| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0025587717895410203, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005117543579082041, | |
| "grad_norm": 236.236328125, | |
| "learning_rate": 1e-05, | |
| "loss": 76.6652, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005117543579082041, | |
| "eval_loss": 4.345206260681152, | |
| "eval_runtime": 121.9863, | |
| "eval_samples_per_second": 26.987, | |
| "eval_steps_per_second": 13.493, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010235087158164081, | |
| "grad_norm": 187.3214569091797, | |
| "learning_rate": 2e-05, | |
| "loss": 64.4183, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0010235087158164081, | |
| "eval_loss": 4.175482273101807, | |
| "eval_runtime": 74.0108, | |
| "eval_samples_per_second": 44.48, | |
| "eval_steps_per_second": 22.24, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0015352630737246122, | |
| "grad_norm": 275.8665466308594, | |
| "learning_rate": 3e-05, | |
| "loss": 75.7036, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0020470174316328162, | |
| "grad_norm": 179.53170776367188, | |
| "learning_rate": 4e-05, | |
| "loss": 59.1669, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0020470174316328162, | |
| "eval_loss": 3.679321527481079, | |
| "eval_runtime": 73.9921, | |
| "eval_samples_per_second": 44.491, | |
| "eval_steps_per_second": 22.246, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0025587717895410203, | |
| "grad_norm": 198.7086181640625, | |
| "learning_rate": 5e-05, | |
| "loss": 61.2642, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3505343598428160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |