| { | |
| "best_metric": 0.4598750174045563, | |
| "best_model_checkpoint": "autotrain-tes2/checkpoint-38", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 38, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02631578947368421, | |
| "grad_norm": 8.360681533813477, | |
| "learning_rate": 1.3157894736842106e-06, | |
| "loss": 0.7789, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05263157894736842, | |
| "grad_norm": 3.473684072494507, | |
| "learning_rate": 2.631578947368421e-06, | |
| "loss": 0.7014, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07894736842105263, | |
| "grad_norm": 4.280536651611328, | |
| "learning_rate": 3.9473684210526315e-06, | |
| "loss": 0.7496, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 5.139090538024902, | |
| "learning_rate": 5.263157894736842e-06, | |
| "loss": 0.7482, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.13157894736842105, | |
| "grad_norm": 7.595941543579102, | |
| "learning_rate": 6.578947368421053e-06, | |
| "loss": 0.7648, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.15789473684210525, | |
| "grad_norm": 6.151755332946777, | |
| "learning_rate": 7.894736842105263e-06, | |
| "loss": 0.6708, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.18421052631578946, | |
| "grad_norm": 4.414488792419434, | |
| "learning_rate": 9.210526315789474e-06, | |
| "loss": 0.6814, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 2.1186416149139404, | |
| "learning_rate": 1.0526315789473684e-05, | |
| "loss": 0.6711, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.23684210526315788, | |
| "grad_norm": 5.158999919891357, | |
| "learning_rate": 1.1842105263157895e-05, | |
| "loss": 0.7188, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 2.7816195487976074, | |
| "learning_rate": 1.3157894736842106e-05, | |
| "loss": 0.6272, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2894736842105263, | |
| "grad_norm": 3.866028308868408, | |
| "learning_rate": 1.4473684210526317e-05, | |
| "loss": 0.6516, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 5.54939079284668, | |
| "learning_rate": 1.5789473684210526e-05, | |
| "loss": 0.6311, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.34210526315789475, | |
| "grad_norm": 1.7745245695114136, | |
| "learning_rate": 1.7105263157894737e-05, | |
| "loss": 0.648, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3684210526315789, | |
| "grad_norm": 5.726246356964111, | |
| "learning_rate": 1.8421052631578947e-05, | |
| "loss": 0.721, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.39473684210526316, | |
| "grad_norm": 3.599973678588867, | |
| "learning_rate": 1.9736842105263158e-05, | |
| "loss": 0.639, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 1.8797402381896973, | |
| "learning_rate": 2.105263157894737e-05, | |
| "loss": 0.6811, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.4473684210526316, | |
| "grad_norm": 2.823983669281006, | |
| "learning_rate": 2.236842105263158e-05, | |
| "loss": 0.5753, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.47368421052631576, | |
| "grad_norm": 4.9799909591674805, | |
| "learning_rate": 2.368421052631579e-05, | |
| "loss": 0.5373, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 3.066366672515869, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.4943, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 2.1961863040924072, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 0.6783, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5526315789473685, | |
| "grad_norm": 4.6081390380859375, | |
| "learning_rate": 2.7631578947368426e-05, | |
| "loss": 0.355, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5789473684210527, | |
| "grad_norm": Infinity, | |
| "learning_rate": 2.7631578947368426e-05, | |
| "loss": 0.5158, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6052631578947368, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7631578947368426e-05, | |
| "loss": 0.5127, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 6.148653984069824, | |
| "learning_rate": 2.8947368421052634e-05, | |
| "loss": 0.3929, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6578947368421053, | |
| "grad_norm": 7.018494129180908, | |
| "learning_rate": 3.0263157894736844e-05, | |
| "loss": 0.6157, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6842105263157895, | |
| "grad_norm": 1.8734830617904663, | |
| "learning_rate": 3.157894736842105e-05, | |
| "loss": 0.4951, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.7105263157894737, | |
| "grad_norm": 2.3880300521850586, | |
| "learning_rate": 3.289473684210527e-05, | |
| "loss": 0.327, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.7368421052631579, | |
| "grad_norm": 1.500815749168396, | |
| "learning_rate": 3.421052631578947e-05, | |
| "loss": 0.2797, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.7631578947368421, | |
| "grad_norm": 3.438194990158081, | |
| "learning_rate": 3.5526315789473684e-05, | |
| "loss": 0.4684, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": 2.816570281982422, | |
| "learning_rate": 3.6842105263157895e-05, | |
| "loss": 0.3406, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8157894736842105, | |
| "grad_norm": 7.311382293701172, | |
| "learning_rate": 3.815789473684211e-05, | |
| "loss": 0.5107, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 4.999342918395996, | |
| "learning_rate": 3.9473684210526316e-05, | |
| "loss": 0.5008, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.868421052631579, | |
| "grad_norm": 2.1701626777648926, | |
| "learning_rate": 4.078947368421053e-05, | |
| "loss": 0.0727, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8947368421052632, | |
| "grad_norm": 13.688937187194824, | |
| "learning_rate": 4.210526315789474e-05, | |
| "loss": 0.6574, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.9210526315789473, | |
| "grad_norm": 26.409658432006836, | |
| "learning_rate": 4.342105263157895e-05, | |
| "loss": 1.0675, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.9473684210526315, | |
| "grad_norm": 2.801671266555786, | |
| "learning_rate": 4.473684210526316e-05, | |
| "loss": 0.4416, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.9736842105263158, | |
| "grad_norm": 8.945662498474121, | |
| "learning_rate": 4.605263157894737e-05, | |
| "loss": 0.4885, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 17.597484588623047, | |
| "learning_rate": 4.736842105263158e-05, | |
| "loss": 0.7419, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.75, | |
| "eval_auc": 0.8781163434903048, | |
| "eval_f1": 0.8571428571428571, | |
| "eval_loss": 0.4598750174045563, | |
| "eval_precision": 0.75, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.1072, | |
| "eval_samples_per_second": 709.107, | |
| "eval_steps_per_second": 46.652, | |
| "step": 38 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 380, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 19930662443520.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |