Upload 14 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-2040/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-2040/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/qwen2.5-3b-unsloth-bnb-4bit
+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 0.12.0

checkpoint-2040/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/qwen2.5-3b-unsloth-bnb-4bit",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-2040/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e4929cae24abe86b335d7939dc2c67773fa11607ee8efeef63bee2ef9c609e4
+size 119801528

checkpoint-2040/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-2040/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:506e6c704b390dbb60b83e1ed8288c02a0701b86204222197160a4cd8b250b5d
+size 239892858

checkpoint-2040/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af0a954e380f7eb9a10b15aefe1bed98935eddc2d46d61efc881ba7a7f35e2e0
+size 14244

checkpoint-2040/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68c637f32115eeaba87d678c1c7250c2689b0b4d728dd26a0a4e92e2042b1f8a
+size 1064

checkpoint-2040/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2040/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d22d96e26b44b3ebafcee04dc9f9b23a198596119f9de96013c2734d0a36a2b4
+size 11421995

checkpoint-2040/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-2040/trainer_state.json

@@ -0,0 +1,1462 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2040,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.024509803921568627,
+      "grad_norm": 0.29983004927635193,
+      "learning_rate": 0.00019950980392156864,
+      "loss": 1.497,
+      "step": 10
+    },
+    {
+      "epoch": 0.049019607843137254,
+      "grad_norm": 0.22434405982494354,
+      "learning_rate": 0.00019901960784313727,
+      "loss": 1.0531,
+      "step": 20
+    },
+    {
+      "epoch": 0.07352941176470588,
+      "grad_norm": 0.1899292916059494,
+      "learning_rate": 0.0001985294117647059,
+      "loss": 0.9282,
+      "step": 30
+    },
+    {
+      "epoch": 0.09803921568627451,
+      "grad_norm": 0.21063339710235596,
+      "learning_rate": 0.00019803921568627454,
+      "loss": 0.9509,
+      "step": 40
+    },
+    {
+      "epoch": 0.12254901960784313,
+      "grad_norm": 0.2021014541387558,
+      "learning_rate": 0.00019754901960784314,
+      "loss": 0.9195,
+      "step": 50
+    },
+    {
+      "epoch": 0.14705882352941177,
+      "grad_norm": 0.22847646474838257,
+      "learning_rate": 0.00019705882352941177,
+      "loss": 0.9314,
+      "step": 60
+    },
+    {
+      "epoch": 0.1715686274509804,
+      "grad_norm": 0.24809524416923523,
+      "learning_rate": 0.00019656862745098038,
+      "loss": 0.8545,
+      "step": 70
+    },
+    {
+      "epoch": 0.19607843137254902,
+      "grad_norm": 0.23628589510917664,
+      "learning_rate": 0.000196078431372549,
+      "loss": 0.8714,
+      "step": 80
+    },
+    {
+      "epoch": 0.22058823529411764,
+      "grad_norm": 0.25221529603004456,
+      "learning_rate": 0.00019558823529411764,
+      "loss": 0.8254,
+      "step": 90
+    },
+    {
+      "epoch": 0.24509803921568626,
+      "grad_norm": 0.25446635484695435,
+      "learning_rate": 0.00019509803921568628,
+      "loss": 0.8309,
+      "step": 100
+    },
+    {
+      "epoch": 0.2696078431372549,
+      "grad_norm": 0.23954473435878754,
+      "learning_rate": 0.0001946078431372549,
+      "loss": 0.879,
+      "step": 110
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 0.2512606382369995,
+      "learning_rate": 0.00019411764705882354,
+      "loss": 0.8101,
+      "step": 120
+    },
+    {
+      "epoch": 0.31862745098039214,
+      "grad_norm": 0.24768000841140747,
+      "learning_rate": 0.00019362745098039217,
+      "loss": 0.8346,
+      "step": 130
+    },
+    {
+      "epoch": 0.3431372549019608,
+      "grad_norm": 0.24737860262393951,
+      "learning_rate": 0.0001931372549019608,
+      "loss": 0.8123,
+      "step": 140
+    },
+    {
+      "epoch": 0.36764705882352944,
+      "grad_norm": 0.2855224013328552,
+      "learning_rate": 0.00019264705882352944,
+      "loss": 0.7965,
+      "step": 150
+    },
+    {
+      "epoch": 0.39215686274509803,
+      "grad_norm": 0.27062663435935974,
+      "learning_rate": 0.00019215686274509807,
+      "loss": 0.8108,
+      "step": 160
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.2578269839286804,
+      "learning_rate": 0.00019166666666666667,
+      "loss": 0.809,
+      "step": 170
+    },
+    {
+      "epoch": 0.4411764705882353,
+      "grad_norm": 0.2555166482925415,
+      "learning_rate": 0.0001911764705882353,
+      "loss": 0.7826,
+      "step": 180
+    },
+    {
+      "epoch": 0.46568627450980393,
+      "grad_norm": 0.3456018567085266,
+      "learning_rate": 0.00019068627450980394,
+      "loss": 0.7771,
+      "step": 190
+    },
+    {
+      "epoch": 0.49019607843137253,
+      "grad_norm": 0.2838132381439209,
+      "learning_rate": 0.00019019607843137254,
+      "loss": 0.7505,
+      "step": 200
+    },
+    {
+      "epoch": 0.5147058823529411,
+      "grad_norm": 0.2752726078033447,
+      "learning_rate": 0.00018970588235294117,
+      "loss": 0.7402,
+      "step": 210
+    },
+    {
+      "epoch": 0.5392156862745098,
+      "grad_norm": 0.26294729113578796,
+      "learning_rate": 0.0001892156862745098,
+      "loss": 0.7353,
+      "step": 220
+    },
+    {
+      "epoch": 0.5637254901960784,
+      "grad_norm": 0.28479790687561035,
+      "learning_rate": 0.00018872549019607844,
+      "loss": 0.8024,
+      "step": 230
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.2948661148548126,
+      "learning_rate": 0.00018823529411764707,
+      "loss": 0.7628,
+      "step": 240
+    },
+    {
+      "epoch": 0.6127450980392157,
+      "grad_norm": 0.26690128445625305,
+      "learning_rate": 0.0001877450980392157,
+      "loss": 0.75,
+      "step": 250
+    },
+    {
+      "epoch": 0.6372549019607843,
+      "grad_norm": 0.2684984803199768,
+      "learning_rate": 0.00018725490196078433,
+      "loss": 0.7458,
+      "step": 260
+    },
+    {
+      "epoch": 0.6617647058823529,
+      "grad_norm": 0.24935846030712128,
+      "learning_rate": 0.00018676470588235297,
+      "loss": 0.7901,
+      "step": 270
+    },
+    {
+      "epoch": 0.6862745098039216,
+      "grad_norm": 0.26486936211586,
+      "learning_rate": 0.00018627450980392157,
+      "loss": 0.7356,
+      "step": 280
+    },
+    {
+      "epoch": 0.7107843137254902,
+      "grad_norm": 0.2598109245300293,
+      "learning_rate": 0.0001857843137254902,
+      "loss": 0.7749,
+      "step": 290
+    },
+    {
+      "epoch": 0.7352941176470589,
+      "grad_norm": 0.29170921444892883,
+      "learning_rate": 0.00018529411764705883,
+      "loss": 0.7322,
+      "step": 300
+    },
+    {
+      "epoch": 0.7598039215686274,
+      "grad_norm": 0.26423102617263794,
+      "learning_rate": 0.00018480392156862747,
+      "loss": 0.7544,
+      "step": 310
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 0.29086926579475403,
+      "learning_rate": 0.00018431372549019607,
+      "loss": 0.7452,
+      "step": 320
+    },
+    {
+      "epoch": 0.8088235294117647,
+      "grad_norm": 0.2983661890029907,
+      "learning_rate": 0.0001838235294117647,
+      "loss": 0.7263,
+      "step": 330
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.27282992005348206,
+      "learning_rate": 0.00018333333333333334,
+      "loss": 0.739,
+      "step": 340
+    },
+    {
+      "epoch": 0.8578431372549019,
+      "grad_norm": 0.2726730704307556,
+      "learning_rate": 0.00018284313725490197,
+      "loss": 0.7134,
+      "step": 350
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 0.282355397939682,
+      "learning_rate": 0.0001823529411764706,
+      "loss": 0.7545,
+      "step": 360
+    },
+    {
+      "epoch": 0.9068627450980392,
+      "grad_norm": 0.2755967080593109,
+      "learning_rate": 0.00018186274509803923,
+      "loss": 0.7286,
+      "step": 370
+    },
+    {
+      "epoch": 0.9313725490196079,
+      "grad_norm": 0.27661100029945374,
+      "learning_rate": 0.00018137254901960786,
+      "loss": 0.7363,
+      "step": 380
+    },
+    {
+      "epoch": 0.9558823529411765,
+      "grad_norm": 0.24934948980808258,
+      "learning_rate": 0.00018088235294117647,
+      "loss": 0.7397,
+      "step": 390
+    },
+    {
+      "epoch": 0.9803921568627451,
+      "grad_norm": 0.28986600041389465,
+      "learning_rate": 0.0001803921568627451,
+      "loss": 0.722,
+      "step": 400
+    },
+    {
+      "epoch": 1.0049019607843137,
+      "grad_norm": 0.24967212975025177,
+      "learning_rate": 0.00017990196078431373,
+      "loss": 0.7431,
+      "step": 410
+    },
+    {
+      "epoch": 1.0294117647058822,
+      "grad_norm": 0.3122069537639618,
+      "learning_rate": 0.00017941176470588236,
+      "loss": 0.6769,
+      "step": 420
+    },
+    {
+      "epoch": 1.053921568627451,
+      "grad_norm": 0.27327316999435425,
+      "learning_rate": 0.000178921568627451,
+      "loss": 0.6854,
+      "step": 430
+    },
+    {
+      "epoch": 1.0784313725490196,
+      "grad_norm": 0.2995717227458954,
+      "learning_rate": 0.00017843137254901963,
+      "loss": 0.6592,
+      "step": 440
+    },
+    {
+      "epoch": 1.1029411764705883,
+      "grad_norm": 0.2795763313770294,
+      "learning_rate": 0.00017794117647058823,
+      "loss": 0.6666,
+      "step": 450
+    },
+    {
+      "epoch": 1.1274509803921569,
+      "grad_norm": 0.2783352732658386,
+      "learning_rate": 0.00017745098039215687,
+      "loss": 0.6626,
+      "step": 460
+    },
+    {
+      "epoch": 1.1519607843137254,
+      "grad_norm": 0.29723408818244934,
+      "learning_rate": 0.0001769607843137255,
+      "loss": 0.6811,
+      "step": 470
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.30281776189804077,
+      "learning_rate": 0.00017647058823529413,
+      "loss": 0.6673,
+      "step": 480
+    },
+    {
+      "epoch": 1.2009803921568627,
+      "grad_norm": 0.32884112000465393,
+      "learning_rate": 0.00017598039215686276,
+      "loss": 0.7036,
+      "step": 490
+    },
+    {
+      "epoch": 1.2254901960784315,
+      "grad_norm": 0.30529946088790894,
+      "learning_rate": 0.00017549019607843137,
+      "loss": 0.6559,
+      "step": 500
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.32612255215644836,
+      "learning_rate": 0.000175,
+      "loss": 0.6739,
+      "step": 510
+    },
+    {
+      "epoch": 1.2745098039215685,
+      "grad_norm": 0.28662651777267456,
+      "learning_rate": 0.00017450980392156863,
+      "loss": 0.6675,
+      "step": 520
+    },
+    {
+      "epoch": 1.2990196078431373,
+      "grad_norm": 0.30719125270843506,
+      "learning_rate": 0.00017401960784313726,
+      "loss": 0.7133,
+      "step": 530
+    },
+    {
+      "epoch": 1.3235294117647058,
+      "grad_norm": 0.29701197147369385,
+      "learning_rate": 0.0001735294117647059,
+      "loss": 0.6542,
+      "step": 540
+    },
+    {
+      "epoch": 1.3480392156862746,
+      "grad_norm": 0.274860143661499,
+      "learning_rate": 0.00017303921568627453,
+      "loss": 0.7098,
+      "step": 550
+    },
+    {
+      "epoch": 1.3725490196078431,
+      "grad_norm": 0.3022995889186859,
+      "learning_rate": 0.00017254901960784316,
+      "loss": 0.6648,
+      "step": 560
+    },
+    {
+      "epoch": 1.3970588235294117,
+      "grad_norm": 0.2775422930717468,
+      "learning_rate": 0.0001720588235294118,
+      "loss": 0.645,
+      "step": 570
+    },
+    {
+      "epoch": 1.4215686274509804,
+      "grad_norm": 0.3129810392856598,
+      "learning_rate": 0.0001715686274509804,
+      "loss": 0.6922,
+      "step": 580
+    },
+    {
+      "epoch": 1.446078431372549,
+      "grad_norm": 0.2952588200569153,
+      "learning_rate": 0.00017107843137254903,
+      "loss": 0.6353,
+      "step": 590
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 0.2810933589935303,
+      "learning_rate": 0.00017058823529411766,
+      "loss": 0.6504,
+      "step": 600
+    },
+    {
+      "epoch": 1.4950980392156863,
+      "grad_norm": 0.3011665940284729,
+      "learning_rate": 0.0001700980392156863,
+      "loss": 0.6622,
+      "step": 610
+    },
+    {
+      "epoch": 1.5196078431372548,
+      "grad_norm": 0.2970154583454132,
+      "learning_rate": 0.0001696078431372549,
+      "loss": 0.6587,
+      "step": 620
+    },
+    {
+      "epoch": 1.5441176470588234,
+      "grad_norm": 0.2876601815223694,
+      "learning_rate": 0.00016911764705882353,
+      "loss": 0.6887,
+      "step": 630
+    },
+    {
+      "epoch": 1.5686274509803921,
+      "grad_norm": 0.29214441776275635,
+      "learning_rate": 0.00016862745098039216,
+      "loss": 0.6893,
+      "step": 640
+    },
+    {
+      "epoch": 1.593137254901961,
+      "grad_norm": 0.29072946310043335,
+      "learning_rate": 0.0001681372549019608,
+      "loss": 0.6752,
+      "step": 650
+    },
+    {
+      "epoch": 1.6176470588235294,
+      "grad_norm": 0.30002114176750183,
+      "learning_rate": 0.00016764705882352942,
+      "loss": 0.6521,
+      "step": 660
+    },
+    {
+      "epoch": 1.642156862745098,
+      "grad_norm": 0.2819446921348572,
+      "learning_rate": 0.00016715686274509806,
+      "loss": 0.6673,
+      "step": 670
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.2847635746002197,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 0.6597,
+      "step": 680
+    },
+    {
+      "epoch": 1.6911764705882353,
+      "grad_norm": 0.28922468423843384,
+      "learning_rate": 0.00016617647058823532,
+      "loss": 0.6467,
+      "step": 690
+    },
+    {
+      "epoch": 1.715686274509804,
+      "grad_norm": 0.29009920358657837,
+      "learning_rate": 0.00016568627450980395,
+      "loss": 0.6578,
+      "step": 700
+    },
+    {
+      "epoch": 1.7401960784313726,
+      "grad_norm": 0.29140380024909973,
+      "learning_rate": 0.00016519607843137256,
+      "loss": 0.6206,
+      "step": 710
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.3021414279937744,
+      "learning_rate": 0.0001647058823529412,
+      "loss": 0.6396,
+      "step": 720
+    },
+    {
+      "epoch": 1.7892156862745097,
+      "grad_norm": 0.3210904002189636,
+      "learning_rate": 0.0001642156862745098,
+      "loss": 0.6672,
+      "step": 730
+    },
+    {
+      "epoch": 1.8137254901960784,
+      "grad_norm": 0.28844767808914185,
+      "learning_rate": 0.00016372549019607843,
+      "loss": 0.6476,
+      "step": 740
+    },
+    {
+      "epoch": 1.8382352941176472,
+      "grad_norm": 0.28307870030403137,
+      "learning_rate": 0.00016323529411764706,
+      "loss": 0.6587,
+      "step": 750
+    },
+    {
+      "epoch": 1.8627450980392157,
+      "grad_norm": 0.2879963219165802,
+      "learning_rate": 0.0001627450980392157,
+      "loss": 0.6213,
+      "step": 760
+    },
+    {
+      "epoch": 1.8872549019607843,
+      "grad_norm": 0.31524136662483215,
+      "learning_rate": 0.00016225490196078432,
+      "loss": 0.6479,
+      "step": 770
+    },
+    {
+      "epoch": 1.9117647058823528,
+      "grad_norm": 0.3042920231819153,
+      "learning_rate": 0.00016176470588235295,
+      "loss": 0.6445,
+      "step": 780
+    },
+    {
+      "epoch": 1.9362745098039216,
+      "grad_norm": 0.29315751791000366,
+      "learning_rate": 0.00016127450980392159,
+      "loss": 0.6675,
+      "step": 790
+    },
+    {
+      "epoch": 1.9607843137254903,
+      "grad_norm": 0.31360578536987305,
+      "learning_rate": 0.00016078431372549022,
+      "loss": 0.6447,
+      "step": 800
+    },
+    {
+      "epoch": 1.9852941176470589,
+      "grad_norm": 0.320044606924057,
+      "learning_rate": 0.00016029411764705885,
+      "loss": 0.6097,
+      "step": 810
+    },
+    {
+      "epoch": 2.0098039215686274,
+      "grad_norm": 0.29187172651290894,
+      "learning_rate": 0.00015980392156862746,
+      "loss": 0.6706,
+      "step": 820
+    },
+    {
+      "epoch": 2.034313725490196,
+      "grad_norm": 0.3306867778301239,
+      "learning_rate": 0.0001593137254901961,
+      "loss": 0.607,
+      "step": 830
+    },
+    {
+      "epoch": 2.0588235294117645,
+      "grad_norm": 0.32475340366363525,
+      "learning_rate": 0.0001588235294117647,
+      "loss": 0.5815,
+      "step": 840
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 0.32624176144599915,
+      "learning_rate": 0.00015833333333333332,
+      "loss": 0.5838,
+      "step": 850
+    },
+    {
+      "epoch": 2.107843137254902,
+      "grad_norm": 0.33117762207984924,
+      "learning_rate": 0.00015784313725490196,
+      "loss": 0.5956,
+      "step": 860
+    },
+    {
+      "epoch": 2.1323529411764706,
+      "grad_norm": 0.3294385075569153,
+      "learning_rate": 0.0001573529411764706,
+      "loss": 0.618,
+      "step": 870
+    },
+    {
+      "epoch": 2.156862745098039,
+      "grad_norm": 0.3245352506637573,
+      "learning_rate": 0.00015686274509803922,
+      "loss": 0.5636,
+      "step": 880
+    },
+    {
+      "epoch": 2.1813725490196076,
+      "grad_norm": 0.32185912132263184,
+      "learning_rate": 0.00015637254901960785,
+      "loss": 0.5796,
+      "step": 890
+    },
+    {
+      "epoch": 2.2058823529411766,
+      "grad_norm": 0.34521356225013733,
+      "learning_rate": 0.00015588235294117648,
+      "loss": 0.5985,
+      "step": 900
+    },
+    {
+      "epoch": 2.230392156862745,
+      "grad_norm": 0.33166056871414185,
+      "learning_rate": 0.00015539215686274512,
+      "loss": 0.5951,
+      "step": 910
+    },
+    {
+      "epoch": 2.2549019607843137,
+      "grad_norm": 0.34369799494743347,
+      "learning_rate": 0.00015490196078431375,
+      "loss": 0.6044,
+      "step": 920
+    },
+    {
+      "epoch": 2.2794117647058822,
+      "grad_norm": 0.3320542871952057,
+      "learning_rate": 0.00015441176470588238,
+      "loss": 0.5903,
+      "step": 930
+    },
+    {
+      "epoch": 2.303921568627451,
+      "grad_norm": 0.34061846137046814,
+      "learning_rate": 0.00015392156862745098,
+      "loss": 0.5792,
+      "step": 940
+    },
+    {
+      "epoch": 2.3284313725490198,
+      "grad_norm": 0.3528592586517334,
+      "learning_rate": 0.00015343137254901962,
+      "loss": 0.5867,
+      "step": 950
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 0.33795326948165894,
+      "learning_rate": 0.00015294117647058822,
+      "loss": 0.5529,
+      "step": 960
+    },
+    {
+      "epoch": 2.377450980392157,
+      "grad_norm": 0.33023008704185486,
+      "learning_rate": 0.00015245098039215685,
+      "loss": 0.6306,
+      "step": 970
+    },
+    {
+      "epoch": 2.4019607843137254,
+      "grad_norm": 0.3331562578678131,
+      "learning_rate": 0.00015196078431372549,
+      "loss": 0.605,
+      "step": 980
+    },
+    {
+      "epoch": 2.426470588235294,
+      "grad_norm": 0.32606229186058044,
+      "learning_rate": 0.00015147058823529412,
+      "loss": 0.5815,
+      "step": 990
+    },
+    {
+      "epoch": 2.450980392156863,
+      "grad_norm": 0.3443799614906311,
+      "learning_rate": 0.00015098039215686275,
+      "loss": 0.5813,
+      "step": 1000
+    },
+    {
+      "epoch": 2.4754901960784315,
+      "grad_norm": 0.3231131434440613,
+      "learning_rate": 0.00015049019607843138,
+      "loss": 0.5854,
+      "step": 1010
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.31584519147872925,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.5808,
+      "step": 1020
+    },
+    {
+      "epoch": 2.5245098039215685,
+      "grad_norm": 0.32220789790153503,
+      "learning_rate": 0.00014950980392156865,
+      "loss": 0.5972,
+      "step": 1030
+    },
+    {
+      "epoch": 2.549019607843137,
+      "grad_norm": 0.33140599727630615,
+      "learning_rate": 0.00014901960784313728,
+      "loss": 0.5811,
+      "step": 1040
+    },
+    {
+      "epoch": 2.5735294117647056,
+      "grad_norm": 0.32509833574295044,
+      "learning_rate": 0.00014852941176470588,
+      "loss": 0.5961,
+      "step": 1050
+    },
+    {
+      "epoch": 2.5980392156862746,
+      "grad_norm": 0.32181331515312195,
+      "learning_rate": 0.00014803921568627451,
+      "loss": 0.5778,
+      "step": 1060
+    },
+    {
+      "epoch": 2.622549019607843,
+      "grad_norm": 0.33203810453414917,
+      "learning_rate": 0.00014754901960784315,
+      "loss": 0.6196,
+      "step": 1070
+    },
+    {
+      "epoch": 2.6470588235294117,
+      "grad_norm": 0.3285435140132904,
+      "learning_rate": 0.00014705882352941178,
+      "loss": 0.6089,
+      "step": 1080
+    },
+    {
+      "epoch": 2.6715686274509802,
+      "grad_norm": 0.29427462816238403,
+      "learning_rate": 0.00014656862745098038,
+      "loss": 0.5616,
+      "step": 1090
+    },
+    {
+      "epoch": 2.696078431372549,
+      "grad_norm": 0.36723700165748596,
+      "learning_rate": 0.00014607843137254902,
+      "loss": 0.5664,
+      "step": 1100
+    },
+    {
+      "epoch": 2.7205882352941178,
+      "grad_norm": 0.32784491777420044,
+      "learning_rate": 0.00014558823529411765,
+      "loss": 0.5627,
+      "step": 1110
+    },
+    {
+      "epoch": 2.7450980392156863,
+      "grad_norm": 0.33356621861457825,
+      "learning_rate": 0.00014509803921568628,
+      "loss": 0.5789,
+      "step": 1120
+    },
+    {
+      "epoch": 2.769607843137255,
+      "grad_norm": 0.3453757166862488,
+      "learning_rate": 0.0001446078431372549,
+      "loss": 0.5839,
+      "step": 1130
+    },
+    {
+      "epoch": 2.7941176470588234,
+      "grad_norm": 0.3244710862636566,
+      "learning_rate": 0.00014411764705882354,
+      "loss": 0.6138,
+      "step": 1140
+    },
+    {
+      "epoch": 2.818627450980392,
+      "grad_norm": 0.36777082085609436,
+      "learning_rate": 0.00014362745098039218,
+      "loss": 0.5741,
+      "step": 1150
+    },
+    {
+      "epoch": 2.843137254901961,
+      "grad_norm": 0.3188980221748352,
+      "learning_rate": 0.00014313725490196078,
+      "loss": 0.5625,
+      "step": 1160
+    },
+    {
+      "epoch": 2.8676470588235294,
+      "grad_norm": 0.32817542552948,
+      "learning_rate": 0.0001426470588235294,
+      "loss": 0.5788,
+      "step": 1170
+    },
+    {
+      "epoch": 2.892156862745098,
+      "grad_norm": 0.3249094784259796,
+      "learning_rate": 0.00014215686274509804,
+      "loss": 0.6042,
+      "step": 1180
+    },
+    {
+      "epoch": 2.9166666666666665,
+      "grad_norm": 0.34067729115486145,
+      "learning_rate": 0.00014166666666666668,
+      "loss": 0.5706,
+      "step": 1190
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 0.3162751793861389,
+      "learning_rate": 0.0001411764705882353,
+      "loss": 0.5599,
+      "step": 1200
+    },
+    {
+      "epoch": 2.965686274509804,
+      "grad_norm": 0.3370027244091034,
+      "learning_rate": 0.00014068627450980394,
+      "loss": 0.5967,
+      "step": 1210
+    },
+    {
+      "epoch": 2.9901960784313726,
+      "grad_norm": 0.3651111423969269,
+      "learning_rate": 0.00014019607843137255,
+      "loss": 0.5765,
+      "step": 1220
+    },
+    {
+      "epoch": 3.014705882352941,
+      "grad_norm": 0.3368529975414276,
+      "learning_rate": 0.00013970588235294118,
+      "loss": 0.5559,
+      "step": 1230
+    },
+    {
+      "epoch": 3.0392156862745097,
+      "grad_norm": 0.366672158241272,
+      "learning_rate": 0.0001392156862745098,
+      "loss": 0.5062,
+      "step": 1240
+    },
+    {
+      "epoch": 3.063725490196078,
+      "grad_norm": 0.406984806060791,
+      "learning_rate": 0.00013872549019607844,
+      "loss": 0.499,
+      "step": 1250
+    },
+    {
+      "epoch": 3.088235294117647,
+      "grad_norm": 0.3747471570968628,
+      "learning_rate": 0.00013823529411764707,
+      "loss": 0.5064,
+      "step": 1260
+    },
+    {
+      "epoch": 3.1127450980392157,
+      "grad_norm": 0.3869905471801758,
+      "learning_rate": 0.00013774509803921568,
+      "loss": 0.5477,
+      "step": 1270
+    },
+    {
+      "epoch": 3.1372549019607843,
+      "grad_norm": 0.40752360224723816,
+      "learning_rate": 0.0001372549019607843,
+      "loss": 0.4915,
+      "step": 1280
+    },
+    {
+      "epoch": 3.161764705882353,
+      "grad_norm": 0.3453763723373413,
+      "learning_rate": 0.00013676470588235294,
+      "loss": 0.5037,
+      "step": 1290
+    },
+    {
+      "epoch": 3.186274509803922,
+      "grad_norm": 0.3654847741127014,
+      "learning_rate": 0.00013627450980392157,
+      "loss": 0.5138,
+      "step": 1300
+    },
+    {
+      "epoch": 3.2107843137254903,
+      "grad_norm": 0.3541817367076874,
+      "learning_rate": 0.0001357843137254902,
+      "loss": 0.5071,
+      "step": 1310
+    },
+    {
+      "epoch": 3.235294117647059,
+      "grad_norm": 0.3879326581954956,
+      "learning_rate": 0.00013529411764705884,
+      "loss": 0.5058,
+      "step": 1320
+    },
+    {
+      "epoch": 3.2598039215686274,
+      "grad_norm": 0.37032464146614075,
+      "learning_rate": 0.00013480392156862747,
+      "loss": 0.5105,
+      "step": 1330
+    },
+    {
+      "epoch": 3.284313725490196,
+      "grad_norm": 0.39336174726486206,
+      "learning_rate": 0.00013431372549019608,
+      "loss": 0.5222,
+      "step": 1340
+    },
+    {
+      "epoch": 3.3088235294117645,
+      "grad_norm": 0.36094290018081665,
+      "learning_rate": 0.0001338235294117647,
+      "loss": 0.5298,
+      "step": 1350
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.3758329153060913,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.4963,
+      "step": 1360
+    },
+    {
+      "epoch": 3.357843137254902,
+      "grad_norm": 0.39011090993881226,
+      "learning_rate": 0.00013284313725490197,
+      "loss": 0.517,
+      "step": 1370
+    },
+    {
+      "epoch": 3.3823529411764706,
+      "grad_norm": 0.37309834361076355,
+      "learning_rate": 0.0001323529411764706,
+      "loss": 0.5451,
+      "step": 1380
+    },
+    {
+      "epoch": 3.406862745098039,
+      "grad_norm": 0.3810550272464752,
+      "learning_rate": 0.0001318627450980392,
+      "loss": 0.5285,
+      "step": 1390
+    },
+    {
+      "epoch": 3.431372549019608,
+      "grad_norm": 0.3513835668563843,
+      "learning_rate": 0.00013137254901960784,
+      "loss": 0.521,
+      "step": 1400
+    },
+    {
+      "epoch": 3.4558823529411766,
+      "grad_norm": 0.3686577081680298,
+      "learning_rate": 0.00013088235294117647,
+      "loss": 0.5392,
+      "step": 1410
+    },
+    {
+      "epoch": 3.480392156862745,
+      "grad_norm": 0.35927894711494446,
+      "learning_rate": 0.0001303921568627451,
+      "loss": 0.5271,
+      "step": 1420
+    },
+    {
+      "epoch": 3.5049019607843137,
+      "grad_norm": 0.3643144369125366,
+      "learning_rate": 0.00012990196078431374,
+      "loss": 0.5284,
+      "step": 1430
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 0.40783992409706116,
+      "learning_rate": 0.00012941176470588237,
+      "loss": 0.5085,
+      "step": 1440
+    },
+    {
+      "epoch": 3.553921568627451,
+      "grad_norm": 0.370568186044693,
+      "learning_rate": 0.000128921568627451,
+      "loss": 0.4918,
+      "step": 1450
+    },
+    {
+      "epoch": 3.5784313725490198,
+      "grad_norm": 0.38452836871147156,
+      "learning_rate": 0.00012843137254901963,
+      "loss": 0.5084,
+      "step": 1460
+    },
+    {
+      "epoch": 3.6029411764705883,
+      "grad_norm": 0.38461601734161377,
+      "learning_rate": 0.00012794117647058824,
+      "loss": 0.528,
+      "step": 1470
+    },
+    {
+      "epoch": 3.627450980392157,
+      "grad_norm": 0.378743052482605,
+      "learning_rate": 0.00012745098039215687,
+      "loss": 0.5476,
+      "step": 1480
+    },
+    {
+      "epoch": 3.6519607843137254,
+      "grad_norm": 0.3925258219242096,
+      "learning_rate": 0.0001269607843137255,
+      "loss": 0.5262,
+      "step": 1490
+    },
+    {
+      "epoch": 3.6764705882352944,
+      "grad_norm": 0.3843972384929657,
+      "learning_rate": 0.0001264705882352941,
+      "loss": 0.5142,
+      "step": 1500
+    },
+    {
+      "epoch": 3.700980392156863,
+      "grad_norm": 0.3720986247062683,
+      "learning_rate": 0.00012598039215686274,
+      "loss": 0.51,
+      "step": 1510
+    },
+    {
+      "epoch": 3.7254901960784315,
+      "grad_norm": 0.38532596826553345,
+      "learning_rate": 0.00012549019607843137,
+      "loss": 0.5019,
+      "step": 1520
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.39480453729629517,
+      "learning_rate": 0.000125,
+      "loss": 0.528,
+      "step": 1530
+    },
+    {
+      "epoch": 3.7745098039215685,
+      "grad_norm": 0.40592941641807556,
+      "learning_rate": 0.00012450980392156863,
+      "loss": 0.5345,
+      "step": 1540
+    },
+    {
+      "epoch": 3.799019607843137,
+      "grad_norm": 0.9979096055030823,
+      "learning_rate": 0.00012401960784313727,
+      "loss": 0.505,
+      "step": 1550
+    },
+    {
+      "epoch": 3.8235294117647056,
+      "grad_norm": 0.38043680787086487,
+      "learning_rate": 0.0001235294117647059,
+      "loss": 0.5057,
+      "step": 1560
+    },
+    {
+      "epoch": 3.8480392156862746,
+      "grad_norm": 0.37059956789016724,
+      "learning_rate": 0.00012303921568627453,
+      "loss": 0.5252,
+      "step": 1570
+    },
+    {
+      "epoch": 3.872549019607843,
+      "grad_norm": 0.3633560240268707,
+      "learning_rate": 0.00012254901960784316,
+      "loss": 0.4987,
+      "step": 1580
+    },
+    {
+      "epoch": 3.8970588235294117,
+      "grad_norm": 0.4094372093677521,
+      "learning_rate": 0.00012205882352941178,
+      "loss": 0.5553,
+      "step": 1590
+    },
+    {
+      "epoch": 3.9215686274509802,
+      "grad_norm": 0.3960098326206207,
+      "learning_rate": 0.00012156862745098039,
+      "loss": 0.5435,
+      "step": 1600
+    },
+    {
+      "epoch": 3.946078431372549,
+      "grad_norm": 0.3884652256965637,
+      "learning_rate": 0.00012107843137254902,
+      "loss": 0.5114,
+      "step": 1610
+    },
+    {
+      "epoch": 3.9705882352941178,
+      "grad_norm": 0.366059809923172,
+      "learning_rate": 0.00012058823529411765,
+      "loss": 0.5084,
+      "step": 1620
+    },
+    {
+      "epoch": 3.9950980392156863,
+      "grad_norm": 0.3853819966316223,
+      "learning_rate": 0.00012009803921568628,
+      "loss": 0.4987,
+      "step": 1630
+    },
+    {
+      "epoch": 4.019607843137255,
+      "grad_norm": 0.3792478144168854,
+      "learning_rate": 0.0001196078431372549,
+      "loss": 0.4352,
+      "step": 1640
+    },
+    {
+      "epoch": 4.044117647058823,
+      "grad_norm": 0.3791177570819855,
+      "learning_rate": 0.00011911764705882353,
+      "loss": 0.4378,
+      "step": 1650
+    },
+    {
+      "epoch": 4.068627450980392,
+      "grad_norm": 0.4122741222381592,
+      "learning_rate": 0.00011862745098039216,
+      "loss": 0.4167,
+      "step": 1660
+    },
+    {
+      "epoch": 4.0931372549019605,
+      "grad_norm": 0.41166090965270996,
+      "learning_rate": 0.0001181372549019608,
+      "loss": 0.4355,
+      "step": 1670
+    },
+    {
+      "epoch": 4.117647058823529,
+      "grad_norm": 0.37315306067466736,
+      "learning_rate": 0.00011764705882352942,
+      "loss": 0.4347,
+      "step": 1680
+    },
+    {
+      "epoch": 4.142156862745098,
+      "grad_norm": 0.4119997024536133,
+      "learning_rate": 0.00011715686274509805,
+      "loss": 0.4396,
+      "step": 1690
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 0.41811785101890564,
+      "learning_rate": 0.00011666666666666668,
+      "loss": 0.4374,
+      "step": 1700
+    },
+    {
+      "epoch": 4.1911764705882355,
+      "grad_norm": 0.4639507532119751,
+      "learning_rate": 0.00011617647058823531,
+      "loss": 0.4688,
+      "step": 1710
+    },
+    {
+      "epoch": 4.215686274509804,
+      "grad_norm": 0.40909409523010254,
+      "learning_rate": 0.00011568627450980394,
+      "loss": 0.4428,
+      "step": 1720
+    },
+    {
+      "epoch": 4.240196078431373,
+      "grad_norm": 0.4439013600349426,
+      "learning_rate": 0.00011519607843137255,
+      "loss": 0.4478,
+      "step": 1730
+    },
+    {
+      "epoch": 4.264705882352941,
+      "grad_norm": 0.4124948978424072,
+      "learning_rate": 0.00011470588235294118,
+      "loss": 0.4317,
+      "step": 1740
+    },
+    {
+      "epoch": 4.28921568627451,
+      "grad_norm": 0.4522900879383087,
+      "learning_rate": 0.0001142156862745098,
+      "loss": 0.4586,
+      "step": 1750
+    },
+    {
+      "epoch": 4.313725490196078,
+      "grad_norm": 0.41997721791267395,
+      "learning_rate": 0.00011372549019607843,
+      "loss": 0.4598,
+      "step": 1760
+    },
+    {
+      "epoch": 4.338235294117647,
+      "grad_norm": 0.3984828591346741,
+      "learning_rate": 0.00011323529411764706,
+      "loss": 0.4482,
+      "step": 1770
+    },
+    {
+      "epoch": 4.362745098039215,
+      "grad_norm": 0.41868138313293457,
+      "learning_rate": 0.0001127450980392157,
+      "loss": 0.4431,
+      "step": 1780
+    },
+    {
+      "epoch": 4.387254901960785,
+      "grad_norm": 0.447293221950531,
+      "learning_rate": 0.00011225490196078433,
+      "loss": 0.4434,
+      "step": 1790
+    },
+    {
+      "epoch": 4.411764705882353,
+      "grad_norm": 0.3910238742828369,
+      "learning_rate": 0.00011176470588235294,
+      "loss": 0.4463,
+      "step": 1800
+    },
+    {
+      "epoch": 4.436274509803922,
+      "grad_norm": 0.40496933460235596,
+      "learning_rate": 0.00011127450980392158,
+      "loss": 0.4793,
+      "step": 1810
+    },
+    {
+      "epoch": 4.46078431372549,
+      "grad_norm": 0.4138587415218353,
+      "learning_rate": 0.00011078431372549021,
+      "loss": 0.4417,
+      "step": 1820
+    },
+    {
+      "epoch": 4.485294117647059,
+      "grad_norm": 0.4713083803653717,
+      "learning_rate": 0.00011029411764705884,
+      "loss": 0.454,
+      "step": 1830
+    },
+    {
+      "epoch": 4.509803921568627,
+      "grad_norm": 0.45029592514038086,
+      "learning_rate": 0.00010980392156862746,
+      "loss": 0.4504,
+      "step": 1840
+    },
+    {
+      "epoch": 4.534313725490196,
+      "grad_norm": 0.42069247364997864,
+      "learning_rate": 0.00010931372549019608,
+      "loss": 0.4794,
+      "step": 1850
+    },
+    {
+      "epoch": 4.5588235294117645,
+      "grad_norm": 0.3917437195777893,
+      "learning_rate": 0.0001088235294117647,
+      "loss": 0.4502,
+      "step": 1860
+    },
+    {
+      "epoch": 4.583333333333333,
+      "grad_norm": 0.417987585067749,
+      "learning_rate": 0.00010833333333333333,
+      "loss": 0.4579,
+      "step": 1870
+    },
+    {
+      "epoch": 4.607843137254902,
+      "grad_norm": 0.4511590301990509,
+      "learning_rate": 0.00010784313725490196,
+      "loss": 0.4686,
+      "step": 1880
+    },
+    {
+      "epoch": 4.632352941176471,
+      "grad_norm": 0.4555961787700653,
+      "learning_rate": 0.00010735294117647059,
+      "loss": 0.4332,
+      "step": 1890
+    },
+    {
+      "epoch": 4.6568627450980395,
+      "grad_norm": 0.4159266948699951,
+      "learning_rate": 0.00010686274509803922,
+      "loss": 0.4721,
+      "step": 1900
+    },
+    {
+      "epoch": 4.681372549019608,
+      "grad_norm": 0.4237167239189148,
+      "learning_rate": 0.00010637254901960784,
+      "loss": 0.4542,
+      "step": 1910
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 0.42502954602241516,
+      "learning_rate": 0.00010588235294117647,
+      "loss": 0.4568,
+      "step": 1920
+    },
+    {
+      "epoch": 4.730392156862745,
+      "grad_norm": 0.4060966968536377,
+      "learning_rate": 0.00010539215686274511,
+      "loss": 0.4588,
+      "step": 1930
+    },
+    {
+      "epoch": 4.754901960784314,
+      "grad_norm": 0.444376140832901,
+      "learning_rate": 0.00010490196078431374,
+      "loss": 0.4617,
+      "step": 1940
+    },
+    {
+      "epoch": 4.779411764705882,
+      "grad_norm": 0.41235941648483276,
+      "learning_rate": 0.00010441176470588237,
+      "loss": 0.4655,
+      "step": 1950
+    },
+    {
+      "epoch": 4.803921568627451,
+      "grad_norm": 0.42703354358673096,
+      "learning_rate": 0.00010392156862745099,
+      "loss": 0.4643,
+      "step": 1960
+    },
+    {
+      "epoch": 4.828431372549019,
+      "grad_norm": 0.4282451272010803,
+      "learning_rate": 0.00010343137254901962,
+      "loss": 0.4435,
+      "step": 1970
+    },
+    {
+      "epoch": 4.852941176470588,
+      "grad_norm": 0.40952056646347046,
+      "learning_rate": 0.00010294117647058823,
+      "loss": 0.4571,
+      "step": 1980
+    },
+    {
+      "epoch": 4.877450980392156,
+      "grad_norm": 0.41904792189598083,
+      "learning_rate": 0.00010245098039215686,
+      "loss": 0.4361,
+      "step": 1990
+    },
+    {
+      "epoch": 4.901960784313726,
+      "grad_norm": 0.4027288258075714,
+      "learning_rate": 0.00010196078431372549,
+      "loss": 0.4507,
+      "step": 2000
+    },
+    {
+      "epoch": 4.926470588235294,
+      "grad_norm": 0.4230017364025116,
+      "learning_rate": 0.00010147058823529412,
+      "loss": 0.4645,
+      "step": 2010
+    },
+    {
+      "epoch": 4.950980392156863,
+      "grad_norm": 0.44512614607810974,
+      "learning_rate": 0.00010098039215686274,
+      "loss": 0.4585,
+      "step": 2020
+    },
+    {
+      "epoch": 4.9754901960784315,
+      "grad_norm": 0.4242990016937256,
+      "learning_rate": 0.00010049019607843137,
+      "loss": 0.4785,
+      "step": 2030
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.4472719132900238,
+      "learning_rate": 0.0001,
+      "loss": 0.4635,
+      "step": 2040
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 4080,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.231691259706409e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2040/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:187af0b38f5c7132235d8bd7d17df624fbe88e4ef222af016e1952a0f9f251e5
+size 5560