| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0006696241734326609, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.696241734326609e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 14.2906, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.696241734326609e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 434.6172, | |
| "eval_samples_per_second": 14.468, | |
| "eval_steps_per_second": 7.234, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00013392483468653219, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00020088725202979828, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 17.227, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00020088725202979828, | |
| "eval_loss": NaN, | |
| "eval_runtime": 434.889, | |
| "eval_samples_per_second": 14.459, | |
| "eval_steps_per_second": 7.229, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00026784966937306437, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00033481208671633044, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00040177450405959656, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 2.6778, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00040177450405959656, | |
| "eval_loss": NaN, | |
| "eval_runtime": 435.0639, | |
| "eval_samples_per_second": 14.453, | |
| "eval_steps_per_second": 7.227, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004687369214028626, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 3.8288, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005356993387461287, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006026617560893949, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006026617560893949, | |
| "eval_loss": NaN, | |
| "eval_runtime": 434.9665, | |
| "eval_samples_per_second": 14.456, | |
| "eval_steps_per_second": 7.228, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006696241734326609, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 4.3123, | |
| "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": 3050742541713408.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |