Add fine-tuned model

README.md

@@ -0,0 +1,201 @@
+---
+base_model: Qwen/Qwen3-1.7B
+library_name: peft
+---
+### Framework versions
+
+- PEFT 0.15.1ide 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 0.15.1

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-1.7B",
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "down_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 sha256:5ec6070150ab47cf480b97d2dcc67f02ccc2f10c9f48d343b72af35e68f670fc
+size 278973888

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 %}

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:baf4233a05cc80d36da049c8c40877aa3b37dab8c9bc156c928f7b2ef5575305
+size 7032431

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,497 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 65,
+  "global_step": 65,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015384615384615385,
+      "grad_norm": 2.836469888687134,
+      "learning_rate": 1e-05,
+      "loss": 2.3399,
+      "step": 1
+    },
+    {
+      "epoch": 0.03076923076923077,
+      "grad_norm": 2.677016496658325,
+      "learning_rate": 9.846153846153848e-06,
+      "loss": 2.2779,
+      "step": 2
+    },
+    {
+      "epoch": 0.046153846153846156,
+      "grad_norm": 2.5800905227661133,
+      "learning_rate": 9.692307692307693e-06,
+      "loss": 2.2556,
+      "step": 3
+    },
+    {
+      "epoch": 0.06153846153846154,
+      "grad_norm": 2.4350876808166504,
+      "learning_rate": 9.53846153846154e-06,
+      "loss": 2.1498,
+      "step": 4
+    },
+    {
+      "epoch": 0.07692307692307693,
+      "grad_norm": 2.4091274738311768,
+      "learning_rate": 9.384615384615385e-06,
+      "loss": 2.2694,
+      "step": 5
+    },
+    {
+      "epoch": 0.09230769230769231,
+      "grad_norm": 2.2378604412078857,
+      "learning_rate": 9.230769230769232e-06,
+      "loss": 2.155,
+      "step": 6
+    },
+    {
+      "epoch": 0.1076923076923077,
+      "grad_norm": 2.0651841163635254,
+      "learning_rate": 9.076923076923078e-06,
+      "loss": 2.1739,
+      "step": 7
+    },
+    {
+      "epoch": 0.12307692307692308,
+      "grad_norm": 1.9772603511810303,
+      "learning_rate": 8.923076923076925e-06,
+      "loss": 2.1405,
+      "step": 8
+    },
+    {
+      "epoch": 0.13846153846153847,
+      "grad_norm": 1.9026098251342773,
+      "learning_rate": 8.76923076923077e-06,
+      "loss": 2.2088,
+      "step": 9
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 1.7011582851409912,
+      "learning_rate": 8.615384615384617e-06,
+      "loss": 2.086,
+      "step": 10
+    },
+    {
+      "epoch": 0.16923076923076924,
+      "grad_norm": 1.5802580118179321,
+      "learning_rate": 8.461538461538462e-06,
+      "loss": 2.1036,
+      "step": 11
+    },
+    {
+      "epoch": 0.18461538461538463,
+      "grad_norm": 1.4898951053619385,
+      "learning_rate": 8.307692307692309e-06,
+      "loss": 2.0906,
+      "step": 12
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.355930209159851,
+      "learning_rate": 8.153846153846154e-06,
+      "loss": 2.0715,
+      "step": 13
+    },
+    {
+      "epoch": 0.2153846153846154,
+      "grad_norm": 1.2688668966293335,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.0705,
+      "step": 14
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 1.1473366022109985,
+      "learning_rate": 7.846153846153847e-06,
+      "loss": 1.9498,
+      "step": 15
+    },
+    {
+      "epoch": 0.24615384615384617,
+      "grad_norm": 1.1260186433792114,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 2.0414,
+      "step": 16
+    },
+    {
+      "epoch": 0.26153846153846155,
+      "grad_norm": 1.0489989519119263,
+      "learning_rate": 7.538461538461539e-06,
+      "loss": 1.9938,
+      "step": 17
+    },
+    {
+      "epoch": 0.27692307692307694,
+      "grad_norm": 1.0498378276824951,
+      "learning_rate": 7.384615384615386e-06,
+      "loss": 1.9979,
+      "step": 18
+    },
+    {
+      "epoch": 0.2923076923076923,
+      "grad_norm": 0.9455246329307556,
+      "learning_rate": 7.230769230769231e-06,
+      "loss": 1.9841,
+      "step": 19
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 0.84403395652771,
+      "learning_rate": 7.076923076923078e-06,
+      "loss": 1.8984,
+      "step": 20
+    },
+    {
+      "epoch": 0.3230769230769231,
+      "grad_norm": 0.8170349597930908,
+      "learning_rate": 6.923076923076923e-06,
+      "loss": 1.9102,
+      "step": 21
+    },
+    {
+      "epoch": 0.3384615384615385,
+      "grad_norm": 0.8285540342330933,
+      "learning_rate": 6.76923076923077e-06,
+      "loss": 1.9854,
+      "step": 22
+    },
+    {
+      "epoch": 0.35384615384615387,
+      "grad_norm": 0.7774664759635925,
+      "learning_rate": 6.615384615384616e-06,
+      "loss": 1.9094,
+      "step": 23
+    },
+    {
+      "epoch": 0.36923076923076925,
+      "grad_norm": 0.7036376595497131,
+      "learning_rate": 6.461538461538463e-06,
+      "loss": 1.8627,
+      "step": 24
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 0.7108537554740906,
+      "learning_rate": 6.307692307692308e-06,
+      "loss": 1.8487,
+      "step": 25
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.7750827074050903,
+      "learning_rate": 6.153846153846155e-06,
+      "loss": 1.9931,
+      "step": 26
+    },
+    {
+      "epoch": 0.4153846153846154,
+      "grad_norm": 0.6978361010551453,
+      "learning_rate": 6e-06,
+      "loss": 1.8797,
+      "step": 27
+    },
+    {
+      "epoch": 0.4307692307692308,
+      "grad_norm": 0.6695581674575806,
+      "learning_rate": 5.846153846153847e-06,
+      "loss": 1.8452,
+      "step": 28
+    },
+    {
+      "epoch": 0.4461538461538462,
+      "grad_norm": 0.6637759208679199,
+      "learning_rate": 5.692307692307692e-06,
+      "loss": 1.8405,
+      "step": 29
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.6361680030822754,
+      "learning_rate": 5.538461538461539e-06,
+      "loss": 1.8006,
+      "step": 30
+    },
+    {
+      "epoch": 0.47692307692307695,
+      "grad_norm": 0.6240224838256836,
+      "learning_rate": 5.384615384615385e-06,
+      "loss": 1.8274,
+      "step": 31
+    },
+    {
+      "epoch": 0.49230769230769234,
+      "grad_norm": 0.6632691621780396,
+      "learning_rate": 5.230769230769232e-06,
+      "loss": 1.885,
+      "step": 32
+    },
+    {
+      "epoch": 0.5076923076923077,
+      "grad_norm": 0.5663037896156311,
+      "learning_rate": 5.076923076923077e-06,
+      "loss": 1.727,
+      "step": 33
+    },
+    {
+      "epoch": 0.5230769230769231,
+      "grad_norm": 0.6215487122535706,
+      "learning_rate": 4.923076923076924e-06,
+      "loss": 1.8381,
+      "step": 34
+    },
+    {
+      "epoch": 0.5384615384615384,
+      "grad_norm": 0.586870551109314,
+      "learning_rate": 4.76923076923077e-06,
+      "loss": 1.7795,
+      "step": 35
+    },
+    {
+      "epoch": 0.5538461538461539,
+      "grad_norm": 0.5890138149261475,
+      "learning_rate": 4.615384615384616e-06,
+      "loss": 1.8026,
+      "step": 36
+    },
+    {
+      "epoch": 0.5692307692307692,
+      "grad_norm": 0.6098945736885071,
+      "learning_rate": 4.461538461538462e-06,
+      "loss": 1.82,
+      "step": 37
+    },
+    {
+      "epoch": 0.5846153846153846,
+      "grad_norm": 0.5617942810058594,
+      "learning_rate": 4.307692307692308e-06,
+      "loss": 1.738,
+      "step": 38
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5747712254524231,
+      "learning_rate": 4.1538461538461545e-06,
+      "loss": 1.7913,
+      "step": 39
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.5543233752250671,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.7804,
+      "step": 40
+    },
+    {
+      "epoch": 0.6307692307692307,
+      "grad_norm": 0.6133182048797607,
+      "learning_rate": 3.846153846153847e-06,
+      "loss": 1.8595,
+      "step": 41
+    },
+    {
+      "epoch": 0.6461538461538462,
+      "grad_norm": 0.5437265038490295,
+      "learning_rate": 3.692307692307693e-06,
+      "loss": 1.7462,
+      "step": 42
+    },
+    {
+      "epoch": 0.6615384615384615,
+      "grad_norm": 0.5499180555343628,
+      "learning_rate": 3.538461538461539e-06,
+      "loss": 1.7903,
+      "step": 43
+    },
+    {
+      "epoch": 0.676923076923077,
+      "grad_norm": 0.5955756902694702,
+      "learning_rate": 3.384615384615385e-06,
+      "loss": 1.8104,
+      "step": 44
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 0.5310032367706299,
+      "learning_rate": 3.2307692307692313e-06,
+      "loss": 1.7232,
+      "step": 45
+    },
+    {
+      "epoch": 0.7076923076923077,
+      "grad_norm": 0.5088897943496704,
+      "learning_rate": 3.0769230769230774e-06,
+      "loss": 1.7128,
+      "step": 46
+    },
+    {
+      "epoch": 0.7230769230769231,
+      "grad_norm": 0.538586437702179,
+      "learning_rate": 2.9230769230769236e-06,
+      "loss": 1.7693,
+      "step": 47
+    },
+    {
+      "epoch": 0.7384615384615385,
+      "grad_norm": 0.5108963847160339,
+      "learning_rate": 2.7692307692307697e-06,
+      "loss": 1.6914,
+      "step": 48
+    },
+    {
+      "epoch": 0.7538461538461538,
+      "grad_norm": 0.5090144276618958,
+      "learning_rate": 2.615384615384616e-06,
+      "loss": 1.7045,
+      "step": 49
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.5341333746910095,
+      "learning_rate": 2.461538461538462e-06,
+      "loss": 1.7172,
+      "step": 50
+    },
+    {
+      "epoch": 0.7846153846153846,
+      "grad_norm": 0.5326001048088074,
+      "learning_rate": 2.307692307692308e-06,
+      "loss": 1.781,
+      "step": 51
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.5432034134864807,
+      "learning_rate": 2.153846153846154e-06,
+      "loss": 1.7552,
+      "step": 52
+    },
+    {
+      "epoch": 0.8153846153846154,
+      "grad_norm": 0.5758304595947266,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.8228,
+      "step": 53
+    },
+    {
+      "epoch": 0.8307692307692308,
+      "grad_norm": 0.5547528266906738,
+      "learning_rate": 1.8461538461538465e-06,
+      "loss": 1.7725,
+      "step": 54
+    },
+    {
+      "epoch": 0.8461538461538461,
+      "grad_norm": 0.5382564663887024,
+      "learning_rate": 1.6923076923076926e-06,
+      "loss": 1.7733,
+      "step": 55
+    },
+    {
+      "epoch": 0.8615384615384616,
+      "grad_norm": 0.4927564561367035,
+      "learning_rate": 1.5384615384615387e-06,
+      "loss": 1.7004,
+      "step": 56
+    },
+    {
+      "epoch": 0.8769230769230769,
+      "grad_norm": 0.5254544019699097,
+      "learning_rate": 1.3846153846153848e-06,
+      "loss": 1.7445,
+      "step": 57
+    },
+    {
+      "epoch": 0.8923076923076924,
+      "grad_norm": 0.5329279899597168,
+      "learning_rate": 1.230769230769231e-06,
+      "loss": 1.7431,
+      "step": 58
+    },
+    {
+      "epoch": 0.9076923076923077,
+      "grad_norm": 0.5610643625259399,
+      "learning_rate": 1.076923076923077e-06,
+      "loss": 1.8071,
+      "step": 59
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.49838006496429443,
+      "learning_rate": 9.230769230769232e-07,
+      "loss": 1.6605,
+      "step": 60
+    },
+    {
+      "epoch": 0.9384615384615385,
+      "grad_norm": 0.4859319031238556,
+      "learning_rate": 7.692307692307694e-07,
+      "loss": 1.677,
+      "step": 61
+    },
+    {
+      "epoch": 0.9538461538461539,
+      "grad_norm": 0.5223917365074158,
+      "learning_rate": 6.153846153846155e-07,
+      "loss": 1.7643,
+      "step": 62
+    },
+    {
+      "epoch": 0.9692307692307692,
+      "grad_norm": 0.5414427518844604,
+      "learning_rate": 4.615384615384616e-07,
+      "loss": 1.764,
+      "step": 63
+    },
+    {
+      "epoch": 0.9846153846153847,
+      "grad_norm": 0.503883421421051,
+      "learning_rate": 3.0769230769230774e-07,
+      "loss": 1.7021,
+      "step": 64
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5149479508399963,
+      "learning_rate": 1.5384615384615387e-07,
+      "loss": 1.7343,
+      "step": 65
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.7402640581130981,
+      "eval_runtime": 1.587,
+      "eval_samples_per_second": 20.794,
+      "eval_steps_per_second": 3.151,
+      "step": 65
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 65,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4688516889968640.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}