| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9926289926289926, | |
| "eval_steps": 500, | |
| "global_step": 101, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.000125, | |
| "loss": 1.6979, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.000375, | |
| "loss": 0.7265, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0004969974623692023, | |
| "loss": 0.1676, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0004640417248825666, | |
| "loss": 0.1557, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00039928964792569654, | |
| "loss": 0.1458, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00031236028601449537, | |
| "loss": 0.1429, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0002161671750624673, | |
| "loss": 0.1502, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00012500000000000006, | |
| "loss": 0.1432, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 5.2401832620310204e-05, | |
| "loss": 0.1426, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 9.157280346029916e-06, | |
| "loss": 0.1354, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "step": 101, | |
| "total_flos": 5.556156411097907e+16, | |
| "train_loss": 0.358406629228946, | |
| "train_runtime": 800.1231, | |
| "train_samples_per_second": 4.066, | |
| "train_steps_per_second": 0.126 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 101, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 5.556156411097907e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |