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/Qwen3-14B
+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/Qwen3-14B",
+  "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": 32,
+  "lora_bias": false,
+  "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": [
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "k_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 sha256:33f88a1b796368dcea5e3df36347b3bc015bd14e39ed48bcd3573e0f881a4ee0
+size 256976504

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 sha256:14c86bdcad02894f867e6ca15aba5bf3d674d9f81f321dcf78e37aa078ae3ab7
+size 514283635

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28a6b1cece7bdb7d0246722ba20cab48c12bf5509ab98a9fe474eb69a574dc21
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:512586781e2e9ce21da755cbc4e17323c507adffe6325b1e671a7c6ec537d3c7
+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": "<|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 +1,286 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 285,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 0.2200665920972824,
+      "learning_rate": 0.0001,
+      "loss": 0.5783,
+      "mean_token_accuracy": 0.8814848005771637,
+      "num_tokens": 229387.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 0.2296973317861557,
+      "learning_rate": 0.0001,
+      "loss": 0.2592,
+      "mean_token_accuracy": 0.9266352355480194,
+      "num_tokens": 460296.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.28599151968955994,
+      "learning_rate": 0.0001,
+      "loss": 0.247,
+      "mean_token_accuracy": 0.9282570332288742,
+      "num_tokens": 689817.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.2100379317998886,
+      "learning_rate": 0.0001,
+      "loss": 0.2182,
+      "mean_token_accuracy": 0.9342806369066239,
+      "num_tokens": 919643.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.22898457944393158,
+      "learning_rate": 0.0001,
+      "loss": 0.1818,
+      "mean_token_accuracy": 0.9437532901763916,
+      "num_tokens": 1149675.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.18718937039375305,
+      "learning_rate": 0.0001,
+      "loss": 0.1798,
+      "mean_token_accuracy": 0.9433006137609482,
+      "num_tokens": 1379359.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.16129809617996216,
+      "learning_rate": 0.0001,
+      "loss": 0.2013,
+      "mean_token_accuracy": 0.9372004717588425,
+      "num_tokens": 1608589.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.15493103861808777,
+      "learning_rate": 0.0001,
+      "loss": 0.1804,
+      "mean_token_accuracy": 0.9407124549150467,
+      "num_tokens": 1838882.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.1514456570148468,
+      "learning_rate": 0.0001,
+      "loss": 0.1793,
+      "mean_token_accuracy": 0.9426521331071853,
+      "num_tokens": 2069909.0,
+      "step": 90
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.17919491231441498,
+      "learning_rate": 0.0001,
+      "loss": 0.1691,
+      "mean_token_accuracy": 0.9444904655218125,
+      "num_tokens": 2299530.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 0.20948663353919983,
+      "learning_rate": 0.0001,
+      "loss": 0.1492,
+      "mean_token_accuracy": 0.9499557614326477,
+      "num_tokens": 2531307.0,
+      "step": 110
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 0.16768105328083038,
+      "learning_rate": 0.0001,
+      "loss": 0.1516,
+      "mean_token_accuracy": 0.9481500267982483,
+      "num_tokens": 2760541.0,
+      "step": 120
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 0.15357017517089844,
+      "learning_rate": 0.0001,
+      "loss": 0.1621,
+      "mean_token_accuracy": 0.9449363112449646,
+      "num_tokens": 2991363.0,
+      "step": 130
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 0.18268407881259918,
+      "learning_rate": 0.0001,
+      "loss": 0.1704,
+      "mean_token_accuracy": 0.9450611799955368,
+      "num_tokens": 3220657.0,
+      "step": 140
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.180303692817688,
+      "learning_rate": 0.0001,
+      "loss": 0.1866,
+      "mean_token_accuracy": 0.9396294564008713,
+      "num_tokens": 3450771.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 0.16212788224220276,
+      "learning_rate": 0.0001,
+      "loss": 0.1645,
+      "mean_token_accuracy": 0.9452700793743134,
+      "num_tokens": 3679376.0,
+      "step": 160
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "grad_norm": 0.15377922356128693,
+      "learning_rate": 0.0001,
+      "loss": 0.1703,
+      "mean_token_accuracy": 0.9441883742809296,
+      "num_tokens": 3909977.0,
+      "step": 170
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 0.20362214744091034,
+      "learning_rate": 0.0001,
+      "loss": 0.1614,
+      "mean_token_accuracy": 0.9447846442461014,
+      "num_tokens": 4139327.0,
+      "step": 180
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.2080821543931961,
+      "learning_rate": 0.0001,
+      "loss": 0.1688,
+      "mean_token_accuracy": 0.9449883460998535,
+      "num_tokens": 4369912.0,
+      "step": 190
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.1884932667016983,
+      "learning_rate": 0.0001,
+      "loss": 0.1514,
+      "mean_token_accuracy": 0.9475339651107788,
+      "num_tokens": 4600029.0,
+      "step": 200
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 0.18963050842285156,
+      "learning_rate": 0.0001,
+      "loss": 0.1448,
+      "mean_token_accuracy": 0.9487747073173523,
+      "num_tokens": 4830261.0,
+      "step": 210
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 0.24761813879013062,
+      "learning_rate": 0.0001,
+      "loss": 0.1437,
+      "mean_token_accuracy": 0.9511690646409988,
+      "num_tokens": 5059425.0,
+      "step": 220
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 0.1822461485862732,
+      "learning_rate": 0.0001,
+      "loss": 0.1458,
+      "mean_token_accuracy": 0.9499670505523682,
+      "num_tokens": 5290100.0,
+      "step": 230
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 0.21711082756519318,
+      "learning_rate": 0.0001,
+      "loss": 0.1446,
+      "mean_token_accuracy": 0.9512652307748795,
+      "num_tokens": 5520023.0,
+      "step": 240
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.21405605971813202,
+      "learning_rate": 0.0001,
+      "loss": 0.1451,
+      "mean_token_accuracy": 0.9491914957761765,
+      "num_tokens": 5750089.0,
+      "step": 250
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 0.1787135899066925,
+      "learning_rate": 0.0001,
+      "loss": 0.1338,
+      "mean_token_accuracy": 0.9524210095405579,
+      "num_tokens": 5979923.0,
+      "step": 260
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 0.20585036277770996,
+      "learning_rate": 0.0001,
+      "loss": 0.1562,
+      "mean_token_accuracy": 0.9469417929649353,
+      "num_tokens": 6209537.0,
+      "step": 270
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 0.16770680248737335,
+      "learning_rate": 0.0001,
+      "loss": 0.1701,
+      "mean_token_accuracy": 0.9429820030927658,
+      "num_tokens": 6439820.0,
+      "step": 280
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 285,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.6153289689849856e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a18ae8a8d5b6be9e8a67cca81e28c5ad5122af3ef2e90ba587109fdc166378f2
+size 6033