| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.10526315789473684, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010526315789473684, | |
| "grad_norm": 33.016944885253906, | |
| "learning_rate": 2e-05, | |
| "loss": 5.8338, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010526315789473684, | |
| "eval_loss": 5.785942554473877, | |
| "eval_runtime": 1.2192, | |
| "eval_samples_per_second": 32.807, | |
| "eval_steps_per_second": 16.404, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.021052631578947368, | |
| "grad_norm": 40.027305603027344, | |
| "learning_rate": 4e-05, | |
| "loss": 5.5921, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.031578947368421054, | |
| "grad_norm": 19.79706573486328, | |
| "learning_rate": 6e-05, | |
| "loss": 5.465, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.031578947368421054, | |
| "eval_loss": 5.628373146057129, | |
| "eval_runtime": 0.726, | |
| "eval_samples_per_second": 55.093, | |
| "eval_steps_per_second": 27.546, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.042105263157894736, | |
| "grad_norm": 17.628948211669922, | |
| "learning_rate": 8e-05, | |
| "loss": 5.7571, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05263157894736842, | |
| "grad_norm": 8.720337867736816, | |
| "learning_rate": 0.0001, | |
| "loss": 5.391, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06315789473684211, | |
| "grad_norm": 6.100517749786377, | |
| "learning_rate": 0.00012, | |
| "loss": 5.3274, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06315789473684211, | |
| "eval_loss": 5.239671230316162, | |
| "eval_runtime": 0.7538, | |
| "eval_samples_per_second": 53.063, | |
| "eval_steps_per_second": 26.531, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07368421052631578, | |
| "grad_norm": 5.213286876678467, | |
| "learning_rate": 0.00014, | |
| "loss": 4.6999, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08421052631578947, | |
| "grad_norm": 5.555608749389648, | |
| "learning_rate": 0.00016, | |
| "loss": 4.5009, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09473684210526316, | |
| "grad_norm": 6.240391731262207, | |
| "learning_rate": 0.00018, | |
| "loss": 4.406, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09473684210526316, | |
| "eval_loss": 4.4296064376831055, | |
| "eval_runtime": 0.7654, | |
| "eval_samples_per_second": 52.259, | |
| "eval_steps_per_second": 26.129, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 6.4179534912109375, | |
| "learning_rate": 0.0002, | |
| "loss": 4.4041, | |
| "step": 10 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 255791978250240.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |