| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.12738853503184713, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006369426751592357, | |
| "eval_loss": NaN, | |
| "eval_runtime": 23.2416, | |
| "eval_samples_per_second": 11.402, | |
| "eval_steps_per_second": 1.463, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01910828025477707, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03184713375796178, | |
| "eval_loss": NaN, | |
| "eval_runtime": 22.968, | |
| "eval_samples_per_second": 11.538, | |
| "eval_steps_per_second": 1.48, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03821656050955414, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05732484076433121, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06369426751592357, | |
| "eval_loss": NaN, | |
| "eval_runtime": 23.0759, | |
| "eval_samples_per_second": 11.484, | |
| "eval_steps_per_second": 1.473, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07643312101910828, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09554140127388536, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09554140127388536, | |
| "eval_loss": NaN, | |
| "eval_runtime": 23.1097, | |
| "eval_samples_per_second": 11.467, | |
| "eval_steps_per_second": 1.471, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11464968152866242, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12738853503184713, | |
| "eval_loss": NaN, | |
| "eval_runtime": 23.1132, | |
| "eval_samples_per_second": 11.465, | |
| "eval_steps_per_second": 1.471, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.3886526320410624e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |