| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "global_step": 5380, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.721189591078067e-05, | |
| "loss": 0.0911, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.442379182156134e-05, | |
| "loss": 0.0481, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.1635687732342008e-05, | |
| "loss": 0.0282, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.8847583643122676e-05, | |
| "loss": 0.0238, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.6059479553903345e-05, | |
| "loss": 0.0167, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 1.3271375464684014e-05, | |
| "loss": 0.0148, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 1.0483271375464685e-05, | |
| "loss": 0.006, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 7.695167286245354e-06, | |
| "loss": 0.0082, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 4.907063197026023e-06, | |
| "loss": 0.004, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 2.1189591078066917e-06, | |
| "loss": 0.0041, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 5380, | |
| "total_flos": 1598937634083120.0, | |
| "train_loss": 0.022965262658534, | |
| "train_runtime": 895.4582, | |
| "train_samples_per_second": 24.032, | |
| "train_steps_per_second": 6.008 | |
| } | |
| ], | |
| "max_steps": 5380, | |
| "num_train_epochs": 5, | |
| "total_flos": 1598937634083120.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |