Duplicate from bbytxt/28ef7971-706c-45ba-97e0-27211138e639

Co-authored-by: Bby TXT <bbytxt@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,165 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 28ef7971-706c-45ba-97e0-27211138e639
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+adapter: lora
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+bf16: true
+chat_template: llama3
+data_processes: 16
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - 721ca1eb26cbf5fe_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/721ca1eb26cbf5fe_train_data.json
+  type:
+    field_instruction: instruction
+    field_output: output
+    format: '{instruction}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+device_map: auto
+do_eval: true
+early_stopping_patience: 5
+eval_batch_size: 2
+eval_max_new_tokens: 128
+eval_steps: 50
+eval_table_size: null
+evals_per_epoch: null
+flash_attention: true
+fp16: false
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: bbytxt/28ef7971-706c-45ba-97e0-27211138e639
+hub_repo: null
+hub_strategy: checkpoint
+hub_token: null
+learning_rate: 0.0001
+load_in_4bit: false
+load_in_8bit: false
+local_rank: null
+logging_steps: 1
+lora_alpha: 128
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 64
+lora_target_linear: true
+lr_scheduler: cosine
+max_grad_norm: 1.0
+max_memory:
+  0: 75GB
+max_steps: 200
+micro_batch_size: 8
+mlflow_experiment_name: /tmp/721ca1eb26cbf5fe_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 3
+optim_args:
+  adam_beta1: 0.9
+  adam_beta2: 0.95
+  adam_epsilon: 1e-5
+optimizer: adamw_torch
+output_dir: miner_id_24
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+s2_attention: null
+sample_packing: false
+save_steps: 50
+saves_per_epoch: null
+sequence_len: 1024
+strict: false
+tf32: true
+tokenizer_type: AutoTokenizer
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.05
+wandb_entity: null
+wandb_mode: online
+wandb_name: bae94509-30ed-4592-8856-f9a8f06a78a0
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: bae94509-30ed-4592-8856-f9a8f06a78a0
+warmup_steps: 30
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# 28ef7971-706c-45ba-97e0-27211138e639
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6194
+
+## 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: 8
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 30
+- training_steps: 200
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.8717        | 0.0007 | 1    | 1.0154          |
+| 1.0443        | 0.0342 | 50   | 0.8211          |
+| 1.0165        | 0.0685 | 100  | 0.7142          |
+| 0.7148        | 0.1027 | 150  | 0.6378          |
+| 0.8487        | 0.1370 | 200  | 0.6194          |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.0
+- Pytorch 2.5.0+cu124
+- Datasets 3.0.1
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a8b2023623e33640c5cf7bafff56a9e4f0b0b6e2a7ba3ab01873cfdc62608ac
+size 295577898

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c16d32e7159ef5189e8512af6b0056ccdb492abe895a1f295c9ae7ce5872b0f
+size 295488936

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+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 0.13.2

last-checkpoint/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

last-checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c16d32e7159ef5189e8512af6b0056ccdb492abe895a1f295c9ae7ce5872b0f
+size 295488936

last-checkpoint/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56494d51815f431b9043fe8a46399a22fec15a1e028f5fb5f92441532ffc3672
+size 591203178

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b4d91e1091607ca4e91757e682bb9579db098f0a5921407c13afcba9350eacf
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
+size 1064

last-checkpoint/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
+  }
+}

last-checkpoint/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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
+    }
+  },
+  "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 not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,1482 @@
+{
+  "best_metric": 0.6194487810134888,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.1369628488272556,
+  "eval_steps": 50,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.000684814244136278,
+      "grad_norm": 0.6065170764923096,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.8717,
+      "step": 1
+    },
+    {
+      "epoch": 0.000684814244136278,
+      "eval_loss": 1.0153580904006958,
+      "eval_runtime": 117.0614,
+      "eval_samples_per_second": 21.015,
+      "eval_steps_per_second": 10.507,
+      "step": 1
+    },
+    {
+      "epoch": 0.001369628488272556,
+      "grad_norm": 0.7065351605415344,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.8447,
+      "step": 2
+    },
+    {
+      "epoch": 0.002054442732408834,
+      "grad_norm": 0.6312601566314697,
+      "learning_rate": 1e-05,
+      "loss": 0.8241,
+      "step": 3
+    },
+    {
+      "epoch": 0.002739256976545112,
+      "grad_norm": 0.6175578236579895,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.8091,
+      "step": 4
+    },
+    {
+      "epoch": 0.00342407122068139,
+      "grad_norm": 0.5381224155426025,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.8509,
+      "step": 5
+    },
+    {
+      "epoch": 0.004108885464817668,
+      "grad_norm": 0.43509674072265625,
+      "learning_rate": 2e-05,
+      "loss": 0.8464,
+      "step": 6
+    },
+    {
+      "epoch": 0.004793699708953946,
+      "grad_norm": 0.46817463636398315,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.8308,
+      "step": 7
+    },
+    {
+      "epoch": 0.005478513953090224,
+      "grad_norm": 0.5534480214118958,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.8167,
+      "step": 8
+    },
+    {
+      "epoch": 0.0061633281972265025,
+      "grad_norm": 0.6555560231208801,
+      "learning_rate": 3e-05,
+      "loss": 0.8359,
+      "step": 9
+    },
+    {
+      "epoch": 0.00684814244136278,
+      "grad_norm": 0.6459038853645325,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.8239,
+      "step": 10
+    },
+    {
+      "epoch": 0.007532956685499058,
+      "grad_norm": 0.5058159828186035,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.8057,
+      "step": 11
+    },
+    {
+      "epoch": 0.008217770929635337,
+      "grad_norm": 0.44996047019958496,
+      "learning_rate": 4e-05,
+      "loss": 0.7935,
+      "step": 12
+    },
+    {
+      "epoch": 0.008902585173771614,
+      "grad_norm": 0.4448314607143402,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.822,
+      "step": 13
+    },
+    {
+      "epoch": 0.009587399417907892,
+      "grad_norm": 0.4350481629371643,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.7829,
+      "step": 14
+    },
+    {
+      "epoch": 0.01027221366204417,
+      "grad_norm": 0.4412112236022949,
+      "learning_rate": 5e-05,
+      "loss": 0.7729,
+      "step": 15
+    },
+    {
+      "epoch": 0.010957027906180448,
+      "grad_norm": 0.3981418013572693,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 0.7258,
+      "step": 16
+    },
+    {
+      "epoch": 0.011641842150316727,
+      "grad_norm": 0.423930823802948,
+      "learning_rate": 5.666666666666667e-05,
+      "loss": 0.7651,
+      "step": 17
+    },
+    {
+      "epoch": 0.012326656394453005,
+      "grad_norm": 0.39327582716941833,
+      "learning_rate": 6e-05,
+      "loss": 0.7602,
+      "step": 18
+    },
+    {
+      "epoch": 0.013011470638589283,
+      "grad_norm": 0.3741708993911743,
+      "learning_rate": 6.333333333333333e-05,
+      "loss": 0.7705,
+      "step": 19
+    },
+    {
+      "epoch": 0.01369628488272556,
+      "grad_norm": 0.35075634717941284,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.7469,
+      "step": 20
+    },
+    {
+      "epoch": 0.014381099126861838,
+      "grad_norm": 0.3413642346858978,
+      "learning_rate": 7e-05,
+      "loss": 0.7501,
+      "step": 21
+    },
+    {
+      "epoch": 0.015065913370998116,
+      "grad_norm": 0.3538333475589752,
+      "learning_rate": 7.333333333333333e-05,
+      "loss": 0.7498,
+      "step": 22
+    },
+    {
+      "epoch": 0.015750727615134394,
+      "grad_norm": 0.3420611619949341,
+      "learning_rate": 7.666666666666667e-05,
+      "loss": 0.7707,
+      "step": 23
+    },
+    {
+      "epoch": 0.016435541859270673,
+      "grad_norm": 0.3365805447101593,
+      "learning_rate": 8e-05,
+      "loss": 0.7313,
+      "step": 24
+    },
+    {
+      "epoch": 0.01712035610340695,
+      "grad_norm": 0.3557707369327545,
+      "learning_rate": 8.333333333333334e-05,
+      "loss": 0.7412,
+      "step": 25
+    },
+    {
+      "epoch": 0.01780517034754323,
+      "grad_norm": 0.375104695558548,
+      "learning_rate": 8.666666666666667e-05,
+      "loss": 0.7806,
+      "step": 26
+    },
+    {
+      "epoch": 0.01848998459167951,
+      "grad_norm": 0.4079211354255676,
+      "learning_rate": 9e-05,
+      "loss": 0.7965,
+      "step": 27
+    },
+    {
+      "epoch": 0.019174798835815784,
+      "grad_norm": 0.41560953855514526,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 0.7843,
+      "step": 28
+    },
+    {
+      "epoch": 0.019859613079952064,
+      "grad_norm": 0.44931986927986145,
+      "learning_rate": 9.666666666666667e-05,
+      "loss": 0.7613,
+      "step": 29
+    },
+    {
+      "epoch": 0.02054442732408834,
+      "grad_norm": 0.42477014660835266,
+      "learning_rate": 0.0001,
+      "loss": 0.7338,
+      "step": 30
+    },
+    {
+      "epoch": 0.02122924156822462,
+      "grad_norm": 0.46810734272003174,
+      "learning_rate": 9.999146252290264e-05,
+      "loss": 0.7776,
+      "step": 31
+    },
+    {
+      "epoch": 0.021914055812360896,
+      "grad_norm": 0.5340303778648376,
+      "learning_rate": 9.996585300715116e-05,
+      "loss": 0.7893,
+      "step": 32
+    },
+    {
+      "epoch": 0.022598870056497175,
+      "grad_norm": 0.7713002562522888,
+      "learning_rate": 9.99231801983717e-05,
+      "loss": 0.7581,
+      "step": 33
+    },
+    {
+      "epoch": 0.023283684300633455,
+      "grad_norm": 0.6131659150123596,
+      "learning_rate": 9.986345866928941e-05,
+      "loss": 0.8021,
+      "step": 34
+    },
+    {
+      "epoch": 0.02396849854476973,
+      "grad_norm": 0.7067255973815918,
+      "learning_rate": 9.978670881475172e-05,
+      "loss": 0.7525,
+      "step": 35
+    },
+    {
+      "epoch": 0.02465331278890601,
+      "grad_norm": 0.7187981605529785,
+      "learning_rate": 9.96929568447637e-05,
+      "loss": 0.746,
+      "step": 36
+    },
+    {
+      "epoch": 0.025338127033042286,
+      "grad_norm": 0.7613598704338074,
+      "learning_rate": 9.958223477553714e-05,
+      "loss": 0.7778,
+      "step": 37
+    },
+    {
+      "epoch": 0.026022941277178566,
+      "grad_norm": 0.9986086487770081,
+      "learning_rate": 9.94545804185573e-05,
+      "loss": 0.8478,
+      "step": 38
+    },
+    {
+      "epoch": 0.02670775552131484,
+      "grad_norm": 1.0249992609024048,
+      "learning_rate": 9.931003736767013e-05,
+      "loss": 0.7883,
+      "step": 39
+    },
+    {
+      "epoch": 0.02739256976545112,
+      "grad_norm": 0.9514560103416443,
+      "learning_rate": 9.91486549841951e-05,
+      "loss": 0.7931,
+      "step": 40
+    },
+    {
+      "epoch": 0.0280773840095874,
+      "grad_norm": 0.9286103248596191,
+      "learning_rate": 9.89704883800683e-05,
+      "loss": 0.7803,
+      "step": 41
+    },
+    {
+      "epoch": 0.028762198253723677,
+      "grad_norm": 1.1426321268081665,
+      "learning_rate": 9.877559839902184e-05,
+      "loss": 0.9289,
+      "step": 42
+    },
+    {
+      "epoch": 0.029447012497859956,
+      "grad_norm": 1.1170059442520142,
+      "learning_rate": 9.85640515958057e-05,
+      "loss": 0.9127,
+      "step": 43
+    },
+    {
+      "epoch": 0.030131826741996232,
+      "grad_norm": 1.0930737257003784,
+      "learning_rate": 9.833592021345937e-05,
+      "loss": 0.7247,
+      "step": 44
+    },
+    {
+      "epoch": 0.030816640986132512,
+      "grad_norm": 1.1028903722763062,
+      "learning_rate": 9.809128215864097e-05,
+      "loss": 0.8079,
+      "step": 45
+    },
+    {
+      "epoch": 0.03150145523026879,
+      "grad_norm": 1.1875572204589844,
+      "learning_rate": 9.783022097502204e-05,
+      "loss": 0.8533,
+      "step": 46
+    },
+    {
+      "epoch": 0.03218626947440507,
+      "grad_norm": 1.261732578277588,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.9092,
+      "step": 47
+    },
+    {
+      "epoch": 0.03287108371854135,
+      "grad_norm": 1.2062290906906128,
+      "learning_rate": 9.725919140804099e-05,
+      "loss": 1.0179,
+      "step": 48
+    },
+    {
+      "epoch": 0.033555897962677626,
+      "grad_norm": 1.4912124872207642,
+      "learning_rate": 9.694941803075283e-05,
+      "loss": 0.8457,
+      "step": 49
+    },
+    {
+      "epoch": 0.0342407122068139,
+      "grad_norm": 1.8033643960952759,
+      "learning_rate": 9.662361147021779e-05,
+      "loss": 1.0443,
+      "step": 50
+    },
+    {
+      "epoch": 0.0342407122068139,
+      "eval_loss": 0.8211315870285034,
+      "eval_runtime": 117.3005,
+      "eval_samples_per_second": 20.972,
+      "eval_steps_per_second": 10.486,
+      "step": 50
+    },
+    {
+      "epoch": 0.03492552645095018,
+      "grad_norm": 1.2030723094940186,
+      "learning_rate": 9.628188298907782e-05,
+      "loss": 0.7513,
+      "step": 51
+    },
+    {
+      "epoch": 0.03561034069508646,
+      "grad_norm": 0.8026916980743408,
+      "learning_rate": 9.592434928729616e-05,
+      "loss": 0.724,
+      "step": 52
+    },
+    {
+      "epoch": 0.03629515493922274,
+      "grad_norm": 0.5238835215568542,
+      "learning_rate": 9.555113246230442e-05,
+      "loss": 0.6913,
+      "step": 53
+    },
+    {
+      "epoch": 0.03697996918335902,
+      "grad_norm": 0.5493408441543579,
+      "learning_rate": 9.516235996730645e-05,
+      "loss": 0.6727,
+      "step": 54
+    },
+    {
+      "epoch": 0.03766478342749529,
+      "grad_norm": 0.5578727126121521,
+      "learning_rate": 9.475816456775313e-05,
+      "loss": 0.6934,
+      "step": 55
+    },
+    {
+      "epoch": 0.03834959767163157,
+      "grad_norm": 0.42513638734817505,
+      "learning_rate": 9.43386842960031e-05,
+      "loss": 0.6234,
+      "step": 56
+    },
+    {
+      "epoch": 0.03903441191576785,
+      "grad_norm": 0.4495171010494232,
+      "learning_rate": 9.39040624041849e-05,
+      "loss": 0.6712,
+      "step": 57
+    },
+    {
+      "epoch": 0.03971922615990413,
+      "grad_norm": 0.3554115295410156,
+      "learning_rate": 9.345444731527642e-05,
+      "loss": 0.648,
+      "step": 58
+    },
+    {
+      "epoch": 0.04040404040404041,
+      "grad_norm": 0.3226708471775055,
+      "learning_rate": 9.298999257241863e-05,
+      "loss": 0.6719,
+      "step": 59
+    },
+    {
+      "epoch": 0.04108885464817668,
+      "grad_norm": 0.3451197147369385,
+      "learning_rate": 9.251085678648072e-05,
+      "loss": 0.6415,
+      "step": 60
+    },
+    {
+      "epoch": 0.04177366889231296,
+      "grad_norm": 0.3728142976760864,
+      "learning_rate": 9.201720358189464e-05,
+      "loss": 0.6698,
+      "step": 61
+    },
+    {
+      "epoch": 0.04245848313644924,
+      "grad_norm": 0.3852943181991577,
+      "learning_rate": 9.150920154077754e-05,
+      "loss": 0.6267,
+      "step": 62
+    },
+    {
+      "epoch": 0.04314329738058552,
+      "grad_norm": 0.33286604285240173,
+      "learning_rate": 9.098702414536107e-05,
+      "loss": 0.6584,
+      "step": 63
+    },
+    {
+      "epoch": 0.04382811162472179,
+      "grad_norm": 0.3130628764629364,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.6385,
+      "step": 64
+    },
+    {
+      "epoch": 0.04451292586885807,
+      "grad_norm": 0.3013477325439453,
+      "learning_rate": 8.9900861364012e-05,
+      "loss": 0.6397,
+      "step": 65
+    },
+    {
+      "epoch": 0.04519774011299435,
+      "grad_norm": 0.2920675277709961,
+      "learning_rate": 8.933724690167417e-05,
+      "loss": 0.5948,
+      "step": 66
+    },
+    {
+      "epoch": 0.04588255435713063,
+      "grad_norm": 0.3020579516887665,
+      "learning_rate": 8.876019880555649e-05,
+      "loss": 0.6419,
+      "step": 67
+    },
+    {
+      "epoch": 0.04656736860126691,
+      "grad_norm": 0.303498774766922,
+      "learning_rate": 8.816991413705516e-05,
+      "loss": 0.6414,
+      "step": 68
+    },
+    {
+      "epoch": 0.04725218284540318,
+      "grad_norm": 0.3015012741088867,
+      "learning_rate": 8.756659447784368e-05,
+      "loss": 0.6232,
+      "step": 69
+    },
+    {
+      "epoch": 0.04793699708953946,
+      "grad_norm": 0.29156970977783203,
+      "learning_rate": 8.695044586103296e-05,
+      "loss": 0.6481,
+      "step": 70
+    },
+    {
+      "epoch": 0.04862181133367574,
+      "grad_norm": 0.2696687579154968,
+      "learning_rate": 8.632167870081121e-05,
+      "loss": 0.6453,
+      "step": 71
+    },
+    {
+      "epoch": 0.04930662557781202,
+      "grad_norm": 0.2634645998477936,
+      "learning_rate": 8.568050772058762e-05,
+      "loss": 0.6074,
+      "step": 72
+    },
+    {
+      "epoch": 0.0499914398219483,
+      "grad_norm": 0.290762335062027,
+      "learning_rate": 8.502715187966455e-05,
+      "loss": 0.6191,
+      "step": 73
+    },
+    {
+      "epoch": 0.05067625406608457,
+      "grad_norm": 0.29839473962783813,
+      "learning_rate": 8.436183429846313e-05,
+      "loss": 0.6309,
+      "step": 74
+    },
+    {
+      "epoch": 0.05136106831022085,
+      "grad_norm": 0.3168591558933258,
+      "learning_rate": 8.368478218232787e-05,
+      "loss": 0.6544,
+      "step": 75
+    },
+    {
+      "epoch": 0.05204588255435713,
+      "grad_norm": 0.34840133786201477,
+      "learning_rate": 8.299622674393614e-05,
+      "loss": 0.6575,
+      "step": 76
+    },
+    {
+      "epoch": 0.05273069679849341,
+      "grad_norm": 0.35292384028434753,
+      "learning_rate": 8.229640312433937e-05,
+      "loss": 0.6425,
+      "step": 77
+    },
+    {
+      "epoch": 0.05341551104262968,
+      "grad_norm": 0.37297260761260986,
+      "learning_rate": 8.158555031266254e-05,
+      "loss": 0.674,
+      "step": 78
+    },
+    {
+      "epoch": 0.05410032528676596,
+      "grad_norm": 0.4122272729873657,
+      "learning_rate": 8.086391106448965e-05,
+      "loss": 0.7044,
+      "step": 79
+    },
+    {
+      "epoch": 0.05478513953090224,
+      "grad_norm": 0.42822644114494324,
+      "learning_rate": 8.013173181896283e-05,
+      "loss": 0.6623,
+      "step": 80
+    },
+    {
+      "epoch": 0.05546995377503852,
+      "grad_norm": 0.43928802013397217,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.6484,
+      "step": 81
+    },
+    {
+      "epoch": 0.0561547680191748,
+      "grad_norm": 0.45708250999450684,
+      "learning_rate": 7.863675700402526e-05,
+      "loss": 0.7157,
+      "step": 82
+    },
+    {
+      "epoch": 0.056839582263311074,
+      "grad_norm": 0.5053125023841858,
+      "learning_rate": 7.787447196714427e-05,
+      "loss": 0.6421,
+      "step": 83
+    },
+    {
+      "epoch": 0.05752439650744735,
+      "grad_norm": 0.5746484398841858,
+      "learning_rate": 7.710266782362247e-05,
+      "loss": 0.7225,
+      "step": 84
+    },
+    {
+      "epoch": 0.05820921075158363,
+      "grad_norm": 0.5479620695114136,
+      "learning_rate": 7.63216081438678e-05,
+      "loss": 0.7049,
+      "step": 85
+    },
+    {
+      "epoch": 0.05889402499571991,
+      "grad_norm": 0.607607364654541,
+      "learning_rate": 7.553155965904535e-05,
+      "loss": 0.7244,
+      "step": 86
+    },
+    {
+      "epoch": 0.05957883923985619,
+      "grad_norm": 0.6662994027137756,
+      "learning_rate": 7.473279216998895e-05,
+      "loss": 0.6861,
+      "step": 87
+    },
+    {
+      "epoch": 0.060263653483992465,
+      "grad_norm": 0.6767815947532654,
+      "learning_rate": 7.392557845506432e-05,
+      "loss": 0.7821,
+      "step": 88
+    },
+    {
+      "epoch": 0.060948467728128744,
+      "grad_norm": 0.7391032576560974,
+      "learning_rate": 7.311019417701566e-05,
+      "loss": 0.6912,
+      "step": 89
+    },
+    {
+      "epoch": 0.061633281972265024,
+      "grad_norm": 0.7538084387779236,
+      "learning_rate": 7.228691778882693e-05,
+      "loss": 0.6911,
+      "step": 90
+    },
+    {
+      "epoch": 0.0623180962164013,
+      "grad_norm": 0.8423702716827393,
+      "learning_rate": 7.145603043863045e-05,
+      "loss": 0.7886,
+      "step": 91
+    },
+    {
+      "epoch": 0.06300291046053758,
+      "grad_norm": 0.8754274249076843,
+      "learning_rate": 7.061781587369519e-05,
+      "loss": 0.7549,
+      "step": 92
+    },
+    {
+      "epoch": 0.06368772470467386,
+      "grad_norm": 0.8859317898750305,
+      "learning_rate": 6.977256034352712e-05,
+      "loss": 0.8041,
+      "step": 93
+    },
+    {
+      "epoch": 0.06437253894881013,
+      "grad_norm": 1.012904167175293,
+      "learning_rate": 6.892055250211552e-05,
+      "loss": 0.6863,
+      "step": 94
+    },
+    {
+      "epoch": 0.06505735319294641,
+      "grad_norm": 1.002065896987915,
+      "learning_rate": 6.806208330935766e-05,
+      "loss": 0.8271,
+      "step": 95
+    },
+    {
+      "epoch": 0.0657421674370827,
+      "grad_norm": 1.0469260215759277,
+      "learning_rate": 6.719744593169641e-05,
+      "loss": 0.7772,
+      "step": 96
+    },
+    {
+      "epoch": 0.06642698168121897,
+      "grad_norm": 1.0503506660461426,
+      "learning_rate": 6.632693564200416e-05,
+      "loss": 0.764,
+      "step": 97
+    },
+    {
+      "epoch": 0.06711179592535525,
+      "grad_norm": 1.3012419939041138,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.893,
+      "step": 98
+    },
+    {
+      "epoch": 0.06779661016949153,
+      "grad_norm": 1.3924188613891602,
+      "learning_rate": 6.456948734446624e-05,
+      "loss": 0.8318,
+      "step": 99
+    },
+    {
+      "epoch": 0.0684814244136278,
+      "grad_norm": 2.090738534927368,
+      "learning_rate": 6.368314950360415e-05,
+      "loss": 1.0165,
+      "step": 100
+    },
+    {
+      "epoch": 0.0684814244136278,
+      "eval_loss": 0.7142184972763062,
+      "eval_runtime": 117.0956,
+      "eval_samples_per_second": 21.008,
+      "eval_steps_per_second": 10.504,
+      "step": 100
+    },
+    {
+      "epoch": 0.06916623865776408,
+      "grad_norm": 0.7509860992431641,
+      "learning_rate": 6.279213887972179e-05,
+      "loss": 0.6405,
+      "step": 101
+    },
+    {
+      "epoch": 0.06985105290190036,
+      "grad_norm": 0.6990787386894226,
+      "learning_rate": 6.189675975213094e-05,
+      "loss": 0.6622,
+      "step": 102
+    },
+    {
+      "epoch": 0.07053586714603664,
+      "grad_norm": 0.5219253301620483,
+      "learning_rate": 6.099731789198344e-05,
+      "loss": 0.6378,
+      "step": 103
+    },
+    {
+      "epoch": 0.07122068139017292,
+      "grad_norm": 0.41139304637908936,
+      "learning_rate": 6.009412045785051e-05,
+      "loss": 0.5977,
+      "step": 104
+    },
+    {
+      "epoch": 0.07190549563430919,
+      "grad_norm": 0.40187910199165344,
+      "learning_rate": 5.918747589082853e-05,
+      "loss": 0.5966,
+      "step": 105
+    },
+    {
+      "epoch": 0.07259030987844547,
+      "grad_norm": 0.4513488709926605,
+      "learning_rate": 5.82776938092065e-05,
+      "loss": 0.6506,
+      "step": 106
+    },
+    {
+      "epoch": 0.07327512412258175,
+      "grad_norm": 0.45315641164779663,
+      "learning_rate": 5.736508490273188e-05,
+      "loss": 0.6162,
+      "step": 107
+    },
+    {
+      "epoch": 0.07395993836671803,
+      "grad_norm": 0.4146612584590912,
+      "learning_rate": 5.644996082651017e-05,
+      "loss": 0.5844,
+      "step": 108
+    },
+    {
+      "epoch": 0.0746447526108543,
+      "grad_norm": 0.4321027994155884,
+      "learning_rate": 5.553263409457504e-05,
+      "loss": 0.593,
+      "step": 109
+    },
+    {
+      "epoch": 0.07532956685499058,
+      "grad_norm": 0.3078586757183075,
+      "learning_rate": 5.4613417973165106e-05,
+      "loss": 0.5522,
+      "step": 110
+    },
+    {
+      "epoch": 0.07601438109912687,
+      "grad_norm": 0.31009235978126526,
+      "learning_rate": 5.3692626373743706e-05,
+      "loss": 0.5662,
+      "step": 111
+    },
+    {
+      "epoch": 0.07669919534326314,
+      "grad_norm": 0.312005877494812,
+      "learning_rate": 5.27705737457985e-05,
+      "loss": 0.5994,
+      "step": 112
+    },
+    {
+      "epoch": 0.07738400958739942,
+      "grad_norm": 0.3025156259536743,
+      "learning_rate": 5.184757496945726e-05,
+      "loss": 0.5671,
+      "step": 113
+    },
+    {
+      "epoch": 0.0780688238315357,
+      "grad_norm": 0.3122718930244446,
+      "learning_rate": 5.092394524795649e-05,
+      "loss": 0.5588,
+      "step": 114
+    },
+    {
+      "epoch": 0.07875363807567197,
+      "grad_norm": 0.32042813301086426,
+      "learning_rate": 5e-05,
+      "loss": 0.6073,
+      "step": 115
+    },
+    {
+      "epoch": 0.07943845231980826,
+      "grad_norm": 0.32439666986465454,
+      "learning_rate": 4.907605475204352e-05,
+      "loss": 0.5978,
+      "step": 116
+    },
+    {
+      "epoch": 0.08012326656394453,
+      "grad_norm": 0.32204368710517883,
+      "learning_rate": 4.8152425030542766e-05,
+      "loss": 0.6123,
+      "step": 117
+    },
+    {
+      "epoch": 0.08080808080808081,
+      "grad_norm": 0.30760934948921204,
+      "learning_rate": 4.72294262542015e-05,
+      "loss": 0.5961,
+      "step": 118
+    },
+    {
+      "epoch": 0.08149289505221709,
+      "grad_norm": 0.26987290382385254,
+      "learning_rate": 4.6307373626256306e-05,
+      "loss": 0.6017,
+      "step": 119
+    },
+    {
+      "epoch": 0.08217770929635336,
+      "grad_norm": 0.28270965814590454,
+      "learning_rate": 4.5386582026834906e-05,
+      "loss": 0.5784,
+      "step": 120
+    },
+    {
+      "epoch": 0.08286252354048965,
+      "grad_norm": 0.29432162642478943,
+      "learning_rate": 4.446736590542497e-05,
+      "loss": 0.6241,
+      "step": 121
+    },
+    {
+      "epoch": 0.08354733778462592,
+      "grad_norm": 0.28419461846351624,
+      "learning_rate": 4.3550039173489845e-05,
+      "loss": 0.614,
+      "step": 122
+    },
+    {
+      "epoch": 0.08423215202876219,
+      "grad_norm": 0.29656660556793213,
+      "learning_rate": 4.2634915097268115e-05,
+      "loss": 0.6272,
+      "step": 123
+    },
+    {
+      "epoch": 0.08491696627289848,
+      "grad_norm": 0.27999988198280334,
+      "learning_rate": 4.1722306190793495e-05,
+      "loss": 0.5919,
+      "step": 124
+    },
+    {
+      "epoch": 0.08560178051703475,
+      "grad_norm": 0.27216336131095886,
+      "learning_rate": 4.0812524109171476e-05,
+      "loss": 0.5959,
+      "step": 125
+    },
+    {
+      "epoch": 0.08628659476117104,
+      "grad_norm": 0.2954910695552826,
+      "learning_rate": 3.99058795421495e-05,
+      "loss": 0.5614,
+      "step": 126
+    },
+    {
+      "epoch": 0.08697140900530731,
+      "grad_norm": 0.3302258849143982,
+      "learning_rate": 3.9002682108016585e-05,
+      "loss": 0.6026,
+      "step": 127
+    },
+    {
+      "epoch": 0.08765622324944358,
+      "grad_norm": 0.31505435705184937,
+      "learning_rate": 3.8103240247869075e-05,
+      "loss": 0.6043,
+      "step": 128
+    },
+    {
+      "epoch": 0.08834103749357987,
+      "grad_norm": 0.3390796482563019,
+      "learning_rate": 3.720786112027822e-05,
+      "loss": 0.6178,
+      "step": 129
+    },
+    {
+      "epoch": 0.08902585173771614,
+      "grad_norm": 0.35363104939460754,
+      "learning_rate": 3.631685049639586e-05,
+      "loss": 0.6161,
+      "step": 130
+    },
+    {
+      "epoch": 0.08971066598185243,
+      "grad_norm": 0.362228661775589,
+      "learning_rate": 3.543051265553377e-05,
+      "loss": 0.5965,
+      "step": 131
+    },
+    {
+      "epoch": 0.0903954802259887,
+      "grad_norm": 0.4063306748867035,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.6248,
+      "step": 132
+    },
+    {
+      "epoch": 0.09108029447012497,
+      "grad_norm": 0.43474704027175903,
+      "learning_rate": 3.367306435799584e-05,
+      "loss": 0.6363,
+      "step": 133
+    },
+    {
+      "epoch": 0.09176510871426126,
+      "grad_norm": 0.46244192123413086,
+      "learning_rate": 3.2802554068303596e-05,
+      "loss": 0.6384,
+      "step": 134
+    },
+    {
+      "epoch": 0.09244992295839753,
+      "grad_norm": 0.472964882850647,
+      "learning_rate": 3.1937916690642356e-05,
+      "loss": 0.604,
+      "step": 135
+    },
+    {
+      "epoch": 0.09313473720253382,
+      "grad_norm": 0.5363974571228027,
+      "learning_rate": 3.107944749788449e-05,
+      "loss": 0.6924,
+      "step": 136
+    },
+    {
+      "epoch": 0.09381955144667009,
+      "grad_norm": 0.568355917930603,
+      "learning_rate": 3.0227439656472877e-05,
+      "loss": 0.6067,
+      "step": 137
+    },
+    {
+      "epoch": 0.09450436569080636,
+      "grad_norm": 0.6210429072380066,
+      "learning_rate": 2.9382184126304834e-05,
+      "loss": 0.6454,
+      "step": 138
+    },
+    {
+      "epoch": 0.09518917993494265,
+      "grad_norm": 0.6779321432113647,
+      "learning_rate": 2.8543969561369556e-05,
+      "loss": 0.6802,
+      "step": 139
+    },
+    {
+      "epoch": 0.09587399417907892,
+      "grad_norm": 0.6606670618057251,
+      "learning_rate": 2.771308221117309e-05,
+      "loss": 0.6787,
+      "step": 140
+    },
+    {
+      "epoch": 0.09655880842321521,
+      "grad_norm": 0.7507839798927307,
+      "learning_rate": 2.688980582298435e-05,
+      "loss": 0.7191,
+      "step": 141
+    },
+    {
+      "epoch": 0.09724362266735148,
+      "grad_norm": 0.7643622159957886,
+      "learning_rate": 2.607442154493568e-05,
+      "loss": 0.7187,
+      "step": 142
+    },
+    {
+      "epoch": 0.09792843691148775,
+      "grad_norm": 0.8402984738349915,
+      "learning_rate": 2.5267207830011068e-05,
+      "loss": 0.7484,
+      "step": 143
+    },
+    {
+      "epoch": 0.09861325115562404,
+      "grad_norm": 0.9446684122085571,
+      "learning_rate": 2.446844034095466e-05,
+      "loss": 0.7155,
+      "step": 144
+    },
+    {
+      "epoch": 0.09929806539976031,
+      "grad_norm": 0.9034938216209412,
+      "learning_rate": 2.3678391856132204e-05,
+      "loss": 0.7414,
+      "step": 145
+    },
+    {
+      "epoch": 0.0999828796438966,
+      "grad_norm": 0.97967129945755,
+      "learning_rate": 2.2897332176377528e-05,
+      "loss": 0.6887,
+      "step": 146
+    },
+    {
+      "epoch": 0.10066769388803287,
+      "grad_norm": 1.0265204906463623,
+      "learning_rate": 2.2125528032855724e-05,
+      "loss": 0.8018,
+      "step": 147
+    },
+    {
+      "epoch": 0.10135250813216914,
+      "grad_norm": 1.198464274406433,
+      "learning_rate": 2.136324299597474e-05,
+      "loss": 0.7592,
+      "step": 148
+    },
+    {
+      "epoch": 0.10203732237630543,
+      "grad_norm": 1.3654637336730957,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.7852,
+      "step": 149
+    },
+    {
+      "epoch": 0.1027221366204417,
+      "grad_norm": 1.3087347745895386,
+      "learning_rate": 1.9868268181037185e-05,
+      "loss": 0.7148,
+      "step": 150
+    },
+    {
+      "epoch": 0.1027221366204417,
+      "eval_loss": 0.6377694606781006,
+      "eval_runtime": 117.1924,
+      "eval_samples_per_second": 20.991,
+      "eval_steps_per_second": 10.496,
+      "step": 150
+    },
+    {
+      "epoch": 0.10340695086457799,
+      "grad_norm": 0.4432825446128845,
+      "learning_rate": 1.9136088935510362e-05,
+      "loss": 0.5578,
+      "step": 151
+    },
+    {
+      "epoch": 0.10409176510871426,
+      "grad_norm": 0.479250967502594,
+      "learning_rate": 1.8414449687337464e-05,
+      "loss": 0.5887,
+      "step": 152
+    },
+    {
+      "epoch": 0.10477657935285054,
+      "grad_norm": 0.41809138655662537,
+      "learning_rate": 1.7703596875660645e-05,
+      "loss": 0.5416,
+      "step": 153
+    },
+    {
+      "epoch": 0.10546139359698682,
+      "grad_norm": 0.42553573846817017,
+      "learning_rate": 1.700377325606388e-05,
+      "loss": 0.597,
+      "step": 154
+    },
+    {
+      "epoch": 0.1061462078411231,
+      "grad_norm": 0.41053974628448486,
+      "learning_rate": 1.631521781767214e-05,
+      "loss": 0.5834,
+      "step": 155
+    },
+    {
+      "epoch": 0.10683102208525937,
+      "grad_norm": 0.37955138087272644,
+      "learning_rate": 1.5638165701536868e-05,
+      "loss": 0.5659,
+      "step": 156
+    },
+    {
+      "epoch": 0.10751583632939565,
+      "grad_norm": 0.3913707733154297,
+      "learning_rate": 1.4972848120335453e-05,
+      "loss": 0.5632,
+      "step": 157
+    },
+    {
+      "epoch": 0.10820065057353193,
+      "grad_norm": 0.35020458698272705,
+      "learning_rate": 1.4319492279412388e-05,
+      "loss": 0.5543,
+      "step": 158
+    },
+    {
+      "epoch": 0.10888546481766821,
+      "grad_norm": 0.3410779535770416,
+      "learning_rate": 1.3678321299188801e-05,
+      "loss": 0.5502,
+      "step": 159
+    },
+    {
+      "epoch": 0.10957027906180448,
+      "grad_norm": 0.34443268179893494,
+      "learning_rate": 1.3049554138967051e-05,
+      "loss": 0.5799,
+      "step": 160
+    },
+    {
+      "epoch": 0.11025509330594076,
+      "grad_norm": 0.3187792897224426,
+      "learning_rate": 1.2433405522156332e-05,
+      "loss": 0.5514,
+      "step": 161
+    },
+    {
+      "epoch": 0.11093990755007704,
+      "grad_norm": 0.3165248930454254,
+      "learning_rate": 1.183008586294485e-05,
+      "loss": 0.5609,
+      "step": 162
+    },
+    {
+      "epoch": 0.11162472179421332,
+      "grad_norm": 0.29232487082481384,
+      "learning_rate": 1.1239801194443506e-05,
+      "loss": 0.5466,
+      "step": 163
+    },
+    {
+      "epoch": 0.1123095360383496,
+      "grad_norm": 0.31247469782829285,
+      "learning_rate": 1.066275309832584e-05,
+      "loss": 0.5624,
+      "step": 164
+    },
+    {
+      "epoch": 0.11299435028248588,
+      "grad_norm": 0.30942830443382263,
+      "learning_rate": 1.0099138635988026e-05,
+      "loss": 0.5738,
+      "step": 165
+    },
+    {
+      "epoch": 0.11367916452662215,
+      "grad_norm": 0.30501317977905273,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.5498,
+      "step": 166
+    },
+    {
+      "epoch": 0.11436397877075843,
+      "grad_norm": 0.3122025728225708,
+      "learning_rate": 9.012975854638949e-06,
+      "loss": 0.5811,
+      "step": 167
+    },
+    {
+      "epoch": 0.1150487930148947,
+      "grad_norm": 0.3021736145019531,
+      "learning_rate": 8.490798459222476e-06,
+      "loss": 0.6069,
+      "step": 168
+    },
+    {
+      "epoch": 0.115733607259031,
+      "grad_norm": 0.27660757303237915,
+      "learning_rate": 7.982796418105371e-06,
+      "loss": 0.5365,
+      "step": 169
+    },
+    {
+      "epoch": 0.11641842150316727,
+      "grad_norm": 0.29351627826690674,
+      "learning_rate": 7.489143213519301e-06,
+      "loss": 0.5798,
+      "step": 170
+    },
+    {
+      "epoch": 0.11710323574730354,
+      "grad_norm": 0.27547141909599304,
+      "learning_rate": 7.010007427581378e-06,
+      "loss": 0.561,
+      "step": 171
+    },
+    {
+      "epoch": 0.11778804999143982,
+      "grad_norm": 0.2924772799015045,
+      "learning_rate": 6.5455526847235825e-06,
+      "loss": 0.5438,
+      "step": 172
+    },
+    {
+      "epoch": 0.1184728642355761,
+      "grad_norm": 0.29513823986053467,
+      "learning_rate": 6.0959375958151045e-06,
+      "loss": 0.5882,
+      "step": 173
+    },
+    {
+      "epoch": 0.11915767847971238,
+      "grad_norm": 0.2879987359046936,
+      "learning_rate": 5.6613157039969055e-06,
+      "loss": 0.5767,
+      "step": 174
+    },
+    {
+      "epoch": 0.11984249272384866,
+      "grad_norm": 0.30210405588150024,
+      "learning_rate": 5.241835432246889e-06,
+      "loss": 0.6167,
+      "step": 175
+    },
+    {
+      "epoch": 0.12052730696798493,
+      "grad_norm": 0.3155370056629181,
+      "learning_rate": 4.837640032693558e-06,
+      "loss": 0.5849,
+      "step": 176
+    },
+    {
+      "epoch": 0.12121212121212122,
+      "grad_norm": 0.32978156208992004,
+      "learning_rate": 4.448867537695578e-06,
+      "loss": 0.6192,
+      "step": 177
+    },
+    {
+      "epoch": 0.12189693545625749,
+      "grad_norm": 0.3881371319293976,
+      "learning_rate": 4.075650712703849e-06,
+      "loss": 0.5813,
+      "step": 178
+    },
+    {
+      "epoch": 0.12258174970039377,
+      "grad_norm": 0.3963642120361328,
+      "learning_rate": 3.71811701092219e-06,
+      "loss": 0.6088,
+      "step": 179
+    },
+    {
+      "epoch": 0.12326656394453005,
+      "grad_norm": 0.3978794515132904,
+      "learning_rate": 3.376388529782215e-06,
+      "loss": 0.6061,
+      "step": 180
+    },
+    {
+      "epoch": 0.12395137818866632,
+      "grad_norm": 0.43060538172721863,
+      "learning_rate": 3.0505819692471792e-06,
+      "loss": 0.5915,
+      "step": 181
+    },
+    {
+      "epoch": 0.1246361924328026,
+      "grad_norm": 0.4637625217437744,
+      "learning_rate": 2.7408085919590264e-06,
+      "loss": 0.6218,
+      "step": 182
+    },
+    {
+      "epoch": 0.12532100667693888,
+      "grad_norm": 0.4725170135498047,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.5826,
+      "step": 183
+    },
+    {
+      "epoch": 0.12600582092107515,
+      "grad_norm": 0.532699704170227,
+      "learning_rate": 2.1697790249779636e-06,
+      "loss": 0.6331,
+      "step": 184
+    },
+    {
+      "epoch": 0.12669063516521142,
+      "grad_norm": 0.6026003360748291,
+      "learning_rate": 1.908717841359048e-06,
+      "loss": 0.6512,
+      "step": 185
+    },
+    {
+      "epoch": 0.12737544940934772,
+      "grad_norm": 0.6390156745910645,
+      "learning_rate": 1.6640797865406288e-06,
+      "loss": 0.6593,
+      "step": 186
+    },
+    {
+      "epoch": 0.128060263653484,
+      "grad_norm": 0.6509230732917786,
+      "learning_rate": 1.4359484041943038e-06,
+      "loss": 0.6658,
+      "step": 187
+    },
+    {
+      "epoch": 0.12874507789762027,
+      "grad_norm": 0.7189095616340637,
+      "learning_rate": 1.2244016009781701e-06,
+      "loss": 0.6296,
+      "step": 188
+    },
+    {
+      "epoch": 0.12942989214175654,
+      "grad_norm": 0.7797378897666931,
+      "learning_rate": 1.0295116199317057e-06,
+      "loss": 0.6571,
+      "step": 189
+    },
+    {
+      "epoch": 0.13011470638589281,
+      "grad_norm": 0.7035871744155884,
+      "learning_rate": 8.513450158049108e-07,
+      "loss": 0.5857,
+      "step": 190
+    },
+    {
+      "epoch": 0.13079952063002911,
+      "grad_norm": 0.7862012982368469,
+      "learning_rate": 6.899626323298713e-07,
+      "loss": 0.6599,
+      "step": 191
+    },
+    {
+      "epoch": 0.1314843348741654,
+      "grad_norm": 0.8630943894386292,
+      "learning_rate": 5.454195814427021e-07,
+      "loss": 0.7652,
+      "step": 192
+    },
+    {
+      "epoch": 0.13216914911830166,
+      "grad_norm": 0.8961440920829773,
+      "learning_rate": 4.177652244628627e-07,
+      "loss": 0.5976,
+      "step": 193
+    },
+    {
+      "epoch": 0.13285396336243793,
+      "grad_norm": 0.8933964967727661,
+      "learning_rate": 3.0704315523631953e-07,
+      "loss": 0.6846,
+      "step": 194
+    },
+    {
+      "epoch": 0.1335387776065742,
+      "grad_norm": 0.9491346478462219,
+      "learning_rate": 2.1329118524827662e-07,
+      "loss": 0.7293,
+      "step": 195
+    },
+    {
+      "epoch": 0.1342235918507105,
+      "grad_norm": 1.0365053415298462,
+      "learning_rate": 1.3654133071059893e-07,
+      "loss": 0.7464,
+      "step": 196
+    },
+    {
+      "epoch": 0.13490840609484678,
+      "grad_norm": 1.1153377294540405,
+      "learning_rate": 7.681980162830282e-08,
+      "loss": 0.699,
+      "step": 197
+    },
+    {
+      "epoch": 0.13559322033898305,
+      "grad_norm": 1.0952070951461792,
+      "learning_rate": 3.4146992848854695e-08,
+      "loss": 0.7628,
+      "step": 198
+    },
+    {
+      "epoch": 0.13627803458311932,
+      "grad_norm": 1.4037970304489136,
+      "learning_rate": 8.537477097364522e-09,
+      "loss": 0.899,
+      "step": 199
+    },
+    {
+      "epoch": 0.1369628488272556,
+      "grad_norm": 1.8042813539505005,
+      "learning_rate": 0.0,
+      "loss": 0.8487,
+      "step": 200
+    },
+    {
+      "epoch": 0.1369628488272556,
+      "eval_loss": 0.6194487810134888,
+      "eval_runtime": 117.4375,
+      "eval_samples_per_second": 20.947,
+      "eval_steps_per_second": 10.474,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.13032382922752e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7229b6343678286cae26888960c5fe04a2571b9e93fffbdb8903e38d0f3212d
+size 6840

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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
+    }
+  },
+  "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 not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7229b6343678286cae26888960c5fe04a2571b9e93fffbdb8903e38d0f3212d
+size 6840