diff --git a/.gitattributes b/.gitattributes
index a6344aac8c09253b3b630fb776ae94478aa0275b..71fddd980274f326098f33749d1d3d5d4b79a484 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-1782/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/README.md b/README.md
index e18c5a62c3264fa04193d228e111b57a3d6451da..918c97b6660775d917f03ce110e735377c3022d2 100644
--- a/README.md
+++ b/README.md
@@ -1,16 +1,61 @@
 ---
-license: cc-by-nc-4.0
+library_name: peft
+license: other
+base_model: google/gemma-3-1b-it
 tags:
-- qwen3
-- mhm
-- text-generation
-library_name: transformers
+- base_model:adapter:google/gemma-3-1b-it
+- llama-factory
+- lora
+- transformers
+pipeline_tag: text-generation
+model-index:
+- name: opencodeinst_5k_sft
+  results: []
 ---
 
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
 # opencodeinst_5k_sft
 
-Auto-uploaded by watcher.
+This model is a fine-tuned version of [google/gemma-3-1b-it](https://huggingface.co/google/gemma-3-1b-it) on the opencodeinst_5k dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-06
+- train_batch_size: 1
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
 
-- Source path: `LlamaFactory/models/opencodeinst_5k_sft`
-- Uploaded at: `2026-05-20T06:02:49.311145`
-- Visibility: `public`
+- PEFT 0.18.1
+- Transformers 5.2.0
+- Pytorch 2.11.0+cu130
+- Datasets 4.0.0
+- Tokenizers 0.22.2
\ No newline at end of file
diff --git a/adapter_config.json b/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..b7033a591cf40ea5b43aae7a6f56ed6a65d3f80c
--- /dev/null
+++ b/adapter_config.json
@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-1b-it",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj",
+    "q_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/adapter_model.safetensors b/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..03edeef75932b07dca7331094b07797a7dcc736b
--- /dev/null
+++ b/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2fccca914644fd456afb68abc1f7307cc09f76cd552cb49bc0a910ee900a73e
+size 26139264
diff --git a/all_results.json b/all_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..f299a99a5a1b6ed7cffbcf87a8ae647059ec8118
--- /dev/null
+++ b/all_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 3.258875338498253e+16,
+    "train_loss": 0.45725877370630985,
+    "train_runtime": 3399.7742,
+    "train_samples_per_second": 4.191,
+    "train_steps_per_second": 0.524
+}
\ No newline at end of file
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..1117055ab8e8c90e1b200be00cddb78943616d9e
--- /dev/null
+++ b/chat_template.jinja
@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}
diff --git a/checkpoint-1400/README.md b/checkpoint-1400/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..cfd546f8318a3a2985d8a7e4c881e529305dd807
--- /dev/null
+++ b/checkpoint-1400/README.md
@@ -0,0 +1,208 @@
+---
+base_model: google/gemma-3-1b-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:google/gemma-3-1b-it
+- llama-factory
+- 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 0.18.1
\ No newline at end of file
diff --git a/checkpoint-1400/adapter_config.json b/checkpoint-1400/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..b7033a591cf40ea5b43aae7a6f56ed6a65d3f80c
--- /dev/null
+++ b/checkpoint-1400/adapter_config.json
@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-1b-it",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj",
+    "q_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/checkpoint-1400/chat_template.jinja b/checkpoint-1400/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..1117055ab8e8c90e1b200be00cddb78943616d9e
--- /dev/null
+++ b/checkpoint-1400/chat_template.jinja
@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}
diff --git a/checkpoint-1400/rng_state.pth b/checkpoint-1400/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..fba144cb67fb15035427f5de27da93b1898a6100
--- /dev/null
+++ b/checkpoint-1400/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5563bee0e6340c81024f327b435c7f4b69444288abbfb077a5d9ac163cb64bd4
+size 14645
diff --git a/checkpoint-1400/scheduler.pt b/checkpoint-1400/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9a93cd0ca289b8fa22b9e5795a6396af5e5c177b
--- /dev/null
+++ b/checkpoint-1400/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50427b778ba4958d014cebb411d4b1ae082125569b84cc46d15eb28aa365f6a6
+size 1465
diff --git a/checkpoint-1400/tokenizer_config.json b/checkpoint-1400/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d83f12eef5a7d73283047b2f05c1ffdd6346556a
--- /dev/null
+++ b/checkpoint-1400/tokenizer_config.json
@@ -0,0 +1,26 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<end_of_turn>",
+  "image_token": "<image_soft_token>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "processor_class": "Gemma3Processor",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-1400/trainer_state.json b/checkpoint-1400/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..38f867d6cab3a746283b5f1da49ceef2aad869b4
--- /dev/null
+++ b/checkpoint-1400/trainer_state.json
@@ -0,0 +1,1014 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.3570526315789473,
+  "eval_steps": 100,
+  "global_step": 1400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016842105263157894,
+      "grad_norm": 0.21757784485816956,
+      "learning_rate": 5.027932960893855e-08,
+      "loss": 0.7252199172973632,
+      "step": 10
+    },
+    {
+      "epoch": 0.03368421052631579,
+      "grad_norm": 0.2456846386194229,
+      "learning_rate": 1.0614525139664805e-07,
+      "loss": 0.6507451057434082,
+      "step": 20
+    },
+    {
+      "epoch": 0.05052631578947368,
+      "grad_norm": 0.20819272100925446,
+      "learning_rate": 1.6201117318435754e-07,
+      "loss": 0.7381344795227051,
+      "step": 30
+    },
+    {
+      "epoch": 0.06736842105263158,
+      "grad_norm": 0.26373574137687683,
+      "learning_rate": 2.17877094972067e-07,
+      "loss": 0.7012194156646728,
+      "step": 40
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 0.2081507444381714,
+      "learning_rate": 2.7374301675977653e-07,
+      "loss": 0.6083873748779297,
+      "step": 50
+    },
+    {
+      "epoch": 0.10105263157894737,
+      "grad_norm": 0.2091236114501953,
+      "learning_rate": 3.29608938547486e-07,
+      "loss": 0.6980491638183594,
+      "step": 60
+    },
+    {
+      "epoch": 0.11789473684210526,
+      "grad_norm": 0.20970331132411957,
+      "learning_rate": 3.8547486033519547e-07,
+      "loss": 0.708641767501831,
+      "step": 70
+    },
+    {
+      "epoch": 0.13473684210526315,
+      "grad_norm": 0.18810197710990906,
+      "learning_rate": 4.41340782122905e-07,
+      "loss": 0.6742453098297119,
+      "step": 80
+    },
+    {
+      "epoch": 0.15157894736842106,
+      "grad_norm": 0.20251069962978363,
+      "learning_rate": 4.972067039106145e-07,
+      "loss": 0.6590609550476074,
+      "step": 90
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "grad_norm": 0.2644217908382416,
+      "learning_rate": 5.53072625698324e-07,
+      "loss": 0.704926872253418,
+      "step": 100
+    },
+    {
+      "epoch": 0.18526315789473685,
+      "grad_norm": 0.23766489326953888,
+      "learning_rate": 6.089385474860335e-07,
+      "loss": 0.7445036888122558,
+      "step": 110
+    },
+    {
+      "epoch": 0.20210526315789473,
+      "grad_norm": 0.27427056431770325,
+      "learning_rate": 6.64804469273743e-07,
+      "loss": 0.7476531028747558,
+      "step": 120
+    },
+    {
+      "epoch": 0.21894736842105264,
+      "grad_norm": 0.3208928406238556,
+      "learning_rate": 7.206703910614524e-07,
+      "loss": 0.7291872501373291,
+      "step": 130
+    },
+    {
+      "epoch": 0.23578947368421052,
+      "grad_norm": 0.3123615086078644,
+      "learning_rate": 7.76536312849162e-07,
+      "loss": 0.721175241470337,
+      "step": 140
+    },
+    {
+      "epoch": 0.25263157894736843,
+      "grad_norm": 0.26158222556114197,
+      "learning_rate": 8.324022346368714e-07,
+      "loss": 0.7556095600128174,
+      "step": 150
+    },
+    {
+      "epoch": 0.2694736842105263,
+      "grad_norm": 0.2592650353908539,
+      "learning_rate": 8.88268156424581e-07,
+      "loss": 0.7328392505645752,
+      "step": 160
+    },
+    {
+      "epoch": 0.2863157894736842,
+      "grad_norm": 0.24533776938915253,
+      "learning_rate": 9.441340782122904e-07,
+      "loss": 0.6990129470825195,
+      "step": 170
+    },
+    {
+      "epoch": 0.3031578947368421,
+      "grad_norm": 0.23409004509449005,
+      "learning_rate": 1e-06,
+      "loss": 0.6694639205932618,
+      "step": 180
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.3267499506473541,
+      "learning_rate": 9.999039806396227e-07,
+      "loss": 0.7123252868652343,
+      "step": 190
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "grad_norm": 0.2115064263343811,
+      "learning_rate": 9.996159594373611e-07,
+      "loss": 0.6858412742614746,
+      "step": 200
+    },
+    {
+      "epoch": 0.35368421052631577,
+      "grad_norm": 0.26226580142974854,
+      "learning_rate": 9.991360470156615e-07,
+      "loss": 0.6541069507598877,
+      "step": 210
+    },
+    {
+      "epoch": 0.3705263157894737,
+      "grad_norm": 0.24552594125270844,
+      "learning_rate": 9.984644276980594e-07,
+      "loss": 0.6506116390228271,
+      "step": 220
+    },
+    {
+      "epoch": 0.3873684210526316,
+      "grad_norm": 0.25084301829338074,
+      "learning_rate": 9.976013594383835e-07,
+      "loss": 0.6540626049041748,
+      "step": 230
+    },
+    {
+      "epoch": 0.40421052631578946,
+      "grad_norm": 0.34244054555892944,
+      "learning_rate": 9.965471737216833e-07,
+      "loss": 0.6737770557403564,
+      "step": 240
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.34752583503723145,
+      "learning_rate": 9.953022754369114e-07,
+      "loss": 0.6755708217620849,
+      "step": 250
+    },
+    {
+      "epoch": 0.4378947368421053,
+      "grad_norm": 0.31017956137657166,
+      "learning_rate": 9.938671427214158e-07,
+      "loss": 0.6578442573547363,
+      "step": 260
+    },
+    {
+      "epoch": 0.45473684210526316,
+      "grad_norm": 0.21509627997875214,
+      "learning_rate": 9.922423267772986e-07,
+      "loss": 0.639409875869751,
+      "step": 270
+    },
+    {
+      "epoch": 0.47157894736842104,
+      "grad_norm": 0.3022947609424591,
+      "learning_rate": 9.904284516597102e-07,
+      "loss": 0.5995691776275635,
+      "step": 280
+    },
+    {
+      "epoch": 0.4884210526315789,
+      "grad_norm": 0.3367304801940918,
+      "learning_rate": 9.884262140371648e-07,
+      "loss": 0.5898309707641601,
+      "step": 290
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "grad_norm": 0.294842928647995,
+      "learning_rate": 9.862363829239662e-07,
+      "loss": 0.6371779441833496,
+      "step": 300
+    },
+    {
+      "epoch": 0.5221052631578947,
+      "grad_norm": 0.25171560049057007,
+      "learning_rate": 9.838597993848456e-07,
+      "loss": 0.5795581817626954,
+      "step": 310
+    },
+    {
+      "epoch": 0.5389473684210526,
+      "grad_norm": 0.2818540036678314,
+      "learning_rate": 9.81297376211928e-07,
+      "loss": 0.5668415546417236,
+      "step": 320
+    },
+    {
+      "epoch": 0.5557894736842105,
+      "grad_norm": 0.32951900362968445,
+      "learning_rate": 9.785500975741498e-07,
+      "loss": 0.5933257102966308,
+      "step": 330
+    },
+    {
+      "epoch": 0.5726315789473684,
+      "grad_norm": 0.2763514518737793,
+      "learning_rate": 9.756190186392615e-07,
+      "loss": 0.5574678897857666,
+      "step": 340
+    },
+    {
+      "epoch": 0.5894736842105263,
+      "grad_norm": 0.3070182204246521,
+      "learning_rate": 9.725052651685612e-07,
+      "loss": 0.5532425880432129,
+      "step": 350
+    },
+    {
+      "epoch": 0.6063157894736843,
+      "grad_norm": 0.2079988420009613,
+      "learning_rate": 9.692100330845153e-07,
+      "loss": 0.5613389492034913,
+      "step": 360
+    },
+    {
+      "epoch": 0.6231578947368421,
+      "grad_norm": 0.282924622297287,
+      "learning_rate": 9.657345880114318e-07,
+      "loss": 0.5131485939025879,
+      "step": 370
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.20901450514793396,
+      "learning_rate": 9.620802647893623e-07,
+      "loss": 0.6279027462005615,
+      "step": 380
+    },
+    {
+      "epoch": 0.6568421052631579,
+      "grad_norm": 0.2637634575366974,
+      "learning_rate": 9.58248466961421e-07,
+      "loss": 0.5403085231781006,
+      "step": 390
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "grad_norm": 0.29078468680381775,
+      "learning_rate": 9.542406662347137e-07,
+      "loss": 0.5678809642791748,
+      "step": 400
+    },
+    {
+      "epoch": 0.6905263157894737,
+      "grad_norm": 0.2865101397037506,
+      "learning_rate": 9.500584019150895e-07,
+      "loss": 0.5479135036468505,
+      "step": 410
+    },
+    {
+      "epoch": 0.7073684210526315,
+      "grad_norm": 0.22857311367988586,
+      "learning_rate": 9.45703280315928e-07,
+      "loss": 0.5604462623596191,
+      "step": 420
+    },
+    {
+      "epoch": 0.7242105263157895,
+      "grad_norm": 0.23971959948539734,
+      "learning_rate": 9.411769741411903e-07,
+      "loss": 0.4704423427581787,
+      "step": 430
+    },
+    {
+      "epoch": 0.7410526315789474,
+      "grad_norm": 0.29793378710746765,
+      "learning_rate": 9.364812218429721e-07,
+      "loss": 0.560968017578125,
+      "step": 440
+    },
+    {
+      "epoch": 0.7578947368421053,
+      "grad_norm": 0.2236040234565735,
+      "learning_rate": 9.316178269538014e-07,
+      "loss": 0.5088452816009521,
+      "step": 450
+    },
+    {
+      "epoch": 0.7747368421052632,
+      "grad_norm": 0.22047854959964752,
+      "learning_rate": 9.265886573939446e-07,
+      "loss": 0.5030550956726074,
+      "step": 460
+    },
+    {
+      "epoch": 0.791578947368421,
+      "grad_norm": 0.2273361086845398,
+      "learning_rate": 9.213956447539792e-07,
+      "loss": 0.46353440284729003,
+      "step": 470
+    },
+    {
+      "epoch": 0.8084210526315789,
+      "grad_norm": 0.2170158326625824,
+      "learning_rate": 9.160407835529136e-07,
+      "loss": 0.49871411323547366,
+      "step": 480
+    },
+    {
+      "epoch": 0.8252631578947368,
+      "grad_norm": 0.19333498179912567,
+      "learning_rate": 9.105261304721375e-07,
+      "loss": 0.4416178226470947,
+      "step": 490
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.18490085005760193,
+      "learning_rate": 9.048538035654969e-07,
+      "loss": 0.39783194065093996,
+      "step": 500
+    },
+    {
+      "epoch": 0.8589473684210527,
+      "grad_norm": 0.22122648358345032,
+      "learning_rate": 8.990259814457977e-07,
+      "loss": 0.4318229198455811,
+      "step": 510
+    },
+    {
+      "epoch": 0.8757894736842106,
+      "grad_norm": 0.17448943853378296,
+      "learning_rate": 8.930449024480491e-07,
+      "loss": 0.42445807456970214,
+      "step": 520
+    },
+    {
+      "epoch": 0.8926315789473684,
+      "grad_norm": 0.18165165185928345,
+      "learning_rate": 8.8691286376977e-07,
+      "loss": 0.46429901123046874,
+      "step": 530
+    },
+    {
+      "epoch": 0.9094736842105263,
+      "grad_norm": 0.16785287857055664,
+      "learning_rate": 8.806322205886873e-07,
+      "loss": 0.3975703239440918,
+      "step": 540
+    },
+    {
+      "epoch": 0.9263157894736842,
+      "grad_norm": 0.1613738089799881,
+      "learning_rate": 8.74205385158165e-07,
+      "loss": 0.4458911418914795,
+      "step": 550
+    },
+    {
+      "epoch": 0.9431578947368421,
+      "grad_norm": 0.15376177430152893,
+      "learning_rate": 8.676348258807121e-07,
+      "loss": 0.45571184158325195,
+      "step": 560
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.14966322481632233,
+      "learning_rate": 8.609230663599254e-07,
+      "loss": 0.4039600372314453,
+      "step": 570
+    },
+    {
+      "epoch": 0.9768421052631578,
+      "grad_norm": 0.16819055378437042,
+      "learning_rate": 8.540726844312294e-07,
+      "loss": 0.4382494926452637,
+      "step": 580
+    },
+    {
+      "epoch": 0.9936842105263158,
+      "grad_norm": 0.16405776143074036,
+      "learning_rate": 8.470863111717889e-07,
+      "loss": 0.4306180477142334,
+      "step": 590
+    },
+    {
+      "epoch": 1.0101052631578948,
+      "grad_norm": 0.18503950536251068,
+      "learning_rate": 8.399666298899706e-07,
+      "loss": 0.39806089401245115,
+      "step": 600
+    },
+    {
+      "epoch": 1.0269473684210526,
+      "grad_norm": 0.14375492930412292,
+      "learning_rate": 8.327163750947457e-07,
+      "loss": 0.4271697044372559,
+      "step": 610
+    },
+    {
+      "epoch": 1.0437894736842106,
+      "grad_norm": 0.1412728875875473,
+      "learning_rate": 8.253383314454263e-07,
+      "loss": 0.3939049243927002,
+      "step": 620
+    },
+    {
+      "epoch": 1.0606315789473684,
+      "grad_norm": 0.20121850073337555,
+      "learning_rate": 8.178353326821404e-07,
+      "loss": 0.43197131156921387,
+      "step": 630
+    },
+    {
+      "epoch": 1.0774736842105264,
+      "grad_norm": 0.17767728865146637,
+      "learning_rate": 8.102102605374566e-07,
+      "loss": 0.437807559967041,
+      "step": 640
+    },
+    {
+      "epoch": 1.0943157894736841,
+      "grad_norm": 0.1498359888792038,
+      "learning_rate": 8.024660436295759e-07,
+      "loss": 0.38409013748168946,
+      "step": 650
+    },
+    {
+      "epoch": 1.1111578947368421,
+      "grad_norm": 0.15958793461322784,
+      "learning_rate": 7.946056563375145e-07,
+      "loss": 0.4204962730407715,
+      "step": 660
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.157291978597641,
+      "learning_rate": 7.866321176587128e-07,
+      "loss": 0.42113161087036133,
+      "step": 670
+    },
+    {
+      "epoch": 1.1448421052631579,
+      "grad_norm": 0.14119838178157806,
+      "learning_rate": 7.785484900495065e-07,
+      "loss": 0.4151731491088867,
+      "step": 680
+    },
+    {
+      "epoch": 1.1616842105263159,
+      "grad_norm": 0.1296525001525879,
+      "learning_rate": 7.703578782489058e-07,
+      "loss": 0.38312902450561526,
+      "step": 690
+    },
+    {
+      "epoch": 1.1785263157894736,
+      "grad_norm": 0.13671696186065674,
+      "learning_rate": 7.620634280861351e-07,
+      "loss": 0.42612557411193847,
+      "step": 700
+    },
+    {
+      "epoch": 1.1953684210526316,
+      "grad_norm": 0.15196114778518677,
+      "learning_rate": 7.536683252723923e-07,
+      "loss": 0.4306772708892822,
+      "step": 710
+    },
+    {
+      "epoch": 1.2122105263157894,
+      "grad_norm": 0.1136903315782547,
+      "learning_rate": 7.451757941772868e-07,
+      "loss": 0.38483757972717286,
+      "step": 720
+    },
+    {
+      "epoch": 1.2290526315789474,
+      "grad_norm": 0.12378744781017303,
+      "learning_rate": 7.365890965904337e-07,
+      "loss": 0.4030342102050781,
+      "step": 730
+    },
+    {
+      "epoch": 1.2458947368421052,
+      "grad_norm": 0.1265542209148407,
+      "learning_rate": 7.279115304686733e-07,
+      "loss": 0.4091166973114014,
+      "step": 740
+    },
+    {
+      "epoch": 1.2627368421052632,
+      "grad_norm": 0.11647409200668335,
+      "learning_rate": 7.191464286694e-07,
+      "loss": 0.41426806449890136,
+      "step": 750
+    },
+    {
+      "epoch": 1.279578947368421,
+      "grad_norm": 0.11192695051431656,
+      "learning_rate": 7.102971576704875e-07,
+      "loss": 0.38181486129760744,
+      "step": 760
+    },
+    {
+      "epoch": 1.296421052631579,
+      "grad_norm": 0.14947861433029175,
+      "learning_rate": 7.013671162773003e-07,
+      "loss": 0.39824953079223635,
+      "step": 770
+    },
+    {
+      "epoch": 1.313263157894737,
+      "grad_norm": 0.11269424855709076,
+      "learning_rate": 6.923597343172891e-07,
+      "loss": 0.40348024368286134,
+      "step": 780
+    },
+    {
+      "epoch": 1.3301052631578947,
+      "grad_norm": 0.3742346167564392,
+      "learning_rate": 6.83278471322672e-07,
+      "loss": 0.38022048473358155,
+      "step": 790
+    },
+    {
+      "epoch": 1.3469473684210527,
+      "grad_norm": 0.1310902237892151,
+      "learning_rate": 6.741268152017057e-07,
+      "loss": 0.42791285514831545,
+      "step": 800
+    },
+    {
+      "epoch": 1.3637894736842107,
+      "grad_norm": 0.1692703813314438,
+      "learning_rate": 6.649082808990585e-07,
+      "loss": 0.4263493061065674,
+      "step": 810
+    },
+    {
+      "epoch": 1.3806315789473684,
+      "grad_norm": 0.1279117316007614,
+      "learning_rate": 6.556264090457998e-07,
+      "loss": 0.37379777431488037,
+      "step": 820
+    },
+    {
+      "epoch": 1.3974736842105262,
+      "grad_norm": 0.12949039041996002,
+      "learning_rate": 6.462847645995237e-07,
+      "loss": 0.38636391162872313,
+      "step": 830
+    },
+    {
+      "epoch": 1.4143157894736842,
+      "grad_norm": 0.10221126675605774,
+      "learning_rate": 6.368869354751284e-07,
+      "loss": 0.408221435546875,
+      "step": 840
+    },
+    {
+      "epoch": 1.4311578947368422,
+      "grad_norm": 0.11505889147520065,
+      "learning_rate": 6.274365311667797e-07,
+      "loss": 0.3951406717300415,
+      "step": 850
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.11054962873458862,
+      "learning_rate": 6.179371813615859e-07,
+      "loss": 0.3732129096984863,
+      "step": 860
+    },
+    {
+      "epoch": 1.464842105263158,
+      "grad_norm": 0.10150120407342911,
+      "learning_rate": 6.083925345455158e-07,
+      "loss": 0.38601529598236084,
+      "step": 870
+    },
+    {
+      "epoch": 1.4816842105263157,
+      "grad_norm": 0.12239400297403336,
+      "learning_rate": 5.988062566020986e-07,
+      "loss": 0.3859985828399658,
+      "step": 880
+    },
+    {
+      "epoch": 1.4985263157894737,
+      "grad_norm": 0.15801067650318146,
+      "learning_rate": 5.891820294044408e-07,
+      "loss": 0.3983951807022095,
+      "step": 890
+    },
+    {
+      "epoch": 1.5153684210526315,
+      "grad_norm": 0.10104545950889587,
+      "learning_rate": 5.795235494011007e-07,
+      "loss": 0.41107850074768065,
+      "step": 900
+    },
+    {
+      "epoch": 1.5322105263157895,
+      "grad_norm": 0.1378099024295807,
+      "learning_rate": 5.698345261963668e-07,
+      "loss": 0.3708331823348999,
+      "step": 910
+    },
+    {
+      "epoch": 1.5490526315789475,
+      "grad_norm": 0.12936057150363922,
+      "learning_rate": 5.601186811254825e-07,
+      "loss": 0.387884521484375,
+      "step": 920
+    },
+    {
+      "epoch": 1.5658947368421052,
+      "grad_norm": 0.12379129230976105,
+      "learning_rate": 5.503797458253646e-07,
+      "loss": 0.43808717727661134,
+      "step": 930
+    },
+    {
+      "epoch": 1.582736842105263,
+      "grad_norm": 0.12017743289470673,
+      "learning_rate": 5.406214608013662e-07,
+      "loss": 0.41345391273498533,
+      "step": 940
+    },
+    {
+      "epoch": 1.5995789473684212,
+      "grad_norm": 0.1095535159111023,
+      "learning_rate": 5.308475739906328e-07,
+      "loss": 0.40022664070129393,
+      "step": 950
+    },
+    {
+      "epoch": 1.616421052631579,
+      "grad_norm": 0.13831396400928497,
+      "learning_rate": 5.210618393226045e-07,
+      "loss": 0.3909924983978271,
+      "step": 960
+    },
+    {
+      "epoch": 1.6332631578947368,
+      "grad_norm": 0.10449163615703583,
+      "learning_rate": 5.112680152772156e-07,
+      "loss": 0.37143146991729736,
+      "step": 970
+    },
+    {
+      "epoch": 1.6501052631578947,
+      "grad_norm": 0.11249610036611557,
+      "learning_rate": 5.01469863441348e-07,
+      "loss": 0.38103113174438474,
+      "step": 980
+    },
+    {
+      "epoch": 1.6669473684210527,
+      "grad_norm": 0.13718819618225098,
+      "learning_rate": 4.916711470640907e-07,
+      "loss": 0.4071629524230957,
+      "step": 990
+    },
+    {
+      "epoch": 1.6837894736842105,
+      "grad_norm": 0.10473571717739105,
+      "learning_rate": 4.818756296113595e-07,
+      "loss": 0.417419958114624,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7006315789473683,
+      "grad_norm": 0.10846224427223206,
+      "learning_rate": 4.7208707332043623e-07,
+      "loss": 0.3998772859573364,
+      "step": 1010
+    },
+    {
+      "epoch": 1.7174736842105263,
+      "grad_norm": 0.10248563438653946,
+      "learning_rate": 4.6230923775497714e-07,
+      "loss": 0.38056583404541017,
+      "step": 1020
+    },
+    {
+      "epoch": 1.7343157894736843,
+      "grad_norm": 0.12221980094909668,
+      "learning_rate": 4.5254587836104964e-07,
+      "loss": 0.39371190071105955,
+      "step": 1030
+    },
+    {
+      "epoch": 1.751157894736842,
+      "grad_norm": 0.10641586035490036,
+      "learning_rate": 4.4280074502475017e-07,
+      "loss": 0.4280440330505371,
+      "step": 1040
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.12907131016254425,
+      "learning_rate": 4.3307758063195796e-07,
+      "loss": 0.3791615962982178,
+      "step": 1050
+    },
+    {
+      "epoch": 1.784842105263158,
+      "grad_norm": 0.12383506447076797,
+      "learning_rate": 4.233801196307762e-07,
+      "loss": 0.347782301902771,
+      "step": 1060
+    },
+    {
+      "epoch": 1.8016842105263158,
+      "grad_norm": 0.12547679245471954,
+      "learning_rate": 4.1371208659721536e-07,
+      "loss": 0.38370628356933595,
+      "step": 1070
+    },
+    {
+      "epoch": 1.8185263157894735,
+      "grad_norm": 0.10580642521381378,
+      "learning_rate": 4.0407719480466736e-07,
+      "loss": 0.40404376983642576,
+      "step": 1080
+    },
+    {
+      "epoch": 1.8353684210526315,
+      "grad_norm": 0.1055402085185051,
+      "learning_rate": 3.944791447977213e-07,
+      "loss": 0.4167450428009033,
+      "step": 1090
+    },
+    {
+      "epoch": 1.8522105263157895,
+      "grad_norm": 0.11053823679685593,
+      "learning_rate": 3.849216229708671e-07,
+      "loss": 0.4046513080596924,
+      "step": 1100
+    },
+    {
+      "epoch": 1.8690526315789473,
+      "grad_norm": 0.10185246914625168,
+      "learning_rate": 3.7540830015263526e-07,
+      "loss": 0.39672977924346925,
+      "step": 1110
+    },
+    {
+      "epoch": 1.8858947368421053,
+      "grad_norm": 0.08342823386192322,
+      "learning_rate": 3.6594283019571416e-07,
+      "loss": 0.39356396198272703,
+      "step": 1120
+    },
+    {
+      "epoch": 1.9027368421052633,
+      "grad_norm": 0.11821646988391876,
+      "learning_rate": 3.565288485735874e-07,
+      "loss": 0.42082643508911133,
+      "step": 1130
+    },
+    {
+      "epoch": 1.919578947368421,
+      "grad_norm": 0.1106327474117279,
+      "learning_rate": 3.4716997098423085e-07,
+      "loss": 0.34105117321014405,
+      "step": 1140
+    },
+    {
+      "epoch": 1.9364210526315788,
+      "grad_norm": 0.11533800512552261,
+      "learning_rate": 3.378697919614045e-07,
+      "loss": 0.3924069404602051,
+      "step": 1150
+    },
+    {
+      "epoch": 1.9532631578947368,
+      "grad_norm": 0.1431114822626114,
+      "learning_rate": 3.286318834940729e-07,
+      "loss": 0.3922377586364746,
+      "step": 1160
+    },
+    {
+      "epoch": 1.9701052631578948,
+      "grad_norm": 0.16050194203853607,
+      "learning_rate": 3.1945979365448517e-07,
+      "loss": 0.3745201587677002,
+      "step": 1170
+    },
+    {
+      "epoch": 1.9869473684210526,
+      "grad_norm": 0.11921833455562592,
+      "learning_rate": 3.103570452354402e-07,
+      "loss": 0.40110602378845217,
+      "step": 1180
+    },
+    {
+      "epoch": 2.0033684210526315,
+      "grad_norm": 0.0832003727555275,
+      "learning_rate": 3.013271343972613e-07,
+      "loss": 0.3981154918670654,
+      "step": 1190
+    },
+    {
+      "epoch": 2.0202105263157897,
+      "grad_norm": 0.09975888580083847,
+      "learning_rate": 2.9237352932500046e-07,
+      "loss": 0.3726134061813354,
+      "step": 1200
+    },
+    {
+      "epoch": 2.0370526315789474,
+      "grad_norm": 0.14600081741809845,
+      "learning_rate": 2.8349966889638615e-07,
+      "loss": 0.42558698654174804,
+      "step": 1210
+    },
+    {
+      "epoch": 2.053894736842105,
+      "grad_norm": 0.10875770449638367,
+      "learning_rate": 2.747089613610278e-07,
+      "loss": 0.3682931184768677,
+      "step": 1220
+    },
+    {
+      "epoch": 2.070736842105263,
+      "grad_norm": 0.10050549358129501,
+      "learning_rate": 2.66004783031385e-07,
+      "loss": 0.3756644487380981,
+      "step": 1230
+    },
+    {
+      "epoch": 2.087578947368421,
+      "grad_norm": 0.08914914727210999,
+      "learning_rate": 2.573904769860009e-07,
+      "loss": 0.3804330825805664,
+      "step": 1240
+    },
+    {
+      "epoch": 2.104421052631579,
+      "grad_norm": 0.08296852558851242,
+      "learning_rate": 2.488693517855016e-07,
+      "loss": 0.3978404521942139,
+      "step": 1250
+    },
+    {
+      "epoch": 2.1212631578947367,
+      "grad_norm": 0.13885149359703064,
+      "learning_rate": 2.404446802018533e-07,
+      "loss": 0.3935218334197998,
+      "step": 1260
+    },
+    {
+      "epoch": 2.138105263157895,
+      "grad_norm": 0.13195137679576874,
+      "learning_rate": 2.3211969796136305e-07,
+      "loss": 0.42966952323913576,
+      "step": 1270
+    },
+    {
+      "epoch": 2.1549473684210527,
+      "grad_norm": 0.13367892801761627,
+      "learning_rate": 2.2389760250191038e-07,
+      "loss": 0.3679579019546509,
+      "step": 1280
+    },
+    {
+      "epoch": 2.1717894736842105,
+      "grad_norm": 0.1288345605134964,
+      "learning_rate": 2.1578155174488343e-07,
+      "loss": 0.41324810981750487,
+      "step": 1290
+    },
+    {
+      "epoch": 2.1886315789473683,
+      "grad_norm": 0.09626021236181259,
+      "learning_rate": 2.0777466288229205e-07,
+      "loss": 0.40120248794555663,
+      "step": 1300
+    },
+    {
+      "epoch": 2.2054736842105265,
+      "grad_norm": 0.10264381766319275,
+      "learning_rate": 1.9988001117952485e-07,
+      "loss": 0.3501007080078125,
+      "step": 1310
+    },
+    {
+      "epoch": 2.2223157894736842,
+      "grad_norm": 0.09031466394662857,
+      "learning_rate": 1.9210062879420973e-07,
+      "loss": 0.3839429378509521,
+      "step": 1320
+    },
+    {
+      "epoch": 2.239157894736842,
+      "grad_norm": 0.12686079740524292,
+      "learning_rate": 1.8443950361162957e-07,
+      "loss": 0.4338528156280518,
+      "step": 1330
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 0.12199016660451889,
+      "learning_rate": 1.7689957809714346e-07,
+      "loss": 0.39229888916015626,
+      "step": 1340
+    },
+    {
+      "epoch": 2.272842105263158,
+      "grad_norm": 0.12029567360877991,
+      "learning_rate": 1.694837481660525e-07,
+      "loss": 0.38006880283355715,
+      "step": 1350
+    },
+    {
+      "epoch": 2.2896842105263158,
+      "grad_norm": 0.08686309307813644,
+      "learning_rate": 1.6219486207134313e-07,
+      "loss": 0.3808159589767456,
+      "step": 1360
+    },
+    {
+      "epoch": 2.3065263157894735,
+      "grad_norm": 0.10810462385416031,
+      "learning_rate": 1.5503571930973785e-07,
+      "loss": 0.401824426651001,
+      "step": 1370
+    },
+    {
+      "epoch": 2.3233684210526317,
+      "grad_norm": 0.10281873494386673,
+      "learning_rate": 1.480090695464723e-07,
+      "loss": 0.40149493217468263,
+      "step": 1380
+    },
+    {
+      "epoch": 2.3402105263157895,
+      "grad_norm": 0.09503985196352005,
+      "learning_rate": 1.4111761155920975e-07,
+      "loss": 0.38567726612091063,
+      "step": 1390
+    },
+    {
+      "epoch": 2.3570526315789473,
+      "grad_norm": 0.10420782119035721,
+      "learning_rate": 1.3436399220150212e-07,
+      "loss": 0.3759742736816406,
+      "step": 1400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1782,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.559039062380339e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1400/training_args.bin b/checkpoint-1400/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..26362bce38749fb4af3e32947d24cd6a387b57ac
--- /dev/null
+++ b/checkpoint-1400/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e59b6aeffb8563cc09210642a0d080410d061efe9a32399cd1e4a1e0abccb0a
+size 5585
diff --git a/checkpoint-1500/README.md b/checkpoint-1500/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..cfd546f8318a3a2985d8a7e4c881e529305dd807
--- /dev/null
+++ b/checkpoint-1500/README.md
@@ -0,0 +1,208 @@
+---
+base_model: google/gemma-3-1b-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:google/gemma-3-1b-it
+- llama-factory
+- 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 0.18.1
\ No newline at end of file
diff --git a/checkpoint-1500/adapter_config.json b/checkpoint-1500/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..b7033a591cf40ea5b43aae7a6f56ed6a65d3f80c
--- /dev/null
+++ b/checkpoint-1500/adapter_config.json
@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-1b-it",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj",
+    "q_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/checkpoint-1500/chat_template.jinja b/checkpoint-1500/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..1117055ab8e8c90e1b200be00cddb78943616d9e
--- /dev/null
+++ b/checkpoint-1500/chat_template.jinja
@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}
diff --git a/checkpoint-1500/optimizer.pt b/checkpoint-1500/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..65cbcda66314bcff8180e5a84029bd369b7e269e
--- /dev/null
+++ b/checkpoint-1500/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd92b20e79099890a866712c75560516d2183b31fabb44bdeefd400ffa79d907
+size 52494119
diff --git a/checkpoint-1500/scheduler.pt b/checkpoint-1500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3ea052b441beb8628eedf7abd810af1164563143
--- /dev/null
+++ b/checkpoint-1500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22054b632e5063c85ccdc7cea2230764df35e2e45f2f169a54122de5c531ca3b
+size 1465
diff --git a/checkpoint-1500/tokenizer_config.json b/checkpoint-1500/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d83f12eef5a7d73283047b2f05c1ffdd6346556a
--- /dev/null
+++ b/checkpoint-1500/tokenizer_config.json
@@ -0,0 +1,26 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<end_of_turn>",
+  "image_token": "<image_soft_token>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "processor_class": "Gemma3Processor",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-1500/trainer_state.json b/checkpoint-1500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..3156fcccc7502afabdf965d7f507c141522a4135
--- /dev/null
+++ b/checkpoint-1500/trainer_state.json
@@ -0,0 +1,1084 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.5254736842105263,
+  "eval_steps": 100,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016842105263157894,
+      "grad_norm": 0.21757784485816956,
+      "learning_rate": 5.027932960893855e-08,
+      "loss": 0.7252199172973632,
+      "step": 10
+    },
+    {
+      "epoch": 0.03368421052631579,
+      "grad_norm": 0.2456846386194229,
+      "learning_rate": 1.0614525139664805e-07,
+      "loss": 0.6507451057434082,
+      "step": 20
+    },
+    {
+      "epoch": 0.05052631578947368,
+      "grad_norm": 0.20819272100925446,
+      "learning_rate": 1.6201117318435754e-07,
+      "loss": 0.7381344795227051,
+      "step": 30
+    },
+    {
+      "epoch": 0.06736842105263158,
+      "grad_norm": 0.26373574137687683,
+      "learning_rate": 2.17877094972067e-07,
+      "loss": 0.7012194156646728,
+      "step": 40
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 0.2081507444381714,
+      "learning_rate": 2.7374301675977653e-07,
+      "loss": 0.6083873748779297,
+      "step": 50
+    },
+    {
+      "epoch": 0.10105263157894737,
+      "grad_norm": 0.2091236114501953,
+      "learning_rate": 3.29608938547486e-07,
+      "loss": 0.6980491638183594,
+      "step": 60
+    },
+    {
+      "epoch": 0.11789473684210526,
+      "grad_norm": 0.20970331132411957,
+      "learning_rate": 3.8547486033519547e-07,
+      "loss": 0.708641767501831,
+      "step": 70
+    },
+    {
+      "epoch": 0.13473684210526315,
+      "grad_norm": 0.18810197710990906,
+      "learning_rate": 4.41340782122905e-07,
+      "loss": 0.6742453098297119,
+      "step": 80
+    },
+    {
+      "epoch": 0.15157894736842106,
+      "grad_norm": 0.20251069962978363,
+      "learning_rate": 4.972067039106145e-07,
+      "loss": 0.6590609550476074,
+      "step": 90
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "grad_norm": 0.2644217908382416,
+      "learning_rate": 5.53072625698324e-07,
+      "loss": 0.704926872253418,
+      "step": 100
+    },
+    {
+      "epoch": 0.18526315789473685,
+      "grad_norm": 0.23766489326953888,
+      "learning_rate": 6.089385474860335e-07,
+      "loss": 0.7445036888122558,
+      "step": 110
+    },
+    {
+      "epoch": 0.20210526315789473,
+      "grad_norm": 0.27427056431770325,
+      "learning_rate": 6.64804469273743e-07,
+      "loss": 0.7476531028747558,
+      "step": 120
+    },
+    {
+      "epoch": 0.21894736842105264,
+      "grad_norm": 0.3208928406238556,
+      "learning_rate": 7.206703910614524e-07,
+      "loss": 0.7291872501373291,
+      "step": 130
+    },
+    {
+      "epoch": 0.23578947368421052,
+      "grad_norm": 0.3123615086078644,
+      "learning_rate": 7.76536312849162e-07,
+      "loss": 0.721175241470337,
+      "step": 140
+    },
+    {
+      "epoch": 0.25263157894736843,
+      "grad_norm": 0.26158222556114197,
+      "learning_rate": 8.324022346368714e-07,
+      "loss": 0.7556095600128174,
+      "step": 150
+    },
+    {
+      "epoch": 0.2694736842105263,
+      "grad_norm": 0.2592650353908539,
+      "learning_rate": 8.88268156424581e-07,
+      "loss": 0.7328392505645752,
+      "step": 160
+    },
+    {
+      "epoch": 0.2863157894736842,
+      "grad_norm": 0.24533776938915253,
+      "learning_rate": 9.441340782122904e-07,
+      "loss": 0.6990129470825195,
+      "step": 170
+    },
+    {
+      "epoch": 0.3031578947368421,
+      "grad_norm": 0.23409004509449005,
+      "learning_rate": 1e-06,
+      "loss": 0.6694639205932618,
+      "step": 180
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.3267499506473541,
+      "learning_rate": 9.999039806396227e-07,
+      "loss": 0.7123252868652343,
+      "step": 190
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "grad_norm": 0.2115064263343811,
+      "learning_rate": 9.996159594373611e-07,
+      "loss": 0.6858412742614746,
+      "step": 200
+    },
+    {
+      "epoch": 0.35368421052631577,
+      "grad_norm": 0.26226580142974854,
+      "learning_rate": 9.991360470156615e-07,
+      "loss": 0.6541069507598877,
+      "step": 210
+    },
+    {
+      "epoch": 0.3705263157894737,
+      "grad_norm": 0.24552594125270844,
+      "learning_rate": 9.984644276980594e-07,
+      "loss": 0.6506116390228271,
+      "step": 220
+    },
+    {
+      "epoch": 0.3873684210526316,
+      "grad_norm": 0.25084301829338074,
+      "learning_rate": 9.976013594383835e-07,
+      "loss": 0.6540626049041748,
+      "step": 230
+    },
+    {
+      "epoch": 0.40421052631578946,
+      "grad_norm": 0.34244054555892944,
+      "learning_rate": 9.965471737216833e-07,
+      "loss": 0.6737770557403564,
+      "step": 240
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.34752583503723145,
+      "learning_rate": 9.953022754369114e-07,
+      "loss": 0.6755708217620849,
+      "step": 250
+    },
+    {
+      "epoch": 0.4378947368421053,
+      "grad_norm": 0.31017956137657166,
+      "learning_rate": 9.938671427214158e-07,
+      "loss": 0.6578442573547363,
+      "step": 260
+    },
+    {
+      "epoch": 0.45473684210526316,
+      "grad_norm": 0.21509627997875214,
+      "learning_rate": 9.922423267772986e-07,
+      "loss": 0.639409875869751,
+      "step": 270
+    },
+    {
+      "epoch": 0.47157894736842104,
+      "grad_norm": 0.3022947609424591,
+      "learning_rate": 9.904284516597102e-07,
+      "loss": 0.5995691776275635,
+      "step": 280
+    },
+    {
+      "epoch": 0.4884210526315789,
+      "grad_norm": 0.3367304801940918,
+      "learning_rate": 9.884262140371648e-07,
+      "loss": 0.5898309707641601,
+      "step": 290
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "grad_norm": 0.294842928647995,
+      "learning_rate": 9.862363829239662e-07,
+      "loss": 0.6371779441833496,
+      "step": 300
+    },
+    {
+      "epoch": 0.5221052631578947,
+      "grad_norm": 0.25171560049057007,
+      "learning_rate": 9.838597993848456e-07,
+      "loss": 0.5795581817626954,
+      "step": 310
+    },
+    {
+      "epoch": 0.5389473684210526,
+      "grad_norm": 0.2818540036678314,
+      "learning_rate": 9.81297376211928e-07,
+      "loss": 0.5668415546417236,
+      "step": 320
+    },
+    {
+      "epoch": 0.5557894736842105,
+      "grad_norm": 0.32951900362968445,
+      "learning_rate": 9.785500975741498e-07,
+      "loss": 0.5933257102966308,
+      "step": 330
+    },
+    {
+      "epoch": 0.5726315789473684,
+      "grad_norm": 0.2763514518737793,
+      "learning_rate": 9.756190186392615e-07,
+      "loss": 0.5574678897857666,
+      "step": 340
+    },
+    {
+      "epoch": 0.5894736842105263,
+      "grad_norm": 0.3070182204246521,
+      "learning_rate": 9.725052651685612e-07,
+      "loss": 0.5532425880432129,
+      "step": 350
+    },
+    {
+      "epoch": 0.6063157894736843,
+      "grad_norm": 0.2079988420009613,
+      "learning_rate": 9.692100330845153e-07,
+      "loss": 0.5613389492034913,
+      "step": 360
+    },
+    {
+      "epoch": 0.6231578947368421,
+      "grad_norm": 0.282924622297287,
+      "learning_rate": 9.657345880114318e-07,
+      "loss": 0.5131485939025879,
+      "step": 370
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.20901450514793396,
+      "learning_rate": 9.620802647893623e-07,
+      "loss": 0.6279027462005615,
+      "step": 380
+    },
+    {
+      "epoch": 0.6568421052631579,
+      "grad_norm": 0.2637634575366974,
+      "learning_rate": 9.58248466961421e-07,
+      "loss": 0.5403085231781006,
+      "step": 390
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "grad_norm": 0.29078468680381775,
+      "learning_rate": 9.542406662347137e-07,
+      "loss": 0.5678809642791748,
+      "step": 400
+    },
+    {
+      "epoch": 0.6905263157894737,
+      "grad_norm": 0.2865101397037506,
+      "learning_rate": 9.500584019150895e-07,
+      "loss": 0.5479135036468505,
+      "step": 410
+    },
+    {
+      "epoch": 0.7073684210526315,
+      "grad_norm": 0.22857311367988586,
+      "learning_rate": 9.45703280315928e-07,
+      "loss": 0.5604462623596191,
+      "step": 420
+    },
+    {
+      "epoch": 0.7242105263157895,
+      "grad_norm": 0.23971959948539734,
+      "learning_rate": 9.411769741411903e-07,
+      "loss": 0.4704423427581787,
+      "step": 430
+    },
+    {
+      "epoch": 0.7410526315789474,
+      "grad_norm": 0.29793378710746765,
+      "learning_rate": 9.364812218429721e-07,
+      "loss": 0.560968017578125,
+      "step": 440
+    },
+    {
+      "epoch": 0.7578947368421053,
+      "grad_norm": 0.2236040234565735,
+      "learning_rate": 9.316178269538014e-07,
+      "loss": 0.5088452816009521,
+      "step": 450
+    },
+    {
+      "epoch": 0.7747368421052632,
+      "grad_norm": 0.22047854959964752,
+      "learning_rate": 9.265886573939446e-07,
+      "loss": 0.5030550956726074,
+      "step": 460
+    },
+    {
+      "epoch": 0.791578947368421,
+      "grad_norm": 0.2273361086845398,
+      "learning_rate": 9.213956447539792e-07,
+      "loss": 0.46353440284729003,
+      "step": 470
+    },
+    {
+      "epoch": 0.8084210526315789,
+      "grad_norm": 0.2170158326625824,
+      "learning_rate": 9.160407835529136e-07,
+      "loss": 0.49871411323547366,
+      "step": 480
+    },
+    {
+      "epoch": 0.8252631578947368,
+      "grad_norm": 0.19333498179912567,
+      "learning_rate": 9.105261304721375e-07,
+      "loss": 0.4416178226470947,
+      "step": 490
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.18490085005760193,
+      "learning_rate": 9.048538035654969e-07,
+      "loss": 0.39783194065093996,
+      "step": 500
+    },
+    {
+      "epoch": 0.8589473684210527,
+      "grad_norm": 0.22122648358345032,
+      "learning_rate": 8.990259814457977e-07,
+      "loss": 0.4318229198455811,
+      "step": 510
+    },
+    {
+      "epoch": 0.8757894736842106,
+      "grad_norm": 0.17448943853378296,
+      "learning_rate": 8.930449024480491e-07,
+      "loss": 0.42445807456970214,
+      "step": 520
+    },
+    {
+      "epoch": 0.8926315789473684,
+      "grad_norm": 0.18165165185928345,
+      "learning_rate": 8.8691286376977e-07,
+      "loss": 0.46429901123046874,
+      "step": 530
+    },
+    {
+      "epoch": 0.9094736842105263,
+      "grad_norm": 0.16785287857055664,
+      "learning_rate": 8.806322205886873e-07,
+      "loss": 0.3975703239440918,
+      "step": 540
+    },
+    {
+      "epoch": 0.9263157894736842,
+      "grad_norm": 0.1613738089799881,
+      "learning_rate": 8.74205385158165e-07,
+      "loss": 0.4458911418914795,
+      "step": 550
+    },
+    {
+      "epoch": 0.9431578947368421,
+      "grad_norm": 0.15376177430152893,
+      "learning_rate": 8.676348258807121e-07,
+      "loss": 0.45571184158325195,
+      "step": 560
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.14966322481632233,
+      "learning_rate": 8.609230663599254e-07,
+      "loss": 0.4039600372314453,
+      "step": 570
+    },
+    {
+      "epoch": 0.9768421052631578,
+      "grad_norm": 0.16819055378437042,
+      "learning_rate": 8.540726844312294e-07,
+      "loss": 0.4382494926452637,
+      "step": 580
+    },
+    {
+      "epoch": 0.9936842105263158,
+      "grad_norm": 0.16405776143074036,
+      "learning_rate": 8.470863111717889e-07,
+      "loss": 0.4306180477142334,
+      "step": 590
+    },
+    {
+      "epoch": 1.0101052631578948,
+      "grad_norm": 0.18503950536251068,
+      "learning_rate": 8.399666298899706e-07,
+      "loss": 0.39806089401245115,
+      "step": 600
+    },
+    {
+      "epoch": 1.0269473684210526,
+      "grad_norm": 0.14375492930412292,
+      "learning_rate": 8.327163750947457e-07,
+      "loss": 0.4271697044372559,
+      "step": 610
+    },
+    {
+      "epoch": 1.0437894736842106,
+      "grad_norm": 0.1412728875875473,
+      "learning_rate": 8.253383314454263e-07,
+      "loss": 0.3939049243927002,
+      "step": 620
+    },
+    {
+      "epoch": 1.0606315789473684,
+      "grad_norm": 0.20121850073337555,
+      "learning_rate": 8.178353326821404e-07,
+      "loss": 0.43197131156921387,
+      "step": 630
+    },
+    {
+      "epoch": 1.0774736842105264,
+      "grad_norm": 0.17767728865146637,
+      "learning_rate": 8.102102605374566e-07,
+      "loss": 0.437807559967041,
+      "step": 640
+    },
+    {
+      "epoch": 1.0943157894736841,
+      "grad_norm": 0.1498359888792038,
+      "learning_rate": 8.024660436295759e-07,
+      "loss": 0.38409013748168946,
+      "step": 650
+    },
+    {
+      "epoch": 1.1111578947368421,
+      "grad_norm": 0.15958793461322784,
+      "learning_rate": 7.946056563375145e-07,
+      "loss": 0.4204962730407715,
+      "step": 660
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.157291978597641,
+      "learning_rate": 7.866321176587128e-07,
+      "loss": 0.42113161087036133,
+      "step": 670
+    },
+    {
+      "epoch": 1.1448421052631579,
+      "grad_norm": 0.14119838178157806,
+      "learning_rate": 7.785484900495065e-07,
+      "loss": 0.4151731491088867,
+      "step": 680
+    },
+    {
+      "epoch": 1.1616842105263159,
+      "grad_norm": 0.1296525001525879,
+      "learning_rate": 7.703578782489058e-07,
+      "loss": 0.38312902450561526,
+      "step": 690
+    },
+    {
+      "epoch": 1.1785263157894736,
+      "grad_norm": 0.13671696186065674,
+      "learning_rate": 7.620634280861351e-07,
+      "loss": 0.42612557411193847,
+      "step": 700
+    },
+    {
+      "epoch": 1.1953684210526316,
+      "grad_norm": 0.15196114778518677,
+      "learning_rate": 7.536683252723923e-07,
+      "loss": 0.4306772708892822,
+      "step": 710
+    },
+    {
+      "epoch": 1.2122105263157894,
+      "grad_norm": 0.1136903315782547,
+      "learning_rate": 7.451757941772868e-07,
+      "loss": 0.38483757972717286,
+      "step": 720
+    },
+    {
+      "epoch": 1.2290526315789474,
+      "grad_norm": 0.12378744781017303,
+      "learning_rate": 7.365890965904337e-07,
+      "loss": 0.4030342102050781,
+      "step": 730
+    },
+    {
+      "epoch": 1.2458947368421052,
+      "grad_norm": 0.1265542209148407,
+      "learning_rate": 7.279115304686733e-07,
+      "loss": 0.4091166973114014,
+      "step": 740
+    },
+    {
+      "epoch": 1.2627368421052632,
+      "grad_norm": 0.11647409200668335,
+      "learning_rate": 7.191464286694e-07,
+      "loss": 0.41426806449890136,
+      "step": 750
+    },
+    {
+      "epoch": 1.279578947368421,
+      "grad_norm": 0.11192695051431656,
+      "learning_rate": 7.102971576704875e-07,
+      "loss": 0.38181486129760744,
+      "step": 760
+    },
+    {
+      "epoch": 1.296421052631579,
+      "grad_norm": 0.14947861433029175,
+      "learning_rate": 7.013671162773003e-07,
+      "loss": 0.39824953079223635,
+      "step": 770
+    },
+    {
+      "epoch": 1.313263157894737,
+      "grad_norm": 0.11269424855709076,
+      "learning_rate": 6.923597343172891e-07,
+      "loss": 0.40348024368286134,
+      "step": 780
+    },
+    {
+      "epoch": 1.3301052631578947,
+      "grad_norm": 0.3742346167564392,
+      "learning_rate": 6.83278471322672e-07,
+      "loss": 0.38022048473358155,
+      "step": 790
+    },
+    {
+      "epoch": 1.3469473684210527,
+      "grad_norm": 0.1310902237892151,
+      "learning_rate": 6.741268152017057e-07,
+      "loss": 0.42791285514831545,
+      "step": 800
+    },
+    {
+      "epoch": 1.3637894736842107,
+      "grad_norm": 0.1692703813314438,
+      "learning_rate": 6.649082808990585e-07,
+      "loss": 0.4263493061065674,
+      "step": 810
+    },
+    {
+      "epoch": 1.3806315789473684,
+      "grad_norm": 0.1279117316007614,
+      "learning_rate": 6.556264090457998e-07,
+      "loss": 0.37379777431488037,
+      "step": 820
+    },
+    {
+      "epoch": 1.3974736842105262,
+      "grad_norm": 0.12949039041996002,
+      "learning_rate": 6.462847645995237e-07,
+      "loss": 0.38636391162872313,
+      "step": 830
+    },
+    {
+      "epoch": 1.4143157894736842,
+      "grad_norm": 0.10221126675605774,
+      "learning_rate": 6.368869354751284e-07,
+      "loss": 0.408221435546875,
+      "step": 840
+    },
+    {
+      "epoch": 1.4311578947368422,
+      "grad_norm": 0.11505889147520065,
+      "learning_rate": 6.274365311667797e-07,
+      "loss": 0.3951406717300415,
+      "step": 850
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.11054962873458862,
+      "learning_rate": 6.179371813615859e-07,
+      "loss": 0.3732129096984863,
+      "step": 860
+    },
+    {
+      "epoch": 1.464842105263158,
+      "grad_norm": 0.10150120407342911,
+      "learning_rate": 6.083925345455158e-07,
+      "loss": 0.38601529598236084,
+      "step": 870
+    },
+    {
+      "epoch": 1.4816842105263157,
+      "grad_norm": 0.12239400297403336,
+      "learning_rate": 5.988062566020986e-07,
+      "loss": 0.3859985828399658,
+      "step": 880
+    },
+    {
+      "epoch": 1.4985263157894737,
+      "grad_norm": 0.15801067650318146,
+      "learning_rate": 5.891820294044408e-07,
+      "loss": 0.3983951807022095,
+      "step": 890
+    },
+    {
+      "epoch": 1.5153684210526315,
+      "grad_norm": 0.10104545950889587,
+      "learning_rate": 5.795235494011007e-07,
+      "loss": 0.41107850074768065,
+      "step": 900
+    },
+    {
+      "epoch": 1.5322105263157895,
+      "grad_norm": 0.1378099024295807,
+      "learning_rate": 5.698345261963668e-07,
+      "loss": 0.3708331823348999,
+      "step": 910
+    },
+    {
+      "epoch": 1.5490526315789475,
+      "grad_norm": 0.12936057150363922,
+      "learning_rate": 5.601186811254825e-07,
+      "loss": 0.387884521484375,
+      "step": 920
+    },
+    {
+      "epoch": 1.5658947368421052,
+      "grad_norm": 0.12379129230976105,
+      "learning_rate": 5.503797458253646e-07,
+      "loss": 0.43808717727661134,
+      "step": 930
+    },
+    {
+      "epoch": 1.582736842105263,
+      "grad_norm": 0.12017743289470673,
+      "learning_rate": 5.406214608013662e-07,
+      "loss": 0.41345391273498533,
+      "step": 940
+    },
+    {
+      "epoch": 1.5995789473684212,
+      "grad_norm": 0.1095535159111023,
+      "learning_rate": 5.308475739906328e-07,
+      "loss": 0.40022664070129393,
+      "step": 950
+    },
+    {
+      "epoch": 1.616421052631579,
+      "grad_norm": 0.13831396400928497,
+      "learning_rate": 5.210618393226045e-07,
+      "loss": 0.3909924983978271,
+      "step": 960
+    },
+    {
+      "epoch": 1.6332631578947368,
+      "grad_norm": 0.10449163615703583,
+      "learning_rate": 5.112680152772156e-07,
+      "loss": 0.37143146991729736,
+      "step": 970
+    },
+    {
+      "epoch": 1.6501052631578947,
+      "grad_norm": 0.11249610036611557,
+      "learning_rate": 5.01469863441348e-07,
+      "loss": 0.38103113174438474,
+      "step": 980
+    },
+    {
+      "epoch": 1.6669473684210527,
+      "grad_norm": 0.13718819618225098,
+      "learning_rate": 4.916711470640907e-07,
+      "loss": 0.4071629524230957,
+      "step": 990
+    },
+    {
+      "epoch": 1.6837894736842105,
+      "grad_norm": 0.10473571717739105,
+      "learning_rate": 4.818756296113595e-07,
+      "loss": 0.417419958114624,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7006315789473683,
+      "grad_norm": 0.10846224427223206,
+      "learning_rate": 4.7208707332043623e-07,
+      "loss": 0.3998772859573364,
+      "step": 1010
+    },
+    {
+      "epoch": 1.7174736842105263,
+      "grad_norm": 0.10248563438653946,
+      "learning_rate": 4.6230923775497714e-07,
+      "loss": 0.38056583404541017,
+      "step": 1020
+    },
+    {
+      "epoch": 1.7343157894736843,
+      "grad_norm": 0.12221980094909668,
+      "learning_rate": 4.5254587836104964e-07,
+      "loss": 0.39371190071105955,
+      "step": 1030
+    },
+    {
+      "epoch": 1.751157894736842,
+      "grad_norm": 0.10641586035490036,
+      "learning_rate": 4.4280074502475017e-07,
+      "loss": 0.4280440330505371,
+      "step": 1040
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.12907131016254425,
+      "learning_rate": 4.3307758063195796e-07,
+      "loss": 0.3791615962982178,
+      "step": 1050
+    },
+    {
+      "epoch": 1.784842105263158,
+      "grad_norm": 0.12383506447076797,
+      "learning_rate": 4.233801196307762e-07,
+      "loss": 0.347782301902771,
+      "step": 1060
+    },
+    {
+      "epoch": 1.8016842105263158,
+      "grad_norm": 0.12547679245471954,
+      "learning_rate": 4.1371208659721536e-07,
+      "loss": 0.38370628356933595,
+      "step": 1070
+    },
+    {
+      "epoch": 1.8185263157894735,
+      "grad_norm": 0.10580642521381378,
+      "learning_rate": 4.0407719480466736e-07,
+      "loss": 0.40404376983642576,
+      "step": 1080
+    },
+    {
+      "epoch": 1.8353684210526315,
+      "grad_norm": 0.1055402085185051,
+      "learning_rate": 3.944791447977213e-07,
+      "loss": 0.4167450428009033,
+      "step": 1090
+    },
+    {
+      "epoch": 1.8522105263157895,
+      "grad_norm": 0.11053823679685593,
+      "learning_rate": 3.849216229708671e-07,
+      "loss": 0.4046513080596924,
+      "step": 1100
+    },
+    {
+      "epoch": 1.8690526315789473,
+      "grad_norm": 0.10185246914625168,
+      "learning_rate": 3.7540830015263526e-07,
+      "loss": 0.39672977924346925,
+      "step": 1110
+    },
+    {
+      "epoch": 1.8858947368421053,
+      "grad_norm": 0.08342823386192322,
+      "learning_rate": 3.6594283019571416e-07,
+      "loss": 0.39356396198272703,
+      "step": 1120
+    },
+    {
+      "epoch": 1.9027368421052633,
+      "grad_norm": 0.11821646988391876,
+      "learning_rate": 3.565288485735874e-07,
+      "loss": 0.42082643508911133,
+      "step": 1130
+    },
+    {
+      "epoch": 1.919578947368421,
+      "grad_norm": 0.1106327474117279,
+      "learning_rate": 3.4716997098423085e-07,
+      "loss": 0.34105117321014405,
+      "step": 1140
+    },
+    {
+      "epoch": 1.9364210526315788,
+      "grad_norm": 0.11533800512552261,
+      "learning_rate": 3.378697919614045e-07,
+      "loss": 0.3924069404602051,
+      "step": 1150
+    },
+    {
+      "epoch": 1.9532631578947368,
+      "grad_norm": 0.1431114822626114,
+      "learning_rate": 3.286318834940729e-07,
+      "loss": 0.3922377586364746,
+      "step": 1160
+    },
+    {
+      "epoch": 1.9701052631578948,
+      "grad_norm": 0.16050194203853607,
+      "learning_rate": 3.1945979365448517e-07,
+      "loss": 0.3745201587677002,
+      "step": 1170
+    },
+    {
+      "epoch": 1.9869473684210526,
+      "grad_norm": 0.11921833455562592,
+      "learning_rate": 3.103570452354402e-07,
+      "loss": 0.40110602378845217,
+      "step": 1180
+    },
+    {
+      "epoch": 2.0033684210526315,
+      "grad_norm": 0.0832003727555275,
+      "learning_rate": 3.013271343972613e-07,
+      "loss": 0.3981154918670654,
+      "step": 1190
+    },
+    {
+      "epoch": 2.0202105263157897,
+      "grad_norm": 0.09975888580083847,
+      "learning_rate": 2.9237352932500046e-07,
+      "loss": 0.3726134061813354,
+      "step": 1200
+    },
+    {
+      "epoch": 2.0370526315789474,
+      "grad_norm": 0.14600081741809845,
+      "learning_rate": 2.8349966889638615e-07,
+      "loss": 0.42558698654174804,
+      "step": 1210
+    },
+    {
+      "epoch": 2.053894736842105,
+      "grad_norm": 0.10875770449638367,
+      "learning_rate": 2.747089613610278e-07,
+      "loss": 0.3682931184768677,
+      "step": 1220
+    },
+    {
+      "epoch": 2.070736842105263,
+      "grad_norm": 0.10050549358129501,
+      "learning_rate": 2.66004783031385e-07,
+      "loss": 0.3756644487380981,
+      "step": 1230
+    },
+    {
+      "epoch": 2.087578947368421,
+      "grad_norm": 0.08914914727210999,
+      "learning_rate": 2.573904769860009e-07,
+      "loss": 0.3804330825805664,
+      "step": 1240
+    },
+    {
+      "epoch": 2.104421052631579,
+      "grad_norm": 0.08296852558851242,
+      "learning_rate": 2.488693517855016e-07,
+      "loss": 0.3978404521942139,
+      "step": 1250
+    },
+    {
+      "epoch": 2.1212631578947367,
+      "grad_norm": 0.13885149359703064,
+      "learning_rate": 2.404446802018533e-07,
+      "loss": 0.3935218334197998,
+      "step": 1260
+    },
+    {
+      "epoch": 2.138105263157895,
+      "grad_norm": 0.13195137679576874,
+      "learning_rate": 2.3211969796136305e-07,
+      "loss": 0.42966952323913576,
+      "step": 1270
+    },
+    {
+      "epoch": 2.1549473684210527,
+      "grad_norm": 0.13367892801761627,
+      "learning_rate": 2.2389760250191038e-07,
+      "loss": 0.3679579019546509,
+      "step": 1280
+    },
+    {
+      "epoch": 2.1717894736842105,
+      "grad_norm": 0.1288345605134964,
+      "learning_rate": 2.1578155174488343e-07,
+      "loss": 0.41324810981750487,
+      "step": 1290
+    },
+    {
+      "epoch": 2.1886315789473683,
+      "grad_norm": 0.09626021236181259,
+      "learning_rate": 2.0777466288229205e-07,
+      "loss": 0.40120248794555663,
+      "step": 1300
+    },
+    {
+      "epoch": 2.2054736842105265,
+      "grad_norm": 0.10264381766319275,
+      "learning_rate": 1.9988001117952485e-07,
+      "loss": 0.3501007080078125,
+      "step": 1310
+    },
+    {
+      "epoch": 2.2223157894736842,
+      "grad_norm": 0.09031466394662857,
+      "learning_rate": 1.9210062879420973e-07,
+      "loss": 0.3839429378509521,
+      "step": 1320
+    },
+    {
+      "epoch": 2.239157894736842,
+      "grad_norm": 0.12686079740524292,
+      "learning_rate": 1.8443950361162957e-07,
+      "loss": 0.4338528156280518,
+      "step": 1330
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 0.12199016660451889,
+      "learning_rate": 1.7689957809714346e-07,
+      "loss": 0.39229888916015626,
+      "step": 1340
+    },
+    {
+      "epoch": 2.272842105263158,
+      "grad_norm": 0.12029567360877991,
+      "learning_rate": 1.694837481660525e-07,
+      "loss": 0.38006880283355715,
+      "step": 1350
+    },
+    {
+      "epoch": 2.2896842105263158,
+      "grad_norm": 0.08686309307813644,
+      "learning_rate": 1.6219486207134313e-07,
+      "loss": 0.3808159589767456,
+      "step": 1360
+    },
+    {
+      "epoch": 2.3065263157894735,
+      "grad_norm": 0.10810462385416031,
+      "learning_rate": 1.5503571930973785e-07,
+      "loss": 0.401824426651001,
+      "step": 1370
+    },
+    {
+      "epoch": 2.3233684210526317,
+      "grad_norm": 0.10281873494386673,
+      "learning_rate": 1.480090695464723e-07,
+      "loss": 0.40149493217468263,
+      "step": 1380
+    },
+    {
+      "epoch": 2.3402105263157895,
+      "grad_norm": 0.09503985196352005,
+      "learning_rate": 1.4111761155920975e-07,
+      "loss": 0.38567726612091063,
+      "step": 1390
+    },
+    {
+      "epoch": 2.3570526315789473,
+      "grad_norm": 0.10420782119035721,
+      "learning_rate": 1.3436399220150212e-07,
+      "loss": 0.3759742736816406,
+      "step": 1400
+    },
+    {
+      "epoch": 2.3738947368421055,
+      "grad_norm": 0.10681115835905075,
+      "learning_rate": 1.2775080538619347e-07,
+      "loss": 0.3913698196411133,
+      "step": 1410
+    },
+    {
+      "epoch": 2.3907368421052633,
+      "grad_norm": 0.10323983430862427,
+      "learning_rate": 1.2128059108915595e-07,
+      "loss": 0.39077584743499755,
+      "step": 1420
+    },
+    {
+      "epoch": 2.407578947368421,
+      "grad_norm": 0.09566064178943634,
+      "learning_rate": 1.1495583437374263e-07,
+      "loss": 0.39895172119140626,
+      "step": 1430
+    },
+    {
+      "epoch": 2.424421052631579,
+      "grad_norm": 0.13018426299095154,
+      "learning_rate": 1.0877896443633117e-07,
+      "loss": 0.38982129096984863,
+      "step": 1440
+    },
+    {
+      "epoch": 2.441263157894737,
+      "grad_norm": 0.10760781168937683,
+      "learning_rate": 1.0275235367332347e-07,
+      "loss": 0.3756714344024658,
+      "step": 1450
+    },
+    {
+      "epoch": 2.458105263157895,
+      "grad_norm": 0.11606904864311218,
+      "learning_rate": 9.687831676996238e-08,
+      "loss": 0.37858171463012696,
+      "step": 1460
+    },
+    {
+      "epoch": 2.4749473684210526,
+      "grad_norm": 0.12957172095775604,
+      "learning_rate": 9.115910981131336e-08,
+      "loss": 0.40050196647644043,
+      "step": 1470
+    },
+    {
+      "epoch": 2.4917894736842103,
+      "grad_norm": 0.11186131089925766,
+      "learning_rate": 8.559692941575231e-08,
+      "loss": 0.3684133291244507,
+      "step": 1480
+    },
+    {
+      "epoch": 2.5086315789473685,
+      "grad_norm": 0.13279542326927185,
+      "learning_rate": 8.019391189129466e-08,
+      "loss": 0.3452518224716187,
+      "step": 1490
+    },
+    {
+      "epoch": 2.5254736842105263,
+      "grad_norm": 0.09041756391525269,
+      "learning_rate": 7.495213241508786e-08,
+      "loss": 0.36301617622375487,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1782,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.742094440984576e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1600/README.md b/checkpoint-1600/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..cfd546f8318a3a2985d8a7e4c881e529305dd807
--- /dev/null
+++ b/checkpoint-1600/README.md
@@ -0,0 +1,208 @@
+---
+base_model: google/gemma-3-1b-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:google/gemma-3-1b-it
+- llama-factory
+- 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 0.18.1
\ No newline at end of file
diff --git a/checkpoint-1600/adapter_config.json b/checkpoint-1600/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..b7033a591cf40ea5b43aae7a6f56ed6a65d3f80c
--- /dev/null
+++ b/checkpoint-1600/adapter_config.json
@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-1b-it",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj",
+    "q_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/checkpoint-1600/chat_template.jinja b/checkpoint-1600/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..1117055ab8e8c90e1b200be00cddb78943616d9e
--- /dev/null
+++ b/checkpoint-1600/chat_template.jinja
@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}
diff --git a/checkpoint-1600/optimizer.pt b/checkpoint-1600/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b5e0d9d3c5804a822c00c5c0f235042867e2f958
--- /dev/null
+++ b/checkpoint-1600/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00e4e0c0ee17f488ebea76d4be58523084a7d82aa17ad91dc55431395752764d
+size 52494119
diff --git a/checkpoint-1600/rng_state.pth b/checkpoint-1600/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1826de380346347959c134a28296793346778937
--- /dev/null
+++ b/checkpoint-1600/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:926b6d8daef5503279afe9a92b1410c52f82ece90d2b637e440d4677105ea8ef
+size 14645
diff --git a/checkpoint-1600/scheduler.pt b/checkpoint-1600/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9f2cade7380b4223e7988f068d9a8353bfba6fcf
--- /dev/null
+++ b/checkpoint-1600/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09e8b402b77d901f345c2fba01c7ef96ce60173c9b1b1245be32661c8e0cee5a
+size 1465
diff --git a/checkpoint-1600/tokenizer_config.json b/checkpoint-1600/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d83f12eef5a7d73283047b2f05c1ffdd6346556a
--- /dev/null
+++ b/checkpoint-1600/tokenizer_config.json
@@ -0,0 +1,26 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<end_of_turn>",
+  "image_token": "<image_soft_token>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "processor_class": "Gemma3Processor",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-1600/trainer_state.json b/checkpoint-1600/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..a36d15f53c916e80b932004887305bd7ec323881
--- /dev/null
+++ b/checkpoint-1600/trainer_state.json
@@ -0,0 +1,1154 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.6938947368421053,
+  "eval_steps": 100,
+  "global_step": 1600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016842105263157894,
+      "grad_norm": 0.21757784485816956,
+      "learning_rate": 5.027932960893855e-08,
+      "loss": 0.7252199172973632,
+      "step": 10
+    },
+    {
+      "epoch": 0.03368421052631579,
+      "grad_norm": 0.2456846386194229,
+      "learning_rate": 1.0614525139664805e-07,
+      "loss": 0.6507451057434082,
+      "step": 20
+    },
+    {
+      "epoch": 0.05052631578947368,
+      "grad_norm": 0.20819272100925446,
+      "learning_rate": 1.6201117318435754e-07,
+      "loss": 0.7381344795227051,
+      "step": 30
+    },
+    {
+      "epoch": 0.06736842105263158,
+      "grad_norm": 0.26373574137687683,
+      "learning_rate": 2.17877094972067e-07,
+      "loss": 0.7012194156646728,
+      "step": 40
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 0.2081507444381714,
+      "learning_rate": 2.7374301675977653e-07,
+      "loss": 0.6083873748779297,
+      "step": 50
+    },
+    {
+      "epoch": 0.10105263157894737,
+      "grad_norm": 0.2091236114501953,
+      "learning_rate": 3.29608938547486e-07,
+      "loss": 0.6980491638183594,
+      "step": 60
+    },
+    {
+      "epoch": 0.11789473684210526,
+      "grad_norm": 0.20970331132411957,
+      "learning_rate": 3.8547486033519547e-07,
+      "loss": 0.708641767501831,
+      "step": 70
+    },
+    {
+      "epoch": 0.13473684210526315,
+      "grad_norm": 0.18810197710990906,
+      "learning_rate": 4.41340782122905e-07,
+      "loss": 0.6742453098297119,
+      "step": 80
+    },
+    {
+      "epoch": 0.15157894736842106,
+      "grad_norm": 0.20251069962978363,
+      "learning_rate": 4.972067039106145e-07,
+      "loss": 0.6590609550476074,
+      "step": 90
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "grad_norm": 0.2644217908382416,
+      "learning_rate": 5.53072625698324e-07,
+      "loss": 0.704926872253418,
+      "step": 100
+    },
+    {
+      "epoch": 0.18526315789473685,
+      "grad_norm": 0.23766489326953888,
+      "learning_rate": 6.089385474860335e-07,
+      "loss": 0.7445036888122558,
+      "step": 110
+    },
+    {
+      "epoch": 0.20210526315789473,
+      "grad_norm": 0.27427056431770325,
+      "learning_rate": 6.64804469273743e-07,
+      "loss": 0.7476531028747558,
+      "step": 120
+    },
+    {
+      "epoch": 0.21894736842105264,
+      "grad_norm": 0.3208928406238556,
+      "learning_rate": 7.206703910614524e-07,
+      "loss": 0.7291872501373291,
+      "step": 130
+    },
+    {
+      "epoch": 0.23578947368421052,
+      "grad_norm": 0.3123615086078644,
+      "learning_rate": 7.76536312849162e-07,
+      "loss": 0.721175241470337,
+      "step": 140
+    },
+    {
+      "epoch": 0.25263157894736843,
+      "grad_norm": 0.26158222556114197,
+      "learning_rate": 8.324022346368714e-07,
+      "loss": 0.7556095600128174,
+      "step": 150
+    },
+    {
+      "epoch": 0.2694736842105263,
+      "grad_norm": 0.2592650353908539,
+      "learning_rate": 8.88268156424581e-07,
+      "loss": 0.7328392505645752,
+      "step": 160
+    },
+    {
+      "epoch": 0.2863157894736842,
+      "grad_norm": 0.24533776938915253,
+      "learning_rate": 9.441340782122904e-07,
+      "loss": 0.6990129470825195,
+      "step": 170
+    },
+    {
+      "epoch": 0.3031578947368421,
+      "grad_norm": 0.23409004509449005,
+      "learning_rate": 1e-06,
+      "loss": 0.6694639205932618,
+      "step": 180
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.3267499506473541,
+      "learning_rate": 9.999039806396227e-07,
+      "loss": 0.7123252868652343,
+      "step": 190
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "grad_norm": 0.2115064263343811,
+      "learning_rate": 9.996159594373611e-07,
+      "loss": 0.6858412742614746,
+      "step": 200
+    },
+    {
+      "epoch": 0.35368421052631577,
+      "grad_norm": 0.26226580142974854,
+      "learning_rate": 9.991360470156615e-07,
+      "loss": 0.6541069507598877,
+      "step": 210
+    },
+    {
+      "epoch": 0.3705263157894737,
+      "grad_norm": 0.24552594125270844,
+      "learning_rate": 9.984644276980594e-07,
+      "loss": 0.6506116390228271,
+      "step": 220
+    },
+    {
+      "epoch": 0.3873684210526316,
+      "grad_norm": 0.25084301829338074,
+      "learning_rate": 9.976013594383835e-07,
+      "loss": 0.6540626049041748,
+      "step": 230
+    },
+    {
+      "epoch": 0.40421052631578946,
+      "grad_norm": 0.34244054555892944,
+      "learning_rate": 9.965471737216833e-07,
+      "loss": 0.6737770557403564,
+      "step": 240
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.34752583503723145,
+      "learning_rate": 9.953022754369114e-07,
+      "loss": 0.6755708217620849,
+      "step": 250
+    },
+    {
+      "epoch": 0.4378947368421053,
+      "grad_norm": 0.31017956137657166,
+      "learning_rate": 9.938671427214158e-07,
+      "loss": 0.6578442573547363,
+      "step": 260
+    },
+    {
+      "epoch": 0.45473684210526316,
+      "grad_norm": 0.21509627997875214,
+      "learning_rate": 9.922423267772986e-07,
+      "loss": 0.639409875869751,
+      "step": 270
+    },
+    {
+      "epoch": 0.47157894736842104,
+      "grad_norm": 0.3022947609424591,
+      "learning_rate": 9.904284516597102e-07,
+      "loss": 0.5995691776275635,
+      "step": 280
+    },
+    {
+      "epoch": 0.4884210526315789,
+      "grad_norm": 0.3367304801940918,
+      "learning_rate": 9.884262140371648e-07,
+      "loss": 0.5898309707641601,
+      "step": 290
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "grad_norm": 0.294842928647995,
+      "learning_rate": 9.862363829239662e-07,
+      "loss": 0.6371779441833496,
+      "step": 300
+    },
+    {
+      "epoch": 0.5221052631578947,
+      "grad_norm": 0.25171560049057007,
+      "learning_rate": 9.838597993848456e-07,
+      "loss": 0.5795581817626954,
+      "step": 310
+    },
+    {
+      "epoch": 0.5389473684210526,
+      "grad_norm": 0.2818540036678314,
+      "learning_rate": 9.81297376211928e-07,
+      "loss": 0.5668415546417236,
+      "step": 320
+    },
+    {
+      "epoch": 0.5557894736842105,
+      "grad_norm": 0.32951900362968445,
+      "learning_rate": 9.785500975741498e-07,
+      "loss": 0.5933257102966308,
+      "step": 330
+    },
+    {
+      "epoch": 0.5726315789473684,
+      "grad_norm": 0.2763514518737793,
+      "learning_rate": 9.756190186392615e-07,
+      "loss": 0.5574678897857666,
+      "step": 340
+    },
+    {
+      "epoch": 0.5894736842105263,
+      "grad_norm": 0.3070182204246521,
+      "learning_rate": 9.725052651685612e-07,
+      "loss": 0.5532425880432129,
+      "step": 350
+    },
+    {
+      "epoch": 0.6063157894736843,
+      "grad_norm": 0.2079988420009613,
+      "learning_rate": 9.692100330845153e-07,
+      "loss": 0.5613389492034913,
+      "step": 360
+    },
+    {
+      "epoch": 0.6231578947368421,
+      "grad_norm": 0.282924622297287,
+      "learning_rate": 9.657345880114318e-07,
+      "loss": 0.5131485939025879,
+      "step": 370
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.20901450514793396,
+      "learning_rate": 9.620802647893623e-07,
+      "loss": 0.6279027462005615,
+      "step": 380
+    },
+    {
+      "epoch": 0.6568421052631579,
+      "grad_norm": 0.2637634575366974,
+      "learning_rate": 9.58248466961421e-07,
+      "loss": 0.5403085231781006,
+      "step": 390
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "grad_norm": 0.29078468680381775,
+      "learning_rate": 9.542406662347137e-07,
+      "loss": 0.5678809642791748,
+      "step": 400
+    },
+    {
+      "epoch": 0.6905263157894737,
+      "grad_norm": 0.2865101397037506,
+      "learning_rate": 9.500584019150895e-07,
+      "loss": 0.5479135036468505,
+      "step": 410
+    },
+    {
+      "epoch": 0.7073684210526315,
+      "grad_norm": 0.22857311367988586,
+      "learning_rate": 9.45703280315928e-07,
+      "loss": 0.5604462623596191,
+      "step": 420
+    },
+    {
+      "epoch": 0.7242105263157895,
+      "grad_norm": 0.23971959948539734,
+      "learning_rate": 9.411769741411903e-07,
+      "loss": 0.4704423427581787,
+      "step": 430
+    },
+    {
+      "epoch": 0.7410526315789474,
+      "grad_norm": 0.29793378710746765,
+      "learning_rate": 9.364812218429721e-07,
+      "loss": 0.560968017578125,
+      "step": 440
+    },
+    {
+      "epoch": 0.7578947368421053,
+      "grad_norm": 0.2236040234565735,
+      "learning_rate": 9.316178269538014e-07,
+      "loss": 0.5088452816009521,
+      "step": 450
+    },
+    {
+      "epoch": 0.7747368421052632,
+      "grad_norm": 0.22047854959964752,
+      "learning_rate": 9.265886573939446e-07,
+      "loss": 0.5030550956726074,
+      "step": 460
+    },
+    {
+      "epoch": 0.791578947368421,
+      "grad_norm": 0.2273361086845398,
+      "learning_rate": 9.213956447539792e-07,
+      "loss": 0.46353440284729003,
+      "step": 470
+    },
+    {
+      "epoch": 0.8084210526315789,
+      "grad_norm": 0.2170158326625824,
+      "learning_rate": 9.160407835529136e-07,
+      "loss": 0.49871411323547366,
+      "step": 480
+    },
+    {
+      "epoch": 0.8252631578947368,
+      "grad_norm": 0.19333498179912567,
+      "learning_rate": 9.105261304721375e-07,
+      "loss": 0.4416178226470947,
+      "step": 490
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.18490085005760193,
+      "learning_rate": 9.048538035654969e-07,
+      "loss": 0.39783194065093996,
+      "step": 500
+    },
+    {
+      "epoch": 0.8589473684210527,
+      "grad_norm": 0.22122648358345032,
+      "learning_rate": 8.990259814457977e-07,
+      "loss": 0.4318229198455811,
+      "step": 510
+    },
+    {
+      "epoch": 0.8757894736842106,
+      "grad_norm": 0.17448943853378296,
+      "learning_rate": 8.930449024480491e-07,
+      "loss": 0.42445807456970214,
+      "step": 520
+    },
+    {
+      "epoch": 0.8926315789473684,
+      "grad_norm": 0.18165165185928345,
+      "learning_rate": 8.8691286376977e-07,
+      "loss": 0.46429901123046874,
+      "step": 530
+    },
+    {
+      "epoch": 0.9094736842105263,
+      "grad_norm": 0.16785287857055664,
+      "learning_rate": 8.806322205886873e-07,
+      "loss": 0.3975703239440918,
+      "step": 540
+    },
+    {
+      "epoch": 0.9263157894736842,
+      "grad_norm": 0.1613738089799881,
+      "learning_rate": 8.74205385158165e-07,
+      "loss": 0.4458911418914795,
+      "step": 550
+    },
+    {
+      "epoch": 0.9431578947368421,
+      "grad_norm": 0.15376177430152893,
+      "learning_rate": 8.676348258807121e-07,
+      "loss": 0.45571184158325195,
+      "step": 560
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.14966322481632233,
+      "learning_rate": 8.609230663599254e-07,
+      "loss": 0.4039600372314453,
+      "step": 570
+    },
+    {
+      "epoch": 0.9768421052631578,
+      "grad_norm": 0.16819055378437042,
+      "learning_rate": 8.540726844312294e-07,
+      "loss": 0.4382494926452637,
+      "step": 580
+    },
+    {
+      "epoch": 0.9936842105263158,
+      "grad_norm": 0.16405776143074036,
+      "learning_rate": 8.470863111717889e-07,
+      "loss": 0.4306180477142334,
+      "step": 590
+    },
+    {
+      "epoch": 1.0101052631578948,
+      "grad_norm": 0.18503950536251068,
+      "learning_rate": 8.399666298899706e-07,
+      "loss": 0.39806089401245115,
+      "step": 600
+    },
+    {
+      "epoch": 1.0269473684210526,
+      "grad_norm": 0.14375492930412292,
+      "learning_rate": 8.327163750947457e-07,
+      "loss": 0.4271697044372559,
+      "step": 610
+    },
+    {
+      "epoch": 1.0437894736842106,
+      "grad_norm": 0.1412728875875473,
+      "learning_rate": 8.253383314454263e-07,
+      "loss": 0.3939049243927002,
+      "step": 620
+    },
+    {
+      "epoch": 1.0606315789473684,
+      "grad_norm": 0.20121850073337555,
+      "learning_rate": 8.178353326821404e-07,
+      "loss": 0.43197131156921387,
+      "step": 630
+    },
+    {
+      "epoch": 1.0774736842105264,
+      "grad_norm": 0.17767728865146637,
+      "learning_rate": 8.102102605374566e-07,
+      "loss": 0.437807559967041,
+      "step": 640
+    },
+    {
+      "epoch": 1.0943157894736841,
+      "grad_norm": 0.1498359888792038,
+      "learning_rate": 8.024660436295759e-07,
+      "loss": 0.38409013748168946,
+      "step": 650
+    },
+    {
+      "epoch": 1.1111578947368421,
+      "grad_norm": 0.15958793461322784,
+      "learning_rate": 7.946056563375145e-07,
+      "loss": 0.4204962730407715,
+      "step": 660
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.157291978597641,
+      "learning_rate": 7.866321176587128e-07,
+      "loss": 0.42113161087036133,
+      "step": 670
+    },
+    {
+      "epoch": 1.1448421052631579,
+      "grad_norm": 0.14119838178157806,
+      "learning_rate": 7.785484900495065e-07,
+      "loss": 0.4151731491088867,
+      "step": 680
+    },
+    {
+      "epoch": 1.1616842105263159,
+      "grad_norm": 0.1296525001525879,
+      "learning_rate": 7.703578782489058e-07,
+      "loss": 0.38312902450561526,
+      "step": 690
+    },
+    {
+      "epoch": 1.1785263157894736,
+      "grad_norm": 0.13671696186065674,
+      "learning_rate": 7.620634280861351e-07,
+      "loss": 0.42612557411193847,
+      "step": 700
+    },
+    {
+      "epoch": 1.1953684210526316,
+      "grad_norm": 0.15196114778518677,
+      "learning_rate": 7.536683252723923e-07,
+      "loss": 0.4306772708892822,
+      "step": 710
+    },
+    {
+      "epoch": 1.2122105263157894,
+      "grad_norm": 0.1136903315782547,
+      "learning_rate": 7.451757941772868e-07,
+      "loss": 0.38483757972717286,
+      "step": 720
+    },
+    {
+      "epoch": 1.2290526315789474,
+      "grad_norm": 0.12378744781017303,
+      "learning_rate": 7.365890965904337e-07,
+      "loss": 0.4030342102050781,
+      "step": 730
+    },
+    {
+      "epoch": 1.2458947368421052,
+      "grad_norm": 0.1265542209148407,
+      "learning_rate": 7.279115304686733e-07,
+      "loss": 0.4091166973114014,
+      "step": 740
+    },
+    {
+      "epoch": 1.2627368421052632,
+      "grad_norm": 0.11647409200668335,
+      "learning_rate": 7.191464286694e-07,
+      "loss": 0.41426806449890136,
+      "step": 750
+    },
+    {
+      "epoch": 1.279578947368421,
+      "grad_norm": 0.11192695051431656,
+      "learning_rate": 7.102971576704875e-07,
+      "loss": 0.38181486129760744,
+      "step": 760
+    },
+    {
+      "epoch": 1.296421052631579,
+      "grad_norm": 0.14947861433029175,
+      "learning_rate": 7.013671162773003e-07,
+      "loss": 0.39824953079223635,
+      "step": 770
+    },
+    {
+      "epoch": 1.313263157894737,
+      "grad_norm": 0.11269424855709076,
+      "learning_rate": 6.923597343172891e-07,
+      "loss": 0.40348024368286134,
+      "step": 780
+    },
+    {
+      "epoch": 1.3301052631578947,
+      "grad_norm": 0.3742346167564392,
+      "learning_rate": 6.83278471322672e-07,
+      "loss": 0.38022048473358155,
+      "step": 790
+    },
+    {
+      "epoch": 1.3469473684210527,
+      "grad_norm": 0.1310902237892151,
+      "learning_rate": 6.741268152017057e-07,
+      "loss": 0.42791285514831545,
+      "step": 800
+    },
+    {
+      "epoch": 1.3637894736842107,
+      "grad_norm": 0.1692703813314438,
+      "learning_rate": 6.649082808990585e-07,
+      "loss": 0.4263493061065674,
+      "step": 810
+    },
+    {
+      "epoch": 1.3806315789473684,
+      "grad_norm": 0.1279117316007614,
+      "learning_rate": 6.556264090457998e-07,
+      "loss": 0.37379777431488037,
+      "step": 820
+    },
+    {
+      "epoch": 1.3974736842105262,
+      "grad_norm": 0.12949039041996002,
+      "learning_rate": 6.462847645995237e-07,
+      "loss": 0.38636391162872313,
+      "step": 830
+    },
+    {
+      "epoch": 1.4143157894736842,
+      "grad_norm": 0.10221126675605774,
+      "learning_rate": 6.368869354751284e-07,
+      "loss": 0.408221435546875,
+      "step": 840
+    },
+    {
+      "epoch": 1.4311578947368422,
+      "grad_norm": 0.11505889147520065,
+      "learning_rate": 6.274365311667797e-07,
+      "loss": 0.3951406717300415,
+      "step": 850
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.11054962873458862,
+      "learning_rate": 6.179371813615859e-07,
+      "loss": 0.3732129096984863,
+      "step": 860
+    },
+    {
+      "epoch": 1.464842105263158,
+      "grad_norm": 0.10150120407342911,
+      "learning_rate": 6.083925345455158e-07,
+      "loss": 0.38601529598236084,
+      "step": 870
+    },
+    {
+      "epoch": 1.4816842105263157,
+      "grad_norm": 0.12239400297403336,
+      "learning_rate": 5.988062566020986e-07,
+      "loss": 0.3859985828399658,
+      "step": 880
+    },
+    {
+      "epoch": 1.4985263157894737,
+      "grad_norm": 0.15801067650318146,
+      "learning_rate": 5.891820294044408e-07,
+      "loss": 0.3983951807022095,
+      "step": 890
+    },
+    {
+      "epoch": 1.5153684210526315,
+      "grad_norm": 0.10104545950889587,
+      "learning_rate": 5.795235494011007e-07,
+      "loss": 0.41107850074768065,
+      "step": 900
+    },
+    {
+      "epoch": 1.5322105263157895,
+      "grad_norm": 0.1378099024295807,
+      "learning_rate": 5.698345261963668e-07,
+      "loss": 0.3708331823348999,
+      "step": 910
+    },
+    {
+      "epoch": 1.5490526315789475,
+      "grad_norm": 0.12936057150363922,
+      "learning_rate": 5.601186811254825e-07,
+      "loss": 0.387884521484375,
+      "step": 920
+    },
+    {
+      "epoch": 1.5658947368421052,
+      "grad_norm": 0.12379129230976105,
+      "learning_rate": 5.503797458253646e-07,
+      "loss": 0.43808717727661134,
+      "step": 930
+    },
+    {
+      "epoch": 1.582736842105263,
+      "grad_norm": 0.12017743289470673,
+      "learning_rate": 5.406214608013662e-07,
+      "loss": 0.41345391273498533,
+      "step": 940
+    },
+    {
+      "epoch": 1.5995789473684212,
+      "grad_norm": 0.1095535159111023,
+      "learning_rate": 5.308475739906328e-07,
+      "loss": 0.40022664070129393,
+      "step": 950
+    },
+    {
+      "epoch": 1.616421052631579,
+      "grad_norm": 0.13831396400928497,
+      "learning_rate": 5.210618393226045e-07,
+      "loss": 0.3909924983978271,
+      "step": 960
+    },
+    {
+      "epoch": 1.6332631578947368,
+      "grad_norm": 0.10449163615703583,
+      "learning_rate": 5.112680152772156e-07,
+      "loss": 0.37143146991729736,
+      "step": 970
+    },
+    {
+      "epoch": 1.6501052631578947,
+      "grad_norm": 0.11249610036611557,
+      "learning_rate": 5.01469863441348e-07,
+      "loss": 0.38103113174438474,
+      "step": 980
+    },
+    {
+      "epoch": 1.6669473684210527,
+      "grad_norm": 0.13718819618225098,
+      "learning_rate": 4.916711470640907e-07,
+      "loss": 0.4071629524230957,
+      "step": 990
+    },
+    {
+      "epoch": 1.6837894736842105,
+      "grad_norm": 0.10473571717739105,
+      "learning_rate": 4.818756296113595e-07,
+      "loss": 0.417419958114624,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7006315789473683,
+      "grad_norm": 0.10846224427223206,
+      "learning_rate": 4.7208707332043623e-07,
+      "loss": 0.3998772859573364,
+      "step": 1010
+    },
+    {
+      "epoch": 1.7174736842105263,
+      "grad_norm": 0.10248563438653946,
+      "learning_rate": 4.6230923775497714e-07,
+      "loss": 0.38056583404541017,
+      "step": 1020
+    },
+    {
+      "epoch": 1.7343157894736843,
+      "grad_norm": 0.12221980094909668,
+      "learning_rate": 4.5254587836104964e-07,
+      "loss": 0.39371190071105955,
+      "step": 1030
+    },
+    {
+      "epoch": 1.751157894736842,
+      "grad_norm": 0.10641586035490036,
+      "learning_rate": 4.4280074502475017e-07,
+      "loss": 0.4280440330505371,
+      "step": 1040
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.12907131016254425,
+      "learning_rate": 4.3307758063195796e-07,
+      "loss": 0.3791615962982178,
+      "step": 1050
+    },
+    {
+      "epoch": 1.784842105263158,
+      "grad_norm": 0.12383506447076797,
+      "learning_rate": 4.233801196307762e-07,
+      "loss": 0.347782301902771,
+      "step": 1060
+    },
+    {
+      "epoch": 1.8016842105263158,
+      "grad_norm": 0.12547679245471954,
+      "learning_rate": 4.1371208659721536e-07,
+      "loss": 0.38370628356933595,
+      "step": 1070
+    },
+    {
+      "epoch": 1.8185263157894735,
+      "grad_norm": 0.10580642521381378,
+      "learning_rate": 4.0407719480466736e-07,
+      "loss": 0.40404376983642576,
+      "step": 1080
+    },
+    {
+      "epoch": 1.8353684210526315,
+      "grad_norm": 0.1055402085185051,
+      "learning_rate": 3.944791447977213e-07,
+      "loss": 0.4167450428009033,
+      "step": 1090
+    },
+    {
+      "epoch": 1.8522105263157895,
+      "grad_norm": 0.11053823679685593,
+      "learning_rate": 3.849216229708671e-07,
+      "loss": 0.4046513080596924,
+      "step": 1100
+    },
+    {
+      "epoch": 1.8690526315789473,
+      "grad_norm": 0.10185246914625168,
+      "learning_rate": 3.7540830015263526e-07,
+      "loss": 0.39672977924346925,
+      "step": 1110
+    },
+    {
+      "epoch": 1.8858947368421053,
+      "grad_norm": 0.08342823386192322,
+      "learning_rate": 3.6594283019571416e-07,
+      "loss": 0.39356396198272703,
+      "step": 1120
+    },
+    {
+      "epoch": 1.9027368421052633,
+      "grad_norm": 0.11821646988391876,
+      "learning_rate": 3.565288485735874e-07,
+      "loss": 0.42082643508911133,
+      "step": 1130
+    },
+    {
+      "epoch": 1.919578947368421,
+      "grad_norm": 0.1106327474117279,
+      "learning_rate": 3.4716997098423085e-07,
+      "loss": 0.34105117321014405,
+      "step": 1140
+    },
+    {
+      "epoch": 1.9364210526315788,
+      "grad_norm": 0.11533800512552261,
+      "learning_rate": 3.378697919614045e-07,
+      "loss": 0.3924069404602051,
+      "step": 1150
+    },
+    {
+      "epoch": 1.9532631578947368,
+      "grad_norm": 0.1431114822626114,
+      "learning_rate": 3.286318834940729e-07,
+      "loss": 0.3922377586364746,
+      "step": 1160
+    },
+    {
+      "epoch": 1.9701052631578948,
+      "grad_norm": 0.16050194203853607,
+      "learning_rate": 3.1945979365448517e-07,
+      "loss": 0.3745201587677002,
+      "step": 1170
+    },
+    {
+      "epoch": 1.9869473684210526,
+      "grad_norm": 0.11921833455562592,
+      "learning_rate": 3.103570452354402e-07,
+      "loss": 0.40110602378845217,
+      "step": 1180
+    },
+    {
+      "epoch": 2.0033684210526315,
+      "grad_norm": 0.0832003727555275,
+      "learning_rate": 3.013271343972613e-07,
+      "loss": 0.3981154918670654,
+      "step": 1190
+    },
+    {
+      "epoch": 2.0202105263157897,
+      "grad_norm": 0.09975888580083847,
+      "learning_rate": 2.9237352932500046e-07,
+      "loss": 0.3726134061813354,
+      "step": 1200
+    },
+    {
+      "epoch": 2.0370526315789474,
+      "grad_norm": 0.14600081741809845,
+      "learning_rate": 2.8349966889638615e-07,
+      "loss": 0.42558698654174804,
+      "step": 1210
+    },
+    {
+      "epoch": 2.053894736842105,
+      "grad_norm": 0.10875770449638367,
+      "learning_rate": 2.747089613610278e-07,
+      "loss": 0.3682931184768677,
+      "step": 1220
+    },
+    {
+      "epoch": 2.070736842105263,
+      "grad_norm": 0.10050549358129501,
+      "learning_rate": 2.66004783031385e-07,
+      "loss": 0.3756644487380981,
+      "step": 1230
+    },
+    {
+      "epoch": 2.087578947368421,
+      "grad_norm": 0.08914914727210999,
+      "learning_rate": 2.573904769860009e-07,
+      "loss": 0.3804330825805664,
+      "step": 1240
+    },
+    {
+      "epoch": 2.104421052631579,
+      "grad_norm": 0.08296852558851242,
+      "learning_rate": 2.488693517855016e-07,
+      "loss": 0.3978404521942139,
+      "step": 1250
+    },
+    {
+      "epoch": 2.1212631578947367,
+      "grad_norm": 0.13885149359703064,
+      "learning_rate": 2.404446802018533e-07,
+      "loss": 0.3935218334197998,
+      "step": 1260
+    },
+    {
+      "epoch": 2.138105263157895,
+      "grad_norm": 0.13195137679576874,
+      "learning_rate": 2.3211969796136305e-07,
+      "loss": 0.42966952323913576,
+      "step": 1270
+    },
+    {
+      "epoch": 2.1549473684210527,
+      "grad_norm": 0.13367892801761627,
+      "learning_rate": 2.2389760250191038e-07,
+      "loss": 0.3679579019546509,
+      "step": 1280
+    },
+    {
+      "epoch": 2.1717894736842105,
+      "grad_norm": 0.1288345605134964,
+      "learning_rate": 2.1578155174488343e-07,
+      "loss": 0.41324810981750487,
+      "step": 1290
+    },
+    {
+      "epoch": 2.1886315789473683,
+      "grad_norm": 0.09626021236181259,
+      "learning_rate": 2.0777466288229205e-07,
+      "loss": 0.40120248794555663,
+      "step": 1300
+    },
+    {
+      "epoch": 2.2054736842105265,
+      "grad_norm": 0.10264381766319275,
+      "learning_rate": 1.9988001117952485e-07,
+      "loss": 0.3501007080078125,
+      "step": 1310
+    },
+    {
+      "epoch": 2.2223157894736842,
+      "grad_norm": 0.09031466394662857,
+      "learning_rate": 1.9210062879420973e-07,
+      "loss": 0.3839429378509521,
+      "step": 1320
+    },
+    {
+      "epoch": 2.239157894736842,
+      "grad_norm": 0.12686079740524292,
+      "learning_rate": 1.8443950361162957e-07,
+      "loss": 0.4338528156280518,
+      "step": 1330
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 0.12199016660451889,
+      "learning_rate": 1.7689957809714346e-07,
+      "loss": 0.39229888916015626,
+      "step": 1340
+    },
+    {
+      "epoch": 2.272842105263158,
+      "grad_norm": 0.12029567360877991,
+      "learning_rate": 1.694837481660525e-07,
+      "loss": 0.38006880283355715,
+      "step": 1350
+    },
+    {
+      "epoch": 2.2896842105263158,
+      "grad_norm": 0.08686309307813644,
+      "learning_rate": 1.6219486207134313e-07,
+      "loss": 0.3808159589767456,
+      "step": 1360
+    },
+    {
+      "epoch": 2.3065263157894735,
+      "grad_norm": 0.10810462385416031,
+      "learning_rate": 1.5503571930973785e-07,
+      "loss": 0.401824426651001,
+      "step": 1370
+    },
+    {
+      "epoch": 2.3233684210526317,
+      "grad_norm": 0.10281873494386673,
+      "learning_rate": 1.480090695464723e-07,
+      "loss": 0.40149493217468263,
+      "step": 1380
+    },
+    {
+      "epoch": 2.3402105263157895,
+      "grad_norm": 0.09503985196352005,
+      "learning_rate": 1.4111761155920975e-07,
+      "loss": 0.38567726612091063,
+      "step": 1390
+    },
+    {
+      "epoch": 2.3570526315789473,
+      "grad_norm": 0.10420782119035721,
+      "learning_rate": 1.3436399220150212e-07,
+      "loss": 0.3759742736816406,
+      "step": 1400
+    },
+    {
+      "epoch": 2.3738947368421055,
+      "grad_norm": 0.10681115835905075,
+      "learning_rate": 1.2775080538619347e-07,
+      "loss": 0.3913698196411133,
+      "step": 1410
+    },
+    {
+      "epoch": 2.3907368421052633,
+      "grad_norm": 0.10323983430862427,
+      "learning_rate": 1.2128059108915595e-07,
+      "loss": 0.39077584743499755,
+      "step": 1420
+    },
+    {
+      "epoch": 2.407578947368421,
+      "grad_norm": 0.09566064178943634,
+      "learning_rate": 1.1495583437374263e-07,
+      "loss": 0.39895172119140626,
+      "step": 1430
+    },
+    {
+      "epoch": 2.424421052631579,
+      "grad_norm": 0.13018426299095154,
+      "learning_rate": 1.0877896443633117e-07,
+      "loss": 0.38982129096984863,
+      "step": 1440
+    },
+    {
+      "epoch": 2.441263157894737,
+      "grad_norm": 0.10760781168937683,
+      "learning_rate": 1.0275235367332347e-07,
+      "loss": 0.3756714344024658,
+      "step": 1450
+    },
+    {
+      "epoch": 2.458105263157895,
+      "grad_norm": 0.11606904864311218,
+      "learning_rate": 9.687831676996238e-08,
+      "loss": 0.37858171463012696,
+      "step": 1460
+    },
+    {
+      "epoch": 2.4749473684210526,
+      "grad_norm": 0.12957172095775604,
+      "learning_rate": 9.115910981131336e-08,
+      "loss": 0.40050196647644043,
+      "step": 1470
+    },
+    {
+      "epoch": 2.4917894736842103,
+      "grad_norm": 0.11186131089925766,
+      "learning_rate": 8.559692941575231e-08,
+      "loss": 0.3684133291244507,
+      "step": 1480
+    },
+    {
+      "epoch": 2.5086315789473685,
+      "grad_norm": 0.13279542326927185,
+      "learning_rate": 8.019391189129466e-08,
+      "loss": 0.3452518224716187,
+      "step": 1490
+    },
+    {
+      "epoch": 2.5254736842105263,
+      "grad_norm": 0.09041756391525269,
+      "learning_rate": 7.495213241508786e-08,
+      "loss": 0.36301617622375487,
+      "step": 1500
+    },
+    {
+      "epoch": 2.542315789473684,
+      "grad_norm": 0.10033190995454788,
+      "learning_rate": 6.987360423638205e-08,
+      "loss": 0.3706004858016968,
+      "step": 1510
+    },
+    {
+      "epoch": 2.559157894736842,
+      "grad_norm": 0.10681814700365067,
+      "learning_rate": 6.49602779032865e-08,
+      "loss": 0.36011199951171874,
+      "step": 1520
+    },
+    {
+      "epoch": 2.576,
+      "grad_norm": 0.1008416935801506,
+      "learning_rate": 6.02140405136089e-08,
+      "loss": 0.37473766803741454,
+      "step": 1530
+    },
+    {
+      "epoch": 2.592842105263158,
+      "grad_norm": 0.11559010297060013,
+      "learning_rate": 5.5636714990062393e-08,
+      "loss": 0.39232525825500486,
+      "step": 1540
+    },
+    {
+      "epoch": 2.609684210526316,
+      "grad_norm": 0.10601615905761719,
+      "learning_rate": 5.1230059380123034e-08,
+      "loss": 0.34370343685150145,
+      "step": 1550
+    },
+    {
+      "epoch": 2.626526315789474,
+      "grad_norm": 0.11516924202442169,
+      "learning_rate": 4.699576618080331e-08,
+      "loss": 0.39509878158569334,
+      "step": 1560
+    },
+    {
+      "epoch": 2.6433684210526316,
+      "grad_norm": 0.11444627493619919,
+      "learning_rate": 4.293546168860163e-08,
+      "loss": 0.3881126165390015,
+      "step": 1570
+    },
+    {
+      "epoch": 2.6602105263157894,
+      "grad_norm": 0.09985339641571045,
+      "learning_rate": 3.9050705374879086e-08,
+      "loss": 0.34624040126800537,
+      "step": 1580
+    },
+    {
+      "epoch": 2.677052631578947,
+      "grad_norm": 0.10439962148666382,
+      "learning_rate": 3.534298928690166e-08,
+      "loss": 0.35141232013702395,
+      "step": 1590
+    },
+    {
+      "epoch": 2.6938947368421053,
+      "grad_norm": 0.12180087715387344,
+      "learning_rate": 3.181373747477822e-08,
+      "loss": 0.39980330467224123,
+      "step": 1600
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1782,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.925778724822016e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1600/training_args.bin b/checkpoint-1600/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..26362bce38749fb4af3e32947d24cd6a387b57ac
--- /dev/null
+++ b/checkpoint-1600/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e59b6aeffb8563cc09210642a0d080410d061efe9a32399cd1e4a1e0abccb0a
+size 5585
diff --git a/checkpoint-1700/README.md b/checkpoint-1700/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..cfd546f8318a3a2985d8a7e4c881e529305dd807
--- /dev/null
+++ b/checkpoint-1700/README.md
@@ -0,0 +1,208 @@
+---
+base_model: google/gemma-3-1b-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:google/gemma-3-1b-it
+- llama-factory
+- 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 0.18.1
\ No newline at end of file
diff --git a/checkpoint-1700/adapter_config.json b/checkpoint-1700/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..b7033a591cf40ea5b43aae7a6f56ed6a65d3f80c
--- /dev/null
+++ b/checkpoint-1700/adapter_config.json
@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-1b-it",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj",
+    "q_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/checkpoint-1700/chat_template.jinja b/checkpoint-1700/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..1117055ab8e8c90e1b200be00cddb78943616d9e
--- /dev/null
+++ b/checkpoint-1700/chat_template.jinja
@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}
diff --git a/checkpoint-1700/optimizer.pt b/checkpoint-1700/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..20867cf71da975c082519afa875726f5e86b5153
--- /dev/null
+++ b/checkpoint-1700/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c0bcdfe6b227477259d00ef78e6870fb90e1f42b41a69b2cc4d605d31c60db6
+size 52494119
diff --git a/checkpoint-1700/tokenizer_config.json b/checkpoint-1700/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d83f12eef5a7d73283047b2f05c1ffdd6346556a
--- /dev/null
+++ b/checkpoint-1700/tokenizer_config.json
@@ -0,0 +1,26 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<end_of_turn>",
+  "image_token": "<image_soft_token>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "processor_class": "Gemma3Processor",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-1700/trainer_state.json b/checkpoint-1700/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..b29d264bffbca24e197e2dfd14ae85f5d42b16b5
--- /dev/null
+++ b/checkpoint-1700/trainer_state.json
@@ -0,0 +1,1224 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.8623157894736844,
+  "eval_steps": 100,
+  "global_step": 1700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016842105263157894,
+      "grad_norm": 0.21757784485816956,
+      "learning_rate": 5.027932960893855e-08,
+      "loss": 0.7252199172973632,
+      "step": 10
+    },
+    {
+      "epoch": 0.03368421052631579,
+      "grad_norm": 0.2456846386194229,
+      "learning_rate": 1.0614525139664805e-07,
+      "loss": 0.6507451057434082,
+      "step": 20
+    },
+    {
+      "epoch": 0.05052631578947368,
+      "grad_norm": 0.20819272100925446,
+      "learning_rate": 1.6201117318435754e-07,
+      "loss": 0.7381344795227051,
+      "step": 30
+    },
+    {
+      "epoch": 0.06736842105263158,
+      "grad_norm": 0.26373574137687683,
+      "learning_rate": 2.17877094972067e-07,
+      "loss": 0.7012194156646728,
+      "step": 40
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 0.2081507444381714,
+      "learning_rate": 2.7374301675977653e-07,
+      "loss": 0.6083873748779297,
+      "step": 50
+    },
+    {
+      "epoch": 0.10105263157894737,
+      "grad_norm": 0.2091236114501953,
+      "learning_rate": 3.29608938547486e-07,
+      "loss": 0.6980491638183594,
+      "step": 60
+    },
+    {
+      "epoch": 0.11789473684210526,
+      "grad_norm": 0.20970331132411957,
+      "learning_rate": 3.8547486033519547e-07,
+      "loss": 0.708641767501831,
+      "step": 70
+    },
+    {
+      "epoch": 0.13473684210526315,
+      "grad_norm": 0.18810197710990906,
+      "learning_rate": 4.41340782122905e-07,
+      "loss": 0.6742453098297119,
+      "step": 80
+    },
+    {
+      "epoch": 0.15157894736842106,
+      "grad_norm": 0.20251069962978363,
+      "learning_rate": 4.972067039106145e-07,
+      "loss": 0.6590609550476074,
+      "step": 90
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "grad_norm": 0.2644217908382416,
+      "learning_rate": 5.53072625698324e-07,
+      "loss": 0.704926872253418,
+      "step": 100
+    },
+    {
+      "epoch": 0.18526315789473685,
+      "grad_norm": 0.23766489326953888,
+      "learning_rate": 6.089385474860335e-07,
+      "loss": 0.7445036888122558,
+      "step": 110
+    },
+    {
+      "epoch": 0.20210526315789473,
+      "grad_norm": 0.27427056431770325,
+      "learning_rate": 6.64804469273743e-07,
+      "loss": 0.7476531028747558,
+      "step": 120
+    },
+    {
+      "epoch": 0.21894736842105264,
+      "grad_norm": 0.3208928406238556,
+      "learning_rate": 7.206703910614524e-07,
+      "loss": 0.7291872501373291,
+      "step": 130
+    },
+    {
+      "epoch": 0.23578947368421052,
+      "grad_norm": 0.3123615086078644,
+      "learning_rate": 7.76536312849162e-07,
+      "loss": 0.721175241470337,
+      "step": 140
+    },
+    {
+      "epoch": 0.25263157894736843,
+      "grad_norm": 0.26158222556114197,
+      "learning_rate": 8.324022346368714e-07,
+      "loss": 0.7556095600128174,
+      "step": 150
+    },
+    {
+      "epoch": 0.2694736842105263,
+      "grad_norm": 0.2592650353908539,
+      "learning_rate": 8.88268156424581e-07,
+      "loss": 0.7328392505645752,
+      "step": 160
+    },
+    {
+      "epoch": 0.2863157894736842,
+      "grad_norm": 0.24533776938915253,
+      "learning_rate": 9.441340782122904e-07,
+      "loss": 0.6990129470825195,
+      "step": 170
+    },
+    {
+      "epoch": 0.3031578947368421,
+      "grad_norm": 0.23409004509449005,
+      "learning_rate": 1e-06,
+      "loss": 0.6694639205932618,
+      "step": 180
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.3267499506473541,
+      "learning_rate": 9.999039806396227e-07,
+      "loss": 0.7123252868652343,
+      "step": 190
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "grad_norm": 0.2115064263343811,
+      "learning_rate": 9.996159594373611e-07,
+      "loss": 0.6858412742614746,
+      "step": 200
+    },
+    {
+      "epoch": 0.35368421052631577,
+      "grad_norm": 0.26226580142974854,
+      "learning_rate": 9.991360470156615e-07,
+      "loss": 0.6541069507598877,
+      "step": 210
+    },
+    {
+      "epoch": 0.3705263157894737,
+      "grad_norm": 0.24552594125270844,
+      "learning_rate": 9.984644276980594e-07,
+      "loss": 0.6506116390228271,
+      "step": 220
+    },
+    {
+      "epoch": 0.3873684210526316,
+      "grad_norm": 0.25084301829338074,
+      "learning_rate": 9.976013594383835e-07,
+      "loss": 0.6540626049041748,
+      "step": 230
+    },
+    {
+      "epoch": 0.40421052631578946,
+      "grad_norm": 0.34244054555892944,
+      "learning_rate": 9.965471737216833e-07,
+      "loss": 0.6737770557403564,
+      "step": 240
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.34752583503723145,
+      "learning_rate": 9.953022754369114e-07,
+      "loss": 0.6755708217620849,
+      "step": 250
+    },
+    {
+      "epoch": 0.4378947368421053,
+      "grad_norm": 0.31017956137657166,
+      "learning_rate": 9.938671427214158e-07,
+      "loss": 0.6578442573547363,
+      "step": 260
+    },
+    {
+      "epoch": 0.45473684210526316,
+      "grad_norm": 0.21509627997875214,
+      "learning_rate": 9.922423267772986e-07,
+      "loss": 0.639409875869751,
+      "step": 270
+    },
+    {
+      "epoch": 0.47157894736842104,
+      "grad_norm": 0.3022947609424591,
+      "learning_rate": 9.904284516597102e-07,
+      "loss": 0.5995691776275635,
+      "step": 280
+    },
+    {
+      "epoch": 0.4884210526315789,
+      "grad_norm": 0.3367304801940918,
+      "learning_rate": 9.884262140371648e-07,
+      "loss": 0.5898309707641601,
+      "step": 290
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "grad_norm": 0.294842928647995,
+      "learning_rate": 9.862363829239662e-07,
+      "loss": 0.6371779441833496,
+      "step": 300
+    },
+    {
+      "epoch": 0.5221052631578947,
+      "grad_norm": 0.25171560049057007,
+      "learning_rate": 9.838597993848456e-07,
+      "loss": 0.5795581817626954,
+      "step": 310
+    },
+    {
+      "epoch": 0.5389473684210526,
+      "grad_norm": 0.2818540036678314,
+      "learning_rate": 9.81297376211928e-07,
+      "loss": 0.5668415546417236,
+      "step": 320
+    },
+    {
+      "epoch": 0.5557894736842105,
+      "grad_norm": 0.32951900362968445,
+      "learning_rate": 9.785500975741498e-07,
+      "loss": 0.5933257102966308,
+      "step": 330
+    },
+    {
+      "epoch": 0.5726315789473684,
+      "grad_norm": 0.2763514518737793,
+      "learning_rate": 9.756190186392615e-07,
+      "loss": 0.5574678897857666,
+      "step": 340
+    },
+    {
+      "epoch": 0.5894736842105263,
+      "grad_norm": 0.3070182204246521,
+      "learning_rate": 9.725052651685612e-07,
+      "loss": 0.5532425880432129,
+      "step": 350
+    },
+    {
+      "epoch": 0.6063157894736843,
+      "grad_norm": 0.2079988420009613,
+      "learning_rate": 9.692100330845153e-07,
+      "loss": 0.5613389492034913,
+      "step": 360
+    },
+    {
+      "epoch": 0.6231578947368421,
+      "grad_norm": 0.282924622297287,
+      "learning_rate": 9.657345880114318e-07,
+      "loss": 0.5131485939025879,
+      "step": 370
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.20901450514793396,
+      "learning_rate": 9.620802647893623e-07,
+      "loss": 0.6279027462005615,
+      "step": 380
+    },
+    {
+      "epoch": 0.6568421052631579,
+      "grad_norm": 0.2637634575366974,
+      "learning_rate": 9.58248466961421e-07,
+      "loss": 0.5403085231781006,
+      "step": 390
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "grad_norm": 0.29078468680381775,
+      "learning_rate": 9.542406662347137e-07,
+      "loss": 0.5678809642791748,
+      "step": 400
+    },
+    {
+      "epoch": 0.6905263157894737,
+      "grad_norm": 0.2865101397037506,
+      "learning_rate": 9.500584019150895e-07,
+      "loss": 0.5479135036468505,
+      "step": 410
+    },
+    {
+      "epoch": 0.7073684210526315,
+      "grad_norm": 0.22857311367988586,
+      "learning_rate": 9.45703280315928e-07,
+      "loss": 0.5604462623596191,
+      "step": 420
+    },
+    {
+      "epoch": 0.7242105263157895,
+      "grad_norm": 0.23971959948539734,
+      "learning_rate": 9.411769741411903e-07,
+      "loss": 0.4704423427581787,
+      "step": 430
+    },
+    {
+      "epoch": 0.7410526315789474,
+      "grad_norm": 0.29793378710746765,
+      "learning_rate": 9.364812218429721e-07,
+      "loss": 0.560968017578125,
+      "step": 440
+    },
+    {
+      "epoch": 0.7578947368421053,
+      "grad_norm": 0.2236040234565735,
+      "learning_rate": 9.316178269538014e-07,
+      "loss": 0.5088452816009521,
+      "step": 450
+    },
+    {
+      "epoch": 0.7747368421052632,
+      "grad_norm": 0.22047854959964752,
+      "learning_rate": 9.265886573939446e-07,
+      "loss": 0.5030550956726074,
+      "step": 460
+    },
+    {
+      "epoch": 0.791578947368421,
+      "grad_norm": 0.2273361086845398,
+      "learning_rate": 9.213956447539792e-07,
+      "loss": 0.46353440284729003,
+      "step": 470
+    },
+    {
+      "epoch": 0.8084210526315789,
+      "grad_norm": 0.2170158326625824,
+      "learning_rate": 9.160407835529136e-07,
+      "loss": 0.49871411323547366,
+      "step": 480
+    },
+    {
+      "epoch": 0.8252631578947368,
+      "grad_norm": 0.19333498179912567,
+      "learning_rate": 9.105261304721375e-07,
+      "loss": 0.4416178226470947,
+      "step": 490
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.18490085005760193,
+      "learning_rate": 9.048538035654969e-07,
+      "loss": 0.39783194065093996,
+      "step": 500
+    },
+    {
+      "epoch": 0.8589473684210527,
+      "grad_norm": 0.22122648358345032,
+      "learning_rate": 8.990259814457977e-07,
+      "loss": 0.4318229198455811,
+      "step": 510
+    },
+    {
+      "epoch": 0.8757894736842106,
+      "grad_norm": 0.17448943853378296,
+      "learning_rate": 8.930449024480491e-07,
+      "loss": 0.42445807456970214,
+      "step": 520
+    },
+    {
+      "epoch": 0.8926315789473684,
+      "grad_norm": 0.18165165185928345,
+      "learning_rate": 8.8691286376977e-07,
+      "loss": 0.46429901123046874,
+      "step": 530
+    },
+    {
+      "epoch": 0.9094736842105263,
+      "grad_norm": 0.16785287857055664,
+      "learning_rate": 8.806322205886873e-07,
+      "loss": 0.3975703239440918,
+      "step": 540
+    },
+    {
+      "epoch": 0.9263157894736842,
+      "grad_norm": 0.1613738089799881,
+      "learning_rate": 8.74205385158165e-07,
+      "loss": 0.4458911418914795,
+      "step": 550
+    },
+    {
+      "epoch": 0.9431578947368421,
+      "grad_norm": 0.15376177430152893,
+      "learning_rate": 8.676348258807121e-07,
+      "loss": 0.45571184158325195,
+      "step": 560
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.14966322481632233,
+      "learning_rate": 8.609230663599254e-07,
+      "loss": 0.4039600372314453,
+      "step": 570
+    },
+    {
+      "epoch": 0.9768421052631578,
+      "grad_norm": 0.16819055378437042,
+      "learning_rate": 8.540726844312294e-07,
+      "loss": 0.4382494926452637,
+      "step": 580
+    },
+    {
+      "epoch": 0.9936842105263158,
+      "grad_norm": 0.16405776143074036,
+      "learning_rate": 8.470863111717889e-07,
+      "loss": 0.4306180477142334,
+      "step": 590
+    },
+    {
+      "epoch": 1.0101052631578948,
+      "grad_norm": 0.18503950536251068,
+      "learning_rate": 8.399666298899706e-07,
+      "loss": 0.39806089401245115,
+      "step": 600
+    },
+    {
+      "epoch": 1.0269473684210526,
+      "grad_norm": 0.14375492930412292,
+      "learning_rate": 8.327163750947457e-07,
+      "loss": 0.4271697044372559,
+      "step": 610
+    },
+    {
+      "epoch": 1.0437894736842106,
+      "grad_norm": 0.1412728875875473,
+      "learning_rate": 8.253383314454263e-07,
+      "loss": 0.3939049243927002,
+      "step": 620
+    },
+    {
+      "epoch": 1.0606315789473684,
+      "grad_norm": 0.20121850073337555,
+      "learning_rate": 8.178353326821404e-07,
+      "loss": 0.43197131156921387,
+      "step": 630
+    },
+    {
+      "epoch": 1.0774736842105264,
+      "grad_norm": 0.17767728865146637,
+      "learning_rate": 8.102102605374566e-07,
+      "loss": 0.437807559967041,
+      "step": 640
+    },
+    {
+      "epoch": 1.0943157894736841,
+      "grad_norm": 0.1498359888792038,
+      "learning_rate": 8.024660436295759e-07,
+      "loss": 0.38409013748168946,
+      "step": 650
+    },
+    {
+      "epoch": 1.1111578947368421,
+      "grad_norm": 0.15958793461322784,
+      "learning_rate": 7.946056563375145e-07,
+      "loss": 0.4204962730407715,
+      "step": 660
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.157291978597641,
+      "learning_rate": 7.866321176587128e-07,
+      "loss": 0.42113161087036133,
+      "step": 670
+    },
+    {
+      "epoch": 1.1448421052631579,
+      "grad_norm": 0.14119838178157806,
+      "learning_rate": 7.785484900495065e-07,
+      "loss": 0.4151731491088867,
+      "step": 680
+    },
+    {
+      "epoch": 1.1616842105263159,
+      "grad_norm": 0.1296525001525879,
+      "learning_rate": 7.703578782489058e-07,
+      "loss": 0.38312902450561526,
+      "step": 690
+    },
+    {
+      "epoch": 1.1785263157894736,
+      "grad_norm": 0.13671696186065674,
+      "learning_rate": 7.620634280861351e-07,
+      "loss": 0.42612557411193847,
+      "step": 700
+    },
+    {
+      "epoch": 1.1953684210526316,
+      "grad_norm": 0.15196114778518677,
+      "learning_rate": 7.536683252723923e-07,
+      "loss": 0.4306772708892822,
+      "step": 710
+    },
+    {
+      "epoch": 1.2122105263157894,
+      "grad_norm": 0.1136903315782547,
+      "learning_rate": 7.451757941772868e-07,
+      "loss": 0.38483757972717286,
+      "step": 720
+    },
+    {
+      "epoch": 1.2290526315789474,
+      "grad_norm": 0.12378744781017303,
+      "learning_rate": 7.365890965904337e-07,
+      "loss": 0.4030342102050781,
+      "step": 730
+    },
+    {
+      "epoch": 1.2458947368421052,
+      "grad_norm": 0.1265542209148407,
+      "learning_rate": 7.279115304686733e-07,
+      "loss": 0.4091166973114014,
+      "step": 740
+    },
+    {
+      "epoch": 1.2627368421052632,
+      "grad_norm": 0.11647409200668335,
+      "learning_rate": 7.191464286694e-07,
+      "loss": 0.41426806449890136,
+      "step": 750
+    },
+    {
+      "epoch": 1.279578947368421,
+      "grad_norm": 0.11192695051431656,
+      "learning_rate": 7.102971576704875e-07,
+      "loss": 0.38181486129760744,
+      "step": 760
+    },
+    {
+      "epoch": 1.296421052631579,
+      "grad_norm": 0.14947861433029175,
+      "learning_rate": 7.013671162773003e-07,
+      "loss": 0.39824953079223635,
+      "step": 770
+    },
+    {
+      "epoch": 1.313263157894737,
+      "grad_norm": 0.11269424855709076,
+      "learning_rate": 6.923597343172891e-07,
+      "loss": 0.40348024368286134,
+      "step": 780
+    },
+    {
+      "epoch": 1.3301052631578947,
+      "grad_norm": 0.3742346167564392,
+      "learning_rate": 6.83278471322672e-07,
+      "loss": 0.38022048473358155,
+      "step": 790
+    },
+    {
+      "epoch": 1.3469473684210527,
+      "grad_norm": 0.1310902237892151,
+      "learning_rate": 6.741268152017057e-07,
+      "loss": 0.42791285514831545,
+      "step": 800
+    },
+    {
+      "epoch": 1.3637894736842107,
+      "grad_norm": 0.1692703813314438,
+      "learning_rate": 6.649082808990585e-07,
+      "loss": 0.4263493061065674,
+      "step": 810
+    },
+    {
+      "epoch": 1.3806315789473684,
+      "grad_norm": 0.1279117316007614,
+      "learning_rate": 6.556264090457998e-07,
+      "loss": 0.37379777431488037,
+      "step": 820
+    },
+    {
+      "epoch": 1.3974736842105262,
+      "grad_norm": 0.12949039041996002,
+      "learning_rate": 6.462847645995237e-07,
+      "loss": 0.38636391162872313,
+      "step": 830
+    },
+    {
+      "epoch": 1.4143157894736842,
+      "grad_norm": 0.10221126675605774,
+      "learning_rate": 6.368869354751284e-07,
+      "loss": 0.408221435546875,
+      "step": 840
+    },
+    {
+      "epoch": 1.4311578947368422,
+      "grad_norm": 0.11505889147520065,
+      "learning_rate": 6.274365311667797e-07,
+      "loss": 0.3951406717300415,
+      "step": 850
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.11054962873458862,
+      "learning_rate": 6.179371813615859e-07,
+      "loss": 0.3732129096984863,
+      "step": 860
+    },
+    {
+      "epoch": 1.464842105263158,
+      "grad_norm": 0.10150120407342911,
+      "learning_rate": 6.083925345455158e-07,
+      "loss": 0.38601529598236084,
+      "step": 870
+    },
+    {
+      "epoch": 1.4816842105263157,
+      "grad_norm": 0.12239400297403336,
+      "learning_rate": 5.988062566020986e-07,
+      "loss": 0.3859985828399658,
+      "step": 880
+    },
+    {
+      "epoch": 1.4985263157894737,
+      "grad_norm": 0.15801067650318146,
+      "learning_rate": 5.891820294044408e-07,
+      "loss": 0.3983951807022095,
+      "step": 890
+    },
+    {
+      "epoch": 1.5153684210526315,
+      "grad_norm": 0.10104545950889587,
+      "learning_rate": 5.795235494011007e-07,
+      "loss": 0.41107850074768065,
+      "step": 900
+    },
+    {
+      "epoch": 1.5322105263157895,
+      "grad_norm": 0.1378099024295807,
+      "learning_rate": 5.698345261963668e-07,
+      "loss": 0.3708331823348999,
+      "step": 910
+    },
+    {
+      "epoch": 1.5490526315789475,
+      "grad_norm": 0.12936057150363922,
+      "learning_rate": 5.601186811254825e-07,
+      "loss": 0.387884521484375,
+      "step": 920
+    },
+    {
+      "epoch": 1.5658947368421052,
+      "grad_norm": 0.12379129230976105,
+      "learning_rate": 5.503797458253646e-07,
+      "loss": 0.43808717727661134,
+      "step": 930
+    },
+    {
+      "epoch": 1.582736842105263,
+      "grad_norm": 0.12017743289470673,
+      "learning_rate": 5.406214608013662e-07,
+      "loss": 0.41345391273498533,
+      "step": 940
+    },
+    {
+      "epoch": 1.5995789473684212,
+      "grad_norm": 0.1095535159111023,
+      "learning_rate": 5.308475739906328e-07,
+      "loss": 0.40022664070129393,
+      "step": 950
+    },
+    {
+      "epoch": 1.616421052631579,
+      "grad_norm": 0.13831396400928497,
+      "learning_rate": 5.210618393226045e-07,
+      "loss": 0.3909924983978271,
+      "step": 960
+    },
+    {
+      "epoch": 1.6332631578947368,
+      "grad_norm": 0.10449163615703583,
+      "learning_rate": 5.112680152772156e-07,
+      "loss": 0.37143146991729736,
+      "step": 970
+    },
+    {
+      "epoch": 1.6501052631578947,
+      "grad_norm": 0.11249610036611557,
+      "learning_rate": 5.01469863441348e-07,
+      "loss": 0.38103113174438474,
+      "step": 980
+    },
+    {
+      "epoch": 1.6669473684210527,
+      "grad_norm": 0.13718819618225098,
+      "learning_rate": 4.916711470640907e-07,
+      "loss": 0.4071629524230957,
+      "step": 990
+    },
+    {
+      "epoch": 1.6837894736842105,
+      "grad_norm": 0.10473571717739105,
+      "learning_rate": 4.818756296113595e-07,
+      "loss": 0.417419958114624,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7006315789473683,
+      "grad_norm": 0.10846224427223206,
+      "learning_rate": 4.7208707332043623e-07,
+      "loss": 0.3998772859573364,
+      "step": 1010
+    },
+    {
+      "epoch": 1.7174736842105263,
+      "grad_norm": 0.10248563438653946,
+      "learning_rate": 4.6230923775497714e-07,
+      "loss": 0.38056583404541017,
+      "step": 1020
+    },
+    {
+      "epoch": 1.7343157894736843,
+      "grad_norm": 0.12221980094909668,
+      "learning_rate": 4.5254587836104964e-07,
+      "loss": 0.39371190071105955,
+      "step": 1030
+    },
+    {
+      "epoch": 1.751157894736842,
+      "grad_norm": 0.10641586035490036,
+      "learning_rate": 4.4280074502475017e-07,
+      "loss": 0.4280440330505371,
+      "step": 1040
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.12907131016254425,
+      "learning_rate": 4.3307758063195796e-07,
+      "loss": 0.3791615962982178,
+      "step": 1050
+    },
+    {
+      "epoch": 1.784842105263158,
+      "grad_norm": 0.12383506447076797,
+      "learning_rate": 4.233801196307762e-07,
+      "loss": 0.347782301902771,
+      "step": 1060
+    },
+    {
+      "epoch": 1.8016842105263158,
+      "grad_norm": 0.12547679245471954,
+      "learning_rate": 4.1371208659721536e-07,
+      "loss": 0.38370628356933595,
+      "step": 1070
+    },
+    {
+      "epoch": 1.8185263157894735,
+      "grad_norm": 0.10580642521381378,
+      "learning_rate": 4.0407719480466736e-07,
+      "loss": 0.40404376983642576,
+      "step": 1080
+    },
+    {
+      "epoch": 1.8353684210526315,
+      "grad_norm": 0.1055402085185051,
+      "learning_rate": 3.944791447977213e-07,
+      "loss": 0.4167450428009033,
+      "step": 1090
+    },
+    {
+      "epoch": 1.8522105263157895,
+      "grad_norm": 0.11053823679685593,
+      "learning_rate": 3.849216229708671e-07,
+      "loss": 0.4046513080596924,
+      "step": 1100
+    },
+    {
+      "epoch": 1.8690526315789473,
+      "grad_norm": 0.10185246914625168,
+      "learning_rate": 3.7540830015263526e-07,
+      "loss": 0.39672977924346925,
+      "step": 1110
+    },
+    {
+      "epoch": 1.8858947368421053,
+      "grad_norm": 0.08342823386192322,
+      "learning_rate": 3.6594283019571416e-07,
+      "loss": 0.39356396198272703,
+      "step": 1120
+    },
+    {
+      "epoch": 1.9027368421052633,
+      "grad_norm": 0.11821646988391876,
+      "learning_rate": 3.565288485735874e-07,
+      "loss": 0.42082643508911133,
+      "step": 1130
+    },
+    {
+      "epoch": 1.919578947368421,
+      "grad_norm": 0.1106327474117279,
+      "learning_rate": 3.4716997098423085e-07,
+      "loss": 0.34105117321014405,
+      "step": 1140
+    },
+    {
+      "epoch": 1.9364210526315788,
+      "grad_norm": 0.11533800512552261,
+      "learning_rate": 3.378697919614045e-07,
+      "loss": 0.3924069404602051,
+      "step": 1150
+    },
+    {
+      "epoch": 1.9532631578947368,
+      "grad_norm": 0.1431114822626114,
+      "learning_rate": 3.286318834940729e-07,
+      "loss": 0.3922377586364746,
+      "step": 1160
+    },
+    {
+      "epoch": 1.9701052631578948,
+      "grad_norm": 0.16050194203853607,
+      "learning_rate": 3.1945979365448517e-07,
+      "loss": 0.3745201587677002,
+      "step": 1170
+    },
+    {
+      "epoch": 1.9869473684210526,
+      "grad_norm": 0.11921833455562592,
+      "learning_rate": 3.103570452354402e-07,
+      "loss": 0.40110602378845217,
+      "step": 1180
+    },
+    {
+      "epoch": 2.0033684210526315,
+      "grad_norm": 0.0832003727555275,
+      "learning_rate": 3.013271343972613e-07,
+      "loss": 0.3981154918670654,
+      "step": 1190
+    },
+    {
+      "epoch": 2.0202105263157897,
+      "grad_norm": 0.09975888580083847,
+      "learning_rate": 2.9237352932500046e-07,
+      "loss": 0.3726134061813354,
+      "step": 1200
+    },
+    {
+      "epoch": 2.0370526315789474,
+      "grad_norm": 0.14600081741809845,
+      "learning_rate": 2.8349966889638615e-07,
+      "loss": 0.42558698654174804,
+      "step": 1210
+    },
+    {
+      "epoch": 2.053894736842105,
+      "grad_norm": 0.10875770449638367,
+      "learning_rate": 2.747089613610278e-07,
+      "loss": 0.3682931184768677,
+      "step": 1220
+    },
+    {
+      "epoch": 2.070736842105263,
+      "grad_norm": 0.10050549358129501,
+      "learning_rate": 2.66004783031385e-07,
+      "loss": 0.3756644487380981,
+      "step": 1230
+    },
+    {
+      "epoch": 2.087578947368421,
+      "grad_norm": 0.08914914727210999,
+      "learning_rate": 2.573904769860009e-07,
+      "loss": 0.3804330825805664,
+      "step": 1240
+    },
+    {
+      "epoch": 2.104421052631579,
+      "grad_norm": 0.08296852558851242,
+      "learning_rate": 2.488693517855016e-07,
+      "loss": 0.3978404521942139,
+      "step": 1250
+    },
+    {
+      "epoch": 2.1212631578947367,
+      "grad_norm": 0.13885149359703064,
+      "learning_rate": 2.404446802018533e-07,
+      "loss": 0.3935218334197998,
+      "step": 1260
+    },
+    {
+      "epoch": 2.138105263157895,
+      "grad_norm": 0.13195137679576874,
+      "learning_rate": 2.3211969796136305e-07,
+      "loss": 0.42966952323913576,
+      "step": 1270
+    },
+    {
+      "epoch": 2.1549473684210527,
+      "grad_norm": 0.13367892801761627,
+      "learning_rate": 2.2389760250191038e-07,
+      "loss": 0.3679579019546509,
+      "step": 1280
+    },
+    {
+      "epoch": 2.1717894736842105,
+      "grad_norm": 0.1288345605134964,
+      "learning_rate": 2.1578155174488343e-07,
+      "loss": 0.41324810981750487,
+      "step": 1290
+    },
+    {
+      "epoch": 2.1886315789473683,
+      "grad_norm": 0.09626021236181259,
+      "learning_rate": 2.0777466288229205e-07,
+      "loss": 0.40120248794555663,
+      "step": 1300
+    },
+    {
+      "epoch": 2.2054736842105265,
+      "grad_norm": 0.10264381766319275,
+      "learning_rate": 1.9988001117952485e-07,
+      "loss": 0.3501007080078125,
+      "step": 1310
+    },
+    {
+      "epoch": 2.2223157894736842,
+      "grad_norm": 0.09031466394662857,
+      "learning_rate": 1.9210062879420973e-07,
+      "loss": 0.3839429378509521,
+      "step": 1320
+    },
+    {
+      "epoch": 2.239157894736842,
+      "grad_norm": 0.12686079740524292,
+      "learning_rate": 1.8443950361162957e-07,
+      "loss": 0.4338528156280518,
+      "step": 1330
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 0.12199016660451889,
+      "learning_rate": 1.7689957809714346e-07,
+      "loss": 0.39229888916015626,
+      "step": 1340
+    },
+    {
+      "epoch": 2.272842105263158,
+      "grad_norm": 0.12029567360877991,
+      "learning_rate": 1.694837481660525e-07,
+      "loss": 0.38006880283355715,
+      "step": 1350
+    },
+    {
+      "epoch": 2.2896842105263158,
+      "grad_norm": 0.08686309307813644,
+      "learning_rate": 1.6219486207134313e-07,
+      "loss": 0.3808159589767456,
+      "step": 1360
+    },
+    {
+      "epoch": 2.3065263157894735,
+      "grad_norm": 0.10810462385416031,
+      "learning_rate": 1.5503571930973785e-07,
+      "loss": 0.401824426651001,
+      "step": 1370
+    },
+    {
+      "epoch": 2.3233684210526317,
+      "grad_norm": 0.10281873494386673,
+      "learning_rate": 1.480090695464723e-07,
+      "loss": 0.40149493217468263,
+      "step": 1380
+    },
+    {
+      "epoch": 2.3402105263157895,
+      "grad_norm": 0.09503985196352005,
+      "learning_rate": 1.4111761155920975e-07,
+      "loss": 0.38567726612091063,
+      "step": 1390
+    },
+    {
+      "epoch": 2.3570526315789473,
+      "grad_norm": 0.10420782119035721,
+      "learning_rate": 1.3436399220150212e-07,
+      "loss": 0.3759742736816406,
+      "step": 1400
+    },
+    {
+      "epoch": 2.3738947368421055,
+      "grad_norm": 0.10681115835905075,
+      "learning_rate": 1.2775080538619347e-07,
+      "loss": 0.3913698196411133,
+      "step": 1410
+    },
+    {
+      "epoch": 2.3907368421052633,
+      "grad_norm": 0.10323983430862427,
+      "learning_rate": 1.2128059108915595e-07,
+      "loss": 0.39077584743499755,
+      "step": 1420
+    },
+    {
+      "epoch": 2.407578947368421,
+      "grad_norm": 0.09566064178943634,
+      "learning_rate": 1.1495583437374263e-07,
+      "loss": 0.39895172119140626,
+      "step": 1430
+    },
+    {
+      "epoch": 2.424421052631579,
+      "grad_norm": 0.13018426299095154,
+      "learning_rate": 1.0877896443633117e-07,
+      "loss": 0.38982129096984863,
+      "step": 1440
+    },
+    {
+      "epoch": 2.441263157894737,
+      "grad_norm": 0.10760781168937683,
+      "learning_rate": 1.0275235367332347e-07,
+      "loss": 0.3756714344024658,
+      "step": 1450
+    },
+    {
+      "epoch": 2.458105263157895,
+      "grad_norm": 0.11606904864311218,
+      "learning_rate": 9.687831676996238e-08,
+      "loss": 0.37858171463012696,
+      "step": 1460
+    },
+    {
+      "epoch": 2.4749473684210526,
+      "grad_norm": 0.12957172095775604,
+      "learning_rate": 9.115910981131336e-08,
+      "loss": 0.40050196647644043,
+      "step": 1470
+    },
+    {
+      "epoch": 2.4917894736842103,
+      "grad_norm": 0.11186131089925766,
+      "learning_rate": 8.559692941575231e-08,
+      "loss": 0.3684133291244507,
+      "step": 1480
+    },
+    {
+      "epoch": 2.5086315789473685,
+      "grad_norm": 0.13279542326927185,
+      "learning_rate": 8.019391189129466e-08,
+      "loss": 0.3452518224716187,
+      "step": 1490
+    },
+    {
+      "epoch": 2.5254736842105263,
+      "grad_norm": 0.09041756391525269,
+      "learning_rate": 7.495213241508786e-08,
+      "loss": 0.36301617622375487,
+      "step": 1500
+    },
+    {
+      "epoch": 2.542315789473684,
+      "grad_norm": 0.10033190995454788,
+      "learning_rate": 6.987360423638205e-08,
+      "loss": 0.3706004858016968,
+      "step": 1510
+    },
+    {
+      "epoch": 2.559157894736842,
+      "grad_norm": 0.10681814700365067,
+      "learning_rate": 6.49602779032865e-08,
+      "loss": 0.36011199951171874,
+      "step": 1520
+    },
+    {
+      "epoch": 2.576,
+      "grad_norm": 0.1008416935801506,
+      "learning_rate": 6.02140405136089e-08,
+      "loss": 0.37473766803741454,
+      "step": 1530
+    },
+    {
+      "epoch": 2.592842105263158,
+      "grad_norm": 0.11559010297060013,
+      "learning_rate": 5.5636714990062393e-08,
+      "loss": 0.39232525825500486,
+      "step": 1540
+    },
+    {
+      "epoch": 2.609684210526316,
+      "grad_norm": 0.10601615905761719,
+      "learning_rate": 5.1230059380123034e-08,
+      "loss": 0.34370343685150145,
+      "step": 1550
+    },
+    {
+      "epoch": 2.626526315789474,
+      "grad_norm": 0.11516924202442169,
+      "learning_rate": 4.699576618080331e-08,
+      "loss": 0.39509878158569334,
+      "step": 1560
+    },
+    {
+      "epoch": 2.6433684210526316,
+      "grad_norm": 0.11444627493619919,
+      "learning_rate": 4.293546168860163e-08,
+      "loss": 0.3881126165390015,
+      "step": 1570
+    },
+    {
+      "epoch": 2.6602105263157894,
+      "grad_norm": 0.09985339641571045,
+      "learning_rate": 3.9050705374879086e-08,
+      "loss": 0.34624040126800537,
+      "step": 1580
+    },
+    {
+      "epoch": 2.677052631578947,
+      "grad_norm": 0.10439962148666382,
+      "learning_rate": 3.534298928690166e-08,
+      "loss": 0.35141232013702395,
+      "step": 1590
+    },
+    {
+      "epoch": 2.6938947368421053,
+      "grad_norm": 0.12180087715387344,
+      "learning_rate": 3.181373747477822e-08,
+      "loss": 0.39980330467224123,
+      "step": 1600
+    },
+    {
+      "epoch": 2.710736842105263,
+      "grad_norm": 0.12150874733924866,
+      "learning_rate": 2.8464305444515112e-08,
+      "loss": 0.3560852766036987,
+      "step": 1610
+    },
+    {
+      "epoch": 2.7275789473684213,
+      "grad_norm": 0.11374734342098236,
+      "learning_rate": 2.5295979637397213e-08,
+      "loss": 0.39339067935943606,
+      "step": 1620
+    },
+    {
+      "epoch": 2.744421052631579,
+      "grad_norm": 0.11705286055803299,
+      "learning_rate": 2.2309976935894203e-08,
+      "loss": 0.38021705150604246,
+      "step": 1630
+    },
+    {
+      "epoch": 2.761263157894737,
+      "grad_norm": 0.09300459921360016,
+      "learning_rate": 1.9507444196284195e-08,
+      "loss": 0.3467890739440918,
+      "step": 1640
+    },
+    {
+      "epoch": 2.7781052631578946,
+      "grad_norm": 0.08709974586963654,
+      "learning_rate": 1.688945780817147e-08,
+      "loss": 0.38266596794128416,
+      "step": 1650
+    },
+    {
+      "epoch": 2.7949473684210524,
+      "grad_norm": 0.12327069044113159,
+      "learning_rate": 1.445702328106979e-08,
+      "loss": 0.34164865016937257,
+      "step": 1660
+    },
+    {
+      "epoch": 2.8117894736842106,
+      "grad_norm": 0.12361253052949905,
+      "learning_rate": 1.2211074858209103e-08,
+      "loss": 0.3876492977142334,
+      "step": 1670
+    },
+    {
+      "epoch": 2.8286315789473684,
+      "grad_norm": 0.120187908411026,
+      "learning_rate": 1.0152475157713392e-08,
+      "loss": 0.3703944206237793,
+      "step": 1680
+    },
+    {
+      "epoch": 2.845473684210526,
+      "grad_norm": 0.10741006582975388,
+      "learning_rate": 8.282014841288653e-09,
+      "loss": 0.3735771656036377,
+      "step": 1690
+    },
+    {
+      "epoch": 2.8623157894736844,
+      "grad_norm": 0.10451704263687134,
+      "learning_rate": 6.600412310547754e-09,
+      "loss": 0.3807518005371094,
+      "step": 1700
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1782,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.1088780591683584e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1782/README.md b/checkpoint-1782/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..cfd546f8318a3a2985d8a7e4c881e529305dd807
--- /dev/null
+++ b/checkpoint-1782/README.md
@@ -0,0 +1,208 @@
+---
+base_model: google/gemma-3-1b-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:google/gemma-3-1b-it
+- llama-factory
+- 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 0.18.1
\ No newline at end of file
diff --git a/checkpoint-1782/adapter_config.json b/checkpoint-1782/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..b7033a591cf40ea5b43aae7a6f56ed6a65d3f80c
--- /dev/null
+++ b/checkpoint-1782/adapter_config.json
@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-1b-it",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj",
+    "q_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/checkpoint-1782/adapter_model.safetensors b/checkpoint-1782/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..03edeef75932b07dca7331094b07797a7dcc736b
--- /dev/null
+++ b/checkpoint-1782/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2fccca914644fd456afb68abc1f7307cc09f76cd552cb49bc0a910ee900a73e
+size 26139264
diff --git a/checkpoint-1782/chat_template.jinja b/checkpoint-1782/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..1117055ab8e8c90e1b200be00cddb78943616d9e
--- /dev/null
+++ b/checkpoint-1782/chat_template.jinja
@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}
diff --git a/checkpoint-1782/optimizer.pt b/checkpoint-1782/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..758c9ac39ed111f4496db5c03fe3210f61e987f6
--- /dev/null
+++ b/checkpoint-1782/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6755df68ed122f1f13f9150cae71db9987413a5e7f10ce12895cbd2aad495e84
+size 52494119
diff --git a/checkpoint-1782/tokenizer.json b/checkpoint-1782/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..899af07a0757e3f45323d537449b3b8525aa272c
--- /dev/null
+++ b/checkpoint-1782/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a74aefb1dc1340a25f29ab8370384b9ed24b2d921d7749ece7bbcfcfdf00d497
+size 33384443
diff --git a/checkpoint-1782/tokenizer_config.json b/checkpoint-1782/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d83f12eef5a7d73283047b2f05c1ffdd6346556a
--- /dev/null
+++ b/checkpoint-1782/tokenizer_config.json
@@ -0,0 +1,26 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<end_of_turn>",
+  "image_token": "<image_soft_token>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "processor_class": "Gemma3Processor",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/checkpoint-1782/trainer_state.json b/checkpoint-1782/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..b9cf4e8987b5fbc4b30f5531f884697f86826199
--- /dev/null
+++ b/checkpoint-1782/trainer_state.json
@@ -0,0 +1,1280 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 100,
+  "global_step": 1782,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016842105263157894,
+      "grad_norm": 0.21757784485816956,
+      "learning_rate": 5.027932960893855e-08,
+      "loss": 0.7252199172973632,
+      "step": 10
+    },
+    {
+      "epoch": 0.03368421052631579,
+      "grad_norm": 0.2456846386194229,
+      "learning_rate": 1.0614525139664805e-07,
+      "loss": 0.6507451057434082,
+      "step": 20
+    },
+    {
+      "epoch": 0.05052631578947368,
+      "grad_norm": 0.20819272100925446,
+      "learning_rate": 1.6201117318435754e-07,
+      "loss": 0.7381344795227051,
+      "step": 30
+    },
+    {
+      "epoch": 0.06736842105263158,
+      "grad_norm": 0.26373574137687683,
+      "learning_rate": 2.17877094972067e-07,
+      "loss": 0.7012194156646728,
+      "step": 40
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 0.2081507444381714,
+      "learning_rate": 2.7374301675977653e-07,
+      "loss": 0.6083873748779297,
+      "step": 50
+    },
+    {
+      "epoch": 0.10105263157894737,
+      "grad_norm": 0.2091236114501953,
+      "learning_rate": 3.29608938547486e-07,
+      "loss": 0.6980491638183594,
+      "step": 60
+    },
+    {
+      "epoch": 0.11789473684210526,
+      "grad_norm": 0.20970331132411957,
+      "learning_rate": 3.8547486033519547e-07,
+      "loss": 0.708641767501831,
+      "step": 70
+    },
+    {
+      "epoch": 0.13473684210526315,
+      "grad_norm": 0.18810197710990906,
+      "learning_rate": 4.41340782122905e-07,
+      "loss": 0.6742453098297119,
+      "step": 80
+    },
+    {
+      "epoch": 0.15157894736842106,
+      "grad_norm": 0.20251069962978363,
+      "learning_rate": 4.972067039106145e-07,
+      "loss": 0.6590609550476074,
+      "step": 90
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "grad_norm": 0.2644217908382416,
+      "learning_rate": 5.53072625698324e-07,
+      "loss": 0.704926872253418,
+      "step": 100
+    },
+    {
+      "epoch": 0.18526315789473685,
+      "grad_norm": 0.23766489326953888,
+      "learning_rate": 6.089385474860335e-07,
+      "loss": 0.7445036888122558,
+      "step": 110
+    },
+    {
+      "epoch": 0.20210526315789473,
+      "grad_norm": 0.27427056431770325,
+      "learning_rate": 6.64804469273743e-07,
+      "loss": 0.7476531028747558,
+      "step": 120
+    },
+    {
+      "epoch": 0.21894736842105264,
+      "grad_norm": 0.3208928406238556,
+      "learning_rate": 7.206703910614524e-07,
+      "loss": 0.7291872501373291,
+      "step": 130
+    },
+    {
+      "epoch": 0.23578947368421052,
+      "grad_norm": 0.3123615086078644,
+      "learning_rate": 7.76536312849162e-07,
+      "loss": 0.721175241470337,
+      "step": 140
+    },
+    {
+      "epoch": 0.25263157894736843,
+      "grad_norm": 0.26158222556114197,
+      "learning_rate": 8.324022346368714e-07,
+      "loss": 0.7556095600128174,
+      "step": 150
+    },
+    {
+      "epoch": 0.2694736842105263,
+      "grad_norm": 0.2592650353908539,
+      "learning_rate": 8.88268156424581e-07,
+      "loss": 0.7328392505645752,
+      "step": 160
+    },
+    {
+      "epoch": 0.2863157894736842,
+      "grad_norm": 0.24533776938915253,
+      "learning_rate": 9.441340782122904e-07,
+      "loss": 0.6990129470825195,
+      "step": 170
+    },
+    {
+      "epoch": 0.3031578947368421,
+      "grad_norm": 0.23409004509449005,
+      "learning_rate": 1e-06,
+      "loss": 0.6694639205932618,
+      "step": 180
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.3267499506473541,
+      "learning_rate": 9.999039806396227e-07,
+      "loss": 0.7123252868652343,
+      "step": 190
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "grad_norm": 0.2115064263343811,
+      "learning_rate": 9.996159594373611e-07,
+      "loss": 0.6858412742614746,
+      "step": 200
+    },
+    {
+      "epoch": 0.35368421052631577,
+      "grad_norm": 0.26226580142974854,
+      "learning_rate": 9.991360470156615e-07,
+      "loss": 0.6541069507598877,
+      "step": 210
+    },
+    {
+      "epoch": 0.3705263157894737,
+      "grad_norm": 0.24552594125270844,
+      "learning_rate": 9.984644276980594e-07,
+      "loss": 0.6506116390228271,
+      "step": 220
+    },
+    {
+      "epoch": 0.3873684210526316,
+      "grad_norm": 0.25084301829338074,
+      "learning_rate": 9.976013594383835e-07,
+      "loss": 0.6540626049041748,
+      "step": 230
+    },
+    {
+      "epoch": 0.40421052631578946,
+      "grad_norm": 0.34244054555892944,
+      "learning_rate": 9.965471737216833e-07,
+      "loss": 0.6737770557403564,
+      "step": 240
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.34752583503723145,
+      "learning_rate": 9.953022754369114e-07,
+      "loss": 0.6755708217620849,
+      "step": 250
+    },
+    {
+      "epoch": 0.4378947368421053,
+      "grad_norm": 0.31017956137657166,
+      "learning_rate": 9.938671427214158e-07,
+      "loss": 0.6578442573547363,
+      "step": 260
+    },
+    {
+      "epoch": 0.45473684210526316,
+      "grad_norm": 0.21509627997875214,
+      "learning_rate": 9.922423267772986e-07,
+      "loss": 0.639409875869751,
+      "step": 270
+    },
+    {
+      "epoch": 0.47157894736842104,
+      "grad_norm": 0.3022947609424591,
+      "learning_rate": 9.904284516597102e-07,
+      "loss": 0.5995691776275635,
+      "step": 280
+    },
+    {
+      "epoch": 0.4884210526315789,
+      "grad_norm": 0.3367304801940918,
+      "learning_rate": 9.884262140371648e-07,
+      "loss": 0.5898309707641601,
+      "step": 290
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "grad_norm": 0.294842928647995,
+      "learning_rate": 9.862363829239662e-07,
+      "loss": 0.6371779441833496,
+      "step": 300
+    },
+    {
+      "epoch": 0.5221052631578947,
+      "grad_norm": 0.25171560049057007,
+      "learning_rate": 9.838597993848456e-07,
+      "loss": 0.5795581817626954,
+      "step": 310
+    },
+    {
+      "epoch": 0.5389473684210526,
+      "grad_norm": 0.2818540036678314,
+      "learning_rate": 9.81297376211928e-07,
+      "loss": 0.5668415546417236,
+      "step": 320
+    },
+    {
+      "epoch": 0.5557894736842105,
+      "grad_norm": 0.32951900362968445,
+      "learning_rate": 9.785500975741498e-07,
+      "loss": 0.5933257102966308,
+      "step": 330
+    },
+    {
+      "epoch": 0.5726315789473684,
+      "grad_norm": 0.2763514518737793,
+      "learning_rate": 9.756190186392615e-07,
+      "loss": 0.5574678897857666,
+      "step": 340
+    },
+    {
+      "epoch": 0.5894736842105263,
+      "grad_norm": 0.3070182204246521,
+      "learning_rate": 9.725052651685612e-07,
+      "loss": 0.5532425880432129,
+      "step": 350
+    },
+    {
+      "epoch": 0.6063157894736843,
+      "grad_norm": 0.2079988420009613,
+      "learning_rate": 9.692100330845153e-07,
+      "loss": 0.5613389492034913,
+      "step": 360
+    },
+    {
+      "epoch": 0.6231578947368421,
+      "grad_norm": 0.282924622297287,
+      "learning_rate": 9.657345880114318e-07,
+      "loss": 0.5131485939025879,
+      "step": 370
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.20901450514793396,
+      "learning_rate": 9.620802647893623e-07,
+      "loss": 0.6279027462005615,
+      "step": 380
+    },
+    {
+      "epoch": 0.6568421052631579,
+      "grad_norm": 0.2637634575366974,
+      "learning_rate": 9.58248466961421e-07,
+      "loss": 0.5403085231781006,
+      "step": 390
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "grad_norm": 0.29078468680381775,
+      "learning_rate": 9.542406662347137e-07,
+      "loss": 0.5678809642791748,
+      "step": 400
+    },
+    {
+      "epoch": 0.6905263157894737,
+      "grad_norm": 0.2865101397037506,
+      "learning_rate": 9.500584019150895e-07,
+      "loss": 0.5479135036468505,
+      "step": 410
+    },
+    {
+      "epoch": 0.7073684210526315,
+      "grad_norm": 0.22857311367988586,
+      "learning_rate": 9.45703280315928e-07,
+      "loss": 0.5604462623596191,
+      "step": 420
+    },
+    {
+      "epoch": 0.7242105263157895,
+      "grad_norm": 0.23971959948539734,
+      "learning_rate": 9.411769741411903e-07,
+      "loss": 0.4704423427581787,
+      "step": 430
+    },
+    {
+      "epoch": 0.7410526315789474,
+      "grad_norm": 0.29793378710746765,
+      "learning_rate": 9.364812218429721e-07,
+      "loss": 0.560968017578125,
+      "step": 440
+    },
+    {
+      "epoch": 0.7578947368421053,
+      "grad_norm": 0.2236040234565735,
+      "learning_rate": 9.316178269538014e-07,
+      "loss": 0.5088452816009521,
+      "step": 450
+    },
+    {
+      "epoch": 0.7747368421052632,
+      "grad_norm": 0.22047854959964752,
+      "learning_rate": 9.265886573939446e-07,
+      "loss": 0.5030550956726074,
+      "step": 460
+    },
+    {
+      "epoch": 0.791578947368421,
+      "grad_norm": 0.2273361086845398,
+      "learning_rate": 9.213956447539792e-07,
+      "loss": 0.46353440284729003,
+      "step": 470
+    },
+    {
+      "epoch": 0.8084210526315789,
+      "grad_norm": 0.2170158326625824,
+      "learning_rate": 9.160407835529136e-07,
+      "loss": 0.49871411323547366,
+      "step": 480
+    },
+    {
+      "epoch": 0.8252631578947368,
+      "grad_norm": 0.19333498179912567,
+      "learning_rate": 9.105261304721375e-07,
+      "loss": 0.4416178226470947,
+      "step": 490
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.18490085005760193,
+      "learning_rate": 9.048538035654969e-07,
+      "loss": 0.39783194065093996,
+      "step": 500
+    },
+    {
+      "epoch": 0.8589473684210527,
+      "grad_norm": 0.22122648358345032,
+      "learning_rate": 8.990259814457977e-07,
+      "loss": 0.4318229198455811,
+      "step": 510
+    },
+    {
+      "epoch": 0.8757894736842106,
+      "grad_norm": 0.17448943853378296,
+      "learning_rate": 8.930449024480491e-07,
+      "loss": 0.42445807456970214,
+      "step": 520
+    },
+    {
+      "epoch": 0.8926315789473684,
+      "grad_norm": 0.18165165185928345,
+      "learning_rate": 8.8691286376977e-07,
+      "loss": 0.46429901123046874,
+      "step": 530
+    },
+    {
+      "epoch": 0.9094736842105263,
+      "grad_norm": 0.16785287857055664,
+      "learning_rate": 8.806322205886873e-07,
+      "loss": 0.3975703239440918,
+      "step": 540
+    },
+    {
+      "epoch": 0.9263157894736842,
+      "grad_norm": 0.1613738089799881,
+      "learning_rate": 8.74205385158165e-07,
+      "loss": 0.4458911418914795,
+      "step": 550
+    },
+    {
+      "epoch": 0.9431578947368421,
+      "grad_norm": 0.15376177430152893,
+      "learning_rate": 8.676348258807121e-07,
+      "loss": 0.45571184158325195,
+      "step": 560
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.14966322481632233,
+      "learning_rate": 8.609230663599254e-07,
+      "loss": 0.4039600372314453,
+      "step": 570
+    },
+    {
+      "epoch": 0.9768421052631578,
+      "grad_norm": 0.16819055378437042,
+      "learning_rate": 8.540726844312294e-07,
+      "loss": 0.4382494926452637,
+      "step": 580
+    },
+    {
+      "epoch": 0.9936842105263158,
+      "grad_norm": 0.16405776143074036,
+      "learning_rate": 8.470863111717889e-07,
+      "loss": 0.4306180477142334,
+      "step": 590
+    },
+    {
+      "epoch": 1.0101052631578948,
+      "grad_norm": 0.18503950536251068,
+      "learning_rate": 8.399666298899706e-07,
+      "loss": 0.39806089401245115,
+      "step": 600
+    },
+    {
+      "epoch": 1.0269473684210526,
+      "grad_norm": 0.14375492930412292,
+      "learning_rate": 8.327163750947457e-07,
+      "loss": 0.4271697044372559,
+      "step": 610
+    },
+    {
+      "epoch": 1.0437894736842106,
+      "grad_norm": 0.1412728875875473,
+      "learning_rate": 8.253383314454263e-07,
+      "loss": 0.3939049243927002,
+      "step": 620
+    },
+    {
+      "epoch": 1.0606315789473684,
+      "grad_norm": 0.20121850073337555,
+      "learning_rate": 8.178353326821404e-07,
+      "loss": 0.43197131156921387,
+      "step": 630
+    },
+    {
+      "epoch": 1.0774736842105264,
+      "grad_norm": 0.17767728865146637,
+      "learning_rate": 8.102102605374566e-07,
+      "loss": 0.437807559967041,
+      "step": 640
+    },
+    {
+      "epoch": 1.0943157894736841,
+      "grad_norm": 0.1498359888792038,
+      "learning_rate": 8.024660436295759e-07,
+      "loss": 0.38409013748168946,
+      "step": 650
+    },
+    {
+      "epoch": 1.1111578947368421,
+      "grad_norm": 0.15958793461322784,
+      "learning_rate": 7.946056563375145e-07,
+      "loss": 0.4204962730407715,
+      "step": 660
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.157291978597641,
+      "learning_rate": 7.866321176587128e-07,
+      "loss": 0.42113161087036133,
+      "step": 670
+    },
+    {
+      "epoch": 1.1448421052631579,
+      "grad_norm": 0.14119838178157806,
+      "learning_rate": 7.785484900495065e-07,
+      "loss": 0.4151731491088867,
+      "step": 680
+    },
+    {
+      "epoch": 1.1616842105263159,
+      "grad_norm": 0.1296525001525879,
+      "learning_rate": 7.703578782489058e-07,
+      "loss": 0.38312902450561526,
+      "step": 690
+    },
+    {
+      "epoch": 1.1785263157894736,
+      "grad_norm": 0.13671696186065674,
+      "learning_rate": 7.620634280861351e-07,
+      "loss": 0.42612557411193847,
+      "step": 700
+    },
+    {
+      "epoch": 1.1953684210526316,
+      "grad_norm": 0.15196114778518677,
+      "learning_rate": 7.536683252723923e-07,
+      "loss": 0.4306772708892822,
+      "step": 710
+    },
+    {
+      "epoch": 1.2122105263157894,
+      "grad_norm": 0.1136903315782547,
+      "learning_rate": 7.451757941772868e-07,
+      "loss": 0.38483757972717286,
+      "step": 720
+    },
+    {
+      "epoch": 1.2290526315789474,
+      "grad_norm": 0.12378744781017303,
+      "learning_rate": 7.365890965904337e-07,
+      "loss": 0.4030342102050781,
+      "step": 730
+    },
+    {
+      "epoch": 1.2458947368421052,
+      "grad_norm": 0.1265542209148407,
+      "learning_rate": 7.279115304686733e-07,
+      "loss": 0.4091166973114014,
+      "step": 740
+    },
+    {
+      "epoch": 1.2627368421052632,
+      "grad_norm": 0.11647409200668335,
+      "learning_rate": 7.191464286694e-07,
+      "loss": 0.41426806449890136,
+      "step": 750
+    },
+    {
+      "epoch": 1.279578947368421,
+      "grad_norm": 0.11192695051431656,
+      "learning_rate": 7.102971576704875e-07,
+      "loss": 0.38181486129760744,
+      "step": 760
+    },
+    {
+      "epoch": 1.296421052631579,
+      "grad_norm": 0.14947861433029175,
+      "learning_rate": 7.013671162773003e-07,
+      "loss": 0.39824953079223635,
+      "step": 770
+    },
+    {
+      "epoch": 1.313263157894737,
+      "grad_norm": 0.11269424855709076,
+      "learning_rate": 6.923597343172891e-07,
+      "loss": 0.40348024368286134,
+      "step": 780
+    },
+    {
+      "epoch": 1.3301052631578947,
+      "grad_norm": 0.3742346167564392,
+      "learning_rate": 6.83278471322672e-07,
+      "loss": 0.38022048473358155,
+      "step": 790
+    },
+    {
+      "epoch": 1.3469473684210527,
+      "grad_norm": 0.1310902237892151,
+      "learning_rate": 6.741268152017057e-07,
+      "loss": 0.42791285514831545,
+      "step": 800
+    },
+    {
+      "epoch": 1.3637894736842107,
+      "grad_norm": 0.1692703813314438,
+      "learning_rate": 6.649082808990585e-07,
+      "loss": 0.4263493061065674,
+      "step": 810
+    },
+    {
+      "epoch": 1.3806315789473684,
+      "grad_norm": 0.1279117316007614,
+      "learning_rate": 6.556264090457998e-07,
+      "loss": 0.37379777431488037,
+      "step": 820
+    },
+    {
+      "epoch": 1.3974736842105262,
+      "grad_norm": 0.12949039041996002,
+      "learning_rate": 6.462847645995237e-07,
+      "loss": 0.38636391162872313,
+      "step": 830
+    },
+    {
+      "epoch": 1.4143157894736842,
+      "grad_norm": 0.10221126675605774,
+      "learning_rate": 6.368869354751284e-07,
+      "loss": 0.408221435546875,
+      "step": 840
+    },
+    {
+      "epoch": 1.4311578947368422,
+      "grad_norm": 0.11505889147520065,
+      "learning_rate": 6.274365311667797e-07,
+      "loss": 0.3951406717300415,
+      "step": 850
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.11054962873458862,
+      "learning_rate": 6.179371813615859e-07,
+      "loss": 0.3732129096984863,
+      "step": 860
+    },
+    {
+      "epoch": 1.464842105263158,
+      "grad_norm": 0.10150120407342911,
+      "learning_rate": 6.083925345455158e-07,
+      "loss": 0.38601529598236084,
+      "step": 870
+    },
+    {
+      "epoch": 1.4816842105263157,
+      "grad_norm": 0.12239400297403336,
+      "learning_rate": 5.988062566020986e-07,
+      "loss": 0.3859985828399658,
+      "step": 880
+    },
+    {
+      "epoch": 1.4985263157894737,
+      "grad_norm": 0.15801067650318146,
+      "learning_rate": 5.891820294044408e-07,
+      "loss": 0.3983951807022095,
+      "step": 890
+    },
+    {
+      "epoch": 1.5153684210526315,
+      "grad_norm": 0.10104545950889587,
+      "learning_rate": 5.795235494011007e-07,
+      "loss": 0.41107850074768065,
+      "step": 900
+    },
+    {
+      "epoch": 1.5322105263157895,
+      "grad_norm": 0.1378099024295807,
+      "learning_rate": 5.698345261963668e-07,
+      "loss": 0.3708331823348999,
+      "step": 910
+    },
+    {
+      "epoch": 1.5490526315789475,
+      "grad_norm": 0.12936057150363922,
+      "learning_rate": 5.601186811254825e-07,
+      "loss": 0.387884521484375,
+      "step": 920
+    },
+    {
+      "epoch": 1.5658947368421052,
+      "grad_norm": 0.12379129230976105,
+      "learning_rate": 5.503797458253646e-07,
+      "loss": 0.43808717727661134,
+      "step": 930
+    },
+    {
+      "epoch": 1.582736842105263,
+      "grad_norm": 0.12017743289470673,
+      "learning_rate": 5.406214608013662e-07,
+      "loss": 0.41345391273498533,
+      "step": 940
+    },
+    {
+      "epoch": 1.5995789473684212,
+      "grad_norm": 0.1095535159111023,
+      "learning_rate": 5.308475739906328e-07,
+      "loss": 0.40022664070129393,
+      "step": 950
+    },
+    {
+      "epoch": 1.616421052631579,
+      "grad_norm": 0.13831396400928497,
+      "learning_rate": 5.210618393226045e-07,
+      "loss": 0.3909924983978271,
+      "step": 960
+    },
+    {
+      "epoch": 1.6332631578947368,
+      "grad_norm": 0.10449163615703583,
+      "learning_rate": 5.112680152772156e-07,
+      "loss": 0.37143146991729736,
+      "step": 970
+    },
+    {
+      "epoch": 1.6501052631578947,
+      "grad_norm": 0.11249610036611557,
+      "learning_rate": 5.01469863441348e-07,
+      "loss": 0.38103113174438474,
+      "step": 980
+    },
+    {
+      "epoch": 1.6669473684210527,
+      "grad_norm": 0.13718819618225098,
+      "learning_rate": 4.916711470640907e-07,
+      "loss": 0.4071629524230957,
+      "step": 990
+    },
+    {
+      "epoch": 1.6837894736842105,
+      "grad_norm": 0.10473571717739105,
+      "learning_rate": 4.818756296113595e-07,
+      "loss": 0.417419958114624,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7006315789473683,
+      "grad_norm": 0.10846224427223206,
+      "learning_rate": 4.7208707332043623e-07,
+      "loss": 0.3998772859573364,
+      "step": 1010
+    },
+    {
+      "epoch": 1.7174736842105263,
+      "grad_norm": 0.10248563438653946,
+      "learning_rate": 4.6230923775497714e-07,
+      "loss": 0.38056583404541017,
+      "step": 1020
+    },
+    {
+      "epoch": 1.7343157894736843,
+      "grad_norm": 0.12221980094909668,
+      "learning_rate": 4.5254587836104964e-07,
+      "loss": 0.39371190071105955,
+      "step": 1030
+    },
+    {
+      "epoch": 1.751157894736842,
+      "grad_norm": 0.10641586035490036,
+      "learning_rate": 4.4280074502475017e-07,
+      "loss": 0.4280440330505371,
+      "step": 1040
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.12907131016254425,
+      "learning_rate": 4.3307758063195796e-07,
+      "loss": 0.3791615962982178,
+      "step": 1050
+    },
+    {
+      "epoch": 1.784842105263158,
+      "grad_norm": 0.12383506447076797,
+      "learning_rate": 4.233801196307762e-07,
+      "loss": 0.347782301902771,
+      "step": 1060
+    },
+    {
+      "epoch": 1.8016842105263158,
+      "grad_norm": 0.12547679245471954,
+      "learning_rate": 4.1371208659721536e-07,
+      "loss": 0.38370628356933595,
+      "step": 1070
+    },
+    {
+      "epoch": 1.8185263157894735,
+      "grad_norm": 0.10580642521381378,
+      "learning_rate": 4.0407719480466736e-07,
+      "loss": 0.40404376983642576,
+      "step": 1080
+    },
+    {
+      "epoch": 1.8353684210526315,
+      "grad_norm": 0.1055402085185051,
+      "learning_rate": 3.944791447977213e-07,
+      "loss": 0.4167450428009033,
+      "step": 1090
+    },
+    {
+      "epoch": 1.8522105263157895,
+      "grad_norm": 0.11053823679685593,
+      "learning_rate": 3.849216229708671e-07,
+      "loss": 0.4046513080596924,
+      "step": 1100
+    },
+    {
+      "epoch": 1.8690526315789473,
+      "grad_norm": 0.10185246914625168,
+      "learning_rate": 3.7540830015263526e-07,
+      "loss": 0.39672977924346925,
+      "step": 1110
+    },
+    {
+      "epoch": 1.8858947368421053,
+      "grad_norm": 0.08342823386192322,
+      "learning_rate": 3.6594283019571416e-07,
+      "loss": 0.39356396198272703,
+      "step": 1120
+    },
+    {
+      "epoch": 1.9027368421052633,
+      "grad_norm": 0.11821646988391876,
+      "learning_rate": 3.565288485735874e-07,
+      "loss": 0.42082643508911133,
+      "step": 1130
+    },
+    {
+      "epoch": 1.919578947368421,
+      "grad_norm": 0.1106327474117279,
+      "learning_rate": 3.4716997098423085e-07,
+      "loss": 0.34105117321014405,
+      "step": 1140
+    },
+    {
+      "epoch": 1.9364210526315788,
+      "grad_norm": 0.11533800512552261,
+      "learning_rate": 3.378697919614045e-07,
+      "loss": 0.3924069404602051,
+      "step": 1150
+    },
+    {
+      "epoch": 1.9532631578947368,
+      "grad_norm": 0.1431114822626114,
+      "learning_rate": 3.286318834940729e-07,
+      "loss": 0.3922377586364746,
+      "step": 1160
+    },
+    {
+      "epoch": 1.9701052631578948,
+      "grad_norm": 0.16050194203853607,
+      "learning_rate": 3.1945979365448517e-07,
+      "loss": 0.3745201587677002,
+      "step": 1170
+    },
+    {
+      "epoch": 1.9869473684210526,
+      "grad_norm": 0.11921833455562592,
+      "learning_rate": 3.103570452354402e-07,
+      "loss": 0.40110602378845217,
+      "step": 1180
+    },
+    {
+      "epoch": 2.0033684210526315,
+      "grad_norm": 0.0832003727555275,
+      "learning_rate": 3.013271343972613e-07,
+      "loss": 0.3981154918670654,
+      "step": 1190
+    },
+    {
+      "epoch": 2.0202105263157897,
+      "grad_norm": 0.09975888580083847,
+      "learning_rate": 2.9237352932500046e-07,
+      "loss": 0.3726134061813354,
+      "step": 1200
+    },
+    {
+      "epoch": 2.0370526315789474,
+      "grad_norm": 0.14600081741809845,
+      "learning_rate": 2.8349966889638615e-07,
+      "loss": 0.42558698654174804,
+      "step": 1210
+    },
+    {
+      "epoch": 2.053894736842105,
+      "grad_norm": 0.10875770449638367,
+      "learning_rate": 2.747089613610278e-07,
+      "loss": 0.3682931184768677,
+      "step": 1220
+    },
+    {
+      "epoch": 2.070736842105263,
+      "grad_norm": 0.10050549358129501,
+      "learning_rate": 2.66004783031385e-07,
+      "loss": 0.3756644487380981,
+      "step": 1230
+    },
+    {
+      "epoch": 2.087578947368421,
+      "grad_norm": 0.08914914727210999,
+      "learning_rate": 2.573904769860009e-07,
+      "loss": 0.3804330825805664,
+      "step": 1240
+    },
+    {
+      "epoch": 2.104421052631579,
+      "grad_norm": 0.08296852558851242,
+      "learning_rate": 2.488693517855016e-07,
+      "loss": 0.3978404521942139,
+      "step": 1250
+    },
+    {
+      "epoch": 2.1212631578947367,
+      "grad_norm": 0.13885149359703064,
+      "learning_rate": 2.404446802018533e-07,
+      "loss": 0.3935218334197998,
+      "step": 1260
+    },
+    {
+      "epoch": 2.138105263157895,
+      "grad_norm": 0.13195137679576874,
+      "learning_rate": 2.3211969796136305e-07,
+      "loss": 0.42966952323913576,
+      "step": 1270
+    },
+    {
+      "epoch": 2.1549473684210527,
+      "grad_norm": 0.13367892801761627,
+      "learning_rate": 2.2389760250191038e-07,
+      "loss": 0.3679579019546509,
+      "step": 1280
+    },
+    {
+      "epoch": 2.1717894736842105,
+      "grad_norm": 0.1288345605134964,
+      "learning_rate": 2.1578155174488343e-07,
+      "loss": 0.41324810981750487,
+      "step": 1290
+    },
+    {
+      "epoch": 2.1886315789473683,
+      "grad_norm": 0.09626021236181259,
+      "learning_rate": 2.0777466288229205e-07,
+      "loss": 0.40120248794555663,
+      "step": 1300
+    },
+    {
+      "epoch": 2.2054736842105265,
+      "grad_norm": 0.10264381766319275,
+      "learning_rate": 1.9988001117952485e-07,
+      "loss": 0.3501007080078125,
+      "step": 1310
+    },
+    {
+      "epoch": 2.2223157894736842,
+      "grad_norm": 0.09031466394662857,
+      "learning_rate": 1.9210062879420973e-07,
+      "loss": 0.3839429378509521,
+      "step": 1320
+    },
+    {
+      "epoch": 2.239157894736842,
+      "grad_norm": 0.12686079740524292,
+      "learning_rate": 1.8443950361162957e-07,
+      "loss": 0.4338528156280518,
+      "step": 1330
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 0.12199016660451889,
+      "learning_rate": 1.7689957809714346e-07,
+      "loss": 0.39229888916015626,
+      "step": 1340
+    },
+    {
+      "epoch": 2.272842105263158,
+      "grad_norm": 0.12029567360877991,
+      "learning_rate": 1.694837481660525e-07,
+      "loss": 0.38006880283355715,
+      "step": 1350
+    },
+    {
+      "epoch": 2.2896842105263158,
+      "grad_norm": 0.08686309307813644,
+      "learning_rate": 1.6219486207134313e-07,
+      "loss": 0.3808159589767456,
+      "step": 1360
+    },
+    {
+      "epoch": 2.3065263157894735,
+      "grad_norm": 0.10810462385416031,
+      "learning_rate": 1.5503571930973785e-07,
+      "loss": 0.401824426651001,
+      "step": 1370
+    },
+    {
+      "epoch": 2.3233684210526317,
+      "grad_norm": 0.10281873494386673,
+      "learning_rate": 1.480090695464723e-07,
+      "loss": 0.40149493217468263,
+      "step": 1380
+    },
+    {
+      "epoch": 2.3402105263157895,
+      "grad_norm": 0.09503985196352005,
+      "learning_rate": 1.4111761155920975e-07,
+      "loss": 0.38567726612091063,
+      "step": 1390
+    },
+    {
+      "epoch": 2.3570526315789473,
+      "grad_norm": 0.10420782119035721,
+      "learning_rate": 1.3436399220150212e-07,
+      "loss": 0.3759742736816406,
+      "step": 1400
+    },
+    {
+      "epoch": 2.3738947368421055,
+      "grad_norm": 0.10681115835905075,
+      "learning_rate": 1.2775080538619347e-07,
+      "loss": 0.3913698196411133,
+      "step": 1410
+    },
+    {
+      "epoch": 2.3907368421052633,
+      "grad_norm": 0.10323983430862427,
+      "learning_rate": 1.2128059108915595e-07,
+      "loss": 0.39077584743499755,
+      "step": 1420
+    },
+    {
+      "epoch": 2.407578947368421,
+      "grad_norm": 0.09566064178943634,
+      "learning_rate": 1.1495583437374263e-07,
+      "loss": 0.39895172119140626,
+      "step": 1430
+    },
+    {
+      "epoch": 2.424421052631579,
+      "grad_norm": 0.13018426299095154,
+      "learning_rate": 1.0877896443633117e-07,
+      "loss": 0.38982129096984863,
+      "step": 1440
+    },
+    {
+      "epoch": 2.441263157894737,
+      "grad_norm": 0.10760781168937683,
+      "learning_rate": 1.0275235367332347e-07,
+      "loss": 0.3756714344024658,
+      "step": 1450
+    },
+    {
+      "epoch": 2.458105263157895,
+      "grad_norm": 0.11606904864311218,
+      "learning_rate": 9.687831676996238e-08,
+      "loss": 0.37858171463012696,
+      "step": 1460
+    },
+    {
+      "epoch": 2.4749473684210526,
+      "grad_norm": 0.12957172095775604,
+      "learning_rate": 9.115910981131336e-08,
+      "loss": 0.40050196647644043,
+      "step": 1470
+    },
+    {
+      "epoch": 2.4917894736842103,
+      "grad_norm": 0.11186131089925766,
+      "learning_rate": 8.559692941575231e-08,
+      "loss": 0.3684133291244507,
+      "step": 1480
+    },
+    {
+      "epoch": 2.5086315789473685,
+      "grad_norm": 0.13279542326927185,
+      "learning_rate": 8.019391189129466e-08,
+      "loss": 0.3452518224716187,
+      "step": 1490
+    },
+    {
+      "epoch": 2.5254736842105263,
+      "grad_norm": 0.09041756391525269,
+      "learning_rate": 7.495213241508786e-08,
+      "loss": 0.36301617622375487,
+      "step": 1500
+    },
+    {
+      "epoch": 2.542315789473684,
+      "grad_norm": 0.10033190995454788,
+      "learning_rate": 6.987360423638205e-08,
+      "loss": 0.3706004858016968,
+      "step": 1510
+    },
+    {
+      "epoch": 2.559157894736842,
+      "grad_norm": 0.10681814700365067,
+      "learning_rate": 6.49602779032865e-08,
+      "loss": 0.36011199951171874,
+      "step": 1520
+    },
+    {
+      "epoch": 2.576,
+      "grad_norm": 0.1008416935801506,
+      "learning_rate": 6.02140405136089e-08,
+      "loss": 0.37473766803741454,
+      "step": 1530
+    },
+    {
+      "epoch": 2.592842105263158,
+      "grad_norm": 0.11559010297060013,
+      "learning_rate": 5.5636714990062393e-08,
+      "loss": 0.39232525825500486,
+      "step": 1540
+    },
+    {
+      "epoch": 2.609684210526316,
+      "grad_norm": 0.10601615905761719,
+      "learning_rate": 5.1230059380123034e-08,
+      "loss": 0.34370343685150145,
+      "step": 1550
+    },
+    {
+      "epoch": 2.626526315789474,
+      "grad_norm": 0.11516924202442169,
+      "learning_rate": 4.699576618080331e-08,
+      "loss": 0.39509878158569334,
+      "step": 1560
+    },
+    {
+      "epoch": 2.6433684210526316,
+      "grad_norm": 0.11444627493619919,
+      "learning_rate": 4.293546168860163e-08,
+      "loss": 0.3881126165390015,
+      "step": 1570
+    },
+    {
+      "epoch": 2.6602105263157894,
+      "grad_norm": 0.09985339641571045,
+      "learning_rate": 3.9050705374879086e-08,
+      "loss": 0.34624040126800537,
+      "step": 1580
+    },
+    {
+      "epoch": 2.677052631578947,
+      "grad_norm": 0.10439962148666382,
+      "learning_rate": 3.534298928690166e-08,
+      "loss": 0.35141232013702395,
+      "step": 1590
+    },
+    {
+      "epoch": 2.6938947368421053,
+      "grad_norm": 0.12180087715387344,
+      "learning_rate": 3.181373747477822e-08,
+      "loss": 0.39980330467224123,
+      "step": 1600
+    },
+    {
+      "epoch": 2.710736842105263,
+      "grad_norm": 0.12150874733924866,
+      "learning_rate": 2.8464305444515112e-08,
+      "loss": 0.3560852766036987,
+      "step": 1610
+    },
+    {
+      "epoch": 2.7275789473684213,
+      "grad_norm": 0.11374734342098236,
+      "learning_rate": 2.5295979637397213e-08,
+      "loss": 0.39339067935943606,
+      "step": 1620
+    },
+    {
+      "epoch": 2.744421052631579,
+      "grad_norm": 0.11705286055803299,
+      "learning_rate": 2.2309976935894203e-08,
+      "loss": 0.38021705150604246,
+      "step": 1630
+    },
+    {
+      "epoch": 2.761263157894737,
+      "grad_norm": 0.09300459921360016,
+      "learning_rate": 1.9507444196284195e-08,
+      "loss": 0.3467890739440918,
+      "step": 1640
+    },
+    {
+      "epoch": 2.7781052631578946,
+      "grad_norm": 0.08709974586963654,
+      "learning_rate": 1.688945780817147e-08,
+      "loss": 0.38266596794128416,
+      "step": 1650
+    },
+    {
+      "epoch": 2.7949473684210524,
+      "grad_norm": 0.12327069044113159,
+      "learning_rate": 1.445702328106979e-08,
+      "loss": 0.34164865016937257,
+      "step": 1660
+    },
+    {
+      "epoch": 2.8117894736842106,
+      "grad_norm": 0.12361253052949905,
+      "learning_rate": 1.2211074858209103e-08,
+      "loss": 0.3876492977142334,
+      "step": 1670
+    },
+    {
+      "epoch": 2.8286315789473684,
+      "grad_norm": 0.120187908411026,
+      "learning_rate": 1.0152475157713392e-08,
+      "loss": 0.3703944206237793,
+      "step": 1680
+    },
+    {
+      "epoch": 2.845473684210526,
+      "grad_norm": 0.10741006582975388,
+      "learning_rate": 8.282014841288653e-09,
+      "loss": 0.3735771656036377,
+      "step": 1690
+    },
+    {
+      "epoch": 2.8623157894736844,
+      "grad_norm": 0.10451704263687134,
+      "learning_rate": 6.600412310547754e-09,
+      "loss": 0.3807518005371094,
+      "step": 1700
+    },
+    {
+      "epoch": 2.879157894736842,
+      "grad_norm": 0.10978730767965317,
+      "learning_rate": 5.1083134310882515e-09,
+      "loss": 0.3799649000167847,
+      "step": 1710
+    },
+    {
+      "epoch": 2.896,
+      "grad_norm": 0.09521365165710449,
+      "learning_rate": 3.806291284430274e-09,
+      "loss": 0.3580306053161621,
+      "step": 1720
+    },
+    {
+      "epoch": 2.9128421052631577,
+      "grad_norm": 0.11443010717630386,
+      "learning_rate": 2.6948459479087526e-09,
+      "loss": 0.4088387966156006,
+      "step": 1730
+    },
+    {
+      "epoch": 2.929684210526316,
+      "grad_norm": 0.10477516055107117,
+      "learning_rate": 1.7744043026048372e-09,
+      "loss": 0.3971900463104248,
+      "step": 1740
+    },
+    {
+      "epoch": 2.9465263157894737,
+      "grad_norm": 0.11358557641506195,
+      "learning_rate": 1.0453198693907706e-09,
+      "loss": 0.35434761047363283,
+      "step": 1750
+    },
+    {
+      "epoch": 2.9633684210526314,
+      "grad_norm": 0.10436985641717911,
+      "learning_rate": 5.07872673150278e-10,
+      "loss": 0.40241618156433107,
+      "step": 1760
+    },
+    {
+      "epoch": 2.9802105263157896,
+      "grad_norm": 0.10179495811462402,
+      "learning_rate": 1.6226913522743302e-10,
+      "loss": 0.34090123176574705,
+      "step": 1770
+    },
+    {
+      "epoch": 2.9970526315789474,
+      "grad_norm": 0.1047094464302063,
+      "learning_rate": 8.641994144853448e-12,
+      "loss": 0.33390347957611083,
+      "step": 1780
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1782,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.258875338498253e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..899af07a0757e3f45323d537449b3b8525aa272c
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a74aefb1dc1340a25f29ab8370384b9ed24b2d921d7749ece7bbcfcfdf00d497
+size 33384443
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d83f12eef5a7d73283047b2f05c1ffdd6346556a
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,26 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<end_of_turn>",
+  "image_token": "<image_soft_token>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "processor_class": "Gemma3Processor",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/train_results.json b/train_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..f299a99a5a1b6ed7cffbcf87a8ae647059ec8118
--- /dev/null
+++ b/train_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 3.258875338498253e+16,
+    "train_loss": 0.45725877370630985,
+    "train_runtime": 3399.7742,
+    "train_samples_per_second": 4.191,
+    "train_steps_per_second": 0.524
+}
\ No newline at end of file
diff --git a/trainer_log.jsonl b/trainer_log.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..b9c657442dcdeb9cda463b4788e346dab814460b
--- /dev/null
+++ b/trainer_log.jsonl
@@ -0,0 +1,179 @@
+{"current_steps": 10, "total_steps": 1782, "loss": 0.7252199172973632, "lr": 5.027932960893855e-08, "epoch": 0.016842105263157894, "percentage": 0.56, "elapsed_time": "0:00:25", "remaining_time": "1:14:15"}
+{"current_steps": 20, "total_steps": 1782, "loss": 0.6507451057434082, "lr": 1.0614525139664805e-07, "epoch": 0.03368421052631579, "percentage": 1.12, "elapsed_time": "0:00:46", "remaining_time": "1:08:40"}
+{"current_steps": 30, "total_steps": 1782, "loss": 0.7381344795227051, "lr": 1.6201117318435754e-07, "epoch": 0.05052631578947368, "percentage": 1.68, "elapsed_time": "0:01:07", "remaining_time": "1:05:28"}
+{"current_steps": 40, "total_steps": 1782, "loss": 0.7012194156646728, "lr": 2.17877094972067e-07, "epoch": 0.06736842105263158, "percentage": 2.24, "elapsed_time": "0:01:26", "remaining_time": "1:03:02"}
+{"current_steps": 50, "total_steps": 1782, "loss": 0.6083873748779297, "lr": 2.7374301675977653e-07, "epoch": 0.08421052631578947, "percentage": 2.81, "elapsed_time": "0:01:45", "remaining_time": "1:01:10"}
+{"current_steps": 60, "total_steps": 1782, "loss": 0.6980491638183594, "lr": 3.29608938547486e-07, "epoch": 0.10105263157894737, "percentage": 3.37, "elapsed_time": "0:02:04", "remaining_time": "0:59:38"}
+{"current_steps": 70, "total_steps": 1782, "loss": 0.708641767501831, "lr": 3.8547486033519547e-07, "epoch": 0.11789473684210526, "percentage": 3.93, "elapsed_time": "0:02:24", "remaining_time": "0:58:54"}
+{"current_steps": 80, "total_steps": 1782, "loss": 0.6742453098297119, "lr": 4.41340782122905e-07, "epoch": 0.13473684210526315, "percentage": 4.49, "elapsed_time": "0:02:43", "remaining_time": "0:58:03"}
+{"current_steps": 90, "total_steps": 1782, "loss": 0.6590609550476074, "lr": 4.972067039106145e-07, "epoch": 0.15157894736842106, "percentage": 5.05, "elapsed_time": "0:03:02", "remaining_time": "0:57:10"}
+{"current_steps": 100, "total_steps": 1782, "loss": 0.704926872253418, "lr": 5.53072625698324e-07, "epoch": 0.16842105263157894, "percentage": 5.61, "elapsed_time": "0:03:20", "remaining_time": "0:56:16"}
+{"current_steps": 110, "total_steps": 1782, "loss": 0.7445036888122558, "lr": 6.089385474860335e-07, "epoch": 0.18526315789473685, "percentage": 6.17, "elapsed_time": "0:03:40", "remaining_time": "0:55:52"}
+{"current_steps": 120, "total_steps": 1782, "loss": 0.7476531028747558, "lr": 6.64804469273743e-07, "epoch": 0.20210526315789473, "percentage": 6.73, "elapsed_time": "0:03:59", "remaining_time": "0:55:13"}
+{"current_steps": 130, "total_steps": 1782, "loss": 0.7291872501373291, "lr": 7.206703910614524e-07, "epoch": 0.21894736842105264, "percentage": 7.3, "elapsed_time": "0:04:17", "remaining_time": "0:54:37"}
+{"current_steps": 140, "total_steps": 1782, "loss": 0.721175241470337, "lr": 7.76536312849162e-07, "epoch": 0.23578947368421052, "percentage": 7.86, "elapsed_time": "0:04:37", "remaining_time": "0:54:09"}
+{"current_steps": 150, "total_steps": 1782, "loss": 0.7556095600128174, "lr": 8.324022346368714e-07, "epoch": 0.25263157894736843, "percentage": 8.42, "elapsed_time": "0:04:55", "remaining_time": "0:53:35"}
+{"current_steps": 160, "total_steps": 1782, "loss": 0.7328392505645752, "lr": 8.88268156424581e-07, "epoch": 0.2694736842105263, "percentage": 8.98, "elapsed_time": "0:05:14", "remaining_time": "0:53:05"}
+{"current_steps": 170, "total_steps": 1782, "loss": 0.6990129470825195, "lr": 9.441340782122904e-07, "epoch": 0.2863157894736842, "percentage": 9.54, "elapsed_time": "0:05:32", "remaining_time": "0:52:35"}
+{"current_steps": 180, "total_steps": 1782, "loss": 0.6694639205932618, "lr": 1e-06, "epoch": 0.3031578947368421, "percentage": 10.1, "elapsed_time": "0:05:51", "remaining_time": "0:52:06"}
+{"current_steps": 190, "total_steps": 1782, "loss": 0.7123252868652343, "lr": 9.999039806396227e-07, "epoch": 0.32, "percentage": 10.66, "elapsed_time": "0:06:09", "remaining_time": "0:51:37"}
+{"current_steps": 200, "total_steps": 1782, "loss": 0.6858412742614746, "lr": 9.996159594373611e-07, "epoch": 0.3368421052631579, "percentage": 11.22, "elapsed_time": "0:06:28", "remaining_time": "0:51:10"}
+{"current_steps": 210, "total_steps": 1782, "loss": 0.6541069507598877, "lr": 9.991360470156615e-07, "epoch": 0.35368421052631577, "percentage": 11.78, "elapsed_time": "0:06:47", "remaining_time": "0:50:48"}
+{"current_steps": 220, "total_steps": 1782, "loss": 0.6506116390228271, "lr": 9.984644276980594e-07, "epoch": 0.3705263157894737, "percentage": 12.35, "elapsed_time": "0:07:06", "remaining_time": "0:50:25"}
+{"current_steps": 230, "total_steps": 1782, "loss": 0.6540626049041748, "lr": 9.976013594383835e-07, "epoch": 0.3873684210526316, "percentage": 12.91, "elapsed_time": "0:07:24", "remaining_time": "0:50:02"}
+{"current_steps": 240, "total_steps": 1782, "loss": 0.6737770557403564, "lr": 9.965471737216833e-07, "epoch": 0.40421052631578946, "percentage": 13.47, "elapsed_time": "0:07:43", "remaining_time": "0:49:36"}
+{"current_steps": 250, "total_steps": 1782, "loss": 0.6755708217620849, "lr": 9.953022754369114e-07, "epoch": 0.42105263157894735, "percentage": 14.03, "elapsed_time": "0:08:01", "remaining_time": "0:49:12"}
+{"current_steps": 260, "total_steps": 1782, "loss": 0.6578442573547363, "lr": 9.938671427214158e-07, "epoch": 0.4378947368421053, "percentage": 14.59, "elapsed_time": "0:08:20", "remaining_time": "0:48:48"}
+{"current_steps": 270, "total_steps": 1782, "loss": 0.639409875869751, "lr": 9.922423267772986e-07, "epoch": 0.45473684210526316, "percentage": 15.15, "elapsed_time": "0:08:38", "remaining_time": "0:48:24"}
+{"current_steps": 280, "total_steps": 1782, "loss": 0.5995691776275635, "lr": 9.904284516597102e-07, "epoch": 0.47157894736842104, "percentage": 15.71, "elapsed_time": "0:08:56", "remaining_time": "0:47:59"}
+{"current_steps": 290, "total_steps": 1782, "loss": 0.5898309707641601, "lr": 9.884262140371648e-07, "epoch": 0.4884210526315789, "percentage": 16.27, "elapsed_time": "0:09:15", "remaining_time": "0:47:36"}
+{"current_steps": 300, "total_steps": 1782, "loss": 0.6371779441833496, "lr": 9.862363829239662e-07, "epoch": 0.5052631578947369, "percentage": 16.84, "elapsed_time": "0:09:33", "remaining_time": "0:47:14"}
+{"current_steps": 310, "total_steps": 1782, "loss": 0.5795581817626954, "lr": 9.838597993848456e-07, "epoch": 0.5221052631578947, "percentage": 17.4, "elapsed_time": "0:09:53", "remaining_time": "0:46:55"}
+{"current_steps": 320, "total_steps": 1782, "loss": 0.5668415546417236, "lr": 9.81297376211928e-07, "epoch": 0.5389473684210526, "percentage": 17.96, "elapsed_time": "0:10:11", "remaining_time": "0:46:33"}
+{"current_steps": 330, "total_steps": 1782, "loss": 0.5933257102966308, "lr": 9.785500975741498e-07, "epoch": 0.5557894736842105, "percentage": 18.52, "elapsed_time": "0:10:34", "remaining_time": "0:46:30"}
+{"current_steps": 340, "total_steps": 1782, "loss": 0.5574678897857666, "lr": 9.756190186392615e-07, "epoch": 0.5726315789473684, "percentage": 19.08, "elapsed_time": "0:10:57", "remaining_time": "0:46:29"}
+{"current_steps": 350, "total_steps": 1782, "loss": 0.5532425880432129, "lr": 9.725052651685612e-07, "epoch": 0.5894736842105263, "percentage": 19.64, "elapsed_time": "0:11:20", "remaining_time": "0:46:23"}
+{"current_steps": 360, "total_steps": 1782, "loss": 0.5613389492034913, "lr": 9.692100330845153e-07, "epoch": 0.6063157894736843, "percentage": 20.2, "elapsed_time": "0:11:40", "remaining_time": "0:46:08"}
+{"current_steps": 370, "total_steps": 1782, "loss": 0.5131485939025879, "lr": 9.657345880114318e-07, "epoch": 0.6231578947368421, "percentage": 20.76, "elapsed_time": "0:12:00", "remaining_time": "0:45:47"}
+{"current_steps": 380, "total_steps": 1782, "loss": 0.6279027462005615, "lr": 9.620802647893623e-07, "epoch": 0.64, "percentage": 21.32, "elapsed_time": "0:12:20", "remaining_time": "0:45:31"}
+{"current_steps": 390, "total_steps": 1782, "loss": 0.5403085231781006, "lr": 9.58248466961421e-07, "epoch": 0.6568421052631579, "percentage": 21.89, "elapsed_time": "0:12:41", "remaining_time": "0:45:18"}
+{"current_steps": 400, "total_steps": 1782, "loss": 0.5678809642791748, "lr": 9.542406662347137e-07, "epoch": 0.6736842105263158, "percentage": 22.45, "elapsed_time": "0:13:03", "remaining_time": "0:45:05"}
+{"current_steps": 410, "total_steps": 1782, "loss": 0.5479135036468505, "lr": 9.500584019150895e-07, "epoch": 0.6905263157894737, "percentage": 23.01, "elapsed_time": "0:13:24", "remaining_time": "0:44:53"}
+{"current_steps": 420, "total_steps": 1782, "loss": 0.5604462623596191, "lr": 9.45703280315928e-07, "epoch": 0.7073684210526315, "percentage": 23.57, "elapsed_time": "0:13:45", "remaining_time": "0:44:38"}
+{"current_steps": 430, "total_steps": 1782, "loss": 0.4704423427581787, "lr": 9.411769741411903e-07, "epoch": 0.7242105263157895, "percentage": 24.13, "elapsed_time": "0:14:06", "remaining_time": "0:44:23"}
+{"current_steps": 440, "total_steps": 1782, "loss": 0.560968017578125, "lr": 9.364812218429721e-07, "epoch": 0.7410526315789474, "percentage": 24.69, "elapsed_time": "0:14:27", "remaining_time": "0:44:04"}
+{"current_steps": 450, "total_steps": 1782, "loss": 0.5088452816009521, "lr": 9.316178269538014e-07, "epoch": 0.7578947368421053, "percentage": 25.25, "elapsed_time": "0:14:48", "remaining_time": "0:43:49"}
+{"current_steps": 460, "total_steps": 1782, "loss": 0.5030550956726074, "lr": 9.265886573939446e-07, "epoch": 0.7747368421052632, "percentage": 25.81, "elapsed_time": "0:15:10", "remaining_time": "0:43:35"}
+{"current_steps": 470, "total_steps": 1782, "loss": 0.46353440284729003, "lr": 9.213956447539792e-07, "epoch": 0.791578947368421, "percentage": 26.37, "elapsed_time": "0:15:31", "remaining_time": "0:43:20"}
+{"current_steps": 480, "total_steps": 1782, "loss": 0.49871411323547366, "lr": 9.160407835529136e-07, "epoch": 0.8084210526315789, "percentage": 26.94, "elapsed_time": "0:15:52", "remaining_time": "0:43:03"}
+{"current_steps": 490, "total_steps": 1782, "loss": 0.4416178226470947, "lr": 9.105261304721375e-07, "epoch": 0.8252631578947368, "percentage": 27.5, "elapsed_time": "0:16:13", "remaining_time": "0:42:47"}
+{"current_steps": 500, "total_steps": 1782, "loss": 0.39783194065093996, "lr": 9.048538035654969e-07, "epoch": 0.8421052631578947, "percentage": 28.06, "elapsed_time": "0:16:34", "remaining_time": "0:42:30"}
+{"current_steps": 510, "total_steps": 1782, "loss": 0.4318229198455811, "lr": 8.990259814457977e-07, "epoch": 0.8589473684210527, "percentage": 28.62, "elapsed_time": "0:16:58", "remaining_time": "0:42:19"}
+{"current_steps": 520, "total_steps": 1782, "loss": 0.42445807456970214, "lr": 8.930449024480491e-07, "epoch": 0.8757894736842106, "percentage": 29.18, "elapsed_time": "0:17:21", "remaining_time": "0:42:07"}
+{"current_steps": 530, "total_steps": 1782, "loss": 0.46429901123046874, "lr": 8.8691286376977e-07, "epoch": 0.8926315789473684, "percentage": 29.74, "elapsed_time": "0:17:43", "remaining_time": "0:41:51"}
+{"current_steps": 540, "total_steps": 1782, "loss": 0.3975703239440918, "lr": 8.806322205886873e-07, "epoch": 0.9094736842105263, "percentage": 30.3, "elapsed_time": "0:18:04", "remaining_time": "0:41:34"}
+{"current_steps": 550, "total_steps": 1782, "loss": 0.4458911418914795, "lr": 8.74205385158165e-07, "epoch": 0.9263157894736842, "percentage": 30.86, "elapsed_time": "0:18:25", "remaining_time": "0:41:16"}
+{"current_steps": 560, "total_steps": 1782, "loss": 0.45571184158325195, "lr": 8.676348258807121e-07, "epoch": 0.9431578947368421, "percentage": 31.43, "elapsed_time": "0:18:46", "remaining_time": "0:40:58"}
+{"current_steps": 570, "total_steps": 1782, "loss": 0.4039600372314453, "lr": 8.609230663599254e-07, "epoch": 0.96, "percentage": 31.99, "elapsed_time": "0:19:07", "remaining_time": "0:40:38"}
+{"current_steps": 580, "total_steps": 1782, "loss": 0.4382494926452637, "lr": 8.540726844312294e-07, "epoch": 0.9768421052631578, "percentage": 32.55, "elapsed_time": "0:19:26", "remaining_time": "0:40:16"}
+{"current_steps": 590, "total_steps": 1782, "loss": 0.4306180477142334, "lr": 8.470863111717889e-07, "epoch": 0.9936842105263158, "percentage": 33.11, "elapsed_time": "0:19:45", "remaining_time": "0:39:54"}
+{"current_steps": 600, "total_steps": 1782, "loss": 0.39806089401245115, "lr": 8.399666298899706e-07, "epoch": 1.0101052631578948, "percentage": 33.67, "elapsed_time": "0:20:04", "remaining_time": "0:39:32"}
+{"current_steps": 610, "total_steps": 1782, "loss": 0.4271697044372559, "lr": 8.327163750947457e-07, "epoch": 1.0269473684210526, "percentage": 34.23, "elapsed_time": "0:20:23", "remaining_time": "0:39:11"}
+{"current_steps": 620, "total_steps": 1782, "loss": 0.3939049243927002, "lr": 8.253383314454263e-07, "epoch": 1.0437894736842106, "percentage": 34.79, "elapsed_time": "0:20:42", "remaining_time": "0:38:48"}
+{"current_steps": 630, "total_steps": 1782, "loss": 0.43197131156921387, "lr": 8.178353326821404e-07, "epoch": 1.0606315789473684, "percentage": 35.35, "elapsed_time": "0:21:01", "remaining_time": "0:38:25"}
+{"current_steps": 640, "total_steps": 1782, "loss": 0.437807559967041, "lr": 8.102102605374566e-07, "epoch": 1.0774736842105264, "percentage": 35.91, "elapsed_time": "0:21:19", "remaining_time": "0:38:03"}
+{"current_steps": 650, "total_steps": 1782, "loss": 0.38409013748168946, "lr": 8.024660436295759e-07, "epoch": 1.0943157894736841, "percentage": 36.48, "elapsed_time": "0:21:37", "remaining_time": "0:37:40"}
+{"current_steps": 660, "total_steps": 1782, "loss": 0.4204962730407715, "lr": 7.946056563375145e-07, "epoch": 1.1111578947368421, "percentage": 37.04, "elapsed_time": "0:21:56", "remaining_time": "0:37:17"}
+{"current_steps": 670, "total_steps": 1782, "loss": 0.42113161087036133, "lr": 7.866321176587128e-07, "epoch": 1.1280000000000001, "percentage": 37.6, "elapsed_time": "0:22:14", "remaining_time": "0:36:55"}
+{"current_steps": 680, "total_steps": 1782, "loss": 0.4151731491088867, "lr": 7.785484900495065e-07, "epoch": 1.1448421052631579, "percentage": 38.16, "elapsed_time": "0:22:33", "remaining_time": "0:36:32"}
+{"current_steps": 690, "total_steps": 1782, "loss": 0.38312902450561526, "lr": 7.703578782489058e-07, "epoch": 1.1616842105263159, "percentage": 38.72, "elapsed_time": "0:22:51", "remaining_time": "0:36:10"}
+{"current_steps": 700, "total_steps": 1782, "loss": 0.42612557411193847, "lr": 7.620634280861351e-07, "epoch": 1.1785263157894736, "percentage": 39.28, "elapsed_time": "0:23:09", "remaining_time": "0:35:48"}
+{"current_steps": 710, "total_steps": 1782, "loss": 0.4306772708892822, "lr": 7.536683252723923e-07, "epoch": 1.1953684210526316, "percentage": 39.84, "elapsed_time": "0:23:28", "remaining_time": "0:35:27"}
+{"current_steps": 720, "total_steps": 1782, "loss": 0.38483757972717286, "lr": 7.451757941772868e-07, "epoch": 1.2122105263157894, "percentage": 40.4, "elapsed_time": "0:23:47", "remaining_time": "0:35:05"}
+{"current_steps": 730, "total_steps": 1782, "loss": 0.4030342102050781, "lr": 7.365890965904337e-07, "epoch": 1.2290526315789474, "percentage": 40.97, "elapsed_time": "0:24:05", "remaining_time": "0:34:43"}
+{"current_steps": 740, "total_steps": 1782, "loss": 0.4091166973114014, "lr": 7.279115304686733e-07, "epoch": 1.2458947368421052, "percentage": 41.53, "elapsed_time": "0:24:24", "remaining_time": "0:34:22"}
+{"current_steps": 750, "total_steps": 1782, "loss": 0.41426806449890136, "lr": 7.191464286694e-07, "epoch": 1.2627368421052632, "percentage": 42.09, "elapsed_time": "0:24:43", "remaining_time": "0:34:00"}
+{"current_steps": 760, "total_steps": 1782, "loss": 0.38181486129760744, "lr": 7.102971576704875e-07, "epoch": 1.279578947368421, "percentage": 42.65, "elapsed_time": "0:25:01", "remaining_time": "0:33:39"}
+{"current_steps": 770, "total_steps": 1782, "loss": 0.39824953079223635, "lr": 7.013671162773003e-07, "epoch": 1.296421052631579, "percentage": 43.21, "elapsed_time": "0:25:19", "remaining_time": "0:33:17"}
+{"current_steps": 780, "total_steps": 1782, "loss": 0.40348024368286134, "lr": 6.923597343172891e-07, "epoch": 1.313263157894737, "percentage": 43.77, "elapsed_time": "0:25:39", "remaining_time": "0:32:57"}
+{"current_steps": 790, "total_steps": 1782, "loss": 0.38022048473358155, "lr": 6.83278471322672e-07, "epoch": 1.3301052631578947, "percentage": 44.33, "elapsed_time": "0:25:57", "remaining_time": "0:32:35"}
+{"current_steps": 800, "total_steps": 1782, "loss": 0.42791285514831545, "lr": 6.741268152017057e-07, "epoch": 1.3469473684210527, "percentage": 44.89, "elapsed_time": "0:26:16", "remaining_time": "0:32:14"}
+{"current_steps": 810, "total_steps": 1782, "loss": 0.4263493061065674, "lr": 6.649082808990585e-07, "epoch": 1.3637894736842107, "percentage": 45.45, "elapsed_time": "0:26:35", "remaining_time": "0:31:54"}
+{"current_steps": 820, "total_steps": 1782, "loss": 0.37379777431488037, "lr": 6.556264090457998e-07, "epoch": 1.3806315789473684, "percentage": 46.02, "elapsed_time": "0:26:53", "remaining_time": "0:31:33"}
+{"current_steps": 830, "total_steps": 1782, "loss": 0.38636391162872313, "lr": 6.462847645995237e-07, "epoch": 1.3974736842105262, "percentage": 46.58, "elapsed_time": "0:27:12", "remaining_time": "0:31:11"}
+{"current_steps": 840, "total_steps": 1782, "loss": 0.408221435546875, "lr": 6.368869354751284e-07, "epoch": 1.4143157894736842, "percentage": 47.14, "elapsed_time": "0:27:30", "remaining_time": "0:30:51"}
+{"current_steps": 850, "total_steps": 1782, "loss": 0.3951406717300415, "lr": 6.274365311667797e-07, "epoch": 1.4311578947368422, "percentage": 47.7, "elapsed_time": "0:27:49", "remaining_time": "0:30:30"}
+{"current_steps": 860, "total_steps": 1782, "loss": 0.3732129096984863, "lr": 6.179371813615859e-07, "epoch": 1.448, "percentage": 48.26, "elapsed_time": "0:28:07", "remaining_time": "0:30:09"}
+{"current_steps": 870, "total_steps": 1782, "loss": 0.38601529598236084, "lr": 6.083925345455158e-07, "epoch": 1.464842105263158, "percentage": 48.82, "elapsed_time": "0:28:26", "remaining_time": "0:29:49"}
+{"current_steps": 880, "total_steps": 1782, "loss": 0.3859985828399658, "lr": 5.988062566020986e-07, "epoch": 1.4816842105263157, "percentage": 49.38, "elapsed_time": "0:28:45", "remaining_time": "0:29:28"}
+{"current_steps": 890, "total_steps": 1782, "loss": 0.3983951807022095, "lr": 5.891820294044408e-07, "epoch": 1.4985263157894737, "percentage": 49.94, "elapsed_time": "0:29:04", "remaining_time": "0:29:08"}
+{"current_steps": 900, "total_steps": 1782, "loss": 0.41107850074768065, "lr": 5.795235494011007e-07, "epoch": 1.5153684210526315, "percentage": 50.51, "elapsed_time": "0:29:22", "remaining_time": "0:28:47"}
+{"current_steps": 910, "total_steps": 1782, "loss": 0.3708331823348999, "lr": 5.698345261963668e-07, "epoch": 1.5322105263157895, "percentage": 51.07, "elapsed_time": "0:29:42", "remaining_time": "0:28:27"}
+{"current_steps": 920, "total_steps": 1782, "loss": 0.387884521484375, "lr": 5.601186811254825e-07, "epoch": 1.5490526315789475, "percentage": 51.63, "elapsed_time": "0:30:00", "remaining_time": "0:28:06"}
+{"current_steps": 930, "total_steps": 1782, "loss": 0.43808717727661134, "lr": 5.503797458253646e-07, "epoch": 1.5658947368421052, "percentage": 52.19, "elapsed_time": "0:30:18", "remaining_time": "0:27:46"}
+{"current_steps": 940, "total_steps": 1782, "loss": 0.41345391273498533, "lr": 5.406214608013662e-07, "epoch": 1.582736842105263, "percentage": 52.75, "elapsed_time": "0:30:37", "remaining_time": "0:27:25"}
+{"current_steps": 950, "total_steps": 1782, "loss": 0.40022664070129393, "lr": 5.308475739906328e-07, "epoch": 1.5995789473684212, "percentage": 53.31, "elapsed_time": "0:30:55", "remaining_time": "0:27:05"}
+{"current_steps": 960, "total_steps": 1782, "loss": 0.3909924983978271, "lr": 5.210618393226045e-07, "epoch": 1.616421052631579, "percentage": 53.87, "elapsed_time": "0:31:14", "remaining_time": "0:26:44"}
+{"current_steps": 970, "total_steps": 1782, "loss": 0.37143146991729736, "lr": 5.112680152772156e-07, "epoch": 1.6332631578947368, "percentage": 54.43, "elapsed_time": "0:31:32", "remaining_time": "0:26:24"}
+{"current_steps": 980, "total_steps": 1782, "loss": 0.38103113174438474, "lr": 5.01469863441348e-07, "epoch": 1.6501052631578947, "percentage": 54.99, "elapsed_time": "0:31:51", "remaining_time": "0:26:04"}
+{"current_steps": 990, "total_steps": 1782, "loss": 0.4071629524230957, "lr": 4.916711470640907e-07, "epoch": 1.6669473684210527, "percentage": 55.56, "elapsed_time": "0:32:10", "remaining_time": "0:25:44"}
+{"current_steps": 1000, "total_steps": 1782, "loss": 0.417419958114624, "lr": 4.818756296113595e-07, "epoch": 1.6837894736842105, "percentage": 56.12, "elapsed_time": "0:32:28", "remaining_time": "0:25:23"}
+{"current_steps": 1010, "total_steps": 1782, "loss": 0.3998772859573364, "lr": 4.7208707332043623e-07, "epoch": 1.7006315789473683, "percentage": 56.68, "elapsed_time": "0:32:48", "remaining_time": "0:25:04"}
+{"current_steps": 1020, "total_steps": 1782, "loss": 0.38056583404541017, "lr": 4.6230923775497714e-07, "epoch": 1.7174736842105263, "percentage": 57.24, "elapsed_time": "0:33:06", "remaining_time": "0:24:44"}
+{"current_steps": 1030, "total_steps": 1782, "loss": 0.39371190071105955, "lr": 4.5254587836104964e-07, "epoch": 1.7343157894736843, "percentage": 57.8, "elapsed_time": "0:33:25", "remaining_time": "0:24:23"}
+{"current_steps": 1040, "total_steps": 1782, "loss": 0.4280440330505371, "lr": 4.4280074502475017e-07, "epoch": 1.751157894736842, "percentage": 58.36, "elapsed_time": "0:33:43", "remaining_time": "0:24:03"}
+{"current_steps": 1050, "total_steps": 1782, "loss": 0.3791615962982178, "lr": 4.3307758063195796e-07, "epoch": 1.768, "percentage": 58.92, "elapsed_time": "0:34:02", "remaining_time": "0:23:43"}
+{"current_steps": 1060, "total_steps": 1782, "loss": 0.347782301902771, "lr": 4.233801196307762e-07, "epoch": 1.784842105263158, "percentage": 59.48, "elapsed_time": "0:34:20", "remaining_time": "0:23:23"}
+{"current_steps": 1070, "total_steps": 1782, "loss": 0.38370628356933595, "lr": 4.1371208659721536e-07, "epoch": 1.8016842105263158, "percentage": 60.04, "elapsed_time": "0:34:39", "remaining_time": "0:23:03"}
+{"current_steps": 1080, "total_steps": 1782, "loss": 0.40404376983642576, "lr": 4.0407719480466736e-07, "epoch": 1.8185263157894735, "percentage": 60.61, "elapsed_time": "0:34:57", "remaining_time": "0:22:43"}
+{"current_steps": 1090, "total_steps": 1782, "loss": 0.4167450428009033, "lr": 3.944791447977213e-07, "epoch": 1.8353684210526315, "percentage": 61.17, "elapsed_time": "0:35:16", "remaining_time": "0:22:23"}
+{"current_steps": 1100, "total_steps": 1782, "loss": 0.4046513080596924, "lr": 3.849216229708671e-07, "epoch": 1.8522105263157895, "percentage": 61.73, "elapsed_time": "0:35:34", "remaining_time": "0:22:03"}
+{"current_steps": 1110, "total_steps": 1782, "loss": 0.39672977924346925, "lr": 3.7540830015263526e-07, "epoch": 1.8690526315789473, "percentage": 62.29, "elapsed_time": "0:35:53", "remaining_time": "0:21:43"}
+{"current_steps": 1120, "total_steps": 1782, "loss": 0.39356396198272703, "lr": 3.6594283019571416e-07, "epoch": 1.8858947368421053, "percentage": 62.85, "elapsed_time": "0:36:11", "remaining_time": "0:21:23"}
+{"current_steps": 1130, "total_steps": 1782, "loss": 0.42082643508911133, "lr": 3.565288485735874e-07, "epoch": 1.9027368421052633, "percentage": 63.41, "elapsed_time": "0:36:30", "remaining_time": "0:21:03"}
+{"current_steps": 1140, "total_steps": 1782, "loss": 0.34105117321014405, "lr": 3.4716997098423085e-07, "epoch": 1.919578947368421, "percentage": 63.97, "elapsed_time": "0:36:48", "remaining_time": "0:20:43"}
+{"current_steps": 1150, "total_steps": 1782, "loss": 0.3924069404602051, "lr": 3.378697919614045e-07, "epoch": 1.9364210526315788, "percentage": 64.53, "elapsed_time": "0:37:06", "remaining_time": "0:20:23"}
+{"current_steps": 1160, "total_steps": 1782, "loss": 0.3922377586364746, "lr": 3.286318834940729e-07, "epoch": 1.9532631578947368, "percentage": 65.1, "elapsed_time": "0:37:25", "remaining_time": "0:20:03"}
+{"current_steps": 1170, "total_steps": 1782, "loss": 0.3745201587677002, "lr": 3.1945979365448517e-07, "epoch": 1.9701052631578948, "percentage": 65.66, "elapsed_time": "0:37:43", "remaining_time": "0:19:44"}
+{"current_steps": 1180, "total_steps": 1782, "loss": 0.40110602378845217, "lr": 3.103570452354402e-07, "epoch": 1.9869473684210526, "percentage": 66.22, "elapsed_time": "0:38:02", "remaining_time": "0:19:24"}
+{"current_steps": 1190, "total_steps": 1782, "loss": 0.3981154918670654, "lr": 3.013271343972613e-07, "epoch": 2.0033684210526315, "percentage": 66.78, "elapsed_time": "0:38:20", "remaining_time": "0:19:04"}
+{"current_steps": 1200, "total_steps": 1782, "loss": 0.3726134061813354, "lr": 2.9237352932500046e-07, "epoch": 2.0202105263157897, "percentage": 67.34, "elapsed_time": "0:38:38", "remaining_time": "0:18:44"}
+{"current_steps": 1210, "total_steps": 1782, "loss": 0.42558698654174804, "lr": 2.8349966889638615e-07, "epoch": 2.0370526315789474, "percentage": 67.9, "elapsed_time": "0:38:58", "remaining_time": "0:18:25"}
+{"current_steps": 1220, "total_steps": 1782, "loss": 0.3682931184768677, "lr": 2.747089613610278e-07, "epoch": 2.053894736842105, "percentage": 68.46, "elapsed_time": "0:39:16", "remaining_time": "0:18:05"}
+{"current_steps": 1230, "total_steps": 1782, "loss": 0.3756644487380981, "lr": 2.66004783031385e-07, "epoch": 2.070736842105263, "percentage": 69.02, "elapsed_time": "0:39:34", "remaining_time": "0:17:45"}
+{"current_steps": 1240, "total_steps": 1782, "loss": 0.3804330825805664, "lr": 2.573904769860009e-07, "epoch": 2.087578947368421, "percentage": 69.58, "elapsed_time": "0:39:53", "remaining_time": "0:17:26"}
+{"current_steps": 1250, "total_steps": 1782, "loss": 0.3978404521942139, "lr": 2.488693517855016e-07, "epoch": 2.104421052631579, "percentage": 70.15, "elapsed_time": "0:40:11", "remaining_time": "0:17:06"}
+{"current_steps": 1260, "total_steps": 1782, "loss": 0.3935218334197998, "lr": 2.404446802018533e-07, "epoch": 2.1212631578947367, "percentage": 70.71, "elapsed_time": "0:40:30", "remaining_time": "0:16:46"}
+{"current_steps": 1270, "total_steps": 1782, "loss": 0.42966952323913576, "lr": 2.3211969796136305e-07, "epoch": 2.138105263157895, "percentage": 71.27, "elapsed_time": "0:40:48", "remaining_time": "0:16:27"}
+{"current_steps": 1280, "total_steps": 1782, "loss": 0.3679579019546509, "lr": 2.2389760250191038e-07, "epoch": 2.1549473684210527, "percentage": 71.83, "elapsed_time": "0:41:06", "remaining_time": "0:16:07"}
+{"current_steps": 1290, "total_steps": 1782, "loss": 0.41324810981750487, "lr": 2.1578155174488343e-07, "epoch": 2.1717894736842105, "percentage": 72.39, "elapsed_time": "0:41:25", "remaining_time": "0:15:47"}
+{"current_steps": 1300, "total_steps": 1782, "loss": 0.40120248794555663, "lr": 2.0777466288229205e-07, "epoch": 2.1886315789473683, "percentage": 72.95, "elapsed_time": "0:41:44", "remaining_time": "0:15:28"}
+{"current_steps": 1310, "total_steps": 1782, "loss": 0.3501007080078125, "lr": 1.9988001117952485e-07, "epoch": 2.2054736842105265, "percentage": 73.51, "elapsed_time": "0:42:03", "remaining_time": "0:15:09"}
+{"current_steps": 1320, "total_steps": 1782, "loss": 0.3839429378509521, "lr": 1.9210062879420973e-07, "epoch": 2.2223157894736842, "percentage": 74.07, "elapsed_time": "0:42:22", "remaining_time": "0:14:49"}
+{"current_steps": 1330, "total_steps": 1782, "loss": 0.4338528156280518, "lr": 1.8443950361162957e-07, "epoch": 2.239157894736842, "percentage": 74.64, "elapsed_time": "0:42:40", "remaining_time": "0:14:30"}
+{"current_steps": 1340, "total_steps": 1782, "loss": 0.39229888916015626, "lr": 1.7689957809714346e-07, "epoch": 2.2560000000000002, "percentage": 75.2, "elapsed_time": "0:42:59", "remaining_time": "0:14:10"}
+{"current_steps": 1350, "total_steps": 1782, "loss": 0.38006880283355715, "lr": 1.694837481660525e-07, "epoch": 2.272842105263158, "percentage": 75.76, "elapsed_time": "0:43:17", "remaining_time": "0:13:51"}
+{"current_steps": 1360, "total_steps": 1782, "loss": 0.3808159589767456, "lr": 1.6219486207134313e-07, "epoch": 2.2896842105263158, "percentage": 76.32, "elapsed_time": "0:43:36", "remaining_time": "0:13:31"}
+{"current_steps": 1370, "total_steps": 1782, "loss": 0.401824426651001, "lr": 1.5503571930973785e-07, "epoch": 2.3065263157894735, "percentage": 76.88, "elapsed_time": "0:43:54", "remaining_time": "0:13:12"}
+{"current_steps": 1380, "total_steps": 1782, "loss": 0.40149493217468263, "lr": 1.480090695464723e-07, "epoch": 2.3233684210526317, "percentage": 77.44, "elapsed_time": "0:44:13", "remaining_time": "0:12:52"}
+{"current_steps": 1390, "total_steps": 1782, "loss": 0.38567726612091063, "lr": 1.4111761155920975e-07, "epoch": 2.3402105263157895, "percentage": 78.0, "elapsed_time": "0:44:31", "remaining_time": "0:12:33"}
+{"current_steps": 1400, "total_steps": 1782, "loss": 0.3759742736816406, "lr": 1.3436399220150212e-07, "epoch": 2.3570526315789473, "percentage": 78.56, "elapsed_time": "0:44:50", "remaining_time": "0:12:14"}
+{"current_steps": 1410, "total_steps": 1782, "loss": 0.3913698196411133, "lr": 1.2775080538619347e-07, "epoch": 2.3738947368421055, "percentage": 79.12, "elapsed_time": "0:45:09", "remaining_time": "0:11:54"}
+{"current_steps": 1420, "total_steps": 1782, "loss": 0.39077584743499755, "lr": 1.2128059108915595e-07, "epoch": 2.3907368421052633, "percentage": 79.69, "elapsed_time": "0:45:28", "remaining_time": "0:11:35"}
+{"current_steps": 1430, "total_steps": 1782, "loss": 0.39895172119140626, "lr": 1.1495583437374263e-07, "epoch": 2.407578947368421, "percentage": 80.25, "elapsed_time": "0:45:47", "remaining_time": "0:11:16"}
+{"current_steps": 1440, "total_steps": 1782, "loss": 0.38982129096984863, "lr": 1.0877896443633117e-07, "epoch": 2.424421052631579, "percentage": 80.81, "elapsed_time": "0:46:05", "remaining_time": "0:10:56"}
+{"current_steps": 1450, "total_steps": 1782, "loss": 0.3756714344024658, "lr": 1.0275235367332347e-07, "epoch": 2.441263157894737, "percentage": 81.37, "elapsed_time": "0:46:24", "remaining_time": "0:10:37"}
+{"current_steps": 1460, "total_steps": 1782, "loss": 0.37858171463012696, "lr": 9.687831676996238e-08, "epoch": 2.458105263157895, "percentage": 81.93, "elapsed_time": "0:46:42", "remaining_time": "0:10:18"}
+{"current_steps": 1470, "total_steps": 1782, "loss": 0.40050196647644043, "lr": 9.115910981131336e-08, "epoch": 2.4749473684210526, "percentage": 82.49, "elapsed_time": "0:47:01", "remaining_time": "0:09:58"}
+{"current_steps": 1480, "total_steps": 1782, "loss": 0.3684133291244507, "lr": 8.559692941575231e-08, "epoch": 2.4917894736842103, "percentage": 83.05, "elapsed_time": "0:47:19", "remaining_time": "0:09:39"}
+{"current_steps": 1490, "total_steps": 1782, "loss": 0.3452518224716187, "lr": 8.019391189129466e-08, "epoch": 2.5086315789473685, "percentage": 83.61, "elapsed_time": "0:47:38", "remaining_time": "0:09:20"}
+{"current_steps": 1500, "total_steps": 1782, "loss": 0.36301617622375487, "lr": 7.495213241508786e-08, "epoch": 2.5254736842105263, "percentage": 84.18, "elapsed_time": "0:47:56", "remaining_time": "0:09:00"}
+{"current_steps": 1510, "total_steps": 1782, "loss": 0.3706004858016968, "lr": 6.987360423638205e-08, "epoch": 2.542315789473684, "percentage": 84.74, "elapsed_time": "0:48:16", "remaining_time": "0:08:41"}
+{"current_steps": 1520, "total_steps": 1782, "loss": 0.36011199951171874, "lr": 6.49602779032865e-08, "epoch": 2.559157894736842, "percentage": 85.3, "elapsed_time": "0:48:34", "remaining_time": "0:08:22"}
+{"current_steps": 1530, "total_steps": 1782, "loss": 0.37473766803741454, "lr": 6.02140405136089e-08, "epoch": 2.576, "percentage": 85.86, "elapsed_time": "0:48:53", "remaining_time": "0:08:03"}
+{"current_steps": 1540, "total_steps": 1782, "loss": 0.39232525825500486, "lr": 5.5636714990062393e-08, "epoch": 2.592842105263158, "percentage": 86.42, "elapsed_time": "0:49:11", "remaining_time": "0:07:43"}
+{"current_steps": 1550, "total_steps": 1782, "loss": 0.34370343685150145, "lr": 5.1230059380123034e-08, "epoch": 2.609684210526316, "percentage": 86.98, "elapsed_time": "0:49:30", "remaining_time": "0:07:24"}
+{"current_steps": 1560, "total_steps": 1782, "loss": 0.39509878158569334, "lr": 4.699576618080331e-08, "epoch": 2.626526315789474, "percentage": 87.54, "elapsed_time": "0:49:48", "remaining_time": "0:07:05"}
+{"current_steps": 1570, "total_steps": 1782, "loss": 0.3881126165390015, "lr": 4.293546168860163e-08, "epoch": 2.6433684210526316, "percentage": 88.1, "elapsed_time": "0:50:06", "remaining_time": "0:06:46"}
+{"current_steps": 1580, "total_steps": 1782, "loss": 0.34624040126800537, "lr": 3.9050705374879086e-08, "epoch": 2.6602105263157894, "percentage": 88.66, "elapsed_time": "0:50:25", "remaining_time": "0:06:26"}
+{"current_steps": 1590, "total_steps": 1782, "loss": 0.35141232013702395, "lr": 3.534298928690166e-08, "epoch": 2.677052631578947, "percentage": 89.23, "elapsed_time": "0:50:43", "remaining_time": "0:06:07"}
+{"current_steps": 1600, "total_steps": 1782, "loss": 0.39980330467224123, "lr": 3.181373747477822e-08, "epoch": 2.6938947368421053, "percentage": 89.79, "elapsed_time": "0:51:02", "remaining_time": "0:05:48"}
+{"current_steps": 1610, "total_steps": 1782, "loss": 0.3560852766036987, "lr": 2.8464305444515112e-08, "epoch": 2.710736842105263, "percentage": 90.35, "elapsed_time": "0:51:21", "remaining_time": "0:05:29"}
+{"current_steps": 1620, "total_steps": 1782, "loss": 0.39339067935943606, "lr": 2.5295979637397213e-08, "epoch": 2.7275789473684213, "percentage": 90.91, "elapsed_time": "0:51:40", "remaining_time": "0:05:10"}
+{"current_steps": 1630, "total_steps": 1782, "loss": 0.38021705150604246, "lr": 2.2309976935894203e-08, "epoch": 2.744421052631579, "percentage": 91.47, "elapsed_time": "0:51:58", "remaining_time": "0:04:50"}
+{"current_steps": 1640, "total_steps": 1782, "loss": 0.3467890739440918, "lr": 1.9507444196284195e-08, "epoch": 2.761263157894737, "percentage": 92.03, "elapsed_time": "0:52:17", "remaining_time": "0:04:31"}
+{"current_steps": 1650, "total_steps": 1782, "loss": 0.38266596794128416, "lr": 1.688945780817147e-08, "epoch": 2.7781052631578946, "percentage": 92.59, "elapsed_time": "0:52:35", "remaining_time": "0:04:12"}
+{"current_steps": 1660, "total_steps": 1782, "loss": 0.34164865016937257, "lr": 1.445702328106979e-08, "epoch": 2.7949473684210524, "percentage": 93.15, "elapsed_time": "0:52:53", "remaining_time": "0:03:53"}
+{"current_steps": 1670, "total_steps": 1782, "loss": 0.3876492977142334, "lr": 1.2211074858209103e-08, "epoch": 2.8117894736842106, "percentage": 93.71, "elapsed_time": "0:53:12", "remaining_time": "0:03:34"}
+{"current_steps": 1680, "total_steps": 1782, "loss": 0.3703944206237793, "lr": 1.0152475157713392e-08, "epoch": 2.8286315789473684, "percentage": 94.28, "elapsed_time": "0:53:30", "remaining_time": "0:03:14"}
+{"current_steps": 1690, "total_steps": 1782, "loss": 0.3735771656036377, "lr": 8.282014841288653e-09, "epoch": 2.845473684210526, "percentage": 94.84, "elapsed_time": "0:53:49", "remaining_time": "0:02:55"}
+{"current_steps": 1700, "total_steps": 1782, "loss": 0.3807518005371094, "lr": 6.600412310547754e-09, "epoch": 2.8623157894736844, "percentage": 95.4, "elapsed_time": "0:54:07", "remaining_time": "0:02:36"}
+{"current_steps": 1710, "total_steps": 1782, "loss": 0.3799649000167847, "lr": 5.1083134310882515e-09, "epoch": 2.879157894736842, "percentage": 95.96, "elapsed_time": "0:54:27", "remaining_time": "0:02:17"}
+{"current_steps": 1720, "total_steps": 1782, "loss": 0.3580306053161621, "lr": 3.806291284430274e-09, "epoch": 2.896, "percentage": 96.52, "elapsed_time": "0:54:45", "remaining_time": "0:01:58"}
+{"current_steps": 1730, "total_steps": 1782, "loss": 0.4088387966156006, "lr": 2.6948459479087526e-09, "epoch": 2.9128421052631577, "percentage": 97.08, "elapsed_time": "0:55:04", "remaining_time": "0:01:39"}
+{"current_steps": 1740, "total_steps": 1782, "loss": 0.3971900463104248, "lr": 1.7744043026048372e-09, "epoch": 2.929684210526316, "percentage": 97.64, "elapsed_time": "0:55:22", "remaining_time": "0:01:20"}
+{"current_steps": 1750, "total_steps": 1782, "loss": 0.35434761047363283, "lr": 1.0453198693907706e-09, "epoch": 2.9465263157894737, "percentage": 98.2, "elapsed_time": "0:55:40", "remaining_time": "0:01:01"}
+{"current_steps": 1760, "total_steps": 1782, "loss": 0.40241618156433107, "lr": 5.07872673150278e-10, "epoch": 2.9633684210526314, "percentage": 98.77, "elapsed_time": "0:55:59", "remaining_time": "0:00:41"}
+{"current_steps": 1770, "total_steps": 1782, "loss": 0.34090123176574705, "lr": 1.6226913522743302e-10, "epoch": 2.9802105263157896, "percentage": 99.33, "elapsed_time": "0:56:17", "remaining_time": "0:00:22"}
+{"current_steps": 1780, "total_steps": 1782, "loss": 0.33390347957611083, "lr": 8.641994144853448e-12, "epoch": 2.9970526315789474, "percentage": 99.89, "elapsed_time": "0:56:35", "remaining_time": "0:00:03"}
+{"current_steps": 1782, "total_steps": 1782, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:56:39", "remaining_time": "0:00:00"}
diff --git a/trainer_state.json b/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..5e0e2d322baacbac0ff1f833c3fd1a556b8ace28
--- /dev/null
+++ b/trainer_state.json
@@ -0,0 +1,1289 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 100,
+  "global_step": 1782,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016842105263157894,
+      "grad_norm": 0.21757784485816956,
+      "learning_rate": 5.027932960893855e-08,
+      "loss": 0.7252199172973632,
+      "step": 10
+    },
+    {
+      "epoch": 0.03368421052631579,
+      "grad_norm": 0.2456846386194229,
+      "learning_rate": 1.0614525139664805e-07,
+      "loss": 0.6507451057434082,
+      "step": 20
+    },
+    {
+      "epoch": 0.05052631578947368,
+      "grad_norm": 0.20819272100925446,
+      "learning_rate": 1.6201117318435754e-07,
+      "loss": 0.7381344795227051,
+      "step": 30
+    },
+    {
+      "epoch": 0.06736842105263158,
+      "grad_norm": 0.26373574137687683,
+      "learning_rate": 2.17877094972067e-07,
+      "loss": 0.7012194156646728,
+      "step": 40
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 0.2081507444381714,
+      "learning_rate": 2.7374301675977653e-07,
+      "loss": 0.6083873748779297,
+      "step": 50
+    },
+    {
+      "epoch": 0.10105263157894737,
+      "grad_norm": 0.2091236114501953,
+      "learning_rate": 3.29608938547486e-07,
+      "loss": 0.6980491638183594,
+      "step": 60
+    },
+    {
+      "epoch": 0.11789473684210526,
+      "grad_norm": 0.20970331132411957,
+      "learning_rate": 3.8547486033519547e-07,
+      "loss": 0.708641767501831,
+      "step": 70
+    },
+    {
+      "epoch": 0.13473684210526315,
+      "grad_norm": 0.18810197710990906,
+      "learning_rate": 4.41340782122905e-07,
+      "loss": 0.6742453098297119,
+      "step": 80
+    },
+    {
+      "epoch": 0.15157894736842106,
+      "grad_norm": 0.20251069962978363,
+      "learning_rate": 4.972067039106145e-07,
+      "loss": 0.6590609550476074,
+      "step": 90
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "grad_norm": 0.2644217908382416,
+      "learning_rate": 5.53072625698324e-07,
+      "loss": 0.704926872253418,
+      "step": 100
+    },
+    {
+      "epoch": 0.18526315789473685,
+      "grad_norm": 0.23766489326953888,
+      "learning_rate": 6.089385474860335e-07,
+      "loss": 0.7445036888122558,
+      "step": 110
+    },
+    {
+      "epoch": 0.20210526315789473,
+      "grad_norm": 0.27427056431770325,
+      "learning_rate": 6.64804469273743e-07,
+      "loss": 0.7476531028747558,
+      "step": 120
+    },
+    {
+      "epoch": 0.21894736842105264,
+      "grad_norm": 0.3208928406238556,
+      "learning_rate": 7.206703910614524e-07,
+      "loss": 0.7291872501373291,
+      "step": 130
+    },
+    {
+      "epoch": 0.23578947368421052,
+      "grad_norm": 0.3123615086078644,
+      "learning_rate": 7.76536312849162e-07,
+      "loss": 0.721175241470337,
+      "step": 140
+    },
+    {
+      "epoch": 0.25263157894736843,
+      "grad_norm": 0.26158222556114197,
+      "learning_rate": 8.324022346368714e-07,
+      "loss": 0.7556095600128174,
+      "step": 150
+    },
+    {
+      "epoch": 0.2694736842105263,
+      "grad_norm": 0.2592650353908539,
+      "learning_rate": 8.88268156424581e-07,
+      "loss": 0.7328392505645752,
+      "step": 160
+    },
+    {
+      "epoch": 0.2863157894736842,
+      "grad_norm": 0.24533776938915253,
+      "learning_rate": 9.441340782122904e-07,
+      "loss": 0.6990129470825195,
+      "step": 170
+    },
+    {
+      "epoch": 0.3031578947368421,
+      "grad_norm": 0.23409004509449005,
+      "learning_rate": 1e-06,
+      "loss": 0.6694639205932618,
+      "step": 180
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.3267499506473541,
+      "learning_rate": 9.999039806396227e-07,
+      "loss": 0.7123252868652343,
+      "step": 190
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "grad_norm": 0.2115064263343811,
+      "learning_rate": 9.996159594373611e-07,
+      "loss": 0.6858412742614746,
+      "step": 200
+    },
+    {
+      "epoch": 0.35368421052631577,
+      "grad_norm": 0.26226580142974854,
+      "learning_rate": 9.991360470156615e-07,
+      "loss": 0.6541069507598877,
+      "step": 210
+    },
+    {
+      "epoch": 0.3705263157894737,
+      "grad_norm": 0.24552594125270844,
+      "learning_rate": 9.984644276980594e-07,
+      "loss": 0.6506116390228271,
+      "step": 220
+    },
+    {
+      "epoch": 0.3873684210526316,
+      "grad_norm": 0.25084301829338074,
+      "learning_rate": 9.976013594383835e-07,
+      "loss": 0.6540626049041748,
+      "step": 230
+    },
+    {
+      "epoch": 0.40421052631578946,
+      "grad_norm": 0.34244054555892944,
+      "learning_rate": 9.965471737216833e-07,
+      "loss": 0.6737770557403564,
+      "step": 240
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.34752583503723145,
+      "learning_rate": 9.953022754369114e-07,
+      "loss": 0.6755708217620849,
+      "step": 250
+    },
+    {
+      "epoch": 0.4378947368421053,
+      "grad_norm": 0.31017956137657166,
+      "learning_rate": 9.938671427214158e-07,
+      "loss": 0.6578442573547363,
+      "step": 260
+    },
+    {
+      "epoch": 0.45473684210526316,
+      "grad_norm": 0.21509627997875214,
+      "learning_rate": 9.922423267772986e-07,
+      "loss": 0.639409875869751,
+      "step": 270
+    },
+    {
+      "epoch": 0.47157894736842104,
+      "grad_norm": 0.3022947609424591,
+      "learning_rate": 9.904284516597102e-07,
+      "loss": 0.5995691776275635,
+      "step": 280
+    },
+    {
+      "epoch": 0.4884210526315789,
+      "grad_norm": 0.3367304801940918,
+      "learning_rate": 9.884262140371648e-07,
+      "loss": 0.5898309707641601,
+      "step": 290
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "grad_norm": 0.294842928647995,
+      "learning_rate": 9.862363829239662e-07,
+      "loss": 0.6371779441833496,
+      "step": 300
+    },
+    {
+      "epoch": 0.5221052631578947,
+      "grad_norm": 0.25171560049057007,
+      "learning_rate": 9.838597993848456e-07,
+      "loss": 0.5795581817626954,
+      "step": 310
+    },
+    {
+      "epoch": 0.5389473684210526,
+      "grad_norm": 0.2818540036678314,
+      "learning_rate": 9.81297376211928e-07,
+      "loss": 0.5668415546417236,
+      "step": 320
+    },
+    {
+      "epoch": 0.5557894736842105,
+      "grad_norm": 0.32951900362968445,
+      "learning_rate": 9.785500975741498e-07,
+      "loss": 0.5933257102966308,
+      "step": 330
+    },
+    {
+      "epoch": 0.5726315789473684,
+      "grad_norm": 0.2763514518737793,
+      "learning_rate": 9.756190186392615e-07,
+      "loss": 0.5574678897857666,
+      "step": 340
+    },
+    {
+      "epoch": 0.5894736842105263,
+      "grad_norm": 0.3070182204246521,
+      "learning_rate": 9.725052651685612e-07,
+      "loss": 0.5532425880432129,
+      "step": 350
+    },
+    {
+      "epoch": 0.6063157894736843,
+      "grad_norm": 0.2079988420009613,
+      "learning_rate": 9.692100330845153e-07,
+      "loss": 0.5613389492034913,
+      "step": 360
+    },
+    {
+      "epoch": 0.6231578947368421,
+      "grad_norm": 0.282924622297287,
+      "learning_rate": 9.657345880114318e-07,
+      "loss": 0.5131485939025879,
+      "step": 370
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.20901450514793396,
+      "learning_rate": 9.620802647893623e-07,
+      "loss": 0.6279027462005615,
+      "step": 380
+    },
+    {
+      "epoch": 0.6568421052631579,
+      "grad_norm": 0.2637634575366974,
+      "learning_rate": 9.58248466961421e-07,
+      "loss": 0.5403085231781006,
+      "step": 390
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "grad_norm": 0.29078468680381775,
+      "learning_rate": 9.542406662347137e-07,
+      "loss": 0.5678809642791748,
+      "step": 400
+    },
+    {
+      "epoch": 0.6905263157894737,
+      "grad_norm": 0.2865101397037506,
+      "learning_rate": 9.500584019150895e-07,
+      "loss": 0.5479135036468505,
+      "step": 410
+    },
+    {
+      "epoch": 0.7073684210526315,
+      "grad_norm": 0.22857311367988586,
+      "learning_rate": 9.45703280315928e-07,
+      "loss": 0.5604462623596191,
+      "step": 420
+    },
+    {
+      "epoch": 0.7242105263157895,
+      "grad_norm": 0.23971959948539734,
+      "learning_rate": 9.411769741411903e-07,
+      "loss": 0.4704423427581787,
+      "step": 430
+    },
+    {
+      "epoch": 0.7410526315789474,
+      "grad_norm": 0.29793378710746765,
+      "learning_rate": 9.364812218429721e-07,
+      "loss": 0.560968017578125,
+      "step": 440
+    },
+    {
+      "epoch": 0.7578947368421053,
+      "grad_norm": 0.2236040234565735,
+      "learning_rate": 9.316178269538014e-07,
+      "loss": 0.5088452816009521,
+      "step": 450
+    },
+    {
+      "epoch": 0.7747368421052632,
+      "grad_norm": 0.22047854959964752,
+      "learning_rate": 9.265886573939446e-07,
+      "loss": 0.5030550956726074,
+      "step": 460
+    },
+    {
+      "epoch": 0.791578947368421,
+      "grad_norm": 0.2273361086845398,
+      "learning_rate": 9.213956447539792e-07,
+      "loss": 0.46353440284729003,
+      "step": 470
+    },
+    {
+      "epoch": 0.8084210526315789,
+      "grad_norm": 0.2170158326625824,
+      "learning_rate": 9.160407835529136e-07,
+      "loss": 0.49871411323547366,
+      "step": 480
+    },
+    {
+      "epoch": 0.8252631578947368,
+      "grad_norm": 0.19333498179912567,
+      "learning_rate": 9.105261304721375e-07,
+      "loss": 0.4416178226470947,
+      "step": 490
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.18490085005760193,
+      "learning_rate": 9.048538035654969e-07,
+      "loss": 0.39783194065093996,
+      "step": 500
+    },
+    {
+      "epoch": 0.8589473684210527,
+      "grad_norm": 0.22122648358345032,
+      "learning_rate": 8.990259814457977e-07,
+      "loss": 0.4318229198455811,
+      "step": 510
+    },
+    {
+      "epoch": 0.8757894736842106,
+      "grad_norm": 0.17448943853378296,
+      "learning_rate": 8.930449024480491e-07,
+      "loss": 0.42445807456970214,
+      "step": 520
+    },
+    {
+      "epoch": 0.8926315789473684,
+      "grad_norm": 0.18165165185928345,
+      "learning_rate": 8.8691286376977e-07,
+      "loss": 0.46429901123046874,
+      "step": 530
+    },
+    {
+      "epoch": 0.9094736842105263,
+      "grad_norm": 0.16785287857055664,
+      "learning_rate": 8.806322205886873e-07,
+      "loss": 0.3975703239440918,
+      "step": 540
+    },
+    {
+      "epoch": 0.9263157894736842,
+      "grad_norm": 0.1613738089799881,
+      "learning_rate": 8.74205385158165e-07,
+      "loss": 0.4458911418914795,
+      "step": 550
+    },
+    {
+      "epoch": 0.9431578947368421,
+      "grad_norm": 0.15376177430152893,
+      "learning_rate": 8.676348258807121e-07,
+      "loss": 0.45571184158325195,
+      "step": 560
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.14966322481632233,
+      "learning_rate": 8.609230663599254e-07,
+      "loss": 0.4039600372314453,
+      "step": 570
+    },
+    {
+      "epoch": 0.9768421052631578,
+      "grad_norm": 0.16819055378437042,
+      "learning_rate": 8.540726844312294e-07,
+      "loss": 0.4382494926452637,
+      "step": 580
+    },
+    {
+      "epoch": 0.9936842105263158,
+      "grad_norm": 0.16405776143074036,
+      "learning_rate": 8.470863111717889e-07,
+      "loss": 0.4306180477142334,
+      "step": 590
+    },
+    {
+      "epoch": 1.0101052631578948,
+      "grad_norm": 0.18503950536251068,
+      "learning_rate": 8.399666298899706e-07,
+      "loss": 0.39806089401245115,
+      "step": 600
+    },
+    {
+      "epoch": 1.0269473684210526,
+      "grad_norm": 0.14375492930412292,
+      "learning_rate": 8.327163750947457e-07,
+      "loss": 0.4271697044372559,
+      "step": 610
+    },
+    {
+      "epoch": 1.0437894736842106,
+      "grad_norm": 0.1412728875875473,
+      "learning_rate": 8.253383314454263e-07,
+      "loss": 0.3939049243927002,
+      "step": 620
+    },
+    {
+      "epoch": 1.0606315789473684,
+      "grad_norm": 0.20121850073337555,
+      "learning_rate": 8.178353326821404e-07,
+      "loss": 0.43197131156921387,
+      "step": 630
+    },
+    {
+      "epoch": 1.0774736842105264,
+      "grad_norm": 0.17767728865146637,
+      "learning_rate": 8.102102605374566e-07,
+      "loss": 0.437807559967041,
+      "step": 640
+    },
+    {
+      "epoch": 1.0943157894736841,
+      "grad_norm": 0.1498359888792038,
+      "learning_rate": 8.024660436295759e-07,
+      "loss": 0.38409013748168946,
+      "step": 650
+    },
+    {
+      "epoch": 1.1111578947368421,
+      "grad_norm": 0.15958793461322784,
+      "learning_rate": 7.946056563375145e-07,
+      "loss": 0.4204962730407715,
+      "step": 660
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.157291978597641,
+      "learning_rate": 7.866321176587128e-07,
+      "loss": 0.42113161087036133,
+      "step": 670
+    },
+    {
+      "epoch": 1.1448421052631579,
+      "grad_norm": 0.14119838178157806,
+      "learning_rate": 7.785484900495065e-07,
+      "loss": 0.4151731491088867,
+      "step": 680
+    },
+    {
+      "epoch": 1.1616842105263159,
+      "grad_norm": 0.1296525001525879,
+      "learning_rate": 7.703578782489058e-07,
+      "loss": 0.38312902450561526,
+      "step": 690
+    },
+    {
+      "epoch": 1.1785263157894736,
+      "grad_norm": 0.13671696186065674,
+      "learning_rate": 7.620634280861351e-07,
+      "loss": 0.42612557411193847,
+      "step": 700
+    },
+    {
+      "epoch": 1.1953684210526316,
+      "grad_norm": 0.15196114778518677,
+      "learning_rate": 7.536683252723923e-07,
+      "loss": 0.4306772708892822,
+      "step": 710
+    },
+    {
+      "epoch": 1.2122105263157894,
+      "grad_norm": 0.1136903315782547,
+      "learning_rate": 7.451757941772868e-07,
+      "loss": 0.38483757972717286,
+      "step": 720
+    },
+    {
+      "epoch": 1.2290526315789474,
+      "grad_norm": 0.12378744781017303,
+      "learning_rate": 7.365890965904337e-07,
+      "loss": 0.4030342102050781,
+      "step": 730
+    },
+    {
+      "epoch": 1.2458947368421052,
+      "grad_norm": 0.1265542209148407,
+      "learning_rate": 7.279115304686733e-07,
+      "loss": 0.4091166973114014,
+      "step": 740
+    },
+    {
+      "epoch": 1.2627368421052632,
+      "grad_norm": 0.11647409200668335,
+      "learning_rate": 7.191464286694e-07,
+      "loss": 0.41426806449890136,
+      "step": 750
+    },
+    {
+      "epoch": 1.279578947368421,
+      "grad_norm": 0.11192695051431656,
+      "learning_rate": 7.102971576704875e-07,
+      "loss": 0.38181486129760744,
+      "step": 760
+    },
+    {
+      "epoch": 1.296421052631579,
+      "grad_norm": 0.14947861433029175,
+      "learning_rate": 7.013671162773003e-07,
+      "loss": 0.39824953079223635,
+      "step": 770
+    },
+    {
+      "epoch": 1.313263157894737,
+      "grad_norm": 0.11269424855709076,
+      "learning_rate": 6.923597343172891e-07,
+      "loss": 0.40348024368286134,
+      "step": 780
+    },
+    {
+      "epoch": 1.3301052631578947,
+      "grad_norm": 0.3742346167564392,
+      "learning_rate": 6.83278471322672e-07,
+      "loss": 0.38022048473358155,
+      "step": 790
+    },
+    {
+      "epoch": 1.3469473684210527,
+      "grad_norm": 0.1310902237892151,
+      "learning_rate": 6.741268152017057e-07,
+      "loss": 0.42791285514831545,
+      "step": 800
+    },
+    {
+      "epoch": 1.3637894736842107,
+      "grad_norm": 0.1692703813314438,
+      "learning_rate": 6.649082808990585e-07,
+      "loss": 0.4263493061065674,
+      "step": 810
+    },
+    {
+      "epoch": 1.3806315789473684,
+      "grad_norm": 0.1279117316007614,
+      "learning_rate": 6.556264090457998e-07,
+      "loss": 0.37379777431488037,
+      "step": 820
+    },
+    {
+      "epoch": 1.3974736842105262,
+      "grad_norm": 0.12949039041996002,
+      "learning_rate": 6.462847645995237e-07,
+      "loss": 0.38636391162872313,
+      "step": 830
+    },
+    {
+      "epoch": 1.4143157894736842,
+      "grad_norm": 0.10221126675605774,
+      "learning_rate": 6.368869354751284e-07,
+      "loss": 0.408221435546875,
+      "step": 840
+    },
+    {
+      "epoch": 1.4311578947368422,
+      "grad_norm": 0.11505889147520065,
+      "learning_rate": 6.274365311667797e-07,
+      "loss": 0.3951406717300415,
+      "step": 850
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.11054962873458862,
+      "learning_rate": 6.179371813615859e-07,
+      "loss": 0.3732129096984863,
+      "step": 860
+    },
+    {
+      "epoch": 1.464842105263158,
+      "grad_norm": 0.10150120407342911,
+      "learning_rate": 6.083925345455158e-07,
+      "loss": 0.38601529598236084,
+      "step": 870
+    },
+    {
+      "epoch": 1.4816842105263157,
+      "grad_norm": 0.12239400297403336,
+      "learning_rate": 5.988062566020986e-07,
+      "loss": 0.3859985828399658,
+      "step": 880
+    },
+    {
+      "epoch": 1.4985263157894737,
+      "grad_norm": 0.15801067650318146,
+      "learning_rate": 5.891820294044408e-07,
+      "loss": 0.3983951807022095,
+      "step": 890
+    },
+    {
+      "epoch": 1.5153684210526315,
+      "grad_norm": 0.10104545950889587,
+      "learning_rate": 5.795235494011007e-07,
+      "loss": 0.41107850074768065,
+      "step": 900
+    },
+    {
+      "epoch": 1.5322105263157895,
+      "grad_norm": 0.1378099024295807,
+      "learning_rate": 5.698345261963668e-07,
+      "loss": 0.3708331823348999,
+      "step": 910
+    },
+    {
+      "epoch": 1.5490526315789475,
+      "grad_norm": 0.12936057150363922,
+      "learning_rate": 5.601186811254825e-07,
+      "loss": 0.387884521484375,
+      "step": 920
+    },
+    {
+      "epoch": 1.5658947368421052,
+      "grad_norm": 0.12379129230976105,
+      "learning_rate": 5.503797458253646e-07,
+      "loss": 0.43808717727661134,
+      "step": 930
+    },
+    {
+      "epoch": 1.582736842105263,
+      "grad_norm": 0.12017743289470673,
+      "learning_rate": 5.406214608013662e-07,
+      "loss": 0.41345391273498533,
+      "step": 940
+    },
+    {
+      "epoch": 1.5995789473684212,
+      "grad_norm": 0.1095535159111023,
+      "learning_rate": 5.308475739906328e-07,
+      "loss": 0.40022664070129393,
+      "step": 950
+    },
+    {
+      "epoch": 1.616421052631579,
+      "grad_norm": 0.13831396400928497,
+      "learning_rate": 5.210618393226045e-07,
+      "loss": 0.3909924983978271,
+      "step": 960
+    },
+    {
+      "epoch": 1.6332631578947368,
+      "grad_norm": 0.10449163615703583,
+      "learning_rate": 5.112680152772156e-07,
+      "loss": 0.37143146991729736,
+      "step": 970
+    },
+    {
+      "epoch": 1.6501052631578947,
+      "grad_norm": 0.11249610036611557,
+      "learning_rate": 5.01469863441348e-07,
+      "loss": 0.38103113174438474,
+      "step": 980
+    },
+    {
+      "epoch": 1.6669473684210527,
+      "grad_norm": 0.13718819618225098,
+      "learning_rate": 4.916711470640907e-07,
+      "loss": 0.4071629524230957,
+      "step": 990
+    },
+    {
+      "epoch": 1.6837894736842105,
+      "grad_norm": 0.10473571717739105,
+      "learning_rate": 4.818756296113595e-07,
+      "loss": 0.417419958114624,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7006315789473683,
+      "grad_norm": 0.10846224427223206,
+      "learning_rate": 4.7208707332043623e-07,
+      "loss": 0.3998772859573364,
+      "step": 1010
+    },
+    {
+      "epoch": 1.7174736842105263,
+      "grad_norm": 0.10248563438653946,
+      "learning_rate": 4.6230923775497714e-07,
+      "loss": 0.38056583404541017,
+      "step": 1020
+    },
+    {
+      "epoch": 1.7343157894736843,
+      "grad_norm": 0.12221980094909668,
+      "learning_rate": 4.5254587836104964e-07,
+      "loss": 0.39371190071105955,
+      "step": 1030
+    },
+    {
+      "epoch": 1.751157894736842,
+      "grad_norm": 0.10641586035490036,
+      "learning_rate": 4.4280074502475017e-07,
+      "loss": 0.4280440330505371,
+      "step": 1040
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.12907131016254425,
+      "learning_rate": 4.3307758063195796e-07,
+      "loss": 0.3791615962982178,
+      "step": 1050
+    },
+    {
+      "epoch": 1.784842105263158,
+      "grad_norm": 0.12383506447076797,
+      "learning_rate": 4.233801196307762e-07,
+      "loss": 0.347782301902771,
+      "step": 1060
+    },
+    {
+      "epoch": 1.8016842105263158,
+      "grad_norm": 0.12547679245471954,
+      "learning_rate": 4.1371208659721536e-07,
+      "loss": 0.38370628356933595,
+      "step": 1070
+    },
+    {
+      "epoch": 1.8185263157894735,
+      "grad_norm": 0.10580642521381378,
+      "learning_rate": 4.0407719480466736e-07,
+      "loss": 0.40404376983642576,
+      "step": 1080
+    },
+    {
+      "epoch": 1.8353684210526315,
+      "grad_norm": 0.1055402085185051,
+      "learning_rate": 3.944791447977213e-07,
+      "loss": 0.4167450428009033,
+      "step": 1090
+    },
+    {
+      "epoch": 1.8522105263157895,
+      "grad_norm": 0.11053823679685593,
+      "learning_rate": 3.849216229708671e-07,
+      "loss": 0.4046513080596924,
+      "step": 1100
+    },
+    {
+      "epoch": 1.8690526315789473,
+      "grad_norm": 0.10185246914625168,
+      "learning_rate": 3.7540830015263526e-07,
+      "loss": 0.39672977924346925,
+      "step": 1110
+    },
+    {
+      "epoch": 1.8858947368421053,
+      "grad_norm": 0.08342823386192322,
+      "learning_rate": 3.6594283019571416e-07,
+      "loss": 0.39356396198272703,
+      "step": 1120
+    },
+    {
+      "epoch": 1.9027368421052633,
+      "grad_norm": 0.11821646988391876,
+      "learning_rate": 3.565288485735874e-07,
+      "loss": 0.42082643508911133,
+      "step": 1130
+    },
+    {
+      "epoch": 1.919578947368421,
+      "grad_norm": 0.1106327474117279,
+      "learning_rate": 3.4716997098423085e-07,
+      "loss": 0.34105117321014405,
+      "step": 1140
+    },
+    {
+      "epoch": 1.9364210526315788,
+      "grad_norm": 0.11533800512552261,
+      "learning_rate": 3.378697919614045e-07,
+      "loss": 0.3924069404602051,
+      "step": 1150
+    },
+    {
+      "epoch": 1.9532631578947368,
+      "grad_norm": 0.1431114822626114,
+      "learning_rate": 3.286318834940729e-07,
+      "loss": 0.3922377586364746,
+      "step": 1160
+    },
+    {
+      "epoch": 1.9701052631578948,
+      "grad_norm": 0.16050194203853607,
+      "learning_rate": 3.1945979365448517e-07,
+      "loss": 0.3745201587677002,
+      "step": 1170
+    },
+    {
+      "epoch": 1.9869473684210526,
+      "grad_norm": 0.11921833455562592,
+      "learning_rate": 3.103570452354402e-07,
+      "loss": 0.40110602378845217,
+      "step": 1180
+    },
+    {
+      "epoch": 2.0033684210526315,
+      "grad_norm": 0.0832003727555275,
+      "learning_rate": 3.013271343972613e-07,
+      "loss": 0.3981154918670654,
+      "step": 1190
+    },
+    {
+      "epoch": 2.0202105263157897,
+      "grad_norm": 0.09975888580083847,
+      "learning_rate": 2.9237352932500046e-07,
+      "loss": 0.3726134061813354,
+      "step": 1200
+    },
+    {
+      "epoch": 2.0370526315789474,
+      "grad_norm": 0.14600081741809845,
+      "learning_rate": 2.8349966889638615e-07,
+      "loss": 0.42558698654174804,
+      "step": 1210
+    },
+    {
+      "epoch": 2.053894736842105,
+      "grad_norm": 0.10875770449638367,
+      "learning_rate": 2.747089613610278e-07,
+      "loss": 0.3682931184768677,
+      "step": 1220
+    },
+    {
+      "epoch": 2.070736842105263,
+      "grad_norm": 0.10050549358129501,
+      "learning_rate": 2.66004783031385e-07,
+      "loss": 0.3756644487380981,
+      "step": 1230
+    },
+    {
+      "epoch": 2.087578947368421,
+      "grad_norm": 0.08914914727210999,
+      "learning_rate": 2.573904769860009e-07,
+      "loss": 0.3804330825805664,
+      "step": 1240
+    },
+    {
+      "epoch": 2.104421052631579,
+      "grad_norm": 0.08296852558851242,
+      "learning_rate": 2.488693517855016e-07,
+      "loss": 0.3978404521942139,
+      "step": 1250
+    },
+    {
+      "epoch": 2.1212631578947367,
+      "grad_norm": 0.13885149359703064,
+      "learning_rate": 2.404446802018533e-07,
+      "loss": 0.3935218334197998,
+      "step": 1260
+    },
+    {
+      "epoch": 2.138105263157895,
+      "grad_norm": 0.13195137679576874,
+      "learning_rate": 2.3211969796136305e-07,
+      "loss": 0.42966952323913576,
+      "step": 1270
+    },
+    {
+      "epoch": 2.1549473684210527,
+      "grad_norm": 0.13367892801761627,
+      "learning_rate": 2.2389760250191038e-07,
+      "loss": 0.3679579019546509,
+      "step": 1280
+    },
+    {
+      "epoch": 2.1717894736842105,
+      "grad_norm": 0.1288345605134964,
+      "learning_rate": 2.1578155174488343e-07,
+      "loss": 0.41324810981750487,
+      "step": 1290
+    },
+    {
+      "epoch": 2.1886315789473683,
+      "grad_norm": 0.09626021236181259,
+      "learning_rate": 2.0777466288229205e-07,
+      "loss": 0.40120248794555663,
+      "step": 1300
+    },
+    {
+      "epoch": 2.2054736842105265,
+      "grad_norm": 0.10264381766319275,
+      "learning_rate": 1.9988001117952485e-07,
+      "loss": 0.3501007080078125,
+      "step": 1310
+    },
+    {
+      "epoch": 2.2223157894736842,
+      "grad_norm": 0.09031466394662857,
+      "learning_rate": 1.9210062879420973e-07,
+      "loss": 0.3839429378509521,
+      "step": 1320
+    },
+    {
+      "epoch": 2.239157894736842,
+      "grad_norm": 0.12686079740524292,
+      "learning_rate": 1.8443950361162957e-07,
+      "loss": 0.4338528156280518,
+      "step": 1330
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 0.12199016660451889,
+      "learning_rate": 1.7689957809714346e-07,
+      "loss": 0.39229888916015626,
+      "step": 1340
+    },
+    {
+      "epoch": 2.272842105263158,
+      "grad_norm": 0.12029567360877991,
+      "learning_rate": 1.694837481660525e-07,
+      "loss": 0.38006880283355715,
+      "step": 1350
+    },
+    {
+      "epoch": 2.2896842105263158,
+      "grad_norm": 0.08686309307813644,
+      "learning_rate": 1.6219486207134313e-07,
+      "loss": 0.3808159589767456,
+      "step": 1360
+    },
+    {
+      "epoch": 2.3065263157894735,
+      "grad_norm": 0.10810462385416031,
+      "learning_rate": 1.5503571930973785e-07,
+      "loss": 0.401824426651001,
+      "step": 1370
+    },
+    {
+      "epoch": 2.3233684210526317,
+      "grad_norm": 0.10281873494386673,
+      "learning_rate": 1.480090695464723e-07,
+      "loss": 0.40149493217468263,
+      "step": 1380
+    },
+    {
+      "epoch": 2.3402105263157895,
+      "grad_norm": 0.09503985196352005,
+      "learning_rate": 1.4111761155920975e-07,
+      "loss": 0.38567726612091063,
+      "step": 1390
+    },
+    {
+      "epoch": 2.3570526315789473,
+      "grad_norm": 0.10420782119035721,
+      "learning_rate": 1.3436399220150212e-07,
+      "loss": 0.3759742736816406,
+      "step": 1400
+    },
+    {
+      "epoch": 2.3738947368421055,
+      "grad_norm": 0.10681115835905075,
+      "learning_rate": 1.2775080538619347e-07,
+      "loss": 0.3913698196411133,
+      "step": 1410
+    },
+    {
+      "epoch": 2.3907368421052633,
+      "grad_norm": 0.10323983430862427,
+      "learning_rate": 1.2128059108915595e-07,
+      "loss": 0.39077584743499755,
+      "step": 1420
+    },
+    {
+      "epoch": 2.407578947368421,
+      "grad_norm": 0.09566064178943634,
+      "learning_rate": 1.1495583437374263e-07,
+      "loss": 0.39895172119140626,
+      "step": 1430
+    },
+    {
+      "epoch": 2.424421052631579,
+      "grad_norm": 0.13018426299095154,
+      "learning_rate": 1.0877896443633117e-07,
+      "loss": 0.38982129096984863,
+      "step": 1440
+    },
+    {
+      "epoch": 2.441263157894737,
+      "grad_norm": 0.10760781168937683,
+      "learning_rate": 1.0275235367332347e-07,
+      "loss": 0.3756714344024658,
+      "step": 1450
+    },
+    {
+      "epoch": 2.458105263157895,
+      "grad_norm": 0.11606904864311218,
+      "learning_rate": 9.687831676996238e-08,
+      "loss": 0.37858171463012696,
+      "step": 1460
+    },
+    {
+      "epoch": 2.4749473684210526,
+      "grad_norm": 0.12957172095775604,
+      "learning_rate": 9.115910981131336e-08,
+      "loss": 0.40050196647644043,
+      "step": 1470
+    },
+    {
+      "epoch": 2.4917894736842103,
+      "grad_norm": 0.11186131089925766,
+      "learning_rate": 8.559692941575231e-08,
+      "loss": 0.3684133291244507,
+      "step": 1480
+    },
+    {
+      "epoch": 2.5086315789473685,
+      "grad_norm": 0.13279542326927185,
+      "learning_rate": 8.019391189129466e-08,
+      "loss": 0.3452518224716187,
+      "step": 1490
+    },
+    {
+      "epoch": 2.5254736842105263,
+      "grad_norm": 0.09041756391525269,
+      "learning_rate": 7.495213241508786e-08,
+      "loss": 0.36301617622375487,
+      "step": 1500
+    },
+    {
+      "epoch": 2.542315789473684,
+      "grad_norm": 0.10033190995454788,
+      "learning_rate": 6.987360423638205e-08,
+      "loss": 0.3706004858016968,
+      "step": 1510
+    },
+    {
+      "epoch": 2.559157894736842,
+      "grad_norm": 0.10681814700365067,
+      "learning_rate": 6.49602779032865e-08,
+      "loss": 0.36011199951171874,
+      "step": 1520
+    },
+    {
+      "epoch": 2.576,
+      "grad_norm": 0.1008416935801506,
+      "learning_rate": 6.02140405136089e-08,
+      "loss": 0.37473766803741454,
+      "step": 1530
+    },
+    {
+      "epoch": 2.592842105263158,
+      "grad_norm": 0.11559010297060013,
+      "learning_rate": 5.5636714990062393e-08,
+      "loss": 0.39232525825500486,
+      "step": 1540
+    },
+    {
+      "epoch": 2.609684210526316,
+      "grad_norm": 0.10601615905761719,
+      "learning_rate": 5.1230059380123034e-08,
+      "loss": 0.34370343685150145,
+      "step": 1550
+    },
+    {
+      "epoch": 2.626526315789474,
+      "grad_norm": 0.11516924202442169,
+      "learning_rate": 4.699576618080331e-08,
+      "loss": 0.39509878158569334,
+      "step": 1560
+    },
+    {
+      "epoch": 2.6433684210526316,
+      "grad_norm": 0.11444627493619919,
+      "learning_rate": 4.293546168860163e-08,
+      "loss": 0.3881126165390015,
+      "step": 1570
+    },
+    {
+      "epoch": 2.6602105263157894,
+      "grad_norm": 0.09985339641571045,
+      "learning_rate": 3.9050705374879086e-08,
+      "loss": 0.34624040126800537,
+      "step": 1580
+    },
+    {
+      "epoch": 2.677052631578947,
+      "grad_norm": 0.10439962148666382,
+      "learning_rate": 3.534298928690166e-08,
+      "loss": 0.35141232013702395,
+      "step": 1590
+    },
+    {
+      "epoch": 2.6938947368421053,
+      "grad_norm": 0.12180087715387344,
+      "learning_rate": 3.181373747477822e-08,
+      "loss": 0.39980330467224123,
+      "step": 1600
+    },
+    {
+      "epoch": 2.710736842105263,
+      "grad_norm": 0.12150874733924866,
+      "learning_rate": 2.8464305444515112e-08,
+      "loss": 0.3560852766036987,
+      "step": 1610
+    },
+    {
+      "epoch": 2.7275789473684213,
+      "grad_norm": 0.11374734342098236,
+      "learning_rate": 2.5295979637397213e-08,
+      "loss": 0.39339067935943606,
+      "step": 1620
+    },
+    {
+      "epoch": 2.744421052631579,
+      "grad_norm": 0.11705286055803299,
+      "learning_rate": 2.2309976935894203e-08,
+      "loss": 0.38021705150604246,
+      "step": 1630
+    },
+    {
+      "epoch": 2.761263157894737,
+      "grad_norm": 0.09300459921360016,
+      "learning_rate": 1.9507444196284195e-08,
+      "loss": 0.3467890739440918,
+      "step": 1640
+    },
+    {
+      "epoch": 2.7781052631578946,
+      "grad_norm": 0.08709974586963654,
+      "learning_rate": 1.688945780817147e-08,
+      "loss": 0.38266596794128416,
+      "step": 1650
+    },
+    {
+      "epoch": 2.7949473684210524,
+      "grad_norm": 0.12327069044113159,
+      "learning_rate": 1.445702328106979e-08,
+      "loss": 0.34164865016937257,
+      "step": 1660
+    },
+    {
+      "epoch": 2.8117894736842106,
+      "grad_norm": 0.12361253052949905,
+      "learning_rate": 1.2211074858209103e-08,
+      "loss": 0.3876492977142334,
+      "step": 1670
+    },
+    {
+      "epoch": 2.8286315789473684,
+      "grad_norm": 0.120187908411026,
+      "learning_rate": 1.0152475157713392e-08,
+      "loss": 0.3703944206237793,
+      "step": 1680
+    },
+    {
+      "epoch": 2.845473684210526,
+      "grad_norm": 0.10741006582975388,
+      "learning_rate": 8.282014841288653e-09,
+      "loss": 0.3735771656036377,
+      "step": 1690
+    },
+    {
+      "epoch": 2.8623157894736844,
+      "grad_norm": 0.10451704263687134,
+      "learning_rate": 6.600412310547754e-09,
+      "loss": 0.3807518005371094,
+      "step": 1700
+    },
+    {
+      "epoch": 2.879157894736842,
+      "grad_norm": 0.10978730767965317,
+      "learning_rate": 5.1083134310882515e-09,
+      "loss": 0.3799649000167847,
+      "step": 1710
+    },
+    {
+      "epoch": 2.896,
+      "grad_norm": 0.09521365165710449,
+      "learning_rate": 3.806291284430274e-09,
+      "loss": 0.3580306053161621,
+      "step": 1720
+    },
+    {
+      "epoch": 2.9128421052631577,
+      "grad_norm": 0.11443010717630386,
+      "learning_rate": 2.6948459479087526e-09,
+      "loss": 0.4088387966156006,
+      "step": 1730
+    },
+    {
+      "epoch": 2.929684210526316,
+      "grad_norm": 0.10477516055107117,
+      "learning_rate": 1.7744043026048372e-09,
+      "loss": 0.3971900463104248,
+      "step": 1740
+    },
+    {
+      "epoch": 2.9465263157894737,
+      "grad_norm": 0.11358557641506195,
+      "learning_rate": 1.0453198693907706e-09,
+      "loss": 0.35434761047363283,
+      "step": 1750
+    },
+    {
+      "epoch": 2.9633684210526314,
+      "grad_norm": 0.10436985641717911,
+      "learning_rate": 5.07872673150278e-10,
+      "loss": 0.40241618156433107,
+      "step": 1760
+    },
+    {
+      "epoch": 2.9802105263157896,
+      "grad_norm": 0.10179495811462402,
+      "learning_rate": 1.6226913522743302e-10,
+      "loss": 0.34090123176574705,
+      "step": 1770
+    },
+    {
+      "epoch": 2.9970526315789474,
+      "grad_norm": 0.1047094464302063,
+      "learning_rate": 8.641994144853448e-12,
+      "loss": 0.33390347957611083,
+      "step": 1780
+    },
+    {
+      "epoch": 3.0,
+      "step": 1782,
+      "total_flos": 3.258875338498253e+16,
+      "train_loss": 0.45725877370630985,
+      "train_runtime": 3399.7742,
+      "train_samples_per_second": 4.191,
+      "train_steps_per_second": 0.524
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1782,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.258875338498253e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/training_args.bin b/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..26362bce38749fb4af3e32947d24cd6a387b57ac
--- /dev/null
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e59b6aeffb8563cc09210642a0d080410d061efe9a32399cd1e4a1e0abccb0a
+size 5585
diff --git a/training_loss.png b/training_loss.png
new file mode 100644
index 0000000000000000000000000000000000000000..f6ea2d99a99cf854683b7904f7805bf06c92a166
Binary files /dev/null and b/training_loss.png differ