| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "global_step": 2950, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.6616949152542374e-05, | |
| "loss": 0.6614, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 1.3227118644067798e-05, | |
| "loss": 0.5209, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 9.837288135593221e-06, | |
| "loss": 0.3374, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 6.461016949152543e-06, | |
| "loss": 0.1943, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 3.0711864406779663e-06, | |
| "loss": 0.0907, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 2950, | |
| "total_flos": 3079055584788480.0, | |
| "train_loss": 0.3138986231917042, | |
| "train_runtime": 144.264, | |
| "train_samples_per_second": 326.727, | |
| "train_steps_per_second": 20.449 | |
| } | |
| ], | |
| "max_steps": 2950, | |
| "num_train_epochs": 5, | |
| "total_flos": 3079055584788480.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |