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
+checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text

.ipynb_checkpoints/adapter_config-checkpoint.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/paddlejob/workspace/env_run/output/llm/Qwen3-8B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

.ipynb_checkpoints/all_results-checkpoint.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 2.0454733263908045e+17,
+    "train_loss": 5.729273645344288,
+    "train_runtime": 5128.0315,
+    "train_samples_per_second": 1.991,
+    "train_steps_per_second": 0.249
+}

.ipynb_checkpoints/tokenizer_config-checkpoint.json

@@ -0,0 +1,245 @@
+{
+  "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
+    },
+    "151669": {
+      "content": "<begin_of_query>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<end_of_query>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<begin_of_query>",
+    "<end_of_query>"
+  ],
+  "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
+}

.ipynb_checkpoints/train_results-checkpoint.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 2.0454733263908045e+17,
+    "train_loss": 5.729273645344288,
+    "train_runtime": 5128.0315,
+    "train_samples_per_second": 1.991,
+    "train_steps_per_second": 0.249
+}

README.md

@@ -0,0 +1,59 @@
+---
+library_name: peft
+license: other
+base_model: Qwen3-8B
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: decom_v2
+  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. -->
+
+# decom_v2
+
+This model is a fine-tuned version of [/root/paddlejob/workspace/env_run/output/llm/Qwen3-8B](https://huggingface.co//root/paddlejob/workspace/env_run/output/llm/Qwen3-8B) on the decom_v1 dataset.
+
+## 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: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
+- optimizer: Use 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
+
+
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.52.4
+- Pytorch 2.6.0+cu124
+- 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": "/root/paddlejob/workspace/env_run/output/llm/Qwen3-8B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

added_tokens.json

@@ -0,0 +1,30 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<begin_of_query>": 151669,
+  "<end_of_query>": 151670,
+  "<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 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 2.0454733263908045e+17,
+    "train_loss": 5.729273645344288,
+    "train_runtime": 5128.0315,
+    "train_samples_per_second": 1.991,
+    "train_steps_per_second": 0.249
+}

chat_template.jinja

@@ -0,0 +1,85 @@
+{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-1000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /root/paddlejob/workspace/env_run/output/llm/Qwen3-8B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

checkpoint-1000/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/paddlejob/workspace/env_run/output/llm/Qwen3-8B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1000/added_tokens.json

@@ -0,0 +1,30 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<begin_of_query>": 151669,
+  "<end_of_query>": 151670,
+  "<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-1000/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf46f466efb5332393249e0821061ec96c0f9a321d3dba615d0255414177c4c5
+size 175012218

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f1989f411175886ba805ce502108fc9b6398172c4842d91872d8f512caa8be0
+size 1064

checkpoint-1000/special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<begin_of_query>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<end_of_query>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "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-1000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f10755b54f711346fad6b550b761027777ad1f1ed4f69fff952825e0c610f6f
+size 11423038

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,245 @@
+{
+  "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
+    },
+    "151669": {
+      "content": "<begin_of_query>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<end_of_query>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<begin_of_query>",
+    "<end_of_query>"
+  ],
+  "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-1000/trainer_state.json

@@ -0,0 +1,734 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.347928298560094,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.023508668821627974,
+      "grad_norm": 84.37700653076172,
+      "learning_rate": 7.031250000000001e-06,
+      "loss": 115.85,
+      "step": 10
+    },
+    {
+      "epoch": 0.04701733764325595,
+      "grad_norm": 106.4520034790039,
+      "learning_rate": 1.484375e-05,
+      "loss": 116.5781,
+      "step": 20
+    },
+    {
+      "epoch": 0.07052600646488393,
+      "grad_norm": 130.89254760742188,
+      "learning_rate": 2.2656250000000002e-05,
+      "loss": 103.3281,
+      "step": 30
+    },
+    {
+      "epoch": 0.0940346752865119,
+      "grad_norm": 37.089256286621094,
+      "learning_rate": 3.0468750000000002e-05,
+      "loss": 60.0406,
+      "step": 40
+    },
+    {
+      "epoch": 0.11754334410813988,
+      "grad_norm": 44.051109313964844,
+      "learning_rate": 3.828125e-05,
+      "loss": 39.75,
+      "step": 50
+    },
+    {
+      "epoch": 0.14105201292976785,
+      "grad_norm": 43.561981201171875,
+      "learning_rate": 4.609375e-05,
+      "loss": 24.7984,
+      "step": 60
+    },
+    {
+      "epoch": 0.16456068175139582,
+      "grad_norm": 34.622520446777344,
+      "learning_rate": 5.3906250000000006e-05,
+      "loss": 11.9723,
+      "step": 70
+    },
+    {
+      "epoch": 0.1880693505730238,
+      "grad_norm": 22.26849937438965,
+      "learning_rate": 6.171875e-05,
+      "loss": 5.4578,
+      "step": 80
+    },
+    {
+      "epoch": 0.2115780193946518,
+      "grad_norm": 9.059814453125,
+      "learning_rate": 6.953125e-05,
+      "loss": 3.992,
+      "step": 90
+    },
+    {
+      "epoch": 0.23508668821627976,
+      "grad_norm": 4.332883834838867,
+      "learning_rate": 7.734375e-05,
+      "loss": 3.1058,
+      "step": 100
+    },
+    {
+      "epoch": 0.2585953570379077,
+      "grad_norm": 6.844908237457275,
+      "learning_rate": 8.515625e-05,
+      "loss": 2.6654,
+      "step": 110
+    },
+    {
+      "epoch": 0.2821040258595357,
+      "grad_norm": 4.539117813110352,
+      "learning_rate": 9.296875e-05,
+      "loss": 2.422,
+      "step": 120
+    },
+    {
+      "epoch": 0.3056126946811637,
+      "grad_norm": 3.098025321960449,
+      "learning_rate": 9.999981342914437e-05,
+      "loss": 2.1623,
+      "step": 130
+    },
+    {
+      "epoch": 0.32912136350279164,
+      "grad_norm": 1.3452321290969849,
+      "learning_rate": 9.997742661115932e-05,
+      "loss": 2.1429,
+      "step": 140
+    },
+    {
+      "epoch": 0.35263003232441964,
+      "grad_norm": 0.37226417660713196,
+      "learning_rate": 9.991774476447404e-05,
+      "loss": 2.1347,
+      "step": 150
+    },
+    {
+      "epoch": 0.3761387011460476,
+      "grad_norm": 3.523218870162964,
+      "learning_rate": 9.982081242591919e-05,
+      "loss": 2.0512,
+      "step": 160
+    },
+    {
+      "epoch": 0.3996473699676756,
+      "grad_norm": 0.33414289355278015,
+      "learning_rate": 9.968670193003843e-05,
+      "loss": 2.047,
+      "step": 170
+    },
+    {
+      "epoch": 0.4231560387893036,
+      "grad_norm": 0.24106919765472412,
+      "learning_rate": 9.951551335510978e-05,
+      "loss": 2.1046,
+      "step": 180
+    },
+    {
+      "epoch": 0.4466647076109315,
+      "grad_norm": 0.328752726316452,
+      "learning_rate": 9.930737444846331e-05,
+      "loss": 2.1397,
+      "step": 190
+    },
+    {
+      "epoch": 0.4701733764325595,
+      "grad_norm": 1.1409285068511963,
+      "learning_rate": 9.906244053115143e-05,
+      "loss": 2.1377,
+      "step": 200
+    },
+    {
+      "epoch": 0.49368204525418746,
+      "grad_norm": 0.0690290704369545,
+      "learning_rate": 9.87808943820424e-05,
+      "loss": 2.0992,
+      "step": 210
+    },
+    {
+      "epoch": 0.5171907140758154,
+      "grad_norm": 0.20527280867099762,
+      "learning_rate": 9.846294610142398e-05,
+      "loss": 2.1339,
+      "step": 220
+    },
+    {
+      "epoch": 0.5406993828974435,
+      "grad_norm": 0.3991909623146057,
+      "learning_rate": 9.810883295421864e-05,
+      "loss": 2.1176,
+      "step": 230
+    },
+    {
+      "epoch": 0.5642080517190714,
+      "grad_norm": 0.08950258791446686,
+      "learning_rate": 9.771881919292765e-05,
+      "loss": 2.0895,
+      "step": 240
+    },
+    {
+      "epoch": 0.5877167205406993,
+      "grad_norm": 0.17848969995975494,
+      "learning_rate": 9.729319586043591e-05,
+      "loss": 2.0877,
+      "step": 250
+    },
+    {
+      "epoch": 0.6112253893623274,
+      "grad_norm": 0.30160897970199585,
+      "learning_rate": 9.683228057282483e-05,
+      "loss": 2.0648,
+      "step": 260
+    },
+    {
+      "epoch": 0.6347340581839553,
+      "grad_norm": 0.11883804202079773,
+      "learning_rate": 9.63364172823554e-05,
+      "loss": 2.0591,
+      "step": 270
+    },
+    {
+      "epoch": 0.6582427270055833,
+      "grad_norm": 0.1619461327791214,
+      "learning_rate": 9.580597602079802e-05,
+      "loss": 2.1386,
+      "step": 280
+    },
+    {
+      "epoch": 0.6817513958272113,
+      "grad_norm": 0.11473017930984497,
+      "learning_rate": 9.524135262330098e-05,
+      "loss": 2.1028,
+      "step": 290
+    },
+    {
+      "epoch": 0.7052600646488393,
+      "grad_norm": 0.059143248945474625,
+      "learning_rate": 9.464296843300342e-05,
+      "loss": 2.0881,
+      "step": 300
+    },
+    {
+      "epoch": 0.7287687334704672,
+      "grad_norm": 0.1624162495136261,
+      "learning_rate": 9.401126998661328e-05,
+      "loss": 2.0971,
+      "step": 310
+    },
+    {
+      "epoch": 0.7522774022920952,
+      "grad_norm": 0.15460653603076935,
+      "learning_rate": 9.334672868118491e-05,
+      "loss": 2.1154,
+      "step": 320
+    },
+    {
+      "epoch": 0.7757860711137232,
+      "grad_norm": 0.4213317334651947,
+      "learning_rate": 9.26498404223449e-05,
+      "loss": 2.1113,
+      "step": 330
+    },
+    {
+      "epoch": 0.7992947399353512,
+      "grad_norm": 0.14529550075531006,
+      "learning_rate": 9.192112525422868e-05,
+      "loss": 2.0867,
+      "step": 340
+    },
+    {
+      "epoch": 0.8228034087569791,
+      "grad_norm": 0.06652400642633438,
+      "learning_rate": 9.116112697140418e-05,
+      "loss": 2.0807,
+      "step": 350
+    },
+    {
+      "epoch": 0.8463120775786072,
+      "grad_norm": 0.12574820220470428,
+      "learning_rate": 9.037041271307188e-05,
+      "loss": 2.1711,
+      "step": 360
+    },
+    {
+      "epoch": 0.8698207464002351,
+      "grad_norm": 0.10869150608778,
+      "learning_rate": 8.954957253984426e-05,
+      "loss": 2.1252,
+      "step": 370
+    },
+    {
+      "epoch": 0.893329415221863,
+      "grad_norm": 0.143524169921875,
+      "learning_rate": 8.869921899342056e-05,
+      "loss": 2.0468,
+      "step": 380
+    },
+    {
+      "epoch": 0.916838084043491,
+      "grad_norm": 0.27682727575302124,
+      "learning_rate": 8.781998663948513e-05,
+      "loss": 2.1023,
+      "step": 390
+    },
+    {
+      "epoch": 0.940346752865119,
+      "grad_norm": 0.08671136200428009,
+      "learning_rate": 8.691253159417074e-05,
+      "loss": 2.0991,
+      "step": 400
+    },
+    {
+      "epoch": 0.963855421686747,
+      "grad_norm": 0.14743109047412872,
+      "learning_rate": 8.597753103444016e-05,
+      "loss": 2.0858,
+      "step": 410
+    },
+    {
+      "epoch": 0.9873640905083749,
+      "grad_norm": 0.14369799196720123,
+      "learning_rate": 8.501568269275126e-05,
+      "loss": 2.1057,
+      "step": 420
+    },
+    {
+      "epoch": 1.0094034675286512,
+      "grad_norm": 0.09220755100250244,
+      "learning_rate": 8.40277043363831e-05,
+      "loss": 1.9405,
+      "step": 430
+    },
+    {
+      "epoch": 1.0329121363502791,
+      "grad_norm": 0.25697803497314453,
+      "learning_rate": 8.301433323181076e-05,
+      "loss": 2.1221,
+      "step": 440
+    },
+    {
+      "epoch": 1.056420805171907,
+      "grad_norm": 0.1321459412574768,
+      "learning_rate": 8.19763255945298e-05,
+      "loss": 2.1576,
+      "step": 450
+    },
+    {
+      "epoch": 1.079929473993535,
+      "grad_norm": 0.11310122162103653,
+      "learning_rate": 8.091445602473972e-05,
+      "loss": 2.0483,
+      "step": 460
+    },
+    {
+      "epoch": 1.1034381428151632,
+      "grad_norm": 0.08170254528522491,
+      "learning_rate": 7.982951692930829e-05,
+      "loss": 2.1367,
+      "step": 470
+    },
+    {
+      "epoch": 1.1269468116367911,
+      "grad_norm": 0.022492246702313423,
+      "learning_rate": 7.87223179304479e-05,
+      "loss": 2.1435,
+      "step": 480
+    },
+    {
+      "epoch": 1.150455480458419,
+      "grad_norm": 0.015893638134002686,
+      "learning_rate": 7.759368526154509e-05,
+      "loss": 2.0666,
+      "step": 490
+    },
+    {
+      "epoch": 1.173964149280047,
+      "grad_norm": 0.053727954626083374,
+      "learning_rate": 7.644446115059425e-05,
+      "loss": 2.0886,
+      "step": 500
+    },
+    {
+      "epoch": 1.197472818101675,
+      "grad_norm": 0.12717482447624207,
+      "learning_rate": 7.527550319169546e-05,
+      "loss": 2.1418,
+      "step": 510
+    },
+    {
+      "epoch": 1.2209814869233029,
+      "grad_norm": 0.030752327293157578,
+      "learning_rate": 7.408768370508576e-05,
+      "loss": 2.0688,
+      "step": 520
+    },
+    {
+      "epoch": 1.244490155744931,
+      "grad_norm": 0.07915918529033661,
+      "learning_rate": 7.288188908618102e-05,
+      "loss": 2.0857,
+      "step": 530
+    },
+    {
+      "epoch": 1.267998824566559,
+      "grad_norm": 0.09853250533342361,
+      "learning_rate": 7.165901914411435e-05,
+      "loss": 2.0392,
+      "step": 540
+    },
+    {
+      "epoch": 1.291507493388187,
+      "grad_norm": 0.21571961045265198,
+      "learning_rate": 7.041998643026511e-05,
+      "loss": 2.0921,
+      "step": 550
+    },
+    {
+      "epoch": 1.3150161622098149,
+      "grad_norm": 0.10290564596652985,
+      "learning_rate": 6.916571555727852e-05,
+      "loss": 2.0686,
+      "step": 560
+    },
+    {
+      "epoch": 1.3385248310314428,
+      "grad_norm": 0.08689925819635391,
+      "learning_rate": 6.789714250908533e-05,
+      "loss": 2.0845,
+      "step": 570
+    },
+    {
+      "epoch": 1.3620334998530708,
+      "grad_norm": 0.1267048567533493,
+      "learning_rate": 6.661521394243533e-05,
+      "loss": 2.1465,
+      "step": 580
+    },
+    {
+      "epoch": 1.3855421686746987,
+      "grad_norm": 0.18292003870010376,
+      "learning_rate": 6.532088648046677e-05,
+      "loss": 2.067,
+      "step": 590
+    },
+    {
+      "epoch": 1.4090508374963266,
+      "grad_norm": 0.051083244383335114,
+      "learning_rate": 6.401512599883818e-05,
+      "loss": 2.0697,
+      "step": 600
+    },
+    {
+      "epoch": 1.4325595063179548,
+      "grad_norm": 0.0492679663002491,
+      "learning_rate": 6.269890690495593e-05,
+      "loss": 2.1064,
+      "step": 610
+    },
+    {
+      "epoch": 1.4560681751395828,
+      "grad_norm": 0.051078781485557556,
+      "learning_rate": 6.137321141083468e-05,
+      "loss": 2.0533,
+      "step": 620
+    },
+    {
+      "epoch": 1.4795768439612107,
+      "grad_norm": 0.11715124547481537,
+      "learning_rate": 6.003902880013416e-05,
+      "loss": 2.1156,
+      "step": 630
+    },
+    {
+      "epoch": 1.5030855127828386,
+      "grad_norm": 0.041975561529397964,
+      "learning_rate": 5.869735468991854e-05,
+      "loss": 2.0543,
+      "step": 640
+    },
+    {
+      "epoch": 1.5265941816044668,
+      "grad_norm": 0.10740803927183151,
+      "learning_rate": 5.73491902876897e-05,
+      "loss": 2.0539,
+      "step": 650
+    },
+    {
+      "epoch": 1.5501028504260947,
+      "grad_norm": 0.07230595499277115,
+      "learning_rate": 5.599554164424859e-05,
+      "loss": 2.1078,
+      "step": 660
+    },
+    {
+      "epoch": 1.5736115192477227,
+      "grad_norm": 0.010545202530920506,
+      "learning_rate": 5.463741890294257e-05,
+      "loss": 2.1434,
+      "step": 670
+    },
+    {
+      "epoch": 1.5971201880693506,
+      "grad_norm": 0.0882532000541687,
+      "learning_rate": 5.327583554585842e-05,
+      "loss": 2.0696,
+      "step": 680
+    },
+    {
+      "epoch": 1.6206288568909786,
+      "grad_norm": 0.15730935335159302,
+      "learning_rate": 5.191180763752418e-05,
+      "loss": 2.0743,
+      "step": 690
+    },
+    {
+      "epoch": 1.6441375257126065,
+      "grad_norm": 0.16760171949863434,
+      "learning_rate": 5.054635306668355e-05,
+      "loss": 2.1303,
+      "step": 700
+    },
+    {
+      "epoch": 1.6676461945342345,
+      "grad_norm": 0.12746253609657288,
+      "learning_rate": 4.9180490786709335e-05,
+      "loss": 2.1359,
+      "step": 710
+    },
+    {
+      "epoch": 1.6911548633558624,
+      "grad_norm": 0.08576823770999908,
+      "learning_rate": 4.781524005522216e-05,
+      "loss": 2.0884,
+      "step": 720
+    },
+    {
+      "epoch": 1.7146635321774903,
+      "grad_norm": 0.01966356858611107,
+      "learning_rate": 4.645161967348223e-05,
+      "loss": 2.1102,
+      "step": 730
+    },
+    {
+      "epoch": 1.7381722009991183,
+      "grad_norm": 0.1140172928571701,
+      "learning_rate": 4.509064722612169e-05,
+      "loss": 2.134,
+      "step": 740
+    },
+    {
+      "epoch": 1.7616808698207465,
+      "grad_norm": 0.11263474822044373,
+      "learning_rate": 4.373333832178478e-05,
+      "loss": 2.212,
+      "step": 750
+    },
+    {
+      "epoch": 1.7851895386423744,
+      "grad_norm": 0.01955031044781208,
+      "learning_rate": 4.2380705835242716e-05,
+      "loss": 2.0876,
+      "step": 760
+    },
+    {
+      "epoch": 1.8086982074640023,
+      "grad_norm": 0.02556225284934044,
+      "learning_rate": 4.10337591515484e-05,
+      "loss": 2.064,
+      "step": 770
+    },
+    {
+      "epoch": 1.8322068762856303,
+      "grad_norm": 0.04094263166189194,
+      "learning_rate": 3.969350341279566e-05,
+      "loss": 2.1206,
+      "step": 780
+    },
+    {
+      "epoch": 1.8557155451072584,
+      "grad_norm": 0.0680101215839386,
+      "learning_rate": 3.8360938768044405e-05,
+      "loss": 2.0975,
+      "step": 790
+    },
+    {
+      "epoch": 1.8792242139288864,
+      "grad_norm": 0.08410263061523438,
+      "learning_rate": 3.7037059626971944e-05,
+      "loss": 2.0519,
+      "step": 800
+    },
+    {
+      "epoch": 1.9027328827505143,
+      "grad_norm": 0.02342092990875244,
+      "learning_rate": 3.572285391780734e-05,
+      "loss": 2.019,
+      "step": 810
+    },
+    {
+      "epoch": 1.9262415515721423,
+      "grad_norm": 0.02327684499323368,
+      "learning_rate": 3.441930235010211e-05,
+      "loss": 2.0966,
+      "step": 820
+    },
+    {
+      "epoch": 1.9497502203937702,
+      "grad_norm": 0.0357813723385334,
+      "learning_rate": 3.312737768288827e-05,
+      "loss": 2.0924,
+      "step": 830
+    },
+    {
+      "epoch": 1.9732588892153982,
+      "grad_norm": 0.07186655700206757,
+      "learning_rate": 3.184804399876886e-05,
+      "loss": 2.0315,
+      "step": 840
+    },
+    {
+      "epoch": 1.996767558037026,
+      "grad_norm": 0.09240284562110901,
+      "learning_rate": 3.0582255984483535e-05,
+      "loss": 2.0409,
+      "step": 850
+    },
+    {
+      "epoch": 2.0188069350573024,
+      "grad_norm": 0.04462951049208641,
+      "learning_rate": 2.9330958218485392e-05,
+      "loss": 1.9696,
+      "step": 860
+    },
+    {
+      "epoch": 2.0423156038789303,
+      "grad_norm": 0.029340475797653198,
+      "learning_rate": 2.8095084466061367e-05,
+      "loss": 2.1055,
+      "step": 870
+    },
+    {
+      "epoch": 2.0658242727005582,
+      "grad_norm": 0.048022590577602386,
+      "learning_rate": 2.6875556982521248e-05,
+      "loss": 2.0865,
+      "step": 880
+    },
+    {
+      "epoch": 2.089332941522186,
+      "grad_norm": 0.04670249670743942,
+      "learning_rate": 2.5673285824976575e-05,
+      "loss": 2.1081,
+      "step": 890
+    },
+    {
+      "epoch": 2.112841610343814,
+      "grad_norm": 0.015516964718699455,
+      "learning_rate": 2.4489168173221567e-05,
+      "loss": 2.1023,
+      "step": 900
+    },
+    {
+      "epoch": 2.136350279165442,
+      "grad_norm": 0.06762902438640594,
+      "learning_rate": 2.33240876602242e-05,
+      "loss": 2.0929,
+      "step": 910
+    },
+    {
+      "epoch": 2.15985894798707,
+      "grad_norm": 0.014990041963756084,
+      "learning_rate": 2.2178913712726045e-05,
+      "loss": 2.0817,
+      "step": 920
+    },
+    {
+      "epoch": 2.1833676168086984,
+      "grad_norm": 0.07376622408628464,
+      "learning_rate": 2.1054500902443423e-05,
+      "loss": 2.0868,
+      "step": 930
+    },
+    {
+      "epoch": 2.2068762856303263,
+      "grad_norm": 0.03299334645271301,
+      "learning_rate": 1.9951688308354133e-05,
+      "loss": 2.1123,
+      "step": 940
+    },
+    {
+      "epoch": 2.2303849544519543,
+      "grad_norm": 0.05409041792154312,
+      "learning_rate": 1.887129889054503e-05,
+      "loss": 2.051,
+      "step": 950
+    },
+    {
+      "epoch": 2.2538936232735822,
+      "grad_norm": 0.041158534586429596,
+      "learning_rate": 1.7814138876088566e-05,
+      "loss": 2.0458,
+      "step": 960
+    },
+    {
+      "epoch": 2.27740229209521,
+      "grad_norm": 0.03300878778100014,
+      "learning_rate": 1.6780997157405846e-05,
+      "loss": 2.0565,
+      "step": 970
+    },
+    {
+      "epoch": 2.300910960916838,
+      "grad_norm": 0.009902500547468662,
+      "learning_rate": 1.5772644703565565e-05,
+      "loss": 2.0952,
+      "step": 980
+    },
+    {
+      "epoch": 2.324419629738466,
+      "grad_norm": 0.44653964042663574,
+      "learning_rate": 1.4789833984957962e-05,
+      "loss": 2.0386,
+      "step": 990
+    },
+    {
+      "epoch": 2.347928298560094,
+      "grad_norm": 0.4100548326969147,
+      "learning_rate": 1.3833298411773276e-05,
+      "loss": 2.0977,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1278,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6003864496160768e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6d936976fffefe6cb91f5925c59c5521f6a35fc9eea849c6f37080cda334d4f
+size 5752

checkpoint-1278/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /root/paddlejob/workspace/env_run/output/llm/Qwen3-8B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

checkpoint-1278/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/paddlejob/workspace/env_run/output/llm/Qwen3-8B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1278/added_tokens.json

@@ -0,0 +1,30 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<begin_of_query>": 151669,
+  "<end_of_query>": 151670,
+  "<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-1278/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-1278/special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<begin_of_query>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<end_of_query>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "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-1278/tokenizer_config.json

@@ -0,0 +1,245 @@
+{
+  "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
+    },
+    "151669": {
+      "content": "<begin_of_query>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<end_of_query>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<begin_of_query>",
+    "<end_of_query>"
+  ],
+  "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-1278/trainer_state.json

@@ -0,0 +1,923 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1278,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.023508668821627974,
+      "grad_norm": 84.37700653076172,
+      "learning_rate": 7.031250000000001e-06,
+      "loss": 115.85,
+      "step": 10
+    },
+    {
+      "epoch": 0.04701733764325595,
+      "grad_norm": 106.4520034790039,
+      "learning_rate": 1.484375e-05,
+      "loss": 116.5781,
+      "step": 20
+    },
+    {
+      "epoch": 0.07052600646488393,
+      "grad_norm": 130.89254760742188,
+      "learning_rate": 2.2656250000000002e-05,
+      "loss": 103.3281,
+      "step": 30
+    },
+    {
+      "epoch": 0.0940346752865119,
+      "grad_norm": 37.089256286621094,
+      "learning_rate": 3.0468750000000002e-05,
+      "loss": 60.0406,
+      "step": 40
+    },
+    {
+      "epoch": 0.11754334410813988,
+      "grad_norm": 44.051109313964844,
+      "learning_rate": 3.828125e-05,
+      "loss": 39.75,
+      "step": 50
+    },
+    {
+      "epoch": 0.14105201292976785,
+      "grad_norm": 43.561981201171875,
+      "learning_rate": 4.609375e-05,
+      "loss": 24.7984,
+      "step": 60
+    },
+    {
+      "epoch": 0.16456068175139582,
+      "grad_norm": 34.622520446777344,
+      "learning_rate": 5.3906250000000006e-05,
+      "loss": 11.9723,
+      "step": 70
+    },
+    {
+      "epoch": 0.1880693505730238,
+      "grad_norm": 22.26849937438965,
+      "learning_rate": 6.171875e-05,
+      "loss": 5.4578,
+      "step": 80
+    },
+    {
+      "epoch": 0.2115780193946518,
+      "grad_norm": 9.059814453125,
+      "learning_rate": 6.953125e-05,
+      "loss": 3.992,
+      "step": 90
+    },
+    {
+      "epoch": 0.23508668821627976,
+      "grad_norm": 4.332883834838867,
+      "learning_rate": 7.734375e-05,
+      "loss": 3.1058,
+      "step": 100
+    },
+    {
+      "epoch": 0.2585953570379077,
+      "grad_norm": 6.844908237457275,
+      "learning_rate": 8.515625e-05,
+      "loss": 2.6654,
+      "step": 110
+    },
+    {
+      "epoch": 0.2821040258595357,
+      "grad_norm": 4.539117813110352,
+      "learning_rate": 9.296875e-05,
+      "loss": 2.422,
+      "step": 120
+    },
+    {
+      "epoch": 0.3056126946811637,
+      "grad_norm": 3.098025321960449,
+      "learning_rate": 9.999981342914437e-05,
+      "loss": 2.1623,
+      "step": 130
+    },
+    {
+      "epoch": 0.32912136350279164,
+      "grad_norm": 1.3452321290969849,
+      "learning_rate": 9.997742661115932e-05,
+      "loss": 2.1429,
+      "step": 140
+    },
+    {
+      "epoch": 0.35263003232441964,
+      "grad_norm": 0.37226417660713196,
+      "learning_rate": 9.991774476447404e-05,
+      "loss": 2.1347,
+      "step": 150
+    },
+    {
+      "epoch": 0.3761387011460476,
+      "grad_norm": 3.523218870162964,
+      "learning_rate": 9.982081242591919e-05,
+      "loss": 2.0512,
+      "step": 160
+    },
+    {
+      "epoch": 0.3996473699676756,
+      "grad_norm": 0.33414289355278015,
+      "learning_rate": 9.968670193003843e-05,
+      "loss": 2.047,
+      "step": 170
+    },
+    {
+      "epoch": 0.4231560387893036,
+      "grad_norm": 0.24106919765472412,
+      "learning_rate": 9.951551335510978e-05,
+      "loss": 2.1046,
+      "step": 180
+    },
+    {
+      "epoch": 0.4466647076109315,
+      "grad_norm": 0.328752726316452,
+      "learning_rate": 9.930737444846331e-05,
+      "loss": 2.1397,
+      "step": 190
+    },
+    {
+      "epoch": 0.4701733764325595,
+      "grad_norm": 1.1409285068511963,
+      "learning_rate": 9.906244053115143e-05,
+      "loss": 2.1377,
+      "step": 200
+    },
+    {
+      "epoch": 0.49368204525418746,
+      "grad_norm": 0.0690290704369545,
+      "learning_rate": 9.87808943820424e-05,
+      "loss": 2.0992,
+      "step": 210
+    },
+    {
+      "epoch": 0.5171907140758154,
+      "grad_norm": 0.20527280867099762,
+      "learning_rate": 9.846294610142398e-05,
+      "loss": 2.1339,
+      "step": 220
+    },
+    {
+      "epoch": 0.5406993828974435,
+      "grad_norm": 0.3991909623146057,
+      "learning_rate": 9.810883295421864e-05,
+      "loss": 2.1176,
+      "step": 230
+    },
+    {
+      "epoch": 0.5642080517190714,
+      "grad_norm": 0.08950258791446686,
+      "learning_rate": 9.771881919292765e-05,
+      "loss": 2.0895,
+      "step": 240
+    },
+    {
+      "epoch": 0.5877167205406993,
+      "grad_norm": 0.17848969995975494,
+      "learning_rate": 9.729319586043591e-05,
+      "loss": 2.0877,
+      "step": 250
+    },
+    {
+      "epoch": 0.6112253893623274,
+      "grad_norm": 0.30160897970199585,
+      "learning_rate": 9.683228057282483e-05,
+      "loss": 2.0648,
+      "step": 260
+    },
+    {
+      "epoch": 0.6347340581839553,
+      "grad_norm": 0.11883804202079773,
+      "learning_rate": 9.63364172823554e-05,
+      "loss": 2.0591,
+      "step": 270
+    },
+    {
+      "epoch": 0.6582427270055833,
+      "grad_norm": 0.1619461327791214,
+      "learning_rate": 9.580597602079802e-05,
+      "loss": 2.1386,
+      "step": 280
+    },
+    {
+      "epoch": 0.6817513958272113,
+      "grad_norm": 0.11473017930984497,
+      "learning_rate": 9.524135262330098e-05,
+      "loss": 2.1028,
+      "step": 290
+    },
+    {
+      "epoch": 0.7052600646488393,
+      "grad_norm": 0.059143248945474625,
+      "learning_rate": 9.464296843300342e-05,
+      "loss": 2.0881,
+      "step": 300
+    },
+    {
+      "epoch": 0.7287687334704672,
+      "grad_norm": 0.1624162495136261,
+      "learning_rate": 9.401126998661328e-05,
+      "loss": 2.0971,
+      "step": 310
+    },
+    {
+      "epoch": 0.7522774022920952,
+      "grad_norm": 0.15460653603076935,
+      "learning_rate": 9.334672868118491e-05,
+      "loss": 2.1154,
+      "step": 320
+    },
+    {
+      "epoch": 0.7757860711137232,
+      "grad_norm": 0.4213317334651947,
+      "learning_rate": 9.26498404223449e-05,
+      "loss": 2.1113,
+      "step": 330
+    },
+    {
+      "epoch": 0.7992947399353512,
+      "grad_norm": 0.14529550075531006,
+      "learning_rate": 9.192112525422868e-05,
+      "loss": 2.0867,
+      "step": 340
+    },
+    {
+      "epoch": 0.8228034087569791,
+      "grad_norm": 0.06652400642633438,
+      "learning_rate": 9.116112697140418e-05,
+      "loss": 2.0807,
+      "step": 350
+    },
+    {
+      "epoch": 0.8463120775786072,
+      "grad_norm": 0.12574820220470428,
+      "learning_rate": 9.037041271307188e-05,
+      "loss": 2.1711,
+      "step": 360
+    },
+    {
+      "epoch": 0.8698207464002351,
+      "grad_norm": 0.10869150608778,
+      "learning_rate": 8.954957253984426e-05,
+      "loss": 2.1252,
+      "step": 370
+    },
+    {
+      "epoch": 0.893329415221863,
+      "grad_norm": 0.143524169921875,
+      "learning_rate": 8.869921899342056e-05,
+      "loss": 2.0468,
+      "step": 380
+    },
+    {
+      "epoch": 0.916838084043491,
+      "grad_norm": 0.27682727575302124,
+      "learning_rate": 8.781998663948513e-05,
+      "loss": 2.1023,
+      "step": 390
+    },
+    {
+      "epoch": 0.940346752865119,
+      "grad_norm": 0.08671136200428009,
+      "learning_rate": 8.691253159417074e-05,
+      "loss": 2.0991,
+      "step": 400
+    },
+    {
+      "epoch": 0.963855421686747,
+      "grad_norm": 0.14743109047412872,
+      "learning_rate": 8.597753103444016e-05,
+      "loss": 2.0858,
+      "step": 410
+    },
+    {
+      "epoch": 0.9873640905083749,
+      "grad_norm": 0.14369799196720123,
+      "learning_rate": 8.501568269275126e-05,
+      "loss": 2.1057,
+      "step": 420
+    },
+    {
+      "epoch": 1.0094034675286512,
+      "grad_norm": 0.09220755100250244,
+      "learning_rate": 8.40277043363831e-05,
+      "loss": 1.9405,
+      "step": 430
+    },
+    {
+      "epoch": 1.0329121363502791,
+      "grad_norm": 0.25697803497314453,
+      "learning_rate": 8.301433323181076e-05,
+      "loss": 2.1221,
+      "step": 440
+    },
+    {
+      "epoch": 1.056420805171907,
+      "grad_norm": 0.1321459412574768,
+      "learning_rate": 8.19763255945298e-05,
+      "loss": 2.1576,
+      "step": 450
+    },
+    {
+      "epoch": 1.079929473993535,
+      "grad_norm": 0.11310122162103653,
+      "learning_rate": 8.091445602473972e-05,
+      "loss": 2.0483,
+      "step": 460
+    },
+    {
+      "epoch": 1.1034381428151632,
+      "grad_norm": 0.08170254528522491,
+      "learning_rate": 7.982951692930829e-05,
+      "loss": 2.1367,
+      "step": 470
+    },
+    {
+      "epoch": 1.1269468116367911,
+      "grad_norm": 0.022492246702313423,
+      "learning_rate": 7.87223179304479e-05,
+      "loss": 2.1435,
+      "step": 480
+    },
+    {
+      "epoch": 1.150455480458419,
+      "grad_norm": 0.015893638134002686,
+      "learning_rate": 7.759368526154509e-05,
+      "loss": 2.0666,
+      "step": 490
+    },
+    {
+      "epoch": 1.173964149280047,
+      "grad_norm": 0.053727954626083374,
+      "learning_rate": 7.644446115059425e-05,
+      "loss": 2.0886,
+      "step": 500
+    },
+    {
+      "epoch": 1.197472818101675,
+      "grad_norm": 0.12717482447624207,
+      "learning_rate": 7.527550319169546e-05,
+      "loss": 2.1418,
+      "step": 510
+    },
+    {
+      "epoch": 1.2209814869233029,
+      "grad_norm": 0.030752327293157578,
+      "learning_rate": 7.408768370508576e-05,
+      "loss": 2.0688,
+      "step": 520
+    },
+    {
+      "epoch": 1.244490155744931,
+      "grad_norm": 0.07915918529033661,
+      "learning_rate": 7.288188908618102e-05,
+      "loss": 2.0857,
+      "step": 530
+    },
+    {
+      "epoch": 1.267998824566559,
+      "grad_norm": 0.09853250533342361,
+      "learning_rate": 7.165901914411435e-05,
+      "loss": 2.0392,
+      "step": 540
+    },
+    {
+      "epoch": 1.291507493388187,
+      "grad_norm": 0.21571961045265198,
+      "learning_rate": 7.041998643026511e-05,
+      "loss": 2.0921,
+      "step": 550
+    },
+    {
+      "epoch": 1.3150161622098149,
+      "grad_norm": 0.10290564596652985,
+      "learning_rate": 6.916571555727852e-05,
+      "loss": 2.0686,
+      "step": 560
+    },
+    {
+      "epoch": 1.3385248310314428,
+      "grad_norm": 0.08689925819635391,
+      "learning_rate": 6.789714250908533e-05,
+      "loss": 2.0845,
+      "step": 570
+    },
+    {
+      "epoch": 1.3620334998530708,
+      "grad_norm": 0.1267048567533493,
+      "learning_rate": 6.661521394243533e-05,
+      "loss": 2.1465,
+      "step": 580
+    },
+    {
+      "epoch": 1.3855421686746987,
+      "grad_norm": 0.18292003870010376,
+      "learning_rate": 6.532088648046677e-05,
+      "loss": 2.067,
+      "step": 590
+    },
+    {
+      "epoch": 1.4090508374963266,
+      "grad_norm": 0.051083244383335114,
+      "learning_rate": 6.401512599883818e-05,
+      "loss": 2.0697,
+      "step": 600
+    },
+    {
+      "epoch": 1.4325595063179548,
+      "grad_norm": 0.0492679663002491,
+      "learning_rate": 6.269890690495593e-05,
+      "loss": 2.1064,
+      "step": 610
+    },
+    {
+      "epoch": 1.4560681751395828,
+      "grad_norm": 0.051078781485557556,
+      "learning_rate": 6.137321141083468e-05,
+      "loss": 2.0533,
+      "step": 620
+    },
+    {
+      "epoch": 1.4795768439612107,
+      "grad_norm": 0.11715124547481537,
+      "learning_rate": 6.003902880013416e-05,
+      "loss": 2.1156,
+      "step": 630
+    },
+    {
+      "epoch": 1.5030855127828386,
+      "grad_norm": 0.041975561529397964,
+      "learning_rate": 5.869735468991854e-05,
+      "loss": 2.0543,
+      "step": 640
+    },
+    {
+      "epoch": 1.5265941816044668,
+      "grad_norm": 0.10740803927183151,
+      "learning_rate": 5.73491902876897e-05,
+      "loss": 2.0539,
+      "step": 650
+    },
+    {
+      "epoch": 1.5501028504260947,
+      "grad_norm": 0.07230595499277115,
+      "learning_rate": 5.599554164424859e-05,
+      "loss": 2.1078,
+      "step": 660
+    },
+    {
+      "epoch": 1.5736115192477227,
+      "grad_norm": 0.010545202530920506,
+      "learning_rate": 5.463741890294257e-05,
+      "loss": 2.1434,
+      "step": 670
+    },
+    {
+      "epoch": 1.5971201880693506,
+      "grad_norm": 0.0882532000541687,
+      "learning_rate": 5.327583554585842e-05,
+      "loss": 2.0696,
+      "step": 680
+    },
+    {
+      "epoch": 1.6206288568909786,
+      "grad_norm": 0.15730935335159302,
+      "learning_rate": 5.191180763752418e-05,
+      "loss": 2.0743,
+      "step": 690
+    },
+    {
+      "epoch": 1.6441375257126065,
+      "grad_norm": 0.16760171949863434,
+      "learning_rate": 5.054635306668355e-05,
+      "loss": 2.1303,
+      "step": 700
+    },
+    {
+      "epoch": 1.6676461945342345,
+      "grad_norm": 0.12746253609657288,
+      "learning_rate": 4.9180490786709335e-05,
+      "loss": 2.1359,
+      "step": 710
+    },
+    {
+      "epoch": 1.6911548633558624,
+      "grad_norm": 0.08576823770999908,
+      "learning_rate": 4.781524005522216e-05,
+      "loss": 2.0884,
+      "step": 720
+    },
+    {
+      "epoch": 1.7146635321774903,
+      "grad_norm": 0.01966356858611107,
+      "learning_rate": 4.645161967348223e-05,
+      "loss": 2.1102,
+      "step": 730
+    },
+    {
+      "epoch": 1.7381722009991183,
+      "grad_norm": 0.1140172928571701,
+      "learning_rate": 4.509064722612169e-05,
+      "loss": 2.134,
+      "step": 740
+    },
+    {
+      "epoch": 1.7616808698207465,
+      "grad_norm": 0.11263474822044373,
+      "learning_rate": 4.373333832178478e-05,
+      "loss": 2.212,
+      "step": 750
+    },
+    {
+      "epoch": 1.7851895386423744,
+      "grad_norm": 0.01955031044781208,
+      "learning_rate": 4.2380705835242716e-05,
+      "loss": 2.0876,
+      "step": 760
+    },
+    {
+      "epoch": 1.8086982074640023,
+      "grad_norm": 0.02556225284934044,
+      "learning_rate": 4.10337591515484e-05,
+      "loss": 2.064,
+      "step": 770
+    },
+    {
+      "epoch": 1.8322068762856303,
+      "grad_norm": 0.04094263166189194,
+      "learning_rate": 3.969350341279566e-05,
+      "loss": 2.1206,
+      "step": 780
+    },
+    {
+      "epoch": 1.8557155451072584,
+      "grad_norm": 0.0680101215839386,
+      "learning_rate": 3.8360938768044405e-05,
+      "loss": 2.0975,
+      "step": 790
+    },
+    {
+      "epoch": 1.8792242139288864,
+      "grad_norm": 0.08410263061523438,
+      "learning_rate": 3.7037059626971944e-05,
+      "loss": 2.0519,
+      "step": 800
+    },
+    {
+      "epoch": 1.9027328827505143,
+      "grad_norm": 0.02342092990875244,
+      "learning_rate": 3.572285391780734e-05,
+      "loss": 2.019,
+      "step": 810
+    },
+    {
+      "epoch": 1.9262415515721423,
+      "grad_norm": 0.02327684499323368,
+      "learning_rate": 3.441930235010211e-05,
+      "loss": 2.0966,
+      "step": 820
+    },
+    {
+      "epoch": 1.9497502203937702,
+      "grad_norm": 0.0357813723385334,
+      "learning_rate": 3.312737768288827e-05,
+      "loss": 2.0924,
+      "step": 830
+    },
+    {
+      "epoch": 1.9732588892153982,
+      "grad_norm": 0.07186655700206757,
+      "learning_rate": 3.184804399876886e-05,
+      "loss": 2.0315,
+      "step": 840
+    },
+    {
+      "epoch": 1.996767558037026,
+      "grad_norm": 0.09240284562110901,
+      "learning_rate": 3.0582255984483535e-05,
+      "loss": 2.0409,
+      "step": 850
+    },
+    {
+      "epoch": 2.0188069350573024,
+      "grad_norm": 0.04462951049208641,
+      "learning_rate": 2.9330958218485392e-05,
+      "loss": 1.9696,
+      "step": 860
+    },
+    {
+      "epoch": 2.0423156038789303,
+      "grad_norm": 0.029340475797653198,
+      "learning_rate": 2.8095084466061367e-05,
+      "loss": 2.1055,
+      "step": 870
+    },
+    {
+      "epoch": 2.0658242727005582,
+      "grad_norm": 0.048022590577602386,
+      "learning_rate": 2.6875556982521248e-05,
+      "loss": 2.0865,
+      "step": 880
+    },
+    {
+      "epoch": 2.089332941522186,
+      "grad_norm": 0.04670249670743942,
+      "learning_rate": 2.5673285824976575e-05,
+      "loss": 2.1081,
+      "step": 890
+    },
+    {
+      "epoch": 2.112841610343814,
+      "grad_norm": 0.015516964718699455,
+      "learning_rate": 2.4489168173221567e-05,
+      "loss": 2.1023,
+      "step": 900
+    },
+    {
+      "epoch": 2.136350279165442,
+      "grad_norm": 0.06762902438640594,
+      "learning_rate": 2.33240876602242e-05,
+      "loss": 2.0929,
+      "step": 910
+    },
+    {
+      "epoch": 2.15985894798707,
+      "grad_norm": 0.014990041963756084,
+      "learning_rate": 2.2178913712726045e-05,
+      "loss": 2.0817,
+      "step": 920
+    },
+    {
+      "epoch": 2.1833676168086984,
+      "grad_norm": 0.07376622408628464,
+      "learning_rate": 2.1054500902443423e-05,
+      "loss": 2.0868,
+      "step": 930
+    },
+    {
+      "epoch": 2.2068762856303263,
+      "grad_norm": 0.03299334645271301,
+      "learning_rate": 1.9951688308354133e-05,
+      "loss": 2.1123,
+      "step": 940
+    },
+    {
+      "epoch": 2.2303849544519543,
+      "grad_norm": 0.05409041792154312,
+      "learning_rate": 1.887129889054503e-05,
+      "loss": 2.051,
+      "step": 950
+    },
+    {
+      "epoch": 2.2538936232735822,
+      "grad_norm": 0.041158534586429596,
+      "learning_rate": 1.7814138876088566e-05,
+      "loss": 2.0458,
+      "step": 960
+    },
+    {
+      "epoch": 2.27740229209521,
+      "grad_norm": 0.03300878778100014,
+      "learning_rate": 1.6780997157405846e-05,
+      "loss": 2.0565,
+      "step": 970
+    },
+    {
+      "epoch": 2.300910960916838,
+      "grad_norm": 0.009902500547468662,
+      "learning_rate": 1.5772644703565565e-05,
+      "loss": 2.0952,
+      "step": 980
+    },
+    {
+      "epoch": 2.324419629738466,
+      "grad_norm": 0.44653964042663574,
+      "learning_rate": 1.4789833984957962e-05,
+      "loss": 2.0386,
+      "step": 990
+    },
+    {
+      "epoch": 2.347928298560094,
+      "grad_norm": 0.4100548326969147,
+      "learning_rate": 1.3833298411773276e-05,
+      "loss": 2.0977,
+      "step": 1000
+    },
+    {
+      "epoch": 2.371436967381722,
+      "grad_norm": 0.00745609262958169,
+      "learning_rate": 1.2903751786703482e-05,
+      "loss": 2.0503,
+      "step": 1010
+    },
+    {
+      "epoch": 2.39494563620335,
+      "grad_norm": 0.05212165042757988,
+      "learning_rate": 1.2001887772276076e-05,
+      "loss": 2.1437,
+      "step": 1020
+    },
+    {
+      "epoch": 2.418454305024978,
+      "grad_norm": 0.0367308035492897,
+      "learning_rate": 1.1128379373217058e-05,
+      "loss": 2.0911,
+      "step": 1030
+    },
+    {
+      "epoch": 2.4419629738466058,
+      "grad_norm": 0.02135683037340641,
+      "learning_rate": 1.028387843422952e-05,
+      "loss": 2.1183,
+      "step": 1040
+    },
+    {
+      "epoch": 2.465471642668234,
+      "grad_norm": 0.02447247877717018,
+      "learning_rate": 9.469015153562855e-06,
+      "loss": 2.1205,
+      "step": 1050
+    },
+    {
+      "epoch": 2.488980311489862,
+      "grad_norm": 0.011414138600230217,
+      "learning_rate": 8.684397612735024e-06,
+      "loss": 2.0027,
+      "step": 1060
+    },
+    {
+      "epoch": 2.51248898031149,
+      "grad_norm": 0.0028556822799146175,
+      "learning_rate": 7.930611322759462e-06,
+      "loss": 2.0682,
+      "step": 1070
+    },
+    {
+      "epoch": 2.535997649133118,
+      "grad_norm": 0.008712991140782833,
+      "learning_rate": 7.2082187872147935e-06,
+      "loss": 2.0895,
+      "step": 1080
+    },
+    {
+      "epoch": 2.559506317954746,
+      "grad_norm": 0.03148069605231285,
+      "learning_rate": 6.517759082483543e-06,
+      "loss": 2.1298,
+      "step": 1090
+    },
+    {
+      "epoch": 2.583014986776374,
+      "grad_norm": 0.03679489344358444,
+      "learning_rate": 5.8597474554731745e-06,
+      "loss": 2.0837,
+      "step": 1100
+    },
+    {
+      "epoch": 2.606523655598002,
+      "grad_norm": 0.05236874148249626,
+      "learning_rate": 5.234674939119538e-06,
+      "loss": 2.1486,
+      "step": 1110
+    },
+    {
+      "epoch": 2.6300323244196298,
+      "grad_norm": 0.03369889780879021,
+      "learning_rate": 4.643007985959641e-06,
+      "loss": 2.0959,
+      "step": 1120
+    },
+    {
+      "epoch": 2.6535409932412577,
+      "grad_norm": 0.006195698864758015,
+      "learning_rate": 4.085188120047362e-06,
+      "loss": 2.0439,
+      "step": 1130
+    },
+    {
+      "epoch": 2.6770496620628856,
+      "grad_norm": 0.03900829330086708,
+      "learning_rate": 3.5616316074715995e-06,
+      "loss": 2.111,
+      "step": 1140
+    },
+    {
+      "epoch": 2.7005583308845136,
+      "grad_norm": 0.00790059007704258,
+      "learning_rate": 3.0727291457229303e-06,
+      "loss": 2.1078,
+      "step": 1150
+    },
+    {
+      "epoch": 2.7240669997061415,
+      "grad_norm": 0.017095139250159264,
+      "learning_rate": 2.618845572140527e-06,
+      "loss": 2.1248,
+      "step": 1160
+    },
+    {
+      "epoch": 2.7475756685277695,
+      "grad_norm": 0.006935155484825373,
+      "learning_rate": 2.2003195916567855e-06,
+      "loss": 2.0573,
+      "step": 1170
+    },
+    {
+      "epoch": 2.7710843373493974,
+      "grad_norm": 0.01475539617240429,
+      "learning_rate": 1.8174635240431282e-06,
+      "loss": 2.0218,
+      "step": 1180
+    },
+    {
+      "epoch": 2.7945930061710254,
+      "grad_norm": 0.08390510082244873,
+      "learning_rate": 1.4705630708451712e-06,
+      "loss": 2.0729,
+      "step": 1190
+    },
+    {
+      "epoch": 2.8181016749926533,
+      "grad_norm": 0.04823232442140579,
+      "learning_rate": 1.1598771021816058e-06,
+      "loss": 2.0432,
+      "step": 1200
+    },
+    {
+      "epoch": 2.8416103438142817,
+      "grad_norm": 0.017384668812155724,
+      "learning_rate": 8.856374635655695e-07,
+      "loss": 2.1005,
+      "step": 1210
+    },
+    {
+      "epoch": 2.8651190126359096,
+      "grad_norm": 0.016273437067866325,
+      "learning_rate": 6.480488028928422e-07,
+      "loss": 2.1043,
+      "step": 1220
+    },
+    {
+      "epoch": 2.8886276814575376,
+      "grad_norm": 0.004406425170600414,
+      "learning_rate": 4.47288417725944e-07,
+      "loss": 2.1214,
+      "step": 1230
+    },
+    {
+      "epoch": 2.9121363502791655,
+      "grad_norm": 0.04330357536673546,
+      "learning_rate": 2.8350612298801427e-07,
+      "loss": 2.0679,
+      "step": 1240
+    },
+    {
+      "epoch": 2.9356450191007935,
+      "grad_norm": 0.005912340711802244,
+      "learning_rate": 1.5682413916531802e-07,
+      "loss": 2.1937,
+      "step": 1250
+    },
+    {
+      "epoch": 2.9591536879224214,
+      "grad_norm": 0.021025869995355606,
+      "learning_rate": 6.733700110174157e-08,
+      "loss": 2.1239,
+      "step": 1260
+    },
+    {
+      "epoch": 2.9826623567440493,
+      "grad_norm": 0.006763559300452471,
+      "learning_rate": 1.511148745335089e-08,
+      "loss": 2.1434,
+      "step": 1270
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1278,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.0454733263908045e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /root/paddlejob/workspace/env_run/output/llm/Qwen3-8B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

checkpoint-500/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/paddlejob/workspace/env_run/output/llm/Qwen3-8B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-500/added_tokens.json

@@ -0,0 +1,30 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<begin_of_query>": 151669,
+  "<end_of_query>": 151670,
+  "<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-500/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e27bd1ce46de9eaac0e09e06cceca450b15d455644787f193b6224ddc1f8e10
+size 175012218

checkpoint-500/special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<begin_of_query>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<end_of_query>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "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-500/tokenizer_config.json

@@ -0,0 +1,245 @@
+{
+  "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
+    },
+    "151669": {
+      "content": "<begin_of_query>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<end_of_query>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<begin_of_query>",
+    "<end_of_query>"
+  ],
+  "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-500/trainer_state.json

@@ -0,0 +1,384 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.173964149280047,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.023508668821627974,
+      "grad_norm": 84.37700653076172,
+      "learning_rate": 7.031250000000001e-06,
+      "loss": 115.85,
+      "step": 10
+    },
+    {
+      "epoch": 0.04701733764325595,
+      "grad_norm": 106.4520034790039,
+      "learning_rate": 1.484375e-05,
+      "loss": 116.5781,
+      "step": 20
+    },
+    {
+      "epoch": 0.07052600646488393,
+      "grad_norm": 130.89254760742188,
+      "learning_rate": 2.2656250000000002e-05,
+      "loss": 103.3281,
+      "step": 30
+    },
+    {
+      "epoch": 0.0940346752865119,
+      "grad_norm": 37.089256286621094,
+      "learning_rate": 3.0468750000000002e-05,
+      "loss": 60.0406,
+      "step": 40
+    },
+    {
+      "epoch": 0.11754334410813988,
+      "grad_norm": 44.051109313964844,
+      "learning_rate": 3.828125e-05,
+      "loss": 39.75,
+      "step": 50
+    },
+    {
+      "epoch": 0.14105201292976785,
+      "grad_norm": 43.561981201171875,
+      "learning_rate": 4.609375e-05,
+      "loss": 24.7984,
+      "step": 60
+    },
+    {
+      "epoch": 0.16456068175139582,
+      "grad_norm": 34.622520446777344,
+      "learning_rate": 5.3906250000000006e-05,
+      "loss": 11.9723,
+      "step": 70
+    },
+    {
+      "epoch": 0.1880693505730238,
+      "grad_norm": 22.26849937438965,
+      "learning_rate": 6.171875e-05,
+      "loss": 5.4578,
+      "step": 80
+    },
+    {
+      "epoch": 0.2115780193946518,
+      "grad_norm": 9.059814453125,
+      "learning_rate": 6.953125e-05,
+      "loss": 3.992,
+      "step": 90
+    },
+    {
+      "epoch": 0.23508668821627976,
+      "grad_norm": 4.332883834838867,
+      "learning_rate": 7.734375e-05,
+      "loss": 3.1058,
+      "step": 100
+    },
+    {
+      "epoch": 0.2585953570379077,
+      "grad_norm": 6.844908237457275,
+      "learning_rate": 8.515625e-05,
+      "loss": 2.6654,
+      "step": 110
+    },
+    {
+      "epoch": 0.2821040258595357,
+      "grad_norm": 4.539117813110352,
+      "learning_rate": 9.296875e-05,
+      "loss": 2.422,
+      "step": 120
+    },
+    {
+      "epoch": 0.3056126946811637,
+      "grad_norm": 3.098025321960449,
+      "learning_rate": 9.999981342914437e-05,
+      "loss": 2.1623,
+      "step": 130
+    },
+    {
+      "epoch": 0.32912136350279164,
+      "grad_norm": 1.3452321290969849,
+      "learning_rate": 9.997742661115932e-05,
+      "loss": 2.1429,
+      "step": 140
+    },
+    {
+      "epoch": 0.35263003232441964,
+      "grad_norm": 0.37226417660713196,
+      "learning_rate": 9.991774476447404e-05,
+      "loss": 2.1347,
+      "step": 150
+    },
+    {
+      "epoch": 0.3761387011460476,
+      "grad_norm": 3.523218870162964,
+      "learning_rate": 9.982081242591919e-05,
+      "loss": 2.0512,
+      "step": 160
+    },
+    {
+      "epoch": 0.3996473699676756,
+      "grad_norm": 0.33414289355278015,
+      "learning_rate": 9.968670193003843e-05,
+      "loss": 2.047,
+      "step": 170
+    },
+    {
+      "epoch": 0.4231560387893036,
+      "grad_norm": 0.24106919765472412,
+      "learning_rate": 9.951551335510978e-05,
+      "loss": 2.1046,
+      "step": 180
+    },
+    {
+      "epoch": 0.4466647076109315,
+      "grad_norm": 0.328752726316452,
+      "learning_rate": 9.930737444846331e-05,
+      "loss": 2.1397,
+      "step": 190
+    },
+    {
+      "epoch": 0.4701733764325595,
+      "grad_norm": 1.1409285068511963,
+      "learning_rate": 9.906244053115143e-05,
+      "loss": 2.1377,
+      "step": 200
+    },
+    {
+      "epoch": 0.49368204525418746,
+      "grad_norm": 0.0690290704369545,
+      "learning_rate": 9.87808943820424e-05,
+      "loss": 2.0992,
+      "step": 210
+    },
+    {
+      "epoch": 0.5171907140758154,
+      "grad_norm": 0.20527280867099762,
+      "learning_rate": 9.846294610142398e-05,
+      "loss": 2.1339,
+      "step": 220
+    },
+    {
+      "epoch": 0.5406993828974435,
+      "grad_norm": 0.3991909623146057,
+      "learning_rate": 9.810883295421864e-05,
+      "loss": 2.1176,
+      "step": 230
+    },
+    {
+      "epoch": 0.5642080517190714,
+      "grad_norm": 0.08950258791446686,
+      "learning_rate": 9.771881919292765e-05,
+      "loss": 2.0895,
+      "step": 240
+    },
+    {
+      "epoch": 0.5877167205406993,
+      "grad_norm": 0.17848969995975494,
+      "learning_rate": 9.729319586043591e-05,
+      "loss": 2.0877,
+      "step": 250
+    },
+    {
+      "epoch": 0.6112253893623274,
+      "grad_norm": 0.30160897970199585,
+      "learning_rate": 9.683228057282483e-05,
+      "loss": 2.0648,
+      "step": 260
+    },
+    {
+      "epoch": 0.6347340581839553,
+      "grad_norm": 0.11883804202079773,
+      "learning_rate": 9.63364172823554e-05,
+      "loss": 2.0591,
+      "step": 270
+    },
+    {
+      "epoch": 0.6582427270055833,
+      "grad_norm": 0.1619461327791214,
+      "learning_rate": 9.580597602079802e-05,
+      "loss": 2.1386,
+      "step": 280
+    },
+    {
+      "epoch": 0.6817513958272113,
+      "grad_norm": 0.11473017930984497,
+      "learning_rate": 9.524135262330098e-05,
+      "loss": 2.1028,
+      "step": 290
+    },
+    {
+      "epoch": 0.7052600646488393,
+      "grad_norm": 0.059143248945474625,
+      "learning_rate": 9.464296843300342e-05,
+      "loss": 2.0881,
+      "step": 300
+    },
+    {
+      "epoch": 0.7287687334704672,
+      "grad_norm": 0.1624162495136261,
+      "learning_rate": 9.401126998661328e-05,
+      "loss": 2.0971,
+      "step": 310
+    },
+    {
+      "epoch": 0.7522774022920952,
+      "grad_norm": 0.15460653603076935,
+      "learning_rate": 9.334672868118491e-05,
+      "loss": 2.1154,
+      "step": 320
+    },
+    {
+      "epoch": 0.7757860711137232,
+      "grad_norm": 0.4213317334651947,
+      "learning_rate": 9.26498404223449e-05,
+      "loss": 2.1113,
+      "step": 330
+    },
+    {
+      "epoch": 0.7992947399353512,
+      "grad_norm": 0.14529550075531006,
+      "learning_rate": 9.192112525422868e-05,
+      "loss": 2.0867,
+      "step": 340
+    },
+    {
+      "epoch": 0.8228034087569791,
+      "grad_norm": 0.06652400642633438,
+      "learning_rate": 9.116112697140418e-05,
+      "loss": 2.0807,
+      "step": 350
+    },
+    {
+      "epoch": 0.8463120775786072,
+      "grad_norm": 0.12574820220470428,
+      "learning_rate": 9.037041271307188e-05,
+      "loss": 2.1711,
+      "step": 360
+    },
+    {
+      "epoch": 0.8698207464002351,
+      "grad_norm": 0.10869150608778,
+      "learning_rate": 8.954957253984426e-05,
+      "loss": 2.1252,
+      "step": 370
+    },
+    {
+      "epoch": 0.893329415221863,
+      "grad_norm": 0.143524169921875,
+      "learning_rate": 8.869921899342056e-05,
+      "loss": 2.0468,
+      "step": 380
+    },
+    {
+      "epoch": 0.916838084043491,
+      "grad_norm": 0.27682727575302124,
+      "learning_rate": 8.781998663948513e-05,
+      "loss": 2.1023,
+      "step": 390
+    },
+    {
+      "epoch": 0.940346752865119,
+      "grad_norm": 0.08671136200428009,
+      "learning_rate": 8.691253159417074e-05,
+      "loss": 2.0991,
+      "step": 400
+    },
+    {
+      "epoch": 0.963855421686747,
+      "grad_norm": 0.14743109047412872,
+      "learning_rate": 8.597753103444016e-05,
+      "loss": 2.0858,
+      "step": 410
+    },
+    {
+      "epoch": 0.9873640905083749,
+      "grad_norm": 0.14369799196720123,
+      "learning_rate": 8.501568269275126e-05,
+      "loss": 2.1057,
+      "step": 420
+    },
+    {
+      "epoch": 1.0094034675286512,
+      "grad_norm": 0.09220755100250244,
+      "learning_rate": 8.40277043363831e-05,
+      "loss": 1.9405,
+      "step": 430
+    },
+    {
+      "epoch": 1.0329121363502791,
+      "grad_norm": 0.25697803497314453,
+      "learning_rate": 8.301433323181076e-05,
+      "loss": 2.1221,
+      "step": 440
+    },
+    {
+      "epoch": 1.056420805171907,
+      "grad_norm": 0.1321459412574768,
+      "learning_rate": 8.19763255945298e-05,
+      "loss": 2.1576,
+      "step": 450
+    },
+    {
+      "epoch": 1.079929473993535,
+      "grad_norm": 0.11310122162103653,
+      "learning_rate": 8.091445602473972e-05,
+      "loss": 2.0483,
+      "step": 460
+    },
+    {
+      "epoch": 1.1034381428151632,
+      "grad_norm": 0.08170254528522491,
+      "learning_rate": 7.982951692930829e-05,
+      "loss": 2.1367,
+      "step": 470
+    },
+    {
+      "epoch": 1.1269468116367911,
+      "grad_norm": 0.022492246702313423,
+      "learning_rate": 7.87223179304479e-05,
+      "loss": 2.1435,
+      "step": 480
+    },
+    {
+      "epoch": 1.150455480458419,
+      "grad_norm": 0.015893638134002686,
+      "learning_rate": 7.759368526154509e-05,
+      "loss": 2.0666,
+      "step": 490
+    },
+    {
+      "epoch": 1.173964149280047,
+      "grad_norm": 0.053727954626083374,
+      "learning_rate": 7.644446115059425e-05,
+      "loss": 2.0886,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1278,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.002988656862822e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<begin_of_query>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<end_of_query>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "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_config.json

@@ -0,0 +1,245 @@
+{
+  "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
+    },
+    "151669": {
+      "content": "<begin_of_query>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<end_of_query>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<begin_of_query>",
+    "<end_of_query>"
+  ],
+  "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
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 2.0454733263908045e+17,
+    "train_loss": 5.729273645344288,
+    "train_runtime": 5128.0315,
+    "train_samples_per_second": 1.991,
+    "train_steps_per_second": 0.249
+}

trainer_log.jsonl

@@ -0,0 +1,128 @@
+{"current_steps": 10, "total_steps": 1278, "loss": 115.85, "lr": 7.031250000000001e-06, "epoch": 0.023508668821627974, "percentage": 0.78, "elapsed_time": "0:00:36", "remaining_time": "1:17:57"}
+{"current_steps": 20, "total_steps": 1278, "loss": 116.5781, "lr": 1.484375e-05, "epoch": 0.04701733764325595, "percentage": 1.56, "elapsed_time": "0:01:12", "remaining_time": "1:15:33"}
+{"current_steps": 30, "total_steps": 1278, "loss": 103.3281, "lr": 2.2656250000000002e-05, "epoch": 0.07052600646488393, "percentage": 2.35, "elapsed_time": "0:01:47", "remaining_time": "1:14:33"}
+{"current_steps": 40, "total_steps": 1278, "loss": 60.0406, "lr": 3.0468750000000002e-05, "epoch": 0.0940346752865119, "percentage": 3.13, "elapsed_time": "0:02:22", "remaining_time": "1:13:25"}
+{"current_steps": 50, "total_steps": 1278, "loss": 39.75, "lr": 3.828125e-05, "epoch": 0.11754334410813988, "percentage": 3.91, "elapsed_time": "0:02:57", "remaining_time": "1:12:34"}
+{"current_steps": 60, "total_steps": 1278, "loss": 24.7984, "lr": 4.609375e-05, "epoch": 0.14105201292976785, "percentage": 4.69, "elapsed_time": "0:03:32", "remaining_time": "1:11:49"}
+{"current_steps": 70, "total_steps": 1278, "loss": 11.9723, "lr": 5.3906250000000006e-05, "epoch": 0.16456068175139582, "percentage": 5.48, "elapsed_time": "0:04:07", "remaining_time": "1:11:10"}
+{"current_steps": 80, "total_steps": 1278, "loss": 5.4578, "lr": 6.171875e-05, "epoch": 0.1880693505730238, "percentage": 6.26, "elapsed_time": "0:04:42", "remaining_time": "1:10:27"}
+{"current_steps": 90, "total_steps": 1278, "loss": 3.992, "lr": 6.953125e-05, "epoch": 0.2115780193946518, "percentage": 7.04, "elapsed_time": "0:05:17", "remaining_time": "1:09:49"}
+{"current_steps": 100, "total_steps": 1278, "loss": 3.1058, "lr": 7.734375e-05, "epoch": 0.23508668821627976, "percentage": 7.82, "elapsed_time": "0:05:52", "remaining_time": "1:09:10"}
+{"current_steps": 110, "total_steps": 1278, "loss": 2.6654, "lr": 8.515625e-05, "epoch": 0.2585953570379077, "percentage": 8.61, "elapsed_time": "0:06:27", "remaining_time": "1:08:32"}
+{"current_steps": 120, "total_steps": 1278, "loss": 2.422, "lr": 9.296875e-05, "epoch": 0.2821040258595357, "percentage": 9.39, "elapsed_time": "0:07:02", "remaining_time": "1:07:57"}
+{"current_steps": 130, "total_steps": 1278, "loss": 2.1623, "lr": 9.999981342914437e-05, "epoch": 0.3056126946811637, "percentage": 10.17, "elapsed_time": "0:07:37", "remaining_time": "1:07:16"}
+{"current_steps": 140, "total_steps": 1278, "loss": 2.1429, "lr": 9.997742661115932e-05, "epoch": 0.32912136350279164, "percentage": 10.95, "elapsed_time": "0:08:12", "remaining_time": "1:06:41"}
+{"current_steps": 150, "total_steps": 1278, "loss": 2.1347, "lr": 9.991774476447404e-05, "epoch": 0.35263003232441964, "percentage": 11.74, "elapsed_time": "0:08:47", "remaining_time": "1:06:03"}
+{"current_steps": 160, "total_steps": 1278, "loss": 2.0512, "lr": 9.982081242591919e-05, "epoch": 0.3761387011460476, "percentage": 12.52, "elapsed_time": "0:09:22", "remaining_time": "1:05:29"}
+{"current_steps": 170, "total_steps": 1278, "loss": 2.047, "lr": 9.968670193003843e-05, "epoch": 0.3996473699676756, "percentage": 13.3, "elapsed_time": "0:09:57", "remaining_time": "1:04:52"}
+{"current_steps": 180, "total_steps": 1278, "loss": 2.1046, "lr": 9.951551335510978e-05, "epoch": 0.4231560387893036, "percentage": 14.08, "elapsed_time": "0:10:32", "remaining_time": "1:04:17"}
+{"current_steps": 190, "total_steps": 1278, "loss": 2.1397, "lr": 9.930737444846331e-05, "epoch": 0.4466647076109315, "percentage": 14.87, "elapsed_time": "0:11:07", "remaining_time": "1:03:44"}
+{"current_steps": 200, "total_steps": 1278, "loss": 2.1377, "lr": 9.906244053115143e-05, "epoch": 0.4701733764325595, "percentage": 15.65, "elapsed_time": "0:11:43", "remaining_time": "1:03:09"}
+{"current_steps": 210, "total_steps": 1278, "loss": 2.0992, "lr": 9.87808943820424e-05, "epoch": 0.49368204525418746, "percentage": 16.43, "elapsed_time": "0:12:18", "remaining_time": "1:02:34"}
+{"current_steps": 220, "total_steps": 1278, "loss": 2.1339, "lr": 9.846294610142398e-05, "epoch": 0.5171907140758154, "percentage": 17.21, "elapsed_time": "0:12:53", "remaining_time": "1:01:59"}
+{"current_steps": 230, "total_steps": 1278, "loss": 2.1176, "lr": 9.810883295421864e-05, "epoch": 0.5406993828974435, "percentage": 18.0, "elapsed_time": "0:13:28", "remaining_time": "1:01:24"}
+{"current_steps": 240, "total_steps": 1278, "loss": 2.0895, "lr": 9.771881919292765e-05, "epoch": 0.5642080517190714, "percentage": 18.78, "elapsed_time": "0:14:03", "remaining_time": "1:00:49"}
+{"current_steps": 250, "total_steps": 1278, "loss": 2.0877, "lr": 9.729319586043591e-05, "epoch": 0.5877167205406993, "percentage": 19.56, "elapsed_time": "0:14:38", "remaining_time": "1:00:12"}
+{"current_steps": 260, "total_steps": 1278, "loss": 2.0648, "lr": 9.683228057282483e-05, "epoch": 0.6112253893623274, "percentage": 20.34, "elapsed_time": "0:15:13", "remaining_time": "0:59:37"}
+{"current_steps": 270, "total_steps": 1278, "loss": 2.0591, "lr": 9.63364172823554e-05, "epoch": 0.6347340581839553, "percentage": 21.13, "elapsed_time": "0:15:48", "remaining_time": "0:59:00"}
+{"current_steps": 280, "total_steps": 1278, "loss": 2.1386, "lr": 9.580597602079802e-05, "epoch": 0.6582427270055833, "percentage": 21.91, "elapsed_time": "0:16:23", "remaining_time": "0:58:25"}
+{"current_steps": 290, "total_steps": 1278, "loss": 2.1028, "lr": 9.524135262330098e-05, "epoch": 0.6817513958272113, "percentage": 22.69, "elapsed_time": "0:16:58", "remaining_time": "0:57:49"}
+{"current_steps": 300, "total_steps": 1278, "loss": 2.0881, "lr": 9.464296843300342e-05, "epoch": 0.7052600646488393, "percentage": 23.47, "elapsed_time": "0:17:33", "remaining_time": "0:57:14"}
+{"current_steps": 310, "total_steps": 1278, "loss": 2.0971, "lr": 9.401126998661328e-05, "epoch": 0.7287687334704672, "percentage": 24.26, "elapsed_time": "0:18:08", "remaining_time": "0:56:39"}
+{"current_steps": 320, "total_steps": 1278, "loss": 2.1154, "lr": 9.334672868118491e-05, "epoch": 0.7522774022920952, "percentage": 25.04, "elapsed_time": "0:18:43", "remaining_time": "0:56:03"}
+{"current_steps": 330, "total_steps": 1278, "loss": 2.1113, "lr": 9.26498404223449e-05, "epoch": 0.7757860711137232, "percentage": 25.82, "elapsed_time": "0:19:19", "remaining_time": "0:55:29"}
+{"current_steps": 340, "total_steps": 1278, "loss": 2.0867, "lr": 9.192112525422868e-05, "epoch": 0.7992947399353512, "percentage": 26.6, "elapsed_time": "0:19:53", "remaining_time": "0:54:53"}
+{"current_steps": 350, "total_steps": 1278, "loss": 2.0807, "lr": 9.116112697140418e-05, "epoch": 0.8228034087569791, "percentage": 27.39, "elapsed_time": "0:20:29", "remaining_time": "0:54:19"}
+{"current_steps": 360, "total_steps": 1278, "loss": 2.1711, "lr": 9.037041271307188e-05, "epoch": 0.8463120775786072, "percentage": 28.17, "elapsed_time": "0:21:04", "remaining_time": "0:53:44"}
+{"current_steps": 370, "total_steps": 1278, "loss": 2.1252, "lr": 8.954957253984426e-05, "epoch": 0.8698207464002351, "percentage": 28.95, "elapsed_time": "0:21:39", "remaining_time": "0:53:09"}
+{"current_steps": 380, "total_steps": 1278, "loss": 2.0468, "lr": 8.869921899342056e-05, "epoch": 0.893329415221863, "percentage": 29.73, "elapsed_time": "0:22:15", "remaining_time": "0:52:36"}
+{"current_steps": 390, "total_steps": 1278, "loss": 2.1023, "lr": 8.781998663948513e-05, "epoch": 0.916838084043491, "percentage": 30.52, "elapsed_time": "0:22:52", "remaining_time": "0:52:04"}
+{"current_steps": 400, "total_steps": 1278, "loss": 2.0991, "lr": 8.691253159417074e-05, "epoch": 0.940346752865119, "percentage": 31.3, "elapsed_time": "0:23:29", "remaining_time": "0:51:33"}
+{"current_steps": 410, "total_steps": 1278, "loss": 2.0858, "lr": 8.597753103444016e-05, "epoch": 0.963855421686747, "percentage": 32.08, "elapsed_time": "0:24:05", "remaining_time": "0:51:00"}
+{"current_steps": 420, "total_steps": 1278, "loss": 2.1057, "lr": 8.501568269275126e-05, "epoch": 0.9873640905083749, "percentage": 32.86, "elapsed_time": "0:24:42", "remaining_time": "0:50:29"}
+{"current_steps": 430, "total_steps": 1278, "loss": 1.9405, "lr": 8.40277043363831e-05, "epoch": 1.0094034675286512, "percentage": 33.65, "elapsed_time": "0:25:17", "remaining_time": "0:49:53"}
+{"current_steps": 440, "total_steps": 1278, "loss": 2.1221, "lr": 8.301433323181076e-05, "epoch": 1.0329121363502791, "percentage": 34.43, "elapsed_time": "0:25:54", "remaining_time": "0:49:21"}
+{"current_steps": 450, "total_steps": 1278, "loss": 2.1576, "lr": 8.19763255945298e-05, "epoch": 1.056420805171907, "percentage": 35.21, "elapsed_time": "0:26:31", "remaining_time": "0:48:47"}
+{"current_steps": 460, "total_steps": 1278, "loss": 2.0483, "lr": 8.091445602473972e-05, "epoch": 1.079929473993535, "percentage": 35.99, "elapsed_time": "0:27:05", "remaining_time": "0:48:10"}
+{"current_steps": 470, "total_steps": 1278, "loss": 2.1367, "lr": 7.982951692930829e-05, "epoch": 1.1034381428151632, "percentage": 36.78, "elapsed_time": "0:27:40", "remaining_time": "0:47:35"}
+{"current_steps": 480, "total_steps": 1278, "loss": 2.1435, "lr": 7.87223179304479e-05, "epoch": 1.1269468116367911, "percentage": 37.56, "elapsed_time": "0:28:15", "remaining_time": "0:46:59"}
+{"current_steps": 490, "total_steps": 1278, "loss": 2.0666, "lr": 7.759368526154509e-05, "epoch": 1.150455480458419, "percentage": 38.34, "elapsed_time": "0:28:50", "remaining_time": "0:46:23"}
+{"current_steps": 500, "total_steps": 1278, "loss": 2.0886, "lr": 7.644446115059425e-05, "epoch": 1.173964149280047, "percentage": 39.12, "elapsed_time": "0:29:25", "remaining_time": "0:45:47"}
+{"current_steps": 510, "total_steps": 1278, "loss": 2.1418, "lr": 7.527550319169546e-05, "epoch": 1.197472818101675, "percentage": 39.91, "elapsed_time": "0:30:07", "remaining_time": "0:45:21"}
+{"current_steps": 520, "total_steps": 1278, "loss": 2.0688, "lr": 7.408768370508576e-05, "epoch": 1.2209814869233029, "percentage": 40.69, "elapsed_time": "0:30:42", "remaining_time": "0:44:46"}
+{"current_steps": 530, "total_steps": 1278, "loss": 2.0857, "lr": 7.288188908618102e-05, "epoch": 1.244490155744931, "percentage": 41.47, "elapsed_time": "0:31:17", "remaining_time": "0:44:10"}
+{"current_steps": 540, "total_steps": 1278, "loss": 2.0392, "lr": 7.165901914411435e-05, "epoch": 1.267998824566559, "percentage": 42.25, "elapsed_time": "0:31:52", "remaining_time": "0:43:33"}
+{"current_steps": 550, "total_steps": 1278, "loss": 2.0921, "lr": 7.041998643026511e-05, "epoch": 1.291507493388187, "percentage": 43.04, "elapsed_time": "0:32:27", "remaining_time": "0:42:57"}
+{"current_steps": 560, "total_steps": 1278, "loss": 2.0686, "lr": 6.916571555727852e-05, "epoch": 1.3150161622098149, "percentage": 43.82, "elapsed_time": "0:33:02", "remaining_time": "0:42:21"}
+{"current_steps": 570, "total_steps": 1278, "loss": 2.0845, "lr": 6.789714250908533e-05, "epoch": 1.3385248310314428, "percentage": 44.6, "elapsed_time": "0:33:37", "remaining_time": "0:41:45"}
+{"current_steps": 580, "total_steps": 1278, "loss": 2.1465, "lr": 6.661521394243533e-05, "epoch": 1.3620334998530708, "percentage": 45.38, "elapsed_time": "0:34:13", "remaining_time": "0:41:10"}
+{"current_steps": 590, "total_steps": 1278, "loss": 2.067, "lr": 6.532088648046677e-05, "epoch": 1.3855421686746987, "percentage": 46.17, "elapsed_time": "0:34:48", "remaining_time": "0:40:35"}
+{"current_steps": 600, "total_steps": 1278, "loss": 2.0697, "lr": 6.401512599883818e-05, "epoch": 1.4090508374963266, "percentage": 46.95, "elapsed_time": "0:35:23", "remaining_time": "0:39:59"}
+{"current_steps": 610, "total_steps": 1278, "loss": 2.1064, "lr": 6.269890690495593e-05, "epoch": 1.4325595063179548, "percentage": 47.73, "elapsed_time": "0:35:58", "remaining_time": "0:39:23"}
+{"current_steps": 620, "total_steps": 1278, "loss": 2.0533, "lr": 6.137321141083468e-05, "epoch": 1.4560681751395828, "percentage": 48.51, "elapsed_time": "0:36:33", "remaining_time": "0:38:48"}
+{"current_steps": 630, "total_steps": 1278, "loss": 2.1156, "lr": 6.003902880013416e-05, "epoch": 1.4795768439612107, "percentage": 49.3, "elapsed_time": "0:37:08", "remaining_time": "0:38:12"}
+{"current_steps": 640, "total_steps": 1278, "loss": 2.0543, "lr": 5.869735468991854e-05, "epoch": 1.5030855127828386, "percentage": 50.08, "elapsed_time": "0:37:43", "remaining_time": "0:37:36"}
+{"current_steps": 650, "total_steps": 1278, "loss": 2.0539, "lr": 5.73491902876897e-05, "epoch": 1.5265941816044668, "percentage": 50.86, "elapsed_time": "0:38:18", "remaining_time": "0:37:00"}
+{"current_steps": 660, "total_steps": 1278, "loss": 2.1078, "lr": 5.599554164424859e-05, "epoch": 1.5501028504260947, "percentage": 51.64, "elapsed_time": "0:38:53", "remaining_time": "0:36:24"}
+{"current_steps": 670, "total_steps": 1278, "loss": 2.1434, "lr": 5.463741890294257e-05, "epoch": 1.5736115192477227, "percentage": 52.43, "elapsed_time": "0:39:28", "remaining_time": "0:35:49"}
+{"current_steps": 680, "total_steps": 1278, "loss": 2.0696, "lr": 5.327583554585842e-05, "epoch": 1.5971201880693506, "percentage": 53.21, "elapsed_time": "0:40:02", "remaining_time": "0:35:13"}
+{"current_steps": 690, "total_steps": 1278, "loss": 2.0743, "lr": 5.191180763752418e-05, "epoch": 1.6206288568909786, "percentage": 53.99, "elapsed_time": "0:40:37", "remaining_time": "0:34:37"}
+{"current_steps": 700, "total_steps": 1278, "loss": 2.1303, "lr": 5.054635306668355e-05, "epoch": 1.6441375257126065, "percentage": 54.77, "elapsed_time": "0:41:15", "remaining_time": "0:34:03"}
+{"current_steps": 710, "total_steps": 1278, "loss": 2.1359, "lr": 4.9180490786709335e-05, "epoch": 1.6676461945342345, "percentage": 55.56, "elapsed_time": "0:41:51", "remaining_time": "0:33:28"}
+{"current_steps": 720, "total_steps": 1278, "loss": 2.0884, "lr": 4.781524005522216e-05, "epoch": 1.6911548633558624, "percentage": 56.34, "elapsed_time": "0:42:26", "remaining_time": "0:32:53"}
+{"current_steps": 730, "total_steps": 1278, "loss": 2.1102, "lr": 4.645161967348223e-05, "epoch": 1.7146635321774903, "percentage": 57.12, "elapsed_time": "0:43:01", "remaining_time": "0:32:18"}
+{"current_steps": 740, "total_steps": 1278, "loss": 2.134, "lr": 4.509064722612169e-05, "epoch": 1.7381722009991183, "percentage": 57.9, "elapsed_time": "0:43:36", "remaining_time": "0:31:42"}
+{"current_steps": 750, "total_steps": 1278, "loss": 2.212, "lr": 4.373333832178478e-05, "epoch": 1.7616808698207465, "percentage": 58.69, "elapsed_time": "0:44:12", "remaining_time": "0:31:07"}
+{"current_steps": 760, "total_steps": 1278, "loss": 2.0876, "lr": 4.2380705835242716e-05, "epoch": 1.7851895386423744, "percentage": 59.47, "elapsed_time": "0:44:47", "remaining_time": "0:30:31"}
+{"current_steps": 770, "total_steps": 1278, "loss": 2.064, "lr": 4.10337591515484e-05, "epoch": 1.8086982074640023, "percentage": 60.25, "elapsed_time": "0:45:22", "remaining_time": "0:29:56"}
+{"current_steps": 780, "total_steps": 1278, "loss": 2.1206, "lr": 3.969350341279566e-05, "epoch": 1.8322068762856303, "percentage": 61.03, "elapsed_time": "0:46:00", "remaining_time": "0:29:22"}
+{"current_steps": 790, "total_steps": 1278, "loss": 2.0975, "lr": 3.8360938768044405e-05, "epoch": 1.8557155451072584, "percentage": 61.82, "elapsed_time": "0:46:35", "remaining_time": "0:28:46"}
+{"current_steps": 800, "total_steps": 1278, "loss": 2.0519, "lr": 3.7037059626971944e-05, "epoch": 1.8792242139288864, "percentage": 62.6, "elapsed_time": "0:47:10", "remaining_time": "0:28:11"}
+{"current_steps": 810, "total_steps": 1278, "loss": 2.019, "lr": 3.572285391780734e-05, "epoch": 1.9027328827505143, "percentage": 63.38, "elapsed_time": "0:47:45", "remaining_time": "0:27:35"}
+{"current_steps": 820, "total_steps": 1278, "loss": 2.0966, "lr": 3.441930235010211e-05, "epoch": 1.9262415515721423, "percentage": 64.16, "elapsed_time": "0:48:20", "remaining_time": "0:26:59"}
+{"current_steps": 830, "total_steps": 1278, "loss": 2.0924, "lr": 3.312737768288827e-05, "epoch": 1.9497502203937702, "percentage": 64.95, "elapsed_time": "0:48:55", "remaining_time": "0:26:24"}
+{"current_steps": 840, "total_steps": 1278, "loss": 2.0315, "lr": 3.184804399876886e-05, "epoch": 1.9732588892153982, "percentage": 65.73, "elapsed_time": "0:49:30", "remaining_time": "0:25:48"}
+{"current_steps": 850, "total_steps": 1278, "loss": 2.0409, "lr": 3.0582255984483535e-05, "epoch": 1.996767558037026, "percentage": 66.51, "elapsed_time": "0:50:05", "remaining_time": "0:25:13"}
+{"current_steps": 860, "total_steps": 1278, "loss": 1.9696, "lr": 2.9330958218485392e-05, "epoch": 2.0188069350573024, "percentage": 67.29, "elapsed_time": "0:50:38", "remaining_time": "0:24:36"}
+{"current_steps": 870, "total_steps": 1278, "loss": 2.1055, "lr": 2.8095084466061367e-05, "epoch": 2.0423156038789303, "percentage": 68.08, "elapsed_time": "0:51:14", "remaining_time": "0:24:01"}
+{"current_steps": 880, "total_steps": 1278, "loss": 2.0865, "lr": 2.6875556982521248e-05, "epoch": 2.0658242727005582, "percentage": 68.86, "elapsed_time": "0:51:49", "remaining_time": "0:23:26"}
+{"current_steps": 890, "total_steps": 1278, "loss": 2.1081, "lr": 2.5673285824976575e-05, "epoch": 2.089332941522186, "percentage": 69.64, "elapsed_time": "0:52:25", "remaining_time": "0:22:51"}
+{"current_steps": 900, "total_steps": 1278, "loss": 2.1023, "lr": 2.4489168173221567e-05, "epoch": 2.112841610343814, "percentage": 70.42, "elapsed_time": "0:53:18", "remaining_time": "0:22:23"}
+{"current_steps": 910, "total_steps": 1278, "loss": 2.0929, "lr": 2.33240876602242e-05, "epoch": 2.136350279165442, "percentage": 71.21, "elapsed_time": "0:54:09", "remaining_time": "0:21:54"}
+{"current_steps": 920, "total_steps": 1278, "loss": 2.0817, "lr": 2.2178913712726045e-05, "epoch": 2.15985894798707, "percentage": 71.99, "elapsed_time": "0:54:45", "remaining_time": "0:21:18"}
+{"current_steps": 930, "total_steps": 1278, "loss": 2.0868, "lr": 2.1054500902443423e-05, "epoch": 2.1833676168086984, "percentage": 72.77, "elapsed_time": "0:55:20", "remaining_time": "0:20:42"}
+{"current_steps": 940, "total_steps": 1278, "loss": 2.1123, "lr": 1.9951688308354133e-05, "epoch": 2.2068762856303263, "percentage": 73.55, "elapsed_time": "0:55:55", "remaining_time": "0:20:06"}
+{"current_steps": 950, "total_steps": 1278, "loss": 2.051, "lr": 1.887129889054503e-05, "epoch": 2.2303849544519543, "percentage": 74.33, "elapsed_time": "0:56:38", "remaining_time": "0:19:33"}
+{"current_steps": 960, "total_steps": 1278, "loss": 2.0458, "lr": 1.7814138876088566e-05, "epoch": 2.2538936232735822, "percentage": 75.12, "elapsed_time": "0:57:26", "remaining_time": "0:19:01"}
+{"current_steps": 970, "total_steps": 1278, "loss": 2.0565, "lr": 1.6780997157405846e-05, "epoch": 2.27740229209521, "percentage": 75.9, "elapsed_time": "0:58:20", "remaining_time": "0:18:31"}
+{"current_steps": 980, "total_steps": 1278, "loss": 2.0952, "lr": 1.5772644703565565e-05, "epoch": 2.300910960916838, "percentage": 76.68, "elapsed_time": "0:59:15", "remaining_time": "0:18:01"}
+{"current_steps": 990, "total_steps": 1278, "loss": 2.0386, "lr": 1.4789833984957962e-05, "epoch": 2.324419629738466, "percentage": 77.46, "elapsed_time": "1:00:10", "remaining_time": "0:17:30"}
+{"current_steps": 1000, "total_steps": 1278, "loss": 2.0977, "lr": 1.3833298411773276e-05, "epoch": 2.347928298560094, "percentage": 78.25, "elapsed_time": "1:01:04", "remaining_time": "0:16:58"}
+{"current_steps": 1010, "total_steps": 1278, "loss": 2.0503, "lr": 1.2903751786703482e-05, "epoch": 2.371436967381722, "percentage": 79.03, "elapsed_time": "1:02:05", "remaining_time": "0:16:28"}
+{"current_steps": 1020, "total_steps": 1278, "loss": 2.1437, "lr": 1.2001887772276076e-05, "epoch": 2.39494563620335, "percentage": 79.81, "elapsed_time": "1:02:58", "remaining_time": "0:15:55"}
+{"current_steps": 1030, "total_steps": 1278, "loss": 2.0911, "lr": 1.1128379373217058e-05, "epoch": 2.418454305024978, "percentage": 80.59, "elapsed_time": "1:03:52", "remaining_time": "0:15:22"}
+{"current_steps": 1040, "total_steps": 1278, "loss": 2.1183, "lr": 1.028387843422952e-05, "epoch": 2.4419629738466058, "percentage": 81.38, "elapsed_time": "1:04:47", "remaining_time": "0:14:49"}
+{"current_steps": 1050, "total_steps": 1278, "loss": 2.1205, "lr": 9.469015153562855e-06, "epoch": 2.465471642668234, "percentage": 82.16, "elapsed_time": "1:05:42", "remaining_time": "0:14:16"}
+{"current_steps": 1060, "total_steps": 1278, "loss": 2.0027, "lr": 8.684397612735024e-06, "epoch": 2.488980311489862, "percentage": 82.94, "elapsed_time": "1:06:35", "remaining_time": "0:13:41"}
+{"current_steps": 1070, "total_steps": 1278, "loss": 2.0682, "lr": 7.930611322759462e-06, "epoch": 2.51248898031149, "percentage": 83.72, "elapsed_time": "1:07:28", "remaining_time": "0:13:07"}
+{"current_steps": 1080, "total_steps": 1278, "loss": 2.0895, "lr": 7.2082187872147935e-06, "epoch": 2.535997649133118, "percentage": 84.51, "elapsed_time": "1:08:22", "remaining_time": "0:12:32"}
+{"current_steps": 1090, "total_steps": 1278, "loss": 2.1298, "lr": 6.517759082483543e-06, "epoch": 2.559506317954746, "percentage": 85.29, "elapsed_time": "1:09:15", "remaining_time": "0:11:56"}
+{"current_steps": 1100, "total_steps": 1278, "loss": 2.0837, "lr": 5.8597474554731745e-06, "epoch": 2.583014986776374, "percentage": 86.07, "elapsed_time": "1:10:08", "remaining_time": "0:11:20"}
+{"current_steps": 1110, "total_steps": 1278, "loss": 2.1486, "lr": 5.234674939119538e-06, "epoch": 2.606523655598002, "percentage": 86.85, "elapsed_time": "1:10:59", "remaining_time": "0:10:44"}
+{"current_steps": 1120, "total_steps": 1278, "loss": 2.0959, "lr": 4.643007985959641e-06, "epoch": 2.6300323244196298, "percentage": 87.64, "elapsed_time": "1:11:49", "remaining_time": "0:10:07"}
+{"current_steps": 1130, "total_steps": 1278, "loss": 2.0439, "lr": 4.085188120047362e-06, "epoch": 2.6535409932412577, "percentage": 88.42, "elapsed_time": "1:12:40", "remaining_time": "0:09:31"}
+{"current_steps": 1140, "total_steps": 1278, "loss": 2.111, "lr": 3.5616316074715995e-06, "epoch": 2.6770496620628856, "percentage": 89.2, "elapsed_time": "1:13:30", "remaining_time": "0:08:53"}
+{"current_steps": 1150, "total_steps": 1278, "loss": 2.1078, "lr": 3.0727291457229303e-06, "epoch": 2.7005583308845136, "percentage": 89.98, "elapsed_time": "1:14:22", "remaining_time": "0:08:16"}
+{"current_steps": 1160, "total_steps": 1278, "loss": 2.1248, "lr": 2.618845572140527e-06, "epoch": 2.7240669997061415, "percentage": 90.77, "elapsed_time": "1:15:14", "remaining_time": "0:07:39"}
+{"current_steps": 1170, "total_steps": 1278, "loss": 2.0573, "lr": 2.2003195916567855e-06, "epoch": 2.7475756685277695, "percentage": 91.55, "elapsed_time": "1:16:05", "remaining_time": "0:07:01"}
+{"current_steps": 1180, "total_steps": 1278, "loss": 2.0218, "lr": 1.8174635240431282e-06, "epoch": 2.7710843373493974, "percentage": 92.33, "elapsed_time": "1:16:55", "remaining_time": "0:06:23"}
+{"current_steps": 1190, "total_steps": 1278, "loss": 2.0729, "lr": 1.4705630708451712e-06, "epoch": 2.7945930061710254, "percentage": 93.11, "elapsed_time": "1:17:47", "remaining_time": "0:05:45"}
+{"current_steps": 1200, "total_steps": 1278, "loss": 2.0432, "lr": 1.1598771021816058e-06, "epoch": 2.8181016749926533, "percentage": 93.9, "elapsed_time": "1:18:38", "remaining_time": "0:05:06"}
+{"current_steps": 1210, "total_steps": 1278, "loss": 2.1005, "lr": 8.856374635655695e-07, "epoch": 2.8416103438142817, "percentage": 94.68, "elapsed_time": "1:19:29", "remaining_time": "0:04:28"}
+{"current_steps": 1220, "total_steps": 1278, "loss": 2.1043, "lr": 6.480488028928422e-07, "epoch": 2.8651190126359096, "percentage": 95.46, "elapsed_time": "1:20:22", "remaining_time": "0:03:49"}
+{"current_steps": 1230, "total_steps": 1278, "loss": 2.1214, "lr": 4.47288417725944e-07, "epoch": 2.8886276814575376, "percentage": 96.24, "elapsed_time": "1:21:15", "remaining_time": "0:03:10"}
+{"current_steps": 1240, "total_steps": 1278, "loss": 2.0679, "lr": 2.8350612298801427e-07, "epoch": 2.9121363502791655, "percentage": 97.03, "elapsed_time": "1:22:06", "remaining_time": "0:02:30"}
+{"current_steps": 1250, "total_steps": 1278, "loss": 2.1937, "lr": 1.5682413916531802e-07, "epoch": 2.9356450191007935, "percentage": 97.81, "elapsed_time": "1:22:58", "remaining_time": "0:01:51"}
+{"current_steps": 1260, "total_steps": 1278, "loss": 2.1239, "lr": 6.733700110174157e-08, "epoch": 2.9591536879224214, "percentage": 98.59, "elapsed_time": "1:23:50", "remaining_time": "0:01:11"}
+{"current_steps": 1270, "total_steps": 1278, "loss": 2.1434, "lr": 1.511148745335089e-08, "epoch": 2.9826623567440493, "percentage": 99.37, "elapsed_time": "1:24:42", "remaining_time": "0:00:32"}
+{"current_steps": 1278, "total_steps": 1278, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:25:28", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,932 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1278,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.023508668821627974,
+      "grad_norm": 84.37700653076172,
+      "learning_rate": 7.031250000000001e-06,
+      "loss": 115.85,
+      "step": 10
+    },
+    {
+      "epoch": 0.04701733764325595,
+      "grad_norm": 106.4520034790039,
+      "learning_rate": 1.484375e-05,
+      "loss": 116.5781,
+      "step": 20
+    },
+    {
+      "epoch": 0.07052600646488393,
+      "grad_norm": 130.89254760742188,
+      "learning_rate": 2.2656250000000002e-05,
+      "loss": 103.3281,
+      "step": 30
+    },
+    {
+      "epoch": 0.0940346752865119,
+      "grad_norm": 37.089256286621094,
+      "learning_rate": 3.0468750000000002e-05,
+      "loss": 60.0406,
+      "step": 40
+    },
+    {
+      "epoch": 0.11754334410813988,
+      "grad_norm": 44.051109313964844,
+      "learning_rate": 3.828125e-05,
+      "loss": 39.75,
+      "step": 50
+    },
+    {
+      "epoch": 0.14105201292976785,
+      "grad_norm": 43.561981201171875,
+      "learning_rate": 4.609375e-05,
+      "loss": 24.7984,
+      "step": 60
+    },
+    {
+      "epoch": 0.16456068175139582,
+      "grad_norm": 34.622520446777344,
+      "learning_rate": 5.3906250000000006e-05,
+      "loss": 11.9723,
+      "step": 70
+    },
+    {
+      "epoch": 0.1880693505730238,
+      "grad_norm": 22.26849937438965,
+      "learning_rate": 6.171875e-05,
+      "loss": 5.4578,
+      "step": 80
+    },
+    {
+      "epoch": 0.2115780193946518,
+      "grad_norm": 9.059814453125,
+      "learning_rate": 6.953125e-05,
+      "loss": 3.992,
+      "step": 90
+    },
+    {
+      "epoch": 0.23508668821627976,
+      "grad_norm": 4.332883834838867,
+      "learning_rate": 7.734375e-05,
+      "loss": 3.1058,
+      "step": 100
+    },
+    {
+      "epoch": 0.2585953570379077,
+      "grad_norm": 6.844908237457275,
+      "learning_rate": 8.515625e-05,
+      "loss": 2.6654,
+      "step": 110
+    },
+    {
+      "epoch": 0.2821040258595357,
+      "grad_norm": 4.539117813110352,
+      "learning_rate": 9.296875e-05,
+      "loss": 2.422,
+      "step": 120
+    },
+    {
+      "epoch": 0.3056126946811637,
+      "grad_norm": 3.098025321960449,
+      "learning_rate": 9.999981342914437e-05,
+      "loss": 2.1623,
+      "step": 130
+    },
+    {
+      "epoch": 0.32912136350279164,
+      "grad_norm": 1.3452321290969849,
+      "learning_rate": 9.997742661115932e-05,
+      "loss": 2.1429,
+      "step": 140
+    },
+    {
+      "epoch": 0.35263003232441964,
+      "grad_norm": 0.37226417660713196,
+      "learning_rate": 9.991774476447404e-05,
+      "loss": 2.1347,
+      "step": 150
+    },
+    {
+      "epoch": 0.3761387011460476,
+      "grad_norm": 3.523218870162964,
+      "learning_rate": 9.982081242591919e-05,
+      "loss": 2.0512,
+      "step": 160
+    },
+    {
+      "epoch": 0.3996473699676756,
+      "grad_norm": 0.33414289355278015,
+      "learning_rate": 9.968670193003843e-05,
+      "loss": 2.047,
+      "step": 170
+    },
+    {
+      "epoch": 0.4231560387893036,
+      "grad_norm": 0.24106919765472412,
+      "learning_rate": 9.951551335510978e-05,
+      "loss": 2.1046,
+      "step": 180
+    },
+    {
+      "epoch": 0.4466647076109315,
+      "grad_norm": 0.328752726316452,
+      "learning_rate": 9.930737444846331e-05,
+      "loss": 2.1397,
+      "step": 190
+    },
+    {
+      "epoch": 0.4701733764325595,
+      "grad_norm": 1.1409285068511963,
+      "learning_rate": 9.906244053115143e-05,
+      "loss": 2.1377,
+      "step": 200
+    },
+    {
+      "epoch": 0.49368204525418746,
+      "grad_norm": 0.0690290704369545,
+      "learning_rate": 9.87808943820424e-05,
+      "loss": 2.0992,
+      "step": 210
+    },
+    {
+      "epoch": 0.5171907140758154,
+      "grad_norm": 0.20527280867099762,
+      "learning_rate": 9.846294610142398e-05,
+      "loss": 2.1339,
+      "step": 220
+    },
+    {
+      "epoch": 0.5406993828974435,
+      "grad_norm": 0.3991909623146057,
+      "learning_rate": 9.810883295421864e-05,
+      "loss": 2.1176,
+      "step": 230
+    },
+    {
+      "epoch": 0.5642080517190714,
+      "grad_norm": 0.08950258791446686,
+      "learning_rate": 9.771881919292765e-05,
+      "loss": 2.0895,
+      "step": 240
+    },
+    {
+      "epoch": 0.5877167205406993,
+      "grad_norm": 0.17848969995975494,
+      "learning_rate": 9.729319586043591e-05,
+      "loss": 2.0877,
+      "step": 250
+    },
+    {
+      "epoch": 0.6112253893623274,
+      "grad_norm": 0.30160897970199585,
+      "learning_rate": 9.683228057282483e-05,
+      "loss": 2.0648,
+      "step": 260
+    },
+    {
+      "epoch": 0.6347340581839553,
+      "grad_norm": 0.11883804202079773,
+      "learning_rate": 9.63364172823554e-05,
+      "loss": 2.0591,
+      "step": 270
+    },
+    {
+      "epoch": 0.6582427270055833,
+      "grad_norm": 0.1619461327791214,
+      "learning_rate": 9.580597602079802e-05,
+      "loss": 2.1386,
+      "step": 280
+    },
+    {
+      "epoch": 0.6817513958272113,
+      "grad_norm": 0.11473017930984497,
+      "learning_rate": 9.524135262330098e-05,
+      "loss": 2.1028,
+      "step": 290
+    },
+    {
+      "epoch": 0.7052600646488393,
+      "grad_norm": 0.059143248945474625,
+      "learning_rate": 9.464296843300342e-05,
+      "loss": 2.0881,
+      "step": 300
+    },
+    {
+      "epoch": 0.7287687334704672,
+      "grad_norm": 0.1624162495136261,
+      "learning_rate": 9.401126998661328e-05,
+      "loss": 2.0971,
+      "step": 310
+    },
+    {
+      "epoch": 0.7522774022920952,
+      "grad_norm": 0.15460653603076935,
+      "learning_rate": 9.334672868118491e-05,
+      "loss": 2.1154,
+      "step": 320
+    },
+    {
+      "epoch": 0.7757860711137232,
+      "grad_norm": 0.4213317334651947,
+      "learning_rate": 9.26498404223449e-05,
+      "loss": 2.1113,
+      "step": 330
+    },
+    {
+      "epoch": 0.7992947399353512,
+      "grad_norm": 0.14529550075531006,
+      "learning_rate": 9.192112525422868e-05,
+      "loss": 2.0867,
+      "step": 340
+    },
+    {
+      "epoch": 0.8228034087569791,
+      "grad_norm": 0.06652400642633438,
+      "learning_rate": 9.116112697140418e-05,
+      "loss": 2.0807,
+      "step": 350
+    },
+    {
+      "epoch": 0.8463120775786072,
+      "grad_norm": 0.12574820220470428,
+      "learning_rate": 9.037041271307188e-05,
+      "loss": 2.1711,
+      "step": 360
+    },
+    {
+      "epoch": 0.8698207464002351,
+      "grad_norm": 0.10869150608778,
+      "learning_rate": 8.954957253984426e-05,
+      "loss": 2.1252,
+      "step": 370
+    },
+    {
+      "epoch": 0.893329415221863,
+      "grad_norm": 0.143524169921875,
+      "learning_rate": 8.869921899342056e-05,
+      "loss": 2.0468,
+      "step": 380
+    },
+    {
+      "epoch": 0.916838084043491,
+      "grad_norm": 0.27682727575302124,
+      "learning_rate": 8.781998663948513e-05,
+      "loss": 2.1023,
+      "step": 390
+    },
+    {
+      "epoch": 0.940346752865119,
+      "grad_norm": 0.08671136200428009,
+      "learning_rate": 8.691253159417074e-05,
+      "loss": 2.0991,
+      "step": 400
+    },
+    {
+      "epoch": 0.963855421686747,
+      "grad_norm": 0.14743109047412872,
+      "learning_rate": 8.597753103444016e-05,
+      "loss": 2.0858,
+      "step": 410
+    },
+    {
+      "epoch": 0.9873640905083749,
+      "grad_norm": 0.14369799196720123,
+      "learning_rate": 8.501568269275126e-05,
+      "loss": 2.1057,
+      "step": 420
+    },
+    {
+      "epoch": 1.0094034675286512,
+      "grad_norm": 0.09220755100250244,
+      "learning_rate": 8.40277043363831e-05,
+      "loss": 1.9405,
+      "step": 430
+    },
+    {
+      "epoch": 1.0329121363502791,
+      "grad_norm": 0.25697803497314453,
+      "learning_rate": 8.301433323181076e-05,
+      "loss": 2.1221,
+      "step": 440
+    },
+    {
+      "epoch": 1.056420805171907,
+      "grad_norm": 0.1321459412574768,
+      "learning_rate": 8.19763255945298e-05,
+      "loss": 2.1576,
+      "step": 450
+    },
+    {
+      "epoch": 1.079929473993535,
+      "grad_norm": 0.11310122162103653,
+      "learning_rate": 8.091445602473972e-05,
+      "loss": 2.0483,
+      "step": 460
+    },
+    {
+      "epoch": 1.1034381428151632,
+      "grad_norm": 0.08170254528522491,
+      "learning_rate": 7.982951692930829e-05,
+      "loss": 2.1367,
+      "step": 470
+    },
+    {
+      "epoch": 1.1269468116367911,
+      "grad_norm": 0.022492246702313423,
+      "learning_rate": 7.87223179304479e-05,
+      "loss": 2.1435,
+      "step": 480
+    },
+    {
+      "epoch": 1.150455480458419,
+      "grad_norm": 0.015893638134002686,
+      "learning_rate": 7.759368526154509e-05,
+      "loss": 2.0666,
+      "step": 490
+    },
+    {
+      "epoch": 1.173964149280047,
+      "grad_norm": 0.053727954626083374,
+      "learning_rate": 7.644446115059425e-05,
+      "loss": 2.0886,
+      "step": 500
+    },
+    {
+      "epoch": 1.197472818101675,
+      "grad_norm": 0.12717482447624207,
+      "learning_rate": 7.527550319169546e-05,
+      "loss": 2.1418,
+      "step": 510
+    },
+    {
+      "epoch": 1.2209814869233029,
+      "grad_norm": 0.030752327293157578,
+      "learning_rate": 7.408768370508576e-05,
+      "loss": 2.0688,
+      "step": 520
+    },
+    {
+      "epoch": 1.244490155744931,
+      "grad_norm": 0.07915918529033661,
+      "learning_rate": 7.288188908618102e-05,
+      "loss": 2.0857,
+      "step": 530
+    },
+    {
+      "epoch": 1.267998824566559,
+      "grad_norm": 0.09853250533342361,
+      "learning_rate": 7.165901914411435e-05,
+      "loss": 2.0392,
+      "step": 540
+    },
+    {
+      "epoch": 1.291507493388187,
+      "grad_norm": 0.21571961045265198,
+      "learning_rate": 7.041998643026511e-05,
+      "loss": 2.0921,
+      "step": 550
+    },
+    {
+      "epoch": 1.3150161622098149,
+      "grad_norm": 0.10290564596652985,
+      "learning_rate": 6.916571555727852e-05,
+      "loss": 2.0686,
+      "step": 560
+    },
+    {
+      "epoch": 1.3385248310314428,
+      "grad_norm": 0.08689925819635391,
+      "learning_rate": 6.789714250908533e-05,
+      "loss": 2.0845,
+      "step": 570
+    },
+    {
+      "epoch": 1.3620334998530708,
+      "grad_norm": 0.1267048567533493,
+      "learning_rate": 6.661521394243533e-05,
+      "loss": 2.1465,
+      "step": 580
+    },
+    {
+      "epoch": 1.3855421686746987,
+      "grad_norm": 0.18292003870010376,
+      "learning_rate": 6.532088648046677e-05,
+      "loss": 2.067,
+      "step": 590
+    },
+    {
+      "epoch": 1.4090508374963266,
+      "grad_norm": 0.051083244383335114,
+      "learning_rate": 6.401512599883818e-05,
+      "loss": 2.0697,
+      "step": 600
+    },
+    {
+      "epoch": 1.4325595063179548,
+      "grad_norm": 0.0492679663002491,
+      "learning_rate": 6.269890690495593e-05,
+      "loss": 2.1064,
+      "step": 610
+    },
+    {
+      "epoch": 1.4560681751395828,
+      "grad_norm": 0.051078781485557556,
+      "learning_rate": 6.137321141083468e-05,
+      "loss": 2.0533,
+      "step": 620
+    },
+    {
+      "epoch": 1.4795768439612107,
+      "grad_norm": 0.11715124547481537,
+      "learning_rate": 6.003902880013416e-05,
+      "loss": 2.1156,
+      "step": 630
+    },
+    {
+      "epoch": 1.5030855127828386,
+      "grad_norm": 0.041975561529397964,
+      "learning_rate": 5.869735468991854e-05,
+      "loss": 2.0543,
+      "step": 640
+    },
+    {
+      "epoch": 1.5265941816044668,
+      "grad_norm": 0.10740803927183151,
+      "learning_rate": 5.73491902876897e-05,
+      "loss": 2.0539,
+      "step": 650
+    },
+    {
+      "epoch": 1.5501028504260947,
+      "grad_norm": 0.07230595499277115,
+      "learning_rate": 5.599554164424859e-05,
+      "loss": 2.1078,
+      "step": 660
+    },
+    {
+      "epoch": 1.5736115192477227,
+      "grad_norm": 0.010545202530920506,
+      "learning_rate": 5.463741890294257e-05,
+      "loss": 2.1434,
+      "step": 670
+    },
+    {
+      "epoch": 1.5971201880693506,
+      "grad_norm": 0.0882532000541687,
+      "learning_rate": 5.327583554585842e-05,
+      "loss": 2.0696,
+      "step": 680
+    },
+    {
+      "epoch": 1.6206288568909786,
+      "grad_norm": 0.15730935335159302,
+      "learning_rate": 5.191180763752418e-05,
+      "loss": 2.0743,
+      "step": 690
+    },
+    {
+      "epoch": 1.6441375257126065,
+      "grad_norm": 0.16760171949863434,
+      "learning_rate": 5.054635306668355e-05,
+      "loss": 2.1303,
+      "step": 700
+    },
+    {
+      "epoch": 1.6676461945342345,
+      "grad_norm": 0.12746253609657288,
+      "learning_rate": 4.9180490786709335e-05,
+      "loss": 2.1359,
+      "step": 710
+    },
+    {
+      "epoch": 1.6911548633558624,
+      "grad_norm": 0.08576823770999908,
+      "learning_rate": 4.781524005522216e-05,
+      "loss": 2.0884,
+      "step": 720
+    },
+    {
+      "epoch": 1.7146635321774903,
+      "grad_norm": 0.01966356858611107,
+      "learning_rate": 4.645161967348223e-05,
+      "loss": 2.1102,
+      "step": 730
+    },
+    {
+      "epoch": 1.7381722009991183,
+      "grad_norm": 0.1140172928571701,
+      "learning_rate": 4.509064722612169e-05,
+      "loss": 2.134,
+      "step": 740
+    },
+    {
+      "epoch": 1.7616808698207465,
+      "grad_norm": 0.11263474822044373,
+      "learning_rate": 4.373333832178478e-05,
+      "loss": 2.212,
+      "step": 750
+    },
+    {
+      "epoch": 1.7851895386423744,
+      "grad_norm": 0.01955031044781208,
+      "learning_rate": 4.2380705835242716e-05,
+      "loss": 2.0876,
+      "step": 760
+    },
+    {
+      "epoch": 1.8086982074640023,
+      "grad_norm": 0.02556225284934044,
+      "learning_rate": 4.10337591515484e-05,
+      "loss": 2.064,
+      "step": 770
+    },
+    {
+      "epoch": 1.8322068762856303,
+      "grad_norm": 0.04094263166189194,
+      "learning_rate": 3.969350341279566e-05,
+      "loss": 2.1206,
+      "step": 780
+    },
+    {
+      "epoch": 1.8557155451072584,
+      "grad_norm": 0.0680101215839386,
+      "learning_rate": 3.8360938768044405e-05,
+      "loss": 2.0975,
+      "step": 790
+    },
+    {
+      "epoch": 1.8792242139288864,
+      "grad_norm": 0.08410263061523438,
+      "learning_rate": 3.7037059626971944e-05,
+      "loss": 2.0519,
+      "step": 800
+    },
+    {
+      "epoch": 1.9027328827505143,
+      "grad_norm": 0.02342092990875244,
+      "learning_rate": 3.572285391780734e-05,
+      "loss": 2.019,
+      "step": 810
+    },
+    {
+      "epoch": 1.9262415515721423,
+      "grad_norm": 0.02327684499323368,
+      "learning_rate": 3.441930235010211e-05,
+      "loss": 2.0966,
+      "step": 820
+    },
+    {
+      "epoch": 1.9497502203937702,
+      "grad_norm": 0.0357813723385334,
+      "learning_rate": 3.312737768288827e-05,
+      "loss": 2.0924,
+      "step": 830
+    },
+    {
+      "epoch": 1.9732588892153982,
+      "grad_norm": 0.07186655700206757,
+      "learning_rate": 3.184804399876886e-05,
+      "loss": 2.0315,
+      "step": 840
+    },
+    {
+      "epoch": 1.996767558037026,
+      "grad_norm": 0.09240284562110901,
+      "learning_rate": 3.0582255984483535e-05,
+      "loss": 2.0409,
+      "step": 850
+    },
+    {
+      "epoch": 2.0188069350573024,
+      "grad_norm": 0.04462951049208641,
+      "learning_rate": 2.9330958218485392e-05,
+      "loss": 1.9696,
+      "step": 860
+    },
+    {
+      "epoch": 2.0423156038789303,
+      "grad_norm": 0.029340475797653198,
+      "learning_rate": 2.8095084466061367e-05,
+      "loss": 2.1055,
+      "step": 870
+    },
+    {
+      "epoch": 2.0658242727005582,
+      "grad_norm": 0.048022590577602386,
+      "learning_rate": 2.6875556982521248e-05,
+      "loss": 2.0865,
+      "step": 880
+    },
+    {
+      "epoch": 2.089332941522186,
+      "grad_norm": 0.04670249670743942,
+      "learning_rate": 2.5673285824976575e-05,
+      "loss": 2.1081,
+      "step": 890
+    },
+    {
+      "epoch": 2.112841610343814,
+      "grad_norm": 0.015516964718699455,
+      "learning_rate": 2.4489168173221567e-05,
+      "loss": 2.1023,
+      "step": 900
+    },
+    {
+      "epoch": 2.136350279165442,
+      "grad_norm": 0.06762902438640594,
+      "learning_rate": 2.33240876602242e-05,
+      "loss": 2.0929,
+      "step": 910
+    },
+    {
+      "epoch": 2.15985894798707,
+      "grad_norm": 0.014990041963756084,
+      "learning_rate": 2.2178913712726045e-05,
+      "loss": 2.0817,
+      "step": 920
+    },
+    {
+      "epoch": 2.1833676168086984,
+      "grad_norm": 0.07376622408628464,
+      "learning_rate": 2.1054500902443423e-05,
+      "loss": 2.0868,
+      "step": 930
+    },
+    {
+      "epoch": 2.2068762856303263,
+      "grad_norm": 0.03299334645271301,
+      "learning_rate": 1.9951688308354133e-05,
+      "loss": 2.1123,
+      "step": 940
+    },
+    {
+      "epoch": 2.2303849544519543,
+      "grad_norm": 0.05409041792154312,
+      "learning_rate": 1.887129889054503e-05,
+      "loss": 2.051,
+      "step": 950
+    },
+    {
+      "epoch": 2.2538936232735822,
+      "grad_norm": 0.041158534586429596,
+      "learning_rate": 1.7814138876088566e-05,
+      "loss": 2.0458,
+      "step": 960
+    },
+    {
+      "epoch": 2.27740229209521,
+      "grad_norm": 0.03300878778100014,
+      "learning_rate": 1.6780997157405846e-05,
+      "loss": 2.0565,
+      "step": 970
+    },
+    {
+      "epoch": 2.300910960916838,
+      "grad_norm": 0.009902500547468662,
+      "learning_rate": 1.5772644703565565e-05,
+      "loss": 2.0952,
+      "step": 980
+    },
+    {
+      "epoch": 2.324419629738466,
+      "grad_norm": 0.44653964042663574,
+      "learning_rate": 1.4789833984957962e-05,
+      "loss": 2.0386,
+      "step": 990
+    },
+    {
+      "epoch": 2.347928298560094,
+      "grad_norm": 0.4100548326969147,
+      "learning_rate": 1.3833298411773276e-05,
+      "loss": 2.0977,
+      "step": 1000
+    },
+    {
+      "epoch": 2.371436967381722,
+      "grad_norm": 0.00745609262958169,
+      "learning_rate": 1.2903751786703482e-05,
+      "loss": 2.0503,
+      "step": 1010
+    },
+    {
+      "epoch": 2.39494563620335,
+      "grad_norm": 0.05212165042757988,
+      "learning_rate": 1.2001887772276076e-05,
+      "loss": 2.1437,
+      "step": 1020
+    },
+    {
+      "epoch": 2.418454305024978,
+      "grad_norm": 0.0367308035492897,
+      "learning_rate": 1.1128379373217058e-05,
+      "loss": 2.0911,
+      "step": 1030
+    },
+    {
+      "epoch": 2.4419629738466058,
+      "grad_norm": 0.02135683037340641,
+      "learning_rate": 1.028387843422952e-05,
+      "loss": 2.1183,
+      "step": 1040
+    },
+    {
+      "epoch": 2.465471642668234,
+      "grad_norm": 0.02447247877717018,
+      "learning_rate": 9.469015153562855e-06,
+      "loss": 2.1205,
+      "step": 1050
+    },
+    {
+      "epoch": 2.488980311489862,
+      "grad_norm": 0.011414138600230217,
+      "learning_rate": 8.684397612735024e-06,
+      "loss": 2.0027,
+      "step": 1060
+    },
+    {
+      "epoch": 2.51248898031149,
+      "grad_norm": 0.0028556822799146175,
+      "learning_rate": 7.930611322759462e-06,
+      "loss": 2.0682,
+      "step": 1070
+    },
+    {
+      "epoch": 2.535997649133118,
+      "grad_norm": 0.008712991140782833,
+      "learning_rate": 7.2082187872147935e-06,
+      "loss": 2.0895,
+      "step": 1080
+    },
+    {
+      "epoch": 2.559506317954746,
+      "grad_norm": 0.03148069605231285,
+      "learning_rate": 6.517759082483543e-06,
+      "loss": 2.1298,
+      "step": 1090
+    },
+    {
+      "epoch": 2.583014986776374,
+      "grad_norm": 0.03679489344358444,
+      "learning_rate": 5.8597474554731745e-06,
+      "loss": 2.0837,
+      "step": 1100
+    },
+    {
+      "epoch": 2.606523655598002,
+      "grad_norm": 0.05236874148249626,
+      "learning_rate": 5.234674939119538e-06,
+      "loss": 2.1486,
+      "step": 1110
+    },
+    {
+      "epoch": 2.6300323244196298,
+      "grad_norm": 0.03369889780879021,
+      "learning_rate": 4.643007985959641e-06,
+      "loss": 2.0959,
+      "step": 1120
+    },
+    {
+      "epoch": 2.6535409932412577,
+      "grad_norm": 0.006195698864758015,
+      "learning_rate": 4.085188120047362e-06,
+      "loss": 2.0439,
+      "step": 1130
+    },
+    {
+      "epoch": 2.6770496620628856,
+      "grad_norm": 0.03900829330086708,
+      "learning_rate": 3.5616316074715995e-06,
+      "loss": 2.111,
+      "step": 1140
+    },
+    {
+      "epoch": 2.7005583308845136,
+      "grad_norm": 0.00790059007704258,
+      "learning_rate": 3.0727291457229303e-06,
+      "loss": 2.1078,
+      "step": 1150
+    },
+    {
+      "epoch": 2.7240669997061415,
+      "grad_norm": 0.017095139250159264,
+      "learning_rate": 2.618845572140527e-06,
+      "loss": 2.1248,
+      "step": 1160
+    },
+    {
+      "epoch": 2.7475756685277695,
+      "grad_norm": 0.006935155484825373,
+      "learning_rate": 2.2003195916567855e-06,
+      "loss": 2.0573,
+      "step": 1170
+    },
+    {
+      "epoch": 2.7710843373493974,
+      "grad_norm": 0.01475539617240429,
+      "learning_rate": 1.8174635240431282e-06,
+      "loss": 2.0218,
+      "step": 1180
+    },
+    {
+      "epoch": 2.7945930061710254,
+      "grad_norm": 0.08390510082244873,
+      "learning_rate": 1.4705630708451712e-06,
+      "loss": 2.0729,
+      "step": 1190
+    },
+    {
+      "epoch": 2.8181016749926533,
+      "grad_norm": 0.04823232442140579,
+      "learning_rate": 1.1598771021816058e-06,
+      "loss": 2.0432,
+      "step": 1200
+    },
+    {
+      "epoch": 2.8416103438142817,
+      "grad_norm": 0.017384668812155724,
+      "learning_rate": 8.856374635655695e-07,
+      "loss": 2.1005,
+      "step": 1210
+    },
+    {
+      "epoch": 2.8651190126359096,
+      "grad_norm": 0.016273437067866325,
+      "learning_rate": 6.480488028928422e-07,
+      "loss": 2.1043,
+      "step": 1220
+    },
+    {
+      "epoch": 2.8886276814575376,
+      "grad_norm": 0.004406425170600414,
+      "learning_rate": 4.47288417725944e-07,
+      "loss": 2.1214,
+      "step": 1230
+    },
+    {
+      "epoch": 2.9121363502791655,
+      "grad_norm": 0.04330357536673546,
+      "learning_rate": 2.8350612298801427e-07,
+      "loss": 2.0679,
+      "step": 1240
+    },
+    {
+      "epoch": 2.9356450191007935,
+      "grad_norm": 0.005912340711802244,
+      "learning_rate": 1.5682413916531802e-07,
+      "loss": 2.1937,
+      "step": 1250
+    },
+    {
+      "epoch": 2.9591536879224214,
+      "grad_norm": 0.021025869995355606,
+      "learning_rate": 6.733700110174157e-08,
+      "loss": 2.1239,
+      "step": 1260
+    },
+    {
+      "epoch": 2.9826623567440493,
+      "grad_norm": 0.006763559300452471,
+      "learning_rate": 1.511148745335089e-08,
+      "loss": 2.1434,
+      "step": 1270
+    },
+    {
+      "epoch": 3.0,
+      "step": 1278,
+      "total_flos": 2.0454733263908045e+17,
+      "train_loss": 5.729273645344288,
+      "train_runtime": 5128.0315,
+      "train_samples_per_second": 1.991,
+      "train_steps_per_second": 0.249
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1278,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.0454733263908045e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}