| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008, | |
| "eval_steps": 500, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.0743815898895264, | |
| "learning_rate": 9e-05, | |
| "loss": 3.3022, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 1.2970468997955322, | |
| "learning_rate": 8e-05, | |
| "loss": 2.4431, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.8511476516723633, | |
| "learning_rate": 7e-05, | |
| "loss": 2.6099, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 1.9492582082748413, | |
| "learning_rate": 6e-05, | |
| "loss": 2.7586, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.705533981323242, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8354, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 1.1676084995269775, | |
| "learning_rate": 4e-05, | |
| "loss": 2.7772, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 1.255302906036377, | |
| "learning_rate": 3e-05, | |
| "loss": 2.2979, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.5516277551651001, | |
| "learning_rate": 2e-05, | |
| "loss": 2.2402, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.6967688798904419, | |
| "learning_rate": 1e-05, | |
| "loss": 1.968, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 1.1630473136901855, | |
| "learning_rate": 0.0, | |
| "loss": 2.3687, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 2.289763230941184e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |