| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4258641493363617, | |
| "eval_steps": 500, | |
| "global_step": 6000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.10646603733409042, | |
| "grad_norm": 0.3511381149291992, | |
| "learning_rate": 4.81935110918419e-05, | |
| "loss": 0.365, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.21293207466818084, | |
| "grad_norm": 0.31686341762542725, | |
| "learning_rate": 4.548377772960474e-05, | |
| "loss": 0.1136, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.31939811200227125, | |
| "grad_norm": 0.3509831726551056, | |
| "learning_rate": 4.277404436736759e-05, | |
| "loss": 0.1087, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.4258641493363617, | |
| "grad_norm": 0.3466353118419647, | |
| "learning_rate": 4.006431100513043e-05, | |
| "loss": 0.1044, | |
| "step": 6000 | |
| } | |
| ], | |
| "logging_steps": 1500, | |
| "max_steps": 28178, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 1500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.2288816668672e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |