| { | |
| "best_metric": 1.8112770318984985, | |
| "best_model_checkpoint": "output/macan/checkpoint-36", | |
| "epoch": 2.0, | |
| "global_step": 36, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00011506151581352585, | |
| "loss": 2.5021, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 6.293505690059801e-05, | |
| "loss": 2.2306, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.4464961055407408e-05, | |
| "loss": 2.1128, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.0351359844207764, | |
| "eval_runtime": 0.9179, | |
| "eval_samples_per_second": 22.88, | |
| "eval_steps_per_second": 3.269, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.137086214086682e-06, | |
| "loss": 2.0597, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 4.513741816785908e-05, | |
| "loss": 2.0438, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00010290000000000001, | |
| "loss": 2.1141, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.00013615781185663748, | |
| "loss": 2.0135, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.8112770318984985, | |
| "eval_runtime": 0.5407, | |
| "eval_samples_per_second": 46.236, | |
| "eval_steps_per_second": 7.398, | |
| "step": 36 | |
| } | |
| ], | |
| "max_steps": 36, | |
| "num_train_epochs": 2, | |
| "total_flos": 36319592448000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |