| { | |
| "best_metric": 0.03319514915347099, | |
| "best_model_checkpoint": "autotrain-4usrt-85kzb/checkpoint-33", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 33, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": 11.761338233947754, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.8704, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 7.499186038970947, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.5885, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2727272727272727, | |
| "grad_norm": 5.171218395233154, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.615, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 10.380544662475586, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6992, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": 5.8920512199401855, | |
| "learning_rate": 4.827586206896552e-05, | |
| "loss": 0.5152, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": 6.648828506469727, | |
| "learning_rate": 4.655172413793104e-05, | |
| "loss": 0.4446, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6363636363636364, | |
| "grad_norm": 12.528966903686523, | |
| "learning_rate": 4.482758620689655e-05, | |
| "loss": 0.4955, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 7.694393157958984, | |
| "learning_rate": 4.3103448275862066e-05, | |
| "loss": 0.5072, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8181818181818182, | |
| "grad_norm": 7.016471862792969, | |
| "learning_rate": 4.1379310344827587e-05, | |
| "loss": 0.2834, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 7.048137664794922, | |
| "learning_rate": 3.965517241379311e-05, | |
| "loss": 0.2472, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 7.261392116546631, | |
| "learning_rate": 3.793103448275862e-05, | |
| "loss": 0.2076, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9523809523809523, | |
| "eval_auc": 1.0, | |
| "eval_f1": 0.9473684210526315, | |
| "eval_loss": 0.1770750731229782, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9, | |
| "eval_runtime": 4.8171, | |
| "eval_samples_per_second": 4.359, | |
| "eval_steps_per_second": 0.415, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0909090909090908, | |
| "grad_norm": 6.019667625427246, | |
| "learning_rate": 3.620689655172414e-05, | |
| "loss": 0.1873, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.1818181818181819, | |
| "grad_norm": 4.4459710121154785, | |
| "learning_rate": 3.4482758620689657e-05, | |
| "loss": 0.119, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.2727272727272727, | |
| "grad_norm": 2.7395246028900146, | |
| "learning_rate": 3.275862068965517e-05, | |
| "loss": 0.0936, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.3636363636363638, | |
| "grad_norm": 2.9547948837280273, | |
| "learning_rate": 3.103448275862069e-05, | |
| "loss": 0.0986, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.4545454545454546, | |
| "grad_norm": 7.345340251922607, | |
| "learning_rate": 2.9310344827586206e-05, | |
| "loss": 0.0939, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.5454545454545454, | |
| "grad_norm": 2.4599573612213135, | |
| "learning_rate": 2.7586206896551727e-05, | |
| "loss": 0.0789, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.6363636363636362, | |
| "grad_norm": 3.887648582458496, | |
| "learning_rate": 2.5862068965517244e-05, | |
| "loss": 0.0814, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.7272727272727273, | |
| "grad_norm": 2.253195285797119, | |
| "learning_rate": 2.413793103448276e-05, | |
| "loss": 0.0746, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.8181818181818183, | |
| "grad_norm": 2.3239686489105225, | |
| "learning_rate": 2.2413793103448276e-05, | |
| "loss": 0.0713, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.9090909090909092, | |
| "grad_norm": 2.0128979682922363, | |
| "learning_rate": 2.0689655172413793e-05, | |
| "loss": 0.0609, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 3.9712774753570557, | |
| "learning_rate": 1.896551724137931e-05, | |
| "loss": 0.0998, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.054505739361047745, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 4.8545, | |
| "eval_samples_per_second": 4.326, | |
| "eval_steps_per_second": 0.412, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.090909090909091, | |
| "grad_norm": 1.6843291521072388, | |
| "learning_rate": 1.7241379310344828e-05, | |
| "loss": 0.0552, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.1818181818181817, | |
| "grad_norm": 1.4115827083587646, | |
| "learning_rate": 1.5517241379310346e-05, | |
| "loss": 0.0461, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.2727272727272725, | |
| "grad_norm": 1.6311649084091187, | |
| "learning_rate": 1.3793103448275863e-05, | |
| "loss": 0.0515, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.3636363636363638, | |
| "grad_norm": 1.2126336097717285, | |
| "learning_rate": 1.206896551724138e-05, | |
| "loss": 0.0385, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.4545454545454546, | |
| "grad_norm": 1.5105429887771606, | |
| "learning_rate": 1.0344827586206897e-05, | |
| "loss": 0.0463, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.5454545454545454, | |
| "grad_norm": 1.3499268293380737, | |
| "learning_rate": 8.620689655172414e-06, | |
| "loss": 0.0418, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.6363636363636362, | |
| "grad_norm": 1.2205418348312378, | |
| "learning_rate": 6.896551724137932e-06, | |
| "loss": 0.0381, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.7272727272727275, | |
| "grad_norm": 1.1028234958648682, | |
| "learning_rate": 5.172413793103448e-06, | |
| "loss": 0.0346, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.8181818181818183, | |
| "grad_norm": 1.0579960346221924, | |
| "learning_rate": 3.448275862068966e-06, | |
| "loss": 0.0336, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.909090909090909, | |
| "grad_norm": 1.2498091459274292, | |
| "learning_rate": 1.724137931034483e-06, | |
| "loss": 0.0392, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 1.5818809270858765, | |
| "learning_rate": 0.0, | |
| "loss": 0.0462, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.03319514915347099, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 4.8139, | |
| "eval_samples_per_second": 4.362, | |
| "eval_steps_per_second": 0.415, | |
| "step": 33 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 33, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 15983996613120.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |