diff --git a/save_lora_instruct_r8_4e4_s11_1/README.md b/save_lora_instruct_r8_4e4_s11_1/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..2aa897f8fa13b49ce76b1fa188781e5f726e7d13
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-2-7b-hf
+library_name: peft
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/adapter_config.json b/save_lora_instruct_r8_4e4_s11_1/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9c81a592f0ff08374a4f61f6003029070a8429ae
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/adapter_config.json
@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "mora_type": 1,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_mora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/adapter_model.safetensors b/save_lora_instruct_r8_4e4_s11_1/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..de1815edef45e5002cf61ce6d1a96946f22bc585
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b877725910cf2bc993f85d0284ffc64a6a01cabf19935b768e3986df210dc2c2
+size 564342240
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/README.md b/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..2aa897f8fa13b49ce76b1fa188781e5f726e7d13
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-2-7b-hf
+library_name: peft
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/adapter_config.json b/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9c81a592f0ff08374a4f61f6003029070a8429ae
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/adapter_config.json
@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "mora_type": 1,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_mora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/adapter_model.safetensors b/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1c734a526953262942cdc6004d1f8187864a13de
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:148b651127bad36ecafe1696dd4410a4dbc7f78c3d1729012f246f0217678672
+size 564342240
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/global_step1500/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/global_step1500/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..38a0438cc33556d9033f1cb028d0b252e04f37ea
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/global_step1500/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc73040c87dbff03438699f1812dbe80616e5733495eebe76f36c37042b2f749
+size 239914224
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/global_step1500/mp_rank_00_model_states.pt b/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/global_step1500/mp_rank_00_model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..42142fb8a4b308dfee3a8da93d3c34995b4e5754
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/global_step1500/mp_rank_00_model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e9748c0d074063aa0be54e4a8a370e66d0671ca8867acc5ce413e208beb76bd
+size 40303404
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/latest b/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/latest
new file mode 100644
index 0000000000000000000000000000000000000000..c56ff7708f44fb7928fea2f70d6d7342ce0d5b67
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/latest
@@ -0,0 +1 @@
+global_step1500
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/rng_state.pth b/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..92f7ec3f5fcd7d29feb614b2c27dbc5978c31643
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb1ba1ceb33f795be7ee4e07148f4508e4f6b4ae91adf50fdaf1077b1ae47da8
+size 14244
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/scheduler.pt b/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3abd97e72b383f0f0f503613a6f4febdf1ef720e
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5f4641faf2b17520c52e00d1eae4553db1b75e4c42cd080785063e0d358be92
+size 1064
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/trainer_state.json b/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..d5e6ec4f9ed0757ed198623a00358892d23a2970
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/trainer_state.json
@@ -0,0 +1,1821 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.598746374777809,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.3798,
+      "step": 5
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 1.3917,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4e-05,
+      "loss": 1.2862,
+      "step": 15
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 1.2046,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.0634,
+      "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8e-05,
+      "loss": 1.0273,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 1.0472,
+      "step": 35
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 1.0301,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00012,
+      "loss": 0.9335,
+      "step": 45
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.921,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00014666666666666666,
+      "loss": 0.9506,
+      "step": 55
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016,
+      "loss": 0.8876,
+      "step": 60
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00017333333333333334,
+      "loss": 0.9335,
+      "step": 65
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 0.8554,
+      "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0002,
+      "loss": 0.8537,
+      "step": 75
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00021333333333333333,
+      "loss": 0.9033,
+      "step": 80
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00022666666666666668,
+      "loss": 0.8203,
+      "step": 85
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00024,
+      "loss": 0.8611,
+      "step": 90
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00025333333333333333,
+      "loss": 0.8303,
+      "step": 95
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002666666666666667,
+      "loss": 0.8528,
+      "step": 100
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00028,
+      "loss": 0.8537,
+      "step": 105
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002933333333333333,
+      "loss": 0.8286,
+      "step": 110
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003066666666666667,
+      "loss": 0.8449,
+      "step": 115
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00032,
+      "loss": 0.8377,
+      "step": 120
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003333333333333334,
+      "loss": 0.8419,
+      "step": 125
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00034666666666666667,
+      "loss": 0.8265,
+      "step": 130
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00036,
+      "loss": 0.8037,
+      "step": 135
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003733333333333334,
+      "loss": 0.7924,
+      "step": 140
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00038666666666666667,
+      "loss": 0.8245,
+      "step": 145
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0004,
+      "loss": 0.8388,
+      "step": 150
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003995884773662552,
+      "loss": 0.8066,
+      "step": 155
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003991769547325103,
+      "loss": 0.8107,
+      "step": 160
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039876543209876544,
+      "loss": 0.8005,
+      "step": 165
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003983539094650206,
+      "loss": 0.7727,
+      "step": 170
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039794238683127576,
+      "loss": 0.8276,
+      "step": 175
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039753086419753086,
+      "loss": 0.8464,
+      "step": 180
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000397119341563786,
+      "loss": 0.8348,
+      "step": 185
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003967078189300412,
+      "loss": 0.8228,
+      "step": 190
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003962962962962963,
+      "loss": 0.8254,
+      "step": 195
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00039588477366255144,
+      "loss": 0.817,
+      "step": 200
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003954732510288066,
+      "loss": 0.8365,
+      "step": 205
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003950617283950617,
+      "loss": 0.793,
+      "step": 210
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00039465020576131686,
+      "loss": 0.8014,
+      "step": 215
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000394238683127572,
+      "loss": 0.8049,
+      "step": 220
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003938271604938272,
+      "loss": 0.7841,
+      "step": 225
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003934156378600823,
+      "loss": 0.7977,
+      "step": 230
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00039300411522633744,
+      "loss": 0.8299,
+      "step": 235
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003925925925925926,
+      "loss": 0.7729,
+      "step": 240
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00039218106995884776,
+      "loss": 0.8082,
+      "step": 245
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003917695473251029,
+      "loss": 0.8173,
+      "step": 250
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000391358024691358,
+      "loss": 0.8379,
+      "step": 255
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003909465020576132,
+      "loss": 0.7962,
+      "step": 260
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00039053497942386834,
+      "loss": 0.8067,
+      "step": 265
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003901234567901235,
+      "loss": 0.7915,
+      "step": 270
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00038971193415637866,
+      "loss": 0.7905,
+      "step": 275
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00038930041152263376,
+      "loss": 0.7862,
+      "step": 280
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003888888888888889,
+      "loss": 0.7709,
+      "step": 285
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003884773662551441,
+      "loss": 0.7773,
+      "step": 290
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00038806584362139924,
+      "loss": 0.8068,
+      "step": 295
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00038765432098765434,
+      "loss": 0.7962,
+      "step": 300
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003872427983539095,
+      "loss": 0.7894,
+      "step": 305
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00038683127572016466,
+      "loss": 0.7705,
+      "step": 310
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00038641975308641976,
+      "loss": 0.7882,
+      "step": 315
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003860082304526749,
+      "loss": 0.7865,
+      "step": 320
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003855967078189301,
+      "loss": 0.7939,
+      "step": 325
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003851851851851852,
+      "loss": 0.7724,
+      "step": 330
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00038477366255144034,
+      "loss": 0.7771,
+      "step": 335
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003843621399176955,
+      "loss": 0.7941,
+      "step": 340
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00038395061728395066,
+      "loss": 0.7822,
+      "step": 345
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00038353909465020577,
+      "loss": 0.8143,
+      "step": 350
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003831275720164609,
+      "loss": 0.795,
+      "step": 355
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003827160493827161,
+      "loss": 0.8049,
+      "step": 360
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003823045267489712,
+      "loss": 0.8309,
+      "step": 365
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00038189300411522635,
+      "loss": 0.8314,
+      "step": 370
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003814814814814815,
+      "loss": 0.801,
+      "step": 375
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00038106995884773666,
+      "loss": 0.8084,
+      "step": 380
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00038065843621399177,
+      "loss": 0.8129,
+      "step": 385
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003802469135802469,
+      "loss": 0.7859,
+      "step": 390
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003798353909465021,
+      "loss": 0.7874,
+      "step": 395
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003794238683127572,
+      "loss": 0.7548,
+      "step": 400
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00037901234567901235,
+      "loss": 0.8092,
+      "step": 405
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003786008230452675,
+      "loss": 0.8041,
+      "step": 410
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00037818930041152266,
+      "loss": 0.777,
+      "step": 415
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00037777777777777777,
+      "loss": 0.7699,
+      "step": 420
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00037736625514403293,
+      "loss": 0.781,
+      "step": 425
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003769547325102881,
+      "loss": 0.7504,
+      "step": 430
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003765432098765432,
+      "loss": 0.7974,
+      "step": 435
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037613168724279835,
+      "loss": 0.7663,
+      "step": 440
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003757201646090535,
+      "loss": 0.8013,
+      "step": 445
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037530864197530867,
+      "loss": 0.7453,
+      "step": 450
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037489711934156377,
+      "loss": 0.7425,
+      "step": 455
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037448559670781893,
+      "loss": 0.7582,
+      "step": 460
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003740740740740741,
+      "loss": 0.7801,
+      "step": 465
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00037366255144032925,
+      "loss": 0.7809,
+      "step": 470
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003732510288065844,
+      "loss": 0.7749,
+      "step": 475
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00037283950617283956,
+      "loss": 0.7807,
+      "step": 480
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00037242798353909467,
+      "loss": 0.7715,
+      "step": 485
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003720164609053498,
+      "loss": 0.7356,
+      "step": 490
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000371604938271605,
+      "loss": 0.7674,
+      "step": 495
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00037119341563786014,
+      "loss": 0.7542,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00037078189300411525,
+      "loss": 0.7583,
+      "step": 505
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003703703703703704,
+      "loss": 0.7767,
+      "step": 510
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036995884773662556,
+      "loss": 0.7853,
+      "step": 515
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036954732510288067,
+      "loss": 0.7733,
+      "step": 520
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036913580246913583,
+      "loss": 0.7758,
+      "step": 525
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.000368724279835391,
+      "loss": 0.7698,
+      "step": 530
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036831275720164614,
+      "loss": 0.7805,
+      "step": 535
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036790123456790125,
+      "loss": 0.7573,
+      "step": 540
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003674897119341564,
+      "loss": 0.7709,
+      "step": 545
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036707818930041157,
+      "loss": 0.7994,
+      "step": 550
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036666666666666667,
+      "loss": 0.7363,
+      "step": 555
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036625514403292183,
+      "loss": 0.7478,
+      "step": 560
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000365843621399177,
+      "loss": 0.8188,
+      "step": 565
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003654320987654321,
+      "loss": 0.7524,
+      "step": 570
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00036502057613168725,
+      "loss": 0.7319,
+      "step": 575
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003646090534979424,
+      "loss": 0.7915,
+      "step": 580
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00036419753086419757,
+      "loss": 0.7722,
+      "step": 585
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00036378600823045267,
+      "loss": 0.7842,
+      "step": 590
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00036337448559670783,
+      "loss": 0.7591,
+      "step": 595
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000362962962962963,
+      "loss": 0.7653,
+      "step": 600
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003625514403292181,
+      "loss": 0.7838,
+      "step": 605
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00036213991769547325,
+      "loss": 0.7937,
+      "step": 610
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003617283950617284,
+      "loss": 0.77,
+      "step": 615
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00036131687242798357,
+      "loss": 0.7899,
+      "step": 620
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003609053497942387,
+      "loss": 0.7815,
+      "step": 625
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00036049382716049383,
+      "loss": 0.7648,
+      "step": 630
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.000360082304526749,
+      "loss": 0.7716,
+      "step": 635
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003596707818930041,
+      "loss": 0.7708,
+      "step": 640
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00035925925925925925,
+      "loss": 0.7306,
+      "step": 645
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003588477366255144,
+      "loss": 0.8007,
+      "step": 650
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003584362139917695,
+      "loss": 0.7551,
+      "step": 655
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003580246913580247,
+      "loss": 0.754,
+      "step": 660
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00035761316872427983,
+      "loss": 0.7599,
+      "step": 665
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.000357201646090535,
+      "loss": 0.7637,
+      "step": 670
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00035679012345679015,
+      "loss": 0.7766,
+      "step": 675
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003563786008230453,
+      "loss": 0.7727,
+      "step": 680
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003559670781893004,
+      "loss": 0.7675,
+      "step": 685
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035555555555555557,
+      "loss": 0.7707,
+      "step": 690
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035514403292181073,
+      "loss": 0.7221,
+      "step": 695
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003547325102880659,
+      "loss": 0.7335,
+      "step": 700
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035432098765432105,
+      "loss": 0.781,
+      "step": 705
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035390946502057615,
+      "loss": 0.7845,
+      "step": 710
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003534979423868313,
+      "loss": 0.7467,
+      "step": 715
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00035308641975308647,
+      "loss": 0.7735,
+      "step": 720
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003526748971193416,
+      "loss": 0.7368,
+      "step": 725
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00035226337448559673,
+      "loss": 0.7678,
+      "step": 730
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003518518518518519,
+      "loss": 0.7756,
+      "step": 735
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00035144032921810705,
+      "loss": 0.7635,
+      "step": 740
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00035102880658436215,
+      "loss": 0.7757,
+      "step": 745
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003506172839506173,
+      "loss": 0.7442,
+      "step": 750
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00035020576131687247,
+      "loss": 0.7584,
+      "step": 755
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003497942386831276,
+      "loss": 0.8333,
+      "step": 760
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00034938271604938273,
+      "loss": 0.7459,
+      "step": 765
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003489711934156379,
+      "loss": 0.7499,
+      "step": 770
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.000348559670781893,
+      "loss": 0.7571,
+      "step": 775
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00034814814814814816,
+      "loss": 0.7243,
+      "step": 780
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003477366255144033,
+      "loss": 0.7443,
+      "step": 785
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003473251028806585,
+      "loss": 0.7759,
+      "step": 790
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003469135802469136,
+      "loss": 0.7452,
+      "step": 795
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00034650205761316874,
+      "loss": 0.7578,
+      "step": 800
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003460905349794239,
+      "loss": 0.7634,
+      "step": 805
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.000345679012345679,
+      "loss": 0.7925,
+      "step": 810
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00034526748971193416,
+      "loss": 0.7966,
+      "step": 815
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003448559670781893,
+      "loss": 0.7601,
+      "step": 820
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003444444444444445,
+      "loss": 0.7617,
+      "step": 825
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003440329218106996,
+      "loss": 0.7526,
+      "step": 830
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00034362139917695474,
+      "loss": 0.7297,
+      "step": 835
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003432098765432099,
+      "loss": 0.7549,
+      "step": 840
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.000342798353909465,
+      "loss": 0.7517,
+      "step": 845
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00034238683127572016,
+      "loss": 0.7626,
+      "step": 850
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003419753086419753,
+      "loss": 0.7987,
+      "step": 855
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003415637860082305,
+      "loss": 0.7573,
+      "step": 860
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003411522633744856,
+      "loss": 0.8367,
+      "step": 865
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00034074074074074074,
+      "loss": 0.7258,
+      "step": 870
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003403292181069959,
+      "loss": 0.7632,
+      "step": 875
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00033991769547325106,
+      "loss": 0.7379,
+      "step": 880
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00033950617283950616,
+      "loss": 0.7529,
+      "step": 885
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003390946502057613,
+      "loss": 0.7391,
+      "step": 890
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003386831275720165,
+      "loss": 0.8061,
+      "step": 895
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00033827160493827164,
+      "loss": 0.7288,
+      "step": 900
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003378600823045268,
+      "loss": 0.7493,
+      "step": 905
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00033744855967078195,
+      "loss": 0.7702,
+      "step": 910
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00033703703703703706,
+      "loss": 0.7538,
+      "step": 915
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003366255144032922,
+      "loss": 0.728,
+      "step": 920
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003362139917695474,
+      "loss": 0.7776,
+      "step": 925
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003358024691358025,
+      "loss": 0.7883,
+      "step": 930
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00033539094650205764,
+      "loss": 0.7471,
+      "step": 935
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003349794238683128,
+      "loss": 0.7464,
+      "step": 940
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00033456790123456795,
+      "loss": 0.7885,
+      "step": 945
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00033415637860082306,
+      "loss": 0.7509,
+      "step": 950
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003337448559670782,
+      "loss": 0.7681,
+      "step": 955
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003333333333333334,
+      "loss": 0.8246,
+      "step": 960
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003329218106995885,
+      "loss": 0.7604,
+      "step": 965
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00033251028806584364,
+      "loss": 0.7755,
+      "step": 970
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003320987654320988,
+      "loss": 0.7641,
+      "step": 975
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003316872427983539,
+      "loss": 0.7708,
+      "step": 980
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00033127572016460906,
+      "loss": 0.7936,
+      "step": 985
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003308641975308642,
+      "loss": 0.7641,
+      "step": 990
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003304526748971194,
+      "loss": 0.7479,
+      "step": 995
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003300411522633745,
+      "loss": 0.7547,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00032962962962962964,
+      "loss": 0.762,
+      "step": 1005
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003292181069958848,
+      "loss": 0.7472,
+      "step": 1010
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003288065843621399,
+      "loss": 0.7542,
+      "step": 1015
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00032839506172839506,
+      "loss": 0.7669,
+      "step": 1020
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003279835390946502,
+      "loss": 0.7812,
+      "step": 1025
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003275720164609054,
+      "loss": 0.7273,
+      "step": 1030
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003271604938271605,
+      "loss": 0.7822,
+      "step": 1035
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00032674897119341564,
+      "loss": 0.7337,
+      "step": 1040
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003263374485596708,
+      "loss": 0.7566,
+      "step": 1045
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003259259259259259,
+      "loss": 0.7377,
+      "step": 1050
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00032551440329218106,
+      "loss": 0.7856,
+      "step": 1055
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003251028806584362,
+      "loss": 0.7981,
+      "step": 1060
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003246913580246914,
+      "loss": 0.7505,
+      "step": 1065
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003242798353909465,
+      "loss": 0.7549,
+      "step": 1070
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00032386831275720164,
+      "loss": 0.7306,
+      "step": 1075
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003234567901234568,
+      "loss": 0.7343,
+      "step": 1080
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003230452674897119,
+      "loss": 0.738,
+      "step": 1085
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00032263374485596707,
+      "loss": 0.7655,
+      "step": 1090
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003222222222222222,
+      "loss": 0.7706,
+      "step": 1095
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003218106995884774,
+      "loss": 0.7512,
+      "step": 1100
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00032139917695473254,
+      "loss": 0.7549,
+      "step": 1105
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003209876543209877,
+      "loss": 0.7839,
+      "step": 1110
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003205761316872428,
+      "loss": 0.7511,
+      "step": 1115
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00032016460905349796,
+      "loss": 0.769,
+      "step": 1120
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003197530864197531,
+      "loss": 0.7685,
+      "step": 1125
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003193415637860083,
+      "loss": 0.7489,
+      "step": 1130
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003189300411522634,
+      "loss": 0.808,
+      "step": 1135
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00031851851851851854,
+      "loss": 0.7654,
+      "step": 1140
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003181069958847737,
+      "loss": 0.7845,
+      "step": 1145
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00031769547325102886,
+      "loss": 0.7886,
+      "step": 1150
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00031728395061728396,
+      "loss": 0.7318,
+      "step": 1155
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003168724279835391,
+      "loss": 0.7231,
+      "step": 1160
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003164609053497943,
+      "loss": 0.7471,
+      "step": 1165
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003160493827160494,
+      "loss": 0.7424,
+      "step": 1170
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00031563786008230454,
+      "loss": 0.7249,
+      "step": 1175
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003152263374485597,
+      "loss": 0.7419,
+      "step": 1180
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00031481481481481486,
+      "loss": 0.7567,
+      "step": 1185
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00031440329218106997,
+      "loss": 0.7707,
+      "step": 1190
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003139917695473251,
+      "loss": 0.7473,
+      "step": 1195
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003135802469135803,
+      "loss": 0.7222,
+      "step": 1200
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003131687242798354,
+      "loss": 0.7383,
+      "step": 1205
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00031275720164609055,
+      "loss": 0.7712,
+      "step": 1210
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003123456790123457,
+      "loss": 0.7602,
+      "step": 1215
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003119341563786008,
+      "loss": 0.7741,
+      "step": 1220
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00031152263374485597,
+      "loss": 0.7428,
+      "step": 1225
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003111111111111111,
+      "loss": 0.7605,
+      "step": 1230
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003106995884773663,
+      "loss": 0.7255,
+      "step": 1235
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003102880658436214,
+      "loss": 0.7468,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00030987654320987655,
+      "loss": 0.7961,
+      "step": 1245
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003094650205761317,
+      "loss": 0.7208,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003090534979423868,
+      "loss": 0.7331,
+      "step": 1255
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00030864197530864197,
+      "loss": 0.7371,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00030823045267489713,
+      "loss": 0.7206,
+      "step": 1265
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003078189300411523,
+      "loss": 0.7617,
+      "step": 1270
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003074074074074074,
+      "loss": 0.7652,
+      "step": 1275
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00030699588477366255,
+      "loss": 0.7635,
+      "step": 1280
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003065843621399177,
+      "loss": 0.7445,
+      "step": 1285
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003061728395061728,
+      "loss": 0.7717,
+      "step": 1290
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030576131687242797,
+      "loss": 0.7535,
+      "step": 1295
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030534979423868313,
+      "loss": 0.7677,
+      "step": 1300
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003049382716049383,
+      "loss": 0.8131,
+      "step": 1305
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030452674897119345,
+      "loss": 0.7754,
+      "step": 1310
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030411522633744855,
+      "loss": 0.76,
+      "step": 1315
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003037037037037037,
+      "loss": 0.7558,
+      "step": 1320
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00030329218106995887,
+      "loss": 0.7604,
+      "step": 1325
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.000302880658436214,
+      "loss": 0.7716,
+      "step": 1330
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003024691358024692,
+      "loss": 0.7669,
+      "step": 1335
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003020576131687243,
+      "loss": 0.7469,
+      "step": 1340
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030164609053497945,
+      "loss": 0.7511,
+      "step": 1345
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003012345679012346,
+      "loss": 0.7483,
+      "step": 1350
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030082304526748976,
+      "loss": 0.7509,
+      "step": 1355
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030041152263374487,
+      "loss": 0.7249,
+      "step": 1360
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.7289,
+      "step": 1365
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002995884773662552,
+      "loss": 0.7605,
+      "step": 1370
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002991769547325103,
+      "loss": 0.7185,
+      "step": 1375
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00029876543209876545,
+      "loss": 0.6974,
+      "step": 1380
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002983539094650206,
+      "loss": 0.7234,
+      "step": 1385
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00029794238683127577,
+      "loss": 0.7506,
+      "step": 1390
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029753086419753087,
+      "loss": 0.7524,
+      "step": 1395
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029711934156378603,
+      "loss": 0.7641,
+      "step": 1400
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002967078189300412,
+      "loss": 0.6967,
+      "step": 1405
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002962962962962963,
+      "loss": 0.735,
+      "step": 1410
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029588477366255145,
+      "loss": 0.7685,
+      "step": 1415
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002954732510288066,
+      "loss": 0.758,
+      "step": 1420
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002950617283950617,
+      "loss": 0.763,
+      "step": 1425
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00029465020576131687,
+      "loss": 0.712,
+      "step": 1430
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00029423868312757203,
+      "loss": 0.7236,
+      "step": 1435
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002938271604938272,
+      "loss": 0.7732,
+      "step": 1440
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002934156378600823,
+      "loss": 0.7689,
+      "step": 1445
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00029300411522633745,
+      "loss": 0.7352,
+      "step": 1450
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002925925925925926,
+      "loss": 0.7711,
+      "step": 1455
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002921810699588477,
+      "loss": 0.7549,
+      "step": 1460
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002917695473251029,
+      "loss": 0.7804,
+      "step": 1465
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00029135802469135803,
+      "loss": 0.7478,
+      "step": 1470
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002909465020576132,
+      "loss": 0.7801,
+      "step": 1475
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002905349794238683,
+      "loss": 0.7544,
+      "step": 1480
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00029012345679012345,
+      "loss": 0.7546,
+      "step": 1485
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002897119341563786,
+      "loss": 0.7648,
+      "step": 1490
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002893004115226337,
+      "loss": 0.7468,
+      "step": 1495
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002888888888888889,
+      "loss": 0.7434,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 5010,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 6.041910864582279e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/training_args.bin b/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..28c7b09fc2b3929abe4ad6608c7959f30a9a9d66
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43458f4cf6aeb211c730b848f93ab15f483827c314fb4dc1e79dd1f658b7dbc8
+size 5944
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/zero_to_fp32.py b/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/zero_to_fp32.py
new file mode 100644
index 0000000000000000000000000000000000000000..c98caae31534368be22b67fc4ae906836c992a8d
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-1500/zero_to_fp32.py
@@ -0,0 +1,587 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel()
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file, tag=args.tag)
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/README.md b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..2aa897f8fa13b49ce76b1fa188781e5f726e7d13
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-2-7b-hf
+library_name: peft
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/adapter_config.json b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9c81a592f0ff08374a4f61f6003029070a8429ae
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/adapter_config.json
@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "mora_type": 1,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_mora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/adapter_model.safetensors b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d8b05cc9e32ed956e9ea408c982222d498246a2e
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9671d2c504106bbfaae3fa086e35ace2d4b25fbf85e5c7020f54b5677be0e97e
+size 564342240
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..11e1dbfb1cf477030e7ae35c18d518247581c4c5
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3933686a0f0a60d101b1032c5bef91c6fceaa0fe41c7f40320e09c7faa2cec0c
+size 239914224
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/global_step2000/mp_rank_00_model_states.pt b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/global_step2000/mp_rank_00_model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4aab6acda7f4d6885ffff8571c12cf196a7a2a6d
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/global_step2000/mp_rank_00_model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4e1ac50aa58a138b91832747cb96f8f87afd194acf2a86a3da4b96105025c18
+size 40303404
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/latest b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/latest
new file mode 100644
index 0000000000000000000000000000000000000000..2a79fdc19587e6bc9de060e90633f3a151b04516
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/latest
@@ -0,0 +1 @@
+global_step2000
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/rng_state.pth b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..01fa155317818024b84adfe6fb7f4c798d9d4aea
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:120654c40ab07680b6e25c6f415f868d33c21d42ff816d413cf88a5c5793ca4b
+size 14244
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/scheduler.pt b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c2ccfb5890d7e3542e533ddfb0eb43acfd5be0ac
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26d324026b4b66cd9b8553682d39e90a564b56f31b1a487c65e1e5128f325560
+size 1064
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/trainer_state.json b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..c1537ff4ae520118b2106046131c76abd6a73664
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/trainer_state.json
@@ -0,0 +1,2421 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.7983284997037453,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.3798,
+      "step": 5
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 1.3917,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4e-05,
+      "loss": 1.2862,
+      "step": 15
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 1.2046,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.0634,
+      "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8e-05,
+      "loss": 1.0273,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 1.0472,
+      "step": 35
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 1.0301,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00012,
+      "loss": 0.9335,
+      "step": 45
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.921,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00014666666666666666,
+      "loss": 0.9506,
+      "step": 55
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016,
+      "loss": 0.8876,
+      "step": 60
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00017333333333333334,
+      "loss": 0.9335,
+      "step": 65
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 0.8554,
+      "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0002,
+      "loss": 0.8537,
+      "step": 75
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00021333333333333333,
+      "loss": 0.9033,
+      "step": 80
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00022666666666666668,
+      "loss": 0.8203,
+      "step": 85
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00024,
+      "loss": 0.8611,
+      "step": 90
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00025333333333333333,
+      "loss": 0.8303,
+      "step": 95
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002666666666666667,
+      "loss": 0.8528,
+      "step": 100
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00028,
+      "loss": 0.8537,
+      "step": 105
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002933333333333333,
+      "loss": 0.8286,
+      "step": 110
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003066666666666667,
+      "loss": 0.8449,
+      "step": 115
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00032,
+      "loss": 0.8377,
+      "step": 120
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003333333333333334,
+      "loss": 0.8419,
+      "step": 125
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00034666666666666667,
+      "loss": 0.8265,
+      "step": 130
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00036,
+      "loss": 0.8037,
+      "step": 135
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003733333333333334,
+      "loss": 0.7924,
+      "step": 140
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00038666666666666667,
+      "loss": 0.8245,
+      "step": 145
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0004,
+      "loss": 0.8388,
+      "step": 150
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003995884773662552,
+      "loss": 0.8066,
+      "step": 155
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003991769547325103,
+      "loss": 0.8107,
+      "step": 160
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039876543209876544,
+      "loss": 0.8005,
+      "step": 165
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003983539094650206,
+      "loss": 0.7727,
+      "step": 170
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039794238683127576,
+      "loss": 0.8276,
+      "step": 175
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039753086419753086,
+      "loss": 0.8464,
+      "step": 180
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000397119341563786,
+      "loss": 0.8348,
+      "step": 185
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003967078189300412,
+      "loss": 0.8228,
+      "step": 190
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003962962962962963,
+      "loss": 0.8254,
+      "step": 195
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00039588477366255144,
+      "loss": 0.817,
+      "step": 200
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003954732510288066,
+      "loss": 0.8365,
+      "step": 205
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003950617283950617,
+      "loss": 0.793,
+      "step": 210
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00039465020576131686,
+      "loss": 0.8014,
+      "step": 215
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000394238683127572,
+      "loss": 0.8049,
+      "step": 220
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003938271604938272,
+      "loss": 0.7841,
+      "step": 225
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003934156378600823,
+      "loss": 0.7977,
+      "step": 230
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00039300411522633744,
+      "loss": 0.8299,
+      "step": 235
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003925925925925926,
+      "loss": 0.7729,
+      "step": 240
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00039218106995884776,
+      "loss": 0.8082,
+      "step": 245
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003917695473251029,
+      "loss": 0.8173,
+      "step": 250
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000391358024691358,
+      "loss": 0.8379,
+      "step": 255
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003909465020576132,
+      "loss": 0.7962,
+      "step": 260
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00039053497942386834,
+      "loss": 0.8067,
+      "step": 265
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003901234567901235,
+      "loss": 0.7915,
+      "step": 270
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00038971193415637866,
+      "loss": 0.7905,
+      "step": 275
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00038930041152263376,
+      "loss": 0.7862,
+      "step": 280
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003888888888888889,
+      "loss": 0.7709,
+      "step": 285
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003884773662551441,
+      "loss": 0.7773,
+      "step": 290
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00038806584362139924,
+      "loss": 0.8068,
+      "step": 295
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00038765432098765434,
+      "loss": 0.7962,
+      "step": 300
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003872427983539095,
+      "loss": 0.7894,
+      "step": 305
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00038683127572016466,
+      "loss": 0.7705,
+      "step": 310
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00038641975308641976,
+      "loss": 0.7882,
+      "step": 315
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003860082304526749,
+      "loss": 0.7865,
+      "step": 320
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003855967078189301,
+      "loss": 0.7939,
+      "step": 325
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003851851851851852,
+      "loss": 0.7724,
+      "step": 330
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00038477366255144034,
+      "loss": 0.7771,
+      "step": 335
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003843621399176955,
+      "loss": 0.7941,
+      "step": 340
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00038395061728395066,
+      "loss": 0.7822,
+      "step": 345
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00038353909465020577,
+      "loss": 0.8143,
+      "step": 350
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003831275720164609,
+      "loss": 0.795,
+      "step": 355
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003827160493827161,
+      "loss": 0.8049,
+      "step": 360
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003823045267489712,
+      "loss": 0.8309,
+      "step": 365
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00038189300411522635,
+      "loss": 0.8314,
+      "step": 370
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003814814814814815,
+      "loss": 0.801,
+      "step": 375
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00038106995884773666,
+      "loss": 0.8084,
+      "step": 380
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00038065843621399177,
+      "loss": 0.8129,
+      "step": 385
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003802469135802469,
+      "loss": 0.7859,
+      "step": 390
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003798353909465021,
+      "loss": 0.7874,
+      "step": 395
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003794238683127572,
+      "loss": 0.7548,
+      "step": 400
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00037901234567901235,
+      "loss": 0.8092,
+      "step": 405
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003786008230452675,
+      "loss": 0.8041,
+      "step": 410
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00037818930041152266,
+      "loss": 0.777,
+      "step": 415
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00037777777777777777,
+      "loss": 0.7699,
+      "step": 420
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00037736625514403293,
+      "loss": 0.781,
+      "step": 425
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003769547325102881,
+      "loss": 0.7504,
+      "step": 430
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003765432098765432,
+      "loss": 0.7974,
+      "step": 435
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037613168724279835,
+      "loss": 0.7663,
+      "step": 440
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003757201646090535,
+      "loss": 0.8013,
+      "step": 445
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037530864197530867,
+      "loss": 0.7453,
+      "step": 450
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037489711934156377,
+      "loss": 0.7425,
+      "step": 455
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037448559670781893,
+      "loss": 0.7582,
+      "step": 460
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003740740740740741,
+      "loss": 0.7801,
+      "step": 465
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00037366255144032925,
+      "loss": 0.7809,
+      "step": 470
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003732510288065844,
+      "loss": 0.7749,
+      "step": 475
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00037283950617283956,
+      "loss": 0.7807,
+      "step": 480
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00037242798353909467,
+      "loss": 0.7715,
+      "step": 485
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003720164609053498,
+      "loss": 0.7356,
+      "step": 490
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000371604938271605,
+      "loss": 0.7674,
+      "step": 495
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00037119341563786014,
+      "loss": 0.7542,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00037078189300411525,
+      "loss": 0.7583,
+      "step": 505
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003703703703703704,
+      "loss": 0.7767,
+      "step": 510
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036995884773662556,
+      "loss": 0.7853,
+      "step": 515
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036954732510288067,
+      "loss": 0.7733,
+      "step": 520
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036913580246913583,
+      "loss": 0.7758,
+      "step": 525
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.000368724279835391,
+      "loss": 0.7698,
+      "step": 530
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036831275720164614,
+      "loss": 0.7805,
+      "step": 535
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036790123456790125,
+      "loss": 0.7573,
+      "step": 540
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003674897119341564,
+      "loss": 0.7709,
+      "step": 545
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036707818930041157,
+      "loss": 0.7994,
+      "step": 550
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036666666666666667,
+      "loss": 0.7363,
+      "step": 555
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036625514403292183,
+      "loss": 0.7478,
+      "step": 560
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000365843621399177,
+      "loss": 0.8188,
+      "step": 565
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003654320987654321,
+      "loss": 0.7524,
+      "step": 570
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00036502057613168725,
+      "loss": 0.7319,
+      "step": 575
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003646090534979424,
+      "loss": 0.7915,
+      "step": 580
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00036419753086419757,
+      "loss": 0.7722,
+      "step": 585
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00036378600823045267,
+      "loss": 0.7842,
+      "step": 590
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00036337448559670783,
+      "loss": 0.7591,
+      "step": 595
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000362962962962963,
+      "loss": 0.7653,
+      "step": 600
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003625514403292181,
+      "loss": 0.7838,
+      "step": 605
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00036213991769547325,
+      "loss": 0.7937,
+      "step": 610
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003617283950617284,
+      "loss": 0.77,
+      "step": 615
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00036131687242798357,
+      "loss": 0.7899,
+      "step": 620
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003609053497942387,
+      "loss": 0.7815,
+      "step": 625
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00036049382716049383,
+      "loss": 0.7648,
+      "step": 630
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.000360082304526749,
+      "loss": 0.7716,
+      "step": 635
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003596707818930041,
+      "loss": 0.7708,
+      "step": 640
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00035925925925925925,
+      "loss": 0.7306,
+      "step": 645
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003588477366255144,
+      "loss": 0.8007,
+      "step": 650
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003584362139917695,
+      "loss": 0.7551,
+      "step": 655
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003580246913580247,
+      "loss": 0.754,
+      "step": 660
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00035761316872427983,
+      "loss": 0.7599,
+      "step": 665
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.000357201646090535,
+      "loss": 0.7637,
+      "step": 670
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00035679012345679015,
+      "loss": 0.7766,
+      "step": 675
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003563786008230453,
+      "loss": 0.7727,
+      "step": 680
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003559670781893004,
+      "loss": 0.7675,
+      "step": 685
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035555555555555557,
+      "loss": 0.7707,
+      "step": 690
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035514403292181073,
+      "loss": 0.7221,
+      "step": 695
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003547325102880659,
+      "loss": 0.7335,
+      "step": 700
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035432098765432105,
+      "loss": 0.781,
+      "step": 705
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035390946502057615,
+      "loss": 0.7845,
+      "step": 710
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003534979423868313,
+      "loss": 0.7467,
+      "step": 715
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00035308641975308647,
+      "loss": 0.7735,
+      "step": 720
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003526748971193416,
+      "loss": 0.7368,
+      "step": 725
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00035226337448559673,
+      "loss": 0.7678,
+      "step": 730
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003518518518518519,
+      "loss": 0.7756,
+      "step": 735
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00035144032921810705,
+      "loss": 0.7635,
+      "step": 740
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00035102880658436215,
+      "loss": 0.7757,
+      "step": 745
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003506172839506173,
+      "loss": 0.7442,
+      "step": 750
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00035020576131687247,
+      "loss": 0.7584,
+      "step": 755
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003497942386831276,
+      "loss": 0.8333,
+      "step": 760
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00034938271604938273,
+      "loss": 0.7459,
+      "step": 765
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003489711934156379,
+      "loss": 0.7499,
+      "step": 770
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.000348559670781893,
+      "loss": 0.7571,
+      "step": 775
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00034814814814814816,
+      "loss": 0.7243,
+      "step": 780
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003477366255144033,
+      "loss": 0.7443,
+      "step": 785
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003473251028806585,
+      "loss": 0.7759,
+      "step": 790
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003469135802469136,
+      "loss": 0.7452,
+      "step": 795
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00034650205761316874,
+      "loss": 0.7578,
+      "step": 800
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003460905349794239,
+      "loss": 0.7634,
+      "step": 805
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.000345679012345679,
+      "loss": 0.7925,
+      "step": 810
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00034526748971193416,
+      "loss": 0.7966,
+      "step": 815
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003448559670781893,
+      "loss": 0.7601,
+      "step": 820
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003444444444444445,
+      "loss": 0.7617,
+      "step": 825
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003440329218106996,
+      "loss": 0.7526,
+      "step": 830
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00034362139917695474,
+      "loss": 0.7297,
+      "step": 835
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003432098765432099,
+      "loss": 0.7549,
+      "step": 840
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.000342798353909465,
+      "loss": 0.7517,
+      "step": 845
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00034238683127572016,
+      "loss": 0.7626,
+      "step": 850
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003419753086419753,
+      "loss": 0.7987,
+      "step": 855
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003415637860082305,
+      "loss": 0.7573,
+      "step": 860
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003411522633744856,
+      "loss": 0.8367,
+      "step": 865
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00034074074074074074,
+      "loss": 0.7258,
+      "step": 870
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003403292181069959,
+      "loss": 0.7632,
+      "step": 875
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00033991769547325106,
+      "loss": 0.7379,
+      "step": 880
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00033950617283950616,
+      "loss": 0.7529,
+      "step": 885
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003390946502057613,
+      "loss": 0.7391,
+      "step": 890
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003386831275720165,
+      "loss": 0.8061,
+      "step": 895
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00033827160493827164,
+      "loss": 0.7288,
+      "step": 900
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003378600823045268,
+      "loss": 0.7493,
+      "step": 905
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00033744855967078195,
+      "loss": 0.7702,
+      "step": 910
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00033703703703703706,
+      "loss": 0.7538,
+      "step": 915
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003366255144032922,
+      "loss": 0.728,
+      "step": 920
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003362139917695474,
+      "loss": 0.7776,
+      "step": 925
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003358024691358025,
+      "loss": 0.7883,
+      "step": 930
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00033539094650205764,
+      "loss": 0.7471,
+      "step": 935
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003349794238683128,
+      "loss": 0.7464,
+      "step": 940
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00033456790123456795,
+      "loss": 0.7885,
+      "step": 945
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00033415637860082306,
+      "loss": 0.7509,
+      "step": 950
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003337448559670782,
+      "loss": 0.7681,
+      "step": 955
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003333333333333334,
+      "loss": 0.8246,
+      "step": 960
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003329218106995885,
+      "loss": 0.7604,
+      "step": 965
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00033251028806584364,
+      "loss": 0.7755,
+      "step": 970
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003320987654320988,
+      "loss": 0.7641,
+      "step": 975
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003316872427983539,
+      "loss": 0.7708,
+      "step": 980
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00033127572016460906,
+      "loss": 0.7936,
+      "step": 985
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003308641975308642,
+      "loss": 0.7641,
+      "step": 990
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003304526748971194,
+      "loss": 0.7479,
+      "step": 995
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003300411522633745,
+      "loss": 0.7547,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00032962962962962964,
+      "loss": 0.762,
+      "step": 1005
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003292181069958848,
+      "loss": 0.7472,
+      "step": 1010
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003288065843621399,
+      "loss": 0.7542,
+      "step": 1015
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00032839506172839506,
+      "loss": 0.7669,
+      "step": 1020
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003279835390946502,
+      "loss": 0.7812,
+      "step": 1025
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003275720164609054,
+      "loss": 0.7273,
+      "step": 1030
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003271604938271605,
+      "loss": 0.7822,
+      "step": 1035
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00032674897119341564,
+      "loss": 0.7337,
+      "step": 1040
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003263374485596708,
+      "loss": 0.7566,
+      "step": 1045
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003259259259259259,
+      "loss": 0.7377,
+      "step": 1050
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00032551440329218106,
+      "loss": 0.7856,
+      "step": 1055
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003251028806584362,
+      "loss": 0.7981,
+      "step": 1060
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003246913580246914,
+      "loss": 0.7505,
+      "step": 1065
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003242798353909465,
+      "loss": 0.7549,
+      "step": 1070
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00032386831275720164,
+      "loss": 0.7306,
+      "step": 1075
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003234567901234568,
+      "loss": 0.7343,
+      "step": 1080
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003230452674897119,
+      "loss": 0.738,
+      "step": 1085
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00032263374485596707,
+      "loss": 0.7655,
+      "step": 1090
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003222222222222222,
+      "loss": 0.7706,
+      "step": 1095
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003218106995884774,
+      "loss": 0.7512,
+      "step": 1100
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00032139917695473254,
+      "loss": 0.7549,
+      "step": 1105
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003209876543209877,
+      "loss": 0.7839,
+      "step": 1110
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003205761316872428,
+      "loss": 0.7511,
+      "step": 1115
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00032016460905349796,
+      "loss": 0.769,
+      "step": 1120
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003197530864197531,
+      "loss": 0.7685,
+      "step": 1125
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003193415637860083,
+      "loss": 0.7489,
+      "step": 1130
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003189300411522634,
+      "loss": 0.808,
+      "step": 1135
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00031851851851851854,
+      "loss": 0.7654,
+      "step": 1140
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003181069958847737,
+      "loss": 0.7845,
+      "step": 1145
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00031769547325102886,
+      "loss": 0.7886,
+      "step": 1150
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00031728395061728396,
+      "loss": 0.7318,
+      "step": 1155
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003168724279835391,
+      "loss": 0.7231,
+      "step": 1160
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003164609053497943,
+      "loss": 0.7471,
+      "step": 1165
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003160493827160494,
+      "loss": 0.7424,
+      "step": 1170
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00031563786008230454,
+      "loss": 0.7249,
+      "step": 1175
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003152263374485597,
+      "loss": 0.7419,
+      "step": 1180
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00031481481481481486,
+      "loss": 0.7567,
+      "step": 1185
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00031440329218106997,
+      "loss": 0.7707,
+      "step": 1190
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003139917695473251,
+      "loss": 0.7473,
+      "step": 1195
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003135802469135803,
+      "loss": 0.7222,
+      "step": 1200
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003131687242798354,
+      "loss": 0.7383,
+      "step": 1205
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00031275720164609055,
+      "loss": 0.7712,
+      "step": 1210
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003123456790123457,
+      "loss": 0.7602,
+      "step": 1215
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003119341563786008,
+      "loss": 0.7741,
+      "step": 1220
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00031152263374485597,
+      "loss": 0.7428,
+      "step": 1225
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003111111111111111,
+      "loss": 0.7605,
+      "step": 1230
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003106995884773663,
+      "loss": 0.7255,
+      "step": 1235
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003102880658436214,
+      "loss": 0.7468,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00030987654320987655,
+      "loss": 0.7961,
+      "step": 1245
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003094650205761317,
+      "loss": 0.7208,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003090534979423868,
+      "loss": 0.7331,
+      "step": 1255
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00030864197530864197,
+      "loss": 0.7371,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00030823045267489713,
+      "loss": 0.7206,
+      "step": 1265
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003078189300411523,
+      "loss": 0.7617,
+      "step": 1270
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003074074074074074,
+      "loss": 0.7652,
+      "step": 1275
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00030699588477366255,
+      "loss": 0.7635,
+      "step": 1280
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003065843621399177,
+      "loss": 0.7445,
+      "step": 1285
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003061728395061728,
+      "loss": 0.7717,
+      "step": 1290
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030576131687242797,
+      "loss": 0.7535,
+      "step": 1295
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030534979423868313,
+      "loss": 0.7677,
+      "step": 1300
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003049382716049383,
+      "loss": 0.8131,
+      "step": 1305
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030452674897119345,
+      "loss": 0.7754,
+      "step": 1310
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030411522633744855,
+      "loss": 0.76,
+      "step": 1315
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003037037037037037,
+      "loss": 0.7558,
+      "step": 1320
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00030329218106995887,
+      "loss": 0.7604,
+      "step": 1325
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.000302880658436214,
+      "loss": 0.7716,
+      "step": 1330
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003024691358024692,
+      "loss": 0.7669,
+      "step": 1335
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003020576131687243,
+      "loss": 0.7469,
+      "step": 1340
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030164609053497945,
+      "loss": 0.7511,
+      "step": 1345
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003012345679012346,
+      "loss": 0.7483,
+      "step": 1350
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030082304526748976,
+      "loss": 0.7509,
+      "step": 1355
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030041152263374487,
+      "loss": 0.7249,
+      "step": 1360
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.7289,
+      "step": 1365
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002995884773662552,
+      "loss": 0.7605,
+      "step": 1370
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002991769547325103,
+      "loss": 0.7185,
+      "step": 1375
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00029876543209876545,
+      "loss": 0.6974,
+      "step": 1380
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002983539094650206,
+      "loss": 0.7234,
+      "step": 1385
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00029794238683127577,
+      "loss": 0.7506,
+      "step": 1390
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029753086419753087,
+      "loss": 0.7524,
+      "step": 1395
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029711934156378603,
+      "loss": 0.7641,
+      "step": 1400
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002967078189300412,
+      "loss": 0.6967,
+      "step": 1405
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002962962962962963,
+      "loss": 0.735,
+      "step": 1410
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029588477366255145,
+      "loss": 0.7685,
+      "step": 1415
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002954732510288066,
+      "loss": 0.758,
+      "step": 1420
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002950617283950617,
+      "loss": 0.763,
+      "step": 1425
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00029465020576131687,
+      "loss": 0.712,
+      "step": 1430
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00029423868312757203,
+      "loss": 0.7236,
+      "step": 1435
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002938271604938272,
+      "loss": 0.7732,
+      "step": 1440
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002934156378600823,
+      "loss": 0.7689,
+      "step": 1445
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00029300411522633745,
+      "loss": 0.7352,
+      "step": 1450
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002925925925925926,
+      "loss": 0.7711,
+      "step": 1455
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002921810699588477,
+      "loss": 0.7549,
+      "step": 1460
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002917695473251029,
+      "loss": 0.7804,
+      "step": 1465
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00029135802469135803,
+      "loss": 0.7478,
+      "step": 1470
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002909465020576132,
+      "loss": 0.7801,
+      "step": 1475
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002905349794238683,
+      "loss": 0.7544,
+      "step": 1480
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00029012345679012345,
+      "loss": 0.7546,
+      "step": 1485
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002897119341563786,
+      "loss": 0.7648,
+      "step": 1490
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002893004115226337,
+      "loss": 0.7468,
+      "step": 1495
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002888888888888889,
+      "loss": 0.7434,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00028847736625514403,
+      "loss": 0.7348,
+      "step": 1505
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002880658436213992,
+      "loss": 0.7515,
+      "step": 1510
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00028765432098765435,
+      "loss": 0.7345,
+      "step": 1515
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00028724279835390946,
+      "loss": 0.7701,
+      "step": 1520
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002868312757201646,
+      "loss": 0.7472,
+      "step": 1525
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00028641975308641977,
+      "loss": 0.7075,
+      "step": 1530
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00028600823045267493,
+      "loss": 0.7483,
+      "step": 1535
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002855967078189301,
+      "loss": 0.712,
+      "step": 1540
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002851851851851852,
+      "loss": 0.7484,
+      "step": 1545
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00028477366255144035,
+      "loss": 0.7471,
+      "step": 1550
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002843621399176955,
+      "loss": 0.7462,
+      "step": 1555
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00028395061728395067,
+      "loss": 0.7371,
+      "step": 1560
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002835390946502058,
+      "loss": 0.7753,
+      "step": 1565
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00028312757201646093,
+      "loss": 0.7374,
+      "step": 1570
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002827160493827161,
+      "loss": 0.7328,
+      "step": 1575
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002823045267489712,
+      "loss": 0.7159,
+      "step": 1580
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00028189300411522635,
+      "loss": 0.7594,
+      "step": 1585
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002814814814814815,
+      "loss": 0.7215,
+      "step": 1590
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00028106995884773667,
+      "loss": 0.7398,
+      "step": 1595
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002806584362139918,
+      "loss": 0.773,
+      "step": 1600
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00028024691358024693,
+      "loss": 0.7584,
+      "step": 1605
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002798353909465021,
+      "loss": 0.7117,
+      "step": 1610
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002794238683127572,
+      "loss": 0.7471,
+      "step": 1615
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00027901234567901236,
+      "loss": 0.7443,
+      "step": 1620
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002786008230452675,
+      "loss": 0.7292,
+      "step": 1625
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002781893004115227,
+      "loss": 0.7716,
+      "step": 1630
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 0.763,
+      "step": 1635
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00027736625514403294,
+      "loss": 0.7408,
+      "step": 1640
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002769547325102881,
+      "loss": 0.7403,
+      "step": 1645
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002765432098765432,
+      "loss": 0.7508,
+      "step": 1650
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00027613168724279836,
+      "loss": 0.7687,
+      "step": 1655
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002757201646090535,
+      "loss": 0.7305,
+      "step": 1660
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002753086419753086,
+      "loss": 0.7165,
+      "step": 1665
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002748971193415638,
+      "loss": 0.8,
+      "step": 1670
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00027448559670781894,
+      "loss": 0.7357,
+      "step": 1675
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002740740740740741,
+      "loss": 0.7988,
+      "step": 1680
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002736625514403292,
+      "loss": 0.7559,
+      "step": 1685
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00027325102880658436,
+      "loss": 0.712,
+      "step": 1690
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002728395061728395,
+      "loss": 0.7486,
+      "step": 1695
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002724279835390946,
+      "loss": 0.7388,
+      "step": 1700
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002720164609053498,
+      "loss": 0.7441,
+      "step": 1705
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00027160493827160494,
+      "loss": 0.7547,
+      "step": 1710
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002711934156378601,
+      "loss": 0.7229,
+      "step": 1715
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002707818930041152,
+      "loss": 0.7383,
+      "step": 1720
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00027037037037037036,
+      "loss": 0.7606,
+      "step": 1725
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002699588477366255,
+      "loss": 0.7529,
+      "step": 1730
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002695473251028807,
+      "loss": 0.752,
+      "step": 1735
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00026913580246913584,
+      "loss": 0.7342,
+      "step": 1740
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.000268724279835391,
+      "loss": 0.7308,
+      "step": 1745
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002683127572016461,
+      "loss": 0.6915,
+      "step": 1750
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00026790123456790126,
+      "loss": 0.7344,
+      "step": 1755
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002674897119341564,
+      "loss": 0.7426,
+      "step": 1760
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002670781893004116,
+      "loss": 0.7088,
+      "step": 1765
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002666666666666667,
+      "loss": 0.7241,
+      "step": 1770
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00026625514403292184,
+      "loss": 0.7552,
+      "step": 1775
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.000265843621399177,
+      "loss": 0.7477,
+      "step": 1780
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002654320987654321,
+      "loss": 0.7115,
+      "step": 1785
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00026502057613168726,
+      "loss": 0.7538,
+      "step": 1790
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002646090534979424,
+      "loss": 0.7321,
+      "step": 1795
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002641975308641976,
+      "loss": 0.7212,
+      "step": 1800
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002637860082304527,
+      "loss": 0.747,
+      "step": 1805
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00026337448559670784,
+      "loss": 0.7606,
+      "step": 1810
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.000262962962962963,
+      "loss": 0.7344,
+      "step": 1815
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002625514403292181,
+      "loss": 0.7783,
+      "step": 1820
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00026213991769547326,
+      "loss": 0.7556,
+      "step": 1825
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002617283950617284,
+      "loss": 0.7585,
+      "step": 1830
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002613168724279836,
+      "loss": 0.7359,
+      "step": 1835
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002609053497942387,
+      "loss": 0.7185,
+      "step": 1840
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00026049382716049384,
+      "loss": 0.7573,
+      "step": 1845
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.000260082304526749,
+      "loss": 0.7619,
+      "step": 1850
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002596707818930041,
+      "loss": 0.7611,
+      "step": 1855
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00025925925925925926,
+      "loss": 0.7647,
+      "step": 1860
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002588477366255144,
+      "loss": 0.7398,
+      "step": 1865
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002584362139917695,
+      "loss": 0.7683,
+      "step": 1870
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002580246913580247,
+      "loss": 0.7817,
+      "step": 1875
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00025761316872427984,
+      "loss": 0.742,
+      "step": 1880
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.000257201646090535,
+      "loss": 0.7509,
+      "step": 1885
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002567901234567901,
+      "loss": 0.7058,
+      "step": 1890
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00025637860082304526,
+      "loss": 0.7635,
+      "step": 1895
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002559670781893004,
+      "loss": 0.734,
+      "step": 1900
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00025555555555555553,
+      "loss": 0.7416,
+      "step": 1905
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002551440329218107,
+      "loss": 0.7071,
+      "step": 1910
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00025473251028806584,
+      "loss": 0.7275,
+      "step": 1915
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.000254320987654321,
+      "loss": 0.7413,
+      "step": 1920
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002539094650205761,
+      "loss": 0.7703,
+      "step": 1925
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00025349794238683127,
+      "loss": 0.7331,
+      "step": 1930
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002530864197530864,
+      "loss": 0.7251,
+      "step": 1935
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002526748971193416,
+      "loss": 0.7341,
+      "step": 1940
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00025226337448559674,
+      "loss": 0.7079,
+      "step": 1945
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00025185185185185185,
+      "loss": 0.7615,
+      "step": 1950
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.000251440329218107,
+      "loss": 0.7144,
+      "step": 1955
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00025102880658436216,
+      "loss": 0.7527,
+      "step": 1960
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0002506172839506173,
+      "loss": 0.7327,
+      "step": 1965
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002502057613168725,
+      "loss": 0.7173,
+      "step": 1970
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002497942386831276,
+      "loss": 0.7239,
+      "step": 1975
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00024938271604938274,
+      "loss": 0.7442,
+      "step": 1980
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002489711934156379,
+      "loss": 0.7396,
+      "step": 1985
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.000248559670781893,
+      "loss": 0.7365,
+      "step": 1990
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00024814814814814816,
+      "loss": 0.7037,
+      "step": 1995
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002477366255144033,
+      "loss": 0.721,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 5010,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 8.056468541093708e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/training_args.bin b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..28c7b09fc2b3929abe4ad6608c7959f30a9a9d66
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43458f4cf6aeb211c730b848f93ab15f483827c314fb4dc1e79dd1f658b7dbc8
+size 5944
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/zero_to_fp32.py b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/zero_to_fp32.py
new file mode 100644
index 0000000000000000000000000000000000000000..c98caae31534368be22b67fc4ae906836c992a8d
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2000/zero_to_fp32.py
@@ -0,0 +1,587 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel()
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file, tag=args.tag)
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/README.md b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..2aa897f8fa13b49ce76b1fa188781e5f726e7d13
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-2-7b-hf
+library_name: peft
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/adapter_config.json b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9c81a592f0ff08374a4f61f6003029070a8429ae
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/adapter_config.json
@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "mora_type": 1,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_mora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/adapter_model.safetensors b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9a8e8e08cb2fdcae1d7e84bb020d23f4adacaf97
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b416d3e258a582396075c05428bff40bfdfca1eb90c49c8d3772f778275bc31
+size 564342240
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/global_step2500/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/global_step2500/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4a67da1db278844423a6f66a10380ee6bc3ff710
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/global_step2500/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcdc9e140d08d1a6a769adf0c31faed7eb8110dc4b7f6518a08d49a23e02294f
+size 239914224
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/global_step2500/mp_rank_00_model_states.pt b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/global_step2500/mp_rank_00_model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ff84619d49a0d06eb54edc4e0cd940c1aa889c6f
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/global_step2500/mp_rank_00_model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f60f73c4622f20dc7ff3cfbb9b219fee35bf8134a14b777c6845e321c049fb20
+size 40303404
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/latest b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/latest
new file mode 100644
index 0000000000000000000000000000000000000000..98f8bed9a5485ee900d9931cc06950de69499848
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/latest
@@ -0,0 +1 @@
+global_step2500
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/rng_state.pth b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3ff6036981fc298701f8a4118eb1ee4fa3ed5ed9
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f825f29d46d68de12985e875822b27efaac55bdba6c419fb26c2f1eb068aef1
+size 14244
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/scheduler.pt b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4965c72bdc2e64c92c4eeb3bf75848b7450ca9b7
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a13f4f8ba2e5988cc6fd82905cf4ea363a21a822e658eabdc1f337bcaed20957
+size 1064
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/trainer_state.json b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..281356506addcbaced4ceae9ff7203986b9632ae
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/trainer_state.json
@@ -0,0 +1,3021 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9979106246296816,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.3798,
+      "step": 5
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 1.3917,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4e-05,
+      "loss": 1.2862,
+      "step": 15
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 1.2046,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.0634,
+      "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8e-05,
+      "loss": 1.0273,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 1.0472,
+      "step": 35
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 1.0301,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00012,
+      "loss": 0.9335,
+      "step": 45
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.921,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00014666666666666666,
+      "loss": 0.9506,
+      "step": 55
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016,
+      "loss": 0.8876,
+      "step": 60
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00017333333333333334,
+      "loss": 0.9335,
+      "step": 65
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 0.8554,
+      "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0002,
+      "loss": 0.8537,
+      "step": 75
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00021333333333333333,
+      "loss": 0.9033,
+      "step": 80
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00022666666666666668,
+      "loss": 0.8203,
+      "step": 85
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00024,
+      "loss": 0.8611,
+      "step": 90
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00025333333333333333,
+      "loss": 0.8303,
+      "step": 95
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002666666666666667,
+      "loss": 0.8528,
+      "step": 100
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00028,
+      "loss": 0.8537,
+      "step": 105
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002933333333333333,
+      "loss": 0.8286,
+      "step": 110
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003066666666666667,
+      "loss": 0.8449,
+      "step": 115
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00032,
+      "loss": 0.8377,
+      "step": 120
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003333333333333334,
+      "loss": 0.8419,
+      "step": 125
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00034666666666666667,
+      "loss": 0.8265,
+      "step": 130
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00036,
+      "loss": 0.8037,
+      "step": 135
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003733333333333334,
+      "loss": 0.7924,
+      "step": 140
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00038666666666666667,
+      "loss": 0.8245,
+      "step": 145
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0004,
+      "loss": 0.8388,
+      "step": 150
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003995884773662552,
+      "loss": 0.8066,
+      "step": 155
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003991769547325103,
+      "loss": 0.8107,
+      "step": 160
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039876543209876544,
+      "loss": 0.8005,
+      "step": 165
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003983539094650206,
+      "loss": 0.7727,
+      "step": 170
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039794238683127576,
+      "loss": 0.8276,
+      "step": 175
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039753086419753086,
+      "loss": 0.8464,
+      "step": 180
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000397119341563786,
+      "loss": 0.8348,
+      "step": 185
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003967078189300412,
+      "loss": 0.8228,
+      "step": 190
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003962962962962963,
+      "loss": 0.8254,
+      "step": 195
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00039588477366255144,
+      "loss": 0.817,
+      "step": 200
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003954732510288066,
+      "loss": 0.8365,
+      "step": 205
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003950617283950617,
+      "loss": 0.793,
+      "step": 210
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00039465020576131686,
+      "loss": 0.8014,
+      "step": 215
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000394238683127572,
+      "loss": 0.8049,
+      "step": 220
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003938271604938272,
+      "loss": 0.7841,
+      "step": 225
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003934156378600823,
+      "loss": 0.7977,
+      "step": 230
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00039300411522633744,
+      "loss": 0.8299,
+      "step": 235
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003925925925925926,
+      "loss": 0.7729,
+      "step": 240
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00039218106995884776,
+      "loss": 0.8082,
+      "step": 245
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003917695473251029,
+      "loss": 0.8173,
+      "step": 250
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000391358024691358,
+      "loss": 0.8379,
+      "step": 255
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003909465020576132,
+      "loss": 0.7962,
+      "step": 260
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00039053497942386834,
+      "loss": 0.8067,
+      "step": 265
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003901234567901235,
+      "loss": 0.7915,
+      "step": 270
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00038971193415637866,
+      "loss": 0.7905,
+      "step": 275
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00038930041152263376,
+      "loss": 0.7862,
+      "step": 280
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003888888888888889,
+      "loss": 0.7709,
+      "step": 285
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003884773662551441,
+      "loss": 0.7773,
+      "step": 290
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00038806584362139924,
+      "loss": 0.8068,
+      "step": 295
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00038765432098765434,
+      "loss": 0.7962,
+      "step": 300
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003872427983539095,
+      "loss": 0.7894,
+      "step": 305
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00038683127572016466,
+      "loss": 0.7705,
+      "step": 310
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00038641975308641976,
+      "loss": 0.7882,
+      "step": 315
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003860082304526749,
+      "loss": 0.7865,
+      "step": 320
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003855967078189301,
+      "loss": 0.7939,
+      "step": 325
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003851851851851852,
+      "loss": 0.7724,
+      "step": 330
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00038477366255144034,
+      "loss": 0.7771,
+      "step": 335
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003843621399176955,
+      "loss": 0.7941,
+      "step": 340
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00038395061728395066,
+      "loss": 0.7822,
+      "step": 345
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00038353909465020577,
+      "loss": 0.8143,
+      "step": 350
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003831275720164609,
+      "loss": 0.795,
+      "step": 355
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003827160493827161,
+      "loss": 0.8049,
+      "step": 360
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003823045267489712,
+      "loss": 0.8309,
+      "step": 365
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00038189300411522635,
+      "loss": 0.8314,
+      "step": 370
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003814814814814815,
+      "loss": 0.801,
+      "step": 375
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00038106995884773666,
+      "loss": 0.8084,
+      "step": 380
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00038065843621399177,
+      "loss": 0.8129,
+      "step": 385
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003802469135802469,
+      "loss": 0.7859,
+      "step": 390
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003798353909465021,
+      "loss": 0.7874,
+      "step": 395
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003794238683127572,
+      "loss": 0.7548,
+      "step": 400
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00037901234567901235,
+      "loss": 0.8092,
+      "step": 405
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003786008230452675,
+      "loss": 0.8041,
+      "step": 410
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00037818930041152266,
+      "loss": 0.777,
+      "step": 415
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00037777777777777777,
+      "loss": 0.7699,
+      "step": 420
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00037736625514403293,
+      "loss": 0.781,
+      "step": 425
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003769547325102881,
+      "loss": 0.7504,
+      "step": 430
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003765432098765432,
+      "loss": 0.7974,
+      "step": 435
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037613168724279835,
+      "loss": 0.7663,
+      "step": 440
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003757201646090535,
+      "loss": 0.8013,
+      "step": 445
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037530864197530867,
+      "loss": 0.7453,
+      "step": 450
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037489711934156377,
+      "loss": 0.7425,
+      "step": 455
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037448559670781893,
+      "loss": 0.7582,
+      "step": 460
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003740740740740741,
+      "loss": 0.7801,
+      "step": 465
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00037366255144032925,
+      "loss": 0.7809,
+      "step": 470
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003732510288065844,
+      "loss": 0.7749,
+      "step": 475
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00037283950617283956,
+      "loss": 0.7807,
+      "step": 480
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00037242798353909467,
+      "loss": 0.7715,
+      "step": 485
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003720164609053498,
+      "loss": 0.7356,
+      "step": 490
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000371604938271605,
+      "loss": 0.7674,
+      "step": 495
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00037119341563786014,
+      "loss": 0.7542,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00037078189300411525,
+      "loss": 0.7583,
+      "step": 505
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003703703703703704,
+      "loss": 0.7767,
+      "step": 510
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036995884773662556,
+      "loss": 0.7853,
+      "step": 515
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036954732510288067,
+      "loss": 0.7733,
+      "step": 520
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036913580246913583,
+      "loss": 0.7758,
+      "step": 525
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.000368724279835391,
+      "loss": 0.7698,
+      "step": 530
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036831275720164614,
+      "loss": 0.7805,
+      "step": 535
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036790123456790125,
+      "loss": 0.7573,
+      "step": 540
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003674897119341564,
+      "loss": 0.7709,
+      "step": 545
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036707818930041157,
+      "loss": 0.7994,
+      "step": 550
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036666666666666667,
+      "loss": 0.7363,
+      "step": 555
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036625514403292183,
+      "loss": 0.7478,
+      "step": 560
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000365843621399177,
+      "loss": 0.8188,
+      "step": 565
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003654320987654321,
+      "loss": 0.7524,
+      "step": 570
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00036502057613168725,
+      "loss": 0.7319,
+      "step": 575
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003646090534979424,
+      "loss": 0.7915,
+      "step": 580
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00036419753086419757,
+      "loss": 0.7722,
+      "step": 585
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00036378600823045267,
+      "loss": 0.7842,
+      "step": 590
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00036337448559670783,
+      "loss": 0.7591,
+      "step": 595
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000362962962962963,
+      "loss": 0.7653,
+      "step": 600
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003625514403292181,
+      "loss": 0.7838,
+      "step": 605
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00036213991769547325,
+      "loss": 0.7937,
+      "step": 610
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003617283950617284,
+      "loss": 0.77,
+      "step": 615
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00036131687242798357,
+      "loss": 0.7899,
+      "step": 620
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003609053497942387,
+      "loss": 0.7815,
+      "step": 625
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00036049382716049383,
+      "loss": 0.7648,
+      "step": 630
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.000360082304526749,
+      "loss": 0.7716,
+      "step": 635
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003596707818930041,
+      "loss": 0.7708,
+      "step": 640
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00035925925925925925,
+      "loss": 0.7306,
+      "step": 645
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003588477366255144,
+      "loss": 0.8007,
+      "step": 650
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003584362139917695,
+      "loss": 0.7551,
+      "step": 655
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003580246913580247,
+      "loss": 0.754,
+      "step": 660
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00035761316872427983,
+      "loss": 0.7599,
+      "step": 665
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.000357201646090535,
+      "loss": 0.7637,
+      "step": 670
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00035679012345679015,
+      "loss": 0.7766,
+      "step": 675
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003563786008230453,
+      "loss": 0.7727,
+      "step": 680
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003559670781893004,
+      "loss": 0.7675,
+      "step": 685
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035555555555555557,
+      "loss": 0.7707,
+      "step": 690
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035514403292181073,
+      "loss": 0.7221,
+      "step": 695
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003547325102880659,
+      "loss": 0.7335,
+      "step": 700
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035432098765432105,
+      "loss": 0.781,
+      "step": 705
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035390946502057615,
+      "loss": 0.7845,
+      "step": 710
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003534979423868313,
+      "loss": 0.7467,
+      "step": 715
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00035308641975308647,
+      "loss": 0.7735,
+      "step": 720
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003526748971193416,
+      "loss": 0.7368,
+      "step": 725
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00035226337448559673,
+      "loss": 0.7678,
+      "step": 730
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003518518518518519,
+      "loss": 0.7756,
+      "step": 735
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00035144032921810705,
+      "loss": 0.7635,
+      "step": 740
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00035102880658436215,
+      "loss": 0.7757,
+      "step": 745
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003506172839506173,
+      "loss": 0.7442,
+      "step": 750
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00035020576131687247,
+      "loss": 0.7584,
+      "step": 755
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003497942386831276,
+      "loss": 0.8333,
+      "step": 760
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00034938271604938273,
+      "loss": 0.7459,
+      "step": 765
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003489711934156379,
+      "loss": 0.7499,
+      "step": 770
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.000348559670781893,
+      "loss": 0.7571,
+      "step": 775
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00034814814814814816,
+      "loss": 0.7243,
+      "step": 780
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003477366255144033,
+      "loss": 0.7443,
+      "step": 785
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003473251028806585,
+      "loss": 0.7759,
+      "step": 790
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003469135802469136,
+      "loss": 0.7452,
+      "step": 795
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00034650205761316874,
+      "loss": 0.7578,
+      "step": 800
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003460905349794239,
+      "loss": 0.7634,
+      "step": 805
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.000345679012345679,
+      "loss": 0.7925,
+      "step": 810
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00034526748971193416,
+      "loss": 0.7966,
+      "step": 815
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003448559670781893,
+      "loss": 0.7601,
+      "step": 820
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003444444444444445,
+      "loss": 0.7617,
+      "step": 825
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003440329218106996,
+      "loss": 0.7526,
+      "step": 830
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00034362139917695474,
+      "loss": 0.7297,
+      "step": 835
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003432098765432099,
+      "loss": 0.7549,
+      "step": 840
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.000342798353909465,
+      "loss": 0.7517,
+      "step": 845
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00034238683127572016,
+      "loss": 0.7626,
+      "step": 850
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003419753086419753,
+      "loss": 0.7987,
+      "step": 855
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003415637860082305,
+      "loss": 0.7573,
+      "step": 860
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003411522633744856,
+      "loss": 0.8367,
+      "step": 865
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00034074074074074074,
+      "loss": 0.7258,
+      "step": 870
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003403292181069959,
+      "loss": 0.7632,
+      "step": 875
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00033991769547325106,
+      "loss": 0.7379,
+      "step": 880
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00033950617283950616,
+      "loss": 0.7529,
+      "step": 885
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003390946502057613,
+      "loss": 0.7391,
+      "step": 890
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003386831275720165,
+      "loss": 0.8061,
+      "step": 895
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00033827160493827164,
+      "loss": 0.7288,
+      "step": 900
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003378600823045268,
+      "loss": 0.7493,
+      "step": 905
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00033744855967078195,
+      "loss": 0.7702,
+      "step": 910
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00033703703703703706,
+      "loss": 0.7538,
+      "step": 915
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003366255144032922,
+      "loss": 0.728,
+      "step": 920
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003362139917695474,
+      "loss": 0.7776,
+      "step": 925
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003358024691358025,
+      "loss": 0.7883,
+      "step": 930
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00033539094650205764,
+      "loss": 0.7471,
+      "step": 935
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003349794238683128,
+      "loss": 0.7464,
+      "step": 940
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00033456790123456795,
+      "loss": 0.7885,
+      "step": 945
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00033415637860082306,
+      "loss": 0.7509,
+      "step": 950
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003337448559670782,
+      "loss": 0.7681,
+      "step": 955
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003333333333333334,
+      "loss": 0.8246,
+      "step": 960
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003329218106995885,
+      "loss": 0.7604,
+      "step": 965
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00033251028806584364,
+      "loss": 0.7755,
+      "step": 970
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003320987654320988,
+      "loss": 0.7641,
+      "step": 975
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003316872427983539,
+      "loss": 0.7708,
+      "step": 980
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00033127572016460906,
+      "loss": 0.7936,
+      "step": 985
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003308641975308642,
+      "loss": 0.7641,
+      "step": 990
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003304526748971194,
+      "loss": 0.7479,
+      "step": 995
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003300411522633745,
+      "loss": 0.7547,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00032962962962962964,
+      "loss": 0.762,
+      "step": 1005
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003292181069958848,
+      "loss": 0.7472,
+      "step": 1010
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003288065843621399,
+      "loss": 0.7542,
+      "step": 1015
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00032839506172839506,
+      "loss": 0.7669,
+      "step": 1020
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003279835390946502,
+      "loss": 0.7812,
+      "step": 1025
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003275720164609054,
+      "loss": 0.7273,
+      "step": 1030
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003271604938271605,
+      "loss": 0.7822,
+      "step": 1035
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00032674897119341564,
+      "loss": 0.7337,
+      "step": 1040
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003263374485596708,
+      "loss": 0.7566,
+      "step": 1045
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003259259259259259,
+      "loss": 0.7377,
+      "step": 1050
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00032551440329218106,
+      "loss": 0.7856,
+      "step": 1055
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003251028806584362,
+      "loss": 0.7981,
+      "step": 1060
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003246913580246914,
+      "loss": 0.7505,
+      "step": 1065
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003242798353909465,
+      "loss": 0.7549,
+      "step": 1070
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00032386831275720164,
+      "loss": 0.7306,
+      "step": 1075
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003234567901234568,
+      "loss": 0.7343,
+      "step": 1080
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003230452674897119,
+      "loss": 0.738,
+      "step": 1085
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00032263374485596707,
+      "loss": 0.7655,
+      "step": 1090
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003222222222222222,
+      "loss": 0.7706,
+      "step": 1095
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003218106995884774,
+      "loss": 0.7512,
+      "step": 1100
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00032139917695473254,
+      "loss": 0.7549,
+      "step": 1105
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003209876543209877,
+      "loss": 0.7839,
+      "step": 1110
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003205761316872428,
+      "loss": 0.7511,
+      "step": 1115
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00032016460905349796,
+      "loss": 0.769,
+      "step": 1120
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003197530864197531,
+      "loss": 0.7685,
+      "step": 1125
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003193415637860083,
+      "loss": 0.7489,
+      "step": 1130
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003189300411522634,
+      "loss": 0.808,
+      "step": 1135
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00031851851851851854,
+      "loss": 0.7654,
+      "step": 1140
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003181069958847737,
+      "loss": 0.7845,
+      "step": 1145
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00031769547325102886,
+      "loss": 0.7886,
+      "step": 1150
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00031728395061728396,
+      "loss": 0.7318,
+      "step": 1155
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003168724279835391,
+      "loss": 0.7231,
+      "step": 1160
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003164609053497943,
+      "loss": 0.7471,
+      "step": 1165
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003160493827160494,
+      "loss": 0.7424,
+      "step": 1170
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00031563786008230454,
+      "loss": 0.7249,
+      "step": 1175
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003152263374485597,
+      "loss": 0.7419,
+      "step": 1180
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00031481481481481486,
+      "loss": 0.7567,
+      "step": 1185
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00031440329218106997,
+      "loss": 0.7707,
+      "step": 1190
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003139917695473251,
+      "loss": 0.7473,
+      "step": 1195
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003135802469135803,
+      "loss": 0.7222,
+      "step": 1200
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003131687242798354,
+      "loss": 0.7383,
+      "step": 1205
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00031275720164609055,
+      "loss": 0.7712,
+      "step": 1210
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003123456790123457,
+      "loss": 0.7602,
+      "step": 1215
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003119341563786008,
+      "loss": 0.7741,
+      "step": 1220
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00031152263374485597,
+      "loss": 0.7428,
+      "step": 1225
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003111111111111111,
+      "loss": 0.7605,
+      "step": 1230
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003106995884773663,
+      "loss": 0.7255,
+      "step": 1235
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003102880658436214,
+      "loss": 0.7468,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00030987654320987655,
+      "loss": 0.7961,
+      "step": 1245
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003094650205761317,
+      "loss": 0.7208,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003090534979423868,
+      "loss": 0.7331,
+      "step": 1255
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00030864197530864197,
+      "loss": 0.7371,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00030823045267489713,
+      "loss": 0.7206,
+      "step": 1265
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003078189300411523,
+      "loss": 0.7617,
+      "step": 1270
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003074074074074074,
+      "loss": 0.7652,
+      "step": 1275
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00030699588477366255,
+      "loss": 0.7635,
+      "step": 1280
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003065843621399177,
+      "loss": 0.7445,
+      "step": 1285
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003061728395061728,
+      "loss": 0.7717,
+      "step": 1290
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030576131687242797,
+      "loss": 0.7535,
+      "step": 1295
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030534979423868313,
+      "loss": 0.7677,
+      "step": 1300
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003049382716049383,
+      "loss": 0.8131,
+      "step": 1305
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030452674897119345,
+      "loss": 0.7754,
+      "step": 1310
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030411522633744855,
+      "loss": 0.76,
+      "step": 1315
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003037037037037037,
+      "loss": 0.7558,
+      "step": 1320
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00030329218106995887,
+      "loss": 0.7604,
+      "step": 1325
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.000302880658436214,
+      "loss": 0.7716,
+      "step": 1330
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003024691358024692,
+      "loss": 0.7669,
+      "step": 1335
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003020576131687243,
+      "loss": 0.7469,
+      "step": 1340
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030164609053497945,
+      "loss": 0.7511,
+      "step": 1345
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003012345679012346,
+      "loss": 0.7483,
+      "step": 1350
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030082304526748976,
+      "loss": 0.7509,
+      "step": 1355
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030041152263374487,
+      "loss": 0.7249,
+      "step": 1360
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.7289,
+      "step": 1365
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002995884773662552,
+      "loss": 0.7605,
+      "step": 1370
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002991769547325103,
+      "loss": 0.7185,
+      "step": 1375
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00029876543209876545,
+      "loss": 0.6974,
+      "step": 1380
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002983539094650206,
+      "loss": 0.7234,
+      "step": 1385
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00029794238683127577,
+      "loss": 0.7506,
+      "step": 1390
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029753086419753087,
+      "loss": 0.7524,
+      "step": 1395
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029711934156378603,
+      "loss": 0.7641,
+      "step": 1400
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002967078189300412,
+      "loss": 0.6967,
+      "step": 1405
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002962962962962963,
+      "loss": 0.735,
+      "step": 1410
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029588477366255145,
+      "loss": 0.7685,
+      "step": 1415
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002954732510288066,
+      "loss": 0.758,
+      "step": 1420
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002950617283950617,
+      "loss": 0.763,
+      "step": 1425
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00029465020576131687,
+      "loss": 0.712,
+      "step": 1430
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00029423868312757203,
+      "loss": 0.7236,
+      "step": 1435
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002938271604938272,
+      "loss": 0.7732,
+      "step": 1440
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002934156378600823,
+      "loss": 0.7689,
+      "step": 1445
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00029300411522633745,
+      "loss": 0.7352,
+      "step": 1450
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002925925925925926,
+      "loss": 0.7711,
+      "step": 1455
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002921810699588477,
+      "loss": 0.7549,
+      "step": 1460
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002917695473251029,
+      "loss": 0.7804,
+      "step": 1465
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00029135802469135803,
+      "loss": 0.7478,
+      "step": 1470
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002909465020576132,
+      "loss": 0.7801,
+      "step": 1475
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002905349794238683,
+      "loss": 0.7544,
+      "step": 1480
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00029012345679012345,
+      "loss": 0.7546,
+      "step": 1485
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002897119341563786,
+      "loss": 0.7648,
+      "step": 1490
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002893004115226337,
+      "loss": 0.7468,
+      "step": 1495
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002888888888888889,
+      "loss": 0.7434,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00028847736625514403,
+      "loss": 0.7348,
+      "step": 1505
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002880658436213992,
+      "loss": 0.7515,
+      "step": 1510
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00028765432098765435,
+      "loss": 0.7345,
+      "step": 1515
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00028724279835390946,
+      "loss": 0.7701,
+      "step": 1520
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002868312757201646,
+      "loss": 0.7472,
+      "step": 1525
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00028641975308641977,
+      "loss": 0.7075,
+      "step": 1530
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00028600823045267493,
+      "loss": 0.7483,
+      "step": 1535
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002855967078189301,
+      "loss": 0.712,
+      "step": 1540
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002851851851851852,
+      "loss": 0.7484,
+      "step": 1545
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00028477366255144035,
+      "loss": 0.7471,
+      "step": 1550
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002843621399176955,
+      "loss": 0.7462,
+      "step": 1555
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00028395061728395067,
+      "loss": 0.7371,
+      "step": 1560
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002835390946502058,
+      "loss": 0.7753,
+      "step": 1565
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00028312757201646093,
+      "loss": 0.7374,
+      "step": 1570
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002827160493827161,
+      "loss": 0.7328,
+      "step": 1575
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002823045267489712,
+      "loss": 0.7159,
+      "step": 1580
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00028189300411522635,
+      "loss": 0.7594,
+      "step": 1585
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002814814814814815,
+      "loss": 0.7215,
+      "step": 1590
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00028106995884773667,
+      "loss": 0.7398,
+      "step": 1595
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002806584362139918,
+      "loss": 0.773,
+      "step": 1600
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00028024691358024693,
+      "loss": 0.7584,
+      "step": 1605
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002798353909465021,
+      "loss": 0.7117,
+      "step": 1610
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002794238683127572,
+      "loss": 0.7471,
+      "step": 1615
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00027901234567901236,
+      "loss": 0.7443,
+      "step": 1620
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002786008230452675,
+      "loss": 0.7292,
+      "step": 1625
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002781893004115227,
+      "loss": 0.7716,
+      "step": 1630
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 0.763,
+      "step": 1635
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00027736625514403294,
+      "loss": 0.7408,
+      "step": 1640
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002769547325102881,
+      "loss": 0.7403,
+      "step": 1645
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002765432098765432,
+      "loss": 0.7508,
+      "step": 1650
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00027613168724279836,
+      "loss": 0.7687,
+      "step": 1655
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002757201646090535,
+      "loss": 0.7305,
+      "step": 1660
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002753086419753086,
+      "loss": 0.7165,
+      "step": 1665
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002748971193415638,
+      "loss": 0.8,
+      "step": 1670
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00027448559670781894,
+      "loss": 0.7357,
+      "step": 1675
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002740740740740741,
+      "loss": 0.7988,
+      "step": 1680
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002736625514403292,
+      "loss": 0.7559,
+      "step": 1685
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00027325102880658436,
+      "loss": 0.712,
+      "step": 1690
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002728395061728395,
+      "loss": 0.7486,
+      "step": 1695
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002724279835390946,
+      "loss": 0.7388,
+      "step": 1700
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002720164609053498,
+      "loss": 0.7441,
+      "step": 1705
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00027160493827160494,
+      "loss": 0.7547,
+      "step": 1710
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002711934156378601,
+      "loss": 0.7229,
+      "step": 1715
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002707818930041152,
+      "loss": 0.7383,
+      "step": 1720
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00027037037037037036,
+      "loss": 0.7606,
+      "step": 1725
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002699588477366255,
+      "loss": 0.7529,
+      "step": 1730
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002695473251028807,
+      "loss": 0.752,
+      "step": 1735
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00026913580246913584,
+      "loss": 0.7342,
+      "step": 1740
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.000268724279835391,
+      "loss": 0.7308,
+      "step": 1745
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002683127572016461,
+      "loss": 0.6915,
+      "step": 1750
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00026790123456790126,
+      "loss": 0.7344,
+      "step": 1755
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002674897119341564,
+      "loss": 0.7426,
+      "step": 1760
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002670781893004116,
+      "loss": 0.7088,
+      "step": 1765
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002666666666666667,
+      "loss": 0.7241,
+      "step": 1770
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00026625514403292184,
+      "loss": 0.7552,
+      "step": 1775
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.000265843621399177,
+      "loss": 0.7477,
+      "step": 1780
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002654320987654321,
+      "loss": 0.7115,
+      "step": 1785
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00026502057613168726,
+      "loss": 0.7538,
+      "step": 1790
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002646090534979424,
+      "loss": 0.7321,
+      "step": 1795
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002641975308641976,
+      "loss": 0.7212,
+      "step": 1800
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002637860082304527,
+      "loss": 0.747,
+      "step": 1805
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00026337448559670784,
+      "loss": 0.7606,
+      "step": 1810
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.000262962962962963,
+      "loss": 0.7344,
+      "step": 1815
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002625514403292181,
+      "loss": 0.7783,
+      "step": 1820
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00026213991769547326,
+      "loss": 0.7556,
+      "step": 1825
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002617283950617284,
+      "loss": 0.7585,
+      "step": 1830
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002613168724279836,
+      "loss": 0.7359,
+      "step": 1835
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002609053497942387,
+      "loss": 0.7185,
+      "step": 1840
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00026049382716049384,
+      "loss": 0.7573,
+      "step": 1845
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.000260082304526749,
+      "loss": 0.7619,
+      "step": 1850
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002596707818930041,
+      "loss": 0.7611,
+      "step": 1855
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00025925925925925926,
+      "loss": 0.7647,
+      "step": 1860
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002588477366255144,
+      "loss": 0.7398,
+      "step": 1865
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002584362139917695,
+      "loss": 0.7683,
+      "step": 1870
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002580246913580247,
+      "loss": 0.7817,
+      "step": 1875
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00025761316872427984,
+      "loss": 0.742,
+      "step": 1880
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.000257201646090535,
+      "loss": 0.7509,
+      "step": 1885
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002567901234567901,
+      "loss": 0.7058,
+      "step": 1890
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00025637860082304526,
+      "loss": 0.7635,
+      "step": 1895
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002559670781893004,
+      "loss": 0.734,
+      "step": 1900
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00025555555555555553,
+      "loss": 0.7416,
+      "step": 1905
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002551440329218107,
+      "loss": 0.7071,
+      "step": 1910
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00025473251028806584,
+      "loss": 0.7275,
+      "step": 1915
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.000254320987654321,
+      "loss": 0.7413,
+      "step": 1920
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002539094650205761,
+      "loss": 0.7703,
+      "step": 1925
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00025349794238683127,
+      "loss": 0.7331,
+      "step": 1930
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002530864197530864,
+      "loss": 0.7251,
+      "step": 1935
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002526748971193416,
+      "loss": 0.7341,
+      "step": 1940
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00025226337448559674,
+      "loss": 0.7079,
+      "step": 1945
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00025185185185185185,
+      "loss": 0.7615,
+      "step": 1950
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.000251440329218107,
+      "loss": 0.7144,
+      "step": 1955
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00025102880658436216,
+      "loss": 0.7527,
+      "step": 1960
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0002506172839506173,
+      "loss": 0.7327,
+      "step": 1965
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002502057613168725,
+      "loss": 0.7173,
+      "step": 1970
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002497942386831276,
+      "loss": 0.7239,
+      "step": 1975
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00024938271604938274,
+      "loss": 0.7442,
+      "step": 1980
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002489711934156379,
+      "loss": 0.7396,
+      "step": 1985
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.000248559670781893,
+      "loss": 0.7365,
+      "step": 1990
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00024814814814814816,
+      "loss": 0.7037,
+      "step": 1995
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002477366255144033,
+      "loss": 0.721,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002473251028806585,
+      "loss": 0.7353,
+      "step": 2005
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002469135802469136,
+      "loss": 0.7648,
+      "step": 2010
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00024650205761316874,
+      "loss": 0.7445,
+      "step": 2015
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0002460905349794239,
+      "loss": 0.7664,
+      "step": 2020
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.000245679012345679,
+      "loss": 0.7202,
+      "step": 2025
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00024526748971193417,
+      "loss": 0.7147,
+      "step": 2030
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0002448559670781893,
+      "loss": 0.722,
+      "step": 2035
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0002444444444444445,
+      "loss": 0.7539,
+      "step": 2040
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002440329218106996,
+      "loss": 0.7681,
+      "step": 2045
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00024362139917695475,
+      "loss": 0.7304,
+      "step": 2050
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002432098765432099,
+      "loss": 0.7432,
+      "step": 2055
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.000242798353909465,
+      "loss": 0.6945,
+      "step": 2060
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00024238683127572017,
+      "loss": 0.7426,
+      "step": 2065
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00024197530864197533,
+      "loss": 0.7144,
+      "step": 2070
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00024156378600823048,
+      "loss": 0.7761,
+      "step": 2075
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0002411522633744856,
+      "loss": 0.7402,
+      "step": 2080
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00024074074074074075,
+      "loss": 0.7376,
+      "step": 2085
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0002403292181069959,
+      "loss": 0.7231,
+      "step": 2090
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023991769547325104,
+      "loss": 0.7461,
+      "step": 2095
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023950617283950617,
+      "loss": 0.7215,
+      "step": 2100
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023909465020576133,
+      "loss": 0.7419,
+      "step": 2105
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023868312757201646,
+      "loss": 0.7502,
+      "step": 2110
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023827160493827162,
+      "loss": 0.7294,
+      "step": 2115
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00023786008230452678,
+      "loss": 0.7904,
+      "step": 2120
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00023744855967078194,
+      "loss": 0.7418,
+      "step": 2125
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00023703703703703704,
+      "loss": 0.7371,
+      "step": 2130
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0002366255144032922,
+      "loss": 0.7384,
+      "step": 2135
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00023621399176954736,
+      "loss": 0.7552,
+      "step": 2140
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023580246913580246,
+      "loss": 0.7516,
+      "step": 2145
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023539094650205762,
+      "loss": 0.7303,
+      "step": 2150
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023497942386831278,
+      "loss": 0.7496,
+      "step": 2155
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023456790123456794,
+      "loss": 0.7135,
+      "step": 2160
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023415637860082304,
+      "loss": 0.7283,
+      "step": 2165
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0002337448559670782,
+      "loss": 0.751,
+      "step": 2170
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00023333333333333336,
+      "loss": 0.7183,
+      "step": 2175
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00023292181069958846,
+      "loss": 0.7242,
+      "step": 2180
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00023251028806584362,
+      "loss": 0.725,
+      "step": 2185
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00023209876543209878,
+      "loss": 0.753,
+      "step": 2190
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002316872427983539,
+      "loss": 0.7664,
+      "step": 2195
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00023127572016460904,
+      "loss": 0.7444,
+      "step": 2200
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002308641975308642,
+      "loss": 0.7226,
+      "step": 2205
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00023045267489711936,
+      "loss": 0.7653,
+      "step": 2210
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002300411522633745,
+      "loss": 0.7382,
+      "step": 2215
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00022962962962962965,
+      "loss": 0.7242,
+      "step": 2220
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002292181069958848,
+      "loss": 0.7215,
+      "step": 2225
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002288065843621399,
+      "loss": 0.724,
+      "step": 2230
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00022839506172839507,
+      "loss": 0.7439,
+      "step": 2235
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00022798353909465023,
+      "loss": 0.699,
+      "step": 2240
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002275720164609054,
+      "loss": 0.7602,
+      "step": 2245
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002271604938271605,
+      "loss": 0.7103,
+      "step": 2250
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00022674897119341565,
+      "loss": 0.7015,
+      "step": 2255
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002263374485596708,
+      "loss": 0.7404,
+      "step": 2260
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00022592592592592591,
+      "loss": 0.7127,
+      "step": 2265
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00022551440329218107,
+      "loss": 0.7299,
+      "step": 2270
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00022510288065843623,
+      "loss": 0.7174,
+      "step": 2275
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002246913580246914,
+      "loss": 0.7454,
+      "step": 2280
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002242798353909465,
+      "loss": 0.7159,
+      "step": 2285
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00022386831275720165,
+      "loss": 0.7263,
+      "step": 2290
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0002234567901234568,
+      "loss": 0.7148,
+      "step": 2295
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00022304526748971192,
+      "loss": 0.7447,
+      "step": 2300
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00022263374485596707,
+      "loss": 0.7326,
+      "step": 2305
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00022222222222222223,
+      "loss": 0.7428,
+      "step": 2310
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00022181069958847736,
+      "loss": 0.7587,
+      "step": 2315
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00022139917695473252,
+      "loss": 0.759,
+      "step": 2320
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00022098765432098768,
+      "loss": 0.7716,
+      "step": 2325
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002205761316872428,
+      "loss": 0.74,
+      "step": 2330
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00022016460905349794,
+      "loss": 0.7255,
+      "step": 2335
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002197530864197531,
+      "loss": 0.7547,
+      "step": 2340
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021934156378600826,
+      "loss": 0.7359,
+      "step": 2345
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021893004115226337,
+      "loss": 0.6987,
+      "step": 2350
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021851851851851852,
+      "loss": 0.7233,
+      "step": 2355
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021810699588477368,
+      "loss": 0.6945,
+      "step": 2360
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021769547325102884,
+      "loss": 0.7566,
+      "step": 2365
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00021728395061728395,
+      "loss": 0.728,
+      "step": 2370
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002168724279835391,
+      "loss": 0.7167,
+      "step": 2375
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00021646090534979426,
+      "loss": 0.7576,
+      "step": 2380
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00021604938271604937,
+      "loss": 0.7246,
+      "step": 2385
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00021563786008230453,
+      "loss": 0.755,
+      "step": 2390
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00021522633744855968,
+      "loss": 0.6983,
+      "step": 2395
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00021481481481481484,
+      "loss": 0.7369,
+      "step": 2400
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00021440329218106995,
+      "loss": 0.7074,
+      "step": 2405
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0002139917695473251,
+      "loss": 0.7317,
+      "step": 2410
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00021358024691358026,
+      "loss": 0.7086,
+      "step": 2415
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0002131687242798354,
+      "loss": 0.7356,
+      "step": 2420
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00021275720164609055,
+      "loss": 0.7652,
+      "step": 2425
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00021234567901234569,
+      "loss": 0.7488,
+      "step": 2430
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00021193415637860082,
+      "loss": 0.746,
+      "step": 2435
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00021152263374485598,
+      "loss": 0.7454,
+      "step": 2440
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00021111111111111113,
+      "loss": 0.72,
+      "step": 2445
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0002106995884773663,
+      "loss": 0.7299,
+      "step": 2450
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0002102880658436214,
+      "loss": 0.7436,
+      "step": 2455
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00020987654320987656,
+      "loss": 0.7068,
+      "step": 2460
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00020946502057613171,
+      "loss": 0.711,
+      "step": 2465
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00020905349794238682,
+      "loss": 0.7473,
+      "step": 2470
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00020864197530864198,
+      "loss": 0.7016,
+      "step": 2475
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00020823045267489714,
+      "loss": 0.7049,
+      "step": 2480
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002078189300411523,
+      "loss": 0.7268,
+      "step": 2485
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002074074074074074,
+      "loss": 0.7239,
+      "step": 2490
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020699588477366256,
+      "loss": 0.698,
+      "step": 2495
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020658436213991772,
+      "loss": 0.7573,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 5010,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 1.006726589213311e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/training_args.bin b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..28c7b09fc2b3929abe4ad6608c7959f30a9a9d66
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43458f4cf6aeb211c730b848f93ab15f483827c314fb4dc1e79dd1f658b7dbc8
+size 5944
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/zero_to_fp32.py b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/zero_to_fp32.py
new file mode 100644
index 0000000000000000000000000000000000000000..c98caae31534368be22b67fc4ae906836c992a8d
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-2500/zero_to_fp32.py
@@ -0,0 +1,587 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel()
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file, tag=args.tag)
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/README.md b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..2aa897f8fa13b49ce76b1fa188781e5f726e7d13
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-2-7b-hf
+library_name: peft
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/adapter_config.json b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9c81a592f0ff08374a4f61f6003029070a8429ae
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/adapter_config.json
@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "mora_type": 1,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_mora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/adapter_model.safetensors b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..775923bf0bd1c9577c6a08f80aa14f7526834f85
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:594b67f8ef6310c9ff1be2eeb1ef6e747610cd7066b4afb6e1565107960ae791
+size 564342240
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..55f87d7d12dc94ca31f0c283745b4eaf01ec74b5
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9040a90f5d8818966640769ae8b1972e8162567456b23ae9d6b84ef4032e980b
+size 239914224
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/global_step3000/mp_rank_00_model_states.pt b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/global_step3000/mp_rank_00_model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9537a96faa8b9d2be2d4f29def191b3480009c8d
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/global_step3000/mp_rank_00_model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fea4b1fe3e6d7ecadb081b903d9a5b6f21d8dd89b942f105211beee91c283886
+size 40303404
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/latest b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/latest
new file mode 100644
index 0000000000000000000000000000000000000000..1d7ba373feda3875a77d01589035020625a7c98e
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/latest
@@ -0,0 +1 @@
+global_step3000
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/rng_state.pth b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f1f38b432152408d45b0c895c52796e871121939
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:602ff114cd2710380875f9cf15b09f6fc6a211d90bdfc8416e511f12377a1bd9
+size 14244
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/scheduler.pt b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e0eea47dbae72c2fb0001a43c6485e5fd4dea837
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:083abc970a85acd0fe0036aee21d5b5cee2ceb437d75185f43bb0e09b5a91147
+size 1064
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/trainer_state.json b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..6e5b8b8d49a2d55febe572e2701178bdd9a18e3c
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/trainer_state.json
@@ -0,0 +1,3621 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.197492749555618,
+  "eval_steps": 500,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.3798,
+      "step": 5
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 1.3917,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4e-05,
+      "loss": 1.2862,
+      "step": 15
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 1.2046,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.0634,
+      "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8e-05,
+      "loss": 1.0273,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 1.0472,
+      "step": 35
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 1.0301,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00012,
+      "loss": 0.9335,
+      "step": 45
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.921,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00014666666666666666,
+      "loss": 0.9506,
+      "step": 55
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016,
+      "loss": 0.8876,
+      "step": 60
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00017333333333333334,
+      "loss": 0.9335,
+      "step": 65
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 0.8554,
+      "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0002,
+      "loss": 0.8537,
+      "step": 75
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00021333333333333333,
+      "loss": 0.9033,
+      "step": 80
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00022666666666666668,
+      "loss": 0.8203,
+      "step": 85
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00024,
+      "loss": 0.8611,
+      "step": 90
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00025333333333333333,
+      "loss": 0.8303,
+      "step": 95
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002666666666666667,
+      "loss": 0.8528,
+      "step": 100
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00028,
+      "loss": 0.8537,
+      "step": 105
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002933333333333333,
+      "loss": 0.8286,
+      "step": 110
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003066666666666667,
+      "loss": 0.8449,
+      "step": 115
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00032,
+      "loss": 0.8377,
+      "step": 120
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003333333333333334,
+      "loss": 0.8419,
+      "step": 125
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00034666666666666667,
+      "loss": 0.8265,
+      "step": 130
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00036,
+      "loss": 0.8037,
+      "step": 135
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003733333333333334,
+      "loss": 0.7924,
+      "step": 140
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00038666666666666667,
+      "loss": 0.8245,
+      "step": 145
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0004,
+      "loss": 0.8388,
+      "step": 150
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003995884773662552,
+      "loss": 0.8066,
+      "step": 155
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003991769547325103,
+      "loss": 0.8107,
+      "step": 160
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039876543209876544,
+      "loss": 0.8005,
+      "step": 165
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003983539094650206,
+      "loss": 0.7727,
+      "step": 170
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039794238683127576,
+      "loss": 0.8276,
+      "step": 175
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039753086419753086,
+      "loss": 0.8464,
+      "step": 180
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000397119341563786,
+      "loss": 0.8348,
+      "step": 185
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003967078189300412,
+      "loss": 0.8228,
+      "step": 190
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003962962962962963,
+      "loss": 0.8254,
+      "step": 195
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00039588477366255144,
+      "loss": 0.817,
+      "step": 200
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003954732510288066,
+      "loss": 0.8365,
+      "step": 205
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003950617283950617,
+      "loss": 0.793,
+      "step": 210
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00039465020576131686,
+      "loss": 0.8014,
+      "step": 215
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000394238683127572,
+      "loss": 0.8049,
+      "step": 220
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003938271604938272,
+      "loss": 0.7841,
+      "step": 225
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003934156378600823,
+      "loss": 0.7977,
+      "step": 230
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00039300411522633744,
+      "loss": 0.8299,
+      "step": 235
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003925925925925926,
+      "loss": 0.7729,
+      "step": 240
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00039218106995884776,
+      "loss": 0.8082,
+      "step": 245
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003917695473251029,
+      "loss": 0.8173,
+      "step": 250
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000391358024691358,
+      "loss": 0.8379,
+      "step": 255
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003909465020576132,
+      "loss": 0.7962,
+      "step": 260
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00039053497942386834,
+      "loss": 0.8067,
+      "step": 265
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003901234567901235,
+      "loss": 0.7915,
+      "step": 270
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00038971193415637866,
+      "loss": 0.7905,
+      "step": 275
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00038930041152263376,
+      "loss": 0.7862,
+      "step": 280
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003888888888888889,
+      "loss": 0.7709,
+      "step": 285
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003884773662551441,
+      "loss": 0.7773,
+      "step": 290
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00038806584362139924,
+      "loss": 0.8068,
+      "step": 295
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00038765432098765434,
+      "loss": 0.7962,
+      "step": 300
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003872427983539095,
+      "loss": 0.7894,
+      "step": 305
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00038683127572016466,
+      "loss": 0.7705,
+      "step": 310
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00038641975308641976,
+      "loss": 0.7882,
+      "step": 315
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003860082304526749,
+      "loss": 0.7865,
+      "step": 320
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003855967078189301,
+      "loss": 0.7939,
+      "step": 325
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003851851851851852,
+      "loss": 0.7724,
+      "step": 330
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00038477366255144034,
+      "loss": 0.7771,
+      "step": 335
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003843621399176955,
+      "loss": 0.7941,
+      "step": 340
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00038395061728395066,
+      "loss": 0.7822,
+      "step": 345
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00038353909465020577,
+      "loss": 0.8143,
+      "step": 350
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003831275720164609,
+      "loss": 0.795,
+      "step": 355
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003827160493827161,
+      "loss": 0.8049,
+      "step": 360
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003823045267489712,
+      "loss": 0.8309,
+      "step": 365
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00038189300411522635,
+      "loss": 0.8314,
+      "step": 370
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003814814814814815,
+      "loss": 0.801,
+      "step": 375
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00038106995884773666,
+      "loss": 0.8084,
+      "step": 380
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00038065843621399177,
+      "loss": 0.8129,
+      "step": 385
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003802469135802469,
+      "loss": 0.7859,
+      "step": 390
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003798353909465021,
+      "loss": 0.7874,
+      "step": 395
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003794238683127572,
+      "loss": 0.7548,
+      "step": 400
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00037901234567901235,
+      "loss": 0.8092,
+      "step": 405
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003786008230452675,
+      "loss": 0.8041,
+      "step": 410
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00037818930041152266,
+      "loss": 0.777,
+      "step": 415
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00037777777777777777,
+      "loss": 0.7699,
+      "step": 420
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00037736625514403293,
+      "loss": 0.781,
+      "step": 425
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003769547325102881,
+      "loss": 0.7504,
+      "step": 430
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003765432098765432,
+      "loss": 0.7974,
+      "step": 435
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037613168724279835,
+      "loss": 0.7663,
+      "step": 440
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003757201646090535,
+      "loss": 0.8013,
+      "step": 445
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037530864197530867,
+      "loss": 0.7453,
+      "step": 450
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037489711934156377,
+      "loss": 0.7425,
+      "step": 455
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037448559670781893,
+      "loss": 0.7582,
+      "step": 460
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003740740740740741,
+      "loss": 0.7801,
+      "step": 465
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00037366255144032925,
+      "loss": 0.7809,
+      "step": 470
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003732510288065844,
+      "loss": 0.7749,
+      "step": 475
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00037283950617283956,
+      "loss": 0.7807,
+      "step": 480
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00037242798353909467,
+      "loss": 0.7715,
+      "step": 485
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003720164609053498,
+      "loss": 0.7356,
+      "step": 490
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000371604938271605,
+      "loss": 0.7674,
+      "step": 495
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00037119341563786014,
+      "loss": 0.7542,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00037078189300411525,
+      "loss": 0.7583,
+      "step": 505
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003703703703703704,
+      "loss": 0.7767,
+      "step": 510
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036995884773662556,
+      "loss": 0.7853,
+      "step": 515
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036954732510288067,
+      "loss": 0.7733,
+      "step": 520
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036913580246913583,
+      "loss": 0.7758,
+      "step": 525
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.000368724279835391,
+      "loss": 0.7698,
+      "step": 530
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036831275720164614,
+      "loss": 0.7805,
+      "step": 535
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036790123456790125,
+      "loss": 0.7573,
+      "step": 540
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003674897119341564,
+      "loss": 0.7709,
+      "step": 545
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036707818930041157,
+      "loss": 0.7994,
+      "step": 550
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036666666666666667,
+      "loss": 0.7363,
+      "step": 555
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036625514403292183,
+      "loss": 0.7478,
+      "step": 560
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000365843621399177,
+      "loss": 0.8188,
+      "step": 565
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003654320987654321,
+      "loss": 0.7524,
+      "step": 570
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00036502057613168725,
+      "loss": 0.7319,
+      "step": 575
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003646090534979424,
+      "loss": 0.7915,
+      "step": 580
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00036419753086419757,
+      "loss": 0.7722,
+      "step": 585
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00036378600823045267,
+      "loss": 0.7842,
+      "step": 590
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00036337448559670783,
+      "loss": 0.7591,
+      "step": 595
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000362962962962963,
+      "loss": 0.7653,
+      "step": 600
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003625514403292181,
+      "loss": 0.7838,
+      "step": 605
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00036213991769547325,
+      "loss": 0.7937,
+      "step": 610
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003617283950617284,
+      "loss": 0.77,
+      "step": 615
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00036131687242798357,
+      "loss": 0.7899,
+      "step": 620
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003609053497942387,
+      "loss": 0.7815,
+      "step": 625
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00036049382716049383,
+      "loss": 0.7648,
+      "step": 630
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.000360082304526749,
+      "loss": 0.7716,
+      "step": 635
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003596707818930041,
+      "loss": 0.7708,
+      "step": 640
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00035925925925925925,
+      "loss": 0.7306,
+      "step": 645
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003588477366255144,
+      "loss": 0.8007,
+      "step": 650
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003584362139917695,
+      "loss": 0.7551,
+      "step": 655
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003580246913580247,
+      "loss": 0.754,
+      "step": 660
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00035761316872427983,
+      "loss": 0.7599,
+      "step": 665
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.000357201646090535,
+      "loss": 0.7637,
+      "step": 670
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00035679012345679015,
+      "loss": 0.7766,
+      "step": 675
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003563786008230453,
+      "loss": 0.7727,
+      "step": 680
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003559670781893004,
+      "loss": 0.7675,
+      "step": 685
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035555555555555557,
+      "loss": 0.7707,
+      "step": 690
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035514403292181073,
+      "loss": 0.7221,
+      "step": 695
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003547325102880659,
+      "loss": 0.7335,
+      "step": 700
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035432098765432105,
+      "loss": 0.781,
+      "step": 705
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035390946502057615,
+      "loss": 0.7845,
+      "step": 710
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003534979423868313,
+      "loss": 0.7467,
+      "step": 715
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00035308641975308647,
+      "loss": 0.7735,
+      "step": 720
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003526748971193416,
+      "loss": 0.7368,
+      "step": 725
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00035226337448559673,
+      "loss": 0.7678,
+      "step": 730
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003518518518518519,
+      "loss": 0.7756,
+      "step": 735
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00035144032921810705,
+      "loss": 0.7635,
+      "step": 740
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00035102880658436215,
+      "loss": 0.7757,
+      "step": 745
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003506172839506173,
+      "loss": 0.7442,
+      "step": 750
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00035020576131687247,
+      "loss": 0.7584,
+      "step": 755
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003497942386831276,
+      "loss": 0.8333,
+      "step": 760
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00034938271604938273,
+      "loss": 0.7459,
+      "step": 765
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003489711934156379,
+      "loss": 0.7499,
+      "step": 770
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.000348559670781893,
+      "loss": 0.7571,
+      "step": 775
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00034814814814814816,
+      "loss": 0.7243,
+      "step": 780
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003477366255144033,
+      "loss": 0.7443,
+      "step": 785
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003473251028806585,
+      "loss": 0.7759,
+      "step": 790
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003469135802469136,
+      "loss": 0.7452,
+      "step": 795
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00034650205761316874,
+      "loss": 0.7578,
+      "step": 800
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003460905349794239,
+      "loss": 0.7634,
+      "step": 805
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.000345679012345679,
+      "loss": 0.7925,
+      "step": 810
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00034526748971193416,
+      "loss": 0.7966,
+      "step": 815
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003448559670781893,
+      "loss": 0.7601,
+      "step": 820
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003444444444444445,
+      "loss": 0.7617,
+      "step": 825
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003440329218106996,
+      "loss": 0.7526,
+      "step": 830
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00034362139917695474,
+      "loss": 0.7297,
+      "step": 835
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003432098765432099,
+      "loss": 0.7549,
+      "step": 840
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.000342798353909465,
+      "loss": 0.7517,
+      "step": 845
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00034238683127572016,
+      "loss": 0.7626,
+      "step": 850
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003419753086419753,
+      "loss": 0.7987,
+      "step": 855
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003415637860082305,
+      "loss": 0.7573,
+      "step": 860
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003411522633744856,
+      "loss": 0.8367,
+      "step": 865
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00034074074074074074,
+      "loss": 0.7258,
+      "step": 870
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003403292181069959,
+      "loss": 0.7632,
+      "step": 875
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00033991769547325106,
+      "loss": 0.7379,
+      "step": 880
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00033950617283950616,
+      "loss": 0.7529,
+      "step": 885
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003390946502057613,
+      "loss": 0.7391,
+      "step": 890
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003386831275720165,
+      "loss": 0.8061,
+      "step": 895
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00033827160493827164,
+      "loss": 0.7288,
+      "step": 900
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003378600823045268,
+      "loss": 0.7493,
+      "step": 905
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00033744855967078195,
+      "loss": 0.7702,
+      "step": 910
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00033703703703703706,
+      "loss": 0.7538,
+      "step": 915
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003366255144032922,
+      "loss": 0.728,
+      "step": 920
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003362139917695474,
+      "loss": 0.7776,
+      "step": 925
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003358024691358025,
+      "loss": 0.7883,
+      "step": 930
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00033539094650205764,
+      "loss": 0.7471,
+      "step": 935
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003349794238683128,
+      "loss": 0.7464,
+      "step": 940
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00033456790123456795,
+      "loss": 0.7885,
+      "step": 945
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00033415637860082306,
+      "loss": 0.7509,
+      "step": 950
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003337448559670782,
+      "loss": 0.7681,
+      "step": 955
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003333333333333334,
+      "loss": 0.8246,
+      "step": 960
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003329218106995885,
+      "loss": 0.7604,
+      "step": 965
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00033251028806584364,
+      "loss": 0.7755,
+      "step": 970
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003320987654320988,
+      "loss": 0.7641,
+      "step": 975
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003316872427983539,
+      "loss": 0.7708,
+      "step": 980
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00033127572016460906,
+      "loss": 0.7936,
+      "step": 985
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003308641975308642,
+      "loss": 0.7641,
+      "step": 990
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003304526748971194,
+      "loss": 0.7479,
+      "step": 995
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003300411522633745,
+      "loss": 0.7547,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00032962962962962964,
+      "loss": 0.762,
+      "step": 1005
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003292181069958848,
+      "loss": 0.7472,
+      "step": 1010
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003288065843621399,
+      "loss": 0.7542,
+      "step": 1015
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00032839506172839506,
+      "loss": 0.7669,
+      "step": 1020
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003279835390946502,
+      "loss": 0.7812,
+      "step": 1025
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003275720164609054,
+      "loss": 0.7273,
+      "step": 1030
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003271604938271605,
+      "loss": 0.7822,
+      "step": 1035
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00032674897119341564,
+      "loss": 0.7337,
+      "step": 1040
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003263374485596708,
+      "loss": 0.7566,
+      "step": 1045
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003259259259259259,
+      "loss": 0.7377,
+      "step": 1050
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00032551440329218106,
+      "loss": 0.7856,
+      "step": 1055
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003251028806584362,
+      "loss": 0.7981,
+      "step": 1060
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003246913580246914,
+      "loss": 0.7505,
+      "step": 1065
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003242798353909465,
+      "loss": 0.7549,
+      "step": 1070
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00032386831275720164,
+      "loss": 0.7306,
+      "step": 1075
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003234567901234568,
+      "loss": 0.7343,
+      "step": 1080
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003230452674897119,
+      "loss": 0.738,
+      "step": 1085
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00032263374485596707,
+      "loss": 0.7655,
+      "step": 1090
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003222222222222222,
+      "loss": 0.7706,
+      "step": 1095
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003218106995884774,
+      "loss": 0.7512,
+      "step": 1100
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00032139917695473254,
+      "loss": 0.7549,
+      "step": 1105
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003209876543209877,
+      "loss": 0.7839,
+      "step": 1110
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003205761316872428,
+      "loss": 0.7511,
+      "step": 1115
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00032016460905349796,
+      "loss": 0.769,
+      "step": 1120
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003197530864197531,
+      "loss": 0.7685,
+      "step": 1125
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003193415637860083,
+      "loss": 0.7489,
+      "step": 1130
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003189300411522634,
+      "loss": 0.808,
+      "step": 1135
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00031851851851851854,
+      "loss": 0.7654,
+      "step": 1140
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003181069958847737,
+      "loss": 0.7845,
+      "step": 1145
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00031769547325102886,
+      "loss": 0.7886,
+      "step": 1150
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00031728395061728396,
+      "loss": 0.7318,
+      "step": 1155
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003168724279835391,
+      "loss": 0.7231,
+      "step": 1160
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003164609053497943,
+      "loss": 0.7471,
+      "step": 1165
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003160493827160494,
+      "loss": 0.7424,
+      "step": 1170
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00031563786008230454,
+      "loss": 0.7249,
+      "step": 1175
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003152263374485597,
+      "loss": 0.7419,
+      "step": 1180
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00031481481481481486,
+      "loss": 0.7567,
+      "step": 1185
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00031440329218106997,
+      "loss": 0.7707,
+      "step": 1190
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003139917695473251,
+      "loss": 0.7473,
+      "step": 1195
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003135802469135803,
+      "loss": 0.7222,
+      "step": 1200
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003131687242798354,
+      "loss": 0.7383,
+      "step": 1205
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00031275720164609055,
+      "loss": 0.7712,
+      "step": 1210
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003123456790123457,
+      "loss": 0.7602,
+      "step": 1215
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003119341563786008,
+      "loss": 0.7741,
+      "step": 1220
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00031152263374485597,
+      "loss": 0.7428,
+      "step": 1225
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003111111111111111,
+      "loss": 0.7605,
+      "step": 1230
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003106995884773663,
+      "loss": 0.7255,
+      "step": 1235
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003102880658436214,
+      "loss": 0.7468,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00030987654320987655,
+      "loss": 0.7961,
+      "step": 1245
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003094650205761317,
+      "loss": 0.7208,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003090534979423868,
+      "loss": 0.7331,
+      "step": 1255
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00030864197530864197,
+      "loss": 0.7371,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00030823045267489713,
+      "loss": 0.7206,
+      "step": 1265
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003078189300411523,
+      "loss": 0.7617,
+      "step": 1270
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003074074074074074,
+      "loss": 0.7652,
+      "step": 1275
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00030699588477366255,
+      "loss": 0.7635,
+      "step": 1280
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003065843621399177,
+      "loss": 0.7445,
+      "step": 1285
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003061728395061728,
+      "loss": 0.7717,
+      "step": 1290
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030576131687242797,
+      "loss": 0.7535,
+      "step": 1295
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030534979423868313,
+      "loss": 0.7677,
+      "step": 1300
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003049382716049383,
+      "loss": 0.8131,
+      "step": 1305
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030452674897119345,
+      "loss": 0.7754,
+      "step": 1310
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030411522633744855,
+      "loss": 0.76,
+      "step": 1315
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003037037037037037,
+      "loss": 0.7558,
+      "step": 1320
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00030329218106995887,
+      "loss": 0.7604,
+      "step": 1325
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.000302880658436214,
+      "loss": 0.7716,
+      "step": 1330
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003024691358024692,
+      "loss": 0.7669,
+      "step": 1335
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003020576131687243,
+      "loss": 0.7469,
+      "step": 1340
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030164609053497945,
+      "loss": 0.7511,
+      "step": 1345
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003012345679012346,
+      "loss": 0.7483,
+      "step": 1350
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030082304526748976,
+      "loss": 0.7509,
+      "step": 1355
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030041152263374487,
+      "loss": 0.7249,
+      "step": 1360
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.7289,
+      "step": 1365
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002995884773662552,
+      "loss": 0.7605,
+      "step": 1370
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002991769547325103,
+      "loss": 0.7185,
+      "step": 1375
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00029876543209876545,
+      "loss": 0.6974,
+      "step": 1380
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002983539094650206,
+      "loss": 0.7234,
+      "step": 1385
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00029794238683127577,
+      "loss": 0.7506,
+      "step": 1390
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029753086419753087,
+      "loss": 0.7524,
+      "step": 1395
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029711934156378603,
+      "loss": 0.7641,
+      "step": 1400
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002967078189300412,
+      "loss": 0.6967,
+      "step": 1405
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002962962962962963,
+      "loss": 0.735,
+      "step": 1410
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029588477366255145,
+      "loss": 0.7685,
+      "step": 1415
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002954732510288066,
+      "loss": 0.758,
+      "step": 1420
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002950617283950617,
+      "loss": 0.763,
+      "step": 1425
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00029465020576131687,
+      "loss": 0.712,
+      "step": 1430
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00029423868312757203,
+      "loss": 0.7236,
+      "step": 1435
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002938271604938272,
+      "loss": 0.7732,
+      "step": 1440
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002934156378600823,
+      "loss": 0.7689,
+      "step": 1445
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00029300411522633745,
+      "loss": 0.7352,
+      "step": 1450
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002925925925925926,
+      "loss": 0.7711,
+      "step": 1455
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002921810699588477,
+      "loss": 0.7549,
+      "step": 1460
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002917695473251029,
+      "loss": 0.7804,
+      "step": 1465
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00029135802469135803,
+      "loss": 0.7478,
+      "step": 1470
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002909465020576132,
+      "loss": 0.7801,
+      "step": 1475
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002905349794238683,
+      "loss": 0.7544,
+      "step": 1480
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00029012345679012345,
+      "loss": 0.7546,
+      "step": 1485
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002897119341563786,
+      "loss": 0.7648,
+      "step": 1490
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002893004115226337,
+      "loss": 0.7468,
+      "step": 1495
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002888888888888889,
+      "loss": 0.7434,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00028847736625514403,
+      "loss": 0.7348,
+      "step": 1505
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002880658436213992,
+      "loss": 0.7515,
+      "step": 1510
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00028765432098765435,
+      "loss": 0.7345,
+      "step": 1515
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00028724279835390946,
+      "loss": 0.7701,
+      "step": 1520
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002868312757201646,
+      "loss": 0.7472,
+      "step": 1525
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00028641975308641977,
+      "loss": 0.7075,
+      "step": 1530
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00028600823045267493,
+      "loss": 0.7483,
+      "step": 1535
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002855967078189301,
+      "loss": 0.712,
+      "step": 1540
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002851851851851852,
+      "loss": 0.7484,
+      "step": 1545
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00028477366255144035,
+      "loss": 0.7471,
+      "step": 1550
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002843621399176955,
+      "loss": 0.7462,
+      "step": 1555
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00028395061728395067,
+      "loss": 0.7371,
+      "step": 1560
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002835390946502058,
+      "loss": 0.7753,
+      "step": 1565
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00028312757201646093,
+      "loss": 0.7374,
+      "step": 1570
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002827160493827161,
+      "loss": 0.7328,
+      "step": 1575
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002823045267489712,
+      "loss": 0.7159,
+      "step": 1580
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00028189300411522635,
+      "loss": 0.7594,
+      "step": 1585
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002814814814814815,
+      "loss": 0.7215,
+      "step": 1590
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00028106995884773667,
+      "loss": 0.7398,
+      "step": 1595
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002806584362139918,
+      "loss": 0.773,
+      "step": 1600
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00028024691358024693,
+      "loss": 0.7584,
+      "step": 1605
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002798353909465021,
+      "loss": 0.7117,
+      "step": 1610
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002794238683127572,
+      "loss": 0.7471,
+      "step": 1615
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00027901234567901236,
+      "loss": 0.7443,
+      "step": 1620
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002786008230452675,
+      "loss": 0.7292,
+      "step": 1625
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002781893004115227,
+      "loss": 0.7716,
+      "step": 1630
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 0.763,
+      "step": 1635
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00027736625514403294,
+      "loss": 0.7408,
+      "step": 1640
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002769547325102881,
+      "loss": 0.7403,
+      "step": 1645
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002765432098765432,
+      "loss": 0.7508,
+      "step": 1650
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00027613168724279836,
+      "loss": 0.7687,
+      "step": 1655
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002757201646090535,
+      "loss": 0.7305,
+      "step": 1660
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002753086419753086,
+      "loss": 0.7165,
+      "step": 1665
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002748971193415638,
+      "loss": 0.8,
+      "step": 1670
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00027448559670781894,
+      "loss": 0.7357,
+      "step": 1675
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002740740740740741,
+      "loss": 0.7988,
+      "step": 1680
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002736625514403292,
+      "loss": 0.7559,
+      "step": 1685
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00027325102880658436,
+      "loss": 0.712,
+      "step": 1690
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002728395061728395,
+      "loss": 0.7486,
+      "step": 1695
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002724279835390946,
+      "loss": 0.7388,
+      "step": 1700
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002720164609053498,
+      "loss": 0.7441,
+      "step": 1705
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00027160493827160494,
+      "loss": 0.7547,
+      "step": 1710
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002711934156378601,
+      "loss": 0.7229,
+      "step": 1715
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002707818930041152,
+      "loss": 0.7383,
+      "step": 1720
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00027037037037037036,
+      "loss": 0.7606,
+      "step": 1725
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002699588477366255,
+      "loss": 0.7529,
+      "step": 1730
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002695473251028807,
+      "loss": 0.752,
+      "step": 1735
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00026913580246913584,
+      "loss": 0.7342,
+      "step": 1740
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.000268724279835391,
+      "loss": 0.7308,
+      "step": 1745
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002683127572016461,
+      "loss": 0.6915,
+      "step": 1750
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00026790123456790126,
+      "loss": 0.7344,
+      "step": 1755
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002674897119341564,
+      "loss": 0.7426,
+      "step": 1760
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002670781893004116,
+      "loss": 0.7088,
+      "step": 1765
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002666666666666667,
+      "loss": 0.7241,
+      "step": 1770
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00026625514403292184,
+      "loss": 0.7552,
+      "step": 1775
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.000265843621399177,
+      "loss": 0.7477,
+      "step": 1780
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002654320987654321,
+      "loss": 0.7115,
+      "step": 1785
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00026502057613168726,
+      "loss": 0.7538,
+      "step": 1790
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002646090534979424,
+      "loss": 0.7321,
+      "step": 1795
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002641975308641976,
+      "loss": 0.7212,
+      "step": 1800
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002637860082304527,
+      "loss": 0.747,
+      "step": 1805
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00026337448559670784,
+      "loss": 0.7606,
+      "step": 1810
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.000262962962962963,
+      "loss": 0.7344,
+      "step": 1815
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002625514403292181,
+      "loss": 0.7783,
+      "step": 1820
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00026213991769547326,
+      "loss": 0.7556,
+      "step": 1825
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002617283950617284,
+      "loss": 0.7585,
+      "step": 1830
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002613168724279836,
+      "loss": 0.7359,
+      "step": 1835
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002609053497942387,
+      "loss": 0.7185,
+      "step": 1840
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00026049382716049384,
+      "loss": 0.7573,
+      "step": 1845
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.000260082304526749,
+      "loss": 0.7619,
+      "step": 1850
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002596707818930041,
+      "loss": 0.7611,
+      "step": 1855
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00025925925925925926,
+      "loss": 0.7647,
+      "step": 1860
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002588477366255144,
+      "loss": 0.7398,
+      "step": 1865
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002584362139917695,
+      "loss": 0.7683,
+      "step": 1870
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002580246913580247,
+      "loss": 0.7817,
+      "step": 1875
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00025761316872427984,
+      "loss": 0.742,
+      "step": 1880
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.000257201646090535,
+      "loss": 0.7509,
+      "step": 1885
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002567901234567901,
+      "loss": 0.7058,
+      "step": 1890
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00025637860082304526,
+      "loss": 0.7635,
+      "step": 1895
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002559670781893004,
+      "loss": 0.734,
+      "step": 1900
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00025555555555555553,
+      "loss": 0.7416,
+      "step": 1905
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002551440329218107,
+      "loss": 0.7071,
+      "step": 1910
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00025473251028806584,
+      "loss": 0.7275,
+      "step": 1915
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.000254320987654321,
+      "loss": 0.7413,
+      "step": 1920
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002539094650205761,
+      "loss": 0.7703,
+      "step": 1925
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00025349794238683127,
+      "loss": 0.7331,
+      "step": 1930
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002530864197530864,
+      "loss": 0.7251,
+      "step": 1935
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002526748971193416,
+      "loss": 0.7341,
+      "step": 1940
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00025226337448559674,
+      "loss": 0.7079,
+      "step": 1945
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00025185185185185185,
+      "loss": 0.7615,
+      "step": 1950
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.000251440329218107,
+      "loss": 0.7144,
+      "step": 1955
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00025102880658436216,
+      "loss": 0.7527,
+      "step": 1960
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0002506172839506173,
+      "loss": 0.7327,
+      "step": 1965
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002502057613168725,
+      "loss": 0.7173,
+      "step": 1970
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002497942386831276,
+      "loss": 0.7239,
+      "step": 1975
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00024938271604938274,
+      "loss": 0.7442,
+      "step": 1980
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002489711934156379,
+      "loss": 0.7396,
+      "step": 1985
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.000248559670781893,
+      "loss": 0.7365,
+      "step": 1990
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00024814814814814816,
+      "loss": 0.7037,
+      "step": 1995
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002477366255144033,
+      "loss": 0.721,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002473251028806585,
+      "loss": 0.7353,
+      "step": 2005
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002469135802469136,
+      "loss": 0.7648,
+      "step": 2010
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00024650205761316874,
+      "loss": 0.7445,
+      "step": 2015
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0002460905349794239,
+      "loss": 0.7664,
+      "step": 2020
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.000245679012345679,
+      "loss": 0.7202,
+      "step": 2025
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00024526748971193417,
+      "loss": 0.7147,
+      "step": 2030
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0002448559670781893,
+      "loss": 0.722,
+      "step": 2035
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0002444444444444445,
+      "loss": 0.7539,
+      "step": 2040
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002440329218106996,
+      "loss": 0.7681,
+      "step": 2045
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00024362139917695475,
+      "loss": 0.7304,
+      "step": 2050
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002432098765432099,
+      "loss": 0.7432,
+      "step": 2055
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.000242798353909465,
+      "loss": 0.6945,
+      "step": 2060
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00024238683127572017,
+      "loss": 0.7426,
+      "step": 2065
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00024197530864197533,
+      "loss": 0.7144,
+      "step": 2070
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00024156378600823048,
+      "loss": 0.7761,
+      "step": 2075
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0002411522633744856,
+      "loss": 0.7402,
+      "step": 2080
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00024074074074074075,
+      "loss": 0.7376,
+      "step": 2085
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0002403292181069959,
+      "loss": 0.7231,
+      "step": 2090
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023991769547325104,
+      "loss": 0.7461,
+      "step": 2095
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023950617283950617,
+      "loss": 0.7215,
+      "step": 2100
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023909465020576133,
+      "loss": 0.7419,
+      "step": 2105
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023868312757201646,
+      "loss": 0.7502,
+      "step": 2110
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023827160493827162,
+      "loss": 0.7294,
+      "step": 2115
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00023786008230452678,
+      "loss": 0.7904,
+      "step": 2120
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00023744855967078194,
+      "loss": 0.7418,
+      "step": 2125
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00023703703703703704,
+      "loss": 0.7371,
+      "step": 2130
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0002366255144032922,
+      "loss": 0.7384,
+      "step": 2135
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00023621399176954736,
+      "loss": 0.7552,
+      "step": 2140
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023580246913580246,
+      "loss": 0.7516,
+      "step": 2145
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023539094650205762,
+      "loss": 0.7303,
+      "step": 2150
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023497942386831278,
+      "loss": 0.7496,
+      "step": 2155
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023456790123456794,
+      "loss": 0.7135,
+      "step": 2160
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023415637860082304,
+      "loss": 0.7283,
+      "step": 2165
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0002337448559670782,
+      "loss": 0.751,
+      "step": 2170
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00023333333333333336,
+      "loss": 0.7183,
+      "step": 2175
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00023292181069958846,
+      "loss": 0.7242,
+      "step": 2180
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00023251028806584362,
+      "loss": 0.725,
+      "step": 2185
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00023209876543209878,
+      "loss": 0.753,
+      "step": 2190
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002316872427983539,
+      "loss": 0.7664,
+      "step": 2195
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00023127572016460904,
+      "loss": 0.7444,
+      "step": 2200
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002308641975308642,
+      "loss": 0.7226,
+      "step": 2205
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00023045267489711936,
+      "loss": 0.7653,
+      "step": 2210
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002300411522633745,
+      "loss": 0.7382,
+      "step": 2215
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00022962962962962965,
+      "loss": 0.7242,
+      "step": 2220
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002292181069958848,
+      "loss": 0.7215,
+      "step": 2225
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002288065843621399,
+      "loss": 0.724,
+      "step": 2230
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00022839506172839507,
+      "loss": 0.7439,
+      "step": 2235
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00022798353909465023,
+      "loss": 0.699,
+      "step": 2240
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002275720164609054,
+      "loss": 0.7602,
+      "step": 2245
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002271604938271605,
+      "loss": 0.7103,
+      "step": 2250
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00022674897119341565,
+      "loss": 0.7015,
+      "step": 2255
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002263374485596708,
+      "loss": 0.7404,
+      "step": 2260
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00022592592592592591,
+      "loss": 0.7127,
+      "step": 2265
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00022551440329218107,
+      "loss": 0.7299,
+      "step": 2270
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00022510288065843623,
+      "loss": 0.7174,
+      "step": 2275
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002246913580246914,
+      "loss": 0.7454,
+      "step": 2280
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002242798353909465,
+      "loss": 0.7159,
+      "step": 2285
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00022386831275720165,
+      "loss": 0.7263,
+      "step": 2290
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0002234567901234568,
+      "loss": 0.7148,
+      "step": 2295
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00022304526748971192,
+      "loss": 0.7447,
+      "step": 2300
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00022263374485596707,
+      "loss": 0.7326,
+      "step": 2305
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00022222222222222223,
+      "loss": 0.7428,
+      "step": 2310
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00022181069958847736,
+      "loss": 0.7587,
+      "step": 2315
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00022139917695473252,
+      "loss": 0.759,
+      "step": 2320
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00022098765432098768,
+      "loss": 0.7716,
+      "step": 2325
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002205761316872428,
+      "loss": 0.74,
+      "step": 2330
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00022016460905349794,
+      "loss": 0.7255,
+      "step": 2335
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002197530864197531,
+      "loss": 0.7547,
+      "step": 2340
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021934156378600826,
+      "loss": 0.7359,
+      "step": 2345
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021893004115226337,
+      "loss": 0.6987,
+      "step": 2350
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021851851851851852,
+      "loss": 0.7233,
+      "step": 2355
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021810699588477368,
+      "loss": 0.6945,
+      "step": 2360
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021769547325102884,
+      "loss": 0.7566,
+      "step": 2365
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00021728395061728395,
+      "loss": 0.728,
+      "step": 2370
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002168724279835391,
+      "loss": 0.7167,
+      "step": 2375
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00021646090534979426,
+      "loss": 0.7576,
+      "step": 2380
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00021604938271604937,
+      "loss": 0.7246,
+      "step": 2385
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00021563786008230453,
+      "loss": 0.755,
+      "step": 2390
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00021522633744855968,
+      "loss": 0.6983,
+      "step": 2395
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00021481481481481484,
+      "loss": 0.7369,
+      "step": 2400
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00021440329218106995,
+      "loss": 0.7074,
+      "step": 2405
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0002139917695473251,
+      "loss": 0.7317,
+      "step": 2410
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00021358024691358026,
+      "loss": 0.7086,
+      "step": 2415
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0002131687242798354,
+      "loss": 0.7356,
+      "step": 2420
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00021275720164609055,
+      "loss": 0.7652,
+      "step": 2425
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00021234567901234569,
+      "loss": 0.7488,
+      "step": 2430
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00021193415637860082,
+      "loss": 0.746,
+      "step": 2435
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00021152263374485598,
+      "loss": 0.7454,
+      "step": 2440
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00021111111111111113,
+      "loss": 0.72,
+      "step": 2445
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0002106995884773663,
+      "loss": 0.7299,
+      "step": 2450
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0002102880658436214,
+      "loss": 0.7436,
+      "step": 2455
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00020987654320987656,
+      "loss": 0.7068,
+      "step": 2460
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00020946502057613171,
+      "loss": 0.711,
+      "step": 2465
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00020905349794238682,
+      "loss": 0.7473,
+      "step": 2470
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00020864197530864198,
+      "loss": 0.7016,
+      "step": 2475
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00020823045267489714,
+      "loss": 0.7049,
+      "step": 2480
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002078189300411523,
+      "loss": 0.7268,
+      "step": 2485
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002074074074074074,
+      "loss": 0.7239,
+      "step": 2490
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020699588477366256,
+      "loss": 0.698,
+      "step": 2495
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020658436213991772,
+      "loss": 0.7573,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020617283950617282,
+      "loss": 0.7309,
+      "step": 2505
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020576131687242798,
+      "loss": 0.6628,
+      "step": 2510
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020534979423868314,
+      "loss": 0.656,
+      "step": 2515
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0002049382716049383,
+      "loss": 0.6737,
+      "step": 2520
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00020452674897119343,
+      "loss": 0.6903,
+      "step": 2525
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00020411522633744856,
+      "loss": 0.6674,
+      "step": 2530
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00020370370370370372,
+      "loss": 0.6507,
+      "step": 2535
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00020329218106995885,
+      "loss": 0.6948,
+      "step": 2540
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.000202880658436214,
+      "loss": 0.6662,
+      "step": 2545
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00020246913580246917,
+      "loss": 0.6624,
+      "step": 2550
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00020205761316872427,
+      "loss": 0.6791,
+      "step": 2555
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00020164609053497943,
+      "loss": 0.7088,
+      "step": 2560
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0002012345679012346,
+      "loss": 0.6796,
+      "step": 2565
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00020082304526748975,
+      "loss": 0.6601,
+      "step": 2570
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00020041152263374485,
+      "loss": 0.6865,
+      "step": 2575
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0002,
+      "loss": 0.6725,
+      "step": 2580
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00019958847736625514,
+      "loss": 0.6743,
+      "step": 2585
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0001991769547325103,
+      "loss": 0.6395,
+      "step": 2590
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00019876543209876543,
+      "loss": 0.6522,
+      "step": 2595
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0001983539094650206,
+      "loss": 0.6868,
+      "step": 2600
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00019794238683127572,
+      "loss": 0.6861,
+      "step": 2605
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00019753086419753085,
+      "loss": 0.6843,
+      "step": 2610
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.000197119341563786,
+      "loss": 0.6732,
+      "step": 2615
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00019670781893004114,
+      "loss": 0.6676,
+      "step": 2620
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0001962962962962963,
+      "loss": 0.6782,
+      "step": 2625
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00019588477366255146,
+      "loss": 0.6937,
+      "step": 2630
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0001954732510288066,
+      "loss": 0.6823,
+      "step": 2635
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00019506172839506175,
+      "loss": 0.6839,
+      "step": 2640
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019465020576131688,
+      "loss": 0.6351,
+      "step": 2645
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019423868312757204,
+      "loss": 0.7157,
+      "step": 2650
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019382716049382717,
+      "loss": 0.6591,
+      "step": 2655
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019341563786008233,
+      "loss": 0.6826,
+      "step": 2660
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019300411522633746,
+      "loss": 0.6732,
+      "step": 2665
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0001925925925925926,
+      "loss": 0.6795,
+      "step": 2670
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00019218106995884775,
+      "loss": 0.6845,
+      "step": 2675
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00019176954732510288,
+      "loss": 0.649,
+      "step": 2680
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00019135802469135804,
+      "loss": 0.6684,
+      "step": 2685
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00019094650205761317,
+      "loss": 0.6712,
+      "step": 2690
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00019053497942386833,
+      "loss": 0.6665,
+      "step": 2695
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00019012345679012346,
+      "loss": 0.6426,
+      "step": 2700
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0001897119341563786,
+      "loss": 0.6561,
+      "step": 2705
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00018930041152263375,
+      "loss": 0.6664,
+      "step": 2710
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00018888888888888888,
+      "loss": 0.6746,
+      "step": 2715
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018847736625514404,
+      "loss": 0.6497,
+      "step": 2720
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018806584362139917,
+      "loss": 0.6811,
+      "step": 2725
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018765432098765433,
+      "loss": 0.6608,
+      "step": 2730
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018724279835390946,
+      "loss": 0.6655,
+      "step": 2735
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018683127572016462,
+      "loss": 0.7014,
+      "step": 2740
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00018641975308641978,
+      "loss": 0.6889,
+      "step": 2745
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0001860082304526749,
+      "loss": 0.6805,
+      "step": 2750
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00018559670781893007,
+      "loss": 0.6629,
+      "step": 2755
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0001851851851851852,
+      "loss": 0.6593,
+      "step": 2760
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00018477366255144033,
+      "loss": 0.6902,
+      "step": 2765
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0001843621399176955,
+      "loss": 0.6777,
+      "step": 2770
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00018395061728395062,
+      "loss": 0.7127,
+      "step": 2775
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00018353909465020578,
+      "loss": 0.6551,
+      "step": 2780
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00018312757201646091,
+      "loss": 0.6703,
+      "step": 2785
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00018271604938271605,
+      "loss": 0.6776,
+      "step": 2790
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0001823045267489712,
+      "loss": 0.6574,
+      "step": 2795
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00018189300411522634,
+      "loss": 0.7154,
+      "step": 2800
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0001814814814814815,
+      "loss": 0.6749,
+      "step": 2805
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00018106995884773663,
+      "loss": 0.695,
+      "step": 2810
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00018065843621399178,
+      "loss": 0.6685,
+      "step": 2815
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00018024691358024692,
+      "loss": 0.642,
+      "step": 2820
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00017983539094650205,
+      "loss": 0.6873,
+      "step": 2825
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0001794238683127572,
+      "loss": 0.6506,
+      "step": 2830
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00017901234567901234,
+      "loss": 0.6695,
+      "step": 2835
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0001786008230452675,
+      "loss": 0.651,
+      "step": 2840
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00017818930041152265,
+      "loss": 0.6585,
+      "step": 2845
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 0.6717,
+      "step": 2850
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00017736625514403294,
+      "loss": 0.6524,
+      "step": 2855
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00017695473251028808,
+      "loss": 0.6679,
+      "step": 2860
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00017654320987654323,
+      "loss": 0.6719,
+      "step": 2865
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00017613168724279837,
+      "loss": 0.6662,
+      "step": 2870
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00017572016460905352,
+      "loss": 0.6624,
+      "step": 2875
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00017530864197530866,
+      "loss": 0.69,
+      "step": 2880
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0001748971193415638,
+      "loss": 0.6629,
+      "step": 2885
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00017448559670781895,
+      "loss": 0.6566,
+      "step": 2890
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00017407407407407408,
+      "loss": 0.6711,
+      "step": 2895
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00017366255144032924,
+      "loss": 0.6995,
+      "step": 2900
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00017325102880658437,
+      "loss": 0.6597,
+      "step": 2905
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0001728395061728395,
+      "loss": 0.6685,
+      "step": 2910
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00017242798353909466,
+      "loss": 0.6649,
+      "step": 2915
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0001720164609053498,
+      "loss": 0.6824,
+      "step": 2920
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00017160493827160495,
+      "loss": 0.6484,
+      "step": 2925
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00017119341563786008,
+      "loss": 0.6693,
+      "step": 2930
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00017078189300411524,
+      "loss": 0.629,
+      "step": 2935
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00017037037037037037,
+      "loss": 0.6588,
+      "step": 2940
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00016995884773662553,
+      "loss": 0.6771,
+      "step": 2945
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00016954732510288066,
+      "loss": 0.6773,
+      "step": 2950
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00016913580246913582,
+      "loss": 0.6307,
+      "step": 2955
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00016872427983539098,
+      "loss": 0.6809,
+      "step": 2960
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0001683127572016461,
+      "loss": 0.6748,
+      "step": 2965
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00016790123456790124,
+      "loss": 0.6708,
+      "step": 2970
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0001674897119341564,
+      "loss": 0.6754,
+      "step": 2975
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00016707818930041153,
+      "loss": 0.6676,
+      "step": 2980
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 0.6662,
+      "step": 2985
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00016625514403292182,
+      "loss": 0.6933,
+      "step": 2990
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00016584362139917695,
+      "loss": 0.6879,
+      "step": 2995
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0001654320987654321,
+      "loss": 0.6979,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 5010,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 1.2080552599774822e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/training_args.bin b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..28c7b09fc2b3929abe4ad6608c7959f30a9a9d66
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43458f4cf6aeb211c730b848f93ab15f483827c314fb4dc1e79dd1f658b7dbc8
+size 5944
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/zero_to_fp32.py b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/zero_to_fp32.py
new file mode 100644
index 0000000000000000000000000000000000000000..c98caae31534368be22b67fc4ae906836c992a8d
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3000/zero_to_fp32.py
@@ -0,0 +1,587 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel()
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file, tag=args.tag)
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/README.md b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..2aa897f8fa13b49ce76b1fa188781e5f726e7d13
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-2-7b-hf
+library_name: peft
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/adapter_config.json b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9c81a592f0ff08374a4f61f6003029070a8429ae
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/adapter_config.json
@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "mora_type": 1,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_mora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/adapter_model.safetensors b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f89ea5d2160acff4f98900c4f172b32ba552d0e3
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:314c9406340ddc3077b70bbc3d2fcace468611bc56918c2090fee77bedbe7876
+size 564342240
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/global_step3500/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/global_step3500/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..100618f078eb7dcf69b09f54c6815cc20d45e5e4
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/global_step3500/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a01ec991d722549ef74ff1b551f8baf8e673b8788975babfdc3dc3bab0fd8908
+size 239914224
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/global_step3500/mp_rank_00_model_states.pt b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/global_step3500/mp_rank_00_model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0756adb042329172121ed89ae3a77bcad43a6a14
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/global_step3500/mp_rank_00_model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3d55e7f8f4a437e9a67462a1293e67ab2b03a41ad52e2af8435d871550cb074
+size 40303404
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/latest b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/latest
new file mode 100644
index 0000000000000000000000000000000000000000..f3af93198d9ca215e3991f85bf3781ae5dfe71f3
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/latest
@@ -0,0 +1 @@
+global_step3500
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/rng_state.pth b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f6488135afbf0a2ed40e30a80b4bac42b6c3ada7
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a416fef4baf7da791f4aa05f7e025ca652472141670ffd3e3487a4df1f3a1fc
+size 14244
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/scheduler.pt b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3305ecffef79efafcf2556476aee087eb925f213
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff5ee0320ce9d7ad88f792008c95002cf68f7ec2fcb536ba4176be364a3f1bf4
+size 1064
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/trainer_state.json b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..73adea684d787b62623da855a706bcc21acdf834
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/trainer_state.json
@@ -0,0 +1,4221 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.3970748744815542,
+  "eval_steps": 500,
+  "global_step": 3500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.3798,
+      "step": 5
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 1.3917,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4e-05,
+      "loss": 1.2862,
+      "step": 15
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 1.2046,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.0634,
+      "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8e-05,
+      "loss": 1.0273,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 1.0472,
+      "step": 35
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 1.0301,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00012,
+      "loss": 0.9335,
+      "step": 45
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.921,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00014666666666666666,
+      "loss": 0.9506,
+      "step": 55
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016,
+      "loss": 0.8876,
+      "step": 60
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00017333333333333334,
+      "loss": 0.9335,
+      "step": 65
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 0.8554,
+      "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0002,
+      "loss": 0.8537,
+      "step": 75
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00021333333333333333,
+      "loss": 0.9033,
+      "step": 80
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00022666666666666668,
+      "loss": 0.8203,
+      "step": 85
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00024,
+      "loss": 0.8611,
+      "step": 90
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00025333333333333333,
+      "loss": 0.8303,
+      "step": 95
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002666666666666667,
+      "loss": 0.8528,
+      "step": 100
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00028,
+      "loss": 0.8537,
+      "step": 105
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002933333333333333,
+      "loss": 0.8286,
+      "step": 110
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003066666666666667,
+      "loss": 0.8449,
+      "step": 115
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00032,
+      "loss": 0.8377,
+      "step": 120
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003333333333333334,
+      "loss": 0.8419,
+      "step": 125
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00034666666666666667,
+      "loss": 0.8265,
+      "step": 130
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00036,
+      "loss": 0.8037,
+      "step": 135
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003733333333333334,
+      "loss": 0.7924,
+      "step": 140
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00038666666666666667,
+      "loss": 0.8245,
+      "step": 145
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0004,
+      "loss": 0.8388,
+      "step": 150
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003995884773662552,
+      "loss": 0.8066,
+      "step": 155
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003991769547325103,
+      "loss": 0.8107,
+      "step": 160
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039876543209876544,
+      "loss": 0.8005,
+      "step": 165
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003983539094650206,
+      "loss": 0.7727,
+      "step": 170
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039794238683127576,
+      "loss": 0.8276,
+      "step": 175
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039753086419753086,
+      "loss": 0.8464,
+      "step": 180
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000397119341563786,
+      "loss": 0.8348,
+      "step": 185
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003967078189300412,
+      "loss": 0.8228,
+      "step": 190
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003962962962962963,
+      "loss": 0.8254,
+      "step": 195
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00039588477366255144,
+      "loss": 0.817,
+      "step": 200
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003954732510288066,
+      "loss": 0.8365,
+      "step": 205
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003950617283950617,
+      "loss": 0.793,
+      "step": 210
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00039465020576131686,
+      "loss": 0.8014,
+      "step": 215
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000394238683127572,
+      "loss": 0.8049,
+      "step": 220
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003938271604938272,
+      "loss": 0.7841,
+      "step": 225
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003934156378600823,
+      "loss": 0.7977,
+      "step": 230
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00039300411522633744,
+      "loss": 0.8299,
+      "step": 235
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003925925925925926,
+      "loss": 0.7729,
+      "step": 240
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00039218106995884776,
+      "loss": 0.8082,
+      "step": 245
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003917695473251029,
+      "loss": 0.8173,
+      "step": 250
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000391358024691358,
+      "loss": 0.8379,
+      "step": 255
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003909465020576132,
+      "loss": 0.7962,
+      "step": 260
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00039053497942386834,
+      "loss": 0.8067,
+      "step": 265
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003901234567901235,
+      "loss": 0.7915,
+      "step": 270
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00038971193415637866,
+      "loss": 0.7905,
+      "step": 275
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00038930041152263376,
+      "loss": 0.7862,
+      "step": 280
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003888888888888889,
+      "loss": 0.7709,
+      "step": 285
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003884773662551441,
+      "loss": 0.7773,
+      "step": 290
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00038806584362139924,
+      "loss": 0.8068,
+      "step": 295
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00038765432098765434,
+      "loss": 0.7962,
+      "step": 300
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003872427983539095,
+      "loss": 0.7894,
+      "step": 305
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00038683127572016466,
+      "loss": 0.7705,
+      "step": 310
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00038641975308641976,
+      "loss": 0.7882,
+      "step": 315
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003860082304526749,
+      "loss": 0.7865,
+      "step": 320
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003855967078189301,
+      "loss": 0.7939,
+      "step": 325
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003851851851851852,
+      "loss": 0.7724,
+      "step": 330
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00038477366255144034,
+      "loss": 0.7771,
+      "step": 335
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003843621399176955,
+      "loss": 0.7941,
+      "step": 340
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00038395061728395066,
+      "loss": 0.7822,
+      "step": 345
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00038353909465020577,
+      "loss": 0.8143,
+      "step": 350
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003831275720164609,
+      "loss": 0.795,
+      "step": 355
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003827160493827161,
+      "loss": 0.8049,
+      "step": 360
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003823045267489712,
+      "loss": 0.8309,
+      "step": 365
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00038189300411522635,
+      "loss": 0.8314,
+      "step": 370
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003814814814814815,
+      "loss": 0.801,
+      "step": 375
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00038106995884773666,
+      "loss": 0.8084,
+      "step": 380
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00038065843621399177,
+      "loss": 0.8129,
+      "step": 385
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003802469135802469,
+      "loss": 0.7859,
+      "step": 390
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003798353909465021,
+      "loss": 0.7874,
+      "step": 395
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003794238683127572,
+      "loss": 0.7548,
+      "step": 400
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00037901234567901235,
+      "loss": 0.8092,
+      "step": 405
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003786008230452675,
+      "loss": 0.8041,
+      "step": 410
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00037818930041152266,
+      "loss": 0.777,
+      "step": 415
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00037777777777777777,
+      "loss": 0.7699,
+      "step": 420
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00037736625514403293,
+      "loss": 0.781,
+      "step": 425
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003769547325102881,
+      "loss": 0.7504,
+      "step": 430
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003765432098765432,
+      "loss": 0.7974,
+      "step": 435
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037613168724279835,
+      "loss": 0.7663,
+      "step": 440
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003757201646090535,
+      "loss": 0.8013,
+      "step": 445
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037530864197530867,
+      "loss": 0.7453,
+      "step": 450
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037489711934156377,
+      "loss": 0.7425,
+      "step": 455
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037448559670781893,
+      "loss": 0.7582,
+      "step": 460
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003740740740740741,
+      "loss": 0.7801,
+      "step": 465
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00037366255144032925,
+      "loss": 0.7809,
+      "step": 470
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003732510288065844,
+      "loss": 0.7749,
+      "step": 475
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00037283950617283956,
+      "loss": 0.7807,
+      "step": 480
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00037242798353909467,
+      "loss": 0.7715,
+      "step": 485
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003720164609053498,
+      "loss": 0.7356,
+      "step": 490
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000371604938271605,
+      "loss": 0.7674,
+      "step": 495
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00037119341563786014,
+      "loss": 0.7542,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00037078189300411525,
+      "loss": 0.7583,
+      "step": 505
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003703703703703704,
+      "loss": 0.7767,
+      "step": 510
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036995884773662556,
+      "loss": 0.7853,
+      "step": 515
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036954732510288067,
+      "loss": 0.7733,
+      "step": 520
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036913580246913583,
+      "loss": 0.7758,
+      "step": 525
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.000368724279835391,
+      "loss": 0.7698,
+      "step": 530
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036831275720164614,
+      "loss": 0.7805,
+      "step": 535
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036790123456790125,
+      "loss": 0.7573,
+      "step": 540
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003674897119341564,
+      "loss": 0.7709,
+      "step": 545
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036707818930041157,
+      "loss": 0.7994,
+      "step": 550
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036666666666666667,
+      "loss": 0.7363,
+      "step": 555
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036625514403292183,
+      "loss": 0.7478,
+      "step": 560
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000365843621399177,
+      "loss": 0.8188,
+      "step": 565
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003654320987654321,
+      "loss": 0.7524,
+      "step": 570
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00036502057613168725,
+      "loss": 0.7319,
+      "step": 575
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003646090534979424,
+      "loss": 0.7915,
+      "step": 580
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00036419753086419757,
+      "loss": 0.7722,
+      "step": 585
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00036378600823045267,
+      "loss": 0.7842,
+      "step": 590
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00036337448559670783,
+      "loss": 0.7591,
+      "step": 595
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000362962962962963,
+      "loss": 0.7653,
+      "step": 600
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003625514403292181,
+      "loss": 0.7838,
+      "step": 605
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00036213991769547325,
+      "loss": 0.7937,
+      "step": 610
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003617283950617284,
+      "loss": 0.77,
+      "step": 615
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00036131687242798357,
+      "loss": 0.7899,
+      "step": 620
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003609053497942387,
+      "loss": 0.7815,
+      "step": 625
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00036049382716049383,
+      "loss": 0.7648,
+      "step": 630
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.000360082304526749,
+      "loss": 0.7716,
+      "step": 635
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003596707818930041,
+      "loss": 0.7708,
+      "step": 640
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00035925925925925925,
+      "loss": 0.7306,
+      "step": 645
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003588477366255144,
+      "loss": 0.8007,
+      "step": 650
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003584362139917695,
+      "loss": 0.7551,
+      "step": 655
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003580246913580247,
+      "loss": 0.754,
+      "step": 660
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00035761316872427983,
+      "loss": 0.7599,
+      "step": 665
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.000357201646090535,
+      "loss": 0.7637,
+      "step": 670
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00035679012345679015,
+      "loss": 0.7766,
+      "step": 675
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003563786008230453,
+      "loss": 0.7727,
+      "step": 680
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003559670781893004,
+      "loss": 0.7675,
+      "step": 685
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035555555555555557,
+      "loss": 0.7707,
+      "step": 690
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035514403292181073,
+      "loss": 0.7221,
+      "step": 695
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003547325102880659,
+      "loss": 0.7335,
+      "step": 700
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035432098765432105,
+      "loss": 0.781,
+      "step": 705
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035390946502057615,
+      "loss": 0.7845,
+      "step": 710
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003534979423868313,
+      "loss": 0.7467,
+      "step": 715
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00035308641975308647,
+      "loss": 0.7735,
+      "step": 720
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003526748971193416,
+      "loss": 0.7368,
+      "step": 725
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00035226337448559673,
+      "loss": 0.7678,
+      "step": 730
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003518518518518519,
+      "loss": 0.7756,
+      "step": 735
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00035144032921810705,
+      "loss": 0.7635,
+      "step": 740
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00035102880658436215,
+      "loss": 0.7757,
+      "step": 745
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003506172839506173,
+      "loss": 0.7442,
+      "step": 750
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00035020576131687247,
+      "loss": 0.7584,
+      "step": 755
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003497942386831276,
+      "loss": 0.8333,
+      "step": 760
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00034938271604938273,
+      "loss": 0.7459,
+      "step": 765
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003489711934156379,
+      "loss": 0.7499,
+      "step": 770
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.000348559670781893,
+      "loss": 0.7571,
+      "step": 775
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00034814814814814816,
+      "loss": 0.7243,
+      "step": 780
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003477366255144033,
+      "loss": 0.7443,
+      "step": 785
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003473251028806585,
+      "loss": 0.7759,
+      "step": 790
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003469135802469136,
+      "loss": 0.7452,
+      "step": 795
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00034650205761316874,
+      "loss": 0.7578,
+      "step": 800
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003460905349794239,
+      "loss": 0.7634,
+      "step": 805
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.000345679012345679,
+      "loss": 0.7925,
+      "step": 810
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00034526748971193416,
+      "loss": 0.7966,
+      "step": 815
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003448559670781893,
+      "loss": 0.7601,
+      "step": 820
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003444444444444445,
+      "loss": 0.7617,
+      "step": 825
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003440329218106996,
+      "loss": 0.7526,
+      "step": 830
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00034362139917695474,
+      "loss": 0.7297,
+      "step": 835
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003432098765432099,
+      "loss": 0.7549,
+      "step": 840
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.000342798353909465,
+      "loss": 0.7517,
+      "step": 845
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00034238683127572016,
+      "loss": 0.7626,
+      "step": 850
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003419753086419753,
+      "loss": 0.7987,
+      "step": 855
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003415637860082305,
+      "loss": 0.7573,
+      "step": 860
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003411522633744856,
+      "loss": 0.8367,
+      "step": 865
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00034074074074074074,
+      "loss": 0.7258,
+      "step": 870
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003403292181069959,
+      "loss": 0.7632,
+      "step": 875
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00033991769547325106,
+      "loss": 0.7379,
+      "step": 880
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00033950617283950616,
+      "loss": 0.7529,
+      "step": 885
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003390946502057613,
+      "loss": 0.7391,
+      "step": 890
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003386831275720165,
+      "loss": 0.8061,
+      "step": 895
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00033827160493827164,
+      "loss": 0.7288,
+      "step": 900
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003378600823045268,
+      "loss": 0.7493,
+      "step": 905
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00033744855967078195,
+      "loss": 0.7702,
+      "step": 910
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00033703703703703706,
+      "loss": 0.7538,
+      "step": 915
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003366255144032922,
+      "loss": 0.728,
+      "step": 920
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003362139917695474,
+      "loss": 0.7776,
+      "step": 925
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003358024691358025,
+      "loss": 0.7883,
+      "step": 930
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00033539094650205764,
+      "loss": 0.7471,
+      "step": 935
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003349794238683128,
+      "loss": 0.7464,
+      "step": 940
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00033456790123456795,
+      "loss": 0.7885,
+      "step": 945
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00033415637860082306,
+      "loss": 0.7509,
+      "step": 950
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003337448559670782,
+      "loss": 0.7681,
+      "step": 955
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003333333333333334,
+      "loss": 0.8246,
+      "step": 960
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003329218106995885,
+      "loss": 0.7604,
+      "step": 965
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00033251028806584364,
+      "loss": 0.7755,
+      "step": 970
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003320987654320988,
+      "loss": 0.7641,
+      "step": 975
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003316872427983539,
+      "loss": 0.7708,
+      "step": 980
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00033127572016460906,
+      "loss": 0.7936,
+      "step": 985
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003308641975308642,
+      "loss": 0.7641,
+      "step": 990
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003304526748971194,
+      "loss": 0.7479,
+      "step": 995
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003300411522633745,
+      "loss": 0.7547,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00032962962962962964,
+      "loss": 0.762,
+      "step": 1005
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003292181069958848,
+      "loss": 0.7472,
+      "step": 1010
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003288065843621399,
+      "loss": 0.7542,
+      "step": 1015
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00032839506172839506,
+      "loss": 0.7669,
+      "step": 1020
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003279835390946502,
+      "loss": 0.7812,
+      "step": 1025
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003275720164609054,
+      "loss": 0.7273,
+      "step": 1030
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003271604938271605,
+      "loss": 0.7822,
+      "step": 1035
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00032674897119341564,
+      "loss": 0.7337,
+      "step": 1040
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003263374485596708,
+      "loss": 0.7566,
+      "step": 1045
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003259259259259259,
+      "loss": 0.7377,
+      "step": 1050
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00032551440329218106,
+      "loss": 0.7856,
+      "step": 1055
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003251028806584362,
+      "loss": 0.7981,
+      "step": 1060
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003246913580246914,
+      "loss": 0.7505,
+      "step": 1065
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003242798353909465,
+      "loss": 0.7549,
+      "step": 1070
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00032386831275720164,
+      "loss": 0.7306,
+      "step": 1075
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003234567901234568,
+      "loss": 0.7343,
+      "step": 1080
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003230452674897119,
+      "loss": 0.738,
+      "step": 1085
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00032263374485596707,
+      "loss": 0.7655,
+      "step": 1090
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003222222222222222,
+      "loss": 0.7706,
+      "step": 1095
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003218106995884774,
+      "loss": 0.7512,
+      "step": 1100
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00032139917695473254,
+      "loss": 0.7549,
+      "step": 1105
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003209876543209877,
+      "loss": 0.7839,
+      "step": 1110
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003205761316872428,
+      "loss": 0.7511,
+      "step": 1115
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00032016460905349796,
+      "loss": 0.769,
+      "step": 1120
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003197530864197531,
+      "loss": 0.7685,
+      "step": 1125
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003193415637860083,
+      "loss": 0.7489,
+      "step": 1130
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003189300411522634,
+      "loss": 0.808,
+      "step": 1135
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00031851851851851854,
+      "loss": 0.7654,
+      "step": 1140
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003181069958847737,
+      "loss": 0.7845,
+      "step": 1145
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00031769547325102886,
+      "loss": 0.7886,
+      "step": 1150
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00031728395061728396,
+      "loss": 0.7318,
+      "step": 1155
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003168724279835391,
+      "loss": 0.7231,
+      "step": 1160
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003164609053497943,
+      "loss": 0.7471,
+      "step": 1165
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003160493827160494,
+      "loss": 0.7424,
+      "step": 1170
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00031563786008230454,
+      "loss": 0.7249,
+      "step": 1175
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003152263374485597,
+      "loss": 0.7419,
+      "step": 1180
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00031481481481481486,
+      "loss": 0.7567,
+      "step": 1185
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00031440329218106997,
+      "loss": 0.7707,
+      "step": 1190
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003139917695473251,
+      "loss": 0.7473,
+      "step": 1195
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003135802469135803,
+      "loss": 0.7222,
+      "step": 1200
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003131687242798354,
+      "loss": 0.7383,
+      "step": 1205
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00031275720164609055,
+      "loss": 0.7712,
+      "step": 1210
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003123456790123457,
+      "loss": 0.7602,
+      "step": 1215
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003119341563786008,
+      "loss": 0.7741,
+      "step": 1220
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00031152263374485597,
+      "loss": 0.7428,
+      "step": 1225
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003111111111111111,
+      "loss": 0.7605,
+      "step": 1230
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003106995884773663,
+      "loss": 0.7255,
+      "step": 1235
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003102880658436214,
+      "loss": 0.7468,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00030987654320987655,
+      "loss": 0.7961,
+      "step": 1245
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003094650205761317,
+      "loss": 0.7208,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003090534979423868,
+      "loss": 0.7331,
+      "step": 1255
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00030864197530864197,
+      "loss": 0.7371,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00030823045267489713,
+      "loss": 0.7206,
+      "step": 1265
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003078189300411523,
+      "loss": 0.7617,
+      "step": 1270
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003074074074074074,
+      "loss": 0.7652,
+      "step": 1275
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00030699588477366255,
+      "loss": 0.7635,
+      "step": 1280
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003065843621399177,
+      "loss": 0.7445,
+      "step": 1285
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003061728395061728,
+      "loss": 0.7717,
+      "step": 1290
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030576131687242797,
+      "loss": 0.7535,
+      "step": 1295
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030534979423868313,
+      "loss": 0.7677,
+      "step": 1300
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003049382716049383,
+      "loss": 0.8131,
+      "step": 1305
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030452674897119345,
+      "loss": 0.7754,
+      "step": 1310
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030411522633744855,
+      "loss": 0.76,
+      "step": 1315
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003037037037037037,
+      "loss": 0.7558,
+      "step": 1320
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00030329218106995887,
+      "loss": 0.7604,
+      "step": 1325
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.000302880658436214,
+      "loss": 0.7716,
+      "step": 1330
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003024691358024692,
+      "loss": 0.7669,
+      "step": 1335
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003020576131687243,
+      "loss": 0.7469,
+      "step": 1340
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030164609053497945,
+      "loss": 0.7511,
+      "step": 1345
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003012345679012346,
+      "loss": 0.7483,
+      "step": 1350
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030082304526748976,
+      "loss": 0.7509,
+      "step": 1355
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030041152263374487,
+      "loss": 0.7249,
+      "step": 1360
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.7289,
+      "step": 1365
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002995884773662552,
+      "loss": 0.7605,
+      "step": 1370
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002991769547325103,
+      "loss": 0.7185,
+      "step": 1375
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00029876543209876545,
+      "loss": 0.6974,
+      "step": 1380
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002983539094650206,
+      "loss": 0.7234,
+      "step": 1385
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00029794238683127577,
+      "loss": 0.7506,
+      "step": 1390
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029753086419753087,
+      "loss": 0.7524,
+      "step": 1395
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029711934156378603,
+      "loss": 0.7641,
+      "step": 1400
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002967078189300412,
+      "loss": 0.6967,
+      "step": 1405
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002962962962962963,
+      "loss": 0.735,
+      "step": 1410
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029588477366255145,
+      "loss": 0.7685,
+      "step": 1415
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002954732510288066,
+      "loss": 0.758,
+      "step": 1420
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002950617283950617,
+      "loss": 0.763,
+      "step": 1425
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00029465020576131687,
+      "loss": 0.712,
+      "step": 1430
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00029423868312757203,
+      "loss": 0.7236,
+      "step": 1435
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002938271604938272,
+      "loss": 0.7732,
+      "step": 1440
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002934156378600823,
+      "loss": 0.7689,
+      "step": 1445
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00029300411522633745,
+      "loss": 0.7352,
+      "step": 1450
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002925925925925926,
+      "loss": 0.7711,
+      "step": 1455
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002921810699588477,
+      "loss": 0.7549,
+      "step": 1460
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002917695473251029,
+      "loss": 0.7804,
+      "step": 1465
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00029135802469135803,
+      "loss": 0.7478,
+      "step": 1470
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002909465020576132,
+      "loss": 0.7801,
+      "step": 1475
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002905349794238683,
+      "loss": 0.7544,
+      "step": 1480
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00029012345679012345,
+      "loss": 0.7546,
+      "step": 1485
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002897119341563786,
+      "loss": 0.7648,
+      "step": 1490
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002893004115226337,
+      "loss": 0.7468,
+      "step": 1495
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002888888888888889,
+      "loss": 0.7434,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00028847736625514403,
+      "loss": 0.7348,
+      "step": 1505
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002880658436213992,
+      "loss": 0.7515,
+      "step": 1510
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00028765432098765435,
+      "loss": 0.7345,
+      "step": 1515
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00028724279835390946,
+      "loss": 0.7701,
+      "step": 1520
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002868312757201646,
+      "loss": 0.7472,
+      "step": 1525
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00028641975308641977,
+      "loss": 0.7075,
+      "step": 1530
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00028600823045267493,
+      "loss": 0.7483,
+      "step": 1535
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002855967078189301,
+      "loss": 0.712,
+      "step": 1540
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002851851851851852,
+      "loss": 0.7484,
+      "step": 1545
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00028477366255144035,
+      "loss": 0.7471,
+      "step": 1550
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002843621399176955,
+      "loss": 0.7462,
+      "step": 1555
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00028395061728395067,
+      "loss": 0.7371,
+      "step": 1560
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002835390946502058,
+      "loss": 0.7753,
+      "step": 1565
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00028312757201646093,
+      "loss": 0.7374,
+      "step": 1570
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002827160493827161,
+      "loss": 0.7328,
+      "step": 1575
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002823045267489712,
+      "loss": 0.7159,
+      "step": 1580
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00028189300411522635,
+      "loss": 0.7594,
+      "step": 1585
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002814814814814815,
+      "loss": 0.7215,
+      "step": 1590
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00028106995884773667,
+      "loss": 0.7398,
+      "step": 1595
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002806584362139918,
+      "loss": 0.773,
+      "step": 1600
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00028024691358024693,
+      "loss": 0.7584,
+      "step": 1605
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002798353909465021,
+      "loss": 0.7117,
+      "step": 1610
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002794238683127572,
+      "loss": 0.7471,
+      "step": 1615
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00027901234567901236,
+      "loss": 0.7443,
+      "step": 1620
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002786008230452675,
+      "loss": 0.7292,
+      "step": 1625
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002781893004115227,
+      "loss": 0.7716,
+      "step": 1630
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 0.763,
+      "step": 1635
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00027736625514403294,
+      "loss": 0.7408,
+      "step": 1640
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002769547325102881,
+      "loss": 0.7403,
+      "step": 1645
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002765432098765432,
+      "loss": 0.7508,
+      "step": 1650
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00027613168724279836,
+      "loss": 0.7687,
+      "step": 1655
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002757201646090535,
+      "loss": 0.7305,
+      "step": 1660
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002753086419753086,
+      "loss": 0.7165,
+      "step": 1665
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002748971193415638,
+      "loss": 0.8,
+      "step": 1670
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00027448559670781894,
+      "loss": 0.7357,
+      "step": 1675
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002740740740740741,
+      "loss": 0.7988,
+      "step": 1680
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002736625514403292,
+      "loss": 0.7559,
+      "step": 1685
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00027325102880658436,
+      "loss": 0.712,
+      "step": 1690
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002728395061728395,
+      "loss": 0.7486,
+      "step": 1695
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002724279835390946,
+      "loss": 0.7388,
+      "step": 1700
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002720164609053498,
+      "loss": 0.7441,
+      "step": 1705
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00027160493827160494,
+      "loss": 0.7547,
+      "step": 1710
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002711934156378601,
+      "loss": 0.7229,
+      "step": 1715
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002707818930041152,
+      "loss": 0.7383,
+      "step": 1720
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00027037037037037036,
+      "loss": 0.7606,
+      "step": 1725
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002699588477366255,
+      "loss": 0.7529,
+      "step": 1730
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002695473251028807,
+      "loss": 0.752,
+      "step": 1735
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00026913580246913584,
+      "loss": 0.7342,
+      "step": 1740
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.000268724279835391,
+      "loss": 0.7308,
+      "step": 1745
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002683127572016461,
+      "loss": 0.6915,
+      "step": 1750
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00026790123456790126,
+      "loss": 0.7344,
+      "step": 1755
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002674897119341564,
+      "loss": 0.7426,
+      "step": 1760
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002670781893004116,
+      "loss": 0.7088,
+      "step": 1765
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002666666666666667,
+      "loss": 0.7241,
+      "step": 1770
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00026625514403292184,
+      "loss": 0.7552,
+      "step": 1775
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.000265843621399177,
+      "loss": 0.7477,
+      "step": 1780
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002654320987654321,
+      "loss": 0.7115,
+      "step": 1785
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00026502057613168726,
+      "loss": 0.7538,
+      "step": 1790
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002646090534979424,
+      "loss": 0.7321,
+      "step": 1795
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002641975308641976,
+      "loss": 0.7212,
+      "step": 1800
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002637860082304527,
+      "loss": 0.747,
+      "step": 1805
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00026337448559670784,
+      "loss": 0.7606,
+      "step": 1810
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.000262962962962963,
+      "loss": 0.7344,
+      "step": 1815
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002625514403292181,
+      "loss": 0.7783,
+      "step": 1820
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00026213991769547326,
+      "loss": 0.7556,
+      "step": 1825
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002617283950617284,
+      "loss": 0.7585,
+      "step": 1830
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002613168724279836,
+      "loss": 0.7359,
+      "step": 1835
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002609053497942387,
+      "loss": 0.7185,
+      "step": 1840
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00026049382716049384,
+      "loss": 0.7573,
+      "step": 1845
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.000260082304526749,
+      "loss": 0.7619,
+      "step": 1850
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002596707818930041,
+      "loss": 0.7611,
+      "step": 1855
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00025925925925925926,
+      "loss": 0.7647,
+      "step": 1860
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002588477366255144,
+      "loss": 0.7398,
+      "step": 1865
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002584362139917695,
+      "loss": 0.7683,
+      "step": 1870
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002580246913580247,
+      "loss": 0.7817,
+      "step": 1875
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00025761316872427984,
+      "loss": 0.742,
+      "step": 1880
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.000257201646090535,
+      "loss": 0.7509,
+      "step": 1885
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002567901234567901,
+      "loss": 0.7058,
+      "step": 1890
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00025637860082304526,
+      "loss": 0.7635,
+      "step": 1895
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002559670781893004,
+      "loss": 0.734,
+      "step": 1900
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00025555555555555553,
+      "loss": 0.7416,
+      "step": 1905
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002551440329218107,
+      "loss": 0.7071,
+      "step": 1910
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00025473251028806584,
+      "loss": 0.7275,
+      "step": 1915
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.000254320987654321,
+      "loss": 0.7413,
+      "step": 1920
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002539094650205761,
+      "loss": 0.7703,
+      "step": 1925
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00025349794238683127,
+      "loss": 0.7331,
+      "step": 1930
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002530864197530864,
+      "loss": 0.7251,
+      "step": 1935
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002526748971193416,
+      "loss": 0.7341,
+      "step": 1940
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00025226337448559674,
+      "loss": 0.7079,
+      "step": 1945
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00025185185185185185,
+      "loss": 0.7615,
+      "step": 1950
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.000251440329218107,
+      "loss": 0.7144,
+      "step": 1955
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00025102880658436216,
+      "loss": 0.7527,
+      "step": 1960
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0002506172839506173,
+      "loss": 0.7327,
+      "step": 1965
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002502057613168725,
+      "loss": 0.7173,
+      "step": 1970
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002497942386831276,
+      "loss": 0.7239,
+      "step": 1975
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00024938271604938274,
+      "loss": 0.7442,
+      "step": 1980
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002489711934156379,
+      "loss": 0.7396,
+      "step": 1985
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.000248559670781893,
+      "loss": 0.7365,
+      "step": 1990
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00024814814814814816,
+      "loss": 0.7037,
+      "step": 1995
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002477366255144033,
+      "loss": 0.721,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002473251028806585,
+      "loss": 0.7353,
+      "step": 2005
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002469135802469136,
+      "loss": 0.7648,
+      "step": 2010
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00024650205761316874,
+      "loss": 0.7445,
+      "step": 2015
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0002460905349794239,
+      "loss": 0.7664,
+      "step": 2020
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.000245679012345679,
+      "loss": 0.7202,
+      "step": 2025
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00024526748971193417,
+      "loss": 0.7147,
+      "step": 2030
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0002448559670781893,
+      "loss": 0.722,
+      "step": 2035
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0002444444444444445,
+      "loss": 0.7539,
+      "step": 2040
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002440329218106996,
+      "loss": 0.7681,
+      "step": 2045
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00024362139917695475,
+      "loss": 0.7304,
+      "step": 2050
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002432098765432099,
+      "loss": 0.7432,
+      "step": 2055
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.000242798353909465,
+      "loss": 0.6945,
+      "step": 2060
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00024238683127572017,
+      "loss": 0.7426,
+      "step": 2065
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00024197530864197533,
+      "loss": 0.7144,
+      "step": 2070
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00024156378600823048,
+      "loss": 0.7761,
+      "step": 2075
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0002411522633744856,
+      "loss": 0.7402,
+      "step": 2080
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00024074074074074075,
+      "loss": 0.7376,
+      "step": 2085
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0002403292181069959,
+      "loss": 0.7231,
+      "step": 2090
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023991769547325104,
+      "loss": 0.7461,
+      "step": 2095
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023950617283950617,
+      "loss": 0.7215,
+      "step": 2100
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023909465020576133,
+      "loss": 0.7419,
+      "step": 2105
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023868312757201646,
+      "loss": 0.7502,
+      "step": 2110
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023827160493827162,
+      "loss": 0.7294,
+      "step": 2115
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00023786008230452678,
+      "loss": 0.7904,
+      "step": 2120
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00023744855967078194,
+      "loss": 0.7418,
+      "step": 2125
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00023703703703703704,
+      "loss": 0.7371,
+      "step": 2130
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0002366255144032922,
+      "loss": 0.7384,
+      "step": 2135
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00023621399176954736,
+      "loss": 0.7552,
+      "step": 2140
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023580246913580246,
+      "loss": 0.7516,
+      "step": 2145
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023539094650205762,
+      "loss": 0.7303,
+      "step": 2150
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023497942386831278,
+      "loss": 0.7496,
+      "step": 2155
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023456790123456794,
+      "loss": 0.7135,
+      "step": 2160
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023415637860082304,
+      "loss": 0.7283,
+      "step": 2165
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0002337448559670782,
+      "loss": 0.751,
+      "step": 2170
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00023333333333333336,
+      "loss": 0.7183,
+      "step": 2175
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00023292181069958846,
+      "loss": 0.7242,
+      "step": 2180
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00023251028806584362,
+      "loss": 0.725,
+      "step": 2185
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00023209876543209878,
+      "loss": 0.753,
+      "step": 2190
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002316872427983539,
+      "loss": 0.7664,
+      "step": 2195
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00023127572016460904,
+      "loss": 0.7444,
+      "step": 2200
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002308641975308642,
+      "loss": 0.7226,
+      "step": 2205
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00023045267489711936,
+      "loss": 0.7653,
+      "step": 2210
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002300411522633745,
+      "loss": 0.7382,
+      "step": 2215
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00022962962962962965,
+      "loss": 0.7242,
+      "step": 2220
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002292181069958848,
+      "loss": 0.7215,
+      "step": 2225
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002288065843621399,
+      "loss": 0.724,
+      "step": 2230
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00022839506172839507,
+      "loss": 0.7439,
+      "step": 2235
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00022798353909465023,
+      "loss": 0.699,
+      "step": 2240
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002275720164609054,
+      "loss": 0.7602,
+      "step": 2245
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002271604938271605,
+      "loss": 0.7103,
+      "step": 2250
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00022674897119341565,
+      "loss": 0.7015,
+      "step": 2255
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002263374485596708,
+      "loss": 0.7404,
+      "step": 2260
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00022592592592592591,
+      "loss": 0.7127,
+      "step": 2265
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00022551440329218107,
+      "loss": 0.7299,
+      "step": 2270
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00022510288065843623,
+      "loss": 0.7174,
+      "step": 2275
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002246913580246914,
+      "loss": 0.7454,
+      "step": 2280
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002242798353909465,
+      "loss": 0.7159,
+      "step": 2285
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00022386831275720165,
+      "loss": 0.7263,
+      "step": 2290
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0002234567901234568,
+      "loss": 0.7148,
+      "step": 2295
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00022304526748971192,
+      "loss": 0.7447,
+      "step": 2300
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00022263374485596707,
+      "loss": 0.7326,
+      "step": 2305
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00022222222222222223,
+      "loss": 0.7428,
+      "step": 2310
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00022181069958847736,
+      "loss": 0.7587,
+      "step": 2315
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00022139917695473252,
+      "loss": 0.759,
+      "step": 2320
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00022098765432098768,
+      "loss": 0.7716,
+      "step": 2325
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002205761316872428,
+      "loss": 0.74,
+      "step": 2330
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00022016460905349794,
+      "loss": 0.7255,
+      "step": 2335
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002197530864197531,
+      "loss": 0.7547,
+      "step": 2340
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021934156378600826,
+      "loss": 0.7359,
+      "step": 2345
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021893004115226337,
+      "loss": 0.6987,
+      "step": 2350
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021851851851851852,
+      "loss": 0.7233,
+      "step": 2355
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021810699588477368,
+      "loss": 0.6945,
+      "step": 2360
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021769547325102884,
+      "loss": 0.7566,
+      "step": 2365
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00021728395061728395,
+      "loss": 0.728,
+      "step": 2370
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002168724279835391,
+      "loss": 0.7167,
+      "step": 2375
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00021646090534979426,
+      "loss": 0.7576,
+      "step": 2380
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00021604938271604937,
+      "loss": 0.7246,
+      "step": 2385
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00021563786008230453,
+      "loss": 0.755,
+      "step": 2390
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00021522633744855968,
+      "loss": 0.6983,
+      "step": 2395
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00021481481481481484,
+      "loss": 0.7369,
+      "step": 2400
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00021440329218106995,
+      "loss": 0.7074,
+      "step": 2405
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0002139917695473251,
+      "loss": 0.7317,
+      "step": 2410
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00021358024691358026,
+      "loss": 0.7086,
+      "step": 2415
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0002131687242798354,
+      "loss": 0.7356,
+      "step": 2420
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00021275720164609055,
+      "loss": 0.7652,
+      "step": 2425
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00021234567901234569,
+      "loss": 0.7488,
+      "step": 2430
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00021193415637860082,
+      "loss": 0.746,
+      "step": 2435
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00021152263374485598,
+      "loss": 0.7454,
+      "step": 2440
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00021111111111111113,
+      "loss": 0.72,
+      "step": 2445
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0002106995884773663,
+      "loss": 0.7299,
+      "step": 2450
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0002102880658436214,
+      "loss": 0.7436,
+      "step": 2455
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00020987654320987656,
+      "loss": 0.7068,
+      "step": 2460
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00020946502057613171,
+      "loss": 0.711,
+      "step": 2465
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00020905349794238682,
+      "loss": 0.7473,
+      "step": 2470
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00020864197530864198,
+      "loss": 0.7016,
+      "step": 2475
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00020823045267489714,
+      "loss": 0.7049,
+      "step": 2480
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002078189300411523,
+      "loss": 0.7268,
+      "step": 2485
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002074074074074074,
+      "loss": 0.7239,
+      "step": 2490
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020699588477366256,
+      "loss": 0.698,
+      "step": 2495
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020658436213991772,
+      "loss": 0.7573,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020617283950617282,
+      "loss": 0.7309,
+      "step": 2505
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020576131687242798,
+      "loss": 0.6628,
+      "step": 2510
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020534979423868314,
+      "loss": 0.656,
+      "step": 2515
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0002049382716049383,
+      "loss": 0.6737,
+      "step": 2520
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00020452674897119343,
+      "loss": 0.6903,
+      "step": 2525
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00020411522633744856,
+      "loss": 0.6674,
+      "step": 2530
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00020370370370370372,
+      "loss": 0.6507,
+      "step": 2535
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00020329218106995885,
+      "loss": 0.6948,
+      "step": 2540
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.000202880658436214,
+      "loss": 0.6662,
+      "step": 2545
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00020246913580246917,
+      "loss": 0.6624,
+      "step": 2550
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00020205761316872427,
+      "loss": 0.6791,
+      "step": 2555
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00020164609053497943,
+      "loss": 0.7088,
+      "step": 2560
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0002012345679012346,
+      "loss": 0.6796,
+      "step": 2565
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00020082304526748975,
+      "loss": 0.6601,
+      "step": 2570
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00020041152263374485,
+      "loss": 0.6865,
+      "step": 2575
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0002,
+      "loss": 0.6725,
+      "step": 2580
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00019958847736625514,
+      "loss": 0.6743,
+      "step": 2585
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0001991769547325103,
+      "loss": 0.6395,
+      "step": 2590
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00019876543209876543,
+      "loss": 0.6522,
+      "step": 2595
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0001983539094650206,
+      "loss": 0.6868,
+      "step": 2600
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00019794238683127572,
+      "loss": 0.6861,
+      "step": 2605
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00019753086419753085,
+      "loss": 0.6843,
+      "step": 2610
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.000197119341563786,
+      "loss": 0.6732,
+      "step": 2615
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00019670781893004114,
+      "loss": 0.6676,
+      "step": 2620
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0001962962962962963,
+      "loss": 0.6782,
+      "step": 2625
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00019588477366255146,
+      "loss": 0.6937,
+      "step": 2630
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0001954732510288066,
+      "loss": 0.6823,
+      "step": 2635
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00019506172839506175,
+      "loss": 0.6839,
+      "step": 2640
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019465020576131688,
+      "loss": 0.6351,
+      "step": 2645
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019423868312757204,
+      "loss": 0.7157,
+      "step": 2650
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019382716049382717,
+      "loss": 0.6591,
+      "step": 2655
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019341563786008233,
+      "loss": 0.6826,
+      "step": 2660
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019300411522633746,
+      "loss": 0.6732,
+      "step": 2665
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0001925925925925926,
+      "loss": 0.6795,
+      "step": 2670
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00019218106995884775,
+      "loss": 0.6845,
+      "step": 2675
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00019176954732510288,
+      "loss": 0.649,
+      "step": 2680
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00019135802469135804,
+      "loss": 0.6684,
+      "step": 2685
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00019094650205761317,
+      "loss": 0.6712,
+      "step": 2690
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00019053497942386833,
+      "loss": 0.6665,
+      "step": 2695
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00019012345679012346,
+      "loss": 0.6426,
+      "step": 2700
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0001897119341563786,
+      "loss": 0.6561,
+      "step": 2705
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00018930041152263375,
+      "loss": 0.6664,
+      "step": 2710
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00018888888888888888,
+      "loss": 0.6746,
+      "step": 2715
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018847736625514404,
+      "loss": 0.6497,
+      "step": 2720
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018806584362139917,
+      "loss": 0.6811,
+      "step": 2725
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018765432098765433,
+      "loss": 0.6608,
+      "step": 2730
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018724279835390946,
+      "loss": 0.6655,
+      "step": 2735
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018683127572016462,
+      "loss": 0.7014,
+      "step": 2740
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00018641975308641978,
+      "loss": 0.6889,
+      "step": 2745
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0001860082304526749,
+      "loss": 0.6805,
+      "step": 2750
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00018559670781893007,
+      "loss": 0.6629,
+      "step": 2755
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0001851851851851852,
+      "loss": 0.6593,
+      "step": 2760
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00018477366255144033,
+      "loss": 0.6902,
+      "step": 2765
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0001843621399176955,
+      "loss": 0.6777,
+      "step": 2770
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00018395061728395062,
+      "loss": 0.7127,
+      "step": 2775
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00018353909465020578,
+      "loss": 0.6551,
+      "step": 2780
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00018312757201646091,
+      "loss": 0.6703,
+      "step": 2785
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00018271604938271605,
+      "loss": 0.6776,
+      "step": 2790
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0001823045267489712,
+      "loss": 0.6574,
+      "step": 2795
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00018189300411522634,
+      "loss": 0.7154,
+      "step": 2800
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0001814814814814815,
+      "loss": 0.6749,
+      "step": 2805
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00018106995884773663,
+      "loss": 0.695,
+      "step": 2810
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00018065843621399178,
+      "loss": 0.6685,
+      "step": 2815
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00018024691358024692,
+      "loss": 0.642,
+      "step": 2820
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00017983539094650205,
+      "loss": 0.6873,
+      "step": 2825
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0001794238683127572,
+      "loss": 0.6506,
+      "step": 2830
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00017901234567901234,
+      "loss": 0.6695,
+      "step": 2835
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0001786008230452675,
+      "loss": 0.651,
+      "step": 2840
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00017818930041152265,
+      "loss": 0.6585,
+      "step": 2845
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 0.6717,
+      "step": 2850
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00017736625514403294,
+      "loss": 0.6524,
+      "step": 2855
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00017695473251028808,
+      "loss": 0.6679,
+      "step": 2860
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00017654320987654323,
+      "loss": 0.6719,
+      "step": 2865
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00017613168724279837,
+      "loss": 0.6662,
+      "step": 2870
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00017572016460905352,
+      "loss": 0.6624,
+      "step": 2875
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00017530864197530866,
+      "loss": 0.69,
+      "step": 2880
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0001748971193415638,
+      "loss": 0.6629,
+      "step": 2885
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00017448559670781895,
+      "loss": 0.6566,
+      "step": 2890
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00017407407407407408,
+      "loss": 0.6711,
+      "step": 2895
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00017366255144032924,
+      "loss": 0.6995,
+      "step": 2900
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00017325102880658437,
+      "loss": 0.6597,
+      "step": 2905
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0001728395061728395,
+      "loss": 0.6685,
+      "step": 2910
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00017242798353909466,
+      "loss": 0.6649,
+      "step": 2915
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0001720164609053498,
+      "loss": 0.6824,
+      "step": 2920
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00017160493827160495,
+      "loss": 0.6484,
+      "step": 2925
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00017119341563786008,
+      "loss": 0.6693,
+      "step": 2930
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00017078189300411524,
+      "loss": 0.629,
+      "step": 2935
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00017037037037037037,
+      "loss": 0.6588,
+      "step": 2940
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00016995884773662553,
+      "loss": 0.6771,
+      "step": 2945
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00016954732510288066,
+      "loss": 0.6773,
+      "step": 2950
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00016913580246913582,
+      "loss": 0.6307,
+      "step": 2955
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00016872427983539098,
+      "loss": 0.6809,
+      "step": 2960
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0001683127572016461,
+      "loss": 0.6748,
+      "step": 2965
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00016790123456790124,
+      "loss": 0.6708,
+      "step": 2970
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0001674897119341564,
+      "loss": 0.6754,
+      "step": 2975
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00016707818930041153,
+      "loss": 0.6676,
+      "step": 2980
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 0.6662,
+      "step": 2985
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00016625514403292182,
+      "loss": 0.6933,
+      "step": 2990
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00016584362139917695,
+      "loss": 0.6879,
+      "step": 2995
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0001654320987654321,
+      "loss": 0.6979,
+      "step": 3000
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00016502057613168724,
+      "loss": 0.657,
+      "step": 3005
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0001646090534979424,
+      "loss": 0.6704,
+      "step": 3010
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00016419753086419753,
+      "loss": 0.6394,
+      "step": 3015
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0001637860082304527,
+      "loss": 0.6594,
+      "step": 3020
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00016337448559670782,
+      "loss": 0.6584,
+      "step": 3025
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00016296296296296295,
+      "loss": 0.6593,
+      "step": 3030
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0001625514403292181,
+      "loss": 0.6538,
+      "step": 3035
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00016213991769547324,
+      "loss": 0.6572,
+      "step": 3040
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0001617283950617284,
+      "loss": 0.6999,
+      "step": 3045
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00016131687242798353,
+      "loss": 0.6658,
+      "step": 3050
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0001609053497942387,
+      "loss": 0.6809,
+      "step": 3055
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00016049382716049385,
+      "loss": 0.6685,
+      "step": 3060
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00016008230452674898,
+      "loss": 0.6532,
+      "step": 3065
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00015967078189300414,
+      "loss": 0.6644,
+      "step": 3070
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00015925925925925927,
+      "loss": 0.6721,
+      "step": 3075
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00015884773662551443,
+      "loss": 0.6569,
+      "step": 3080
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00015843621399176956,
+      "loss": 0.6832,
+      "step": 3085
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.0001580246913580247,
+      "loss": 0.6721,
+      "step": 3090
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00015761316872427985,
+      "loss": 0.6532,
+      "step": 3095
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00015720164609053498,
+      "loss": 0.6955,
+      "step": 3100
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00015679012345679014,
+      "loss": 0.6853,
+      "step": 3105
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00015637860082304527,
+      "loss": 0.6943,
+      "step": 3110
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0001559670781893004,
+      "loss": 0.6815,
+      "step": 3115
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 0.6972,
+      "step": 3120
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0001551440329218107,
+      "loss": 0.6959,
+      "step": 3125
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00015473251028806585,
+      "loss": 0.6795,
+      "step": 3130
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00015432098765432098,
+      "loss": 0.6352,
+      "step": 3135
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00015390946502057614,
+      "loss": 0.6601,
+      "step": 3140
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00015349794238683127,
+      "loss": 0.676,
+      "step": 3145
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0001530864197530864,
+      "loss": 0.6352,
+      "step": 3150
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00015267489711934156,
+      "loss": 0.6434,
+      "step": 3155
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00015226337448559672,
+      "loss": 0.673,
+      "step": 3160
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00015185185185185185,
+      "loss": 0.6963,
+      "step": 3165
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.000151440329218107,
+      "loss": 0.6643,
+      "step": 3170
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00015102880658436214,
+      "loss": 0.6757,
+      "step": 3175
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0001506172839506173,
+      "loss": 0.6681,
+      "step": 3180
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00015020576131687243,
+      "loss": 0.6935,
+      "step": 3185
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0001497942386831276,
+      "loss": 0.6894,
+      "step": 3190
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00014938271604938272,
+      "loss": 0.64,
+      "step": 3195
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00014897119341563788,
+      "loss": 0.6481,
+      "step": 3200
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00014855967078189301,
+      "loss": 0.6644,
+      "step": 3205
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00014814814814814815,
+      "loss": 0.6358,
+      "step": 3210
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0001477366255144033,
+      "loss": 0.6678,
+      "step": 3215
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00014732510288065844,
+      "loss": 0.6755,
+      "step": 3220
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0001469135802469136,
+      "loss": 0.6486,
+      "step": 3225
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00014650205761316873,
+      "loss": 0.666,
+      "step": 3230
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00014609053497942386,
+      "loss": 0.6689,
+      "step": 3235
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00014567901234567902,
+      "loss": 0.6737,
+      "step": 3240
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00014526748971193415,
+      "loss": 0.6659,
+      "step": 3245
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0001448559670781893,
+      "loss": 0.6744,
+      "step": 3250
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00014444444444444444,
+      "loss": 0.648,
+      "step": 3255
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0001440329218106996,
+      "loss": 0.6455,
+      "step": 3260
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00014362139917695473,
+      "loss": 0.659,
+      "step": 3265
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00014320987654320989,
+      "loss": 0.6519,
+      "step": 3270
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00014279835390946504,
+      "loss": 0.6972,
+      "step": 3275
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00014238683127572018,
+      "loss": 0.6592,
+      "step": 3280
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00014197530864197534,
+      "loss": 0.6757,
+      "step": 3285
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00014156378600823047,
+      "loss": 0.6684,
+      "step": 3290
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0001411522633744856,
+      "loss": 0.6754,
+      "step": 3295
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00014074074074074076,
+      "loss": 0.6738,
+      "step": 3300
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0001403292181069959,
+      "loss": 0.683,
+      "step": 3305
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00013991769547325105,
+      "loss": 0.6434,
+      "step": 3310
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00013950617283950618,
+      "loss": 0.6416,
+      "step": 3315
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00013909465020576134,
+      "loss": 0.6687,
+      "step": 3320
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00013868312757201647,
+      "loss": 0.6663,
+      "step": 3325
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0001382716049382716,
+      "loss": 0.7113,
+      "step": 3330
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00013786008230452676,
+      "loss": 0.6625,
+      "step": 3335
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0001374485596707819,
+      "loss": 0.6593,
+      "step": 3340
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00013703703703703705,
+      "loss": 0.6707,
+      "step": 3345
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00013662551440329218,
+      "loss": 0.6567,
+      "step": 3350
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0001362139917695473,
+      "loss": 0.6622,
+      "step": 3355
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00013580246913580247,
+      "loss": 0.6849,
+      "step": 3360
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0001353909465020576,
+      "loss": 0.657,
+      "step": 3365
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00013497942386831276,
+      "loss": 0.6452,
+      "step": 3370
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00013456790123456792,
+      "loss": 0.6486,
+      "step": 3375
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00013415637860082305,
+      "loss": 0.6737,
+      "step": 3380
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0001337448559670782,
+      "loss": 0.6793,
+      "step": 3385
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.6869,
+      "step": 3390
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0001329218106995885,
+      "loss": 0.6594,
+      "step": 3395
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00013251028806584363,
+      "loss": 0.6793,
+      "step": 3400
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0001320987654320988,
+      "loss": 0.6879,
+      "step": 3405
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00013168724279835392,
+      "loss": 0.695,
+      "step": 3410
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00013127572016460905,
+      "loss": 0.6648,
+      "step": 3415
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.0001308641975308642,
+      "loss": 0.6162,
+      "step": 3420
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00013045267489711934,
+      "loss": 0.642,
+      "step": 3425
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.0001300411522633745,
+      "loss": 0.6618,
+      "step": 3430
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00012962962962962963,
+      "loss": 0.6535,
+      "step": 3435
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00012921810699588476,
+      "loss": 0.6664,
+      "step": 3440
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00012880658436213992,
+      "loss": 0.6427,
+      "step": 3445
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00012839506172839505,
+      "loss": 0.6584,
+      "step": 3450
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0001279835390946502,
+      "loss": 0.657,
+      "step": 3455
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00012757201646090534,
+      "loss": 0.6494,
+      "step": 3460
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0001271604938271605,
+      "loss": 0.6553,
+      "step": 3465
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00012674897119341563,
+      "loss": 0.6755,
+      "step": 3470
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0001263374485596708,
+      "loss": 0.6599,
+      "step": 3475
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00012592592592592592,
+      "loss": 0.6564,
+      "step": 3480
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00012551440329218108,
+      "loss": 0.6526,
+      "step": 3485
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00012510288065843624,
+      "loss": 0.6439,
+      "step": 3490
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00012469135802469137,
+      "loss": 0.6459,
+      "step": 3495
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0001242798353909465,
+      "loss": 0.6573,
+      "step": 3500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 5010,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 1.408889273989464e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/training_args.bin b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..28c7b09fc2b3929abe4ad6608c7959f30a9a9d66
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43458f4cf6aeb211c730b848f93ab15f483827c314fb4dc1e79dd1f658b7dbc8
+size 5944
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/zero_to_fp32.py b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/zero_to_fp32.py
new file mode 100644
index 0000000000000000000000000000000000000000..c98caae31534368be22b67fc4ae906836c992a8d
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-3500/zero_to_fp32.py
@@ -0,0 +1,587 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel()
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file, tag=args.tag)
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/README.md b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..2aa897f8fa13b49ce76b1fa188781e5f726e7d13
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-2-7b-hf
+library_name: peft
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/adapter_config.json b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9c81a592f0ff08374a4f61f6003029070a8429ae
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/adapter_config.json
@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "mora_type": 1,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_mora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/adapter_model.safetensors b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d22cdd621e83ad395e1af5a384543e7b971d6fd1
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48e8835db17842835998b647d89832f3dd74b64f3e14569bf96e13e047ce0e17
+size 564342240
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d9583b2b269c306c15397f4eb5a853611322d895
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2da2f2f38b4229ce7515afd86b1a7684301d4c246b47946cb32ee1de4d9dcb77
+size 239914224
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/global_step4000/mp_rank_00_model_states.pt b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/global_step4000/mp_rank_00_model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b688ff0b9782b36367863a7bfb3018756f3348a5
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/global_step4000/mp_rank_00_model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d88c8e43b34628c750fad5bfea01690f590647573fb44741fe6ef91ac06d0ba2
+size 40303404
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/latest b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/latest
new file mode 100644
index 0000000000000000000000000000000000000000..641c40ce8d5e05e04a0840d69bcc5fac045a3fbd
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/latest
@@ -0,0 +1 @@
+global_step4000
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/rng_state.pth b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c1f34143f345a3a07de72bbfc65ff1e6940c3c90
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d71993ac3ca0024cc1313d07edd34ca691097104341c6887989afddf4094c8c
+size 14244
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/scheduler.pt b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a7dac2f28452436c134cb7ce69619bc8006d61a4
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dec7d2e204bbbd2ca4a34cd64f61177e1ab182018d934964c88d53bde6725f70
+size 1064
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/trainer_state.json b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..b088350b021852f4743bd90cdd4e8b93d166032f
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/trainer_state.json
@@ -0,0 +1,4821 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.5966569994074906,
+  "eval_steps": 500,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.3798,
+      "step": 5
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 1.3917,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4e-05,
+      "loss": 1.2862,
+      "step": 15
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 1.2046,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.0634,
+      "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8e-05,
+      "loss": 1.0273,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 1.0472,
+      "step": 35
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 1.0301,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00012,
+      "loss": 0.9335,
+      "step": 45
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.921,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00014666666666666666,
+      "loss": 0.9506,
+      "step": 55
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016,
+      "loss": 0.8876,
+      "step": 60
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00017333333333333334,
+      "loss": 0.9335,
+      "step": 65
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 0.8554,
+      "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0002,
+      "loss": 0.8537,
+      "step": 75
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00021333333333333333,
+      "loss": 0.9033,
+      "step": 80
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00022666666666666668,
+      "loss": 0.8203,
+      "step": 85
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00024,
+      "loss": 0.8611,
+      "step": 90
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00025333333333333333,
+      "loss": 0.8303,
+      "step": 95
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002666666666666667,
+      "loss": 0.8528,
+      "step": 100
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00028,
+      "loss": 0.8537,
+      "step": 105
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002933333333333333,
+      "loss": 0.8286,
+      "step": 110
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003066666666666667,
+      "loss": 0.8449,
+      "step": 115
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00032,
+      "loss": 0.8377,
+      "step": 120
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003333333333333334,
+      "loss": 0.8419,
+      "step": 125
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00034666666666666667,
+      "loss": 0.8265,
+      "step": 130
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00036,
+      "loss": 0.8037,
+      "step": 135
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003733333333333334,
+      "loss": 0.7924,
+      "step": 140
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00038666666666666667,
+      "loss": 0.8245,
+      "step": 145
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0004,
+      "loss": 0.8388,
+      "step": 150
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003995884773662552,
+      "loss": 0.8066,
+      "step": 155
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003991769547325103,
+      "loss": 0.8107,
+      "step": 160
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039876543209876544,
+      "loss": 0.8005,
+      "step": 165
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003983539094650206,
+      "loss": 0.7727,
+      "step": 170
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039794238683127576,
+      "loss": 0.8276,
+      "step": 175
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039753086419753086,
+      "loss": 0.8464,
+      "step": 180
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000397119341563786,
+      "loss": 0.8348,
+      "step": 185
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003967078189300412,
+      "loss": 0.8228,
+      "step": 190
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003962962962962963,
+      "loss": 0.8254,
+      "step": 195
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00039588477366255144,
+      "loss": 0.817,
+      "step": 200
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003954732510288066,
+      "loss": 0.8365,
+      "step": 205
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003950617283950617,
+      "loss": 0.793,
+      "step": 210
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00039465020576131686,
+      "loss": 0.8014,
+      "step": 215
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000394238683127572,
+      "loss": 0.8049,
+      "step": 220
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003938271604938272,
+      "loss": 0.7841,
+      "step": 225
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003934156378600823,
+      "loss": 0.7977,
+      "step": 230
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00039300411522633744,
+      "loss": 0.8299,
+      "step": 235
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003925925925925926,
+      "loss": 0.7729,
+      "step": 240
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00039218106995884776,
+      "loss": 0.8082,
+      "step": 245
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003917695473251029,
+      "loss": 0.8173,
+      "step": 250
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000391358024691358,
+      "loss": 0.8379,
+      "step": 255
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003909465020576132,
+      "loss": 0.7962,
+      "step": 260
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00039053497942386834,
+      "loss": 0.8067,
+      "step": 265
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003901234567901235,
+      "loss": 0.7915,
+      "step": 270
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00038971193415637866,
+      "loss": 0.7905,
+      "step": 275
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00038930041152263376,
+      "loss": 0.7862,
+      "step": 280
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003888888888888889,
+      "loss": 0.7709,
+      "step": 285
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003884773662551441,
+      "loss": 0.7773,
+      "step": 290
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00038806584362139924,
+      "loss": 0.8068,
+      "step": 295
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00038765432098765434,
+      "loss": 0.7962,
+      "step": 300
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003872427983539095,
+      "loss": 0.7894,
+      "step": 305
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00038683127572016466,
+      "loss": 0.7705,
+      "step": 310
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00038641975308641976,
+      "loss": 0.7882,
+      "step": 315
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003860082304526749,
+      "loss": 0.7865,
+      "step": 320
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003855967078189301,
+      "loss": 0.7939,
+      "step": 325
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003851851851851852,
+      "loss": 0.7724,
+      "step": 330
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00038477366255144034,
+      "loss": 0.7771,
+      "step": 335
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003843621399176955,
+      "loss": 0.7941,
+      "step": 340
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00038395061728395066,
+      "loss": 0.7822,
+      "step": 345
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00038353909465020577,
+      "loss": 0.8143,
+      "step": 350
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003831275720164609,
+      "loss": 0.795,
+      "step": 355
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003827160493827161,
+      "loss": 0.8049,
+      "step": 360
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003823045267489712,
+      "loss": 0.8309,
+      "step": 365
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00038189300411522635,
+      "loss": 0.8314,
+      "step": 370
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003814814814814815,
+      "loss": 0.801,
+      "step": 375
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00038106995884773666,
+      "loss": 0.8084,
+      "step": 380
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00038065843621399177,
+      "loss": 0.8129,
+      "step": 385
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003802469135802469,
+      "loss": 0.7859,
+      "step": 390
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003798353909465021,
+      "loss": 0.7874,
+      "step": 395
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003794238683127572,
+      "loss": 0.7548,
+      "step": 400
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00037901234567901235,
+      "loss": 0.8092,
+      "step": 405
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003786008230452675,
+      "loss": 0.8041,
+      "step": 410
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00037818930041152266,
+      "loss": 0.777,
+      "step": 415
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00037777777777777777,
+      "loss": 0.7699,
+      "step": 420
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00037736625514403293,
+      "loss": 0.781,
+      "step": 425
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003769547325102881,
+      "loss": 0.7504,
+      "step": 430
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003765432098765432,
+      "loss": 0.7974,
+      "step": 435
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037613168724279835,
+      "loss": 0.7663,
+      "step": 440
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003757201646090535,
+      "loss": 0.8013,
+      "step": 445
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037530864197530867,
+      "loss": 0.7453,
+      "step": 450
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037489711934156377,
+      "loss": 0.7425,
+      "step": 455
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037448559670781893,
+      "loss": 0.7582,
+      "step": 460
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003740740740740741,
+      "loss": 0.7801,
+      "step": 465
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00037366255144032925,
+      "loss": 0.7809,
+      "step": 470
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003732510288065844,
+      "loss": 0.7749,
+      "step": 475
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00037283950617283956,
+      "loss": 0.7807,
+      "step": 480
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00037242798353909467,
+      "loss": 0.7715,
+      "step": 485
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003720164609053498,
+      "loss": 0.7356,
+      "step": 490
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000371604938271605,
+      "loss": 0.7674,
+      "step": 495
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00037119341563786014,
+      "loss": 0.7542,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00037078189300411525,
+      "loss": 0.7583,
+      "step": 505
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003703703703703704,
+      "loss": 0.7767,
+      "step": 510
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036995884773662556,
+      "loss": 0.7853,
+      "step": 515
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036954732510288067,
+      "loss": 0.7733,
+      "step": 520
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036913580246913583,
+      "loss": 0.7758,
+      "step": 525
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.000368724279835391,
+      "loss": 0.7698,
+      "step": 530
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036831275720164614,
+      "loss": 0.7805,
+      "step": 535
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036790123456790125,
+      "loss": 0.7573,
+      "step": 540
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003674897119341564,
+      "loss": 0.7709,
+      "step": 545
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036707818930041157,
+      "loss": 0.7994,
+      "step": 550
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036666666666666667,
+      "loss": 0.7363,
+      "step": 555
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036625514403292183,
+      "loss": 0.7478,
+      "step": 560
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000365843621399177,
+      "loss": 0.8188,
+      "step": 565
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003654320987654321,
+      "loss": 0.7524,
+      "step": 570
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00036502057613168725,
+      "loss": 0.7319,
+      "step": 575
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003646090534979424,
+      "loss": 0.7915,
+      "step": 580
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00036419753086419757,
+      "loss": 0.7722,
+      "step": 585
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00036378600823045267,
+      "loss": 0.7842,
+      "step": 590
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00036337448559670783,
+      "loss": 0.7591,
+      "step": 595
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000362962962962963,
+      "loss": 0.7653,
+      "step": 600
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003625514403292181,
+      "loss": 0.7838,
+      "step": 605
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00036213991769547325,
+      "loss": 0.7937,
+      "step": 610
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003617283950617284,
+      "loss": 0.77,
+      "step": 615
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00036131687242798357,
+      "loss": 0.7899,
+      "step": 620
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003609053497942387,
+      "loss": 0.7815,
+      "step": 625
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00036049382716049383,
+      "loss": 0.7648,
+      "step": 630
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.000360082304526749,
+      "loss": 0.7716,
+      "step": 635
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003596707818930041,
+      "loss": 0.7708,
+      "step": 640
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00035925925925925925,
+      "loss": 0.7306,
+      "step": 645
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003588477366255144,
+      "loss": 0.8007,
+      "step": 650
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003584362139917695,
+      "loss": 0.7551,
+      "step": 655
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003580246913580247,
+      "loss": 0.754,
+      "step": 660
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00035761316872427983,
+      "loss": 0.7599,
+      "step": 665
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.000357201646090535,
+      "loss": 0.7637,
+      "step": 670
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00035679012345679015,
+      "loss": 0.7766,
+      "step": 675
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003563786008230453,
+      "loss": 0.7727,
+      "step": 680
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003559670781893004,
+      "loss": 0.7675,
+      "step": 685
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035555555555555557,
+      "loss": 0.7707,
+      "step": 690
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035514403292181073,
+      "loss": 0.7221,
+      "step": 695
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003547325102880659,
+      "loss": 0.7335,
+      "step": 700
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035432098765432105,
+      "loss": 0.781,
+      "step": 705
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035390946502057615,
+      "loss": 0.7845,
+      "step": 710
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003534979423868313,
+      "loss": 0.7467,
+      "step": 715
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00035308641975308647,
+      "loss": 0.7735,
+      "step": 720
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003526748971193416,
+      "loss": 0.7368,
+      "step": 725
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00035226337448559673,
+      "loss": 0.7678,
+      "step": 730
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003518518518518519,
+      "loss": 0.7756,
+      "step": 735
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00035144032921810705,
+      "loss": 0.7635,
+      "step": 740
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00035102880658436215,
+      "loss": 0.7757,
+      "step": 745
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003506172839506173,
+      "loss": 0.7442,
+      "step": 750
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00035020576131687247,
+      "loss": 0.7584,
+      "step": 755
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003497942386831276,
+      "loss": 0.8333,
+      "step": 760
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00034938271604938273,
+      "loss": 0.7459,
+      "step": 765
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003489711934156379,
+      "loss": 0.7499,
+      "step": 770
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.000348559670781893,
+      "loss": 0.7571,
+      "step": 775
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00034814814814814816,
+      "loss": 0.7243,
+      "step": 780
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003477366255144033,
+      "loss": 0.7443,
+      "step": 785
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003473251028806585,
+      "loss": 0.7759,
+      "step": 790
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003469135802469136,
+      "loss": 0.7452,
+      "step": 795
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00034650205761316874,
+      "loss": 0.7578,
+      "step": 800
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003460905349794239,
+      "loss": 0.7634,
+      "step": 805
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.000345679012345679,
+      "loss": 0.7925,
+      "step": 810
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00034526748971193416,
+      "loss": 0.7966,
+      "step": 815
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003448559670781893,
+      "loss": 0.7601,
+      "step": 820
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003444444444444445,
+      "loss": 0.7617,
+      "step": 825
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003440329218106996,
+      "loss": 0.7526,
+      "step": 830
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00034362139917695474,
+      "loss": 0.7297,
+      "step": 835
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003432098765432099,
+      "loss": 0.7549,
+      "step": 840
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.000342798353909465,
+      "loss": 0.7517,
+      "step": 845
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00034238683127572016,
+      "loss": 0.7626,
+      "step": 850
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003419753086419753,
+      "loss": 0.7987,
+      "step": 855
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003415637860082305,
+      "loss": 0.7573,
+      "step": 860
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003411522633744856,
+      "loss": 0.8367,
+      "step": 865
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00034074074074074074,
+      "loss": 0.7258,
+      "step": 870
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003403292181069959,
+      "loss": 0.7632,
+      "step": 875
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00033991769547325106,
+      "loss": 0.7379,
+      "step": 880
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00033950617283950616,
+      "loss": 0.7529,
+      "step": 885
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003390946502057613,
+      "loss": 0.7391,
+      "step": 890
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003386831275720165,
+      "loss": 0.8061,
+      "step": 895
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00033827160493827164,
+      "loss": 0.7288,
+      "step": 900
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003378600823045268,
+      "loss": 0.7493,
+      "step": 905
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00033744855967078195,
+      "loss": 0.7702,
+      "step": 910
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00033703703703703706,
+      "loss": 0.7538,
+      "step": 915
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003366255144032922,
+      "loss": 0.728,
+      "step": 920
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003362139917695474,
+      "loss": 0.7776,
+      "step": 925
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003358024691358025,
+      "loss": 0.7883,
+      "step": 930
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00033539094650205764,
+      "loss": 0.7471,
+      "step": 935
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003349794238683128,
+      "loss": 0.7464,
+      "step": 940
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00033456790123456795,
+      "loss": 0.7885,
+      "step": 945
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00033415637860082306,
+      "loss": 0.7509,
+      "step": 950
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003337448559670782,
+      "loss": 0.7681,
+      "step": 955
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003333333333333334,
+      "loss": 0.8246,
+      "step": 960
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003329218106995885,
+      "loss": 0.7604,
+      "step": 965
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00033251028806584364,
+      "loss": 0.7755,
+      "step": 970
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003320987654320988,
+      "loss": 0.7641,
+      "step": 975
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003316872427983539,
+      "loss": 0.7708,
+      "step": 980
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00033127572016460906,
+      "loss": 0.7936,
+      "step": 985
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003308641975308642,
+      "loss": 0.7641,
+      "step": 990
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003304526748971194,
+      "loss": 0.7479,
+      "step": 995
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003300411522633745,
+      "loss": 0.7547,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00032962962962962964,
+      "loss": 0.762,
+      "step": 1005
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003292181069958848,
+      "loss": 0.7472,
+      "step": 1010
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003288065843621399,
+      "loss": 0.7542,
+      "step": 1015
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00032839506172839506,
+      "loss": 0.7669,
+      "step": 1020
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003279835390946502,
+      "loss": 0.7812,
+      "step": 1025
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003275720164609054,
+      "loss": 0.7273,
+      "step": 1030
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003271604938271605,
+      "loss": 0.7822,
+      "step": 1035
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00032674897119341564,
+      "loss": 0.7337,
+      "step": 1040
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003263374485596708,
+      "loss": 0.7566,
+      "step": 1045
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003259259259259259,
+      "loss": 0.7377,
+      "step": 1050
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00032551440329218106,
+      "loss": 0.7856,
+      "step": 1055
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003251028806584362,
+      "loss": 0.7981,
+      "step": 1060
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003246913580246914,
+      "loss": 0.7505,
+      "step": 1065
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003242798353909465,
+      "loss": 0.7549,
+      "step": 1070
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00032386831275720164,
+      "loss": 0.7306,
+      "step": 1075
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003234567901234568,
+      "loss": 0.7343,
+      "step": 1080
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003230452674897119,
+      "loss": 0.738,
+      "step": 1085
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00032263374485596707,
+      "loss": 0.7655,
+      "step": 1090
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003222222222222222,
+      "loss": 0.7706,
+      "step": 1095
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003218106995884774,
+      "loss": 0.7512,
+      "step": 1100
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00032139917695473254,
+      "loss": 0.7549,
+      "step": 1105
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003209876543209877,
+      "loss": 0.7839,
+      "step": 1110
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003205761316872428,
+      "loss": 0.7511,
+      "step": 1115
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00032016460905349796,
+      "loss": 0.769,
+      "step": 1120
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003197530864197531,
+      "loss": 0.7685,
+      "step": 1125
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003193415637860083,
+      "loss": 0.7489,
+      "step": 1130
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003189300411522634,
+      "loss": 0.808,
+      "step": 1135
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00031851851851851854,
+      "loss": 0.7654,
+      "step": 1140
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003181069958847737,
+      "loss": 0.7845,
+      "step": 1145
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00031769547325102886,
+      "loss": 0.7886,
+      "step": 1150
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00031728395061728396,
+      "loss": 0.7318,
+      "step": 1155
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003168724279835391,
+      "loss": 0.7231,
+      "step": 1160
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003164609053497943,
+      "loss": 0.7471,
+      "step": 1165
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003160493827160494,
+      "loss": 0.7424,
+      "step": 1170
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00031563786008230454,
+      "loss": 0.7249,
+      "step": 1175
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003152263374485597,
+      "loss": 0.7419,
+      "step": 1180
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00031481481481481486,
+      "loss": 0.7567,
+      "step": 1185
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00031440329218106997,
+      "loss": 0.7707,
+      "step": 1190
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003139917695473251,
+      "loss": 0.7473,
+      "step": 1195
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003135802469135803,
+      "loss": 0.7222,
+      "step": 1200
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003131687242798354,
+      "loss": 0.7383,
+      "step": 1205
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00031275720164609055,
+      "loss": 0.7712,
+      "step": 1210
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003123456790123457,
+      "loss": 0.7602,
+      "step": 1215
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003119341563786008,
+      "loss": 0.7741,
+      "step": 1220
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00031152263374485597,
+      "loss": 0.7428,
+      "step": 1225
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003111111111111111,
+      "loss": 0.7605,
+      "step": 1230
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003106995884773663,
+      "loss": 0.7255,
+      "step": 1235
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003102880658436214,
+      "loss": 0.7468,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00030987654320987655,
+      "loss": 0.7961,
+      "step": 1245
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003094650205761317,
+      "loss": 0.7208,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003090534979423868,
+      "loss": 0.7331,
+      "step": 1255
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00030864197530864197,
+      "loss": 0.7371,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00030823045267489713,
+      "loss": 0.7206,
+      "step": 1265
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003078189300411523,
+      "loss": 0.7617,
+      "step": 1270
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003074074074074074,
+      "loss": 0.7652,
+      "step": 1275
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00030699588477366255,
+      "loss": 0.7635,
+      "step": 1280
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003065843621399177,
+      "loss": 0.7445,
+      "step": 1285
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003061728395061728,
+      "loss": 0.7717,
+      "step": 1290
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030576131687242797,
+      "loss": 0.7535,
+      "step": 1295
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030534979423868313,
+      "loss": 0.7677,
+      "step": 1300
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003049382716049383,
+      "loss": 0.8131,
+      "step": 1305
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030452674897119345,
+      "loss": 0.7754,
+      "step": 1310
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030411522633744855,
+      "loss": 0.76,
+      "step": 1315
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003037037037037037,
+      "loss": 0.7558,
+      "step": 1320
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00030329218106995887,
+      "loss": 0.7604,
+      "step": 1325
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.000302880658436214,
+      "loss": 0.7716,
+      "step": 1330
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003024691358024692,
+      "loss": 0.7669,
+      "step": 1335
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003020576131687243,
+      "loss": 0.7469,
+      "step": 1340
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030164609053497945,
+      "loss": 0.7511,
+      "step": 1345
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003012345679012346,
+      "loss": 0.7483,
+      "step": 1350
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030082304526748976,
+      "loss": 0.7509,
+      "step": 1355
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030041152263374487,
+      "loss": 0.7249,
+      "step": 1360
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.7289,
+      "step": 1365
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002995884773662552,
+      "loss": 0.7605,
+      "step": 1370
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002991769547325103,
+      "loss": 0.7185,
+      "step": 1375
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00029876543209876545,
+      "loss": 0.6974,
+      "step": 1380
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002983539094650206,
+      "loss": 0.7234,
+      "step": 1385
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00029794238683127577,
+      "loss": 0.7506,
+      "step": 1390
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029753086419753087,
+      "loss": 0.7524,
+      "step": 1395
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029711934156378603,
+      "loss": 0.7641,
+      "step": 1400
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002967078189300412,
+      "loss": 0.6967,
+      "step": 1405
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002962962962962963,
+      "loss": 0.735,
+      "step": 1410
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029588477366255145,
+      "loss": 0.7685,
+      "step": 1415
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002954732510288066,
+      "loss": 0.758,
+      "step": 1420
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002950617283950617,
+      "loss": 0.763,
+      "step": 1425
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00029465020576131687,
+      "loss": 0.712,
+      "step": 1430
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00029423868312757203,
+      "loss": 0.7236,
+      "step": 1435
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002938271604938272,
+      "loss": 0.7732,
+      "step": 1440
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002934156378600823,
+      "loss": 0.7689,
+      "step": 1445
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00029300411522633745,
+      "loss": 0.7352,
+      "step": 1450
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002925925925925926,
+      "loss": 0.7711,
+      "step": 1455
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002921810699588477,
+      "loss": 0.7549,
+      "step": 1460
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002917695473251029,
+      "loss": 0.7804,
+      "step": 1465
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00029135802469135803,
+      "loss": 0.7478,
+      "step": 1470
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002909465020576132,
+      "loss": 0.7801,
+      "step": 1475
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002905349794238683,
+      "loss": 0.7544,
+      "step": 1480
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00029012345679012345,
+      "loss": 0.7546,
+      "step": 1485
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002897119341563786,
+      "loss": 0.7648,
+      "step": 1490
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002893004115226337,
+      "loss": 0.7468,
+      "step": 1495
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002888888888888889,
+      "loss": 0.7434,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00028847736625514403,
+      "loss": 0.7348,
+      "step": 1505
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002880658436213992,
+      "loss": 0.7515,
+      "step": 1510
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00028765432098765435,
+      "loss": 0.7345,
+      "step": 1515
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00028724279835390946,
+      "loss": 0.7701,
+      "step": 1520
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002868312757201646,
+      "loss": 0.7472,
+      "step": 1525
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00028641975308641977,
+      "loss": 0.7075,
+      "step": 1530
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00028600823045267493,
+      "loss": 0.7483,
+      "step": 1535
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002855967078189301,
+      "loss": 0.712,
+      "step": 1540
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002851851851851852,
+      "loss": 0.7484,
+      "step": 1545
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00028477366255144035,
+      "loss": 0.7471,
+      "step": 1550
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002843621399176955,
+      "loss": 0.7462,
+      "step": 1555
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00028395061728395067,
+      "loss": 0.7371,
+      "step": 1560
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002835390946502058,
+      "loss": 0.7753,
+      "step": 1565
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00028312757201646093,
+      "loss": 0.7374,
+      "step": 1570
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002827160493827161,
+      "loss": 0.7328,
+      "step": 1575
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002823045267489712,
+      "loss": 0.7159,
+      "step": 1580
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00028189300411522635,
+      "loss": 0.7594,
+      "step": 1585
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002814814814814815,
+      "loss": 0.7215,
+      "step": 1590
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00028106995884773667,
+      "loss": 0.7398,
+      "step": 1595
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002806584362139918,
+      "loss": 0.773,
+      "step": 1600
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00028024691358024693,
+      "loss": 0.7584,
+      "step": 1605
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002798353909465021,
+      "loss": 0.7117,
+      "step": 1610
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002794238683127572,
+      "loss": 0.7471,
+      "step": 1615
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00027901234567901236,
+      "loss": 0.7443,
+      "step": 1620
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002786008230452675,
+      "loss": 0.7292,
+      "step": 1625
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002781893004115227,
+      "loss": 0.7716,
+      "step": 1630
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 0.763,
+      "step": 1635
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00027736625514403294,
+      "loss": 0.7408,
+      "step": 1640
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002769547325102881,
+      "loss": 0.7403,
+      "step": 1645
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002765432098765432,
+      "loss": 0.7508,
+      "step": 1650
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00027613168724279836,
+      "loss": 0.7687,
+      "step": 1655
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002757201646090535,
+      "loss": 0.7305,
+      "step": 1660
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002753086419753086,
+      "loss": 0.7165,
+      "step": 1665
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002748971193415638,
+      "loss": 0.8,
+      "step": 1670
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00027448559670781894,
+      "loss": 0.7357,
+      "step": 1675
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002740740740740741,
+      "loss": 0.7988,
+      "step": 1680
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002736625514403292,
+      "loss": 0.7559,
+      "step": 1685
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00027325102880658436,
+      "loss": 0.712,
+      "step": 1690
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002728395061728395,
+      "loss": 0.7486,
+      "step": 1695
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002724279835390946,
+      "loss": 0.7388,
+      "step": 1700
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002720164609053498,
+      "loss": 0.7441,
+      "step": 1705
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00027160493827160494,
+      "loss": 0.7547,
+      "step": 1710
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002711934156378601,
+      "loss": 0.7229,
+      "step": 1715
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002707818930041152,
+      "loss": 0.7383,
+      "step": 1720
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00027037037037037036,
+      "loss": 0.7606,
+      "step": 1725
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002699588477366255,
+      "loss": 0.7529,
+      "step": 1730
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002695473251028807,
+      "loss": 0.752,
+      "step": 1735
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00026913580246913584,
+      "loss": 0.7342,
+      "step": 1740
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.000268724279835391,
+      "loss": 0.7308,
+      "step": 1745
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002683127572016461,
+      "loss": 0.6915,
+      "step": 1750
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00026790123456790126,
+      "loss": 0.7344,
+      "step": 1755
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002674897119341564,
+      "loss": 0.7426,
+      "step": 1760
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002670781893004116,
+      "loss": 0.7088,
+      "step": 1765
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002666666666666667,
+      "loss": 0.7241,
+      "step": 1770
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00026625514403292184,
+      "loss": 0.7552,
+      "step": 1775
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.000265843621399177,
+      "loss": 0.7477,
+      "step": 1780
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002654320987654321,
+      "loss": 0.7115,
+      "step": 1785
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00026502057613168726,
+      "loss": 0.7538,
+      "step": 1790
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002646090534979424,
+      "loss": 0.7321,
+      "step": 1795
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002641975308641976,
+      "loss": 0.7212,
+      "step": 1800
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002637860082304527,
+      "loss": 0.747,
+      "step": 1805
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00026337448559670784,
+      "loss": 0.7606,
+      "step": 1810
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.000262962962962963,
+      "loss": 0.7344,
+      "step": 1815
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002625514403292181,
+      "loss": 0.7783,
+      "step": 1820
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00026213991769547326,
+      "loss": 0.7556,
+      "step": 1825
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002617283950617284,
+      "loss": 0.7585,
+      "step": 1830
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002613168724279836,
+      "loss": 0.7359,
+      "step": 1835
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002609053497942387,
+      "loss": 0.7185,
+      "step": 1840
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00026049382716049384,
+      "loss": 0.7573,
+      "step": 1845
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.000260082304526749,
+      "loss": 0.7619,
+      "step": 1850
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002596707818930041,
+      "loss": 0.7611,
+      "step": 1855
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00025925925925925926,
+      "loss": 0.7647,
+      "step": 1860
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002588477366255144,
+      "loss": 0.7398,
+      "step": 1865
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002584362139917695,
+      "loss": 0.7683,
+      "step": 1870
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002580246913580247,
+      "loss": 0.7817,
+      "step": 1875
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00025761316872427984,
+      "loss": 0.742,
+      "step": 1880
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.000257201646090535,
+      "loss": 0.7509,
+      "step": 1885
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002567901234567901,
+      "loss": 0.7058,
+      "step": 1890
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00025637860082304526,
+      "loss": 0.7635,
+      "step": 1895
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002559670781893004,
+      "loss": 0.734,
+      "step": 1900
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00025555555555555553,
+      "loss": 0.7416,
+      "step": 1905
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002551440329218107,
+      "loss": 0.7071,
+      "step": 1910
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00025473251028806584,
+      "loss": 0.7275,
+      "step": 1915
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.000254320987654321,
+      "loss": 0.7413,
+      "step": 1920
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002539094650205761,
+      "loss": 0.7703,
+      "step": 1925
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00025349794238683127,
+      "loss": 0.7331,
+      "step": 1930
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002530864197530864,
+      "loss": 0.7251,
+      "step": 1935
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002526748971193416,
+      "loss": 0.7341,
+      "step": 1940
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00025226337448559674,
+      "loss": 0.7079,
+      "step": 1945
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00025185185185185185,
+      "loss": 0.7615,
+      "step": 1950
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.000251440329218107,
+      "loss": 0.7144,
+      "step": 1955
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00025102880658436216,
+      "loss": 0.7527,
+      "step": 1960
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0002506172839506173,
+      "loss": 0.7327,
+      "step": 1965
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002502057613168725,
+      "loss": 0.7173,
+      "step": 1970
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002497942386831276,
+      "loss": 0.7239,
+      "step": 1975
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00024938271604938274,
+      "loss": 0.7442,
+      "step": 1980
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002489711934156379,
+      "loss": 0.7396,
+      "step": 1985
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.000248559670781893,
+      "loss": 0.7365,
+      "step": 1990
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00024814814814814816,
+      "loss": 0.7037,
+      "step": 1995
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002477366255144033,
+      "loss": 0.721,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002473251028806585,
+      "loss": 0.7353,
+      "step": 2005
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002469135802469136,
+      "loss": 0.7648,
+      "step": 2010
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00024650205761316874,
+      "loss": 0.7445,
+      "step": 2015
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0002460905349794239,
+      "loss": 0.7664,
+      "step": 2020
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.000245679012345679,
+      "loss": 0.7202,
+      "step": 2025
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00024526748971193417,
+      "loss": 0.7147,
+      "step": 2030
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0002448559670781893,
+      "loss": 0.722,
+      "step": 2035
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0002444444444444445,
+      "loss": 0.7539,
+      "step": 2040
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002440329218106996,
+      "loss": 0.7681,
+      "step": 2045
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00024362139917695475,
+      "loss": 0.7304,
+      "step": 2050
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002432098765432099,
+      "loss": 0.7432,
+      "step": 2055
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.000242798353909465,
+      "loss": 0.6945,
+      "step": 2060
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00024238683127572017,
+      "loss": 0.7426,
+      "step": 2065
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00024197530864197533,
+      "loss": 0.7144,
+      "step": 2070
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00024156378600823048,
+      "loss": 0.7761,
+      "step": 2075
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0002411522633744856,
+      "loss": 0.7402,
+      "step": 2080
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00024074074074074075,
+      "loss": 0.7376,
+      "step": 2085
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0002403292181069959,
+      "loss": 0.7231,
+      "step": 2090
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023991769547325104,
+      "loss": 0.7461,
+      "step": 2095
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023950617283950617,
+      "loss": 0.7215,
+      "step": 2100
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023909465020576133,
+      "loss": 0.7419,
+      "step": 2105
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023868312757201646,
+      "loss": 0.7502,
+      "step": 2110
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023827160493827162,
+      "loss": 0.7294,
+      "step": 2115
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00023786008230452678,
+      "loss": 0.7904,
+      "step": 2120
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00023744855967078194,
+      "loss": 0.7418,
+      "step": 2125
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00023703703703703704,
+      "loss": 0.7371,
+      "step": 2130
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0002366255144032922,
+      "loss": 0.7384,
+      "step": 2135
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00023621399176954736,
+      "loss": 0.7552,
+      "step": 2140
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023580246913580246,
+      "loss": 0.7516,
+      "step": 2145
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023539094650205762,
+      "loss": 0.7303,
+      "step": 2150
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023497942386831278,
+      "loss": 0.7496,
+      "step": 2155
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023456790123456794,
+      "loss": 0.7135,
+      "step": 2160
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023415637860082304,
+      "loss": 0.7283,
+      "step": 2165
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0002337448559670782,
+      "loss": 0.751,
+      "step": 2170
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00023333333333333336,
+      "loss": 0.7183,
+      "step": 2175
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00023292181069958846,
+      "loss": 0.7242,
+      "step": 2180
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00023251028806584362,
+      "loss": 0.725,
+      "step": 2185
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00023209876543209878,
+      "loss": 0.753,
+      "step": 2190
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002316872427983539,
+      "loss": 0.7664,
+      "step": 2195
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00023127572016460904,
+      "loss": 0.7444,
+      "step": 2200
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002308641975308642,
+      "loss": 0.7226,
+      "step": 2205
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00023045267489711936,
+      "loss": 0.7653,
+      "step": 2210
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002300411522633745,
+      "loss": 0.7382,
+      "step": 2215
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00022962962962962965,
+      "loss": 0.7242,
+      "step": 2220
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002292181069958848,
+      "loss": 0.7215,
+      "step": 2225
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002288065843621399,
+      "loss": 0.724,
+      "step": 2230
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00022839506172839507,
+      "loss": 0.7439,
+      "step": 2235
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00022798353909465023,
+      "loss": 0.699,
+      "step": 2240
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002275720164609054,
+      "loss": 0.7602,
+      "step": 2245
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002271604938271605,
+      "loss": 0.7103,
+      "step": 2250
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00022674897119341565,
+      "loss": 0.7015,
+      "step": 2255
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002263374485596708,
+      "loss": 0.7404,
+      "step": 2260
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00022592592592592591,
+      "loss": 0.7127,
+      "step": 2265
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00022551440329218107,
+      "loss": 0.7299,
+      "step": 2270
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00022510288065843623,
+      "loss": 0.7174,
+      "step": 2275
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002246913580246914,
+      "loss": 0.7454,
+      "step": 2280
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002242798353909465,
+      "loss": 0.7159,
+      "step": 2285
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00022386831275720165,
+      "loss": 0.7263,
+      "step": 2290
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0002234567901234568,
+      "loss": 0.7148,
+      "step": 2295
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00022304526748971192,
+      "loss": 0.7447,
+      "step": 2300
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00022263374485596707,
+      "loss": 0.7326,
+      "step": 2305
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00022222222222222223,
+      "loss": 0.7428,
+      "step": 2310
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00022181069958847736,
+      "loss": 0.7587,
+      "step": 2315
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00022139917695473252,
+      "loss": 0.759,
+      "step": 2320
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00022098765432098768,
+      "loss": 0.7716,
+      "step": 2325
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002205761316872428,
+      "loss": 0.74,
+      "step": 2330
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00022016460905349794,
+      "loss": 0.7255,
+      "step": 2335
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002197530864197531,
+      "loss": 0.7547,
+      "step": 2340
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021934156378600826,
+      "loss": 0.7359,
+      "step": 2345
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021893004115226337,
+      "loss": 0.6987,
+      "step": 2350
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021851851851851852,
+      "loss": 0.7233,
+      "step": 2355
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021810699588477368,
+      "loss": 0.6945,
+      "step": 2360
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021769547325102884,
+      "loss": 0.7566,
+      "step": 2365
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00021728395061728395,
+      "loss": 0.728,
+      "step": 2370
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002168724279835391,
+      "loss": 0.7167,
+      "step": 2375
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00021646090534979426,
+      "loss": 0.7576,
+      "step": 2380
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00021604938271604937,
+      "loss": 0.7246,
+      "step": 2385
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00021563786008230453,
+      "loss": 0.755,
+      "step": 2390
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00021522633744855968,
+      "loss": 0.6983,
+      "step": 2395
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00021481481481481484,
+      "loss": 0.7369,
+      "step": 2400
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00021440329218106995,
+      "loss": 0.7074,
+      "step": 2405
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0002139917695473251,
+      "loss": 0.7317,
+      "step": 2410
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00021358024691358026,
+      "loss": 0.7086,
+      "step": 2415
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0002131687242798354,
+      "loss": 0.7356,
+      "step": 2420
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00021275720164609055,
+      "loss": 0.7652,
+      "step": 2425
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00021234567901234569,
+      "loss": 0.7488,
+      "step": 2430
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00021193415637860082,
+      "loss": 0.746,
+      "step": 2435
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00021152263374485598,
+      "loss": 0.7454,
+      "step": 2440
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00021111111111111113,
+      "loss": 0.72,
+      "step": 2445
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0002106995884773663,
+      "loss": 0.7299,
+      "step": 2450
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0002102880658436214,
+      "loss": 0.7436,
+      "step": 2455
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00020987654320987656,
+      "loss": 0.7068,
+      "step": 2460
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00020946502057613171,
+      "loss": 0.711,
+      "step": 2465
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00020905349794238682,
+      "loss": 0.7473,
+      "step": 2470
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00020864197530864198,
+      "loss": 0.7016,
+      "step": 2475
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00020823045267489714,
+      "loss": 0.7049,
+      "step": 2480
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002078189300411523,
+      "loss": 0.7268,
+      "step": 2485
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002074074074074074,
+      "loss": 0.7239,
+      "step": 2490
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020699588477366256,
+      "loss": 0.698,
+      "step": 2495
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020658436213991772,
+      "loss": 0.7573,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020617283950617282,
+      "loss": 0.7309,
+      "step": 2505
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020576131687242798,
+      "loss": 0.6628,
+      "step": 2510
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020534979423868314,
+      "loss": 0.656,
+      "step": 2515
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0002049382716049383,
+      "loss": 0.6737,
+      "step": 2520
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00020452674897119343,
+      "loss": 0.6903,
+      "step": 2525
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00020411522633744856,
+      "loss": 0.6674,
+      "step": 2530
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00020370370370370372,
+      "loss": 0.6507,
+      "step": 2535
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00020329218106995885,
+      "loss": 0.6948,
+      "step": 2540
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.000202880658436214,
+      "loss": 0.6662,
+      "step": 2545
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00020246913580246917,
+      "loss": 0.6624,
+      "step": 2550
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00020205761316872427,
+      "loss": 0.6791,
+      "step": 2555
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00020164609053497943,
+      "loss": 0.7088,
+      "step": 2560
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0002012345679012346,
+      "loss": 0.6796,
+      "step": 2565
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00020082304526748975,
+      "loss": 0.6601,
+      "step": 2570
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00020041152263374485,
+      "loss": 0.6865,
+      "step": 2575
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0002,
+      "loss": 0.6725,
+      "step": 2580
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00019958847736625514,
+      "loss": 0.6743,
+      "step": 2585
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0001991769547325103,
+      "loss": 0.6395,
+      "step": 2590
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00019876543209876543,
+      "loss": 0.6522,
+      "step": 2595
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0001983539094650206,
+      "loss": 0.6868,
+      "step": 2600
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00019794238683127572,
+      "loss": 0.6861,
+      "step": 2605
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00019753086419753085,
+      "loss": 0.6843,
+      "step": 2610
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.000197119341563786,
+      "loss": 0.6732,
+      "step": 2615
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00019670781893004114,
+      "loss": 0.6676,
+      "step": 2620
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0001962962962962963,
+      "loss": 0.6782,
+      "step": 2625
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00019588477366255146,
+      "loss": 0.6937,
+      "step": 2630
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0001954732510288066,
+      "loss": 0.6823,
+      "step": 2635
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00019506172839506175,
+      "loss": 0.6839,
+      "step": 2640
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019465020576131688,
+      "loss": 0.6351,
+      "step": 2645
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019423868312757204,
+      "loss": 0.7157,
+      "step": 2650
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019382716049382717,
+      "loss": 0.6591,
+      "step": 2655
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019341563786008233,
+      "loss": 0.6826,
+      "step": 2660
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019300411522633746,
+      "loss": 0.6732,
+      "step": 2665
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0001925925925925926,
+      "loss": 0.6795,
+      "step": 2670
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00019218106995884775,
+      "loss": 0.6845,
+      "step": 2675
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00019176954732510288,
+      "loss": 0.649,
+      "step": 2680
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00019135802469135804,
+      "loss": 0.6684,
+      "step": 2685
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00019094650205761317,
+      "loss": 0.6712,
+      "step": 2690
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00019053497942386833,
+      "loss": 0.6665,
+      "step": 2695
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00019012345679012346,
+      "loss": 0.6426,
+      "step": 2700
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0001897119341563786,
+      "loss": 0.6561,
+      "step": 2705
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00018930041152263375,
+      "loss": 0.6664,
+      "step": 2710
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00018888888888888888,
+      "loss": 0.6746,
+      "step": 2715
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018847736625514404,
+      "loss": 0.6497,
+      "step": 2720
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018806584362139917,
+      "loss": 0.6811,
+      "step": 2725
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018765432098765433,
+      "loss": 0.6608,
+      "step": 2730
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018724279835390946,
+      "loss": 0.6655,
+      "step": 2735
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018683127572016462,
+      "loss": 0.7014,
+      "step": 2740
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00018641975308641978,
+      "loss": 0.6889,
+      "step": 2745
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0001860082304526749,
+      "loss": 0.6805,
+      "step": 2750
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00018559670781893007,
+      "loss": 0.6629,
+      "step": 2755
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0001851851851851852,
+      "loss": 0.6593,
+      "step": 2760
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00018477366255144033,
+      "loss": 0.6902,
+      "step": 2765
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0001843621399176955,
+      "loss": 0.6777,
+      "step": 2770
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00018395061728395062,
+      "loss": 0.7127,
+      "step": 2775
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00018353909465020578,
+      "loss": 0.6551,
+      "step": 2780
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00018312757201646091,
+      "loss": 0.6703,
+      "step": 2785
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00018271604938271605,
+      "loss": 0.6776,
+      "step": 2790
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0001823045267489712,
+      "loss": 0.6574,
+      "step": 2795
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00018189300411522634,
+      "loss": 0.7154,
+      "step": 2800
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0001814814814814815,
+      "loss": 0.6749,
+      "step": 2805
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00018106995884773663,
+      "loss": 0.695,
+      "step": 2810
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00018065843621399178,
+      "loss": 0.6685,
+      "step": 2815
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00018024691358024692,
+      "loss": 0.642,
+      "step": 2820
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00017983539094650205,
+      "loss": 0.6873,
+      "step": 2825
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0001794238683127572,
+      "loss": 0.6506,
+      "step": 2830
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00017901234567901234,
+      "loss": 0.6695,
+      "step": 2835
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0001786008230452675,
+      "loss": 0.651,
+      "step": 2840
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00017818930041152265,
+      "loss": 0.6585,
+      "step": 2845
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 0.6717,
+      "step": 2850
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00017736625514403294,
+      "loss": 0.6524,
+      "step": 2855
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00017695473251028808,
+      "loss": 0.6679,
+      "step": 2860
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00017654320987654323,
+      "loss": 0.6719,
+      "step": 2865
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00017613168724279837,
+      "loss": 0.6662,
+      "step": 2870
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00017572016460905352,
+      "loss": 0.6624,
+      "step": 2875
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00017530864197530866,
+      "loss": 0.69,
+      "step": 2880
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0001748971193415638,
+      "loss": 0.6629,
+      "step": 2885
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00017448559670781895,
+      "loss": 0.6566,
+      "step": 2890
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00017407407407407408,
+      "loss": 0.6711,
+      "step": 2895
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00017366255144032924,
+      "loss": 0.6995,
+      "step": 2900
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00017325102880658437,
+      "loss": 0.6597,
+      "step": 2905
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0001728395061728395,
+      "loss": 0.6685,
+      "step": 2910
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00017242798353909466,
+      "loss": 0.6649,
+      "step": 2915
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0001720164609053498,
+      "loss": 0.6824,
+      "step": 2920
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00017160493827160495,
+      "loss": 0.6484,
+      "step": 2925
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00017119341563786008,
+      "loss": 0.6693,
+      "step": 2930
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00017078189300411524,
+      "loss": 0.629,
+      "step": 2935
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00017037037037037037,
+      "loss": 0.6588,
+      "step": 2940
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00016995884773662553,
+      "loss": 0.6771,
+      "step": 2945
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00016954732510288066,
+      "loss": 0.6773,
+      "step": 2950
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00016913580246913582,
+      "loss": 0.6307,
+      "step": 2955
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00016872427983539098,
+      "loss": 0.6809,
+      "step": 2960
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0001683127572016461,
+      "loss": 0.6748,
+      "step": 2965
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00016790123456790124,
+      "loss": 0.6708,
+      "step": 2970
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0001674897119341564,
+      "loss": 0.6754,
+      "step": 2975
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00016707818930041153,
+      "loss": 0.6676,
+      "step": 2980
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 0.6662,
+      "step": 2985
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00016625514403292182,
+      "loss": 0.6933,
+      "step": 2990
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00016584362139917695,
+      "loss": 0.6879,
+      "step": 2995
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0001654320987654321,
+      "loss": 0.6979,
+      "step": 3000
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00016502057613168724,
+      "loss": 0.657,
+      "step": 3005
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0001646090534979424,
+      "loss": 0.6704,
+      "step": 3010
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00016419753086419753,
+      "loss": 0.6394,
+      "step": 3015
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0001637860082304527,
+      "loss": 0.6594,
+      "step": 3020
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00016337448559670782,
+      "loss": 0.6584,
+      "step": 3025
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00016296296296296295,
+      "loss": 0.6593,
+      "step": 3030
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0001625514403292181,
+      "loss": 0.6538,
+      "step": 3035
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00016213991769547324,
+      "loss": 0.6572,
+      "step": 3040
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0001617283950617284,
+      "loss": 0.6999,
+      "step": 3045
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00016131687242798353,
+      "loss": 0.6658,
+      "step": 3050
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0001609053497942387,
+      "loss": 0.6809,
+      "step": 3055
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00016049382716049385,
+      "loss": 0.6685,
+      "step": 3060
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00016008230452674898,
+      "loss": 0.6532,
+      "step": 3065
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00015967078189300414,
+      "loss": 0.6644,
+      "step": 3070
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00015925925925925927,
+      "loss": 0.6721,
+      "step": 3075
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00015884773662551443,
+      "loss": 0.6569,
+      "step": 3080
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00015843621399176956,
+      "loss": 0.6832,
+      "step": 3085
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.0001580246913580247,
+      "loss": 0.6721,
+      "step": 3090
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00015761316872427985,
+      "loss": 0.6532,
+      "step": 3095
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00015720164609053498,
+      "loss": 0.6955,
+      "step": 3100
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00015679012345679014,
+      "loss": 0.6853,
+      "step": 3105
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00015637860082304527,
+      "loss": 0.6943,
+      "step": 3110
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0001559670781893004,
+      "loss": 0.6815,
+      "step": 3115
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 0.6972,
+      "step": 3120
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0001551440329218107,
+      "loss": 0.6959,
+      "step": 3125
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00015473251028806585,
+      "loss": 0.6795,
+      "step": 3130
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00015432098765432098,
+      "loss": 0.6352,
+      "step": 3135
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00015390946502057614,
+      "loss": 0.6601,
+      "step": 3140
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00015349794238683127,
+      "loss": 0.676,
+      "step": 3145
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0001530864197530864,
+      "loss": 0.6352,
+      "step": 3150
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00015267489711934156,
+      "loss": 0.6434,
+      "step": 3155
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00015226337448559672,
+      "loss": 0.673,
+      "step": 3160
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00015185185185185185,
+      "loss": 0.6963,
+      "step": 3165
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.000151440329218107,
+      "loss": 0.6643,
+      "step": 3170
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00015102880658436214,
+      "loss": 0.6757,
+      "step": 3175
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0001506172839506173,
+      "loss": 0.6681,
+      "step": 3180
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00015020576131687243,
+      "loss": 0.6935,
+      "step": 3185
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0001497942386831276,
+      "loss": 0.6894,
+      "step": 3190
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00014938271604938272,
+      "loss": 0.64,
+      "step": 3195
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00014897119341563788,
+      "loss": 0.6481,
+      "step": 3200
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00014855967078189301,
+      "loss": 0.6644,
+      "step": 3205
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00014814814814814815,
+      "loss": 0.6358,
+      "step": 3210
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0001477366255144033,
+      "loss": 0.6678,
+      "step": 3215
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00014732510288065844,
+      "loss": 0.6755,
+      "step": 3220
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0001469135802469136,
+      "loss": 0.6486,
+      "step": 3225
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00014650205761316873,
+      "loss": 0.666,
+      "step": 3230
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00014609053497942386,
+      "loss": 0.6689,
+      "step": 3235
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00014567901234567902,
+      "loss": 0.6737,
+      "step": 3240
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00014526748971193415,
+      "loss": 0.6659,
+      "step": 3245
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0001448559670781893,
+      "loss": 0.6744,
+      "step": 3250
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00014444444444444444,
+      "loss": 0.648,
+      "step": 3255
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0001440329218106996,
+      "loss": 0.6455,
+      "step": 3260
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00014362139917695473,
+      "loss": 0.659,
+      "step": 3265
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00014320987654320989,
+      "loss": 0.6519,
+      "step": 3270
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00014279835390946504,
+      "loss": 0.6972,
+      "step": 3275
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00014238683127572018,
+      "loss": 0.6592,
+      "step": 3280
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00014197530864197534,
+      "loss": 0.6757,
+      "step": 3285
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00014156378600823047,
+      "loss": 0.6684,
+      "step": 3290
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0001411522633744856,
+      "loss": 0.6754,
+      "step": 3295
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00014074074074074076,
+      "loss": 0.6738,
+      "step": 3300
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0001403292181069959,
+      "loss": 0.683,
+      "step": 3305
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00013991769547325105,
+      "loss": 0.6434,
+      "step": 3310
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00013950617283950618,
+      "loss": 0.6416,
+      "step": 3315
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00013909465020576134,
+      "loss": 0.6687,
+      "step": 3320
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00013868312757201647,
+      "loss": 0.6663,
+      "step": 3325
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0001382716049382716,
+      "loss": 0.7113,
+      "step": 3330
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00013786008230452676,
+      "loss": 0.6625,
+      "step": 3335
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0001374485596707819,
+      "loss": 0.6593,
+      "step": 3340
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00013703703703703705,
+      "loss": 0.6707,
+      "step": 3345
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00013662551440329218,
+      "loss": 0.6567,
+      "step": 3350
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0001362139917695473,
+      "loss": 0.6622,
+      "step": 3355
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00013580246913580247,
+      "loss": 0.6849,
+      "step": 3360
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0001353909465020576,
+      "loss": 0.657,
+      "step": 3365
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00013497942386831276,
+      "loss": 0.6452,
+      "step": 3370
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00013456790123456792,
+      "loss": 0.6486,
+      "step": 3375
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00013415637860082305,
+      "loss": 0.6737,
+      "step": 3380
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0001337448559670782,
+      "loss": 0.6793,
+      "step": 3385
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.6869,
+      "step": 3390
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0001329218106995885,
+      "loss": 0.6594,
+      "step": 3395
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00013251028806584363,
+      "loss": 0.6793,
+      "step": 3400
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0001320987654320988,
+      "loss": 0.6879,
+      "step": 3405
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00013168724279835392,
+      "loss": 0.695,
+      "step": 3410
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00013127572016460905,
+      "loss": 0.6648,
+      "step": 3415
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.0001308641975308642,
+      "loss": 0.6162,
+      "step": 3420
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00013045267489711934,
+      "loss": 0.642,
+      "step": 3425
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.0001300411522633745,
+      "loss": 0.6618,
+      "step": 3430
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00012962962962962963,
+      "loss": 0.6535,
+      "step": 3435
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00012921810699588476,
+      "loss": 0.6664,
+      "step": 3440
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00012880658436213992,
+      "loss": 0.6427,
+      "step": 3445
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00012839506172839505,
+      "loss": 0.6584,
+      "step": 3450
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0001279835390946502,
+      "loss": 0.657,
+      "step": 3455
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00012757201646090534,
+      "loss": 0.6494,
+      "step": 3460
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0001271604938271605,
+      "loss": 0.6553,
+      "step": 3465
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00012674897119341563,
+      "loss": 0.6755,
+      "step": 3470
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0001263374485596708,
+      "loss": 0.6599,
+      "step": 3475
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00012592592592592592,
+      "loss": 0.6564,
+      "step": 3480
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00012551440329218108,
+      "loss": 0.6526,
+      "step": 3485
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00012510288065843624,
+      "loss": 0.6439,
+      "step": 3490
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00012469135802469137,
+      "loss": 0.6459,
+      "step": 3495
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0001242798353909465,
+      "loss": 0.6573,
+      "step": 3500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00012386831275720166,
+      "loss": 0.6773,
+      "step": 3505
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0001234567901234568,
+      "loss": 0.68,
+      "step": 3510
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00012304526748971195,
+      "loss": 0.6615,
+      "step": 3515
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00012263374485596708,
+      "loss": 0.6886,
+      "step": 3520
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00012222222222222224,
+      "loss": 0.667,
+      "step": 3525
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00012181069958847737,
+      "loss": 0.677,
+      "step": 3530
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.0001213991769547325,
+      "loss": 0.6709,
+      "step": 3535
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00012098765432098766,
+      "loss": 0.6258,
+      "step": 3540
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.0001205761316872428,
+      "loss": 0.6795,
+      "step": 3545
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00012016460905349795,
+      "loss": 0.6673,
+      "step": 3550
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00011975308641975308,
+      "loss": 0.6708,
+      "step": 3555
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00011934156378600823,
+      "loss": 0.6466,
+      "step": 3560
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00011893004115226339,
+      "loss": 0.6339,
+      "step": 3565
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00011851851851851852,
+      "loss": 0.6838,
+      "step": 3570
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00011810699588477368,
+      "loss": 0.6179,
+      "step": 3575
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00011769547325102881,
+      "loss": 0.6357,
+      "step": 3580
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00011728395061728397,
+      "loss": 0.6807,
+      "step": 3585
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.0001168724279835391,
+      "loss": 0.6365,
+      "step": 3590
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00011646090534979423,
+      "loss": 0.6518,
+      "step": 3595
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00011604938271604939,
+      "loss": 0.6467,
+      "step": 3600
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00011563786008230452,
+      "loss": 0.6537,
+      "step": 3605
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00011522633744855968,
+      "loss": 0.6324,
+      "step": 3610
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00011481481481481482,
+      "loss": 0.6826,
+      "step": 3615
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00011440329218106996,
+      "loss": 0.6643,
+      "step": 3620
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00011399176954732511,
+      "loss": 0.6464,
+      "step": 3625
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00011358024691358025,
+      "loss": 0.6601,
+      "step": 3630
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.0001131687242798354,
+      "loss": 0.6596,
+      "step": 3635
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00011275720164609054,
+      "loss": 0.72,
+      "step": 3640
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.0001123456790123457,
+      "loss": 0.7157,
+      "step": 3645
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00011193415637860083,
+      "loss": 0.6641,
+      "step": 3650
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00011152263374485596,
+      "loss": 0.6631,
+      "step": 3655
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 0.6454,
+      "step": 3660
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00011069958847736626,
+      "loss": 0.6957,
+      "step": 3665
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.0001102880658436214,
+      "loss": 0.6535,
+      "step": 3670
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00010987654320987655,
+      "loss": 0.6675,
+      "step": 3675
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00010946502057613168,
+      "loss": 0.6458,
+      "step": 3680
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00010905349794238684,
+      "loss": 0.6507,
+      "step": 3685
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00010864197530864197,
+      "loss": 0.6818,
+      "step": 3690
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00010823045267489713,
+      "loss": 0.6752,
+      "step": 3695
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00010781893004115226,
+      "loss": 0.6645,
+      "step": 3700
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00010740740740740742,
+      "loss": 0.6414,
+      "step": 3705
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00010699588477366255,
+      "loss": 0.675,
+      "step": 3710
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.0001065843621399177,
+      "loss": 0.6597,
+      "step": 3715
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00010617283950617284,
+      "loss": 0.6637,
+      "step": 3720
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00010576131687242799,
+      "loss": 0.664,
+      "step": 3725
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00010534979423868315,
+      "loss": 0.6638,
+      "step": 3730
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00010493827160493828,
+      "loss": 0.6413,
+      "step": 3735
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00010452674897119341,
+      "loss": 0.6242,
+      "step": 3740
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00010411522633744857,
+      "loss": 0.6653,
+      "step": 3745
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.0001037037037037037,
+      "loss": 0.6947,
+      "step": 3750
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00010329218106995886,
+      "loss": 0.6801,
+      "step": 3755
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00010288065843621399,
+      "loss": 0.671,
+      "step": 3760
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00010246913580246915,
+      "loss": 0.6505,
+      "step": 3765
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00010205761316872428,
+      "loss": 0.6738,
+      "step": 3770
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00010164609053497942,
+      "loss": 0.6478,
+      "step": 3775
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00010123456790123458,
+      "loss": 0.6652,
+      "step": 3780
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00010082304526748971,
+      "loss": 0.6456,
+      "step": 3785
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00010041152263374487,
+      "loss": 0.6509,
+      "step": 3790
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.0001,
+      "loss": 0.6623,
+      "step": 3795
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 9.958847736625515e-05,
+      "loss": 0.6727,
+      "step": 3800
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 9.91769547325103e-05,
+      "loss": 0.676,
+      "step": 3805
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 9.876543209876543e-05,
+      "loss": 0.6662,
+      "step": 3810
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 9.835390946502057e-05,
+      "loss": 0.6767,
+      "step": 3815
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 9.794238683127573e-05,
+      "loss": 0.6278,
+      "step": 3820
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 9.753086419753087e-05,
+      "loss": 0.6769,
+      "step": 3825
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 9.711934156378602e-05,
+      "loss": 0.667,
+      "step": 3830
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 9.670781893004116e-05,
+      "loss": 0.6392,
+      "step": 3835
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 9.62962962962963e-05,
+      "loss": 0.6479,
+      "step": 3840
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 9.588477366255144e-05,
+      "loss": 0.6958,
+      "step": 3845
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 9.547325102880659e-05,
+      "loss": 0.6636,
+      "step": 3850
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 9.506172839506173e-05,
+      "loss": 0.6722,
+      "step": 3855
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 9.465020576131688e-05,
+      "loss": 0.6688,
+      "step": 3860
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 9.423868312757202e-05,
+      "loss": 0.6814,
+      "step": 3865
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 9.382716049382717e-05,
+      "loss": 0.679,
+      "step": 3870
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.341563786008231e-05,
+      "loss": 0.6536,
+      "step": 3875
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.300411522633746e-05,
+      "loss": 0.6783,
+      "step": 3880
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.25925925925926e-05,
+      "loss": 0.6424,
+      "step": 3885
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.218106995884775e-05,
+      "loss": 0.6695,
+      "step": 3890
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.176954732510289e-05,
+      "loss": 0.6941,
+      "step": 3895
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.135802469135802e-05,
+      "loss": 0.6887,
+      "step": 3900
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.094650205761317e-05,
+      "loss": 0.6789,
+      "step": 3905
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.053497942386831e-05,
+      "loss": 0.6819,
+      "step": 3910
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.012345679012346e-05,
+      "loss": 0.6571,
+      "step": 3915
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 8.97119341563786e-05,
+      "loss": 0.6527,
+      "step": 3920
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 8.930041152263375e-05,
+      "loss": 0.6656,
+      "step": 3925
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 0.6551,
+      "step": 3930
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 8.847736625514404e-05,
+      "loss": 0.6502,
+      "step": 3935
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 8.806584362139918e-05,
+      "loss": 0.6458,
+      "step": 3940
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 8.765432098765433e-05,
+      "loss": 0.6617,
+      "step": 3945
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 8.724279835390947e-05,
+      "loss": 0.6444,
+      "step": 3950
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 8.683127572016462e-05,
+      "loss": 0.6629,
+      "step": 3955
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 8.641975308641975e-05,
+      "loss": 0.6683,
+      "step": 3960
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 8.60082304526749e-05,
+      "loss": 0.6483,
+      "step": 3965
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 8.559670781893004e-05,
+      "loss": 0.6623,
+      "step": 3970
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 8.518518518518518e-05,
+      "loss": 0.6491,
+      "step": 3975
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 8.477366255144033e-05,
+      "loss": 0.6394,
+      "step": 3980
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 8.436213991769549e-05,
+      "loss": 0.6494,
+      "step": 3985
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 8.395061728395062e-05,
+      "loss": 0.6516,
+      "step": 3990
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 8.353909465020576e-05,
+      "loss": 0.6664,
+      "step": 3995
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 8.312757201646091e-05,
+      "loss": 0.6822,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 5010,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 1.6102337306911834e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/training_args.bin b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..28c7b09fc2b3929abe4ad6608c7959f30a9a9d66
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43458f4cf6aeb211c730b848f93ab15f483827c314fb4dc1e79dd1f658b7dbc8
+size 5944
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/zero_to_fp32.py b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/zero_to_fp32.py
new file mode 100644
index 0000000000000000000000000000000000000000..c98caae31534368be22b67fc4ae906836c992a8d
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4000/zero_to_fp32.py
@@ -0,0 +1,587 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel()
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file, tag=args.tag)
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/README.md b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..2aa897f8fa13b49ce76b1fa188781e5f726e7d13
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-2-7b-hf
+library_name: peft
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/adapter_config.json b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9c81a592f0ff08374a4f61f6003029070a8429ae
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/adapter_config.json
@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "mora_type": 1,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_mora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/adapter_model.safetensors b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..324c20eb80314fcedcf477c1faf2e4b5e453a99d
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02dd3c890f7e84fb98dbbc4305c2013226f5e34d5dd720f332ab2adf38b69ba2
+size 564342240
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/global_step4500/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/global_step4500/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6b2558835aa3ace7253ac23b5e00b835c9738428
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/global_step4500/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:776e6554eef8fdd2f76b83cd0dd293946635373180354bb1b8ba990b8d023990
+size 239914224
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/global_step4500/mp_rank_00_model_states.pt b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/global_step4500/mp_rank_00_model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..dad6ae5db7face15f62813a4ee50348ae04b5c53
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/global_step4500/mp_rank_00_model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:244329fee9472820bef1df66785a200ead14a1a637e42f4c7de2a518cf2743e2
+size 40303404
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/latest b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/latest
new file mode 100644
index 0000000000000000000000000000000000000000..982b8ddd9a759078550e0894b3ed06c6084c9e9c
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/latest
@@ -0,0 +1 @@
+global_step4500
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/rng_state.pth b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9ca0f22355d7c99215c54c6fb7472555b5e6c9b3
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7224daa5bbdc8c06383cff73437e9cd9d12f97c9793d5c00d39be052a9142c9c
+size 14244
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/scheduler.pt b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d0272ae81a71d8378677b37dd7b4e335fae7b9f6
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250f876d4d8087a170bed36e61e55ad2b2da3497e02d544cdd03167f9e3a5f54
+size 1064
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/trainer_state.json b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..aa4df3cb59d6aae0347fc51b091f6004bf382bba
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/trainer_state.json
@@ -0,0 +1,5421 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.796239124333427,
+  "eval_steps": 500,
+  "global_step": 4500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.3798,
+      "step": 5
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 1.3917,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4e-05,
+      "loss": 1.2862,
+      "step": 15
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 1.2046,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.0634,
+      "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8e-05,
+      "loss": 1.0273,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 1.0472,
+      "step": 35
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 1.0301,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00012,
+      "loss": 0.9335,
+      "step": 45
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.921,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00014666666666666666,
+      "loss": 0.9506,
+      "step": 55
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016,
+      "loss": 0.8876,
+      "step": 60
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00017333333333333334,
+      "loss": 0.9335,
+      "step": 65
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 0.8554,
+      "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0002,
+      "loss": 0.8537,
+      "step": 75
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00021333333333333333,
+      "loss": 0.9033,
+      "step": 80
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00022666666666666668,
+      "loss": 0.8203,
+      "step": 85
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00024,
+      "loss": 0.8611,
+      "step": 90
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00025333333333333333,
+      "loss": 0.8303,
+      "step": 95
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002666666666666667,
+      "loss": 0.8528,
+      "step": 100
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00028,
+      "loss": 0.8537,
+      "step": 105
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002933333333333333,
+      "loss": 0.8286,
+      "step": 110
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003066666666666667,
+      "loss": 0.8449,
+      "step": 115
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00032,
+      "loss": 0.8377,
+      "step": 120
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003333333333333334,
+      "loss": 0.8419,
+      "step": 125
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00034666666666666667,
+      "loss": 0.8265,
+      "step": 130
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00036,
+      "loss": 0.8037,
+      "step": 135
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003733333333333334,
+      "loss": 0.7924,
+      "step": 140
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00038666666666666667,
+      "loss": 0.8245,
+      "step": 145
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0004,
+      "loss": 0.8388,
+      "step": 150
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003995884773662552,
+      "loss": 0.8066,
+      "step": 155
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003991769547325103,
+      "loss": 0.8107,
+      "step": 160
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039876543209876544,
+      "loss": 0.8005,
+      "step": 165
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003983539094650206,
+      "loss": 0.7727,
+      "step": 170
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039794238683127576,
+      "loss": 0.8276,
+      "step": 175
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039753086419753086,
+      "loss": 0.8464,
+      "step": 180
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000397119341563786,
+      "loss": 0.8348,
+      "step": 185
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003967078189300412,
+      "loss": 0.8228,
+      "step": 190
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003962962962962963,
+      "loss": 0.8254,
+      "step": 195
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00039588477366255144,
+      "loss": 0.817,
+      "step": 200
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003954732510288066,
+      "loss": 0.8365,
+      "step": 205
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003950617283950617,
+      "loss": 0.793,
+      "step": 210
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00039465020576131686,
+      "loss": 0.8014,
+      "step": 215
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000394238683127572,
+      "loss": 0.8049,
+      "step": 220
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003938271604938272,
+      "loss": 0.7841,
+      "step": 225
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003934156378600823,
+      "loss": 0.7977,
+      "step": 230
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00039300411522633744,
+      "loss": 0.8299,
+      "step": 235
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003925925925925926,
+      "loss": 0.7729,
+      "step": 240
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00039218106995884776,
+      "loss": 0.8082,
+      "step": 245
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003917695473251029,
+      "loss": 0.8173,
+      "step": 250
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000391358024691358,
+      "loss": 0.8379,
+      "step": 255
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003909465020576132,
+      "loss": 0.7962,
+      "step": 260
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00039053497942386834,
+      "loss": 0.8067,
+      "step": 265
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003901234567901235,
+      "loss": 0.7915,
+      "step": 270
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00038971193415637866,
+      "loss": 0.7905,
+      "step": 275
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00038930041152263376,
+      "loss": 0.7862,
+      "step": 280
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003888888888888889,
+      "loss": 0.7709,
+      "step": 285
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003884773662551441,
+      "loss": 0.7773,
+      "step": 290
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00038806584362139924,
+      "loss": 0.8068,
+      "step": 295
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00038765432098765434,
+      "loss": 0.7962,
+      "step": 300
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003872427983539095,
+      "loss": 0.7894,
+      "step": 305
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00038683127572016466,
+      "loss": 0.7705,
+      "step": 310
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00038641975308641976,
+      "loss": 0.7882,
+      "step": 315
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003860082304526749,
+      "loss": 0.7865,
+      "step": 320
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003855967078189301,
+      "loss": 0.7939,
+      "step": 325
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003851851851851852,
+      "loss": 0.7724,
+      "step": 330
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00038477366255144034,
+      "loss": 0.7771,
+      "step": 335
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003843621399176955,
+      "loss": 0.7941,
+      "step": 340
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00038395061728395066,
+      "loss": 0.7822,
+      "step": 345
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00038353909465020577,
+      "loss": 0.8143,
+      "step": 350
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003831275720164609,
+      "loss": 0.795,
+      "step": 355
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003827160493827161,
+      "loss": 0.8049,
+      "step": 360
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003823045267489712,
+      "loss": 0.8309,
+      "step": 365
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00038189300411522635,
+      "loss": 0.8314,
+      "step": 370
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003814814814814815,
+      "loss": 0.801,
+      "step": 375
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00038106995884773666,
+      "loss": 0.8084,
+      "step": 380
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00038065843621399177,
+      "loss": 0.8129,
+      "step": 385
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003802469135802469,
+      "loss": 0.7859,
+      "step": 390
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003798353909465021,
+      "loss": 0.7874,
+      "step": 395
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003794238683127572,
+      "loss": 0.7548,
+      "step": 400
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00037901234567901235,
+      "loss": 0.8092,
+      "step": 405
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003786008230452675,
+      "loss": 0.8041,
+      "step": 410
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00037818930041152266,
+      "loss": 0.777,
+      "step": 415
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00037777777777777777,
+      "loss": 0.7699,
+      "step": 420
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00037736625514403293,
+      "loss": 0.781,
+      "step": 425
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003769547325102881,
+      "loss": 0.7504,
+      "step": 430
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003765432098765432,
+      "loss": 0.7974,
+      "step": 435
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037613168724279835,
+      "loss": 0.7663,
+      "step": 440
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003757201646090535,
+      "loss": 0.8013,
+      "step": 445
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037530864197530867,
+      "loss": 0.7453,
+      "step": 450
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037489711934156377,
+      "loss": 0.7425,
+      "step": 455
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037448559670781893,
+      "loss": 0.7582,
+      "step": 460
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003740740740740741,
+      "loss": 0.7801,
+      "step": 465
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00037366255144032925,
+      "loss": 0.7809,
+      "step": 470
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003732510288065844,
+      "loss": 0.7749,
+      "step": 475
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00037283950617283956,
+      "loss": 0.7807,
+      "step": 480
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00037242798353909467,
+      "loss": 0.7715,
+      "step": 485
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003720164609053498,
+      "loss": 0.7356,
+      "step": 490
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000371604938271605,
+      "loss": 0.7674,
+      "step": 495
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00037119341563786014,
+      "loss": 0.7542,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00037078189300411525,
+      "loss": 0.7583,
+      "step": 505
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003703703703703704,
+      "loss": 0.7767,
+      "step": 510
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036995884773662556,
+      "loss": 0.7853,
+      "step": 515
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036954732510288067,
+      "loss": 0.7733,
+      "step": 520
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036913580246913583,
+      "loss": 0.7758,
+      "step": 525
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.000368724279835391,
+      "loss": 0.7698,
+      "step": 530
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036831275720164614,
+      "loss": 0.7805,
+      "step": 535
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036790123456790125,
+      "loss": 0.7573,
+      "step": 540
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003674897119341564,
+      "loss": 0.7709,
+      "step": 545
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036707818930041157,
+      "loss": 0.7994,
+      "step": 550
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036666666666666667,
+      "loss": 0.7363,
+      "step": 555
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036625514403292183,
+      "loss": 0.7478,
+      "step": 560
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000365843621399177,
+      "loss": 0.8188,
+      "step": 565
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003654320987654321,
+      "loss": 0.7524,
+      "step": 570
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00036502057613168725,
+      "loss": 0.7319,
+      "step": 575
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003646090534979424,
+      "loss": 0.7915,
+      "step": 580
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00036419753086419757,
+      "loss": 0.7722,
+      "step": 585
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00036378600823045267,
+      "loss": 0.7842,
+      "step": 590
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00036337448559670783,
+      "loss": 0.7591,
+      "step": 595
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000362962962962963,
+      "loss": 0.7653,
+      "step": 600
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003625514403292181,
+      "loss": 0.7838,
+      "step": 605
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00036213991769547325,
+      "loss": 0.7937,
+      "step": 610
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003617283950617284,
+      "loss": 0.77,
+      "step": 615
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00036131687242798357,
+      "loss": 0.7899,
+      "step": 620
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003609053497942387,
+      "loss": 0.7815,
+      "step": 625
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00036049382716049383,
+      "loss": 0.7648,
+      "step": 630
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.000360082304526749,
+      "loss": 0.7716,
+      "step": 635
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003596707818930041,
+      "loss": 0.7708,
+      "step": 640
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00035925925925925925,
+      "loss": 0.7306,
+      "step": 645
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003588477366255144,
+      "loss": 0.8007,
+      "step": 650
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003584362139917695,
+      "loss": 0.7551,
+      "step": 655
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003580246913580247,
+      "loss": 0.754,
+      "step": 660
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00035761316872427983,
+      "loss": 0.7599,
+      "step": 665
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.000357201646090535,
+      "loss": 0.7637,
+      "step": 670
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00035679012345679015,
+      "loss": 0.7766,
+      "step": 675
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003563786008230453,
+      "loss": 0.7727,
+      "step": 680
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003559670781893004,
+      "loss": 0.7675,
+      "step": 685
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035555555555555557,
+      "loss": 0.7707,
+      "step": 690
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035514403292181073,
+      "loss": 0.7221,
+      "step": 695
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003547325102880659,
+      "loss": 0.7335,
+      "step": 700
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035432098765432105,
+      "loss": 0.781,
+      "step": 705
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035390946502057615,
+      "loss": 0.7845,
+      "step": 710
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003534979423868313,
+      "loss": 0.7467,
+      "step": 715
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00035308641975308647,
+      "loss": 0.7735,
+      "step": 720
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003526748971193416,
+      "loss": 0.7368,
+      "step": 725
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00035226337448559673,
+      "loss": 0.7678,
+      "step": 730
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003518518518518519,
+      "loss": 0.7756,
+      "step": 735
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00035144032921810705,
+      "loss": 0.7635,
+      "step": 740
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00035102880658436215,
+      "loss": 0.7757,
+      "step": 745
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003506172839506173,
+      "loss": 0.7442,
+      "step": 750
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00035020576131687247,
+      "loss": 0.7584,
+      "step": 755
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003497942386831276,
+      "loss": 0.8333,
+      "step": 760
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00034938271604938273,
+      "loss": 0.7459,
+      "step": 765
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003489711934156379,
+      "loss": 0.7499,
+      "step": 770
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.000348559670781893,
+      "loss": 0.7571,
+      "step": 775
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00034814814814814816,
+      "loss": 0.7243,
+      "step": 780
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003477366255144033,
+      "loss": 0.7443,
+      "step": 785
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003473251028806585,
+      "loss": 0.7759,
+      "step": 790
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003469135802469136,
+      "loss": 0.7452,
+      "step": 795
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00034650205761316874,
+      "loss": 0.7578,
+      "step": 800
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003460905349794239,
+      "loss": 0.7634,
+      "step": 805
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.000345679012345679,
+      "loss": 0.7925,
+      "step": 810
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00034526748971193416,
+      "loss": 0.7966,
+      "step": 815
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003448559670781893,
+      "loss": 0.7601,
+      "step": 820
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003444444444444445,
+      "loss": 0.7617,
+      "step": 825
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003440329218106996,
+      "loss": 0.7526,
+      "step": 830
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00034362139917695474,
+      "loss": 0.7297,
+      "step": 835
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003432098765432099,
+      "loss": 0.7549,
+      "step": 840
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.000342798353909465,
+      "loss": 0.7517,
+      "step": 845
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00034238683127572016,
+      "loss": 0.7626,
+      "step": 850
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003419753086419753,
+      "loss": 0.7987,
+      "step": 855
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003415637860082305,
+      "loss": 0.7573,
+      "step": 860
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003411522633744856,
+      "loss": 0.8367,
+      "step": 865
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00034074074074074074,
+      "loss": 0.7258,
+      "step": 870
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003403292181069959,
+      "loss": 0.7632,
+      "step": 875
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00033991769547325106,
+      "loss": 0.7379,
+      "step": 880
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00033950617283950616,
+      "loss": 0.7529,
+      "step": 885
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003390946502057613,
+      "loss": 0.7391,
+      "step": 890
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003386831275720165,
+      "loss": 0.8061,
+      "step": 895
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00033827160493827164,
+      "loss": 0.7288,
+      "step": 900
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003378600823045268,
+      "loss": 0.7493,
+      "step": 905
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00033744855967078195,
+      "loss": 0.7702,
+      "step": 910
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00033703703703703706,
+      "loss": 0.7538,
+      "step": 915
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003366255144032922,
+      "loss": 0.728,
+      "step": 920
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003362139917695474,
+      "loss": 0.7776,
+      "step": 925
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003358024691358025,
+      "loss": 0.7883,
+      "step": 930
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00033539094650205764,
+      "loss": 0.7471,
+      "step": 935
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003349794238683128,
+      "loss": 0.7464,
+      "step": 940
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00033456790123456795,
+      "loss": 0.7885,
+      "step": 945
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00033415637860082306,
+      "loss": 0.7509,
+      "step": 950
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003337448559670782,
+      "loss": 0.7681,
+      "step": 955
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003333333333333334,
+      "loss": 0.8246,
+      "step": 960
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003329218106995885,
+      "loss": 0.7604,
+      "step": 965
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00033251028806584364,
+      "loss": 0.7755,
+      "step": 970
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003320987654320988,
+      "loss": 0.7641,
+      "step": 975
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003316872427983539,
+      "loss": 0.7708,
+      "step": 980
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00033127572016460906,
+      "loss": 0.7936,
+      "step": 985
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003308641975308642,
+      "loss": 0.7641,
+      "step": 990
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003304526748971194,
+      "loss": 0.7479,
+      "step": 995
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003300411522633745,
+      "loss": 0.7547,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00032962962962962964,
+      "loss": 0.762,
+      "step": 1005
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003292181069958848,
+      "loss": 0.7472,
+      "step": 1010
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003288065843621399,
+      "loss": 0.7542,
+      "step": 1015
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00032839506172839506,
+      "loss": 0.7669,
+      "step": 1020
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003279835390946502,
+      "loss": 0.7812,
+      "step": 1025
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003275720164609054,
+      "loss": 0.7273,
+      "step": 1030
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003271604938271605,
+      "loss": 0.7822,
+      "step": 1035
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00032674897119341564,
+      "loss": 0.7337,
+      "step": 1040
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003263374485596708,
+      "loss": 0.7566,
+      "step": 1045
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003259259259259259,
+      "loss": 0.7377,
+      "step": 1050
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00032551440329218106,
+      "loss": 0.7856,
+      "step": 1055
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003251028806584362,
+      "loss": 0.7981,
+      "step": 1060
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003246913580246914,
+      "loss": 0.7505,
+      "step": 1065
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003242798353909465,
+      "loss": 0.7549,
+      "step": 1070
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00032386831275720164,
+      "loss": 0.7306,
+      "step": 1075
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003234567901234568,
+      "loss": 0.7343,
+      "step": 1080
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003230452674897119,
+      "loss": 0.738,
+      "step": 1085
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00032263374485596707,
+      "loss": 0.7655,
+      "step": 1090
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003222222222222222,
+      "loss": 0.7706,
+      "step": 1095
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003218106995884774,
+      "loss": 0.7512,
+      "step": 1100
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00032139917695473254,
+      "loss": 0.7549,
+      "step": 1105
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003209876543209877,
+      "loss": 0.7839,
+      "step": 1110
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003205761316872428,
+      "loss": 0.7511,
+      "step": 1115
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00032016460905349796,
+      "loss": 0.769,
+      "step": 1120
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003197530864197531,
+      "loss": 0.7685,
+      "step": 1125
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003193415637860083,
+      "loss": 0.7489,
+      "step": 1130
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003189300411522634,
+      "loss": 0.808,
+      "step": 1135
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00031851851851851854,
+      "loss": 0.7654,
+      "step": 1140
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003181069958847737,
+      "loss": 0.7845,
+      "step": 1145
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00031769547325102886,
+      "loss": 0.7886,
+      "step": 1150
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00031728395061728396,
+      "loss": 0.7318,
+      "step": 1155
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003168724279835391,
+      "loss": 0.7231,
+      "step": 1160
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003164609053497943,
+      "loss": 0.7471,
+      "step": 1165
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003160493827160494,
+      "loss": 0.7424,
+      "step": 1170
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00031563786008230454,
+      "loss": 0.7249,
+      "step": 1175
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003152263374485597,
+      "loss": 0.7419,
+      "step": 1180
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00031481481481481486,
+      "loss": 0.7567,
+      "step": 1185
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00031440329218106997,
+      "loss": 0.7707,
+      "step": 1190
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003139917695473251,
+      "loss": 0.7473,
+      "step": 1195
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003135802469135803,
+      "loss": 0.7222,
+      "step": 1200
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003131687242798354,
+      "loss": 0.7383,
+      "step": 1205
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00031275720164609055,
+      "loss": 0.7712,
+      "step": 1210
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003123456790123457,
+      "loss": 0.7602,
+      "step": 1215
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003119341563786008,
+      "loss": 0.7741,
+      "step": 1220
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00031152263374485597,
+      "loss": 0.7428,
+      "step": 1225
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003111111111111111,
+      "loss": 0.7605,
+      "step": 1230
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003106995884773663,
+      "loss": 0.7255,
+      "step": 1235
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003102880658436214,
+      "loss": 0.7468,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00030987654320987655,
+      "loss": 0.7961,
+      "step": 1245
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003094650205761317,
+      "loss": 0.7208,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003090534979423868,
+      "loss": 0.7331,
+      "step": 1255
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00030864197530864197,
+      "loss": 0.7371,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00030823045267489713,
+      "loss": 0.7206,
+      "step": 1265
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003078189300411523,
+      "loss": 0.7617,
+      "step": 1270
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003074074074074074,
+      "loss": 0.7652,
+      "step": 1275
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00030699588477366255,
+      "loss": 0.7635,
+      "step": 1280
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003065843621399177,
+      "loss": 0.7445,
+      "step": 1285
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003061728395061728,
+      "loss": 0.7717,
+      "step": 1290
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030576131687242797,
+      "loss": 0.7535,
+      "step": 1295
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030534979423868313,
+      "loss": 0.7677,
+      "step": 1300
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003049382716049383,
+      "loss": 0.8131,
+      "step": 1305
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030452674897119345,
+      "loss": 0.7754,
+      "step": 1310
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030411522633744855,
+      "loss": 0.76,
+      "step": 1315
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003037037037037037,
+      "loss": 0.7558,
+      "step": 1320
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00030329218106995887,
+      "loss": 0.7604,
+      "step": 1325
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.000302880658436214,
+      "loss": 0.7716,
+      "step": 1330
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003024691358024692,
+      "loss": 0.7669,
+      "step": 1335
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003020576131687243,
+      "loss": 0.7469,
+      "step": 1340
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030164609053497945,
+      "loss": 0.7511,
+      "step": 1345
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003012345679012346,
+      "loss": 0.7483,
+      "step": 1350
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030082304526748976,
+      "loss": 0.7509,
+      "step": 1355
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030041152263374487,
+      "loss": 0.7249,
+      "step": 1360
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.7289,
+      "step": 1365
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002995884773662552,
+      "loss": 0.7605,
+      "step": 1370
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002991769547325103,
+      "loss": 0.7185,
+      "step": 1375
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00029876543209876545,
+      "loss": 0.6974,
+      "step": 1380
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002983539094650206,
+      "loss": 0.7234,
+      "step": 1385
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00029794238683127577,
+      "loss": 0.7506,
+      "step": 1390
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029753086419753087,
+      "loss": 0.7524,
+      "step": 1395
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029711934156378603,
+      "loss": 0.7641,
+      "step": 1400
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002967078189300412,
+      "loss": 0.6967,
+      "step": 1405
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002962962962962963,
+      "loss": 0.735,
+      "step": 1410
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029588477366255145,
+      "loss": 0.7685,
+      "step": 1415
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002954732510288066,
+      "loss": 0.758,
+      "step": 1420
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002950617283950617,
+      "loss": 0.763,
+      "step": 1425
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00029465020576131687,
+      "loss": 0.712,
+      "step": 1430
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00029423868312757203,
+      "loss": 0.7236,
+      "step": 1435
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002938271604938272,
+      "loss": 0.7732,
+      "step": 1440
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002934156378600823,
+      "loss": 0.7689,
+      "step": 1445
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00029300411522633745,
+      "loss": 0.7352,
+      "step": 1450
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002925925925925926,
+      "loss": 0.7711,
+      "step": 1455
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002921810699588477,
+      "loss": 0.7549,
+      "step": 1460
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002917695473251029,
+      "loss": 0.7804,
+      "step": 1465
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00029135802469135803,
+      "loss": 0.7478,
+      "step": 1470
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002909465020576132,
+      "loss": 0.7801,
+      "step": 1475
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002905349794238683,
+      "loss": 0.7544,
+      "step": 1480
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00029012345679012345,
+      "loss": 0.7546,
+      "step": 1485
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002897119341563786,
+      "loss": 0.7648,
+      "step": 1490
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002893004115226337,
+      "loss": 0.7468,
+      "step": 1495
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002888888888888889,
+      "loss": 0.7434,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00028847736625514403,
+      "loss": 0.7348,
+      "step": 1505
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002880658436213992,
+      "loss": 0.7515,
+      "step": 1510
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00028765432098765435,
+      "loss": 0.7345,
+      "step": 1515
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00028724279835390946,
+      "loss": 0.7701,
+      "step": 1520
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002868312757201646,
+      "loss": 0.7472,
+      "step": 1525
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00028641975308641977,
+      "loss": 0.7075,
+      "step": 1530
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00028600823045267493,
+      "loss": 0.7483,
+      "step": 1535
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002855967078189301,
+      "loss": 0.712,
+      "step": 1540
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002851851851851852,
+      "loss": 0.7484,
+      "step": 1545
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00028477366255144035,
+      "loss": 0.7471,
+      "step": 1550
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002843621399176955,
+      "loss": 0.7462,
+      "step": 1555
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00028395061728395067,
+      "loss": 0.7371,
+      "step": 1560
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002835390946502058,
+      "loss": 0.7753,
+      "step": 1565
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00028312757201646093,
+      "loss": 0.7374,
+      "step": 1570
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002827160493827161,
+      "loss": 0.7328,
+      "step": 1575
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002823045267489712,
+      "loss": 0.7159,
+      "step": 1580
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00028189300411522635,
+      "loss": 0.7594,
+      "step": 1585
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002814814814814815,
+      "loss": 0.7215,
+      "step": 1590
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00028106995884773667,
+      "loss": 0.7398,
+      "step": 1595
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002806584362139918,
+      "loss": 0.773,
+      "step": 1600
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00028024691358024693,
+      "loss": 0.7584,
+      "step": 1605
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002798353909465021,
+      "loss": 0.7117,
+      "step": 1610
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002794238683127572,
+      "loss": 0.7471,
+      "step": 1615
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00027901234567901236,
+      "loss": 0.7443,
+      "step": 1620
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002786008230452675,
+      "loss": 0.7292,
+      "step": 1625
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002781893004115227,
+      "loss": 0.7716,
+      "step": 1630
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 0.763,
+      "step": 1635
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00027736625514403294,
+      "loss": 0.7408,
+      "step": 1640
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002769547325102881,
+      "loss": 0.7403,
+      "step": 1645
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002765432098765432,
+      "loss": 0.7508,
+      "step": 1650
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00027613168724279836,
+      "loss": 0.7687,
+      "step": 1655
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002757201646090535,
+      "loss": 0.7305,
+      "step": 1660
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002753086419753086,
+      "loss": 0.7165,
+      "step": 1665
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002748971193415638,
+      "loss": 0.8,
+      "step": 1670
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00027448559670781894,
+      "loss": 0.7357,
+      "step": 1675
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002740740740740741,
+      "loss": 0.7988,
+      "step": 1680
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002736625514403292,
+      "loss": 0.7559,
+      "step": 1685
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00027325102880658436,
+      "loss": 0.712,
+      "step": 1690
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002728395061728395,
+      "loss": 0.7486,
+      "step": 1695
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002724279835390946,
+      "loss": 0.7388,
+      "step": 1700
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002720164609053498,
+      "loss": 0.7441,
+      "step": 1705
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00027160493827160494,
+      "loss": 0.7547,
+      "step": 1710
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002711934156378601,
+      "loss": 0.7229,
+      "step": 1715
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002707818930041152,
+      "loss": 0.7383,
+      "step": 1720
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00027037037037037036,
+      "loss": 0.7606,
+      "step": 1725
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002699588477366255,
+      "loss": 0.7529,
+      "step": 1730
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002695473251028807,
+      "loss": 0.752,
+      "step": 1735
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00026913580246913584,
+      "loss": 0.7342,
+      "step": 1740
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.000268724279835391,
+      "loss": 0.7308,
+      "step": 1745
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002683127572016461,
+      "loss": 0.6915,
+      "step": 1750
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00026790123456790126,
+      "loss": 0.7344,
+      "step": 1755
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002674897119341564,
+      "loss": 0.7426,
+      "step": 1760
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002670781893004116,
+      "loss": 0.7088,
+      "step": 1765
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002666666666666667,
+      "loss": 0.7241,
+      "step": 1770
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00026625514403292184,
+      "loss": 0.7552,
+      "step": 1775
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.000265843621399177,
+      "loss": 0.7477,
+      "step": 1780
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002654320987654321,
+      "loss": 0.7115,
+      "step": 1785
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00026502057613168726,
+      "loss": 0.7538,
+      "step": 1790
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002646090534979424,
+      "loss": 0.7321,
+      "step": 1795
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002641975308641976,
+      "loss": 0.7212,
+      "step": 1800
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002637860082304527,
+      "loss": 0.747,
+      "step": 1805
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00026337448559670784,
+      "loss": 0.7606,
+      "step": 1810
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.000262962962962963,
+      "loss": 0.7344,
+      "step": 1815
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002625514403292181,
+      "loss": 0.7783,
+      "step": 1820
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00026213991769547326,
+      "loss": 0.7556,
+      "step": 1825
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002617283950617284,
+      "loss": 0.7585,
+      "step": 1830
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002613168724279836,
+      "loss": 0.7359,
+      "step": 1835
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002609053497942387,
+      "loss": 0.7185,
+      "step": 1840
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00026049382716049384,
+      "loss": 0.7573,
+      "step": 1845
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.000260082304526749,
+      "loss": 0.7619,
+      "step": 1850
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002596707818930041,
+      "loss": 0.7611,
+      "step": 1855
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00025925925925925926,
+      "loss": 0.7647,
+      "step": 1860
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002588477366255144,
+      "loss": 0.7398,
+      "step": 1865
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002584362139917695,
+      "loss": 0.7683,
+      "step": 1870
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002580246913580247,
+      "loss": 0.7817,
+      "step": 1875
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00025761316872427984,
+      "loss": 0.742,
+      "step": 1880
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.000257201646090535,
+      "loss": 0.7509,
+      "step": 1885
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002567901234567901,
+      "loss": 0.7058,
+      "step": 1890
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00025637860082304526,
+      "loss": 0.7635,
+      "step": 1895
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002559670781893004,
+      "loss": 0.734,
+      "step": 1900
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00025555555555555553,
+      "loss": 0.7416,
+      "step": 1905
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002551440329218107,
+      "loss": 0.7071,
+      "step": 1910
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00025473251028806584,
+      "loss": 0.7275,
+      "step": 1915
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.000254320987654321,
+      "loss": 0.7413,
+      "step": 1920
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002539094650205761,
+      "loss": 0.7703,
+      "step": 1925
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00025349794238683127,
+      "loss": 0.7331,
+      "step": 1930
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002530864197530864,
+      "loss": 0.7251,
+      "step": 1935
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002526748971193416,
+      "loss": 0.7341,
+      "step": 1940
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00025226337448559674,
+      "loss": 0.7079,
+      "step": 1945
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00025185185185185185,
+      "loss": 0.7615,
+      "step": 1950
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.000251440329218107,
+      "loss": 0.7144,
+      "step": 1955
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00025102880658436216,
+      "loss": 0.7527,
+      "step": 1960
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0002506172839506173,
+      "loss": 0.7327,
+      "step": 1965
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002502057613168725,
+      "loss": 0.7173,
+      "step": 1970
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002497942386831276,
+      "loss": 0.7239,
+      "step": 1975
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00024938271604938274,
+      "loss": 0.7442,
+      "step": 1980
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002489711934156379,
+      "loss": 0.7396,
+      "step": 1985
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.000248559670781893,
+      "loss": 0.7365,
+      "step": 1990
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00024814814814814816,
+      "loss": 0.7037,
+      "step": 1995
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002477366255144033,
+      "loss": 0.721,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002473251028806585,
+      "loss": 0.7353,
+      "step": 2005
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002469135802469136,
+      "loss": 0.7648,
+      "step": 2010
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00024650205761316874,
+      "loss": 0.7445,
+      "step": 2015
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0002460905349794239,
+      "loss": 0.7664,
+      "step": 2020
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.000245679012345679,
+      "loss": 0.7202,
+      "step": 2025
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00024526748971193417,
+      "loss": 0.7147,
+      "step": 2030
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0002448559670781893,
+      "loss": 0.722,
+      "step": 2035
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0002444444444444445,
+      "loss": 0.7539,
+      "step": 2040
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002440329218106996,
+      "loss": 0.7681,
+      "step": 2045
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00024362139917695475,
+      "loss": 0.7304,
+      "step": 2050
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002432098765432099,
+      "loss": 0.7432,
+      "step": 2055
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.000242798353909465,
+      "loss": 0.6945,
+      "step": 2060
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00024238683127572017,
+      "loss": 0.7426,
+      "step": 2065
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00024197530864197533,
+      "loss": 0.7144,
+      "step": 2070
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00024156378600823048,
+      "loss": 0.7761,
+      "step": 2075
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0002411522633744856,
+      "loss": 0.7402,
+      "step": 2080
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00024074074074074075,
+      "loss": 0.7376,
+      "step": 2085
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0002403292181069959,
+      "loss": 0.7231,
+      "step": 2090
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023991769547325104,
+      "loss": 0.7461,
+      "step": 2095
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023950617283950617,
+      "loss": 0.7215,
+      "step": 2100
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023909465020576133,
+      "loss": 0.7419,
+      "step": 2105
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023868312757201646,
+      "loss": 0.7502,
+      "step": 2110
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023827160493827162,
+      "loss": 0.7294,
+      "step": 2115
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00023786008230452678,
+      "loss": 0.7904,
+      "step": 2120
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00023744855967078194,
+      "loss": 0.7418,
+      "step": 2125
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00023703703703703704,
+      "loss": 0.7371,
+      "step": 2130
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0002366255144032922,
+      "loss": 0.7384,
+      "step": 2135
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00023621399176954736,
+      "loss": 0.7552,
+      "step": 2140
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023580246913580246,
+      "loss": 0.7516,
+      "step": 2145
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023539094650205762,
+      "loss": 0.7303,
+      "step": 2150
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023497942386831278,
+      "loss": 0.7496,
+      "step": 2155
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023456790123456794,
+      "loss": 0.7135,
+      "step": 2160
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023415637860082304,
+      "loss": 0.7283,
+      "step": 2165
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0002337448559670782,
+      "loss": 0.751,
+      "step": 2170
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00023333333333333336,
+      "loss": 0.7183,
+      "step": 2175
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00023292181069958846,
+      "loss": 0.7242,
+      "step": 2180
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00023251028806584362,
+      "loss": 0.725,
+      "step": 2185
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00023209876543209878,
+      "loss": 0.753,
+      "step": 2190
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002316872427983539,
+      "loss": 0.7664,
+      "step": 2195
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00023127572016460904,
+      "loss": 0.7444,
+      "step": 2200
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002308641975308642,
+      "loss": 0.7226,
+      "step": 2205
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00023045267489711936,
+      "loss": 0.7653,
+      "step": 2210
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002300411522633745,
+      "loss": 0.7382,
+      "step": 2215
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00022962962962962965,
+      "loss": 0.7242,
+      "step": 2220
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002292181069958848,
+      "loss": 0.7215,
+      "step": 2225
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002288065843621399,
+      "loss": 0.724,
+      "step": 2230
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00022839506172839507,
+      "loss": 0.7439,
+      "step": 2235
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00022798353909465023,
+      "loss": 0.699,
+      "step": 2240
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002275720164609054,
+      "loss": 0.7602,
+      "step": 2245
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002271604938271605,
+      "loss": 0.7103,
+      "step": 2250
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00022674897119341565,
+      "loss": 0.7015,
+      "step": 2255
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002263374485596708,
+      "loss": 0.7404,
+      "step": 2260
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00022592592592592591,
+      "loss": 0.7127,
+      "step": 2265
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00022551440329218107,
+      "loss": 0.7299,
+      "step": 2270
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00022510288065843623,
+      "loss": 0.7174,
+      "step": 2275
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002246913580246914,
+      "loss": 0.7454,
+      "step": 2280
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002242798353909465,
+      "loss": 0.7159,
+      "step": 2285
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00022386831275720165,
+      "loss": 0.7263,
+      "step": 2290
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0002234567901234568,
+      "loss": 0.7148,
+      "step": 2295
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00022304526748971192,
+      "loss": 0.7447,
+      "step": 2300
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00022263374485596707,
+      "loss": 0.7326,
+      "step": 2305
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00022222222222222223,
+      "loss": 0.7428,
+      "step": 2310
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00022181069958847736,
+      "loss": 0.7587,
+      "step": 2315
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00022139917695473252,
+      "loss": 0.759,
+      "step": 2320
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00022098765432098768,
+      "loss": 0.7716,
+      "step": 2325
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002205761316872428,
+      "loss": 0.74,
+      "step": 2330
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00022016460905349794,
+      "loss": 0.7255,
+      "step": 2335
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002197530864197531,
+      "loss": 0.7547,
+      "step": 2340
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021934156378600826,
+      "loss": 0.7359,
+      "step": 2345
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021893004115226337,
+      "loss": 0.6987,
+      "step": 2350
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021851851851851852,
+      "loss": 0.7233,
+      "step": 2355
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021810699588477368,
+      "loss": 0.6945,
+      "step": 2360
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021769547325102884,
+      "loss": 0.7566,
+      "step": 2365
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00021728395061728395,
+      "loss": 0.728,
+      "step": 2370
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002168724279835391,
+      "loss": 0.7167,
+      "step": 2375
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00021646090534979426,
+      "loss": 0.7576,
+      "step": 2380
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00021604938271604937,
+      "loss": 0.7246,
+      "step": 2385
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00021563786008230453,
+      "loss": 0.755,
+      "step": 2390
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00021522633744855968,
+      "loss": 0.6983,
+      "step": 2395
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00021481481481481484,
+      "loss": 0.7369,
+      "step": 2400
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00021440329218106995,
+      "loss": 0.7074,
+      "step": 2405
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0002139917695473251,
+      "loss": 0.7317,
+      "step": 2410
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00021358024691358026,
+      "loss": 0.7086,
+      "step": 2415
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0002131687242798354,
+      "loss": 0.7356,
+      "step": 2420
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00021275720164609055,
+      "loss": 0.7652,
+      "step": 2425
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00021234567901234569,
+      "loss": 0.7488,
+      "step": 2430
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00021193415637860082,
+      "loss": 0.746,
+      "step": 2435
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00021152263374485598,
+      "loss": 0.7454,
+      "step": 2440
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00021111111111111113,
+      "loss": 0.72,
+      "step": 2445
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0002106995884773663,
+      "loss": 0.7299,
+      "step": 2450
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0002102880658436214,
+      "loss": 0.7436,
+      "step": 2455
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00020987654320987656,
+      "loss": 0.7068,
+      "step": 2460
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00020946502057613171,
+      "loss": 0.711,
+      "step": 2465
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00020905349794238682,
+      "loss": 0.7473,
+      "step": 2470
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00020864197530864198,
+      "loss": 0.7016,
+      "step": 2475
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00020823045267489714,
+      "loss": 0.7049,
+      "step": 2480
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002078189300411523,
+      "loss": 0.7268,
+      "step": 2485
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002074074074074074,
+      "loss": 0.7239,
+      "step": 2490
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020699588477366256,
+      "loss": 0.698,
+      "step": 2495
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020658436213991772,
+      "loss": 0.7573,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020617283950617282,
+      "loss": 0.7309,
+      "step": 2505
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020576131687242798,
+      "loss": 0.6628,
+      "step": 2510
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020534979423868314,
+      "loss": 0.656,
+      "step": 2515
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0002049382716049383,
+      "loss": 0.6737,
+      "step": 2520
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00020452674897119343,
+      "loss": 0.6903,
+      "step": 2525
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00020411522633744856,
+      "loss": 0.6674,
+      "step": 2530
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00020370370370370372,
+      "loss": 0.6507,
+      "step": 2535
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00020329218106995885,
+      "loss": 0.6948,
+      "step": 2540
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.000202880658436214,
+      "loss": 0.6662,
+      "step": 2545
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00020246913580246917,
+      "loss": 0.6624,
+      "step": 2550
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00020205761316872427,
+      "loss": 0.6791,
+      "step": 2555
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00020164609053497943,
+      "loss": 0.7088,
+      "step": 2560
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0002012345679012346,
+      "loss": 0.6796,
+      "step": 2565
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00020082304526748975,
+      "loss": 0.6601,
+      "step": 2570
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00020041152263374485,
+      "loss": 0.6865,
+      "step": 2575
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0002,
+      "loss": 0.6725,
+      "step": 2580
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00019958847736625514,
+      "loss": 0.6743,
+      "step": 2585
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0001991769547325103,
+      "loss": 0.6395,
+      "step": 2590
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00019876543209876543,
+      "loss": 0.6522,
+      "step": 2595
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0001983539094650206,
+      "loss": 0.6868,
+      "step": 2600
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00019794238683127572,
+      "loss": 0.6861,
+      "step": 2605
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00019753086419753085,
+      "loss": 0.6843,
+      "step": 2610
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.000197119341563786,
+      "loss": 0.6732,
+      "step": 2615
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00019670781893004114,
+      "loss": 0.6676,
+      "step": 2620
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0001962962962962963,
+      "loss": 0.6782,
+      "step": 2625
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00019588477366255146,
+      "loss": 0.6937,
+      "step": 2630
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0001954732510288066,
+      "loss": 0.6823,
+      "step": 2635
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00019506172839506175,
+      "loss": 0.6839,
+      "step": 2640
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019465020576131688,
+      "loss": 0.6351,
+      "step": 2645
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019423868312757204,
+      "loss": 0.7157,
+      "step": 2650
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019382716049382717,
+      "loss": 0.6591,
+      "step": 2655
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019341563786008233,
+      "loss": 0.6826,
+      "step": 2660
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019300411522633746,
+      "loss": 0.6732,
+      "step": 2665
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0001925925925925926,
+      "loss": 0.6795,
+      "step": 2670
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00019218106995884775,
+      "loss": 0.6845,
+      "step": 2675
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00019176954732510288,
+      "loss": 0.649,
+      "step": 2680
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00019135802469135804,
+      "loss": 0.6684,
+      "step": 2685
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00019094650205761317,
+      "loss": 0.6712,
+      "step": 2690
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00019053497942386833,
+      "loss": 0.6665,
+      "step": 2695
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00019012345679012346,
+      "loss": 0.6426,
+      "step": 2700
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0001897119341563786,
+      "loss": 0.6561,
+      "step": 2705
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00018930041152263375,
+      "loss": 0.6664,
+      "step": 2710
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00018888888888888888,
+      "loss": 0.6746,
+      "step": 2715
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018847736625514404,
+      "loss": 0.6497,
+      "step": 2720
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018806584362139917,
+      "loss": 0.6811,
+      "step": 2725
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018765432098765433,
+      "loss": 0.6608,
+      "step": 2730
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018724279835390946,
+      "loss": 0.6655,
+      "step": 2735
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018683127572016462,
+      "loss": 0.7014,
+      "step": 2740
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00018641975308641978,
+      "loss": 0.6889,
+      "step": 2745
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0001860082304526749,
+      "loss": 0.6805,
+      "step": 2750
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00018559670781893007,
+      "loss": 0.6629,
+      "step": 2755
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0001851851851851852,
+      "loss": 0.6593,
+      "step": 2760
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00018477366255144033,
+      "loss": 0.6902,
+      "step": 2765
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0001843621399176955,
+      "loss": 0.6777,
+      "step": 2770
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00018395061728395062,
+      "loss": 0.7127,
+      "step": 2775
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00018353909465020578,
+      "loss": 0.6551,
+      "step": 2780
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00018312757201646091,
+      "loss": 0.6703,
+      "step": 2785
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00018271604938271605,
+      "loss": 0.6776,
+      "step": 2790
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0001823045267489712,
+      "loss": 0.6574,
+      "step": 2795
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00018189300411522634,
+      "loss": 0.7154,
+      "step": 2800
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0001814814814814815,
+      "loss": 0.6749,
+      "step": 2805
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00018106995884773663,
+      "loss": 0.695,
+      "step": 2810
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00018065843621399178,
+      "loss": 0.6685,
+      "step": 2815
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00018024691358024692,
+      "loss": 0.642,
+      "step": 2820
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00017983539094650205,
+      "loss": 0.6873,
+      "step": 2825
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0001794238683127572,
+      "loss": 0.6506,
+      "step": 2830
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00017901234567901234,
+      "loss": 0.6695,
+      "step": 2835
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0001786008230452675,
+      "loss": 0.651,
+      "step": 2840
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00017818930041152265,
+      "loss": 0.6585,
+      "step": 2845
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 0.6717,
+      "step": 2850
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00017736625514403294,
+      "loss": 0.6524,
+      "step": 2855
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00017695473251028808,
+      "loss": 0.6679,
+      "step": 2860
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00017654320987654323,
+      "loss": 0.6719,
+      "step": 2865
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00017613168724279837,
+      "loss": 0.6662,
+      "step": 2870
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00017572016460905352,
+      "loss": 0.6624,
+      "step": 2875
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00017530864197530866,
+      "loss": 0.69,
+      "step": 2880
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0001748971193415638,
+      "loss": 0.6629,
+      "step": 2885
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00017448559670781895,
+      "loss": 0.6566,
+      "step": 2890
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00017407407407407408,
+      "loss": 0.6711,
+      "step": 2895
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00017366255144032924,
+      "loss": 0.6995,
+      "step": 2900
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00017325102880658437,
+      "loss": 0.6597,
+      "step": 2905
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0001728395061728395,
+      "loss": 0.6685,
+      "step": 2910
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00017242798353909466,
+      "loss": 0.6649,
+      "step": 2915
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0001720164609053498,
+      "loss": 0.6824,
+      "step": 2920
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00017160493827160495,
+      "loss": 0.6484,
+      "step": 2925
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00017119341563786008,
+      "loss": 0.6693,
+      "step": 2930
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00017078189300411524,
+      "loss": 0.629,
+      "step": 2935
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00017037037037037037,
+      "loss": 0.6588,
+      "step": 2940
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00016995884773662553,
+      "loss": 0.6771,
+      "step": 2945
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00016954732510288066,
+      "loss": 0.6773,
+      "step": 2950
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00016913580246913582,
+      "loss": 0.6307,
+      "step": 2955
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00016872427983539098,
+      "loss": 0.6809,
+      "step": 2960
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0001683127572016461,
+      "loss": 0.6748,
+      "step": 2965
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00016790123456790124,
+      "loss": 0.6708,
+      "step": 2970
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0001674897119341564,
+      "loss": 0.6754,
+      "step": 2975
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00016707818930041153,
+      "loss": 0.6676,
+      "step": 2980
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 0.6662,
+      "step": 2985
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00016625514403292182,
+      "loss": 0.6933,
+      "step": 2990
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00016584362139917695,
+      "loss": 0.6879,
+      "step": 2995
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0001654320987654321,
+      "loss": 0.6979,
+      "step": 3000
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00016502057613168724,
+      "loss": 0.657,
+      "step": 3005
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0001646090534979424,
+      "loss": 0.6704,
+      "step": 3010
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00016419753086419753,
+      "loss": 0.6394,
+      "step": 3015
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0001637860082304527,
+      "loss": 0.6594,
+      "step": 3020
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00016337448559670782,
+      "loss": 0.6584,
+      "step": 3025
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00016296296296296295,
+      "loss": 0.6593,
+      "step": 3030
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0001625514403292181,
+      "loss": 0.6538,
+      "step": 3035
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00016213991769547324,
+      "loss": 0.6572,
+      "step": 3040
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0001617283950617284,
+      "loss": 0.6999,
+      "step": 3045
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00016131687242798353,
+      "loss": 0.6658,
+      "step": 3050
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0001609053497942387,
+      "loss": 0.6809,
+      "step": 3055
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00016049382716049385,
+      "loss": 0.6685,
+      "step": 3060
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00016008230452674898,
+      "loss": 0.6532,
+      "step": 3065
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00015967078189300414,
+      "loss": 0.6644,
+      "step": 3070
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00015925925925925927,
+      "loss": 0.6721,
+      "step": 3075
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00015884773662551443,
+      "loss": 0.6569,
+      "step": 3080
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00015843621399176956,
+      "loss": 0.6832,
+      "step": 3085
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.0001580246913580247,
+      "loss": 0.6721,
+      "step": 3090
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00015761316872427985,
+      "loss": 0.6532,
+      "step": 3095
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00015720164609053498,
+      "loss": 0.6955,
+      "step": 3100
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00015679012345679014,
+      "loss": 0.6853,
+      "step": 3105
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00015637860082304527,
+      "loss": 0.6943,
+      "step": 3110
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0001559670781893004,
+      "loss": 0.6815,
+      "step": 3115
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 0.6972,
+      "step": 3120
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0001551440329218107,
+      "loss": 0.6959,
+      "step": 3125
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00015473251028806585,
+      "loss": 0.6795,
+      "step": 3130
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00015432098765432098,
+      "loss": 0.6352,
+      "step": 3135
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00015390946502057614,
+      "loss": 0.6601,
+      "step": 3140
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00015349794238683127,
+      "loss": 0.676,
+      "step": 3145
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0001530864197530864,
+      "loss": 0.6352,
+      "step": 3150
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00015267489711934156,
+      "loss": 0.6434,
+      "step": 3155
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00015226337448559672,
+      "loss": 0.673,
+      "step": 3160
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00015185185185185185,
+      "loss": 0.6963,
+      "step": 3165
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.000151440329218107,
+      "loss": 0.6643,
+      "step": 3170
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00015102880658436214,
+      "loss": 0.6757,
+      "step": 3175
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0001506172839506173,
+      "loss": 0.6681,
+      "step": 3180
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00015020576131687243,
+      "loss": 0.6935,
+      "step": 3185
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0001497942386831276,
+      "loss": 0.6894,
+      "step": 3190
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00014938271604938272,
+      "loss": 0.64,
+      "step": 3195
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00014897119341563788,
+      "loss": 0.6481,
+      "step": 3200
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00014855967078189301,
+      "loss": 0.6644,
+      "step": 3205
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00014814814814814815,
+      "loss": 0.6358,
+      "step": 3210
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0001477366255144033,
+      "loss": 0.6678,
+      "step": 3215
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00014732510288065844,
+      "loss": 0.6755,
+      "step": 3220
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0001469135802469136,
+      "loss": 0.6486,
+      "step": 3225
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00014650205761316873,
+      "loss": 0.666,
+      "step": 3230
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00014609053497942386,
+      "loss": 0.6689,
+      "step": 3235
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00014567901234567902,
+      "loss": 0.6737,
+      "step": 3240
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00014526748971193415,
+      "loss": 0.6659,
+      "step": 3245
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0001448559670781893,
+      "loss": 0.6744,
+      "step": 3250
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00014444444444444444,
+      "loss": 0.648,
+      "step": 3255
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0001440329218106996,
+      "loss": 0.6455,
+      "step": 3260
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00014362139917695473,
+      "loss": 0.659,
+      "step": 3265
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00014320987654320989,
+      "loss": 0.6519,
+      "step": 3270
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00014279835390946504,
+      "loss": 0.6972,
+      "step": 3275
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00014238683127572018,
+      "loss": 0.6592,
+      "step": 3280
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00014197530864197534,
+      "loss": 0.6757,
+      "step": 3285
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00014156378600823047,
+      "loss": 0.6684,
+      "step": 3290
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0001411522633744856,
+      "loss": 0.6754,
+      "step": 3295
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00014074074074074076,
+      "loss": 0.6738,
+      "step": 3300
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0001403292181069959,
+      "loss": 0.683,
+      "step": 3305
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00013991769547325105,
+      "loss": 0.6434,
+      "step": 3310
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00013950617283950618,
+      "loss": 0.6416,
+      "step": 3315
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00013909465020576134,
+      "loss": 0.6687,
+      "step": 3320
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00013868312757201647,
+      "loss": 0.6663,
+      "step": 3325
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0001382716049382716,
+      "loss": 0.7113,
+      "step": 3330
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00013786008230452676,
+      "loss": 0.6625,
+      "step": 3335
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0001374485596707819,
+      "loss": 0.6593,
+      "step": 3340
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00013703703703703705,
+      "loss": 0.6707,
+      "step": 3345
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00013662551440329218,
+      "loss": 0.6567,
+      "step": 3350
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0001362139917695473,
+      "loss": 0.6622,
+      "step": 3355
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00013580246913580247,
+      "loss": 0.6849,
+      "step": 3360
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0001353909465020576,
+      "loss": 0.657,
+      "step": 3365
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00013497942386831276,
+      "loss": 0.6452,
+      "step": 3370
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00013456790123456792,
+      "loss": 0.6486,
+      "step": 3375
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00013415637860082305,
+      "loss": 0.6737,
+      "step": 3380
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0001337448559670782,
+      "loss": 0.6793,
+      "step": 3385
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.6869,
+      "step": 3390
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0001329218106995885,
+      "loss": 0.6594,
+      "step": 3395
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00013251028806584363,
+      "loss": 0.6793,
+      "step": 3400
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0001320987654320988,
+      "loss": 0.6879,
+      "step": 3405
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00013168724279835392,
+      "loss": 0.695,
+      "step": 3410
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00013127572016460905,
+      "loss": 0.6648,
+      "step": 3415
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.0001308641975308642,
+      "loss": 0.6162,
+      "step": 3420
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00013045267489711934,
+      "loss": 0.642,
+      "step": 3425
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.0001300411522633745,
+      "loss": 0.6618,
+      "step": 3430
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00012962962962962963,
+      "loss": 0.6535,
+      "step": 3435
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00012921810699588476,
+      "loss": 0.6664,
+      "step": 3440
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00012880658436213992,
+      "loss": 0.6427,
+      "step": 3445
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00012839506172839505,
+      "loss": 0.6584,
+      "step": 3450
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0001279835390946502,
+      "loss": 0.657,
+      "step": 3455
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00012757201646090534,
+      "loss": 0.6494,
+      "step": 3460
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0001271604938271605,
+      "loss": 0.6553,
+      "step": 3465
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00012674897119341563,
+      "loss": 0.6755,
+      "step": 3470
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0001263374485596708,
+      "loss": 0.6599,
+      "step": 3475
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00012592592592592592,
+      "loss": 0.6564,
+      "step": 3480
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00012551440329218108,
+      "loss": 0.6526,
+      "step": 3485
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00012510288065843624,
+      "loss": 0.6439,
+      "step": 3490
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00012469135802469137,
+      "loss": 0.6459,
+      "step": 3495
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0001242798353909465,
+      "loss": 0.6573,
+      "step": 3500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00012386831275720166,
+      "loss": 0.6773,
+      "step": 3505
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0001234567901234568,
+      "loss": 0.68,
+      "step": 3510
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00012304526748971195,
+      "loss": 0.6615,
+      "step": 3515
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00012263374485596708,
+      "loss": 0.6886,
+      "step": 3520
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00012222222222222224,
+      "loss": 0.667,
+      "step": 3525
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00012181069958847737,
+      "loss": 0.677,
+      "step": 3530
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.0001213991769547325,
+      "loss": 0.6709,
+      "step": 3535
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00012098765432098766,
+      "loss": 0.6258,
+      "step": 3540
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.0001205761316872428,
+      "loss": 0.6795,
+      "step": 3545
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00012016460905349795,
+      "loss": 0.6673,
+      "step": 3550
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00011975308641975308,
+      "loss": 0.6708,
+      "step": 3555
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00011934156378600823,
+      "loss": 0.6466,
+      "step": 3560
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00011893004115226339,
+      "loss": 0.6339,
+      "step": 3565
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00011851851851851852,
+      "loss": 0.6838,
+      "step": 3570
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00011810699588477368,
+      "loss": 0.6179,
+      "step": 3575
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00011769547325102881,
+      "loss": 0.6357,
+      "step": 3580
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00011728395061728397,
+      "loss": 0.6807,
+      "step": 3585
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.0001168724279835391,
+      "loss": 0.6365,
+      "step": 3590
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00011646090534979423,
+      "loss": 0.6518,
+      "step": 3595
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00011604938271604939,
+      "loss": 0.6467,
+      "step": 3600
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00011563786008230452,
+      "loss": 0.6537,
+      "step": 3605
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00011522633744855968,
+      "loss": 0.6324,
+      "step": 3610
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00011481481481481482,
+      "loss": 0.6826,
+      "step": 3615
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00011440329218106996,
+      "loss": 0.6643,
+      "step": 3620
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00011399176954732511,
+      "loss": 0.6464,
+      "step": 3625
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00011358024691358025,
+      "loss": 0.6601,
+      "step": 3630
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.0001131687242798354,
+      "loss": 0.6596,
+      "step": 3635
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00011275720164609054,
+      "loss": 0.72,
+      "step": 3640
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.0001123456790123457,
+      "loss": 0.7157,
+      "step": 3645
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00011193415637860083,
+      "loss": 0.6641,
+      "step": 3650
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00011152263374485596,
+      "loss": 0.6631,
+      "step": 3655
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 0.6454,
+      "step": 3660
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00011069958847736626,
+      "loss": 0.6957,
+      "step": 3665
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.0001102880658436214,
+      "loss": 0.6535,
+      "step": 3670
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00010987654320987655,
+      "loss": 0.6675,
+      "step": 3675
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00010946502057613168,
+      "loss": 0.6458,
+      "step": 3680
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00010905349794238684,
+      "loss": 0.6507,
+      "step": 3685
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00010864197530864197,
+      "loss": 0.6818,
+      "step": 3690
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00010823045267489713,
+      "loss": 0.6752,
+      "step": 3695
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00010781893004115226,
+      "loss": 0.6645,
+      "step": 3700
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00010740740740740742,
+      "loss": 0.6414,
+      "step": 3705
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00010699588477366255,
+      "loss": 0.675,
+      "step": 3710
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.0001065843621399177,
+      "loss": 0.6597,
+      "step": 3715
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00010617283950617284,
+      "loss": 0.6637,
+      "step": 3720
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00010576131687242799,
+      "loss": 0.664,
+      "step": 3725
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00010534979423868315,
+      "loss": 0.6638,
+      "step": 3730
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00010493827160493828,
+      "loss": 0.6413,
+      "step": 3735
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00010452674897119341,
+      "loss": 0.6242,
+      "step": 3740
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00010411522633744857,
+      "loss": 0.6653,
+      "step": 3745
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.0001037037037037037,
+      "loss": 0.6947,
+      "step": 3750
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00010329218106995886,
+      "loss": 0.6801,
+      "step": 3755
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00010288065843621399,
+      "loss": 0.671,
+      "step": 3760
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00010246913580246915,
+      "loss": 0.6505,
+      "step": 3765
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00010205761316872428,
+      "loss": 0.6738,
+      "step": 3770
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00010164609053497942,
+      "loss": 0.6478,
+      "step": 3775
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00010123456790123458,
+      "loss": 0.6652,
+      "step": 3780
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00010082304526748971,
+      "loss": 0.6456,
+      "step": 3785
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00010041152263374487,
+      "loss": 0.6509,
+      "step": 3790
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.0001,
+      "loss": 0.6623,
+      "step": 3795
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 9.958847736625515e-05,
+      "loss": 0.6727,
+      "step": 3800
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 9.91769547325103e-05,
+      "loss": 0.676,
+      "step": 3805
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 9.876543209876543e-05,
+      "loss": 0.6662,
+      "step": 3810
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 9.835390946502057e-05,
+      "loss": 0.6767,
+      "step": 3815
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 9.794238683127573e-05,
+      "loss": 0.6278,
+      "step": 3820
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 9.753086419753087e-05,
+      "loss": 0.6769,
+      "step": 3825
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 9.711934156378602e-05,
+      "loss": 0.667,
+      "step": 3830
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 9.670781893004116e-05,
+      "loss": 0.6392,
+      "step": 3835
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 9.62962962962963e-05,
+      "loss": 0.6479,
+      "step": 3840
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 9.588477366255144e-05,
+      "loss": 0.6958,
+      "step": 3845
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 9.547325102880659e-05,
+      "loss": 0.6636,
+      "step": 3850
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 9.506172839506173e-05,
+      "loss": 0.6722,
+      "step": 3855
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 9.465020576131688e-05,
+      "loss": 0.6688,
+      "step": 3860
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 9.423868312757202e-05,
+      "loss": 0.6814,
+      "step": 3865
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 9.382716049382717e-05,
+      "loss": 0.679,
+      "step": 3870
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.341563786008231e-05,
+      "loss": 0.6536,
+      "step": 3875
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.300411522633746e-05,
+      "loss": 0.6783,
+      "step": 3880
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.25925925925926e-05,
+      "loss": 0.6424,
+      "step": 3885
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.218106995884775e-05,
+      "loss": 0.6695,
+      "step": 3890
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.176954732510289e-05,
+      "loss": 0.6941,
+      "step": 3895
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.135802469135802e-05,
+      "loss": 0.6887,
+      "step": 3900
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.094650205761317e-05,
+      "loss": 0.6789,
+      "step": 3905
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.053497942386831e-05,
+      "loss": 0.6819,
+      "step": 3910
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.012345679012346e-05,
+      "loss": 0.6571,
+      "step": 3915
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 8.97119341563786e-05,
+      "loss": 0.6527,
+      "step": 3920
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 8.930041152263375e-05,
+      "loss": 0.6656,
+      "step": 3925
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 0.6551,
+      "step": 3930
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 8.847736625514404e-05,
+      "loss": 0.6502,
+      "step": 3935
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 8.806584362139918e-05,
+      "loss": 0.6458,
+      "step": 3940
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 8.765432098765433e-05,
+      "loss": 0.6617,
+      "step": 3945
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 8.724279835390947e-05,
+      "loss": 0.6444,
+      "step": 3950
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 8.683127572016462e-05,
+      "loss": 0.6629,
+      "step": 3955
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 8.641975308641975e-05,
+      "loss": 0.6683,
+      "step": 3960
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 8.60082304526749e-05,
+      "loss": 0.6483,
+      "step": 3965
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 8.559670781893004e-05,
+      "loss": 0.6623,
+      "step": 3970
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 8.518518518518518e-05,
+      "loss": 0.6491,
+      "step": 3975
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 8.477366255144033e-05,
+      "loss": 0.6394,
+      "step": 3980
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 8.436213991769549e-05,
+      "loss": 0.6494,
+      "step": 3985
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 8.395061728395062e-05,
+      "loss": 0.6516,
+      "step": 3990
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 8.353909465020576e-05,
+      "loss": 0.6664,
+      "step": 3995
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 8.312757201646091e-05,
+      "loss": 0.6822,
+      "step": 4000
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 8.271604938271605e-05,
+      "loss": 0.6335,
+      "step": 4005
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 8.23045267489712e-05,
+      "loss": 0.6386,
+      "step": 4010
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 8.189300411522634e-05,
+      "loss": 0.6495,
+      "step": 4015
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.6784,
+      "step": 4020
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 8.106995884773662e-05,
+      "loss": 0.6522,
+      "step": 4025
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 8.065843621399177e-05,
+      "loss": 0.6292,
+      "step": 4030
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 8.024691358024692e-05,
+      "loss": 0.6513,
+      "step": 4035
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 7.983539094650207e-05,
+      "loss": 0.622,
+      "step": 4040
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 7.942386831275721e-05,
+      "loss": 0.6619,
+      "step": 4045
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 7.901234567901235e-05,
+      "loss": 0.651,
+      "step": 4050
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 7.860082304526749e-05,
+      "loss": 0.6538,
+      "step": 4055
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 7.818930041152264e-05,
+      "loss": 0.6572,
+      "step": 4060
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 7.777777777777778e-05,
+      "loss": 0.6935,
+      "step": 4065
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 7.736625514403293e-05,
+      "loss": 0.6598,
+      "step": 4070
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 7.695473251028807e-05,
+      "loss": 0.6533,
+      "step": 4075
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 7.65432098765432e-05,
+      "loss": 0.665,
+      "step": 4080
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 7.613168724279836e-05,
+      "loss": 0.651,
+      "step": 4085
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 7.57201646090535e-05,
+      "loss": 0.6914,
+      "step": 4090
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 7.530864197530865e-05,
+      "loss": 0.6431,
+      "step": 4095
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 7.48971193415638e-05,
+      "loss": 0.6753,
+      "step": 4100
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 7.448559670781894e-05,
+      "loss": 0.6814,
+      "step": 4105
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 7.407407407407407e-05,
+      "loss": 0.6386,
+      "step": 4110
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 7.366255144032922e-05,
+      "loss": 0.6307,
+      "step": 4115
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 7.325102880658436e-05,
+      "loss": 0.6401,
+      "step": 4120
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 7.283950617283951e-05,
+      "loss": 0.6496,
+      "step": 4125
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 7.242798353909465e-05,
+      "loss": 0.6593,
+      "step": 4130
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 7.20164609053498e-05,
+      "loss": 0.6472,
+      "step": 4135
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 7.160493827160494e-05,
+      "loss": 0.6746,
+      "step": 4140
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 7.119341563786009e-05,
+      "loss": 0.6498,
+      "step": 4145
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 7.078189300411523e-05,
+      "loss": 0.6597,
+      "step": 4150
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 7.037037037037038e-05,
+      "loss": 0.671,
+      "step": 4155
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 6.995884773662552e-05,
+      "loss": 0.6786,
+      "step": 4160
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 6.954732510288067e-05,
+      "loss": 0.6846,
+      "step": 4165
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 6.91358024691358e-05,
+      "loss": 0.6619,
+      "step": 4170
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 6.872427983539094e-05,
+      "loss": 0.6755,
+      "step": 4175
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 6.831275720164609e-05,
+      "loss": 0.6406,
+      "step": 4180
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 6.790123456790123e-05,
+      "loss": 0.671,
+      "step": 4185
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 6.748971193415638e-05,
+      "loss": 0.6448,
+      "step": 4190
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 6.707818930041152e-05,
+      "loss": 0.6594,
+      "step": 4195
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.6626,
+      "step": 4200
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 6.625514403292181e-05,
+      "loss": 0.6577,
+      "step": 4205
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 6.584362139917696e-05,
+      "loss": 0.6468,
+      "step": 4210
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 6.54320987654321e-05,
+      "loss": 0.6836,
+      "step": 4215
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 6.502057613168725e-05,
+      "loss": 0.6766,
+      "step": 4220
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 6.460905349794238e-05,
+      "loss": 0.6639,
+      "step": 4225
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 6.419753086419753e-05,
+      "loss": 0.6653,
+      "step": 4230
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 6.378600823045267e-05,
+      "loss": 0.6501,
+      "step": 4235
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 6.337448559670782e-05,
+      "loss": 0.6775,
+      "step": 4240
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 6.296296296296296e-05,
+      "loss": 0.661,
+      "step": 4245
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 6.255144032921812e-05,
+      "loss": 0.6417,
+      "step": 4250
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 6.213991769547325e-05,
+      "loss": 0.6626,
+      "step": 4255
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 6.17283950617284e-05,
+      "loss": 0.667,
+      "step": 4260
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 6.131687242798354e-05,
+      "loss": 0.6683,
+      "step": 4265
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 6.0905349794238687e-05,
+      "loss": 0.6523,
+      "step": 4270
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 6.049382716049383e-05,
+      "loss": 0.6686,
+      "step": 4275
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 6.0082304526748977e-05,
+      "loss": 0.6365,
+      "step": 4280
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 5.9670781893004115e-05,
+      "loss": 0.6211,
+      "step": 4285
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 5.925925925925926e-05,
+      "loss": 0.6414,
+      "step": 4290
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 5.8847736625514405e-05,
+      "loss": 0.6488,
+      "step": 4295
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 5.843621399176955e-05,
+      "loss": 0.6506,
+      "step": 4300
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 5.8024691358024695e-05,
+      "loss": 0.6692,
+      "step": 4305
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 5.761316872427984e-05,
+      "loss": 0.6617,
+      "step": 4310
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 5.720164609053498e-05,
+      "loss": 0.6464,
+      "step": 4315
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 5.679012345679012e-05,
+      "loss": 0.6432,
+      "step": 4320
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 5.637860082304527e-05,
+      "loss": 0.6642,
+      "step": 4325
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 5.596707818930041e-05,
+      "loss": 0.6487,
+      "step": 4330
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 5.555555555555556e-05,
+      "loss": 0.6384,
+      "step": 4335
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 5.51440329218107e-05,
+      "loss": 0.6167,
+      "step": 4340
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 5.473251028806584e-05,
+      "loss": 0.6576,
+      "step": 4345
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 5.4320987654320986e-05,
+      "loss": 0.6482,
+      "step": 4350
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 5.390946502057613e-05,
+      "loss": 0.6526,
+      "step": 4355
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 5.3497942386831277e-05,
+      "loss": 0.6427,
+      "step": 4360
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 5.308641975308642e-05,
+      "loss": 0.6425,
+      "step": 4365
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 5.267489711934157e-05,
+      "loss": 0.713,
+      "step": 4370
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 5.2263374485596705e-05,
+      "loss": 0.6414,
+      "step": 4375
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 5.185185185185185e-05,
+      "loss": 0.6578,
+      "step": 4380
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 5.1440329218106995e-05,
+      "loss": 0.6461,
+      "step": 4385
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 5.102880658436214e-05,
+      "loss": 0.651,
+      "step": 4390
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 5.061728395061729e-05,
+      "loss": 0.6523,
+      "step": 4395
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 5.020576131687244e-05,
+      "loss": 0.6625,
+      "step": 4400
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 4.9794238683127575e-05,
+      "loss": 0.6763,
+      "step": 4405
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 4.938271604938271e-05,
+      "loss": 0.6759,
+      "step": 4410
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 4.8971193415637865e-05,
+      "loss": 0.6742,
+      "step": 4415
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 4.855967078189301e-05,
+      "loss": 0.6617,
+      "step": 4420
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 4.814814814814815e-05,
+      "loss": 0.6604,
+      "step": 4425
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 4.773662551440329e-05,
+      "loss": 0.6739,
+      "step": 4430
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 4.732510288065844e-05,
+      "loss": 0.641,
+      "step": 4435
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 4.691358024691358e-05,
+      "loss": 0.6322,
+      "step": 4440
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 4.650205761316873e-05,
+      "loss": 0.6392,
+      "step": 4445
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 4.609053497942387e-05,
+      "loss": 0.6795,
+      "step": 4450
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 4.567901234567901e-05,
+      "loss": 0.6712,
+      "step": 4455
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 4.5267489711934157e-05,
+      "loss": 0.6353,
+      "step": 4460
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 4.48559670781893e-05,
+      "loss": 0.6587,
+      "step": 4465
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.6748,
+      "step": 4470
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 4.403292181069959e-05,
+      "loss": 0.6755,
+      "step": 4475
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 4.3621399176954737e-05,
+      "loss": 0.6513,
+      "step": 4480
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 4.3209876543209875e-05,
+      "loss": 0.6728,
+      "step": 4485
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 4.279835390946502e-05,
+      "loss": 0.6536,
+      "step": 4490
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 4.2386831275720165e-05,
+      "loss": 0.6652,
+      "step": 4495
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 4.197530864197531e-05,
+      "loss": 0.6715,
+      "step": 4500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 5010,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 1.8116033382918914e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/training_args.bin b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..28c7b09fc2b3929abe4ad6608c7959f30a9a9d66
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43458f4cf6aeb211c730b848f93ab15f483827c314fb4dc1e79dd1f658b7dbc8
+size 5944
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/zero_to_fp32.py b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/zero_to_fp32.py
new file mode 100644
index 0000000000000000000000000000000000000000..c98caae31534368be22b67fc4ae906836c992a8d
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-4500/zero_to_fp32.py
@@ -0,0 +1,587 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel()
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file, tag=args.tag)
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/README.md b/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..2aa897f8fa13b49ce76b1fa188781e5f726e7d13
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-2-7b-hf
+library_name: peft
+---
+
+# 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 0.9.0
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/adapter_config.json b/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9c81a592f0ff08374a4f61f6003029070a8429ae
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/adapter_config.json
@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "mora_type": 1,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_mora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/adapter_model.safetensors b/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0bff03721c370581aee4a814f2c1c923f114137a
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93aecab0c925b7a6e8258f70ed3a42f1ded6fe8105f3089ae0e12c2c90ea8d66
+size 564342240
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3fa58d966e922fdb8be02350526101f999dc482c
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd7759054b9e1e0db5bf9c715f98f03aa5510344586ffde464584706c4bc3c76
+size 239914224
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/global_step5000/mp_rank_00_model_states.pt b/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/global_step5000/mp_rank_00_model_states.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7692d57d1e1291919804627959eb552d19a96177
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/global_step5000/mp_rank_00_model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:901b8f659aaec8b1456be9879061f2a2ce4ad05da9f7836ec57ecf94440a400f
+size 40303404
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/latest b/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/latest
new file mode 100644
index 0000000000000000000000000000000000000000..f805186fa43374540c3fa51dfd3cca9ac06e56a5
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/latest
@@ -0,0 +1 @@
+global_step5000
\ No newline at end of file
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/rng_state.pth b/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3c6de7275177babc64c0b8fa5415c4f432f1fcca
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0ceba3e4ac4338be0a98a101dd5a5ef23235014c3c81e4406a9e40c7aeb8eb1
+size 14244
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/scheduler.pt b/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..58013943b0573258b9a78b895c969b632731d6b0
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09f3e0c796e5bf366538f45448005c2ee1408939e532a21fd4f4135857c049e6
+size 1064
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/trainer_state.json b/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..55eae9786ee5a7a07da26d8556c1331628460300
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/trainer_state.json
@@ -0,0 +1,6021 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9958212492593632,
+  "eval_steps": 500,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.3798,
+      "step": 5
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 1.3917,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4e-05,
+      "loss": 1.2862,
+      "step": 15
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 1.2046,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.0634,
+      "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8e-05,
+      "loss": 1.0273,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 1.0472,
+      "step": 35
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 1.0301,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00012,
+      "loss": 0.9335,
+      "step": 45
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.921,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00014666666666666666,
+      "loss": 0.9506,
+      "step": 55
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016,
+      "loss": 0.8876,
+      "step": 60
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00017333333333333334,
+      "loss": 0.9335,
+      "step": 65
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 0.8554,
+      "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0002,
+      "loss": 0.8537,
+      "step": 75
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00021333333333333333,
+      "loss": 0.9033,
+      "step": 80
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00022666666666666668,
+      "loss": 0.8203,
+      "step": 85
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00024,
+      "loss": 0.8611,
+      "step": 90
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00025333333333333333,
+      "loss": 0.8303,
+      "step": 95
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002666666666666667,
+      "loss": 0.8528,
+      "step": 100
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00028,
+      "loss": 0.8537,
+      "step": 105
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002933333333333333,
+      "loss": 0.8286,
+      "step": 110
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003066666666666667,
+      "loss": 0.8449,
+      "step": 115
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00032,
+      "loss": 0.8377,
+      "step": 120
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003333333333333334,
+      "loss": 0.8419,
+      "step": 125
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00034666666666666667,
+      "loss": 0.8265,
+      "step": 130
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00036,
+      "loss": 0.8037,
+      "step": 135
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003733333333333334,
+      "loss": 0.7924,
+      "step": 140
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00038666666666666667,
+      "loss": 0.8245,
+      "step": 145
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0004,
+      "loss": 0.8388,
+      "step": 150
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003995884773662552,
+      "loss": 0.8066,
+      "step": 155
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003991769547325103,
+      "loss": 0.8107,
+      "step": 160
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039876543209876544,
+      "loss": 0.8005,
+      "step": 165
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003983539094650206,
+      "loss": 0.7727,
+      "step": 170
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039794238683127576,
+      "loss": 0.8276,
+      "step": 175
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039753086419753086,
+      "loss": 0.8464,
+      "step": 180
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000397119341563786,
+      "loss": 0.8348,
+      "step": 185
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003967078189300412,
+      "loss": 0.8228,
+      "step": 190
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003962962962962963,
+      "loss": 0.8254,
+      "step": 195
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00039588477366255144,
+      "loss": 0.817,
+      "step": 200
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003954732510288066,
+      "loss": 0.8365,
+      "step": 205
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003950617283950617,
+      "loss": 0.793,
+      "step": 210
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00039465020576131686,
+      "loss": 0.8014,
+      "step": 215
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000394238683127572,
+      "loss": 0.8049,
+      "step": 220
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003938271604938272,
+      "loss": 0.7841,
+      "step": 225
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003934156378600823,
+      "loss": 0.7977,
+      "step": 230
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00039300411522633744,
+      "loss": 0.8299,
+      "step": 235
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003925925925925926,
+      "loss": 0.7729,
+      "step": 240
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00039218106995884776,
+      "loss": 0.8082,
+      "step": 245
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003917695473251029,
+      "loss": 0.8173,
+      "step": 250
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000391358024691358,
+      "loss": 0.8379,
+      "step": 255
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003909465020576132,
+      "loss": 0.7962,
+      "step": 260
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00039053497942386834,
+      "loss": 0.8067,
+      "step": 265
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003901234567901235,
+      "loss": 0.7915,
+      "step": 270
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00038971193415637866,
+      "loss": 0.7905,
+      "step": 275
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00038930041152263376,
+      "loss": 0.7862,
+      "step": 280
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003888888888888889,
+      "loss": 0.7709,
+      "step": 285
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003884773662551441,
+      "loss": 0.7773,
+      "step": 290
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00038806584362139924,
+      "loss": 0.8068,
+      "step": 295
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00038765432098765434,
+      "loss": 0.7962,
+      "step": 300
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003872427983539095,
+      "loss": 0.7894,
+      "step": 305
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00038683127572016466,
+      "loss": 0.7705,
+      "step": 310
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00038641975308641976,
+      "loss": 0.7882,
+      "step": 315
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003860082304526749,
+      "loss": 0.7865,
+      "step": 320
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003855967078189301,
+      "loss": 0.7939,
+      "step": 325
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003851851851851852,
+      "loss": 0.7724,
+      "step": 330
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00038477366255144034,
+      "loss": 0.7771,
+      "step": 335
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003843621399176955,
+      "loss": 0.7941,
+      "step": 340
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00038395061728395066,
+      "loss": 0.7822,
+      "step": 345
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00038353909465020577,
+      "loss": 0.8143,
+      "step": 350
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003831275720164609,
+      "loss": 0.795,
+      "step": 355
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003827160493827161,
+      "loss": 0.8049,
+      "step": 360
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003823045267489712,
+      "loss": 0.8309,
+      "step": 365
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00038189300411522635,
+      "loss": 0.8314,
+      "step": 370
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003814814814814815,
+      "loss": 0.801,
+      "step": 375
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00038106995884773666,
+      "loss": 0.8084,
+      "step": 380
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00038065843621399177,
+      "loss": 0.8129,
+      "step": 385
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003802469135802469,
+      "loss": 0.7859,
+      "step": 390
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003798353909465021,
+      "loss": 0.7874,
+      "step": 395
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003794238683127572,
+      "loss": 0.7548,
+      "step": 400
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00037901234567901235,
+      "loss": 0.8092,
+      "step": 405
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003786008230452675,
+      "loss": 0.8041,
+      "step": 410
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00037818930041152266,
+      "loss": 0.777,
+      "step": 415
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00037777777777777777,
+      "loss": 0.7699,
+      "step": 420
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00037736625514403293,
+      "loss": 0.781,
+      "step": 425
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003769547325102881,
+      "loss": 0.7504,
+      "step": 430
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003765432098765432,
+      "loss": 0.7974,
+      "step": 435
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037613168724279835,
+      "loss": 0.7663,
+      "step": 440
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003757201646090535,
+      "loss": 0.8013,
+      "step": 445
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037530864197530867,
+      "loss": 0.7453,
+      "step": 450
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037489711934156377,
+      "loss": 0.7425,
+      "step": 455
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00037448559670781893,
+      "loss": 0.7582,
+      "step": 460
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003740740740740741,
+      "loss": 0.7801,
+      "step": 465
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00037366255144032925,
+      "loss": 0.7809,
+      "step": 470
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003732510288065844,
+      "loss": 0.7749,
+      "step": 475
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00037283950617283956,
+      "loss": 0.7807,
+      "step": 480
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00037242798353909467,
+      "loss": 0.7715,
+      "step": 485
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003720164609053498,
+      "loss": 0.7356,
+      "step": 490
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000371604938271605,
+      "loss": 0.7674,
+      "step": 495
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00037119341563786014,
+      "loss": 0.7542,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00037078189300411525,
+      "loss": 0.7583,
+      "step": 505
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003703703703703704,
+      "loss": 0.7767,
+      "step": 510
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036995884773662556,
+      "loss": 0.7853,
+      "step": 515
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036954732510288067,
+      "loss": 0.7733,
+      "step": 520
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036913580246913583,
+      "loss": 0.7758,
+      "step": 525
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.000368724279835391,
+      "loss": 0.7698,
+      "step": 530
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00036831275720164614,
+      "loss": 0.7805,
+      "step": 535
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036790123456790125,
+      "loss": 0.7573,
+      "step": 540
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003674897119341564,
+      "loss": 0.7709,
+      "step": 545
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036707818930041157,
+      "loss": 0.7994,
+      "step": 550
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036666666666666667,
+      "loss": 0.7363,
+      "step": 555
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00036625514403292183,
+      "loss": 0.7478,
+      "step": 560
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000365843621399177,
+      "loss": 0.8188,
+      "step": 565
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003654320987654321,
+      "loss": 0.7524,
+      "step": 570
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00036502057613168725,
+      "loss": 0.7319,
+      "step": 575
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003646090534979424,
+      "loss": 0.7915,
+      "step": 580
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00036419753086419757,
+      "loss": 0.7722,
+      "step": 585
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00036378600823045267,
+      "loss": 0.7842,
+      "step": 590
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00036337448559670783,
+      "loss": 0.7591,
+      "step": 595
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000362962962962963,
+      "loss": 0.7653,
+      "step": 600
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003625514403292181,
+      "loss": 0.7838,
+      "step": 605
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00036213991769547325,
+      "loss": 0.7937,
+      "step": 610
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003617283950617284,
+      "loss": 0.77,
+      "step": 615
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00036131687242798357,
+      "loss": 0.7899,
+      "step": 620
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003609053497942387,
+      "loss": 0.7815,
+      "step": 625
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00036049382716049383,
+      "loss": 0.7648,
+      "step": 630
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.000360082304526749,
+      "loss": 0.7716,
+      "step": 635
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003596707818930041,
+      "loss": 0.7708,
+      "step": 640
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00035925925925925925,
+      "loss": 0.7306,
+      "step": 645
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003588477366255144,
+      "loss": 0.8007,
+      "step": 650
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003584362139917695,
+      "loss": 0.7551,
+      "step": 655
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003580246913580247,
+      "loss": 0.754,
+      "step": 660
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00035761316872427983,
+      "loss": 0.7599,
+      "step": 665
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.000357201646090535,
+      "loss": 0.7637,
+      "step": 670
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00035679012345679015,
+      "loss": 0.7766,
+      "step": 675
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003563786008230453,
+      "loss": 0.7727,
+      "step": 680
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003559670781893004,
+      "loss": 0.7675,
+      "step": 685
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035555555555555557,
+      "loss": 0.7707,
+      "step": 690
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035514403292181073,
+      "loss": 0.7221,
+      "step": 695
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003547325102880659,
+      "loss": 0.7335,
+      "step": 700
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035432098765432105,
+      "loss": 0.781,
+      "step": 705
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00035390946502057615,
+      "loss": 0.7845,
+      "step": 710
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003534979423868313,
+      "loss": 0.7467,
+      "step": 715
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00035308641975308647,
+      "loss": 0.7735,
+      "step": 720
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003526748971193416,
+      "loss": 0.7368,
+      "step": 725
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00035226337448559673,
+      "loss": 0.7678,
+      "step": 730
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003518518518518519,
+      "loss": 0.7756,
+      "step": 735
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00035144032921810705,
+      "loss": 0.7635,
+      "step": 740
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00035102880658436215,
+      "loss": 0.7757,
+      "step": 745
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003506172839506173,
+      "loss": 0.7442,
+      "step": 750
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00035020576131687247,
+      "loss": 0.7584,
+      "step": 755
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003497942386831276,
+      "loss": 0.8333,
+      "step": 760
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00034938271604938273,
+      "loss": 0.7459,
+      "step": 765
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003489711934156379,
+      "loss": 0.7499,
+      "step": 770
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.000348559670781893,
+      "loss": 0.7571,
+      "step": 775
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00034814814814814816,
+      "loss": 0.7243,
+      "step": 780
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003477366255144033,
+      "loss": 0.7443,
+      "step": 785
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003473251028806585,
+      "loss": 0.7759,
+      "step": 790
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003469135802469136,
+      "loss": 0.7452,
+      "step": 795
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00034650205761316874,
+      "loss": 0.7578,
+      "step": 800
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003460905349794239,
+      "loss": 0.7634,
+      "step": 805
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.000345679012345679,
+      "loss": 0.7925,
+      "step": 810
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00034526748971193416,
+      "loss": 0.7966,
+      "step": 815
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003448559670781893,
+      "loss": 0.7601,
+      "step": 820
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003444444444444445,
+      "loss": 0.7617,
+      "step": 825
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003440329218106996,
+      "loss": 0.7526,
+      "step": 830
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00034362139917695474,
+      "loss": 0.7297,
+      "step": 835
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003432098765432099,
+      "loss": 0.7549,
+      "step": 840
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.000342798353909465,
+      "loss": 0.7517,
+      "step": 845
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00034238683127572016,
+      "loss": 0.7626,
+      "step": 850
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003419753086419753,
+      "loss": 0.7987,
+      "step": 855
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003415637860082305,
+      "loss": 0.7573,
+      "step": 860
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003411522633744856,
+      "loss": 0.8367,
+      "step": 865
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00034074074074074074,
+      "loss": 0.7258,
+      "step": 870
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003403292181069959,
+      "loss": 0.7632,
+      "step": 875
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00033991769547325106,
+      "loss": 0.7379,
+      "step": 880
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00033950617283950616,
+      "loss": 0.7529,
+      "step": 885
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003390946502057613,
+      "loss": 0.7391,
+      "step": 890
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003386831275720165,
+      "loss": 0.8061,
+      "step": 895
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00033827160493827164,
+      "loss": 0.7288,
+      "step": 900
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003378600823045268,
+      "loss": 0.7493,
+      "step": 905
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00033744855967078195,
+      "loss": 0.7702,
+      "step": 910
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00033703703703703706,
+      "loss": 0.7538,
+      "step": 915
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003366255144032922,
+      "loss": 0.728,
+      "step": 920
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003362139917695474,
+      "loss": 0.7776,
+      "step": 925
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003358024691358025,
+      "loss": 0.7883,
+      "step": 930
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00033539094650205764,
+      "loss": 0.7471,
+      "step": 935
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003349794238683128,
+      "loss": 0.7464,
+      "step": 940
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00033456790123456795,
+      "loss": 0.7885,
+      "step": 945
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00033415637860082306,
+      "loss": 0.7509,
+      "step": 950
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003337448559670782,
+      "loss": 0.7681,
+      "step": 955
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003333333333333334,
+      "loss": 0.8246,
+      "step": 960
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003329218106995885,
+      "loss": 0.7604,
+      "step": 965
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00033251028806584364,
+      "loss": 0.7755,
+      "step": 970
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003320987654320988,
+      "loss": 0.7641,
+      "step": 975
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003316872427983539,
+      "loss": 0.7708,
+      "step": 980
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00033127572016460906,
+      "loss": 0.7936,
+      "step": 985
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003308641975308642,
+      "loss": 0.7641,
+      "step": 990
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003304526748971194,
+      "loss": 0.7479,
+      "step": 995
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003300411522633745,
+      "loss": 0.7547,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00032962962962962964,
+      "loss": 0.762,
+      "step": 1005
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003292181069958848,
+      "loss": 0.7472,
+      "step": 1010
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003288065843621399,
+      "loss": 0.7542,
+      "step": 1015
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00032839506172839506,
+      "loss": 0.7669,
+      "step": 1020
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003279835390946502,
+      "loss": 0.7812,
+      "step": 1025
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003275720164609054,
+      "loss": 0.7273,
+      "step": 1030
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003271604938271605,
+      "loss": 0.7822,
+      "step": 1035
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00032674897119341564,
+      "loss": 0.7337,
+      "step": 1040
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003263374485596708,
+      "loss": 0.7566,
+      "step": 1045
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003259259259259259,
+      "loss": 0.7377,
+      "step": 1050
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00032551440329218106,
+      "loss": 0.7856,
+      "step": 1055
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003251028806584362,
+      "loss": 0.7981,
+      "step": 1060
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003246913580246914,
+      "loss": 0.7505,
+      "step": 1065
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003242798353909465,
+      "loss": 0.7549,
+      "step": 1070
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00032386831275720164,
+      "loss": 0.7306,
+      "step": 1075
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003234567901234568,
+      "loss": 0.7343,
+      "step": 1080
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003230452674897119,
+      "loss": 0.738,
+      "step": 1085
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00032263374485596707,
+      "loss": 0.7655,
+      "step": 1090
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003222222222222222,
+      "loss": 0.7706,
+      "step": 1095
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003218106995884774,
+      "loss": 0.7512,
+      "step": 1100
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00032139917695473254,
+      "loss": 0.7549,
+      "step": 1105
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003209876543209877,
+      "loss": 0.7839,
+      "step": 1110
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003205761316872428,
+      "loss": 0.7511,
+      "step": 1115
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00032016460905349796,
+      "loss": 0.769,
+      "step": 1120
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003197530864197531,
+      "loss": 0.7685,
+      "step": 1125
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003193415637860083,
+      "loss": 0.7489,
+      "step": 1130
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003189300411522634,
+      "loss": 0.808,
+      "step": 1135
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00031851851851851854,
+      "loss": 0.7654,
+      "step": 1140
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003181069958847737,
+      "loss": 0.7845,
+      "step": 1145
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00031769547325102886,
+      "loss": 0.7886,
+      "step": 1150
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00031728395061728396,
+      "loss": 0.7318,
+      "step": 1155
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003168724279835391,
+      "loss": 0.7231,
+      "step": 1160
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003164609053497943,
+      "loss": 0.7471,
+      "step": 1165
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003160493827160494,
+      "loss": 0.7424,
+      "step": 1170
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00031563786008230454,
+      "loss": 0.7249,
+      "step": 1175
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003152263374485597,
+      "loss": 0.7419,
+      "step": 1180
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00031481481481481486,
+      "loss": 0.7567,
+      "step": 1185
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00031440329218106997,
+      "loss": 0.7707,
+      "step": 1190
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003139917695473251,
+      "loss": 0.7473,
+      "step": 1195
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003135802469135803,
+      "loss": 0.7222,
+      "step": 1200
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003131687242798354,
+      "loss": 0.7383,
+      "step": 1205
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00031275720164609055,
+      "loss": 0.7712,
+      "step": 1210
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003123456790123457,
+      "loss": 0.7602,
+      "step": 1215
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003119341563786008,
+      "loss": 0.7741,
+      "step": 1220
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00031152263374485597,
+      "loss": 0.7428,
+      "step": 1225
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003111111111111111,
+      "loss": 0.7605,
+      "step": 1230
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003106995884773663,
+      "loss": 0.7255,
+      "step": 1235
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003102880658436214,
+      "loss": 0.7468,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00030987654320987655,
+      "loss": 0.7961,
+      "step": 1245
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003094650205761317,
+      "loss": 0.7208,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003090534979423868,
+      "loss": 0.7331,
+      "step": 1255
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00030864197530864197,
+      "loss": 0.7371,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00030823045267489713,
+      "loss": 0.7206,
+      "step": 1265
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003078189300411523,
+      "loss": 0.7617,
+      "step": 1270
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003074074074074074,
+      "loss": 0.7652,
+      "step": 1275
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00030699588477366255,
+      "loss": 0.7635,
+      "step": 1280
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003065843621399177,
+      "loss": 0.7445,
+      "step": 1285
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003061728395061728,
+      "loss": 0.7717,
+      "step": 1290
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030576131687242797,
+      "loss": 0.7535,
+      "step": 1295
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030534979423868313,
+      "loss": 0.7677,
+      "step": 1300
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003049382716049383,
+      "loss": 0.8131,
+      "step": 1305
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030452674897119345,
+      "loss": 0.7754,
+      "step": 1310
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00030411522633744855,
+      "loss": 0.76,
+      "step": 1315
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003037037037037037,
+      "loss": 0.7558,
+      "step": 1320
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00030329218106995887,
+      "loss": 0.7604,
+      "step": 1325
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.000302880658436214,
+      "loss": 0.7716,
+      "step": 1330
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003024691358024692,
+      "loss": 0.7669,
+      "step": 1335
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003020576131687243,
+      "loss": 0.7469,
+      "step": 1340
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030164609053497945,
+      "loss": 0.7511,
+      "step": 1345
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003012345679012346,
+      "loss": 0.7483,
+      "step": 1350
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030082304526748976,
+      "loss": 0.7509,
+      "step": 1355
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030041152263374487,
+      "loss": 0.7249,
+      "step": 1360
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.7289,
+      "step": 1365
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002995884773662552,
+      "loss": 0.7605,
+      "step": 1370
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002991769547325103,
+      "loss": 0.7185,
+      "step": 1375
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00029876543209876545,
+      "loss": 0.6974,
+      "step": 1380
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002983539094650206,
+      "loss": 0.7234,
+      "step": 1385
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00029794238683127577,
+      "loss": 0.7506,
+      "step": 1390
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029753086419753087,
+      "loss": 0.7524,
+      "step": 1395
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029711934156378603,
+      "loss": 0.7641,
+      "step": 1400
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002967078189300412,
+      "loss": 0.6967,
+      "step": 1405
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002962962962962963,
+      "loss": 0.735,
+      "step": 1410
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029588477366255145,
+      "loss": 0.7685,
+      "step": 1415
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002954732510288066,
+      "loss": 0.758,
+      "step": 1420
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002950617283950617,
+      "loss": 0.763,
+      "step": 1425
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00029465020576131687,
+      "loss": 0.712,
+      "step": 1430
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00029423868312757203,
+      "loss": 0.7236,
+      "step": 1435
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002938271604938272,
+      "loss": 0.7732,
+      "step": 1440
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002934156378600823,
+      "loss": 0.7689,
+      "step": 1445
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00029300411522633745,
+      "loss": 0.7352,
+      "step": 1450
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002925925925925926,
+      "loss": 0.7711,
+      "step": 1455
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002921810699588477,
+      "loss": 0.7549,
+      "step": 1460
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002917695473251029,
+      "loss": 0.7804,
+      "step": 1465
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00029135802469135803,
+      "loss": 0.7478,
+      "step": 1470
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002909465020576132,
+      "loss": 0.7801,
+      "step": 1475
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002905349794238683,
+      "loss": 0.7544,
+      "step": 1480
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00029012345679012345,
+      "loss": 0.7546,
+      "step": 1485
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002897119341563786,
+      "loss": 0.7648,
+      "step": 1490
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002893004115226337,
+      "loss": 0.7468,
+      "step": 1495
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002888888888888889,
+      "loss": 0.7434,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00028847736625514403,
+      "loss": 0.7348,
+      "step": 1505
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002880658436213992,
+      "loss": 0.7515,
+      "step": 1510
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00028765432098765435,
+      "loss": 0.7345,
+      "step": 1515
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00028724279835390946,
+      "loss": 0.7701,
+      "step": 1520
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002868312757201646,
+      "loss": 0.7472,
+      "step": 1525
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00028641975308641977,
+      "loss": 0.7075,
+      "step": 1530
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00028600823045267493,
+      "loss": 0.7483,
+      "step": 1535
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002855967078189301,
+      "loss": 0.712,
+      "step": 1540
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002851851851851852,
+      "loss": 0.7484,
+      "step": 1545
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00028477366255144035,
+      "loss": 0.7471,
+      "step": 1550
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002843621399176955,
+      "loss": 0.7462,
+      "step": 1555
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00028395061728395067,
+      "loss": 0.7371,
+      "step": 1560
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002835390946502058,
+      "loss": 0.7753,
+      "step": 1565
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00028312757201646093,
+      "loss": 0.7374,
+      "step": 1570
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002827160493827161,
+      "loss": 0.7328,
+      "step": 1575
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002823045267489712,
+      "loss": 0.7159,
+      "step": 1580
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00028189300411522635,
+      "loss": 0.7594,
+      "step": 1585
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002814814814814815,
+      "loss": 0.7215,
+      "step": 1590
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00028106995884773667,
+      "loss": 0.7398,
+      "step": 1595
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002806584362139918,
+      "loss": 0.773,
+      "step": 1600
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00028024691358024693,
+      "loss": 0.7584,
+      "step": 1605
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002798353909465021,
+      "loss": 0.7117,
+      "step": 1610
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002794238683127572,
+      "loss": 0.7471,
+      "step": 1615
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00027901234567901236,
+      "loss": 0.7443,
+      "step": 1620
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002786008230452675,
+      "loss": 0.7292,
+      "step": 1625
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002781893004115227,
+      "loss": 0.7716,
+      "step": 1630
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 0.763,
+      "step": 1635
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00027736625514403294,
+      "loss": 0.7408,
+      "step": 1640
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002769547325102881,
+      "loss": 0.7403,
+      "step": 1645
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002765432098765432,
+      "loss": 0.7508,
+      "step": 1650
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00027613168724279836,
+      "loss": 0.7687,
+      "step": 1655
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002757201646090535,
+      "loss": 0.7305,
+      "step": 1660
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002753086419753086,
+      "loss": 0.7165,
+      "step": 1665
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002748971193415638,
+      "loss": 0.8,
+      "step": 1670
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00027448559670781894,
+      "loss": 0.7357,
+      "step": 1675
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002740740740740741,
+      "loss": 0.7988,
+      "step": 1680
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002736625514403292,
+      "loss": 0.7559,
+      "step": 1685
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00027325102880658436,
+      "loss": 0.712,
+      "step": 1690
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002728395061728395,
+      "loss": 0.7486,
+      "step": 1695
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002724279835390946,
+      "loss": 0.7388,
+      "step": 1700
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002720164609053498,
+      "loss": 0.7441,
+      "step": 1705
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00027160493827160494,
+      "loss": 0.7547,
+      "step": 1710
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002711934156378601,
+      "loss": 0.7229,
+      "step": 1715
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002707818930041152,
+      "loss": 0.7383,
+      "step": 1720
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00027037037037037036,
+      "loss": 0.7606,
+      "step": 1725
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002699588477366255,
+      "loss": 0.7529,
+      "step": 1730
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002695473251028807,
+      "loss": 0.752,
+      "step": 1735
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00026913580246913584,
+      "loss": 0.7342,
+      "step": 1740
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.000268724279835391,
+      "loss": 0.7308,
+      "step": 1745
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002683127572016461,
+      "loss": 0.6915,
+      "step": 1750
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00026790123456790126,
+      "loss": 0.7344,
+      "step": 1755
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002674897119341564,
+      "loss": 0.7426,
+      "step": 1760
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002670781893004116,
+      "loss": 0.7088,
+      "step": 1765
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002666666666666667,
+      "loss": 0.7241,
+      "step": 1770
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00026625514403292184,
+      "loss": 0.7552,
+      "step": 1775
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.000265843621399177,
+      "loss": 0.7477,
+      "step": 1780
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002654320987654321,
+      "loss": 0.7115,
+      "step": 1785
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00026502057613168726,
+      "loss": 0.7538,
+      "step": 1790
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002646090534979424,
+      "loss": 0.7321,
+      "step": 1795
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002641975308641976,
+      "loss": 0.7212,
+      "step": 1800
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002637860082304527,
+      "loss": 0.747,
+      "step": 1805
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00026337448559670784,
+      "loss": 0.7606,
+      "step": 1810
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.000262962962962963,
+      "loss": 0.7344,
+      "step": 1815
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002625514403292181,
+      "loss": 0.7783,
+      "step": 1820
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00026213991769547326,
+      "loss": 0.7556,
+      "step": 1825
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002617283950617284,
+      "loss": 0.7585,
+      "step": 1830
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002613168724279836,
+      "loss": 0.7359,
+      "step": 1835
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002609053497942387,
+      "loss": 0.7185,
+      "step": 1840
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00026049382716049384,
+      "loss": 0.7573,
+      "step": 1845
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.000260082304526749,
+      "loss": 0.7619,
+      "step": 1850
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002596707818930041,
+      "loss": 0.7611,
+      "step": 1855
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00025925925925925926,
+      "loss": 0.7647,
+      "step": 1860
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002588477366255144,
+      "loss": 0.7398,
+      "step": 1865
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002584362139917695,
+      "loss": 0.7683,
+      "step": 1870
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002580246913580247,
+      "loss": 0.7817,
+      "step": 1875
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00025761316872427984,
+      "loss": 0.742,
+      "step": 1880
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.000257201646090535,
+      "loss": 0.7509,
+      "step": 1885
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002567901234567901,
+      "loss": 0.7058,
+      "step": 1890
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00025637860082304526,
+      "loss": 0.7635,
+      "step": 1895
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002559670781893004,
+      "loss": 0.734,
+      "step": 1900
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00025555555555555553,
+      "loss": 0.7416,
+      "step": 1905
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002551440329218107,
+      "loss": 0.7071,
+      "step": 1910
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00025473251028806584,
+      "loss": 0.7275,
+      "step": 1915
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.000254320987654321,
+      "loss": 0.7413,
+      "step": 1920
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002539094650205761,
+      "loss": 0.7703,
+      "step": 1925
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00025349794238683127,
+      "loss": 0.7331,
+      "step": 1930
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002530864197530864,
+      "loss": 0.7251,
+      "step": 1935
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002526748971193416,
+      "loss": 0.7341,
+      "step": 1940
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00025226337448559674,
+      "loss": 0.7079,
+      "step": 1945
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00025185185185185185,
+      "loss": 0.7615,
+      "step": 1950
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.000251440329218107,
+      "loss": 0.7144,
+      "step": 1955
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00025102880658436216,
+      "loss": 0.7527,
+      "step": 1960
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0002506172839506173,
+      "loss": 0.7327,
+      "step": 1965
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002502057613168725,
+      "loss": 0.7173,
+      "step": 1970
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002497942386831276,
+      "loss": 0.7239,
+      "step": 1975
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00024938271604938274,
+      "loss": 0.7442,
+      "step": 1980
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002489711934156379,
+      "loss": 0.7396,
+      "step": 1985
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.000248559670781893,
+      "loss": 0.7365,
+      "step": 1990
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00024814814814814816,
+      "loss": 0.7037,
+      "step": 1995
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002477366255144033,
+      "loss": 0.721,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002473251028806585,
+      "loss": 0.7353,
+      "step": 2005
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002469135802469136,
+      "loss": 0.7648,
+      "step": 2010
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00024650205761316874,
+      "loss": 0.7445,
+      "step": 2015
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0002460905349794239,
+      "loss": 0.7664,
+      "step": 2020
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.000245679012345679,
+      "loss": 0.7202,
+      "step": 2025
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00024526748971193417,
+      "loss": 0.7147,
+      "step": 2030
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0002448559670781893,
+      "loss": 0.722,
+      "step": 2035
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0002444444444444445,
+      "loss": 0.7539,
+      "step": 2040
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002440329218106996,
+      "loss": 0.7681,
+      "step": 2045
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00024362139917695475,
+      "loss": 0.7304,
+      "step": 2050
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002432098765432099,
+      "loss": 0.7432,
+      "step": 2055
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.000242798353909465,
+      "loss": 0.6945,
+      "step": 2060
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00024238683127572017,
+      "loss": 0.7426,
+      "step": 2065
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00024197530864197533,
+      "loss": 0.7144,
+      "step": 2070
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00024156378600823048,
+      "loss": 0.7761,
+      "step": 2075
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0002411522633744856,
+      "loss": 0.7402,
+      "step": 2080
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00024074074074074075,
+      "loss": 0.7376,
+      "step": 2085
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0002403292181069959,
+      "loss": 0.7231,
+      "step": 2090
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023991769547325104,
+      "loss": 0.7461,
+      "step": 2095
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023950617283950617,
+      "loss": 0.7215,
+      "step": 2100
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023909465020576133,
+      "loss": 0.7419,
+      "step": 2105
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023868312757201646,
+      "loss": 0.7502,
+      "step": 2110
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00023827160493827162,
+      "loss": 0.7294,
+      "step": 2115
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00023786008230452678,
+      "loss": 0.7904,
+      "step": 2120
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00023744855967078194,
+      "loss": 0.7418,
+      "step": 2125
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00023703703703703704,
+      "loss": 0.7371,
+      "step": 2130
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0002366255144032922,
+      "loss": 0.7384,
+      "step": 2135
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00023621399176954736,
+      "loss": 0.7552,
+      "step": 2140
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023580246913580246,
+      "loss": 0.7516,
+      "step": 2145
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023539094650205762,
+      "loss": 0.7303,
+      "step": 2150
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023497942386831278,
+      "loss": 0.7496,
+      "step": 2155
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023456790123456794,
+      "loss": 0.7135,
+      "step": 2160
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00023415637860082304,
+      "loss": 0.7283,
+      "step": 2165
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0002337448559670782,
+      "loss": 0.751,
+      "step": 2170
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00023333333333333336,
+      "loss": 0.7183,
+      "step": 2175
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00023292181069958846,
+      "loss": 0.7242,
+      "step": 2180
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00023251028806584362,
+      "loss": 0.725,
+      "step": 2185
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00023209876543209878,
+      "loss": 0.753,
+      "step": 2190
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002316872427983539,
+      "loss": 0.7664,
+      "step": 2195
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00023127572016460904,
+      "loss": 0.7444,
+      "step": 2200
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002308641975308642,
+      "loss": 0.7226,
+      "step": 2205
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00023045267489711936,
+      "loss": 0.7653,
+      "step": 2210
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002300411522633745,
+      "loss": 0.7382,
+      "step": 2215
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00022962962962962965,
+      "loss": 0.7242,
+      "step": 2220
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002292181069958848,
+      "loss": 0.7215,
+      "step": 2225
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002288065843621399,
+      "loss": 0.724,
+      "step": 2230
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00022839506172839507,
+      "loss": 0.7439,
+      "step": 2235
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00022798353909465023,
+      "loss": 0.699,
+      "step": 2240
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002275720164609054,
+      "loss": 0.7602,
+      "step": 2245
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002271604938271605,
+      "loss": 0.7103,
+      "step": 2250
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00022674897119341565,
+      "loss": 0.7015,
+      "step": 2255
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002263374485596708,
+      "loss": 0.7404,
+      "step": 2260
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00022592592592592591,
+      "loss": 0.7127,
+      "step": 2265
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00022551440329218107,
+      "loss": 0.7299,
+      "step": 2270
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00022510288065843623,
+      "loss": 0.7174,
+      "step": 2275
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002246913580246914,
+      "loss": 0.7454,
+      "step": 2280
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002242798353909465,
+      "loss": 0.7159,
+      "step": 2285
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00022386831275720165,
+      "loss": 0.7263,
+      "step": 2290
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0002234567901234568,
+      "loss": 0.7148,
+      "step": 2295
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00022304526748971192,
+      "loss": 0.7447,
+      "step": 2300
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00022263374485596707,
+      "loss": 0.7326,
+      "step": 2305
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00022222222222222223,
+      "loss": 0.7428,
+      "step": 2310
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00022181069958847736,
+      "loss": 0.7587,
+      "step": 2315
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00022139917695473252,
+      "loss": 0.759,
+      "step": 2320
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00022098765432098768,
+      "loss": 0.7716,
+      "step": 2325
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002205761316872428,
+      "loss": 0.74,
+      "step": 2330
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00022016460905349794,
+      "loss": 0.7255,
+      "step": 2335
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002197530864197531,
+      "loss": 0.7547,
+      "step": 2340
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021934156378600826,
+      "loss": 0.7359,
+      "step": 2345
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021893004115226337,
+      "loss": 0.6987,
+      "step": 2350
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021851851851851852,
+      "loss": 0.7233,
+      "step": 2355
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021810699588477368,
+      "loss": 0.6945,
+      "step": 2360
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00021769547325102884,
+      "loss": 0.7566,
+      "step": 2365
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00021728395061728395,
+      "loss": 0.728,
+      "step": 2370
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002168724279835391,
+      "loss": 0.7167,
+      "step": 2375
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00021646090534979426,
+      "loss": 0.7576,
+      "step": 2380
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00021604938271604937,
+      "loss": 0.7246,
+      "step": 2385
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00021563786008230453,
+      "loss": 0.755,
+      "step": 2390
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00021522633744855968,
+      "loss": 0.6983,
+      "step": 2395
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00021481481481481484,
+      "loss": 0.7369,
+      "step": 2400
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00021440329218106995,
+      "loss": 0.7074,
+      "step": 2405
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0002139917695473251,
+      "loss": 0.7317,
+      "step": 2410
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00021358024691358026,
+      "loss": 0.7086,
+      "step": 2415
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0002131687242798354,
+      "loss": 0.7356,
+      "step": 2420
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00021275720164609055,
+      "loss": 0.7652,
+      "step": 2425
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00021234567901234569,
+      "loss": 0.7488,
+      "step": 2430
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00021193415637860082,
+      "loss": 0.746,
+      "step": 2435
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00021152263374485598,
+      "loss": 0.7454,
+      "step": 2440
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00021111111111111113,
+      "loss": 0.72,
+      "step": 2445
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0002106995884773663,
+      "loss": 0.7299,
+      "step": 2450
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0002102880658436214,
+      "loss": 0.7436,
+      "step": 2455
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00020987654320987656,
+      "loss": 0.7068,
+      "step": 2460
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00020946502057613171,
+      "loss": 0.711,
+      "step": 2465
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00020905349794238682,
+      "loss": 0.7473,
+      "step": 2470
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00020864197530864198,
+      "loss": 0.7016,
+      "step": 2475
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00020823045267489714,
+      "loss": 0.7049,
+      "step": 2480
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002078189300411523,
+      "loss": 0.7268,
+      "step": 2485
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002074074074074074,
+      "loss": 0.7239,
+      "step": 2490
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020699588477366256,
+      "loss": 0.698,
+      "step": 2495
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020658436213991772,
+      "loss": 0.7573,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020617283950617282,
+      "loss": 0.7309,
+      "step": 2505
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020576131687242798,
+      "loss": 0.6628,
+      "step": 2510
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00020534979423868314,
+      "loss": 0.656,
+      "step": 2515
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0002049382716049383,
+      "loss": 0.6737,
+      "step": 2520
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00020452674897119343,
+      "loss": 0.6903,
+      "step": 2525
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00020411522633744856,
+      "loss": 0.6674,
+      "step": 2530
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00020370370370370372,
+      "loss": 0.6507,
+      "step": 2535
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00020329218106995885,
+      "loss": 0.6948,
+      "step": 2540
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.000202880658436214,
+      "loss": 0.6662,
+      "step": 2545
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00020246913580246917,
+      "loss": 0.6624,
+      "step": 2550
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00020205761316872427,
+      "loss": 0.6791,
+      "step": 2555
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00020164609053497943,
+      "loss": 0.7088,
+      "step": 2560
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0002012345679012346,
+      "loss": 0.6796,
+      "step": 2565
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00020082304526748975,
+      "loss": 0.6601,
+      "step": 2570
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00020041152263374485,
+      "loss": 0.6865,
+      "step": 2575
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0002,
+      "loss": 0.6725,
+      "step": 2580
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00019958847736625514,
+      "loss": 0.6743,
+      "step": 2585
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0001991769547325103,
+      "loss": 0.6395,
+      "step": 2590
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00019876543209876543,
+      "loss": 0.6522,
+      "step": 2595
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0001983539094650206,
+      "loss": 0.6868,
+      "step": 2600
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00019794238683127572,
+      "loss": 0.6861,
+      "step": 2605
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00019753086419753085,
+      "loss": 0.6843,
+      "step": 2610
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.000197119341563786,
+      "loss": 0.6732,
+      "step": 2615
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00019670781893004114,
+      "loss": 0.6676,
+      "step": 2620
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0001962962962962963,
+      "loss": 0.6782,
+      "step": 2625
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00019588477366255146,
+      "loss": 0.6937,
+      "step": 2630
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0001954732510288066,
+      "loss": 0.6823,
+      "step": 2635
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00019506172839506175,
+      "loss": 0.6839,
+      "step": 2640
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019465020576131688,
+      "loss": 0.6351,
+      "step": 2645
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019423868312757204,
+      "loss": 0.7157,
+      "step": 2650
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019382716049382717,
+      "loss": 0.6591,
+      "step": 2655
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019341563786008233,
+      "loss": 0.6826,
+      "step": 2660
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019300411522633746,
+      "loss": 0.6732,
+      "step": 2665
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0001925925925925926,
+      "loss": 0.6795,
+      "step": 2670
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00019218106995884775,
+      "loss": 0.6845,
+      "step": 2675
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00019176954732510288,
+      "loss": 0.649,
+      "step": 2680
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00019135802469135804,
+      "loss": 0.6684,
+      "step": 2685
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00019094650205761317,
+      "loss": 0.6712,
+      "step": 2690
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00019053497942386833,
+      "loss": 0.6665,
+      "step": 2695
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00019012345679012346,
+      "loss": 0.6426,
+      "step": 2700
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0001897119341563786,
+      "loss": 0.6561,
+      "step": 2705
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00018930041152263375,
+      "loss": 0.6664,
+      "step": 2710
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00018888888888888888,
+      "loss": 0.6746,
+      "step": 2715
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018847736625514404,
+      "loss": 0.6497,
+      "step": 2720
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018806584362139917,
+      "loss": 0.6811,
+      "step": 2725
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018765432098765433,
+      "loss": 0.6608,
+      "step": 2730
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018724279835390946,
+      "loss": 0.6655,
+      "step": 2735
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018683127572016462,
+      "loss": 0.7014,
+      "step": 2740
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00018641975308641978,
+      "loss": 0.6889,
+      "step": 2745
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0001860082304526749,
+      "loss": 0.6805,
+      "step": 2750
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00018559670781893007,
+      "loss": 0.6629,
+      "step": 2755
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0001851851851851852,
+      "loss": 0.6593,
+      "step": 2760
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00018477366255144033,
+      "loss": 0.6902,
+      "step": 2765
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0001843621399176955,
+      "loss": 0.6777,
+      "step": 2770
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00018395061728395062,
+      "loss": 0.7127,
+      "step": 2775
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00018353909465020578,
+      "loss": 0.6551,
+      "step": 2780
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00018312757201646091,
+      "loss": 0.6703,
+      "step": 2785
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00018271604938271605,
+      "loss": 0.6776,
+      "step": 2790
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0001823045267489712,
+      "loss": 0.6574,
+      "step": 2795
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00018189300411522634,
+      "loss": 0.7154,
+      "step": 2800
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0001814814814814815,
+      "loss": 0.6749,
+      "step": 2805
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00018106995884773663,
+      "loss": 0.695,
+      "step": 2810
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00018065843621399178,
+      "loss": 0.6685,
+      "step": 2815
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00018024691358024692,
+      "loss": 0.642,
+      "step": 2820
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00017983539094650205,
+      "loss": 0.6873,
+      "step": 2825
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0001794238683127572,
+      "loss": 0.6506,
+      "step": 2830
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00017901234567901234,
+      "loss": 0.6695,
+      "step": 2835
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0001786008230452675,
+      "loss": 0.651,
+      "step": 2840
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00017818930041152265,
+      "loss": 0.6585,
+      "step": 2845
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 0.6717,
+      "step": 2850
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00017736625514403294,
+      "loss": 0.6524,
+      "step": 2855
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00017695473251028808,
+      "loss": 0.6679,
+      "step": 2860
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00017654320987654323,
+      "loss": 0.6719,
+      "step": 2865
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00017613168724279837,
+      "loss": 0.6662,
+      "step": 2870
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00017572016460905352,
+      "loss": 0.6624,
+      "step": 2875
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00017530864197530866,
+      "loss": 0.69,
+      "step": 2880
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0001748971193415638,
+      "loss": 0.6629,
+      "step": 2885
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00017448559670781895,
+      "loss": 0.6566,
+      "step": 2890
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00017407407407407408,
+      "loss": 0.6711,
+      "step": 2895
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00017366255144032924,
+      "loss": 0.6995,
+      "step": 2900
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00017325102880658437,
+      "loss": 0.6597,
+      "step": 2905
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0001728395061728395,
+      "loss": 0.6685,
+      "step": 2910
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00017242798353909466,
+      "loss": 0.6649,
+      "step": 2915
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0001720164609053498,
+      "loss": 0.6824,
+      "step": 2920
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00017160493827160495,
+      "loss": 0.6484,
+      "step": 2925
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00017119341563786008,
+      "loss": 0.6693,
+      "step": 2930
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00017078189300411524,
+      "loss": 0.629,
+      "step": 2935
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00017037037037037037,
+      "loss": 0.6588,
+      "step": 2940
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00016995884773662553,
+      "loss": 0.6771,
+      "step": 2945
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00016954732510288066,
+      "loss": 0.6773,
+      "step": 2950
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00016913580246913582,
+      "loss": 0.6307,
+      "step": 2955
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00016872427983539098,
+      "loss": 0.6809,
+      "step": 2960
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0001683127572016461,
+      "loss": 0.6748,
+      "step": 2965
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00016790123456790124,
+      "loss": 0.6708,
+      "step": 2970
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0001674897119341564,
+      "loss": 0.6754,
+      "step": 2975
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00016707818930041153,
+      "loss": 0.6676,
+      "step": 2980
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 0.6662,
+      "step": 2985
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00016625514403292182,
+      "loss": 0.6933,
+      "step": 2990
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00016584362139917695,
+      "loss": 0.6879,
+      "step": 2995
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0001654320987654321,
+      "loss": 0.6979,
+      "step": 3000
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00016502057613168724,
+      "loss": 0.657,
+      "step": 3005
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0001646090534979424,
+      "loss": 0.6704,
+      "step": 3010
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00016419753086419753,
+      "loss": 0.6394,
+      "step": 3015
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0001637860082304527,
+      "loss": 0.6594,
+      "step": 3020
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00016337448559670782,
+      "loss": 0.6584,
+      "step": 3025
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00016296296296296295,
+      "loss": 0.6593,
+      "step": 3030
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0001625514403292181,
+      "loss": 0.6538,
+      "step": 3035
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00016213991769547324,
+      "loss": 0.6572,
+      "step": 3040
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0001617283950617284,
+      "loss": 0.6999,
+      "step": 3045
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00016131687242798353,
+      "loss": 0.6658,
+      "step": 3050
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0001609053497942387,
+      "loss": 0.6809,
+      "step": 3055
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00016049382716049385,
+      "loss": 0.6685,
+      "step": 3060
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00016008230452674898,
+      "loss": 0.6532,
+      "step": 3065
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00015967078189300414,
+      "loss": 0.6644,
+      "step": 3070
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00015925925925925927,
+      "loss": 0.6721,
+      "step": 3075
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00015884773662551443,
+      "loss": 0.6569,
+      "step": 3080
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00015843621399176956,
+      "loss": 0.6832,
+      "step": 3085
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.0001580246913580247,
+      "loss": 0.6721,
+      "step": 3090
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00015761316872427985,
+      "loss": 0.6532,
+      "step": 3095
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00015720164609053498,
+      "loss": 0.6955,
+      "step": 3100
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00015679012345679014,
+      "loss": 0.6853,
+      "step": 3105
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00015637860082304527,
+      "loss": 0.6943,
+      "step": 3110
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0001559670781893004,
+      "loss": 0.6815,
+      "step": 3115
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 0.6972,
+      "step": 3120
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0001551440329218107,
+      "loss": 0.6959,
+      "step": 3125
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00015473251028806585,
+      "loss": 0.6795,
+      "step": 3130
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00015432098765432098,
+      "loss": 0.6352,
+      "step": 3135
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00015390946502057614,
+      "loss": 0.6601,
+      "step": 3140
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00015349794238683127,
+      "loss": 0.676,
+      "step": 3145
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0001530864197530864,
+      "loss": 0.6352,
+      "step": 3150
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00015267489711934156,
+      "loss": 0.6434,
+      "step": 3155
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00015226337448559672,
+      "loss": 0.673,
+      "step": 3160
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00015185185185185185,
+      "loss": 0.6963,
+      "step": 3165
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.000151440329218107,
+      "loss": 0.6643,
+      "step": 3170
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00015102880658436214,
+      "loss": 0.6757,
+      "step": 3175
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0001506172839506173,
+      "loss": 0.6681,
+      "step": 3180
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00015020576131687243,
+      "loss": 0.6935,
+      "step": 3185
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0001497942386831276,
+      "loss": 0.6894,
+      "step": 3190
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00014938271604938272,
+      "loss": 0.64,
+      "step": 3195
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00014897119341563788,
+      "loss": 0.6481,
+      "step": 3200
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00014855967078189301,
+      "loss": 0.6644,
+      "step": 3205
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00014814814814814815,
+      "loss": 0.6358,
+      "step": 3210
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0001477366255144033,
+      "loss": 0.6678,
+      "step": 3215
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00014732510288065844,
+      "loss": 0.6755,
+      "step": 3220
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0001469135802469136,
+      "loss": 0.6486,
+      "step": 3225
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00014650205761316873,
+      "loss": 0.666,
+      "step": 3230
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00014609053497942386,
+      "loss": 0.6689,
+      "step": 3235
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00014567901234567902,
+      "loss": 0.6737,
+      "step": 3240
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00014526748971193415,
+      "loss": 0.6659,
+      "step": 3245
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0001448559670781893,
+      "loss": 0.6744,
+      "step": 3250
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00014444444444444444,
+      "loss": 0.648,
+      "step": 3255
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0001440329218106996,
+      "loss": 0.6455,
+      "step": 3260
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00014362139917695473,
+      "loss": 0.659,
+      "step": 3265
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00014320987654320989,
+      "loss": 0.6519,
+      "step": 3270
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00014279835390946504,
+      "loss": 0.6972,
+      "step": 3275
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00014238683127572018,
+      "loss": 0.6592,
+      "step": 3280
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00014197530864197534,
+      "loss": 0.6757,
+      "step": 3285
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00014156378600823047,
+      "loss": 0.6684,
+      "step": 3290
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0001411522633744856,
+      "loss": 0.6754,
+      "step": 3295
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00014074074074074076,
+      "loss": 0.6738,
+      "step": 3300
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0001403292181069959,
+      "loss": 0.683,
+      "step": 3305
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00013991769547325105,
+      "loss": 0.6434,
+      "step": 3310
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00013950617283950618,
+      "loss": 0.6416,
+      "step": 3315
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00013909465020576134,
+      "loss": 0.6687,
+      "step": 3320
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00013868312757201647,
+      "loss": 0.6663,
+      "step": 3325
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0001382716049382716,
+      "loss": 0.7113,
+      "step": 3330
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00013786008230452676,
+      "loss": 0.6625,
+      "step": 3335
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0001374485596707819,
+      "loss": 0.6593,
+      "step": 3340
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00013703703703703705,
+      "loss": 0.6707,
+      "step": 3345
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00013662551440329218,
+      "loss": 0.6567,
+      "step": 3350
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0001362139917695473,
+      "loss": 0.6622,
+      "step": 3355
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00013580246913580247,
+      "loss": 0.6849,
+      "step": 3360
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0001353909465020576,
+      "loss": 0.657,
+      "step": 3365
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00013497942386831276,
+      "loss": 0.6452,
+      "step": 3370
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00013456790123456792,
+      "loss": 0.6486,
+      "step": 3375
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00013415637860082305,
+      "loss": 0.6737,
+      "step": 3380
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0001337448559670782,
+      "loss": 0.6793,
+      "step": 3385
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.6869,
+      "step": 3390
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0001329218106995885,
+      "loss": 0.6594,
+      "step": 3395
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00013251028806584363,
+      "loss": 0.6793,
+      "step": 3400
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0001320987654320988,
+      "loss": 0.6879,
+      "step": 3405
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00013168724279835392,
+      "loss": 0.695,
+      "step": 3410
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00013127572016460905,
+      "loss": 0.6648,
+      "step": 3415
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.0001308641975308642,
+      "loss": 0.6162,
+      "step": 3420
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00013045267489711934,
+      "loss": 0.642,
+      "step": 3425
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.0001300411522633745,
+      "loss": 0.6618,
+      "step": 3430
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00012962962962962963,
+      "loss": 0.6535,
+      "step": 3435
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00012921810699588476,
+      "loss": 0.6664,
+      "step": 3440
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00012880658436213992,
+      "loss": 0.6427,
+      "step": 3445
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00012839506172839505,
+      "loss": 0.6584,
+      "step": 3450
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0001279835390946502,
+      "loss": 0.657,
+      "step": 3455
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00012757201646090534,
+      "loss": 0.6494,
+      "step": 3460
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0001271604938271605,
+      "loss": 0.6553,
+      "step": 3465
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00012674897119341563,
+      "loss": 0.6755,
+      "step": 3470
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0001263374485596708,
+      "loss": 0.6599,
+      "step": 3475
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00012592592592592592,
+      "loss": 0.6564,
+      "step": 3480
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00012551440329218108,
+      "loss": 0.6526,
+      "step": 3485
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00012510288065843624,
+      "loss": 0.6439,
+      "step": 3490
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00012469135802469137,
+      "loss": 0.6459,
+      "step": 3495
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0001242798353909465,
+      "loss": 0.6573,
+      "step": 3500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00012386831275720166,
+      "loss": 0.6773,
+      "step": 3505
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0001234567901234568,
+      "loss": 0.68,
+      "step": 3510
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00012304526748971195,
+      "loss": 0.6615,
+      "step": 3515
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00012263374485596708,
+      "loss": 0.6886,
+      "step": 3520
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00012222222222222224,
+      "loss": 0.667,
+      "step": 3525
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00012181069958847737,
+      "loss": 0.677,
+      "step": 3530
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.0001213991769547325,
+      "loss": 0.6709,
+      "step": 3535
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00012098765432098766,
+      "loss": 0.6258,
+      "step": 3540
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.0001205761316872428,
+      "loss": 0.6795,
+      "step": 3545
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00012016460905349795,
+      "loss": 0.6673,
+      "step": 3550
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00011975308641975308,
+      "loss": 0.6708,
+      "step": 3555
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00011934156378600823,
+      "loss": 0.6466,
+      "step": 3560
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00011893004115226339,
+      "loss": 0.6339,
+      "step": 3565
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00011851851851851852,
+      "loss": 0.6838,
+      "step": 3570
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00011810699588477368,
+      "loss": 0.6179,
+      "step": 3575
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00011769547325102881,
+      "loss": 0.6357,
+      "step": 3580
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00011728395061728397,
+      "loss": 0.6807,
+      "step": 3585
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.0001168724279835391,
+      "loss": 0.6365,
+      "step": 3590
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00011646090534979423,
+      "loss": 0.6518,
+      "step": 3595
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00011604938271604939,
+      "loss": 0.6467,
+      "step": 3600
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00011563786008230452,
+      "loss": 0.6537,
+      "step": 3605
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00011522633744855968,
+      "loss": 0.6324,
+      "step": 3610
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00011481481481481482,
+      "loss": 0.6826,
+      "step": 3615
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00011440329218106996,
+      "loss": 0.6643,
+      "step": 3620
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00011399176954732511,
+      "loss": 0.6464,
+      "step": 3625
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00011358024691358025,
+      "loss": 0.6601,
+      "step": 3630
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.0001131687242798354,
+      "loss": 0.6596,
+      "step": 3635
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00011275720164609054,
+      "loss": 0.72,
+      "step": 3640
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.0001123456790123457,
+      "loss": 0.7157,
+      "step": 3645
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00011193415637860083,
+      "loss": 0.6641,
+      "step": 3650
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00011152263374485596,
+      "loss": 0.6631,
+      "step": 3655
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 0.6454,
+      "step": 3660
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00011069958847736626,
+      "loss": 0.6957,
+      "step": 3665
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.0001102880658436214,
+      "loss": 0.6535,
+      "step": 3670
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00010987654320987655,
+      "loss": 0.6675,
+      "step": 3675
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00010946502057613168,
+      "loss": 0.6458,
+      "step": 3680
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00010905349794238684,
+      "loss": 0.6507,
+      "step": 3685
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00010864197530864197,
+      "loss": 0.6818,
+      "step": 3690
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00010823045267489713,
+      "loss": 0.6752,
+      "step": 3695
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00010781893004115226,
+      "loss": 0.6645,
+      "step": 3700
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00010740740740740742,
+      "loss": 0.6414,
+      "step": 3705
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00010699588477366255,
+      "loss": 0.675,
+      "step": 3710
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.0001065843621399177,
+      "loss": 0.6597,
+      "step": 3715
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00010617283950617284,
+      "loss": 0.6637,
+      "step": 3720
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00010576131687242799,
+      "loss": 0.664,
+      "step": 3725
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00010534979423868315,
+      "loss": 0.6638,
+      "step": 3730
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00010493827160493828,
+      "loss": 0.6413,
+      "step": 3735
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00010452674897119341,
+      "loss": 0.6242,
+      "step": 3740
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00010411522633744857,
+      "loss": 0.6653,
+      "step": 3745
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.0001037037037037037,
+      "loss": 0.6947,
+      "step": 3750
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00010329218106995886,
+      "loss": 0.6801,
+      "step": 3755
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00010288065843621399,
+      "loss": 0.671,
+      "step": 3760
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00010246913580246915,
+      "loss": 0.6505,
+      "step": 3765
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00010205761316872428,
+      "loss": 0.6738,
+      "step": 3770
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00010164609053497942,
+      "loss": 0.6478,
+      "step": 3775
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00010123456790123458,
+      "loss": 0.6652,
+      "step": 3780
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00010082304526748971,
+      "loss": 0.6456,
+      "step": 3785
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00010041152263374487,
+      "loss": 0.6509,
+      "step": 3790
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.0001,
+      "loss": 0.6623,
+      "step": 3795
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 9.958847736625515e-05,
+      "loss": 0.6727,
+      "step": 3800
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 9.91769547325103e-05,
+      "loss": 0.676,
+      "step": 3805
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 9.876543209876543e-05,
+      "loss": 0.6662,
+      "step": 3810
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 9.835390946502057e-05,
+      "loss": 0.6767,
+      "step": 3815
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 9.794238683127573e-05,
+      "loss": 0.6278,
+      "step": 3820
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 9.753086419753087e-05,
+      "loss": 0.6769,
+      "step": 3825
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 9.711934156378602e-05,
+      "loss": 0.667,
+      "step": 3830
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 9.670781893004116e-05,
+      "loss": 0.6392,
+      "step": 3835
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 9.62962962962963e-05,
+      "loss": 0.6479,
+      "step": 3840
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 9.588477366255144e-05,
+      "loss": 0.6958,
+      "step": 3845
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 9.547325102880659e-05,
+      "loss": 0.6636,
+      "step": 3850
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 9.506172839506173e-05,
+      "loss": 0.6722,
+      "step": 3855
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 9.465020576131688e-05,
+      "loss": 0.6688,
+      "step": 3860
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 9.423868312757202e-05,
+      "loss": 0.6814,
+      "step": 3865
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 9.382716049382717e-05,
+      "loss": 0.679,
+      "step": 3870
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.341563786008231e-05,
+      "loss": 0.6536,
+      "step": 3875
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.300411522633746e-05,
+      "loss": 0.6783,
+      "step": 3880
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.25925925925926e-05,
+      "loss": 0.6424,
+      "step": 3885
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.218106995884775e-05,
+      "loss": 0.6695,
+      "step": 3890
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.176954732510289e-05,
+      "loss": 0.6941,
+      "step": 3895
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.135802469135802e-05,
+      "loss": 0.6887,
+      "step": 3900
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.094650205761317e-05,
+      "loss": 0.6789,
+      "step": 3905
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.053497942386831e-05,
+      "loss": 0.6819,
+      "step": 3910
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.012345679012346e-05,
+      "loss": 0.6571,
+      "step": 3915
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 8.97119341563786e-05,
+      "loss": 0.6527,
+      "step": 3920
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 8.930041152263375e-05,
+      "loss": 0.6656,
+      "step": 3925
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 0.6551,
+      "step": 3930
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 8.847736625514404e-05,
+      "loss": 0.6502,
+      "step": 3935
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 8.806584362139918e-05,
+      "loss": 0.6458,
+      "step": 3940
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 8.765432098765433e-05,
+      "loss": 0.6617,
+      "step": 3945
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 8.724279835390947e-05,
+      "loss": 0.6444,
+      "step": 3950
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 8.683127572016462e-05,
+      "loss": 0.6629,
+      "step": 3955
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 8.641975308641975e-05,
+      "loss": 0.6683,
+      "step": 3960
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 8.60082304526749e-05,
+      "loss": 0.6483,
+      "step": 3965
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 8.559670781893004e-05,
+      "loss": 0.6623,
+      "step": 3970
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 8.518518518518518e-05,
+      "loss": 0.6491,
+      "step": 3975
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 8.477366255144033e-05,
+      "loss": 0.6394,
+      "step": 3980
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 8.436213991769549e-05,
+      "loss": 0.6494,
+      "step": 3985
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 8.395061728395062e-05,
+      "loss": 0.6516,
+      "step": 3990
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 8.353909465020576e-05,
+      "loss": 0.6664,
+      "step": 3995
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 8.312757201646091e-05,
+      "loss": 0.6822,
+      "step": 4000
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 8.271604938271605e-05,
+      "loss": 0.6335,
+      "step": 4005
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 8.23045267489712e-05,
+      "loss": 0.6386,
+      "step": 4010
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 8.189300411522634e-05,
+      "loss": 0.6495,
+      "step": 4015
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.6784,
+      "step": 4020
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 8.106995884773662e-05,
+      "loss": 0.6522,
+      "step": 4025
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 8.065843621399177e-05,
+      "loss": 0.6292,
+      "step": 4030
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 8.024691358024692e-05,
+      "loss": 0.6513,
+      "step": 4035
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 7.983539094650207e-05,
+      "loss": 0.622,
+      "step": 4040
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 7.942386831275721e-05,
+      "loss": 0.6619,
+      "step": 4045
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 7.901234567901235e-05,
+      "loss": 0.651,
+      "step": 4050
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 7.860082304526749e-05,
+      "loss": 0.6538,
+      "step": 4055
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 7.818930041152264e-05,
+      "loss": 0.6572,
+      "step": 4060
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 7.777777777777778e-05,
+      "loss": 0.6935,
+      "step": 4065
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 7.736625514403293e-05,
+      "loss": 0.6598,
+      "step": 4070
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 7.695473251028807e-05,
+      "loss": 0.6533,
+      "step": 4075
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 7.65432098765432e-05,
+      "loss": 0.665,
+      "step": 4080
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 7.613168724279836e-05,
+      "loss": 0.651,
+      "step": 4085
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 7.57201646090535e-05,
+      "loss": 0.6914,
+      "step": 4090
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 7.530864197530865e-05,
+      "loss": 0.6431,
+      "step": 4095
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 7.48971193415638e-05,
+      "loss": 0.6753,
+      "step": 4100
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 7.448559670781894e-05,
+      "loss": 0.6814,
+      "step": 4105
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 7.407407407407407e-05,
+      "loss": 0.6386,
+      "step": 4110
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 7.366255144032922e-05,
+      "loss": 0.6307,
+      "step": 4115
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 7.325102880658436e-05,
+      "loss": 0.6401,
+      "step": 4120
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 7.283950617283951e-05,
+      "loss": 0.6496,
+      "step": 4125
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 7.242798353909465e-05,
+      "loss": 0.6593,
+      "step": 4130
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 7.20164609053498e-05,
+      "loss": 0.6472,
+      "step": 4135
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 7.160493827160494e-05,
+      "loss": 0.6746,
+      "step": 4140
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 7.119341563786009e-05,
+      "loss": 0.6498,
+      "step": 4145
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 7.078189300411523e-05,
+      "loss": 0.6597,
+      "step": 4150
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 7.037037037037038e-05,
+      "loss": 0.671,
+      "step": 4155
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 6.995884773662552e-05,
+      "loss": 0.6786,
+      "step": 4160
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 6.954732510288067e-05,
+      "loss": 0.6846,
+      "step": 4165
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 6.91358024691358e-05,
+      "loss": 0.6619,
+      "step": 4170
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 6.872427983539094e-05,
+      "loss": 0.6755,
+      "step": 4175
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 6.831275720164609e-05,
+      "loss": 0.6406,
+      "step": 4180
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 6.790123456790123e-05,
+      "loss": 0.671,
+      "step": 4185
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 6.748971193415638e-05,
+      "loss": 0.6448,
+      "step": 4190
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 6.707818930041152e-05,
+      "loss": 0.6594,
+      "step": 4195
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.6626,
+      "step": 4200
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 6.625514403292181e-05,
+      "loss": 0.6577,
+      "step": 4205
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 6.584362139917696e-05,
+      "loss": 0.6468,
+      "step": 4210
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 6.54320987654321e-05,
+      "loss": 0.6836,
+      "step": 4215
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 6.502057613168725e-05,
+      "loss": 0.6766,
+      "step": 4220
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 6.460905349794238e-05,
+      "loss": 0.6639,
+      "step": 4225
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 6.419753086419753e-05,
+      "loss": 0.6653,
+      "step": 4230
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 6.378600823045267e-05,
+      "loss": 0.6501,
+      "step": 4235
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 6.337448559670782e-05,
+      "loss": 0.6775,
+      "step": 4240
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 6.296296296296296e-05,
+      "loss": 0.661,
+      "step": 4245
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 6.255144032921812e-05,
+      "loss": 0.6417,
+      "step": 4250
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 6.213991769547325e-05,
+      "loss": 0.6626,
+      "step": 4255
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 6.17283950617284e-05,
+      "loss": 0.667,
+      "step": 4260
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 6.131687242798354e-05,
+      "loss": 0.6683,
+      "step": 4265
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 6.0905349794238687e-05,
+      "loss": 0.6523,
+      "step": 4270
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 6.049382716049383e-05,
+      "loss": 0.6686,
+      "step": 4275
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 6.0082304526748977e-05,
+      "loss": 0.6365,
+      "step": 4280
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 5.9670781893004115e-05,
+      "loss": 0.6211,
+      "step": 4285
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 5.925925925925926e-05,
+      "loss": 0.6414,
+      "step": 4290
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 5.8847736625514405e-05,
+      "loss": 0.6488,
+      "step": 4295
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 5.843621399176955e-05,
+      "loss": 0.6506,
+      "step": 4300
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 5.8024691358024695e-05,
+      "loss": 0.6692,
+      "step": 4305
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 5.761316872427984e-05,
+      "loss": 0.6617,
+      "step": 4310
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 5.720164609053498e-05,
+      "loss": 0.6464,
+      "step": 4315
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 5.679012345679012e-05,
+      "loss": 0.6432,
+      "step": 4320
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 5.637860082304527e-05,
+      "loss": 0.6642,
+      "step": 4325
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 5.596707818930041e-05,
+      "loss": 0.6487,
+      "step": 4330
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 5.555555555555556e-05,
+      "loss": 0.6384,
+      "step": 4335
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 5.51440329218107e-05,
+      "loss": 0.6167,
+      "step": 4340
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 5.473251028806584e-05,
+      "loss": 0.6576,
+      "step": 4345
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 5.4320987654320986e-05,
+      "loss": 0.6482,
+      "step": 4350
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 5.390946502057613e-05,
+      "loss": 0.6526,
+      "step": 4355
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 5.3497942386831277e-05,
+      "loss": 0.6427,
+      "step": 4360
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 5.308641975308642e-05,
+      "loss": 0.6425,
+      "step": 4365
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 5.267489711934157e-05,
+      "loss": 0.713,
+      "step": 4370
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 5.2263374485596705e-05,
+      "loss": 0.6414,
+      "step": 4375
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 5.185185185185185e-05,
+      "loss": 0.6578,
+      "step": 4380
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 5.1440329218106995e-05,
+      "loss": 0.6461,
+      "step": 4385
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 5.102880658436214e-05,
+      "loss": 0.651,
+      "step": 4390
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 5.061728395061729e-05,
+      "loss": 0.6523,
+      "step": 4395
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 5.020576131687244e-05,
+      "loss": 0.6625,
+      "step": 4400
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 4.9794238683127575e-05,
+      "loss": 0.6763,
+      "step": 4405
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 4.938271604938271e-05,
+      "loss": 0.6759,
+      "step": 4410
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 4.8971193415637865e-05,
+      "loss": 0.6742,
+      "step": 4415
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 4.855967078189301e-05,
+      "loss": 0.6617,
+      "step": 4420
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 4.814814814814815e-05,
+      "loss": 0.6604,
+      "step": 4425
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 4.773662551440329e-05,
+      "loss": 0.6739,
+      "step": 4430
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 4.732510288065844e-05,
+      "loss": 0.641,
+      "step": 4435
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 4.691358024691358e-05,
+      "loss": 0.6322,
+      "step": 4440
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 4.650205761316873e-05,
+      "loss": 0.6392,
+      "step": 4445
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 4.609053497942387e-05,
+      "loss": 0.6795,
+      "step": 4450
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 4.567901234567901e-05,
+      "loss": 0.6712,
+      "step": 4455
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 4.5267489711934157e-05,
+      "loss": 0.6353,
+      "step": 4460
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 4.48559670781893e-05,
+      "loss": 0.6587,
+      "step": 4465
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.6748,
+      "step": 4470
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 4.403292181069959e-05,
+      "loss": 0.6755,
+      "step": 4475
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 4.3621399176954737e-05,
+      "loss": 0.6513,
+      "step": 4480
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 4.3209876543209875e-05,
+      "loss": 0.6728,
+      "step": 4485
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 4.279835390946502e-05,
+      "loss": 0.6536,
+      "step": 4490
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 4.2386831275720165e-05,
+      "loss": 0.6652,
+      "step": 4495
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 4.197530864197531e-05,
+      "loss": 0.6715,
+      "step": 4500
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 4.1563786008230455e-05,
+      "loss": 0.6523,
+      "step": 4505
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 4.11522633744856e-05,
+      "loss": 0.6856,
+      "step": 4510
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 4.074074074074074e-05,
+      "loss": 0.6658,
+      "step": 4515
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 4.032921810699588e-05,
+      "loss": 0.6122,
+      "step": 4520
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 3.9917695473251035e-05,
+      "loss": 0.6719,
+      "step": 4525
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 3.950617283950617e-05,
+      "loss": 0.6618,
+      "step": 4530
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 3.909465020576132e-05,
+      "loss": 0.6594,
+      "step": 4535
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 3.868312757201646e-05,
+      "loss": 0.6576,
+      "step": 4540
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 3.82716049382716e-05,
+      "loss": 0.6726,
+      "step": 4545
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 3.786008230452675e-05,
+      "loss": 0.6573,
+      "step": 4550
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 3.74485596707819e-05,
+      "loss": 0.6503,
+      "step": 4555
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.7026,
+      "step": 4560
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 3.662551440329218e-05,
+      "loss": 0.6261,
+      "step": 4565
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 3.6213991769547327e-05,
+      "loss": 0.6328,
+      "step": 4570
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 3.580246913580247e-05,
+      "loss": 0.6771,
+      "step": 4575
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 3.539094650205762e-05,
+      "loss": 0.6563,
+      "step": 4580
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 3.497942386831276e-05,
+      "loss": 0.6415,
+      "step": 4585
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 3.45679012345679e-05,
+      "loss": 0.6735,
+      "step": 4590
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 3.4156378600823045e-05,
+      "loss": 0.667,
+      "step": 4595
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.374485596707819e-05,
+      "loss": 0.6917,
+      "step": 4600
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.661,
+      "step": 4605
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.292181069958848e-05,
+      "loss": 0.6424,
+      "step": 4610
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.2510288065843625e-05,
+      "loss": 0.6321,
+      "step": 4615
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.209876543209876e-05,
+      "loss": 0.658,
+      "step": 4620
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 3.168724279835391e-05,
+      "loss": 0.6707,
+      "step": 4625
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 3.127572016460906e-05,
+      "loss": 0.6416,
+      "step": 4630
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 3.08641975308642e-05,
+      "loss": 0.6478,
+      "step": 4635
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 3.0452674897119343e-05,
+      "loss": 0.6555,
+      "step": 4640
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 3.0041152263374488e-05,
+      "loss": 0.6557,
+      "step": 4645
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2.962962962962963e-05,
+      "loss": 0.6711,
+      "step": 4650
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2.9218106995884775e-05,
+      "loss": 0.6738,
+      "step": 4655
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2.880658436213992e-05,
+      "loss": 0.6428,
+      "step": 4660
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2.839506172839506e-05,
+      "loss": 0.6652,
+      "step": 4665
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2.7983539094650207e-05,
+      "loss": 0.6601,
+      "step": 4670
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.757201646090535e-05,
+      "loss": 0.6358,
+      "step": 4675
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.7160493827160493e-05,
+      "loss": 0.6661,
+      "step": 4680
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.6748971193415638e-05,
+      "loss": 0.6708,
+      "step": 4685
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.6337448559670787e-05,
+      "loss": 0.6475,
+      "step": 4690
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 0.6776,
+      "step": 4695
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 2.551440329218107e-05,
+      "loss": 0.6767,
+      "step": 4700
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 2.510288065843622e-05,
+      "loss": 0.6882,
+      "step": 4705
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 2.4691358024691357e-05,
+      "loss": 0.6538,
+      "step": 4710
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 2.4279835390946505e-05,
+      "loss": 0.6402,
+      "step": 4715
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 2.3868312757201647e-05,
+      "loss": 0.6678,
+      "step": 4720
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 2.345679012345679e-05,
+      "loss": 0.6654,
+      "step": 4725
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 2.3045267489711937e-05,
+      "loss": 0.6839,
+      "step": 4730
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 2.2633744855967078e-05,
+      "loss": 0.6487,
+      "step": 4735
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 0.6501,
+      "step": 4740
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 2.1810699588477368e-05,
+      "loss": 0.6946,
+      "step": 4745
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 2.139917695473251e-05,
+      "loss": 0.6906,
+      "step": 4750
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 2.0987654320987655e-05,
+      "loss": 0.6598,
+      "step": 4755
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 2.05761316872428e-05,
+      "loss": 0.6733,
+      "step": 4760
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 2.016460905349794e-05,
+      "loss": 0.6685,
+      "step": 4765
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.9753086419753087e-05,
+      "loss": 0.6703,
+      "step": 4770
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.934156378600823e-05,
+      "loss": 0.6416,
+      "step": 4775
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.8930041152263377e-05,
+      "loss": 0.651,
+      "step": 4780
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.8518518518518518e-05,
+      "loss": 0.6446,
+      "step": 4785
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.8106995884773663e-05,
+      "loss": 0.6406,
+      "step": 4790
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.769547325102881e-05,
+      "loss": 0.6725,
+      "step": 4795
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.728395061728395e-05,
+      "loss": 0.6469,
+      "step": 4800
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.6872427983539095e-05,
+      "loss": 0.6931,
+      "step": 4805
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.646090534979424e-05,
+      "loss": 0.6506,
+      "step": 4810
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.604938271604938e-05,
+      "loss": 0.6687,
+      "step": 4815
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.563786008230453e-05,
+      "loss": 0.6673,
+      "step": 4820
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.5226337448559672e-05,
+      "loss": 0.6436,
+      "step": 4825
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.4814814814814815e-05,
+      "loss": 0.6722,
+      "step": 4830
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.440329218106996e-05,
+      "loss": 0.6492,
+      "step": 4835
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.3991769547325103e-05,
+      "loss": 0.6737,
+      "step": 4840
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.3580246913580247e-05,
+      "loss": 0.6645,
+      "step": 4845
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.3168724279835393e-05,
+      "loss": 0.6598,
+      "step": 4850
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.2757201646090535e-05,
+      "loss": 0.6383,
+      "step": 4855
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.2345679012345678e-05,
+      "loss": 0.666,
+      "step": 4860
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.1934156378600823e-05,
+      "loss": 0.6434,
+      "step": 4865
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.1522633744855968e-05,
+      "loss": 0.666,
+      "step": 4870
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 0.6517,
+      "step": 4875
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.0699588477366255e-05,
+      "loss": 0.6581,
+      "step": 4880
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.02880658436214e-05,
+      "loss": 0.6621,
+      "step": 4885
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 9.876543209876543e-06,
+      "loss": 0.6856,
+      "step": 4890
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 9.465020576131688e-06,
+      "loss": 0.6572,
+      "step": 4895
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 9.053497942386832e-06,
+      "loss": 0.6864,
+      "step": 4900
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 8.641975308641975e-06,
+      "loss": 0.6465,
+      "step": 4905
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 8.23045267489712e-06,
+      "loss": 0.659,
+      "step": 4910
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 7.818930041152265e-06,
+      "loss": 0.6617,
+      "step": 4915
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 0.651,
+      "step": 4920
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 6.995884773662552e-06,
+      "loss": 0.658,
+      "step": 4925
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 6.584362139917697e-06,
+      "loss": 0.6701,
+      "step": 4930
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 6.172839506172839e-06,
+      "loss": 0.6471,
+      "step": 4935
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 5.761316872427984e-06,
+      "loss": 0.6536,
+      "step": 4940
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 5.3497942386831275e-06,
+      "loss": 0.6737,
+      "step": 4945
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 4.938271604938272e-06,
+      "loss": 0.679,
+      "step": 4950
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 4.526748971193416e-06,
+      "loss": 0.6192,
+      "step": 4955
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 4.11522633744856e-06,
+      "loss": 0.6323,
+      "step": 4960
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 0.6555,
+      "step": 4965
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 3.2921810699588483e-06,
+      "loss": 0.6657,
+      "step": 4970
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 2.880658436213992e-06,
+      "loss": 0.6712,
+      "step": 4975
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 2.469135802469136e-06,
+      "loss": 0.6563,
+      "step": 4980
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 2.05761316872428e-06,
+      "loss": 0.6885,
+      "step": 4985
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.6460905349794242e-06,
+      "loss": 0.6666,
+      "step": 4990
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.234567901234568e-06,
+      "loss": 0.6696,
+      "step": 4995
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8.230452674897121e-07,
+      "loss": 0.699,
+      "step": 5000
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 5010,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 2.0132950426699956e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/training_args.bin b/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..28c7b09fc2b3929abe4ad6608c7959f30a9a9d66
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43458f4cf6aeb211c730b848f93ab15f483827c314fb4dc1e79dd1f658b7dbc8
+size 5944
diff --git a/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/zero_to_fp32.py b/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/zero_to_fp32.py
new file mode 100644
index 0000000000000000000000000000000000000000..c98caae31534368be22b67fc4ae906836c992a8d
--- /dev/null
+++ b/save_lora_instruct_r8_4e4_s11_1/checkpoint-5000/zero_to_fp32.py
@@ -0,0 +1,587 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel()
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file, tag=args.tag)