Upload folder using huggingface_hub

.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 +1,154 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: unsloth/Qwen2.5-Math-1.5B
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: b36bc019-5c8a-4b59-a55f-1b7c3e3e285b
+  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: unsloth/Qwen2.5-Math-1.5B
+bf16: auto
+chat_template: llama3
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - 13c030c9fab986d3_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/13c030c9fab986d3_train_data.json
+  type:
+    field_input: anime_tags
+    field_instruction: text_description
+    field_output: llm_op_text
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+early_stopping_patience: 1
+eval_max_new_tokens: 128
+eval_steps: 25
+eval_table_size: null
+flash_attention: true
+fp16: false
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 16
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: sn56b1/b36bc019-5c8a-4b59-a55f-1b7c3e3e285b
+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: 64
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 32
+lora_target_linear: true
+lr_scheduler: cosine
+max_steps: 50
+micro_batch_size: 2
+mlflow_experiment_name: /tmp/13c030c9fab986d3_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
+sequence_len: 2048
+strict: false
+tf32: false
+tokenizer_type: AutoTokenizer
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.05
+wandb_entity: sn56-miner
+wandb_mode: disabled
+wandb_name: b36bc019-5c8a-4b59-a55f-1b7c3e3e285b
+wandb_project: god
+wandb_run: davw
+wandb_runid: b36bc019-5c8a-4b59-a55f-1b7c3e3e285b
+warmup_ratio: 0.05
+weight_decay: 0.01
+xformers_attention: true
+
+```
+
+</details><br>
+
+# b36bc019-5c8a-4b59-a55f-1b7c3e3e285b
+
+This model is a fine-tuned version of [unsloth/Qwen2.5-Math-1.5B](https://huggingface.co/unsloth/Qwen2.5-Math-1.5B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2436
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 128
+- total_eval_batch_size: 8
+- 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: 2
+- training_steps: 50
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.4725        | 0.0561 | 1    | 1.7714          |
+| 0.3322        | 1.4281 | 25   | 0.2938          |
+| 0.2261        | 2.8561 | 50   | 0.2436          |
+
+
+### 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": "unsloth/Qwen2.5-Math-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": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "q_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:fe13ac801131af82cd95f3cb14f6fd719dcc9449617f37dae7cd0303b78356cb
+size 147859242

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d38d27c92dd533940dd998cc802805b5702fa6682fe85d3f6ae2e905829b60e2
+size 147770496

added_tokens.json

@@ -0,0 +1,25 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|PAD_TOKEN|>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "unsloth/Qwen2.5-Math-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": 4096,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151665,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0",
+  "unsloth_fixed": true,
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Qwen2.5-Math-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": "unsloth/Qwen2.5-Math-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": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "q_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:d38d27c92dd533940dd998cc802805b5702fa6682fe85d3f6ae2e905829b60e2
+size 147770496

last-checkpoint/added_tokens.json

@@ -0,0 +1,25 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|PAD_TOKEN|>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a78b922ac19dc3a4c47726c9bd463072afed1356a9aed04db7b335693818b145
+size 295765866

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1118170ce6b3b11c670928298934ec609f01804610ebb3b9d61988e3615352f
+size 15024

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c7a1b70ba68ae9b203dd9c20f9a14bed84a7e7bdb12c2491a30555571c36869
+size 15024

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:466f1cbcded58f72c5e5b78de48e7cf86bb4e1e4cd768631af568e528dc90ef5
+size 15024

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f62073cb712929d890de00b14b61773caf317c8ce7e33e95c8f4cbc3bd347f96
+size 15024

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": "<|PAD_TOKEN|>",
+    "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:fab42efe8d17406525a9154b728cf9e957629a8ed7ce997770efdd71128c6a1a
+size 11422086

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,216 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,416 @@
+{
+  "best_metric": 0.24364762008190155,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.856140350877193,
+  "eval_steps": 25,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.056140350877192984,
+      "grad_norm": 0.5651276707649231,
+      "learning_rate": 5e-05,
+      "loss": 1.4725,
+      "step": 1
+    },
+    {
+      "epoch": 0.056140350877192984,
+      "eval_loss": 1.7714346647262573,
+      "eval_runtime": 1.3479,
+      "eval_samples_per_second": 89.029,
+      "eval_steps_per_second": 11.129,
+      "step": 1
+    },
+    {
+      "epoch": 0.11228070175438597,
+      "grad_norm": 0.6416943669319153,
+      "learning_rate": 0.0001,
+      "loss": 1.6539,
+      "step": 2
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "grad_norm": 0.6658276915550232,
+      "learning_rate": 9.989294616193017e-05,
+      "loss": 1.7257,
+      "step": 3
+    },
+    {
+      "epoch": 0.22456140350877193,
+      "grad_norm": 0.8303353786468506,
+      "learning_rate": 9.957224306869053e-05,
+      "loss": 2.0857,
+      "step": 4
+    },
+    {
+      "epoch": 0.2807017543859649,
+      "grad_norm": 0.5310768485069275,
+      "learning_rate": 9.903926402016153e-05,
+      "loss": 1.2739,
+      "step": 5
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "grad_norm": 0.5690150856971741,
+      "learning_rate": 9.829629131445342e-05,
+      "loss": 1.2439,
+      "step": 6
+    },
+    {
+      "epoch": 0.3929824561403509,
+      "grad_norm": 0.6279029846191406,
+      "learning_rate": 9.73465064747553e-05,
+      "loss": 1.1812,
+      "step": 7
+    },
+    {
+      "epoch": 0.44912280701754387,
+      "grad_norm": 0.9386560320854187,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.304,
+      "step": 8
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "grad_norm": 0.7043356895446777,
+      "learning_rate": 9.484363707663442e-05,
+      "loss": 0.8478,
+      "step": 9
+    },
+    {
+      "epoch": 0.5614035087719298,
+      "grad_norm": 1.41144597530365,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 0.7629,
+      "step": 10
+    },
+    {
+      "epoch": 0.6175438596491228,
+      "grad_norm": 0.870070219039917,
+      "learning_rate": 9.157348061512727e-05,
+      "loss": 0.6928,
+      "step": 11
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "grad_norm": 0.7913166284561157,
+      "learning_rate": 8.966766701456177e-05,
+      "loss": 0.6501,
+      "step": 12
+    },
+    {
+      "epoch": 0.7298245614035088,
+      "grad_norm": 0.7600938081741333,
+      "learning_rate": 8.759199037394887e-05,
+      "loss": 0.5388,
+      "step": 13
+    },
+    {
+      "epoch": 0.7859649122807018,
+      "grad_norm": 0.6539992094039917,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.4374,
+      "step": 14
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.864997923374176,
+      "learning_rate": 8.296729075500344e-05,
+      "loss": 0.4098,
+      "step": 15
+    },
+    {
+      "epoch": 0.8982456140350877,
+      "grad_norm": 0.3268994987010956,
+      "learning_rate": 8.043807145043604e-05,
+      "loss": 0.3976,
+      "step": 16
+    },
+    {
+      "epoch": 0.9543859649122807,
+      "grad_norm": 0.32331573963165283,
+      "learning_rate": 7.777851165098012e-05,
+      "loss": 0.3891,
+      "step": 17
+    },
+    {
+      "epoch": 1.0350877192982457,
+      "grad_norm": 0.33268672227859497,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.5223,
+      "step": 18
+    },
+    {
+      "epoch": 1.0912280701754387,
+      "grad_norm": 0.17669150233268738,
+      "learning_rate": 7.211443451095007e-05,
+      "loss": 0.3078,
+      "step": 19
+    },
+    {
+      "epoch": 1.1473684210526316,
+      "grad_norm": 0.17232191562652588,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.3084,
+      "step": 20
+    },
+    {
+      "epoch": 1.2035087719298245,
+      "grad_norm": 0.19485709071159363,
+      "learning_rate": 6.607197326515808e-05,
+      "loss": 0.3945,
+      "step": 21
+    },
+    {
+      "epoch": 1.2596491228070175,
+      "grad_norm": 0.14998270571231842,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.2605,
+      "step": 22
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.14380517601966858,
+      "learning_rate": 5.9754516100806423e-05,
+      "loss": 0.3034,
+      "step": 23
+    },
+    {
+      "epoch": 1.3719298245614036,
+      "grad_norm": 0.12622232735157013,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.2755,
+      "step": 24
+    },
+    {
+      "epoch": 1.4280701754385965,
+      "grad_norm": 0.15098120272159576,
+      "learning_rate": 5.327015646150716e-05,
+      "loss": 0.3322,
+      "step": 25
+    },
+    {
+      "epoch": 1.4280701754385965,
+      "eval_loss": 0.2937827408313751,
+      "eval_runtime": 1.3438,
+      "eval_samples_per_second": 89.301,
+      "eval_steps_per_second": 11.163,
+      "step": 25
+    },
+    {
+      "epoch": 1.4842105263157894,
+      "grad_norm": 0.14724570512771606,
+      "learning_rate": 5e-05,
+      "loss": 0.2336,
+      "step": 26
+    },
+    {
+      "epoch": 1.5403508771929824,
+      "grad_norm": 0.1329941749572754,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.2956,
+      "step": 27
+    },
+    {
+      "epoch": 1.5964912280701755,
+      "grad_norm": 0.12431260943412781,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.2782,
+      "step": 28
+    },
+    {
+      "epoch": 1.6526315789473685,
+      "grad_norm": 0.14311625063419342,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3268,
+      "step": 29
+    },
+    {
+      "epoch": 1.7087719298245614,
+      "grad_norm": 0.15831390023231506,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.2467,
+      "step": 30
+    },
+    {
+      "epoch": 1.7649122807017545,
+      "grad_norm": 0.13795287907123566,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.2934,
+      "step": 31
+    },
+    {
+      "epoch": 1.8210526315789473,
+      "grad_norm": 0.135288804769516,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.259,
+      "step": 32
+    },
+    {
+      "epoch": 1.8771929824561404,
+      "grad_norm": 0.1479368656873703,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.2468,
+      "step": 33
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 0.17140528559684753,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3291,
+      "step": 34
+    },
+    {
+      "epoch": 2.0140350877192983,
+      "grad_norm": 0.23568753898143768,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.4309,
+      "step": 35
+    },
+    {
+      "epoch": 2.0701754385964914,
+      "grad_norm": 0.1325768381357193,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.2595,
+      "step": 36
+    },
+    {
+      "epoch": 2.126315789473684,
+      "grad_norm": 0.14927180111408234,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.2653,
+      "step": 37
+    },
+    {
+      "epoch": 2.1824561403508773,
+      "grad_norm": 0.1620611846446991,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2591,
+      "step": 38
+    },
+    {
+      "epoch": 2.23859649122807,
+      "grad_norm": 0.17460227012634277,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.2285,
+      "step": 39
+    },
+    {
+      "epoch": 2.294736842105263,
+      "grad_norm": 0.1393241584300995,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.2285,
+      "step": 40
+    },
+    {
+      "epoch": 2.3508771929824563,
+      "grad_norm": 0.14091889560222626,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.2552,
+      "step": 41
+    },
+    {
+      "epoch": 2.407017543859649,
+      "grad_norm": 0.15764474868774414,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2962,
+      "step": 42
+    },
+    {
+      "epoch": 2.463157894736842,
+      "grad_norm": 0.16738121211528778,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.2559,
+      "step": 43
+    },
+    {
+      "epoch": 2.519298245614035,
+      "grad_norm": 0.138456791639328,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2269,
+      "step": 44
+    },
+    {
+      "epoch": 2.575438596491228,
+      "grad_norm": 0.1286228895187378,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.2557,
+      "step": 45
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.13272061944007874,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.1985,
+      "step": 46
+    },
+    {
+      "epoch": 2.687719298245614,
+      "grad_norm": 0.1482582837343216,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.2735,
+      "step": 47
+    },
+    {
+      "epoch": 2.743859649122807,
+      "grad_norm": 0.14489953219890594,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.2213,
+      "step": 48
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.12907636165618896,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.2865,
+      "step": 49
+    },
+    {
+      "epoch": 2.856140350877193,
+      "grad_norm": 0.13516248762607574,
+      "learning_rate": 0.0,
+      "loss": 0.2261,
+      "step": 50
+    },
+    {
+      "epoch": 2.856140350877193,
+      "eval_loss": 0.24364762008190155,
+      "eval_runtime": 1.3454,
+      "eval_samples_per_second": 89.192,
+      "eval_steps_per_second": 11.149,
+      "step": 50
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 50,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 1,
+        "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": 1.059536353886208e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d99d8987969ec6f7b199af20afa570be973a14f1af3f3372c4aac20652ae7a0
+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": "<|PAD_TOKEN|>",
+    "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:fab42efe8d17406525a9154b728cf9e957629a8ed7ce997770efdd71128c6a1a
+size 11422086

tokenizer_config.json

@@ -0,0 +1,216 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "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 sha256:1d99d8987969ec6f7b199af20afa570be973a14f1af3f3372c4aac20652ae7a0
+size 6776