| { | |
| "best_metric": 2.2854506969451904, | |
| "best_model_checkpoint": "/home/datta0/models/lora_final/Mistral-7B-v0.3_pct_ortho/checkpoint-8", | |
| "epoch": 0.020631850419084462, | |
| "eval_steps": 8, | |
| "global_step": 8, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0025789813023855577, | |
| "grad_norm": 10.031487464904785, | |
| "learning_rate": 3.75e-05, | |
| "loss": 2.128, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010315925209542231, | |
| "grad_norm": 7.364378929138184, | |
| "learning_rate": 0.00015, | |
| "loss": 2.0612, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.020631850419084462, | |
| "grad_norm": 23.759828567504883, | |
| "learning_rate": 0.0003, | |
| "loss": 2.1243, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.020631850419084462, | |
| "eval_loss": 2.2854506969451904, | |
| "eval_runtime": 11.1093, | |
| "eval_samples_per_second": 22.054, | |
| "eval_steps_per_second": 2.79, | |
| "step": 8 | |
| } | |
| ], | |
| "logging_steps": 4, | |
| "max_steps": 387, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 8, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.8441287540146176e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |