| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5020242914979757, | |
| "eval_steps": 4, | |
| "global_step": 62, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008097165991902834, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.3376, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.032388663967611336, | |
| "grad_norm": 1.2224464807826465, | |
| "learning_rate": 6.000000000000001e-07, | |
| "loss": 2.2226, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06477732793522267, | |
| "grad_norm": 1.249787428874952, | |
| "learning_rate": 1.8e-06, | |
| "loss": 2.224, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09716599190283401, | |
| "grad_norm": 1.1989218543082716, | |
| "learning_rate": 2.9482456140350876e-06, | |
| "loss": 2.185, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12955465587044535, | |
| "grad_norm": 1.047534730978336, | |
| "learning_rate": 2.7412280701754384e-06, | |
| "loss": 2.1673, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.16194331983805668, | |
| "grad_norm": 2.14703390516359, | |
| "learning_rate": 2.5342105263157892e-06, | |
| "loss": 2.1744, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19433198380566802, | |
| "grad_norm": 0.7818039451289659, | |
| "learning_rate": 2.3789473684210525e-06, | |
| "loss": 2.118, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.22672064777327935, | |
| "grad_norm": 0.859921298398603, | |
| "learning_rate": 2.171929824561404e-06, | |
| "loss": 2.1748, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2591093117408907, | |
| "grad_norm": 2.0323669699673155, | |
| "learning_rate": 1.9649122807017546e-06, | |
| "loss": 2.127, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.291497975708502, | |
| "grad_norm": 1.1342217106934134, | |
| "learning_rate": 1.7578947368421054e-06, | |
| "loss": 2.1423, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.32388663967611336, | |
| "grad_norm": 0.6686240505828185, | |
| "learning_rate": 1.5508771929824563e-06, | |
| "loss": 2.1232, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3562753036437247, | |
| "grad_norm": 1.5929473542709194, | |
| "learning_rate": 1.343859649122807e-06, | |
| "loss": 2.087, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.38866396761133604, | |
| "grad_norm": 0.6948600696268362, | |
| "learning_rate": 1.136842105263158e-06, | |
| "loss": 2.1718, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 0.8188351127023403, | |
| "learning_rate": 9.298245614035089e-07, | |
| "loss": 2.1318, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.4534412955465587, | |
| "grad_norm": 0.821077911987751, | |
| "learning_rate": 7.228070175438598e-07, | |
| "loss": 2.123, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.48582995951417, | |
| "grad_norm": 0.8343208133751057, | |
| "learning_rate": 5.675438596491229e-07, | |
| "loss": 2.1087, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5020242914979757, | |
| "step": 62, | |
| "total_flos": 247899069874176.0, | |
| "train_loss": 2.158404092634878, | |
| "train_runtime": 19521.141, | |
| "train_samples_per_second": 0.404, | |
| "train_steps_per_second": 0.003 | |
| } | |
| ], | |
| "logging_steps": 4, | |
| "max_steps": 62, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "total_flos": 247899069874176.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |