| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.6382978723404253, | |
| "eval_steps": 500, | |
| "global_step": 90, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00012, | |
| "loss": 1.7547, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00019523809523809525, | |
| "loss": 1.4052, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00018095238095238095, | |
| "loss": 1.0347, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 0.8677, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00015238095238095237, | |
| "loss": 0.7763, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.0001380952380952381, | |
| "loss": 0.773, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.0001238095238095238, | |
| "loss": 0.7175, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.00010952380952380953, | |
| "loss": 0.7261, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 9.523809523809524e-05, | |
| "loss": 0.6696, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 8.095238095238096e-05, | |
| "loss": 0.6708, | |
| "step": 90 | |
| } | |
| ], | |
| "logging_steps": 9, | |
| "max_steps": 141, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 7194529404813312.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |