File size: 3,625 Bytes
2176d46 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 |
{
"best_metric": 0.0023566017149643857,
"best_model_checkpoint": "ProtBert-finetuned-1000-labels/checkpoint-10671",
"epoch": 7.0,
"global_step": 24899,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"learning_rate": 4.9500000000000004e-05,
"loss": 0.1046,
"step": 3557
},
{
"epoch": 1.0,
"eval_accuracy": 0.0,
"eval_f1": 0.0015764799415315758,
"eval_loss": 0.10419555753469467,
"eval_precision": 0.0013009841827768013,
"eval_recall": 0.002,
"eval_runtime": 36.7492,
"eval_samples_per_second": 774.166,
"eval_steps_per_second": 24.218,
"step": 3557
},
{
"epoch": 2.0,
"learning_rate": 4.9e-05,
"loss": 0.1047,
"step": 7114
},
{
"epoch": 2.0,
"eval_accuracy": 0.0,
"eval_f1": 0.0015764799415315758,
"eval_loss": 0.10421660542488098,
"eval_precision": 0.0013009841827768013,
"eval_recall": 0.002,
"eval_runtime": 36.6962,
"eval_samples_per_second": 775.284,
"eval_steps_per_second": 24.253,
"step": 7114
},
{
"epoch": 3.0,
"learning_rate": 4.85e-05,
"loss": 0.1046,
"step": 10671
},
{
"epoch": 3.0,
"eval_accuracy": 0.0,
"eval_f1": 0.0023566017149643857,
"eval_loss": 0.10416813939809799,
"eval_precision": 0.0019404920913884008,
"eval_recall": 0.003,
"eval_runtime": 36.5239,
"eval_samples_per_second": 778.941,
"eval_steps_per_second": 24.368,
"step": 10671
},
{
"epoch": 4.0,
"learning_rate": 4.8e-05,
"loss": 0.1046,
"step": 14228
},
{
"epoch": 4.0,
"eval_accuracy": 0.0,
"eval_f1": 0.0023566017149643857,
"eval_loss": 0.10419166833162308,
"eval_precision": 0.0019404920913884008,
"eval_recall": 0.003,
"eval_runtime": 36.7991,
"eval_samples_per_second": 773.116,
"eval_steps_per_second": 24.185,
"step": 14228
},
{
"epoch": 5.0,
"learning_rate": 4.75e-05,
"loss": 0.1046,
"step": 17785
},
{
"epoch": 5.0,
"eval_accuracy": 0.0,
"eval_f1": 0.0023566017149643857,
"eval_loss": 0.10412722080945969,
"eval_precision": 0.0019404920913884008,
"eval_recall": 0.003,
"eval_runtime": 37.0346,
"eval_samples_per_second": 768.201,
"eval_steps_per_second": 24.032,
"step": 17785
},
{
"epoch": 6.0,
"learning_rate": 4.7e-05,
"loss": 0.1046,
"step": 21342
},
{
"epoch": 6.0,
"eval_accuracy": 0.0,
"eval_f1": 0.0023566017149643857,
"eval_loss": 0.10410485416650772,
"eval_precision": 0.0019404920913884008,
"eval_recall": 0.003,
"eval_runtime": 36.6252,
"eval_samples_per_second": 776.788,
"eval_steps_per_second": 24.3,
"step": 21342
},
{
"epoch": 7.0,
"learning_rate": 4.6500000000000005e-05,
"loss": 0.1046,
"step": 24899
},
{
"epoch": 7.0,
"eval_accuracy": 0.0,
"eval_f1": 0.0023566017149643857,
"eval_loss": 0.1041363775730133,
"eval_precision": 0.0019404920913884008,
"eval_recall": 0.003,
"eval_runtime": 36.6525,
"eval_samples_per_second": 776.21,
"eval_steps_per_second": 24.282,
"step": 24899
}
],
"max_steps": 355700,
"num_train_epochs": 100,
"total_flos": 5448027239540928.0,
"trial_name": null,
"trial_params": null
}
|