| { | |
| "best_metric": 0.0005376620101742446, | |
| "best_model_checkpoint": "autotrain-okqe6-pd7eh/checkpoint-52", | |
| "epoch": 13.0, | |
| "eval_steps": 500, | |
| "global_step": 52, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 14.21432876586914, | |
| "learning_rate": 2.5e-06, | |
| "loss": 1.7194, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 26.781686782836914, | |
| "learning_rate": 5e-06, | |
| "loss": 1.6298, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 11.112658500671387, | |
| "learning_rate": 7.5e-06, | |
| "loss": 1.5897, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 27.626598358154297, | |
| "learning_rate": 1e-05, | |
| "loss": 5.1747, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5714285714285714, | |
| "eval_auc": 0.7619047619047619, | |
| "eval_f1": 0.625, | |
| "eval_loss": 2.144031047821045, | |
| "eval_precision": 0.9090909090909091, | |
| "eval_recall": 0.47619047619047616, | |
| "eval_runtime": 9.1146, | |
| "eval_samples_per_second": 3.072, | |
| "eval_steps_per_second": 0.219, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 15.852094650268555, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.758, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 12.443609237670898, | |
| "learning_rate": 1.5e-05, | |
| "loss": 2.5724, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 10.946976661682129, | |
| "learning_rate": 1.75e-05, | |
| "loss": 0.4912, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 14.185081481933594, | |
| "learning_rate": 2e-05, | |
| "loss": 1.245, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6428571428571429, | |
| "eval_auc": 0.8095238095238095, | |
| "eval_f1": 0.7058823529411765, | |
| "eval_loss": 1.4039461612701416, | |
| "eval_precision": 0.9230769230769231, | |
| "eval_recall": 0.5714285714285714, | |
| "eval_runtime": 8.4655, | |
| "eval_samples_per_second": 3.308, | |
| "eval_steps_per_second": 0.236, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "grad_norm": 14.650551795959473, | |
| "learning_rate": 2.25e-05, | |
| "loss": 0.7346, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 10.59030818939209, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.124, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "grad_norm": 15.367939949035645, | |
| "learning_rate": 2.7500000000000004e-05, | |
| "loss": 2.1564, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 2.77498459815979, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0703, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.75, | |
| "eval_auc": 0.9047619047619048, | |
| "eval_f1": 0.8108108108108109, | |
| "eval_loss": 0.6543990969657898, | |
| "eval_precision": 0.9375, | |
| "eval_recall": 0.7142857142857143, | |
| "eval_runtime": 8.6388, | |
| "eval_samples_per_second": 3.241, | |
| "eval_steps_per_second": 0.232, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "grad_norm": 19.424549102783203, | |
| "learning_rate": 3.2500000000000004e-05, | |
| "loss": 1.2086, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "grad_norm": 15.029265403747559, | |
| "learning_rate": 3.5e-05, | |
| "loss": 1.5127, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "grad_norm": 6.021083354949951, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.1327, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 23.40821647644043, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3535, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8928571428571429, | |
| "eval_auc": 0.9795918367346939, | |
| "eval_f1": 0.9230769230769231, | |
| "eval_loss": 0.28167834877967834, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.8571428571428571, | |
| "eval_runtime": 9.1138, | |
| "eval_samples_per_second": 3.072, | |
| "eval_steps_per_second": 0.219, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "grad_norm": 5.730878829956055, | |
| "learning_rate": 4.25e-05, | |
| "loss": 0.3334, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "grad_norm": 13.562226295471191, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.4879, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "grad_norm": 15.55147647857666, | |
| "learning_rate": 4.75e-05, | |
| "loss": 0.6376, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 4.316409111022949, | |
| "learning_rate": 5e-05, | |
| "loss": 0.143, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.10469154268503189, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 8.9428, | |
| "eval_samples_per_second": 3.131, | |
| "eval_steps_per_second": 0.224, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "grad_norm": 4.850322246551514, | |
| "learning_rate": 4.972222222222223e-05, | |
| "loss": 0.1503, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "grad_norm": 7.610826015472412, | |
| "learning_rate": 4.9444444444444446e-05, | |
| "loss": 0.3183, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "grad_norm": 9.175180435180664, | |
| "learning_rate": 4.9166666666666665e-05, | |
| "loss": 0.6048, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 5.765699863433838, | |
| "learning_rate": 4.888888888888889e-05, | |
| "loss": 0.0806, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.0491504967212677, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 9.0668, | |
| "eval_samples_per_second": 3.088, | |
| "eval_steps_per_second": 0.221, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "grad_norm": 10.618638038635254, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 0.2229, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "grad_norm": 2.024526596069336, | |
| "learning_rate": 4.8333333333333334e-05, | |
| "loss": 0.0809, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "grad_norm": 3.5910582542419434, | |
| "learning_rate": 4.805555555555556e-05, | |
| "loss": 0.2059, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 0.8639962077140808, | |
| "learning_rate": 4.7777777777777784e-05, | |
| "loss": 0.0232, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.033924441784620285, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 8.9013, | |
| "eval_samples_per_second": 3.146, | |
| "eval_steps_per_second": 0.225, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "grad_norm": 6.809825897216797, | |
| "learning_rate": 4.75e-05, | |
| "loss": 0.2383, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "grad_norm": 1.3117998838424683, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 0.0335, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "grad_norm": 4.045058250427246, | |
| "learning_rate": 4.6944444444444446e-05, | |
| "loss": 0.1796, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 10.013517379760742, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 0.3612, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.010722639039158821, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 8.7618, | |
| "eval_samples_per_second": 3.196, | |
| "eval_steps_per_second": 0.228, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "grad_norm": 3.8245110511779785, | |
| "learning_rate": 4.638888888888889e-05, | |
| "loss": 0.0614, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "grad_norm": 0.46702659130096436, | |
| "learning_rate": 4.6111111111111115e-05, | |
| "loss": 0.0137, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "grad_norm": 0.9684951901435852, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 0.024, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 0.3815953731536865, | |
| "learning_rate": 4.555555555555556e-05, | |
| "loss": 0.0101, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.002381645841524005, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 8.8895, | |
| "eval_samples_per_second": 3.15, | |
| "eval_steps_per_second": 0.225, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "grad_norm": 0.10922980308532715, | |
| "learning_rate": 4.527777777777778e-05, | |
| "loss": 0.0026, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "grad_norm": 10.054232597351074, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.2193, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "grad_norm": 0.452944278717041, | |
| "learning_rate": 4.472222222222223e-05, | |
| "loss": 0.0045, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 31.92047119140625, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.4483, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.0012448489433154464, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 9.1493, | |
| "eval_samples_per_second": 3.06, | |
| "eval_steps_per_second": 0.219, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 10.25, | |
| "grad_norm": 0.061426494270563126, | |
| "learning_rate": 4.4166666666666665e-05, | |
| "loss": 0.0023, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 10.5, | |
| "grad_norm": 4.463461399078369, | |
| "learning_rate": 4.388888888888889e-05, | |
| "loss": 0.0456, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 10.75, | |
| "grad_norm": 1.7845221757888794, | |
| "learning_rate": 4.3611111111111116e-05, | |
| "loss": 0.0437, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "grad_norm": 0.04194610193371773, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 0.001, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.0008708243840374053, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 8.9245, | |
| "eval_samples_per_second": 3.137, | |
| "eval_steps_per_second": 0.224, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 11.25, | |
| "grad_norm": 1.2456785440444946, | |
| "learning_rate": 4.305555555555556e-05, | |
| "loss": 0.018, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 11.5, | |
| "grad_norm": 10.299635887145996, | |
| "learning_rate": 4.277777777777778e-05, | |
| "loss": 0.1391, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 11.75, | |
| "grad_norm": 0.06855878978967667, | |
| "learning_rate": 4.25e-05, | |
| "loss": 0.0014, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 5.5674285888671875, | |
| "learning_rate": 4.222222222222222e-05, | |
| "loss": 0.0784, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.0006320010288618505, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 9.1551, | |
| "eval_samples_per_second": 3.058, | |
| "eval_steps_per_second": 0.218, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 12.25, | |
| "grad_norm": 0.02712714672088623, | |
| "learning_rate": 4.194444444444445e-05, | |
| "loss": 0.0012, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "grad_norm": 0.01984160952270031, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.001, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 12.75, | |
| "grad_norm": 0.0771925300359726, | |
| "learning_rate": 4.138888888888889e-05, | |
| "loss": 0.0012, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "grad_norm": 12.30930233001709, | |
| "learning_rate": 4.111111111111111e-05, | |
| "loss": 0.2424, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.0005376620101742446, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 9.5896, | |
| "eval_samples_per_second": 2.92, | |
| "eval_steps_per_second": 0.209, | |
| "step": 52 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "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": 2.820708421971149e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |