| { | |
| "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": 2.0671271678531755, | |
| "learning_rate": 0.0, | |
| "loss": 0.866, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "grad_norm": 2.2900714872410477, | |
| "learning_rate": 7.142857142857143e-06, | |
| "loss": 1.043, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 1.861548862699238, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 0.9408, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.14035087719298245, | |
| "grad_norm": 1.5918887111051039, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 0.9754, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.17543859649122806, | |
| "grad_norm": 2.461157666875476, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 0.9909, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 3.269351348810357, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.9765, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.24561403508771928, | |
| "grad_norm": 2.891039729725391, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 0.976, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2807017543859649, | |
| "grad_norm": 1.7833187830275166, | |
| "learning_rate": 5e-05, | |
| "loss": 0.985, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 1.6508430392003424, | |
| "learning_rate": 4.9993025930300686e-05, | |
| "loss": 0.9983, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3508771929824561, | |
| "grad_norm": 1.3325514749958667, | |
| "learning_rate": 4.99721076122146e-05, | |
| "loss": 0.9611, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.38596491228070173, | |
| "grad_norm": 1.1508459362776429, | |
| "learning_rate": 4.9937256716606394e-05, | |
| "loss": 0.8505, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 0.8112441764899212, | |
| "learning_rate": 4.9888492687682096e-05, | |
| "loss": 0.8723, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.45614035087719296, | |
| "grad_norm": 0.8092302145893412, | |
| "learning_rate": 4.982584273214061e-05, | |
| "loss": 0.9396, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.49122807017543857, | |
| "grad_norm": 0.7597090899690478, | |
| "learning_rate": 4.9749341803994465e-05, | |
| "loss": 0.8441, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 0.6679585780372033, | |
| "learning_rate": 4.965903258506806e-05, | |
| "loss": 0.8723, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5614035087719298, | |
| "grad_norm": 0.5980287018483266, | |
| "learning_rate": 4.955496546118439e-05, | |
| "loss": 0.8188, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5964912280701754, | |
| "grad_norm": 0.7845483827995335, | |
| "learning_rate": 4.9437198494053464e-05, | |
| "loss": 0.9303, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 0.5932466105687543, | |
| "learning_rate": 4.9305797388878264e-05, | |
| "loss": 0.8304, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.5537040595976515, | |
| "learning_rate": 4.916083545769607e-05, | |
| "loss": 0.8943, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7017543859649122, | |
| "grad_norm": 0.5092981470635746, | |
| "learning_rate": 4.9002393578475816e-05, | |
| "loss": 0.8906, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7368421052631579, | |
| "grad_norm": 0.5487294714158888, | |
| "learning_rate": 4.883056014999423e-05, | |
| "loss": 0.8584, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7719298245614035, | |
| "grad_norm": 0.4922358015626094, | |
| "learning_rate": 4.864543104251587e-05, | |
| "loss": 0.8129, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8070175438596491, | |
| "grad_norm": 0.5397899665966813, | |
| "learning_rate": 4.8447109544304636e-05, | |
| "loss": 0.8779, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 0.5043199211637701, | |
| "learning_rate": 4.823570630399665e-05, | |
| "loss": 0.8482, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8771929824561403, | |
| "grad_norm": 0.4889597930942473, | |
| "learning_rate": 4.8011339268866505e-05, | |
| "loss": 0.8361, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9122807017543859, | |
| "grad_norm": 0.4769108041878493, | |
| "learning_rate": 4.7774133619021514e-05, | |
| "loss": 0.904, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9473684210526315, | |
| "grad_norm": 0.41632944677923917, | |
| "learning_rate": 4.752422169756048e-05, | |
| "loss": 0.8032, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9824561403508771, | |
| "grad_norm": 0.5107558694810208, | |
| "learning_rate": 4.726174293673612e-05, | |
| "loss": 0.8312, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.5107558694810208, | |
| "learning_rate": 4.698684378016222e-05, | |
| "loss": 0.6911, | |
| "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 | |
| } | |