| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 29, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03508771929824561, | |
| "grad_norm": 2.0673070244813063, | |
| "learning_rate": 0.0, | |
| "loss": 0.866, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "grad_norm": 2.290645149886701, | |
| "learning_rate": 1.4285714285714286e-06, | |
| "loss": 1.043, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 2.0384407294665747, | |
| "learning_rate": 2.8571428571428573e-06, | |
| "loss": 0.9475, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.14035087719298245, | |
| "grad_norm": 2.0751386251214314, | |
| "learning_rate": 4.2857142857142855e-06, | |
| "loss": 1.0015, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.17543859649122806, | |
| "grad_norm": 1.8611754309476487, | |
| "learning_rate": 5.7142857142857145e-06, | |
| "loss": 1.0106, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 1.5605070320275363, | |
| "learning_rate": 7.1428571428571436e-06, | |
| "loss": 0.9839, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.24561403508771928, | |
| "grad_norm": 1.323817282105345, | |
| "learning_rate": 8.571428571428571e-06, | |
| "loss": 0.9658, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2807017543859649, | |
| "grad_norm": 1.1766396808562414, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9877, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 1.920335999253467, | |
| "learning_rate": 9.998605186060138e-06, | |
| "loss": 1.0056, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3508771929824561, | |
| "grad_norm": 1.8982677371348105, | |
| "learning_rate": 9.99442152244292e-06, | |
| "loss": 0.9781, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.38596491228070173, | |
| "grad_norm": 1.7435846632830103, | |
| "learning_rate": 9.98745134332128e-06, | |
| "loss": 0.8702, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 1.8684092704303354, | |
| "learning_rate": 9.97769853753642e-06, | |
| "loss": 0.8934, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.45614035087719296, | |
| "grad_norm": 1.761909365090902, | |
| "learning_rate": 9.965168546428122e-06, | |
| "loss": 0.9624, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.49122807017543857, | |
| "grad_norm": 1.3688611326166515, | |
| "learning_rate": 9.949868360798893e-06, | |
| "loss": 0.8695, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 1.1087321036703561, | |
| "learning_rate": 9.931806517013612e-06, | |
| "loss": 0.8931, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5614035087719298, | |
| "grad_norm": 0.8075436412081172, | |
| "learning_rate": 9.910993092236878e-06, | |
| "loss": 0.8353, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5964912280701754, | |
| "grad_norm": 0.836233225723369, | |
| "learning_rate": 9.887439698810694e-06, | |
| "loss": 0.9445, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 0.715862149797478, | |
| "learning_rate": 9.861159477775653e-06, | |
| "loss": 0.8434, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.7888763860979434, | |
| "learning_rate": 9.832167091539215e-06, | |
| "loss": 0.9075, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7017543859649122, | |
| "grad_norm": 0.7782919163094735, | |
| "learning_rate": 9.800478715695165e-06, | |
| "loss": 0.9018, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7368421052631579, | |
| "grad_norm": 0.8319523753602327, | |
| "learning_rate": 9.766112029998847e-06, | |
| "loss": 0.869, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7719298245614035, | |
| "grad_norm": 0.7124372949071385, | |
| "learning_rate": 9.729086208503174e-06, | |
| "loss": 0.822, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8070175438596491, | |
| "grad_norm": 0.7500909047451202, | |
| "learning_rate": 9.689421908860928e-06, | |
| "loss": 0.8867, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 0.5886562659462773, | |
| "learning_rate": 9.64714126079933e-06, | |
| "loss": 0.8565, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8771929824561403, | |
| "grad_norm": 0.5469375245913981, | |
| "learning_rate": 9.602267853773301e-06, | |
| "loss": 0.8436, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9122807017543859, | |
| "grad_norm": 0.48742789244387086, | |
| "learning_rate": 9.554826723804304e-06, | |
| "loss": 0.91, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9473684210526315, | |
| "grad_norm": 0.481986089398419, | |
| "learning_rate": 9.504844339512096e-06, | |
| "loss": 0.808, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9824561403508771, | |
| "grad_norm": 0.5338814362033426, | |
| "learning_rate": 9.452348587347224e-06, | |
| "loss": 0.8373, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.5338814362033426, | |
| "learning_rate": 9.397368756032445e-06, | |
| "loss": 0.7497, | |
| "step": 29 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 140, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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": 12946871943168.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |