| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.024052916416115455, | |
| "eval_steps": 8, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0024052916416115455, | |
| "eval_loss": 2.8067831993103027, | |
| "eval_runtime": 3.6543, | |
| "eval_samples_per_second": 47.889, | |
| "eval_steps_per_second": 24.082, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0072158749248346366, | |
| "grad_norm": 0.44602859020233154, | |
| "learning_rate": 6e-05, | |
| "loss": 2.9609, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014431749849669273, | |
| "grad_norm": 0.6594803333282471, | |
| "learning_rate": 0.00012, | |
| "loss": 3.0153, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.019242333132892364, | |
| "eval_loss": 2.7753758430480957, | |
| "eval_runtime": 2.4839, | |
| "eval_samples_per_second": 70.453, | |
| "eval_steps_per_second": 35.428, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02164762477450391, | |
| "grad_norm": 0.4808473289012909, | |
| "learning_rate": 0.00018, | |
| "loss": 3.1571, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 69418793041920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |