train_log", "step": 4274, "epoch": 1.8440129449838187, "progress_pct": 30.73, "epoch_pct": 30.73, "eta": "37:34:53", "max_grad_norm": 1.0, "loss": 0.6918519735336304, "grad_norm": 0.4578206241130829, "learning_rate": 0.0001713802369897142}
+{"ts": "2025-12-24T07:09:03", "event": "train_log", "step": 4276, "epoch": 1.8448759439050701, "progress_pct": 30.74, "epoch_pct": 30.75, "eta": "37:33:55", "max_grad_norm": 1.0, "loss": 0.6955613493919373, "grad_norm": 0.46908026933670044, "learning_rate": 0.00017134583673839439}
+{"ts": "2025-12-24T07:09:17", "event": "train_log", "step": 4278, "epoch": 1.8457389428263213, "progress_pct": 30.76, "epoch_pct": 30.76, "eta": "37:32:54", "max_grad_norm": 1.0, "loss": 0.7485507130622864, "grad_norm": 0.48165956139564514, "learning_rate": 0.0001713114192823477}
+{"ts": "2025-12-24T07:09:31", "event": "train_log", "step": 4280, "epoch": 1.846601941747573, "progress_pct": 30.77, "epoch_pct": 30.78, "eta": "37:31:54", "max_grad_norm": 1.0, "loss": 0.799237847328186, "grad_norm": 0.4701056480407715, "learning_rate": 0.00017127698462987367}
+{"ts": "2025-12-24T07:09:47", "event": "train_log", "step": 4282, "epoch": 1.8474649406688242, "progress_pct": 30.79, "epoch_pct": 30.79, "eta": "37:30:59", "max_grad_norm": 1.0, "loss": 0.6577883958816528, "grad_norm": 0.3776571452617645, "learning_rate": 0.00017124253278927616}
+{"ts": "2025-12-24T07:10:02", "event": "train_log", "step": 4284, "epoch": 1.8483279395900754, "progress_pct": 30.8, "epoch_pct": 30.81, "eta": "37:30:03", "max_grad_norm": 1.0, "loss": 0.7250326871871948, "grad_norm": 0.4055720567703247, "learning_rate": 0.00017120806376886302}
+{"ts": "2025-12-24T07:10:17", "event": "train_log", "step": 4286, "epoch": 1.849190938511327, "progress_pct": 30.82, "epoch_pct": 30.82, "eta": "37:29:05", "max_grad_norm": 1.0, "loss": 0.7517069578170776, "grad_norm": 0.4074631333351135, "learning_rate": 0.00017117357757694634}
+{"ts": "2025-12-24T07:10:32", "event": "train_log", "step": 4288, "epoch": 1.8500539374325782, "progress_pct": 30.83, "epoch_pct": 30.83, "eta": "37:28:08", "max_grad_norm": 1.0, "loss": 0.6158990859985352, "grad_norm": 0.4045642614364624, "learning_rate": 0.00017113907422184224}
+{"ts": "2025-12-24T07:10:47", "event": "train_log", "step": 4290, "epoch": 1.8509169363538296, "progress_pct": 30.85, "epoch_pct": 30.85, "eta": "37:27:10", "max_grad_norm": 1.0, "loss": 0.7236425876617432, "grad_norm": 0.4492259621620178, "learning_rate": 0.0001711045537118711}
+{"ts": "2025-12-24T07:11:01", "event": "train_log", "step": 4292, "epoch": 1.851779935275081, "progress_pct": 30.86, "epoch_pct": 30.86, "eta": "37:26:12", "max_grad_norm": 1.0, "loss": 0.7718945741653442, "grad_norm": 0.4565478265285492, "learning_rate": 0.00017107001605535737}
+{"ts": "2025-12-24T07:11:16", "event": "train_log", "step": 4294, "epoch": 1.8526429341963322, "progress_pct": 30.87, "epoch_pct": 30.88, "eta": "37:25:14", "max_grad_norm": 1.0, "loss": 0.7165213227272034, "grad_norm": 0.42028820514678955, "learning_rate": 0.00017103546126062967}
+{"ts": "2025-12-24T07:11:31", "event": "train_log", "step": 4296, "epoch": 1.8535059331175836, "progress_pct": 30.89, "epoch_pct": 30.89, "eta": "37:24:16", "max_grad_norm": 1.0, "loss": 0.6750491857528687, "grad_norm": 0.43695729970932007, "learning_rate": 0.0001710008893360207}
+{"ts": "2025-12-24T07:11:46", "event": "train_log", "step": 4298, "epoch": 1.854368932038835, "progress_pct": 30.9, "epoch_pct": 30.91, "eta": "37:23:18", "max_grad_norm": 1.0, "loss": 0.7486634850502014, "grad_norm": 0.4253435730934143, "learning_rate": 0.00017096630028986734}
+{"ts": "2025-12-24T07:12:01", "event": "train_log", "step": 4300, "epoch": 1.8552319309600862, "progress_pct": 30.92, "epoch_pct": 30.92, "eta": "37:22:21", "max_grad_norm": 1.0, "loss": 0.6766000986099243, "grad_norm": 0.4334436058998108, "learning_rate": 0.0001709316941305106}
+{"ts": "2025-12-24T07:22:55", "event": "train_log", "step": 4300, "epoch": 1.8552319309600862, "progress_pct": 30.92, "epoch_pct": 30.92, "eta": "37:46:44", "max_grad_norm": 1.0, "eval_loss": 0.7747175693511963, "eval_runtime": 654.7294, "eval_samples_per_second": 3.146, "eval_steps_per_second": 3.146}
+{"ts": "2025-12-24T07:23:11", "event": "train_log", "step": 4302, "epoch": 1.8560949298813376, "progress_pct": 30.93, "epoch_pct": 30.93, "eta": "37:45:48", "max_grad_norm": 1.0, "loss": 0.6958843469619751, "grad_norm": 0.4382997453212738, "learning_rate": 0.00017089707086629557}
+{"ts": "2025-12-24T07:23:26", "event": "train_log", "step": 4304, "epoch": 1.856957928802589, "progress_pct": 30.95, "epoch_pct": 30.95, "eta": "37:44:49", "max_grad_norm": 1.0, "loss": 0.7561178803443909, "grad_norm": 0.4810338616371155, "learning_rate": 0.0001708624305055715}
+{"ts": "2025-12-24T07:23:40", "event": "train_log", "step": 4306, "epoch": 1.8578209277238402, "progress_pct": 30.96, "epoch_pct": 30.96, "eta": "37:43:50", "max_grad_norm": 1.0, "loss": 0.8058216571807861, "grad_norm": 0.47984233498573303, "learning_rate": 0.00017082777305669176}
+{"ts": "2025-12-24T07:23:56", "event": "train_log", "step": 4308, "epoch": 1.8586839266450919, "progress_pct": 30.97, "epoch_pct": 30.98, "eta": "37:42:53", "max_grad_norm": 1.0, "loss": 0.7262290120124817, "grad_norm": 0.4484567642211914, "learning_rate": 0.00017079309852801385}
+{"ts": "2025-12-24T07:24:12", "event": "train_log", "step": 4310, "epoch": 1.859546925566343, "progress_pct": 30.99, "epoch_pct": 30.99, "eta": "37:41:59", "max_grad_norm": 1.0, "loss": 0.7000281810760498, "grad_norm": 0.41116195917129517, "learning_rate": 0.00017075840692789938}
+{"ts": "2025-12-24T07:24:28", "event": "train_log", "step": 4312, "epoch": 1.8604099244875942, "progress_pct": 31.0, "epoch_pct": 31.01, "eta": "37:41:02", "max_grad_norm": 1.0, "loss": 0.7535883188247681, "grad_norm": 0.4403190016746521, "learning_rate": 0.00017072369826471407}
+{"ts": "2025-12-24T07:24:43", "event": "train_log", "step": 4314, "epoch": 1.8612729234088459, "progress_pct": 31.02, "epoch_pct": 31.02, "eta": "37:40:05", "max_grad_norm": 1.0, "loss": 0.792589008808136, "grad_norm": 0.43298110365867615, "learning_rate": 0.0001706889725468277}
+{"ts": "2025-12-24T07:24:59", "event": "train_log", "step": 4316, "epoch": 1.862135922330097, "progress_pct": 31.03, "epoch_pct": 31.04, "eta": "37:39:08", "max_grad_norm": 1.0, "loss": 0.7327062487602234, "grad_norm": 0.5362349152565002, "learning_rate": 0.0001706542297826143}
+{"ts": "2025-12-24T07:25:14", "event": "train_log", "step": 4318, "epoch": 1.8629989212513485, "progress_pct": 31.05, "epoch_pct": 31.05, "eta": "37:38:11", "max_grad_norm": 1.0, "loss": 0.7859953045845032, "grad_norm": 0.5060083270072937, "learning_rate": 0.00017061946998045188}
+{"ts": "2025-12-24T07:25:29", "event": "train_log", "step": 4320, "epoch": 1.8638619201725999, "progress_pct": 31.06, "epoch_pct": 31.06, "eta": "37:37:13", "max_grad_norm": 1.0, "loss": 0.702696681022644, "grad_norm": 0.4489237368106842, "learning_rate": 0.00017058469314872266}
+{"ts": "2025-12-24T07:25:44", "event": "train_log", "step": 4322, "epoch": 1.864724919093851, "progress_pct": 31.08, "epoch_pct": 31.08, "eta": "37:36:17", "max_grad_norm": 1.0, "loss": 0.7487955093383789, "grad_norm": 0.4355533719062805, "learning_rate": 0.00017054989929581288}
+{"ts": "2025-12-24T07:26:01", "event": "train_log", "step": 4324, "epoch": 1.8655879180151025, "progress_pct": 31.09, "epoch_pct": 31.09, "eta": "37:35:22", "max_grad_norm": 1.0, "loss": 0.6919105648994446, "grad_norm": 0.413460910320282, "learning_rate": 0.0001705150884301129}
+{"ts": "2025-12-24T07:26:17", "event": "train_log", "step": 4326, "epoch": 1.866450916936354, "progress_pct": 31.1, "epoch_pct": 31.11, "eta": "37:34:27", "max_grad_norm": 1.0, "loss": 0.6864221096038818, "grad_norm": 0.4663568139076233, "learning_rate": 0.00017048026056001723}
+{"ts": "2025-12-24T07:26:32", "event": "train_log", "step": 4328, "epoch": 1.867313915857605, "progress_pct": 31.12, "epoch_pct": 31.12, "eta": "37:33:30", "max_grad_norm": 1.0, "loss": 0.6459081172943115, "grad_norm": 0.36837631464004517, "learning_rate": 0.00017044541569392446}
+{"ts": "2025-12-24T07:26:49", "event": "train_log", "step": 4330, "epoch": 1.8681769147788565, "progress_pct": 31.13, "epoch_pct": 31.14, "eta": "37:32:36", "max_grad_norm": 1.0, "loss": 0.7037135362625122, "grad_norm": 0.386055052280426, "learning_rate": 0.00017041055384023728}
+{"ts": "2025-12-24T07:27:05", "event": "train_log", "step": 4332, "epoch": 1.869039913700108, "progress_pct": 31.15, "epoch_pct": 31.15, "eta": "37:31:41", "max_grad_norm": 1.0, "loss": 0.7065625190734863, "grad_norm": 0.500342607498169, "learning_rate": 0.00017037567500736246}
+{"ts": "2025-12-24T07:27:20", "event": "train_log", "step": 4334, "epoch": 1.869902912621359, "progress_pct": 31.16, "epoch_pct": 31.17, "eta": "37:30:44", "max_grad_norm": 1.0, "loss": 0.7432923316955566, "grad_norm": 0.543442964553833, "learning_rate": 0.00017034077920371083}
+{"ts": "2025-12-24T07:27:35", "event": "train_log", "step": 4336, "epoch": 1.8707659115426107, "progress_pct": 31.18, "epoch_pct": 31.18, "eta": "37:29:48", "max_grad_norm": 1.0, "loss": 0.6966627240180969, "grad_norm": 0.4365047812461853, "learning_rate": 0.0001703058664376974}
+{"ts": "2025-12-24T07:27:51", "event": "train_log", "step": 4338, "epoch": 1.871628910463862, "progress_pct": 31.19, "epoch_pct": 31.19, "eta": "37:28:53", "max_grad_norm": 1.0, "loss": 0.7880892753601074, "grad_norm": 0.43488597869873047, "learning_rate": 0.00017027093671774122}
+{"ts": "2025-12-24T07:28:06", "event": "train_log", "step": 4340, "epoch": 1.8724919093851131, "progress_pct": 31.21, "epoch_pct": 31.21, "eta": "37:27:54", "max_grad_norm": 1.0, "loss": 0.7417665123939514, "grad_norm": 0.4579373896121979, "learning_rate": 0.00017023599005226546}
+{"ts": "2025-12-24T07:28:21", "event": "train_log", "step": 4342, "epoch": 1.8733549083063648, "progress_pct": 31.22, "epoch_pct": 31.22, "eta": "37:26:58", "max_grad_norm": 1.0, "loss": 0.7073261141777039, "grad_norm": 0.4457826316356659, "learning_rate": 0.00017020102644969728}
+{"ts": "2025-12-24T07:28:37", "event": "train_log", "step": 4344, "epoch": 1.874217907227616, "progress_pct": 31.23, "epoch_pct": 31.24, "eta": "37:26:03", "max_grad_norm": 1.0, "loss": 0.7597265243530273, "grad_norm": 0.47289299964904785, "learning_rate": 0.0001701660459184681}
+{"ts": "2025-12-24T07:28:53", "event": "train_log", "step": 4346, "epoch": 1.8750809061488674, "progress_pct": 31.25, "epoch_pct": 31.25, "eta": "37:25:06", "max_grad_norm": 1.0, "loss": 0.703773021697998, "grad_norm": 0.4678288996219635, "learning_rate": 0.0001701310484670132}
+{"ts": "2025-12-24T07:29:08", "event": "train_log", "step": 4348, "epoch": 1.8759439050701188, "progress_pct": 31.26, "epoch_pct": 31.27, "eta": "37:24:11", "max_grad_norm": 1.0, "loss": 0.7227264046669006, "grad_norm": 0.4159858226776123, "learning_rate": 0.00017009603410377214}
+{"ts": "2025-12-24T07:29:24", "event": "train_log", "step": 4350, "epoch": 1.87680690399137, "progress_pct": 31.28, "epoch_pct": 31.28, "eta": "37:23:15", "max_grad_norm": 1.0, "loss": 0.7137405872344971, "grad_norm": 0.42966076731681824, "learning_rate": 0.00017006100283718846}
+{"ts": "2025-12-24T07:29:40", "event": "train_log", "step": 4352, "epoch": 1.8776699029126214, "progress_pct": 31.29, "epoch_pct": 31.29, "eta": "37:22:20", "max_grad_norm": 1.0, "loss": 0.835712730884552, "grad_norm": 0.4697307050228119, "learning_rate": 0.0001700259546757098}
+{"ts": "2025-12-24T07:29:55", "event": "train_log", "step": 4354, "epoch": 1.8785329018338728, "progress_pct": 31.31, "epoch_pct": 31.31, "eta": "37:21:23", "max_grad_norm": 1.0, "loss": 0.720323383808136, "grad_norm": 0.4686335027217865, "learning_rate": 0.0001699908896277878}
+{"ts": "2025-12-24T07:30:10", "event": "train_log", "step": 4356, "epoch": 1.879395900755124, "progress_pct": 31.32, "epoch_pct": 31.32, "eta": "37:20:27", "max_grad_norm": 1.0, "loss": 0.7081778645515442, "grad_norm": 0.4535554051399231, "learning_rate": 0.00016995580770187832}
+{"ts": "2025-12-24T07:30:27", "event": "train_log", "step": 4358, "epoch": 1.8802588996763754, "progress_pct": 31.33, "epoch_pct": 31.34, "eta": "37:19:33", "max_grad_norm": 1.0, "loss": 0.6428251266479492, "grad_norm": 0.42280903458595276, "learning_rate": 0.00016992070890644114}
+{"ts": "2025-12-24T07:30:41", "event": "train_log", "step": 4360, "epoch": 1.8811218985976268, "progress_pct": 31.35, "epoch_pct": 31.35, "eta": "37:18:35", "max_grad_norm": 1.0, "loss": 0.7378063201904297, "grad_norm": 0.46084120869636536, "learning_rate": 0.0001698855932499402}
+{"ts": "2025-12-24T07:30:57", "event": "train_log", "step": 4362, "epoch": 1.881984897518878, "progress_pct": 31.36, "epoch_pct": 31.37, "eta": "37:17:40", "max_grad_norm": 1.0, "loss": 0.745130717754364, "grad_norm": 0.4233613610267639, "learning_rate": 0.00016985046074084357}
+{"ts": "2025-12-24T07:31:12", "event": "train_log", "step": 4364, "epoch": 1.8828478964401294, "progress_pct": 31.38, "epoch_pct": 31.38, "eta": "37:16:43", "max_grad_norm": 1.0, "loss": 0.7285540103912354, "grad_norm": 0.43696120381355286, "learning_rate": 0.00016981531138762318}
+{"ts": "2025-12-24T07:31:27", "event": "train_log", "step": 4366, "epoch": 1.8837108953613808, "progress_pct": 31.39, "epoch_pct": 31.4, "eta": "37:15:47", "max_grad_norm": 1.0, "loss": 0.7078036069869995, "grad_norm": 0.458446204662323, "learning_rate": 0.00016978014519875516}
+{"ts": "2025-12-24T07:31:43", "event": "train_log", "step": 4368, "epoch": 1.884573894282632, "progress_pct": 31.41, "epoch_pct": 31.41, "eta": "37:14:52", "max_grad_norm": 1.0, "loss": 0.6465590596199036, "grad_norm": 0.41318631172180176, "learning_rate": 0.00016974496218271972}
+{"ts": "2025-12-24T07:31:58", "event": "train_log", "step": 4370, "epoch": 1.8854368932038836, "progress_pct": 31.42, "epoch_pct": 31.42, "eta": "37:13:56", "max_grad_norm": 1.0, "loss": 0.6374526023864746, "grad_norm": 0.43945857882499695, "learning_rate": 0.00016970976234800104}
+{"ts": "2025-12-24T07:32:14", "event": "train_log", "step": 4372, "epoch": 1.8862998921251348, "progress_pct": 31.44, "epoch_pct": 31.44, "eta": "37:13:01", "max_grad_norm": 1.0, "loss": 0.7523587346076965, "grad_norm": 0.4725545048713684, "learning_rate": 0.00016967454570308746}
+{"ts": "2025-12-24T07:32:29", "event": "train_log", "step": 4374, "epoch": 1.8871628910463862, "progress_pct": 31.45, "epoch_pct": 31.45, "eta": "37:12:04", "max_grad_norm": 1.0, "loss": 0.764968991279602, "grad_norm": 0.44840991497039795, "learning_rate": 0.00016963931225647124}
+{"ts": "2025-12-24T07:32:45", "event": "train_log", "step": 4376, "epoch": 1.8880258899676376, "progress_pct": 31.46, "epoch_pct": 31.47, "eta": "37:11:09", "max_grad_norm": 1.0, "loss": 0.7077135443687439, "grad_norm": 0.40001222491264343, "learning_rate": 0.00016960406201664883}
+{"ts": "2025-12-24T07:32:59", "event": "train_log", "step": 4378, "epoch": 1.8888888888888888, "progress_pct": 31.48, "epoch_pct": 31.48, "eta": "37:10:10", "max_grad_norm": 1.0, "loss": 0.7109629511833191, "grad_norm": 0.4679710268974304, "learning_rate": 0.00016956879499212062}
+{"ts": "2025-12-24T07:33:15", "event": "train_log", "step": 4380, "epoch": 1.8897518878101403, "progress_pct": 31.49, "epoch_pct": 31.5, "eta": "37:09:16", "max_grad_norm": 1.0, "loss": 0.6676799654960632, "grad_norm": 0.4309675991535187, "learning_rate": 0.00016953351119139114}
+{"ts": "2025-12-24T07:33:31", "event": "train_log", "step": 4382, "epoch": 1.8906148867313917, "progress_pct": 31.51, "epoch_pct": 31.51, "eta": "37:08:22", "max_grad_norm": 1.0, "loss": 0.7011449337005615, "grad_norm": 0.4097946882247925, "learning_rate": 0.00016949821062296888}
+{"ts": "2025-12-24T07:33:46", "event": "train_log", "step": 4384, "epoch": 1.8914778856526429, "progress_pct": 31.52, "epoch_pct": 31.52, "eta": "37:07:25", "max_grad_norm": 1.0, "loss": 0.7500543594360352, "grad_norm": 0.4526914060115814, "learning_rate": 0.00016946289329536641}
+{"ts": "2025-12-24T07:34:01", "event": "train_log", "step": 4386, "epoch": 1.8923408845738943, "progress_pct": 31.54, "epoch_pct": 31.54, "eta": "37:06:28", "max_grad_norm": 1.0, "loss": 0.8412749767303467, "grad_norm": 0.448703408241272, "learning_rate": 0.0001694275592171004}
+{"ts": "2025-12-24T07:34:17", "event": "train_log", "step": 4388, "epoch": 1.8932038834951457, "progress_pct": 31.55, "epoch_pct": 31.55, "eta": "37:05:34", "max_grad_norm": 1.0, "loss": 0.7479212284088135, "grad_norm": 0.3906726539134979, "learning_rate": 0.00016939220839669143}
+{"ts": "2025-12-24T07:34:33", "event": "train_log", "step": 4390, "epoch": 1.8940668824163969, "progress_pct": 31.56, "epoch_pct": 31.57, "eta": "37:04:41", "max_grad_norm": 1.0, "loss": 0.7404555082321167, "grad_norm": 0.44968852400779724, "learning_rate": 0.00016935684084266425}
+{"ts": "2025-12-24T07:34:49", "event": "train_log", "step": 4392, "epoch": 1.8949298813376483, "progress_pct": 31.58, "epoch_pct": 31.58, "eta": "37:03:47", "max_grad_norm": 1.0, "loss": 0.7160722017288208, "grad_norm": 0.4262198805809021, "learning_rate": 0.00016932145656354758}
+{"ts": "2025-12-24T07:35:05", "event": "train_log", "step": 4394, "epoch": 1.8957928802588997, "progress_pct": 31.59, "epoch_pct": 31.6, "eta": "37:02:52", "max_grad_norm": 1.0, "loss": 0.6597195863723755, "grad_norm": 0.4741004705429077, "learning_rate": 0.00016928605556787413}
+{"ts": "2025-12-24T07:35:20", "event": "train_log", "step": 4396, "epoch": 1.8966558791801509, "progress_pct": 31.61, "epoch_pct": 31.61, "eta": "37:01:57", "max_grad_norm": 1.0, "loss": 0.7020326852798462, "grad_norm": 0.4941152334213257, "learning_rate": 0.0001692506378641807}
+{"ts": "2025-12-24T07:35:36", "event": "train_log", "step": 4398, "epoch": 1.8975188781014025, "progress_pct": 31.62, "epoch_pct": 31.63, "eta": "37:01:03", "max_grad_norm": 1.0, "loss": 0.6817783713340759, "grad_norm": 0.4449406564235687, "learning_rate": 0.0001692152034610082}
+{"ts": "2025-12-24T07:35:52", "event": "train_log", "step": 4400, "epoch": 1.8983818770226537, "progress_pct": 31.64, "epoch_pct": 31.64, "eta": "37:00:09", "max_grad_norm": 1.0, "loss": 0.6696207523345947, "grad_norm": 0.4189581274986267, "learning_rate": 0.00016917975236690138}
+{"ts": "2025-12-24T07:46:41", "event": "train_log", "step": 4400, "epoch": 1.8983818770226537, "progress_pct": 31.64, "epoch_pct": 31.64, "eta": "37:23:30", "max_grad_norm": 1.0, "eval_loss": 0.7715606689453125, "eval_runtime": 648.4164, "eval_samples_per_second": 3.177, "eval_steps_per_second": 3.177}
+{"ts": "2025-12-24T07:46:55", "event": "train_log", "step": 4402, "epoch": 1.8992448759439051, "progress_pct": 31.65, "epoch_pct": 31.65, "eta": "37:22:32", "max_grad_norm": 1.0, "loss": 0.6992137432098389, "grad_norm": 0.4761787950992584, "learning_rate": 0.0001691442845904091}
+{"ts": "2025-12-24T07:47:10", "event": "train_log", "step": 4404, "epoch": 1.9001078748651565, "progress_pct": 31.67, "epoch_pct": 31.67, "eta": "37:21:34", "max_grad_norm": 1.0, "loss": 0.6070076823234558, "grad_norm": 0.438167542219162, "learning_rate": 0.00016910880014008438}
+{"ts": "2025-12-24T07:47:24", "event": "train_log", "step": 4406, "epoch": 1.9009708737864077, "progress_pct": 31.68, "epoch_pct": 31.68, "eta": "37:20:34", "max_grad_norm": 1.0, "loss": 0.6767536401748657, "grad_norm": 0.4941405653953552, "learning_rate": 0.00016907329902448397}
+{"ts": "2025-12-24T07:47:39", "event": "train_log", "step": 4408, "epoch": 1.9018338727076591, "progress_pct": 31.69, "epoch_pct": 31.7, "eta": "37:19:37", "max_grad_norm": 1.0, "loss": 0.6732425093650818, "grad_norm": 0.39704009890556335, "learning_rate": 0.00016903778125216892}
+{"ts": "2025-12-24T07:47:53", "event": "train_log", "step": 4410, "epoch": 1.9026968716289105, "progress_pct": 31.71, "epoch_pct": 31.71, "eta": "37:18:39", "max_grad_norm": 1.0, "loss": 0.7694390416145325, "grad_norm": 0.4666280448436737, "learning_rate": 0.00016900224683170413}
+{"ts": "2025-12-24T07:48:08", "event": "train_log", "step": 4412, "epoch": 1.9035598705501617, "progress_pct": 31.72, "epoch_pct": 31.73, "eta": "37:17:42", "max_grad_norm": 1.0, "loss": 0.8102390170097351, "grad_norm": 0.3905762732028961, "learning_rate": 0.0001689666957716586}
+{"ts": "2025-12-24T07:48:23", "event": "train_log", "step": 4414, "epoch": 1.9044228694714131, "progress_pct": 31.74, "epoch_pct": 31.74, "eta": "37:16:45", "max_grad_norm": 1.0, "loss": 0.6950157284736633, "grad_norm": 0.45140960812568665, "learning_rate": 0.00016893112808060527}
+{"ts": "2025-12-24T07:48:38", "event": "train_log", "step": 4416, "epoch": 1.9052858683926646, "progress_pct": 31.75, "epoch_pct": 31.75, "eta": "37:15:48", "max_grad_norm": 1.0, "loss": 0.6316207051277161, "grad_norm": 0.36071425676345825, "learning_rate": 0.0001688955437671212}
+{"ts": "2025-12-24T07:48:53", "event": "train_log", "step": 4418, "epoch": 1.9061488673139158, "progress_pct": 31.77, "epoch_pct": 31.77, "eta": "37:14:51", "max_grad_norm": 1.0, "loss": 0.736228883266449, "grad_norm": 0.4559943974018097, "learning_rate": 0.00016885994283978725}
+{"ts": "2025-12-24T07:49:08", "event": "train_log", "step": 4420, "epoch": 1.9070118662351672, "progress_pct": 31.78, "epoch_pct": 31.78, "eta": "37:13:55", "max_grad_norm": 1.0, "loss": 0.663848876953125, "grad_norm": 0.42006543278694153, "learning_rate": 0.00016882432530718856}
+{"ts": "2025-12-24T07:49:23", "event": "train_log", "step": 4422, "epoch": 1.9078748651564186, "progress_pct": 31.79, "epoch_pct": 31.8, "eta": "37:12:57", "max_grad_norm": 1.0, "loss": 0.7144405841827393, "grad_norm": 0.4335814118385315, "learning_rate": 0.00016878869117791404}
+{"ts": "2025-12-24T07:49:37", "event": "train_log", "step": 4424, "epoch": 1.9087378640776698, "progress_pct": 31.81, "epoch_pct": 31.81, "eta": "37:12:00", "max_grad_norm": 1.0, "loss": 0.7918539643287659, "grad_norm": 0.454925537109375, "learning_rate": 0.0001687530404605568}
+{"ts": "2025-12-24T07:49:52", "event": "train_log", "step": 4426, "epoch": 1.9096008629989214, "progress_pct": 31.82, "epoch_pct": 31.83, "eta": "37:11:04", "max_grad_norm": 1.0, "loss": 0.7775250673294067, "grad_norm": 0.4195649325847626, "learning_rate": 0.00016871737316371375}
+{"ts": "2025-12-24T07:50:08", "event": "train_log", "step": 4428, "epoch": 1.9104638619201726, "progress_pct": 31.84, "epoch_pct": 31.84, "eta": "37:10:09", "max_grad_norm": 1.0, "loss": 0.7011466026306152, "grad_norm": 0.40194037556648254, "learning_rate": 0.00016868168929598596}
+{"ts": "2025-12-24T07:50:23", "event": "train_log", "step": 4430, "epoch": 1.911326860841424, "progress_pct": 31.85, "epoch_pct": 31.86, "eta": "37:09:12", "max_grad_norm": 1.0, "loss": 0.7481483817100525, "grad_norm": 0.4803355932235718, "learning_rate": 0.0001686459888659784}
+{"ts": "2025-12-24T07:50:38", "event": "train_log", "step": 4432, "epoch": 1.9121898597626754, "progress_pct": 31.87, "epoch_pct": 31.87, "eta": "37:08:16", "max_grad_norm": 1.0, "loss": 0.7103830575942993, "grad_norm": 0.4976218342781067, "learning_rate": 0.00016861027188230012}
+{"ts": "2025-12-24T07:50:55", "event": "train_log", "step": 4434, "epoch": 1.9130528586839266, "progress_pct": 31.88, "epoch_pct": 31.88, "eta": "37:07:22", "max_grad_norm": 1.0, "loss": 0.6993346810340881, "grad_norm": 0.4329865276813507, "learning_rate": 0.00016857453835356401}
+{"ts": "2025-12-24T07:51:10", "event": "train_log", "step": 4436, "epoch": 1.913915857605178, "progress_pct": 31.9, "epoch_pct": 31.9, "eta": "37:06:28", "max_grad_norm": 1.0, "loss": 0.7064663171768188, "grad_norm": 0.39290672540664673, "learning_rate": 0.00016853878828838718}
+{"ts": "2025-12-24T07:51:26", "event": "train_log", "step": 4438, "epoch": 1.9147788565264294, "progress_pct": 31.91, "epoch_pct": 31.91, "eta": "37:05:33", "max_grad_norm": 1.0, "loss": 0.7383471727371216, "grad_norm": 0.4755532741546631, "learning_rate": 0.0001685030216953905}
+{"ts": "2025-12-24T07:51:43", "event": "train_log", "step": 4440, "epoch": 1.9156418554476806, "progress_pct": 31.92, "epoch_pct": 31.93, "eta": "37:04:40", "max_grad_norm": 1.0, "loss": 0.6742298603057861, "grad_norm": 0.4168999195098877, "learning_rate": 0.00016846723858319896}
+{"ts": "2025-12-24T07:51:58", "event": "train_log", "step": 4442, "epoch": 1.916504854368932, "progress_pct": 31.94, "epoch_pct": 31.94, "eta": "37:03:45", "max_grad_norm": 1.0, "loss": 0.7861196994781494, "grad_norm": 0.4728643000125885, "learning_rate": 0.00016843143896044146}
+{"ts": "2025-12-24T07:52:13", "event": "train_log", "step": 4444, "epoch": 1.9173678532901834, "progress_pct": 31.95, "epoch_pct": 31.96, "eta": "37:02:49", "max_grad_norm": 1.0, "loss": 0.7680529952049255, "grad_norm": 0.4734310209751129, "learning_rate": 0.00016839562283575097}
+{"ts": "2025-12-24T07:52:29", "event": "train_log", "step": 4446, "epoch": 1.9182308522114346, "progress_pct": 31.97, "epoch_pct": 31.97, "eta": "37:01:53", "max_grad_norm": 1.0, "loss": 0.7587183713912964, "grad_norm": 0.44408535957336426, "learning_rate": 0.00016835979021776433}
+{"ts": "2025-12-24T07:52:45", "event": "train_log", "step": 4448, "epoch": 1.919093851132686, "progress_pct": 31.98, "epoch_pct": 31.98, "eta": "37:01:00", "max_grad_norm": 1.0, "loss": 0.6908396482467651, "grad_norm": 0.4441621005535126, "learning_rate": 0.00016832394111512247}
+{"ts": "2025-12-24T07:53:02", "event": "train_log", "step": 4450, "epoch": 1.9199568500539375, "progress_pct": 32.0, "epoch_pct": 32.0, "eta": "37:00:07", "max_grad_norm": 1.0, "loss": 0.7139167189598083, "grad_norm": 0.4286157488822937, "learning_rate": 0.00016828807553647023}
+{"ts": "2025-12-24T07:53:17", "event": "train_log", "step": 4452, "epoch": 1.9208198489751886, "progress_pct": 32.01, "epoch_pct": 32.01, "eta": "36:59:12", "max_grad_norm": 1.0, "loss": 0.7594030499458313, "grad_norm": 0.46225154399871826, "learning_rate": 0.0001682521934904564}
+{"ts": "2025-12-24T07:53:33", "event": "train_log", "step": 4454, "epoch": 1.9216828478964403, "progress_pct": 32.02, "epoch_pct": 32.03, "eta": "36:58:17", "max_grad_norm": 1.0, "loss": 0.7202461957931519, "grad_norm": 0.46970534324645996, "learning_rate": 0.0001682162949857338}
+{"ts": "2025-12-24T07:53:47", "event": "train_log", "step": 4456, "epoch": 1.9225458468176915, "progress_pct": 32.04, "epoch_pct": 32.04, "eta": "36:57:21", "max_grad_norm": 1.0, "loss": 0.7119565606117249, "grad_norm": 0.5053386092185974, "learning_rate": 0.00016818038003095918}
+{"ts": "2025-12-24T07:54:03", "event": "train_log", "step": 4458, "epoch": 1.9234088457389427, "progress_pct": 32.05, "epoch_pct": 32.06, "eta": "36:56:26", "max_grad_norm": 1.0, "loss": 0.6812665462493896, "grad_norm": 0.4012000560760498, "learning_rate": 0.00016814444863479325}
+{"ts": "2025-12-24T07:54:17", "event": "train_log", "step": 4460, "epoch": 1.9242718446601943, "progress_pct": 32.07, "epoch_pct": 32.07, "eta": "36:55:29", "max_grad_norm": 1.0, "loss": 0.7549154758453369, "grad_norm": 0.47809499502182007, "learning_rate": 0.00016810850080590077}
+{"ts": "2025-12-24T07:54:32", "event": "train_log", "step": 4462, "epoch": 1.9251348435814455, "progress_pct": 32.08, "epoch_pct": 32.09, "eta": "36:54:33", "max_grad_norm": 1.0, "loss": 0.6555595993995667, "grad_norm": 0.42006292939186096, "learning_rate": 0.00016807253655295033}
+{"ts": "2025-12-24T07:54:48", "event": "train_log", "step": 4464, "epoch": 1.925997842502697, "progress_pct": 32.1, "epoch_pct": 32.1, "eta": "36:53:39", "max_grad_norm": 1.0, "loss": 0.688592255115509, "grad_norm": 0.39846277236938477, "learning_rate": 0.00016803655588461459}
+{"ts": "2025-12-24T07:55:04", "event": "train_log", "step": 4466, "epoch": 1.9268608414239483, "progress_pct": 32.11, "epoch_pct": 32.11, "eta": "36:52:45", "max_grad_norm": 1.0, "loss": 0.7375786900520325, "grad_norm": 0.4685076177120209, "learning_rate": 0.00016800055880957011}
+{"ts": "2025-12-24T07:55:19", "event": "train_log", "step": 4468, "epoch": 1.9277238403451995, "progress_pct": 32.13, "epoch_pct": 32.13, "eta": "36:51:48", "max_grad_norm": 1.0, "loss": 0.7663659453392029, "grad_norm": 0.4540894031524658, "learning_rate": 0.00016796454533649742}
+{"ts": "2025-12-24T07:55:35", "event": "train_log", "step": 4470, "epoch": 1.928586839266451, "progress_pct": 32.14, "epoch_pct": 32.14, "eta": "36:50:54", "max_grad_norm": 1.0, "loss": 0.7322548031806946, "grad_norm": 0.3871139585971832, "learning_rate": 0.000167928515474081}
+{"ts": "2025-12-24T07:55:50", "event": "train_log", "step": 4472, "epoch": 1.9294498381877023, "progress_pct": 32.15, "epoch_pct": 32.16, "eta": "36:49:59", "max_grad_norm": 1.0, "loss": 0.7807921767234802, "grad_norm": 0.5056940317153931, "learning_rate": 0.0001678924692310093}
+{"ts": "2025-12-24T07:56:05", "event": "train_log", "step": 4474, "epoch": 1.9303128371089535, "progress_pct": 32.17, "epoch_pct": 32.17, "eta": "36:49:04", "max_grad_norm": 1.0, "loss": 0.7619108557701111, "grad_norm": 0.5218532681465149, "learning_rate": 0.00016785640661597467}
+{"ts": "2025-12-24T07:56:20", "event": "train_log", "step": 4476, "epoch": 1.931175836030205, "progress_pct": 32.18, "epoch_pct": 32.19, "eta": "36:48:07", "max_grad_norm": 1.0, "loss": 0.7600476741790771, "grad_norm": 0.49141281843185425, "learning_rate": 0.00016782032763767356}
+{"ts": "2025-12-24T07:56:35", "event": "train_log", "step": 4478, "epoch": 1.9320388349514563, "progress_pct": 32.2, "epoch_pct": 32.2, "eta": "36:47:12", "max_grad_norm": 1.0, "loss": 0.724636971950531, "grad_norm": 0.44819942116737366, "learning_rate": 0.00016778423230480612}
+{"ts": "2025-12-24T07:56:51", "event": "train_log", "step": 4480, "epoch": 1.9329018338727075, "progress_pct": 32.21, "epoch_pct": 32.22, "eta": "36:46:17", "max_grad_norm": 1.0, "loss": 0.7845118045806885, "grad_norm": 0.4031332731246948, "learning_rate": 0.00016774812062607665}
+{"ts": "2025-12-24T07:57:06", "event": "train_log", "step": 4482, "epoch": 1.9337648327939592, "progress_pct": 32.23, "epoch_pct": 32.23, "eta": "36:45:23", "max_grad_norm": 1.0, "loss": 0.6626143455505371, "grad_norm": 0.45330920815467834, "learning_rate": 0.00016771199261019328}
+{"ts": "2025-12-24T07:57:22", "event": "train_log", "step": 4484, "epoch": 1.9346278317152104, "progress_pct": 32.24, "epoch_pct": 32.24, "eta": "36:44:28", "max_grad_norm": 1.0, "loss": 0.7041512727737427, "grad_norm": 0.42102664709091187, "learning_rate": 0.00016767584826586816}
+{"ts": "2025-12-24T07:57:36", "event": "train_log", "step": 4486, "epoch": 1.9354908306364615, "progress_pct": 32.25, "epoch_pct": 32.26, "eta": "36:43:32", "max_grad_norm": 1.0, "loss": 0.6547129154205322, "grad_norm": 0.44634684920310974, "learning_rate": 0.0001676396876018173}
+{"ts": "2025-12-24T07:57:52", "event": "train_log", "step": 4488, "epoch": 1.9363538295577132, "progress_pct": 32.27, "epoch_pct": 32.27, "eta": "36:42:38", "max_grad_norm": 1.0, "loss": 0.7318123579025269, "grad_norm": 0.4141015410423279, "learning_rate": 0.00016760351062676074}
+{"ts": "2025-12-24T07:58:08", "event": "train_log", "step": 4490, "epoch": 1.9372168284789644, "progress_pct": 32.28, "epoch_pct": 32.29, "eta": "36:41:45", "max_grad_norm": 1.0, "loss": 0.7246537208557129, "grad_norm": 0.42240142822265625, "learning_rate": 0.0001675673173494223}
+{"ts": "2025-12-24T07:58:23", "event": "train_log", "step": 4492, "epoch": 1.9380798274002158, "progress_pct": 32.3, "epoch_pct": 32.3, "eta": "36:40:50", "max_grad_norm": 1.0, "loss": 0.6859333515167236, "grad_norm": 0.4295092225074768, "learning_rate": 0.0001675311077785299}
+{"ts": "2025-12-24T07:58:40", "event": "train_log", "step": 4494, "epoch": 1.9389428263214672, "progress_pct": 32.31, "epoch_pct": 32.32, "eta": "36:39:58", "max_grad_norm": 1.0, "loss": 0.6654847264289856, "grad_norm": 0.4344942569732666, "learning_rate": 0.0001674948819228153}
+{"ts": "2025-12-24T07:58:54", "event": "train_log", "step": 4496, "epoch": 1.9398058252427184, "progress_pct": 32.33, "epoch_pct": 32.33, "eta": "36:39:02", "max_grad_norm": 1.0, "loss": 0.7616198658943176, "grad_norm": 0.48967039585113525, "learning_rate": 0.00016745863979101416}
+{"ts": "2025-12-24T07:59:09", "event": "train_log", "step": 4498, "epoch": 1.9406688241639698, "progress_pct": 32.34, "epoch_pct": 32.34, "eta": "36:38:06", "max_grad_norm": 1.0, "loss": 0.7908874154090881, "grad_norm": 0.5314980745315552, "learning_rate": 0.00016742238139186617}
+{"ts": "2025-12-24T07:59:25", "event": "train_log", "step": 4500, "epoch": 1.9415318230852212, "progress_pct": 32.36, "epoch_pct": 32.36, "eta": "36:37:12", "max_grad_norm": 1.0, "loss": 0.7347621917724609, "grad_norm": 0.4205719530582428, "learning_rate": 0.00016738610673411485}
+{"ts": "2025-12-24T08:10:25", "event": "train_log", "step": 4500, "epoch": 1.9415318230852212, "progress_pct": 32.36, "epoch_pct": 32.36, "eta": "37:00:13", "max_grad_norm": 1.0, "eval_loss": 0.771009087562561, "eval_runtime": 660.4659, "eval_samples_per_second": 3.119, "eval_steps_per_second": 3.119}
+{"ts": "2025-12-24T08:10:41", "event": "train_log", "step": 4502, "epoch": 1.9423948220064724, "progress_pct": 32.37, "epoch_pct": 32.37, "eta": "36:59:18", "max_grad_norm": 1.0, "loss": 0.6706517934799194, "grad_norm": 0.4044483006000519, "learning_rate": 0.00016734981582650763}
+{"ts": "2025-12-24T08:10:56", "event": "train_log", "step": 4504, "epoch": 1.9432578209277238, "progress_pct": 32.38, "epoch_pct": 32.39, "eta": "36:58:21", "max_grad_norm": 1.0, "loss": 0.7005504369735718, "grad_norm": 0.4619632363319397, "learning_rate": 0.00016731350867779597}
+{"ts": "2025-12-24T08:11:10", "event": "train_log", "step": 4506, "epoch": 1.9441208198489752, "progress_pct": 32.4, "epoch_pct": 32.4, "eta": "36:57:24", "max_grad_norm": 1.0, "loss": 0.7157896757125854, "grad_norm": 0.4387263357639313, "learning_rate": 0.00016727718529673514}
+{"ts": "2025-12-24T08:11:24", "event": "train_log", "step": 4508, "epoch": 1.9449838187702264, "progress_pct": 32.41, "epoch_pct": 32.42, "eta": "36:56:26", "max_grad_norm": 1.0, "loss": 0.7862341403961182, "grad_norm": 0.4543296694755554, "learning_rate": 0.00016724084569208435}
+{"ts": "2025-12-24T08:11:40", "event": "train_log", "step": 4510, "epoch": 1.945846817691478, "progress_pct": 32.43, "epoch_pct": 32.43, "eta": "36:55:31", "max_grad_norm": 1.0, "loss": 0.6545839309692383, "grad_norm": 0.39784348011016846, "learning_rate": 0.00016720448987260676}
+{"ts": "2025-12-24T08:11:54", "event": "train_log", "step": 4512, "epoch": 1.9467098166127292, "progress_pct": 32.44, "epoch_pct": 32.45, "eta": "36:54:35", "max_grad_norm": 1.0, "loss": 0.673794150352478, "grad_norm": 0.3748764097690582, "learning_rate": 0.00016716811784706938}
+{"ts": "2025-12-24T08:12:09", "event": "train_log", "step": 4514, "epoch": 1.9475728155339804, "progress_pct": 32.46, "epoch_pct": 32.46, "eta": "36:53:39", "max_grad_norm": 1.0, "loss": 0.7945805191993713, "grad_norm": 0.3885408043861389, "learning_rate": 0.00016713172962424318}
+{"ts": "2025-12-24T08:12:24", "event": "train_log", "step": 4516, "epoch": 1.948435814455232, "progress_pct": 32.47, "epoch_pct": 32.47, "eta": "36:52:41", "max_grad_norm": 1.0, "loss": 0.7191757559776306, "grad_norm": 0.47125545144081116, "learning_rate": 0.00016709532521290302}
+{"ts": "2025-12-24T08:12:38", "event": "train_log", "step": 4518, "epoch": 1.9492988133764833, "progress_pct": 32.48, "epoch_pct": 32.49, "eta": "36:51:45", "max_grad_norm": 1.0, "loss": 0.645935595035553, "grad_norm": 0.40436047315597534, "learning_rate": 0.00016705890462182768}
+{"ts": "2025-12-24T08:12:53", "event": "train_log", "step": 4520, "epoch": 1.9501618122977347, "progress_pct": 32.5, "epoch_pct": 32.5, "eta": "36:50:48", "max_grad_norm": 1.0, "loss": 0.7455692291259766, "grad_norm": 0.44247058033943176, "learning_rate": 0.00016702246785979974}
+{"ts": "2025-12-24T08:13:08", "event": "train_log", "step": 4522, "epoch": 1.951024811218986, "progress_pct": 32.51, "epoch_pct": 32.52, "eta": "36:49:52", "max_grad_norm": 1.0, "loss": 0.7447270750999451, "grad_norm": 0.4673680067062378, "learning_rate": 0.00016698601493560586}
+{"ts": "2025-12-24T08:13:22", "event": "train_log", "step": 4524, "epoch": 1.9518878101402373, "progress_pct": 32.53, "epoch_pct": 32.53, "eta": "36:48:55", "max_grad_norm": 1.0, "loss": 0.6882420778274536, "grad_norm": 0.4142216742038727, "learning_rate": 0.00016694954585803643}
+{"ts": "2025-12-24T08:13:37", "event": "train_log", "step": 4526, "epoch": 1.9527508090614887, "progress_pct": 32.54, "epoch_pct": 32.55, "eta": "36:47:59", "max_grad_norm": 1.0, "loss": 0.6677885055541992, "grad_norm": 0.42105594277381897, "learning_rate": 0.00016691306063588583}
+{"ts": "2025-12-24T08:13:52", "event": "train_log", "step": 4528, "epoch": 1.95361380798274, "progress_pct": 32.56, "epoch_pct": 32.56, "eta": "36:47:03", "max_grad_norm": 1.0, "loss": 0.7364463210105896, "grad_norm": 0.45304399728775024, "learning_rate": 0.00016687655927795228}
+{"ts": "2025-12-24T08:14:07", "event": "train_log", "step": 4530, "epoch": 1.9544768069039913, "progress_pct": 32.57, "epoch_pct": 32.57, "eta": "36:46:07", "max_grad_norm": 1.0, "loss": 0.7233486175537109, "grad_norm": 0.47123080492019653, "learning_rate": 0.000166840041793038}
+{"ts": "2025-12-24T08:14:21", "event": "train_log", "step": 4532, "epoch": 1.9553398058252427, "progress_pct": 32.59, "epoch_pct": 32.59, "eta": "36:45:10", "max_grad_norm": 1.0, "loss": 0.7176171541213989, "grad_norm": 0.49601346254348755, "learning_rate": 0.00016680350818994893}
+{"ts": "2025-12-24T08:14:37", "event": "train_log", "step": 4534, "epoch": 1.956202804746494, "progress_pct": 32.6, "epoch_pct": 32.6, "eta": "36:44:16", "max_grad_norm": 1.0, "loss": 0.6606364250183105, "grad_norm": 0.4189842641353607, "learning_rate": 0.00016676695847749499}
+{"ts": "2025-12-24T08:14:52", "event": "train_log", "step": 4536, "epoch": 1.9570658036677453, "progress_pct": 32.61, "epoch_pct": 32.62, "eta": "36:43:20", "max_grad_norm": 1.0, "loss": 0.6760656237602234, "grad_norm": 0.3644670248031616, "learning_rate": 0.00016673039266449}
+{"ts": "2025-12-24T08:15:06", "event": "train_log", "step": 4538, "epoch": 1.9579288025889967, "progress_pct": 32.63, "epoch_pct": 32.63, "eta": "36:42:24", "max_grad_norm": 1.0, "loss": 0.7179452776908875, "grad_norm": 0.43236833810806274, "learning_rate": 0.0001666938107597517}
+{"ts": "2025-12-24T08:15:21", "event": "train_log", "step": 4540, "epoch": 1.9587918015102481, "progress_pct": 32.64, "epoch_pct": 32.65, "eta": "36:41:27", "max_grad_norm": 1.0, "loss": 0.796003520488739, "grad_norm": 0.46566686034202576, "learning_rate": 0.00016665721277210152}
+{"ts": "2025-12-24T08:15:36", "event": "train_log", "step": 4542, "epoch": 1.9596548004314993, "progress_pct": 32.66, "epoch_pct": 32.66, "eta": "36:40:32", "max_grad_norm": 1.0, "loss": 0.6422439217567444, "grad_norm": 0.3825298249721527, "learning_rate": 0.000166620598710365}
+{"ts": "2025-12-24T08:15:50", "event": "train_log", "step": 4544, "epoch": 1.960517799352751, "progress_pct": 32.67, "epoch_pct": 32.68, "eta": "36:39:36", "max_grad_norm": 1.0, "loss": 0.7824487686157227, "grad_norm": 0.5343096852302551, "learning_rate": 0.00016658396858337145}
+{"ts": "2025-12-24T08:16:05", "event": "train_log", "step": 4546, "epoch": 1.9613807982740021, "progress_pct": 32.69, "epoch_pct": 32.69, "eta": "36:38:39", "max_grad_norm": 1.0, "loss": 0.7899296879768372, "grad_norm": 0.42387035489082336, "learning_rate": 0.000166547322399954}
+{"ts": "2025-12-24T08:16:19", "event": "train_log", "step": 4548, "epoch": 1.9622437971952535, "progress_pct": 32.7, "epoch_pct": 32.7, "eta": "36:37:43", "max_grad_norm": 1.0, "loss": 0.7320859432220459, "grad_norm": 0.45924878120422363, "learning_rate": 0.00016651066016894976}
+{"ts": "2025-12-24T08:16:34", "event": "train_log", "step": 4550, "epoch": 1.963106796116505, "progress_pct": 32.71, "epoch_pct": 32.72, "eta": "36:36:46", "max_grad_norm": 1.0, "loss": 0.6994174122810364, "grad_norm": 0.44048014283180237, "learning_rate": 0.00016647398189919966}
+{"ts": "2025-12-24T08:16:49", "event": "train_log", "step": 4552, "epoch": 1.9639697950377561, "progress_pct": 32.73, "epoch_pct": 32.73, "eta": "36:35:51", "max_grad_norm": 1.0, "loss": 0.6603167057037354, "grad_norm": 0.4648546576499939, "learning_rate": 0.0001664372875995485}
+{"ts": "2025-12-24T08:17:04", "event": "train_log", "step": 4554, "epoch": 1.9648327939590076, "progress_pct": 32.74, "epoch_pct": 32.75, "eta": "36:34:56", "max_grad_norm": 1.0, "loss": 0.6613137125968933, "grad_norm": 0.41362452507019043, "learning_rate": 0.00016640057727884493}
+{"ts": "2025-12-24T08:17:19", "event": "train_log", "step": 4556, "epoch": 1.965695792880259, "progress_pct": 32.76, "epoch_pct": 32.76, "eta": "36:34:01", "max_grad_norm": 1.0, "loss": 0.6949821710586548, "grad_norm": 0.37311485409736633, "learning_rate": 0.00016636385094594147}
+{"ts": "2025-12-24T08:17:33", "event": "train_log", "step": 4558, "epoch": 1.9665587918015102, "progress_pct": 32.77, "epoch_pct": 32.78, "eta": "36:33:04", "max_grad_norm": 1.0, "loss": 0.7660812139511108, "grad_norm": 0.4713662564754486, "learning_rate": 0.0001663271086096945}
+{"ts": "2025-12-24T08:17:48", "event": "train_log", "step": 4560, "epoch": 1.9674217907227616, "progress_pct": 32.79, "epoch_pct": 32.79, "eta": "36:32:10", "max_grad_norm": 1.0, "loss": 0.6518822908401489, "grad_norm": 0.43874675035476685, "learning_rate": 0.00016629035027896437}
+{"ts": "2025-12-24T08:18:03", "event": "train_log", "step": 4562, "epoch": 1.968284789644013, "progress_pct": 32.8, "epoch_pct": 32.8, "eta": "36:31:14", "max_grad_norm": 1.0, "loss": 0.7194673418998718, "grad_norm": 0.4186612367630005, "learning_rate": 0.00016625357596261505}
+{"ts": "2025-12-24T08:18:18", "event": "train_log", "step": 4564, "epoch": 1.9691477885652642, "progress_pct": 32.82, "epoch_pct": 32.82, "eta": "36:30:18", "max_grad_norm": 1.0, "loss": 0.6897136569023132, "grad_norm": 0.4130612313747406, "learning_rate": 0.0001662167856695146}
+{"ts": "2025-12-24T08:18:32", "event": "train_log", "step": 4566, "epoch": 1.9700107874865156, "progress_pct": 32.83, "epoch_pct": 32.83, "eta": "36:29:23", "max_grad_norm": 1.0, "loss": 0.7318847179412842, "grad_norm": 0.45674464106559753, "learning_rate": 0.00016617997940853477}
+{"ts": "2025-12-24T08:18:48", "event": "train_log", "step": 4568, "epoch": 1.970873786407767, "progress_pct": 32.84, "epoch_pct": 32.85, "eta": "36:28:28", "max_grad_norm": 1.0, "loss": 0.6961532831192017, "grad_norm": 0.4126178026199341, "learning_rate": 0.00016614315718855124}
+{"ts": "2025-12-24T08:19:02", "event": "train_log", "step": 4570, "epoch": 1.9717367853290182, "progress_pct": 32.86, "epoch_pct": 32.86, "eta": "36:27:33", "max_grad_norm": 1.0, "loss": 0.6798923015594482, "grad_norm": 0.4192276895046234, "learning_rate": 0.00016610631901844354}
+{"ts": "2025-12-24T08:19:17", "event": "train_log", "step": 4572, "epoch": 1.9725997842502698, "progress_pct": 32.87, "epoch_pct": 32.88, "eta": "36:26:38", "max_grad_norm": 1.0, "loss": 0.7198042869567871, "grad_norm": 0.47822800278663635, "learning_rate": 0.000166069464907095}
+{"ts": "2025-12-24T08:19:32", "event": "train_log", "step": 4574, "epoch": 1.973462783171521, "progress_pct": 32.89, "epoch_pct": 32.89, "eta": "36:25:41", "max_grad_norm": 1.0, "loss": 0.7586894035339355, "grad_norm": 0.5018525719642639, "learning_rate": 0.00016603259486339288}
+{"ts": "2025-12-24T08:19:46", "event": "train_log", "step": 4576, "epoch": 1.9743257820927724, "progress_pct": 32.9, "epoch_pct": 32.91, "eta": "36:24:46", "max_grad_norm": 1.0, "loss": 0.689724862575531, "grad_norm": 0.4475814700126648, "learning_rate": 0.00016599570889622812}
+{"ts": "2025-12-24T08:20:03", "event": "train_log", "step": 4578, "epoch": 1.9751887810140238, "progress_pct": 32.92, "epoch_pct": 32.92, "eta": "36:23:54", "max_grad_norm": 1.0, "loss": 0.7210922837257385, "grad_norm": 0.3784774839878082, "learning_rate": 0.00016595880701449574}
+{"ts": "2025-12-24T08:20:18", "event": "train_log", "step": 4580, "epoch": 1.976051779935275, "progress_pct": 32.93, "epoch_pct": 32.93, "eta": "36:23:00", "max_grad_norm": 1.0, "loss": 0.690231442451477, "grad_norm": 0.42436331510543823, "learning_rate": 0.00016592188922709436}
+{"ts": "2025-12-24T08:20:34", "event": "train_log", "step": 4582, "epoch": 1.9769147788565264, "progress_pct": 32.95, "epoch_pct": 32.95, "eta": "36:22:07", "max_grad_norm": 1.0, "loss": 0.69464510679245, "grad_norm": 0.4346679449081421, "learning_rate": 0.00016588495554292656}
+{"ts": "2025-12-24T08:20:49", "event": "train_log", "step": 4584, "epoch": 1.9777777777777779, "progress_pct": 32.96, "epoch_pct": 32.96, "eta": "36:21:14", "max_grad_norm": 1.0, "loss": 0.7262688279151917, "grad_norm": 0.39857980608940125, "learning_rate": 0.00016584800597089876}
+{"ts": "2025-12-24T08:21:04", "event": "train_log", "step": 4586, "epoch": 1.978640776699029, "progress_pct": 32.97, "epoch_pct": 32.98, "eta": "36:20:18", "max_grad_norm": 1.0, "loss": 0.7584139108657837, "grad_norm": 0.45271673798561096, "learning_rate": 0.00016581104051992113}
+{"ts": "2025-12-24T08:21:21", "event": "train_log", "step": 4588, "epoch": 1.9795037756202805, "progress_pct": 32.99, "epoch_pct": 32.99, "eta": "36:19:27", "max_grad_norm": 1.0, "loss": 0.6850265860557556, "grad_norm": 0.41194021701812744, "learning_rate": 0.00016577405919890778}
+{"ts": "2025-12-24T08:21:37", "event": "train_log", "step": 4590, "epoch": 1.9803667745415319, "progress_pct": 33.0, "epoch_pct": 33.01, "eta": "36:18:36", "max_grad_norm": 1.0, "loss": 0.8458948135375977, "grad_norm": 0.4431819021701813, "learning_rate": 0.0001657370620167766}
+{"ts": "2025-12-24T08:21:53", "event": "train_log", "step": 4592, "epoch": 1.981229773462783, "progress_pct": 33.02, "epoch_pct": 33.02, "eta": "36:17:42", "max_grad_norm": 1.0, "loss": 0.6918507814407349, "grad_norm": 0.40193578600883484, "learning_rate": 0.00016570004898244922}
+{"ts": "2025-12-24T08:22:08", "event": "train_log", "step": 4594, "epoch": 1.9820927723840345, "progress_pct": 33.03, "epoch_pct": 33.03, "eta": "36:16:49", "max_grad_norm": 1.0, "loss": 0.6753236055374146, "grad_norm": 0.41715008020401, "learning_rate": 0.0001656630201048512}
+{"ts": "2025-12-24T08:22:24", "event": "train_log", "step": 4596, "epoch": 1.9829557713052859, "progress_pct": 33.05, "epoch_pct": 33.05, "eta": "36:15:56", "max_grad_norm": 1.0, "loss": 0.7096498608589172, "grad_norm": 0.4450492262840271, "learning_rate": 0.00016562597539291192}
+{"ts": "2025-12-24T08:22:42", "event": "train_log", "step": 4598, "epoch": 1.983818770226537, "progress_pct": 33.06, "epoch_pct": 33.06, "eta": "36:15:06", "max_grad_norm": 1.0, "loss": 0.6265234351158142, "grad_norm": 0.4278895854949951, "learning_rate": 0.0001655889148555645}
+{"ts": "2025-12-24T08:22:57", "event": "train_log", "step": 4600, "epoch": 1.9846817691477887, "progress_pct": 33.07, "epoch_pct": 33.08, "eta": "36:14:13", "max_grad_norm": 1.0, "loss": 0.6720689535140991, "grad_norm": 0.47390851378440857, "learning_rate": 0.00016555183850174593}
+{"ts": "2025-12-24T08:34:04", "event": "train_log", "step": 4600, "epoch": 1.9846817691477887, "progress_pct": 33.07, "epoch_pct": 33.08, "eta": "36:36:42", "max_grad_norm": 1.0, "eval_loss": 0.7693634033203125, "eval_runtime": 666.3969, "eval_samples_per_second": 3.091, "eval_steps_per_second": 3.091}
+{"ts": "2025-12-24T08:34:19", "event": "train_log", "step": 4602, "epoch": 1.98554476806904, "progress_pct": 33.09, "epoch_pct": 33.09, "eta": "36:35:46", "max_grad_norm": 1.0, "loss": 0.6512941122055054, "grad_norm": 0.41023409366607666, "learning_rate": 0.00016551474634039702}
+{"ts": "2025-12-24T08:34:34", "event": "train_log", "step": 4604, "epoch": 1.9864077669902913, "progress_pct": 33.1, "epoch_pct": 33.11, "eta": "36:34:52", "max_grad_norm": 1.0, "loss": 0.7818425893783569, "grad_norm": 0.4961327910423279, "learning_rate": 0.00016547763838046237}
+{"ts": "2025-12-24T08:34:50", "event": "train_log", "step": 4606, "epoch": 1.9872707659115427, "progress_pct": 33.12, "epoch_pct": 33.12, "eta": "36:33:58", "max_grad_norm": 1.0, "loss": 0.6233832240104675, "grad_norm": 0.4500366449356079, "learning_rate": 0.00016544051463089044}
+{"ts": "2025-12-24T08:35:06", "event": "train_log", "step": 4608, "epoch": 1.988133764832794, "progress_pct": 33.13, "epoch_pct": 33.14, "eta": "36:33:06", "max_grad_norm": 1.0, "loss": 0.6287953853607178, "grad_norm": 0.3829202651977539, "learning_rate": 0.00016540337510063336}
+{"ts": "2025-12-24T08:35:20", "event": "train_log", "step": 4610, "epoch": 1.9889967637540453, "progress_pct": 33.15, "epoch_pct": 33.15, "eta": "36:32:09", "max_grad_norm": 1.0, "loss": 0.717572033405304, "grad_norm": 0.49972304701805115, "learning_rate": 0.00016536621979864723}
+{"ts": "2025-12-24T08:35:34", "event": "train_log", "step": 4612, "epoch": 1.9898597626752967, "progress_pct": 33.16, "epoch_pct": 33.16, "eta": "36:31:12", "max_grad_norm": 1.0, "loss": 0.7110126614570618, "grad_norm": 0.460709810256958, "learning_rate": 0.00016532904873389187}
+{"ts": "2025-12-24T08:35:50", "event": "train_log", "step": 4614, "epoch": 1.990722761596548, "progress_pct": 33.18, "epoch_pct": 33.18, "eta": "36:30:18", "max_grad_norm": 1.0, "loss": 0.6038979291915894, "grad_norm": 0.4055844247341156, "learning_rate": 0.00016529186191533094}
+{"ts": "2025-12-24T08:36:04", "event": "train_log", "step": 4616, "epoch": 1.9915857605177993, "progress_pct": 33.19, "epoch_pct": 33.19, "eta": "36:29:22", "max_grad_norm": 1.0, "loss": 0.696323573589325, "grad_norm": 0.4324508309364319, "learning_rate": 0.00016525465935193182}
+{"ts": "2025-12-24T08:36:19", "event": "train_log", "step": 4618, "epoch": 1.9924487594390508, "progress_pct": 33.2, "epoch_pct": 33.21, "eta": "36:28:26", "max_grad_norm": 1.0, "loss": 0.7562056183815002, "grad_norm": 0.4611187279224396, "learning_rate": 0.00016521744105266577}
+{"ts": "2025-12-24T08:36:33", "event": "train_log", "step": 4620, "epoch": 1.993311758360302, "progress_pct": 33.22, "epoch_pct": 33.22, "eta": "36:27:30", "max_grad_norm": 1.0, "loss": 0.7664333581924438, "grad_norm": 0.47493883967399597, "learning_rate": 0.0001651802070265078}
+{"ts": "2025-12-24T08:36:48", "event": "train_log", "step": 4622, "epoch": 1.9941747572815534, "progress_pct": 33.23, "epoch_pct": 33.24, "eta": "36:26:34", "max_grad_norm": 1.0, "loss": 0.6699361205101013, "grad_norm": 0.4092567563056946, "learning_rate": 0.00016514295728243676}
+{"ts": "2025-12-24T08:37:03", "event": "train_log", "step": 4624, "epoch": 1.9950377562028048, "progress_pct": 33.25, "epoch_pct": 33.25, "eta": "36:25:39", "max_grad_norm": 1.0, "loss": 0.595447838306427, "grad_norm": 0.4346120059490204, "learning_rate": 0.00016510569182943524}
+{"ts": "2025-12-24T08:37:17", "event": "train_log", "step": 4626, "epoch": 1.995900755124056, "progress_pct": 33.26, "epoch_pct": 33.27, "eta": "36:24:43", "max_grad_norm": 1.0, "loss": 0.7328130602836609, "grad_norm": 0.4573204815387726, "learning_rate": 0.00016506841067648963}
+{"ts": "2025-12-24T08:37:32", "event": "train_log", "step": 4628, "epoch": 1.9967637540453076, "progress_pct": 33.28, "epoch_pct": 33.28, "eta": "36:23:47", "max_grad_norm": 1.0, "loss": 0.7281216979026794, "grad_norm": 0.4462505877017975, "learning_rate": 0.00016503111383259008}
+{"ts": "2025-12-24T08:37:46", "event": "train_log", "step": 4630, "epoch": 1.9976267529665588, "progress_pct": 33.29, "epoch_pct": 33.29, "eta": "36:22:51", "max_grad_norm": 1.0, "loss": 0.708483874797821, "grad_norm": 0.4535468816757202, "learning_rate": 0.00016499380130673063}
+{"ts": "2025-12-24T08:38:01", "event": "train_log", "step": 4632, "epoch": 1.9984897518878102, "progress_pct": 33.3, "epoch_pct": 33.31, "eta": "36:21:56", "max_grad_norm": 1.0, "loss": 0.7145193815231323, "grad_norm": 0.43400564789772034, "learning_rate": 0.00016495647310790895}
+{"ts": "2025-12-24T08:38:17", "event": "train_log", "step": 4634, "epoch": 1.9993527508090616, "progress_pct": 33.32, "epoch_pct": 33.32, "eta": "36:21:04", "max_grad_norm": 1.0, "loss": 0.6042786240577698, "grad_norm": 0.3664472699165344, "learning_rate": 0.00016491912924512664}
+{"ts": "2025-12-24T08:38:28", "event": "train_log", "step": 4636, "epoch": 2.0, "progress_pct": 33.33, "epoch_pct": 33.33, "eta": "36:20:01", "max_grad_norm": 1.0, "loss": 0.6522378325462341, "grad_norm": 0.6387348175048828, "learning_rate": 0.00016488176972738897}
+{"ts": "2025-12-24T08:38:42", "event": "train_log", "step": 4638, "epoch": 2.000862998921251, "progress_pct": 33.35, "epoch_pct": 33.35, "eta": "36:19:04", "max_grad_norm": 1.0, "loss": 0.6835677027702332, "grad_norm": 0.5207704305648804, "learning_rate": 0.000164844394563705}
+{"ts": "2025-12-24T08:38:57", "event": "train_log", "step": 4640, "epoch": 2.001725997842503, "progress_pct": 33.36, "epoch_pct": 33.36, "eta": "36:18:10", "max_grad_norm": 1.0, "loss": 0.660594642162323, "grad_norm": 0.41845715045928955, "learning_rate": 0.00016480700376308763}
+{"ts": "2025-12-24T08:39:12", "event": "train_log", "step": 4642, "epoch": 2.002588996763754, "progress_pct": 33.38, "epoch_pct": 33.38, "eta": "36:17:14", "max_grad_norm": 1.0, "loss": 0.686377227306366, "grad_norm": 0.4118453860282898, "learning_rate": 0.00016476959733455345}
+{"ts": "2025-12-24T08:39:26", "event": "train_log", "step": 4644, "epoch": 2.003451995685005, "progress_pct": 33.39, "epoch_pct": 33.39, "eta": "36:16:19", "max_grad_norm": 1.0, "loss": 0.572327733039856, "grad_norm": 0.4191179871559143, "learning_rate": 0.00016473217528712282}
+{"ts": "2025-12-24T08:39:40", "event": "train_log", "step": 4646, "epoch": 2.004314994606257, "progress_pct": 33.41, "epoch_pct": 33.41, "eta": "36:15:23", "max_grad_norm": 1.0, "loss": 0.6413782238960266, "grad_norm": 0.46276384592056274, "learning_rate": 0.00016469473762981997}
+{"ts": "2025-12-24T08:39:55", "event": "train_log", "step": 4648, "epoch": 2.005177993527508, "progress_pct": 33.42, "epoch_pct": 33.42, "eta": "36:14:27", "max_grad_norm": 1.0, "loss": 0.6797998547554016, "grad_norm": 0.4543590843677521, "learning_rate": 0.00016465728437167277}
+{"ts": "2025-12-24T08:40:09", "event": "train_log", "step": 4650, "epoch": 2.006040992448759, "progress_pct": 33.43, "epoch_pct": 33.43, "eta": "36:13:32", "max_grad_norm": 1.0, "loss": 0.7034262418746948, "grad_norm": 0.4565536379814148, "learning_rate": 0.0001646198155217129}
+{"ts": "2025-12-24T08:40:25", "event": "train_log", "step": 4652, "epoch": 2.006903991370011, "progress_pct": 33.45, "epoch_pct": 33.45, "eta": "36:12:39", "max_grad_norm": 1.0, "loss": 0.5970950126647949, "grad_norm": 0.5048449635505676, "learning_rate": 0.00016458233108897585}
+{"ts": "2025-12-24T08:40:41", "event": "train_log", "step": 4654, "epoch": 2.007766990291262, "progress_pct": 33.46, "epoch_pct": 33.46, "eta": "36:11:46", "max_grad_norm": 1.0, "loss": 0.6356200575828552, "grad_norm": 0.4608653783798218, "learning_rate": 0.0001645448310825008}
+{"ts": "2025-12-24T08:40:55", "event": "train_log", "step": 4656, "epoch": 2.0086299892125137, "progress_pct": 33.48, "epoch_pct": 33.48, "eta": "36:10:50", "max_grad_norm": 1.0, "loss": 0.7133077383041382, "grad_norm": 0.4787193238735199, "learning_rate": 0.0001645073155113307}
+{"ts": "2025-12-24T08:41:09", "event": "train_log", "step": 4658, "epoch": 2.009492988133765, "progress_pct": 33.49, "epoch_pct": 33.49, "eta": "36:09:55", "max_grad_norm": 1.0, "loss": 0.6743806004524231, "grad_norm": 0.4269030690193176, "learning_rate": 0.00016446978438451227}
+{"ts": "2025-12-24T08:41:24", "event": "train_log", "step": 4660, "epoch": 2.010355987055016, "progress_pct": 33.51, "epoch_pct": 33.51, "eta": "36:09:00", "max_grad_norm": 1.0, "loss": 0.6571159362792969, "grad_norm": 0.4306720793247223, "learning_rate": 0.00016443223771109595}
+{"ts": "2025-12-24T08:41:39", "event": "train_log", "step": 4662, "epoch": 2.0112189859762677, "progress_pct": 33.52, "epoch_pct": 33.52, "eta": "36:08:05", "max_grad_norm": 1.0, "loss": 0.6420291662216187, "grad_norm": 0.44306403398513794, "learning_rate": 0.000164394675500136}
+{"ts": "2025-12-24T08:41:54", "event": "train_log", "step": 4664, "epoch": 2.012081984897519, "progress_pct": 33.53, "epoch_pct": 33.53, "eta": "36:07:11", "max_grad_norm": 1.0, "loss": 0.6432573199272156, "grad_norm": 0.39896103739738464, "learning_rate": 0.00016435709776069032}
+{"ts": "2025-12-24T08:42:08", "event": "train_log", "step": 4666, "epoch": 2.01294498381877, "progress_pct": 33.55, "epoch_pct": 33.55, "eta": "36:06:15", "max_grad_norm": 1.0, "loss": 0.6163631677627563, "grad_norm": 0.48287299275398254, "learning_rate": 0.00016431950450182062}
+{"ts": "2025-12-24T08:42:23", "event": "train_log", "step": 4668, "epoch": 2.0138079827400217, "progress_pct": 33.56, "epoch_pct": 33.56, "eta": "36:05:20", "max_grad_norm": 1.0, "loss": 0.6431483626365662, "grad_norm": 0.4574606418609619, "learning_rate": 0.0001642818957325924}
+{"ts": "2025-12-24T08:42:38", "event": "train_log", "step": 4670, "epoch": 2.014670981661273, "progress_pct": 33.58, "epoch_pct": 33.58, "eta": "36:04:27", "max_grad_norm": 1.0, "loss": 0.6710224747657776, "grad_norm": 0.42676475644111633, "learning_rate": 0.0001642442714620748}
+{"ts": "2025-12-24T08:42:54", "event": "train_log", "step": 4672, "epoch": 2.015533980582524, "progress_pct": 33.59, "epoch_pct": 33.59, "eta": "36:03:34", "max_grad_norm": 1.0, "loss": 0.6850066184997559, "grad_norm": 0.4235379993915558, "learning_rate": 0.00016420663169934075}
+{"ts": "2025-12-24T08:43:08", "event": "train_log", "step": 4674, "epoch": 2.0163969795037757, "progress_pct": 33.61, "epoch_pct": 33.61, "eta": "36:02:40", "max_grad_norm": 1.0, "loss": 0.7138109803199768, "grad_norm": 0.5073016285896301, "learning_rate": 0.0001641689764534669}
+{"ts": "2025-12-24T08:43:24", "event": "train_log", "step": 4676, "epoch": 2.017259978425027, "progress_pct": 33.62, "epoch_pct": 33.62, "eta": "36:01:47", "max_grad_norm": 1.0, "loss": 0.5495269298553467, "grad_norm": 0.36213043332099915, "learning_rate": 0.00016413130573353363}
+{"ts": "2025-12-24T08:43:39", "event": "train_log", "step": 4678, "epoch": 2.018122977346278, "progress_pct": 33.64, "epoch_pct": 33.64, "eta": "36:00:53", "max_grad_norm": 1.0, "loss": 0.65972900390625, "grad_norm": 0.5076286196708679, "learning_rate": 0.00016409361954862513}
+{"ts": "2025-12-24T08:43:54", "event": "train_log", "step": 4680, "epoch": 2.0189859762675297, "progress_pct": 33.65, "epoch_pct": 33.65, "eta": "35:59:59", "max_grad_norm": 1.0, "loss": 0.7322002053260803, "grad_norm": 0.4341578781604767, "learning_rate": 0.0001640559179078292}
+{"ts": "2025-12-24T08:44:09", "event": "train_log", "step": 4682, "epoch": 2.019848975188781, "progress_pct": 33.66, "epoch_pct": 33.66, "eta": "35:59:05", "max_grad_norm": 1.0, "loss": 0.6621085405349731, "grad_norm": 0.4757557809352875, "learning_rate": 0.00016401820082023743}
+{"ts": "2025-12-24T08:44:24", "event": "train_log", "step": 4684, "epoch": 2.0207119741100326, "progress_pct": 33.68, "epoch_pct": 33.68, "eta": "35:58:11", "max_grad_norm": 1.0, "loss": 0.6278486847877502, "grad_norm": 0.509813129901886, "learning_rate": 0.00016398046829494512}
+{"ts": "2025-12-24T08:44:39", "event": "train_log", "step": 4686, "epoch": 2.0215749730312838, "progress_pct": 33.69, "epoch_pct": 33.69, "eta": "35:57:18", "max_grad_norm": 1.0, "loss": 0.6266241669654846, "grad_norm": 0.42560887336730957, "learning_rate": 0.0001639427203410513}
+{"ts": "2025-12-24T08:44:54", "event": "train_log", "step": 4688, "epoch": 2.022437971952535, "progress_pct": 33.71, "epoch_pct": 33.71, "eta": "35:56:24", "max_grad_norm": 1.0, "loss": 0.5831415057182312, "grad_norm": 0.42648500204086304, "learning_rate": 0.00016390495696765874}
+{"ts": "2025-12-24T08:45:09", "event": "train_log", "step": 4690, "epoch": 2.0233009708737866, "progress_pct": 33.72, "epoch_pct": 33.72, "eta": "35:55:31", "max_grad_norm": 1.0, "loss": 0.5532339811325073, "grad_norm": 0.41927891969680786, "learning_rate": 0.00016386717818387393}
+{"ts": "2025-12-24T08:45:24", "event": "train_log", "step": 4692, "epoch": 2.0241639697950378, "progress_pct": 33.74, "epoch_pct": 33.74, "eta": "35:54:36", "max_grad_norm": 1.0, "loss": 0.6643280386924744, "grad_norm": 0.47799861431121826, "learning_rate": 0.00016382938399880695}
+{"ts": "2025-12-24T08:45:39", "event": "train_log", "step": 4694, "epoch": 2.025026968716289, "progress_pct": 33.75, "epoch_pct": 33.75, "eta": "35:53:42", "max_grad_norm": 1.0, "loss": 0.6012117266654968, "grad_norm": 0.4548218548297882, "learning_rate": 0.0001637915744215718}
+{"ts": "2025-12-24T08:45:53", "event": "train_log", "step": 4696, "epoch": 2.0258899676375406, "progress_pct": 33.76, "epoch_pct": 33.76, "eta": "35:52:48", "max_grad_norm": 1.0, "loss": 0.6531984806060791, "grad_norm": 0.46845319867134094, "learning_rate": 0.00016375374946128604}
+{"ts": "2025-12-24T08:46:08", "event": "train_log", "step": 4698, "epoch": 2.026752966558792, "progress_pct": 33.78, "epoch_pct": 33.78, "eta": "35:51:53", "max_grad_norm": 1.0, "loss": 0.6862936615943909, "grad_norm": 0.513229489326477, "learning_rate": 0.000163715909127071}
+{"ts": "2025-12-24T08:46:22", "event": "train_log", "step": 4700, "epoch": 2.027615965480043, "progress_pct": 33.79, "epoch_pct": 33.79, "eta": "35:50:57", "max_grad_norm": 1.0, "loss": 0.640913188457489, "grad_norm": 0.4894806146621704, "learning_rate": 0.00016367805342805172}
+{"ts": "2025-12-24T08:57:23", "event": "train_log", "step": 4700, "epoch": 2.027615965480043, "progress_pct": 33.79, "epoch_pct": 33.79, "eta": "36:12:33", "max_grad_norm": 1.0, "eval_loss": 0.7736310362815857, "eval_runtime": 661.1886, "eval_samples_per_second": 3.116, "eval_steps_per_second": 3.116}
+{"ts": "2025-12-24T08:57:38", "event": "train_log", "step": 4702, "epoch": 2.0284789644012946, "progress_pct": 33.81, "epoch_pct": 33.81, "eta": "36:11:39", "max_grad_norm": 1.0, "loss": 0.6296554207801819, "grad_norm": 0.4949263036251068, "learning_rate": 0.00016364018237335687}
+{"ts": "2025-12-24T08:57:55", "event": "train_log", "step": 4704, "epoch": 2.029341963322546, "progress_pct": 33.82, "epoch_pct": 33.82, "eta": "36:10:48", "max_grad_norm": 1.0, "loss": 0.6197080016136169, "grad_norm": 0.46869733929634094, "learning_rate": 0.000163602295972119}
+{"ts": "2025-12-24T08:58:10", "event": "train_log", "step": 4706, "epoch": 2.030204962243797, "progress_pct": 33.84, "epoch_pct": 33.84, "eta": "36:09:54", "max_grad_norm": 1.0, "loss": 0.6469756364822388, "grad_norm": 0.4212348759174347, "learning_rate": 0.00016356439423347415}
+{"ts": "2025-12-24T08:58:26", "event": "train_log", "step": 4708, "epoch": 2.0310679611650486, "progress_pct": 33.85, "epoch_pct": 33.85, "eta": "36:09:02", "max_grad_norm": 1.0, "loss": 0.6279610991477966, "grad_norm": 0.5471233129501343, "learning_rate": 0.00016352647716656217}
+{"ts": "2025-12-24T08:58:40", "event": "train_log", "step": 4710, "epoch": 2.0319309600863, "progress_pct": 33.87, "epoch_pct": 33.87, "eta": "36:08:06", "max_grad_norm": 1.0, "loss": 0.7317426204681396, "grad_norm": 0.4614807069301605, "learning_rate": 0.0001634885447805266}
+{"ts": "2025-12-24T08:58:56", "event": "train_log", "step": 4712, "epoch": 2.0327939590075514, "progress_pct": 33.88, "epoch_pct": 33.88, "eta": "36:07:13", "max_grad_norm": 1.0, "loss": 0.7015593647956848, "grad_norm": 0.48236316442489624, "learning_rate": 0.00016345059708451469}
+{"ts": "2025-12-24T08:59:13", "event": "train_log", "step": 4714, "epoch": 2.0336569579288026, "progress_pct": 33.89, "epoch_pct": 33.89, "eta": "36:06:23", "max_grad_norm": 1.0, "loss": 0.565079927444458, "grad_norm": 0.4641088843345642, "learning_rate": 0.00016341263408767732}
+{"ts": "2025-12-24T08:59:29", "event": "train_log", "step": 4716, "epoch": 2.034519956850054, "progress_pct": 33.91, "epoch_pct": 33.91, "eta": "36:05:30", "max_grad_norm": 1.0, "loss": 0.6572306156158447, "grad_norm": 0.5252481698989868, "learning_rate": 0.00016337465579916905}
+{"ts": "2025-12-24T08:59:44", "event": "train_log", "step": 4718, "epoch": 2.0353829557713055, "progress_pct": 33.92, "epoch_pct": 33.92, "eta": "36:04:37", "max_grad_norm": 1.0, "loss": 0.7526581287384033, "grad_norm": 0.5171546339988708, "learning_rate": 0.0001633366622281483}
+{"ts": "2025-12-24T08:59:59", "event": "train_log", "step": 4720, "epoch": 2.0362459546925566, "progress_pct": 33.94, "epoch_pct": 33.94, "eta": "36:03:42", "max_grad_norm": 1.0, "loss": 0.665242075920105, "grad_norm": 0.47234100103378296, "learning_rate": 0.00016329865338377694}
+{"ts": "2025-12-24T09:00:13", "event": "train_log", "step": 4722, "epoch": 2.037108953613808, "progress_pct": 33.95, "epoch_pct": 33.95, "eta": "36:02:47", "max_grad_norm": 1.0, "loss": 0.7099222540855408, "grad_norm": 0.4645795524120331, "learning_rate": 0.0001632606292752207}
+{"ts": "2025-12-24T09:00:29", "event": "train_log", "step": 4724, "epoch": 2.0379719525350595, "progress_pct": 33.97, "epoch_pct": 33.97, "eta": "36:01:54", "max_grad_norm": 1.0, "loss": 0.6820752620697021, "grad_norm": 0.5478292107582092, "learning_rate": 0.00016322258991164888}
+{"ts": "2025-12-24T09:00:45", "event": "train_log", "step": 4726, "epoch": 2.0388349514563107, "progress_pct": 33.98, "epoch_pct": 33.98, "eta": "36:01:01", "max_grad_norm": 1.0, "loss": 0.6409106254577637, "grad_norm": 0.43450072407722473, "learning_rate": 0.0001631845353022345}
+{"ts": "2025-12-24T09:00:59", "event": "train_log", "step": 4728, "epoch": 2.039697950377562, "progress_pct": 33.99, "epoch_pct": 33.99, "eta": "36:00:07", "max_grad_norm": 1.0, "loss": 0.6333857774734497, "grad_norm": 0.45651859045028687, "learning_rate": 0.00016314646545615425}
+{"ts": "2025-12-24T09:01:14", "event": "train_log", "step": 4730, "epoch": 2.0405609492988135, "progress_pct": 34.01, "epoch_pct": 34.01, "eta": "35:59:13", "max_grad_norm": 1.0, "loss": 0.6916699409484863, "grad_norm": 0.5757591724395752, "learning_rate": 0.00016310838038258857}
+{"ts": "2025-12-24T09:01:29", "event": "train_log", "step": 4732, "epoch": 2.0414239482200647, "progress_pct": 34.02, "epoch_pct": 34.02, "eta": "35:58:19", "max_grad_norm": 1.0, "loss": 0.6683944463729858, "grad_norm": 0.4671119451522827, "learning_rate": 0.00016307028009072142}
+{"ts": "2025-12-24T09:01:45", "event": "train_log", "step": 4734, "epoch": 2.042286947141316, "progress_pct": 34.04, "epoch_pct": 34.04, "eta": "35:57:26", "max_grad_norm": 1.0, "loss": 0.646324872970581, "grad_norm": 0.4907313585281372, "learning_rate": 0.00016303216458974057}
+{"ts": "2025-12-24T09:02:01", "event": "train_log", "step": 4736, "epoch": 2.0431499460625675, "progress_pct": 34.05, "epoch_pct": 34.05, "eta": "35:56:35", "max_grad_norm": 1.0, "loss": 0.5972960591316223, "grad_norm": 0.5115658044815063, "learning_rate": 0.00016299403388883734}
+{"ts": "2025-12-24T09:02:17", "event": "train_log", "step": 4738, "epoch": 2.0440129449838187, "progress_pct": 34.07, "epoch_pct": 34.07, "eta": "35:55:42", "max_grad_norm": 1.0, "loss": 0.6689629554748535, "grad_norm": 0.5354726910591125, "learning_rate": 0.00016295588799720685}
+{"ts": "2025-12-24T09:02:33", "event": "train_log", "step": 4740, "epoch": 2.0448759439050703, "progress_pct": 34.08, "epoch_pct": 34.08, "eta": "35:54:51", "max_grad_norm": 1.0, "loss": 0.6738830804824829, "grad_norm": 0.43958503007888794, "learning_rate": 0.00016291772692404778}
+{"ts": "2025-12-24T09:02:49", "event": "train_log", "step": 4742, "epoch": 2.0457389428263215, "progress_pct": 34.1, "epoch_pct": 34.1, "eta": "35:53:59", "max_grad_norm": 1.0, "loss": 0.6682393550872803, "grad_norm": 0.4534682631492615, "learning_rate": 0.00016287955067856248}
+{"ts": "2025-12-24T09:03:05", "event": "train_log", "step": 4744, "epoch": 2.0466019417475727, "progress_pct": 34.11, "epoch_pct": 34.11, "eta": "35:53:08", "max_grad_norm": 1.0, "loss": 0.6737524271011353, "grad_norm": 0.42065930366516113, "learning_rate": 0.00016284135926995701}
+{"ts": "2025-12-24T09:03:19", "event": "train_log", "step": 4746, "epoch": 2.0474649406688243, "progress_pct": 34.12, "epoch_pct": 34.12, "eta": "35:52:12", "max_grad_norm": 1.0, "loss": 0.6920300722122192, "grad_norm": 0.4378197491168976, "learning_rate": 0.00016280315270744103}
+{"ts": "2025-12-24T09:03:36", "event": "train_log", "step": 4748, "epoch": 2.0483279395900755, "progress_pct": 34.14, "epoch_pct": 34.14, "eta": "35:51:23", "max_grad_norm": 1.0, "loss": 0.6725178360939026, "grad_norm": 0.4674663245677948, "learning_rate": 0.0001627649310002279}
+{"ts": "2025-12-24T09:03:52", "event": "train_log", "step": 4750, "epoch": 2.0491909385113267, "progress_pct": 34.15, "epoch_pct": 34.15, "eta": "35:50:30", "max_grad_norm": 1.0, "loss": 0.6869958639144897, "grad_norm": 0.5681027173995972, "learning_rate": 0.00016272669415753462}
+{"ts": "2025-12-24T09:04:07", "event": "train_log", "step": 4752, "epoch": 2.0500539374325784, "progress_pct": 34.17, "epoch_pct": 34.17, "eta": "35:49:38", "max_grad_norm": 1.0, "loss": 0.6425879001617432, "grad_norm": 0.4629790484905243, "learning_rate": 0.00016268844218858178}
+{"ts": "2025-12-24T09:04:24", "event": "train_log", "step": 4754, "epoch": 2.0509169363538295, "progress_pct": 34.18, "epoch_pct": 34.18, "eta": "35:48:47", "max_grad_norm": 1.0, "loss": 0.5698254704475403, "grad_norm": 0.4134989380836487, "learning_rate": 0.00016265017510259372}
+{"ts": "2025-12-24T09:04:40", "event": "train_log", "step": 4756, "epoch": 2.0517799352750807, "progress_pct": 34.2, "epoch_pct": 34.2, "eta": "35:47:56", "max_grad_norm": 1.0, "loss": 0.6877186298370361, "grad_norm": 0.47246792912483215, "learning_rate": 0.0001626118929087984}
+{"ts": "2025-12-24T09:04:56", "event": "train_log", "step": 4758, "epoch": 2.0526429341963324, "progress_pct": 34.21, "epoch_pct": 34.21, "eta": "35:47:05", "max_grad_norm": 1.0, "loss": 0.6143110990524292, "grad_norm": 0.46164244413375854, "learning_rate": 0.00016257359561642728}
+{"ts": "2025-12-24T09:05:11", "event": "train_log", "step": 4760, "epoch": 2.0535059331175836, "progress_pct": 34.22, "epoch_pct": 34.23, "eta": "35:46:11", "max_grad_norm": 1.0, "loss": 0.5955761075019836, "grad_norm": 0.4283512234687805, "learning_rate": 0.00016253528323471574}
+{"ts": "2025-12-24T09:05:26", "event": "train_log", "step": 4762, "epoch": 2.0543689320388347, "progress_pct": 34.24, "epoch_pct": 34.24, "eta": "35:45:18", "max_grad_norm": 1.0, "loss": 0.675889790058136, "grad_norm": 0.5213261842727661, "learning_rate": 0.00016249695577290254}
+{"ts": "2025-12-24T09:05:43", "event": "train_log", "step": 4764, "epoch": 2.0552319309600864, "progress_pct": 34.25, "epoch_pct": 34.25, "eta": "35:44:27", "max_grad_norm": 1.0, "loss": 0.6699239015579224, "grad_norm": 0.4362858831882477, "learning_rate": 0.00016245861324023014}
+{"ts": "2025-12-24T09:05:57", "event": "train_log", "step": 4766, "epoch": 2.0560949298813376, "progress_pct": 34.27, "epoch_pct": 34.27, "eta": "35:43:32", "max_grad_norm": 1.0, "loss": 0.6341968774795532, "grad_norm": 0.41920483112335205, "learning_rate": 0.0001624202556459448}
+{"ts": "2025-12-24T09:06:12", "event": "train_log", "step": 4768, "epoch": 2.056957928802589, "progress_pct": 34.28, "epoch_pct": 34.28, "eta": "35:42:38", "max_grad_norm": 1.0, "loss": 0.6707322597503662, "grad_norm": 0.4359661936759949, "learning_rate": 0.00016238188299929615}
+{"ts": "2025-12-24T09:06:26", "event": "train_log", "step": 4770, "epoch": 2.0578209277238404, "progress_pct": 34.3, "epoch_pct": 34.3, "eta": "35:41:44", "max_grad_norm": 1.0, "loss": 0.6224585175514221, "grad_norm": 0.4793999493122101, "learning_rate": 0.00016234349530953765}
+{"ts": "2025-12-24T09:06:41", "event": "train_log", "step": 4772, "epoch": 2.0586839266450916, "progress_pct": 34.31, "epoch_pct": 34.31, "eta": "35:40:51", "max_grad_norm": 1.0, "loss": 0.6421643495559692, "grad_norm": 0.47932904958724976, "learning_rate": 0.00016230509258592632}
+{"ts": "2025-12-24T09:06:56", "event": "train_log", "step": 4774, "epoch": 2.0595469255663432, "progress_pct": 34.33, "epoch_pct": 34.33, "eta": "35:39:57", "max_grad_norm": 1.0, "loss": 0.637798011302948, "grad_norm": 0.47485774755477905, "learning_rate": 0.00016226667483772275}
+{"ts": "2025-12-24T09:07:11", "event": "train_log", "step": 4776, "epoch": 2.0604099244875944, "progress_pct": 34.34, "epoch_pct": 34.34, "eta": "35:39:04", "max_grad_norm": 1.0, "loss": 0.6509931683540344, "grad_norm": 0.4462059438228607, "learning_rate": 0.00016222824207419128}
+{"ts": "2025-12-24T09:07:25", "event": "train_log", "step": 4778, "epoch": 2.0612729234088456, "progress_pct": 34.35, "epoch_pct": 34.35, "eta": "35:38:08", "max_grad_norm": 1.0, "loss": 0.6493304967880249, "grad_norm": 0.4955538511276245, "learning_rate": 0.00016218979430459972}
+{"ts": "2025-12-24T09:07:39", "event": "train_log", "step": 4780, "epoch": 2.0621359223300972, "progress_pct": 34.37, "epoch_pct": 34.37, "eta": "35:37:14", "max_grad_norm": 1.0, "loss": 0.6730417013168335, "grad_norm": 0.5239408612251282, "learning_rate": 0.00016215133153821967}
+{"ts": "2025-12-24T09:07:54", "event": "train_log", "step": 4782, "epoch": 2.0629989212513484, "progress_pct": 34.38, "epoch_pct": 34.38, "eta": "35:36:20", "max_grad_norm": 1.0, "loss": 0.6881803870201111, "grad_norm": 0.4394422173500061, "learning_rate": 0.00016211285378432615}
+{"ts": "2025-12-24T09:08:08", "event": "train_log", "step": 4784, "epoch": 2.0638619201725996, "progress_pct": 34.4, "epoch_pct": 34.4, "eta": "35:35:27", "max_grad_norm": 1.0, "loss": 0.6820991039276123, "grad_norm": 0.5362744927406311, "learning_rate": 0.00016207436105219797}
+{"ts": "2025-12-24T09:08:24", "event": "train_log", "step": 4786, "epoch": 2.0647249190938513, "progress_pct": 34.41, "epoch_pct": 34.41, "eta": "35:34:34", "max_grad_norm": 1.0, "loss": 0.6306631565093994, "grad_norm": 0.43284544348716736, "learning_rate": 0.00016203585335111743}
+{"ts": "2025-12-24T09:08:38", "event": "train_log", "step": 4788, "epoch": 2.0655879180151024, "progress_pct": 34.43, "epoch_pct": 34.43, "eta": "35:33:40", "max_grad_norm": 1.0, "loss": 0.6391012072563171, "grad_norm": 0.5029301643371582, "learning_rate": 0.00016199733069037055}
+{"ts": "2025-12-24T09:08:52", "event": "train_log", "step": 4790, "epoch": 2.0664509169363536, "progress_pct": 34.44, "epoch_pct": 34.44, "eta": "35:32:46", "max_grad_norm": 1.0, "loss": 0.6401529908180237, "grad_norm": 0.5301947593688965, "learning_rate": 0.00016195879307924683}
+{"ts": "2025-12-24T09:09:07", "event": "train_log", "step": 4792, "epoch": 2.0673139158576053, "progress_pct": 34.45, "epoch_pct": 34.46, "eta": "35:31:52", "max_grad_norm": 1.0, "loss": 0.6239875555038452, "grad_norm": 0.4390850067138672, "learning_rate": 0.0001619202405270395}
+{"ts": "2025-12-24T09:09:21", "event": "train_log", "step": 4794, "epoch": 2.0681769147788565, "progress_pct": 34.47, "epoch_pct": 34.47, "eta": "35:30:58", "max_grad_norm": 1.0, "loss": 0.690622091293335, "grad_norm": 0.4700588583946228, "learning_rate": 0.0001618816730430453}
+{"ts": "2025-12-24T09:09:36", "event": "train_log", "step": 4796, "epoch": 2.0690399137001076, "progress_pct": 34.48, "epoch_pct": 34.48, "eta": "35:30:04", "max_grad_norm": 1.0, "loss": 0.6091710329055786, "grad_norm": 0.49601292610168457, "learning_rate": 0.00016184309063656458}
+{"ts": "2025-12-24T09:09:51", "event": "train_log", "step": 4798, "epoch": 2.0699029126213593, "progress_pct": 34.5, "epoch_pct": 34.5, "eta": "35:29:12", "max_grad_norm": 1.0, "loss": 0.6168843507766724, "grad_norm": 0.4593116044998169, "learning_rate": 0.00016180449331690134}
+{"ts": "2025-12-24T09:10:06", "event": "train_log", "step": 4800, "epoch": 2.0707659115426105, "progress_pct": 34.51, "epoch_pct": 34.51, "eta": "35:28:20", "max_grad_norm": 1.0, "loss": 0.6540603041648865, "grad_norm": 0.4720041751861572, "learning_rate": 0.0001617658810933632}
+{"ts": "2025-12-24T09:20:58", "event": "train_log", "step": 4800, "epoch": 2.0707659115426105, "progress_pct": 34.51, "epoch_pct": 34.51, "eta": "35:48:56", "max_grad_norm": 1.0, "eval_loss": 0.7749598026275635, "eval_runtime": 651.5576, "eval_samples_per_second": 3.162, "eval_steps_per_second": 3.162}
+{"ts": "2025-12-24T09:21:13", "event": "train_log", "step": 4802, "epoch": 2.071628910463862, "progress_pct": 34.53, "epoch_pct": 34.53, "eta": "35:48:02", "max_grad_norm": 1.0, "loss": 0.5709460973739624, "grad_norm": 0.4562988877296448, "learning_rate": 0.00016172725397526122}
+{"ts": "2025-12-24T09:21:27", "event": "train_log", "step": 4804, "epoch": 2.0724919093851133, "progress_pct": 34.54, "epoch_pct": 34.54, "eta": "35:47:07", "max_grad_norm": 1.0, "loss": 0.6872497797012329, "grad_norm": 0.43549156188964844, "learning_rate": 0.00016168861197191027}
+{"ts": "2025-12-24T09:21:41", "event": "train_log", "step": 4806, "epoch": 2.0733549083063645, "progress_pct": 34.56, "epoch_pct": 34.56, "eta": "35:46:12", "max_grad_norm": 1.0, "loss": 0.6759166121482849, "grad_norm": 0.469290554523468, "learning_rate": 0.00016164995509262858}
+{"ts": "2025-12-24T09:21:57", "event": "train_log", "step": 4808, "epoch": 2.074217907227616, "progress_pct": 34.57, "epoch_pct": 34.57, "eta": "35:45:19", "max_grad_norm": 1.0, "loss": 0.7064661383628845, "grad_norm": 0.49189457297325134, "learning_rate": 0.0001616112833467382}
+{"ts": "2025-12-24T09:22:12", "event": "train_log", "step": 4810, "epoch": 2.0750809061488673, "progress_pct": 34.58, "epoch_pct": 34.58, "eta": "35:44:26", "max_grad_norm": 1.0, "loss": 0.6480143070220947, "grad_norm": 0.4290579855442047, "learning_rate": 0.00016157259674356452}
+{"ts": "2025-12-24T09:22:27", "event": "train_log", "step": 4812, "epoch": 2.0759439050701185, "progress_pct": 34.6, "epoch_pct": 34.6, "eta": "35:43:34", "max_grad_norm": 1.0, "loss": 0.635689377784729, "grad_norm": 0.4433795213699341, "learning_rate": 0.00016153389529243676}
+{"ts": "2025-12-24T09:22:41", "event": "train_log", "step": 4814, "epoch": 2.07680690399137, "progress_pct": 34.61, "epoch_pct": 34.61, "eta": "35:42:39", "max_grad_norm": 1.0, "loss": 0.7547900676727295, "grad_norm": 0.6109093427658081, "learning_rate": 0.0001614951790026875}
+{"ts": "2025-12-24T09:22:57", "event": "train_log", "step": 4816, "epoch": 2.0776699029126213, "progress_pct": 34.63, "epoch_pct": 34.63, "eta": "35:41:46", "max_grad_norm": 1.0, "loss": 0.6653686761856079, "grad_norm": 0.5321441888809204, "learning_rate": 0.0001614564478836531}
+{"ts": "2025-12-24T09:23:11", "event": "train_log", "step": 4818, "epoch": 2.0785329018338725, "progress_pct": 34.64, "epoch_pct": 34.64, "eta": "35:40:51", "max_grad_norm": 1.0, "loss": 0.6075063347816467, "grad_norm": 0.506106436252594, "learning_rate": 0.0001614177019446733}
+{"ts": "2025-12-24T09:23:27", "event": "train_log", "step": 4820, "epoch": 2.079395900755124, "progress_pct": 34.66, "epoch_pct": 34.66, "eta": "35:40:00", "max_grad_norm": 1.0, "loss": 0.6817623376846313, "grad_norm": 0.5259274840354919, "learning_rate": 0.00016137894119509156}
+{"ts": "2025-12-24T09:23:41", "event": "train_log", "step": 4822, "epoch": 2.0802588996763753, "progress_pct": 34.67, "epoch_pct": 34.67, "eta": "35:39:06", "max_grad_norm": 1.0, "loss": 0.5794091820716858, "grad_norm": 0.42217540740966797, "learning_rate": 0.00016134016564425485}
+{"ts": "2025-12-24T09:23:57", "event": "train_log", "step": 4824, "epoch": 2.081121898597627, "progress_pct": 34.69, "epoch_pct": 34.69, "eta": "35:38:14", "max_grad_norm": 1.0, "loss": 0.690514862537384, "grad_norm": 0.4804263114929199, "learning_rate": 0.0001613013753015137}
+{"ts": "2025-12-24T09:24:12", "event": "train_log", "step": 4826, "epoch": 2.081984897518878, "progress_pct": 34.7, "epoch_pct": 34.7, "eta": "35:37:21", "max_grad_norm": 1.0, "loss": 0.7252055406570435, "grad_norm": 0.4771824777126312, "learning_rate": 0.00016126257017622225}
+{"ts": "2025-12-24T09:24:27", "event": "train_log", "step": 4828, "epoch": 2.0828478964401294, "progress_pct": 34.71, "epoch_pct": 34.71, "eta": "35:36:27", "max_grad_norm": 1.0, "loss": 0.6873422265052795, "grad_norm": 0.44665834307670593, "learning_rate": 0.0001612237502777382}
+{"ts": "2025-12-24T09:24:42", "event": "train_log", "step": 4830, "epoch": 2.083710895361381, "progress_pct": 34.73, "epoch_pct": 34.73, "eta": "35:35:34", "max_grad_norm": 1.0, "loss": 0.6000558733940125, "grad_norm": 0.46783381700515747, "learning_rate": 0.00016118491561542276}
+{"ts": "2025-12-24T09:24:58", "event": "train_log", "step": 4832, "epoch": 2.084573894282632, "progress_pct": 34.74, "epoch_pct": 34.74, "eta": "35:34:43", "max_grad_norm": 1.0, "loss": 0.6226951479911804, "grad_norm": 0.4223193824291229, "learning_rate": 0.00016114606619864073}
+{"ts": "2025-12-24T09:25:13", "event": "train_log", "step": 4834, "epoch": 2.0854368932038834, "progress_pct": 34.76, "epoch_pct": 34.76, "eta": "35:33:49", "max_grad_norm": 1.0, "loss": 0.7194363474845886, "grad_norm": 0.5119433999061584, "learning_rate": 0.00016110720203676052}
+{"ts": "2025-12-24T09:25:28", "event": "train_log", "step": 4836, "epoch": 2.086299892125135, "progress_pct": 34.77, "epoch_pct": 34.77, "eta": "35:32:57", "max_grad_norm": 1.0, "loss": 0.5572496056556702, "grad_norm": 0.44145917892456055, "learning_rate": 0.00016106832313915397}
+{"ts": "2025-12-24T09:25:44", "event": "train_log", "step": 4838, "epoch": 2.087162891046386, "progress_pct": 34.79, "epoch_pct": 34.79, "eta": "35:32:05", "max_grad_norm": 1.0, "loss": 0.6001632213592529, "grad_norm": 0.570189356803894, "learning_rate": 0.00016102942951519658}
+{"ts": "2025-12-24T09:25:59", "event": "train_log", "step": 4840, "epoch": 2.0880258899676374, "progress_pct": 34.8, "epoch_pct": 34.8, "eta": "35:31:13", "max_grad_norm": 1.0, "loss": 0.6026968359947205, "grad_norm": 0.4330277144908905, "learning_rate": 0.00016099052117426741}
+{"ts": "2025-12-24T09:26:16", "event": "train_log", "step": 4842, "epoch": 2.088888888888889, "progress_pct": 34.81, "epoch_pct": 34.81, "eta": "35:30:23", "max_grad_norm": 1.0, "loss": 0.6872023940086365, "grad_norm": 0.557523250579834, "learning_rate": 0.00016095159812574901}
+{"ts": "2025-12-24T09:26:31", "event": "train_log", "step": 4844, "epoch": 2.08975188781014, "progress_pct": 34.83, "epoch_pct": 34.83, "eta": "35:29:30", "max_grad_norm": 1.0, "loss": 0.6541061997413635, "grad_norm": 0.47656843066215515, "learning_rate": 0.0001609126603790275}
+{"ts": "2025-12-24T09:26:45", "event": "train_log", "step": 4846, "epoch": 2.0906148867313914, "progress_pct": 34.84, "epoch_pct": 34.84, "eta": "35:28:36", "max_grad_norm": 1.0, "loss": 0.6052494049072266, "grad_norm": 0.49972298741340637, "learning_rate": 0.0001608737079434925}
+{"ts": "2025-12-24T09:27:00", "event": "train_log", "step": 4848, "epoch": 2.091477885652643, "progress_pct": 34.86, "epoch_pct": 34.86, "eta": "35:27:43", "max_grad_norm": 1.0, "loss": 0.601698637008667, "grad_norm": 0.415645569562912, "learning_rate": 0.0001608347408285373}
+{"ts": "2025-12-24T09:27:16", "event": "train_log", "step": 4850, "epoch": 2.092340884573894, "progress_pct": 34.87, "epoch_pct": 34.87, "eta": "35:26:52", "max_grad_norm": 1.0, "loss": 0.5893869400024414, "grad_norm": 0.47933652997016907, "learning_rate": 0.00016079575904355857}
+{"ts": "2025-12-24T09:27:33", "event": "train_log", "step": 4852, "epoch": 2.0932038834951454, "progress_pct": 34.89, "epoch_pct": 34.89, "eta": "35:26:04", "max_grad_norm": 1.0, "loss": 0.6397660970687866, "grad_norm": 0.4597874581813812, "learning_rate": 0.0001607567625979566}
+{"ts": "2025-12-24T09:27:48", "event": "train_log", "step": 4854, "epoch": 2.094066882416397, "progress_pct": 34.9, "epoch_pct": 34.9, "eta": "35:25:10", "max_grad_norm": 1.0, "loss": 0.6468450427055359, "grad_norm": 0.4965691566467285, "learning_rate": 0.00016071775150113525}
+{"ts": "2025-12-24T09:28:03", "event": "train_log", "step": 4856, "epoch": 2.0949298813376482, "progress_pct": 34.92, "epoch_pct": 34.92, "eta": "35:24:18", "max_grad_norm": 1.0, "loss": 0.6750592589378357, "grad_norm": 0.45494288206100464, "learning_rate": 0.0001606787257625018}
+{"ts": "2025-12-24T09:28:19", "event": "train_log", "step": 4858, "epoch": 2.0957928802589, "progress_pct": 34.93, "epoch_pct": 34.93, "eta": "35:23:27", "max_grad_norm": 1.0, "loss": 0.6462316513061523, "grad_norm": 0.4151075482368469, "learning_rate": 0.0001606396853914672}
+{"ts": "2025-12-24T09:28:34", "event": "train_log", "step": 4860, "epoch": 2.096655879180151, "progress_pct": 34.94, "epoch_pct": 34.94, "eta": "35:22:34", "max_grad_norm": 1.0, "loss": 0.6318191885948181, "grad_norm": 0.554997444152832, "learning_rate": 0.00016060063039744583}
+{"ts": "2025-12-24T09:28:50", "event": "train_log", "step": 4862, "epoch": 2.0975188781014023, "progress_pct": 34.96, "epoch_pct": 34.96, "eta": "35:21:44", "max_grad_norm": 1.0, "loss": 0.6247371435165405, "grad_norm": 0.4213683009147644, "learning_rate": 0.00016056156078985562}
+{"ts": "2025-12-24T09:29:06", "event": "train_log", "step": 4864, "epoch": 2.098381877022654, "progress_pct": 34.97, "epoch_pct": 34.97, "eta": "35:20:53", "max_grad_norm": 1.0, "loss": 0.674854040145874, "grad_norm": 0.48299139738082886, "learning_rate": 0.00016052247657811805}
+{"ts": "2025-12-24T09:29:21", "event": "train_log", "step": 4866, "epoch": 2.099244875943905, "progress_pct": 34.99, "epoch_pct": 34.99, "eta": "35:20:01", "max_grad_norm": 1.0, "loss": 0.6188970804214478, "grad_norm": 0.48760414123535156, "learning_rate": 0.00016048337777165811}
+{"ts": "2025-12-24T09:29:36", "event": "train_log", "step": 4868, "epoch": 2.1001078748651563, "progress_pct": 35.0, "epoch_pct": 35.0, "eta": "35:19:08", "max_grad_norm": 1.0, "loss": 0.7034997344017029, "grad_norm": 0.49093401432037354, "learning_rate": 0.00016044426437990426}
+{"ts": "2025-12-24T09:29:52", "event": "train_log", "step": 4870, "epoch": 2.100970873786408, "progress_pct": 35.02, "epoch_pct": 35.02, "eta": "35:18:16", "max_grad_norm": 1.0, "loss": 0.6546196937561035, "grad_norm": 0.4612952768802643, "learning_rate": 0.00016040513641228855}
+{"ts": "2025-12-24T09:30:07", "event": "train_log", "step": 4872, "epoch": 2.101833872707659, "progress_pct": 35.03, "epoch_pct": 35.03, "eta": "35:17:24", "max_grad_norm": 1.0, "loss": 0.7384663820266724, "grad_norm": 0.531837522983551, "learning_rate": 0.00016036599387824648}
+{"ts": "2025-12-24T09:30:22", "event": "train_log", "step": 4874, "epoch": 2.1026968716289103, "progress_pct": 35.04, "epoch_pct": 35.04, "eta": "35:16:32", "max_grad_norm": 1.0, "loss": 0.6188966035842896, "grad_norm": 0.4080790579319, "learning_rate": 0.00016032683678721715}
+{"ts": "2025-12-24T09:30:40", "event": "train_log", "step": 4876, "epoch": 2.103559870550162, "progress_pct": 35.06, "epoch_pct": 35.06, "eta": "35:15:45", "max_grad_norm": 1.0, "loss": 0.5405320525169373, "grad_norm": 0.3449578583240509, "learning_rate": 0.00016028766514864304}
+{"ts": "2025-12-24T09:30:55", "event": "train_log", "step": 4878, "epoch": 2.104422869471413, "progress_pct": 35.07, "epoch_pct": 35.07, "eta": "35:14:53", "max_grad_norm": 1.0, "loss": 0.6256349682807922, "grad_norm": 0.4911097586154938, "learning_rate": 0.00016024847897197028}
+{"ts": "2025-12-24T09:31:11", "event": "train_log", "step": 4880, "epoch": 2.1052858683926643, "progress_pct": 35.09, "epoch_pct": 35.09, "eta": "35:14:02", "max_grad_norm": 1.0, "loss": 0.6339661478996277, "grad_norm": 0.44275417923927307, "learning_rate": 0.0001602092782666484}
+{"ts": "2025-12-24T09:31:27", "event": "train_log", "step": 4882, "epoch": 2.106148867313916, "progress_pct": 35.1, "epoch_pct": 35.1, "eta": "35:13:12", "max_grad_norm": 1.0, "loss": 0.6473315954208374, "grad_norm": 0.4649251401424408, "learning_rate": 0.00016017006304213052}
+{"ts": "2025-12-24T09:31:42", "event": "train_log", "step": 4884, "epoch": 2.107011866235167, "progress_pct": 35.12, "epoch_pct": 35.12, "eta": "35:12:20", "max_grad_norm": 1.0, "loss": 0.6582548022270203, "grad_norm": 0.5085191130638123, "learning_rate": 0.00016013083330787317}
+{"ts": "2025-12-24T09:31:57", "event": "train_log", "step": 4886, "epoch": 2.1078748651564188, "progress_pct": 35.13, "epoch_pct": 35.13, "eta": "35:11:28", "max_grad_norm": 1.0, "loss": 0.7063833475112915, "grad_norm": 0.5697877407073975, "learning_rate": 0.00016009158907333645}
+{"ts": "2025-12-24T09:32:13", "event": "train_log", "step": 4888, "epoch": 2.10873786407767, "progress_pct": 35.15, "epoch_pct": 35.15, "eta": "35:10:36", "max_grad_norm": 1.0, "loss": 0.6098092794418335, "grad_norm": 0.4935518801212311, "learning_rate": 0.0001600523303479839}
+{"ts": "2025-12-24T09:32:28", "event": "train_log", "step": 4890, "epoch": 2.109600862998921, "progress_pct": 35.16, "epoch_pct": 35.16, "eta": "35:09:45", "max_grad_norm": 1.0, "loss": 0.5643852949142456, "grad_norm": 0.47223731875419617, "learning_rate": 0.00016001305714128265}
+{"ts": "2025-12-24T09:32:44", "event": "train_log", "step": 4892, "epoch": 2.1104638619201728, "progress_pct": 35.17, "epoch_pct": 35.17, "eta": "35:08:54", "max_grad_norm": 1.0, "loss": 0.6599231958389282, "grad_norm": 0.5232506394386292, "learning_rate": 0.00015997376946270318}
+{"ts": "2025-12-24T09:33:00", "event": "train_log", "step": 4894, "epoch": 2.111326860841424, "progress_pct": 35.19, "epoch_pct": 35.19, "eta": "35:08:03", "max_grad_norm": 1.0, "loss": 0.7038850784301758, "grad_norm": 0.5681605339050293, "learning_rate": 0.00015993446732171955}
+{"ts": "2025-12-24T09:33:16", "event": "train_log", "step": 4896, "epoch": 2.112189859762675, "progress_pct": 35.2, "epoch_pct": 35.2, "eta": "35:07:14", "max_grad_norm": 1.0, "loss": 0.6107864379882812, "grad_norm": 0.4312243163585663, "learning_rate": 0.00015989515072780934}
+{"ts": "2025-12-24T09:33:32", "event": "train_log", "step": 4898, "epoch": 2.113052858683927, "progress_pct": 35.22, "epoch_pct": 35.22, "eta": "35:06:24", "max_grad_norm": 1.0, "loss": 0.7147808074951172, "grad_norm": 0.5554447770118713, "learning_rate": 0.0001598558196904535}
+{"ts": "2025-12-24T09:33:48", "event": "train_log", "step": 4900, "epoch": 2.113915857605178, "progress_pct": 35.23, "epoch_pct": 35.23, "eta": "35:05:33", "max_grad_norm": 1.0, "loss": 0.6425569653511047, "grad_norm": 0.44741159677505493, "learning_rate": 0.0001598164742191366}
+{"ts": "2025-12-24T09:44:37", "event": "train_log", "step": 4900, "epoch": 2.113915857605178, "progress_pct": 35.23, "epoch_pct": 35.23, "eta": "35:25:27", "max_grad_norm": 1.0, "eval_loss": 0.7710265517234802, "eval_runtime": 649.6739, "eval_samples_per_second": 3.171, "eval_steps_per_second": 3.171}
+{"ts": "2025-12-24T09:44:37", "event": "train_log", "step": 4900, "epoch": 2.113915857605178, "progress_pct": 35.23, "epoch_pct": 35.23, "eta": "35:25:27", "max_grad_norm": 1.0, "train_runtime": 69370.1166, "train_samples_per_second": 1.604, "train_steps_per_second": 0.2, "total_flos": 2.9383334939106386e+18, "train_loss": 0.8349519448864217}
+{"ts": "2025-12-24T09:55:38", "event": "train_log", "step": 4900, "epoch": 2.113915857605178, "progress_pct": 35.23, "epoch_pct": 35.23, "eta": "35:45:41", "max_grad_norm": 1.0, "eval_loss": 0.771009087562561, "eval_runtime": 660.1524, "eval_samples_per_second": 3.12, "eval_steps_per_second": 3.12}
diff --git a/sft_qwen_14B/wandb/debug-internal.log b/sft_qwen_14B/wandb/debug-internal.log
new file mode 100644
index 0000000000000000000000000000000000000000..fe7b2c0e805207da8a7e3ea54a831c4f0e6aad9a
--- /dev/null
+++ b/sft_qwen_14B/wandb/debug-internal.log
@@ -0,0 +1,12 @@
+{"time":"2025-12-23T14:27:02.483579527Z","level":"INFO","msg":"stream: starting","core version":"0.23.1"}
+{"time":"2025-12-23T14:27:02.637028075Z","level":"INFO","msg":"stream: created new stream","id":"ldjr67u6"}
+{"time":"2025-12-23T14:27:02.637166774Z","level":"INFO","msg":"handler: started","stream_id":"ldjr67u6"}
+{"time":"2025-12-23T14:27:02.637274386Z","level":"INFO","msg":"stream: started","id":"ldjr67u6"}
+{"time":"2025-12-23T14:27:02.637294935Z","level":"INFO","msg":"writer: started","stream_id":"ldjr67u6"}
+{"time":"2025-12-23T14:27:02.637323084Z","level":"INFO","msg":"sender: started","stream_id":"ldjr67u6"}
+{"time":"2025-12-24T09:56:33.315646376Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2025-12-24T09:56:33.395280157Z","level":"INFO","msg":"handler: operation stats","stats":{}}
+{"time":"2025-12-24T09:56:33.399794124Z","level":"INFO","msg":"stream: closing","id":"ldjr67u6"}
+{"time":"2025-12-24T09:56:33.399816195Z","level":"INFO","msg":"handler: closed","stream_id":"ldjr67u6"}
+{"time":"2025-12-24T09:56:33.399912405Z","level":"INFO","msg":"sender: closed","stream_id":"ldjr67u6"}
+{"time":"2025-12-24T09:56:33.399932943Z","level":"INFO","msg":"stream: closed","id":"ldjr67u6"}
diff --git a/sft_qwen_14B/wandb/debug.log b/sft_qwen_14B/wandb/debug.log
new file mode 100644
index 0000000000000000000000000000000000000000..f59e39ffea6fa02662b169817984263afc30c6cc
--- /dev/null
+++ b/sft_qwen_14B/wandb/debug.log
@@ -0,0 +1,29 @@
+2025-12-23 14:27:02,030 INFO    MainThread:926994 [wandb_setup.py:_flush():80] Current SDK version is 0.23.1
+2025-12-23 14:27:02,031 INFO    MainThread:926994 [wandb_setup.py:_flush():80] Configure stats pid to 926994
+2025-12-23 14:27:02,031 INFO    MainThread:926994 [wandb_setup.py:_flush():80] Loading settings from /root/.config/wandb/settings
+2025-12-23 14:27:02,031 INFO    MainThread:926994 [wandb_setup.py:_flush():80] Loading settings from /workspace/wandb/settings
+2025-12-23 14:27:02,031 INFO    MainThread:926994 [wandb_setup.py:_flush():80] Loading settings from environment variables
+2025-12-23 14:27:02,031 INFO    MainThread:926994 [wandb_init.py:setup_run_log_directory():714] Logging user logs to runs/instruct_run_14b_v1/wandb/run-20251223_142702-ldjr67u6/logs/debug.log
+2025-12-23 14:27:02,031 INFO    MainThread:926994 [wandb_init.py:setup_run_log_directory():715] Logging internal logs to runs/instruct_run_14b_v1/wandb/run-20251223_142702-ldjr67u6/logs/debug-internal.log
+2025-12-23 14:27:02,031 INFO    MainThread:926994 [wandb_init.py:init():841] calling init triggers
+2025-12-23 14:27:02,031 INFO    MainThread:926994 [wandb_init.py:init():846] wandb.init called with sweep_config: {}
+config: {'model': {'repo_id': './runs/cpt_run_14b/merged_14b_cpt_lora', 'revision': None, 'base_local_dir': 'base_model', 'trust_remote_code': True, 'tokenizer_use_fast': True, 'device_map': 'auto', 'torch_dtype': 'bfloat16', 'use_4bit': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': False, 'bnb_4bit_compute_dtype': 'bfloat16', 'attn_implementation': None}, 'data': {'train_jsonl': 'sft_dataset.jsonl', 'eval_jsonl': None, 'eval_split_ratio': 0.1, 'instruction_field': 'instruction', 'input_field': 'input', 'output_field': 'output', 'format_type': 'custom', 'system_prompt': 'You are a Hyperswitch Rust code analyzer. Identify functions/structs that need modification for a given task.\n\n## Output Format\n\n##OUTPUT\nExplain the data flow and why each component must change:\n- Flow: [Input → Processing → Output with arrows]\n- For each component: "The [ComponentName] ([path]) must [action] because [reason]—without this, [consequence]"\n- Explain coupling between components\n\n##SELECT\nmodify::crates/path/to/file.rs::impl::ComponentName\nadd::crates/another/file.rs::function::AnotherComponent\n<EOS>\n\n## Rules\n\n1. Use full paths: `remove::crates/folder/file.rs::Type::Name`\n2. Use `::` for nested items: `status::StructName::Type::Name`\n3. Always explain "must change because" and "without this"\n3. Types of components: function, struct, enum, impl, trait\n4. If there is extra information (e.g., enum variants), include that too.\n5. Start with ##OUTPUT, end with ##SELECT, terminate with <EOS>\n\n## Example\n\n##TASK\nAdd webhook subscription support\n\n##OUTPUT\nThe webhook system routes events via EventClass enum. Flow: webhook → EventClass → handler → processing. The EventClass enum (crates/common_enums/src/enums.rs::EventClass) must add Subscriptions variant because it defines event routing—without this, subscription events cannot be processed. The SubscriptionStatus impl (crates/common_enums/src/transformers.rs::SubscriptionStatus) must map to EventType because it converts status to events—without this, status changes don\'t trigger webhooks. These are coupled: EventClass routes to handlers that use SubscriptionStatus mappings.\n\n##SELECT\ncrates/common_enums/src/enums.rs::EventClass\ncrates/common_enums/src/transformers.rs::SubscriptionStatus\n<EOS>\n', 'custom_template': '##INSTRUCTION\n{instruction}<|im_end|>\n##TASK\n{input}<|im_end|>\n##OUTPUT\n{output}<|im_end|>', 'max_length': 2048, 'shuffle': True, 'num_proc': 4}, 'peft': {'enabled': True, 'r': 16, 'lora_alpha': 32, 'lora_dropout': 0.05, 'bias': 'none', 'target_modules': 'auto'}, 'train': {'num_train_epochs': 6, 'per_device_train_batch_size': 1, 'per_device_eval_batch_size': 1, 'gradient_accumulation_steps': 8, 'learning_rate': '2e-4', 'weight_decay': 0.0, 'warmup_ratio': 0.08, 'lr_scheduler_type': 'cosine', 'optim': 'adamw_torch', 'max_grad_norm': 1.0, 'gradient_checkpointing': True, 'logging_steps': 2, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 20, 'evaluation_strategy': 'steps', 'eval_steps': 100, 'load_best_model_at_end': True, 'early_stopping': {'enabled': True, 'patience': 3, 'min_delta': 0.001, 'metric': 'eval_loss', 'mode': 'min'}, 'resume_from_checkpoint': 'auto'}, 'run_dir': 'runs/instruct_run_14b_v1', '_wandb': {}}
+2025-12-23 14:27:02,031 INFO    MainThread:926994 [wandb_init.py:init():889] starting backend
+2025-12-23 14:27:02,477 INFO    MainThread:926994 [wandb_init.py:init():892] sending inform_init request
+2025-12-23 14:27:02,481 INFO    MainThread:926994 [wandb_init.py:init():900] backend started and connected
+2025-12-23 14:27:02,483 INFO    MainThread:926994 [wandb_init.py:init():970] updated telemetry
+2025-12-23 14:27:02,484 INFO    MainThread:926994 [wandb_init.py:init():994] communicating run to backend with 90.0 second timeout
+2025-12-23 14:27:02,870 INFO    MainThread:926994 [wandb_init.py:init():1041] starting run threads in backend
+2025-12-23 14:27:02,969 INFO    MainThread:926994 [wandb_run.py:_console_start():2521] atexit reg
+2025-12-23 14:27:02,970 INFO    MainThread:926994 [wandb_run.py:_redirect():2369] redirect: wrap_raw
+2025-12-23 14:27:02,970 INFO    MainThread:926994 [wandb_run.py:_redirect():2438] Wrapping output streams.
+2025-12-23 14:27:02,970 INFO    MainThread:926994 [wandb_run.py:_redirect():2461] Redirects installed.
+2025-12-23 14:27:02,973 INFO    MainThread:926994 [wandb_init.py:init():1081] run started, returning control to user process
+2025-12-23 14:28:27,753 INFO    MainThread:926994 [wandb_run.py:_config_callback():1396] config_cb None None {'peft_config': {'default': {'task_type': 'CAUSAL_LM', 'peft_type': 'LORA', 'auto_mapping': None, 'peft_version': '0.18.0', 'base_model_name_or_path': 'runs/cpt_run_14b/merged_14b_cpt_lora', 'revision': None, 'inference_mode': False, 'r': 16, 'target_modules': ['q_proj', 'o_proj', 'v_proj', 'k_proj'], 'exclude_modules': None, 'lora_alpha': 32, 'lora_dropout': 0.05, 'fan_in_fan_out': False, 'bias': 'none', 'use_rslora': False, 'modules_to_save': None, 'init_lora_weights': True, 'layers_to_transform': None, 'layers_pattern': None, 'rank_pattern': {}, 'alpha_pattern': {}, 'megatron_config': None, 'megatron_core': 'megatron.core', 'trainable_token_indices': None, 'loftq_config': {}, 'eva_config': None, 'corda_config': None, 'use_dora': False, 'alora_invocation_tokens': None, 'use_qalora': False, 'qalora_group_size': 16, 'layer_replication': None, 'runtime_config': {'ephemeral_gpu_offload': False}, 'lora_bias': False, 'target_parameters': None, 'arrow_config': None, 'ensure_weight_tying': False}}, 'vocab_size': 152064, 'max_position_embeddings': 32768, 'hidden_size': 5120, 'intermediate_size': 13824, 'num_hidden_layers': 48, 'num_attention_heads': 40, 'use_sliding_window': False, 'sliding_window': None, 'max_window_layers': 48, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'attention_dropout': 0.0, 'layer_types': ['full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention'], 'rope_parameters': {'rope_theta': 1000000.0, 'rope_type': 'default'}, 'return_dict': True, 'output_hidden_states': False, 'dtype': 'bfloat16', 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'architectures': ['Qwen2ForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'task_specific_params': None, 'problem_type': None, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 151643, 'pad_token_id': None, 'eos_token_id': 151643, 'sep_token_id': None, 'decoder_start_token_id': None, '_name_or_path': 'runs/cpt_run_14b/merged_14b_cpt_lora', 'transformers_version': '5.0.0.dev0', 'model_type': 'qwen2', 'output_attentions': False, 'output_dir': 'runs/instruct_run_14b_v1/checkpoints', 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 1, 'per_device_eval_batch_size': 1, 'gradient_accumulation_steps': 8, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 0.0002, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 6.0, 'max_steps': -1, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': None, 'warmup_ratio': 0.08, 'warmup_steps': 0.08, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': None, 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 2, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 20, 'enable_jit_checkpoint': False, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'use_cpu': False, 'seed': 42, 'data_seed': None, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': -1, 'ddp_backend': None, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 100, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'run_name': None, 'disable_tqdm': False, 'remove_unused_columns': False, 'label_names': None, 'load_best_model_at_end': True, 'metric_for_best_model': 'eval_loss', 'greater_is_better': False, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'project': 'huggingface', 'trackio_space_id': 'trackio', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_always_push': False, 'hub_revision': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'auto_find_batch_size': False, 'full_determinism': False, 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'include_num_input_tokens_seen': 'no', 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'liger_kernel_config': None, 'eval_use_gather_object': False, 'average_tokens_across_devices': True}
+2025-12-23 14:28:27,762 INFO    MainThread:926994 [wandb_config.py:__setitem__():154] [no run ID] config set model/num_parameters = 14795199488 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7a729b20d8a0>>
+2025-12-23 14:28:27,762 INFO    MainThread:926994 [wandb_run.py:_config_callback():1396] config_cb model/num_parameters 14795199488 None
+2025-12-24 09:56:32,985 INFO    MainThread:926994 [wandb_run.py:_finish():2287] finishing run sirajuddin-shaik-007/sft-training/ldjr67u6
+2025-12-24 09:56:32,986 INFO    MainThread:926994 [wandb_run.py:_atexit_cleanup():2486] got exitcode: 0
+2025-12-24 09:56:32,986 INFO    MainThread:926994 [wandb_run.py:_restore():2468] restore
+2025-12-24 09:56:32,986 INFO    MainThread:926994 [wandb_run.py:_restore():2474] restore done
+2025-12-24 09:56:33,398 INFO    MainThread:926994 [wandb_run.py:_footer_sync_info():3862] logging synced files
diff --git a/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/files/config.yaml b/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/files/config.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..4c7180f77a80c9c12f9c4ef2b33af26cdb25d48a
--- /dev/null
+++ b/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/files/config.yaml
@@ -0,0 +1,601 @@
+_name_or_path:
+    value: runs/cpt_run_14b/merged_14b_cpt_lora
+_wandb:
+    value:
+        cli_version: 0.23.1
+        e:
+            x2eg684gxvwjptbq4zszw1o13xocb8ht:
+                args:
+                    - --config
+                    - ./SFT/config_instruct.yaml
+                codePath: SFT/run_instruct.py
+                codePathLocal: SFT/run_instruct.py
+                cpu_count: 12
+                cpu_count_logical: 24
+                cudaVersion: "13.0"
+                disk:
+                    /:
+                        total: "791251738624"
+                        used: "330236313600"
+                email: shaiksirajuddin9949@gmail.com
+                executable: /workspace/CPT-env/bin/python
+                gpu: NVIDIA A100-SXM4-80GB
+                gpu_count: 2
+                gpu_nvidia:
+                    - architecture: Ampere
+                      cudaCores: 6912
+                      memoryTotal: "85899345920"
+                      name: NVIDIA A100-SXM4-80GB
+                      uuid: GPU-989794b0-ec3b-13bf-db9f-3fbe341497ba
+                    - architecture: Ampere
+                      cudaCores: 6912
+                      memoryTotal: "85899345920"
+                      name: NVIDIA A100-SXM4-80GB
+                      uuid: GPU-3790aa64-60ef-9eac-b0b1-b278ee8c0d40
+                host: a100-2gpu-shell-session-9c959f5f-mx8rm
+                memory:
+                    total: "359047892992"
+                os: Linux-6.12.46+-x86_64-with-glibc2.35
+                program: /workspace/SFT/run_instruct.py
+                python: CPython 3.10.12
+                root: runs/instruct_run_14b_v1
+                startedAt: "2025-12-23T14:27:02.029304Z"
+                writerId: x2eg684gxvwjptbq4zszw1o13xocb8ht
+        m:
+            - "1": train/global_step
+              "6":
+                - 3
+              "7": []
+            - "2": '*'
+              "5": 1
+              "6":
+                - 1
+              "7": []
+        python_version: 3.10.12
+        t:
+            "1":
+                - 1
+                - 11
+                - 49
+                - 51
+                - 71
+                - 98
+            "2":
+                - 1
+                - 11
+                - 49
+                - 51
+                - 71
+                - 98
+            "3":
+                - 2
+                - 7
+                - 15
+                - 16
+                - 19
+                - 62
+                - 66
+            "4": 3.10.12
+            "5": 0.23.1
+            "6": 5.0.0.dev0
+            "9":
+                "1": transformers_trainer
+            "12": 0.23.1
+            "13": linux-x86_64
+accelerator_config:
+    value:
+        dispatch_batches: null
+        even_batches: true
+        gradient_accumulation_kwargs: null
+        non_blocking: false
+        split_batches: false
+        use_seedable_sampler: true
+adam_beta1:
+    value: 0.9
+adam_beta2:
+    value: 0.999
+adam_epsilon:
+    value: 1e-08
+add_cross_attention:
+    value: false
+architectures:
+    value:
+        - Qwen2ForCausalLM
+attention_dropout:
+    value: 0
+auto_find_batch_size:
+    value: false
+average_tokens_across_devices:
+    value: true
+batch_eval_metrics:
+    value: false
+bf16:
+    value: true
+bf16_full_eval:
+    value: false
+bos_token_id:
+    value: 151643
+chunk_size_feed_forward:
+    value: 0
+cross_attention_hidden_size:
+    value: null
+data:
+    value:
+        custom_template: |-
+            ##INSTRUCTION
+            {instruction}<|im_end|>
+            ##TASK
+            {input}<|im_end|>
+            ##OUTPUT
+            {output}<|im_end|>
+        eval_jsonl: null
+        eval_split_ratio: 0.1
+        format_type: custom
+        input_field: input
+        instruction_field: instruction
+        max_length: 2048
+        num_proc: 4
+        output_field: output
+        shuffle: true
+        system_prompt: |
+            You are a Hyperswitch Rust code analyzer. Identify functions/structs that need modification for a given task.
+
+            ## Output Format
+
+            ##OUTPUT
+            Explain the data flow and why each component must change:
+            - Flow: [Input → Processing → Output with arrows]
+            - For each component: "The [ComponentName] ([path]) must [action] because [reason]—without this, [consequence]"
+            - Explain coupling between components
+
+            ##SELECT
+            modify::crates/path/to/file.rs::impl::ComponentName
+            add::crates/another/file.rs::function::AnotherComponent
+            <EOS>
+
+            ## Rules
+
+            1. Use full paths: `remove::crates/folder/file.rs::Type::Name`
+            2. Use `::` for nested items: `status::StructName::Type::Name`
+            3. Always explain "must change because" and "without this"
+            3. Types of components: function, struct, enum, impl, trait
+            4. If there is extra information (e.g., enum variants), include that too.
+            5. Start with ##OUTPUT, end with ##SELECT, terminate with <EOS>
+
+            ## Example
+
+            ##TASK
+            Add webhook subscription support
+
+            ##OUTPUT
+            The webhook system routes events via EventClass enum. Flow: webhook → EventClass → handler → processing. The EventClass enum (crates/common_enums/src/enums.rs::EventClass) must add Subscriptions variant because it defines event routing—without this, subscription events cannot be processed. The SubscriptionStatus impl (crates/common_enums/src/transformers.rs::SubscriptionStatus) must map to EventType because it converts status to events—without this, status changes don't trigger webhooks. These are coupled: EventClass routes to handlers that use SubscriptionStatus mappings.
+
+            ##SELECT
+            crates/common_enums/src/enums.rs::EventClass
+            crates/common_enums/src/transformers.rs::SubscriptionStatus
+            <EOS>
+        train_jsonl: sft_dataset.jsonl
+data_seed:
+    value: null
+dataloader_drop_last:
+    value: false
+dataloader_num_workers:
+    value: 0
+dataloader_persistent_workers:
+    value: false
+dataloader_pin_memory:
+    value: true
+dataloader_prefetch_factor:
+    value: null
+ddp_backend:
+    value: null
+ddp_broadcast_buffers:
+    value: null
+ddp_bucket_cap_mb:
+    value: null
+ddp_find_unused_parameters:
+    value: null
+ddp_timeout:
+    value: 1800
+debug:
+    value: []
+decoder_start_token_id:
+    value: null
+deepspeed:
+    value: null
+disable_tqdm:
+    value: false
+do_eval:
+    value: true
+do_predict:
+    value: false
+do_train:
+    value: false
+dtype:
+    value: bfloat16
+enable_jit_checkpoint:
+    value: false
+eos_token_id:
+    value: 151643
+eval_accumulation_steps:
+    value: null
+eval_delay:
+    value: 0
+eval_do_concat_batches:
+    value: true
+eval_on_start:
+    value: false
+eval_steps:
+    value: 100
+eval_strategy:
+    value: steps
+eval_use_gather_object:
+    value: false
+finetuning_task:
+    value: null
+fp16:
+    value: false
+fp16_full_eval:
+    value: false
+fsdp:
+    value: []
+fsdp_config:
+    value:
+        min_num_params: 0
+        xla: false
+        xla_fsdp_grad_ckpt: false
+        xla_fsdp_v2: false
+full_determinism:
+    value: false
+gradient_accumulation_steps:
+    value: 8
+gradient_checkpointing:
+    value: false
+gradient_checkpointing_kwargs:
+    value: null
+greater_is_better:
+    value: false
+group_by_length:
+    value: false
+hidden_act:
+    value: silu
+hidden_size:
+    value: 5120
+hub_always_push:
+    value: false
+hub_model_id:
+    value: null
+hub_private_repo:
+    value: null
+hub_revision:
+    value: null
+hub_strategy:
+    value: every_save
+hub_token:
+    value: <HUB_TOKEN>
+id2label:
+    value:
+        "0": LABEL_0
+        "1": LABEL_1
+ignore_data_skip:
+    value: false
+include_for_metrics:
+    value: []
+include_num_input_tokens_seen:
+    value: "no"
+initializer_range:
+    value: 0.02
+intermediate_size:
+    value: 13824
+is_decoder:
+    value: false
+is_encoder_decoder:
+    value: false
+label_names:
+    value: null
+label_smoothing_factor:
+    value: 0
+label2id:
+    value:
+        LABEL_0: 0
+        LABEL_1: 1
+layer_types:
+    value:
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+        - full_attention
+learning_rate:
+    value: 0.0002
+length_column_name:
+    value: length
+liger_kernel_config:
+    value: null
+load_best_model_at_end:
+    value: true
+local_rank:
+    value: -1
+log_level:
+    value: passive
+log_level_replica:
+    value: warning
+log_on_each_node:
+    value: true
+logging_dir:
+    value: null
+logging_first_step:
+    value: false
+logging_nan_inf_filter:
+    value: true
+logging_steps:
+    value: 2
+logging_strategy:
+    value: steps
+lr_scheduler_kwargs:
+    value: null
+lr_scheduler_type:
+    value: cosine
+max_grad_norm:
+    value: 1
+max_position_embeddings:
+    value: 32768
+max_steps:
+    value: -1
+max_window_layers:
+    value: 48
+metric_for_best_model:
+    value: eval_loss
+model:
+    value:
+        attn_implementation: null
+        base_local_dir: base_model
+        bnb_4bit_compute_dtype: bfloat16
+        bnb_4bit_quant_type: nf4
+        bnb_4bit_use_double_quant: false
+        device_map: auto
+        repo_id: ./runs/cpt_run_14b/merged_14b_cpt_lora
+        revision: null
+        tokenizer_use_fast: true
+        torch_dtype: bfloat16
+        trust_remote_code: true
+        use_4bit: false
+model/num_parameters:
+    value: 14795199488
+model_type:
+    value: qwen2
+neftune_noise_alpha:
+    value: null
+num_attention_heads:
+    value: 40
+num_hidden_layers:
+    value: 48
+num_key_value_heads:
+    value: 8
+num_train_epochs:
+    value: 6
+optim:
+    value: adamw_torch
+optim_args:
+    value: null
+optim_target_modules:
+    value: null
+output_attentions:
+    value: false
+output_dir:
+    value: runs/instruct_run_14b_v1/checkpoints
+output_hidden_states:
+    value: false
+pad_token_id:
+    value: null
+parallelism_config:
+    value: null
+peft:
+    value:
+        bias: none
+        enabled: true
+        lora_alpha: 32
+        lora_dropout: 0.05
+        r: 16
+        target_modules: auto
+peft_config:
+    value:
+        default:
+            alora_invocation_tokens: null
+            arrow_config: null
+            auto_mapping: null
+            base_model_name_or_path: runs/cpt_run_14b/merged_14b_cpt_lora
+            bias: none
+            corda_config: null
+            ensure_weight_tying: false
+            eva_config: null
+            exclude_modules: null
+            fan_in_fan_out: false
+            inference_mode: false
+            init_lora_weights: true
+            layer_replication: null
+            layers_pattern: null
+            layers_to_transform: null
+            lora_alpha: 32
+            lora_bias: false
+            lora_dropout: 0.05
+            megatron_config: null
+            megatron_core: megatron.core
+            modules_to_save: null
+            peft_type: LORA
+            peft_version: 0.18.0
+            qalora_group_size: 16
+            r: 16
+            revision: null
+            runtime_config:
+                ephemeral_gpu_offload: false
+            target_modules:
+                - q_proj
+                - o_proj
+                - v_proj
+                - k_proj
+            target_parameters: null
+            task_type: CAUSAL_LM
+            trainable_token_indices: null
+            use_dora: false
+            use_qalora: false
+            use_rslora: false
+per_device_eval_batch_size:
+    value: 1
+per_device_train_batch_size:
+    value: 1
+prediction_loss_only:
+    value: false
+prefix:
+    value: null
+problem_type:
+    value: null
+project:
+    value: huggingface
+push_to_hub:
+    value: false
+remove_unused_columns:
+    value: false
+report_to:
+    value:
+        - wandb
+restore_callback_states_from_checkpoint:
+    value: false
+resume_from_checkpoint:
+    value: null
+return_dict:
+    value: true
+rms_norm_eps:
+    value: 1e-06
+rope_parameters:
+    value:
+        rope_theta: 1e+06
+        rope_type: default
+run_dir:
+    value: runs/instruct_run_14b_v1
+run_name:
+    value: null
+save_on_each_node:
+    value: false
+save_only_model:
+    value: false
+save_steps:
+    value: 500
+save_strategy:
+    value: steps
+save_total_limit:
+    value: 20
+seed:
+    value: 42
+sep_token_id:
+    value: null
+skip_memory_metrics:
+    value: true
+sliding_window:
+    value: null
+task_specific_params:
+    value: null
+tf32:
+    value: null
+tie_word_embeddings:
+    value: false
+tokenizer_class:
+    value: null
+torch_compile:
+    value: false
+torch_compile_backend:
+    value: null
+torch_compile_mode:
+    value: null
+torch_empty_cache_steps:
+    value: null
+trackio_space_id:
+    value: trackio
+train:
+    value:
+        early_stopping:
+            enabled: true
+            metric: eval_loss
+            min_delta: 0.001
+            mode: min
+            patience: 3
+        eval_steps: 100
+        evaluation_strategy: steps
+        gradient_accumulation_steps: 8
+        gradient_checkpointing: true
+        learning_rate: "2e-4"
+        load_best_model_at_end: true
+        logging_steps: 2
+        lr_scheduler_type: cosine
+        max_grad_norm: 1
+        num_train_epochs: 6
+        optim: adamw_torch
+        per_device_eval_batch_size: 1
+        per_device_train_batch_size: 1
+        resume_from_checkpoint: auto
+        save_steps: 500
+        save_strategy: steps
+        save_total_limit: 20
+        warmup_ratio: 0.08
+        weight_decay: 0
+transformers_version:
+    value: 5.0.0.dev0
+use_cache:
+    value: false
+use_cpu:
+    value: false
+use_liger_kernel:
+    value: false
+use_sliding_window:
+    value: false
+vocab_size:
+    value: 152064
+warmup_ratio:
+    value: 0.08
+warmup_steps:
+    value: 0.08
+weight_decay:
+    value: 0
diff --git a/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/files/output.log b/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/files/output.log
new file mode 100644
index 0000000000000000000000000000000000000000..54765c8d1fc55aa2bb154565f21dbe790356caac
--- /dev/null
+++ b/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/files/output.log
@@ -0,0 +1,2518 @@
+Wandb initialized: project='sft-training', name='auto-generated'
+`torch_dtype` is deprecated! Use `dtype` instead!
+Loading weights: 100%|██████████████| 579/579 [00:08<00:00, 64.67it/s, Materializing param=model.norm.weight]
+Formatting train instructions (num_proc=4): 100%|█████████████| 18540/18540 [00:10<00:00, 1730.74 examples/s]
+Formatting eval instructions (num_proc=4): 100%|█████████████████| 2060/2060 [00:10<00:00, 194.51 examples/s]
+Tokenizing and masking train (num_proc=4): 100%|███████████████| 18540/18540 [00:25<00:00, 740.22 examples/s]
+Tokenizing and masking eval (num_proc=4): 100%|██████████████████| 2060/2060 [00:12<00:00, 169.17 examples/s]
+warmup_ratio is deprecated and will be removed in v5.2. Use `warmup_steps` instead.
+Early stopping enabled: patience=3, min_delta=0.001
+Starting instruction fine-tuning...
+                                                                                                             
+{'loss': '1.679', 'grad_norm': '0.3657', 'learning_rate': '1.797e-07', 'epoch': '0.000863'}
+{'loss': '1.685', 'grad_norm': '0.4025', 'learning_rate': '5.391e-07', 'epoch': '0.001726'}
+{'loss': '1.762', 'grad_norm': '0.402', 'learning_rate': '8.985e-07', 'epoch': '0.002589'}
+{'loss': '1.633', 'grad_norm': '0.3541', 'learning_rate': '1.258e-06', 'epoch': '0.003452'}
+{'loss': '1.737', 'grad_norm': '0.3909', 'learning_rate': '1.617e-06', 'epoch': '0.004315'}
+{'loss': '1.696', 'grad_norm': '0.3587', 'learning_rate': '1.977e-06', 'epoch': '0.005178'}
+{'loss': '1.721', 'grad_norm': '0.3276', 'learning_rate': '2.336e-06', 'epoch': '0.006041'}
+{'loss': '1.696', 'grad_norm': '0.4055', 'learning_rate': '2.695e-06', 'epoch': '0.006904'}
+{'loss': '1.729', 'grad_norm': '0.3759', 'learning_rate': '3.055e-06', 'epoch': '0.007767'}
+{'loss': '1.727', 'grad_norm': '0.3345', 'learning_rate': '3.414e-06', 'epoch': '0.00863'}
+{'loss': '1.673', 'grad_norm': '0.3575', 'learning_rate': '3.774e-06', 'epoch': '0.009493'}
+{'loss': '1.652', 'grad_norm': '0.3912', 'learning_rate': '4.133e-06', 'epoch': '0.01036'}
+{'loss': '1.787', 'grad_norm': '0.4712', 'learning_rate': '4.492e-06', 'epoch': '0.01122'}
+{'loss': '1.613', 'grad_norm': '0.3411', 'learning_rate': '4.852e-06', 'epoch': '0.01208'}
+{'loss': '1.786', 'grad_norm': '0.5072', 'learning_rate': '5.211e-06', 'epoch': '0.01294'}
+{'loss': '1.712', 'grad_norm': '0.4205', 'learning_rate': '5.571e-06', 'epoch': '0.01381'}
+{'loss': '1.738', 'grad_norm': '0.4888', 'learning_rate': '5.93e-06', 'epoch': '0.01467'}
+{'loss': '1.558', 'grad_norm': '0.3311', 'learning_rate': '6.289e-06', 'epoch': '0.01553'}
+{'loss': '1.72', 'grad_norm': '0.5179', 'learning_rate': '6.649e-06', 'epoch': '0.0164'}
+{'loss': '1.728', 'grad_norm': '0.471', 'learning_rate': '7.008e-06', 'epoch': '0.01726'}
+{'loss': '1.654', 'grad_norm': '0.5052', 'learning_rate': '7.367e-06', 'epoch': '0.01812'}
+{'loss': '1.709', 'grad_norm': '0.4645', 'learning_rate': '7.727e-06', 'epoch': '0.01899'}
+{'loss': '1.702', 'grad_norm': '0.5185', 'learning_rate': '8.086e-06', 'epoch': '0.01985'}
+{'loss': '1.682', 'grad_norm': '0.4544', 'learning_rate': '8.446e-06', 'epoch': '0.02071'}
+{'loss': '1.577', 'grad_norm': '0.4441', 'learning_rate': '8.805e-06', 'epoch': '0.02157'}
+{'loss': '1.498', 'grad_norm': '0.3409', 'learning_rate': '9.164e-06', 'epoch': '0.02244'}
+{'loss': '1.619', 'grad_norm': '0.421', 'learning_rate': '9.524e-06', 'epoch': '0.0233'}
+{'loss': '1.46', 'grad_norm': '0.3756', 'learning_rate': '9.883e-06', 'epoch': '0.02416'}
+{'loss': '1.504', 'grad_norm': '0.3621', 'learning_rate': '1.024e-05', 'epoch': '0.02503'}
+{'loss': '1.591', 'grad_norm': '0.4089', 'learning_rate': '1.06e-05', 'epoch': '0.02589'}
+{'loss': '1.296', 'grad_norm': '0.2871', 'learning_rate': '1.096e-05', 'epoch': '0.02675'}
+{'loss': '1.465', 'grad_norm': '0.3046', 'learning_rate': '1.132e-05', 'epoch': '0.02762'}
+{'loss': '1.608', 'grad_norm': '0.3652', 'learning_rate': '1.168e-05', 'epoch': '0.02848'}
+{'loss': '1.597', 'grad_norm': '0.3793', 'learning_rate': '1.204e-05', 'epoch': '0.02934'}
+{'loss': '1.431', 'grad_norm': '0.3054', 'learning_rate': '1.24e-05', 'epoch': '0.0302'}
+{'loss': '1.41', 'grad_norm': '0.3029', 'learning_rate': '1.276e-05', 'epoch': '0.03107'}
+{'loss': '1.455', 'grad_norm': '0.2965', 'learning_rate': '1.312e-05', 'epoch': '0.03193'}
+{'loss': '1.462', 'grad_norm': '0.2603', 'learning_rate': '1.348e-05', 'epoch': '0.03279'}
+{'loss': '1.518', 'grad_norm': '0.3356', 'learning_rate': '1.384e-05', 'epoch': '0.03366'}
+{'loss': '1.44', 'grad_norm': '0.2831', 'learning_rate': '1.42e-05', 'epoch': '0.03452'}
+{'loss': '1.464', 'grad_norm': '0.3452', 'learning_rate': '1.456e-05', 'epoch': '0.03538'}
+{'loss': '1.355', 'grad_norm': '0.3249', 'learning_rate': '1.491e-05', 'epoch': '0.03625'}
+{'loss': '1.281', 'grad_norm': '0.2855', 'learning_rate': '1.527e-05', 'epoch': '0.03711'}
+{'loss': '1.428', 'grad_norm': '0.3337', 'learning_rate': '1.563e-05', 'epoch': '0.03797'}
+{'loss': '1.349', 'grad_norm': '0.341', 'learning_rate': '1.599e-05', 'epoch': '0.03883'}
+{'loss': '1.301', 'grad_norm': '0.3925', 'learning_rate': '1.635e-05', 'epoch': '0.0397'}
+{'loss': '1.292', 'grad_norm': '0.3269', 'learning_rate': '1.671e-05', 'epoch': '0.04056'}
+{'loss': '1.5', 'grad_norm': '0.4345', 'learning_rate': '1.707e-05', 'epoch': '0.04142'}
+{'loss': '1.33', 'grad_norm': '0.3252', 'learning_rate': '1.743e-05', 'epoch': '0.04229'}
+{'loss': '1.305', 'grad_norm': '0.3198', 'learning_rate': '1.779e-05', 'epoch': '0.04315'}
+                                                                                                             
+{'eval_loss': '1.367', 'eval_runtime': '651.8', 'eval_samples_per_second': '3.16', 'eval_steps_per_second': '3.16', 'epoch': '0.04315'}
+{'loss': '1.314', 'grad_norm': '0.3736', 'learning_rate': '1.815e-05', 'epoch': '0.04401'}
+{'loss': '1.274', 'grad_norm': '0.3938', 'learning_rate': '1.851e-05', 'epoch': '0.04488'}
+{'loss': '1.311', 'grad_norm': '0.3522', 'learning_rate': '1.887e-05', 'epoch': '0.04574'}
+{'loss': '1.325', 'grad_norm': '0.3353', 'learning_rate': '1.923e-05', 'epoch': '0.0466'}
+{'loss': '1.324', 'grad_norm': '0.356', 'learning_rate': '1.959e-05', 'epoch': '0.04746'}
+{'loss': '1.183', 'grad_norm': '0.3603', 'learning_rate': '1.995e-05', 'epoch': '0.04833'}
+{'loss': '1.274', 'grad_norm': '0.4211', 'learning_rate': '2.031e-05', 'epoch': '0.04919'}
+{'loss': '1.305', 'grad_norm': '0.3968', 'learning_rate': '2.066e-05', 'epoch': '0.05005'}
+{'loss': '1.247', 'grad_norm': '0.4414', 'learning_rate': '2.102e-05', 'epoch': '0.05092'}
+{'loss': '1.334', 'grad_norm': '0.4287', 'learning_rate': '2.138e-05', 'epoch': '0.05178'}
+{'loss': '1.323', 'grad_norm': '0.3834', 'learning_rate': '2.174e-05', 'epoch': '0.05264'}
+{'loss': '1.217', 'grad_norm': '0.4105', 'learning_rate': '2.21e-05', 'epoch': '0.05351'}
+{'loss': '1.209', 'grad_norm': '0.3946', 'learning_rate': '2.246e-05', 'epoch': '0.05437'}
+{'loss': '1.297', 'grad_norm': '0.4283', 'learning_rate': '2.282e-05', 'epoch': '0.05523'}
+{'loss': '1.189', 'grad_norm': '0.3941', 'learning_rate': '2.318e-05', 'epoch': '0.05609'}
+{'loss': '1.208', 'grad_norm': '0.4501', 'learning_rate': '2.354e-05', 'epoch': '0.05696'}
+{'loss': '1.239', 'grad_norm': '0.4606', 'learning_rate': '2.39e-05', 'epoch': '0.05782'}
+{'loss': '1.194', 'grad_norm': '0.4109', 'learning_rate': '2.426e-05', 'epoch': '0.05868'}
+{'loss': '1.151', 'grad_norm': '0.4024', 'learning_rate': '2.462e-05', 'epoch': '0.05955'}
+{'loss': '1.163', 'grad_norm': '0.3894', 'learning_rate': '2.498e-05', 'epoch': '0.06041'}
+{'loss': '1.163', 'grad_norm': '0.4456', 'learning_rate': '2.534e-05', 'epoch': '0.06127'}
+{'loss': '1.304', 'grad_norm': '0.505', 'learning_rate': '2.57e-05', 'epoch': '0.06214'}
+{'loss': '1.171', 'grad_norm': '0.4071', 'learning_rate': '2.606e-05', 'epoch': '0.063'}
+{'loss': '1.215', 'grad_norm': '0.4363', 'learning_rate': '2.642e-05', 'epoch': '0.06386'}
+{'loss': '1.194', 'grad_norm': '0.4437', 'learning_rate': '2.677e-05', 'epoch': '0.06472'}
+{'loss': '1.18', 'grad_norm': '0.4069', 'learning_rate': '2.713e-05', 'epoch': '0.06559'}
+{'loss': '1.183', 'grad_norm': '0.5291', 'learning_rate': '2.749e-05', 'epoch': '0.06645'}
+{'loss': '1.17', 'grad_norm': '0.441', 'learning_rate': '2.785e-05', 'epoch': '0.06731'}
+{'loss': '1.204', 'grad_norm': '0.4858', 'learning_rate': '2.821e-05', 'epoch': '0.06818'}
+{'loss': '1.115', 'grad_norm': '0.4537', 'learning_rate': '2.857e-05', 'epoch': '0.06904'}
+{'loss': '1.174', 'grad_norm': '0.4881', 'learning_rate': '2.893e-05', 'epoch': '0.0699'}
+{'loss': '1.25', 'grad_norm': '0.5769', 'learning_rate': '2.929e-05', 'epoch': '0.07077'}
+{'loss': '1.072', 'grad_norm': '0.49', 'learning_rate': '2.965e-05', 'epoch': '0.07163'}
+{'loss': '1.069', 'grad_norm': '0.444', 'learning_rate': '3.001e-05', 'epoch': '0.07249'}
+{'loss': '1.21', 'grad_norm': '0.4267', 'learning_rate': '3.037e-05', 'epoch': '0.07335'}
+{'loss': '1.078', 'grad_norm': '0.6063', 'learning_rate': '3.073e-05', 'epoch': '0.07422'}
+{'loss': '1.144', 'grad_norm': '0.4951', 'learning_rate': '3.109e-05', 'epoch': '0.07508'}
+{'loss': '1.166', 'grad_norm': '0.4671', 'learning_rate': '3.145e-05', 'epoch': '0.07594'}
+{'loss': '1.167', 'grad_norm': '0.5615', 'learning_rate': '3.181e-05', 'epoch': '0.07681'}
+{'loss': '1.134', 'grad_norm': '0.4731', 'learning_rate': '3.217e-05', 'epoch': '0.07767'}
+{'loss': '1.073', 'grad_norm': '0.5127', 'learning_rate': '3.252e-05', 'epoch': '0.07853'}
+{'loss': '1.158', 'grad_norm': '0.6324', 'learning_rate': '3.288e-05', 'epoch': '0.0794'}
+{'loss': '1.119', 'grad_norm': '0.4041', 'learning_rate': '3.324e-05', 'epoch': '0.08026'}
+{'loss': '1.147', 'grad_norm': '0.5239', 'learning_rate': '3.36e-05', 'epoch': '0.08112'}
+{'loss': '1.002', 'grad_norm': '0.4487', 'learning_rate': '3.396e-05', 'epoch': '0.08198'}
+{'loss': '1.19', 'grad_norm': '0.4994', 'learning_rate': '3.432e-05', 'epoch': '0.08285'}
+{'loss': '1.14', 'grad_norm': '0.5024', 'learning_rate': '3.468e-05', 'epoch': '0.08371'}
+{'loss': '1.139', 'grad_norm': '0.5078', 'learning_rate': '3.504e-05', 'epoch': '0.08457'}
+{'loss': '1.141', 'grad_norm': '0.5528', 'learning_rate': '3.54e-05', 'epoch': '0.08544'}
+{'loss': '1.071', 'grad_norm': '0.5572', 'learning_rate': '3.576e-05', 'epoch': '0.0863'}
+{'eval_loss': '1.152', 'eval_runtime': '654.6', 'eval_samples_per_second': '3.147', 'eval_steps_per_second': '3.147', 'epoch': '0.0863'}
+{'loss': '1.138', 'grad_norm': '0.5134', 'learning_rate': '3.612e-05', 'epoch': '0.08716'}
+{'loss': '1.112', 'grad_norm': '0.5166', 'learning_rate': '3.648e-05', 'epoch': '0.08803'}
+{'loss': '1.103', 'grad_norm': '0.5337', 'learning_rate': '3.684e-05', 'epoch': '0.08889'}
+{'loss': '1.039', 'grad_norm': '0.829', 'learning_rate': '3.72e-05', 'epoch': '0.08975'}
+{'loss': '1.095', 'grad_norm': '0.4799', 'learning_rate': '3.756e-05', 'epoch': '0.09061'}
+{'loss': '1.036', 'grad_norm': '0.563', 'learning_rate': '3.792e-05', 'epoch': '0.09148'}
+{'loss': '1.092', 'grad_norm': '0.5515', 'learning_rate': '3.827e-05', 'epoch': '0.09234'}
+{'loss': '1.087', 'grad_norm': '0.5079', 'learning_rate': '3.863e-05', 'epoch': '0.0932'}
+{'loss': '1.123', 'grad_norm': '0.6046', 'learning_rate': '3.899e-05', 'epoch': '0.09407'}
+{'loss': '1.099', 'grad_norm': '0.6256', 'learning_rate': '3.935e-05', 'epoch': '0.09493'}
+{'loss': '1.056', 'grad_norm': '0.6037', 'learning_rate': '3.971e-05', 'epoch': '0.09579'}
+{'loss': '1.047', 'grad_norm': '0.5521', 'learning_rate': '4.007e-05', 'epoch': '0.09666'}
+{'loss': '1.179', 'grad_norm': '0.5959', 'learning_rate': '4.043e-05', 'epoch': '0.09752'}
+{'loss': '1.104', 'grad_norm': '0.5283', 'learning_rate': '4.079e-05', 'epoch': '0.09838'}
+{'loss': '1.09', 'grad_norm': '0.5609', 'learning_rate': '4.115e-05', 'epoch': '0.09924'}
+{'loss': '0.9887', 'grad_norm': '0.556', 'learning_rate': '4.151e-05', 'epoch': '0.1001'}
+{'loss': '1.13', 'grad_norm': '0.5876', 'learning_rate': '4.187e-05', 'epoch': '0.101'}
+{'loss': '1.096', 'grad_norm': '0.4545', 'learning_rate': '4.223e-05', 'epoch': '0.1018'}
+{'loss': '1.033', 'grad_norm': '0.5641', 'learning_rate': '4.259e-05', 'epoch': '0.1027'}
+{'loss': '1.109', 'grad_norm': '0.6286', 'learning_rate': '4.295e-05', 'epoch': '0.1036'}
+{'loss': '1.129', 'grad_norm': '0.6442', 'learning_rate': '4.331e-05', 'epoch': '0.1044'}
+{'loss': '1.176', 'grad_norm': '0.6137', 'learning_rate': '4.367e-05', 'epoch': '0.1053'}
+{'loss': '1.148', 'grad_norm': '0.5907', 'learning_rate': '4.403e-05', 'epoch': '0.1061'}
+{'loss': '1.075', 'grad_norm': '0.5383', 'learning_rate': '4.438e-05', 'epoch': '0.107'}
+{'loss': '1.224', 'grad_norm': '0.6185', 'learning_rate': '4.474e-05', 'epoch': '0.1079'}
+{'loss': '1.139', 'grad_norm': '0.5982', 'learning_rate': '4.51e-05', 'epoch': '0.1087'}
+{'loss': '1.172', 'grad_norm': '0.5665', 'learning_rate': '4.546e-05', 'epoch': '0.1096'}
+{'loss': '1.17', 'grad_norm': '0.7072', 'learning_rate': '4.582e-05', 'epoch': '0.1105'}
+{'loss': '1.062', 'grad_norm': '0.5816', 'learning_rate': '4.618e-05', 'epoch': '0.1113'}
+{'loss': '1.082', 'grad_norm': '0.6482', 'learning_rate': '4.654e-05', 'epoch': '0.1122'}
+{'loss': '1.088', 'grad_norm': '0.5989', 'learning_rate': '4.69e-05', 'epoch': '0.1131'}
+{'loss': '1.094', 'grad_norm': '0.6545', 'learning_rate': '4.726e-05', 'epoch': '0.1139'}
+{'loss': '1.043', 'grad_norm': '0.5826', 'learning_rate': '4.762e-05', 'epoch': '0.1148'}
+{'loss': '1.072', 'grad_norm': '0.5908', 'learning_rate': '4.798e-05', 'epoch': '0.1156'}
+{'loss': '1.023', 'grad_norm': '0.5244', 'learning_rate': '4.834e-05', 'epoch': '0.1165'}
+{'loss': '0.9906', 'grad_norm': '0.5473', 'learning_rate': '4.87e-05', 'epoch': '0.1174'}
+{'loss': '1.214', 'grad_norm': '0.7279', 'learning_rate': '4.906e-05', 'epoch': '0.1182'}
+{'loss': '1.005', 'grad_norm': '0.601', 'learning_rate': '4.942e-05', 'epoch': '0.1191'}
+{'loss': '1.108', 'grad_norm': '0.6565', 'learning_rate': '4.978e-05', 'epoch': '0.12'}
+{'loss': '0.9701', 'grad_norm': '0.6501', 'learning_rate': '5.013e-05', 'epoch': '0.1208'}
+{'loss': '1.038', 'grad_norm': '0.5773', 'learning_rate': '5.049e-05', 'epoch': '0.1217'}
+{'loss': '1.106', 'grad_norm': '0.7293', 'learning_rate': '5.085e-05', 'epoch': '0.1225'}
+{'loss': '1.128', 'grad_norm': '0.7937', 'learning_rate': '5.121e-05', 'epoch': '0.1234'}
+{'loss': '0.9439', 'grad_norm': '0.485', 'learning_rate': '5.157e-05', 'epoch': '0.1243'}
+{'loss': '1.087', 'grad_norm': '0.6011', 'learning_rate': '5.193e-05', 'epoch': '0.1251'}
+{'loss': '1.111', 'grad_norm': '0.6241', 'learning_rate': '5.229e-05', 'epoch': '0.126'}
+{'loss': '1.111', 'grad_norm': '0.7173', 'learning_rate': '5.265e-05', 'epoch': '0.1269'}
+{'loss': '1.056', 'grad_norm': '0.6442', 'learning_rate': '5.301e-05', 'epoch': '0.1277'}
+{'loss': '1.072', 'grad_norm': '0.7075', 'learning_rate': '5.337e-05', 'epoch': '0.1286'}
+{'loss': '0.9778', 'grad_norm': '0.5278', 'learning_rate': '5.373e-05', 'epoch': '0.1294'}
+{'eval_loss': '1.098', 'eval_runtime': '662.2', 'eval_samples_per_second': '3.111', 'eval_steps_per_second': '3.111', 'epoch': '0.1294'}
+{'loss': '1.076', 'grad_norm': '0.7252', 'learning_rate': '5.409e-05', 'epoch': '0.1303'}
+{'loss': '1.112', 'grad_norm': '0.7003', 'learning_rate': '5.445e-05', 'epoch': '0.1312'}
+{'loss': '1.029', 'grad_norm': '0.5878', 'learning_rate': '5.481e-05', 'epoch': '0.132'}
+{'loss': '1.02', 'grad_norm': '0.7134', 'learning_rate': '5.517e-05', 'epoch': '0.1329'}
+{'loss': '1.013', 'grad_norm': '0.6098', 'learning_rate': '5.553e-05', 'epoch': '0.1338'}
+{'loss': '1.16', 'grad_norm': '0.6387', 'learning_rate': '5.588e-05', 'epoch': '0.1346'}
+{'loss': '1.092', 'grad_norm': '0.6563', 'learning_rate': '5.624e-05', 'epoch': '0.1355'}
+{'loss': '1.02', 'grad_norm': '0.6388', 'learning_rate': '5.66e-05', 'epoch': '0.1364'}
+{'loss': '0.9339', 'grad_norm': '0.6026', 'learning_rate': '5.696e-05', 'epoch': '0.1372'}
+{'loss': '1.027', 'grad_norm': '0.6198', 'learning_rate': '5.732e-05', 'epoch': '0.1381'}
+{'loss': '1.139', 'grad_norm': '0.5925', 'learning_rate': '5.768e-05', 'epoch': '0.1389'}
+{'loss': '1.002', 'grad_norm': '0.6829', 'learning_rate': '5.804e-05', 'epoch': '0.1398'}
+{'loss': '1.133', 'grad_norm': '0.7013', 'learning_rate': '5.84e-05', 'epoch': '0.1407'}
+{'loss': '1.186', 'grad_norm': '0.7922', 'learning_rate': '5.876e-05', 'epoch': '0.1415'}
+{'loss': '1.09', 'grad_norm': '0.6373', 'learning_rate': '5.912e-05', 'epoch': '0.1424'}
+{'loss': '1.069', 'grad_norm': '0.6174', 'learning_rate': '5.948e-05', 'epoch': '0.1433'}
+{'loss': '1.014', 'grad_norm': '0.5111', 'learning_rate': '5.984e-05', 'epoch': '0.1441'}
+{'loss': '0.9955', 'grad_norm': '0.5581', 'learning_rate': '6.02e-05', 'epoch': '0.145'}
+{'loss': '0.9863', 'grad_norm': '0.6427', 'learning_rate': '6.056e-05', 'epoch': '0.1458'}
+{'loss': '1.068', 'grad_norm': '0.7465', 'learning_rate': '6.092e-05', 'epoch': '0.1467'}
+{'loss': '1.034', 'grad_norm': '0.5999', 'learning_rate': '6.128e-05', 'epoch': '0.1476'}
+{'loss': '1.078', 'grad_norm': '0.632', 'learning_rate': '6.164e-05', 'epoch': '0.1484'}
+{'loss': '1.049', 'grad_norm': '0.6565', 'learning_rate': '6.199e-05', 'epoch': '0.1493'}
+{'loss': '1.047', 'grad_norm': '0.6512', 'learning_rate': '6.235e-05', 'epoch': '0.1502'}
+{'loss': '1.099', 'grad_norm': '0.8487', 'learning_rate': '6.271e-05', 'epoch': '0.151'}
+{'loss': '1.071', 'grad_norm': '0.6719', 'learning_rate': '6.307e-05', 'epoch': '0.1519'}
+{'loss': '1.06', 'grad_norm': '0.8175', 'learning_rate': '6.343e-05', 'epoch': '0.1528'}
+{'loss': '0.9268', 'grad_norm': '0.6359', 'learning_rate': '6.379e-05', 'epoch': '0.1536'}
+{'loss': '0.9838', 'grad_norm': '0.6424', 'learning_rate': '6.415e-05', 'epoch': '0.1545'}
+{'loss': '1.049', 'grad_norm': '0.6497', 'learning_rate': '6.451e-05', 'epoch': '0.1553'}
+{'loss': '1.091', 'grad_norm': '0.6537', 'learning_rate': '6.487e-05', 'epoch': '0.1562'}
+{'loss': '0.9971', 'grad_norm': '0.5832', 'learning_rate': '6.523e-05', 'epoch': '0.1571'}
+{'loss': '1.05', 'grad_norm': '0.6648', 'learning_rate': '6.559e-05', 'epoch': '0.1579'}
+{'loss': '0.9559', 'grad_norm': '0.6233', 'learning_rate': '6.595e-05', 'epoch': '0.1588'}
+{'loss': '1.13', 'grad_norm': '0.6312', 'learning_rate': '6.631e-05', 'epoch': '0.1597'}
+{'loss': '0.8746', 'grad_norm': '0.5306', 'learning_rate': '6.667e-05', 'epoch': '0.1605'}
+{'loss': '0.9105', 'grad_norm': '0.625', 'learning_rate': '6.703e-05', 'epoch': '0.1614'}
+{'loss': '1.044', 'grad_norm': '0.6243', 'learning_rate': '6.739e-05', 'epoch': '0.1622'}
+{'loss': '1.05', 'grad_norm': '0.6833', 'learning_rate': '6.774e-05', 'epoch': '0.1631'}
+{'loss': '1.061', 'grad_norm': '0.7124', 'learning_rate': '6.81e-05', 'epoch': '0.164'}
+{'loss': '1.165', 'grad_norm': '0.7521', 'learning_rate': '6.846e-05', 'epoch': '0.1648'}
+{'loss': '1.063', 'grad_norm': '0.7122', 'learning_rate': '6.882e-05', 'epoch': '0.1657'}
+{'loss': '1.012', 'grad_norm': '0.6825', 'learning_rate': '6.918e-05', 'epoch': '0.1666'}
+{'loss': '1.058', 'grad_norm': '0.4923', 'learning_rate': '6.954e-05', 'epoch': '0.1674'}
+{'loss': '1.039', 'grad_norm': '0.6122', 'learning_rate': '6.99e-05', 'epoch': '0.1683'}
+{'loss': '1.176', 'grad_norm': '0.6349', 'learning_rate': '7.026e-05', 'epoch': '0.1691'}
+{'loss': '0.9096', 'grad_norm': '0.6206', 'learning_rate': '7.062e-05', 'epoch': '0.17'}
+{'loss': '1.083', 'grad_norm': '0.6151', 'learning_rate': '7.098e-05', 'epoch': '0.1709'}
+{'loss': '1.072', 'grad_norm': '0.6482', 'learning_rate': '7.134e-05', 'epoch': '0.1717'}
+{'loss': '0.9617', 'grad_norm': '0.4871', 'learning_rate': '7.17e-05', 'epoch': '0.1726'}
+{'eval_loss': '1.065', 'eval_runtime': '668.6', 'eval_samples_per_second': '3.081', 'eval_steps_per_second': '3.081', 'epoch': '0.1726'}
+{'loss': '1.048', 'grad_norm': '0.568', 'learning_rate': '7.206e-05', 'epoch': '0.1735'}
+{'loss': '0.9851', 'grad_norm': '0.6418', 'learning_rate': '7.242e-05', 'epoch': '0.1743'}
+{'loss': '1.013', 'grad_norm': '0.66', 'learning_rate': '7.278e-05', 'epoch': '0.1752'}
+{'loss': '0.9347', 'grad_norm': '0.6734', 'learning_rate': '7.314e-05', 'epoch': '0.1761'}
+{'loss': '0.989', 'grad_norm': '0.6812', 'learning_rate': '7.35e-05', 'epoch': '0.1769'}
+{'loss': '0.8788', 'grad_norm': '0.638', 'learning_rate': '7.385e-05', 'epoch': '0.1778'}
+{'loss': '1.024', 'grad_norm': '0.6005', 'learning_rate': '7.421e-05', 'epoch': '0.1786'}
+{'loss': '0.9972', 'grad_norm': '0.6569', 'learning_rate': '7.457e-05', 'epoch': '0.1795'}
+{'loss': '0.9594', 'grad_norm': '0.6762', 'learning_rate': '7.493e-05', 'epoch': '0.1804'}
+{'loss': '1.043', 'grad_norm': '0.7329', 'learning_rate': '7.529e-05', 'epoch': '0.1812'}
+{'loss': '0.9608', 'grad_norm': '0.6256', 'learning_rate': '7.565e-05', 'epoch': '0.1821'}
+{'loss': '1.016', 'grad_norm': '1.255', 'learning_rate': '7.601e-05', 'epoch': '0.183'}
+{'loss': '1.131', 'grad_norm': '0.6752', 'learning_rate': '7.637e-05', 'epoch': '0.1838'}
+{'loss': '1.038', 'grad_norm': '0.703', 'learning_rate': '7.673e-05', 'epoch': '0.1847'}
+{'loss': '1.017', 'grad_norm': '0.6444', 'learning_rate': '7.709e-05', 'epoch': '0.1855'}
+{'loss': '1.005', 'grad_norm': '0.6785', 'learning_rate': '7.745e-05', 'epoch': '0.1864'}
+{'loss': '1.027', 'grad_norm': '0.5989', 'learning_rate': '7.781e-05', 'epoch': '0.1873'}
+{'loss': '0.9891', 'grad_norm': '0.6503', 'learning_rate': '7.817e-05', 'epoch': '0.1881'}
+{'loss': '0.9663', 'grad_norm': '0.6176', 'learning_rate': '7.853e-05', 'epoch': '0.189'}
+{'loss': '1.123', 'grad_norm': '0.6802', 'learning_rate': '7.889e-05', 'epoch': '0.1899'}
+{'loss': '1.047', 'grad_norm': '0.6719', 'learning_rate': '7.925e-05', 'epoch': '0.1907'}
+{'loss': '1.095', 'grad_norm': '0.6761', 'learning_rate': '7.96e-05', 'epoch': '0.1916'}
+{'loss': '0.9548', 'grad_norm': '0.6356', 'learning_rate': '7.996e-05', 'epoch': '0.1924'}
+{'loss': '0.9941', 'grad_norm': '0.6799', 'learning_rate': '8.032e-05', 'epoch': '0.1933'}
+{'loss': '1.035', 'grad_norm': '0.6511', 'learning_rate': '8.068e-05', 'epoch': '0.1942'}
+{'loss': '1.005', 'grad_norm': '0.6061', 'learning_rate': '8.104e-05', 'epoch': '0.195'}
+{'loss': '1.078', 'grad_norm': '0.6279', 'learning_rate': '8.14e-05', 'epoch': '0.1959'}
+{'loss': '1.034', 'grad_norm': '0.6866', 'learning_rate': '8.176e-05', 'epoch': '0.1968'}
+{'loss': '1.066', 'grad_norm': '0.7338', 'learning_rate': '8.212e-05', 'epoch': '0.1976'}
+{'loss': '0.9665', 'grad_norm': '0.6811', 'learning_rate': '8.248e-05', 'epoch': '0.1985'}
+{'loss': '1.025', 'grad_norm': '0.678', 'learning_rate': '8.284e-05', 'epoch': '0.1994'}
+{'loss': '0.9699', 'grad_norm': '0.6487', 'learning_rate': '8.32e-05', 'epoch': '0.2002'}
+{'loss': '0.954', 'grad_norm': '0.7022', 'learning_rate': '8.356e-05', 'epoch': '0.2011'}
+{'loss': '0.9253', 'grad_norm': '0.5923', 'learning_rate': '8.392e-05', 'epoch': '0.2019'}
+{'loss': '0.9988', 'grad_norm': '0.7077', 'learning_rate': '8.428e-05', 'epoch': '0.2028'}
+{'loss': '1.025', 'grad_norm': '0.6491', 'learning_rate': '8.464e-05', 'epoch': '0.2037'}
+{'loss': '1.058', 'grad_norm': '0.6784', 'learning_rate': '8.5e-05', 'epoch': '0.2045'}
+{'loss': '1.131', 'grad_norm': '0.6453', 'learning_rate': '8.535e-05', 'epoch': '0.2054'}
+{'loss': '1.059', 'grad_norm': '0.7431', 'learning_rate': '8.571e-05', 'epoch': '0.2063'}
+{'loss': '0.9337', 'grad_norm': '0.6098', 'learning_rate': '8.607e-05', 'epoch': '0.2071'}
+{'loss': '0.9089', 'grad_norm': '0.5693', 'learning_rate': '8.643e-05', 'epoch': '0.208'}
+{'loss': '1.073', 'grad_norm': '0.7377', 'learning_rate': '8.679e-05', 'epoch': '0.2088'}
+{'loss': '1.043', 'grad_norm': '0.7399', 'learning_rate': '8.715e-05', 'epoch': '0.2097'}
+{'loss': '0.994', 'grad_norm': '0.6771', 'learning_rate': '8.751e-05', 'epoch': '0.2106'}
+{'loss': '1.012', 'grad_norm': '0.7127', 'learning_rate': '8.787e-05', 'epoch': '0.2114'}
+{'loss': '1.005', 'grad_norm': '0.6664', 'learning_rate': '8.823e-05', 'epoch': '0.2123'}
+{'loss': '1.017', 'grad_norm': '0.6661', 'learning_rate': '8.859e-05', 'epoch': '0.2132'}
+{'loss': '1.147', 'grad_norm': '0.6976', 'learning_rate': '8.895e-05', 'epoch': '0.214'}
+{'loss': '0.962', 'grad_norm': '0.6594', 'learning_rate': '8.931e-05', 'epoch': '0.2149'}
+{'loss': '0.9971', 'grad_norm': '0.7217', 'learning_rate': '8.967e-05', 'epoch': '0.2157'}
+{'eval_loss': '1.042', 'eval_runtime': '659.3', 'eval_samples_per_second': '3.124', 'eval_steps_per_second': '3.124', 'epoch': '0.2157'}
+{'loss': '1.031', 'grad_norm': '0.6188', 'learning_rate': '9.003e-05', 'epoch': '0.2166'}
+{'loss': '1.019', 'grad_norm': '0.6716', 'learning_rate': '9.039e-05', 'epoch': '0.2175'}
+{'loss': '0.9765', 'grad_norm': '0.6791', 'learning_rate': '9.075e-05', 'epoch': '0.2183'}
+{'loss': '0.9488', 'grad_norm': '0.6765', 'learning_rate': '9.111e-05', 'epoch': '0.2192'}
+{'loss': '1.008', 'grad_norm': '0.6211', 'learning_rate': '9.146e-05', 'epoch': '0.2201'}
+{'loss': '1.166', 'grad_norm': '0.7739', 'learning_rate': '9.182e-05', 'epoch': '0.2209'}
+{'loss': '1.033', 'grad_norm': '0.7056', 'learning_rate': '9.218e-05', 'epoch': '0.2218'}
+{'loss': '1.001', 'grad_norm': '0.6079', 'learning_rate': '9.254e-05', 'epoch': '0.2227'}
+{'loss': '0.9422', 'grad_norm': '0.5974', 'learning_rate': '9.29e-05', 'epoch': '0.2235'}
+{'loss': '0.9363', 'grad_norm': '0.5963', 'learning_rate': '9.326e-05', 'epoch': '0.2244'}
+{'loss': '1.054', 'grad_norm': '0.6824', 'learning_rate': '9.362e-05', 'epoch': '0.2252'}
+{'loss': '1.048', 'grad_norm': '0.641', 'learning_rate': '9.398e-05', 'epoch': '0.2261'}
+{'loss': '0.9668', 'grad_norm': '0.6867', 'learning_rate': '9.434e-05', 'epoch': '0.227'}
+{'loss': '1.009', 'grad_norm': '0.5691', 'learning_rate': '9.47e-05', 'epoch': '0.2278'}
+{'loss': '1.082', 'grad_norm': '0.5965', 'learning_rate': '9.506e-05', 'epoch': '0.2287'}
+{'loss': '0.9266', 'grad_norm': '0.6274', 'learning_rate': '9.542e-05', 'epoch': '0.2296'}
+{'loss': '0.9805', 'grad_norm': '0.5862', 'learning_rate': '9.578e-05', 'epoch': '0.2304'}
+{'loss': '0.9628', 'grad_norm': '0.5574', 'learning_rate': '9.614e-05', 'epoch': '0.2313'}
+{'loss': '1.001', 'grad_norm': '0.6705', 'learning_rate': '9.65e-05', 'epoch': '0.2321'}
+{'loss': '0.9568', 'grad_norm': '0.6251', 'learning_rate': '9.686e-05', 'epoch': '0.233'}
+{'loss': '1.032', 'grad_norm': '0.6466', 'learning_rate': '9.721e-05', 'epoch': '0.2339'}
+{'loss': '0.8604', 'grad_norm': '0.5184', 'learning_rate': '9.757e-05', 'epoch': '0.2347'}
+{'loss': '1.037', 'grad_norm': '0.6726', 'learning_rate': '9.793e-05', 'epoch': '0.2356'}
+{'loss': '0.9305', 'grad_norm': '0.5972', 'learning_rate': '9.829e-05', 'epoch': '0.2365'}
+{'loss': '0.9576', 'grad_norm': '0.532', 'learning_rate': '9.865e-05', 'epoch': '0.2373'}
+{'loss': '1.031', 'grad_norm': '0.6503', 'learning_rate': '9.901e-05', 'epoch': '0.2382'}
+{'loss': '1.052', 'grad_norm': '0.6734', 'learning_rate': '9.937e-05', 'epoch': '0.2391'}
+{'loss': '1.019', 'grad_norm': '0.5668', 'learning_rate': '9.973e-05', 'epoch': '0.2399'}
+{'loss': '1.076', 'grad_norm': '0.637', 'learning_rate': '0.0001001', 'epoch': '0.2408'}
+{'loss': '1.041', 'grad_norm': '0.6897', 'learning_rate': '0.0001004', 'epoch': '0.2416'}
+{'loss': '0.987', 'grad_norm': '0.6304', 'learning_rate': '0.0001008', 'epoch': '0.2425'}
+{'loss': '1.02', 'grad_norm': '0.6797', 'learning_rate': '0.0001012', 'epoch': '0.2434'}
+{'loss': '0.9947', 'grad_norm': '0.5994', 'learning_rate': '0.0001015', 'epoch': '0.2442'}
+{'loss': '0.9723', 'grad_norm': '0.637', 'learning_rate': '0.0001019', 'epoch': '0.2451'}
+{'loss': '0.9717', 'grad_norm': '0.6942', 'learning_rate': '0.0001022', 'epoch': '0.246'}
+{'loss': '0.9798', 'grad_norm': '0.5403', 'learning_rate': '0.0001026', 'epoch': '0.2468'}
+{'loss': '0.9854', 'grad_norm': '0.5208', 'learning_rate': '0.000103', 'epoch': '0.2477'}
+{'loss': '1.075', 'grad_norm': '0.6751', 'learning_rate': '0.0001033', 'epoch': '0.2485'}
+{'loss': '0.9274', 'grad_norm': '0.5653', 'learning_rate': '0.0001037', 'epoch': '0.2494'}
+{'loss': '0.9872', 'grad_norm': '0.6859', 'learning_rate': '0.000104', 'epoch': '0.2503'}
+{'loss': '1.004', 'grad_norm': '0.7091', 'learning_rate': '0.0001044', 'epoch': '0.2511'}
+{'loss': '1.011', 'grad_norm': '0.6494', 'learning_rate': '0.0001048', 'epoch': '0.252'}
+{'loss': '1.002', 'grad_norm': '0.6108', 'learning_rate': '0.0001051', 'epoch': '0.2529'}
+{'loss': '0.961', 'grad_norm': '0.6878', 'learning_rate': '0.0001055', 'epoch': '0.2537'}
+{'loss': '0.9725', 'grad_norm': '0.664', 'learning_rate': '0.0001058', 'epoch': '0.2546'}
+{'loss': '0.9907', 'grad_norm': '0.64', 'learning_rate': '0.0001062', 'epoch': '0.2554'}
+{'loss': '0.965', 'grad_norm': '0.6163', 'learning_rate': '0.0001066', 'epoch': '0.2563'}
+{'loss': '1.01', 'grad_norm': '0.6008', 'learning_rate': '0.0001069', 'epoch': '0.2572'}
+{'loss': '0.9102', 'grad_norm': '0.6752', 'learning_rate': '0.0001073', 'epoch': '0.258'}
+{'loss': '1.046', 'grad_norm': '0.6789', 'learning_rate': '0.0001076', 'epoch': '0.2589'}
+{'eval_loss': '1.021', 'eval_runtime': '648.2', 'eval_samples_per_second': '3.178', 'eval_steps_per_second': '3.178', 'epoch': '0.2589'}
+{'loss': '0.9582', 'grad_norm': '0.5661', 'learning_rate': '0.000108', 'epoch': '0.2598'}
+{'loss': '1.076', 'grad_norm': '0.6727', 'learning_rate': '0.0001084', 'epoch': '0.2606'}
+{'loss': '1.043', 'grad_norm': '0.6069', 'learning_rate': '0.0001087', 'epoch': '0.2615'}
+{'loss': '0.9831', 'grad_norm': '0.5732', 'learning_rate': '0.0001091', 'epoch': '0.2624'}
+{'loss': '1.044', 'grad_norm': '0.6778', 'learning_rate': '0.0001094', 'epoch': '0.2632'}
+{'loss': '1', 'grad_norm': '0.6373', 'learning_rate': '0.0001098', 'epoch': '0.2641'}
+{'loss': '1.036', 'grad_norm': '0.6606', 'learning_rate': '0.0001102', 'epoch': '0.2649'}
+{'loss': '0.9403', 'grad_norm': '0.6083', 'learning_rate': '0.0001105', 'epoch': '0.2658'}
+{'loss': '0.9274', 'grad_norm': '0.6319', 'learning_rate': '0.0001109', 'epoch': '0.2667'}
+{'loss': '0.9884', 'grad_norm': '0.6282', 'learning_rate': '0.0001112', 'epoch': '0.2675'}
+{'loss': '1.032', 'grad_norm': '0.5962', 'learning_rate': '0.0001116', 'epoch': '0.2684'}
+{'loss': '0.9776', 'grad_norm': '0.5995', 'learning_rate': '0.0001119', 'epoch': '0.2693'}
+{'loss': '1.011', 'grad_norm': '0.6639', 'learning_rate': '0.0001123', 'epoch': '0.2701'}
+{'loss': '1.055', 'grad_norm': '0.6349', 'learning_rate': '0.0001127', 'epoch': '0.271'}
+{'loss': '1.026', 'grad_norm': '0.593', 'learning_rate': '0.000113', 'epoch': '0.2718'}
+{'loss': '1.03', 'grad_norm': '0.6052', 'learning_rate': '0.0001134', 'epoch': '0.2727'}
+{'loss': '0.9898', 'grad_norm': '0.6495', 'learning_rate': '0.0001137', 'epoch': '0.2736'}
+{'loss': '1.003', 'grad_norm': '0.6006', 'learning_rate': '0.0001141', 'epoch': '0.2744'}
+{'loss': '1.002', 'grad_norm': '0.6478', 'learning_rate': '0.0001145', 'epoch': '0.2753'}
+{'loss': '0.9808', 'grad_norm': '0.5805', 'learning_rate': '0.0001148', 'epoch': '0.2762'}
+{'loss': '0.9842', 'grad_norm': '0.6325', 'learning_rate': '0.0001152', 'epoch': '0.277'}
+{'loss': '0.8902', 'grad_norm': '0.534', 'learning_rate': '0.0001155', 'epoch': '0.2779'}
+{'loss': '0.9019', 'grad_norm': '0.5902', 'learning_rate': '0.0001159', 'epoch': '0.2787'}
+{'loss': '0.9384', 'grad_norm': '0.6666', 'learning_rate': '0.0001163', 'epoch': '0.2796'}
+{'loss': '1.067', 'grad_norm': '0.7', 'learning_rate': '0.0001166', 'epoch': '0.2805'}
+{'loss': '1', 'grad_norm': '0.6637', 'learning_rate': '0.000117', 'epoch': '0.2813'}
+{'loss': '0.945', 'grad_norm': '0.6098', 'learning_rate': '0.0001173', 'epoch': '0.2822'}
+{'loss': '0.9481', 'grad_norm': '0.6131', 'learning_rate': '0.0001177', 'epoch': '0.2831'}
+{'loss': '1.138', 'grad_norm': '0.7091', 'learning_rate': '0.0001181', 'epoch': '0.2839'}
+{'loss': '0.9421', 'grad_norm': '0.6557', 'learning_rate': '0.0001184', 'epoch': '0.2848'}
+{'loss': '0.9727', 'grad_norm': '0.6683', 'learning_rate': '0.0001188', 'epoch': '0.2857'}
+{'loss': '0.8997', 'grad_norm': '0.5225', 'learning_rate': '0.0001191', 'epoch': '0.2865'}
+{'loss': '0.968', 'grad_norm': '0.5914', 'learning_rate': '0.0001195', 'epoch': '0.2874'}
+{'loss': '0.8743', 'grad_norm': '0.6176', 'learning_rate': '0.0001199', 'epoch': '0.2882'}
+{'loss': '0.9742', 'grad_norm': '0.6019', 'learning_rate': '0.0001202', 'epoch': '0.2891'}
+{'loss': '0.9516', 'grad_norm': '0.6081', 'learning_rate': '0.0001206', 'epoch': '0.29'}
+{'loss': '1.123', 'grad_norm': '0.5886', 'learning_rate': '0.0001209', 'epoch': '0.2908'}
+{'loss': '1.011', 'grad_norm': '0.6635', 'learning_rate': '0.0001213', 'epoch': '0.2917'}
+{'loss': '0.9063', 'grad_norm': '0.5805', 'learning_rate': '0.0001217', 'epoch': '0.2926'}
+{'loss': '1.01', 'grad_norm': '0.598', 'learning_rate': '0.000122', 'epoch': '0.2934'}
+{'loss': '1.037', 'grad_norm': '0.6798', 'learning_rate': '0.0001224', 'epoch': '0.2943'}
+{'loss': '0.9758', 'grad_norm': '0.6281', 'learning_rate': '0.0001227', 'epoch': '0.2951'}
+{'loss': '0.9112', 'grad_norm': '0.5116', 'learning_rate': '0.0001231', 'epoch': '0.296'}
+{'loss': '0.8866', 'grad_norm': '0.5782', 'learning_rate': '0.0001235', 'epoch': '0.2969'}
+{'loss': '0.9768', 'grad_norm': '0.6514', 'learning_rate': '0.0001238', 'epoch': '0.2977'}
+{'loss': '0.9992', 'grad_norm': '0.6109', 'learning_rate': '0.0001242', 'epoch': '0.2986'}
+{'loss': '0.9548', 'grad_norm': '0.6599', 'learning_rate': '0.0001245', 'epoch': '0.2995'}
+{'loss': '0.993', 'grad_norm': '0.5633', 'learning_rate': '0.0001249', 'epoch': '0.3003'}
+{'loss': '0.971', 'grad_norm': '0.6099', 'learning_rate': '0.0001252', 'epoch': '0.3012'}
+{'loss': '1.018', 'grad_norm': '0.6197', 'learning_rate': '0.0001256', 'epoch': '0.302'}
+{'eval_loss': '1.003', 'eval_runtime': '655.5', 'eval_samples_per_second': '3.143', 'eval_steps_per_second': '3.143', 'epoch': '0.302'}
+{'loss': '0.9147', 'grad_norm': '0.5817', 'learning_rate': '0.000126', 'epoch': '0.3029'}
+{'loss': '0.9318', 'grad_norm': '0.5977', 'learning_rate': '0.0001263', 'epoch': '0.3038'}
+{'loss': '0.9501', 'grad_norm': '0.639', 'learning_rate': '0.0001267', 'epoch': '0.3046'}
+{'loss': '1.027', 'grad_norm': '0.6486', 'learning_rate': '0.000127', 'epoch': '0.3055'}
+{'loss': '0.9782', 'grad_norm': '0.5802', 'learning_rate': '0.0001274', 'epoch': '0.3064'}
+{'loss': '1.02', 'grad_norm': '0.6359', 'learning_rate': '0.0001278', 'epoch': '0.3072'}
+{'loss': '0.9251', 'grad_norm': '0.5975', 'learning_rate': '0.0001281', 'epoch': '0.3081'}
+{'loss': '0.9888', 'grad_norm': '0.6431', 'learning_rate': '0.0001285', 'epoch': '0.309'}
+{'loss': '0.971', 'grad_norm': '0.6043', 'learning_rate': '0.0001288', 'epoch': '0.3098'}
+{'loss': '1.027', 'grad_norm': '0.5687', 'learning_rate': '0.0001292', 'epoch': '0.3107'}
+{'loss': '0.937', 'grad_norm': '0.5688', 'learning_rate': '0.0001296', 'epoch': '0.3115'}
+{'loss': '0.9536', 'grad_norm': '0.5611', 'learning_rate': '0.0001299', 'epoch': '0.3124'}
+{'loss': '1.019', 'grad_norm': '0.6338', 'learning_rate': '0.0001303', 'epoch': '0.3133'}
+{'loss': '0.9254', 'grad_norm': '0.5366', 'learning_rate': '0.0001306', 'epoch': '0.3141'}
+{'loss': '0.8941', 'grad_norm': '0.5599', 'learning_rate': '0.000131', 'epoch': '0.315'}
+{'loss': '0.9831', 'grad_norm': '0.606', 'learning_rate': '0.0001314', 'epoch': '0.3159'}
+{'loss': '0.9332', 'grad_norm': '0.5596', 'learning_rate': '0.0001317', 'epoch': '0.3167'}
+{'loss': '0.9083', 'grad_norm': '0.5618', 'learning_rate': '0.0001321', 'epoch': '0.3176'}
+{'loss': '1.009', 'grad_norm': '0.6412', 'learning_rate': '0.0001324', 'epoch': '0.3184'}
+{'loss': '0.9598', 'grad_norm': '0.5742', 'learning_rate': '0.0001328', 'epoch': '0.3193'}
+{'loss': '0.9893', 'grad_norm': '0.647', 'learning_rate': '0.0001332', 'epoch': '0.3202'}
+{'loss': '0.8677', 'grad_norm': '0.5598', 'learning_rate': '0.0001335', 'epoch': '0.321'}
+{'loss': '0.9463', 'grad_norm': '0.5441', 'learning_rate': '0.0001339', 'epoch': '0.3219'}
+{'loss': '0.9947', 'grad_norm': '0.5859', 'learning_rate': '0.0001342', 'epoch': '0.3228'}
+{'loss': '0.9387', 'grad_norm': '0.5114', 'learning_rate': '0.0001346', 'epoch': '0.3236'}
+{'loss': '0.9474', 'grad_norm': '0.478', 'learning_rate': '0.000135', 'epoch': '0.3245'}
+{'loss': '0.9375', 'grad_norm': '0.5907', 'learning_rate': '0.0001353', 'epoch': '0.3254'}
+{'loss': '1.029', 'grad_norm': '0.6187', 'learning_rate': '0.0001357', 'epoch': '0.3262'}
+{'loss': '0.942', 'grad_norm': '0.5235', 'learning_rate': '0.000136', 'epoch': '0.3271'}
+{'loss': '1.025', 'grad_norm': '0.7036', 'learning_rate': '0.0001364', 'epoch': '0.3279'}
+{'loss': '0.8454', 'grad_norm': '0.5543', 'learning_rate': '0.0001367', 'epoch': '0.3288'}
+{'loss': '0.866', 'grad_norm': '0.5439', 'learning_rate': '0.0001371', 'epoch': '0.3297'}
+{'loss': '1.038', 'grad_norm': '0.6391', 'learning_rate': '0.0001375', 'epoch': '0.3305'}
+{'loss': '0.8999', 'grad_norm': '0.5007', 'learning_rate': '0.0001378', 'epoch': '0.3314'}
+{'loss': '0.9713', 'grad_norm': '0.5982', 'learning_rate': '0.0001382', 'epoch': '0.3323'}
+{'loss': '0.9428', 'grad_norm': '0.6589', 'learning_rate': '0.0001385', 'epoch': '0.3331'}
+{'loss': '0.8962', 'grad_norm': '0.6022', 'learning_rate': '0.0001389', 'epoch': '0.334'}
+{'loss': '0.9526', 'grad_norm': '0.6596', 'learning_rate': '0.0001393', 'epoch': '0.3348'}
+{'loss': '0.9219', 'grad_norm': '0.521', 'learning_rate': '0.0001396', 'epoch': '0.3357'}
+{'loss': '0.878', 'grad_norm': '0.5497', 'learning_rate': '0.00014', 'epoch': '0.3366'}
+{'loss': '0.867', 'grad_norm': '0.536', 'learning_rate': '0.0001403', 'epoch': '0.3374'}
+{'loss': '0.9561', 'grad_norm': '0.6147', 'learning_rate': '0.0001407', 'epoch': '0.3383'}
+{'loss': '0.9133', 'grad_norm': '0.5798', 'learning_rate': '0.0001411', 'epoch': '0.3392'}
+{'loss': '0.9298', 'grad_norm': '0.6267', 'learning_rate': '0.0001414', 'epoch': '0.34'}
+{'loss': '0.9382', 'grad_norm': '0.6045', 'learning_rate': '0.0001418', 'epoch': '0.3409'}
+{'loss': '0.9079', 'grad_norm': '0.6125', 'learning_rate': '0.0001421', 'epoch': '0.3417'}
+{'loss': '0.8991', 'grad_norm': '0.5927', 'learning_rate': '0.0001425', 'epoch': '0.3426'}
+{'loss': '1.028', 'grad_norm': '0.6316', 'learning_rate': '0.0001429', 'epoch': '0.3435'}
+{'loss': '0.8988', 'grad_norm': '0.5493', 'learning_rate': '0.0001432', 'epoch': '0.3443'}
+{'loss': '1.049', 'grad_norm': '0.6344', 'learning_rate': '0.0001436', 'epoch': '0.3452'}
+{'eval_loss': '0.9865', 'eval_runtime': '667.4', 'eval_samples_per_second': '3.087', 'eval_steps_per_second': '3.087', 'epoch': '0.3452'}
+{'loss': '0.8774', 'grad_norm': '0.5625', 'learning_rate': '0.0001439', 'epoch': '0.3461'}
+{'loss': '0.9116', 'grad_norm': '0.5932', 'learning_rate': '0.0001443', 'epoch': '0.3469'}
+{'loss': '0.9124', 'grad_norm': '0.519', 'learning_rate': '0.0001447', 'epoch': '0.3478'}
+{'loss': '0.9518', 'grad_norm': '0.5392', 'learning_rate': '0.000145', 'epoch': '0.3487'}
+{'loss': '0.9948', 'grad_norm': '0.5584', 'learning_rate': '0.0001454', 'epoch': '0.3495'}
+{'loss': '0.9314', 'grad_norm': '0.5189', 'learning_rate': '0.0001457', 'epoch': '0.3504'}
+{'loss': '0.9136', 'grad_norm': '0.5784', 'learning_rate': '0.0001461', 'epoch': '0.3512'}
+{'loss': '0.9665', 'grad_norm': '0.551', 'learning_rate': '0.0001465', 'epoch': '0.3521'}
+{'loss': '0.9837', 'grad_norm': '0.6013', 'learning_rate': '0.0001468', 'epoch': '0.353'}
+{'loss': '0.89', 'grad_norm': '0.4922', 'learning_rate': '0.0001472', 'epoch': '0.3538'}
+{'loss': '0.8769', 'grad_norm': '0.5517', 'learning_rate': '0.0001475', 'epoch': '0.3547'}
+{'loss': '0.9745', 'grad_norm': '0.6063', 'learning_rate': '0.0001479', 'epoch': '0.3556'}
+{'loss': '0.8875', 'grad_norm': '0.5132', 'learning_rate': '0.0001482', 'epoch': '0.3564'}
+{'loss': '0.9627', 'grad_norm': '0.5518', 'learning_rate': '0.0001486', 'epoch': '0.3573'}
+{'loss': '0.8998', 'grad_norm': '0.6047', 'learning_rate': '0.000149', 'epoch': '0.3581'}
+{'loss': '0.9541', 'grad_norm': '0.56', 'learning_rate': '0.0001493', 'epoch': '0.359'}
+{'loss': '0.9078', 'grad_norm': '0.6441', 'learning_rate': '0.0001497', 'epoch': '0.3599'}
+{'loss': '1.03', 'grad_norm': '0.5636', 'learning_rate': '0.00015', 'epoch': '0.3607'}
+{'loss': '0.8875', 'grad_norm': '0.5528', 'learning_rate': '0.0001504', 'epoch': '0.3616'}
+{'loss': '0.9679', 'grad_norm': '0.5345', 'learning_rate': '0.0001508', 'epoch': '0.3625'}
+{'loss': '0.9235', 'grad_norm': '0.5551', 'learning_rate': '0.0001511', 'epoch': '0.3633'}
+{'loss': '0.8624', 'grad_norm': '0.5132', 'learning_rate': '0.0001515', 'epoch': '0.3642'}
+{'loss': '1.036', 'grad_norm': '0.6811', 'learning_rate': '0.0001518', 'epoch': '0.365'}
+{'loss': '0.9254', 'grad_norm': '0.641', 'learning_rate': '0.0001522', 'epoch': '0.3659'}
+{'loss': '0.8901', 'grad_norm': '0.5534', 'learning_rate': '0.0001526', 'epoch': '0.3668'}
+{'loss': '0.8852', 'grad_norm': '0.4999', 'learning_rate': '0.0001529', 'epoch': '0.3676'}
+{'loss': '0.9564', 'grad_norm': '0.5806', 'learning_rate': '0.0001533', 'epoch': '0.3685'}
+{'loss': '0.8909', 'grad_norm': '0.5485', 'learning_rate': '0.0001536', 'epoch': '0.3694'}
+{'loss': '0.9146', 'grad_norm': '0.5318', 'learning_rate': '0.000154', 'epoch': '0.3702'}
+{'loss': '1.015', 'grad_norm': '0.6073', 'learning_rate': '0.0001544', 'epoch': '0.3711'}
+{'loss': '0.9942', 'grad_norm': '0.5667', 'learning_rate': '0.0001547', 'epoch': '0.372'}
+{'loss': '1.006', 'grad_norm': '0.5262', 'learning_rate': '0.0001551', 'epoch': '0.3728'}
+{'loss': '1.033', 'grad_norm': '0.6264', 'learning_rate': '0.0001554', 'epoch': '0.3737'}
+{'loss': '1.022', 'grad_norm': '0.6575', 'learning_rate': '0.0001558', 'epoch': '0.3745'}
+{'loss': '0.955', 'grad_norm': '0.6292', 'learning_rate': '0.0001562', 'epoch': '0.3754'}
+{'loss': '0.9862', 'grad_norm': '0.6711', 'learning_rate': '0.0001565', 'epoch': '0.3763'}
+{'loss': '0.9719', 'grad_norm': '0.5506', 'learning_rate': '0.0001569', 'epoch': '0.3771'}
+{'loss': '0.8698', 'grad_norm': '0.5055', 'learning_rate': '0.0001572', 'epoch': '0.378'}
+{'loss': '1.029', 'grad_norm': '0.5936', 'learning_rate': '0.0001576', 'epoch': '0.3789'}
+{'loss': '0.923', 'grad_norm': '0.5383', 'learning_rate': '0.000158', 'epoch': '0.3797'}
+{'loss': '0.9394', 'grad_norm': '0.5873', 'learning_rate': '0.0001583', 'epoch': '0.3806'}
+{'loss': '0.9472', 'grad_norm': '0.591', 'learning_rate': '0.0001587', 'epoch': '0.3814'}
+{'loss': '0.9028', 'grad_norm': '0.629', 'learning_rate': '0.000159', 'epoch': '0.3823'}
+{'loss': '0.9579', 'grad_norm': '0.5028', 'learning_rate': '0.0001594', 'epoch': '0.3832'}
+{'loss': '0.8319', 'grad_norm': '0.5372', 'learning_rate': '0.0001597', 'epoch': '0.384'}
+{'loss': '0.9805', 'grad_norm': '0.6314', 'learning_rate': '0.0001601', 'epoch': '0.3849'}
+{'loss': '1.008', 'grad_norm': '0.5545', 'learning_rate': '0.0001605', 'epoch': '0.3858'}
+{'loss': '0.9269', 'grad_norm': '0.4674', 'learning_rate': '0.0001608', 'epoch': '0.3866'}
+{'loss': '0.8928', 'grad_norm': '1.589', 'learning_rate': '0.0001612', 'epoch': '0.3875'}
+{'loss': '0.9081', 'grad_norm': '0.5217', 'learning_rate': '0.0001615', 'epoch': '0.3883'}
+{'eval_loss': '0.9742', 'eval_runtime': '667.2', 'eval_samples_per_second': '3.087', 'eval_steps_per_second': '3.087', 'epoch': '0.3883'}
+{'loss': '0.966', 'grad_norm': '0.4705', 'learning_rate': '0.0001619', 'epoch': '0.3892'}
+{'loss': '0.9236', 'grad_norm': '0.5111', 'learning_rate': '0.0001623', 'epoch': '0.3901'}
+{'loss': '1.006', 'grad_norm': '0.5873', 'learning_rate': '0.0001626', 'epoch': '0.3909'}
+{'loss': '0.8347', 'grad_norm': '0.5151', 'learning_rate': '0.000163', 'epoch': '0.3918'}
+{'loss': '0.9091', 'grad_norm': '0.4655', 'learning_rate': '0.0001633', 'epoch': '0.3927'}
+{'loss': '0.93', 'grad_norm': '0.5293', 'learning_rate': '0.0001637', 'epoch': '0.3935'}
+{'loss': '0.9423', 'grad_norm': '0.5177', 'learning_rate': '0.0001641', 'epoch': '0.3944'}
+{'loss': '0.8253', 'grad_norm': '0.5564', 'learning_rate': '0.0001644', 'epoch': '0.3953'}
+{'loss': '0.8769', 'grad_norm': '0.5573', 'learning_rate': '0.0001648', 'epoch': '0.3961'}
+{'loss': '0.895', 'grad_norm': '0.7295', 'learning_rate': '0.0001651', 'epoch': '0.397'}
+{'loss': '0.8458', 'grad_norm': '0.5234', 'learning_rate': '0.0001655', 'epoch': '0.3978'}
+{'loss': '0.908', 'grad_norm': '0.5274', 'learning_rate': '0.0001659', 'epoch': '0.3987'}
+{'loss': '1.03', 'grad_norm': '0.5795', 'learning_rate': '0.0001662', 'epoch': '0.3996'}
+{'loss': '0.89', 'grad_norm': '0.6153', 'learning_rate': '0.0001666', 'epoch': '0.4004'}
+{'loss': '1.013', 'grad_norm': '0.6293', 'learning_rate': '0.0001669', 'epoch': '0.4013'}
+{'loss': '0.9339', 'grad_norm': '0.5455', 'learning_rate': '0.0001673', 'epoch': '0.4022'}
+{'loss': '0.9629', 'grad_norm': '0.5349', 'learning_rate': '0.0001677', 'epoch': '0.403'}
+{'loss': '0.8923', 'grad_norm': '0.4912', 'learning_rate': '0.000168', 'epoch': '0.4039'}
+{'loss': '1.047', 'grad_norm': '0.6331', 'learning_rate': '0.0001684', 'epoch': '0.4047'}
+{'loss': '0.8868', 'grad_norm': '0.6079', 'learning_rate': '0.0001687', 'epoch': '0.4056'}
+{'loss': '0.9939', 'grad_norm': '0.5327', 'learning_rate': '0.0001691', 'epoch': '0.4065'}
+{'loss': '0.828', 'grad_norm': '0.4775', 'learning_rate': '0.0001695', 'epoch': '0.4073'}
+{'loss': '1.09', 'grad_norm': '0.6683', 'learning_rate': '0.0001698', 'epoch': '0.4082'}
+{'loss': '0.8536', 'grad_norm': '0.428', 'learning_rate': '0.0001702', 'epoch': '0.4091'}
+{'loss': '0.9039', 'grad_norm': '0.6', 'learning_rate': '0.0001705', 'epoch': '0.4099'}
+{'loss': '0.8786', 'grad_norm': '0.5753', 'learning_rate': '0.0001709', 'epoch': '0.4108'}
+{'loss': '0.9206', 'grad_norm': '0.5122', 'learning_rate': '0.0001712', 'epoch': '0.4117'}
+{'loss': '0.9247', 'grad_norm': '0.6111', 'learning_rate': '0.0001716', 'epoch': '0.4125'}
+{'loss': '0.9222', 'grad_norm': '0.5101', 'learning_rate': '0.000172', 'epoch': '0.4134'}
+{'loss': '0.9073', 'grad_norm': '0.5681', 'learning_rate': '0.0001723', 'epoch': '0.4142'}
+{'loss': '0.9461', 'grad_norm': '0.4787', 'learning_rate': '0.0001727', 'epoch': '0.4151'}
+{'loss': '0.9122', 'grad_norm': '0.4986', 'learning_rate': '0.000173', 'epoch': '0.416'}
+{'loss': '0.8827', 'grad_norm': '0.4303', 'learning_rate': '0.0001734', 'epoch': '0.4168'}
+{'loss': '0.8756', 'grad_norm': '0.46', 'learning_rate': '0.0001738', 'epoch': '0.4177'}
+{'loss': '0.9171', 'grad_norm': '0.5298', 'learning_rate': '0.0001741', 'epoch': '0.4186'}
+{'loss': '0.8888', 'grad_norm': '0.4907', 'learning_rate': '0.0001745', 'epoch': '0.4194'}
+{'loss': '0.8346', 'grad_norm': '0.4926', 'learning_rate': '0.0001748', 'epoch': '0.4203'}
+{'loss': '0.9687', 'grad_norm': '0.5707', 'learning_rate': '0.0001752', 'epoch': '0.4211'}
+{'loss': '0.9729', 'grad_norm': '0.527', 'learning_rate': '0.0001756', 'epoch': '0.422'}
+{'loss': '0.9639', 'grad_norm': '0.4706', 'learning_rate': '0.0001759', 'epoch': '0.4229'}
+{'loss': '0.8952', 'grad_norm': '0.5323', 'learning_rate': '0.0001763', 'epoch': '0.4237'}
+{'loss': '0.8933', 'grad_norm': '0.5751', 'learning_rate': '0.0001766', 'epoch': '0.4246'}
+{'loss': '0.9166', 'grad_norm': '0.554', 'learning_rate': '0.000177', 'epoch': '0.4255'}
+{'loss': '0.967', 'grad_norm': '0.568', 'learning_rate': '0.0001774', 'epoch': '0.4263'}
+{'loss': '1.009', 'grad_norm': '0.6011', 'learning_rate': '0.0001777', 'epoch': '0.4272'}
+{'loss': '0.9811', 'grad_norm': '0.6083', 'learning_rate': '0.0001781', 'epoch': '0.428'}
+{'loss': '0.9524', 'grad_norm': '0.5077', 'learning_rate': '0.0001784', 'epoch': '0.4289'}
+{'loss': '0.8813', 'grad_norm': '0.5261', 'learning_rate': '0.0001788', 'epoch': '0.4298'}
+{'loss': '0.9138', 'grad_norm': '0.613', 'learning_rate': '0.0001792', 'epoch': '0.4306'}
+{'loss': '0.8861', 'grad_norm': '0.5346', 'learning_rate': '0.0001795', 'epoch': '0.4315'}
+{'eval_loss': '0.9607', 'eval_runtime': '655.4', 'eval_samples_per_second': '3.143', 'eval_steps_per_second': '3.143', 'epoch': '0.4315'}
+{'loss': '0.8712', 'grad_norm': '0.5977', 'learning_rate': '0.0001799', 'epoch': '0.4324'}
+{'loss': '0.9393', 'grad_norm': '0.5548', 'learning_rate': '0.0001802', 'epoch': '0.4332'}
+{'loss': '0.9486', 'grad_norm': '0.5369', 'learning_rate': '0.0001806', 'epoch': '0.4341'}
+{'loss': '0.9042', 'grad_norm': '0.477', 'learning_rate': '0.000181', 'epoch': '0.435'}
+{'loss': '0.9785', 'grad_norm': '0.5555', 'learning_rate': '0.0001813', 'epoch': '0.4358'}
+{'loss': '0.8382', 'grad_norm': '0.5113', 'learning_rate': '0.0001817', 'epoch': '0.4367'}
+{'loss': '0.8577', 'grad_norm': '0.4519', 'learning_rate': '0.000182', 'epoch': '0.4375'}
+{'loss': '0.8518', 'grad_norm': '0.5115', 'learning_rate': '0.0001824', 'epoch': '0.4384'}
+{'loss': '0.9597', 'grad_norm': '0.5485', 'learning_rate': '0.0001827', 'epoch': '0.4393'}
+{'loss': '1.041', 'grad_norm': '0.5743', 'learning_rate': '0.0001831', 'epoch': '0.4401'}
+{'loss': '0.8696', 'grad_norm': '0.4487', 'learning_rate': '0.0001835', 'epoch': '0.441'}
+{'loss': '0.9674', 'grad_norm': '0.518', 'learning_rate': '0.0001838', 'epoch': '0.4419'}
+{'loss': '0.9597', 'grad_norm': '0.5405', 'learning_rate': '0.0001842', 'epoch': '0.4427'}
+{'loss': '0.8484', 'grad_norm': '0.4777', 'learning_rate': '0.0001845', 'epoch': '0.4436'}
+{'loss': '0.9331', 'grad_norm': '0.5034', 'learning_rate': '0.0001849', 'epoch': '0.4444'}
+{'loss': '0.9341', 'grad_norm': '0.6129', 'learning_rate': '0.0001853', 'epoch': '0.4453'}
+{'loss': '0.9139', 'grad_norm': '0.4498', 'learning_rate': '0.0001856', 'epoch': '0.4462'}
+{'loss': '0.8875', 'grad_norm': '0.537', 'learning_rate': '0.000186', 'epoch': '0.447'}
+{'loss': '0.9654', 'grad_norm': '0.5947', 'learning_rate': '0.0001863', 'epoch': '0.4479'}
+{'loss': '0.9553', 'grad_norm': '0.665', 'learning_rate': '0.0001867', 'epoch': '0.4488'}
+{'loss': '0.9042', 'grad_norm': '0.5369', 'learning_rate': '0.0001871', 'epoch': '0.4496'}
+{'loss': '0.8838', 'grad_norm': '0.4957', 'learning_rate': '0.0001874', 'epoch': '0.4505'}
+{'loss': '0.8965', 'grad_norm': '0.4805', 'learning_rate': '0.0001878', 'epoch': '0.4513'}
+{'loss': '0.9106', 'grad_norm': '0.4926', 'learning_rate': '0.0001881', 'epoch': '0.4522'}
+{'loss': '0.9627', 'grad_norm': '0.5131', 'learning_rate': '0.0001885', 'epoch': '0.4531'}
+{'loss': '0.8797', 'grad_norm': '0.4357', 'learning_rate': '0.0001889', 'epoch': '0.4539'}
+{'loss': '0.9464', 'grad_norm': '0.5009', 'learning_rate': '0.0001892', 'epoch': '0.4548'}
+{'loss': '0.903', 'grad_norm': '0.477', 'learning_rate': '0.0001896', 'epoch': '0.4557'}
+{'loss': '0.987', 'grad_norm': '0.4959', 'learning_rate': '0.0001899', 'epoch': '0.4565'}
+{'loss': '0.9297', 'grad_norm': '0.5875', 'learning_rate': '0.0001903', 'epoch': '0.4574'}
+{'loss': '1.006', 'grad_norm': '0.5553', 'learning_rate': '0.0001907', 'epoch': '0.4583'}
+{'loss': '0.895', 'grad_norm': '0.4928', 'learning_rate': '0.000191', 'epoch': '0.4591'}
+{'loss': '0.9998', 'grad_norm': '0.4952', 'learning_rate': '0.0001914', 'epoch': '0.46'}
+{'loss': '0.9532', 'grad_norm': '0.5155', 'learning_rate': '0.0001917', 'epoch': '0.4608'}
+{'loss': '0.896', 'grad_norm': '0.5548', 'learning_rate': '0.0001921', 'epoch': '0.4617'}
+{'loss': '0.8201', 'grad_norm': '0.5002', 'learning_rate': '0.0001925', 'epoch': '0.4626'}
+{'loss': '0.8255', 'grad_norm': '0.4182', 'learning_rate': '0.0001928', 'epoch': '0.4634'}
+{'loss': '0.896', 'grad_norm': '0.5614', 'learning_rate': '0.0001932', 'epoch': '0.4643'}
+{'loss': '0.8832', 'grad_norm': '0.5001', 'learning_rate': '0.0001935', 'epoch': '0.4652'}
+{'loss': '0.9788', 'grad_norm': '0.6322', 'learning_rate': '0.0001939', 'epoch': '0.466'}
+{'loss': '0.9334', 'grad_norm': '0.4844', 'learning_rate': '0.0001942', 'epoch': '0.4669'}
+{'loss': '0.9047', 'grad_norm': '0.5373', 'learning_rate': '0.0001946', 'epoch': '0.4677'}
+{'loss': '0.9626', 'grad_norm': '0.5761', 'learning_rate': '0.000195', 'epoch': '0.4686'}
+{'loss': '0.9281', 'grad_norm': '0.521', 'learning_rate': '0.0001953', 'epoch': '0.4695'}
+{'loss': '0.8236', 'grad_norm': '0.5384', 'learning_rate': '0.0001957', 'epoch': '0.4703'}
+{'loss': '0.9404', 'grad_norm': '0.4994', 'learning_rate': '0.000196', 'epoch': '0.4712'}
+{'loss': '0.8518', 'grad_norm': '0.5178', 'learning_rate': '0.0001964', 'epoch': '0.4721'}
+{'loss': '0.8214', 'grad_norm': '0.5375', 'learning_rate': '0.0001968', 'epoch': '0.4729'}
+{'loss': '1.016', 'grad_norm': '0.5544', 'learning_rate': '0.0001971', 'epoch': '0.4738'}
+{'loss': '0.8425', 'grad_norm': '0.5126', 'learning_rate': '0.0001975', 'epoch': '0.4746'}
+{'eval_loss': '0.9446', 'eval_runtime': '649.9', 'eval_samples_per_second': '3.17', 'eval_steps_per_second': '3.17', 'epoch': '0.4746'}
+{'loss': '0.9445', 'grad_norm': '0.5204', 'learning_rate': '0.0001978', 'epoch': '0.4755'}
+{'loss': '0.8771', 'grad_norm': '0.4609', 'learning_rate': '0.0001982', 'epoch': '0.4764'}
+{'loss': '0.9215', 'grad_norm': '0.527', 'learning_rate': '0.0001986', 'epoch': '0.4772'}
+{'loss': '0.8867', 'grad_norm': '0.4895', 'learning_rate': '0.0001989', 'epoch': '0.4781'}
+{'loss': '0.9641', 'grad_norm': '0.5204', 'learning_rate': '0.0001993', 'epoch': '0.479'}
+{'loss': '1.022', 'grad_norm': '0.6399', 'learning_rate': '0.0001996', 'epoch': '0.4798'}
+{'loss': '0.819', 'grad_norm': '0.3979', 'learning_rate': '0.0002', 'epoch': '0.4807'}
+{'loss': '0.8324', 'grad_norm': '0.4783', 'learning_rate': '0.0002', 'epoch': '0.4816'}
+{'loss': '0.9371', 'grad_norm': '0.5236', 'learning_rate': '0.0002', 'epoch': '0.4824'}
+{'loss': '0.7768', 'grad_norm': '0.4543', 'learning_rate': '0.0002', 'epoch': '0.4833'}
+{'loss': '1.01', 'grad_norm': '0.6191', 'learning_rate': '0.0002', 'epoch': '0.4841'}
+{'loss': '0.8721', 'grad_norm': '0.4539', 'learning_rate': '0.0002', 'epoch': '0.485'}
+{'loss': '0.7859', 'grad_norm': '0.4275', 'learning_rate': '0.0002', 'epoch': '0.4859'}
+{'loss': '0.9154', 'grad_norm': '0.4953', 'learning_rate': '0.0002', 'epoch': '0.4867'}
+{'loss': '0.9076', 'grad_norm': '0.5522', 'learning_rate': '0.0002', 'epoch': '0.4876'}
+{'loss': '0.8934', 'grad_norm': '0.5356', 'learning_rate': '0.0002', 'epoch': '0.4885'}
+{'loss': '0.9161', 'grad_norm': '0.4613', 'learning_rate': '0.0002', 'epoch': '0.4893'}
+{'loss': '0.8552', 'grad_norm': '0.4759', 'learning_rate': '0.0002', 'epoch': '0.4902'}
+{'loss': '0.998', 'grad_norm': '0.4549', 'learning_rate': '0.0002', 'epoch': '0.491'}
+{'loss': '0.9295', 'grad_norm': '0.4363', 'learning_rate': '0.0002', 'epoch': '0.4919'}
+{'loss': '0.8737', 'grad_norm': '0.5091', 'learning_rate': '0.0002', 'epoch': '0.4928'}
+{'loss': '0.8313', 'grad_norm': '0.4534', 'learning_rate': '0.0002', 'epoch': '0.4936'}
+{'loss': '0.9105', 'grad_norm': '0.4771', 'learning_rate': '0.0002', 'epoch': '0.4945'}
+{'loss': '0.8578', 'grad_norm': '0.5251', 'learning_rate': '0.0002', 'epoch': '0.4954'}
+{'loss': '0.9194', 'grad_norm': '0.4913', 'learning_rate': '0.0002', 'epoch': '0.4962'}
+{'loss': '0.9141', 'grad_norm': '0.5559', 'learning_rate': '0.0002', 'epoch': '0.4971'}
+{'loss': '0.9058', 'grad_norm': '0.4587', 'learning_rate': '0.0002', 'epoch': '0.498'}
+{'loss': '0.8462', 'grad_norm': '0.471', 'learning_rate': '0.0002', 'epoch': '0.4988'}
+{'loss': '0.8961', 'grad_norm': '0.4806', 'learning_rate': '0.0002', 'epoch': '0.4997'}
+{'loss': '0.9075', 'grad_norm': '0.5108', 'learning_rate': '0.0002', 'epoch': '0.5005'}
+{'loss': '0.971', 'grad_norm': '0.4957', 'learning_rate': '0.0002', 'epoch': '0.5014'}
+{'loss': '0.8878', 'grad_norm': '0.5305', 'learning_rate': '0.0002', 'epoch': '0.5023'}
+{'loss': '0.8955', 'grad_norm': '0.5007', 'learning_rate': '0.0002', 'epoch': '0.5031'}
+{'loss': '0.9479', 'grad_norm': '0.5695', 'learning_rate': '0.0002', 'epoch': '0.504'}
+{'loss': '0.9685', 'grad_norm': '0.5355', 'learning_rate': '0.0002', 'epoch': '0.5049'}
+{'loss': '0.9222', 'grad_norm': '0.5478', 'learning_rate': '0.0002', 'epoch': '0.5057'}
+{'loss': '0.9105', 'grad_norm': '0.492', 'learning_rate': '0.0002', 'epoch': '0.5066'}
+{'loss': '0.9176', 'grad_norm': '0.5274', 'learning_rate': '0.0002', 'epoch': '0.5074'}
+{'loss': '0.839', 'grad_norm': '0.4257', 'learning_rate': '0.0002', 'epoch': '0.5083'}
+{'loss': '1.016', 'grad_norm': '0.4948', 'learning_rate': '0.0002', 'epoch': '0.5092'}
+{'loss': '0.9901', 'grad_norm': '0.5541', 'learning_rate': '0.0002', 'epoch': '0.51'}
+{'loss': '0.8798', 'grad_norm': '0.4793', 'learning_rate': '0.0002', 'epoch': '0.5109'}
+{'loss': '0.9623', 'grad_norm': '0.4743', 'learning_rate': '0.0002', 'epoch': '0.5118'}
+{'loss': '0.8604', 'grad_norm': '0.4492', 'learning_rate': '0.0002', 'epoch': '0.5126'}
+{'loss': '1.033', 'grad_norm': '0.567', 'learning_rate': '0.0002', 'epoch': '0.5135'}
+{'loss': '0.7659', 'grad_norm': '0.4672', 'learning_rate': '0.0002', 'epoch': '0.5143'}
+{'loss': '0.9365', 'grad_norm': '0.4231', 'learning_rate': '0.0002', 'epoch': '0.5152'}
+{'loss': '0.771', 'grad_norm': '0.4653', 'learning_rate': '0.0002', 'epoch': '0.5161'}
+{'loss': '0.9124', 'grad_norm': '0.5048', 'learning_rate': '0.0002', 'epoch': '0.5169'}
+{'loss': '0.8976', 'grad_norm': '0.5446', 'learning_rate': '0.0002', 'epoch': '0.5178'}
+{'eval_loss': '0.9344', 'eval_runtime': '658.7', 'eval_samples_per_second': '3.127', 'eval_steps_per_second': '3.127', 'epoch': '0.5178'}
+{'loss': '0.891', 'grad_norm': '0.5044', 'learning_rate': '0.0002', 'epoch': '0.5187'}
+{'loss': '0.9139', 'grad_norm': '0.4672', 'learning_rate': '0.0002', 'epoch': '0.5195'}
+{'loss': '0.8946', 'grad_norm': '0.4575', 'learning_rate': '0.0002', 'epoch': '0.5204'}
+{'loss': '0.8661', 'grad_norm': '0.4829', 'learning_rate': '0.0002', 'epoch': '0.5213'}
+{'loss': '0.7685', 'grad_norm': '0.3975', 'learning_rate': '0.0002', 'epoch': '0.5221'}
+{'loss': '0.9668', 'grad_norm': '0.5642', 'learning_rate': '0.0002', 'epoch': '0.523'}
+{'loss': '0.8679', 'grad_norm': '0.4907', 'learning_rate': '0.0002', 'epoch': '0.5238'}
+{'loss': '0.8803', 'grad_norm': '0.4621', 'learning_rate': '0.0002', 'epoch': '0.5247'}
+{'loss': '0.8494', 'grad_norm': '0.4355', 'learning_rate': '0.0002', 'epoch': '0.5256'}
+{'loss': '0.895', 'grad_norm': '0.4294', 'learning_rate': '0.0002', 'epoch': '0.5264'}
+{'loss': '0.9497', 'grad_norm': '0.5452', 'learning_rate': '0.0002', 'epoch': '0.5273'}
+{'loss': '0.9171', 'grad_norm': '0.4587', 'learning_rate': '0.0002', 'epoch': '0.5282'}
+{'loss': '0.7557', 'grad_norm': '0.4414', 'learning_rate': '0.0002', 'epoch': '0.529'}
+{'loss': '0.849', 'grad_norm': '0.4892', 'learning_rate': '0.0002', 'epoch': '0.5299'}
+{'loss': '0.9556', 'grad_norm': '0.5048', 'learning_rate': '0.0002', 'epoch': '0.5307'}
+{'loss': '0.8081', 'grad_norm': '0.5007', 'learning_rate': '0.0002', 'epoch': '0.5316'}
+{'loss': '0.8638', 'grad_norm': '0.5422', 'learning_rate': '0.0002', 'epoch': '0.5325'}
+{'loss': '0.8891', 'grad_norm': '0.4535', 'learning_rate': '0.0002', 'epoch': '0.5333'}
+{'loss': '0.8803', 'grad_norm': '0.4589', 'learning_rate': '0.0002', 'epoch': '0.5342'}
+{'loss': '0.9695', 'grad_norm': '0.4937', 'learning_rate': '0.0002', 'epoch': '0.5351'}
+{'loss': '0.8368', 'grad_norm': '0.4199', 'learning_rate': '0.0002', 'epoch': '0.5359'}
+{'loss': '0.9423', 'grad_norm': '0.5242', 'learning_rate': '0.0001999', 'epoch': '0.5368'}
+{'loss': '0.8927', 'grad_norm': '0.49', 'learning_rate': '0.0001999', 'epoch': '0.5376'}
+{'loss': '0.9989', 'grad_norm': '0.5497', 'learning_rate': '0.0001999', 'epoch': '0.5385'}
+{'loss': '0.8873', 'grad_norm': '0.4497', 'learning_rate': '0.0001999', 'epoch': '0.5394'}
+{'loss': '0.9041', 'grad_norm': '0.4257', 'learning_rate': '0.0001999', 'epoch': '0.5402'}
+{'loss': '0.7648', 'grad_norm': '0.3691', 'learning_rate': '0.0001999', 'epoch': '0.5411'}
+{'loss': '0.8892', 'grad_norm': '0.5376', 'learning_rate': '0.0001999', 'epoch': '0.542'}
+{'loss': '0.8639', 'grad_norm': '0.4946', 'learning_rate': '0.0001999', 'epoch': '0.5428'}
+{'loss': '0.8165', 'grad_norm': '0.5052', 'learning_rate': '0.0001999', 'epoch': '0.5437'}
+{'loss': '0.91', 'grad_norm': '0.4737', 'learning_rate': '0.0001999', 'epoch': '0.5446'}
+{'loss': '0.8557', 'grad_norm': '0.46', 'learning_rate': '0.0001999', 'epoch': '0.5454'}
+{'loss': '0.9136', 'grad_norm': '0.5685', 'learning_rate': '0.0001999', 'epoch': '0.5463'}
+{'loss': '0.7907', 'grad_norm': '0.5151', 'learning_rate': '0.0001999', 'epoch': '0.5471'}
+{'loss': '0.9327', 'grad_norm': '0.4858', 'learning_rate': '0.0001999', 'epoch': '0.548'}
+{'loss': '0.9734', 'grad_norm': '0.4905', 'learning_rate': '0.0001999', 'epoch': '0.5489'}
+{'loss': '0.8728', 'grad_norm': '0.5092', 'learning_rate': '0.0001999', 'epoch': '0.5497'}
+{'loss': '0.7573', 'grad_norm': '0.3843', 'learning_rate': '0.0001999', 'epoch': '0.5506'}
+{'loss': '0.8895', 'grad_norm': '0.5343', 'learning_rate': '0.0001999', 'epoch': '0.5515'}
+{'loss': '0.9318', 'grad_norm': '0.4567', 'learning_rate': '0.0001999', 'epoch': '0.5523'}
+{'loss': '0.8542', 'grad_norm': '0.4846', 'learning_rate': '0.0001999', 'epoch': '0.5532'}
+{'loss': '0.9779', 'grad_norm': '0.557', 'learning_rate': '0.0001999', 'epoch': '0.554'}
+{'loss': '0.8861', 'grad_norm': '0.4637', 'learning_rate': '0.0001999', 'epoch': '0.5549'}
+{'loss': '0.843', 'grad_norm': '0.4097', 'learning_rate': '0.0001999', 'epoch': '0.5558'}
+{'loss': '0.8511', 'grad_norm': '0.5222', 'learning_rate': '0.0001999', 'epoch': '0.5566'}
+{'loss': '0.8971', 'grad_norm': '0.5156', 'learning_rate': '0.0001999', 'epoch': '0.5575'}
+{'loss': '0.903', 'grad_norm': '0.5065', 'learning_rate': '0.0001999', 'epoch': '0.5584'}
+{'loss': '0.7866', 'grad_norm': '0.4055', 'learning_rate': '0.0001999', 'epoch': '0.5592'}
+{'loss': '0.9478', 'grad_norm': '0.5009', 'learning_rate': '0.0001999', 'epoch': '0.5601'}
+{'loss': '0.9207', 'grad_norm': '0.5192', 'learning_rate': '0.0001999', 'epoch': '0.5609'}
+{'eval_loss': '0.9177', 'eval_runtime': '665.3', 'eval_samples_per_second': '3.096', 'eval_steps_per_second': '3.096', 'epoch': '0.5609'}
+{'loss': '0.9517', 'grad_norm': '0.558', 'learning_rate': '0.0001999', 'epoch': '0.5618'}
+{'loss': '0.7726', 'grad_norm': '0.4151', 'learning_rate': '0.0001999', 'epoch': '0.5627'}
+{'loss': '0.9242', 'grad_norm': '0.5633', 'learning_rate': '0.0001999', 'epoch': '0.5635'}
+{'loss': '0.8352', 'grad_norm': '0.4484', 'learning_rate': '0.0001999', 'epoch': '0.5644'}
+{'loss': '0.9033', 'grad_norm': '0.5415', 'learning_rate': '0.0001999', 'epoch': '0.5653'}
+{'loss': '0.8885', 'grad_norm': '0.5284', 'learning_rate': '0.0001999', 'epoch': '0.5661'}
+{'loss': '0.836', 'grad_norm': '0.4585', 'learning_rate': '0.0001999', 'epoch': '0.567'}
+{'loss': '0.8328', 'grad_norm': '0.4444', 'learning_rate': '0.0001999', 'epoch': '0.5679'}
+{'loss': '0.9355', 'grad_norm': '0.5491', 'learning_rate': '0.0001999', 'epoch': '0.5687'}
+{'loss': '0.9441', 'grad_norm': '0.5502', 'learning_rate': '0.0001999', 'epoch': '0.5696'}
+{'loss': '0.9515', 'grad_norm': '0.4717', 'learning_rate': '0.0001999', 'epoch': '0.5704'}
+{'loss': '0.9455', 'grad_norm': '0.5137', 'learning_rate': '0.0001999', 'epoch': '0.5713'}
+{'loss': '0.8627', 'grad_norm': '0.4823', 'learning_rate': '0.0001999', 'epoch': '0.5722'}
+{'loss': '0.8857', 'grad_norm': '0.4639', 'learning_rate': '0.0001999', 'epoch': '0.573'}
+{'loss': '0.9198', 'grad_norm': '0.5225', 'learning_rate': '0.0001999', 'epoch': '0.5739'}
+{'loss': '0.8785', 'grad_norm': '0.475', 'learning_rate': '0.0001999', 'epoch': '0.5748'}
+{'loss': '0.9594', 'grad_norm': '0.5022', 'learning_rate': '0.0001999', 'epoch': '0.5756'}
+{'loss': '0.9862', 'grad_norm': '0.4573', 'learning_rate': '0.0001999', 'epoch': '0.5765'}
+{'loss': '0.9164', 'grad_norm': '0.5154', 'learning_rate': '0.0001998', 'epoch': '0.5773'}
+{'loss': '0.8816', 'grad_norm': '0.4814', 'learning_rate': '0.0001998', 'epoch': '0.5782'}
+{'loss': '0.857', 'grad_norm': '0.432', 'learning_rate': '0.0001998', 'epoch': '0.5791'}
+{'loss': '0.8939', 'grad_norm': '0.5129', 'learning_rate': '0.0001998', 'epoch': '0.5799'}
+{'loss': '0.9267', 'grad_norm': '0.4145', 'learning_rate': '0.0001998', 'epoch': '0.5808'}
+{'loss': '0.8495', 'grad_norm': '0.4292', 'learning_rate': '0.0001998', 'epoch': '0.5817'}
+{'loss': '0.972', 'grad_norm': '0.44', 'learning_rate': '0.0001998', 'epoch': '0.5825'}
+{'loss': '0.9401', 'grad_norm': '0.5064', 'learning_rate': '0.0001998', 'epoch': '0.5834'}
+{'loss': '0.8658', 'grad_norm': '0.503', 'learning_rate': '0.0001998', 'epoch': '0.5843'}
+{'loss': '0.8594', 'grad_norm': '0.4552', 'learning_rate': '0.0001998', 'epoch': '0.5851'}
+{'loss': '0.8658', 'grad_norm': '0.4912', 'learning_rate': '0.0001998', 'epoch': '0.586'}
+{'loss': '0.8045', 'grad_norm': '0.4535', 'learning_rate': '0.0001998', 'epoch': '0.5868'}
+{'loss': '0.9177', 'grad_norm': '0.5192', 'learning_rate': '0.0001998', 'epoch': '0.5877'}
+{'loss': '0.8453', 'grad_norm': '0.4792', 'learning_rate': '0.0001998', 'epoch': '0.5886'}
+{'loss': '0.9344', 'grad_norm': '0.5105', 'learning_rate': '0.0001998', 'epoch': '0.5894'}
+{'loss': '0.8951', 'grad_norm': '0.4459', 'learning_rate': '0.0001998', 'epoch': '0.5903'}
+{'loss': '0.8614', 'grad_norm': '0.4376', 'learning_rate': '0.0001998', 'epoch': '0.5912'}
+{'loss': '0.8982', 'grad_norm': '0.5139', 'learning_rate': '0.0001998', 'epoch': '0.592'}
+{'loss': '0.9372', 'grad_norm': '0.4547', 'learning_rate': '0.0001998', 'epoch': '0.5929'}
+{'loss': '0.8759', 'grad_norm': '0.4961', 'learning_rate': '0.0001998', 'epoch': '0.5937'}
+{'loss': '0.9852', 'grad_norm': '0.5673', 'learning_rate': '0.0001998', 'epoch': '0.5946'}
+{'loss': '0.8451', 'grad_norm': '0.4491', 'learning_rate': '0.0001998', 'epoch': '0.5955'}
+{'loss': '0.8382', 'grad_norm': '0.476', 'learning_rate': '0.0001998', 'epoch': '0.5963'}
+{'loss': '0.8821', 'grad_norm': '0.4936', 'learning_rate': '0.0001998', 'epoch': '0.5972'}
+{'loss': '0.9157', 'grad_norm': '0.4498', 'learning_rate': '0.0001998', 'epoch': '0.5981'}
+{'loss': '0.8285', 'grad_norm': '0.452', 'learning_rate': '0.0001998', 'epoch': '0.5989'}
+{'loss': '0.811', 'grad_norm': '0.4579', 'learning_rate': '0.0001998', 'epoch': '0.5998'}
+{'loss': '0.8286', 'grad_norm': '0.4795', 'learning_rate': '0.0001998', 'epoch': '0.6006'}
+{'loss': '0.9498', 'grad_norm': '0.5027', 'learning_rate': '0.0001998', 'epoch': '0.6015'}
+{'loss': '0.9172', 'grad_norm': '0.4995', 'learning_rate': '0.0001998', 'epoch': '0.6024'}
+{'loss': '0.7894', 'grad_norm': '0.479', 'learning_rate': '0.0001998', 'epoch': '0.6032'}
+{'loss': '0.8942', 'grad_norm': '0.4228', 'learning_rate': '0.0001998', 'epoch': '0.6041'}
+{'eval_loss': '0.908', 'eval_runtime': '661.5', 'eval_samples_per_second': '3.114', 'eval_steps_per_second': '3.114', 'epoch': '0.6041'}
+{'loss': '0.8938', 'grad_norm': '0.579', 'learning_rate': '0.0001998', 'epoch': '0.605'}
+{'loss': '0.8746', 'grad_norm': '0.4612', 'learning_rate': '0.0001997', 'epoch': '0.6058'}
+{'loss': '0.8651', 'grad_norm': '0.5196', 'learning_rate': '0.0001997', 'epoch': '0.6067'}
+{'loss': '0.8853', 'grad_norm': '0.4693', 'learning_rate': '0.0001997', 'epoch': '0.6076'}
+{'loss': '0.7866', 'grad_norm': '0.4087', 'learning_rate': '0.0001997', 'epoch': '0.6084'}
+{'loss': '0.9075', 'grad_norm': '0.5398', 'learning_rate': '0.0001997', 'epoch': '0.6093'}
+{'loss': '0.8683', 'grad_norm': '0.511', 'learning_rate': '0.0001997', 'epoch': '0.6101'}
+{'loss': '0.8786', 'grad_norm': '0.4448', 'learning_rate': '0.0001997', 'epoch': '0.611'}
+{'loss': '0.9022', 'grad_norm': '0.4768', 'learning_rate': '0.0001997', 'epoch': '0.6119'}
+{'loss': '0.7737', 'grad_norm': '0.4327', 'learning_rate': '0.0001997', 'epoch': '0.6127'}
+{'loss': '0.8763', 'grad_norm': '0.5257', 'learning_rate': '0.0001997', 'epoch': '0.6136'}
+{'loss': '0.8504', 'grad_norm': '0.4821', 'learning_rate': '0.0001997', 'epoch': '0.6145'}
+{'loss': '0.946', 'grad_norm': '0.6033', 'learning_rate': '0.0001997', 'epoch': '0.6153'}
+{'loss': '0.8837', 'grad_norm': '0.4492', 'learning_rate': '0.0001997', 'epoch': '0.6162'}
+{'loss': '0.8614', 'grad_norm': '0.475', 'learning_rate': '0.0001997', 'epoch': '0.617'}
+{'loss': '0.842', 'grad_norm': '0.448', 'learning_rate': '0.0001997', 'epoch': '0.6179'}
+{'loss': '0.8256', 'grad_norm': '0.4506', 'learning_rate': '0.0001997', 'epoch': '0.6188'}
+{'loss': '0.913', 'grad_norm': '0.459', 'learning_rate': '0.0001997', 'epoch': '0.6196'}
+{'loss': '0.7408', 'grad_norm': '0.4891', 'learning_rate': '0.0001997', 'epoch': '0.6205'}
+{'loss': '0.8538', 'grad_norm': '0.4582', 'learning_rate': '0.0001997', 'epoch': '0.6214'}
+{'loss': '0.878', 'grad_norm': '0.4872', 'learning_rate': '0.0001997', 'epoch': '0.6222'}
+{'loss': '0.8341', 'grad_norm': '0.4291', 'learning_rate': '0.0001997', 'epoch': '0.6231'}
+{'loss': '0.8652', 'grad_norm': '0.4773', 'learning_rate': '0.0001997', 'epoch': '0.6239'}
+{'loss': '0.834', 'grad_norm': '0.4556', 'learning_rate': '0.0001997', 'epoch': '0.6248'}
+{'loss': '0.9129', 'grad_norm': '0.5127', 'learning_rate': '0.0001997', 'epoch': '0.6257'}
+{'loss': '0.9058', 'grad_norm': '0.6067', 'learning_rate': '0.0001997', 'epoch': '0.6265'}
+{'loss': '0.8741', 'grad_norm': '0.4643', 'learning_rate': '0.0001997', 'epoch': '0.6274'}
+{'loss': '0.9156', 'grad_norm': '0.4811', 'learning_rate': '0.0001996', 'epoch': '0.6283'}
+{'loss': '0.906', 'grad_norm': '0.473', 'learning_rate': '0.0001996', 'epoch': '0.6291'}
+{'loss': '0.9775', 'grad_norm': '0.4892', 'learning_rate': '0.0001996', 'epoch': '0.63'}
+{'loss': '0.8951', 'grad_norm': '0.4408', 'learning_rate': '0.0001996', 'epoch': '0.6309'}
+{'loss': '0.8532', 'grad_norm': '0.5018', 'learning_rate': '0.0001996', 'epoch': '0.6317'}
+{'loss': '0.7776', 'grad_norm': '0.4325', 'learning_rate': '0.0001996', 'epoch': '0.6326'}
+{'loss': '0.8316', 'grad_norm': '0.5029', 'learning_rate': '0.0001996', 'epoch': '0.6334'}
+{'loss': '0.8491', 'grad_norm': '0.4697', 'learning_rate': '0.0001996', 'epoch': '0.6343'}
+{'loss': '0.8829', 'grad_norm': '0.4673', 'learning_rate': '0.0001996', 'epoch': '0.6352'}
+{'loss': '0.8501', 'grad_norm': '0.4301', 'learning_rate': '0.0001996', 'epoch': '0.636'}
+{'loss': '0.7913', 'grad_norm': '0.4664', 'learning_rate': '0.0001996', 'epoch': '0.6369'}
+{'loss': '0.9073', 'grad_norm': '0.4414', 'learning_rate': '0.0001996', 'epoch': '0.6378'}
+{'loss': '0.8977', 'grad_norm': '0.4746', 'learning_rate': '0.0001996', 'epoch': '0.6386'}
+{'loss': '0.8142', 'grad_norm': '0.4597', 'learning_rate': '0.0001996', 'epoch': '0.6395'}
+{'loss': '0.8606', 'grad_norm': '0.484', 'learning_rate': '0.0001996', 'epoch': '0.6403'}
+{'loss': '0.7587', 'grad_norm': '0.3543', 'learning_rate': '0.0001996', 'epoch': '0.6412'}
+{'loss': '0.9354', 'grad_norm': '0.5423', 'learning_rate': '0.0001996', 'epoch': '0.6421'}
+{'loss': '0.9919', 'grad_norm': '0.4581', 'learning_rate': '0.0001996', 'epoch': '0.6429'}
+{'loss': '0.8721', 'grad_norm': '0.4212', 'learning_rate': '0.0001996', 'epoch': '0.6438'}
+{'loss': '0.8661', 'grad_norm': '0.4583', 'learning_rate': '0.0001996', 'epoch': '0.6447'}
+{'loss': '0.8171', 'grad_norm': '0.436', 'learning_rate': '0.0001996', 'epoch': '0.6455'}
+{'loss': '0.8607', 'grad_norm': '0.4643', 'learning_rate': '0.0001996', 'epoch': '0.6464'}
+{'loss': '0.8375', 'grad_norm': '0.4496', 'learning_rate': '0.0001996', 'epoch': '0.6472'}
+{'eval_loss': '0.8973', 'eval_runtime': '649.8', 'eval_samples_per_second': '3.17', 'eval_steps_per_second': '3.17', 'epoch': '0.6472'}
+{'loss': '0.9355', 'grad_norm': '0.4836', 'learning_rate': '0.0001995', 'epoch': '0.6481'}
+{'loss': '0.8287', 'grad_norm': '0.4468', 'learning_rate': '0.0001995', 'epoch': '0.649'}
+{'loss': '0.8904', 'grad_norm': '0.511', 'learning_rate': '0.0001995', 'epoch': '0.6498'}
+{'loss': '0.8117', 'grad_norm': '0.4353', 'learning_rate': '0.0001995', 'epoch': '0.6507'}
+{'loss': '0.8256', 'grad_norm': '0.4732', 'learning_rate': '0.0001995', 'epoch': '0.6516'}
+{'loss': '0.9371', 'grad_norm': '0.5447', 'learning_rate': '0.0001995', 'epoch': '0.6524'}
+{'loss': '0.8533', 'grad_norm': '0.4762', 'learning_rate': '0.0001995', 'epoch': '0.6533'}
+{'loss': '0.8799', 'grad_norm': '0.4412', 'learning_rate': '0.0001995', 'epoch': '0.6542'}
+{'loss': '0.8396', 'grad_norm': '0.4699', 'learning_rate': '0.0001995', 'epoch': '0.655'}
+{'loss': '0.9557', 'grad_norm': '0.5236', 'learning_rate': '0.0001995', 'epoch': '0.6559'}
+{'loss': '0.8524', 'grad_norm': '0.4442', 'learning_rate': '0.0001995', 'epoch': '0.6567'}
+{'loss': '0.9214', 'grad_norm': '0.4173', 'learning_rate': '0.0001995', 'epoch': '0.6576'}
+{'loss': '0.9237', 'grad_norm': '0.4404', 'learning_rate': '0.0001995', 'epoch': '0.6585'}
+{'loss': '0.8373', 'grad_norm': '0.4586', 'learning_rate': '0.0001995', 'epoch': '0.6593'}
+{'loss': '0.8257', 'grad_norm': '0.4136', 'learning_rate': '0.0001995', 'epoch': '0.6602'}
+{'loss': '0.8581', 'grad_norm': '0.5007', 'learning_rate': '0.0001995', 'epoch': '0.6611'}
+{'loss': '0.7648', 'grad_norm': '0.3905', 'learning_rate': '0.0001995', 'epoch': '0.6619'}
+{'loss': '0.9043', 'grad_norm': '0.4641', 'learning_rate': '0.0001995', 'epoch': '0.6628'}
+{'loss': '0.9114', 'grad_norm': '0.5305', 'learning_rate': '0.0001995', 'epoch': '0.6636'}
+{'loss': '0.8239', 'grad_norm': '0.5426', 'learning_rate': '0.0001995', 'epoch': '0.6645'}
+{'loss': '0.8091', 'grad_norm': '0.4489', 'learning_rate': '0.0001994', 'epoch': '0.6654'}
+{'loss': '0.9202', 'grad_norm': '0.4294', 'learning_rate': '0.0001994', 'epoch': '0.6662'}
+{'loss': '0.8885', 'grad_norm': '0.4496', 'learning_rate': '0.0001994', 'epoch': '0.6671'}
+{'loss': '0.8391', 'grad_norm': '0.4517', 'learning_rate': '0.0001994', 'epoch': '0.668'}
+{'loss': '0.7388', 'grad_norm': '0.4223', 'learning_rate': '0.0001994', 'epoch': '0.6688'}
+{'loss': '0.9268', 'grad_norm': '0.5806', 'learning_rate': '0.0001994', 'epoch': '0.6697'}
+{'loss': '0.7979', 'grad_norm': '0.4436', 'learning_rate': '0.0001994', 'epoch': '0.6706'}
+{'loss': '0.8229', 'grad_norm': '0.415', 'learning_rate': '0.0001994', 'epoch': '0.6714'}
+{'loss': '0.8555', 'grad_norm': '0.4992', 'learning_rate': '0.0001994', 'epoch': '0.6723'}
+{'loss': '0.9136', 'grad_norm': '0.4533', 'learning_rate': '0.0001994', 'epoch': '0.6731'}
+{'loss': '0.777', 'grad_norm': '0.4864', 'learning_rate': '0.0001994', 'epoch': '0.674'}
+{'loss': '0.9626', 'grad_norm': '0.5073', 'learning_rate': '0.0001994', 'epoch': '0.6749'}
+{'loss': '0.8507', 'grad_norm': '0.4647', 'learning_rate': '0.0001994', 'epoch': '0.6757'}
+{'loss': '0.8173', 'grad_norm': '0.4343', 'learning_rate': '0.0001994', 'epoch': '0.6766'}
+{'loss': '0.9216', 'grad_norm': '0.4689', 'learning_rate': '0.0001994', 'epoch': '0.6775'}
+{'loss': '0.81', 'grad_norm': '0.5121', 'learning_rate': '0.0001994', 'epoch': '0.6783'}
+{'loss': '0.8675', 'grad_norm': '0.4652', 'learning_rate': '0.0001994', 'epoch': '0.6792'}
+{'loss': '0.7939', 'grad_norm': '0.4599', 'learning_rate': '0.0001994', 'epoch': '0.68'}
+{'loss': '0.8611', 'grad_norm': '0.4738', 'learning_rate': '0.0001994', 'epoch': '0.6809'}
+{'loss': '0.9199', 'grad_norm': '0.5161', 'learning_rate': '0.0001993', 'epoch': '0.6818'}
+{'loss': '0.7716', 'grad_norm': '0.4285', 'learning_rate': '0.0001993', 'epoch': '0.6826'}
+{'loss': '0.8861', 'grad_norm': '0.5118', 'learning_rate': '0.0001993', 'epoch': '0.6835'}
+{'loss': '0.807', 'grad_norm': '0.4964', 'learning_rate': '0.0001993', 'epoch': '0.6844'}
+{'loss': '0.7964', 'grad_norm': '0.47', 'learning_rate': '0.0001993', 'epoch': '0.6852'}
+{'loss': '0.9406', 'grad_norm': '0.5329', 'learning_rate': '0.0001993', 'epoch': '0.6861'}
+{'loss': '0.8518', 'grad_norm': '0.4982', 'learning_rate': '0.0001993', 'epoch': '0.6869'}
+{'loss': '0.8704', 'grad_norm': '0.4525', 'learning_rate': '0.0001993', 'epoch': '0.6878'}
+{'loss': '0.9035', 'grad_norm': '0.4752', 'learning_rate': '0.0001993', 'epoch': '0.6887'}
+{'loss': '0.9174', 'grad_norm': '0.4538', 'learning_rate': '0.0001993', 'epoch': '0.6895'}
+{'loss': '0.8574', 'grad_norm': '0.4247', 'learning_rate': '0.0001993', 'epoch': '0.6904'}
+{'eval_loss': '0.8881', 'eval_runtime': '654', 'eval_samples_per_second': '3.15', 'eval_steps_per_second': '3.15', 'epoch': '0.6904'}
+{'loss': '0.8493', 'grad_norm': '0.4388', 'learning_rate': '0.0001993', 'epoch': '0.6913'}
+{'loss': '0.8298', 'grad_norm': '0.4609', 'learning_rate': '0.0001993', 'epoch': '0.6921'}
+{'loss': '0.8861', 'grad_norm': '0.4297', 'learning_rate': '0.0001993', 'epoch': '0.693'}
+{'loss': '0.7973', 'grad_norm': '0.4301', 'learning_rate': '0.0001993', 'epoch': '0.6939'}
+{'loss': '0.8662', 'grad_norm': '0.3705', 'learning_rate': '0.0001993', 'epoch': '0.6947'}
+{'loss': '0.835', 'grad_norm': '0.4052', 'learning_rate': '0.0001993', 'epoch': '0.6956'}
+{'loss': '0.7921', 'grad_norm': '0.4773', 'learning_rate': '0.0001992', 'epoch': '0.6964'}
+{'loss': '0.8644', 'grad_norm': '0.4682', 'learning_rate': '0.0001992', 'epoch': '0.6973'}
+{'loss': '0.9898', 'grad_norm': '0.5695', 'learning_rate': '0.0001992', 'epoch': '0.6982'}
+{'loss': '0.691', 'grad_norm': '0.4014', 'learning_rate': '0.0001992', 'epoch': '0.699'}
+{'loss': '0.8296', 'grad_norm': '0.4208', 'learning_rate': '0.0001992', 'epoch': '0.6999'}
+{'loss': '0.8209', 'grad_norm': '0.4473', 'learning_rate': '0.0001992', 'epoch': '0.7008'}
+{'loss': '0.8319', 'grad_norm': '0.4391', 'learning_rate': '0.0001992', 'epoch': '0.7016'}
+{'loss': '0.8589', 'grad_norm': '0.4758', 'learning_rate': '0.0001992', 'epoch': '0.7025'}
+{'loss': '0.9219', 'grad_norm': '0.5064', 'learning_rate': '0.0001992', 'epoch': '0.7033'}
+{'loss': '0.7825', 'grad_norm': '0.4398', 'learning_rate': '0.0001992', 'epoch': '0.7042'}
+{'loss': '0.8472', 'grad_norm': '0.3879', 'learning_rate': '0.0001992', 'epoch': '0.7051'}
+{'loss': '0.825', 'grad_norm': '0.4224', 'learning_rate': '0.0001992', 'epoch': '0.7059'}
+{'loss': '0.9491', 'grad_norm': '0.5235', 'learning_rate': '0.0001992', 'epoch': '0.7068'}
+{'loss': '0.9609', 'grad_norm': '0.5195', 'learning_rate': '0.0001992', 'epoch': '0.7077'}
+{'loss': '0.8961', 'grad_norm': '0.5016', 'learning_rate': '0.0001992', 'epoch': '0.7085'}
+{'loss': '0.8883', 'grad_norm': '0.551', 'learning_rate': '0.0001992', 'epoch': '0.7094'}
+{'loss': '0.7969', 'grad_norm': '0.4492', 'learning_rate': '0.0001991', 'epoch': '0.7102'}
+{'loss': '0.7869', 'grad_norm': '0.419', 'learning_rate': '0.0001991', 'epoch': '0.7111'}
+{'loss': '0.8424', 'grad_norm': '0.4591', 'learning_rate': '0.0001991', 'epoch': '0.712'}
+{'loss': '0.8955', 'grad_norm': '0.5059', 'learning_rate': '0.0001991', 'epoch': '0.7128'}
+{'loss': '0.8738', 'grad_norm': '0.4905', 'learning_rate': '0.0001991', 'epoch': '0.7137'}
+{'loss': '0.802', 'grad_norm': '0.4671', 'learning_rate': '0.0001991', 'epoch': '0.7146'}
+{'loss': '0.9474', 'grad_norm': '0.5303', 'learning_rate': '0.0001991', 'epoch': '0.7154'}
+{'loss': '0.8739', 'grad_norm': '0.4251', 'learning_rate': '0.0001991', 'epoch': '0.7163'}
+{'loss': '0.9578', 'grad_norm': '0.4897', 'learning_rate': '0.0001991', 'epoch': '0.7172'}
+{'loss': '0.8116', 'grad_norm': '0.5', 'learning_rate': '0.0001991', 'epoch': '0.718'}
+{'loss': '0.8783', 'grad_norm': '0.4335', 'learning_rate': '0.0001991', 'epoch': '0.7189'}
+{'loss': '0.8223', 'grad_norm': '0.4354', 'learning_rate': '0.0001991', 'epoch': '0.7197'}
+{'loss': '1.005', 'grad_norm': '0.4907', 'learning_rate': '0.0001991', 'epoch': '0.7206'}
+{'loss': '0.8108', 'grad_norm': '0.4055', 'learning_rate': '0.0001991', 'epoch': '0.7215'}
+{'loss': '0.7808', 'grad_norm': '0.3819', 'learning_rate': '0.0001991', 'epoch': '0.7223'}
+{'loss': '0.8189', 'grad_norm': '0.4129', 'learning_rate': '0.000199', 'epoch': '0.7232'}
+{'loss': '0.8365', 'grad_norm': '0.469', 'learning_rate': '0.000199', 'epoch': '0.7241'}
+{'loss': '0.8058', 'grad_norm': '0.4931', 'learning_rate': '0.000199', 'epoch': '0.7249'}
+{'loss': '0.8524', 'grad_norm': '0.4441', 'learning_rate': '0.000199', 'epoch': '0.7258'}
+{'loss': '0.9179', 'grad_norm': '0.5211', 'learning_rate': '0.000199', 'epoch': '0.7266'}
+{'loss': '0.8229', 'grad_norm': '0.4737', 'learning_rate': '0.000199', 'epoch': '0.7275'}
+{'loss': '0.9242', 'grad_norm': '0.5417', 'learning_rate': '0.000199', 'epoch': '0.7284'}
+{'loss': '0.8896', 'grad_norm': '0.4524', 'learning_rate': '0.000199', 'epoch': '0.7292'}
+{'loss': '0.8491', 'grad_norm': '0.4526', 'learning_rate': '0.000199', 'epoch': '0.7301'}
+{'loss': '0.8833', 'grad_norm': '0.5347', 'learning_rate': '0.000199', 'epoch': '0.731'}
+{'loss': '0.8535', 'grad_norm': '0.4696', 'learning_rate': '0.000199', 'epoch': '0.7318'}
+{'loss': '0.8273', 'grad_norm': '0.4305', 'learning_rate': '0.000199', 'epoch': '0.7327'}
+{'loss': '0.8759', 'grad_norm': '0.5086', 'learning_rate': '0.000199', 'epoch': '0.7335'}
+{'eval_loss': '0.8791', 'eval_runtime': '663.1', 'eval_samples_per_second': '3.107', 'eval_steps_per_second': '3.107', 'epoch': '0.7335'}
+{'loss': '0.8526', 'grad_norm': '0.4842', 'learning_rate': '0.000199', 'epoch': '0.7344'}
+{'loss': '0.8782', 'grad_norm': '0.4819', 'learning_rate': '0.000199', 'epoch': '0.7353'}
+{'loss': '0.8964', 'grad_norm': '0.417', 'learning_rate': '0.0001989', 'epoch': '0.7361'}
+{'loss': '0.748', 'grad_norm': '0.4271', 'learning_rate': '0.0001989', 'epoch': '0.737'}
+{'loss': '0.819', 'grad_norm': '0.5052', 'learning_rate': '0.0001989', 'epoch': '0.7379'}
+{'loss': '0.8647', 'grad_norm': '0.4405', 'learning_rate': '0.0001989', 'epoch': '0.7387'}
+{'loss': '0.8743', 'grad_norm': '0.4451', 'learning_rate': '0.0001989', 'epoch': '0.7396'}
+{'loss': '0.8892', 'grad_norm': '0.4591', 'learning_rate': '0.0001989', 'epoch': '0.7405'}
+{'loss': '0.7032', 'grad_norm': '0.3917', 'learning_rate': '0.0001989', 'epoch': '0.7413'}
+{'loss': '0.8548', 'grad_norm': '0.4695', 'learning_rate': '0.0001989', 'epoch': '0.7422'}
+{'loss': '0.8231', 'grad_norm': '0.424', 'learning_rate': '0.0001989', 'epoch': '0.743'}
+{'loss': '0.8444', 'grad_norm': '0.4042', 'learning_rate': '0.0001989', 'epoch': '0.7439'}
+{'loss': '0.8787', 'grad_norm': '0.455', 'learning_rate': '0.0001989', 'epoch': '0.7448'}
+{'loss': '0.8441', 'grad_norm': '0.4226', 'learning_rate': '0.0001989', 'epoch': '0.7456'}
+{'loss': '0.8392', 'grad_norm': '0.4638', 'learning_rate': '0.0001989', 'epoch': '0.7465'}
+{'loss': '0.8011', 'grad_norm': '0.4264', 'learning_rate': '0.0001989', 'epoch': '0.7474'}
+{'loss': '0.8502', 'grad_norm': '0.3693', 'learning_rate': '0.0001988', 'epoch': '0.7482'}
+{'loss': '0.7782', 'grad_norm': '0.4772', 'learning_rate': '0.0001988', 'epoch': '0.7491'}
+{'loss': '0.8338', 'grad_norm': '0.4001', 'learning_rate': '0.0001988', 'epoch': '0.7499'}
+{'loss': '0.8287', 'grad_norm': '0.5007', 'learning_rate': '0.0001988', 'epoch': '0.7508'}
+{'loss': '0.8656', 'grad_norm': '0.44', 'learning_rate': '0.0001988', 'epoch': '0.7517'}
+{'loss': '0.8695', 'grad_norm': '0.5116', 'learning_rate': '0.0001988', 'epoch': '0.7525'}
+{'loss': '0.9207', 'grad_norm': '0.5036', 'learning_rate': '0.0001988', 'epoch': '0.7534'}
+{'loss': '0.8799', 'grad_norm': '0.469', 'learning_rate': '0.0001988', 'epoch': '0.7543'}
+{'loss': '0.7738', 'grad_norm': '0.4731', 'learning_rate': '0.0001988', 'epoch': '0.7551'}
+{'loss': '0.9295', 'grad_norm': '0.4901', 'learning_rate': '0.0001988', 'epoch': '0.756'}
+{'loss': '0.8156', 'grad_norm': '0.4347', 'learning_rate': '0.0001988', 'epoch': '0.7569'}
+{'loss': '0.8082', 'grad_norm': '0.5074', 'learning_rate': '0.0001988', 'epoch': '0.7577'}
+{'loss': '0.8906', 'grad_norm': '0.4734', 'learning_rate': '0.0001988', 'epoch': '0.7586'}
+{'loss': '0.8795', 'grad_norm': '0.467', 'learning_rate': '0.0001987', 'epoch': '0.7594'}
+{'loss': '0.8414', 'grad_norm': '0.4952', 'learning_rate': '0.0001987', 'epoch': '0.7603'}
+{'loss': '0.9068', 'grad_norm': '0.5479', 'learning_rate': '0.0001987', 'epoch': '0.7612'}
+{'loss': '0.8932', 'grad_norm': '0.4822', 'learning_rate': '0.0001987', 'epoch': '0.762'}
+{'loss': '0.8497', 'grad_norm': '0.4689', 'learning_rate': '0.0001987', 'epoch': '0.7629'}
+{'loss': '0.9233', 'grad_norm': '0.4728', 'learning_rate': '0.0001987', 'epoch': '0.7638'}
+{'loss': '0.8498', 'grad_norm': '0.445', 'learning_rate': '0.0001987', 'epoch': '0.7646'}
+{'loss': '0.8258', 'grad_norm': '0.4189', 'learning_rate': '0.0001987', 'epoch': '0.7655'}
+{'loss': '0.8763', 'grad_norm': '0.5145', 'learning_rate': '0.0001987', 'epoch': '0.7663'}
+{'loss': '0.8732', 'grad_norm': '0.5048', 'learning_rate': '0.0001987', 'epoch': '0.7672'}
+{'loss': '0.8733', 'grad_norm': '0.4164', 'learning_rate': '0.0001987', 'epoch': '0.7681'}
+{'loss': '0.8454', 'grad_norm': '0.5268', 'learning_rate': '0.0001987', 'epoch': '0.7689'}
+{'loss': '0.878', 'grad_norm': '0.4704', 'learning_rate': '0.0001986', 'epoch': '0.7698'}
+{'loss': '0.8508', 'grad_norm': '0.4536', 'learning_rate': '0.0001986', 'epoch': '0.7707'}
+{'loss': '0.8225', 'grad_norm': '0.4608', 'learning_rate': '0.0001986', 'epoch': '0.7715'}
+{'loss': '0.8446', 'grad_norm': '0.5191', 'learning_rate': '0.0001986', 'epoch': '0.7724'}
+{'loss': '0.8144', 'grad_norm': '0.425', 'learning_rate': '0.0001986', 'epoch': '0.7732'}
+{'loss': '0.8836', 'grad_norm': '0.4711', 'learning_rate': '0.0001986', 'epoch': '0.7741'}
+{'loss': '0.8846', 'grad_norm': '0.4841', 'learning_rate': '0.0001986', 'epoch': '0.775'}
+{'loss': '0.7993', 'grad_norm': '0.467', 'learning_rate': '0.0001986', 'epoch': '0.7758'}
+{'loss': '0.8389', 'grad_norm': '0.4194', 'learning_rate': '0.0001986', 'epoch': '0.7767'}
+{'eval_loss': '0.8728', 'eval_runtime': '668.2', 'eval_samples_per_second': '3.083', 'eval_steps_per_second': '3.083', 'epoch': '0.7767'}
+{'loss': '0.8824', 'grad_norm': '0.4567', 'learning_rate': '0.0001986', 'epoch': '0.7776'}
+{'loss': '0.809', 'grad_norm': '0.4799', 'learning_rate': '0.0001986', 'epoch': '0.7784'}
+{'loss': '0.9553', 'grad_norm': '0.466', 'learning_rate': '0.0001986', 'epoch': '0.7793'}
+{'loss': '0.8143', 'grad_norm': '0.4857', 'learning_rate': '0.0001986', 'epoch': '0.7802'}
+{'loss': '0.8756', 'grad_norm': '0.47', 'learning_rate': '0.0001985', 'epoch': '0.781'}
+{'loss': '0.8098', 'grad_norm': '0.4211', 'learning_rate': '0.0001985', 'epoch': '0.7819'}
+{'loss': '0.822', 'grad_norm': '0.4218', 'learning_rate': '0.0001985', 'epoch': '0.7827'}
+{'loss': '0.8314', 'grad_norm': '0.4991', 'learning_rate': '0.0001985', 'epoch': '0.7836'}
+{'loss': '0.7985', 'grad_norm': '0.4242', 'learning_rate': '0.0001985', 'epoch': '0.7845'}
+{'loss': '0.8528', 'grad_norm': '0.4635', 'learning_rate': '0.0001985', 'epoch': '0.7853'}
+{'loss': '0.8659', 'grad_norm': '0.4433', 'learning_rate': '0.0001985', 'epoch': '0.7862'}
+{'loss': '0.8676', 'grad_norm': '0.4828', 'learning_rate': '0.0001985', 'epoch': '0.7871'}
+{'loss': '0.855', 'grad_norm': '0.5439', 'learning_rate': '0.0001985', 'epoch': '0.7879'}
+{'loss': '0.7291', 'grad_norm': '0.4575', 'learning_rate': '0.0001985', 'epoch': '0.7888'}
+{'loss': '0.8619', 'grad_norm': '0.4655', 'learning_rate': '0.0001985', 'epoch': '0.7896'}
+{'loss': '0.825', 'grad_norm': '0.4263', 'learning_rate': '0.0001985', 'epoch': '0.7905'}
+{'loss': '0.7139', 'grad_norm': '0.4747', 'learning_rate': '0.0001984', 'epoch': '0.7914'}
+{'loss': '0.9033', 'grad_norm': '0.4462', 'learning_rate': '0.0001984', 'epoch': '0.7922'}
+{'loss': '0.757', 'grad_norm': '0.4581', 'learning_rate': '0.0001984', 'epoch': '0.7931'}
+{'loss': '0.8063', 'grad_norm': '0.4183', 'learning_rate': '0.0001984', 'epoch': '0.794'}
+{'loss': '0.8115', 'grad_norm': '0.3954', 'learning_rate': '0.0001984', 'epoch': '0.7948'}
+{'loss': '0.8416', 'grad_norm': '0.4622', 'learning_rate': '0.0001984', 'epoch': '0.7957'}
+{'loss': '0.8019', 'grad_norm': '0.4781', 'learning_rate': '0.0001984', 'epoch': '0.7965'}
+{'loss': '0.9343', 'grad_norm': '0.4802', 'learning_rate': '0.0001984', 'epoch': '0.7974'}
+{'loss': '0.9163', 'grad_norm': '0.4907', 'learning_rate': '0.0001984', 'epoch': '0.7983'}
+{'loss': '0.8018', 'grad_norm': '0.4857', 'learning_rate': '0.0001984', 'epoch': '0.7991'}
+{'loss': '0.8375', 'grad_norm': '0.494', 'learning_rate': '0.0001984', 'epoch': '0.8'}
+{'loss': '0.8214', 'grad_norm': '0.4238', 'learning_rate': '0.0001983', 'epoch': '0.8009'}
+{'loss': '0.8086', 'grad_norm': '0.3978', 'learning_rate': '0.0001983', 'epoch': '0.8017'}
+{'loss': '0.9402', 'grad_norm': '0.4353', 'learning_rate': '0.0001983', 'epoch': '0.8026'}
+{'loss': '0.7731', 'grad_norm': '0.4075', 'learning_rate': '0.0001983', 'epoch': '0.8035'}
+{'loss': '0.9186', 'grad_norm': '0.488', 'learning_rate': '0.0001983', 'epoch': '0.8043'}
+{'loss': '0.8578', 'grad_norm': '0.4436', 'learning_rate': '0.0001983', 'epoch': '0.8052'}
+{'loss': '0.8682', 'grad_norm': '0.4665', 'learning_rate': '0.0001983', 'epoch': '0.806'}
+{'loss': '0.7845', 'grad_norm': '0.4527', 'learning_rate': '0.0001983', 'epoch': '0.8069'}
+{'loss': '0.8768', 'grad_norm': '0.4104', 'learning_rate': '0.0001983', 'epoch': '0.8078'}
+{'loss': '0.8503', 'grad_norm': '0.5258', 'learning_rate': '0.0001983', 'epoch': '0.8086'}
+{'loss': '0.8234', 'grad_norm': '0.4668', 'learning_rate': '0.0001983', 'epoch': '0.8095'}
+{'loss': '0.8131', 'grad_norm': '0.4632', 'learning_rate': '0.0001982', 'epoch': '0.8104'}
+{'loss': '0.768', 'grad_norm': '0.4767', 'learning_rate': '0.0001982', 'epoch': '0.8112'}
+{'loss': '0.7891', 'grad_norm': '0.3903', 'learning_rate': '0.0001982', 'epoch': '0.8121'}
+{'loss': '0.799', 'grad_norm': '0.4672', 'learning_rate': '0.0001982', 'epoch': '0.8129'}
+{'loss': '0.7828', 'grad_norm': '0.4431', 'learning_rate': '0.0001982', 'epoch': '0.8138'}
+{'loss': '0.8977', 'grad_norm': '0.451', 'learning_rate': '0.0001982', 'epoch': '0.8147'}
+{'loss': '0.7988', 'grad_norm': '0.4668', 'learning_rate': '0.0001982', 'epoch': '0.8155'}
+{'loss': '0.795', 'grad_norm': '0.4438', 'learning_rate': '0.0001982', 'epoch': '0.8164'}
+{'loss': '0.879', 'grad_norm': '0.4201', 'learning_rate': '0.0001982', 'epoch': '0.8173'}
+{'loss': '0.816', 'grad_norm': '0.4359', 'learning_rate': '0.0001982', 'epoch': '0.8181'}
+{'loss': '0.8488', 'grad_norm': '0.4471', 'learning_rate': '0.0001982', 'epoch': '0.819'}
+{'loss': '0.8468', 'grad_norm': '0.4315', 'learning_rate': '0.0001981', 'epoch': '0.8198'}
+{'eval_loss': '0.8643', 'eval_runtime': '658.7', 'eval_samples_per_second': '3.127', 'eval_steps_per_second': '3.127', 'epoch': '0.8198'}
+{'loss': '0.7399', 'grad_norm': '0.3553', 'learning_rate': '0.0001981', 'epoch': '0.8207'}
+{'loss': '0.8544', 'grad_norm': '0.4695', 'learning_rate': '0.0001981', 'epoch': '0.8216'}
+{'loss': '0.8243', 'grad_norm': '0.4962', 'learning_rate': '0.0001981', 'epoch': '0.8224'}
+{'loss': '0.7857', 'grad_norm': '0.4584', 'learning_rate': '0.0001981', 'epoch': '0.8233'}
+{'loss': '0.8362', 'grad_norm': '0.4446', 'learning_rate': '0.0001981', 'epoch': '0.8242'}
+{'loss': '0.8993', 'grad_norm': '0.4471', 'learning_rate': '0.0001981', 'epoch': '0.825'}
+{'loss': '0.8703', 'grad_norm': '0.4488', 'learning_rate': '0.0001981', 'epoch': '0.8259'}
+{'loss': '0.8454', 'grad_norm': '0.4322', 'learning_rate': '0.0001981', 'epoch': '0.8268'}
+{'loss': '0.8622', 'grad_norm': '0.4525', 'learning_rate': '0.0001981', 'epoch': '0.8276'}
+{'loss': '0.8662', 'grad_norm': '0.4617', 'learning_rate': '0.000198', 'epoch': '0.8285'}
+{'loss': '0.8377', 'grad_norm': '0.4253', 'learning_rate': '0.000198', 'epoch': '0.8293'}
+{'loss': '0.9258', 'grad_norm': '0.446', 'learning_rate': '0.000198', 'epoch': '0.8302'}
+{'loss': '0.8805', 'grad_norm': '0.4887', 'learning_rate': '0.000198', 'epoch': '0.8311'}
+{'loss': '0.8561', 'grad_norm': '0.5357', 'learning_rate': '0.000198', 'epoch': '0.8319'}
+{'loss': '0.7822', 'grad_norm': '0.3964', 'learning_rate': '0.000198', 'epoch': '0.8328'}
+{'loss': '0.9048', 'grad_norm': '0.5211', 'learning_rate': '0.000198', 'epoch': '0.8337'}
+{'loss': '0.927', 'grad_norm': '0.4724', 'learning_rate': '0.000198', 'epoch': '0.8345'}
+{'loss': '0.8621', 'grad_norm': '0.4283', 'learning_rate': '0.000198', 'epoch': '0.8354'}
+{'loss': '0.8017', 'grad_norm': '0.4305', 'learning_rate': '0.000198', 'epoch': '0.8362'}
+{'loss': '0.8792', 'grad_norm': '0.4996', 'learning_rate': '0.000198', 'epoch': '0.8371'}
+{'loss': '0.9477', 'grad_norm': '0.4923', 'learning_rate': '0.0001979', 'epoch': '0.838'}
+{'loss': '0.8654', 'grad_norm': '0.4576', 'learning_rate': '0.0001979', 'epoch': '0.8388'}
+{'loss': '0.7793', 'grad_norm': '0.4855', 'learning_rate': '0.0001979', 'epoch': '0.8397'}
+{'loss': '0.8', 'grad_norm': '0.4359', 'learning_rate': '0.0001979', 'epoch': '0.8406'}
+{'loss': '0.8184', 'grad_norm': '0.4225', 'learning_rate': '0.0001979', 'epoch': '0.8414'}
+{'loss': '0.7272', 'grad_norm': '0.3895', 'learning_rate': '0.0001979', 'epoch': '0.8423'}
+{'loss': '0.8941', 'grad_norm': '0.5061', 'learning_rate': '0.0001979', 'epoch': '0.8431'}
+{'loss': '0.8784', 'grad_norm': '0.4165', 'learning_rate': '0.0001979', 'epoch': '0.844'}
+{'loss': '0.8391', 'grad_norm': '0.4877', 'learning_rate': '0.0001979', 'epoch': '0.8449'}
+{'loss': '0.8808', 'grad_norm': '0.4302', 'learning_rate': '0.0001979', 'epoch': '0.8457'}
+{'loss': '0.8038', 'grad_norm': '0.443', 'learning_rate': '0.0001978', 'epoch': '0.8466'}
+{'loss': '0.8341', 'grad_norm': '0.4164', 'learning_rate': '0.0001978', 'epoch': '0.8475'}
+{'loss': '0.8548', 'grad_norm': '0.4536', 'learning_rate': '0.0001978', 'epoch': '0.8483'}
+{'loss': '0.8528', 'grad_norm': '0.4316', 'learning_rate': '0.0001978', 'epoch': '0.8492'}
+{'loss': '0.7462', 'grad_norm': '0.4581', 'learning_rate': '0.0001978', 'epoch': '0.8501'}
+{'loss': '0.8844', 'grad_norm': '0.4958', 'learning_rate': '0.0001978', 'epoch': '0.8509'}
+{'loss': '0.8559', 'grad_norm': '0.4366', 'learning_rate': '0.0001978', 'epoch': '0.8518'}
+{'loss': '0.7564', 'grad_norm': '0.4862', 'learning_rate': '0.0001978', 'epoch': '0.8526'}
+{'loss': '0.8346', 'grad_norm': '0.5163', 'learning_rate': '0.0001978', 'epoch': '0.8535'}
+{'loss': '0.8702', 'grad_norm': '0.5825', 'learning_rate': '0.0001977', 'epoch': '0.8544'}
+{'loss': '0.8935', 'grad_norm': '0.4297', 'learning_rate': '0.0001977', 'epoch': '0.8552'}
+{'loss': '0.8201', 'grad_norm': '0.4298', 'learning_rate': '0.0001977', 'epoch': '0.8561'}
+{'loss': '0.908', 'grad_norm': '0.5193', 'learning_rate': '0.0001977', 'epoch': '0.857'}
+{'loss': '0.8518', 'grad_norm': '0.4527', 'learning_rate': '0.0001977', 'epoch': '0.8578'}
+{'loss': '0.9427', 'grad_norm': '0.4372', 'learning_rate': '0.0001977', 'epoch': '0.8587'}
+{'loss': '0.8065', 'grad_norm': '0.446', 'learning_rate': '0.0001977', 'epoch': '0.8595'}
+{'loss': '0.7674', 'grad_norm': '0.4355', 'learning_rate': '0.0001977', 'epoch': '0.8604'}
+{'loss': '0.8138', 'grad_norm': '0.4375', 'learning_rate': '0.0001977', 'epoch': '0.8613'}
+{'loss': '0.7871', 'grad_norm': '0.4589', 'learning_rate': '0.0001977', 'epoch': '0.8621'}
+{'loss': '0.8383', 'grad_norm': '0.4171', 'learning_rate': '0.0001976', 'epoch': '0.863'}
+{'eval_loss': '0.8567', 'eval_runtime': '646.6', 'eval_samples_per_second': '3.186', 'eval_steps_per_second': '3.186', 'epoch': '0.863'}
+{'loss': '0.8262', 'grad_norm': '0.4819', 'learning_rate': '0.0001976', 'epoch': '0.8639'}
+{'loss': '0.8493', 'grad_norm': '0.4215', 'learning_rate': '0.0001976', 'epoch': '0.8647'}
+{'loss': '0.8645', 'grad_norm': '0.4545', 'learning_rate': '0.0001976', 'epoch': '0.8656'}
+{'loss': '0.8816', 'grad_norm': '0.4436', 'learning_rate': '0.0001976', 'epoch': '0.8665'}
+{'loss': '0.7622', 'grad_norm': '0.4266', 'learning_rate': '0.0001976', 'epoch': '0.8673'}
+{'loss': '0.7844', 'grad_norm': '0.3936', 'learning_rate': '0.0001976', 'epoch': '0.8682'}
+{'loss': '0.8295', 'grad_norm': '0.446', 'learning_rate': '0.0001976', 'epoch': '0.869'}
+{'loss': '0.8513', 'grad_norm': '0.4704', 'learning_rate': '0.0001976', 'epoch': '0.8699'}
+{'loss': '0.845', 'grad_norm': '0.4579', 'learning_rate': '0.0001975', 'epoch': '0.8708'}
+{'loss': '0.8586', 'grad_norm': '0.4436', 'learning_rate': '0.0001975', 'epoch': '0.8716'}
+{'loss': '0.83', 'grad_norm': '0.4501', 'learning_rate': '0.0001975', 'epoch': '0.8725'}
+{'loss': '0.805', 'grad_norm': '0.433', 'learning_rate': '0.0001975', 'epoch': '0.8734'}
+{'loss': '0.8228', 'grad_norm': '0.4387', 'learning_rate': '0.0001975', 'epoch': '0.8742'}
+{'loss': '0.8491', 'grad_norm': '0.4756', 'learning_rate': '0.0001975', 'epoch': '0.8751'}
+{'loss': '0.8163', 'grad_norm': '0.4285', 'learning_rate': '0.0001975', 'epoch': '0.8759'}
+{'loss': '0.9229', 'grad_norm': '0.4763', 'learning_rate': '0.0001975', 'epoch': '0.8768'}
+{'loss': '0.9847', 'grad_norm': '0.4986', 'learning_rate': '0.0001975', 'epoch': '0.8777'}
+{'loss': '0.8305', 'grad_norm': '0.5164', 'learning_rate': '0.0001974', 'epoch': '0.8785'}
+{'loss': '0.7909', 'grad_norm': '0.4783', 'learning_rate': '0.0001974', 'epoch': '0.8794'}
+{'loss': '0.8092', 'grad_norm': '0.4408', 'learning_rate': '0.0001974', 'epoch': '0.8803'}
+{'loss': '0.8064', 'grad_norm': '0.4693', 'learning_rate': '0.0001974', 'epoch': '0.8811'}
+{'loss': '0.8135', 'grad_norm': '0.4224', 'learning_rate': '0.0001974', 'epoch': '0.882'}
+{'loss': '0.8048', 'grad_norm': '0.4633', 'learning_rate': '0.0001974', 'epoch': '0.8828'}
+{'loss': '0.7897', 'grad_norm': '0.4137', 'learning_rate': '0.0001974', 'epoch': '0.8837'}
+{'loss': '0.8412', 'grad_norm': '0.4277', 'learning_rate': '0.0001974', 'epoch': '0.8846'}
+{'loss': '0.7907', 'grad_norm': '0.4199', 'learning_rate': '0.0001974', 'epoch': '0.8854'}
+{'loss': '0.9043', 'grad_norm': '0.4323', 'learning_rate': '0.0001973', 'epoch': '0.8863'}
+{'loss': '0.8178', 'grad_norm': '0.4115', 'learning_rate': '0.0001973', 'epoch': '0.8872'}
+{'loss': '0.8867', 'grad_norm': '0.4596', 'learning_rate': '0.0001973', 'epoch': '0.888'}
+{'loss': '0.7209', 'grad_norm': '0.398', 'learning_rate': '0.0001973', 'epoch': '0.8889'}
+{'loss': '0.9158', 'grad_norm': '0.4434', 'learning_rate': '0.0001973', 'epoch': '0.8898'}
+{'loss': '0.8103', 'grad_norm': '0.4001', 'learning_rate': '0.0001973', 'epoch': '0.8906'}
+{'loss': '0.778', 'grad_norm': '0.4191', 'learning_rate': '0.0001973', 'epoch': '0.8915'}
+{'loss': '0.7106', 'grad_norm': '0.4837', 'learning_rate': '0.0001973', 'epoch': '0.8923'}
+{'loss': '0.753', 'grad_norm': '0.4272', 'learning_rate': '0.0001973', 'epoch': '0.8932'}
+{'loss': '0.8368', 'grad_norm': '0.4876', 'learning_rate': '0.0001972', 'epoch': '0.8941'}
+{'loss': '0.8773', 'grad_norm': '0.4781', 'learning_rate': '0.0001972', 'epoch': '0.8949'}
+{'loss': '0.7152', 'grad_norm': '0.4011', 'learning_rate': '0.0001972', 'epoch': '0.8958'}
+{'loss': '0.8349', 'grad_norm': '0.4864', 'learning_rate': '0.0001972', 'epoch': '0.8967'}
+{'loss': '0.8452', 'grad_norm': '0.4575', 'learning_rate': '0.0001972', 'epoch': '0.8975'}
+{'loss': '0.8746', 'grad_norm': '0.4165', 'learning_rate': '0.0001972', 'epoch': '0.8984'}
+{'loss': '0.8253', 'grad_norm': '0.4588', 'learning_rate': '0.0001972', 'epoch': '0.8992'}
+{'loss': '0.7057', 'grad_norm': '0.371', 'learning_rate': '0.0001972', 'epoch': '0.9001'}
+{'loss': '0.8306', 'grad_norm': '0.4251', 'learning_rate': '0.0001972', 'epoch': '0.901'}
+{'loss': '0.8432', 'grad_norm': '0.4843', 'learning_rate': '0.0001971', 'epoch': '0.9018'}
+{'loss': '0.8312', 'grad_norm': '0.5384', 'learning_rate': '0.0001971', 'epoch': '0.9027'}
+{'loss': '0.8077', 'grad_norm': '0.452', 'learning_rate': '0.0001971', 'epoch': '0.9036'}
+{'loss': '0.8454', 'grad_norm': '0.4427', 'learning_rate': '0.0001971', 'epoch': '0.9044'}
+{'loss': '0.8551', 'grad_norm': '0.4896', 'learning_rate': '0.0001971', 'epoch': '0.9053'}
+{'loss': '0.9159', 'grad_norm': '0.472', 'learning_rate': '0.0001971', 'epoch': '0.9061'}
+{'eval_loss': '0.8525', 'eval_runtime': '655.8', 'eval_samples_per_second': '3.141', 'eval_steps_per_second': '3.141', 'epoch': '0.9061'}
+{'loss': '0.8301', 'grad_norm': '0.4538', 'learning_rate': '0.0001971', 'epoch': '0.907'}
+{'loss': '0.8191', 'grad_norm': '0.4775', 'learning_rate': '0.0001971', 'epoch': '0.9079'}
+{'loss': '0.8334', 'grad_norm': '0.4089', 'learning_rate': '0.000197', 'epoch': '0.9087'}
+{'loss': '0.7917', 'grad_norm': '0.4202', 'learning_rate': '0.000197', 'epoch': '0.9096'}
+{'loss': '0.8018', 'grad_norm': '0.3916', 'learning_rate': '0.000197', 'epoch': '0.9105'}
+{'loss': '0.882', 'grad_norm': '0.4623', 'learning_rate': '0.000197', 'epoch': '0.9113'}
+{'loss': '0.7653', 'grad_norm': '0.4518', 'learning_rate': '0.000197', 'epoch': '0.9122'}
+{'loss': '0.8172', 'grad_norm': '0.4562', 'learning_rate': '0.000197', 'epoch': '0.9131'}
+{'loss': '0.8223', 'grad_norm': '0.4596', 'learning_rate': '0.000197', 'epoch': '0.9139'}
+{'loss': '0.7717', 'grad_norm': '0.446', 'learning_rate': '0.000197', 'epoch': '0.9148'}
+{'loss': '0.8205', 'grad_norm': '0.438', 'learning_rate': '0.000197', 'epoch': '0.9156'}
+{'loss': '0.8126', 'grad_norm': '0.4026', 'learning_rate': '0.0001969', 'epoch': '0.9165'}
+{'loss': '0.7841', 'grad_norm': '0.4243', 'learning_rate': '0.0001969', 'epoch': '0.9174'}
+{'loss': '0.9391', 'grad_norm': '0.4683', 'learning_rate': '0.0001969', 'epoch': '0.9182'}
+{'loss': '0.8336', 'grad_norm': '0.4768', 'learning_rate': '0.0001969', 'epoch': '0.9191'}
+{'loss': '0.9175', 'grad_norm': '0.4567', 'learning_rate': '0.0001969', 'epoch': '0.92'}
+{'loss': '0.7798', 'grad_norm': '0.4373', 'learning_rate': '0.0001969', 'epoch': '0.9208'}
+{'loss': '0.7416', 'grad_norm': '0.4497', 'learning_rate': '0.0001969', 'epoch': '0.9217'}
+{'loss': '0.7714', 'grad_norm': '0.4893', 'learning_rate': '0.0001969', 'epoch': '0.9225'}
+{'loss': '0.821', 'grad_norm': '0.4905', 'learning_rate': '0.0001968', 'epoch': '0.9234'}
+{'loss': '0.7961', 'grad_norm': '0.4362', 'learning_rate': '0.0001968', 'epoch': '0.9243'}
+{'loss': '0.7378', 'grad_norm': '0.42', 'learning_rate': '0.0001968', 'epoch': '0.9251'}
+{'loss': '0.8225', 'grad_norm': '0.4537', 'learning_rate': '0.0001968', 'epoch': '0.926'}
+{'loss': '0.8268', 'grad_norm': '0.4335', 'learning_rate': '0.0001968', 'epoch': '0.9269'}
+{'loss': '0.8528', 'grad_norm': '0.4694', 'learning_rate': '0.0001968', 'epoch': '0.9277'}
+{'loss': '0.8101', 'grad_norm': '0.4282', 'learning_rate': '0.0001968', 'epoch': '0.9286'}
+{'loss': '0.8998', 'grad_norm': '0.4662', 'learning_rate': '0.0001968', 'epoch': '0.9294'}
+{'loss': '0.8378', 'grad_norm': '0.4181', 'learning_rate': '0.0001967', 'epoch': '0.9303'}
+{'loss': '0.8562', 'grad_norm': '0.4789', 'learning_rate': '0.0001967', 'epoch': '0.9312'}
+{'loss': '0.7846', 'grad_norm': '0.4371', 'learning_rate': '0.0001967', 'epoch': '0.932'}
+{'loss': '0.8058', 'grad_norm': '0.4442', 'learning_rate': '0.0001967', 'epoch': '0.9329'}
+{'loss': '0.9161', 'grad_norm': '0.4896', 'learning_rate': '0.0001967', 'epoch': '0.9338'}
+{'loss': '0.8805', 'grad_norm': '0.399', 'learning_rate': '0.0001967', 'epoch': '0.9346'}
+{'loss': '0.8611', 'grad_norm': '0.4299', 'learning_rate': '0.0001967', 'epoch': '0.9355'}
+{'loss': '0.843', 'grad_norm': '0.5267', 'learning_rate': '0.0001967', 'epoch': '0.9364'}
+{'loss': '0.8058', 'grad_norm': '0.4667', 'learning_rate': '0.0001966', 'epoch': '0.9372'}
+{'loss': '0.7457', 'grad_norm': '0.414', 'learning_rate': '0.0001966', 'epoch': '0.9381'}
+{'loss': '0.732', 'grad_norm': '0.4237', 'learning_rate': '0.0001966', 'epoch': '0.9389'}
+{'loss': '0.785', 'grad_norm': '0.4076', 'learning_rate': '0.0001966', 'epoch': '0.9398'}
+{'loss': '0.8228', 'grad_norm': '0.4638', 'learning_rate': '0.0001966', 'epoch': '0.9407'}
+{'loss': '0.8459', 'grad_norm': '0.4642', 'learning_rate': '0.0001966', 'epoch': '0.9415'}
+{'loss': '0.8002', 'grad_norm': '0.4287', 'learning_rate': '0.0001966', 'epoch': '0.9424'}
+{'loss': '0.9096', 'grad_norm': '0.4727', 'learning_rate': '0.0001966', 'epoch': '0.9433'}
+{'loss': '0.7508', 'grad_norm': '0.4036', 'learning_rate': '0.0001965', 'epoch': '0.9441'}
+{'loss': '0.8899', 'grad_norm': '0.4695', 'learning_rate': '0.0001965', 'epoch': '0.945'}
+{'loss': '0.8605', 'grad_norm': '0.4564', 'learning_rate': '0.0001965', 'epoch': '0.9458'}
+{'loss': '0.8315', 'grad_norm': '0.4367', 'learning_rate': '0.0001965', 'epoch': '0.9467'}
+{'loss': '0.8511', 'grad_norm': '0.5415', 'learning_rate': '0.0001965', 'epoch': '0.9476'}
+{'loss': '0.9248', 'grad_norm': '0.4525', 'learning_rate': '0.0001965', 'epoch': '0.9484'}
+{'loss': '0.8114', 'grad_norm': '0.4624', 'learning_rate': '0.0001965', 'epoch': '0.9493'}
+{'eval_loss': '0.8443', 'eval_runtime': '666.6', 'eval_samples_per_second': '3.09', 'eval_steps_per_second': '3.09', 'epoch': '0.9493'}
+{'loss': '0.8152', 'grad_norm': '0.4506', 'learning_rate': '0.0001965', 'epoch': '0.9502'}
+{'loss': '0.9207', 'grad_norm': '0.4287', 'learning_rate': '0.0001964', 'epoch': '0.951'}
+{'loss': '0.8228', 'grad_norm': '0.3899', 'learning_rate': '0.0001964', 'epoch': '0.9519'}
+{'loss': '0.7484', 'grad_norm': '0.4247', 'learning_rate': '0.0001964', 'epoch': '0.9528'}
+{'loss': '0.7357', 'grad_norm': '0.4047', 'learning_rate': '0.0001964', 'epoch': '0.9536'}
+{'loss': '0.7375', 'grad_norm': '0.4608', 'learning_rate': '0.0001964', 'epoch': '0.9545'}
+{'loss': '0.9129', 'grad_norm': '0.4485', 'learning_rate': '0.0001964', 'epoch': '0.9553'}
+{'loss': '0.6984', 'grad_norm': '0.4477', 'learning_rate': '0.0001964', 'epoch': '0.9562'}
+{'loss': '0.8543', 'grad_norm': '0.4146', 'learning_rate': '0.0001963', 'epoch': '0.9571'}
+{'loss': '0.8866', 'grad_norm': '0.5271', 'learning_rate': '0.0001963', 'epoch': '0.9579'}
+{'loss': '0.8415', 'grad_norm': '0.4497', 'learning_rate': '0.0001963', 'epoch': '0.9588'}
+{'loss': '0.886', 'grad_norm': '0.4772', 'learning_rate': '0.0001963', 'epoch': '0.9597'}
+{'loss': '0.8348', 'grad_norm': '0.525', 'learning_rate': '0.0001963', 'epoch': '0.9605'}
+{'loss': '0.7893', 'grad_norm': '0.4931', 'learning_rate': '0.0001963', 'epoch': '0.9614'}
+{'loss': '0.8156', 'grad_norm': '0.4501', 'learning_rate': '0.0001963', 'epoch': '0.9622'}
+{'loss': '0.8073', 'grad_norm': '0.4295', 'learning_rate': '0.0001963', 'epoch': '0.9631'}
+{'loss': '0.8135', 'grad_norm': '0.435', 'learning_rate': '0.0001962', 'epoch': '0.964'}
+{'loss': '0.8021', 'grad_norm': '0.4184', 'learning_rate': '0.0001962', 'epoch': '0.9648'}
+{'loss': '0.7597', 'grad_norm': '0.4581', 'learning_rate': '0.0001962', 'epoch': '0.9657'}
+{'loss': '0.7609', 'grad_norm': '0.3806', 'learning_rate': '0.0001962', 'epoch': '0.9666'}
+{'loss': '0.783', 'grad_norm': '0.391', 'learning_rate': '0.0001962', 'epoch': '0.9674'}
+{'loss': '0.7571', 'grad_norm': '0.3841', 'learning_rate': '0.0001962', 'epoch': '0.9683'}
+{'loss': '0.8635', 'grad_norm': '0.4145', 'learning_rate': '0.0001962', 'epoch': '0.9691'}
+{'loss': '0.9003', 'grad_norm': '0.499', 'learning_rate': '0.0001961', 'epoch': '0.97'}
+{'loss': '0.7588', 'grad_norm': '0.4317', 'learning_rate': '0.0001961', 'epoch': '0.9709'}
+{'loss': '0.6862', 'grad_norm': '0.4129', 'learning_rate': '0.0001961', 'epoch': '0.9717'}
+{'loss': '0.7895', 'grad_norm': '0.4025', 'learning_rate': '0.0001961', 'epoch': '0.9726'}
+{'loss': '0.836', 'grad_norm': '0.4297', 'learning_rate': '0.0001961', 'epoch': '0.9735'}
+{'loss': '0.7625', 'grad_norm': '0.4056', 'learning_rate': '0.0001961', 'epoch': '0.9743'}
+{'loss': '0.8285', 'grad_norm': '0.4487', 'learning_rate': '0.0001961', 'epoch': '0.9752'}
+{'loss': '0.7952', 'grad_norm': '0.3707', 'learning_rate': '0.0001961', 'epoch': '0.9761'}
+{'loss': '0.7641', 'grad_norm': '0.4337', 'learning_rate': '0.000196', 'epoch': '0.9769'}
+{'loss': '0.845', 'grad_norm': '0.4254', 'learning_rate': '0.000196', 'epoch': '0.9778'}
+{'loss': '0.8207', 'grad_norm': '0.4618', 'learning_rate': '0.000196', 'epoch': '0.9786'}
+{'loss': '0.7754', 'grad_norm': '0.3835', 'learning_rate': '0.000196', 'epoch': '0.9795'}
+{'loss': '0.8845', 'grad_norm': '0.4396', 'learning_rate': '0.000196', 'epoch': '0.9804'}
+{'loss': '0.7796', 'grad_norm': '0.4241', 'learning_rate': '0.000196', 'epoch': '0.9812'}
+{'loss': '0.6961', 'grad_norm': '0.4187', 'learning_rate': '0.000196', 'epoch': '0.9821'}
+{'loss': '0.771', 'grad_norm': '0.4387', 'learning_rate': '0.0001959', 'epoch': '0.983'}
+{'loss': '0.7324', 'grad_norm': '0.4533', 'learning_rate': '0.0001959', 'epoch': '0.9838'}
+{'loss': '0.8721', 'grad_norm': '0.43', 'learning_rate': '0.0001959', 'epoch': '0.9847'}
+{'loss': '0.7396', 'grad_norm': '0.4479', 'learning_rate': '0.0001959', 'epoch': '0.9855'}
+{'loss': '0.8304', 'grad_norm': '0.4391', 'learning_rate': '0.0001959', 'epoch': '0.9864'}
+{'loss': '0.7396', 'grad_norm': '0.4047', 'learning_rate': '0.0001959', 'epoch': '0.9873'}
+{'loss': '0.7448', 'grad_norm': '0.462', 'learning_rate': '0.0001959', 'epoch': '0.9881'}
+{'loss': '0.8184', 'grad_norm': '0.4604', 'learning_rate': '0.0001958', 'epoch': '0.989'}
+{'loss': '0.907', 'grad_norm': '0.4829', 'learning_rate': '0.0001958', 'epoch': '0.9899'}
+{'loss': '0.6629', 'grad_norm': '0.3747', 'learning_rate': '0.0001958', 'epoch': '0.9907'}
+{'loss': '0.7712', 'grad_norm': '0.43', 'learning_rate': '0.0001958', 'epoch': '0.9916'}
+{'loss': '0.7796', 'grad_norm': '0.4368', 'learning_rate': '0.0001958', 'epoch': '0.9924'}
+{'eval_loss': '0.8397', 'eval_runtime': '666.2', 'eval_samples_per_second': '3.092', 'eval_steps_per_second': '3.092', 'epoch': '0.9924'}
+{'loss': '0.7504', 'grad_norm': '0.4384', 'learning_rate': '0.0001958', 'epoch': '0.9933'}
+{'loss': '0.7299', 'grad_norm': '0.3896', 'learning_rate': '0.0001958', 'epoch': '0.9942'}
+{'loss': '0.9137', 'grad_norm': '0.495', 'learning_rate': '0.0001957', 'epoch': '0.995'}
+{'loss': '0.9203', 'grad_norm': '0.5116', 'learning_rate': '0.0001957', 'epoch': '0.9959'}
+{'loss': '0.7709', 'grad_norm': '0.4315', 'learning_rate': '0.0001957', 'epoch': '0.9968'}
+{'loss': '0.7911', 'grad_norm': '0.3958', 'learning_rate': '0.0001957', 'epoch': '0.9976'}
+{'loss': '0.8282', 'grad_norm': '0.4569', 'learning_rate': '0.0001957', 'epoch': '0.9985'}
+{'loss': '0.8659', 'grad_norm': '0.4336', 'learning_rate': '0.0001957', 'epoch': '0.9994'}
+{'loss': '0.7823', 'grad_norm': '0.689', 'learning_rate': '0.0001957', 'epoch': '1'}
+{'loss': '0.8244', 'grad_norm': '0.3945', 'learning_rate': '0.0001956', 'epoch': '1.001'}
+{'loss': '0.8228', 'grad_norm': '0.5314', 'learning_rate': '0.0001956', 'epoch': '1.002'}
+{'loss': '0.8628', 'grad_norm': '0.4773', 'learning_rate': '0.0001956', 'epoch': '1.003'}
+{'loss': '0.8811', 'grad_norm': '0.4706', 'learning_rate': '0.0001956', 'epoch': '1.003'}
+{'loss': '0.7736', 'grad_norm': '0.4334', 'learning_rate': '0.0001956', 'epoch': '1.004'}
+{'loss': '0.9185', 'grad_norm': '0.4958', 'learning_rate': '0.0001956', 'epoch': '1.005'}
+{'loss': '0.7388', 'grad_norm': '0.4363', 'learning_rate': '0.0001956', 'epoch': '1.006'}
+{'loss': '0.6722', 'grad_norm': '0.4258', 'learning_rate': '0.0001955', 'epoch': '1.007'}
+{'loss': '0.7638', 'grad_norm': '0.4007', 'learning_rate': '0.0001955', 'epoch': '1.008'}
+{'loss': '0.793', 'grad_norm': '0.4999', 'learning_rate': '0.0001955', 'epoch': '1.009'}
+{'loss': '0.7129', 'grad_norm': '0.3826', 'learning_rate': '0.0001955', 'epoch': '1.009'}
+{'loss': '0.713', 'grad_norm': '0.4654', 'learning_rate': '0.0001955', 'epoch': '1.01'}
+{'loss': '0.7843', 'grad_norm': '0.4199', 'learning_rate': '0.0001955', 'epoch': '1.011'}
+{'loss': '0.6763', 'grad_norm': '0.436', 'learning_rate': '0.0001955', 'epoch': '1.012'}
+{'loss': '0.7426', 'grad_norm': '0.4742', 'learning_rate': '0.0001954', 'epoch': '1.013'}
+{'loss': '0.7419', 'grad_norm': '0.4475', 'learning_rate': '0.0001954', 'epoch': '1.014'}
+{'loss': '0.7374', 'grad_norm': '0.4176', 'learning_rate': '0.0001954', 'epoch': '1.015'}
+{'loss': '0.764', 'grad_norm': '0.4038', 'learning_rate': '0.0001954', 'epoch': '1.016'}
+{'loss': '0.7797', 'grad_norm': '0.4166', 'learning_rate': '0.0001954', 'epoch': '1.016'}
+{'loss': '0.8259', 'grad_norm': '0.4341', 'learning_rate': '0.0001954', 'epoch': '1.017'}
+{'loss': '0.7664', 'grad_norm': '0.4708', 'learning_rate': '0.0001954', 'epoch': '1.018'}
+{'loss': '0.7411', 'grad_norm': '0.4127', 'learning_rate': '0.0001953', 'epoch': '1.019'}
+{'loss': '0.7514', 'grad_norm': '0.4528', 'learning_rate': '0.0001953', 'epoch': '1.02'}
+{'loss': '0.7545', 'grad_norm': '0.4857', 'learning_rate': '0.0001953', 'epoch': '1.021'}
+{'loss': '0.7247', 'grad_norm': '0.5233', 'learning_rate': '0.0001953', 'epoch': '1.022'}
+{'loss': '0.7399', 'grad_norm': '0.4435', 'learning_rate': '0.0001953', 'epoch': '1.022'}
+{'loss': '0.7209', 'grad_norm': '0.4471', 'learning_rate': '0.0001953', 'epoch': '1.023'}
+{'loss': '0.7618', 'grad_norm': '0.4321', 'learning_rate': '0.0001953', 'epoch': '1.024'}
+{'loss': '0.6574', 'grad_norm': '0.4322', 'learning_rate': '0.0001952', 'epoch': '1.025'}
+{'loss': '0.8118', 'grad_norm': '0.4777', 'learning_rate': '0.0001952', 'epoch': '1.026'}
+{'loss': '0.7812', 'grad_norm': '0.5015', 'learning_rate': '0.0001952', 'epoch': '1.027'}
+{'loss': '0.8399', 'grad_norm': '0.5164', 'learning_rate': '0.0001952', 'epoch': '1.028'}
+{'loss': '0.7865', 'grad_norm': '0.4787', 'learning_rate': '0.0001952', 'epoch': '1.028'}
+{'loss': '0.7837', 'grad_norm': '0.4845', 'learning_rate': '0.0001952', 'epoch': '1.029'}
+{'loss': '0.834', 'grad_norm': '0.4762', 'learning_rate': '0.0001951', 'epoch': '1.03'}
+{'loss': '0.7689', 'grad_norm': '0.4281', 'learning_rate': '0.0001951', 'epoch': '1.031'}
+{'loss': '0.8143', 'grad_norm': '0.4785', 'learning_rate': '0.0001951', 'epoch': '1.032'}
+{'loss': '0.7278', 'grad_norm': '0.4499', 'learning_rate': '0.0001951', 'epoch': '1.033'}
+{'loss': '0.8445', 'grad_norm': '0.5142', 'learning_rate': '0.0001951', 'epoch': '1.034'}
+{'loss': '0.7662', 'grad_norm': '0.4857', 'learning_rate': '0.0001951', 'epoch': '1.035'}
+{'loss': '0.7628', 'grad_norm': '0.5076', 'learning_rate': '0.0001951', 'epoch': '1.035'}
+{'eval_loss': '0.837', 'eval_runtime': '653.2', 'eval_samples_per_second': '3.154', 'eval_steps_per_second': '3.154', 'epoch': '1.035'}
+{'loss': '0.8226', 'grad_norm': '0.4942', 'learning_rate': '0.000195', 'epoch': '1.036'}
+{'loss': '0.8239', 'grad_norm': '0.4559', 'learning_rate': '0.000195', 'epoch': '1.037'}
+{'loss': '0.7805', 'grad_norm': '0.4865', 'learning_rate': '0.000195', 'epoch': '1.038'}
+{'loss': '0.8669', 'grad_norm': '0.4411', 'learning_rate': '0.000195', 'epoch': '1.039'}
+{'loss': '0.7602', 'grad_norm': '0.4617', 'learning_rate': '0.000195', 'epoch': '1.04'}
+{'loss': '0.8156', 'grad_norm': '0.4793', 'learning_rate': '0.000195', 'epoch': '1.041'}
+{'loss': '0.788', 'grad_norm': '0.454', 'learning_rate': '0.0001949', 'epoch': '1.041'}
+{'loss': '0.7197', 'grad_norm': '0.4454', 'learning_rate': '0.0001949', 'epoch': '1.042'}
+{'loss': '0.7288', 'grad_norm': '0.4452', 'learning_rate': '0.0001949', 'epoch': '1.043'}
+{'loss': '0.7182', 'grad_norm': '0.4359', 'learning_rate': '0.0001949', 'epoch': '1.044'}
+{'loss': '0.7005', 'grad_norm': '0.444', 'learning_rate': '0.0001949', 'epoch': '1.045'}
+{'loss': '0.7155', 'grad_norm': '0.4658', 'learning_rate': '0.0001949', 'epoch': '1.046'}
+{'loss': '0.717', 'grad_norm': '0.4468', 'learning_rate': '0.0001949', 'epoch': '1.047'}
+{'loss': '0.8346', 'grad_norm': '0.5302', 'learning_rate': '0.0001948', 'epoch': '1.047'}
+{'loss': '0.7129', 'grad_norm': '0.4658', 'learning_rate': '0.0001948', 'epoch': '1.048'}
+{'loss': '0.7991', 'grad_norm': '0.3892', 'learning_rate': '0.0001948', 'epoch': '1.049'}
+{'loss': '0.8573', 'grad_norm': '0.4599', 'learning_rate': '0.0001948', 'epoch': '1.05'}
+{'loss': '0.8108', 'grad_norm': '0.4751', 'learning_rate': '0.0001948', 'epoch': '1.051'}
+{'loss': '0.7433', 'grad_norm': '0.4137', 'learning_rate': '0.0001948', 'epoch': '1.052'}
+{'loss': '0.8034', 'grad_norm': '0.4666', 'learning_rate': '0.0001947', 'epoch': '1.053'}
+{'loss': '0.732', 'grad_norm': '0.4162', 'learning_rate': '0.0001947', 'epoch': '1.054'}
+{'loss': '0.7743', 'grad_norm': '0.4352', 'learning_rate': '0.0001947', 'epoch': '1.054'}
+{'loss': '0.8302', 'grad_norm': '0.5152', 'learning_rate': '0.0001947', 'epoch': '1.055'}
+{'loss': '0.8371', 'grad_norm': '0.5661', 'learning_rate': '0.0001947', 'epoch': '1.056'}
+{'loss': '0.7324', 'grad_norm': '0.4257', 'learning_rate': '0.0001947', 'epoch': '1.057'}
+{'loss': '0.741', 'grad_norm': '0.5477', 'learning_rate': '0.0001947', 'epoch': '1.058'}
+{'loss': '0.6647', 'grad_norm': '0.3736', 'learning_rate': '0.0001946', 'epoch': '1.059'}
+{'loss': '0.7774', 'grad_norm': '0.438', 'learning_rate': '0.0001946', 'epoch': '1.06'}
+{'loss': '0.8978', 'grad_norm': '0.5114', 'learning_rate': '0.0001946', 'epoch': '1.06'}
+{'loss': '0.8128', 'grad_norm': '0.434', 'learning_rate': '0.0001946', 'epoch': '1.061'}
+{'loss': '0.8097', 'grad_norm': '0.4923', 'learning_rate': '0.0001946', 'epoch': '1.062'}
+{'loss': '0.7966', 'grad_norm': '0.4723', 'learning_rate': '0.0001946', 'epoch': '1.063'}
+{'loss': '0.7137', 'grad_norm': '0.4519', 'learning_rate': '0.0001945', 'epoch': '1.064'}
+{'loss': '0.8136', 'grad_norm': '0.4488', 'learning_rate': '0.0001945', 'epoch': '1.065'}
+{'loss': '0.784', 'grad_norm': '0.4224', 'learning_rate': '0.0001945', 'epoch': '1.066'}
+{'loss': '0.8203', 'grad_norm': '0.4979', 'learning_rate': '0.0001945', 'epoch': '1.066'}
+{'loss': '0.8608', 'grad_norm': '0.5551', 'learning_rate': '0.0001945', 'epoch': '1.067'}
+{'loss': '0.7203', 'grad_norm': '0.3981', 'learning_rate': '0.0001945', 'epoch': '1.068'}
+{'loss': '0.8302', 'grad_norm': '0.5393', 'learning_rate': '0.0001944', 'epoch': '1.069'}
+{'loss': '0.7006', 'grad_norm': '0.4772', 'learning_rate': '0.0001944', 'epoch': '1.07'}
+{'loss': '0.795', 'grad_norm': '0.5198', 'learning_rate': '0.0001944', 'epoch': '1.071'}
+{'loss': '0.8052', 'grad_norm': '0.5289', 'learning_rate': '0.0001944', 'epoch': '1.072'}
+{'loss': '0.751', 'grad_norm': '0.436', 'learning_rate': '0.0001944', 'epoch': '1.072'}
+{'loss': '0.6632', 'grad_norm': '0.3865', 'learning_rate': '0.0001944', 'epoch': '1.073'}
+{'loss': '0.7995', 'grad_norm': '0.4376', 'learning_rate': '0.0001943', 'epoch': '1.074'}
+{'loss': '0.7634', 'grad_norm': '0.4664', 'learning_rate': '0.0001943', 'epoch': '1.075'}
+{'loss': '0.7282', 'grad_norm': '0.435', 'learning_rate': '0.0001943', 'epoch': '1.076'}
+{'loss': '0.7314', 'grad_norm': '0.3968', 'learning_rate': '0.0001943', 'epoch': '1.077'}
+{'loss': '0.712', 'grad_norm': '0.4546', 'learning_rate': '0.0001943', 'epoch': '1.078'}
+{'loss': '0.7526', 'grad_norm': '0.5041', 'learning_rate': '0.0001943', 'epoch': '1.079'}
+{'eval_loss': '0.8323', 'eval_runtime': '652.4', 'eval_samples_per_second': '3.158', 'eval_steps_per_second': '3.158', 'epoch': '1.079'}
+{'loss': '0.772', 'grad_norm': '0.4895', 'learning_rate': '0.0001942', 'epoch': '1.079'}
+{'loss': '0.7921', 'grad_norm': '0.501', 'learning_rate': '0.0001942', 'epoch': '1.08'}
+{'loss': '0.7714', 'grad_norm': '0.4699', 'learning_rate': '0.0001942', 'epoch': '1.081'}
+{'loss': '0.6982', 'grad_norm': '0.4439', 'learning_rate': '0.0001942', 'epoch': '1.082'}
+{'loss': '0.7822', 'grad_norm': '0.4993', 'learning_rate': '0.0001942', 'epoch': '1.083'}
+{'loss': '0.7167', 'grad_norm': '0.3954', 'learning_rate': '0.0001942', 'epoch': '1.084'}
+{'loss': '0.7287', 'grad_norm': '0.4729', 'learning_rate': '0.0001941', 'epoch': '1.085'}
+{'loss': '0.7672', 'grad_norm': '0.4317', 'learning_rate': '0.0001941', 'epoch': '1.085'}
+{'loss': '0.7427', 'grad_norm': '0.4542', 'learning_rate': '0.0001941', 'epoch': '1.086'}
+{'loss': '0.7429', 'grad_norm': '0.4921', 'learning_rate': '0.0001941', 'epoch': '1.087'}
+{'loss': '0.7671', 'grad_norm': '0.5404', 'learning_rate': '0.0001941', 'epoch': '1.088'}
+{'loss': '0.673', 'grad_norm': '0.4543', 'learning_rate': '0.0001941', 'epoch': '1.089'}
+{'loss': '0.6908', 'grad_norm': '0.4917', 'learning_rate': '0.0001941', 'epoch': '1.09'}
+{'loss': '0.7644', 'grad_norm': '0.4913', 'learning_rate': '0.000194', 'epoch': '1.091'}
+{'loss': '0.8071', 'grad_norm': '0.5279', 'learning_rate': '0.000194', 'epoch': '1.091'}
+{'loss': '0.79', 'grad_norm': '0.4319', 'learning_rate': '0.000194', 'epoch': '1.092'}
+{'loss': '0.7778', 'grad_norm': '0.4903', 'learning_rate': '0.000194', 'epoch': '1.093'}
+{'loss': '0.7759', 'grad_norm': '0.4835', 'learning_rate': '0.000194', 'epoch': '1.094'}
+{'loss': '0.7928', 'grad_norm': '0.4713', 'learning_rate': '0.0001939', 'epoch': '1.095'}
+{'loss': '0.7885', 'grad_norm': '0.4672', 'learning_rate': '0.0001939', 'epoch': '1.096'}
+{'loss': '0.7664', 'grad_norm': '0.4627', 'learning_rate': '0.0001939', 'epoch': '1.097'}
+{'loss': '0.6656', 'grad_norm': '0.4319', 'learning_rate': '0.0001939', 'epoch': '1.098'}
+{'loss': '0.7955', 'grad_norm': '0.5139', 'learning_rate': '0.0001939', 'epoch': '1.098'}
+{'loss': '0.8073', 'grad_norm': '0.468', 'learning_rate': '0.0001939', 'epoch': '1.099'}
+{'loss': '0.6828', 'grad_norm': '0.4731', 'learning_rate': '0.0001938', 'epoch': '1.1'}
+{'loss': '0.867', 'grad_norm': '0.4994', 'learning_rate': '0.0001938', 'epoch': '1.101'}
+{'loss': '0.7383', 'grad_norm': '0.474', 'learning_rate': '0.0001938', 'epoch': '1.102'}
+{'loss': '0.7241', 'grad_norm': '0.478', 'learning_rate': '0.0001938', 'epoch': '1.103'}
+{'loss': '0.7362', 'grad_norm': '0.4535', 'learning_rate': '0.0001938', 'epoch': '1.104'}
+{'loss': '0.7365', 'grad_norm': '0.4594', 'learning_rate': '0.0001938', 'epoch': '1.104'}
+{'loss': '0.8036', 'grad_norm': '0.4535', 'learning_rate': '0.0001937', 'epoch': '1.105'}
+{'loss': '0.7224', 'grad_norm': '0.4731', 'learning_rate': '0.0001937', 'epoch': '1.106'}
+{'loss': '0.7446', 'grad_norm': '0.4453', 'learning_rate': '0.0001937', 'epoch': '1.107'}
+{'loss': '0.7666', 'grad_norm': '0.5266', 'learning_rate': '0.0001937', 'epoch': '1.108'}
+{'loss': '0.8593', 'grad_norm': '0.4414', 'learning_rate': '0.0001937', 'epoch': '1.109'}
+{'loss': '0.7769', 'grad_norm': '0.5524', 'learning_rate': '0.0001937', 'epoch': '1.11'}
+{'loss': '0.7357', 'grad_norm': '0.4223', 'learning_rate': '0.0001936', 'epoch': '1.11'}
+{'loss': '0.7694', 'grad_norm': '0.5105', 'learning_rate': '0.0001936', 'epoch': '1.111'}
+{'loss': '0.7651', 'grad_norm': '0.4071', 'learning_rate': '0.0001936', 'epoch': '1.112'}
+{'loss': '0.8427', 'grad_norm': '0.4819', 'learning_rate': '0.0001936', 'epoch': '1.113'}
+{'loss': '0.7783', 'grad_norm': '0.4587', 'learning_rate': '0.0001936', 'epoch': '1.114'}
+{'loss': '0.6625', 'grad_norm': '0.4395', 'learning_rate': '0.0001936', 'epoch': '1.115'}
+{'loss': '0.7208', 'grad_norm': '0.4524', 'learning_rate': '0.0001935', 'epoch': '1.116'}
+{'loss': '0.7567', 'grad_norm': '0.4748', 'learning_rate': '0.0001935', 'epoch': '1.117'}
+{'loss': '0.7632', 'grad_norm': '0.4494', 'learning_rate': '0.0001935', 'epoch': '1.117'}
+{'loss': '0.7757', 'grad_norm': '0.454', 'learning_rate': '0.0001935', 'epoch': '1.118'}
+{'loss': '0.7517', 'grad_norm': '0.4246', 'learning_rate': '0.0001935', 'epoch': '1.119'}
+{'loss': '0.7058', 'grad_norm': '0.448', 'learning_rate': '0.0001935', 'epoch': '1.12'}
+{'loss': '0.8071', 'grad_norm': '0.4591', 'learning_rate': '0.0001934', 'epoch': '1.121'}
+{'loss': '0.6992', 'grad_norm': '0.3947', 'learning_rate': '0.0001934', 'epoch': '1.122'}
+{'eval_loss': '0.83', 'eval_runtime': '658.9', 'eval_samples_per_second': '3.126', 'eval_steps_per_second': '3.126', 'epoch': '1.122'}
+{'loss': '0.7683', 'grad_norm': '0.4091', 'learning_rate': '0.0001934', 'epoch': '1.123'}
+{'loss': '0.7049', 'grad_norm': '0.4274', 'learning_rate': '0.0001934', 'epoch': '1.123'}
+{'loss': '0.7207', 'grad_norm': '0.4436', 'learning_rate': '0.0001934', 'epoch': '1.124'}
+{'loss': '0.823', 'grad_norm': '0.4841', 'learning_rate': '0.0001933', 'epoch': '1.125'}
+{'loss': '0.7833', 'grad_norm': '0.5061', 'learning_rate': '0.0001933', 'epoch': '1.126'}
+{'loss': '0.7786', 'grad_norm': '0.489', 'learning_rate': '0.0001933', 'epoch': '1.127'}
+{'loss': '0.8003', 'grad_norm': '0.4618', 'learning_rate': '0.0001933', 'epoch': '1.128'}
+{'loss': '0.7647', 'grad_norm': '0.4946', 'learning_rate': '0.0001933', 'epoch': '1.129'}
+{'loss': '0.7272', 'grad_norm': '0.4154', 'learning_rate': '0.0001933', 'epoch': '1.129'}
+{'loss': '0.7927', 'grad_norm': '0.4671', 'learning_rate': '0.0001932', 'epoch': '1.13'}
+{'loss': '0.8107', 'grad_norm': '0.4981', 'learning_rate': '0.0001932', 'epoch': '1.131'}
+{'loss': '0.7209', 'grad_norm': '0.4301', 'learning_rate': '0.0001932', 'epoch': '1.132'}
+{'loss': '0.7212', 'grad_norm': '0.4757', 'learning_rate': '0.0001932', 'epoch': '1.133'}
+{'loss': '0.6726', 'grad_norm': '0.4502', 'learning_rate': '0.0001932', 'epoch': '1.134'}
+{'loss': '0.7583', 'grad_norm': '0.4846', 'learning_rate': '0.0001932', 'epoch': '1.135'}
+{'loss': '0.7708', 'grad_norm': '0.4589', 'learning_rate': '0.0001931', 'epoch': '1.135'}
+{'loss': '0.7825', 'grad_norm': '0.4708', 'learning_rate': '0.0001931', 'epoch': '1.136'}
+{'loss': '0.775', 'grad_norm': '0.5212', 'learning_rate': '0.0001931', 'epoch': '1.137'}
+{'loss': '0.7692', 'grad_norm': '0.4952', 'learning_rate': '0.0001931', 'epoch': '1.138'}
+{'loss': '0.7372', 'grad_norm': '0.4428', 'learning_rate': '0.0001931', 'epoch': '1.139'}
+{'loss': '0.7488', 'grad_norm': '0.5063', 'learning_rate': '0.000193', 'epoch': '1.14'}
+{'loss': '0.7647', 'grad_norm': '0.4572', 'learning_rate': '0.000193', 'epoch': '1.141'}
+{'loss': '0.8173', 'grad_norm': '0.4918', 'learning_rate': '0.000193', 'epoch': '1.142'}
+{'loss': '0.6473', 'grad_norm': '0.4006', 'learning_rate': '0.000193', 'epoch': '1.142'}
+{'loss': '0.8463', 'grad_norm': '0.4328', 'learning_rate': '0.000193', 'epoch': '1.143'}
+{'loss': '0.8084', 'grad_norm': '0.3654', 'learning_rate': '0.000193', 'epoch': '1.144'}
+{'loss': '0.7144', 'grad_norm': '0.4236', 'learning_rate': '0.0001929', 'epoch': '1.145'}
+{'loss': '0.6932', 'grad_norm': '0.4316', 'learning_rate': '0.0001929', 'epoch': '1.146'}
+{'loss': '0.7982', 'grad_norm': '0.4309', 'learning_rate': '0.0001929', 'epoch': '1.147'}
+{'loss': '0.7343', 'grad_norm': '0.4201', 'learning_rate': '0.0001929', 'epoch': '1.148'}
+{'loss': '0.724', 'grad_norm': '0.4462', 'learning_rate': '0.0001929', 'epoch': '1.148'}
+{'loss': '0.6575', 'grad_norm': '0.3945', 'learning_rate': '0.0001928', 'epoch': '1.149'}
+{'loss': '0.7754', 'grad_norm': '0.4653', 'learning_rate': '0.0001928', 'epoch': '1.15'}
+{'loss': '0.6839', 'grad_norm': '0.4754', 'learning_rate': '0.0001928', 'epoch': '1.151'}
+{'loss': '0.6908', 'grad_norm': '0.4192', 'learning_rate': '0.0001928', 'epoch': '1.152'}
+{'loss': '0.8363', 'grad_norm': '0.4643', 'learning_rate': '0.0001928', 'epoch': '1.153'}
+{'loss': '0.7377', 'grad_norm': '0.4214', 'learning_rate': '0.0001928', 'epoch': '1.154'}
+{'loss': '0.7618', 'grad_norm': '0.5371', 'learning_rate': '0.0001927', 'epoch': '1.154'}
+{'loss': '0.7253', 'grad_norm': '0.478', 'learning_rate': '0.0001927', 'epoch': '1.155'}
+{'loss': '0.7671', 'grad_norm': '0.4865', 'learning_rate': '0.0001927', 'epoch': '1.156'}
+{'loss': '0.8649', 'grad_norm': '0.5375', 'learning_rate': '0.0001927', 'epoch': '1.157'}
+{'loss': '0.6848', 'grad_norm': '0.4217', 'learning_rate': '0.0001927', 'epoch': '1.158'}
+{'loss': '0.6891', 'grad_norm': '0.3887', 'learning_rate': '0.0001926', 'epoch': '1.159'}
+{'loss': '0.74', 'grad_norm': '0.4271', 'learning_rate': '0.0001926', 'epoch': '1.16'}
+{'loss': '0.8026', 'grad_norm': '0.488', 'learning_rate': '0.0001926', 'epoch': '1.161'}
+{'loss': '0.759', 'grad_norm': '0.4717', 'learning_rate': '0.0001926', 'epoch': '1.161'}
+{'loss': '0.7621', 'grad_norm': '0.4741', 'learning_rate': '0.0001926', 'epoch': '1.162'}
+{'loss': '0.7989', 'grad_norm': '0.5378', 'learning_rate': '0.0001926', 'epoch': '1.163'}
+{'loss': '0.7551', 'grad_norm': '0.4499', 'learning_rate': '0.0001925', 'epoch': '1.164'}
+{'loss': '0.792', 'grad_norm': '0.4633', 'learning_rate': '0.0001925', 'epoch': '1.165'}
+{'eval_loss': '0.8251', 'eval_runtime': '667', 'eval_samples_per_second': '3.088', 'eval_steps_per_second': '3.088', 'epoch': '1.165'}
+{'loss': '0.8141', 'grad_norm': '0.434', 'learning_rate': '0.0001925', 'epoch': '1.166'}
+{'loss': '0.8462', 'grad_norm': '0.5794', 'learning_rate': '0.0001925', 'epoch': '1.167'}
+{'loss': '0.7469', 'grad_norm': '0.4182', 'learning_rate': '0.0001925', 'epoch': '1.167'}
+{'loss': '0.6948', 'grad_norm': '0.4002', 'learning_rate': '0.0001924', 'epoch': '1.168'}
+{'loss': '0.7513', 'grad_norm': '0.4775', 'learning_rate': '0.0001924', 'epoch': '1.169'}
+{'loss': '0.807', 'grad_norm': '0.4585', 'learning_rate': '0.0001924', 'epoch': '1.17'}
+{'loss': '0.7023', 'grad_norm': '0.4337', 'learning_rate': '0.0001924', 'epoch': '1.171'}
+{'loss': '0.6904', 'grad_norm': '0.4004', 'learning_rate': '0.0001924', 'epoch': '1.172'}
+{'loss': '0.7925', 'grad_norm': '0.4845', 'learning_rate': '0.0001923', 'epoch': '1.173'}
+{'loss': '0.7384', 'grad_norm': '0.4917', 'learning_rate': '0.0001923', 'epoch': '1.173'}
+{'loss': '0.7509', 'grad_norm': '0.4363', 'learning_rate': '0.0001923', 'epoch': '1.174'}
+{'loss': '0.7815', 'grad_norm': '0.452', 'learning_rate': '0.0001923', 'epoch': '1.175'}
+{'loss': '0.7012', 'grad_norm': '0.4676', 'learning_rate': '0.0001923', 'epoch': '1.176'}
+{'loss': '0.7415', 'grad_norm': '0.4754', 'learning_rate': '0.0001922', 'epoch': '1.177'}
+{'loss': '0.7949', 'grad_norm': '0.5456', 'learning_rate': '0.0001922', 'epoch': '1.178'}
+{'loss': '0.8139', 'grad_norm': '0.4898', 'learning_rate': '0.0001922', 'epoch': '1.179'}
+{'loss': '0.7445', 'grad_norm': '0.4677', 'learning_rate': '0.0001922', 'epoch': '1.18'}
+{'loss': '0.7938', 'grad_norm': '0.415', 'learning_rate': '0.0001922', 'epoch': '1.18'}
+{'loss': '0.7342', 'grad_norm': '0.4191', 'learning_rate': '0.0001922', 'epoch': '1.181'}
+{'loss': '0.7534', 'grad_norm': '0.4782', 'learning_rate': '0.0001921', 'epoch': '1.182'}
+{'loss': '0.7999', 'grad_norm': '0.4491', 'learning_rate': '0.0001921', 'epoch': '1.183'}
+{'loss': '0.7469', 'grad_norm': '0.4805', 'learning_rate': '0.0001921', 'epoch': '1.184'}
+{'loss': '0.7423', 'grad_norm': '0.4311', 'learning_rate': '0.0001921', 'epoch': '1.185'}
+{'loss': '0.7046', 'grad_norm': '0.4394', 'learning_rate': '0.0001921', 'epoch': '1.186'}
+{'loss': '0.7285', 'grad_norm': '0.423', 'learning_rate': '0.000192', 'epoch': '1.186'}
+{'loss': '0.7298', 'grad_norm': '0.4583', 'learning_rate': '0.000192', 'epoch': '1.187'}
+{'loss': '0.7171', 'grad_norm': '0.4453', 'learning_rate': '0.000192', 'epoch': '1.188'}
+{'loss': '0.7746', 'grad_norm': '0.4666', 'learning_rate': '0.000192', 'epoch': '1.189'}
+{'loss': '0.7382', 'grad_norm': '0.4023', 'learning_rate': '0.000192', 'epoch': '1.19'}
+{'loss': '0.7951', 'grad_norm': '0.5126', 'learning_rate': '0.0001919', 'epoch': '1.191'}
+{'loss': '0.6928', 'grad_norm': '0.4056', 'learning_rate': '0.0001919', 'epoch': '1.192'}
+{'loss': '0.7494', 'grad_norm': '0.4923', 'learning_rate': '0.0001919', 'epoch': '1.192'}
+{'loss': '0.8541', 'grad_norm': '0.4782', 'learning_rate': '0.0001919', 'epoch': '1.193'}
+{'loss': '0.8018', 'grad_norm': '0.4618', 'learning_rate': '0.0001919', 'epoch': '1.194'}
+{'loss': '0.7509', 'grad_norm': '0.4889', 'learning_rate': '0.0001918', 'epoch': '1.195'}
+{'loss': '0.7124', 'grad_norm': '0.4141', 'learning_rate': '0.0001918', 'epoch': '1.196'}
+{'loss': '0.7371', 'grad_norm': '0.4918', 'learning_rate': '0.0001918', 'epoch': '1.197'}
+{'loss': '0.7086', 'grad_norm': '0.4822', 'learning_rate': '0.0001918', 'epoch': '1.198'}
+{'loss': '0.7277', 'grad_norm': '0.4559', 'learning_rate': '0.0001918', 'epoch': '1.198'}
+{'loss': '0.7502', 'grad_norm': '0.3959', 'learning_rate': '0.0001917', 'epoch': '1.199'}
+{'loss': '0.8843', 'grad_norm': '0.6229', 'learning_rate': '0.0001917', 'epoch': '1.2'}
+{'loss': '0.7009', 'grad_norm': '0.4347', 'learning_rate': '0.0001917', 'epoch': '1.201'}
+{'loss': '0.7204', 'grad_norm': '0.6913', 'learning_rate': '0.0001917', 'epoch': '1.202'}
+{'loss': '0.7171', 'grad_norm': '0.422', 'learning_rate': '0.0001917', 'epoch': '1.203'}
+{'loss': '0.7895', 'grad_norm': '0.464', 'learning_rate': '0.0001917', 'epoch': '1.204'}
+{'loss': '0.7323', 'grad_norm': '0.4494', 'learning_rate': '0.0001916', 'epoch': '1.205'}
+{'loss': '0.7487', 'grad_norm': '0.4363', 'learning_rate': '0.0001916', 'epoch': '1.205'}
+{'loss': '0.7771', 'grad_norm': '0.4298', 'learning_rate': '0.0001916', 'epoch': '1.206'}
+{'loss': '0.8006', 'grad_norm': '0.4631', 'learning_rate': '0.0001916', 'epoch': '1.207'}
+{'loss': '0.6764', 'grad_norm': '0.4361', 'learning_rate': '0.0001916', 'epoch': '1.208'}
+{'eval_loss': '0.8219', 'eval_runtime': '661.5', 'eval_samples_per_second': '3.114', 'eval_steps_per_second': '3.114', 'epoch': '1.208'}
+{'loss': '0.7569', 'grad_norm': '0.491', 'learning_rate': '0.0001915', 'epoch': '1.209'}
+{'loss': '0.7344', 'grad_norm': '0.4993', 'learning_rate': '0.0001915', 'epoch': '1.21'}
+{'loss': '0.7191', 'grad_norm': '0.4874', 'learning_rate': '0.0001915', 'epoch': '1.211'}
+{'loss': '0.8491', 'grad_norm': '0.4084', 'learning_rate': '0.0001915', 'epoch': '1.211'}
+{'loss': '0.7605', 'grad_norm': '0.4316', 'learning_rate': '0.0001915', 'epoch': '1.212'}
+{'loss': '0.774', 'grad_norm': '0.4295', 'learning_rate': '0.0001914', 'epoch': '1.213'}
+{'loss': '0.7625', 'grad_norm': '0.4774', 'learning_rate': '0.0001914', 'epoch': '1.214'}
+{'loss': '0.7225', 'grad_norm': '0.4615', 'learning_rate': '0.0001914', 'epoch': '1.215'}
+{'loss': '0.7709', 'grad_norm': '0.4363', 'learning_rate': '0.0001914', 'epoch': '1.216'}
+{'loss': '0.855', 'grad_norm': '0.4959', 'learning_rate': '0.0001914', 'epoch': '1.217'}
+{'loss': '0.7816', 'grad_norm': '0.4672', 'learning_rate': '0.0001913', 'epoch': '1.217'}
+{'loss': '0.8608', 'grad_norm': '0.5249', 'learning_rate': '0.0001913', 'epoch': '1.218'}
+{'loss': '0.7157', 'grad_norm': '0.5133', 'learning_rate': '0.0001913', 'epoch': '1.219'}
+{'loss': '0.728', 'grad_norm': '0.4292', 'learning_rate': '0.0001913', 'epoch': '1.22'}
+{'loss': '0.7165', 'grad_norm': '0.3699', 'learning_rate': '0.0001913', 'epoch': '1.221'}
+{'loss': '0.8114', 'grad_norm': '0.5034', 'learning_rate': '0.0001912', 'epoch': '1.222'}
+{'loss': '0.735', 'grad_norm': '0.4612', 'learning_rate': '0.0001912', 'epoch': '1.223'}
+{'loss': '0.8156', 'grad_norm': '0.4434', 'learning_rate': '0.0001912', 'epoch': '1.224'}
+{'loss': '0.7824', 'grad_norm': '0.4701', 'learning_rate': '0.0001912', 'epoch': '1.224'}
+{'loss': '0.8136', 'grad_norm': '0.4854', 'learning_rate': '0.0001912', 'epoch': '1.225'}
+{'loss': '0.7042', 'grad_norm': '0.4404', 'learning_rate': '0.0001911', 'epoch': '1.226'}
+{'loss': '0.7599', 'grad_norm': '0.4311', 'learning_rate': '0.0001911', 'epoch': '1.227'}
+{'loss': '0.8001', 'grad_norm': '0.5552', 'learning_rate': '0.0001911', 'epoch': '1.228'}
+{'loss': '0.6875', 'grad_norm': '0.4415', 'learning_rate': '0.0001911', 'epoch': '1.229'}
+{'loss': '0.7484', 'grad_norm': '0.4473', 'learning_rate': '0.0001911', 'epoch': '1.23'}
+{'loss': '0.7513', 'grad_norm': '0.471', 'learning_rate': '0.000191', 'epoch': '1.23'}
+{'loss': '0.7161', 'grad_norm': '0.4305', 'learning_rate': '0.000191', 'epoch': '1.231'}
+{'loss': '0.7222', 'grad_norm': '0.4651', 'learning_rate': '0.000191', 'epoch': '1.232'}
+{'loss': '0.8201', 'grad_norm': '0.5231', 'learning_rate': '0.000191', 'epoch': '1.233'}
+{'loss': '0.753', 'grad_norm': '0.4557', 'learning_rate': '0.000191', 'epoch': '1.234'}
+{'loss': '0.7574', 'grad_norm': '0.4452', 'learning_rate': '0.0001909', 'epoch': '1.235'}
+{'loss': '0.8461', 'grad_norm': '0.4558', 'learning_rate': '0.0001909', 'epoch': '1.236'}
+{'loss': '0.791', 'grad_norm': '0.4112', 'learning_rate': '0.0001909', 'epoch': '1.236'}
+{'loss': '0.8319', 'grad_norm': '0.5088', 'learning_rate': '0.0001909', 'epoch': '1.237'}
+{'loss': '0.7134', 'grad_norm': '0.4244', 'learning_rate': '0.0001908', 'epoch': '1.238'}
+{'loss': '0.7698', 'grad_norm': '0.3965', 'learning_rate': '0.0001908', 'epoch': '1.239'}
+{'loss': '0.7438', 'grad_norm': '0.4493', 'learning_rate': '0.0001908', 'epoch': '1.24'}
+{'loss': '0.8581', 'grad_norm': '0.519', 'learning_rate': '0.0001908', 'epoch': '1.241'}
+{'loss': '0.7235', 'grad_norm': '0.3946', 'learning_rate': '0.0001908', 'epoch': '1.242'}
+{'loss': '0.7996', 'grad_norm': '0.5248', 'learning_rate': '0.0001907', 'epoch': '1.243'}
+{'loss': '0.8404', 'grad_norm': '0.4873', 'learning_rate': '0.0001907', 'epoch': '1.243'}
+{'loss': '0.7541', 'grad_norm': '0.4592', 'learning_rate': '0.0001907', 'epoch': '1.244'}
+{'loss': '0.7567', 'grad_norm': '0.484', 'learning_rate': '0.0001907', 'epoch': '1.245'}
+{'loss': '0.7141', 'grad_norm': '0.4854', 'learning_rate': '0.0001907', 'epoch': '1.246'}
+{'loss': '0.7798', 'grad_norm': '0.4585', 'learning_rate': '0.0001906', 'epoch': '1.247'}
+{'loss': '0.7212', 'grad_norm': '0.4585', 'learning_rate': '0.0001906', 'epoch': '1.248'}
+{'loss': '0.8268', 'grad_norm': '0.5283', 'learning_rate': '0.0001906', 'epoch': '1.249'}
+{'loss': '0.7513', 'grad_norm': '0.41', 'learning_rate': '0.0001906', 'epoch': '1.249'}
+{'loss': '0.6681', 'grad_norm': '0.3956', 'learning_rate': '0.0001906', 'epoch': '1.25'}
+{'loss': '0.7308', 'grad_norm': '0.42', 'learning_rate': '0.0001905', 'epoch': '1.251'}
+{'eval_loss': '0.8156', 'eval_runtime': '650.6', 'eval_samples_per_second': '3.166', 'eval_steps_per_second': '3.166', 'epoch': '1.251'}
+{'loss': '0.7316', 'grad_norm': '0.3915', 'learning_rate': '0.0001905', 'epoch': '1.252'}
+{'loss': '0.8977', 'grad_norm': '0.4894', 'learning_rate': '0.0001905', 'epoch': '1.253'}
+{'loss': '0.7962', 'grad_norm': '0.4892', 'learning_rate': '0.0001905', 'epoch': '1.254'}
+{'loss': '0.7914', 'grad_norm': '0.5324', 'learning_rate': '0.0001905', 'epoch': '1.255'}
+{'loss': '0.7218', 'grad_norm': '0.4478', 'learning_rate': '0.0001904', 'epoch': '1.255'}
+{'loss': '0.7381', 'grad_norm': '0.4763', 'learning_rate': '0.0001904', 'epoch': '1.256'}
+{'loss': '0.7586', 'grad_norm': '0.498', 'learning_rate': '0.0001904', 'epoch': '1.257'}
+{'loss': '0.7635', 'grad_norm': '0.4618', 'learning_rate': '0.0001904', 'epoch': '1.258'}
+{'loss': '0.7479', 'grad_norm': '0.4319', 'learning_rate': '0.0001903', 'epoch': '1.259'}
+{'loss': '0.7355', 'grad_norm': '0.4288', 'learning_rate': '0.0001903', 'epoch': '1.26'}
+{'loss': '0.7763', 'grad_norm': '0.4771', 'learning_rate': '0.0001903', 'epoch': '1.261'}
+{'loss': '0.6964', 'grad_norm': '0.4478', 'learning_rate': '0.0001903', 'epoch': '1.261'}
+{'loss': '0.7415', 'grad_norm': '0.4531', 'learning_rate': '0.0001903', 'epoch': '1.262'}
+{'loss': '0.7639', 'grad_norm': '0.4624', 'learning_rate': '0.0001902', 'epoch': '1.263'}
+{'loss': '0.8005', 'grad_norm': '0.4363', 'learning_rate': '0.0001902', 'epoch': '1.264'}
+{'loss': '0.796', 'grad_norm': '0.4285', 'learning_rate': '0.0001902', 'epoch': '1.265'}
+{'loss': '0.7544', 'grad_norm': '0.4748', 'learning_rate': '0.0001902', 'epoch': '1.266'}
+{'loss': '0.782', 'grad_norm': '0.4585', 'learning_rate': '0.0001902', 'epoch': '1.267'}
+{'loss': '0.7719', 'grad_norm': '0.5465', 'learning_rate': '0.0001901', 'epoch': '1.268'}
+{'loss': '0.7442', 'grad_norm': '0.4202', 'learning_rate': '0.0001901', 'epoch': '1.268'}
+{'loss': '0.6696', 'grad_norm': '0.4375', 'learning_rate': '0.0001901', 'epoch': '1.269'}
+{'loss': '0.7048', 'grad_norm': '0.4136', 'learning_rate': '0.0001901', 'epoch': '1.27'}
+{'loss': '0.7588', 'grad_norm': '0.4463', 'learning_rate': '0.0001901', 'epoch': '1.271'}
+{'loss': '0.7741', 'grad_norm': '0.4317', 'learning_rate': '0.00019', 'epoch': '1.272'}
+{'loss': '0.7572', 'grad_norm': '0.519', 'learning_rate': '0.00019', 'epoch': '1.273'}
+{'loss': '0.7743', 'grad_norm': '0.4256', 'learning_rate': '0.00019', 'epoch': '1.274'}
+{'loss': '0.7288', 'grad_norm': '0.4305', 'learning_rate': '0.00019', 'epoch': '1.274'}
+{'loss': '0.7931', 'grad_norm': '0.4894', 'learning_rate': '0.0001899', 'epoch': '1.275'}
+{'loss': '0.7283', 'grad_norm': '0.3856', 'learning_rate': '0.0001899', 'epoch': '1.276'}
+{'loss': '0.7218', 'grad_norm': '0.4671', 'learning_rate': '0.0001899', 'epoch': '1.277'}
+{'loss': '0.6679', 'grad_norm': '0.3664', 'learning_rate': '0.0001899', 'epoch': '1.278'}
+{'loss': '0.8022', 'grad_norm': '0.5075', 'learning_rate': '0.0001899', 'epoch': '1.279'}
+{'loss': '0.8313', 'grad_norm': '0.4903', 'learning_rate': '0.0001898', 'epoch': '1.28'}
+{'loss': '0.833', 'grad_norm': '0.5023', 'learning_rate': '0.0001898', 'epoch': '1.28'}
+{'loss': '0.8806', 'grad_norm': '0.4823', 'learning_rate': '0.0001898', 'epoch': '1.281'}
+{'loss': '0.6835', 'grad_norm': '0.4014', 'learning_rate': '0.0001898', 'epoch': '1.282'}
+{'loss': '0.7208', 'grad_norm': '0.4368', 'learning_rate': '0.0001898', 'epoch': '1.283'}
+{'loss': '0.691', 'grad_norm': '0.3999', 'learning_rate': '0.0001897', 'epoch': '1.284'}
+{'loss': '0.8384', 'grad_norm': '0.4826', 'learning_rate': '0.0001897', 'epoch': '1.285'}
+{'loss': '0.7693', 'grad_norm': '0.4861', 'learning_rate': '0.0001897', 'epoch': '1.286'}
+{'loss': '0.7662', 'grad_norm': '0.4362', 'learning_rate': '0.0001897', 'epoch': '1.287'}
+{'loss': '0.7524', 'grad_norm': '0.4533', 'learning_rate': '0.0001896', 'epoch': '1.287'}
+{'loss': '0.7524', 'grad_norm': '0.4825', 'learning_rate': '0.0001896', 'epoch': '1.288'}
+{'loss': '0.8565', 'grad_norm': '0.5304', 'learning_rate': '0.0001896', 'epoch': '1.289'}
+{'loss': '0.7839', 'grad_norm': '0.4386', 'learning_rate': '0.0001896', 'epoch': '1.29'}
+{'loss': '0.7581', 'grad_norm': '0.438', 'learning_rate': '0.0001896', 'epoch': '1.291'}
+{'loss': '0.7014', 'grad_norm': '0.4498', 'learning_rate': '0.0001895', 'epoch': '1.292'}
+{'loss': '0.822', 'grad_norm': '0.566', 'learning_rate': '0.0001895', 'epoch': '1.293'}
+{'loss': '0.688', 'grad_norm': '0.485', 'learning_rate': '0.0001895', 'epoch': '1.293'}
+{'loss': '0.7444', 'grad_norm': '0.4254', 'learning_rate': '0.0001895', 'epoch': '1.294'}
+{'eval_loss': '0.8128', 'eval_runtime': '650.4', 'eval_samples_per_second': '3.167', 'eval_steps_per_second': '3.167', 'epoch': '1.294'}
+{'loss': '0.6589', 'grad_norm': '0.3746', 'learning_rate': '0.0001894', 'epoch': '1.295'}
+{'loss': '0.7135', 'grad_norm': '0.4039', 'learning_rate': '0.0001894', 'epoch': '1.296'}
+{'loss': '0.7896', 'grad_norm': '0.4575', 'learning_rate': '0.0001894', 'epoch': '1.297'}
+{'loss': '0.7864', 'grad_norm': '0.499', 'learning_rate': '0.0001894', 'epoch': '1.298'}
+{'loss': '0.7953', 'grad_norm': '0.47', 'learning_rate': '0.0001894', 'epoch': '1.299'}
+{'loss': '0.7313', 'grad_norm': '0.4367', 'learning_rate': '0.0001893', 'epoch': '1.299'}
+{'loss': '0.7332', 'grad_norm': '0.4843', 'learning_rate': '0.0001893', 'epoch': '1.3'}
+{'loss': '0.7046', 'grad_norm': '0.4234', 'learning_rate': '0.0001893', 'epoch': '1.301'}
+{'loss': '0.8217', 'grad_norm': '0.6326', 'learning_rate': '0.0001893', 'epoch': '1.302'}
+{'loss': '0.6478', 'grad_norm': '0.4097', 'learning_rate': '0.0001892', 'epoch': '1.303'}
+{'loss': '0.6409', 'grad_norm': '0.387', 'learning_rate': '0.0001892', 'epoch': '1.304'}
+{'loss': '0.7397', 'grad_norm': '0.4401', 'learning_rate': '0.0001892', 'epoch': '1.305'}
+{'loss': '0.6409', 'grad_norm': '0.3969', 'learning_rate': '0.0001892', 'epoch': '1.306'}
+{'loss': '0.7826', 'grad_norm': '0.4994', 'learning_rate': '0.0001892', 'epoch': '1.306'}
+{'loss': '0.7182', 'grad_norm': '0.4394', 'learning_rate': '0.0001891', 'epoch': '1.307'}
+{'loss': '0.7603', 'grad_norm': '0.4391', 'learning_rate': '0.0001891', 'epoch': '1.308'}
+{'loss': '0.7308', 'grad_norm': '0.4173', 'learning_rate': '0.0001891', 'epoch': '1.309'}
+{'loss': '0.7821', 'grad_norm': '0.4964', 'learning_rate': '0.0001891', 'epoch': '1.31'}
+{'loss': '0.7879', 'grad_norm': '0.4989', 'learning_rate': '0.000189', 'epoch': '1.311'}
+{'loss': '0.6731', 'grad_norm': '0.4269', 'learning_rate': '0.000189', 'epoch': '1.312'}
+{'loss': '0.7211', 'grad_norm': '0.4962', 'learning_rate': '0.000189', 'epoch': '1.312'}
+{'loss': '0.7317', 'grad_norm': '0.4515', 'learning_rate': '0.000189', 'epoch': '1.313'}
+{'loss': '0.7839', 'grad_norm': '0.5013', 'learning_rate': '0.000189', 'epoch': '1.314'}
+{'loss': '0.8207', 'grad_norm': '0.5605', 'learning_rate': '0.0001889', 'epoch': '1.315'}
+{'loss': '0.746', 'grad_norm': '0.4337', 'learning_rate': '0.0001889', 'epoch': '1.316'}
+{'loss': '0.7973', 'grad_norm': '0.4392', 'learning_rate': '0.0001889', 'epoch': '1.317'}
+{'loss': '0.6952', 'grad_norm': '0.455', 'learning_rate': '0.0001889', 'epoch': '1.318'}
+{'loss': '0.7353', 'grad_norm': '0.4059', 'learning_rate': '0.0001888', 'epoch': '1.318'}
+{'loss': '0.7759', 'grad_norm': '0.4158', 'learning_rate': '0.0001888', 'epoch': '1.319'}
+{'loss': '0.6808', 'grad_norm': '0.4412', 'learning_rate': '0.0001888', 'epoch': '1.32'}
+{'loss': '0.7781', 'grad_norm': '0.4674', 'learning_rate': '0.0001888', 'epoch': '1.321'}
+{'loss': '0.776', 'grad_norm': '0.4415', 'learning_rate': '0.0001888', 'epoch': '1.322'}
+{'loss': '0.743', 'grad_norm': '0.4805', 'learning_rate': '0.0001887', 'epoch': '1.323'}
+{'loss': '0.6975', 'grad_norm': '0.4892', 'learning_rate': '0.0001887', 'epoch': '1.324'}
+{'loss': '0.6833', 'grad_norm': '0.4104', 'learning_rate': '0.0001887', 'epoch': '1.324'}
+{'loss': '0.77', 'grad_norm': '0.4509', 'learning_rate': '0.0001887', 'epoch': '1.325'}
+{'loss': '0.7442', 'grad_norm': '0.4793', 'learning_rate': '0.0001886', 'epoch': '1.326'}
+{'loss': '0.7196', 'grad_norm': '0.7564', 'learning_rate': '0.0001886', 'epoch': '1.327'}
+{'loss': '0.6693', 'grad_norm': '0.479', 'learning_rate': '0.0001886', 'epoch': '1.328'}
+{'loss': '0.6883', 'grad_norm': '0.4327', 'learning_rate': '0.0001886', 'epoch': '1.329'}
+{'loss': '0.93', 'grad_norm': '0.4955', 'learning_rate': '0.0001886', 'epoch': '1.33'}
+{'loss': '0.8391', 'grad_norm': '0.4639', 'learning_rate': '0.0001885', 'epoch': '1.331'}
+{'loss': '0.7136', 'grad_norm': '0.4086', 'learning_rate': '0.0001885', 'epoch': '1.331'}
+{'loss': '0.6887', 'grad_norm': '0.4456', 'learning_rate': '0.0001885', 'epoch': '1.332'}
+{'loss': '0.7261', 'grad_norm': '0.4336', 'learning_rate': '0.0001885', 'epoch': '1.333'}
+{'loss': '0.853', 'grad_norm': '0.5323', 'learning_rate': '0.0001884', 'epoch': '1.334'}
+{'loss': '0.8132', 'grad_norm': '0.4505', 'learning_rate': '0.0001884', 'epoch': '1.335'}
+{'loss': '0.801', 'grad_norm': '0.441', 'learning_rate': '0.0001884', 'epoch': '1.336'}
+{'loss': '0.711', 'grad_norm': '0.4659', 'learning_rate': '0.0001884', 'epoch': '1.337'}
+{'loss': '0.7825', 'grad_norm': '0.4656', 'learning_rate': '0.0001883', 'epoch': '1.337'}
+{'eval_loss': '0.8109', 'eval_runtime': '662.6', 'eval_samples_per_second': '3.109', 'eval_steps_per_second': '3.109', 'epoch': '1.337'}
+{'loss': '0.7444', 'grad_norm': '0.4943', 'learning_rate': '0.0001883', 'epoch': '1.338'}
+{'loss': '0.8249', 'grad_norm': '0.528', 'learning_rate': '0.0001883', 'epoch': '1.339'}
+{'loss': '0.7753', 'grad_norm': '0.4131', 'learning_rate': '0.0001883', 'epoch': '1.34'}
+{'loss': '0.7512', 'grad_norm': '0.3846', 'learning_rate': '0.0001883', 'epoch': '1.341'}
+{'loss': '0.7761', 'grad_norm': '0.472', 'learning_rate': '0.0001882', 'epoch': '1.342'}
+{'loss': '0.7802', 'grad_norm': '0.4759', 'learning_rate': '0.0001882', 'epoch': '1.343'}
+{'loss': '0.7037', 'grad_norm': '0.4646', 'learning_rate': '0.0001882', 'epoch': '1.343'}
+{'loss': '0.7476', 'grad_norm': '0.4358', 'learning_rate': '0.0001882', 'epoch': '1.344'}
+{'loss': '0.8274', 'grad_norm': '0.5237', 'learning_rate': '0.0001881', 'epoch': '1.345'}
+{'loss': '0.7408', 'grad_norm': '0.524', 'learning_rate': '0.0001881', 'epoch': '1.346'}
+{'loss': '0.7087', 'grad_norm': '0.4445', 'learning_rate': '0.0001881', 'epoch': '1.347'}
+{'loss': '0.7244', 'grad_norm': '0.4377', 'learning_rate': '0.0001881', 'epoch': '1.348'}
+{'loss': '0.7604', 'grad_norm': '0.4478', 'learning_rate': '0.000188', 'epoch': '1.349'}
+{'loss': '0.7546', 'grad_norm': '0.4425', 'learning_rate': '0.000188', 'epoch': '1.35'}
+{'loss': '0.7925', 'grad_norm': '0.4583', 'learning_rate': '0.000188', 'epoch': '1.35'}
+{'loss': '0.7393', 'grad_norm': '0.4329', 'learning_rate': '0.000188', 'epoch': '1.351'}
+{'loss': '0.734', 'grad_norm': '0.4477', 'learning_rate': '0.000188', 'epoch': '1.352'}
+{'loss': '0.6679', 'grad_norm': '0.3931', 'learning_rate': '0.0001879', 'epoch': '1.353'}
+{'loss': '0.806', 'grad_norm': '0.4769', 'learning_rate': '0.0001879', 'epoch': '1.354'}
+{'loss': '0.7618', 'grad_norm': '0.4464', 'learning_rate': '0.0001879', 'epoch': '1.355'}
+{'loss': '0.7277', 'grad_norm': '0.4116', 'learning_rate': '0.0001879', 'epoch': '1.356'}
+{'loss': '0.7588', 'grad_norm': '0.4048', 'learning_rate': '0.0001878', 'epoch': '1.356'}
+{'loss': '0.7897', 'grad_norm': '0.5233', 'learning_rate': '0.0001878', 'epoch': '1.357'}
+{'loss': '0.83', 'grad_norm': '0.5604', 'learning_rate': '0.0001878', 'epoch': '1.358'}
+{'loss': '0.8129', 'grad_norm': '0.4842', 'learning_rate': '0.0001878', 'epoch': '1.359'}
+{'loss': '0.7274', 'grad_norm': '0.4339', 'learning_rate': '0.0001877', 'epoch': '1.36'}
+{'loss': '0.813', 'grad_norm': '0.4887', 'learning_rate': '0.0001877', 'epoch': '1.361'}
+{'loss': '0.7693', 'grad_norm': '0.507', 'learning_rate': '0.0001877', 'epoch': '1.362'}
+{'loss': '0.6611', 'grad_norm': '0.461', 'learning_rate': '0.0001877', 'epoch': '1.362'}
+{'loss': '0.7724', 'grad_norm': '0.4481', 'learning_rate': '0.0001876', 'epoch': '1.363'}
+{'loss': '0.7167', 'grad_norm': '0.3805', 'learning_rate': '0.0001876', 'epoch': '1.364'}
+{'loss': '0.7535', 'grad_norm': '0.4011', 'learning_rate': '0.0001876', 'epoch': '1.365'}
+{'loss': '0.7471', 'grad_norm': '0.4114', 'learning_rate': '0.0001876', 'epoch': '1.366'}
+{'loss': '0.6911', 'grad_norm': '0.3678', 'learning_rate': '0.0001876', 'epoch': '1.367'}
+{'loss': '0.7567', 'grad_norm': '0.51', 'learning_rate': '0.0001875', 'epoch': '1.368'}
+{'loss': '0.722', 'grad_norm': '0.4347', 'learning_rate': '0.0001875', 'epoch': '1.369'}
+{'loss': '0.737', 'grad_norm': '0.4222', 'learning_rate': '0.0001875', 'epoch': '1.369'}
+{'loss': '0.7523', 'grad_norm': '0.4664', 'learning_rate': '0.0001875', 'epoch': '1.37'}
+{'loss': '0.7404', 'grad_norm': '0.4494', 'learning_rate': '0.0001874', 'epoch': '1.371'}
+{'loss': '0.6999', 'grad_norm': '0.4246', 'learning_rate': '0.0001874', 'epoch': '1.372'}
+{'loss': '0.6736', 'grad_norm': '0.4704', 'learning_rate': '0.0001874', 'epoch': '1.373'}
+{'loss': '0.7646', 'grad_norm': '0.5369', 'learning_rate': '0.0001874', 'epoch': '1.374'}
+{'loss': '0.7491', 'grad_norm': '0.4965', 'learning_rate': '0.0001873', 'epoch': '1.375'}
+{'loss': '0.6871', 'grad_norm': '0.4168', 'learning_rate': '0.0001873', 'epoch': '1.375'}
+{'loss': '0.7642', 'grad_norm': '0.4886', 'learning_rate': '0.0001873', 'epoch': '1.376'}
+{'loss': '0.7054', 'grad_norm': '0.4587', 'learning_rate': '0.0001873', 'epoch': '1.377'}
+{'loss': '0.7476', 'grad_norm': '0.4557', 'learning_rate': '0.0001872', 'epoch': '1.378'}
+{'loss': '0.745', 'grad_norm': '0.436', 'learning_rate': '0.0001872', 'epoch': '1.379'}
+{'loss': '0.6332', 'grad_norm': '0.4514', 'learning_rate': '0.0001872', 'epoch': '1.38'}
+{'loss': '0.7', 'grad_norm': '0.4052', 'learning_rate': '0.0001872', 'epoch': '1.381'}
+{'eval_loss': '0.8053', 'eval_runtime': '668.3', 'eval_samples_per_second': '3.082', 'eval_steps_per_second': '3.082', 'epoch': '1.381'}
+{'loss': '0.6753', 'grad_norm': '0.4362', 'learning_rate': '0.0001871', 'epoch': '1.381'}
+{'loss': '0.8099', 'grad_norm': '0.5163', 'learning_rate': '0.0001871', 'epoch': '1.382'}
+{'loss': '0.7266', 'grad_norm': '0.5262', 'learning_rate': '0.0001871', 'epoch': '1.383'}
+{'loss': '0.8171', 'grad_norm': '0.5289', 'learning_rate': '0.0001871', 'epoch': '1.384'}
+{'loss': '0.8008', 'grad_norm': '0.4559', 'learning_rate': '0.000187', 'epoch': '1.385'}
+{'loss': '0.7034', 'grad_norm': '0.4709', 'learning_rate': '0.000187', 'epoch': '1.386'}
+{'loss': '0.6707', 'grad_norm': '0.4143', 'learning_rate': '0.000187', 'epoch': '1.387'}
+{'loss': '0.7554', 'grad_norm': '0.4664', 'learning_rate': '0.000187', 'epoch': '1.387'}
+{'loss': '0.6853', 'grad_norm': '0.372', 'learning_rate': '0.000187', 'epoch': '1.388'}
+{'loss': '0.7975', 'grad_norm': '0.4676', 'learning_rate': '0.0001869', 'epoch': '1.389'}
+{'loss': '0.6644', 'grad_norm': '0.4088', 'learning_rate': '0.0001869', 'epoch': '1.39'}
+{'loss': '0.6455', 'grad_norm': '0.4357', 'learning_rate': '0.0001869', 'epoch': '1.391'}
+{'loss': '0.7152', 'grad_norm': '0.4833', 'learning_rate': '0.0001869', 'epoch': '1.392'}
+{'loss': '0.7148', 'grad_norm': '0.4443', 'learning_rate': '0.0001868', 'epoch': '1.393'}
+{'loss': '0.7785', 'grad_norm': '0.4571', 'learning_rate': '0.0001868', 'epoch': '1.394'}
+{'loss': '0.7226', 'grad_norm': '0.4618', 'learning_rate': '0.0001868', 'epoch': '1.394'}
+{'loss': '0.7417', 'grad_norm': '0.5473', 'learning_rate': '0.0001868', 'epoch': '1.395'}
+{'loss': '0.7774', 'grad_norm': '0.4563', 'learning_rate': '0.0001867', 'epoch': '1.396'}
+{'loss': '0.7063', 'grad_norm': '0.4549', 'learning_rate': '0.0001867', 'epoch': '1.397'}
+{'loss': '0.7901', 'grad_norm': '0.453', 'learning_rate': '0.0001867', 'epoch': '1.398'}
+{'loss': '0.7322', 'grad_norm': '0.4527', 'learning_rate': '0.0001867', 'epoch': '1.399'}
+{'loss': '0.7809', 'grad_norm': '0.4717', 'learning_rate': '0.0001866', 'epoch': '1.4'}
+{'loss': '0.7125', 'grad_norm': '0.4421', 'learning_rate': '0.0001866', 'epoch': '1.4'}
+{'loss': '0.7868', 'grad_norm': '0.4507', 'learning_rate': '0.0001866', 'epoch': '1.401'}
+{'loss': '0.7364', 'grad_norm': '0.4546', 'learning_rate': '0.0001866', 'epoch': '1.402'}
+{'loss': '0.7381', 'grad_norm': '0.4487', 'learning_rate': '0.0001865', 'epoch': '1.403'}
+{'loss': '0.6975', 'grad_norm': '0.4335', 'learning_rate': '0.0001865', 'epoch': '1.404'}
+{'loss': '0.7639', 'grad_norm': '0.4576', 'learning_rate': '0.0001865', 'epoch': '1.405'}
+{'loss': '0.7302', 'grad_norm': '0.4452', 'learning_rate': '0.0001865', 'epoch': '1.406'}
+{'loss': '0.7708', 'grad_norm': '0.5451', 'learning_rate': '0.0001864', 'epoch': '1.406'}
+{'loss': '0.7637', 'grad_norm': '0.4734', 'learning_rate': '0.0001864', 'epoch': '1.407'}
+{'loss': '0.7141', 'grad_norm': '0.4809', 'learning_rate': '0.0001864', 'epoch': '1.408'}
+{'loss': '0.6539', 'grad_norm': '0.4122', 'learning_rate': '0.0001864', 'epoch': '1.409'}
+{'loss': '0.7154', 'grad_norm': '0.4457', 'learning_rate': '0.0001863', 'epoch': '1.41'}
+{'loss': '0.714', 'grad_norm': '0.4153', 'learning_rate': '0.0001863', 'epoch': '1.411'}
+{'loss': '0.7194', 'grad_norm': '0.4711', 'learning_rate': '0.0001863', 'epoch': '1.412'}
+{'loss': '0.7134', 'grad_norm': '0.3974', 'learning_rate': '0.0001863', 'epoch': '1.413'}
+{'loss': '0.8119', 'grad_norm': '0.4809', 'learning_rate': '0.0001862', 'epoch': '1.413'}
+{'loss': '0.8126', 'grad_norm': '0.4608', 'learning_rate': '0.0001862', 'epoch': '1.414'}
+{'loss': '0.7066', 'grad_norm': '0.4152', 'learning_rate': '0.0001862', 'epoch': '1.415'}
+{'loss': '0.7346', 'grad_norm': '0.4667', 'learning_rate': '0.0001862', 'epoch': '1.416'}
+{'loss': '0.759', 'grad_norm': '0.4744', 'learning_rate': '0.0001861', 'epoch': '1.417'}
+{'loss': '0.7862', 'grad_norm': '0.4906', 'learning_rate': '0.0001861', 'epoch': '1.418'}
+{'loss': '0.6855', 'grad_norm': '0.4511', 'learning_rate': '0.0001861', 'epoch': '1.419'}
+{'loss': '0.8294', 'grad_norm': '0.5547', 'learning_rate': '0.0001861', 'epoch': '1.419'}
+{'loss': '0.6352', 'grad_norm': '0.4101', 'learning_rate': '0.000186', 'epoch': '1.42'}
+{'loss': '0.7823', 'grad_norm': '0.4772', 'learning_rate': '0.000186', 'epoch': '1.421'}
+{'loss': '0.7675', 'grad_norm': '0.4581', 'learning_rate': '0.000186', 'epoch': '1.422'}
+{'loss': '0.7995', 'grad_norm': '0.4794', 'learning_rate': '0.000186', 'epoch': '1.423'}
+{'loss': '0.7677', 'grad_norm': '0.4587', 'learning_rate': '0.0001859', 'epoch': '1.424'}
+{'eval_loss': '0.803', 'eval_runtime': '658.5', 'eval_samples_per_second': '3.128', 'eval_steps_per_second': '3.128', 'epoch': '1.424'}
+{'loss': '0.7642', 'grad_norm': '0.46', 'learning_rate': '0.0001859', 'epoch': '1.425'}
+{'loss': '0.7753', 'grad_norm': '0.5013', 'learning_rate': '0.0001859', 'epoch': '1.425'}
+{'loss': '0.7227', 'grad_norm': '0.4497', 'learning_rate': '0.0001859', 'epoch': '1.426'}
+{'loss': '0.753', 'grad_norm': '0.4731', 'learning_rate': '0.0001858', 'epoch': '1.427'}
+{'loss': '0.7653', 'grad_norm': '0.4577', 'learning_rate': '0.0001858', 'epoch': '1.428'}
+{'loss': '0.808', 'grad_norm': '0.4726', 'learning_rate': '0.0001858', 'epoch': '1.429'}
+{'loss': '0.8084', 'grad_norm': '0.443', 'learning_rate': '0.0001858', 'epoch': '1.43'}
+{'loss': '0.7861', 'grad_norm': '0.4197', 'learning_rate': '0.0001857', 'epoch': '1.431'}
+{'loss': '0.8125', 'grad_norm': '0.4048', 'learning_rate': '0.0001857', 'epoch': '1.431'}
+{'loss': '0.7792', 'grad_norm': '0.5689', 'learning_rate': '0.0001857', 'epoch': '1.432'}
+{'loss': '0.7556', 'grad_norm': '0.478', 'learning_rate': '0.0001857', 'epoch': '1.433'}
+{'loss': '0.6761', 'grad_norm': '0.4296', 'learning_rate': '0.0001856', 'epoch': '1.434'}
+{'loss': '0.7466', 'grad_norm': '0.4606', 'learning_rate': '0.0001856', 'epoch': '1.435'}
+{'loss': '0.746', 'grad_norm': '0.4823', 'learning_rate': '0.0001856', 'epoch': '1.436'}
+{'loss': '0.6451', 'grad_norm': '0.4655', 'learning_rate': '0.0001856', 'epoch': '1.437'}
+{'loss': '0.7649', 'grad_norm': '0.4615', 'learning_rate': '0.0001855', 'epoch': '1.438'}
+{'loss': '0.771', 'grad_norm': '0.475', 'learning_rate': '0.0001855', 'epoch': '1.438'}
+{'loss': '0.8471', 'grad_norm': '0.5408', 'learning_rate': '0.0001855', 'epoch': '1.439'}
+{'loss': '0.7709', 'grad_norm': '0.4475', 'learning_rate': '0.0001855', 'epoch': '1.44'}
+{'loss': '0.691', 'grad_norm': '0.3824', 'learning_rate': '0.0001854', 'epoch': '1.441'}
+{'loss': '0.7685', 'grad_norm': '0.4221', 'learning_rate': '0.0001854', 'epoch': '1.442'}
+{'loss': '0.7546', 'grad_norm': '0.4514', 'learning_rate': '0.0001854', 'epoch': '1.443'}
+{'loss': '0.7303', 'grad_norm': '0.429', 'learning_rate': '0.0001854', 'epoch': '1.444'}
+{'loss': '0.7611', 'grad_norm': '0.4459', 'learning_rate': '0.0001853', 'epoch': '1.444'}
+{'loss': '0.7714', 'grad_norm': '0.4371', 'learning_rate': '0.0001853', 'epoch': '1.445'}
+{'loss': '0.6729', 'grad_norm': '0.4023', 'learning_rate': '0.0001853', 'epoch': '1.446'}
+{'loss': '0.7663', 'grad_norm': '0.436', 'learning_rate': '0.0001853', 'epoch': '1.447'}
+{'loss': '0.8269', 'grad_norm': '0.4581', 'learning_rate': '0.0001852', 'epoch': '1.448'}
+{'loss': '0.8172', 'grad_norm': '0.4839', 'learning_rate': '0.0001852', 'epoch': '1.449'}
+{'loss': '0.8057', 'grad_norm': '0.4174', 'learning_rate': '0.0001852', 'epoch': '1.45'}
+{'loss': '0.735', 'grad_norm': '0.4105', 'learning_rate': '0.0001851', 'epoch': '1.45'}
+{'loss': '0.7771', 'grad_norm': '0.4941', 'learning_rate': '0.0001851', 'epoch': '1.451'}
+{'loss': '0.8042', 'grad_norm': '0.4836', 'learning_rate': '0.0001851', 'epoch': '1.452'}
+{'loss': '0.7079', 'grad_norm': '0.4455', 'learning_rate': '0.0001851', 'epoch': '1.453'}
+{'loss': '0.7564', 'grad_norm': '0.4199', 'learning_rate': '0.000185', 'epoch': '1.454'}
+{'loss': '0.6955', 'grad_norm': '0.4005', 'learning_rate': '0.000185', 'epoch': '1.455'}
+{'loss': '0.6564', 'grad_norm': '0.432', 'learning_rate': '0.000185', 'epoch': '1.456'}
+{'loss': '0.6716', 'grad_norm': '0.4266', 'learning_rate': '0.000185', 'epoch': '1.457'}
+{'loss': '0.7801', 'grad_norm': '0.4835', 'learning_rate': '0.0001849', 'epoch': '1.457'}
+{'loss': '0.765', 'grad_norm': '0.5084', 'learning_rate': '0.0001849', 'epoch': '1.458'}
+{'loss': '0.7308', 'grad_norm': '0.4168', 'learning_rate': '0.0001849', 'epoch': '1.459'}
+{'loss': '0.7258', 'grad_norm': '0.4184', 'learning_rate': '0.0001849', 'epoch': '1.46'}
+{'loss': '0.7981', 'grad_norm': '0.5055', 'learning_rate': '0.0001848', 'epoch': '1.461'}
+{'loss': '0.7803', 'grad_norm': '0.4449', 'learning_rate': '0.0001848', 'epoch': '1.462'}
+{'loss': '0.68', 'grad_norm': '0.3827', 'learning_rate': '0.0001848', 'epoch': '1.463'}
+{'loss': '0.7276', 'grad_norm': '0.4157', 'learning_rate': '0.0001848', 'epoch': '1.463'}
+{'loss': '0.698', 'grad_norm': '0.4724', 'learning_rate': '0.0001847', 'epoch': '1.464'}
+{'loss': '0.7209', 'grad_norm': '0.4341', 'learning_rate': '0.0001847', 'epoch': '1.465'}
+{'loss': '0.6597', 'grad_norm': '0.399', 'learning_rate': '0.0001847', 'epoch': '1.466'}
+{'loss': '0.7703', 'grad_norm': '0.4282', 'learning_rate': '0.0001847', 'epoch': '1.467'}
+{'eval_loss': '0.8002', 'eval_runtime': '649.7', 'eval_samples_per_second': '3.17', 'eval_steps_per_second': '3.17', 'epoch': '1.467'}
+{'loss': '0.7407', 'grad_norm': '0.393', 'learning_rate': '0.0001846', 'epoch': '1.468'}
+{'loss': '0.6625', 'grad_norm': '0.4466', 'learning_rate': '0.0001846', 'epoch': '1.469'}
+{'loss': '0.7233', 'grad_norm': '0.4866', 'learning_rate': '0.0001846', 'epoch': '1.469'}
+{'loss': '0.6909', 'grad_norm': '0.4432', 'learning_rate': '0.0001846', 'epoch': '1.47'}
+{'loss': '0.7288', 'grad_norm': '0.4537', 'learning_rate': '0.0001845', 'epoch': '1.471'}
+{'loss': '0.6632', 'grad_norm': '0.4268', 'learning_rate': '0.0001845', 'epoch': '1.472'}
+{'loss': '0.7257', 'grad_norm': '0.4689', 'learning_rate': '0.0001845', 'epoch': '1.473'}
+{'loss': '0.7732', 'grad_norm': '0.4158', 'learning_rate': '0.0001844', 'epoch': '1.474'}
+{'loss': '0.6603', 'grad_norm': '0.4289', 'learning_rate': '0.0001844', 'epoch': '1.475'}
+{'loss': '0.7164', 'grad_norm': '0.4597', 'learning_rate': '0.0001844', 'epoch': '1.476'}
+{'loss': '0.7289', 'grad_norm': '0.4251', 'learning_rate': '0.0001844', 'epoch': '1.476'}
+{'loss': '0.7456', 'grad_norm': '0.3899', 'learning_rate': '0.0001843', 'epoch': '1.477'}
+{'loss': '0.7043', 'grad_norm': '0.4342', 'learning_rate': '0.0001843', 'epoch': '1.478'}
+{'loss': '0.7601', 'grad_norm': '0.4131', 'learning_rate': '0.0001843', 'epoch': '1.479'}
+{'loss': '0.722', 'grad_norm': '0.4154', 'learning_rate': '0.0001843', 'epoch': '1.48'}
+{'loss': '0.8417', 'grad_norm': '0.4529', 'learning_rate': '0.0001842', 'epoch': '1.481'}
+{'loss': '0.7626', 'grad_norm': '0.4439', 'learning_rate': '0.0001842', 'epoch': '1.482'}
+{'loss': '0.7759', 'grad_norm': '0.4985', 'learning_rate': '0.0001842', 'epoch': '1.482'}
+{'loss': '0.6921', 'grad_norm': '0.3774', 'learning_rate': '0.0001842', 'epoch': '1.483'}
+{'loss': '0.679', 'grad_norm': '0.4495', 'learning_rate': '0.0001841', 'epoch': '1.484'}
+{'loss': '0.6904', 'grad_norm': '0.4084', 'learning_rate': '0.0001841', 'epoch': '1.485'}
+{'loss': '0.7037', 'grad_norm': '0.4473', 'learning_rate': '0.0001841', 'epoch': '1.486'}
+{'loss': '0.7732', 'grad_norm': '0.4696', 'learning_rate': '0.0001841', 'epoch': '1.487'}
+{'loss': '0.7676', 'grad_norm': '0.4684', 'learning_rate': '0.000184', 'epoch': '1.488'}
+{'loss': '0.8146', 'grad_norm': '0.474', 'learning_rate': '0.000184', 'epoch': '1.488'}
+{'loss': '0.7848', 'grad_norm': '0.5148', 'learning_rate': '0.000184', 'epoch': '1.489'}
+{'loss': '0.7849', 'grad_norm': '0.5376', 'learning_rate': '0.0001839', 'epoch': '1.49'}
+{'loss': '0.7197', 'grad_norm': '0.4689', 'learning_rate': '0.0001839', 'epoch': '1.491'}
+{'loss': '0.8277', 'grad_norm': '0.5116', 'learning_rate': '0.0001839', 'epoch': '1.492'}
+{'loss': '0.7628', 'grad_norm': '0.4', 'learning_rate': '0.0001839', 'epoch': '1.493'}
+{'loss': '0.7173', 'grad_norm': '0.4474', 'learning_rate': '0.0001838', 'epoch': '1.494'}
+{'loss': '0.7366', 'grad_norm': '0.4175', 'learning_rate': '0.0001838', 'epoch': '1.494'}
+{'loss': '0.7563', 'grad_norm': '0.4939', 'learning_rate': '0.0001838', 'epoch': '1.495'}
+{'loss': '0.8225', 'grad_norm': '0.437', 'learning_rate': '0.0001838', 'epoch': '1.496'}
+{'loss': '0.7571', 'grad_norm': '0.4824', 'learning_rate': '0.0001837', 'epoch': '1.497'}
+{'loss': '0.7152', 'grad_norm': '0.4626', 'learning_rate': '0.0001837', 'epoch': '1.498'}
+{'loss': '0.6635', 'grad_norm': '0.4452', 'learning_rate': '0.0001837', 'epoch': '1.499'}
+{'loss': '0.7814', 'grad_norm': '0.4698', 'learning_rate': '0.0001836', 'epoch': '1.5'}
+{'loss': '0.6941', 'grad_norm': '0.4432', 'learning_rate': '0.0001836', 'epoch': '1.501'}
+{'loss': '0.7583', 'grad_norm': '0.4673', 'learning_rate': '0.0001836', 'epoch': '1.501'}
+{'loss': '0.9018', 'grad_norm': '0.5454', 'learning_rate': '0.0001836', 'epoch': '1.502'}
+{'loss': '0.8088', 'grad_norm': '0.5125', 'learning_rate': '0.0001835', 'epoch': '1.503'}
+{'loss': '0.787', 'grad_norm': '0.4635', 'learning_rate': '0.0001835', 'epoch': '1.504'}
+{'loss': '0.7509', 'grad_norm': '0.3963', 'learning_rate': '0.0001835', 'epoch': '1.505'}
+{'loss': '0.711', 'grad_norm': '0.4888', 'learning_rate': '0.0001835', 'epoch': '1.506'}
+{'loss': '0.7632', 'grad_norm': '0.4784', 'learning_rate': '0.0001834', 'epoch': '1.507'}
+{'loss': '0.7417', 'grad_norm': '0.458', 'learning_rate': '0.0001834', 'epoch': '1.507'}
+{'loss': '0.8117', 'grad_norm': '0.4267', 'learning_rate': '0.0001834', 'epoch': '1.508'}
+{'loss': '0.7246', 'grad_norm': '0.484', 'learning_rate': '0.0001834', 'epoch': '1.509'}
+{'loss': '0.8396', 'grad_norm': '0.5218', 'learning_rate': '0.0001833', 'epoch': '1.51'}
+{'eval_loss': '0.7971', 'eval_runtime': '655.3', 'eval_samples_per_second': '3.144', 'eval_steps_per_second': '3.144', 'epoch': '1.51'}
+{'loss': '0.7151', 'grad_norm': '0.4358', 'learning_rate': '0.0001833', 'epoch': '1.511'}
+{'loss': '0.6746', 'grad_norm': '0.4225', 'learning_rate': '0.0001833', 'epoch': '1.512'}
+{'loss': '0.787', 'grad_norm': '0.4675', 'learning_rate': '0.0001832', 'epoch': '1.513'}
+{'loss': '0.7771', 'grad_norm': '0.4414', 'learning_rate': '0.0001832', 'epoch': '1.513'}
+{'loss': '0.7992', 'grad_norm': '0.5092', 'learning_rate': '0.0001832', 'epoch': '1.514'}
+{'loss': '0.7679', 'grad_norm': '0.4273', 'learning_rate': '0.0001832', 'epoch': '1.515'}
+{'loss': '0.7972', 'grad_norm': '0.4707', 'learning_rate': '0.0001831', 'epoch': '1.516'}
+{'loss': '0.7281', 'grad_norm': '0.4251', 'learning_rate': '0.0001831', 'epoch': '1.517'}
+{'loss': '0.7346', 'grad_norm': '0.4261', 'learning_rate': '0.0001831', 'epoch': '1.518'}
+{'loss': '0.7653', 'grad_norm': '0.4935', 'learning_rate': '0.0001831', 'epoch': '1.519'}
+{'loss': '0.7074', 'grad_norm': '0.4547', 'learning_rate': '0.000183', 'epoch': '1.52'}
+{'loss': '0.6813', 'grad_norm': '0.4881', 'learning_rate': '0.000183', 'epoch': '1.52'}
+{'loss': '0.6736', 'grad_norm': '0.4397', 'learning_rate': '0.000183', 'epoch': '1.521'}
+{'loss': '0.7214', 'grad_norm': '0.4427', 'learning_rate': '0.0001829', 'epoch': '1.522'}
+{'loss': '0.8269', 'grad_norm': '0.5235', 'learning_rate': '0.0001829', 'epoch': '1.523'}
+{'loss': '0.708', 'grad_norm': '0.4708', 'learning_rate': '0.0001829', 'epoch': '1.524'}
+{'loss': '0.7506', 'grad_norm': '0.4719', 'learning_rate': '0.0001829', 'epoch': '1.525'}
+{'loss': '0.7439', 'grad_norm': '0.4707', 'learning_rate': '0.0001828', 'epoch': '1.526'}
+{'loss': '0.7528', 'grad_norm': '0.4208', 'learning_rate': '0.0001828', 'epoch': '1.526'}
+{'loss': '0.7296', 'grad_norm': '0.4747', 'learning_rate': '0.0001828', 'epoch': '1.527'}
+{'loss': '0.7707', 'grad_norm': '0.4989', 'learning_rate': '0.0001828', 'epoch': '1.528'}
+{'loss': '0.7032', 'grad_norm': '0.443', 'learning_rate': '0.0001827', 'epoch': '1.529'}
+{'loss': '0.6652', 'grad_norm': '0.4144', 'learning_rate': '0.0001827', 'epoch': '1.53'}
+{'loss': '0.7447', 'grad_norm': '0.4155', 'learning_rate': '0.0001827', 'epoch': '1.531'}
+{'loss': '0.8003', 'grad_norm': '0.4627', 'learning_rate': '0.0001826', 'epoch': '1.532'}
+{'loss': '0.8398', 'grad_norm': '0.4699', 'learning_rate': '0.0001826', 'epoch': '1.532'}
+{'loss': '0.708', 'grad_norm': '0.4587', 'learning_rate': '0.0001826', 'epoch': '1.533'}
+{'loss': '0.7791', 'grad_norm': '0.4651', 'learning_rate': '0.0001826', 'epoch': '1.534'}
+{'loss': '0.7549', 'grad_norm': '0.4353', 'learning_rate': '0.0001825', 'epoch': '1.535'}
+{'loss': '0.7493', 'grad_norm': '0.4259', 'learning_rate': '0.0001825', 'epoch': '1.536'}
+{'loss': '0.8031', 'grad_norm': '0.4782', 'learning_rate': '0.0001825', 'epoch': '1.537'}
+{'loss': '0.7439', 'grad_norm': '0.4471', 'learning_rate': '0.0001824', 'epoch': '1.538'}
+{'loss': '0.8053', 'grad_norm': '0.4181', 'learning_rate': '0.0001824', 'epoch': '1.539'}
+{'loss': '0.8259', 'grad_norm': '0.5137', 'learning_rate': '0.0001824', 'epoch': '1.539'}
+{'loss': '0.7037', 'grad_norm': '0.4378', 'learning_rate': '0.0001824', 'epoch': '1.54'}
+{'loss': '0.7298', 'grad_norm': '0.4427', 'learning_rate': '0.0001823', 'epoch': '1.541'}
+{'loss': '0.7508', 'grad_norm': '0.4432', 'learning_rate': '0.0001823', 'epoch': '1.542'}
+{'loss': '0.772', 'grad_norm': '0.4874', 'learning_rate': '0.0001823', 'epoch': '1.543'}
+{'loss': '0.8001', 'grad_norm': '0.4608', 'learning_rate': '0.0001823', 'epoch': '1.544'}
+{'loss': '0.7971', 'grad_norm': '0.4563', 'learning_rate': '0.0001822', 'epoch': '1.545'}
+{'loss': '0.7255', 'grad_norm': '0.4687', 'learning_rate': '0.0001822', 'epoch': '1.545'}
+{'loss': '0.7372', 'grad_norm': '0.4808', 'learning_rate': '0.0001822', 'epoch': '1.546'}
+{'loss': '0.6277', 'grad_norm': '0.4227', 'learning_rate': '0.0001821', 'epoch': '1.547'}
+{'loss': '0.7299', 'grad_norm': '0.4223', 'learning_rate': '0.0001821', 'epoch': '1.548'}
+{'loss': '0.6685', 'grad_norm': '0.4649', 'learning_rate': '0.0001821', 'epoch': '1.549'}
+{'loss': '0.6579', 'grad_norm': '0.3962', 'learning_rate': '0.0001821', 'epoch': '1.55'}
+{'loss': '0.6956', 'grad_norm': '0.5002', 'learning_rate': '0.000182', 'epoch': '1.551'}
+{'loss': '0.6726', 'grad_norm': '0.52', 'learning_rate': '0.000182', 'epoch': '1.551'}
+{'loss': '0.7727', 'grad_norm': '0.4894', 'learning_rate': '0.000182', 'epoch': '1.552'}
+{'loss': '0.8291', 'grad_norm': '0.4876', 'learning_rate': '0.0001819', 'epoch': '1.553'}
+{'eval_loss': '0.7936', 'eval_runtime': '666.5', 'eval_samples_per_second': '3.091', 'eval_steps_per_second': '3.091', 'epoch': '1.553'}
+{'loss': '0.682', 'grad_norm': '0.4057', 'learning_rate': '0.0001819', 'epoch': '1.554'}
+{'loss': '0.671', 'grad_norm': '0.4338', 'learning_rate': '0.0001819', 'epoch': '1.555'}
+{'loss': '0.6785', 'grad_norm': '0.4366', 'learning_rate': '0.0001819', 'epoch': '1.556'}
+{'loss': '0.7771', 'grad_norm': '0.4633', 'learning_rate': '0.0001818', 'epoch': '1.557'}
+{'loss': '0.8117', 'grad_norm': '0.4541', 'learning_rate': '0.0001818', 'epoch': '1.557'}
+{'loss': '0.7269', 'grad_norm': '0.4931', 'learning_rate': '0.0001818', 'epoch': '1.558'}
+{'loss': '0.7986', 'grad_norm': '0.4711', 'learning_rate': '0.0001817', 'epoch': '1.559'}
+{'loss': '0.7606', 'grad_norm': '0.4705', 'learning_rate': '0.0001817', 'epoch': '1.56'}
+{'loss': '0.7445', 'grad_norm': '0.4613', 'learning_rate': '0.0001817', 'epoch': '1.561'}
+{'loss': '0.7394', 'grad_norm': '0.4276', 'learning_rate': '0.0001817', 'epoch': '1.562'}
+{'loss': '0.7669', 'grad_norm': '0.576', 'learning_rate': '0.0001816', 'epoch': '1.563'}
+{'loss': '0.7251', 'grad_norm': '0.4177', 'learning_rate': '0.0001816', 'epoch': '1.564'}
+{'loss': '0.7881', 'grad_norm': '0.4017', 'learning_rate': '0.0001816', 'epoch': '1.564'}
+{'loss': '0.7755', 'grad_norm': '0.427', 'learning_rate': '0.0001815', 'epoch': '1.565'}
+{'loss': '0.7012', 'grad_norm': '0.4618', 'learning_rate': '0.0001815', 'epoch': '1.566'}
+{'loss': '0.7202', 'grad_norm': '0.394', 'learning_rate': '0.0001815', 'epoch': '1.567'}
+{'loss': '0.6649', 'grad_norm': '0.4321', 'learning_rate': '0.0001815', 'epoch': '1.568'}
+{'loss': '0.7597', 'grad_norm': '0.4672', 'learning_rate': '0.0001814', 'epoch': '1.569'}
+{'loss': '0.7265', 'grad_norm': '0.4994', 'learning_rate': '0.0001814', 'epoch': '1.57'}
+{'loss': '0.6903', 'grad_norm': '0.416', 'learning_rate': '0.0001814', 'epoch': '1.57'}
+{'loss': '0.759', 'grad_norm': '0.4712', 'learning_rate': '0.0001813', 'epoch': '1.571'}
+{'loss': '0.7304', 'grad_norm': '0.5137', 'learning_rate': '0.0001813', 'epoch': '1.572'}
+{'loss': '0.6473', 'grad_norm': '0.4594', 'learning_rate': '0.0001813', 'epoch': '1.573'}
+{'loss': '0.7312', 'grad_norm': '0.5189', 'learning_rate': '0.0001813', 'epoch': '1.574'}
+{'loss': '0.7791', 'grad_norm': '0.4912', 'learning_rate': '0.0001812', 'epoch': '1.575'}
+{'loss': '0.714', 'grad_norm': '0.4291', 'learning_rate': '0.0001812', 'epoch': '1.576'}
+{'loss': '0.7498', 'grad_norm': '0.423', 'learning_rate': '0.0001812', 'epoch': '1.576'}
+{'loss': '0.7693', 'grad_norm': '0.4447', 'learning_rate': '0.0001811', 'epoch': '1.577'}
+{'loss': '0.7771', 'grad_norm': '0.4416', 'learning_rate': '0.0001811', 'epoch': '1.578'}
+{'loss': '0.7666', 'grad_norm': '0.4212', 'learning_rate': '0.0001811', 'epoch': '1.579'}
+{'loss': '0.7253', 'grad_norm': '0.4013', 'learning_rate': '0.0001811', 'epoch': '1.58'}
+{'loss': '0.6984', 'grad_norm': '0.3757', 'learning_rate': '0.000181', 'epoch': '1.581'}
+{'loss': '0.7309', 'grad_norm': '0.4789', 'learning_rate': '0.000181', 'epoch': '1.582'}
+{'loss': '0.7519', 'grad_norm': '0.4396', 'learning_rate': '0.000181', 'epoch': '1.583'}
+{'loss': '0.6878', 'grad_norm': '0.4019', 'learning_rate': '0.0001809', 'epoch': '1.583'}
+{'loss': '0.7189', 'grad_norm': '0.4395', 'learning_rate': '0.0001809', 'epoch': '1.584'}
+{'loss': '0.6966', 'grad_norm': '0.424', 'learning_rate': '0.0001809', 'epoch': '1.585'}
+{'loss': '0.6944', 'grad_norm': '0.4552', 'learning_rate': '0.0001809', 'epoch': '1.586'}
+{'loss': '0.7711', 'grad_norm': '0.4877', 'learning_rate': '0.0001808', 'epoch': '1.587'}
+{'loss': '0.7489', 'grad_norm': '0.4542', 'learning_rate': '0.0001808', 'epoch': '1.588'}
+{'loss': '0.6809', 'grad_norm': '0.4038', 'learning_rate': '0.0001808', 'epoch': '1.589'}
+{'loss': '0.7147', 'grad_norm': '0.5006', 'learning_rate': '0.0001807', 'epoch': '1.589'}
+{'loss': '0.7934', 'grad_norm': '0.554', 'learning_rate': '0.0001807', 'epoch': '1.59'}
+{'loss': '0.6979', 'grad_norm': '0.4132', 'learning_rate': '0.0001807', 'epoch': '1.591'}
+{'loss': '0.8193', 'grad_norm': '0.5138', 'learning_rate': '0.0001807', 'epoch': '1.592'}
+{'loss': '0.7387', 'grad_norm': '0.4599', 'learning_rate': '0.0001806', 'epoch': '1.593'}
+{'loss': '0.7734', 'grad_norm': '0.4464', 'learning_rate': '0.0001806', 'epoch': '1.594'}
+{'loss': '0.718', 'grad_norm': '0.4188', 'learning_rate': '0.0001806', 'epoch': '1.595'}
+{'loss': '0.7522', 'grad_norm': '0.4579', 'learning_rate': '0.0001805', 'epoch': '1.595'}
+{'loss': '0.6498', 'grad_norm': '0.4338', 'learning_rate': '0.0001805', 'epoch': '1.596'}
+{'eval_loss': '0.7915', 'eval_runtime': '669', 'eval_samples_per_second': '3.079', 'eval_steps_per_second': '3.079', 'epoch': '1.596'}
+{'loss': '0.7064', 'grad_norm': '0.3935', 'learning_rate': '0.0001805', 'epoch': '1.597'}
+{'loss': '0.686', 'grad_norm': '0.3876', 'learning_rate': '0.0001805', 'epoch': '1.598'}
+{'loss': '0.8459', 'grad_norm': '0.4838', 'learning_rate': '0.0001804', 'epoch': '1.599'}
+{'loss': '0.6575', 'grad_norm': '0.4688', 'learning_rate': '0.0001804', 'epoch': '1.6'}
+{'loss': '0.8128', 'grad_norm': '0.537', 'learning_rate': '0.0001804', 'epoch': '1.601'}
+{'loss': '0.7411', 'grad_norm': '0.3991', 'learning_rate': '0.0001803', 'epoch': '1.602'}
+{'loss': '0.7165', 'grad_norm': '0.3804', 'learning_rate': '0.0001803', 'epoch': '1.602'}
+{'loss': '0.7165', 'grad_norm': '0.4591', 'learning_rate': '0.0001803', 'epoch': '1.603'}
+{'loss': '0.6929', 'grad_norm': '0.3746', 'learning_rate': '0.0001802', 'epoch': '1.604'}
+{'loss': '0.6571', 'grad_norm': '0.4337', 'learning_rate': '0.0001802', 'epoch': '1.605'}
+{'loss': '0.6813', 'grad_norm': '0.4127', 'learning_rate': '0.0001802', 'epoch': '1.606'}
+{'loss': '0.7538', 'grad_norm': '0.434', 'learning_rate': '0.0001802', 'epoch': '1.607'}
+{'loss': '0.6768', 'grad_norm': '0.4112', 'learning_rate': '0.0001801', 'epoch': '1.608'}
+{'loss': '0.7152', 'grad_norm': '0.4283', 'learning_rate': '0.0001801', 'epoch': '1.608'}
+{'loss': '0.8154', 'grad_norm': '0.4464', 'learning_rate': '0.0001801', 'epoch': '1.609'}
+{'loss': '0.7119', 'grad_norm': '0.4176', 'learning_rate': '0.00018', 'epoch': '1.61'}
+{'loss': '0.778', 'grad_norm': '0.4225', 'learning_rate': '0.00018', 'epoch': '1.611'}
+{'loss': '0.5716', 'grad_norm': '0.4763', 'learning_rate': '0.00018', 'epoch': '1.612'}
+{'loss': '0.7327', 'grad_norm': '0.4721', 'learning_rate': '0.00018', 'epoch': '1.613'}
+{'loss': '0.7873', 'grad_norm': '0.3892', 'learning_rate': '0.0001799', 'epoch': '1.614'}
+{'loss': '0.8007', 'grad_norm': '0.4307', 'learning_rate': '0.0001799', 'epoch': '1.614'}
+{'loss': '0.7694', 'grad_norm': '0.3984', 'learning_rate': '0.0001799', 'epoch': '1.615'}
+{'loss': '0.7483', 'grad_norm': '0.4323', 'learning_rate': '0.0001798', 'epoch': '1.616'}
+{'loss': '0.7643', 'grad_norm': '0.5203', 'learning_rate': '0.0001798', 'epoch': '1.617'}
+{'loss': '0.7415', 'grad_norm': '0.4319', 'learning_rate': '0.0001798', 'epoch': '1.618'}
+{'loss': '0.7392', 'grad_norm': '0.4943', 'learning_rate': '0.0001797', 'epoch': '1.619'}
+{'loss': '0.7524', 'grad_norm': '0.4687', 'learning_rate': '0.0001797', 'epoch': '1.62'}
+{'loss': '0.6767', 'grad_norm': '0.4705', 'learning_rate': '0.0001797', 'epoch': '1.62'}
+{'loss': '0.7278', 'grad_norm': '0.4398', 'learning_rate': '0.0001797', 'epoch': '1.621'}
+{'loss': '0.7649', 'grad_norm': '0.4139', 'learning_rate': '0.0001796', 'epoch': '1.622'}
+{'loss': '0.7034', 'grad_norm': '0.4612', 'learning_rate': '0.0001796', 'epoch': '1.623'}
+{'loss': '0.8075', 'grad_norm': '0.4777', 'learning_rate': '0.0001796', 'epoch': '1.624'}
+{'loss': '0.7541', 'grad_norm': '0.5022', 'learning_rate': '0.0001795', 'epoch': '1.625'}
+{'loss': '0.7038', 'grad_norm': '0.4622', 'learning_rate': '0.0001795', 'epoch': '1.626'}
+{'loss': '0.6658', 'grad_norm': '0.3449', 'learning_rate': '0.0001795', 'epoch': '1.627'}
+{'loss': '0.7999', 'grad_norm': '0.3806', 'learning_rate': '0.0001794', 'epoch': '1.627'}
+{'loss': '0.7157', 'grad_norm': '0.4882', 'learning_rate': '0.0001794', 'epoch': '1.628'}
+{'loss': '0.6898', 'grad_norm': '0.4214', 'learning_rate': '0.0001794', 'epoch': '1.629'}
+{'loss': '0.6738', 'grad_norm': '0.3886', 'learning_rate': '0.0001794', 'epoch': '1.63'}
+{'loss': '0.6532', 'grad_norm': '0.4051', 'learning_rate': '0.0001793', 'epoch': '1.631'}
+{'loss': '0.8739', 'grad_norm': '0.5424', 'learning_rate': '0.0001793', 'epoch': '1.632'}
+{'loss': '0.7771', 'grad_norm': '0.4324', 'learning_rate': '0.0001793', 'epoch': '1.633'}
+{'loss': '0.7665', 'grad_norm': '0.4749', 'learning_rate': '0.0001792', 'epoch': '1.633'}
+{'loss': '0.6508', 'grad_norm': '0.3801', 'learning_rate': '0.0001792', 'epoch': '1.634'}
+{'loss': '0.6949', 'grad_norm': '0.39', 'learning_rate': '0.0001792', 'epoch': '1.635'}
+{'loss': '0.7225', 'grad_norm': '0.4039', 'learning_rate': '0.0001791', 'epoch': '1.636'}
+{'loss': '0.7177', 'grad_norm': '0.4537', 'learning_rate': '0.0001791', 'epoch': '1.637'}
+{'loss': '0.8428', 'grad_norm': '0.5124', 'learning_rate': '0.0001791', 'epoch': '1.638'}
+{'loss': '0.7885', 'grad_norm': '0.5055', 'learning_rate': '0.0001791', 'epoch': '1.639'}
+{'loss': '0.8027', 'grad_norm': '0.5442', 'learning_rate': '0.000179', 'epoch': '1.639'}
+{'eval_loss': '0.7888', 'eval_runtime': '655.8', 'eval_samples_per_second': '3.141', 'eval_steps_per_second': '3.141', 'epoch': '1.639'}
+{'loss': '0.6836', 'grad_norm': '0.3747', 'learning_rate': '0.000179', 'epoch': '1.64'}
+{'loss': '0.7481', 'grad_norm': '0.4163', 'learning_rate': '0.000179', 'epoch': '1.641'}
+{'loss': '0.7534', 'grad_norm': '0.4738', 'learning_rate': '0.0001789', 'epoch': '1.642'}
+{'loss': '0.7779', 'grad_norm': '0.4688', 'learning_rate': '0.0001789', 'epoch': '1.643'}
+{'loss': '0.6942', 'grad_norm': '0.4367', 'learning_rate': '0.0001789', 'epoch': '1.644'}
+{'loss': '0.7554', 'grad_norm': '0.4334', 'learning_rate': '0.0001788', 'epoch': '1.645'}
+{'loss': '0.7388', 'grad_norm': '0.4791', 'learning_rate': '0.0001788', 'epoch': '1.646'}
+{'loss': '0.723', 'grad_norm': '0.4524', 'learning_rate': '0.0001788', 'epoch': '1.646'}
+{'loss': '0.6808', 'grad_norm': '0.4564', 'learning_rate': '0.0001788', 'epoch': '1.647'}
+{'loss': '0.6959', 'grad_norm': '0.4523', 'learning_rate': '0.0001787', 'epoch': '1.648'}
+{'loss': '0.7347', 'grad_norm': '0.5678', 'learning_rate': '0.0001787', 'epoch': '1.649'}
+{'loss': '0.728', 'grad_norm': '0.5029', 'learning_rate': '0.0001787', 'epoch': '1.65'}
+{'loss': '0.7351', 'grad_norm': '0.4217', 'learning_rate': '0.0001786', 'epoch': '1.651'}
+{'loss': '0.8166', 'grad_norm': '0.4701', 'learning_rate': '0.0001786', 'epoch': '1.652'}
+{'loss': '0.7146', 'grad_norm': '0.4151', 'learning_rate': '0.0001786', 'epoch': '1.652'}
+{'loss': '0.785', 'grad_norm': '0.524', 'learning_rate': '0.0001785', 'epoch': '1.653'}
+{'loss': '0.6815', 'grad_norm': '0.4594', 'learning_rate': '0.0001785', 'epoch': '1.654'}
+{'loss': '0.711', 'grad_norm': '0.4176', 'learning_rate': '0.0001785', 'epoch': '1.655'}
+{'loss': '0.7869', 'grad_norm': '0.4596', 'learning_rate': '0.0001785', 'epoch': '1.656'}
+{'loss': '0.7309', 'grad_norm': '0.3695', 'learning_rate': '0.0001784', 'epoch': '1.657'}
+{'loss': '0.6846', 'grad_norm': '0.4252', 'learning_rate': '0.0001784', 'epoch': '1.658'}
+{'loss': '0.7138', 'grad_norm': '0.4016', 'learning_rate': '0.0001784', 'epoch': '1.658'}
+{'loss': '0.7908', 'grad_norm': '0.4787', 'learning_rate': '0.0001783', 'epoch': '1.659'}
+{'loss': '0.6919', 'grad_norm': '0.4505', 'learning_rate': '0.0001783', 'epoch': '1.66'}
+{'loss': '0.7223', 'grad_norm': '0.4301', 'learning_rate': '0.0001783', 'epoch': '1.661'}
+{'loss': '0.8077', 'grad_norm': '0.4761', 'learning_rate': '0.0001782', 'epoch': '1.662'}
+{'loss': '0.7656', 'grad_norm': '0.4806', 'learning_rate': '0.0001782', 'epoch': '1.663'}
+{'loss': '0.7252', 'grad_norm': '0.3812', 'learning_rate': '0.0001782', 'epoch': '1.664'}
+{'loss': '0.7477', 'grad_norm': '0.479', 'learning_rate': '0.0001781', 'epoch': '1.665'}
+{'loss': '0.6986', 'grad_norm': '0.4554', 'learning_rate': '0.0001781', 'epoch': '1.665'}
+{'loss': '0.834', 'grad_norm': '0.4966', 'learning_rate': '0.0001781', 'epoch': '1.666'}
+{'loss': '0.7291', 'grad_norm': '0.4051', 'learning_rate': '0.0001781', 'epoch': '1.667'}
+{'loss': '0.7972', 'grad_norm': '0.4423', 'learning_rate': '0.000178', 'epoch': '1.668'}
+{'loss': '0.7099', 'grad_norm': '0.4735', 'learning_rate': '0.000178', 'epoch': '1.669'}
+{'loss': '0.721', 'grad_norm': '0.3836', 'learning_rate': '0.000178', 'epoch': '1.67'}
+{'loss': '0.6639', 'grad_norm': '0.3697', 'learning_rate': '0.0001779', 'epoch': '1.671'}
+{'loss': '0.8337', 'grad_norm': '0.456', 'learning_rate': '0.0001779', 'epoch': '1.671'}
+{'loss': '0.6762', 'grad_norm': '0.4367', 'learning_rate': '0.0001779', 'epoch': '1.672'}
+{'loss': '0.6977', 'grad_norm': '0.3745', 'learning_rate': '0.0001778', 'epoch': '1.673'}
+{'loss': '0.6759', 'grad_norm': '0.3762', 'learning_rate': '0.0001778', 'epoch': '1.674'}
+{'loss': '0.6577', 'grad_norm': '0.4134', 'learning_rate': '0.0001778', 'epoch': '1.675'}
+{'loss': '0.7117', 'grad_norm': '0.4174', 'learning_rate': '0.0001777', 'epoch': '1.676'}
+{'loss': '0.6871', 'grad_norm': '0.4187', 'learning_rate': '0.0001777', 'epoch': '1.677'}
+{'loss': '0.7383', 'grad_norm': '0.4779', 'learning_rate': '0.0001777', 'epoch': '1.677'}
+{'loss': '0.6783', 'grad_norm': '0.4502', 'learning_rate': '0.0001777', 'epoch': '1.678'}
+{'loss': '0.7115', 'grad_norm': '0.4124', 'learning_rate': '0.0001776', 'epoch': '1.679'}
+{'loss': '0.6699', 'grad_norm': '0.4502', 'learning_rate': '0.0001776', 'epoch': '1.68'}
+{'loss': '0.7979', 'grad_norm': '0.4966', 'learning_rate': '0.0001776', 'epoch': '1.681'}
+{'loss': '0.7991', 'grad_norm': '0.4429', 'learning_rate': '0.0001775', 'epoch': '1.682'}
+{'loss': '0.7352', 'grad_norm': '0.457', 'learning_rate': '0.0001775', 'epoch': '1.683'}
+{'eval_loss': '0.7848', 'eval_runtime': '648.2', 'eval_samples_per_second': '3.178', 'eval_steps_per_second': '3.178', 'epoch': '1.683'}
+{'loss': '0.7446', 'grad_norm': '0.3948', 'learning_rate': '0.0001775', 'epoch': '1.683'}
+{'loss': '0.7507', 'grad_norm': '0.4636', 'learning_rate': '0.0001774', 'epoch': '1.684'}
+{'loss': '0.719', 'grad_norm': '0.4355', 'learning_rate': '0.0001774', 'epoch': '1.685'}
+{'loss': '0.7768', 'grad_norm': '0.4515', 'learning_rate': '0.0001774', 'epoch': '1.686'}
+{'loss': '0.7727', 'grad_norm': '0.4586', 'learning_rate': '0.0001773', 'epoch': '1.687'}
+{'loss': '0.6987', 'grad_norm': '0.448', 'learning_rate': '0.0001773', 'epoch': '1.688'}
+{'loss': '0.6895', 'grad_norm': '0.4898', 'learning_rate': '0.0001773', 'epoch': '1.689'}
+{'loss': '0.746', 'grad_norm': '0.4865', 'learning_rate': '0.0001773', 'epoch': '1.69'}
+{'loss': '0.7301', 'grad_norm': '0.5053', 'learning_rate': '0.0001772', 'epoch': '1.69'}
+{'loss': '0.7636', 'grad_norm': '0.4818', 'learning_rate': '0.0001772', 'epoch': '1.691'}
+{'loss': '0.7761', 'grad_norm': '0.5297', 'learning_rate': '0.0001772', 'epoch': '1.692'}
+{'loss': '0.7989', 'grad_norm': '0.5226', 'learning_rate': '0.0001771', 'epoch': '1.693'}
+{'loss': '0.7615', 'grad_norm': '0.3812', 'learning_rate': '0.0001771', 'epoch': '1.694'}
+{'loss': '0.7634', 'grad_norm': '0.4084', 'learning_rate': '0.0001771', 'epoch': '1.695'}
+{'loss': '0.7364', 'grad_norm': '0.4941', 'learning_rate': '0.000177', 'epoch': '1.696'}
+{'loss': '0.6875', 'grad_norm': '0.412', 'learning_rate': '0.000177', 'epoch': '1.696'}
+{'loss': '0.7504', 'grad_norm': '0.5014', 'learning_rate': '0.000177', 'epoch': '1.697'}
+{'loss': '0.7194', 'grad_norm': '0.4563', 'learning_rate': '0.0001769', 'epoch': '1.698'}
+{'loss': '0.7517', 'grad_norm': '0.4374', 'learning_rate': '0.0001769', 'epoch': '1.699'}
+{'loss': '0.732', 'grad_norm': '0.4022', 'learning_rate': '0.0001769', 'epoch': '1.7'}
+{'loss': '0.695', 'grad_norm': '0.4292', 'learning_rate': '0.0001768', 'epoch': '1.701'}
+{'loss': '0.6977', 'grad_norm': '0.4453', 'learning_rate': '0.0001768', 'epoch': '1.702'}
+{'loss': '0.6952', 'grad_norm': '0.4532', 'learning_rate': '0.0001768', 'epoch': '1.702'}
+{'loss': '0.7816', 'grad_norm': '0.4669', 'learning_rate': '0.0001768', 'epoch': '1.703'}
+{'loss': '0.7812', 'grad_norm': '0.4818', 'learning_rate': '0.0001767', 'epoch': '1.704'}
+{'loss': '0.7351', 'grad_norm': '0.4045', 'learning_rate': '0.0001767', 'epoch': '1.705'}
+{'loss': '0.7493', 'grad_norm': '0.4597', 'learning_rate': '0.0001767', 'epoch': '1.706'}
+{'loss': '0.7472', 'grad_norm': '0.5224', 'learning_rate': '0.0001766', 'epoch': '1.707'}
+{'loss': '0.7837', 'grad_norm': '0.4571', 'learning_rate': '0.0001766', 'epoch': '1.708'}
+{'loss': '0.7454', 'grad_norm': '0.437', 'learning_rate': '0.0001766', 'epoch': '1.709'}
+{'loss': '0.7094', 'grad_norm': '0.4259', 'learning_rate': '0.0001765', 'epoch': '1.709'}
+{'loss': '0.7037', 'grad_norm': '0.412', 'learning_rate': '0.0001765', 'epoch': '1.71'}
+{'loss': '0.7217', 'grad_norm': '0.4062', 'learning_rate': '0.0001765', 'epoch': '1.711'}
+{'loss': '0.7318', 'grad_norm': '0.4649', 'learning_rate': '0.0001764', 'epoch': '1.712'}
+{'loss': '0.7065', 'grad_norm': '0.4936', 'learning_rate': '0.0001764', 'epoch': '1.713'}
+{'loss': '0.6983', 'grad_norm': '0.4545', 'learning_rate': '0.0001764', 'epoch': '1.714'}
+{'loss': '0.7517', 'grad_norm': '0.4358', 'learning_rate': '0.0001763', 'epoch': '1.715'}
+{'loss': '0.7914', 'grad_norm': '0.4218', 'learning_rate': '0.0001763', 'epoch': '1.715'}
+{'loss': '0.7101', 'grad_norm': '0.455', 'learning_rate': '0.0001763', 'epoch': '1.716'}
+{'loss': '0.7711', 'grad_norm': '0.4313', 'learning_rate': '0.0001762', 'epoch': '1.717'}
+{'loss': '0.6814', 'grad_norm': '0.4635', 'learning_rate': '0.0001762', 'epoch': '1.718'}
+{'loss': '0.7418', 'grad_norm': '0.501', 'learning_rate': '0.0001762', 'epoch': '1.719'}
+{'loss': '0.7768', 'grad_norm': '0.4253', 'learning_rate': '0.0001762', 'epoch': '1.72'}
+{'loss': '0.7049', 'grad_norm': '0.4896', 'learning_rate': '0.0001761', 'epoch': '1.721'}
+{'loss': '0.7224', 'grad_norm': '0.4293', 'learning_rate': '0.0001761', 'epoch': '1.721'}
+{'loss': '0.7204', 'grad_norm': '0.496', 'learning_rate': '0.0001761', 'epoch': '1.722'}
+{'loss': '0.6614', 'grad_norm': '0.3868', 'learning_rate': '0.000176', 'epoch': '1.723'}
+{'loss': '0.7201', 'grad_norm': '0.4299', 'learning_rate': '0.000176', 'epoch': '1.724'}
+{'loss': '0.7156', 'grad_norm': '0.4325', 'learning_rate': '0.000176', 'epoch': '1.725'}
+{'loss': '0.7259', 'grad_norm': '0.4263', 'learning_rate': '0.0001759', 'epoch': '1.726'}
+{'eval_loss': '0.7844', 'eval_runtime': '657.9', 'eval_samples_per_second': '3.131', 'eval_steps_per_second': '3.131', 'epoch': '1.726'}
+{'loss': '0.729', 'grad_norm': '0.4646', 'learning_rate': '0.0001759', 'epoch': '1.727'}
+{'loss': '0.7125', 'grad_norm': '0.4184', 'learning_rate': '0.0001759', 'epoch': '1.728'}
+{'loss': '0.7418', 'grad_norm': '0.4271', 'learning_rate': '0.0001758', 'epoch': '1.728'}
+{'loss': '0.6775', 'grad_norm': '0.4102', 'learning_rate': '0.0001758', 'epoch': '1.729'}
+{'loss': '0.7206', 'grad_norm': '0.5101', 'learning_rate': '0.0001758', 'epoch': '1.73'}
+{'loss': '0.6633', 'grad_norm': '0.435', 'learning_rate': '0.0001757', 'epoch': '1.731'}
+{'loss': '0.7945', 'grad_norm': '0.4399', 'learning_rate': '0.0001757', 'epoch': '1.732'}
+{'loss': '0.7411', 'grad_norm': '0.5157', 'learning_rate': '0.0001757', 'epoch': '1.733'}
+{'loss': '0.7249', 'grad_norm': '0.4514', 'learning_rate': '0.0001756', 'epoch': '1.734'}
+{'loss': '0.7548', 'grad_norm': '0.498', 'learning_rate': '0.0001756', 'epoch': '1.734'}
+{'loss': '0.6763', 'grad_norm': '0.4263', 'learning_rate': '0.0001756', 'epoch': '1.735'}
+{'loss': '0.8445', 'grad_norm': '0.4775', 'learning_rate': '0.0001755', 'epoch': '1.736'}
+{'loss': '0.7031', 'grad_norm': '0.4614', 'learning_rate': '0.0001755', 'epoch': '1.737'}
+{'loss': '0.7708', 'grad_norm': '0.4658', 'learning_rate': '0.0001755', 'epoch': '1.738'}
+{'loss': '0.7013', 'grad_norm': '0.4373', 'learning_rate': '0.0001754', 'epoch': '1.739'}
+{'loss': '0.7645', 'grad_norm': '0.523', 'learning_rate': '0.0001754', 'epoch': '1.74'}
+{'loss': '0.7312', 'grad_norm': '0.4254', 'learning_rate': '0.0001754', 'epoch': '1.74'}
+{'loss': '0.8043', 'grad_norm': '0.4068', 'learning_rate': '0.0001753', 'epoch': '1.741'}
+{'loss': '0.7261', 'grad_norm': '0.4729', 'learning_rate': '0.0001753', 'epoch': '1.742'}
+{'loss': '0.7968', 'grad_norm': '0.5014', 'learning_rate': '0.0001753', 'epoch': '1.743'}
+{'loss': '0.6835', 'grad_norm': '0.5017', 'learning_rate': '0.0001753', 'epoch': '1.744'}
+{'loss': '0.7421', 'grad_norm': '0.4537', 'learning_rate': '0.0001752', 'epoch': '1.745'}
+{'loss': '0.7213', 'grad_norm': '0.4342', 'learning_rate': '0.0001752', 'epoch': '1.746'}
+{'loss': '0.6757', 'grad_norm': '0.3888', 'learning_rate': '0.0001752', 'epoch': '1.746'}
+{'loss': '0.6822', 'grad_norm': '0.391', 'learning_rate': '0.0001751', 'epoch': '1.747'}
+{'loss': '0.6802', 'grad_norm': '0.4092', 'learning_rate': '0.0001751', 'epoch': '1.748'}
+{'loss': '0.7369', 'grad_norm': '0.4645', 'learning_rate': '0.0001751', 'epoch': '1.749'}
+{'loss': '0.7422', 'grad_norm': '0.4795', 'learning_rate': '0.000175', 'epoch': '1.75'}
+{'loss': '0.7371', 'grad_norm': '0.4741', 'learning_rate': '0.000175', 'epoch': '1.751'}
+{'loss': '0.6774', 'grad_norm': '0.3987', 'learning_rate': '0.000175', 'epoch': '1.752'}
+{'loss': '0.7171', 'grad_norm': '0.4111', 'learning_rate': '0.0001749', 'epoch': '1.753'}
+{'loss': '0.6958', 'grad_norm': '0.4328', 'learning_rate': '0.0001749', 'epoch': '1.753'}
+{'loss': '0.754', 'grad_norm': '0.4489', 'learning_rate': '0.0001749', 'epoch': '1.754'}
+{'loss': '0.7582', 'grad_norm': '0.4418', 'learning_rate': '0.0001748', 'epoch': '1.755'}
+{'loss': '0.7013', 'grad_norm': '0.4246', 'learning_rate': '0.0001748', 'epoch': '1.756'}
+{'loss': '0.6658', 'grad_norm': '0.4418', 'learning_rate': '0.0001748', 'epoch': '1.757'}
+{'loss': '0.6813', 'grad_norm': '0.4621', 'learning_rate': '0.0001747', 'epoch': '1.758'}
+{'loss': '0.7491', 'grad_norm': '0.4724', 'learning_rate': '0.0001747', 'epoch': '1.759'}
+{'loss': '0.7485', 'grad_norm': '0.4392', 'learning_rate': '0.0001747', 'epoch': '1.759'}
+{'loss': '0.8235', 'grad_norm': '0.4546', 'learning_rate': '0.0001746', 'epoch': '1.76'}
+{'loss': '0.8201', 'grad_norm': '0.4797', 'learning_rate': '0.0001746', 'epoch': '1.761'}
+{'loss': '0.746', 'grad_norm': '0.4489', 'learning_rate': '0.0001746', 'epoch': '1.762'}
+{'loss': '0.7544', 'grad_norm': '0.4407', 'learning_rate': '0.0001745', 'epoch': '1.763'}
+{'loss': '0.7942', 'grad_norm': '0.5178', 'learning_rate': '0.0001745', 'epoch': '1.764'}
+{'loss': '0.6762', 'grad_norm': '0.4069', 'learning_rate': '0.0001745', 'epoch': '1.765'}
+{'loss': '0.6959', 'grad_norm': '0.4211', 'learning_rate': '0.0001744', 'epoch': '1.765'}
+{'loss': '0.8068', 'grad_norm': '0.4824', 'learning_rate': '0.0001744', 'epoch': '1.766'}
+{'loss': '0.8048', 'grad_norm': '0.4846', 'learning_rate': '0.0001744', 'epoch': '1.767'}
+{'loss': '0.7465', 'grad_norm': '0.4789', 'learning_rate': '0.0001743', 'epoch': '1.768'}
+{'loss': '0.7087', 'grad_norm': '0.4116', 'learning_rate': '0.0001743', 'epoch': '1.769'}
+{'eval_loss': '0.7808', 'eval_runtime': '666.6', 'eval_samples_per_second': '3.09', 'eval_steps_per_second': '3.09', 'epoch': '1.769'}
+{'loss': '0.6838', 'grad_norm': '0.4018', 'learning_rate': '0.0001743', 'epoch': '1.77'}
+{'loss': '0.7254', 'grad_norm': '0.47', 'learning_rate': '0.0001742', 'epoch': '1.771'}
+{'loss': '0.7273', 'grad_norm': '0.503', 'learning_rate': '0.0001742', 'epoch': '1.772'}
+{'loss': '0.704', 'grad_norm': '0.463', 'learning_rate': '0.0001742', 'epoch': '1.772'}
+{'loss': '0.7253', 'grad_norm': '0.4318', 'learning_rate': '0.0001741', 'epoch': '1.773'}
+{'loss': '0.6736', 'grad_norm': '0.4026', 'learning_rate': '0.0001741', 'epoch': '1.774'}
+{'loss': '0.6925', 'grad_norm': '0.4419', 'learning_rate': '0.0001741', 'epoch': '1.775'}
+{'loss': '0.7089', 'grad_norm': '0.5186', 'learning_rate': '0.000174', 'epoch': '1.776'}
+{'loss': '0.6548', 'grad_norm': '0.4504', 'learning_rate': '0.000174', 'epoch': '1.777'}
+{'loss': '0.6819', 'grad_norm': '0.4164', 'learning_rate': '0.000174', 'epoch': '1.778'}
+{'loss': '0.7921', 'grad_norm': '0.4045', 'learning_rate': '0.0001739', 'epoch': '1.778'}
+{'loss': '0.7775', 'grad_norm': '0.417', 'learning_rate': '0.0001739', 'epoch': '1.779'}
+{'loss': '0.7777', 'grad_norm': '0.4969', 'learning_rate': '0.0001739', 'epoch': '1.78'}
+{'loss': '0.6679', 'grad_norm': '0.3691', 'learning_rate': '0.0001738', 'epoch': '1.781'}
+{'loss': '0.7692', 'grad_norm': '0.4766', 'learning_rate': '0.0001738', 'epoch': '1.782'}
+{'loss': '0.7128', 'grad_norm': '0.4597', 'learning_rate': '0.0001738', 'epoch': '1.783'}
+{'loss': '0.7562', 'grad_norm': '0.4738', 'learning_rate': '0.0001737', 'epoch': '1.784'}
+{'loss': '0.7397', 'grad_norm': '0.4069', 'learning_rate': '0.0001737', 'epoch': '1.784'}
+{'loss': '0.8365', 'grad_norm': '0.4962', 'learning_rate': '0.0001737', 'epoch': '1.785'}
+{'loss': '0.7582', 'grad_norm': '0.4428', 'learning_rate': '0.0001736', 'epoch': '1.786'}
+{'loss': '0.6731', 'grad_norm': '0.4294', 'learning_rate': '0.0001736', 'epoch': '1.787'}
+{'loss': '0.8141', 'grad_norm': '0.4188', 'learning_rate': '0.0001736', 'epoch': '1.788'}
+{'loss': '0.7832', 'grad_norm': '0.4143', 'learning_rate': '0.0001735', 'epoch': '1.789'}
+{'loss': '0.6969', 'grad_norm': '0.4523', 'learning_rate': '0.0001735', 'epoch': '1.79'}
+{'loss': '0.6733', 'grad_norm': '0.5915', 'learning_rate': '0.0001735', 'epoch': '1.791'}
+{'loss': '0.7403', 'grad_norm': '0.4138', 'learning_rate': '0.0001734', 'epoch': '1.791'}
+{'loss': '0.6875', 'grad_norm': '0.3962', 'learning_rate': '0.0001734', 'epoch': '1.792'}
+{'loss': '0.6919', 'grad_norm': '0.464', 'learning_rate': '0.0001734', 'epoch': '1.793'}
+{'loss': '0.7563', 'grad_norm': '0.4031', 'learning_rate': '0.0001733', 'epoch': '1.794'}
+{'loss': '0.7299', 'grad_norm': '0.4478', 'learning_rate': '0.0001733', 'epoch': '1.795'}
+{'loss': '0.8119', 'grad_norm': '0.5002', 'learning_rate': '0.0001733', 'epoch': '1.796'}
+{'loss': '0.6835', 'grad_norm': '0.4646', 'learning_rate': '0.0001732', 'epoch': '1.797'}
+{'loss': '0.7309', 'grad_norm': '0.3974', 'learning_rate': '0.0001732', 'epoch': '1.797'}
+{'loss': '0.6358', 'grad_norm': '0.3675', 'learning_rate': '0.0001732', 'epoch': '1.798'}
+{'loss': '0.7257', 'grad_norm': '0.5021', 'learning_rate': '0.0001731', 'epoch': '1.799'}
+{'loss': '0.653', 'grad_norm': '0.4399', 'learning_rate': '0.0001731', 'epoch': '1.8'}
+{'loss': '0.7407', 'grad_norm': '0.4718', 'learning_rate': '0.0001731', 'epoch': '1.801'}
+{'loss': '0.7142', 'grad_norm': '0.423', 'learning_rate': '0.000173', 'epoch': '1.802'}
+{'loss': '0.7233', 'grad_norm': '0.4779', 'learning_rate': '0.000173', 'epoch': '1.803'}
+{'loss': '0.7121', 'grad_norm': '0.3854', 'learning_rate': '0.000173', 'epoch': '1.803'}
+{'loss': '0.7121', 'grad_norm': '0.4333', 'learning_rate': '0.0001729', 'epoch': '1.804'}
+{'loss': '0.7958', 'grad_norm': '0.4874', 'learning_rate': '0.0001729', 'epoch': '1.805'}
+{'loss': '0.6963', 'grad_norm': '0.4764', 'learning_rate': '0.0001729', 'epoch': '1.806'}
+{'loss': '0.6778', 'grad_norm': '0.45', 'learning_rate': '0.0001728', 'epoch': '1.807'}
+{'loss': '0.7178', 'grad_norm': '0.4615', 'learning_rate': '0.0001728', 'epoch': '1.808'}
+{'loss': '0.6446', 'grad_norm': '0.3912', 'learning_rate': '0.0001728', 'epoch': '1.809'}
+{'loss': '0.8183', 'grad_norm': '0.4416', 'learning_rate': '0.0001727', 'epoch': '1.809'}
+{'loss': '0.7083', 'grad_norm': '0.4512', 'learning_rate': '0.0001727', 'epoch': '1.81'}
+{'loss': '0.7655', 'grad_norm': '0.5312', 'learning_rate': '0.0001727', 'epoch': '1.811'}
+{'loss': '0.8182', 'grad_norm': '0.4402', 'learning_rate': '0.0001726', 'epoch': '1.812'}
+{'eval_loss': '0.7769', 'eval_runtime': '664.5', 'eval_samples_per_second': '3.1', 'eval_steps_per_second': '3.1', 'epoch': '1.812'}
+{'loss': '0.6492', 'grad_norm': '0.4037', 'learning_rate': '0.0001726', 'epoch': '1.813'}
+{'loss': '0.723', 'grad_norm': '0.495', 'learning_rate': '0.0001726', 'epoch': '1.814'}
+{'loss': '0.7157', 'grad_norm': '0.4659', 'learning_rate': '0.0001725', 'epoch': '1.815'}
+{'loss': '0.7164', 'grad_norm': '0.4222', 'learning_rate': '0.0001725', 'epoch': '1.816'}
+{'loss': '0.8364', 'grad_norm': '0.4654', 'learning_rate': '0.0001725', 'epoch': '1.816'}
+{'loss': '0.7097', 'grad_norm': '0.42', 'learning_rate': '0.0001724', 'epoch': '1.817'}
+{'loss': '0.767', 'grad_norm': '0.4079', 'learning_rate': '0.0001724', 'epoch': '1.818'}
+{'loss': '0.8242', 'grad_norm': '0.5402', 'learning_rate': '0.0001724', 'epoch': '1.819'}
+{'loss': '0.7157', 'grad_norm': '0.5155', 'learning_rate': '0.0001723', 'epoch': '1.82'}
+{'loss': '0.6946', 'grad_norm': '0.4135', 'learning_rate': '0.0001723', 'epoch': '1.821'}
+{'loss': '0.7904', 'grad_norm': '0.496', 'learning_rate': '0.0001723', 'epoch': '1.822'}
+{'loss': '0.7332', 'grad_norm': '0.4391', 'learning_rate': '0.0001722', 'epoch': '1.822'}
+{'loss': '0.71', 'grad_norm': '0.4315', 'learning_rate': '0.0001722', 'epoch': '1.823'}
+{'loss': '0.7503', 'grad_norm': '0.4149', 'learning_rate': '0.0001722', 'epoch': '1.824'}
+{'loss': '0.7042', 'grad_norm': '0.3963', 'learning_rate': '0.0001721', 'epoch': '1.825'}
+{'loss': '0.6458', 'grad_norm': '0.4038', 'learning_rate': '0.0001721', 'epoch': '1.826'}
+{'loss': '0.7379', 'grad_norm': '0.4731', 'learning_rate': '0.0001721', 'epoch': '1.827'}
+{'loss': '0.7307', 'grad_norm': '0.4866', 'learning_rate': '0.000172', 'epoch': '1.828'}
+{'loss': '0.743', 'grad_norm': '0.4285', 'learning_rate': '0.000172', 'epoch': '1.828'}
+{'loss': '0.8381', 'grad_norm': '0.4573', 'learning_rate': '0.000172', 'epoch': '1.829'}
+{'loss': '0.7591', 'grad_norm': '0.415', 'learning_rate': '0.0001719', 'epoch': '1.83'}
+{'loss': '0.6875', 'grad_norm': '0.5213', 'learning_rate': '0.0001719', 'epoch': '1.831'}
+{'loss': '0.6905', 'grad_norm': '0.399', 'learning_rate': '0.0001719', 'epoch': '1.832'}
+{'loss': '0.7298', 'grad_norm': '0.4724', 'learning_rate': '0.0001718', 'epoch': '1.833'}
+{'loss': '0.63', 'grad_norm': '0.3762', 'learning_rate': '0.0001718', 'epoch': '1.834'}
+{'loss': '0.703', 'grad_norm': '0.4741', 'learning_rate': '0.0001718', 'epoch': '1.835'}
+{'loss': '0.639', 'grad_norm': '0.3599', 'learning_rate': '0.0001717', 'epoch': '1.835'}
+{'loss': '0.6876', 'grad_norm': '0.4635', 'learning_rate': '0.0001717', 'epoch': '1.836'}
+{'loss': '0.7721', 'grad_norm': '0.461', 'learning_rate': '0.0001717', 'epoch': '1.837'}
+{'loss': '0.7186', 'grad_norm': '0.4015', 'learning_rate': '0.0001716', 'epoch': '1.838'}
+{'loss': '0.7027', 'grad_norm': '0.4806', 'learning_rate': '0.0001716', 'epoch': '1.839'}
+{'loss': '0.699', 'grad_norm': '0.4234', 'learning_rate': '0.0001716', 'epoch': '1.84'}
+{'loss': '0.6705', 'grad_norm': '0.412', 'learning_rate': '0.0001715', 'epoch': '1.841'}
+{'loss': '0.6863', 'grad_norm': '0.4329', 'learning_rate': '0.0001715', 'epoch': '1.841'}
+{'loss': '0.7469', 'grad_norm': '0.5093', 'learning_rate': '0.0001714', 'epoch': '1.842'}
+{'loss': '0.7447', 'grad_norm': '0.4891', 'learning_rate': '0.0001714', 'epoch': '1.843'}
+{'loss': '0.6919', 'grad_norm': '0.4578', 'learning_rate': '0.0001714', 'epoch': '1.844'}
+{'loss': '0.6956', 'grad_norm': '0.4691', 'learning_rate': '0.0001713', 'epoch': '1.845'}
+{'loss': '0.7486', 'grad_norm': '0.4817', 'learning_rate': '0.0001713', 'epoch': '1.846'}
+{'loss': '0.7992', 'grad_norm': '0.4701', 'learning_rate': '0.0001713', 'epoch': '1.847'}
+{'loss': '0.6578', 'grad_norm': '0.3777', 'learning_rate': '0.0001712', 'epoch': '1.847'}
+{'loss': '0.725', 'grad_norm': '0.4056', 'learning_rate': '0.0001712', 'epoch': '1.848'}
+{'loss': '0.7517', 'grad_norm': '0.4075', 'learning_rate': '0.0001712', 'epoch': '1.849'}
+{'loss': '0.6159', 'grad_norm': '0.4046', 'learning_rate': '0.0001711', 'epoch': '1.85'}
+{'loss': '0.7236', 'grad_norm': '0.4492', 'learning_rate': '0.0001711', 'epoch': '1.851'}
+{'loss': '0.7719', 'grad_norm': '0.4565', 'learning_rate': '0.0001711', 'epoch': '1.852'}
+{'loss': '0.7165', 'grad_norm': '0.4203', 'learning_rate': '0.000171', 'epoch': '1.853'}
+{'loss': '0.675', 'grad_norm': '0.437', 'learning_rate': '0.000171', 'epoch': '1.854'}
+{'loss': '0.7487', 'grad_norm': '0.4253', 'learning_rate': '0.000171', 'epoch': '1.854'}
+{'loss': '0.6766', 'grad_norm': '0.4334', 'learning_rate': '0.0001709', 'epoch': '1.855'}
+{'eval_loss': '0.7747', 'eval_runtime': '654.7', 'eval_samples_per_second': '3.146', 'eval_steps_per_second': '3.146', 'epoch': '1.855'}
+{'loss': '0.6959', 'grad_norm': '0.4383', 'learning_rate': '0.0001709', 'epoch': '1.856'}
+{'loss': '0.7561', 'grad_norm': '0.481', 'learning_rate': '0.0001709', 'epoch': '1.857'}
+{'loss': '0.8058', 'grad_norm': '0.4798', 'learning_rate': '0.0001708', 'epoch': '1.858'}
+{'loss': '0.7262', 'grad_norm': '0.4485', 'learning_rate': '0.0001708', 'epoch': '1.859'}
+{'loss': '0.7', 'grad_norm': '0.4112', 'learning_rate': '0.0001708', 'epoch': '1.86'}
+{'loss': '0.7536', 'grad_norm': '0.4403', 'learning_rate': '0.0001707', 'epoch': '1.86'}
+{'loss': '0.7926', 'grad_norm': '0.433', 'learning_rate': '0.0001707', 'epoch': '1.861'}
+{'loss': '0.7327', 'grad_norm': '0.5362', 'learning_rate': '0.0001707', 'epoch': '1.862'}
+{'loss': '0.786', 'grad_norm': '0.506', 'learning_rate': '0.0001706', 'epoch': '1.863'}
+{'loss': '0.7027', 'grad_norm': '0.4489', 'learning_rate': '0.0001706', 'epoch': '1.864'}
+{'loss': '0.7488', 'grad_norm': '0.4356', 'learning_rate': '0.0001705', 'epoch': '1.865'}
+{'loss': '0.6919', 'grad_norm': '0.4135', 'learning_rate': '0.0001705', 'epoch': '1.866'}
+{'loss': '0.6864', 'grad_norm': '0.4664', 'learning_rate': '0.0001705', 'epoch': '1.866'}
+{'loss': '0.6459', 'grad_norm': '0.3684', 'learning_rate': '0.0001704', 'epoch': '1.867'}
+{'loss': '0.7037', 'grad_norm': '0.3861', 'learning_rate': '0.0001704', 'epoch': '1.868'}
+{'loss': '0.7066', 'grad_norm': '0.5003', 'learning_rate': '0.0001704', 'epoch': '1.869'}
+{'loss': '0.7433', 'grad_norm': '0.5434', 'learning_rate': '0.0001703', 'epoch': '1.87'}
+{'loss': '0.6967', 'grad_norm': '0.4365', 'learning_rate': '0.0001703', 'epoch': '1.871'}
+{'loss': '0.7881', 'grad_norm': '0.4349', 'learning_rate': '0.0001703', 'epoch': '1.872'}
+{'loss': '0.7418', 'grad_norm': '0.4579', 'learning_rate': '0.0001702', 'epoch': '1.872'}
+{'loss': '0.7073', 'grad_norm': '0.4458', 'learning_rate': '0.0001702', 'epoch': '1.873'}
+{'loss': '0.7597', 'grad_norm': '0.4729', 'learning_rate': '0.0001702', 'epoch': '1.874'}
+{'loss': '0.7038', 'grad_norm': '0.4678', 'learning_rate': '0.0001701', 'epoch': '1.875'}
+{'loss': '0.7227', 'grad_norm': '0.416', 'learning_rate': '0.0001701', 'epoch': '1.876'}
+{'loss': '0.7137', 'grad_norm': '0.4297', 'learning_rate': '0.0001701', 'epoch': '1.877'}
+{'loss': '0.8357', 'grad_norm': '0.4697', 'learning_rate': '0.00017', 'epoch': '1.878'}
+{'loss': '0.7203', 'grad_norm': '0.4686', 'learning_rate': '0.00017', 'epoch': '1.879'}
+{'loss': '0.7082', 'grad_norm': '0.4536', 'learning_rate': '0.00017', 'epoch': '1.879'}
+{'loss': '0.6428', 'grad_norm': '0.4228', 'learning_rate': '0.0001699', 'epoch': '1.88'}
+{'loss': '0.7378', 'grad_norm': '0.4608', 'learning_rate': '0.0001699', 'epoch': '1.881'}
+{'loss': '0.7451', 'grad_norm': '0.4234', 'learning_rate': '0.0001699', 'epoch': '1.882'}
+{'loss': '0.7286', 'grad_norm': '0.437', 'learning_rate': '0.0001698', 'epoch': '1.883'}
+{'loss': '0.7078', 'grad_norm': '0.4584', 'learning_rate': '0.0001698', 'epoch': '1.884'}
+{'loss': '0.6466', 'grad_norm': '0.4132', 'learning_rate': '0.0001697', 'epoch': '1.885'}
+{'loss': '0.6375', 'grad_norm': '0.4395', 'learning_rate': '0.0001697', 'epoch': '1.885'}
+{'loss': '0.7524', 'grad_norm': '0.4726', 'learning_rate': '0.0001697', 'epoch': '1.886'}
+{'loss': '0.765', 'grad_norm': '0.4484', 'learning_rate': '0.0001696', 'epoch': '1.887'}
+{'loss': '0.7077', 'grad_norm': '0.4', 'learning_rate': '0.0001696', 'epoch': '1.888'}
+{'loss': '0.711', 'grad_norm': '0.468', 'learning_rate': '0.0001696', 'epoch': '1.889'}
+{'loss': '0.6677', 'grad_norm': '0.431', 'learning_rate': '0.0001695', 'epoch': '1.89'}
+{'loss': '0.7011', 'grad_norm': '0.4098', 'learning_rate': '0.0001695', 'epoch': '1.891'}
+{'loss': '0.7501', 'grad_norm': '0.4527', 'learning_rate': '0.0001695', 'epoch': '1.891'}
+{'loss': '0.8413', 'grad_norm': '0.4487', 'learning_rate': '0.0001694', 'epoch': '1.892'}
+{'loss': '0.7479', 'grad_norm': '0.3907', 'learning_rate': '0.0001694', 'epoch': '1.893'}
+{'loss': '0.7405', 'grad_norm': '0.4497', 'learning_rate': '0.0001694', 'epoch': '1.894'}
+{'loss': '0.7161', 'grad_norm': '0.4262', 'learning_rate': '0.0001693', 'epoch': '1.895'}
+{'loss': '0.6597', 'grad_norm': '0.4741', 'learning_rate': '0.0001693', 'epoch': '1.896'}
+{'loss': '0.702', 'grad_norm': '0.4941', 'learning_rate': '0.0001693', 'epoch': '1.897'}
+{'loss': '0.6818', 'grad_norm': '0.4449', 'learning_rate': '0.0001692', 'epoch': '1.898'}
+{'loss': '0.6696', 'grad_norm': '0.419', 'learning_rate': '0.0001692', 'epoch': '1.898'}
+{'eval_loss': '0.7716', 'eval_runtime': '648.4', 'eval_samples_per_second': '3.177', 'eval_steps_per_second': '3.177', 'epoch': '1.898'}
+{'loss': '0.6992', 'grad_norm': '0.4762', 'learning_rate': '0.0001691', 'epoch': '1.899'}
+{'loss': '0.607', 'grad_norm': '0.4382', 'learning_rate': '0.0001691', 'epoch': '1.9'}
+{'loss': '0.6768', 'grad_norm': '0.4941', 'learning_rate': '0.0001691', 'epoch': '1.901'}
+{'loss': '0.6732', 'grad_norm': '0.397', 'learning_rate': '0.000169', 'epoch': '1.902'}
+{'loss': '0.7694', 'grad_norm': '0.4666', 'learning_rate': '0.000169', 'epoch': '1.903'}
+{'loss': '0.8102', 'grad_norm': '0.3906', 'learning_rate': '0.000169', 'epoch': '1.904'}
+{'loss': '0.695', 'grad_norm': '0.4514', 'learning_rate': '0.0001689', 'epoch': '1.904'}
+{'loss': '0.6316', 'grad_norm': '0.3607', 'learning_rate': '0.0001689', 'epoch': '1.905'}
+{'loss': '0.7362', 'grad_norm': '0.456', 'learning_rate': '0.0001689', 'epoch': '1.906'}
+{'loss': '0.6638', 'grad_norm': '0.4201', 'learning_rate': '0.0001688', 'epoch': '1.907'}
+{'loss': '0.7144', 'grad_norm': '0.4336', 'learning_rate': '0.0001688', 'epoch': '1.908'}
+{'loss': '0.7919', 'grad_norm': '0.4549', 'learning_rate': '0.0001688', 'epoch': '1.909'}
+{'loss': '0.7775', 'grad_norm': '0.4196', 'learning_rate': '0.0001687', 'epoch': '1.91'}
+{'loss': '0.7011', 'grad_norm': '0.4019', 'learning_rate': '0.0001687', 'epoch': '1.91'}
+{'loss': '0.7481', 'grad_norm': '0.4803', 'learning_rate': '0.0001686', 'epoch': '1.911'}
+{'loss': '0.7104', 'grad_norm': '0.4976', 'learning_rate': '0.0001686', 'epoch': '1.912'}
+{'loss': '0.6993', 'grad_norm': '0.433', 'learning_rate': '0.0001686', 'epoch': '1.913'}
+{'loss': '0.7065', 'grad_norm': '0.3929', 'learning_rate': '0.0001685', 'epoch': '1.914'}
+{'loss': '0.7383', 'grad_norm': '0.4756', 'learning_rate': '0.0001685', 'epoch': '1.915'}
+{'loss': '0.6742', 'grad_norm': '0.4169', 'learning_rate': '0.0001685', 'epoch': '1.916'}
+{'loss': '0.7861', 'grad_norm': '0.4729', 'learning_rate': '0.0001684', 'epoch': '1.917'}
+{'loss': '0.7681', 'grad_norm': '0.4734', 'learning_rate': '0.0001684', 'epoch': '1.917'}
+{'loss': '0.7587', 'grad_norm': '0.4441', 'learning_rate': '0.0001684', 'epoch': '1.918'}
+{'loss': '0.6908', 'grad_norm': '0.4442', 'learning_rate': '0.0001683', 'epoch': '1.919'}
+{'loss': '0.7139', 'grad_norm': '0.4286', 'learning_rate': '0.0001683', 'epoch': '1.92'}
+{'loss': '0.7594', 'grad_norm': '0.4623', 'learning_rate': '0.0001683', 'epoch': '1.921'}
+{'loss': '0.7202', 'grad_norm': '0.4697', 'learning_rate': '0.0001682', 'epoch': '1.922'}
+{'loss': '0.712', 'grad_norm': '0.5053', 'learning_rate': '0.0001682', 'epoch': '1.923'}
+{'loss': '0.6813', 'grad_norm': '0.4012', 'learning_rate': '0.0001681', 'epoch': '1.923'}
+{'loss': '0.7549', 'grad_norm': '0.4781', 'learning_rate': '0.0001681', 'epoch': '1.924'}
+{'loss': '0.6556', 'grad_norm': '0.4201', 'learning_rate': '0.0001681', 'epoch': '1.925'}
+{'loss': '0.6886', 'grad_norm': '0.3985', 'learning_rate': '0.000168', 'epoch': '1.926'}
+{'loss': '0.7376', 'grad_norm': '0.4685', 'learning_rate': '0.000168', 'epoch': '1.927'}
+{'loss': '0.7664', 'grad_norm': '0.4541', 'learning_rate': '0.000168', 'epoch': '1.928'}
+{'loss': '0.7323', 'grad_norm': '0.3871', 'learning_rate': '0.0001679', 'epoch': '1.929'}
+{'loss': '0.7808', 'grad_norm': '0.5057', 'learning_rate': '0.0001679', 'epoch': '1.929'}
+{'loss': '0.7619', 'grad_norm': '0.5219', 'learning_rate': '0.0001679', 'epoch': '1.93'}
+{'loss': '0.76', 'grad_norm': '0.4914', 'learning_rate': '0.0001678', 'epoch': '1.931'}
+{'loss': '0.7246', 'grad_norm': '0.4482', 'learning_rate': '0.0001678', 'epoch': '1.932'}
+{'loss': '0.7845', 'grad_norm': '0.4031', 'learning_rate': '0.0001677', 'epoch': '1.933'}
+{'loss': '0.6626', 'grad_norm': '0.4533', 'learning_rate': '0.0001677', 'epoch': '1.934'}
+{'loss': '0.7042', 'grad_norm': '0.421', 'learning_rate': '0.0001677', 'epoch': '1.935'}
+{'loss': '0.6547', 'grad_norm': '0.4463', 'learning_rate': '0.0001676', 'epoch': '1.935'}
+{'loss': '0.7318', 'grad_norm': '0.4141', 'learning_rate': '0.0001676', 'epoch': '1.936'}
+{'loss': '0.7247', 'grad_norm': '0.4224', 'learning_rate': '0.0001676', 'epoch': '1.937'}
+{'loss': '0.6859', 'grad_norm': '0.4295', 'learning_rate': '0.0001675', 'epoch': '1.938'}
+{'loss': '0.6655', 'grad_norm': '0.4345', 'learning_rate': '0.0001675', 'epoch': '1.939'}
+{'loss': '0.7616', 'grad_norm': '0.4897', 'learning_rate': '0.0001675', 'epoch': '1.94'}
+{'loss': '0.7909', 'grad_norm': '0.5315', 'learning_rate': '0.0001674', 'epoch': '1.941'}
+{'loss': '0.7348', 'grad_norm': '0.4206', 'learning_rate': '0.0001674', 'epoch': '1.942'}
+{'eval_loss': '0.771', 'eval_runtime': '660.5', 'eval_samples_per_second': '3.119', 'eval_steps_per_second': '3.119', 'epoch': '1.942'}
+{'loss': '0.6707', 'grad_norm': '0.4044', 'learning_rate': '0.0001673', 'epoch': '1.942'}
+{'loss': '0.7006', 'grad_norm': '0.462', 'learning_rate': '0.0001673', 'epoch': '1.943'}
+{'loss': '0.7158', 'grad_norm': '0.4387', 'learning_rate': '0.0001673', 'epoch': '1.944'}
+{'loss': '0.7862', 'grad_norm': '0.4543', 'learning_rate': '0.0001672', 'epoch': '1.945'}
+{'loss': '0.6546', 'grad_norm': '0.3978', 'learning_rate': '0.0001672', 'epoch': '1.946'}
+{'loss': '0.6738', 'grad_norm': '0.3749', 'learning_rate': '0.0001672', 'epoch': '1.947'}
+{'loss': '0.7946', 'grad_norm': '0.3885', 'learning_rate': '0.0001671', 'epoch': '1.948'}
+{'loss': '0.7192', 'grad_norm': '0.4713', 'learning_rate': '0.0001671', 'epoch': '1.948'}
+{'loss': '0.6459', 'grad_norm': '0.4044', 'learning_rate': '0.0001671', 'epoch': '1.949'}
+{'loss': '0.7456', 'grad_norm': '0.4425', 'learning_rate': '0.000167', 'epoch': '1.95'}
+{'loss': '0.7447', 'grad_norm': '0.4674', 'learning_rate': '0.000167', 'epoch': '1.951'}
+{'loss': '0.6882', 'grad_norm': '0.4142', 'learning_rate': '0.0001669', 'epoch': '1.952'}
+{'loss': '0.6678', 'grad_norm': '0.4211', 'learning_rate': '0.0001669', 'epoch': '1.953'}
+{'loss': '0.7364', 'grad_norm': '0.453', 'learning_rate': '0.0001669', 'epoch': '1.954'}
+{'loss': '0.7233', 'grad_norm': '0.4712', 'learning_rate': '0.0001668', 'epoch': '1.954'}
+{'loss': '0.7176', 'grad_norm': '0.496', 'learning_rate': '0.0001668', 'epoch': '1.955'}
+{'loss': '0.6606', 'grad_norm': '0.419', 'learning_rate': '0.0001668', 'epoch': '1.956'}
+{'loss': '0.6761', 'grad_norm': '0.3645', 'learning_rate': '0.0001667', 'epoch': '1.957'}
+{'loss': '0.7179', 'grad_norm': '0.4324', 'learning_rate': '0.0001667', 'epoch': '1.958'}
+{'loss': '0.796', 'grad_norm': '0.4657', 'learning_rate': '0.0001667', 'epoch': '1.959'}
+{'loss': '0.6422', 'grad_norm': '0.3825', 'learning_rate': '0.0001666', 'epoch': '1.96'}
+{'loss': '0.7824', 'grad_norm': '0.5343', 'learning_rate': '0.0001666', 'epoch': '1.961'}
+{'loss': '0.7899', 'grad_norm': '0.4239', 'learning_rate': '0.0001665', 'epoch': '1.961'}
+{'loss': '0.7321', 'grad_norm': '0.4592', 'learning_rate': '0.0001665', 'epoch': '1.962'}
+{'loss': '0.6994', 'grad_norm': '0.4405', 'learning_rate': '0.0001665', 'epoch': '1.963'}
+{'loss': '0.6603', 'grad_norm': '0.4649', 'learning_rate': '0.0001664', 'epoch': '1.964'}
+{'loss': '0.6613', 'grad_norm': '0.4136', 'learning_rate': '0.0001664', 'epoch': '1.965'}
+{'loss': '0.695', 'grad_norm': '0.3731', 'learning_rate': '0.0001664', 'epoch': '1.966'}
+{'loss': '0.7661', 'grad_norm': '0.4714', 'learning_rate': '0.0001663', 'epoch': '1.967'}
+{'loss': '0.6519', 'grad_norm': '0.4387', 'learning_rate': '0.0001663', 'epoch': '1.967'}
+{'loss': '0.7195', 'grad_norm': '0.4187', 'learning_rate': '0.0001663', 'epoch': '1.968'}
+{'loss': '0.6897', 'grad_norm': '0.4131', 'learning_rate': '0.0001662', 'epoch': '1.969'}
+{'loss': '0.7319', 'grad_norm': '0.4567', 'learning_rate': '0.0001662', 'epoch': '1.97'}
+{'loss': '0.6962', 'grad_norm': '0.4126', 'learning_rate': '0.0001661', 'epoch': '1.971'}
+{'loss': '0.6799', 'grad_norm': '0.4192', 'learning_rate': '0.0001661', 'epoch': '1.972'}
+{'loss': '0.7198', 'grad_norm': '0.4782', 'learning_rate': '0.0001661', 'epoch': '1.973'}
+{'loss': '0.7587', 'grad_norm': '0.5019', 'learning_rate': '0.000166', 'epoch': '1.973'}
+{'loss': '0.6897', 'grad_norm': '0.4476', 'learning_rate': '0.000166', 'epoch': '1.974'}
+{'loss': '0.7211', 'grad_norm': '0.3785', 'learning_rate': '0.000166', 'epoch': '1.975'}
+{'loss': '0.6902', 'grad_norm': '0.4244', 'learning_rate': '0.0001659', 'epoch': '1.976'}
+{'loss': '0.6946', 'grad_norm': '0.4347', 'learning_rate': '0.0001659', 'epoch': '1.977'}
+{'loss': '0.7263', 'grad_norm': '0.3986', 'learning_rate': '0.0001658', 'epoch': '1.978'}
+{'loss': '0.7584', 'grad_norm': '0.4527', 'learning_rate': '0.0001658', 'epoch': '1.979'}
+{'loss': '0.685', 'grad_norm': '0.4119', 'learning_rate': '0.0001658', 'epoch': '1.98'}
+{'loss': '0.8459', 'grad_norm': '0.4432', 'learning_rate': '0.0001657', 'epoch': '1.98'}
+{'loss': '0.6919', 'grad_norm': '0.4019', 'learning_rate': '0.0001657', 'epoch': '1.981'}
+{'loss': '0.6753', 'grad_norm': '0.4172', 'learning_rate': '0.0001657', 'epoch': '1.982'}
+{'loss': '0.7096', 'grad_norm': '0.445', 'learning_rate': '0.0001656', 'epoch': '1.983'}
+{'loss': '0.6265', 'grad_norm': '0.4279', 'learning_rate': '0.0001656', 'epoch': '1.984'}
+{'loss': '0.6721', 'grad_norm': '0.4739', 'learning_rate': '0.0001656', 'epoch': '1.985'}
+{'eval_loss': '0.7694', 'eval_runtime': '666.4', 'eval_samples_per_second': '3.091', 'eval_steps_per_second': '3.091', 'epoch': '1.985'}
+{'loss': '0.6513', 'grad_norm': '0.4102', 'learning_rate': '0.0001655', 'epoch': '1.986'}
+{'loss': '0.7818', 'grad_norm': '0.4961', 'learning_rate': '0.0001655', 'epoch': '1.986'}
+{'loss': '0.6234', 'grad_norm': '0.45', 'learning_rate': '0.0001654', 'epoch': '1.987'}
+{'loss': '0.6288', 'grad_norm': '0.3829', 'learning_rate': '0.0001654', 'epoch': '1.988'}
+{'loss': '0.7176', 'grad_norm': '0.4997', 'learning_rate': '0.0001654', 'epoch': '1.989'}
+{'loss': '0.711', 'grad_norm': '0.4607', 'learning_rate': '0.0001653', 'epoch': '1.99'}
+{'loss': '0.6039', 'grad_norm': '0.4056', 'learning_rate': '0.0001653', 'epoch': '1.991'}
+{'loss': '0.6963', 'grad_norm': '0.4325', 'learning_rate': '0.0001653', 'epoch': '1.992'}
+{'loss': '0.7562', 'grad_norm': '0.4611', 'learning_rate': '0.0001652', 'epoch': '1.992'}
+{'loss': '0.7664', 'grad_norm': '0.4749', 'learning_rate': '0.0001652', 'epoch': '1.993'}
+{'loss': '0.6699', 'grad_norm': '0.4093', 'learning_rate': '0.0001651', 'epoch': '1.994'}
+{'loss': '0.5954', 'grad_norm': '0.4346', 'learning_rate': '0.0001651', 'epoch': '1.995'}
+{'loss': '0.7328', 'grad_norm': '0.4573', 'learning_rate': '0.0001651', 'epoch': '1.996'}
+{'loss': '0.7281', 'grad_norm': '0.4463', 'learning_rate': '0.000165', 'epoch': '1.997'}
+{'loss': '0.7085', 'grad_norm': '0.4535', 'learning_rate': '0.000165', 'epoch': '1.998'}
+{'loss': '0.7145', 'grad_norm': '0.434', 'learning_rate': '0.000165', 'epoch': '1.998'}
+{'loss': '0.6043', 'grad_norm': '0.3664', 'learning_rate': '0.0001649', 'epoch': '1.999'}
+{'loss': '0.6522', 'grad_norm': '0.6387', 'learning_rate': '0.0001649', 'epoch': '2'}
+{'loss': '0.6836', 'grad_norm': '0.5208', 'learning_rate': '0.0001648', 'epoch': '2.001'}
+{'loss': '0.6606', 'grad_norm': '0.4185', 'learning_rate': '0.0001648', 'epoch': '2.002'}
+{'loss': '0.6864', 'grad_norm': '0.4118', 'learning_rate': '0.0001648', 'epoch': '2.003'}
+{'loss': '0.5723', 'grad_norm': '0.4191', 'learning_rate': '0.0001647', 'epoch': '2.003'}
+{'loss': '0.6414', 'grad_norm': '0.4628', 'learning_rate': '0.0001647', 'epoch': '2.004'}
+{'loss': '0.6798', 'grad_norm': '0.4544', 'learning_rate': '0.0001647', 'epoch': '2.005'}
+{'loss': '0.7034', 'grad_norm': '0.4566', 'learning_rate': '0.0001646', 'epoch': '2.006'}
+{'loss': '0.5971', 'grad_norm': '0.5048', 'learning_rate': '0.0001646', 'epoch': '2.007'}
+{'loss': '0.6356', 'grad_norm': '0.4609', 'learning_rate': '0.0001645', 'epoch': '2.008'}
+{'loss': '0.7133', 'grad_norm': '0.4787', 'learning_rate': '0.0001645', 'epoch': '2.009'}
+{'loss': '0.6744', 'grad_norm': '0.4269', 'learning_rate': '0.0001645', 'epoch': '2.009'}
+{'loss': '0.6571', 'grad_norm': '0.4307', 'learning_rate': '0.0001644', 'epoch': '2.01'}
+{'loss': '0.642', 'grad_norm': '0.4431', 'learning_rate': '0.0001644', 'epoch': '2.011'}
+{'loss': '0.6433', 'grad_norm': '0.399', 'learning_rate': '0.0001644', 'epoch': '2.012'}
+{'loss': '0.6164', 'grad_norm': '0.4829', 'learning_rate': '0.0001643', 'epoch': '2.013'}
+{'loss': '0.6431', 'grad_norm': '0.4575', 'learning_rate': '0.0001643', 'epoch': '2.014'}
+{'loss': '0.671', 'grad_norm': '0.4268', 'learning_rate': '0.0001642', 'epoch': '2.015'}
+{'loss': '0.685', 'grad_norm': '0.4235', 'learning_rate': '0.0001642', 'epoch': '2.016'}
+{'loss': '0.7138', 'grad_norm': '0.5073', 'learning_rate': '0.0001642', 'epoch': '2.016'}
+{'loss': '0.5495', 'grad_norm': '0.3621', 'learning_rate': '0.0001641', 'epoch': '2.017'}
+{'loss': '0.6597', 'grad_norm': '0.5076', 'learning_rate': '0.0001641', 'epoch': '2.018'}
+{'loss': '0.7322', 'grad_norm': '0.4342', 'learning_rate': '0.0001641', 'epoch': '2.019'}
+{'loss': '0.6621', 'grad_norm': '0.4758', 'learning_rate': '0.000164', 'epoch': '2.02'}
+{'loss': '0.6278', 'grad_norm': '0.5098', 'learning_rate': '0.000164', 'epoch': '2.021'}
+{'loss': '0.6266', 'grad_norm': '0.4256', 'learning_rate': '0.0001639', 'epoch': '2.022'}
+{'loss': '0.5831', 'grad_norm': '0.4265', 'learning_rate': '0.0001639', 'epoch': '2.022'}
+{'loss': '0.5532', 'grad_norm': '0.4193', 'learning_rate': '0.0001639', 'epoch': '2.023'}
+{'loss': '0.6643', 'grad_norm': '0.478', 'learning_rate': '0.0001638', 'epoch': '2.024'}
+{'loss': '0.6012', 'grad_norm': '0.4548', 'learning_rate': '0.0001638', 'epoch': '2.025'}
+{'loss': '0.6532', 'grad_norm': '0.4685', 'learning_rate': '0.0001638', 'epoch': '2.026'}
+{'loss': '0.6863', 'grad_norm': '0.5132', 'learning_rate': '0.0001637', 'epoch': '2.027'}
+{'loss': '0.6409', 'grad_norm': '0.4895', 'learning_rate': '0.0001637', 'epoch': '2.028'}
+{'eval_loss': '0.7736', 'eval_runtime': '661.2', 'eval_samples_per_second': '3.116', 'eval_steps_per_second': '3.116', 'epoch': '2.028'}
+{'loss': '0.6297', 'grad_norm': '0.4949', 'learning_rate': '0.0001636', 'epoch': '2.028'}
+{'loss': '0.6197', 'grad_norm': '0.4687', 'learning_rate': '0.0001636', 'epoch': '2.029'}
+{'loss': '0.647', 'grad_norm': '0.4212', 'learning_rate': '0.0001636', 'epoch': '2.03'}
+{'loss': '0.628', 'grad_norm': '0.5471', 'learning_rate': '0.0001635', 'epoch': '2.031'}
+{'loss': '0.7317', 'grad_norm': '0.4615', 'learning_rate': '0.0001635', 'epoch': '2.032'}
+{'loss': '0.7016', 'grad_norm': '0.4824', 'learning_rate': '0.0001635', 'epoch': '2.033'}
+{'loss': '0.5651', 'grad_norm': '0.4641', 'learning_rate': '0.0001634', 'epoch': '2.034'}
+{'loss': '0.6572', 'grad_norm': '0.5252', 'learning_rate': '0.0001634', 'epoch': '2.035'}
+{'loss': '0.7527', 'grad_norm': '0.5172', 'learning_rate': '0.0001633', 'epoch': '2.035'}
+{'loss': '0.6652', 'grad_norm': '0.4723', 'learning_rate': '0.0001633', 'epoch': '2.036'}
+{'loss': '0.7099', 'grad_norm': '0.4646', 'learning_rate': '0.0001633', 'epoch': '2.037'}
+{'loss': '0.6821', 'grad_norm': '0.5478', 'learning_rate': '0.0001632', 'epoch': '2.038'}
+{'loss': '0.6409', 'grad_norm': '0.4345', 'learning_rate': '0.0001632', 'epoch': '2.039'}
+{'loss': '0.6334', 'grad_norm': '0.4565', 'learning_rate': '0.0001631', 'epoch': '2.04'}
+{'loss': '0.6917', 'grad_norm': '0.5758', 'learning_rate': '0.0001631', 'epoch': '2.041'}
+{'loss': '0.6684', 'grad_norm': '0.4671', 'learning_rate': '0.0001631', 'epoch': '2.041'}
+{'loss': '0.6463', 'grad_norm': '0.4907', 'learning_rate': '0.000163', 'epoch': '2.042'}
+{'loss': '0.5973', 'grad_norm': '0.5116', 'learning_rate': '0.000163', 'epoch': '2.043'}
+{'loss': '0.669', 'grad_norm': '0.5355', 'learning_rate': '0.000163', 'epoch': '2.044'}
+{'loss': '0.6739', 'grad_norm': '0.4396', 'learning_rate': '0.0001629', 'epoch': '2.045'}
+{'loss': '0.6682', 'grad_norm': '0.4535', 'learning_rate': '0.0001629', 'epoch': '2.046'}
+{'loss': '0.6738', 'grad_norm': '0.4207', 'learning_rate': '0.0001628', 'epoch': '2.047'}
+{'loss': '0.692', 'grad_norm': '0.4378', 'learning_rate': '0.0001628', 'epoch': '2.047'}
+{'loss': '0.6725', 'grad_norm': '0.4675', 'learning_rate': '0.0001628', 'epoch': '2.048'}
+{'loss': '0.687', 'grad_norm': '0.5681', 'learning_rate': '0.0001627', 'epoch': '2.049'}
+{'loss': '0.6426', 'grad_norm': '0.463', 'learning_rate': '0.0001627', 'epoch': '2.05'}
+{'loss': '0.5698', 'grad_norm': '0.4135', 'learning_rate': '0.0001627', 'epoch': '2.051'}
+{'loss': '0.6877', 'grad_norm': '0.4725', 'learning_rate': '0.0001626', 'epoch': '2.052'}
+{'loss': '0.6143', 'grad_norm': '0.4616', 'learning_rate': '0.0001626', 'epoch': '2.053'}
+{'loss': '0.5956', 'grad_norm': '0.4284', 'learning_rate': '0.0001625', 'epoch': '2.054'}
+{'loss': '0.6759', 'grad_norm': '0.5213', 'learning_rate': '0.0001625', 'epoch': '2.054'}
+{'loss': '0.6699', 'grad_norm': '0.4363', 'learning_rate': '0.0001625', 'epoch': '2.055'}
+{'loss': '0.6342', 'grad_norm': '0.4192', 'learning_rate': '0.0001624', 'epoch': '2.056'}
+{'loss': '0.6707', 'grad_norm': '0.436', 'learning_rate': '0.0001624', 'epoch': '2.057'}
+{'loss': '0.6225', 'grad_norm': '0.4794', 'learning_rate': '0.0001623', 'epoch': '2.058'}
+{'loss': '0.6422', 'grad_norm': '0.4793', 'learning_rate': '0.0001623', 'epoch': '2.059'}
+{'loss': '0.6378', 'grad_norm': '0.4749', 'learning_rate': '0.0001623', 'epoch': '2.06'}
+{'loss': '0.651', 'grad_norm': '0.4462', 'learning_rate': '0.0001622', 'epoch': '2.06'}
+{'loss': '0.6493', 'grad_norm': '0.4956', 'learning_rate': '0.0001622', 'epoch': '2.061'}
+{'loss': '0.673', 'grad_norm': '0.5239', 'learning_rate': '0.0001622', 'epoch': '2.062'}
+{'loss': '0.6882', 'grad_norm': '0.4394', 'learning_rate': '0.0001621', 'epoch': '2.063'}
+{'loss': '0.6821', 'grad_norm': '0.5363', 'learning_rate': '0.0001621', 'epoch': '2.064'}
+{'loss': '0.6307', 'grad_norm': '0.4328', 'learning_rate': '0.000162', 'epoch': '2.065'}
+{'loss': '0.6391', 'grad_norm': '0.5029', 'learning_rate': '0.000162', 'epoch': '2.066'}
+{'loss': '0.6402', 'grad_norm': '0.5302', 'learning_rate': '0.000162', 'epoch': '2.066'}
+{'loss': '0.624', 'grad_norm': '0.4391', 'learning_rate': '0.0001619', 'epoch': '2.067'}
+{'loss': '0.6906', 'grad_norm': '0.4701', 'learning_rate': '0.0001619', 'epoch': '2.068'}
+{'loss': '0.6092', 'grad_norm': '0.496', 'learning_rate': '0.0001618', 'epoch': '2.069'}
+{'loss': '0.6169', 'grad_norm': '0.4593', 'learning_rate': '0.0001618', 'epoch': '2.07'}
+{'loss': '0.6541', 'grad_norm': '0.472', 'learning_rate': '0.0001618', 'epoch': '2.071'}
+{'eval_loss': '0.775', 'eval_runtime': '651.6', 'eval_samples_per_second': '3.162', 'eval_steps_per_second': '3.162', 'epoch': '2.071'}
+{'loss': '0.5709', 'grad_norm': '0.4563', 'learning_rate': '0.0001617', 'epoch': '2.072'}
+{'loss': '0.6872', 'grad_norm': '0.4355', 'learning_rate': '0.0001617', 'epoch': '2.072'}
+{'loss': '0.6759', 'grad_norm': '0.4693', 'learning_rate': '0.0001616', 'epoch': '2.073'}
+{'loss': '0.7065', 'grad_norm': '0.4919', 'learning_rate': '0.0001616', 'epoch': '2.074'}
+{'loss': '0.648', 'grad_norm': '0.4291', 'learning_rate': '0.0001616', 'epoch': '2.075'}
+{'loss': '0.6357', 'grad_norm': '0.4434', 'learning_rate': '0.0001615', 'epoch': '2.076'}
+{'loss': '0.7548', 'grad_norm': '0.6109', 'learning_rate': '0.0001615', 'epoch': '2.077'}
+{'loss': '0.6654', 'grad_norm': '0.5321', 'learning_rate': '0.0001615', 'epoch': '2.078'}
+{'loss': '0.6075', 'grad_norm': '0.5061', 'learning_rate': '0.0001614', 'epoch': '2.079'}
+{'loss': '0.6818', 'grad_norm': '0.5259', 'learning_rate': '0.0001614', 'epoch': '2.079'}
+{'loss': '0.5794', 'grad_norm': '0.4222', 'learning_rate': '0.0001613', 'epoch': '2.08'}
+{'loss': '0.6905', 'grad_norm': '0.4804', 'learning_rate': '0.0001613', 'epoch': '2.081'}
+{'loss': '0.7252', 'grad_norm': '0.4772', 'learning_rate': '0.0001613', 'epoch': '2.082'}
+{'loss': '0.6873', 'grad_norm': '0.4467', 'learning_rate': '0.0001612', 'epoch': '2.083'}
+{'loss': '0.6001', 'grad_norm': '0.4678', 'learning_rate': '0.0001612', 'epoch': '2.084'}
+{'loss': '0.6227', 'grad_norm': '0.4223', 'learning_rate': '0.0001611', 'epoch': '2.085'}
+{'loss': '0.7194', 'grad_norm': '0.5119', 'learning_rate': '0.0001611', 'epoch': '2.085'}
+{'loss': '0.5572', 'grad_norm': '0.4415', 'learning_rate': '0.0001611', 'epoch': '2.086'}
+{'loss': '0.6002', 'grad_norm': '0.5702', 'learning_rate': '0.000161', 'epoch': '2.087'}
+{'loss': '0.6027', 'grad_norm': '0.433', 'learning_rate': '0.000161', 'epoch': '2.088'}
+{'loss': '0.6872', 'grad_norm': '0.5575', 'learning_rate': '0.000161', 'epoch': '2.089'}
+{'loss': '0.6541', 'grad_norm': '0.4766', 'learning_rate': '0.0001609', 'epoch': '2.09'}
+{'loss': '0.6052', 'grad_norm': '0.4997', 'learning_rate': '0.0001609', 'epoch': '2.091'}
+{'loss': '0.6017', 'grad_norm': '0.4156', 'learning_rate': '0.0001608', 'epoch': '2.091'}
+{'loss': '0.5894', 'grad_norm': '0.4793', 'learning_rate': '0.0001608', 'epoch': '2.092'}
+{'loss': '0.6398', 'grad_norm': '0.4598', 'learning_rate': '0.0001608', 'epoch': '2.093'}
+{'loss': '0.6468', 'grad_norm': '0.4966', 'learning_rate': '0.0001607', 'epoch': '2.094'}
+{'loss': '0.6751', 'grad_norm': '0.4549', 'learning_rate': '0.0001607', 'epoch': '2.095'}
+{'loss': '0.6462', 'grad_norm': '0.4151', 'learning_rate': '0.0001606', 'epoch': '2.096'}
+{'loss': '0.6318', 'grad_norm': '0.555', 'learning_rate': '0.0001606', 'epoch': '2.097'}
+{'loss': '0.6247', 'grad_norm': '0.4214', 'learning_rate': '0.0001606', 'epoch': '2.098'}
+{'loss': '0.6749', 'grad_norm': '0.483', 'learning_rate': '0.0001605', 'epoch': '2.098'}
+{'loss': '0.6189', 'grad_norm': '0.4876', 'learning_rate': '0.0001605', 'epoch': '2.099'}
+{'loss': '0.7035', 'grad_norm': '0.4909', 'learning_rate': '0.0001604', 'epoch': '2.1'}
+{'loss': '0.6546', 'grad_norm': '0.4613', 'learning_rate': '0.0001604', 'epoch': '2.101'}
+{'loss': '0.7385', 'grad_norm': '0.5318', 'learning_rate': '0.0001604', 'epoch': '2.102'}
+{'loss': '0.6189', 'grad_norm': '0.4081', 'learning_rate': '0.0001603', 'epoch': '2.103'}
+{'loss': '0.5405', 'grad_norm': '0.345', 'learning_rate': '0.0001603', 'epoch': '2.104'}
+{'loss': '0.6256', 'grad_norm': '0.4911', 'learning_rate': '0.0001602', 'epoch': '2.104'}
+{'loss': '0.634', 'grad_norm': '0.4428', 'learning_rate': '0.0001602', 'epoch': '2.105'}
+{'loss': '0.6473', 'grad_norm': '0.4649', 'learning_rate': '0.0001602', 'epoch': '2.106'}
+{'loss': '0.6583', 'grad_norm': '0.5085', 'learning_rate': '0.0001601', 'epoch': '2.107'}
+{'loss': '0.7064', 'grad_norm': '0.5698', 'learning_rate': '0.0001601', 'epoch': '2.108'}
+{'loss': '0.6098', 'grad_norm': '0.4936', 'learning_rate': '0.0001601', 'epoch': '2.109'}
+{'loss': '0.5644', 'grad_norm': '0.4722', 'learning_rate': '0.00016', 'epoch': '2.11'}
+{'loss': '0.6599', 'grad_norm': '0.5233', 'learning_rate': '0.00016', 'epoch': '2.11'}
+{'loss': '0.7039', 'grad_norm': '0.5682', 'learning_rate': '0.0001599', 'epoch': '2.111'}
+{'loss': '0.6108', 'grad_norm': '0.4312', 'learning_rate': '0.0001599', 'epoch': '2.112'}
+{'loss': '0.7148', 'grad_norm': '0.5554', 'learning_rate': '0.0001599', 'epoch': '2.113'}
+{'loss': '0.6426', 'grad_norm': '0.4474', 'learning_rate': '0.0001598', 'epoch': '2.114'}
+{'eval_loss': '0.771', 'eval_runtime': '649.7', 'eval_samples_per_second': '3.171', 'eval_steps_per_second': '3.171', 'epoch': '2.114'}
+{'train_runtime': '6.937e+04', 'train_samples_per_second': '1.604', 'train_steps_per_second': '0.2', 'train_loss': '0.835', 'epoch': '2.114'}
+Saved best adapter -> runs/instruct_run_14b_v1/best_adapter
+Final eval_loss=0.771009087562561, ppl=2.1619467470189244
+--- Merge: runs/instruct_run_14b_v1/best_adapter + runs/cpt_run_14b/merged_14b_cpt_lora -> runs/instruct_run_14b_v1/merged_14b_instruct_lora ---
+Loading weights: 100%|██████████████████████████████████████| 579/579 [00:00<00:00, 724.25it/s, Materializing param=model.norm.weight]
+Writing model shards: 100%|███████████████████████████████████████████████████████████████████████████| 16/16 [00:38<00:00,  2.39s/it]
+--- Merge complete ---
diff --git a/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/files/requirements.txt b/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/files/requirements.txt
new file mode 100644
index 0000000000000000000000000000000000000000..e7931173f4304b55fcec981001d950eebb55e97c
--- /dev/null
+++ b/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/files/requirements.txt
@@ -0,0 +1,90 @@
+exceptiongroup==1.3.1
+python-dateutil==2.9.0.post0
+nvidia-ml-py==13.580.82
+huggingface_hub==1.2.3
+idna==3.11
+click==8.3.1
+numpy==2.2.6
+httpx==0.28.1
+nvidia-nvshmem-cu12==3.3.20
+tokenizers==0.22.1
+nvidia-cufile-cu12==1.13.1.3
+nvidia-cublas-cu12==12.8.4.1
+MarkupSafe==3.0.3
+yarl==1.22.0
+async-timeout==5.0.1
+sympy==1.14.0
+datasets==4.4.2
+platformdirs==4.5.1
+nvidia-cusolver-cu12==11.7.3.90
+smmap==5.0.2
+accelerate==1.12.0
+requests==2.32.5
+nvidia-nccl-cu12==2.27.5
+nvidia-cuda-nvrtc-cu12==12.8.93
+aiohttp==3.13.2
+bitsandbytes==0.49.0
+mpmath==1.3.0
+typing-inspection==0.4.2
+nvidia-cudnn-cu12==9.10.2.21
+GitPython==3.1.45
+xxhash==3.6.0
+pydantic_core==2.41.5
+setuptools==59.6.0
+six==1.17.0
+typing_extensions==4.15.0
+filelock==3.20.1
+charset-normalizer==3.4.4
+nvitop==1.6.1
+wandb==0.23.1
+regex==2025.11.3
+nvidia-cuda-runtime-cu12==12.8.90
+absl-py==2.3.1
+pytz==2025.2
+rouge-score==0.1.2
+torch==2.9.1
+Jinja2==3.1.6
+nvidia-cusparse-cu12==12.5.8.93
+psutil==7.1.3
+nltk==3.9.2
+packaging==25.0
+safetensors==0.7.0
+sentry-sdk==2.48.0
+gitdb==4.0.12
+httpcore==1.0.9
+anyio==4.12.0
+transformers==5.0.0.dev0
+pydantic==2.12.5
+fsspec==2025.10.0
+PyYAML==6.0.3
+hf-xet==1.2.0
+typer-slim==0.20.1
+triton==3.5.1
+nvidia-nvtx-cu12==12.8.90
+tqdm==4.67.1
+attrs==25.4.0
+peft==0.18.0
+aiohappyeyeballs==2.6.1
+networkx==3.4.2
+nvidia-cufft-cu12==11.3.3.83
+certifi==2025.11.12
+pyarrow==22.0.0
+dill==0.4.0
+protobuf==6.33.2
+aiosignal==1.4.0
+frozenlist==1.8.0
+urllib3==2.6.2
+propcache==0.4.1
+tzdata==2025.3
+pandas==2.3.3
+annotated-types==0.7.0
+shellingham==1.5.4
+multidict==6.7.0
+nvidia-cuda-cupti-cu12==12.8.90
+nvidia-cusparselt-cu12==0.7.1
+joblib==1.5.3
+nvidia-nvjitlink-cu12==12.8.93
+h11==0.16.0
+multiprocess==0.70.18
+nvidia-curand-cu12==10.3.9.90
+pip==22.0.2
diff --git a/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/files/wandb-metadata.json b/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/files/wandb-metadata.json
new file mode 100644
index 0000000000000000000000000000000000000000..be0ea414109a0367e43636bf8634bfcb63b826f1
--- /dev/null
+++ b/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/files/wandb-metadata.json
@@ -0,0 +1,47 @@
+{
+  "os":  "Linux-6.12.46+-x86_64-with-glibc2.35",
+  "python":  "CPython 3.10.12",
+  "startedAt":  "2025-12-23T14:27:02.029304Z",
+  "args":  [
+    "--config",
+    "./SFT/config_instruct.yaml"
+  ],
+  "program":  "/workspace/SFT/run_instruct.py",
+  "codePath":  "SFT/run_instruct.py",
+  "codePathLocal":  "SFT/run_instruct.py",
+  "email":  "shaiksirajuddin9949@gmail.com",
+  "root":  "runs/instruct_run_14b_v1",
+  "host":  "a100-2gpu-shell-session-9c959f5f-mx8rm",
+  "executable":  "/workspace/CPT-env/bin/python",
+  "cpu_count":  12,
+  "cpu_count_logical":  24,
+  "gpu":  "NVIDIA A100-SXM4-80GB",
+  "gpu_count":  2,
+  "disk":  {
+    "/":  {
+      "total":  "791251738624",
+      "used":  "330236313600"
+    }
+  },
+  "memory":  {
+    "total":  "359047892992"
+  },
+  "gpu_nvidia":  [
+    {
+      "name":  "NVIDIA A100-SXM4-80GB",
+      "memoryTotal":  "85899345920",
+      "cudaCores":  6912,
+      "architecture":  "Ampere",
+      "uuid":  "GPU-989794b0-ec3b-13bf-db9f-3fbe341497ba"
+    },
+    {
+      "name":  "NVIDIA A100-SXM4-80GB",
+      "memoryTotal":  "85899345920",
+      "cudaCores":  6912,
+      "architecture":  "Ampere",
+      "uuid":  "GPU-3790aa64-60ef-9eac-b0b1-b278ee8c0d40"
+    }
+  ],
+  "cudaVersion":  "13.0",
+  "writerId":  "x2eg684gxvwjptbq4zszw1o13xocb8ht"
+}
\ No newline at end of file
diff --git a/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/files/wandb-summary.json b/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/files/wandb-summary.json
new file mode 100644
index 0000000000000000000000000000000000000000..3486d34eb7b7f4771059e79c6f10965bfb4fa756
--- /dev/null
+++ b/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/files/wandb-summary.json
@@ -0,0 +1 @@
+{"train/global_step":4900,"_step":2500,"train/learning_rate":0.0001598164742191366,"eval/samples_per_second":3.12,"eval/steps_per_second":3.12,"eval/loss":0.771009087562561,"train/epoch":2.113915857605178,"train_runtime":69370.1166,"_wandb":{"runtime":70170},"train/grad_norm":0.44741159677505493,"train_loss":0.8349519448864217,"train_steps_per_second":0.2,"_timestamp":1.7665701382619302e+09,"train_samples_per_second":1.604,"_runtime":70170,"total_flos":2.9383334939106386e+18,"eval/runtime":660.1524,"train/loss":0.6425569653511047}
\ No newline at end of file
diff --git a/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/logs/debug-core.log b/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/logs/debug-core.log
new file mode 100644
index 0000000000000000000000000000000000000000..622c0a5ab947546d81accbaa23e3e96cbcbd3677
--- /dev/null
+++ b/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/logs/debug-core.log
@@ -0,0 +1,16 @@
+{"time":"2025-12-23T14:27:02.290551087Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmp36r63qv2/port-926994.txt","pid":926994,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
+{"time":"2025-12-23T14:27:02.291201571Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":926994}
+{"time":"2025-12-23T14:27:02.291176839Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-926994-927094-2238975194/socket","Net":"unix"}}
+{"time":"2025-12-23T14:27:02.476901177Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
+{"time":"2025-12-23T14:27:02.483454288Z","level":"INFO","msg":"handleInformInit: received","streamId":"ldjr67u6","id":"1(@)"}
+{"time":"2025-12-23T14:27:02.637286702Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"ldjr67u6","id":"1(@)"}
+{"time":"2025-12-24T09:56:33.399756851Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"ldjr67u6","id":"1(@)"}
+{"time":"2025-12-24T09:56:33.400561239Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"ldjr67u6","id":"1(@)"}
+{"time":"2025-12-24T09:56:33.467843662Z","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
+{"time":"2025-12-24T09:56:33.467897304Z","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
+{"time":"2025-12-24T09:56:33.467911064Z","level":"INFO","msg":"connection: closing","id":"1(@)"}
+{"time":"2025-12-24T09:56:33.467950514Z","level":"INFO","msg":"server is shutting down"}
+{"time":"2025-12-24T09:56:33.467959217Z","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
+{"time":"2025-12-24T09:56:33.468002049Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
+{"time":"2025-12-24T09:56:33.468079402Z","level":"INFO","msg":"server: listener closed","addr":{"Name":"/tmp/wandb-926994-927094-2238975194/socket","Net":"unix"}}
+{"time":"2025-12-24T09:56:33.468112386Z","level":"INFO","msg":"server is closed"}
diff --git a/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/logs/debug-internal.log b/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/logs/debug-internal.log
new file mode 100644
index 0000000000000000000000000000000000000000..fe7b2c0e805207da8a7e3ea54a831c4f0e6aad9a
--- /dev/null
+++ b/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/logs/debug-internal.log
@@ -0,0 +1,12 @@
+{"time":"2025-12-23T14:27:02.483579527Z","level":"INFO","msg":"stream: starting","core version":"0.23.1"}
+{"time":"2025-12-23T14:27:02.637028075Z","level":"INFO","msg":"stream: created new stream","id":"ldjr67u6"}
+{"time":"2025-12-23T14:27:02.637166774Z","level":"INFO","msg":"handler: started","stream_id":"ldjr67u6"}
+{"time":"2025-12-23T14:27:02.637274386Z","level":"INFO","msg":"stream: started","id":"ldjr67u6"}
+{"time":"2025-12-23T14:27:02.637294935Z","level":"INFO","msg":"writer: started","stream_id":"ldjr67u6"}
+{"time":"2025-12-23T14:27:02.637323084Z","level":"INFO","msg":"sender: started","stream_id":"ldjr67u6"}
+{"time":"2025-12-24T09:56:33.315646376Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2025-12-24T09:56:33.395280157Z","level":"INFO","msg":"handler: operation stats","stats":{}}
+{"time":"2025-12-24T09:56:33.399794124Z","level":"INFO","msg":"stream: closing","id":"ldjr67u6"}
+{"time":"2025-12-24T09:56:33.399816195Z","level":"INFO","msg":"handler: closed","stream_id":"ldjr67u6"}
+{"time":"2025-12-24T09:56:33.399912405Z","level":"INFO","msg":"sender: closed","stream_id":"ldjr67u6"}
+{"time":"2025-12-24T09:56:33.399932943Z","level":"INFO","msg":"stream: closed","id":"ldjr67u6"}
diff --git a/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/logs/debug.log b/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/logs/debug.log
new file mode 100644
index 0000000000000000000000000000000000000000..f59e39ffea6fa02662b169817984263afc30c6cc
--- /dev/null
+++ b/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/logs/debug.log
@@ -0,0 +1,29 @@
+2025-12-23 14:27:02,030 INFO    MainThread:926994 [wandb_setup.py:_flush():80] Current SDK version is 0.23.1
+2025-12-23 14:27:02,031 INFO    MainThread:926994 [wandb_setup.py:_flush():80] Configure stats pid to 926994
+2025-12-23 14:27:02,031 INFO    MainThread:926994 [wandb_setup.py:_flush():80] Loading settings from /root/.config/wandb/settings
+2025-12-23 14:27:02,031 INFO    MainThread:926994 [wandb_setup.py:_flush():80] Loading settings from /workspace/wandb/settings
+2025-12-23 14:27:02,031 INFO    MainThread:926994 [wandb_setup.py:_flush():80] Loading settings from environment variables
+2025-12-23 14:27:02,031 INFO    MainThread:926994 [wandb_init.py:setup_run_log_directory():714] Logging user logs to runs/instruct_run_14b_v1/wandb/run-20251223_142702-ldjr67u6/logs/debug.log
+2025-12-23 14:27:02,031 INFO    MainThread:926994 [wandb_init.py:setup_run_log_directory():715] Logging internal logs to runs/instruct_run_14b_v1/wandb/run-20251223_142702-ldjr67u6/logs/debug-internal.log
+2025-12-23 14:27:02,031 INFO    MainThread:926994 [wandb_init.py:init():841] calling init triggers
+2025-12-23 14:27:02,031 INFO    MainThread:926994 [wandb_init.py:init():846] wandb.init called with sweep_config: {}
+config: {'model': {'repo_id': './runs/cpt_run_14b/merged_14b_cpt_lora', 'revision': None, 'base_local_dir': 'base_model', 'trust_remote_code': True, 'tokenizer_use_fast': True, 'device_map': 'auto', 'torch_dtype': 'bfloat16', 'use_4bit': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': False, 'bnb_4bit_compute_dtype': 'bfloat16', 'attn_implementation': None}, 'data': {'train_jsonl': 'sft_dataset.jsonl', 'eval_jsonl': None, 'eval_split_ratio': 0.1, 'instruction_field': 'instruction', 'input_field': 'input', 'output_field': 'output', 'format_type': 'custom', 'system_prompt': 'You are a Hyperswitch Rust code analyzer. Identify functions/structs that need modification for a given task.\n\n## Output Format\n\n##OUTPUT\nExplain the data flow and why each component must change:\n- Flow: [Input → Processing → Output with arrows]\n- For each component: "The [ComponentName] ([path]) must [action] because [reason]—without this, [consequence]"\n- Explain coupling between components\n\n##SELECT\nmodify::crates/path/to/file.rs::impl::ComponentName\nadd::crates/another/file.rs::function::AnotherComponent\n<EOS>\n\n## Rules\n\n1. Use full paths: `remove::crates/folder/file.rs::Type::Name`\n2. Use `::` for nested items: `status::StructName::Type::Name`\n3. Always explain "must change because" and "without this"\n3. Types of components: function, struct, enum, impl, trait\n4. If there is extra information (e.g., enum variants), include that too.\n5. Start with ##OUTPUT, end with ##SELECT, terminate with <EOS>\n\n## Example\n\n##TASK\nAdd webhook subscription support\n\n##OUTPUT\nThe webhook system routes events via EventClass enum. Flow: webhook → EventClass → handler → processing. The EventClass enum (crates/common_enums/src/enums.rs::EventClass) must add Subscriptions variant because it defines event routing—without this, subscription events cannot be processed. The SubscriptionStatus impl (crates/common_enums/src/transformers.rs::SubscriptionStatus) must map to EventType because it converts status to events—without this, status changes don\'t trigger webhooks. These are coupled: EventClass routes to handlers that use SubscriptionStatus mappings.\n\n##SELECT\ncrates/common_enums/src/enums.rs::EventClass\ncrates/common_enums/src/transformers.rs::SubscriptionStatus\n<EOS>\n', 'custom_template': '##INSTRUCTION\n{instruction}<|im_end|>\n##TASK\n{input}<|im_end|>\n##OUTPUT\n{output}<|im_end|>', 'max_length': 2048, 'shuffle': True, 'num_proc': 4}, 'peft': {'enabled': True, 'r': 16, 'lora_alpha': 32, 'lora_dropout': 0.05, 'bias': 'none', 'target_modules': 'auto'}, 'train': {'num_train_epochs': 6, 'per_device_train_batch_size': 1, 'per_device_eval_batch_size': 1, 'gradient_accumulation_steps': 8, 'learning_rate': '2e-4', 'weight_decay': 0.0, 'warmup_ratio': 0.08, 'lr_scheduler_type': 'cosine', 'optim': 'adamw_torch', 'max_grad_norm': 1.0, 'gradient_checkpointing': True, 'logging_steps': 2, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 20, 'evaluation_strategy': 'steps', 'eval_steps': 100, 'load_best_model_at_end': True, 'early_stopping': {'enabled': True, 'patience': 3, 'min_delta': 0.001, 'metric': 'eval_loss', 'mode': 'min'}, 'resume_from_checkpoint': 'auto'}, 'run_dir': 'runs/instruct_run_14b_v1', '_wandb': {}}
+2025-12-23 14:27:02,031 INFO    MainThread:926994 [wandb_init.py:init():889] starting backend
+2025-12-23 14:27:02,477 INFO    MainThread:926994 [wandb_init.py:init():892] sending inform_init request
+2025-12-23 14:27:02,481 INFO    MainThread:926994 [wandb_init.py:init():900] backend started and connected
+2025-12-23 14:27:02,483 INFO    MainThread:926994 [wandb_init.py:init():970] updated telemetry
+2025-12-23 14:27:02,484 INFO    MainThread:926994 [wandb_init.py:init():994] communicating run to backend with 90.0 second timeout
+2025-12-23 14:27:02,870 INFO    MainThread:926994 [wandb_init.py:init():1041] starting run threads in backend
+2025-12-23 14:27:02,969 INFO    MainThread:926994 [wandb_run.py:_console_start():2521] atexit reg
+2025-12-23 14:27:02,970 INFO    MainThread:926994 [wandb_run.py:_redirect():2369] redirect: wrap_raw
+2025-12-23 14:27:02,970 INFO    MainThread:926994 [wandb_run.py:_redirect():2438] Wrapping output streams.
+2025-12-23 14:27:02,970 INFO    MainThread:926994 [wandb_run.py:_redirect():2461] Redirects installed.
+2025-12-23 14:27:02,973 INFO    MainThread:926994 [wandb_init.py:init():1081] run started, returning control to user process
+2025-12-23 14:28:27,753 INFO    MainThread:926994 [wandb_run.py:_config_callback():1396] config_cb None None {'peft_config': {'default': {'task_type': 'CAUSAL_LM', 'peft_type': 'LORA', 'auto_mapping': None, 'peft_version': '0.18.0', 'base_model_name_or_path': 'runs/cpt_run_14b/merged_14b_cpt_lora', 'revision': None, 'inference_mode': False, 'r': 16, 'target_modules': ['q_proj', 'o_proj', 'v_proj', 'k_proj'], 'exclude_modules': None, 'lora_alpha': 32, 'lora_dropout': 0.05, 'fan_in_fan_out': False, 'bias': 'none', 'use_rslora': False, 'modules_to_save': None, 'init_lora_weights': True, 'layers_to_transform': None, 'layers_pattern': None, 'rank_pattern': {}, 'alpha_pattern': {}, 'megatron_config': None, 'megatron_core': 'megatron.core', 'trainable_token_indices': None, 'loftq_config': {}, 'eva_config': None, 'corda_config': None, 'use_dora': False, 'alora_invocation_tokens': None, 'use_qalora': False, 'qalora_group_size': 16, 'layer_replication': None, 'runtime_config': {'ephemeral_gpu_offload': False}, 'lora_bias': False, 'target_parameters': None, 'arrow_config': None, 'ensure_weight_tying': False}}, 'vocab_size': 152064, 'max_position_embeddings': 32768, 'hidden_size': 5120, 'intermediate_size': 13824, 'num_hidden_layers': 48, 'num_attention_heads': 40, 'use_sliding_window': False, 'sliding_window': None, 'max_window_layers': 48, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'attention_dropout': 0.0, 'layer_types': ['full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention'], 'rope_parameters': {'rope_theta': 1000000.0, 'rope_type': 'default'}, 'return_dict': True, 'output_hidden_states': False, 'dtype': 'bfloat16', 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'architectures': ['Qwen2ForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'task_specific_params': None, 'problem_type': None, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 151643, 'pad_token_id': None, 'eos_token_id': 151643, 'sep_token_id': None, 'decoder_start_token_id': None, '_name_or_path': 'runs/cpt_run_14b/merged_14b_cpt_lora', 'transformers_version': '5.0.0.dev0', 'model_type': 'qwen2', 'output_attentions': False, 'output_dir': 'runs/instruct_run_14b_v1/checkpoints', 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 1, 'per_device_eval_batch_size': 1, 'gradient_accumulation_steps': 8, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 0.0002, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 6.0, 'max_steps': -1, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': None, 'warmup_ratio': 0.08, 'warmup_steps': 0.08, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': None, 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 2, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 20, 'enable_jit_checkpoint': False, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'use_cpu': False, 'seed': 42, 'data_seed': None, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': -1, 'ddp_backend': None, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 100, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'run_name': None, 'disable_tqdm': False, 'remove_unused_columns': False, 'label_names': None, 'load_best_model_at_end': True, 'metric_for_best_model': 'eval_loss', 'greater_is_better': False, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'project': 'huggingface', 'trackio_space_id': 'trackio', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_always_push': False, 'hub_revision': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'auto_find_batch_size': False, 'full_determinism': False, 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'include_num_input_tokens_seen': 'no', 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'liger_kernel_config': None, 'eval_use_gather_object': False, 'average_tokens_across_devices': True}
+2025-12-23 14:28:27,762 INFO    MainThread:926994 [wandb_config.py:__setitem__():154] [no run ID] config set model/num_parameters = 14795199488 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7a729b20d8a0>>
+2025-12-23 14:28:27,762 INFO    MainThread:926994 [wandb_run.py:_config_callback():1396] config_cb model/num_parameters 14795199488 None
+2025-12-24 09:56:32,985 INFO    MainThread:926994 [wandb_run.py:_finish():2287] finishing run sirajuddin-shaik-007/sft-training/ldjr67u6
+2025-12-24 09:56:32,986 INFO    MainThread:926994 [wandb_run.py:_atexit_cleanup():2486] got exitcode: 0
+2025-12-24 09:56:32,986 INFO    MainThread:926994 [wandb_run.py:_restore():2468] restore
+2025-12-24 09:56:32,986 INFO    MainThread:926994 [wandb_run.py:_restore():2474] restore done
+2025-12-24 09:56:33,398 INFO    MainThread:926994 [wandb_run.py:_footer_sync_info():3862] logging synced files
diff --git a/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/run-ldjr67u6.wandb b/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/run-ldjr67u6.wandb
new file mode 100644
index 0000000000000000000000000000000000000000..dd0c7f9ca30f788922d98c4d58e641821d8a3450
--- /dev/null
+++ b/sft_qwen_14B/wandb/run-20251223_142702-ldjr67u6/run-ldjr67u6.wandb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:673466e652e90b7b3d0057b3edb459767d72c9e4feff40c547699a37f4128626
+size 46754173