| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0003793266951161688, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.21474105684632e-05, | |
| "grad_norm": 0.011248151771724224, | |
| "learning_rate": 2e-05, | |
| "loss": 11.7653, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.21474105684632e-05, | |
| "eval_loss": 11.765829086303711, | |
| "eval_runtime": 131.7311, | |
| "eval_samples_per_second": 75.836, | |
| "eval_steps_per_second": 37.918, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.42948211369264e-05, | |
| "grad_norm": 0.01069817878305912, | |
| "learning_rate": 4e-05, | |
| "loss": 11.7684, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001264422317053896, | |
| "grad_norm": 0.012802043929696083, | |
| "learning_rate": 6e-05, | |
| "loss": 11.7666, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001264422317053896, | |
| "eval_loss": 11.765822410583496, | |
| "eval_runtime": 132.995, | |
| "eval_samples_per_second": 75.116, | |
| "eval_steps_per_second": 37.558, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001685896422738528, | |
| "grad_norm": 0.01624899171292782, | |
| "learning_rate": 8e-05, | |
| "loss": 11.765, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.000210737052842316, | |
| "grad_norm": 0.012532914988696575, | |
| "learning_rate": 0.0001, | |
| "loss": 11.764, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0002528844634107792, | |
| "grad_norm": 0.012021192349493504, | |
| "learning_rate": 0.00012, | |
| "loss": 11.7684, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002528844634107792, | |
| "eval_loss": 11.765796661376953, | |
| "eval_runtime": 132.0054, | |
| "eval_samples_per_second": 75.679, | |
| "eval_steps_per_second": 37.839, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002950318739792424, | |
| "grad_norm": 0.01062710676342249, | |
| "learning_rate": 0.00014, | |
| "loss": 11.7684, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0003371792845477056, | |
| "grad_norm": 0.012556190602481365, | |
| "learning_rate": 0.00016, | |
| "loss": 11.7639, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0003793266951161688, | |
| "grad_norm": 0.014915535226464272, | |
| "learning_rate": 0.00018, | |
| "loss": 11.7665, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003793266951161688, | |
| "eval_loss": 11.76574993133545, | |
| "eval_runtime": 131.8391, | |
| "eval_samples_per_second": 75.774, | |
| "eval_steps_per_second": 37.887, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 723619381248.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |