| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2381593389525131, | |
| "global_step": 11500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0019792904922649986, | |
| "loss": 0.1744, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0019585809845299976, | |
| "loss": 0.1699, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0019378714767949966, | |
| "loss": 0.1663, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0019171619690599956, | |
| "loss": 0.1502, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0018964524613249943, | |
| "loss": 0.1528, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0018757429535899933, | |
| "loss": 0.1716, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.001855033445854992, | |
| "loss": 0.1643, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.001834323938119991, | |
| "loss": 0.1735, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0018136144303849897, | |
| "loss": 0.1576, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0017929049226499886, | |
| "loss": 0.1652, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0017721954149149874, | |
| "loss": 0.1676, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0017514859071799864, | |
| "loss": 0.1612, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0017307763994449852, | |
| "loss": 0.1681, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0017100668917099842, | |
| "loss": 0.1696, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.001689357383974983, | |
| "loss": 0.1692, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0016686478762399817, | |
| "loss": 0.172, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0016479383685049807, | |
| "loss": 0.159, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0016272288607699795, | |
| "loss": 0.1675, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0016065193530349785, | |
| "loss": 0.16, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0015858098452999772, | |
| "loss": 0.1647, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0015651003375649762, | |
| "loss": 0.1572, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.001544390829829975, | |
| "loss": 0.1548, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.001523681322094974, | |
| "loss": 0.1642, | |
| "step": 11500 | |
| } | |
| ], | |
| "max_steps": 48287, | |
| "num_train_epochs": 1, | |
| "total_flos": 3.7354337206272e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |