| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 8419, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.88122104763036e-05, | |
| "loss": 0.6229, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.76244209526072e-05, | |
| "loss": 0.5352, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.64366314289108e-05, | |
| "loss": 0.4817, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.5248841905214398e-05, | |
| "loss": 0.4653, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.4061052381517997e-05, | |
| "loss": 0.4314, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.2873262857821596e-05, | |
| "loss": 0.419, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.1685473334125195e-05, | |
| "loss": 0.4161, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.0497683810428794e-05, | |
| "loss": 0.3852, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.309894286732392e-06, | |
| "loss": 0.366, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.12210476303599e-06, | |
| "loss": 0.3779, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 6.93431523933959e-06, | |
| "loss": 0.3502, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5.746525715643189e-06, | |
| "loss": 0.3532, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.558736191946788e-06, | |
| "loss": 0.3524, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.370946668250386e-06, | |
| "loss": 0.3522, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 2.183157144553985e-06, | |
| "loss": 0.3374, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 9.953676208575841e-07, | |
| "loss": 0.3306, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 8419, | |
| "total_flos": 4430066616860160.0, | |
| "train_loss": 0.4067993889031692, | |
| "train_runtime": 975.4755, | |
| "train_samples_per_second": 69.042, | |
| "train_steps_per_second": 8.631 | |
| } | |
| ], | |
| "max_steps": 8419, | |
| "num_train_epochs": 1, | |
| "total_flos": 4430066616860160.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |