Add files using upload-large-folder tool

.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

Modelfile

@@ -0,0 +1,14 @@
+# ollama modelfile auto-generated by llamafactory
+
+FROM .
+
+TEMPLATE """{{ if .System }}<|im_start|>system
+{{ .System }}<|im_end|>
+{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<|im_start|>user
+{{ .Content }}<|im_end|>
+<|im_start|>assistant
+{{ else if eq .Role "assistant" }}{{ .Content }}<|im_end|>
+{{ end }}{{ end }}"""
+
+PARAMETER stop "<|im_end|>"
+PARAMETER num_ctx 4096

README.md

@@ -0,0 +1,118 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen3-32B
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: Qwen3-32B-alpaca-th-52k-dolly-th-15k-wangchan-instruct-seed-4201
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Qwen3-32B-alpaca-th-52k-dolly-th-15k-wangchan-instruct-seed-4201
+
+This model is a fine-tuned version of [Qwen/Qwen3-32B](https://huggingface.co//Qwen/Qwen3-32B) on the alpaca-th-52k, the dolly-th-15k and the wangchan-instruct datasets.
+It achieves the following results on the evaluation set:
+- Loss: 0.6413
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 4201
+- distributed_type: multi-GPU
+- num_devices: 32
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 512
+- total_eval_batch_size: 64
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9293        | 0.0575 | 10   | 1.0471          |
+| 0.8085        | 0.1149 | 20   | 0.8245          |
+| 0.7547        | 0.1724 | 30   | 0.7581          |
+| 0.7289        | 0.2299 | 40   | 0.7386          |
+| 0.6965        | 0.2874 | 50   | 0.7242          |
+| 0.6848        | 0.3448 | 60   | 0.7109          |
+| 0.693         | 0.4023 | 70   | 0.7022          |
+| 0.7101        | 0.4598 | 80   | 0.6947          |
+| 0.7293        | 0.5172 | 90   | 0.6888          |
+| 0.6852        | 0.5747 | 100  | 0.6822          |
+| 0.7033        | 0.6322 | 110  | 0.6770          |
+| 0.6815        | 0.6897 | 120  | 0.6736          |
+| 0.679         | 0.7471 | 130  | 0.6707          |
+| 0.6571        | 0.8046 | 140  | 0.6682          |
+| 0.6491        | 0.8621 | 150  | 0.6660          |
+| 0.7015        | 0.9195 | 160  | 0.6636          |
+| 0.6523        | 0.9770 | 170  | 0.6619          |
+| 0.6672        | 1.0345 | 180  | 0.6602          |
+| 0.6862        | 1.0920 | 190  | 0.6588          |
+| 0.6755        | 1.1494 | 200  | 0.6577          |
+| 0.6279        | 1.2069 | 210  | 0.6563          |
+| 0.6622        | 1.2644 | 220  | 0.6551          |
+| 0.6329        | 1.3218 | 230  | 0.6542          |
+| 0.6559        | 1.3793 | 240  | 0.6528          |
+| 0.6389        | 1.4368 | 250  | 0.6517          |
+| 0.6476        | 1.4943 | 260  | 0.6506          |
+| 0.6412        | 1.5517 | 270  | 0.6497          |
+| 0.6232        | 1.6092 | 280  | 0.6485          |
+| 0.6243        | 1.6667 | 290  | 0.6478          |
+| 0.6467        | 1.7241 | 300  | 0.6469          |
+| 0.6146        | 1.7816 | 310  | 0.6460          |
+| 0.6386        | 1.8391 | 320  | 0.6450          |
+| 0.6456        | 1.8966 | 330  | 0.6443          |
+| 0.6402        | 1.9540 | 340  | 0.6437          |
+| 0.6455        | 2.0115 | 350  | 0.6434          |
+| 0.5888        | 2.0690 | 360  | 0.6437          |
+| 0.6267        | 2.1264 | 370  | 0.6435          |
+| 0.6292        | 2.1839 | 380  | 0.6434          |
+| 0.6058        | 2.2414 | 390  | 0.6432          |
+| 0.6221        | 2.2989 | 400  | 0.6427          |
+| 0.6254        | 2.3563 | 410  | 0.6428          |
+| 0.6178        | 2.4138 | 420  | 0.6423          |
+| 0.6161        | 2.4713 | 430  | 0.6420          |
+| 0.634         | 2.5287 | 440  | 0.6419          |
+| 0.6241        | 2.5862 | 450  | 0.6418          |
+| 0.6084        | 2.6437 | 460  | 0.6416          |
+| 0.6264        | 2.7011 | 470  | 0.6415          |
+| 0.608         | 2.7586 | 480  | 0.6413          |
+| 0.6039        | 2.8161 | 490  | 0.6413          |
+| 0.6445        | 2.8736 | 500  | 0.6413          |
+| 0.6249        | 2.9310 | 510  | 0.6413          |
+| 0.6006        | 2.9885 | 520  | 0.6413          |
+
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.52.3
+- Pytorch 2.7.0+cu126
+- Datasets 3.6.0
+- Tokenizers 0.21.1

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/project/lt200252-wcbart/pumet/models/Qwen3-32B",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "v_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 sha256:453ebc8f5c1bea2bd1524f679458ecb8dcf688b79fb369961e2c028fc821299c
+size 268555264

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
+}

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.6412659883499146,
+    "eval_runtime": 413.4377,
+    "eval_samples_per_second": 23.941,
+    "eval_steps_per_second": 0.375,
+    "total_flos": 5.0940118456365744e+19,
+    "train_loss": 0.6584736234383565,
+    "train_runtime": 47270.2985,
+    "train_samples_per_second": 5.653,
+    "train_steps_per_second": 0.011
+}

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 %}

checkpoint-450/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /project/lt200252-wcbart/pumet/models/Qwen3-32B
+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

checkpoint-450/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/project/lt200252-wcbart/pumet/models/Qwen3-32B",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-450/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
+}

checkpoint-450/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 %}

checkpoint-450/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
+  }
+}

checkpoint-450/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
+}

checkpoint-450/trainer_state.json

@@ -0,0 +1,3544 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.586206896551724,
+  "eval_steps": 10,
+  "global_step": 450,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005747126436781609,
+      "grad_norm": 0.10123365372419357,
+      "learning_rate": 0.0,
+      "loss": 0.9918,
+      "step": 1
+    },
+    {
+      "epoch": 0.011494252873563218,
+      "grad_norm": 0.09671098738908768,
+      "learning_rate": 3.7735849056603773e-06,
+      "loss": 0.9604,
+      "step": 2
+    },
+    {
+      "epoch": 0.017241379310344827,
+      "grad_norm": 0.0981190875172615,
+      "learning_rate": 7.547169811320755e-06,
+      "loss": 0.9868,
+      "step": 3
+    },
+    {
+      "epoch": 0.022988505747126436,
+      "grad_norm": 0.10396745055913925,
+      "learning_rate": 1.1320754716981132e-05,
+      "loss": 0.962,
+      "step": 4
+    },
+    {
+      "epoch": 0.028735632183908046,
+      "grad_norm": 0.0982985869050026,
+      "learning_rate": 1.509433962264151e-05,
+      "loss": 0.9684,
+      "step": 5
+    },
+    {
+      "epoch": 0.034482758620689655,
+      "grad_norm": 0.10332155227661133,
+      "learning_rate": 1.8867924528301888e-05,
+      "loss": 0.9442,
+      "step": 6
+    },
+    {
+      "epoch": 0.040229885057471264,
+      "grad_norm": 0.1124059334397316,
+      "learning_rate": 2.2641509433962265e-05,
+      "loss": 0.9382,
+      "step": 7
+    },
+    {
+      "epoch": 0.04597701149425287,
+      "grad_norm": 0.12120208889245987,
+      "learning_rate": 2.641509433962264e-05,
+      "loss": 0.9416,
+      "step": 8
+    },
+    {
+      "epoch": 0.05172413793103448,
+      "grad_norm": 0.12729395925998688,
+      "learning_rate": 3.018867924528302e-05,
+      "loss": 0.9356,
+      "step": 9
+    },
+    {
+      "epoch": 0.05747126436781609,
+      "grad_norm": 0.13560789823532104,
+      "learning_rate": 3.39622641509434e-05,
+      "loss": 0.9293,
+      "step": 10
+    },
+    {
+      "epoch": 0.05747126436781609,
+      "eval_loss": 1.0470749139785767,
+      "eval_runtime": 412.2553,
+      "eval_samples_per_second": 24.009,
+      "eval_steps_per_second": 0.376,
+      "step": 10
+    },
+    {
+      "epoch": 0.06321839080459771,
+      "grad_norm": 0.1474100798368454,
+      "learning_rate": 3.7735849056603776e-05,
+      "loss": 0.9533,
+      "step": 11
+    },
+    {
+      "epoch": 0.06896551724137931,
+      "grad_norm": 0.16510824859142303,
+      "learning_rate": 4.150943396226415e-05,
+      "loss": 0.9206,
+      "step": 12
+    },
+    {
+      "epoch": 0.07471264367816093,
+      "grad_norm": 0.17097796499729156,
+      "learning_rate": 4.528301886792453e-05,
+      "loss": 0.8921,
+      "step": 13
+    },
+    {
+      "epoch": 0.08045977011494253,
+      "grad_norm": 0.17923878133296967,
+      "learning_rate": 4.9056603773584906e-05,
+      "loss": 0.8861,
+      "step": 14
+    },
+    {
+      "epoch": 0.08620689655172414,
+      "grad_norm": 0.18173959851264954,
+      "learning_rate": 5.283018867924528e-05,
+      "loss": 0.8904,
+      "step": 15
+    },
+    {
+      "epoch": 0.09195402298850575,
+      "grad_norm": 0.17235629260540009,
+      "learning_rate": 5.660377358490566e-05,
+      "loss": 0.8424,
+      "step": 16
+    },
+    {
+      "epoch": 0.09770114942528736,
+      "grad_norm": 0.16792210936546326,
+      "learning_rate": 6.037735849056604e-05,
+      "loss": 0.8395,
+      "step": 17
+    },
+    {
+      "epoch": 0.10344827586206896,
+      "grad_norm": 0.14939646422863007,
+      "learning_rate": 6.415094339622641e-05,
+      "loss": 0.8203,
+      "step": 18
+    },
+    {
+      "epoch": 0.10919540229885058,
+      "grad_norm": 0.14632105827331543,
+      "learning_rate": 6.79245283018868e-05,
+      "loss": 0.8464,
+      "step": 19
+    },
+    {
+      "epoch": 0.11494252873563218,
+      "grad_norm": 0.14770475029945374,
+      "learning_rate": 7.169811320754717e-05,
+      "loss": 0.8085,
+      "step": 20
+    },
+    {
+      "epoch": 0.11494252873563218,
+      "eval_loss": 0.8244547247886658,
+      "eval_runtime": 404.4489,
+      "eval_samples_per_second": 24.473,
+      "eval_steps_per_second": 0.383,
+      "step": 20
+    },
+    {
+      "epoch": 0.1206896551724138,
+      "grad_norm": 0.1725720465183258,
+      "learning_rate": 7.547169811320755e-05,
+      "loss": 0.8219,
+      "step": 21
+    },
+    {
+      "epoch": 0.12643678160919541,
+      "grad_norm": 0.1685618907213211,
+      "learning_rate": 7.924528301886794e-05,
+      "loss": 0.8148,
+      "step": 22
+    },
+    {
+      "epoch": 0.13218390804597702,
+      "grad_norm": 0.1653290092945099,
+      "learning_rate": 8.30188679245283e-05,
+      "loss": 0.7846,
+      "step": 23
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 0.16122524440288544,
+      "learning_rate": 8.679245283018869e-05,
+      "loss": 0.7903,
+      "step": 24
+    },
+    {
+      "epoch": 0.14367816091954022,
+      "grad_norm": 0.12793505191802979,
+      "learning_rate": 9.056603773584906e-05,
+      "loss": 0.7741,
+      "step": 25
+    },
+    {
+      "epoch": 0.14942528735632185,
+      "grad_norm": 0.10620377957820892,
+      "learning_rate": 9.433962264150944e-05,
+      "loss": 0.7308,
+      "step": 26
+    },
+    {
+      "epoch": 0.15517241379310345,
+      "grad_norm": 0.10993366688489914,
+      "learning_rate": 9.811320754716981e-05,
+      "loss": 0.7559,
+      "step": 27
+    },
+    {
+      "epoch": 0.16091954022988506,
+      "grad_norm": 0.11916384100914001,
+      "learning_rate": 0.0001018867924528302,
+      "loss": 0.7622,
+      "step": 28
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.13500399887561798,
+      "learning_rate": 0.00010566037735849057,
+      "loss": 0.7436,
+      "step": 29
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 0.12777844071388245,
+      "learning_rate": 0.00010943396226415095,
+      "loss": 0.7547,
+      "step": 30
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "eval_loss": 0.7580565214157104,
+      "eval_runtime": 404.708,
+      "eval_samples_per_second": 24.457,
+      "eval_steps_per_second": 0.383,
+      "step": 30
+    },
+    {
+      "epoch": 0.1781609195402299,
+      "grad_norm": 0.11721828579902649,
+      "learning_rate": 0.00011320754716981132,
+      "loss": 0.7337,
+      "step": 31
+    },
+    {
+      "epoch": 0.1839080459770115,
+      "grad_norm": 0.08667382597923279,
+      "learning_rate": 0.0001169811320754717,
+      "loss": 0.7538,
+      "step": 32
+    },
+    {
+      "epoch": 0.1896551724137931,
+      "grad_norm": 0.06665026396512985,
+      "learning_rate": 0.00012075471698113207,
+      "loss": 0.7186,
+      "step": 33
+    },
+    {
+      "epoch": 0.19540229885057472,
+      "grad_norm": 0.04627465456724167,
+      "learning_rate": 0.00012452830188679244,
+      "loss": 0.7719,
+      "step": 34
+    },
+    {
+      "epoch": 0.20114942528735633,
+      "grad_norm": 0.04290887340903282,
+      "learning_rate": 0.00012830188679245283,
+      "loss": 0.752,
+      "step": 35
+    },
+    {
+      "epoch": 0.20689655172413793,
+      "grad_norm": 0.056834809482097626,
+      "learning_rate": 0.0001320754716981132,
+      "loss": 0.7429,
+      "step": 36
+    },
+    {
+      "epoch": 0.21264367816091953,
+      "grad_norm": 0.062055498361587524,
+      "learning_rate": 0.0001358490566037736,
+      "loss": 0.7208,
+      "step": 37
+    },
+    {
+      "epoch": 0.21839080459770116,
+      "grad_norm": 0.070551298558712,
+      "learning_rate": 0.00013962264150943395,
+      "loss": 0.7651,
+      "step": 38
+    },
+    {
+      "epoch": 0.22413793103448276,
+      "grad_norm": 0.07514140754938126,
+      "learning_rate": 0.00014339622641509434,
+      "loss": 0.7456,
+      "step": 39
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "grad_norm": 0.06458627432584763,
+      "learning_rate": 0.00014716981132075472,
+      "loss": 0.7289,
+      "step": 40
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "eval_loss": 0.7386028170585632,
+      "eval_runtime": 407.409,
+      "eval_samples_per_second": 24.295,
+      "eval_steps_per_second": 0.38,
+      "step": 40
+    },
+    {
+      "epoch": 0.23563218390804597,
+      "grad_norm": 0.056490588933229446,
+      "learning_rate": 0.0001509433962264151,
+      "loss": 0.7503,
+      "step": 41
+    },
+    {
+      "epoch": 0.2413793103448276,
+      "grad_norm": 0.036972932517528534,
+      "learning_rate": 0.0001547169811320755,
+      "loss": 0.7392,
+      "step": 42
+    },
+    {
+      "epoch": 0.2471264367816092,
+      "grad_norm": 0.038239240646362305,
+      "learning_rate": 0.00015849056603773587,
+      "loss": 0.7206,
+      "step": 43
+    },
+    {
+      "epoch": 0.25287356321839083,
+      "grad_norm": 0.033113010227680206,
+      "learning_rate": 0.00016226415094339625,
+      "loss": 0.7198,
+      "step": 44
+    },
+    {
+      "epoch": 0.25862068965517243,
+      "grad_norm": 0.03197947517037392,
+      "learning_rate": 0.0001660377358490566,
+      "loss": 0.7393,
+      "step": 45
+    },
+    {
+      "epoch": 0.26436781609195403,
+      "grad_norm": 0.03696918115019798,
+      "learning_rate": 0.000169811320754717,
+      "loss": 0.7576,
+      "step": 46
+    },
+    {
+      "epoch": 0.27011494252873564,
+      "grad_norm": 0.04209383204579353,
+      "learning_rate": 0.00017358490566037738,
+      "loss": 0.7157,
+      "step": 47
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 0.035038772970438004,
+      "learning_rate": 0.00017735849056603776,
+      "loss": 0.7256,
+      "step": 48
+    },
+    {
+      "epoch": 0.28160919540229884,
+      "grad_norm": 0.03674735128879547,
+      "learning_rate": 0.00018113207547169812,
+      "loss": 0.7295,
+      "step": 49
+    },
+    {
+      "epoch": 0.28735632183908044,
+      "grad_norm": 0.046050041913986206,
+      "learning_rate": 0.0001849056603773585,
+      "loss": 0.6965,
+      "step": 50
+    },
+    {
+      "epoch": 0.28735632183908044,
+      "eval_loss": 0.724204421043396,
+      "eval_runtime": 405.0004,
+      "eval_samples_per_second": 24.439,
+      "eval_steps_per_second": 0.383,
+      "step": 50
+    },
+    {
+      "epoch": 0.29310344827586204,
+      "grad_norm": 0.036520447582006454,
+      "learning_rate": 0.00018867924528301889,
+      "loss": 0.7273,
+      "step": 51
+    },
+    {
+      "epoch": 0.2988505747126437,
+      "grad_norm": 0.03720232844352722,
+      "learning_rate": 0.00019245283018867927,
+      "loss": 0.7084,
+      "step": 52
+    },
+    {
+      "epoch": 0.3045977011494253,
+      "grad_norm": 0.03159736469388008,
+      "learning_rate": 0.00019622641509433963,
+      "loss": 0.7485,
+      "step": 53
+    },
+    {
+      "epoch": 0.3103448275862069,
+      "grad_norm": 0.03695262596011162,
+      "learning_rate": 0.0002,
+      "loss": 0.745,
+      "step": 54
+    },
+    {
+      "epoch": 0.3160919540229885,
+      "grad_norm": 0.041795678436756134,
+      "learning_rate": 0.00019999775651876987,
+      "loss": 0.7165,
+      "step": 55
+    },
+    {
+      "epoch": 0.3218390804597701,
+      "grad_norm": 0.03494727239012718,
+      "learning_rate": 0.00019999102617574365,
+      "loss": 0.7499,
+      "step": 56
+    },
+    {
+      "epoch": 0.3275862068965517,
+      "grad_norm": 0.033885981887578964,
+      "learning_rate": 0.00019997980927290927,
+      "loss": 0.7118,
+      "step": 57
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.03606434166431427,
+      "learning_rate": 0.00019996410631356498,
+      "loss": 0.6945,
+      "step": 58
+    },
+    {
+      "epoch": 0.3390804597701149,
+      "grad_norm": 0.04015219211578369,
+      "learning_rate": 0.00019994391800229666,
+      "loss": 0.6982,
+      "step": 59
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 0.0380714014172554,
+      "learning_rate": 0.00019991924524494627,
+      "loss": 0.6848,
+      "step": 60
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "eval_loss": 0.7109408378601074,
+      "eval_runtime": 404.9798,
+      "eval_samples_per_second": 24.441,
+      "eval_steps_per_second": 0.383,
+      "step": 60
+    },
+    {
+      "epoch": 0.3505747126436782,
+      "grad_norm": 0.04110811650753021,
+      "learning_rate": 0.00019989008914857116,
+      "loss": 0.6899,
+      "step": 61
+    },
+    {
+      "epoch": 0.3563218390804598,
+      "grad_norm": 0.03853503614664078,
+      "learning_rate": 0.0001998564510213944,
+      "loss": 0.7094,
+      "step": 62
+    },
+    {
+      "epoch": 0.3620689655172414,
+      "grad_norm": 0.0391794852912426,
+      "learning_rate": 0.00019981833237274618,
+      "loss": 0.6975,
+      "step": 63
+    },
+    {
+      "epoch": 0.367816091954023,
+      "grad_norm": 0.03894927725195885,
+      "learning_rate": 0.00019977573491299598,
+      "loss": 0.714,
+      "step": 64
+    },
+    {
+      "epoch": 0.3735632183908046,
+      "grad_norm": 0.04239923506975174,
+      "learning_rate": 0.00019972866055347572,
+      "loss": 0.7339,
+      "step": 65
+    },
+    {
+      "epoch": 0.3793103448275862,
+      "grad_norm": 0.03982697054743767,
+      "learning_rate": 0.0001996771114063943,
+      "loss": 0.6821,
+      "step": 66
+    },
+    {
+      "epoch": 0.3850574712643678,
+      "grad_norm": 0.04431302100419998,
+      "learning_rate": 0.00019962108978474263,
+      "loss": 0.7273,
+      "step": 67
+    },
+    {
+      "epoch": 0.39080459770114945,
+      "grad_norm": 0.043787937611341476,
+      "learning_rate": 0.00019956059820218982,
+      "loss": 0.6984,
+      "step": 68
+    },
+    {
+      "epoch": 0.39655172413793105,
+      "grad_norm": 0.054389603435993195,
+      "learning_rate": 0.00019949563937297045,
+      "loss": 0.6778,
+      "step": 69
+    },
+    {
+      "epoch": 0.40229885057471265,
+      "grad_norm": 0.041256386786699295,
+      "learning_rate": 0.00019942621621176282,
+      "loss": 0.693,
+      "step": 70
+    },
+    {
+      "epoch": 0.40229885057471265,
+      "eval_loss": 0.7021871209144592,
+      "eval_runtime": 406.6755,
+      "eval_samples_per_second": 24.339,
+      "eval_steps_per_second": 0.381,
+      "step": 70
+    },
+    {
+      "epoch": 0.40804597701149425,
+      "grad_norm": 0.05022790655493736,
+      "learning_rate": 0.0001993523318335581,
+      "loss": 0.6967,
+      "step": 71
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 0.06086933612823486,
+      "learning_rate": 0.00019927398955352061,
+      "loss": 0.7279,
+      "step": 72
+    },
+    {
+      "epoch": 0.41954022988505746,
+      "grad_norm": 0.04689742252230644,
+      "learning_rate": 0.00019919119288683908,
+      "loss": 0.6792,
+      "step": 73
+    },
+    {
+      "epoch": 0.42528735632183906,
+      "grad_norm": 0.04852883517742157,
+      "learning_rate": 0.00019910394554856876,
+      "loss": 0.701,
+      "step": 74
+    },
+    {
+      "epoch": 0.43103448275862066,
+      "grad_norm": 0.06196567416191101,
+      "learning_rate": 0.0001990122514534651,
+      "loss": 0.6805,
+      "step": 75
+    },
+    {
+      "epoch": 0.4367816091954023,
+      "grad_norm": 0.047033004462718964,
+      "learning_rate": 0.00019891611471580764,
+      "loss": 0.7058,
+      "step": 76
+    },
+    {
+      "epoch": 0.4425287356321839,
+      "grad_norm": 0.047392234206199646,
+      "learning_rate": 0.00019881553964921572,
+      "loss": 0.6861,
+      "step": 77
+    },
+    {
+      "epoch": 0.4482758620689655,
+      "grad_norm": 0.054070815443992615,
+      "learning_rate": 0.00019871053076645488,
+      "loss": 0.6969,
+      "step": 78
+    },
+    {
+      "epoch": 0.4540229885057471,
+      "grad_norm": 0.055412329733371735,
+      "learning_rate": 0.00019860109277923418,
+      "loss": 0.7001,
+      "step": 79
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "grad_norm": 0.05274376645684242,
+      "learning_rate": 0.00019848723059799506,
+      "loss": 0.7101,
+      "step": 80
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "eval_loss": 0.694656252861023,
+      "eval_runtime": 410.9173,
+      "eval_samples_per_second": 24.088,
+      "eval_steps_per_second": 0.377,
+      "step": 80
+    },
+    {
+      "epoch": 0.46551724137931033,
+      "grad_norm": 0.05915577709674835,
+      "learning_rate": 0.00019836894933169088,
+      "loss": 0.6836,
+      "step": 81
+    },
+    {
+      "epoch": 0.47126436781609193,
+      "grad_norm": 0.051574286073446274,
+      "learning_rate": 0.0001982462542875576,
+      "loss": 0.7181,
+      "step": 82
+    },
+    {
+      "epoch": 0.47701149425287354,
+      "grad_norm": 0.050167519599199295,
+      "learning_rate": 0.00019811915097087587,
+      "loss": 0.6645,
+      "step": 83
+    },
+    {
+      "epoch": 0.4827586206896552,
+      "grad_norm": 0.06501943618059158,
+      "learning_rate": 0.00019798764508472373,
+      "loss": 0.6891,
+      "step": 84
+    },
+    {
+      "epoch": 0.4885057471264368,
+      "grad_norm": 0.05396122857928276,
+      "learning_rate": 0.00019785174252972092,
+      "loss": 0.6842,
+      "step": 85
+    },
+    {
+      "epoch": 0.4942528735632184,
+      "grad_norm": 0.051826637238264084,
+      "learning_rate": 0.0001977114494037641,
+      "loss": 0.7047,
+      "step": 86
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.05442539602518082,
+      "learning_rate": 0.00019756677200175315,
+      "loss": 0.7261,
+      "step": 87
+    },
+    {
+      "epoch": 0.5057471264367817,
+      "grad_norm": 0.05559674650430679,
+      "learning_rate": 0.0001974177168153088,
+      "loss": 0.6699,
+      "step": 88
+    },
+    {
+      "epoch": 0.5114942528735632,
+      "grad_norm": 0.058047693222761154,
+      "learning_rate": 0.0001972642905324813,
+      "loss": 0.6831,
+      "step": 89
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 0.051893047988414764,
+      "learning_rate": 0.0001971065000374504,
+      "loss": 0.7293,
+      "step": 90
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "eval_loss": 0.6888386607170105,
+      "eval_runtime": 405.4362,
+      "eval_samples_per_second": 24.413,
+      "eval_steps_per_second": 0.382,
+      "step": 90
+    },
+    {
+      "epoch": 0.5229885057471264,
+      "grad_norm": 0.051870737224817276,
+      "learning_rate": 0.0001969443524102163,
+      "loss": 0.6945,
+      "step": 91
+    },
+    {
+      "epoch": 0.5287356321839081,
+      "grad_norm": 0.04907568544149399,
+      "learning_rate": 0.0001967778549262822,
+      "loss": 0.6985,
+      "step": 92
+    },
+    {
+      "epoch": 0.5344827586206896,
+      "grad_norm": 0.05802120640873909,
+      "learning_rate": 0.00019660701505632772,
+      "loss": 0.6911,
+      "step": 93
+    },
+    {
+      "epoch": 0.5402298850574713,
+      "grad_norm": 0.06809733808040619,
+      "learning_rate": 0.0001964318404658737,
+      "loss": 0.6815,
+      "step": 94
+    },
+    {
+      "epoch": 0.5459770114942529,
+      "grad_norm": 0.05489501729607582,
+      "learning_rate": 0.00019625233901493822,
+      "loss": 0.6664,
+      "step": 95
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 0.0648936778306961,
+      "learning_rate": 0.000196068518757684,
+      "loss": 0.6689,
+      "step": 96
+    },
+    {
+      "epoch": 0.5574712643678161,
+      "grad_norm": 0.054548367857933044,
+      "learning_rate": 0.00019588038794205703,
+      "loss": 0.6695,
+      "step": 97
+    },
+    {
+      "epoch": 0.5632183908045977,
+      "grad_norm": 0.0626642182469368,
+      "learning_rate": 0.00019568795500941635,
+      "loss": 0.7062,
+      "step": 98
+    },
+    {
+      "epoch": 0.5689655172413793,
+      "grad_norm": 0.0539688840508461,
+      "learning_rate": 0.00019549122859415538,
+      "loss": 0.6891,
+      "step": 99
+    },
+    {
+      "epoch": 0.5747126436781609,
+      "grad_norm": 0.05761811137199402,
+      "learning_rate": 0.00019529021752331453,
+      "loss": 0.6852,
+      "step": 100
+    },
+    {
+      "epoch": 0.5747126436781609,
+      "eval_loss": 0.6821601986885071,
+      "eval_runtime": 404.287,
+      "eval_samples_per_second": 24.483,
+      "eval_steps_per_second": 0.383,
+      "step": 100
+    },
+    {
+      "epoch": 0.5804597701149425,
+      "grad_norm": 0.054896607995033264,
+      "learning_rate": 0.00019508493081618513,
+      "loss": 0.6785,
+      "step": 101
+    },
+    {
+      "epoch": 0.5862068965517241,
+      "grad_norm": 0.06048964709043503,
+      "learning_rate": 0.00019487537768390464,
+      "loss": 0.6724,
+      "step": 102
+    },
+    {
+      "epoch": 0.5919540229885057,
+      "grad_norm": 0.06828396022319794,
+      "learning_rate": 0.00019466156752904343,
+      "loss": 0.7117,
+      "step": 103
+    },
+    {
+      "epoch": 0.5977011494252874,
+      "grad_norm": 0.06610234081745148,
+      "learning_rate": 0.0001944435099451829,
+      "loss": 0.6982,
+      "step": 104
+    },
+    {
+      "epoch": 0.603448275862069,
+      "grad_norm": 0.06762486696243286,
+      "learning_rate": 0.00019422121471648497,
+      "loss": 0.6768,
+      "step": 105
+    },
+    {
+      "epoch": 0.6091954022988506,
+      "grad_norm": 0.05772867798805237,
+      "learning_rate": 0.0001939946918172531,
+      "loss": 0.7073,
+      "step": 106
+    },
+    {
+      "epoch": 0.6149425287356322,
+      "grad_norm": 0.11993183940649033,
+      "learning_rate": 0.00019376395141148476,
+      "loss": 0.6831,
+      "step": 107
+    },
+    {
+      "epoch": 0.6206896551724138,
+      "grad_norm": 0.08105713874101639,
+      "learning_rate": 0.00019352900385241536,
+      "loss": 0.6857,
+      "step": 108
+    },
+    {
+      "epoch": 0.6264367816091954,
+      "grad_norm": 0.06035466492176056,
+      "learning_rate": 0.0001932898596820536,
+      "loss": 0.672,
+      "step": 109
+    },
+    {
+      "epoch": 0.632183908045977,
+      "grad_norm": 0.09288731962442398,
+      "learning_rate": 0.0001930465296307087,
+      "loss": 0.7033,
+      "step": 110
+    },
+    {
+      "epoch": 0.632183908045977,
+      "eval_loss": 0.677044153213501,
+      "eval_runtime": 405.2323,
+      "eval_samples_per_second": 24.425,
+      "eval_steps_per_second": 0.382,
+      "step": 110
+    },
+    {
+      "epoch": 0.6379310344827587,
+      "grad_norm": 0.06630638986825943,
+      "learning_rate": 0.00019279902461650866,
+      "loss": 0.6831,
+      "step": 111
+    },
+    {
+      "epoch": 0.6436781609195402,
+      "grad_norm": 0.05605092644691467,
+      "learning_rate": 0.00019254735574491058,
+      "loss": 0.6654,
+      "step": 112
+    },
+    {
+      "epoch": 0.6494252873563219,
+      "grad_norm": 0.07270795851945877,
+      "learning_rate": 0.00019229153430820232,
+      "loss": 0.6744,
+      "step": 113
+    },
+    {
+      "epoch": 0.6551724137931034,
+      "grad_norm": 0.06772006303071976,
+      "learning_rate": 0.0001920315717849956,
+      "loss": 0.6833,
+      "step": 114
+    },
+    {
+      "epoch": 0.6609195402298851,
+      "grad_norm": 0.06296226382255554,
+      "learning_rate": 0.0001917674798397113,
+      "loss": 0.677,
+      "step": 115
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.06553810834884644,
+      "learning_rate": 0.00019149927032205587,
+      "loss": 0.6828,
+      "step": 116
+    },
+    {
+      "epoch": 0.6724137931034483,
+      "grad_norm": 0.057245928794145584,
+      "learning_rate": 0.00019122695526648968,
+      "loss": 0.6858,
+      "step": 117
+    },
+    {
+      "epoch": 0.6781609195402298,
+      "grad_norm": 0.06503669917583466,
+      "learning_rate": 0.00019095054689168705,
+      "loss": 0.6591,
+      "step": 118
+    },
+    {
+      "epoch": 0.6839080459770115,
+      "grad_norm": 0.05912588909268379,
+      "learning_rate": 0.00019067005759998797,
+      "loss": 0.6669,
+      "step": 119
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.06517963111400604,
+      "learning_rate": 0.0001903854999768417,
+      "loss": 0.6815,
+      "step": 120
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "eval_loss": 0.6735538244247437,
+      "eval_runtime": 405.8319,
+      "eval_samples_per_second": 24.389,
+      "eval_steps_per_second": 0.382,
+      "step": 120
+    },
+    {
+      "epoch": 0.6954022988505747,
+      "grad_norm": 0.06089121848344803,
+      "learning_rate": 0.0001900968867902419,
+      "loss": 0.67,
+      "step": 121
+    },
+    {
+      "epoch": 0.7011494252873564,
+      "grad_norm": 0.05764375999569893,
+      "learning_rate": 0.00018980423099015402,
+      "loss": 0.6733,
+      "step": 122
+    },
+    {
+      "epoch": 0.7068965517241379,
+      "grad_norm": 0.06278955936431885,
+      "learning_rate": 0.00018950754570793384,
+      "loss": 0.6702,
+      "step": 123
+    },
+    {
+      "epoch": 0.7126436781609196,
+      "grad_norm": 0.06360521912574768,
+      "learning_rate": 0.00018920684425573865,
+      "loss": 0.6619,
+      "step": 124
+    },
+    {
+      "epoch": 0.7183908045977011,
+      "grad_norm": 0.0599365159869194,
+      "learning_rate": 0.00018890214012592975,
+      "loss": 0.6851,
+      "step": 125
+    },
+    {
+      "epoch": 0.7241379310344828,
+      "grad_norm": 0.061885766685009,
+      "learning_rate": 0.000188593446990467,
+      "loss": 0.6346,
+      "step": 126
+    },
+    {
+      "epoch": 0.7298850574712644,
+      "grad_norm": 0.061761509627103806,
+      "learning_rate": 0.00018828077870029552,
+      "loss": 0.6834,
+      "step": 127
+    },
+    {
+      "epoch": 0.735632183908046,
+      "grad_norm": 0.075982965528965,
+      "learning_rate": 0.00018796414928472417,
+      "loss": 0.6279,
+      "step": 128
+    },
+    {
+      "epoch": 0.7413793103448276,
+      "grad_norm": 0.05802853778004646,
+      "learning_rate": 0.0001876435729507959,
+      "loss": 0.6348,
+      "step": 129
+    },
+    {
+      "epoch": 0.7471264367816092,
+      "grad_norm": 0.06642711162567139,
+      "learning_rate": 0.0001873190640826505,
+      "loss": 0.679,
+      "step": 130
+    },
+    {
+      "epoch": 0.7471264367816092,
+      "eval_loss": 0.6707044243812561,
+      "eval_runtime": 407.4212,
+      "eval_samples_per_second": 24.294,
+      "eval_steps_per_second": 0.38,
+      "step": 130
+    },
+    {
+      "epoch": 0.7528735632183908,
+      "grad_norm": 0.06452522426843643,
+      "learning_rate": 0.00018699063724087904,
+      "loss": 0.6423,
+      "step": 131
+    },
+    {
+      "epoch": 0.7586206896551724,
+      "grad_norm": 0.05988775193691254,
+      "learning_rate": 0.00018665830716187065,
+      "loss": 0.6654,
+      "step": 132
+    },
+    {
+      "epoch": 0.764367816091954,
+      "grad_norm": 0.059349820017814636,
+      "learning_rate": 0.0001863220887571512,
+      "loss": 0.6866,
+      "step": 133
+    },
+    {
+      "epoch": 0.7701149425287356,
+      "grad_norm": 0.06473397463560104,
+      "learning_rate": 0.0001859819971127143,
+      "loss": 0.7014,
+      "step": 134
+    },
+    {
+      "epoch": 0.7758620689655172,
+      "grad_norm": 0.06945810467004776,
+      "learning_rate": 0.00018563804748834438,
+      "loss": 0.6769,
+      "step": 135
+    },
+    {
+      "epoch": 0.7816091954022989,
+      "grad_norm": 0.06217830255627632,
+      "learning_rate": 0.000185290255316932,
+      "loss": 0.6821,
+      "step": 136
+    },
+    {
+      "epoch": 0.7873563218390804,
+      "grad_norm": 0.07021711021661758,
+      "learning_rate": 0.00018493863620378122,
+      "loss": 0.6614,
+      "step": 137
+    },
+    {
+      "epoch": 0.7931034482758621,
+      "grad_norm": 0.0640297532081604,
+      "learning_rate": 0.00018458320592590975,
+      "loss": 0.6699,
+      "step": 138
+    },
+    {
+      "epoch": 0.7988505747126436,
+      "grad_norm": 0.0640842542052269,
+      "learning_rate": 0.00018422398043134067,
+      "loss": 0.6795,
+      "step": 139
+    },
+    {
+      "epoch": 0.8045977011494253,
+      "grad_norm": 0.07371507585048676,
+      "learning_rate": 0.00018386097583838714,
+      "loss": 0.6571,
+      "step": 140
+    },
+    {
+      "epoch": 0.8045977011494253,
+      "eval_loss": 0.6682229042053223,
+      "eval_runtime": 404.8694,
+      "eval_samples_per_second": 24.447,
+      "eval_steps_per_second": 0.383,
+      "step": 140
+    },
+    {
+      "epoch": 0.8103448275862069,
+      "grad_norm": 0.06185011938214302,
+      "learning_rate": 0.00018349420843492888,
+      "loss": 0.6524,
+      "step": 141
+    },
+    {
+      "epoch": 0.8160919540229885,
+      "grad_norm": 0.08427827060222626,
+      "learning_rate": 0.00018312369467768166,
+      "loss": 0.6685,
+      "step": 142
+    },
+    {
+      "epoch": 0.8218390804597702,
+      "grad_norm": 0.06529568880796432,
+      "learning_rate": 0.0001827494511914587,
+      "loss": 0.659,
+      "step": 143
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 0.07357680797576904,
+      "learning_rate": 0.0001823714947684247,
+      "loss": 0.6792,
+      "step": 144
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.09026575833559036,
+      "learning_rate": 0.00018198984236734246,
+      "loss": 0.6954,
+      "step": 145
+    },
+    {
+      "epoch": 0.8390804597701149,
+      "grad_norm": 0.06157710403203964,
+      "learning_rate": 0.000181604511112812,
+      "loss": 0.6527,
+      "step": 146
+    },
+    {
+      "epoch": 0.8448275862068966,
+      "grad_norm": 0.08122924715280533,
+      "learning_rate": 0.000181215518294502,
+      "loss": 0.6571,
+      "step": 147
+    },
+    {
+      "epoch": 0.8505747126436781,
+      "grad_norm": 0.05926045402884483,
+      "learning_rate": 0.00018082288136637422,
+      "loss": 0.6773,
+      "step": 148
+    },
+    {
+      "epoch": 0.8563218390804598,
+      "grad_norm": 0.07869191467761993,
+      "learning_rate": 0.00018042661794590023,
+      "loss": 0.7066,
+      "step": 149
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 0.07564139366149902,
+      "learning_rate": 0.00018002674581327094,
+      "loss": 0.6491,
+      "step": 150
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "eval_loss": 0.6660047769546509,
+      "eval_runtime": 406.5581,
+      "eval_samples_per_second": 24.346,
+      "eval_steps_per_second": 0.381,
+      "step": 150
+    },
+    {
+      "epoch": 0.867816091954023,
+      "grad_norm": 0.05749671533703804,
+      "learning_rate": 0.00017962328291059888,
+      "loss": 0.7081,
+      "step": 151
+    },
+    {
+      "epoch": 0.8735632183908046,
+      "grad_norm": 0.08154609054327011,
+      "learning_rate": 0.00017921624734111292,
+      "loss": 0.6622,
+      "step": 152
+    },
+    {
+      "epoch": 0.8793103448275862,
+      "grad_norm": 0.08773736655712128,
+      "learning_rate": 0.0001788056573683464,
+      "loss": 0.6393,
+      "step": 153
+    },
+    {
+      "epoch": 0.8850574712643678,
+      "grad_norm": 0.06756340712308884,
+      "learning_rate": 0.00017839153141531718,
+      "loss": 0.6384,
+      "step": 154
+    },
+    {
+      "epoch": 0.8908045977011494,
+      "grad_norm": 0.08763930201530457,
+      "learning_rate": 0.00017797388806370132,
+      "loss": 0.6512,
+      "step": 155
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 0.0647486001253128,
+      "learning_rate": 0.00017755274605299923,
+      "loss": 0.6502,
+      "step": 156
+    },
+    {
+      "epoch": 0.9022988505747126,
+      "grad_norm": 0.11679747700691223,
+      "learning_rate": 0.00017712812427969485,
+      "loss": 0.6666,
+      "step": 157
+    },
+    {
+      "epoch": 0.9080459770114943,
+      "grad_norm": 0.06472433358430862,
+      "learning_rate": 0.00017670004179640774,
+      "loss": 0.6495,
+      "step": 158
+    },
+    {
+      "epoch": 0.9137931034482759,
+      "grad_norm": 0.09902803599834442,
+      "learning_rate": 0.0001762685178110382,
+      "loss": 0.6747,
+      "step": 159
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 0.06362438946962357,
+      "learning_rate": 0.0001758335716859055,
+      "loss": 0.7015,
+      "step": 160
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "eval_loss": 0.663636326789856,
+      "eval_runtime": 404.5915,
+      "eval_samples_per_second": 24.464,
+      "eval_steps_per_second": 0.383,
+      "step": 160
+    },
+    {
+      "epoch": 0.9252873563218391,
+      "grad_norm": 0.07304941862821579,
+      "learning_rate": 0.00017539522293687898,
+      "loss": 0.6825,
+      "step": 161
+    },
+    {
+      "epoch": 0.9310344827586207,
+      "grad_norm": 0.08923015743494034,
+      "learning_rate": 0.00017495349123250242,
+      "loss": 0.674,
+      "step": 162
+    },
+    {
+      "epoch": 0.9367816091954023,
+      "grad_norm": 0.062135376036167145,
+      "learning_rate": 0.00017450839639311162,
+      "loss": 0.6477,
+      "step": 163
+    },
+    {
+      "epoch": 0.9425287356321839,
+      "grad_norm": 0.1098598912358284,
+      "learning_rate": 0.00017405995838994494,
+      "loss": 0.6742,
+      "step": 164
+    },
+    {
+      "epoch": 0.9482758620689655,
+      "grad_norm": 0.06947540491819382,
+      "learning_rate": 0.00017360819734424715,
+      "loss": 0.6509,
+      "step": 165
+    },
+    {
+      "epoch": 0.9540229885057471,
+      "grad_norm": 0.11134368181228638,
+      "learning_rate": 0.0001731531335263669,
+      "loss": 0.6602,
+      "step": 166
+    },
+    {
+      "epoch": 0.9597701149425287,
+      "grad_norm": 0.06717904657125473,
+      "learning_rate": 0.00017269478735484683,
+      "loss": 0.6697,
+      "step": 167
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 0.06737629324197769,
+      "learning_rate": 0.00017223317939550753,
+      "loss": 0.6636,
+      "step": 168
+    },
+    {
+      "epoch": 0.9712643678160919,
+      "grad_norm": 0.08558724075555801,
+      "learning_rate": 0.00017176833036052495,
+      "loss": 0.6733,
+      "step": 169
+    },
+    {
+      "epoch": 0.9770114942528736,
+      "grad_norm": 0.07127804309129715,
+      "learning_rate": 0.0001713002611075007,
+      "loss": 0.6523,
+      "step": 170
+    },
+    {
+      "epoch": 0.9770114942528736,
+      "eval_loss": 0.6618800759315491,
+      "eval_runtime": 411.375,
+      "eval_samples_per_second": 24.061,
+      "eval_steps_per_second": 0.377,
+      "step": 170
+    },
+    {
+      "epoch": 0.9827586206896551,
+      "grad_norm": 0.08060283958911896,
+      "learning_rate": 0.0001708289926385265,
+      "loss": 0.658,
+      "step": 171
+    },
+    {
+      "epoch": 0.9885057471264368,
+      "grad_norm": 0.06496579200029373,
+      "learning_rate": 0.0001703545460992416,
+      "loss": 0.6697,
+      "step": 172
+    },
+    {
+      "epoch": 0.9942528735632183,
+      "grad_norm": 0.0646037757396698,
+      "learning_rate": 0.00016987694277788417,
+      "loss": 0.6231,
+      "step": 173
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.08516079187393188,
+      "learning_rate": 0.0001693962041043359,
+      "loss": 0.6374,
+      "step": 174
+    },
+    {
+      "epoch": 1.0057471264367817,
+      "grad_norm": 0.06554190069437027,
+      "learning_rate": 0.00016891235164916065,
+      "loss": 0.6271,
+      "step": 175
+    },
+    {
+      "epoch": 1.0114942528735633,
+      "grad_norm": 0.06361629068851471,
+      "learning_rate": 0.00016842540712263637,
+      "loss": 0.649,
+      "step": 176
+    },
+    {
+      "epoch": 1.0172413793103448,
+      "grad_norm": 0.0814083069562912,
+      "learning_rate": 0.00016793539237378128,
+      "loss": 0.654,
+      "step": 177
+    },
+    {
+      "epoch": 1.0229885057471264,
+      "grad_norm": 0.06498701125383377,
+      "learning_rate": 0.00016744232938937308,
+      "loss": 0.6313,
+      "step": 178
+    },
+    {
+      "epoch": 1.028735632183908,
+      "grad_norm": 0.11292543262243271,
+      "learning_rate": 0.0001669462402929629,
+      "loss": 0.6803,
+      "step": 179
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 0.0661187544465065,
+      "learning_rate": 0.00016644714734388217,
+      "loss": 0.6672,
+      "step": 180
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "eval_loss": 0.6602174043655396,
+      "eval_runtime": 410.2914,
+      "eval_samples_per_second": 24.124,
+      "eval_steps_per_second": 0.378,
+      "step": 180
+    },
+    {
+      "epoch": 1.0402298850574712,
+      "grad_norm": 0.08441785722970963,
+      "learning_rate": 0.00016594507293624425,
+      "loss": 0.6257,
+      "step": 181
+    },
+    {
+      "epoch": 1.0459770114942528,
+      "grad_norm": 0.09075969457626343,
+      "learning_rate": 0.00016544003959793925,
+      "loss": 0.641,
+      "step": 182
+    },
+    {
+      "epoch": 1.0517241379310345,
+      "grad_norm": 0.07677901536226273,
+      "learning_rate": 0.00016493206998962354,
+      "loss": 0.6351,
+      "step": 183
+    },
+    {
+      "epoch": 1.0574712643678161,
+      "grad_norm": 0.09646302461624146,
+      "learning_rate": 0.0001644211869037027,
+      "loss": 0.6635,
+      "step": 184
+    },
+    {
+      "epoch": 1.0632183908045978,
+      "grad_norm": 0.06928115338087082,
+      "learning_rate": 0.00016390741326330907,
+      "loss": 0.6458,
+      "step": 185
+    },
+    {
+      "epoch": 1.0689655172413792,
+      "grad_norm": 0.1076992079615593,
+      "learning_rate": 0.00016339077212127294,
+      "loss": 0.6209,
+      "step": 186
+    },
+    {
+      "epoch": 1.0747126436781609,
+      "grad_norm": 0.08489565551280975,
+      "learning_rate": 0.0001628712866590885,
+      "loss": 0.6336,
+      "step": 187
+    },
+    {
+      "epoch": 1.0804597701149425,
+      "grad_norm": 0.11920158565044403,
+      "learning_rate": 0.00016234898018587337,
+      "loss": 0.6496,
+      "step": 188
+    },
+    {
+      "epoch": 1.0862068965517242,
+      "grad_norm": 0.07987701892852783,
+      "learning_rate": 0.00016182387613732291,
+      "loss": 0.668,
+      "step": 189
+    },
+    {
+      "epoch": 1.0919540229885056,
+      "grad_norm": 0.1095438227057457,
+      "learning_rate": 0.00016129599807465875,
+      "loss": 0.6862,
+      "step": 190
+    },
+    {
+      "epoch": 1.0919540229885056,
+      "eval_loss": 0.6588147282600403,
+      "eval_runtime": 406.5115,
+      "eval_samples_per_second": 24.349,
+      "eval_steps_per_second": 0.381,
+      "step": 190
+    },
+    {
+      "epoch": 1.0977011494252873,
+      "grad_norm": 0.08076825737953186,
+      "learning_rate": 0.0001607653696835713,
+      "loss": 0.6367,
+      "step": 191
+    },
+    {
+      "epoch": 1.103448275862069,
+      "grad_norm": 0.09829648584127426,
+      "learning_rate": 0.00016023201477315731,
+      "loss": 0.6391,
+      "step": 192
+    },
+    {
+      "epoch": 1.1091954022988506,
+      "grad_norm": 0.09008080512285233,
+      "learning_rate": 0.0001596959572748514,
+      "loss": 0.6462,
+      "step": 193
+    },
+    {
+      "epoch": 1.1149425287356323,
+      "grad_norm": 0.07725552469491959,
+      "learning_rate": 0.00015915722124135227,
+      "loss": 0.6356,
+      "step": 194
+    },
+    {
+      "epoch": 1.1206896551724137,
+      "grad_norm": 0.08215273171663284,
+      "learning_rate": 0.00015861583084554349,
+      "loss": 0.6557,
+      "step": 195
+    },
+    {
+      "epoch": 1.1264367816091954,
+      "grad_norm": 0.07044622302055359,
+      "learning_rate": 0.0001580718103794089,
+      "loss": 0.6401,
+      "step": 196
+    },
+    {
+      "epoch": 1.132183908045977,
+      "grad_norm": 0.06852877885103226,
+      "learning_rate": 0.00015752518425294257,
+      "loss": 0.6641,
+      "step": 197
+    },
+    {
+      "epoch": 1.1379310344827587,
+      "grad_norm": 0.07775932550430298,
+      "learning_rate": 0.00015697597699305366,
+      "loss": 0.6689,
+      "step": 198
+    },
+    {
+      "epoch": 1.1436781609195403,
+      "grad_norm": 0.07384389638900757,
+      "learning_rate": 0.00015642421324246568,
+      "loss": 0.663,
+      "step": 199
+    },
+    {
+      "epoch": 1.1494252873563218,
+      "grad_norm": 0.074593685567379,
+      "learning_rate": 0.00015586991775861102,
+      "loss": 0.6755,
+      "step": 200
+    },
+    {
+      "epoch": 1.1494252873563218,
+      "eval_loss": 0.6577329635620117,
+      "eval_runtime": 406.5534,
+      "eval_samples_per_second": 24.346,
+      "eval_steps_per_second": 0.381,
+      "step": 200
+    },
+    {
+      "epoch": 1.1551724137931034,
+      "grad_norm": 0.07201389968395233,
+      "learning_rate": 0.00015531311541251995,
+      "loss": 0.62,
+      "step": 201
+    },
+    {
+      "epoch": 1.160919540229885,
+      "grad_norm": 0.07052464783191681,
+      "learning_rate": 0.00015475383118770472,
+      "loss": 0.6456,
+      "step": 202
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 0.07045558094978333,
+      "learning_rate": 0.00015419209017903852,
+      "loss": 0.6421,
+      "step": 203
+    },
+    {
+      "epoch": 1.1724137931034484,
+      "grad_norm": 0.0870729386806488,
+      "learning_rate": 0.0001536279175916296,
+      "loss": 0.6342,
+      "step": 204
+    },
+    {
+      "epoch": 1.1781609195402298,
+      "grad_norm": 0.0703926831483841,
+      "learning_rate": 0.0001530613387396901,
+      "loss": 0.6533,
+      "step": 205
+    },
+    {
+      "epoch": 1.1839080459770115,
+      "grad_norm": 0.07181324064731598,
+      "learning_rate": 0.0001524923790454004,
+      "loss": 0.6511,
+      "step": 206
+    },
+    {
+      "epoch": 1.1896551724137931,
+      "grad_norm": 0.07455940544605255,
+      "learning_rate": 0.00015192106403776848,
+      "loss": 0.6363,
+      "step": 207
+    },
+    {
+      "epoch": 1.1954022988505748,
+      "grad_norm": 0.08370154350996017,
+      "learning_rate": 0.0001513474193514842,
+      "loss": 0.6517,
+      "step": 208
+    },
+    {
+      "epoch": 1.2011494252873562,
+      "grad_norm": 0.08015818893909454,
+      "learning_rate": 0.00015077147072576933,
+      "loss": 0.6264,
+      "step": 209
+    },
+    {
+      "epoch": 1.206896551724138,
+      "grad_norm": 0.093206986784935,
+      "learning_rate": 0.00015019324400322243,
+      "loss": 0.6279,
+      "step": 210
+    },
+    {
+      "epoch": 1.206896551724138,
+      "eval_loss": 0.6562607884407043,
+      "eval_runtime": 407.9222,
+      "eval_samples_per_second": 24.264,
+      "eval_steps_per_second": 0.38,
+      "step": 210
+    },
+    {
+      "epoch": 1.2126436781609196,
+      "grad_norm": 0.07707002758979797,
+      "learning_rate": 0.00014961276512865954,
+      "loss": 0.6726,
+      "step": 211
+    },
+    {
+      "epoch": 1.2183908045977012,
+      "grad_norm": 0.08275868743658066,
+      "learning_rate": 0.00014903006014794983,
+      "loss": 0.6493,
+      "step": 212
+    },
+    {
+      "epoch": 1.2241379310344827,
+      "grad_norm": 0.11222587525844574,
+      "learning_rate": 0.00014844515520684703,
+      "loss": 0.6367,
+      "step": 213
+    },
+    {
+      "epoch": 1.2298850574712643,
+      "grad_norm": 0.09210342168807983,
+      "learning_rate": 0.00014785807654981627,
+      "loss": 0.6734,
+      "step": 214
+    },
+    {
+      "epoch": 1.235632183908046,
+      "grad_norm": 0.08821109682321548,
+      "learning_rate": 0.00014726885051885653,
+      "loss": 0.6354,
+      "step": 215
+    },
+    {
+      "epoch": 1.2413793103448276,
+      "grad_norm": 0.12253956496715546,
+      "learning_rate": 0.0001466775035523186,
+      "loss": 0.6412,
+      "step": 216
+    },
+    {
+      "epoch": 1.2471264367816093,
+      "grad_norm": 0.08476684242486954,
+      "learning_rate": 0.00014608406218371894,
+      "loss": 0.6635,
+      "step": 217
+    },
+    {
+      "epoch": 1.2528735632183907,
+      "grad_norm": 0.08554086089134216,
+      "learning_rate": 0.00014548855304054886,
+      "loss": 0.6403,
+      "step": 218
+    },
+    {
+      "epoch": 1.2586206896551724,
+      "grad_norm": 0.10986476391553879,
+      "learning_rate": 0.00014489100284308017,
+      "loss": 0.6253,
+      "step": 219
+    },
+    {
+      "epoch": 1.264367816091954,
+      "grad_norm": 0.09221742302179337,
+      "learning_rate": 0.00014429143840316585,
+      "loss": 0.6622,
+      "step": 220
+    },
+    {
+      "epoch": 1.264367816091954,
+      "eval_loss": 0.6551185250282288,
+      "eval_runtime": 408.2025,
+      "eval_samples_per_second": 24.248,
+      "eval_steps_per_second": 0.38,
+      "step": 220
+    },
+    {
+      "epoch": 1.2701149425287357,
+      "grad_norm": 0.08050013333559036,
+      "learning_rate": 0.00014368988662303732,
+      "loss": 0.6226,
+      "step": 221
+    },
+    {
+      "epoch": 1.2758620689655173,
+      "grad_norm": 0.16257594525814056,
+      "learning_rate": 0.00014308637449409706,
+      "loss": 0.6661,
+      "step": 222
+    },
+    {
+      "epoch": 1.2816091954022988,
+      "grad_norm": 0.07793809473514557,
+      "learning_rate": 0.00014248092909570774,
+      "loss": 0.6243,
+      "step": 223
+    },
+    {
+      "epoch": 1.2873563218390804,
+      "grad_norm": 0.0975632593035698,
+      "learning_rate": 0.00014187357759397714,
+      "loss": 0.6348,
+      "step": 224
+    },
+    {
+      "epoch": 1.293103448275862,
+      "grad_norm": 0.07041144371032715,
+      "learning_rate": 0.00014126434724053913,
+      "loss": 0.6386,
+      "step": 225
+    },
+    {
+      "epoch": 1.2988505747126438,
+      "grad_norm": 0.12080610543489456,
+      "learning_rate": 0.00014065326537133094,
+      "loss": 0.6276,
+      "step": 226
+    },
+    {
+      "epoch": 1.3045977011494254,
+      "grad_norm": 0.09340126812458038,
+      "learning_rate": 0.0001400403594053667,
+      "loss": 0.6431,
+      "step": 227
+    },
+    {
+      "epoch": 1.3103448275862069,
+      "grad_norm": 0.09178619831800461,
+      "learning_rate": 0.00013942565684350698,
+      "loss": 0.6457,
+      "step": 228
+    },
+    {
+      "epoch": 1.3160919540229885,
+      "grad_norm": 0.134804829955101,
+      "learning_rate": 0.00013880918526722497,
+      "loss": 0.6247,
+      "step": 229
+    },
+    {
+      "epoch": 1.3218390804597702,
+      "grad_norm": 0.07517404854297638,
+      "learning_rate": 0.00013819097233736888,
+      "loss": 0.6329,
+      "step": 230
+    },
+    {
+      "epoch": 1.3218390804597702,
+      "eval_loss": 0.6541800498962402,
+      "eval_runtime": 404.9523,
+      "eval_samples_per_second": 24.442,
+      "eval_steps_per_second": 0.383,
+      "step": 230
+    },
+    {
+      "epoch": 1.3275862068965516,
+      "grad_norm": 0.1385478675365448,
+      "learning_rate": 0.00013757104579292082,
+      "loss": 0.6697,
+      "step": 231
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.08156240731477737,
+      "learning_rate": 0.00013694943344975212,
+      "loss": 0.6279,
+      "step": 232
+    },
+    {
+      "epoch": 1.339080459770115,
+      "grad_norm": 0.10937108844518661,
+      "learning_rate": 0.00013632616319937522,
+      "loss": 0.6487,
+      "step": 233
+    },
+    {
+      "epoch": 1.3448275862068966,
+      "grad_norm": 0.12300366908311844,
+      "learning_rate": 0.00013570126300769232,
+      "loss": 0.6456,
+      "step": 234
+    },
+    {
+      "epoch": 1.3505747126436782,
+      "grad_norm": 0.07707128673791885,
+      "learning_rate": 0.0001350747609137404,
+      "loss": 0.6302,
+      "step": 235
+    },
+    {
+      "epoch": 1.3563218390804597,
+      "grad_norm": 0.0954674631357193,
+      "learning_rate": 0.0001344466850284333,
+      "loss": 0.6184,
+      "step": 236
+    },
+    {
+      "epoch": 1.3620689655172413,
+      "grad_norm": 0.10317125916481018,
+      "learning_rate": 0.00013381706353330014,
+      "loss": 0.6618,
+      "step": 237
+    },
+    {
+      "epoch": 1.367816091954023,
+      "grad_norm": 0.08765599131584167,
+      "learning_rate": 0.0001331859246792211,
+      "loss": 0.6191,
+      "step": 238
+    },
+    {
+      "epoch": 1.3735632183908046,
+      "grad_norm": 0.10305018723011017,
+      "learning_rate": 0.0001325532967851596,
+      "loss": 0.6397,
+      "step": 239
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.08769567310810089,
+      "learning_rate": 0.00013191920823689177,
+      "loss": 0.6559,
+      "step": 240
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "eval_loss": 0.6528159379959106,
+      "eval_runtime": 407.607,
+      "eval_samples_per_second": 24.283,
+      "eval_steps_per_second": 0.38,
+      "step": 240
+    },
+    {
+      "epoch": 1.3850574712643677,
+      "grad_norm": 0.09783841669559479,
+      "learning_rate": 0.00013128368748573273,
+      "loss": 0.6736,
+      "step": 241
+    },
+    {
+      "epoch": 1.3908045977011494,
+      "grad_norm": 0.08165410906076431,
+      "learning_rate": 0.00013064676304726,
+      "loss": 0.6467,
+      "step": 242
+    },
+    {
+      "epoch": 1.396551724137931,
+      "grad_norm": 0.10928885638713837,
+      "learning_rate": 0.0001300084635000341,
+      "loss": 0.6956,
+      "step": 243
+    },
+    {
+      "epoch": 1.4022988505747127,
+      "grad_norm": 0.09388460218906403,
+      "learning_rate": 0.000129368817484316,
+      "loss": 0.6474,
+      "step": 244
+    },
+    {
+      "epoch": 1.4080459770114944,
+      "grad_norm": 0.08257792145013809,
+      "learning_rate": 0.0001287278537007824,
+      "loss": 0.6301,
+      "step": 245
+    },
+    {
+      "epoch": 1.4137931034482758,
+      "grad_norm": 0.07570406794548035,
+      "learning_rate": 0.00012808560090923758,
+      "loss": 0.6238,
+      "step": 246
+    },
+    {
+      "epoch": 1.4195402298850575,
+      "grad_norm": 0.097509004175663,
+      "learning_rate": 0.00012744208792732324,
+      "loss": 0.6383,
+      "step": 247
+    },
+    {
+      "epoch": 1.4252873563218391,
+      "grad_norm": 0.07778667658567429,
+      "learning_rate": 0.00012679734362922528,
+      "loss": 0.642,
+      "step": 248
+    },
+    {
+      "epoch": 1.4310344827586206,
+      "grad_norm": 0.08389262855052948,
+      "learning_rate": 0.00012615139694437835,
+      "loss": 0.6152,
+      "step": 249
+    },
+    {
+      "epoch": 1.4367816091954024,
+      "grad_norm": 0.08290071040391922,
+      "learning_rate": 0.00012550427685616765,
+      "loss": 0.6389,
+      "step": 250
+    },
+    {
+      "epoch": 1.4367816091954024,
+      "eval_loss": 0.6516815423965454,
+      "eval_runtime": 411.2719,
+      "eval_samples_per_second": 24.067,
+      "eval_steps_per_second": 0.377,
+      "step": 250
+    },
+    {
+      "epoch": 1.4425287356321839,
+      "grad_norm": 0.08134254068136215,
+      "learning_rate": 0.00012485601240062869,
+      "loss": 0.6365,
+      "step": 251
+    },
+    {
+      "epoch": 1.4482758620689655,
+      "grad_norm": 0.11836981773376465,
+      "learning_rate": 0.00012420663266514417,
+      "loss": 0.6345,
+      "step": 252
+    },
+    {
+      "epoch": 1.4540229885057472,
+      "grad_norm": 0.07629366219043732,
+      "learning_rate": 0.0001235561667871391,
+      "loss": 0.6365,
+      "step": 253
+    },
+    {
+      "epoch": 1.4597701149425286,
+      "grad_norm": 0.09142953902482986,
+      "learning_rate": 0.0001229046439527732,
+      "loss": 0.6316,
+      "step": 254
+    },
+    {
+      "epoch": 1.4655172413793103,
+      "grad_norm": 0.12063657492399216,
+      "learning_rate": 0.00012225209339563145,
+      "loss": 0.6221,
+      "step": 255
+    },
+    {
+      "epoch": 1.471264367816092,
+      "grad_norm": 0.07524894177913666,
+      "learning_rate": 0.00012159854439541245,
+      "loss": 0.6485,
+      "step": 256
+    },
+    {
+      "epoch": 1.4770114942528736,
+      "grad_norm": 0.08384133875370026,
+      "learning_rate": 0.00012094402627661447,
+      "loss": 0.6607,
+      "step": 257
+    },
+    {
+      "epoch": 1.4827586206896552,
+      "grad_norm": 0.08039575815200806,
+      "learning_rate": 0.00012028856840721974,
+      "loss": 0.6764,
+      "step": 258
+    },
+    {
+      "epoch": 1.4885057471264367,
+      "grad_norm": 0.09115740656852722,
+      "learning_rate": 0.00011963220019737691,
+      "loss": 0.6587,
+      "step": 259
+    },
+    {
+      "epoch": 1.4942528735632183,
+      "grad_norm": 0.08291927725076675,
+      "learning_rate": 0.00011897495109808107,
+      "loss": 0.6476,
+      "step": 260
+    },
+    {
+      "epoch": 1.4942528735632183,
+      "eval_loss": 0.6506026983261108,
+      "eval_runtime": 407.6949,
+      "eval_samples_per_second": 24.278,
+      "eval_steps_per_second": 0.38,
+      "step": 260
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.09679999202489853,
+      "learning_rate": 0.00011831685059985262,
+      "loss": 0.6378,
+      "step": 261
+    },
+    {
+      "epoch": 1.5057471264367817,
+      "grad_norm": 0.07858405262231827,
+      "learning_rate": 0.00011765792823141384,
+      "loss": 0.6679,
+      "step": 262
+    },
+    {
+      "epoch": 1.5114942528735633,
+      "grad_norm": 0.07274090498685837,
+      "learning_rate": 0.00011699821355836409,
+      "loss": 0.6199,
+      "step": 263
+    },
+    {
+      "epoch": 1.5172413793103448,
+      "grad_norm": 0.11862179636955261,
+      "learning_rate": 0.00011633773618185302,
+      "loss": 0.6369,
+      "step": 264
+    },
+    {
+      "epoch": 1.5229885057471264,
+      "grad_norm": 0.08915189653635025,
+      "learning_rate": 0.00011567652573725262,
+      "loss": 0.6248,
+      "step": 265
+    },
+    {
+      "epoch": 1.528735632183908,
+      "grad_norm": 0.12184260040521622,
+      "learning_rate": 0.00011501461189282733,
+      "loss": 0.645,
+      "step": 266
+    },
+    {
+      "epoch": 1.5344827586206895,
+      "grad_norm": 0.09939936548471451,
+      "learning_rate": 0.00011435202434840287,
+      "loss": 0.6382,
+      "step": 267
+    },
+    {
+      "epoch": 1.5402298850574714,
+      "grad_norm": 0.07167995721101761,
+      "learning_rate": 0.0001136887928340336,
+      "loss": 0.6064,
+      "step": 268
+    },
+    {
+      "epoch": 1.5459770114942528,
+      "grad_norm": 0.09978017210960388,
+      "learning_rate": 0.00011302494710866857,
+      "loss": 0.6467,
+      "step": 269
+    },
+    {
+      "epoch": 1.5517241379310345,
+      "grad_norm": 0.09598653763532639,
+      "learning_rate": 0.00011236051695881633,
+      "loss": 0.6412,
+      "step": 270
+    },
+    {
+      "epoch": 1.5517241379310345,
+      "eval_loss": 0.6497076749801636,
+      "eval_runtime": 407.5672,
+      "eval_samples_per_second": 24.286,
+      "eval_steps_per_second": 0.38,
+      "step": 270
+    },
+    {
+      "epoch": 1.5574712643678161,
+      "grad_norm": 0.08118661493062973,
+      "learning_rate": 0.00011169553219720828,
+      "loss": 0.6659,
+      "step": 271
+    },
+    {
+      "epoch": 1.5632183908045976,
+      "grad_norm": 0.11158329248428345,
+      "learning_rate": 0.00011103002266146096,
+      "loss": 0.6578,
+      "step": 272
+    },
+    {
+      "epoch": 1.5689655172413794,
+      "grad_norm": 0.12230509519577026,
+      "learning_rate": 0.0001103640182127375,
+      "loss": 0.6187,
+      "step": 273
+    },
+    {
+      "epoch": 1.5747126436781609,
+      "grad_norm": 0.07973505556583405,
+      "learning_rate": 0.00010969754873440743,
+      "loss": 0.6507,
+      "step": 274
+    },
+    {
+      "epoch": 1.5804597701149425,
+      "grad_norm": 0.07436943054199219,
+      "learning_rate": 0.00010903064413070612,
+      "loss": 0.6381,
+      "step": 275
+    },
+    {
+      "epoch": 1.5862068965517242,
+      "grad_norm": 0.0804380401968956,
+      "learning_rate": 0.00010836333432539272,
+      "loss": 0.6302,
+      "step": 276
+    },
+    {
+      "epoch": 1.5919540229885056,
+      "grad_norm": 0.07640023529529572,
+      "learning_rate": 0.00010769564926040769,
+      "loss": 0.618,
+      "step": 277
+    },
+    {
+      "epoch": 1.5977011494252875,
+      "grad_norm": 0.0787947028875351,
+      "learning_rate": 0.0001070276188945293,
+      "loss": 0.6308,
+      "step": 278
+    },
+    {
+      "epoch": 1.603448275862069,
+      "grad_norm": 0.08764500916004181,
+      "learning_rate": 0.00010635927320202928,
+      "loss": 0.6316,
+      "step": 279
+    },
+    {
+      "epoch": 1.6091954022988506,
+      "grad_norm": 0.07885821908712387,
+      "learning_rate": 0.00010569064217132791,
+      "loss": 0.6232,
+      "step": 280
+    },
+    {
+      "epoch": 1.6091954022988506,
+      "eval_loss": 0.6484516859054565,
+      "eval_runtime": 406.5349,
+      "eval_samples_per_second": 24.347,
+      "eval_steps_per_second": 0.381,
+      "step": 280
+    },
+    {
+      "epoch": 1.6149425287356323,
+      "grad_norm": 0.08910427987575531,
+      "learning_rate": 0.00010502175580364857,
+      "loss": 0.6207,
+      "step": 281
+    },
+    {
+      "epoch": 1.6206896551724137,
+      "grad_norm": 0.08195802569389343,
+      "learning_rate": 0.00010435264411167148,
+      "loss": 0.6604,
+      "step": 282
+    },
+    {
+      "epoch": 1.6264367816091954,
+      "grad_norm": 0.09276524186134338,
+      "learning_rate": 0.0001036833371181871,
+      "loss": 0.6444,
+      "step": 283
+    },
+    {
+      "epoch": 1.632183908045977,
+      "grad_norm": 0.07577691972255707,
+      "learning_rate": 0.00010301386485474889,
+      "loss": 0.6439,
+      "step": 284
+    },
+    {
+      "epoch": 1.6379310344827587,
+      "grad_norm": 0.07871613651514053,
+      "learning_rate": 0.00010234425736032607,
+      "loss": 0.639,
+      "step": 285
+    },
+    {
+      "epoch": 1.6436781609195403,
+      "grad_norm": 0.07570876181125641,
+      "learning_rate": 0.00010167454467995549,
+      "loss": 0.6056,
+      "step": 286
+    },
+    {
+      "epoch": 1.6494252873563218,
+      "grad_norm": 0.09836837649345398,
+      "learning_rate": 0.00010100475686339379,
+      "loss": 0.6341,
+      "step": 287
+    },
+    {
+      "epoch": 1.6551724137931034,
+      "grad_norm": 0.08796896785497665,
+      "learning_rate": 0.00010033492396376878,
+      "loss": 0.6193,
+      "step": 288
+    },
+    {
+      "epoch": 1.660919540229885,
+      "grad_norm": 0.07815764099359512,
+      "learning_rate": 9.966507603623125e-05,
+      "loss": 0.6227,
+      "step": 289
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.13016292452812195,
+      "learning_rate": 9.899524313660624e-05,
+      "loss": 0.6243,
+      "step": 290
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "eval_loss": 0.6477526426315308,
+      "eval_runtime": 405.0855,
+      "eval_samples_per_second": 24.434,
+      "eval_steps_per_second": 0.383,
+      "step": 290
+    },
+    {
+      "epoch": 1.6724137931034484,
+      "grad_norm": 0.09747885912656784,
+      "learning_rate": 9.832545532004454e-05,
+      "loss": 0.6328,
+      "step": 291
+    },
+    {
+      "epoch": 1.6781609195402298,
+      "grad_norm": 0.10131366550922394,
+      "learning_rate": 9.765574263967396e-05,
+      "loss": 0.6212,
+      "step": 292
+    },
+    {
+      "epoch": 1.6839080459770115,
+      "grad_norm": 0.1203976571559906,
+      "learning_rate": 9.698613514525116e-05,
+      "loss": 0.6563,
+      "step": 293
+    },
+    {
+      "epoch": 1.6896551724137931,
+      "grad_norm": 0.07119957357645035,
+      "learning_rate": 9.631666288181293e-05,
+      "loss": 0.6278,
+      "step": 294
+    },
+    {
+      "epoch": 1.6954022988505746,
+      "grad_norm": 0.11370845884084702,
+      "learning_rate": 9.564735588832856e-05,
+      "loss": 0.6376,
+      "step": 295
+    },
+    {
+      "epoch": 1.7011494252873565,
+      "grad_norm": 0.07851264625787735,
+      "learning_rate": 9.497824419635144e-05,
+      "loss": 0.6149,
+      "step": 296
+    },
+    {
+      "epoch": 1.706896551724138,
+      "grad_norm": 0.0818655788898468,
+      "learning_rate": 9.430935782867212e-05,
+      "loss": 0.6048,
+      "step": 297
+    },
+    {
+      "epoch": 1.7126436781609196,
+      "grad_norm": 0.07335007190704346,
+      "learning_rate": 9.364072679797073e-05,
+      "loss": 0.6292,
+      "step": 298
+    },
+    {
+      "epoch": 1.7183908045977012,
+      "grad_norm": 0.07759315520524979,
+      "learning_rate": 9.297238110547074e-05,
+      "loss": 0.6464,
+      "step": 299
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 0.0833640992641449,
+      "learning_rate": 9.230435073959232e-05,
+      "loss": 0.6467,
+      "step": 300
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "eval_loss": 0.6469475030899048,
+      "eval_runtime": 408.9385,
+      "eval_samples_per_second": 24.204,
+      "eval_steps_per_second": 0.379,
+      "step": 300
+    },
+    {
+      "epoch": 1.7298850574712645,
+      "grad_norm": 0.08030898869037628,
+      "learning_rate": 9.163666567460733e-05,
+      "loss": 0.6268,
+      "step": 301
+    },
+    {
+      "epoch": 1.735632183908046,
+      "grad_norm": 0.08017026633024216,
+      "learning_rate": 9.096935586929392e-05,
+      "loss": 0.6367,
+      "step": 302
+    },
+    {
+      "epoch": 1.7413793103448276,
+      "grad_norm": 0.07945988327264786,
+      "learning_rate": 9.030245126559262e-05,
+      "loss": 0.6318,
+      "step": 303
+    },
+    {
+      "epoch": 1.7471264367816093,
+      "grad_norm": 0.09426795691251755,
+      "learning_rate": 8.963598178726254e-05,
+      "loss": 0.6399,
+      "step": 304
+    },
+    {
+      "epoch": 1.7528735632183907,
+      "grad_norm": 0.08182523399591446,
+      "learning_rate": 8.896997733853903e-05,
+      "loss": 0.6203,
+      "step": 305
+    },
+    {
+      "epoch": 1.7586206896551724,
+      "grad_norm": 0.07778620719909668,
+      "learning_rate": 8.830446780279176e-05,
+      "loss": 0.6816,
+      "step": 306
+    },
+    {
+      "epoch": 1.764367816091954,
+      "grad_norm": 0.11482707411050797,
+      "learning_rate": 8.763948304118368e-05,
+      "loss": 0.6442,
+      "step": 307
+    },
+    {
+      "epoch": 1.7701149425287355,
+      "grad_norm": 0.07546856999397278,
+      "learning_rate": 8.697505289133145e-05,
+      "loss": 0.6445,
+      "step": 308
+    },
+    {
+      "epoch": 1.7758620689655173,
+      "grad_norm": 0.11665278673171997,
+      "learning_rate": 8.631120716596641e-05,
+      "loss": 0.6374,
+      "step": 309
+    },
+    {
+      "epoch": 1.7816091954022988,
+      "grad_norm": 0.1181105300784111,
+      "learning_rate": 8.564797565159714e-05,
+      "loss": 0.6146,
+      "step": 310
+    },
+    {
+      "epoch": 1.7816091954022988,
+      "eval_loss": 0.6459708213806152,
+      "eval_runtime": 405.0602,
+      "eval_samples_per_second": 24.436,
+      "eval_steps_per_second": 0.383,
+      "step": 310
+    },
+    {
+      "epoch": 1.7873563218390804,
+      "grad_norm": 0.07805997133255005,
+      "learning_rate": 8.498538810717267e-05,
+      "loss": 0.6679,
+      "step": 311
+    },
+    {
+      "epoch": 1.793103448275862,
+      "grad_norm": 0.08421120047569275,
+      "learning_rate": 8.432347426274739e-05,
+      "loss": 0.642,
+      "step": 312
+    },
+    {
+      "epoch": 1.7988505747126435,
+      "grad_norm": 0.10425391793251038,
+      "learning_rate": 8.366226381814697e-05,
+      "loss": 0.6354,
+      "step": 313
+    },
+    {
+      "epoch": 1.8045977011494254,
+      "grad_norm": 0.08861584216356277,
+      "learning_rate": 8.300178644163594e-05,
+      "loss": 0.6397,
+      "step": 314
+    },
+    {
+      "epoch": 1.8103448275862069,
+      "grad_norm": 0.08726219832897186,
+      "learning_rate": 8.234207176858614e-05,
+      "loss": 0.6474,
+      "step": 315
+    },
+    {
+      "epoch": 1.8160919540229885,
+      "grad_norm": 0.12218604981899261,
+      "learning_rate": 8.16831494001474e-05,
+      "loss": 0.6459,
+      "step": 316
+    },
+    {
+      "epoch": 1.8218390804597702,
+      "grad_norm": 0.08113615214824677,
+      "learning_rate": 8.102504890191892e-05,
+      "loss": 0.6114,
+      "step": 317
+    },
+    {
+      "epoch": 1.8275862068965516,
+      "grad_norm": 0.08763635903596878,
+      "learning_rate": 8.036779980262311e-05,
+      "loss": 0.6602,
+      "step": 318
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 0.1053246557712555,
+      "learning_rate": 7.971143159278026e-05,
+      "loss": 0.6182,
+      "step": 319
+    },
+    {
+      "epoch": 1.839080459770115,
+      "grad_norm": 0.09522312134504318,
+      "learning_rate": 7.905597372338558e-05,
+      "loss": 0.6386,
+      "step": 320
+    },
+    {
+      "epoch": 1.839080459770115,
+      "eval_loss": 0.6449984908103943,
+      "eval_runtime": 405.9165,
+      "eval_samples_per_second": 24.384,
+      "eval_steps_per_second": 0.382,
+      "step": 320
+    },
+    {
+      "epoch": 1.8448275862068966,
+      "grad_norm": 0.09493348747491837,
+      "learning_rate": 7.840145560458756e-05,
+      "loss": 0.6522,
+      "step": 321
+    },
+    {
+      "epoch": 1.8505747126436782,
+      "grad_norm": 0.10554379224777222,
+      "learning_rate": 7.774790660436858e-05,
+      "loss": 0.6401,
+      "step": 322
+    },
+    {
+      "epoch": 1.8563218390804597,
+      "grad_norm": 0.09237196296453476,
+      "learning_rate": 7.709535604722684e-05,
+      "loss": 0.6315,
+      "step": 323
+    },
+    {
+      "epoch": 1.8620689655172413,
+      "grad_norm": 0.07175464183092117,
+      "learning_rate": 7.644383321286094e-05,
+      "loss": 0.6559,
+      "step": 324
+    },
+    {
+      "epoch": 1.867816091954023,
+      "grad_norm": 0.08578918129205704,
+      "learning_rate": 7.579336733485584e-05,
+      "loss": 0.6297,
+      "step": 325
+    },
+    {
+      "epoch": 1.8735632183908046,
+      "grad_norm": 0.14390091598033905,
+      "learning_rate": 7.514398759937135e-05,
+      "loss": 0.6155,
+      "step": 326
+    },
+    {
+      "epoch": 1.8793103448275863,
+      "grad_norm": 0.07774030417203903,
+      "learning_rate": 7.449572314383237e-05,
+      "loss": 0.6551,
+      "step": 327
+    },
+    {
+      "epoch": 1.8850574712643677,
+      "grad_norm": 0.07927459478378296,
+      "learning_rate": 7.384860305562172e-05,
+      "loss": 0.6312,
+      "step": 328
+    },
+    {
+      "epoch": 1.8908045977011494,
+      "grad_norm": 0.11287631094455719,
+      "learning_rate": 7.320265637077473e-05,
+      "loss": 0.66,
+      "step": 329
+    },
+    {
+      "epoch": 1.896551724137931,
+      "grad_norm": 0.09955232590436935,
+      "learning_rate": 7.255791207267679e-05,
+      "loss": 0.6456,
+      "step": 330
+    },
+    {
+      "epoch": 1.896551724137931,
+      "eval_loss": 0.6442980766296387,
+      "eval_runtime": 404.2901,
+      "eval_samples_per_second": 24.482,
+      "eval_steps_per_second": 0.383,
+      "step": 330
+    },
+    {
+      "epoch": 1.9022988505747125,
+      "grad_norm": 0.07881880551576614,
+      "learning_rate": 7.191439909076243e-05,
+      "loss": 0.6398,
+      "step": 331
+    },
+    {
+      "epoch": 1.9080459770114944,
+      "grad_norm": 0.15244217216968536,
+      "learning_rate": 7.127214629921765e-05,
+      "loss": 0.6614,
+      "step": 332
+    },
+    {
+      "epoch": 1.9137931034482758,
+      "grad_norm": 0.07337264716625214,
+      "learning_rate": 7.0631182515684e-05,
+      "loss": 0.6294,
+      "step": 333
+    },
+    {
+      "epoch": 1.9195402298850575,
+      "grad_norm": 0.07102935016155243,
+      "learning_rate": 6.999153649996595e-05,
+      "loss": 0.6237,
+      "step": 334
+    },
+    {
+      "epoch": 1.9252873563218391,
+      "grad_norm": 0.09349462389945984,
+      "learning_rate": 6.935323695274002e-05,
+      "loss": 0.6051,
+      "step": 335
+    },
+    {
+      "epoch": 1.9310344827586206,
+      "grad_norm": 0.0851803794503212,
+      "learning_rate": 6.871631251426728e-05,
+      "loss": 0.6548,
+      "step": 336
+    },
+    {
+      "epoch": 1.9367816091954024,
+      "grad_norm": 0.08571562170982361,
+      "learning_rate": 6.808079176310827e-05,
+      "loss": 0.6136,
+      "step": 337
+    },
+    {
+      "epoch": 1.9425287356321839,
+      "grad_norm": 0.0772768035531044,
+      "learning_rate": 6.744670321484043e-05,
+      "loss": 0.6668,
+      "step": 338
+    },
+    {
+      "epoch": 1.9482758620689655,
+      "grad_norm": 0.08812547475099564,
+      "learning_rate": 6.681407532077895e-05,
+      "loss": 0.6427,
+      "step": 339
+    },
+    {
+      "epoch": 1.9540229885057472,
+      "grad_norm": 0.09011583775281906,
+      "learning_rate": 6.618293646669986e-05,
+      "loss": 0.6402,
+      "step": 340
+    },
+    {
+      "epoch": 1.9540229885057472,
+      "eval_loss": 0.6436823606491089,
+      "eval_runtime": 413.0204,
+      "eval_samples_per_second": 23.965,
+      "eval_steps_per_second": 0.375,
+      "step": 340
+    },
+    {
+      "epoch": 1.9597701149425286,
+      "grad_norm": 0.08234158158302307,
+      "learning_rate": 6.555331497156672e-05,
+      "loss": 0.6362,
+      "step": 341
+    },
+    {
+      "epoch": 1.9655172413793105,
+      "grad_norm": 0.0780014768242836,
+      "learning_rate": 6.492523908625959e-05,
+      "loss": 0.6454,
+      "step": 342
+    },
+    {
+      "epoch": 1.971264367816092,
+      "grad_norm": 0.08458276093006134,
+      "learning_rate": 6.42987369923077e-05,
+      "loss": 0.6587,
+      "step": 343
+    },
+    {
+      "epoch": 1.9770114942528736,
+      "grad_norm": 0.11979149281978607,
+      "learning_rate": 6.367383680062478e-05,
+      "loss": 0.6369,
+      "step": 344
+    },
+    {
+      "epoch": 1.9827586206896552,
+      "grad_norm": 0.08782167732715607,
+      "learning_rate": 6.30505665502479e-05,
+      "loss": 0.6382,
+      "step": 345
+    },
+    {
+      "epoch": 1.9885057471264367,
+      "grad_norm": 0.07542918622493744,
+      "learning_rate": 6.242895420707917e-05,
+      "loss": 0.6238,
+      "step": 346
+    },
+    {
+      "epoch": 1.9942528735632183,
+      "grad_norm": 0.09390002489089966,
+      "learning_rate": 6.180902766263113e-05,
+      "loss": 0.632,
+      "step": 347
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.10154885053634644,
+      "learning_rate": 6.119081473277501e-05,
+      "loss": 0.6078,
+      "step": 348
+    },
+    {
+      "epoch": 2.0057471264367814,
+      "grad_norm": 0.09035320580005646,
+      "learning_rate": 6.057434315649304e-05,
+      "loss": 0.6331,
+      "step": 349
+    },
+    {
+      "epoch": 2.0114942528735633,
+      "grad_norm": 0.1151895746588707,
+      "learning_rate": 5.99596405946333e-05,
+      "loss": 0.6455,
+      "step": 350
+    },
+    {
+      "epoch": 2.0114942528735633,
+      "eval_loss": 0.6433547139167786,
+      "eval_runtime": 409.0063,
+      "eval_samples_per_second": 24.2,
+      "eval_steps_per_second": 0.379,
+      "step": 350
+    },
+    {
+      "epoch": 2.0172413793103448,
+      "grad_norm": 0.10666079819202423,
+      "learning_rate": 5.9346734628669065e-05,
+      "loss": 0.6473,
+      "step": 351
+    },
+    {
+      "epoch": 2.0229885057471266,
+      "grad_norm": 0.09095422178506851,
+      "learning_rate": 5.873565275946088e-05,
+      "loss": 0.6335,
+      "step": 352
+    },
+    {
+      "epoch": 2.028735632183908,
+      "grad_norm": 0.09256957471370697,
+      "learning_rate": 5.8126422406022885e-05,
+      "loss": 0.5969,
+      "step": 353
+    },
+    {
+      "epoch": 2.0344827586206895,
+      "grad_norm": 0.1397576928138733,
+      "learning_rate": 5.7519070904292247e-05,
+      "loss": 0.5919,
+      "step": 354
+    },
+    {
+      "epoch": 2.0402298850574714,
+      "grad_norm": 0.0867573469877243,
+      "learning_rate": 5.691362550590297e-05,
+      "loss": 0.5909,
+      "step": 355
+    },
+    {
+      "epoch": 2.045977011494253,
+      "grad_norm": 0.07953327894210815,
+      "learning_rate": 5.631011337696271e-05,
+      "loss": 0.5959,
+      "step": 356
+    },
+    {
+      "epoch": 2.0517241379310347,
+      "grad_norm": 0.09324570745229721,
+      "learning_rate": 5.570856159683418e-05,
+      "loss": 0.6216,
+      "step": 357
+    },
+    {
+      "epoch": 2.057471264367816,
+      "grad_norm": 0.10510014742612839,
+      "learning_rate": 5.510899715691984e-05,
+      "loss": 0.6172,
+      "step": 358
+    },
+    {
+      "epoch": 2.0632183908045976,
+      "grad_norm": 0.08669542521238327,
+      "learning_rate": 5.451144695945116e-05,
+      "loss": 0.5931,
+      "step": 359
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "grad_norm": 0.09054102748632431,
+      "learning_rate": 5.3915937816281095e-05,
+      "loss": 0.5888,
+      "step": 360
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "eval_loss": 0.643742024898529,
+      "eval_runtime": 404.2471,
+      "eval_samples_per_second": 24.485,
+      "eval_steps_per_second": 0.383,
+      "step": 360
+    },
+    {
+      "epoch": 2.074712643678161,
+      "grad_norm": 0.11839323490858078,
+      "learning_rate": 5.3322496447681414e-05,
+      "loss": 0.6093,
+      "step": 361
+    },
+    {
+      "epoch": 2.0804597701149423,
+      "grad_norm": 0.1050933375954628,
+      "learning_rate": 5.273114948114346e-05,
+      "loss": 0.6247,
+      "step": 362
+    },
+    {
+      "epoch": 2.086206896551724,
+      "grad_norm": 0.09781333059072495,
+      "learning_rate": 5.214192345018374e-05,
+      "loss": 0.6274,
+      "step": 363
+    },
+    {
+      "epoch": 2.0919540229885056,
+      "grad_norm": 0.09329628199338913,
+      "learning_rate": 5.1554844793153e-05,
+      "loss": 0.6243,
+      "step": 364
+    },
+    {
+      "epoch": 2.0977011494252875,
+      "grad_norm": 0.08716364949941635,
+      "learning_rate": 5.096993985205023e-05,
+      "loss": 0.6149,
+      "step": 365
+    },
+    {
+      "epoch": 2.103448275862069,
+      "grad_norm": 0.09969545155763626,
+      "learning_rate": 5.0387234871340486e-05,
+      "loss": 0.635,
+      "step": 366
+    },
+    {
+      "epoch": 2.1091954022988504,
+      "grad_norm": 0.10841623693704605,
+      "learning_rate": 4.980675599677757e-05,
+      "loss": 0.6544,
+      "step": 367
+    },
+    {
+      "epoch": 2.1149425287356323,
+      "grad_norm": 0.07902085781097412,
+      "learning_rate": 4.9228529274230695e-05,
+      "loss": 0.6144,
+      "step": 368
+    },
+    {
+      "epoch": 2.1206896551724137,
+      "grad_norm": 0.11440268158912659,
+      "learning_rate": 4.865258064851579e-05,
+      "loss": 0.6217,
+      "step": 369
+    },
+    {
+      "epoch": 2.1264367816091956,
+      "grad_norm": 0.09594007581472397,
+      "learning_rate": 4.807893596223152e-05,
+      "loss": 0.6267,
+      "step": 370
+    },
+    {
+      "epoch": 2.1264367816091956,
+      "eval_loss": 0.6434890031814575,
+      "eval_runtime": 404.1508,
+      "eval_samples_per_second": 24.491,
+      "eval_steps_per_second": 0.384,
+      "step": 370
+    },
+    {
+      "epoch": 2.132183908045977,
+      "grad_norm": 0.09025128185749054,
+      "learning_rate": 4.75076209545996e-05,
+      "loss": 0.6122,
+      "step": 371
+    },
+    {
+      "epoch": 2.1379310344827585,
+      "grad_norm": 0.09677668660879135,
+      "learning_rate": 4.693866126030995e-05,
+      "loss": 0.6339,
+      "step": 372
+    },
+    {
+      "epoch": 2.1436781609195403,
+      "grad_norm": 0.08178266882896423,
+      "learning_rate": 4.637208240837042e-05,
+      "loss": 0.6392,
+      "step": 373
+    },
+    {
+      "epoch": 2.1494252873563218,
+      "grad_norm": 0.10616466403007507,
+      "learning_rate": 4.5807909820961494e-05,
+      "loss": 0.6207,
+      "step": 374
+    },
+    {
+      "epoch": 2.1551724137931036,
+      "grad_norm": 0.08333076536655426,
+      "learning_rate": 4.5246168812295286e-05,
+      "loss": 0.6148,
+      "step": 375
+    },
+    {
+      "epoch": 2.160919540229885,
+      "grad_norm": 0.1016552671790123,
+      "learning_rate": 4.468688458748006e-05,
+      "loss": 0.6306,
+      "step": 376
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 0.08546506613492966,
+      "learning_rate": 4.413008224138897e-05,
+      "loss": 0.606,
+      "step": 377
+    },
+    {
+      "epoch": 2.1724137931034484,
+      "grad_norm": 0.08369904011487961,
+      "learning_rate": 4.357578675753432e-05,
+      "loss": 0.6007,
+      "step": 378
+    },
+    {
+      "epoch": 2.17816091954023,
+      "grad_norm": 0.08523935824632645,
+      "learning_rate": 4.302402300694636e-05,
+      "loss": 0.5884,
+      "step": 379
+    },
+    {
+      "epoch": 2.1839080459770113,
+      "grad_norm": 0.0944519191980362,
+      "learning_rate": 4.247481574705744e-05,
+      "loss": 0.6292,
+      "step": 380
+    },
+    {
+      "epoch": 2.1839080459770113,
+      "eval_loss": 0.6433520913124084,
+      "eval_runtime": 404.2218,
+      "eval_samples_per_second": 24.487,
+      "eval_steps_per_second": 0.383,
+      "step": 380
+    },
+    {
+      "epoch": 2.189655172413793,
+      "grad_norm": 0.11311980336904526,
+      "learning_rate": 4.1928189620591116e-05,
+      "loss": 0.6103,
+      "step": 381
+    },
+    {
+      "epoch": 2.1954022988505746,
+      "grad_norm": 0.08662451803684235,
+      "learning_rate": 4.138416915445655e-05,
+      "loss": 0.5852,
+      "step": 382
+    },
+    {
+      "epoch": 2.2011494252873565,
+      "grad_norm": 0.09417479485273361,
+      "learning_rate": 4.084277875864776e-05,
+      "loss": 0.6467,
+      "step": 383
+    },
+    {
+      "epoch": 2.206896551724138,
+      "grad_norm": 0.09818896651268005,
+      "learning_rate": 4.030404272514864e-05,
+      "loss": 0.6112,
+      "step": 384
+    },
+    {
+      "epoch": 2.2126436781609193,
+      "grad_norm": 0.08806431293487549,
+      "learning_rate": 3.9767985226842696e-05,
+      "loss": 0.5822,
+      "step": 385
+    },
+    {
+      "epoch": 2.218390804597701,
+      "grad_norm": 0.0837361216545105,
+      "learning_rate": 3.923463031642872e-05,
+      "loss": 0.6137,
+      "step": 386
+    },
+    {
+      "epoch": 2.2241379310344827,
+      "grad_norm": 0.10712449252605438,
+      "learning_rate": 3.870400192534128e-05,
+      "loss": 0.602,
+      "step": 387
+    },
+    {
+      "epoch": 2.2298850574712645,
+      "grad_norm": 0.11590448766946793,
+      "learning_rate": 3.81761238626771e-05,
+      "loss": 0.6215,
+      "step": 388
+    },
+    {
+      "epoch": 2.235632183908046,
+      "grad_norm": 0.08264652639627457,
+      "learning_rate": 3.7651019814126654e-05,
+      "loss": 0.6002,
+      "step": 389
+    },
+    {
+      "epoch": 2.2413793103448274,
+      "grad_norm": 0.08986306935548782,
+      "learning_rate": 3.7128713340911535e-05,
+      "loss": 0.6058,
+      "step": 390
+    },
+    {
+      "epoch": 2.2413793103448274,
+      "eval_loss": 0.6431533098220825,
+      "eval_runtime": 419.2567,
+      "eval_samples_per_second": 23.608,
+      "eval_steps_per_second": 0.37,
+      "step": 390
+    },
+    {
+      "epoch": 2.2471264367816093,
+      "grad_norm": 0.3949902057647705,
+      "learning_rate": 3.660922787872706e-05,
+      "loss": 0.643,
+      "step": 391
+    },
+    {
+      "epoch": 2.2528735632183907,
+      "grad_norm": 0.09183293581008911,
+      "learning_rate": 3.609258673669097e-05,
+      "loss": 0.5931,
+      "step": 392
+    },
+    {
+      "epoch": 2.2586206896551726,
+      "grad_norm": 0.0786626785993576,
+      "learning_rate": 3.557881309629729e-05,
+      "loss": 0.5795,
+      "step": 393
+    },
+    {
+      "epoch": 2.264367816091954,
+      "grad_norm": 0.08318330347537994,
+      "learning_rate": 3.5067930010376484e-05,
+      "loss": 0.6173,
+      "step": 394
+    },
+    {
+      "epoch": 2.2701149425287355,
+      "grad_norm": 0.09149078279733658,
+      "learning_rate": 3.455996040206076e-05,
+      "loss": 0.6238,
+      "step": 395
+    },
+    {
+      "epoch": 2.2758620689655173,
+      "grad_norm": 0.09578599780797958,
+      "learning_rate": 3.4054927063755796e-05,
+      "loss": 0.6264,
+      "step": 396
+    },
+    {
+      "epoch": 2.281609195402299,
+      "grad_norm": 0.08735264092683792,
+      "learning_rate": 3.355285265611784e-05,
+      "loss": 0.6269,
+      "step": 397
+    },
+    {
+      "epoch": 2.2873563218390807,
+      "grad_norm": 0.0886816754937172,
+      "learning_rate": 3.305375970703711e-05,
+      "loss": 0.6043,
+      "step": 398
+    },
+    {
+      "epoch": 2.293103448275862,
+      "grad_norm": 0.07559609413146973,
+      "learning_rate": 3.2557670610626925e-05,
+      "loss": 0.6416,
+      "step": 399
+    },
+    {
+      "epoch": 2.2988505747126435,
+      "grad_norm": 0.11379113793373108,
+      "learning_rate": 3.206460762621873e-05,
+      "loss": 0.6221,
+      "step": 400
+    },
+    {
+      "epoch": 2.2988505747126435,
+      "eval_loss": 0.6427375078201294,
+      "eval_runtime": 405.8229,
+      "eval_samples_per_second": 24.39,
+      "eval_steps_per_second": 0.382,
+      "step": 400
+    },
+    {
+      "epoch": 2.3045977011494254,
+      "grad_norm": 0.08930199593305588,
+      "learning_rate": 3.157459287736362e-05,
+      "loss": 0.599,
+      "step": 401
+    },
+    {
+      "epoch": 2.310344827586207,
+      "grad_norm": 0.11189960688352585,
+      "learning_rate": 3.108764835083938e-05,
+      "loss": 0.6243,
+      "step": 402
+    },
+    {
+      "epoch": 2.3160919540229887,
+      "grad_norm": 0.0793476328253746,
+      "learning_rate": 3.0603795895664124e-05,
+      "loss": 0.615,
+      "step": 403
+    },
+    {
+      "epoch": 2.32183908045977,
+      "grad_norm": 0.0860418751835823,
+      "learning_rate": 3.0123057222115836e-05,
+      "loss": 0.5968,
+      "step": 404
+    },
+    {
+      "epoch": 2.3275862068965516,
+      "grad_norm": 0.08753317594528198,
+      "learning_rate": 2.964545390075841e-05,
+      "loss": 0.6192,
+      "step": 405
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.09598301351070404,
+      "learning_rate": 2.9171007361473514e-05,
+      "loss": 0.6237,
+      "step": 406
+    },
+    {
+      "epoch": 2.339080459770115,
+      "grad_norm": 0.10627751052379608,
+      "learning_rate": 2.8699738892499328e-05,
+      "loss": 0.6123,
+      "step": 407
+    },
+    {
+      "epoch": 2.344827586206897,
+      "grad_norm": 0.08839675039052963,
+      "learning_rate": 2.8231669639475067e-05,
+      "loss": 0.6123,
+      "step": 408
+    },
+    {
+      "epoch": 2.3505747126436782,
+      "grad_norm": 0.08533503860235214,
+      "learning_rate": 2.776682060449247e-05,
+      "loss": 0.6251,
+      "step": 409
+    },
+    {
+      "epoch": 2.3563218390804597,
+      "grad_norm": 0.10517686605453491,
+      "learning_rate": 2.7305212645153212e-05,
+      "loss": 0.6254,
+      "step": 410
+    },
+    {
+      "epoch": 2.3563218390804597,
+      "eval_loss": 0.6428195238113403,
+      "eval_runtime": 404.1758,
+      "eval_samples_per_second": 24.489,
+      "eval_steps_per_second": 0.383,
+      "step": 410
+    },
+    {
+      "epoch": 2.3620689655172415,
+      "grad_norm": 0.10578128695487976,
+      "learning_rate": 2.6846866473633125e-05,
+      "loss": 0.6216,
+      "step": 411
+    },
+    {
+      "epoch": 2.367816091954023,
+      "grad_norm": 0.10083532333374023,
+      "learning_rate": 2.6391802655752853e-05,
+      "loss": 0.6052,
+      "step": 412
+    },
+    {
+      "epoch": 2.3735632183908044,
+      "grad_norm": 0.08413968980312347,
+      "learning_rate": 2.594004161005511e-05,
+      "loss": 0.6007,
+      "step": 413
+    },
+    {
+      "epoch": 2.3793103448275863,
+      "grad_norm": 0.08840201050043106,
+      "learning_rate": 2.549160360688838e-05,
+      "loss": 0.5876,
+      "step": 414
+    },
+    {
+      "epoch": 2.3850574712643677,
+      "grad_norm": 0.09680577367544174,
+      "learning_rate": 2.50465087674976e-05,
+      "loss": 0.6183,
+      "step": 415
+    },
+    {
+      "epoch": 2.3908045977011496,
+      "grad_norm": 0.09196774661540985,
+      "learning_rate": 2.4604777063121033e-05,
+      "loss": 0.613,
+      "step": 416
+    },
+    {
+      "epoch": 2.396551724137931,
+      "grad_norm": 0.0849708616733551,
+      "learning_rate": 2.4166428314094514e-05,
+      "loss": 0.6443,
+      "step": 417
+    },
+    {
+      "epoch": 2.4022988505747125,
+      "grad_norm": 0.09316956251859665,
+      "learning_rate": 2.3731482188961818e-05,
+      "loss": 0.6062,
+      "step": 418
+    },
+    {
+      "epoch": 2.4080459770114944,
+      "grad_norm": 0.08482903987169266,
+      "learning_rate": 2.32999582035923e-05,
+      "loss": 0.6099,
+      "step": 419
+    },
+    {
+      "epoch": 2.413793103448276,
+      "grad_norm": 0.08352029323577881,
+      "learning_rate": 2.287187572030516e-05,
+      "loss": 0.6178,
+      "step": 420
+    },
+    {
+      "epoch": 2.413793103448276,
+      "eval_loss": 0.6422638297080994,
+      "eval_runtime": 404.4609,
+      "eval_samples_per_second": 24.472,
+      "eval_steps_per_second": 0.383,
+      "step": 420
+    },
+    {
+      "epoch": 2.4195402298850572,
+      "grad_norm": 0.09856913238763809,
+      "learning_rate": 2.244725394700079e-05,
+      "loss": 0.6166,
+      "step": 421
+    },
+    {
+      "epoch": 2.425287356321839,
+      "grad_norm": 0.10127527266740799,
+      "learning_rate": 2.202611193629869e-05,
+      "loss": 0.6195,
+      "step": 422
+    },
+    {
+      "epoch": 2.4310344827586206,
+      "grad_norm": 0.09415800124406815,
+      "learning_rate": 2.160846858468285e-05,
+      "loss": 0.6157,
+      "step": 423
+    },
+    {
+      "epoch": 2.4367816091954024,
+      "grad_norm": 0.08563528954982758,
+      "learning_rate": 2.1194342631653607e-05,
+      "loss": 0.6212,
+      "step": 424
+    },
+    {
+      "epoch": 2.442528735632184,
+      "grad_norm": 0.0861605629324913,
+      "learning_rate": 2.0783752658887066e-05,
+      "loss": 0.6095,
+      "step": 425
+    },
+    {
+      "epoch": 2.4482758620689653,
+      "grad_norm": 0.1125798374414444,
+      "learning_rate": 2.0376717089401164e-05,
+      "loss": 0.606,
+      "step": 426
+    },
+    {
+      "epoch": 2.454022988505747,
+      "grad_norm": 0.09633134305477142,
+      "learning_rate": 1.9973254186729086e-05,
+      "loss": 0.6109,
+      "step": 427
+    },
+    {
+      "epoch": 2.4597701149425286,
+      "grad_norm": 0.08123010396957397,
+      "learning_rate": 1.9573382054099786e-05,
+      "loss": 0.5896,
+      "step": 428
+    },
+    {
+      "epoch": 2.4655172413793105,
+      "grad_norm": 0.08620712906122208,
+      "learning_rate": 1.9177118633625814e-05,
+      "loss": 0.6022,
+      "step": 429
+    },
+    {
+      "epoch": 2.471264367816092,
+      "grad_norm": 0.08710537105798721,
+      "learning_rate": 1.8784481705498015e-05,
+      "loss": 0.6161,
+      "step": 430
+    },
+    {
+      "epoch": 2.471264367816092,
+      "eval_loss": 0.642048180103302,
+      "eval_runtime": 405.7821,
+      "eval_samples_per_second": 24.392,
+      "eval_steps_per_second": 0.382,
+      "step": 430
+    },
+    {
+      "epoch": 2.4770114942528734,
+      "grad_norm": 0.08711250126361847,
+      "learning_rate": 1.8395488887188005e-05,
+      "loss": 0.581,
+      "step": 431
+    },
+    {
+      "epoch": 2.4827586206896552,
+      "grad_norm": 0.08405685424804688,
+      "learning_rate": 1.8010157632657543e-05,
+      "loss": 0.6149,
+      "step": 432
+    },
+    {
+      "epoch": 2.4885057471264367,
+      "grad_norm": 0.08080325275659561,
+      "learning_rate": 1.762850523157532e-05,
+      "loss": 0.6264,
+      "step": 433
+    },
+    {
+      "epoch": 2.4942528735632186,
+      "grad_norm": 0.09836191684007645,
+      "learning_rate": 1.7250548808541322e-05,
+      "loss": 0.6055,
+      "step": 434
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.10626177489757538,
+      "learning_rate": 1.687630532231833e-05,
+      "loss": 0.5907,
+      "step": 435
+    },
+    {
+      "epoch": 2.5057471264367814,
+      "grad_norm": 0.08308445662260056,
+      "learning_rate": 1.6505791565071138e-05,
+      "loss": 0.6189,
+      "step": 436
+    },
+    {
+      "epoch": 2.5114942528735633,
+      "grad_norm": 0.10249936580657959,
+      "learning_rate": 1.613902416161288e-05,
+      "loss": 0.6084,
+      "step": 437
+    },
+    {
+      "epoch": 2.5172413793103448,
+      "grad_norm": 0.08516431599855423,
+      "learning_rate": 1.5776019568659338e-05,
+      "loss": 0.624,
+      "step": 438
+    },
+    {
+      "epoch": 2.5229885057471266,
+      "grad_norm": 0.08852159231901169,
+      "learning_rate": 1.5416794074090258e-05,
+      "loss": 0.6374,
+      "step": 439
+    },
+    {
+      "epoch": 2.528735632183908,
+      "grad_norm": 0.09616044908761978,
+      "learning_rate": 1.5061363796218785e-05,
+      "loss": 0.634,
+      "step": 440
+    },
+    {
+      "epoch": 2.528735632183908,
+      "eval_loss": 0.6419377326965332,
+      "eval_runtime": 416.5131,
+      "eval_samples_per_second": 23.764,
+      "eval_steps_per_second": 0.372,
+      "step": 440
+    },
+    {
+      "epoch": 2.5344827586206895,
+      "grad_norm": 0.1012992411851883,
+      "learning_rate": 1.4709744683068039e-05,
+      "loss": 0.6443,
+      "step": 441
+    },
+    {
+      "epoch": 2.5402298850574714,
+      "grad_norm": 0.102021224796772,
+      "learning_rate": 1.4361952511655618e-05,
+      "loss": 0.6111,
+      "step": 442
+    },
+    {
+      "epoch": 2.545977011494253,
+      "grad_norm": 0.08464264124631882,
+      "learning_rate": 1.4018002887285687e-05,
+      "loss": 0.6007,
+      "step": 443
+    },
+    {
+      "epoch": 2.5517241379310347,
+      "grad_norm": 0.0829034224152565,
+      "learning_rate": 1.3677911242848806e-05,
+      "loss": 0.6083,
+      "step": 444
+    },
+    {
+      "epoch": 2.557471264367816,
+      "grad_norm": 0.08752921968698502,
+      "learning_rate": 1.334169283812936e-05,
+      "loss": 0.6227,
+      "step": 445
+    },
+    {
+      "epoch": 2.5632183908045976,
+      "grad_norm": 0.080236054956913,
+      "learning_rate": 1.300936275912098e-05,
+      "loss": 0.6212,
+      "step": 446
+    },
+    {
+      "epoch": 2.5689655172413794,
+      "grad_norm": 0.08524277061223984,
+      "learning_rate": 1.2680935917349523e-05,
+      "loss": 0.5915,
+      "step": 447
+    },
+    {
+      "epoch": 2.574712643678161,
+      "grad_norm": 0.09109287708997726,
+      "learning_rate": 1.2356427049204122e-05,
+      "loss": 0.5972,
+      "step": 448
+    },
+    {
+      "epoch": 2.5804597701149428,
+      "grad_norm": 0.11969230324029922,
+      "learning_rate": 1.2035850715275865e-05,
+      "loss": 0.6358,
+      "step": 449
+    },
+    {
+      "epoch": 2.586206896551724,
+      "grad_norm": 0.08512509614229202,
+      "learning_rate": 1.1719221299704497e-05,
+      "loss": 0.6241,
+      "step": 450
+    },
+    {
+      "epoch": 2.586206896551724,
+      "eval_loss": 0.641758382320404,
+      "eval_runtime": 404.7765,
+      "eval_samples_per_second": 24.453,
+      "eval_steps_per_second": 0.383,
+      "step": 450
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 522,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.392870399484468e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /project/lt200252-wcbart/pumet/models/Qwen3-32B
+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

checkpoint-522/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /project/lt200252-wcbart/pumet/models/Qwen3-32B
+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

checkpoint-522/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/project/lt200252-wcbart/pumet/models/Qwen3-32B",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-522/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
+}

checkpoint-522/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 %}

checkpoint-522/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
+  }
+}

checkpoint-522/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
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 25600,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 64,
+  "model_type": "qwen3",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

dataset/dataset_dict.json

@@ -0,0 +1 @@
+{"splits": ["train", "validation"]}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.6412659883499146,
+    "eval_runtime": 413.4377,
+    "eval_samples_per_second": 23.941,
+    "eval_steps_per_second": 0.375
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.52.3"
+}

model-00001-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:504d2a880eebf9b143a30dcee5b771d2b0a4ad4982aa67a7849ebe679100b359
+size 4537714712

model-00004-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7726306ad162c12b6fe9a615896af1d06c2b5581c9b25fb646ae6b38ad0b8db
+size 4802607584

model-00006-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29eeb9e343d96cedec2c28dec7f71703f9f12084c7d046e4bb26de9e0f1d33b8
+size 4802607616

model-00012-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04f765b7ef6326108452139580cbe065fc7c1e6ca1040d499bd534283e86657d
+size 4802607616

model-00019-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e008b34e332710bedc58b86092567a92c6a62734a08970d679cadf36b49081f9
+size 4949365464

model-00024-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9945bae5807983b82092dacff21e6623153cdef5ce9b208b1d7533ed01e8837
+size 4802607616

model-00025-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a311443c000b751b73a686c3a7dc57a71fa4ccbc9f9300ad941e3c637e6ecc5
+size 4949365464

model-00026-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32c6459a0da2199f179dd2b694a035273ee9dc85753f8b8e3bc461b8653a84a4
+size 4802607616

model.safetensors.index.json

@@ -0,0 +1,714 @@
+{
+  "metadata": {
+    "total_size": 131048493056
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00027-of-00027.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00027.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00027.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00027.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00005-of-00027.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00005-of-00027.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00007-of-00027.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00027.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00007-of-00027.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00027.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00007-of-00027.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00007-of-00027.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00007-of-00027.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00007-of-00027.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00009-of-00027.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00027.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00009-of-00027.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00027.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00009-of-00027.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00009-of-00027.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00009-of-00027.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00009-of-00027.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00011-of-00027.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00027.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00011-of-00027.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00027.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00011-of-00027.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00011-of-00027.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00011-of-00027.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00011-of-00027.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00013-of-00027.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00013-of-00027.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00013-of-00027.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00027.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00013-of-00027.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00013-of-00027.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00027.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00027.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00013-of-00027.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00013-of-00027.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00015-of-00027.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00015-of-00027.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00015-of-00027.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00015-of-00027.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00015-of-00027.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00015-of-00027.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00015-of-00027.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00015-of-00027.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.36.self_attn.k_norm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.36.self_attn.q_norm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.37.self_attn.k_norm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.37.self_attn.q_norm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00017-of-00027.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00017-of-00027.safetensors",
+    "model.layers.38.self_attn.k_norm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.38.self_attn.q_norm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00017-of-00027.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00017-of-00027.safetensors",
+    "model.layers.39.self_attn.k_norm.weight": "model-00017-of-00027.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.39.self_attn.q_norm.weight": "model-00017-of-00027.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00027.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00027.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00003-of-00027.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00003-of-00027.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.40.self_attn.k_norm.weight": "model-00017-of-00027.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.40.self_attn.q_norm.weight": "model-00017-of-00027.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.41.self_attn.k_norm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.41.self_attn.q_norm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.42.self_attn.k_norm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.42.self_attn.q_norm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00019-of-00027.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00019-of-00027.safetensors",
+    "model.layers.43.self_attn.k_norm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.43.self_attn.q_norm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00019-of-00027.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00019-of-00027.safetensors",
+    "model.layers.44.self_attn.k_norm.weight": "model-00019-of-00027.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.44.self_attn.q_norm.weight": "model-00019-of-00027.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.45.self_attn.k_norm.weight": "model-00019-of-00027.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.45.self_attn.q_norm.weight": "model-00019-of-00027.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.46.self_attn.k_norm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.46.self_attn.q_norm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.47.self_attn.k_norm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.47.self_attn.q_norm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00021-of-00027.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00021-of-00027.safetensors",
+    "model.layers.48.self_attn.k_norm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.48.self_attn.q_norm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00021-of-00027.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00021-of-00027.safetensors",
+    "model.layers.49.self_attn.k_norm.weight": "model-00021-of-00027.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.49.self_attn.q_norm.weight": "model-00021-of-00027.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00003-of-00027.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00003-of-00027.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.50.self_attn.k_norm.weight": "model-00021-of-00027.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.50.self_attn.q_norm.weight": "model-00021-of-00027.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.51.self_attn.k_norm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.51.self_attn.q_norm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.52.self_attn.k_norm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.52.self_attn.q_norm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00023-of-00027.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00023-of-00027.safetensors",
+    "model.layers.53.self_attn.k_norm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.53.self_attn.q_norm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00023-of-00027.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00023-of-00027.safetensors",
+    "model.layers.54.self_attn.k_norm.weight": "model-00023-of-00027.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.54.self_attn.q_norm.weight": "model-00023-of-00027.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.55.self_attn.k_norm.weight": "model-00023-of-00027.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.55.self_attn.q_norm.weight": "model-00023-of-00027.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.56.self_attn.k_norm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.56.self_attn.q_norm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.57.self_attn.k_norm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.57.self_attn.q_norm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00025-of-00027.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00025-of-00027.safetensors",
+    "model.layers.58.self_attn.k_norm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.58.self_attn.q_norm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00025-of-00027.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00025-of-00027.safetensors",
+    "model.layers.59.self_attn.k_norm.weight": "model-00025-of-00027.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.59.self_attn.q_norm.weight": "model-00025-of-00027.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.60.self_attn.k_norm.weight": "model-00025-of-00027.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.60.self_attn.q_norm.weight": "model-00025-of-00027.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.61.self_attn.k_norm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.61.self_attn.q_norm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.62.self_attn.k_norm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.62.self_attn.q_norm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00027-of-00027.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00027-of-00027.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00027-of-00027.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00027-of-00027.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00027-of-00027.safetensors",
+    "model.layers.63.self_attn.k_norm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.63.self_attn.q_norm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00005-of-00027.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00027.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00027.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00027.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00005-of-00027.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00005-of-00027.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00027.safetensors",
+    "model.norm.weight": "model-00027-of-00027.safetensors"
+  }
+}

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 +1,240 @@
+{
+  "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": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 5.0940118456365744e+19,
+    "train_loss": 0.6584736234383565,
+    "train_runtime": 47270.2985,
+    "train_samples_per_second": 5.653,
+    "train_steps_per_second": 0.011
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a38d64247c50b3652298877b4e74d17364af0af1094483a594536051460c2437
+size 6161