| base_model: Qwen/Qwen2.5-Math-7B-Instruct | |
| batch_size: 32 | |
| bf16: true | |
| chat_template: tokenizer_default_fallback_alpaca | |
| datasets: | |
| - data_files: | |
| - 63970f9aa6060c87_train_data.json | |
| ds_type: json | |
| format: custom | |
| path: /workspace/input_data/63970f9aa6060c87_train_data.json | |
| type: | |
| field_instruction: question | |
| field_output: answer | |
| format: '{instruction}' | |
| no_input_format: '{instruction}' | |
| system_format: '{system}' | |
| system_prompt: '' | |
| eval_steps: 20 | |
| flash_attention: true | |
| gpu_memory_limit: 80GiB | |
| gradient_checkpointing: true | |
| group_by_length: true | |
| hub_model_id: willtensora/e48fbbf8-54f7-401b-bc8f-38d51942e140 | |
| hub_strategy: checkpoint | |
| learning_rate: 0.0002 | |
| logging_steps: 10 | |
| lr_scheduler: cosine | |
| max_steps: 2500 | |
| micro_batch_size: 4 | |
| model_type: AutoModelForCausalLM | |
| optimizer: adamw_bnb_8bit | |
| output_dir: /workspace/axolotl/configs | |
| pad_to_sequence_len: true | |
| resize_token_embeddings_to_32x: false | |
| sample_packing: false | |
| save_steps: 40 | |
| save_total_limit: 1 | |
| sequence_len: 2048 | |
| tokenizer_type: Qwen2TokenizerFast | |
| train_on_inputs: false | |
| trust_remote_code: true | |
| val_set_size: 0.1 | |
| wandb_entity: '' | |
| wandb_mode: online | |
| wandb_name: Qwen/Qwen2.5-Math-7B-Instruct-/workspace/input_data/63970f9aa6060c87_train_data.json | |
| wandb_project: Gradients-On-Demand | |
| wandb_run: your_name | |
| wandb_runid: default | |
| warmup_ratio: 0.05 | |
| xformers_attention: true | |