| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1654601861427094, | |
| "eval_steps": 500, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.643, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.6409, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.5779, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.6641, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 2e-05, | |
| "loss": 0.61, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.6653, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 0.6101, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.7479, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.6357, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4e-05, | |
| "loss": 0.6214, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 180, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 10, | |
| "total_flos": 3.6412092186624e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |