Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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-9482/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+library_name: peft
+license: other
+#base_model: /data/group/project1/models/Qwen3-32B
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: widthIrplus_msg_qm9s_mb_msd
+  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. -->
+
+# widthIrplus_msg_qm9s_mb_msd
+
+This model is a fine-tuned version of [/data/group/project1/models/Qwen3-32B](https://huggingface.co//data/group/project1/models/Qwen3-32B) on the QM9S_ir_train, the QM9S_uv_train, the QM9S_raman_train, the QM9S_all_train, the MB_train, the MSG_train, the MSD_ms_train, the MSD_nmr_train, the MSD_ir_train and the MSD_all_train datasets.
+
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 256
+- total_eval_batch_size: 64
+- 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
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.15.1
+- Transformers 4.51.3
+- Pytorch 2.7.0+cu126
+- Datasets 3.5.0
+- Tokenizers 0.21.1

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/data/group/project1/models/Qwen3-32B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb59010a00a7ac2e3ce13ac35918ce6968023fa8da77b50c2a76ab695d626638
+size 268555264

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.999973634949511,
+    "num_input_tokens_seen": 2098994560,
+    "total_flos": 4.036532744878576e+20,
+    "train_loss": 0.5513084518635382,
+    "train_runtime": 186000.3322,
+    "train_samples_per_second": 13.051,
+    "train_steps_per_second": 0.051
+}

checkpoint-9482/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /data/group/project1/models/Qwen3-32B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.1

checkpoint-9482/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/data/group/project1/models/Qwen3-32B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-9482/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb59010a00a7ac2e3ce13ac35918ce6968023fa8da77b50c2a76ab695d626638
+size 268555264

checkpoint-9482/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-9482/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1feddda1c28ecc6d25975487ec0647591f016325995d0faebbfdddfc7501975
+size 537627747

checkpoint-9482/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:815a6cb0b751f71436c772260ac0301805655316e370646d156fc13ff7f9c2e6
+size 16325

checkpoint-9482/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce29a8767a7d907dd24987aa2c3e654d4317f3042fbc13b5b72cadb46d43311a
+size 16389

checkpoint-9482/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a48db011646b4e9a867bf12f4a233cad5dfbfe309686f8996c250196d3783a
+size 16389

checkpoint-9482/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9562ee822472a4f01dcd6349ab3d1ef42a48915fe3b92e843a0c37db53c8421
+size 16389

checkpoint-9482/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7d2767d83c3bf27f12db022b0632e2c4f8c164274ba75e380cf18f9d5f21819
+size 16389

checkpoint-9482/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76816358d4e5db8149d60d55234db658d67a13c0c1ce05d7404cf7125a676a5c
+size 16389

checkpoint-9482/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1562e7520c977d178183d641f70abcf3f57da2489938756cfbebf9b6e6c1a9fd
+size 16389

checkpoint-9482/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6b6cabaed045c5398cd1b732f7ec48bd363f3b43cd24e0e70e641a42bd00c28
+size 16389

checkpoint-9482/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4460a024da49a8eddf21b5eec3734b8b897e25a9a27de32a1152e855249e27a
+size 1465

checkpoint-9482/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-9482/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-9482/tokenizer_config.json

@@ -0,0 +1,241 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "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-9482/trainer_state.json

@@ -0,0 +1,410 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.999973634949511,
+  "eval_steps": 500,
+  "global_step": 9482,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02109204039125735,
+      "grad_norm": 0.40668317675590515,
+      "learning_rate": 4.994568013593584e-05,
+      "loss": 0.947,
+      "num_input_tokens_seen": 44211392,
+      "step": 200
+    },
+    {
+      "epoch": 0.0421840807825147,
+      "grad_norm": 0.5519078373908997,
+      "learning_rate": 4.9781866145835606e-05,
+      "loss": 0.7951,
+      "num_input_tokens_seen": 88542848,
+      "step": 400
+    },
+    {
+      "epoch": 0.06327612117377204,
+      "grad_norm": 0.7488412857055664,
+      "learning_rate": 4.950927569562368e-05,
+      "loss": 0.7381,
+      "num_input_tokens_seen": 132711296,
+      "step": 600
+    },
+    {
+      "epoch": 0.0843681615650294,
+      "grad_norm": 0.8657649159431458,
+      "learning_rate": 4.912910528212802e-05,
+      "loss": 0.706,
+      "num_input_tokens_seen": 177102464,
+      "step": 800
+    },
+    {
+      "epoch": 0.10546020195628675,
+      "grad_norm": 0.835016131401062,
+      "learning_rate": 4.864302360905221e-05,
+      "loss": 0.6805,
+      "num_input_tokens_seen": 221189952,
+      "step": 1000
+    },
+    {
+      "epoch": 0.12655224234754409,
+      "grad_norm": 0.8248361945152283,
+      "learning_rate": 4.8053164262439e-05,
+      "loss": 0.6578,
+      "num_input_tokens_seen": 265373568,
+      "step": 1200
+    },
+    {
+      "epoch": 0.14764428273880145,
+      "grad_norm": 0.9251222014427185,
+      "learning_rate": 4.736211634559929e-05,
+      "loss": 0.645,
+      "num_input_tokens_seen": 309590976,
+      "step": 1400
+    },
+    {
+      "epoch": 0.1687363231300588,
+      "grad_norm": 1.0570456981658936,
+      "learning_rate": 4.657291311461312e-05,
+      "loss": 0.6295,
+      "num_input_tokens_seen": 353823104,
+      "step": 1600
+    },
+    {
+      "epoch": 0.18982836352131616,
+      "grad_norm": 0.8825539350509644,
+      "learning_rate": 4.5689018664285547e-05,
+      "loss": 0.6153,
+      "num_input_tokens_seen": 397997888,
+      "step": 1800
+    },
+    {
+      "epoch": 0.2109204039125735,
+      "grad_norm": 0.9760900735855103,
+      "learning_rate": 4.471431272299751e-05,
+      "loss": 0.6042,
+      "num_input_tokens_seen": 442188672,
+      "step": 2000
+    },
+    {
+      "epoch": 0.23201244430383083,
+      "grad_norm": 0.95518559217453,
+      "learning_rate": 4.365307362319256e-05,
+      "loss": 0.5945,
+      "num_input_tokens_seen": 486364032,
+      "step": 2200
+    },
+    {
+      "epoch": 0.25310448469508817,
+      "grad_norm": 0.9054489135742188,
+      "learning_rate": 4.2509959522247934e-05,
+      "loss": 0.5865,
+      "num_input_tokens_seen": 530501120,
+      "step": 2400
+    },
+    {
+      "epoch": 0.27419652508634557,
+      "grad_norm": 1.0242657661437988,
+      "learning_rate": 4.128998795615841e-05,
+      "loss": 0.58,
+      "num_input_tokens_seen": 574837120,
+      "step": 2600
+    },
+    {
+      "epoch": 0.2952885654776029,
+      "grad_norm": 1.1412681341171265,
+      "learning_rate": 3.999851381577905e-05,
+      "loss": 0.5707,
+      "num_input_tokens_seen": 618964480,
+      "step": 2800
+    },
+    {
+      "epoch": 0.31638060586886024,
+      "grad_norm": 1.0616246461868286,
+      "learning_rate": 3.864120584229707e-05,
+      "loss": 0.5639,
+      "num_input_tokens_seen": 663315776,
+      "step": 3000
+    },
+    {
+      "epoch": 0.3374726462601176,
+      "grad_norm": 1.0734329223632812,
+      "learning_rate": 3.722402174510236e-05,
+      "loss": 0.5597,
+      "num_input_tokens_seen": 707722240,
+      "step": 3200
+    },
+    {
+      "epoch": 0.3585646866513749,
+      "grad_norm": 1.0842781066894531,
+      "learning_rate": 3.5753182051273594e-05,
+      "loss": 0.5533,
+      "num_input_tokens_seen": 751884864,
+      "step": 3400
+    },
+    {
+      "epoch": 0.3796567270426323,
+      "grad_norm": 1.0658433437347412,
+      "learning_rate": 3.423514280146341e-05,
+      "loss": 0.5442,
+      "num_input_tokens_seen": 796284224,
+      "step": 3600
+    },
+    {
+      "epoch": 0.40074876743388965,
+      "grad_norm": 1.0794566869735718,
+      "learning_rate": 3.267656721203064e-05,
+      "loss": 0.542,
+      "num_input_tokens_seen": 840569728,
+      "step": 3800
+    },
+    {
+      "epoch": 0.421840807825147,
+      "grad_norm": 1.2425159215927124,
+      "learning_rate": 3.108429642780421e-05,
+      "loss": 0.5361,
+      "num_input_tokens_seen": 884788608,
+      "step": 4000
+    },
+    {
+      "epoch": 0.44293284821640433,
+      "grad_norm": 1.080336332321167,
+      "learning_rate": 2.9465319493855552e-05,
+      "loss": 0.531,
+      "num_input_tokens_seen": 929015680,
+      "step": 4200
+    },
+    {
+      "epoch": 0.46402488860766167,
+      "grad_norm": 1.1406266689300537,
+      "learning_rate": 2.7826742678084e-05,
+      "loss": 0.5287,
+      "num_input_tokens_seen": 973320448,
+      "step": 4400
+    },
+    {
+      "epoch": 0.485116928998919,
+      "grad_norm": 1.081685185432434,
+      "learning_rate": 2.6175758279269303e-05,
+      "loss": 0.521,
+      "num_input_tokens_seen": 1017647040,
+      "step": 4600
+    },
+    {
+      "epoch": 0.5062089693901763,
+      "grad_norm": 1.0887905359268188,
+      "learning_rate": 2.451961305750393e-05,
+      "loss": 0.5184,
+      "num_input_tokens_seen": 1061997888,
+      "step": 4800
+    },
+    {
+      "epoch": 0.5273010097814337,
+      "grad_norm": 1.0519535541534424,
+      "learning_rate": 2.2865576425575215e-05,
+      "loss": 0.5141,
+      "num_input_tokens_seen": 1106436416,
+      "step": 5000
+    },
+    {
+      "epoch": 0.5483930501726911,
+      "grad_norm": 1.1306272745132446,
+      "learning_rate": 2.122090854091672e-05,
+      "loss": 0.5101,
+      "num_input_tokens_seen": 1150734720,
+      "step": 5200
+    },
+    {
+      "epoch": 0.5694850905639485,
+      "grad_norm": 1.2493129968643188,
+      "learning_rate": 1.9592828438184685e-05,
+      "loss": 0.5068,
+      "num_input_tokens_seen": 1195030080,
+      "step": 5400
+    },
+    {
+      "epoch": 0.5905771309552058,
+      "grad_norm": 1.1448969841003418,
+      "learning_rate": 1.7988482342336927e-05,
+      "loss": 0.5012,
+      "num_input_tokens_seen": 1239434432,
+      "step": 5600
+    },
+    {
+      "epoch": 0.6116691713464631,
+      "grad_norm": 1.1951446533203125,
+      "learning_rate": 1.6414912301299696e-05,
+      "loss": 0.5006,
+      "num_input_tokens_seen": 1283707776,
+      "step": 5800
+    },
+    {
+      "epoch": 0.6327612117377205,
+      "grad_norm": 1.19136381149292,
+      "learning_rate": 1.4879025275904534e-05,
+      "loss": 0.4975,
+      "num_input_tokens_seen": 1327901312,
+      "step": 6000
+    },
+    {
+      "epoch": 0.6538532521289778,
+      "grad_norm": 1.2069401741027832,
+      "learning_rate": 1.3387562822770727e-05,
+      "loss": 0.4938,
+      "num_input_tokens_seen": 1372311040,
+      "step": 6200
+    },
+    {
+      "epoch": 0.6749452925202352,
+      "grad_norm": 1.2452600002288818,
+      "learning_rate": 1.194707150320592e-05,
+      "loss": 0.4925,
+      "num_input_tokens_seen": 1416523904,
+      "step": 6400
+    },
+    {
+      "epoch": 0.6960373329114925,
+      "grad_norm": 1.3586419820785522,
+      "learning_rate": 1.0563874148010725e-05,
+      "loss": 0.4888,
+      "num_input_tokens_seen": 1460803456,
+      "step": 6600
+    },
+    {
+      "epoch": 0.7171293733027498,
+      "grad_norm": 1.186355471611023,
+      "learning_rate": 9.244042104316522e-06,
+      "loss": 0.4858,
+      "num_input_tokens_seen": 1505213888,
+      "step": 6800
+    },
+    {
+      "epoch": 0.7382214136940072,
+      "grad_norm": 1.15864896774292,
+      "learning_rate": 7.993368586274711e-06,
+      "loss": 0.4834,
+      "num_input_tokens_seen": 1549483328,
+      "step": 7000
+    },
+    {
+      "epoch": 0.7593134540852646,
+      "grad_norm": 1.2812916040420532,
+      "learning_rate": 6.817343246571176e-06,
+      "loss": 0.483,
+      "num_input_tokens_seen": 1593631168,
+      "step": 7200
+    },
+    {
+      "epoch": 0.780405494476522,
+      "grad_norm": 1.3027392625808716,
+      "learning_rate": 5.7211280803801945e-06,
+      "loss": 0.4826,
+      "num_input_tokens_seen": 1637873600,
+      "step": 7400
+    },
+    {
+      "epoch": 0.8014975348677793,
+      "grad_norm": 1.2680199146270752,
+      "learning_rate": 4.7095347675243015e-06,
+      "loss": 0.4799,
+      "num_input_tokens_seen": 1682312384,
+      "step": 7600
+    },
+    {
+      "epoch": 0.8225895752590366,
+      "grad_norm": 1.323339819908142,
+      "learning_rate": 3.7870035522933416e-06,
+      "loss": 0.4776,
+      "num_input_tokens_seen": 1726473216,
+      "step": 7800
+    },
+    {
+      "epoch": 0.843681615650294,
+      "grad_norm": 1.3831522464752197,
+      "learning_rate": 2.9575837536265804e-06,
+      "loss": 0.4783,
+      "num_input_tokens_seen": 1770914880,
+      "step": 8000
+    },
+    {
+      "epoch": 0.8647736560415513,
+      "grad_norm": 1.3245904445648193,
+      "learning_rate": 2.2249159912059698e-06,
+      "loss": 0.4757,
+      "num_input_tokens_seen": 1815006528,
+      "step": 8200
+    },
+    {
+      "epoch": 0.8858656964328087,
+      "grad_norm": 1.2998374700546265,
+      "learning_rate": 1.592216205476227e-06,
+      "loss": 0.4747,
+      "num_input_tokens_seen": 1859331136,
+      "step": 8400
+    },
+    {
+      "epoch": 0.906957736824066,
+      "grad_norm": 1.2577829360961914,
+      "learning_rate": 1.0622615417338333e-06,
+      "loss": 0.474,
+      "num_input_tokens_seen": 1903616448,
+      "step": 8600
+    },
+    {
+      "epoch": 0.9280497772153233,
+      "grad_norm": 1.3561482429504395,
+      "learning_rate": 6.373781602446283e-07,
+      "loss": 0.4727,
+      "num_input_tokens_seen": 1947822592,
+      "step": 8800
+    },
+    {
+      "epoch": 0.9491418176065807,
+      "grad_norm": 1.2875652313232422,
+      "learning_rate": 3.194310258956973e-07,
+      "loss": 0.473,
+      "num_input_tokens_seen": 1992285376,
+      "step": 9000
+    },
+    {
+      "epoch": 0.970233857997838,
+      "grad_norm": 1.2597335577011108,
+      "learning_rate": 1.0981572219854463e-07,
+      "loss": 0.475,
+      "num_input_tokens_seen": 2036784768,
+      "step": 9200
+    },
+    {
+      "epoch": 0.9913258983890955,
+      "grad_norm": 1.3087178468704224,
+      "learning_rate": 9.452325574654808e-09,
+      "loss": 0.4727,
+      "num_input_tokens_seen": 2080910400,
+      "step": 9400
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 9482,
+  "num_input_tokens_seen": 2098994560,
+  "num_train_epochs": 1,
+  "save_steps": 5000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.036532744878576e+20,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-9482/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b67a849052e63a79cac3d48fab6344509c199df76d24cab58ea474286c1afc7c
+size 6225

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

swanlab_public_config.json

@@ -0,0 +1,13 @@
+{
+  "project_name": "Qwen3-32B_sft",
+  "version": "0.6.4",
+  "run_id": "a3b1799d",
+  "swanlog_dir": "/data/home/zdhs0020/code/swanlog",
+  "run_dir": "/data/home/zdhs0020/code/swanlog/run-20250715_231914-a3b1799d",
+  "cloud": {
+    "project_name": "Qwen3-32B_sft",
+    "project_url": "https://swanlab.cn/@ccjh/Qwen3-32B_sft",
+    "experiment_name": "widthIrplus_msg_qm9s_mb_msd",
+    "experiment_url": "https://swanlab.cn/@ccjh/Qwen3-32B_sft/runs/vlt9qhgnjutu7cvjptqzw"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,241 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "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 +1,9 @@
+{
+    "epoch": 0.999973634949511,
+    "num_input_tokens_seen": 2098994560,
+    "total_flos": 4.036532744878576e+20,
+    "train_loss": 0.5513084518635382,
+    "train_runtime": 186000.3322,
+    "train_samples_per_second": 13.051,
+    "train_steps_per_second": 0.051
+}

trainer_log.jsonl

@@ -0,0 +1,48 @@
+{"current_steps": 200, "total_steps": 9482, "loss": 0.947, "lr": 4.994568013593584e-05, "epoch": 0.02109204039125735, "percentage": 2.11, "elapsed_time": "1:05:25", "remaining_time": "2 days, 2:36:08", "throughput": 11263.47, "total_tokens": 44211392}
+{"current_steps": 400, "total_steps": 9482, "loss": 0.7951, "lr": 4.9781866145835606e-05, "epoch": 0.0421840807825147, "percentage": 4.22, "elapsed_time": "2:10:28", "remaining_time": "2 days, 1:22:22", "throughput": 11310.55, "total_tokens": 88542848}
+{"current_steps": 600, "total_steps": 9482, "loss": 0.7381, "lr": 4.950927569562368e-05, "epoch": 0.06327612117377204, "percentage": 6.33, "elapsed_time": "3:15:20", "remaining_time": "2 days, 0:11:39", "throughput": 11323.18, "total_tokens": 132711296}
+{"current_steps": 800, "total_steps": 9482, "loss": 0.706, "lr": 4.912910528212802e-05, "epoch": 0.0843681615650294, "percentage": 8.44, "elapsed_time": "4:21:11", "remaining_time": "1 day, 23:14:30", "throughput": 11301.2, "total_tokens": 177102464}
+{"current_steps": 1000, "total_steps": 9482, "loss": 0.6805, "lr": 4.864302360905221e-05, "epoch": 0.10546020195628675, "percentage": 10.55, "elapsed_time": "5:26:02", "remaining_time": "1 day, 22:05:27", "throughput": 11306.92, "total_tokens": 221189952}
+{"current_steps": 1200, "total_steps": 9482, "loss": 0.6578, "lr": 4.8053164262439e-05, "epoch": 0.12655224234754409, "percentage": 12.66, "elapsed_time": "6:31:23", "remaining_time": "1 day, 21:01:14", "throughput": 11300.46, "total_tokens": 265373568}
+{"current_steps": 1400, "total_steps": 9482, "loss": 0.645, "lr": 4.736211634559929e-05, "epoch": 0.14764428273880145, "percentage": 14.76, "elapsed_time": "7:36:06", "remaining_time": "1 day, 19:53:01", "throughput": 11312.86, "total_tokens": 309590976}
+{"current_steps": 1600, "total_steps": 9482, "loss": 0.6295, "lr": 4.657291311461312e-05, "epoch": 0.1687363231300588, "percentage": 16.87, "elapsed_time": "8:41:30", "remaining_time": "1 day, 18:49:06", "throughput": 11307.57, "total_tokens": 353823104}
+{"current_steps": 1800, "total_steps": 9482, "loss": 0.6153, "lr": 4.5689018664285547e-05, "epoch": 0.18982836352131616, "percentage": 18.98, "elapsed_time": "9:46:44", "remaining_time": "1 day, 17:44:06", "throughput": 11305.22, "total_tokens": 397997888}
+{"current_steps": 2000, "total_steps": 9482, "loss": 0.6042, "lr": 4.471431272299751e-05, "epoch": 0.2109204039125735, "percentage": 21.09, "elapsed_time": "10:52:18", "remaining_time": "1 day, 16:40:15", "throughput": 11298.18, "total_tokens": 442188672}
+{"current_steps": 2200, "total_steps": 9482, "loss": 0.5945, "lr": 4.365307362319256e-05, "epoch": 0.23201244430383083, "percentage": 23.2, "elapsed_time": "11:57:31", "remaining_time": "1 day, 15:34:58", "throughput": 11297.39, "total_tokens": 486364032}
+{"current_steps": 2400, "total_steps": 9482, "loss": 0.5865, "lr": 4.2509959522247934e-05, "epoch": 0.25310448469508817, "percentage": 25.31, "elapsed_time": "13:02:26", "remaining_time": "1 day, 14:28:50", "throughput": 11300.15, "total_tokens": 530501120}
+{"current_steps": 2600, "total_steps": 9482, "loss": 0.58, "lr": 4.128998795615841e-05, "epoch": 0.27419652508634557, "percentage": 27.42, "elapsed_time": "14:07:57", "remaining_time": "1 day, 13:24:30", "throughput": 11298.35, "total_tokens": 574837120}
+{"current_steps": 2800, "total_steps": 9482, "loss": 0.5707, "lr": 3.999851381577905e-05, "epoch": 0.2952885654776029, "percentage": 29.53, "elapsed_time": "15:13:17", "remaining_time": "1 day, 12:19:30", "throughput": 11295.47, "total_tokens": 618964480}
+{"current_steps": 3000, "total_steps": 9482, "loss": 0.5639, "lr": 3.864120584229707e-05, "epoch": 0.31638060586886024, "percentage": 31.64, "elapsed_time": "16:18:40", "remaining_time": "1 day, 11:14:35", "throughput": 11296.18, "total_tokens": 663315776}
+{"current_steps": 3200, "total_steps": 9482, "loss": 0.5597, "lr": 3.722402174510236e-05, "epoch": 0.3374726462601176, "percentage": 33.75, "elapsed_time": "17:24:06", "remaining_time": "1 day, 10:09:43", "throughput": 11297.01, "total_tokens": 707722240}
+{"current_steps": 3400, "total_steps": 9482, "loss": 0.5533, "lr": 3.5753182051273594e-05, "epoch": 0.3585646866513749, "percentage": 35.86, "elapsed_time": "18:29:14", "remaining_time": "1 day, 9:04:14", "throughput": 11297.24, "total_tokens": 751884864}
+{"current_steps": 3600, "total_steps": 9482, "loss": 0.5442, "lr": 3.423514280146341e-05, "epoch": 0.3796567270426323, "percentage": 37.97, "elapsed_time": "19:34:26", "remaining_time": "1 day, 7:58:54", "throughput": 11300.22, "total_tokens": 796284224}
+{"current_steps": 3800, "total_steps": 9482, "loss": 0.542, "lr": 3.267656721203064e-05, "epoch": 0.40074876743388965, "percentage": 40.08, "elapsed_time": "20:40:12", "remaining_time": "1 day, 6:54:26", "throughput": 11296.01, "total_tokens": 840569728}
+{"current_steps": 4000, "total_steps": 9482, "loss": 0.5361, "lr": 3.108429642780421e-05, "epoch": 0.421840807825147, "percentage": 42.19, "elapsed_time": "21:45:31", "remaining_time": "1 day, 5:49:13", "throughput": 11295.47, "total_tokens": 884788608}
+{"current_steps": 4200, "total_steps": 9482, "loss": 0.531, "lr": 2.9465319493855552e-05, "epoch": 0.44293284821640433, "percentage": 44.29, "elapsed_time": "22:50:53", "remaining_time": "1 day, 4:44:04", "throughput": 11294.48, "total_tokens": 929015680}
+{"current_steps": 4400, "total_steps": 9482, "loss": 0.5287, "lr": 2.7826742678084e-05, "epoch": 0.46402488860766167, "percentage": 46.4, "elapsed_time": "23:56:23", "remaining_time": "1 day, 3:39:01", "throughput": 11293.62, "total_tokens": 973320448}
+{"current_steps": 4600, "total_steps": 9482, "loss": 0.521, "lr": 2.6175758279269303e-05, "epoch": 0.485116928998919, "percentage": 48.51, "elapsed_time": "1 day, 1:01:52", "remaining_time": "1 day, 2:33:56", "throughput": 11293.13, "total_tokens": 1017647040}
+{"current_steps": 4800, "total_steps": 9482, "loss": 0.5184, "lr": 2.451961305750393e-05, "epoch": 0.5062089693901763, "percentage": 50.62, "elapsed_time": "1 day, 2:07:39", "remaining_time": "1 day, 1:29:06", "throughput": 11290.74, "total_tokens": 1061997888}
+{"current_steps": 5000, "total_steps": 9482, "loss": 0.5141, "lr": 2.2865576425575215e-05, "epoch": 0.5273010097814337, "percentage": 52.73, "elapsed_time": "1 day, 3:13:18", "remaining_time": "1 day, 0:24:05", "throughput": 11290.37, "total_tokens": 1106436416}
+{"current_steps": 5200, "total_steps": 9482, "loss": 0.5101, "lr": 2.122090854091672e-05, "epoch": 0.5483930501726911, "percentage": 54.84, "elapsed_time": "1 day, 4:19:16", "remaining_time": "23:19:17", "throughput": 11286.56, "total_tokens": 1150734720}
+{"current_steps": 5400, "total_steps": 9482, "loss": 0.5068, "lr": 1.9592828438184685e-05, "epoch": 0.5694850905639485, "percentage": 56.95, "elapsed_time": "1 day, 5:24:29", "remaining_time": "22:13:49", "throughput": 11287.77, "total_tokens": 1195030080}
+{"current_steps": 5600, "total_steps": 9482, "loss": 0.5012, "lr": 1.7988482342336927e-05, "epoch": 0.5905771309552058, "percentage": 59.06, "elapsed_time": "1 day, 6:30:17", "remaining_time": "21:08:47", "throughput": 11286.3, "total_tokens": 1239434432}
+{"current_steps": 5800, "total_steps": 9482, "loss": 0.5006, "lr": 1.6414912301299696e-05, "epoch": 0.6116691713464631, "percentage": 61.17, "elapsed_time": "1 day, 7:35:32", "remaining_time": "20:03:20", "throughput": 11287.08, "total_tokens": 1283707776}
+{"current_steps": 6000, "total_steps": 9482, "loss": 0.4975, "lr": 1.4879025275904534e-05, "epoch": 0.6327612117377205, "percentage": 63.28, "elapsed_time": "1 day, 8:41:08", "remaining_time": "18:58:07", "throughput": 11285.07, "total_tokens": 1327901312}
+{"current_steps": 6200, "total_steps": 9482, "loss": 0.4938, "lr": 1.3387562822770727e-05, "epoch": 0.6538532521289778, "percentage": 65.39, "elapsed_time": "1 day, 9:46:43", "remaining_time": "17:52:51", "throughput": 11285.16, "total_tokens": 1372311040}
+{"current_steps": 6400, "total_steps": 9482, "loss": 0.4925, "lr": 1.194707150320592e-05, "epoch": 0.6749452925202352, "percentage": 67.5, "elapsed_time": "1 day, 10:51:56", "remaining_time": "16:47:24", "throughput": 11285.56, "total_tokens": 1416523904}
+{"current_steps": 6600, "total_steps": 9482, "loss": 0.4888, "lr": 1.0563874148010725e-05, "epoch": 0.6960373329114925, "percentage": 69.61, "elapsed_time": "1 day, 11:56:59", "remaining_time": "15:41:53", "throughput": 11287.34, "total_tokens": 1460803456}
+{"current_steps": 6800, "total_steps": 9482, "loss": 0.4858, "lr": 9.244042104316522e-06, "epoch": 0.7171293733027498, "percentage": 71.71, "elapsed_time": "1 day, 13:02:34", "remaining_time": "14:36:36", "throughput": 11287.27, "total_tokens": 1505213888}
+{"current_steps": 7000, "total_steps": 9482, "loss": 0.4834, "lr": 7.993368586274711e-06, "epoch": 0.7382214136940072, "percentage": 73.82, "elapsed_time": "1 day, 14:08:05", "remaining_time": "13:31:17", "throughput": 11286.6, "total_tokens": 1549483328}
+{"current_steps": 7200, "total_steps": 9482, "loss": 0.483, "lr": 6.817343246571176e-06, "epoch": 0.7593134540852646, "percentage": 75.93, "elapsed_time": "1 day, 15:13:24", "remaining_time": "12:25:53", "throughput": 11286.02, "total_tokens": 1593631168}
+{"current_steps": 7400, "total_steps": 9482, "loss": 0.4826, "lr": 5.7211280803801945e-06, "epoch": 0.780405494476522, "percentage": 78.04, "elapsed_time": "1 day, 16:18:38", "remaining_time": "11:20:29", "throughput": 11286.42, "total_tokens": 1637873600}
+{"current_steps": 7600, "total_steps": 9482, "loss": 0.4799, "lr": 4.7095347675243015e-06, "epoch": 0.8014975348677793, "percentage": 80.15, "elapsed_time": "1 day, 17:24:13", "remaining_time": "10:15:10", "throughput": 11286.64, "total_tokens": 1682312384}
+{"current_steps": 7800, "total_steps": 9482, "loss": 0.4776, "lr": 3.7870035522933416e-06, "epoch": 0.8225895752590366, "percentage": 82.26, "elapsed_time": "1 day, 18:29:21", "remaining_time": "9:09:44", "throughput": 11286.97, "total_tokens": 1726473216}
+{"current_steps": 8000, "total_steps": 9482, "loss": 0.4783, "lr": 2.9575837536265804e-06, "epoch": 0.843681615650294, "percentage": 84.37, "elapsed_time": "1 day, 19:34:57", "remaining_time": "8:04:25", "throughput": 11287.05, "total_tokens": 1770914880}
+{"current_steps": 8200, "total_steps": 9482, "loss": 0.4757, "lr": 2.2249159912059698e-06, "epoch": 0.8647736560415513, "percentage": 86.48, "elapsed_time": "1 day, 20:40:29", "remaining_time": "6:59:04", "throughput": 11285.31, "total_tokens": 1815006528}
+{"current_steps": 8400, "total_steps": 9482, "loss": 0.4747, "lr": 1.592216205476227e-06, "epoch": 0.8858656964328087, "percentage": 88.59, "elapsed_time": "1 day, 21:45:38", "remaining_time": "5:53:39", "throughput": 11286.54, "total_tokens": 1859331136}
+{"current_steps": 8600, "total_steps": 9482, "loss": 0.474, "lr": 1.0622615417338333e-06, "epoch": 0.906957736824066, "percentage": 90.7, "elapsed_time": "1 day, 22:50:54", "remaining_time": "4:48:16", "throughput": 11287.08, "total_tokens": 1903616448}
+{"current_steps": 8800, "total_steps": 9482, "loss": 0.4727, "lr": 6.373781602446283e-07, "epoch": 0.9280497772153233, "percentage": 92.81, "elapsed_time": "1 day, 23:56:15", "remaining_time": "3:42:54", "throughput": 11286.82, "total_tokens": 1947822592}
+{"current_steps": 9000, "total_steps": 9482, "loss": 0.473, "lr": 3.194310258956973e-07, "epoch": 0.9491418176065807, "percentage": 94.92, "elapsed_time": "2 days, 1:01:56", "remaining_time": "2:37:33", "throughput": 11286.67, "total_tokens": 1992285376}
+{"current_steps": 9200, "total_steps": 9482, "loss": 0.475, "lr": 1.0981572219854463e-07, "epoch": 0.970233857997838, "percentage": 97.03, "elapsed_time": "2 days, 2:08:02", "remaining_time": "1:32:12", "throughput": 11285.23, "total_tokens": 2036784768}
+{"current_steps": 9400, "total_steps": 9482, "loss": 0.4727, "lr": 9.452325574654808e-09, "epoch": 0.9913258983890955, "percentage": 99.14, "elapsed_time": "2 days, 3:13:15", "remaining_time": "0:26:48", "throughput": 11285.04, "total_tokens": 2080910400}
+{"current_steps": 9482, "total_steps": 9482, "epoch": 0.999973634949511, "percentage": 100.0, "elapsed_time": "2 days, 3:40:00", "remaining_time": "0:00:00", "throughput": 11284.9, "total_tokens": 2098994560}

trainer_state.json

@@ -0,0 +1,420 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.999973634949511,
+  "eval_steps": 500,
+  "global_step": 9482,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02109204039125735,
+      "grad_norm": 0.40668317675590515,
+      "learning_rate": 4.994568013593584e-05,
+      "loss": 0.947,
+      "num_input_tokens_seen": 44211392,
+      "step": 200
+    },
+    {
+      "epoch": 0.0421840807825147,
+      "grad_norm": 0.5519078373908997,
+      "learning_rate": 4.9781866145835606e-05,
+      "loss": 0.7951,
+      "num_input_tokens_seen": 88542848,
+      "step": 400
+    },
+    {
+      "epoch": 0.06327612117377204,
+      "grad_norm": 0.7488412857055664,
+      "learning_rate": 4.950927569562368e-05,
+      "loss": 0.7381,
+      "num_input_tokens_seen": 132711296,
+      "step": 600
+    },
+    {
+      "epoch": 0.0843681615650294,
+      "grad_norm": 0.8657649159431458,
+      "learning_rate": 4.912910528212802e-05,
+      "loss": 0.706,
+      "num_input_tokens_seen": 177102464,
+      "step": 800
+    },
+    {
+      "epoch": 0.10546020195628675,
+      "grad_norm": 0.835016131401062,
+      "learning_rate": 4.864302360905221e-05,
+      "loss": 0.6805,
+      "num_input_tokens_seen": 221189952,
+      "step": 1000
+    },
+    {
+      "epoch": 0.12655224234754409,
+      "grad_norm": 0.8248361945152283,
+      "learning_rate": 4.8053164262439e-05,
+      "loss": 0.6578,
+      "num_input_tokens_seen": 265373568,
+      "step": 1200
+    },
+    {
+      "epoch": 0.14764428273880145,
+      "grad_norm": 0.9251222014427185,
+      "learning_rate": 4.736211634559929e-05,
+      "loss": 0.645,
+      "num_input_tokens_seen": 309590976,
+      "step": 1400
+    },
+    {
+      "epoch": 0.1687363231300588,
+      "grad_norm": 1.0570456981658936,
+      "learning_rate": 4.657291311461312e-05,
+      "loss": 0.6295,
+      "num_input_tokens_seen": 353823104,
+      "step": 1600
+    },
+    {
+      "epoch": 0.18982836352131616,
+      "grad_norm": 0.8825539350509644,
+      "learning_rate": 4.5689018664285547e-05,
+      "loss": 0.6153,
+      "num_input_tokens_seen": 397997888,
+      "step": 1800
+    },
+    {
+      "epoch": 0.2109204039125735,
+      "grad_norm": 0.9760900735855103,
+      "learning_rate": 4.471431272299751e-05,
+      "loss": 0.6042,
+      "num_input_tokens_seen": 442188672,
+      "step": 2000
+    },
+    {
+      "epoch": 0.23201244430383083,
+      "grad_norm": 0.95518559217453,
+      "learning_rate": 4.365307362319256e-05,
+      "loss": 0.5945,
+      "num_input_tokens_seen": 486364032,
+      "step": 2200
+    },
+    {
+      "epoch": 0.25310448469508817,
+      "grad_norm": 0.9054489135742188,
+      "learning_rate": 4.2509959522247934e-05,
+      "loss": 0.5865,
+      "num_input_tokens_seen": 530501120,
+      "step": 2400
+    },
+    {
+      "epoch": 0.27419652508634557,
+      "grad_norm": 1.0242657661437988,
+      "learning_rate": 4.128998795615841e-05,
+      "loss": 0.58,
+      "num_input_tokens_seen": 574837120,
+      "step": 2600
+    },
+    {
+      "epoch": 0.2952885654776029,
+      "grad_norm": 1.1412681341171265,
+      "learning_rate": 3.999851381577905e-05,
+      "loss": 0.5707,
+      "num_input_tokens_seen": 618964480,
+      "step": 2800
+    },
+    {
+      "epoch": 0.31638060586886024,
+      "grad_norm": 1.0616246461868286,
+      "learning_rate": 3.864120584229707e-05,
+      "loss": 0.5639,
+      "num_input_tokens_seen": 663315776,
+      "step": 3000
+    },
+    {
+      "epoch": 0.3374726462601176,
+      "grad_norm": 1.0734329223632812,
+      "learning_rate": 3.722402174510236e-05,
+      "loss": 0.5597,
+      "num_input_tokens_seen": 707722240,
+      "step": 3200
+    },
+    {
+      "epoch": 0.3585646866513749,
+      "grad_norm": 1.0842781066894531,
+      "learning_rate": 3.5753182051273594e-05,
+      "loss": 0.5533,
+      "num_input_tokens_seen": 751884864,
+      "step": 3400
+    },
+    {
+      "epoch": 0.3796567270426323,
+      "grad_norm": 1.0658433437347412,
+      "learning_rate": 3.423514280146341e-05,
+      "loss": 0.5442,
+      "num_input_tokens_seen": 796284224,
+      "step": 3600
+    },
+    {
+      "epoch": 0.40074876743388965,
+      "grad_norm": 1.0794566869735718,
+      "learning_rate": 3.267656721203064e-05,
+      "loss": 0.542,
+      "num_input_tokens_seen": 840569728,
+      "step": 3800
+    },
+    {
+      "epoch": 0.421840807825147,
+      "grad_norm": 1.2425159215927124,
+      "learning_rate": 3.108429642780421e-05,
+      "loss": 0.5361,
+      "num_input_tokens_seen": 884788608,
+      "step": 4000
+    },
+    {
+      "epoch": 0.44293284821640433,
+      "grad_norm": 1.080336332321167,
+      "learning_rate": 2.9465319493855552e-05,
+      "loss": 0.531,
+      "num_input_tokens_seen": 929015680,
+      "step": 4200
+    },
+    {
+      "epoch": 0.46402488860766167,
+      "grad_norm": 1.1406266689300537,
+      "learning_rate": 2.7826742678084e-05,
+      "loss": 0.5287,
+      "num_input_tokens_seen": 973320448,
+      "step": 4400
+    },
+    {
+      "epoch": 0.485116928998919,
+      "grad_norm": 1.081685185432434,
+      "learning_rate": 2.6175758279269303e-05,
+      "loss": 0.521,
+      "num_input_tokens_seen": 1017647040,
+      "step": 4600
+    },
+    {
+      "epoch": 0.5062089693901763,
+      "grad_norm": 1.0887905359268188,
+      "learning_rate": 2.451961305750393e-05,
+      "loss": 0.5184,
+      "num_input_tokens_seen": 1061997888,
+      "step": 4800
+    },
+    {
+      "epoch": 0.5273010097814337,
+      "grad_norm": 1.0519535541534424,
+      "learning_rate": 2.2865576425575215e-05,
+      "loss": 0.5141,
+      "num_input_tokens_seen": 1106436416,
+      "step": 5000
+    },
+    {
+      "epoch": 0.5483930501726911,
+      "grad_norm": 1.1306272745132446,
+      "learning_rate": 2.122090854091672e-05,
+      "loss": 0.5101,
+      "num_input_tokens_seen": 1150734720,
+      "step": 5200
+    },
+    {
+      "epoch": 0.5694850905639485,
+      "grad_norm": 1.2493129968643188,
+      "learning_rate": 1.9592828438184685e-05,
+      "loss": 0.5068,
+      "num_input_tokens_seen": 1195030080,
+      "step": 5400
+    },
+    {
+      "epoch": 0.5905771309552058,
+      "grad_norm": 1.1448969841003418,
+      "learning_rate": 1.7988482342336927e-05,
+      "loss": 0.5012,
+      "num_input_tokens_seen": 1239434432,
+      "step": 5600
+    },
+    {
+      "epoch": 0.6116691713464631,
+      "grad_norm": 1.1951446533203125,
+      "learning_rate": 1.6414912301299696e-05,
+      "loss": 0.5006,
+      "num_input_tokens_seen": 1283707776,
+      "step": 5800
+    },
+    {
+      "epoch": 0.6327612117377205,
+      "grad_norm": 1.19136381149292,
+      "learning_rate": 1.4879025275904534e-05,
+      "loss": 0.4975,
+      "num_input_tokens_seen": 1327901312,
+      "step": 6000
+    },
+    {
+      "epoch": 0.6538532521289778,
+      "grad_norm": 1.2069401741027832,
+      "learning_rate": 1.3387562822770727e-05,
+      "loss": 0.4938,
+      "num_input_tokens_seen": 1372311040,
+      "step": 6200
+    },
+    {
+      "epoch": 0.6749452925202352,
+      "grad_norm": 1.2452600002288818,
+      "learning_rate": 1.194707150320592e-05,
+      "loss": 0.4925,
+      "num_input_tokens_seen": 1416523904,
+      "step": 6400
+    },
+    {
+      "epoch": 0.6960373329114925,
+      "grad_norm": 1.3586419820785522,
+      "learning_rate": 1.0563874148010725e-05,
+      "loss": 0.4888,
+      "num_input_tokens_seen": 1460803456,
+      "step": 6600
+    },
+    {
+      "epoch": 0.7171293733027498,
+      "grad_norm": 1.186355471611023,
+      "learning_rate": 9.244042104316522e-06,
+      "loss": 0.4858,
+      "num_input_tokens_seen": 1505213888,
+      "step": 6800
+    },
+    {
+      "epoch": 0.7382214136940072,
+      "grad_norm": 1.15864896774292,
+      "learning_rate": 7.993368586274711e-06,
+      "loss": 0.4834,
+      "num_input_tokens_seen": 1549483328,
+      "step": 7000
+    },
+    {
+      "epoch": 0.7593134540852646,
+      "grad_norm": 1.2812916040420532,
+      "learning_rate": 6.817343246571176e-06,
+      "loss": 0.483,
+      "num_input_tokens_seen": 1593631168,
+      "step": 7200
+    },
+    {
+      "epoch": 0.780405494476522,
+      "grad_norm": 1.3027392625808716,
+      "learning_rate": 5.7211280803801945e-06,
+      "loss": 0.4826,
+      "num_input_tokens_seen": 1637873600,
+      "step": 7400
+    },
+    {
+      "epoch": 0.8014975348677793,
+      "grad_norm": 1.2680199146270752,
+      "learning_rate": 4.7095347675243015e-06,
+      "loss": 0.4799,
+      "num_input_tokens_seen": 1682312384,
+      "step": 7600
+    },
+    {
+      "epoch": 0.8225895752590366,
+      "grad_norm": 1.323339819908142,
+      "learning_rate": 3.7870035522933416e-06,
+      "loss": 0.4776,
+      "num_input_tokens_seen": 1726473216,
+      "step": 7800
+    },
+    {
+      "epoch": 0.843681615650294,
+      "grad_norm": 1.3831522464752197,
+      "learning_rate": 2.9575837536265804e-06,
+      "loss": 0.4783,
+      "num_input_tokens_seen": 1770914880,
+      "step": 8000
+    },
+    {
+      "epoch": 0.8647736560415513,
+      "grad_norm": 1.3245904445648193,
+      "learning_rate": 2.2249159912059698e-06,
+      "loss": 0.4757,
+      "num_input_tokens_seen": 1815006528,
+      "step": 8200
+    },
+    {
+      "epoch": 0.8858656964328087,
+      "grad_norm": 1.2998374700546265,
+      "learning_rate": 1.592216205476227e-06,
+      "loss": 0.4747,
+      "num_input_tokens_seen": 1859331136,
+      "step": 8400
+    },
+    {
+      "epoch": 0.906957736824066,
+      "grad_norm": 1.2577829360961914,
+      "learning_rate": 1.0622615417338333e-06,
+      "loss": 0.474,
+      "num_input_tokens_seen": 1903616448,
+      "step": 8600
+    },
+    {
+      "epoch": 0.9280497772153233,
+      "grad_norm": 1.3561482429504395,
+      "learning_rate": 6.373781602446283e-07,
+      "loss": 0.4727,
+      "num_input_tokens_seen": 1947822592,
+      "step": 8800
+    },
+    {
+      "epoch": 0.9491418176065807,
+      "grad_norm": 1.2875652313232422,
+      "learning_rate": 3.194310258956973e-07,
+      "loss": 0.473,
+      "num_input_tokens_seen": 1992285376,
+      "step": 9000
+    },
+    {
+      "epoch": 0.970233857997838,
+      "grad_norm": 1.2597335577011108,
+      "learning_rate": 1.0981572219854463e-07,
+      "loss": 0.475,
+      "num_input_tokens_seen": 2036784768,
+      "step": 9200
+    },
+    {
+      "epoch": 0.9913258983890955,
+      "grad_norm": 1.3087178468704224,
+      "learning_rate": 9.452325574654808e-09,
+      "loss": 0.4727,
+      "num_input_tokens_seen": 2080910400,
+      "step": 9400
+    },
+    {
+      "epoch": 0.999973634949511,
+      "num_input_tokens_seen": 2098994560,
+      "step": 9482,
+      "total_flos": 4.036532744878576e+20,
+      "train_loss": 0.5513084518635382,
+      "train_runtime": 186000.3322,
+      "train_samples_per_second": 13.051,
+      "train_steps_per_second": 0.051
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 9482,
+  "num_input_tokens_seen": 2098994560,
+  "num_train_epochs": 1,
+  "save_steps": 5000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.036532744878576e+20,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b67a849052e63a79cac3d48fab6344509c199df76d24cab58ea474286c1afc7c
+size 6225