{
"best_metric": 0.17235368490219116,
"best_model_checkpoint": "autotrain-dhurg-4zloz/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": 8.779764175415039,
"learning_rate": 6.666666666666667e-06,
"loss": 0.7021,
"step": 2
},
{
"epoch": 0.08,
"grad_norm": 11.571272850036621,
"learning_rate": 1.3333333333333333e-05,
"loss": 0.7476,
"step": 4
},
{
"epoch": 0.12,
"grad_norm": 7.2595109939575195,
"learning_rate": 2e-05,
"loss": 0.6407,
"step": 6
},
{
"epoch": 0.16,
"grad_norm": 22.257381439208984,
"learning_rate": 2.6666666666666667e-05,
"loss": 0.7677,
"step": 8
},
{
"epoch": 0.2,
"grad_norm": 9.527205467224121,
"learning_rate": 3.3333333333333335e-05,
"loss": 0.6452,
"step": 10
},
{
"epoch": 0.24,
"grad_norm": 6.193709373474121,
"learning_rate": 4e-05,
"loss": 0.4157,
"step": 12
},
{
"epoch": 0.28,
"grad_norm": 8.290445327758789,
"learning_rate": 4.666666666666667e-05,
"loss": 0.6082,
"step": 14
},
{
"epoch": 0.32,
"grad_norm": 15.103638648986816,
"learning_rate": 4.962962962962963e-05,
"loss": 0.8635,
"step": 16
},
{
"epoch": 0.36,
"grad_norm": 9.055012702941895,
"learning_rate": 4.888888888888889e-05,
"loss": 0.4496,
"step": 18
},
{
"epoch": 0.4,
"grad_norm": 7.674185276031494,
"learning_rate": 4.814814814814815e-05,
"loss": 0.4544,
"step": 20
},
{
"epoch": 0.44,
"grad_norm": 5.750149250030518,
"learning_rate": 4.740740740740741e-05,
"loss": 0.4023,
"step": 22
},
{
"epoch": 0.48,
"grad_norm": 9.68493938446045,
"learning_rate": 4.666666666666667e-05,
"loss": 0.4952,
"step": 24
},
{
"epoch": 0.52,
"grad_norm": 5.293528079986572,
"learning_rate": 4.592592592592593e-05,
"loss": 0.5546,
"step": 26
},
{
"epoch": 0.56,
"grad_norm": 7.6056647300720215,
"learning_rate": 4.518518518518519e-05,
"loss": 0.3908,
"step": 28
},
{
"epoch": 0.6,
"grad_norm": 6.408599853515625,
"learning_rate": 4.4444444444444447e-05,
"loss": 0.2509,
"step": 30
},
{
"epoch": 0.64,
"grad_norm": 6.033527374267578,
"learning_rate": 4.3703703703703705e-05,
"loss": 0.2029,
"step": 32
},
{
"epoch": 0.68,
"grad_norm": 11.087029457092285,
"learning_rate": 4.296296296296296e-05,
"loss": 0.5078,
"step": 34
},
{
"epoch": 0.72,
"grad_norm": 6.722639560699463,
"learning_rate": 4.222222222222222e-05,
"loss": 0.4449,
"step": 36
},
{
"epoch": 0.76,
"grad_norm": 5.349610805511475,
"learning_rate": 4.148148148148148e-05,
"loss": 0.3874,
"step": 38
},
{
"epoch": 0.8,
"grad_norm": 7.29227352142334,
"learning_rate": 4.074074074074074e-05,
"loss": 0.5953,
"step": 40
},
{
"epoch": 0.84,
"grad_norm": 8.242330551147461,
"learning_rate": 4e-05,
"loss": 0.3056,
"step": 42
},
{
"epoch": 0.88,
"grad_norm": 3.6587088108062744,
"learning_rate": 3.925925925925926e-05,
"loss": 0.1099,
"step": 44
},
{
"epoch": 0.92,
"grad_norm": 3.0559661388397217,
"learning_rate": 3.851851851851852e-05,
"loss": 0.37,
"step": 46
},
{
"epoch": 0.96,
"grad_norm": 4.720924377441406,
"learning_rate": 3.777777777777778e-05,
"loss": 0.1703,
"step": 48
},
{
"epoch": 1.0,
"grad_norm": 3.9827725887298584,
"learning_rate": 3.7037037037037037e-05,
"loss": 0.3503,
"step": 50
},
{
"epoch": 1.0,
"eval_accuracy": 0.95,
"eval_auc": 0.964,
"eval_f1": 0.9494949494949495,
"eval_loss": 0.21780452132225037,
"eval_precision": 0.9591836734693877,
"eval_recall": 0.94,
"eval_runtime": 26.0018,
"eval_samples_per_second": 3.846,
"eval_steps_per_second": 0.269,
"step": 50
},
{
"epoch": 1.04,
"grad_norm": 2.406909465789795,
"learning_rate": 3.62962962962963e-05,
"loss": 0.1008,
"step": 52
},
{
"epoch": 1.08,
"grad_norm": 11.02933406829834,
"learning_rate": 3.555555555555556e-05,
"loss": 0.2756,
"step": 54
},
{
"epoch": 1.12,
"grad_norm": 8.120884895324707,
"learning_rate": 3.481481481481482e-05,
"loss": 0.2622,
"step": 56
},
{
"epoch": 1.16,
"grad_norm": 5.108714580535889,
"learning_rate": 3.4074074074074077e-05,
"loss": 0.1122,
"step": 58
},
{
"epoch": 1.2,
"grad_norm": 13.36482048034668,
"learning_rate": 3.3333333333333335e-05,
"loss": 0.2356,
"step": 60
},
{
"epoch": 1.24,
"grad_norm": 4.833813190460205,
"learning_rate": 3.25925925925926e-05,
"loss": 0.1811,
"step": 62
},
{
"epoch": 1.28,
"grad_norm": 4.81235933303833,
"learning_rate": 3.185185185185185e-05,
"loss": 0.1474,
"step": 64
},
{
"epoch": 1.32,
"grad_norm": 0.43874427676200867,
"learning_rate": 3.111111111111111e-05,
"loss": 0.2348,
"step": 66
},
{
"epoch": 1.3599999999999999,
"grad_norm": 1.1349278688430786,
"learning_rate": 3.037037037037037e-05,
"loss": 0.0234,
"step": 68
},
{
"epoch": 1.4,
"grad_norm": 2.6060400009155273,
"learning_rate": 2.962962962962963e-05,
"loss": 0.1018,
"step": 70
},
{
"epoch": 1.44,
"grad_norm": 6.894038200378418,
"learning_rate": 2.8888888888888888e-05,
"loss": 0.3433,
"step": 72
},
{
"epoch": 1.48,
"grad_norm": 0.4274143576622009,
"learning_rate": 2.814814814814815e-05,
"loss": 0.3128,
"step": 74
},
{
"epoch": 1.52,
"grad_norm": 4.964171886444092,
"learning_rate": 2.7407407407407408e-05,
"loss": 0.1867,
"step": 76
},
{
"epoch": 1.56,
"grad_norm": 3.660466194152832,
"learning_rate": 2.6666666666666667e-05,
"loss": 0.1936,
"step": 78
},
{
"epoch": 1.6,
"grad_norm": 9.657711029052734,
"learning_rate": 2.5925925925925925e-05,
"loss": 0.2673,
"step": 80
},
{
"epoch": 1.6400000000000001,
"grad_norm": 7.678964614868164,
"learning_rate": 2.5185185185185183e-05,
"loss": 0.2198,
"step": 82
},
{
"epoch": 1.6800000000000002,
"grad_norm": 2.8848860263824463,
"learning_rate": 2.4444444444444445e-05,
"loss": 0.2738,
"step": 84
},
{
"epoch": 1.72,
"grad_norm": 13.012591361999512,
"learning_rate": 2.3703703703703707e-05,
"loss": 0.2112,
"step": 86
},
{
"epoch": 1.76,
"grad_norm": 8.288191795349121,
"learning_rate": 2.2962962962962965e-05,
"loss": 0.1981,
"step": 88
},
{
"epoch": 1.8,
"grad_norm": 9.876968383789062,
"learning_rate": 2.2222222222222223e-05,
"loss": 0.3836,
"step": 90
},
{
"epoch": 1.8399999999999999,
"grad_norm": 0.2542683184146881,
"learning_rate": 2.148148148148148e-05,
"loss": 0.2617,
"step": 92
},
{
"epoch": 1.88,
"grad_norm": 1.3072165250778198,
"learning_rate": 2.074074074074074e-05,
"loss": 0.2146,
"step": 94
},
{
"epoch": 1.92,
"grad_norm": 5.043093681335449,
"learning_rate": 2e-05,
"loss": 0.0965,
"step": 96
},
{
"epoch": 1.96,
"grad_norm": 7.184999942779541,
"learning_rate": 1.925925925925926e-05,
"loss": 0.232,
"step": 98
},
{
"epoch": 2.0,
"grad_norm": 7.763317584991455,
"learning_rate": 1.8518518518518518e-05,
"loss": 0.3054,
"step": 100
},
{
"epoch": 2.0,
"eval_accuracy": 0.94,
"eval_auc": 0.9796,
"eval_f1": 0.94,
"eval_loss": 0.17235368490219116,
"eval_precision": 0.94,
"eval_recall": 0.94,
"eval_runtime": 24.1401,
"eval_samples_per_second": 4.142,
"eval_steps_per_second": 0.29,
"step": 100
}
],
"logging_steps": 2,
"max_steps": 150,
"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": 6.19935916916736e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}