| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.000263641816228472, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.63641816228472e-05, | |
| "grad_norm": 3.3858017921447754, | |
| "learning_rate": 2e-05, | |
| "loss": 2.5932, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.63641816228472e-05, | |
| "eval_loss": 3.4614310264587402, | |
| "eval_runtime": 593.621, | |
| "eval_samples_per_second": 26.904, | |
| "eval_steps_per_second": 13.453, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.27283632456944e-05, | |
| "grad_norm": 4.082881927490234, | |
| "learning_rate": 4e-05, | |
| "loss": 3.7065, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 7.90925448685416e-05, | |
| "grad_norm": 4.037023067474365, | |
| "learning_rate": 6e-05, | |
| "loss": 3.8842, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 7.90925448685416e-05, | |
| "eval_loss": 3.4087717533111572, | |
| "eval_runtime": 595.8606, | |
| "eval_samples_per_second": 26.803, | |
| "eval_steps_per_second": 13.402, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001054567264913888, | |
| "grad_norm": 4.399959564208984, | |
| "learning_rate": 8e-05, | |
| "loss": 4.1243, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.000131820908114236, | |
| "grad_norm": 3.1502976417541504, | |
| "learning_rate": 0.0001, | |
| "loss": 2.606, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0001581850897370832, | |
| "grad_norm": 3.2664148807525635, | |
| "learning_rate": 0.00012, | |
| "loss": 2.7721, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001581850897370832, | |
| "eval_loss": 2.749638080596924, | |
| "eval_runtime": 592.7248, | |
| "eval_samples_per_second": 26.945, | |
| "eval_steps_per_second": 13.473, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001845492713599304, | |
| "grad_norm": 4.0232625007629395, | |
| "learning_rate": 0.00014, | |
| "loss": 3.1844, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0002109134529827776, | |
| "grad_norm": 3.1623497009277344, | |
| "learning_rate": 0.00016, | |
| "loss": 2.5837, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002372776346056248, | |
| "grad_norm": 3.2371985912323, | |
| "learning_rate": 0.00018, | |
| "loss": 2.6483, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002372776346056248, | |
| "eval_loss": 1.8183720111846924, | |
| "eval_runtime": 593.4027, | |
| "eval_samples_per_second": 26.914, | |
| "eval_steps_per_second": 13.458, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000263641816228472, | |
| "grad_norm": 3.4679648876190186, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8774, | |
| "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": 925180061810688.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |