| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 11049, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.7737351796542676e-05, | |
| "loss": 2.2042, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.547470359308535e-05, | |
| "loss": 2.087, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.321205538962802e-05, | |
| "loss": 2.0242, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.09494071861707e-05, | |
| "loss": 1.978, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.868675898271337e-05, | |
| "loss": 1.9701, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.6424110779256044e-05, | |
| "loss": 1.9814, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.416146257579871e-05, | |
| "loss": 1.9524, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.189881437234139e-05, | |
| "loss": 1.9124, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 2.963616616888406e-05, | |
| "loss": 1.8723, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.7373517965426738e-05, | |
| "loss": 1.8591, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2.511086976196941e-05, | |
| "loss": 1.8822, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 2.2848221558512085e-05, | |
| "loss": 1.8402, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.058557335505476e-05, | |
| "loss": 1.8634, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 1.8322925151597432e-05, | |
| "loss": 1.8638, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.6060276948140106e-05, | |
| "loss": 1.8548, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.3797628744682778e-05, | |
| "loss": 1.8085, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.1534980541225452e-05, | |
| "loss": 1.8086, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 9.272332337768125e-06, | |
| "loss": 1.809, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 7.009684134310799e-06, | |
| "loss": 1.8238, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.747035930853471e-06, | |
| "loss": 1.7984, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 2.4843877273961445e-06, | |
| "loss": 1.7959, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 2.21739523938818e-07, | |
| "loss": 1.7938, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 11049, | |
| "total_flos": 3178708656685056.0, | |
| "train_loss": 1.8986893418320963, | |
| "train_runtime": 35727.9633, | |
| "train_samples_per_second": 1.237, | |
| "train_steps_per_second": 0.309 | |
| } | |
| ], | |
| "max_steps": 11049, | |
| "num_train_epochs": 3, | |
| "total_flos": 3178708656685056.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |