| { | |
| "best_metric": 0.5335766077041626, | |
| "best_model_checkpoint": "autotrain-roberta-sentiment/checkpoint-100", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 3.4940836429595947, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.1535, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 3.262470245361328, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.1256, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 2.512415647506714, | |
| "learning_rate": 1.2e-05, | |
| "loss": 1.0537, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.9540835022926331, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 1.1332, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 1.4703962802886963, | |
| "learning_rate": 2e-05, | |
| "loss": 1.0453, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 2.3024346828460693, | |
| "learning_rate": 2.4e-05, | |
| "loss": 1.0759, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 4.083477973937988, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 1.0091, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 2.6913983821868896, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 1.0225, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 2.0365138053894043, | |
| "learning_rate": 3.6e-05, | |
| "loss": 1.0758, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 2.462596893310547, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0949, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 2.2764413356781006, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 1.1325, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 2.8556883335113525, | |
| "learning_rate": 4.8e-05, | |
| "loss": 1.0637, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 2.2826690673828125, | |
| "learning_rate": 4.977777777777778e-05, | |
| "loss": 1.1215, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 2.986983299255371, | |
| "learning_rate": 4.933333333333334e-05, | |
| "loss": 1.1464, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 3.0181400775909424, | |
| "learning_rate": 4.888888888888889e-05, | |
| "loss": 1.0994, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 2.1268210411071777, | |
| "learning_rate": 4.844444444444445e-05, | |
| "loss": 1.0626, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 2.155054807662964, | |
| "learning_rate": 4.8e-05, | |
| "loss": 1.1088, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 3.4121484756469727, | |
| "learning_rate": 4.755555555555556e-05, | |
| "loss": 1.0775, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 2.4863100051879883, | |
| "learning_rate": 4.711111111111111e-05, | |
| "loss": 1.0617, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 6.520081043243408, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 1.0156, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 7.486565589904785, | |
| "learning_rate": 4.6222222222222224e-05, | |
| "loss": 0.8929, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 18.066055297851562, | |
| "learning_rate": 4.577777777777778e-05, | |
| "loss": 1.2286, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 10.362664222717285, | |
| "learning_rate": 4.5333333333333335e-05, | |
| "loss": 0.9297, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 6.666133403778076, | |
| "learning_rate": 4.4888888888888894e-05, | |
| "loss": 0.9551, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 8.330809593200684, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.972, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.465, | |
| "eval_f1_macro": 0.3169122948031185, | |
| "eval_f1_micro": 0.465, | |
| "eval_f1_weighted": 0.3513784524105401, | |
| "eval_loss": 0.9785851240158081, | |
| "eval_precision_macro": 0.8102836879432624, | |
| "eval_precision_micro": 0.465, | |
| "eval_precision_weighted": 0.7694946808510639, | |
| "eval_recall_macro": 0.398005698005698, | |
| "eval_recall_micro": 0.465, | |
| "eval_recall_weighted": 0.465, | |
| "eval_runtime": 38.6621, | |
| "eval_samples_per_second": 5.173, | |
| "eval_steps_per_second": 0.181, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 8.873079299926758, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 1.0789, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 12.436768531799316, | |
| "learning_rate": 4.355555555555556e-05, | |
| "loss": 0.9067, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 19.907135009765625, | |
| "learning_rate": 4.311111111111111e-05, | |
| "loss": 0.7823, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 39.21774673461914, | |
| "learning_rate": 4.266666666666667e-05, | |
| "loss": 1.3983, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 27.241775512695312, | |
| "learning_rate": 4.222222222222222e-05, | |
| "loss": 1.1425, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 50.450050354003906, | |
| "learning_rate": 4.177777777777778e-05, | |
| "loss": 1.0617, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 19.874343872070312, | |
| "learning_rate": 4.133333333333333e-05, | |
| "loss": 1.1376, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 15.969518661499023, | |
| "learning_rate": 4.088888888888889e-05, | |
| "loss": 1.042, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.3599999999999999, | |
| "grad_norm": 12.018631935119629, | |
| "learning_rate": 4.0444444444444444e-05, | |
| "loss": 0.7554, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 9.8690767288208, | |
| "learning_rate": 4e-05, | |
| "loss": 0.9531, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 7.842430114746094, | |
| "learning_rate": 3.9555555555555556e-05, | |
| "loss": 0.8799, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 8.438117027282715, | |
| "learning_rate": 3.9111111111111115e-05, | |
| "loss": 0.7729, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 6.847545623779297, | |
| "learning_rate": 3.866666666666667e-05, | |
| "loss": 0.792, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 7.344234943389893, | |
| "learning_rate": 3.8222222222222226e-05, | |
| "loss": 0.7008, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 19.439647674560547, | |
| "learning_rate": 3.777777777777778e-05, | |
| "loss": 0.6895, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.6400000000000001, | |
| "grad_norm": 8.48671817779541, | |
| "learning_rate": 3.733333333333334e-05, | |
| "loss": 0.5814, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.6800000000000002, | |
| "grad_norm": 12.682677268981934, | |
| "learning_rate": 3.688888888888889e-05, | |
| "loss": 0.6957, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 21.3659610748291, | |
| "learning_rate": 3.644444444444445e-05, | |
| "loss": 0.539, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 26.52878189086914, | |
| "learning_rate": 3.6e-05, | |
| "loss": 1.0977, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 17.535959243774414, | |
| "learning_rate": 3.555555555555556e-05, | |
| "loss": 0.5173, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.8399999999999999, | |
| "grad_norm": 15.361188888549805, | |
| "learning_rate": 3.511111111111111e-05, | |
| "loss": 0.5678, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 17.405290603637695, | |
| "learning_rate": 3.466666666666667e-05, | |
| "loss": 0.7743, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 20.69967269897461, | |
| "learning_rate": 3.4222222222222224e-05, | |
| "loss": 0.7244, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 15.444042205810547, | |
| "learning_rate": 3.377777777777778e-05, | |
| "loss": 0.6662, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 17.32610511779785, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.6937, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8, | |
| "eval_f1_macro": 0.8027609455799637, | |
| "eval_f1_micro": 0.8, | |
| "eval_f1_weighted": 0.798510908659599, | |
| "eval_loss": 0.5335766077041626, | |
| "eval_precision_macro": 0.8034159941442764, | |
| "eval_precision_micro": 0.8, | |
| "eval_precision_weighted": 0.8030223296082353, | |
| "eval_recall_macro": 0.8077239632795189, | |
| "eval_recall_micro": 0.8, | |
| "eval_recall_weighted": 0.8, | |
| "eval_runtime": 35.6379, | |
| "eval_samples_per_second": 5.612, | |
| "eval_steps_per_second": 0.196, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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": 105113810382336.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |