End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,160 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: Qwen/Qwen2.5-1.5B
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 59c2eda2-c88e-47d1-ad10-99cf5c7714cd
+  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
+bf16: true
+chat_template: llama3
+datasets:
+- data_files:
+  - f96a5129ff7fb986_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/f96a5129ff7fb986_train_data.json
+  type:
+    field_instruction: task_name
+    field_output: meta_info
+    format: '{instruction}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+early_stopping_patience: null
+eval_max_new_tokens: 128
+eval_table_size: null
+evals_per_epoch: 4
+flash_attention: false
+fp16: false
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 2
+gradient_checkpointing: true
+group_by_length: false
+hub_model_id: sn56/59c2eda2-c88e-47d1-ad10-99cf5c7714cd
+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: 32
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 16
+lora_target_linear: true
+lr_scheduler: cosine
+max_memory:
+  0: 77GiB
+max_steps: 50
+micro_batch_size: 8
+mlflow_experiment_name: /tmp/f96a5129ff7fb986_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 3
+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: 25
+save_strategy: steps
+sequence_len: 1024
+strict: false
+tf32: false
+tokenizer_type: AutoTokenizer
+train_on_inputs: true
+trust_remote_code: true
+val_set_size: 0.05
+wandb_entity: sn56-miner
+wandb_mode: disabled
+wandb_name: 59c2eda2-c88e-47d1-ad10-99cf5c7714cd
+wandb_project: god
+wandb_run: srkv
+wandb_runid: 59c2eda2-c88e-47d1-ad10-99cf5c7714cd
+warmup_steps: 10
+weight_decay: 0.01
+xformers_attention: false
+
+```
+
+</details><br>
+
+# 59c2eda2-c88e-47d1-ad10-99cf5c7714cd
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7098
+
+## 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: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- training_steps: 50
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 2.5398        | 0.0084 | 1    | 2.5376          |
+| 2.1979        | 0.0420 | 5    | 2.5045          |
+| 1.6824        | 0.0840 | 10   | 2.2800          |
+| 1.972         | 0.1261 | 15   | 2.0205          |
+| 1.481         | 0.1681 | 20   | 1.8793          |
+| 1.7239        | 0.2101 | 25   | 1.7845          |
+| 1.7557        | 0.2521 | 30   | 1.7457          |
+| 1.3495        | 0.2941 | 35   | 1.7243          |
+| 1.4501        | 0.3361 | 40   | 1.7142          |
+| 1.4294        | 0.3782 | 45   | 1.7095          |
+| 1.6555        | 0.4202 | 50   | 1.7098          |
+
+
+### 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",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "k_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:ef80058e1636e9c78680b4ed8ac5f8c91bdc3cb39320b07a92b67127a0224e4f
+size 74000170

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b8c5dec1c7af13d1574ede95c5131058cf479214bc9377bf2a99ce010585ed9
+size 73911112

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 +1,30 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "Qwen/Qwen2.5-1.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "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_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-1.5B
+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",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "k_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 sha256:0b8c5dec1c7af13d1574ede95c5131058cf479214bc9377bf2a99ce010585ed9
+size 73911112

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 sha256:2490b57f1d564a25333116d9da5ec61aa5633a93eaf85b2171eb5b792eed349a
+size 148047722

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa4ca207c46b0d33b1cf177b91c7ffe6fe9e46ac795285514db389e980780824
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
+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": "<|endoftext|>",
+    "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": "<|endoftext|>",
+  "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 +1,471 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.42016806722689076,
+  "eval_steps": 5,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008403361344537815,
+      "grad_norm": 0.9718410968780518,
+      "learning_rate": 1e-05,
+      "loss": 2.5398,
+      "step": 1
+    },
+    {
+      "epoch": 0.008403361344537815,
+      "eval_loss": 2.5376181602478027,
+      "eval_runtime": 4.7323,
+      "eval_samples_per_second": 21.131,
+      "eval_steps_per_second": 2.747,
+      "step": 1
+    },
+    {
+      "epoch": 0.01680672268907563,
+      "grad_norm": 1.2425260543823242,
+      "learning_rate": 2e-05,
+      "loss": 3.1017,
+      "step": 2
+    },
+    {
+      "epoch": 0.025210084033613446,
+      "grad_norm": 0.9760674238204956,
+      "learning_rate": 3e-05,
+      "loss": 2.6444,
+      "step": 3
+    },
+    {
+      "epoch": 0.03361344537815126,
+      "grad_norm": 0.9310340285301208,
+      "learning_rate": 4e-05,
+      "loss": 2.5076,
+      "step": 4
+    },
+    {
+      "epoch": 0.04201680672268908,
+      "grad_norm": 0.8421019315719604,
+      "learning_rate": 5e-05,
+      "loss": 2.1979,
+      "step": 5
+    },
+    {
+      "epoch": 0.04201680672268908,
+      "eval_loss": 2.5044827461242676,
+      "eval_runtime": 3.9594,
+      "eval_samples_per_second": 25.256,
+      "eval_steps_per_second": 3.283,
+      "step": 5
+    },
+    {
+      "epoch": 0.05042016806722689,
+      "grad_norm": 0.7519902586936951,
+      "learning_rate": 6e-05,
+      "loss": 2.2747,
+      "step": 6
+    },
+    {
+      "epoch": 0.058823529411764705,
+      "grad_norm": 0.6263223886489868,
+      "learning_rate": 7e-05,
+      "loss": 1.7218,
+      "step": 7
+    },
+    {
+      "epoch": 0.06722689075630252,
+      "grad_norm": 1.0422320365905762,
+      "learning_rate": 8e-05,
+      "loss": 2.2464,
+      "step": 8
+    },
+    {
+      "epoch": 0.07563025210084033,
+      "grad_norm": 1.0980831384658813,
+      "learning_rate": 9e-05,
+      "loss": 2.2116,
+      "step": 9
+    },
+    {
+      "epoch": 0.08403361344537816,
+      "grad_norm": 0.6562592387199402,
+      "learning_rate": 0.0001,
+      "loss": 1.6824,
+      "step": 10
+    },
+    {
+      "epoch": 0.08403361344537816,
+      "eval_loss": 2.2799768447875977,
+      "eval_runtime": 3.9601,
+      "eval_samples_per_second": 25.252,
+      "eval_steps_per_second": 3.283,
+      "step": 10
+    },
+    {
+      "epoch": 0.09243697478991597,
+      "grad_norm": 1.1841509342193604,
+      "learning_rate": 9.98458666866564e-05,
+      "loss": 2.2025,
+      "step": 11
+    },
+    {
+      "epoch": 0.10084033613445378,
+      "grad_norm": 1.2198749780654907,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 2.2509,
+      "step": 12
+    },
+    {
+      "epoch": 0.1092436974789916,
+      "grad_norm": 0.6274753212928772,
+      "learning_rate": 9.861849601988383e-05,
+      "loss": 1.6681,
+      "step": 13
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 0.727944552898407,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 1.6158,
+      "step": 14
+    },
+    {
+      "epoch": 0.12605042016806722,
+      "grad_norm": 0.7959132194519043,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.972,
+      "step": 15
+    },
+    {
+      "epoch": 0.12605042016806722,
+      "eval_loss": 2.0204756259918213,
+      "eval_runtime": 3.9575,
+      "eval_samples_per_second": 25.268,
+      "eval_steps_per_second": 3.285,
+      "step": 15
+    },
+    {
+      "epoch": 0.13445378151260504,
+      "grad_norm": 0.7673566937446594,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 1.6918,
+      "step": 16
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.5823358297348022,
+      "learning_rate": 9.263200821770461e-05,
+      "loss": 1.6083,
+      "step": 17
+    },
+    {
+      "epoch": 0.15126050420168066,
+      "grad_norm": 1.1220409870147705,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.2063,
+      "step": 18
+    },
+    {
+      "epoch": 0.15966386554621848,
+      "grad_norm": 0.7490441799163818,
+      "learning_rate": 8.802029828000156e-05,
+      "loss": 1.7555,
+      "step": 19
+    },
+    {
+      "epoch": 0.16806722689075632,
+      "grad_norm": 0.7441122531890869,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.481,
+      "step": 20
+    },
+    {
+      "epoch": 0.16806722689075632,
+      "eval_loss": 1.8792790174484253,
+      "eval_runtime": 3.9583,
+      "eval_samples_per_second": 25.263,
+      "eval_steps_per_second": 3.284,
+      "step": 20
+    },
+    {
+      "epoch": 0.17647058823529413,
+      "grad_norm": 0.7857601642608643,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 1.6773,
+      "step": 21
+    },
+    {
+      "epoch": 0.18487394957983194,
+      "grad_norm": 0.6967548727989197,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.5601,
+      "step": 22
+    },
+    {
+      "epoch": 0.19327731092436976,
+      "grad_norm": 0.840194582939148,
+      "learning_rate": 7.612492823579745e-05,
+      "loss": 1.5747,
+      "step": 23
+    },
+    {
+      "epoch": 0.20168067226890757,
+      "grad_norm": 1.0659984350204468,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 1.8827,
+      "step": 24
+    },
+    {
+      "epoch": 0.21008403361344538,
+      "grad_norm": 0.9314756989479065,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.7239,
+      "step": 25
+    },
+    {
+      "epoch": 0.21008403361344538,
+      "eval_loss": 1.7845157384872437,
+      "eval_runtime": 3.9589,
+      "eval_samples_per_second": 25.26,
+      "eval_steps_per_second": 3.284,
+      "step": 25
+    },
+    {
+      "epoch": 0.2184873949579832,
+      "grad_norm": 0.6591042280197144,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.477,
+      "step": 26
+    },
+    {
+      "epoch": 0.226890756302521,
+      "grad_norm": 0.6459179520606995,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 1.7481,
+      "step": 27
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 0.5227776169776917,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 1.4044,
+      "step": 28
+    },
+    {
+      "epoch": 0.24369747899159663,
+      "grad_norm": 0.5983021855354309,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 1.7172,
+      "step": 29
+    },
+    {
+      "epoch": 0.25210084033613445,
+      "grad_norm": 0.7925629615783691,
+      "learning_rate": 5e-05,
+      "loss": 1.7557,
+      "step": 30
+    },
+    {
+      "epoch": 0.25210084033613445,
+      "eval_loss": 1.7456642389297485,
+      "eval_runtime": 3.9705,
+      "eval_samples_per_second": 25.186,
+      "eval_steps_per_second": 3.274,
+      "step": 30
+    },
+    {
+      "epoch": 0.2605042016806723,
+      "grad_norm": 0.48578646779060364,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 1.4043,
+      "step": 31
+    },
+    {
+      "epoch": 0.2689075630252101,
+      "grad_norm": 0.44603151082992554,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.2389,
+      "step": 32
+    },
+    {
+      "epoch": 0.2773109243697479,
+      "grad_norm": 0.5053887963294983,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 1.4407,
+      "step": 33
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.6158613562583923,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.6911,
+      "step": 34
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 0.4589507281780243,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.3495,
+      "step": 35
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "eval_loss": 1.7243127822875977,
+      "eval_runtime": 3.9587,
+      "eval_samples_per_second": 25.261,
+      "eval_steps_per_second": 3.284,
+      "step": 35
+    },
+    {
+      "epoch": 0.3025210084033613,
+      "grad_norm": 0.5226029753684998,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 1.6909,
+      "step": 36
+    },
+    {
+      "epoch": 0.31092436974789917,
+      "grad_norm": 0.7531144022941589,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 1.7232,
+      "step": 37
+    },
+    {
+      "epoch": 0.31932773109243695,
+      "grad_norm": 0.5438137054443359,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.4005,
+      "step": 38
+    },
+    {
+      "epoch": 0.3277310924369748,
+      "grad_norm": 0.6636350750923157,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 1.7133,
+      "step": 39
+    },
+    {
+      "epoch": 0.33613445378151263,
+      "grad_norm": 0.4282049536705017,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.4501,
+      "step": 40
+    },
+    {
+      "epoch": 0.33613445378151263,
+      "eval_loss": 1.7142012119293213,
+      "eval_runtime": 3.9507,
+      "eval_samples_per_second": 25.312,
+      "eval_steps_per_second": 3.291,
+      "step": 40
+    },
+    {
+      "epoch": 0.3445378151260504,
+      "grad_norm": 0.755547285079956,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 1.6602,
+      "step": 41
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": 0.5774405002593994,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.8706,
+      "step": 42
+    },
+    {
+      "epoch": 0.36134453781512604,
+      "grad_norm": 0.5662205815315247,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 1.5593,
+      "step": 43
+    },
+    {
+      "epoch": 0.3697478991596639,
+      "grad_norm": 0.5752977132797241,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.3166,
+      "step": 44
+    },
+    {
+      "epoch": 0.37815126050420167,
+      "grad_norm": 0.6292284727096558,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.4294,
+      "step": 45
+    },
+    {
+      "epoch": 0.37815126050420167,
+      "eval_loss": 1.7095458507537842,
+      "eval_runtime": 3.9571,
+      "eval_samples_per_second": 25.271,
+      "eval_steps_per_second": 3.285,
+      "step": 45
+    },
+    {
+      "epoch": 0.3865546218487395,
+      "grad_norm": 1.0096640586853027,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.0052,
+      "step": 46
+    },
+    {
+      "epoch": 0.3949579831932773,
+      "grad_norm": 1.2999299764633179,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 2.0057,
+      "step": 47
+    },
+    {
+      "epoch": 0.40336134453781514,
+      "grad_norm": 0.6547578573226929,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 1.6589,
+      "step": 48
+    },
+    {
+      "epoch": 0.4117647058823529,
+      "grad_norm": 0.4350292682647705,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 1.3996,
+      "step": 49
+    },
+    {
+      "epoch": 0.42016806722689076,
+      "grad_norm": 0.5918790698051453,
+      "learning_rate": 0.0,
+      "loss": 1.6555,
+      "step": 50
+    },
+    {
+      "epoch": 0.42016806722689076,
+      "eval_loss": 1.709800124168396,
+      "eval_runtime": 3.9539,
+      "eval_samples_per_second": 25.291,
+      "eval_steps_per_second": 3.288,
+      "step": 50
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 50,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6531344184115200.0,
+  "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:e17c09e3676a9cee87fad08b8dcaae8ed05749e123ef1543922902603b02c8f2
+size 6776

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": "<|endoftext|>",
+    "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": "<|endoftext|>",
+  "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:e17c09e3676a9cee87fad08b8dcaae8ed05749e123ef1543922902603b02c8f2
+size 6776