Upload folder using huggingface_hub

.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,208 @@
+---
+base_model: unsloth/Qwen2.5-Coder-3b-Instruct-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen2.5-Coder-3b-Instruct-bnb-4bit
+- lora
+- transformers
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen2.5-Coder-3b-Instruct-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8089723a019d3d6f8dcf82ef2e3c0c72ef40b6c36a53cdc5e13f1adabbe6784a
+size 239536272

added_tokens.json

@@ -0,0 +1,25 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|PAD_TOKEN|>": 151665,
+  "<|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
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7af210e754bdb6d694d896312867d791a238f4964143bfed07a98bc0f5083007
+size 479370187

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcbea41e90cc92b60dad673f2ff016d8f09c52f90fd6b0b6d0e682698edfa779
+size 14581

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3911e34dd78c40167877be69fac0c2ef313e2e9fd85ef6cb6d3b309c03037999
+size 1465

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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|PAD_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fab42efe8d17406525a9154b728cf9e957629a8ed7ce997770efdd71128c6a1a
+size 11422086

tokenizer_config.json

@@ -0,0 +1,216 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1189 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 8256,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04844961240310078,
+      "grad_norm": 0.41548049449920654,
+      "learning_rate": 4.999565439780451e-05,
+      "loss": 0.9259,
+      "step": 50
+    },
+    {
+      "epoch": 0.09689922480620156,
+      "grad_norm": 0.4070381224155426,
+      "learning_rate": 4.9982262622162004e-05,
+      "loss": 0.8252,
+      "step": 100
+    },
+    {
+      "epoch": 0.14534883720930233,
+      "grad_norm": 0.26511862874031067,
+      "learning_rate": 4.9959827710691796e-05,
+      "loss": 0.789,
+      "step": 150
+    },
+    {
+      "epoch": 0.1937984496124031,
+      "grad_norm": 0.379682719707489,
+      "learning_rate": 4.992835778443379e-05,
+      "loss": 0.8257,
+      "step": 200
+    },
+    {
+      "epoch": 0.24224806201550386,
+      "grad_norm": 0.34141114354133606,
+      "learning_rate": 4.988786423494294e-05,
+      "loss": 0.8357,
+      "step": 250
+    },
+    {
+      "epoch": 0.29069767441860467,
+      "grad_norm": 0.33835941553115845,
+      "learning_rate": 4.983836172016573e-05,
+      "loss": 0.8025,
+      "step": 300
+    },
+    {
+      "epoch": 0.3391472868217054,
+      "grad_norm": 0.28619295358657837,
+      "learning_rate": 4.97798681591342e-05,
+      "loss": 0.7223,
+      "step": 350
+    },
+    {
+      "epoch": 0.3875968992248062,
+      "grad_norm": 1.7040114402770996,
+      "learning_rate": 4.971240472547967e-05,
+      "loss": 0.7843,
+      "step": 400
+    },
+    {
+      "epoch": 0.436046511627907,
+      "grad_norm": 0.4446117877960205,
+      "learning_rate": 4.963599583976813e-05,
+      "loss": 0.8503,
+      "step": 450
+    },
+    {
+      "epoch": 0.4844961240310077,
+      "grad_norm": 0.285826712846756,
+      "learning_rate": 4.9550669160660576e-05,
+      "loss": 0.8192,
+      "step": 500
+    },
+    {
+      "epoch": 0.5329457364341085,
+      "grad_norm": 2.5809340476989746,
+      "learning_rate": 4.945645557490094e-05,
+      "loss": 0.7493,
+      "step": 550
+    },
+    {
+      "epoch": 0.5813953488372093,
+      "grad_norm": 0.31858932971954346,
+      "learning_rate": 4.935338918613571e-05,
+      "loss": 0.847,
+      "step": 600
+    },
+    {
+      "epoch": 0.6298449612403101,
+      "grad_norm": 0.3342924416065216,
+      "learning_rate": 4.924150730256899e-05,
+      "loss": 0.7255,
+      "step": 650
+    },
+    {
+      "epoch": 0.6782945736434108,
+      "grad_norm": 0.2791895568370819,
+      "learning_rate": 4.91208504234576e-05,
+      "loss": 0.8075,
+      "step": 700
+    },
+    {
+      "epoch": 0.7267441860465116,
+      "grad_norm": 0.4308435618877411,
+      "learning_rate": 4.899146222445105e-05,
+      "loss": 0.839,
+      "step": 750
+    },
+    {
+      "epoch": 0.7751937984496124,
+      "grad_norm": 0.47363415360450745,
+      "learning_rate": 4.8853389541781726e-05,
+      "loss": 0.7479,
+      "step": 800
+    },
+    {
+      "epoch": 0.8236434108527132,
+      "grad_norm": 0.39904293417930603,
+      "learning_rate": 4.870668235531106e-05,
+      "loss": 0.7821,
+      "step": 850
+    },
+    {
+      "epoch": 0.872093023255814,
+      "grad_norm": 0.3194170594215393,
+      "learning_rate": 4.8551393770437626e-05,
+      "loss": 0.8012,
+      "step": 900
+    },
+    {
+      "epoch": 0.9205426356589147,
+      "grad_norm": 0.8215324282646179,
+      "learning_rate": 4.838757999887399e-05,
+      "loss": 0.6319,
+      "step": 950
+    },
+    {
+      "epoch": 0.9689922480620154,
+      "grad_norm": 0.46082744002342224,
+      "learning_rate": 4.821530033829902e-05,
+      "loss": 0.494,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0174418604651163,
+      "grad_norm": 0.25258105993270874,
+      "learning_rate": 4.8034617150893216e-05,
+      "loss": 0.7785,
+      "step": 1050
+    },
+    {
+      "epoch": 1.0658914728682172,
+      "grad_norm": 0.44710302352905273,
+      "learning_rate": 4.78455958407647e-05,
+      "loss": 0.573,
+      "step": 1100
+    },
+    {
+      "epoch": 1.1143410852713178,
+      "grad_norm": 0.25971588492393494,
+      "learning_rate": 4.764830483027408e-05,
+      "loss": 0.6463,
+      "step": 1150
+    },
+    {
+      "epoch": 1.1627906976744187,
+      "grad_norm": 0.5416250228881836,
+      "learning_rate": 4.744281553526676e-05,
+      "loss": 0.5477,
+      "step": 1200
+    },
+    {
+      "epoch": 1.2112403100775193,
+      "grad_norm": 0.6827994585037231,
+      "learning_rate": 4.7229202339221676e-05,
+      "loss": 0.6475,
+      "step": 1250
+    },
+    {
+      "epoch": 1.2596899224806202,
+      "grad_norm": 0.7923223376274109,
+      "learning_rate": 4.7007542566325844e-05,
+      "loss": 0.6066,
+      "step": 1300
+    },
+    {
+      "epoch": 1.308139534883721,
+      "grad_norm": 0.30041930079460144,
+      "learning_rate": 4.6777916453484305e-05,
+      "loss": 0.7032,
+      "step": 1350
+    },
+    {
+      "epoch": 1.3565891472868217,
+      "grad_norm": 0.30808496475219727,
+      "learning_rate": 4.654040712127581e-05,
+      "loss": 0.7161,
+      "step": 1400
+    },
+    {
+      "epoch": 1.4050387596899225,
+      "grad_norm": 0.2858184278011322,
+      "learning_rate": 4.629510054386468e-05,
+      "loss": 0.6813,
+      "step": 1450
+    },
+    {
+      "epoch": 1.4534883720930232,
+      "grad_norm": 0.4461047053337097,
+      "learning_rate": 4.604208551787964e-05,
+      "loss": 0.6757,
+      "step": 1500
+    },
+    {
+      "epoch": 1.501937984496124,
+      "grad_norm": 0.294251024723053,
+      "learning_rate": 4.578145363027104e-05,
+      "loss": 0.559,
+      "step": 1550
+    },
+    {
+      "epoch": 1.550387596899225,
+      "grad_norm": 0.4968578517436981,
+      "learning_rate": 4.5513299225158014e-05,
+      "loss": 0.7046,
+      "step": 1600
+    },
+    {
+      "epoch": 1.5988372093023255,
+      "grad_norm": 0.2557980418205261,
+      "learning_rate": 4.523771936967754e-05,
+      "loss": 0.6828,
+      "step": 1650
+    },
+    {
+      "epoch": 1.6472868217054264,
+      "grad_norm": 0.30303144454956055,
+      "learning_rate": 4.4954813818847886e-05,
+      "loss": 0.7159,
+      "step": 1700
+    },
+    {
+      "epoch": 1.695736434108527,
+      "grad_norm": 0.1948225349187851,
+      "learning_rate": 4.466468497945909e-05,
+      "loss": 0.7042,
+      "step": 1750
+    },
+    {
+      "epoch": 1.744186046511628,
+      "grad_norm": 0.39648470282554626,
+      "learning_rate": 4.436743787300346e-05,
+      "loss": 0.7765,
+      "step": 1800
+    },
+    {
+      "epoch": 1.7926356589147288,
+      "grad_norm": 0.38730746507644653,
+      "learning_rate": 4.406318009765971e-05,
+      "loss": 0.7311,
+      "step": 1850
+    },
+    {
+      "epoch": 1.8410852713178296,
+      "grad_norm": 0.226152241230011,
+      "learning_rate": 4.3752021789344286e-05,
+      "loss": 0.5145,
+      "step": 1900
+    },
+    {
+      "epoch": 1.8895348837209303,
+      "grad_norm": 0.6462261080741882,
+      "learning_rate": 4.343407558184415e-05,
+      "loss": 0.3022,
+      "step": 1950
+    },
+    {
+      "epoch": 1.937984496124031,
+      "grad_norm": 0.5680636763572693,
+      "learning_rate": 4.310945656604535e-05,
+      "loss": 0.6364,
+      "step": 2000
+    },
+    {
+      "epoch": 1.9864341085271318,
+      "grad_norm": 0.342068076133728,
+      "learning_rate": 4.277828224827213e-05,
+      "loss": 0.5432,
+      "step": 2050
+    },
+    {
+      "epoch": 2.0348837209302326,
+      "grad_norm": 0.3184409737586975,
+      "learning_rate": 4.244067250775174e-05,
+      "loss": 0.5958,
+      "step": 2100
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 0.4073927402496338,
+      "learning_rate": 4.209674955322029e-05,
+      "loss": 0.639,
+      "step": 2150
+    },
+    {
+      "epoch": 2.1317829457364343,
+      "grad_norm": 1.1842104196548462,
+      "learning_rate": 4.174663787868537e-05,
+      "loss": 0.6331,
+      "step": 2200
+    },
+    {
+      "epoch": 2.1802325581395348,
+      "grad_norm": 0.8454262614250183,
+      "learning_rate": 4.139046421836137e-05,
+      "loss": 0.6085,
+      "step": 2250
+    },
+    {
+      "epoch": 2.2286821705426356,
+      "grad_norm": 0.31670165061950684,
+      "learning_rate": 4.1028357500794024e-05,
+      "loss": 0.4542,
+      "step": 2300
+    },
+    {
+      "epoch": 2.2771317829457365,
+      "grad_norm": 0.3827883005142212,
+      "learning_rate": 4.06604488021905e-05,
+      "loss": 0.5486,
+      "step": 2350
+    },
+    {
+      "epoch": 2.3255813953488373,
+      "grad_norm": 0.4175989031791687,
+      "learning_rate": 4.0286871298972154e-05,
+      "loss": 0.5972,
+      "step": 2400
+    },
+    {
+      "epoch": 2.374031007751938,
+      "grad_norm": 0.3741699457168579,
+      "learning_rate": 3.9907760219567055e-05,
+      "loss": 0.5973,
+      "step": 2450
+    },
+    {
+      "epoch": 2.4224806201550386,
+      "grad_norm": 0.5313114523887634,
+      "learning_rate": 3.9523252795459676e-05,
+      "loss": 0.6082,
+      "step": 2500
+    },
+    {
+      "epoch": 2.4709302325581395,
+      "grad_norm": 0.3255683183670044,
+      "learning_rate": 3.91334882115155e-05,
+      "loss": 0.6618,
+      "step": 2550
+    },
+    {
+      "epoch": 2.5193798449612403,
+      "grad_norm": 0.6780579686164856,
+      "learning_rate": 3.873860755559862e-05,
+      "loss": 0.6439,
+      "step": 2600
+    },
+    {
+      "epoch": 2.567829457364341,
+      "grad_norm": 0.7427515387535095,
+      "learning_rate": 3.83387537675004e-05,
+      "loss": 0.4145,
+      "step": 2650
+    },
+    {
+      "epoch": 2.616279069767442,
+      "grad_norm": 0.3860374689102173,
+      "learning_rate": 3.793407158719784e-05,
+      "loss": 0.6016,
+      "step": 2700
+    },
+    {
+      "epoch": 2.6647286821705425,
+      "grad_norm": 0.5163136124610901,
+      "learning_rate": 3.752470750246023e-05,
+      "loss": 0.5656,
+      "step": 2750
+    },
+    {
+      "epoch": 2.7131782945736433,
+      "grad_norm": 0.31362855434417725,
+      "learning_rate": 3.711080969582321e-05,
+      "loss": 0.6171,
+      "step": 2800
+    },
+    {
+      "epoch": 2.761627906976744,
+      "grad_norm": 0.5183291435241699,
+      "learning_rate": 3.66925279909493e-05,
+      "loss": 0.5906,
+      "step": 2850
+    },
+    {
+      "epoch": 2.810077519379845,
+      "grad_norm": 0.6666070818901062,
+      "learning_rate": 3.6270013798394403e-05,
+      "loss": 0.489,
+      "step": 2900
+    },
+    {
+      "epoch": 2.858527131782946,
+      "grad_norm": 0.32670509815216064,
+      "learning_rate": 3.5843420060799874e-05,
+      "loss": 0.6118,
+      "step": 2950
+    },
+    {
+      "epoch": 2.9069767441860463,
+      "grad_norm": 0.1764584183692932,
+      "learning_rate": 3.541290119753e-05,
+      "loss": 0.1986,
+      "step": 3000
+    },
+    {
+      "epoch": 2.955426356589147,
+      "grad_norm": 0.2792399227619171,
+      "learning_rate": 3.49786130487749e-05,
+      "loss": 0.5696,
+      "step": 3050
+    },
+    {
+      "epoch": 3.003875968992248,
+      "grad_norm": 0.3555202782154083,
+      "learning_rate": 3.454071281913918e-05,
+      "loss": 0.48,
+      "step": 3100
+    },
+    {
+      "epoch": 3.052325581395349,
+      "grad_norm": 0.5549014806747437,
+      "learning_rate": 3.4099359020736636e-05,
+      "loss": 0.5539,
+      "step": 3150
+    },
+    {
+      "epoch": 3.10077519379845,
+      "grad_norm": 0.4574868083000183,
+      "learning_rate": 3.365471141581167e-05,
+      "loss": 0.5123,
+      "step": 3200
+    },
+    {
+      "epoch": 3.14922480620155,
+      "grad_norm": 0.268303781747818,
+      "learning_rate": 3.320693095890823e-05,
+      "loss": 0.521,
+      "step": 3250
+    },
+    {
+      "epoch": 3.197674418604651,
+      "grad_norm": 0.5150983929634094,
+      "learning_rate": 3.275617973860707e-05,
+      "loss": 0.5431,
+      "step": 3300
+    },
+    {
+      "epoch": 3.246124031007752,
+      "grad_norm": 0.39754441380500793,
+      "learning_rate": 3.230262091885261e-05,
+      "loss": 0.2304,
+      "step": 3350
+    },
+    {
+      "epoch": 3.294573643410853,
+      "grad_norm": 0.41833576560020447,
+      "learning_rate": 3.184641867989045e-05,
+      "loss": 0.4382,
+      "step": 3400
+    },
+    {
+      "epoch": 3.3430232558139537,
+      "grad_norm": 0.45826929807662964,
+      "learning_rate": 3.138773815883702e-05,
+      "loss": 0.4938,
+      "step": 3450
+    },
+    {
+      "epoch": 3.391472868217054,
+      "grad_norm": 0.2432149201631546,
+      "learning_rate": 3.092674538990294e-05,
+      "loss": 0.4546,
+      "step": 3500
+    },
+    {
+      "epoch": 3.439922480620155,
+      "grad_norm": 0.3492552638053894,
+      "learning_rate": 3.04636072442915e-05,
+      "loss": 0.5489,
+      "step": 3550
+    },
+    {
+      "epoch": 3.488372093023256,
+      "grad_norm": 0.4332628548145294,
+      "learning_rate": 2.9998491369794306e-05,
+      "loss": 0.5029,
+      "step": 3600
+    },
+    {
+      "epoch": 3.5368217054263567,
+      "grad_norm": 0.4654231369495392,
+      "learning_rate": 2.9531566130105735e-05,
+      "loss": 0.5832,
+      "step": 3650
+    },
+    {
+      "epoch": 3.5852713178294575,
+      "grad_norm": 0.49778714776039124,
+      "learning_rate": 2.906300054387823e-05,
+      "loss": 0.4908,
+      "step": 3700
+    },
+    {
+      "epoch": 3.633720930232558,
+      "grad_norm": 0.38342729210853577,
+      "learning_rate": 2.8592964223540608e-05,
+      "loss": 0.5958,
+      "step": 3750
+    },
+    {
+      "epoch": 3.682170542635659,
+      "grad_norm": 0.2664441168308258,
+      "learning_rate": 2.812162731390133e-05,
+      "loss": 0.4951,
+      "step": 3800
+    },
+    {
+      "epoch": 3.7306201550387597,
+      "grad_norm": 0.3066735565662384,
+      "learning_rate": 2.7649160430559105e-05,
+      "loss": 0.5901,
+      "step": 3850
+    },
+    {
+      "epoch": 3.7790697674418605,
+      "grad_norm": 0.365209698677063,
+      "learning_rate": 2.7175734598143088e-05,
+      "loss": 0.573,
+      "step": 3900
+    },
+    {
+      "epoch": 3.8275193798449614,
+      "grad_norm": 0.29753512144088745,
+      "learning_rate": 2.6701521188404965e-05,
+      "loss": 0.5557,
+      "step": 3950
+    },
+    {
+      "epoch": 3.875968992248062,
+      "grad_norm": 0.4851069152355194,
+      "learning_rate": 2.6226691858185454e-05,
+      "loss": 0.3863,
+      "step": 4000
+    },
+    {
+      "epoch": 3.9244186046511627,
+      "grad_norm": 0.39727818965911865,
+      "learning_rate": 2.5751418487277544e-05,
+      "loss": 0.5019,
+      "step": 4050
+    },
+    {
+      "epoch": 3.9728682170542635,
+      "grad_norm": 0.5351327061653137,
+      "learning_rate": 2.5275873116209104e-05,
+      "loss": 0.4453,
+      "step": 4100
+    },
+    {
+      "epoch": 4.021317829457364,
+      "grad_norm": 0.3918212354183197,
+      "learning_rate": 2.48002278839672e-05,
+      "loss": 0.528,
+      "step": 4150
+    },
+    {
+      "epoch": 4.069767441860465,
+      "grad_norm": 0.3745068609714508,
+      "learning_rate": 2.432465496568689e-05,
+      "loss": 0.5476,
+      "step": 4200
+    },
+    {
+      "epoch": 4.118217054263566,
+      "grad_norm": 0.9149877429008484,
+      "learning_rate": 2.3849326510326875e-05,
+      "loss": 0.4632,
+      "step": 4250
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 0.6120011210441589,
+      "learning_rate": 2.3374414578354577e-05,
+      "loss": 0.5309,
+      "step": 4300
+    },
+    {
+      "epoch": 4.215116279069767,
+      "grad_norm": 0.3835127651691437,
+      "learning_rate": 2.290009107946337e-05,
+      "loss": 0.4484,
+      "step": 4350
+    },
+    {
+      "epoch": 4.263565891472869,
+      "grad_norm": 0.2763288617134094,
+      "learning_rate": 2.2426527710344296e-05,
+      "loss": 0.2135,
+      "step": 4400
+    },
+    {
+      "epoch": 4.312015503875969,
+      "grad_norm": 0.36940285563468933,
+      "learning_rate": 2.1953895892534886e-05,
+      "loss": 0.3706,
+      "step": 4450
+    },
+    {
+      "epoch": 4.3604651162790695,
+      "grad_norm": 0.3598892092704773,
+      "learning_rate": 2.148236671036765e-05,
+      "loss": 0.5161,
+      "step": 4500
+    },
+    {
+      "epoch": 4.408914728682171,
+      "grad_norm": 0.41965949535369873,
+      "learning_rate": 2.1012110849040533e-05,
+      "loss": 0.5151,
+      "step": 4550
+    },
+    {
+      "epoch": 4.457364341085271,
+      "grad_norm": 0.6105883717536926,
+      "learning_rate": 2.054329853283194e-05,
+      "loss": 0.4699,
+      "step": 4600
+    },
+    {
+      "epoch": 4.5058139534883725,
+      "grad_norm": 1.0464669466018677,
+      "learning_rate": 2.0076099463482557e-05,
+      "loss": 0.5253,
+      "step": 4650
+    },
+    {
+      "epoch": 4.554263565891473,
+      "grad_norm": 0.7042683959007263,
+      "learning_rate": 1.9610682758766316e-05,
+      "loss": 0.5089,
+      "step": 4700
+    },
+    {
+      "epoch": 4.602713178294573,
+      "grad_norm": 0.4324445128440857,
+      "learning_rate": 1.914721689127281e-05,
+      "loss": 0.5323,
+      "step": 4750
+    },
+    {
+      "epoch": 4.651162790697675,
+      "grad_norm": 0.337740957736969,
+      "learning_rate": 1.868586962742312e-05,
+      "loss": 0.4622,
+      "step": 4800
+    },
+    {
+      "epoch": 4.699612403100775,
+      "grad_norm": 0.30157017707824707,
+      "learning_rate": 1.8226807966741426e-05,
+      "loss": 0.2995,
+      "step": 4850
+    },
+    {
+      "epoch": 4.748062015503876,
+      "grad_norm": 0.28458529710769653,
+      "learning_rate": 1.777019808140412e-05,
+      "loss": 0.4785,
+      "step": 4900
+    },
+    {
+      "epoch": 4.796511627906977,
+      "grad_norm": 0.17888276278972626,
+      "learning_rate": 1.7316205256088396e-05,
+      "loss": 0.4547,
+      "step": 4950
+    },
+    {
+      "epoch": 4.844961240310077,
+      "grad_norm": 0.9857609272003174,
+      "learning_rate": 1.6864993828142177e-05,
+      "loss": 0.3773,
+      "step": 5000
+    },
+    {
+      "epoch": 4.8934108527131785,
+      "grad_norm": 0.2999161183834076,
+      "learning_rate": 1.6416727128096866e-05,
+      "loss": 0.5057,
+      "step": 5050
+    },
+    {
+      "epoch": 4.941860465116279,
+      "grad_norm": 0.3053271472454071,
+      "learning_rate": 1.5971567420544616e-05,
+      "loss": 0.4571,
+      "step": 5100
+    },
+    {
+      "epoch": 4.99031007751938,
+      "grad_norm": 0.2922804057598114,
+      "learning_rate": 1.5529675845401433e-05,
+      "loss": 0.3809,
+      "step": 5150
+    },
+    {
+      "epoch": 5.038759689922481,
+      "grad_norm": 0.37198856472969055,
+      "learning_rate": 1.5091212359577361e-05,
+      "loss": 0.5042,
+      "step": 5200
+    },
+    {
+      "epoch": 5.087209302325581,
+      "grad_norm": 0.2848919928073883,
+      "learning_rate": 1.4656335679074957e-05,
+      "loss": 0.3718,
+      "step": 5250
+    },
+    {
+      "epoch": 5.135658914728682,
+      "grad_norm": 0.4509316384792328,
+      "learning_rate": 1.422520322153686e-05,
+      "loss": 0.4388,
+      "step": 5300
+    },
+    {
+      "epoch": 5.184108527131783,
+      "grad_norm": 0.5705945491790771,
+      "learning_rate": 1.3797971049263427e-05,
+      "loss": 0.3232,
+      "step": 5350
+    },
+    {
+      "epoch": 5.232558139534884,
+      "grad_norm": 0.41659048199653625,
+      "learning_rate": 1.3374793812720998e-05,
+      "loss": 0.4727,
+      "step": 5400
+    },
+    {
+      "epoch": 5.2810077519379846,
+      "grad_norm": 0.44602829217910767,
+      "learning_rate": 1.2955824694561041e-05,
+      "loss": 0.4916,
+      "step": 5450
+    },
+    {
+      "epoch": 5.329457364341085,
+      "grad_norm": 0.4279162287712097,
+      "learning_rate": 1.254121535417091e-05,
+      "loss": 0.4178,
+      "step": 5500
+    },
+    {
+      "epoch": 5.377906976744186,
+      "grad_norm": 0.6180667281150818,
+      "learning_rate": 1.213111587277571e-05,
+      "loss": 0.429,
+      "step": 5550
+    },
+    {
+      "epoch": 5.426356589147287,
+      "grad_norm": 0.38391199707984924,
+      "learning_rate": 1.1725674699111622e-05,
+      "loss": 0.3601,
+      "step": 5600
+    },
+    {
+      "epoch": 5.474806201550388,
+      "grad_norm": 0.12185677886009216,
+      "learning_rate": 1.1325038595690074e-05,
+      "loss": 0.2,
+      "step": 5650
+    },
+    {
+      "epoch": 5.523255813953488,
+      "grad_norm": 0.3772415816783905,
+      "learning_rate": 1.0929352585672316e-05,
+      "loss": 0.4003,
+      "step": 5700
+    },
+    {
+      "epoch": 5.571705426356589,
+      "grad_norm": 0.4929804503917694,
+      "learning_rate": 1.0538759900373618e-05,
+      "loss": 0.4523,
+      "step": 5750
+    },
+    {
+      "epoch": 5.62015503875969,
+      "grad_norm": 0.24463126063346863,
+      "learning_rate": 1.0153401927416057e-05,
+      "loss": 0.373,
+      "step": 5800
+    },
+    {
+      "epoch": 5.6686046511627906,
+      "grad_norm": 0.4997948408126831,
+      "learning_rate": 9.773418159548738e-06,
+      "loss": 0.5103,
+      "step": 5850
+    },
+    {
+      "epoch": 5.717054263565892,
+      "grad_norm": 0.36583212018013,
+      "learning_rate": 9.398946144153872e-06,
+      "loss": 0.3983,
+      "step": 5900
+    },
+    {
+      "epoch": 5.765503875968992,
+      "grad_norm": 0.5164257287979126,
+      "learning_rate": 9.030121433457026e-06,
+      "loss": 0.4945,
+      "step": 5950
+    },
+    {
+      "epoch": 5.813953488372093,
+      "grad_norm": 0.4246552288532257,
+      "learning_rate": 8.667077535459714e-06,
+      "loss": 0.4677,
+      "step": 6000
+    },
+    {
+      "epoch": 5.862403100775194,
+      "grad_norm": 0.5210244655609131,
+      "learning_rate": 8.309945865611793e-06,
+      "loss": 0.4652,
+      "step": 6050
+    },
+    {
+      "epoch": 5.910852713178294,
+      "grad_norm": 0.43867701292037964,
+      "learning_rate": 7.958855699241427e-06,
+      "loss": 0.4393,
+      "step": 6100
+    },
+    {
+      "epoch": 5.959302325581396,
+      "grad_norm": 0.3301217257976532,
+      "learning_rate": 7.613934124759711e-06,
+      "loss": 0.5171,
+      "step": 6150
+    },
+    {
+      "epoch": 6.007751937984496,
+      "grad_norm": 0.5201098918914795,
+      "learning_rate": 7.27530599765692e-06,
+      "loss": 0.4175,
+      "step": 6200
+    },
+    {
+      "epoch": 6.0562015503875966,
+      "grad_norm": 0.46548280119895935,
+      "learning_rate": 6.94309389530706e-06,
+      "loss": 0.3947,
+      "step": 6250
+    },
+    {
+      "epoch": 6.104651162790698,
+      "grad_norm": 0.0748455747961998,
+      "learning_rate": 6.6174180725969624e-06,
+      "loss": 0.4261,
+      "step": 6300
+    },
+    {
+      "epoch": 6.153100775193798,
+      "grad_norm": 0.4305146634578705,
+      "learning_rate": 6.298396418396249e-06,
+      "loss": 0.3665,
+      "step": 6350
+    },
+    {
+      "epoch": 6.2015503875969,
+      "grad_norm": 0.5521872639656067,
+      "learning_rate": 5.986144412883582e-06,
+      "loss": 0.4068,
+      "step": 6400
+    },
+    {
+      "epoch": 6.25,
+      "grad_norm": 0.3403307795524597,
+      "learning_rate": 5.680775085744877e-06,
+      "loss": 0.4345,
+      "step": 6450
+    },
+    {
+      "epoch": 6.2984496124031,
+      "grad_norm": 0.4251650869846344,
+      "learning_rate": 5.382398975258643e-06,
+      "loss": 0.4144,
+      "step": 6500
+    },
+    {
+      "epoch": 6.346899224806202,
+      "grad_norm": 0.3254774212837219,
+      "learning_rate": 5.0911240882830085e-06,
+      "loss": 0.4702,
+      "step": 6550
+    },
+    {
+      "epoch": 6.395348837209302,
+      "grad_norm": 0.20938007533550262,
+      "learning_rate": 4.8070558611591846e-06,
+      "loss": 0.4185,
+      "step": 6600
+    },
+    {
+      "epoch": 6.4437984496124034,
+      "grad_norm": 0.2960624396800995,
+      "learning_rate": 4.53029712154538e-06,
+      "loss": 0.4124,
+      "step": 6650
+    },
+    {
+      "epoch": 6.492248062015504,
+      "grad_norm": 0.07721071690320969,
+      "learning_rate": 4.26094805119501e-06,
+      "loss": 0.1426,
+      "step": 6700
+    },
+    {
+      "epoch": 6.540697674418604,
+      "grad_norm": 0.23349162936210632,
+      "learning_rate": 3.9991061496926965e-06,
+      "loss": 0.4447,
+      "step": 6750
+    },
+    {
+      "epoch": 6.589147286821706,
+      "grad_norm": 0.3078431785106659,
+      "learning_rate": 3.7448661991611012e-06,
+      "loss": 0.3905,
+      "step": 6800
+    },
+    {
+      "epoch": 6.637596899224806,
+      "grad_norm": 0.5103276371955872,
+      "learning_rate": 3.4983202299515403e-06,
+      "loss": 0.4237,
+      "step": 6850
+    },
+    {
+      "epoch": 6.686046511627907,
+      "grad_norm": 0.3160223662853241,
+      "learning_rate": 3.259557487330586e-06,
+      "loss": 0.3905,
+      "step": 6900
+    },
+    {
+      "epoch": 6.734496124031008,
+      "grad_norm": 0.26788458228111267,
+      "learning_rate": 3.0286643991748742e-06,
+      "loss": 0.3543,
+      "step": 6950
+    },
+    {
+      "epoch": 6.782945736434108,
+      "grad_norm": 0.6616643071174622,
+      "learning_rate": 2.8057245446857614e-06,
+      "loss": 0.37,
+      "step": 7000
+    },
+    {
+      "epoch": 6.8313953488372094,
+      "grad_norm": 0.7186428308486938,
+      "learning_rate": 2.5908186241351107e-06,
+      "loss": 0.443,
+      "step": 7050
+    },
+    {
+      "epoch": 6.87984496124031,
+      "grad_norm": 0.5220199823379517,
+      "learning_rate": 2.3840244296532534e-06,
+      "loss": 0.4607,
+      "step": 7100
+    },
+    {
+      "epoch": 6.928294573643411,
+      "grad_norm": 0.4159252345561981,
+      "learning_rate": 2.1854168170695967e-06,
+      "loss": 0.4479,
+      "step": 7150
+    },
+    {
+      "epoch": 6.976744186046512,
+      "grad_norm": 0.5149658918380737,
+      "learning_rate": 1.9950676788161425e-06,
+      "loss": 0.5063,
+      "step": 7200
+    },
+    {
+      "epoch": 7.025193798449612,
+      "grad_norm": 0.44880130887031555,
+      "learning_rate": 1.813045917903733e-06,
+      "loss": 0.4645,
+      "step": 7250
+    },
+    {
+      "epoch": 7.073643410852713,
+      "grad_norm": 0.2966916263103485,
+      "learning_rate": 1.6394174229803244e-06,
+      "loss": 0.4564,
+      "step": 7300
+    },
+    {
+      "epoch": 7.122093023255814,
+      "grad_norm": 0.33741477131843567,
+      "learning_rate": 1.4742450444805296e-06,
+      "loss": 0.4172,
+      "step": 7350
+    },
+    {
+      "epoch": 7.170542635658915,
+      "grad_norm": 0.3214058578014374,
+      "learning_rate": 1.3175885718748366e-06,
+      "loss": 0.4658,
+      "step": 7400
+    },
+    {
+      "epoch": 7.2189922480620154,
+      "grad_norm": 0.3869069218635559,
+      "learning_rate": 1.1695047120268892e-06,
+      "loss": 0.3009,
+      "step": 7450
+    },
+    {
+      "epoch": 7.267441860465116,
+      "grad_norm": 0.4083672761917114,
+      "learning_rate": 1.030047068666612e-06,
+      "loss": 0.459,
+      "step": 7500
+    },
+    {
+      "epoch": 7.315891472868217,
+      "grad_norm": 0.3610597550868988,
+      "learning_rate": 8.992661229866056e-07,
+      "loss": 0.3833,
+      "step": 7550
+    },
+    {
+      "epoch": 7.364341085271318,
+      "grad_norm": 0.539691150188446,
+      "learning_rate": 7.772092153688598e-07,
+      "loss": 0.4663,
+      "step": 7600
+    },
+    {
+      "epoch": 7.412790697674419,
+      "grad_norm": 0.2774708569049835,
+      "learning_rate": 6.639205282483713e-07,
+      "loss": 0.2524,
+      "step": 7650
+    },
+    {
+      "epoch": 7.461240310077519,
+      "grad_norm": 0.4285198748111725,
+      "learning_rate": 5.59441070119876e-07,
+      "loss": 0.2562,
+      "step": 7700
+    },
+    {
+      "epoch": 7.50968992248062,
+      "grad_norm": 0.19247202575206757,
+      "learning_rate": 4.638086606935238e-07,
+      "loss": 0.3872,
+      "step": 7750
+    },
+    {
+      "epoch": 7.558139534883721,
+      "grad_norm": 0.3917827606201172,
+      "learning_rate": 3.770579172047817e-07,
+      "loss": 0.3324,
+      "step": 7800
+    },
+    {
+      "epoch": 7.6065891472868215,
+      "grad_norm": 0.439827024936676,
+      "learning_rate": 2.9922024188365206e-07,
+      "loss": 0.4872,
+      "step": 7850
+    },
+    {
+      "epoch": 7.655038759689923,
+      "grad_norm": 0.6945509314537048,
+      "learning_rate": 2.3032381058757658e-07,
+      "loss": 0.4528,
+      "step": 7900
+    },
+    {
+      "epoch": 7.703488372093023,
+      "grad_norm": 0.29122206568717957,
+      "learning_rate": 1.7039356260231122e-07,
+      "loss": 0.4036,
+      "step": 7950
+    },
+    {
+      "epoch": 7.751937984496124,
+      "grad_norm": 0.3214813768863678,
+      "learning_rate": 1.1945119161432817e-07,
+      "loss": 0.3775,
+      "step": 8000
+    },
+    {
+      "epoch": 7.800387596899225,
+      "grad_norm": 0.35670900344848633,
+      "learning_rate": 7.751513785809183e-08,
+      "loss": 0.388,
+      "step": 8050
+    },
+    {
+      "epoch": 7.848837209302325,
+      "grad_norm": 0.6631624698638916,
+      "learning_rate": 4.460058144102608e-08,
+      "loss": 0.4559,
+      "step": 8100
+    },
+    {
+      "epoch": 7.897286821705427,
+      "grad_norm": 0.3693590462207794,
+      "learning_rate": 2.071943684856803e-08,
+      "loss": 0.3987,
+      "step": 8150
+    },
+    {
+      "epoch": 7.945736434108527,
+      "grad_norm": 0.37362340092658997,
+      "learning_rate": 5.880348631362442e-09,
+      "loss": 0.3428,
+      "step": 8200
+    },
+    {
+      "epoch": 7.9941860465116275,
+      "grad_norm": 0.41830864548683167,
+      "learning_rate": 8.868827605923446e-11,
+      "loss": 0.4124,
+      "step": 8250
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 8256,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.682679674077476e+19,
+  "train_batch_size": 92,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:870345ecc5101b92b53fd7e4027f3d9e08ef772960ac6122713637a2c31edc31
+size 5969