| { | |
| "best_metric": 0.9220191240310669, | |
| "best_model_checkpoint": "/home/datta0/models/lora_final/Qwen2-7B_magiccoder_default/checkpoint-4", | |
| "epoch": 0.026101141924959218, | |
| "eval_steps": 4, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0065252854812398045, | |
| "grad_norm": 6.940319538116455, | |
| "learning_rate": 7.5e-05, | |
| "loss": 0.8051, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013050570962479609, | |
| "grad_norm": 5.597632884979248, | |
| "learning_rate": 0.00015, | |
| "loss": 0.9302, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.026101141924959218, | |
| "grad_norm": 4.383840084075928, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8215, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.026101141924959218, | |
| "eval_loss": 0.9220191240310669, | |
| "eval_runtime": 24.7526, | |
| "eval_samples_per_second": 19.756, | |
| "eval_steps_per_second": 2.505, | |
| "step": 4 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 153, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 4, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9312211371294720.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |