| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 123, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0408997955010225, |
| "grad_norm": 9.2357177734375, |
| "learning_rate": 3.3333333333333333e-06, |
| "loss": 0.7318, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.081799591002045, |
| "grad_norm": 9.753511428833008, |
| "learning_rate": 7.500000000000001e-06, |
| "loss": 0.6559, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.12269938650306748, |
| "grad_norm": 8.666117668151855, |
| "learning_rate": 9.999225623611208e-06, |
| "loss": 0.702, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.16359918200409, |
| "grad_norm": 7.023216247558594, |
| "learning_rate": 9.990516643685222e-06, |
| "loss": 0.6079, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.20449897750511248, |
| "grad_norm": 8.54660415649414, |
| "learning_rate": 9.972147627352593e-06, |
| "loss": 0.7299, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.24539877300613497, |
| "grad_norm": 6.48859167098999, |
| "learning_rate": 9.944154131125643e-06, |
| "loss": 0.7183, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.28629856850715746, |
| "grad_norm": 7.0337629318237305, |
| "learning_rate": 9.906590341416725e-06, |
| "loss": 0.721, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.32719836400818, |
| "grad_norm": 6.987436294555664, |
| "learning_rate": 9.859528969650739e-06, |
| "loss": 0.6602, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.36809815950920244, |
| "grad_norm": 7.1492791175842285, |
| "learning_rate": 9.803061111519188e-06, |
| "loss": 0.6731, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.40899795501022496, |
| "grad_norm": 6.402842044830322, |
| "learning_rate": 9.737296070648187e-06, |
| "loss": 0.6957, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.4498977505112474, |
| "grad_norm": 6.457306385040283, |
| "learning_rate": 9.66236114702178e-06, |
| "loss": 0.6972, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.49079754601226994, |
| "grad_norm": 6.941644191741943, |
| "learning_rate": 9.57840139057007e-06, |
| "loss": 0.6772, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.5316973415132924, |
| "grad_norm": 7.459963321685791, |
| "learning_rate": 9.485579320399184e-06, |
| "loss": 0.639, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.5725971370143149, |
| "grad_norm": 7.600812911987305, |
| "learning_rate": 9.384074610206495e-06, |
| "loss": 0.6781, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.6134969325153374, |
| "grad_norm": 6.6164093017578125, |
| "learning_rate": 9.274083740490097e-06, |
| "loss": 0.7323, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.65439672801636, |
| "grad_norm": 6.039959907531738, |
| "learning_rate": 9.155819618225707e-06, |
| "loss": 0.69, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.6952965235173824, |
| "grad_norm": 6.699795246124268, |
| "learning_rate": 9.029511164747175e-06, |
| "loss": 0.6654, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.7361963190184049, |
| "grad_norm": 7.462390422821045, |
| "learning_rate": 8.895402872628352e-06, |
| "loss": 0.6825, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.7770961145194274, |
| "grad_norm": 7.326976299285889, |
| "learning_rate": 8.753754332424047e-06, |
| "loss": 0.6797, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.8179959100204499, |
| "grad_norm": 7.3194050788879395, |
| "learning_rate": 8.604839730186125e-06, |
| "loss": 0.7153, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.8588957055214724, |
| "grad_norm": 7.875491619110107, |
| "learning_rate": 8.448947316727444e-06, |
| "loss": 0.6896, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.8997955010224948, |
| "grad_norm": 7.002596378326416, |
| "learning_rate": 8.286378849660895e-06, |
| "loss": 0.6507, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.9406952965235174, |
| "grad_norm": 6.086474895477295, |
| "learning_rate": 8.117449009293668e-06, |
| "loss": 0.6434, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.9815950920245399, |
| "grad_norm": 6.344010353088379, |
| "learning_rate": 7.942484789507282e-06, |
| "loss": 0.6802, |
| "step": 120 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 369, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.660948990352425e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
