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 +1,202 @@
+---
+base_model: Qwen/Qwen3-8B
+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 0.15.2

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-8B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a565e26dd3ca9f5937e37c1eb1d628b3c67fc082232cf99de40ab656df88ff18
+size 349243752

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 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 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56930aea70938c6b332e53276e116098663130b74afc376af916c386d0013e3c
+size 177919028

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:800f5d7dbad54cb4b752acd04b5819b97456d681a09cf651dcd762da8f27132f
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0834abff2e2be0e31897a2d43e27b51aef41dd8aa02ef4a01493c70895515be6
+size 1064

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": "<|endoftext|>",
+    "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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,574 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.066477070742979,
+  "eval_steps": 500,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017774617845716316,
+      "grad_norm": 0.35813066363334656,
+      "learning_rate": 4.3516873889875667e-07,
+      "loss": 2.0692,
+      "mean_token_accuracy": 0.6023900508880615,
+      "num_tokens": 204800.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.03554923569143263,
+      "grad_norm": 0.32111021876335144,
+      "learning_rate": 8.792184724689167e-07,
+      "loss": 2.0543,
+      "mean_token_accuracy": 0.6035288572311401,
+      "num_tokens": 409600.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.053323853537148955,
+      "grad_norm": 0.32630783319473267,
+      "learning_rate": 1.3232682060390764e-06,
+      "loss": 2.0209,
+      "mean_token_accuracy": 0.6055229902267456,
+      "num_tokens": 614400.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.07109847138286526,
+      "grad_norm": 0.28461402654647827,
+      "learning_rate": 1.7673179396092362e-06,
+      "loss": 1.9593,
+      "mean_token_accuracy": 0.6079961061477661,
+      "num_tokens": 819200.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.08887308922858159,
+      "grad_norm": 0.26054471731185913,
+      "learning_rate": 2.211367673179396e-06,
+      "loss": 1.856,
+      "mean_token_accuracy": 0.619281530380249,
+      "num_tokens": 1024000.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.10664770707429791,
+      "grad_norm": 0.2539742588996887,
+      "learning_rate": 2.6554174067495562e-06,
+      "loss": 1.7108,
+      "mean_token_accuracy": 0.6380449533462524,
+      "num_tokens": 1228800.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.12442232492001422,
+      "grad_norm": 0.2737816274166107,
+      "learning_rate": 3.0994671403197163e-06,
+      "loss": 1.5271,
+      "mean_token_accuracy": 0.6642766416072845,
+      "num_tokens": 1433600.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.14219694276573053,
+      "grad_norm": 0.4782876968383789,
+      "learning_rate": 3.543516873889876e-06,
+      "loss": 1.2194,
+      "mean_token_accuracy": 0.7056109464168548,
+      "num_tokens": 1638400.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.15997156061144685,
+      "grad_norm": 0.33332306146621704,
+      "learning_rate": 3.987566607460036e-06,
+      "loss": 0.5046,
+      "mean_token_accuracy": 0.8682502424716949,
+      "num_tokens": 1843200.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.17774617845716317,
+      "grad_norm": 0.07436951249837875,
+      "learning_rate": 4.431616341030196e-06,
+      "loss": 0.0607,
+      "mean_token_accuracy": 0.9876881837844849,
+      "num_tokens": 2048000.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.1955207963028795,
+      "grad_norm": 0.0204151701182127,
+      "learning_rate": 4.875666074600356e-06,
+      "loss": 0.0215,
+      "mean_token_accuracy": 0.9962121248245239,
+      "num_tokens": 2252800.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.21329541414859582,
+      "grad_norm": 0.02164212055504322,
+      "learning_rate": 4.999376292672713e-06,
+      "loss": 0.0167,
+      "mean_token_accuracy": 0.9970674514770508,
+      "num_tokens": 2457600.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.23107003199431211,
+      "grad_norm": 0.020050790160894394,
+      "learning_rate": 4.996441329770864e-06,
+      "loss": 0.0139,
+      "mean_token_accuracy": 0.9980645179748535,
+      "num_tokens": 2662400.0,
+      "step": 650
+    },
+    {
+      "epoch": 0.24884464984002844,
+      "grad_norm": 0.01833987981081009,
+      "learning_rate": 4.991103606682987e-06,
+      "loss": 0.0114,
+      "mean_token_accuracy": 0.9990224838256836,
+      "num_tokens": 2867200.0,
+      "step": 700
+    },
+    {
+      "epoch": 0.26661926768574473,
+      "grad_norm": 0.017948873341083527,
+      "learning_rate": 4.983368260829447e-06,
+      "loss": 0.0097,
+      "mean_token_accuracy": 0.9990224838256836,
+      "num_tokens": 3072000.0,
+      "step": 750
+    },
+    {
+      "epoch": 0.28439388553146105,
+      "grad_norm": 0.016040902584791183,
+      "learning_rate": 4.973242737280479e-06,
+      "loss": 0.0088,
+      "mean_token_accuracy": 0.9990224838256836,
+      "num_tokens": 3276800.0,
+      "step": 800
+    },
+    {
+      "epoch": 0.3021685033771774,
+      "grad_norm": 0.019489038735628128,
+      "learning_rate": 4.9607367815905074e-06,
+      "loss": 0.0077,
+      "mean_token_accuracy": 0.9990224838256836,
+      "num_tokens": 3481600.0,
+      "step": 850
+    },
+    {
+      "epoch": 0.3199431212228937,
+      "grad_norm": 0.023746857419610023,
+      "learning_rate": 4.9458624304183e-06,
+      "loss": 0.0066,
+      "mean_token_accuracy": 0.9990224838256836,
+      "num_tokens": 3686400.0,
+      "step": 900
+    },
+    {
+      "epoch": 0.33771773906861,
+      "grad_norm": 0.02442137524485588,
+      "learning_rate": 4.928633999941995e-06,
+      "loss": 0.0052,
+      "mean_token_accuracy": 0.9994232654571533,
+      "num_tokens": 3891200.0,
+      "step": 950
+    },
+    {
+      "epoch": 0.35549235691432635,
+      "grad_norm": 0.024948744103312492,
+      "learning_rate": 4.909068072080152e-06,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9999169111251831,
+      "num_tokens": 4096000.0,
+      "step": 1000
+    },
+    {
+      "epoch": 0.37326697476004267,
+      "grad_norm": 0.010364473797380924,
+      "learning_rate": 4.887183478532081e-06,
+      "loss": 0.0013,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 4300800.0,
+      "step": 1050
+    },
+    {
+      "epoch": 0.391041592605759,
+      "grad_norm": 0.004597879946231842,
+      "learning_rate": 4.86300128265282e-06,
+      "loss": 0.0005,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 4505600.0,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4088162104514753,
+      "grad_norm": 0.0024459899868816137,
+      "learning_rate": 4.836544759180206e-06,
+      "loss": 0.0002,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 4710400.0,
+      "step": 1150
+    },
+    {
+      "epoch": 0.42659082829719164,
+      "grad_norm": 0.0013584563275799155,
+      "learning_rate": 4.807839371833534e-06,
+      "loss": 0.0002,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 4915200.0,
+      "step": 1200
+    },
+    {
+      "epoch": 0.4443654461429079,
+      "grad_norm": 0.0022760790307074785,
+      "learning_rate": 4.776912748805392e-06,
+      "loss": 0.0002,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 5120000.0,
+      "step": 1250
+    },
+    {
+      "epoch": 0.46214006398862423,
+      "grad_norm": 0.0010678465478122234,
+      "learning_rate": 4.743794656170235e-06,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 5324800.0,
+      "step": 1300
+    },
+    {
+      "epoch": 0.47991468183434055,
+      "grad_norm": 0.0008997164550237358,
+      "learning_rate": 4.7085169692353175e-06,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 5529600.0,
+      "step": 1350
+    },
+    {
+      "epoch": 0.4976892996800569,
+      "grad_norm": 0.0007172881159931421,
+      "learning_rate": 4.671113641861523e-06,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 5734400.0,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5154639175257731,
+      "grad_norm": 0.0006771351909264922,
+      "learning_rate": 4.631620673783662e-06,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 5939200.0,
+      "step": 1450
+    },
+    {
+      "epoch": 0.5332385353714895,
+      "grad_norm": 0.0018679159693419933,
+      "learning_rate": 4.590076075961653e-06,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 6144000.0,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5510131532172058,
+      "grad_norm": 0.0005585107719525695,
+      "learning_rate": 4.546519833995959e-06,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 6348800.0,
+      "step": 1550
+    },
+    {
+      "epoch": 0.5687877710629221,
+      "grad_norm": 0.0008035791106522083,
+      "learning_rate": 4.5009938696424816e-06,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 6553600.0,
+      "step": 1600
+    },
+    {
+      "epoch": 0.5865623889086384,
+      "grad_norm": 0.0005080197588540614,
+      "learning_rate": 4.453542000463954e-06,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 6758400.0,
+      "step": 1650
+    },
+    {
+      "epoch": 0.6043370067543548,
+      "grad_norm": 0.0005295136361382902,
+      "learning_rate": 4.404209897656672e-06,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 6963200.0,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6221116246000711,
+      "grad_norm": 0.0004332393582444638,
+      "learning_rate": 4.353045042093153e-06,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 7168000.0,
+      "step": 1750
+    },
+    {
+      "epoch": 0.6398862424457874,
+      "grad_norm": 0.0006319705280475318,
+      "learning_rate": 4.3000966786230145e-06,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 7372800.0,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6576608602915037,
+      "grad_norm": 0.0003928539517801255,
+      "learning_rate": 4.245415768676092e-06,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 7577600.0,
+      "step": 1850
+    },
+    {
+      "epoch": 0.67543547813722,
+      "grad_norm": 0.00046053010737523437,
+      "learning_rate": 4.189054941213374e-06,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 7782400.0,
+      "step": 1900
+    },
+    {
+      "epoch": 0.6932100959829364,
+      "grad_norm": 0.0005214207340031862,
+      "learning_rate": 4.131068442072993e-06,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 7987200.0,
+      "step": 1950
+    },
+    {
+      "epoch": 0.7109847138286527,
+      "grad_norm": 0.00034946095547638834,
+      "learning_rate": 4.071512081760004e-06,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 8192000.0,
+      "step": 2000
+    },
+    {
+      "epoch": 0.728759331674369,
+      "grad_norm": 0.0003215207834728062,
+      "learning_rate": 4.010443181730227e-06,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 8396800.0,
+      "step": 2050
+    },
+    {
+      "epoch": 0.7465339495200853,
+      "grad_norm": 0.000304091430734843,
+      "learning_rate": 3.947920519219819e-06,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 8601600.0,
+      "step": 2100
+    },
+    {
+      "epoch": 0.7643085673658017,
+      "grad_norm": 0.0002895969955716282,
+      "learning_rate": 3.884004270673711e-06,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 8806400.0,
+      "step": 2150
+    },
+    {
+      "epoch": 0.782083185211518,
+      "grad_norm": 0.000491043902002275,
+      "learning_rate": 3.8187559538273364e-06,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 9011200.0,
+      "step": 2200
+    },
+    {
+      "epoch": 0.7998578030572343,
+      "grad_norm": 0.0006208749837242067,
+      "learning_rate": 3.7522383684973994e-06,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 9216000.0,
+      "step": 2250
+    },
+    {
+      "epoch": 0.8176324209029506,
+      "grad_norm": 0.0002920223632827401,
+      "learning_rate": 3.684515536138678e-06,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 9420800.0,
+      "step": 2300
+    },
+    {
+      "epoch": 0.835407038748667,
+      "grad_norm": 0.0002676283475011587,
+      "learning_rate": 3.615652638225031e-06,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 9625600.0,
+      "step": 2350
+    },
+    {
+      "epoch": 0.8531816565943833,
+      "grad_norm": 0.00026544969296082854,
+      "learning_rate": 3.5457159535139164e-06,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 9830400.0,
+      "step": 2400
+    },
+    {
+      "epoch": 0.8709562744400995,
+      "grad_norm": 0.0002422648831270635,
+      "learning_rate": 3.474772794254798e-06,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 10035200.0,
+      "step": 2450
+    },
+    {
+      "epoch": 0.8887308922858158,
+      "grad_norm": 0.00023040748783387244,
+      "learning_rate": 3.4028914414028546e-06,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 10240000.0,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9065055101315321,
+      "grad_norm": 0.00022141206136438996,
+      "learning_rate": 3.3301410789003196e-06,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 10444800.0,
+      "step": 2550
+    },
+    {
+      "epoch": 0.9242801279772485,
+      "grad_norm": 0.00022032092965673655,
+      "learning_rate": 3.256591727088731e-06,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 10649600.0,
+      "step": 2600
+    },
+    {
+      "epoch": 0.9420547458229648,
+      "grad_norm": 0.00034698573290370405,
+      "learning_rate": 3.182314175316163e-06,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 10854400.0,
+      "step": 2650
+    },
+    {
+      "epoch": 0.9598293636686811,
+      "grad_norm": 0.0002007318107644096,
+      "learning_rate": 3.1073799138043115e-06,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 11059200.0,
+      "step": 2700
+    },
+    {
+      "epoch": 0.9776039815143974,
+      "grad_norm": 0.0008882895344868302,
+      "learning_rate": 3.0318610648410037e-06,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 11264000.0,
+      "step": 2750
+    },
+    {
+      "epoch": 0.9953785993601137,
+      "grad_norm": 0.00027154191047884524,
+      "learning_rate": 2.955830313364363e-06,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 11468800.0,
+      "step": 2800
+    },
+    {
+      "epoch": 1.0131532172058302,
+      "grad_norm": 0.00027565049822442234,
+      "learning_rate": 2.879360837005437e-06,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 11671552.0,
+      "step": 2850
+    },
+    {
+      "epoch": 1.0309278350515463,
+      "grad_norm": 0.00022640528914052993,
+      "learning_rate": 2.80252623565662e-06,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 11876352.0,
+      "step": 2900
+    },
+    {
+      "epoch": 1.0487024528972626,
+      "grad_norm": 0.00019061467901337892,
+      "learning_rate": 2.725400460633664e-06,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 12081152.0,
+      "step": 2950
+    },
+    {
+      "epoch": 1.066477070742979,
+      "grad_norm": 0.00017320447659585625,
+      "learning_rate": 2.648057743499445e-06,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 12285952.0,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 5626,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 5.643453362570527e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d9f0575136a857f445de49de3fdb013734e9a30d452f7755a747a21ae85cdc6
+size 5560