| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9894736842105263, | |
| "eval_steps": 500, | |
| "global_step": 47, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08421052631578947, | |
| "grad_norm": 64.44918823242188, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 5.9893, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.16842105263157894, | |
| "grad_norm": 1.1460206508636475, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 1.7662, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.25263157894736843, | |
| "grad_norm": 0.8948838710784912, | |
| "learning_rate": 6.111111111111112e-05, | |
| "loss": 0.8212, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3368421052631579, | |
| "grad_norm": 0.5042845606803894, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 0.533, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 0.5063032507896423, | |
| "learning_rate": 0.00010555555555555557, | |
| "loss": 0.425, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5052631578947369, | |
| "grad_norm": 0.4761255383491516, | |
| "learning_rate": 0.00012777777777777776, | |
| "loss": 0.3875, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5894736842105263, | |
| "grad_norm": 0.4021145701408386, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.3799, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6736842105263158, | |
| "grad_norm": 0.441383421421051, | |
| "learning_rate": 0.00017222222222222224, | |
| "loss": 0.3438, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7578947368421053, | |
| "grad_norm": 0.3923978805541992, | |
| "learning_rate": 0.00019444444444444446, | |
| "loss": 0.2952, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 0.39148256182670593, | |
| "learning_rate": 0.00019999007677495127, | |
| "loss": 0.2766, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9263157894736842, | |
| "grad_norm": 0.3753437101840973, | |
| "learning_rate": 0.0001999459775237086, | |
| "loss": 0.329, | |
| "step": 44 | |
| } | |
| ], | |
| "logging_steps": 4, | |
| "max_steps": 705, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "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": 1.906455948243763e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |