| { | |
| "best_metric": 0.6774867177009583, | |
| "best_model_checkpoint": "autotrain-xt6nb-pf6ri/checkpoint-1000", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.048, | |
| "grad_norm": 4.167473793029785, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.0876, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 5.14194917678833, | |
| "learning_rate": 1.5666666666666667e-05, | |
| "loss": 1.1048, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.144, | |
| "grad_norm": 8.47073745727539, | |
| "learning_rate": 2.3666666666666668e-05, | |
| "loss": 1.085, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 6.285531997680664, | |
| "learning_rate": 3.1e-05, | |
| "loss": 1.0327, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 10.787246704101562, | |
| "learning_rate": 3.9000000000000006e-05, | |
| "loss": 1.0035, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.288, | |
| "grad_norm": 11.439258575439453, | |
| "learning_rate": 4.7e-05, | |
| "loss": 1.0177, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.336, | |
| "grad_norm": 6.169108867645264, | |
| "learning_rate": 4.9444444444444446e-05, | |
| "loss": 0.8407, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.384, | |
| "grad_norm": 7.220673084259033, | |
| "learning_rate": 4.8592592592592596e-05, | |
| "loss": 1.0002, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.432, | |
| "grad_norm": 8.805166244506836, | |
| "learning_rate": 4.770370370370371e-05, | |
| "loss": 0.8377, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 15.92953872680664, | |
| "learning_rate": 4.681481481481482e-05, | |
| "loss": 0.975, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.528, | |
| "grad_norm": 12.280447006225586, | |
| "learning_rate": 4.592592592592593e-05, | |
| "loss": 0.8324, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.576, | |
| "grad_norm": 7.390661716461182, | |
| "learning_rate": 4.503703703703704e-05, | |
| "loss": 0.8676, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.624, | |
| "grad_norm": 3.326416492462158, | |
| "learning_rate": 4.414814814814815e-05, | |
| "loss": 1.0311, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.672, | |
| "grad_norm": 1.4128365516662598, | |
| "learning_rate": 4.325925925925926e-05, | |
| "loss": 0.9408, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 1.4254629611968994, | |
| "learning_rate": 4.237037037037037e-05, | |
| "loss": 0.9534, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.768, | |
| "grad_norm": 5.265137195587158, | |
| "learning_rate": 4.148148148148148e-05, | |
| "loss": 0.8517, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.816, | |
| "grad_norm": 139.75430297851562, | |
| "learning_rate": 4.059259259259259e-05, | |
| "loss": 0.9692, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.864, | |
| "grad_norm": 172.7858123779297, | |
| "learning_rate": 3.97037037037037e-05, | |
| "loss": 0.9143, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.912, | |
| "grad_norm": 42.714324951171875, | |
| "learning_rate": 3.885185185185186e-05, | |
| "loss": 0.8104, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 7.165309906005859, | |
| "learning_rate": 3.7962962962962964e-05, | |
| "loss": 0.9425, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6906906906906907, | |
| "eval_f1_macro": 0.6632603879089224, | |
| "eval_f1_micro": 0.6906906906906907, | |
| "eval_f1_weighted": 0.6878712561273783, | |
| "eval_loss": 0.8078358769416809, | |
| "eval_precision_macro": 0.6746375251220212, | |
| "eval_precision_micro": 0.6906906906906907, | |
| "eval_precision_weighted": 0.6963016741978844, | |
| "eval_recall_macro": 0.6637361051449268, | |
| "eval_recall_micro": 0.6906906906906907, | |
| "eval_recall_weighted": 0.6906906906906907, | |
| "eval_runtime": 2.1598, | |
| "eval_samples_per_second": 462.551, | |
| "eval_steps_per_second": 29.17, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.008, | |
| "grad_norm": 40.330535888671875, | |
| "learning_rate": 3.7074074074074075e-05, | |
| "loss": 0.8571, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 1.056, | |
| "grad_norm": 18.710975646972656, | |
| "learning_rate": 3.6185185185185186e-05, | |
| "loss": 0.8107, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 1.104, | |
| "grad_norm": 7.848007678985596, | |
| "learning_rate": 3.52962962962963e-05, | |
| "loss": 0.8219, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 1.152, | |
| "grad_norm": 12.77737808227539, | |
| "learning_rate": 3.440740740740741e-05, | |
| "loss": 0.6249, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 4.067225456237793, | |
| "learning_rate": 3.351851851851852e-05, | |
| "loss": 0.7372, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.248, | |
| "grad_norm": 22.771604537963867, | |
| "learning_rate": 3.262962962962963e-05, | |
| "loss": 0.6791, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 1.296, | |
| "grad_norm": 32.429100036621094, | |
| "learning_rate": 3.174074074074074e-05, | |
| "loss": 0.7434, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 1.3439999999999999, | |
| "grad_norm": 7.296426773071289, | |
| "learning_rate": 3.0851851851851854e-05, | |
| "loss": 0.7742, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 1.392, | |
| "grad_norm": 52.18477249145508, | |
| "learning_rate": 2.9962962962962966e-05, | |
| "loss": 0.7379, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 47.735477447509766, | |
| "learning_rate": 2.9074074074074077e-05, | |
| "loss": 0.7652, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.488, | |
| "grad_norm": 214.20318603515625, | |
| "learning_rate": 2.8185185185185185e-05, | |
| "loss": 0.6941, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 1.536, | |
| "grad_norm": 20.468931198120117, | |
| "learning_rate": 2.7296296296296296e-05, | |
| "loss": 0.7389, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 1.584, | |
| "grad_norm": 4.2643866539001465, | |
| "learning_rate": 2.6407407407407408e-05, | |
| "loss": 0.7372, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 1.6320000000000001, | |
| "grad_norm": 18.783554077148438, | |
| "learning_rate": 2.551851851851852e-05, | |
| "loss": 0.711, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 1.6800000000000002, | |
| "grad_norm": 28.915599822998047, | |
| "learning_rate": 2.462962962962963e-05, | |
| "loss": 0.7423, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.728, | |
| "grad_norm": 4.792373180389404, | |
| "learning_rate": 2.3740740740740742e-05, | |
| "loss": 0.6692, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 1.776, | |
| "grad_norm": 19.33057975769043, | |
| "learning_rate": 2.2851851851851853e-05, | |
| "loss": 0.631, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 1.8239999999999998, | |
| "grad_norm": 18.55846405029297, | |
| "learning_rate": 2.1962962962962964e-05, | |
| "loss": 0.6367, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 1.8719999999999999, | |
| "grad_norm": 5.190149784088135, | |
| "learning_rate": 2.1074074074074072e-05, | |
| "loss": 0.6872, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 38.714290618896484, | |
| "learning_rate": 2.0185185185185187e-05, | |
| "loss": 0.6252, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.968, | |
| "grad_norm": 20.541481018066406, | |
| "learning_rate": 1.92962962962963e-05, | |
| "loss": 0.6303, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7177177177177178, | |
| "eval_f1_macro": 0.6839774417313933, | |
| "eval_f1_micro": 0.7177177177177178, | |
| "eval_f1_weighted": 0.7107988255501857, | |
| "eval_loss": 0.6774867177009583, | |
| "eval_precision_macro": 0.7089199316136637, | |
| "eval_precision_micro": 0.7177177177177178, | |
| "eval_precision_weighted": 0.7240729310198633, | |
| "eval_recall_macro": 0.6773815101662369, | |
| "eval_recall_micro": 0.7177177177177178, | |
| "eval_recall_weighted": 0.7177177177177178, | |
| "eval_runtime": 2.1078, | |
| "eval_samples_per_second": 473.965, | |
| "eval_steps_per_second": 29.89, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 24, | |
| "max_steps": 1500, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 525305938493952.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |