| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.32, | |
| "eval_steps": 500, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 19.88896369934082, | |
| "learning_rate": 0.00015555555555555556, | |
| "loss": 9.6148, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 3.0083649158477783, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 5.1146, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.6400000000000001, | |
| "grad_norm": 17.57530975341797, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 8.3805, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 3.7451229095458984, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 4.5262, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "step": 9, | |
| "total_flos": 87485929268832.0, | |
| "train_loss": 7.02129332224528, | |
| "train_runtime": 224.2171, | |
| "train_samples_per_second": 2.676, | |
| "train_steps_per_second": 0.04 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 9, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 87485929268832.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |