End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +769 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 17.86,
|
| 3 |
+
"total_flos": 5.536126404560683e+18,
|
| 4 |
+
"train_loss": 1.1784635154149865,
|
| 5 |
+
"train_runtime": 5483.2083,
|
| 6 |
+
"train_samples_per_second": 13.131,
|
| 7 |
+
"train_steps_per_second": 0.102
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 17.86,
|
| 3 |
+
"total_flos": 5.536126404560683e+18,
|
| 4 |
+
"train_loss": 1.1784635154149865,
|
| 5 |
+
"train_runtime": 5483.2083,
|
| 6 |
+
"train_samples_per_second": 13.131,
|
| 7 |
+
"train_steps_per_second": 0.102
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,769 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 17.856,
|
| 5 |
+
"global_step": 558,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 8.928571428571428e-07,
|
| 13 |
+
"loss": 2.9786,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.26,
|
| 18 |
+
"learning_rate": 7.142857142857143e-06,
|
| 19 |
+
"loss": 3.0172,
|
| 20 |
+
"step": 8
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.51,
|
| 24 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 25 |
+
"loss": 2.9016,
|
| 26 |
+
"step": 16
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.77,
|
| 30 |
+
"learning_rate": 2.1428571428571428e-05,
|
| 31 |
+
"loss": 2.7266,
|
| 32 |
+
"step": 24
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.99,
|
| 36 |
+
"eval_Macro F1": 0.18274435256625565,
|
| 37 |
+
"eval_Macro Precision": 0.22464899203701116,
|
| 38 |
+
"eval_Macro Recall": 0.21014375581515982,
|
| 39 |
+
"eval_Micro F1": 0.208,
|
| 40 |
+
"eval_Micro Precision": 0.208,
|
| 41 |
+
"eval_Micro Recall": 0.208,
|
| 42 |
+
"eval_Weighted F1": 0.18112534226726865,
|
| 43 |
+
"eval_Weighted Precision": 0.21432408746391318,
|
| 44 |
+
"eval_Weighted Recall": 0.208,
|
| 45 |
+
"eval_accuracy": 0.208,
|
| 46 |
+
"eval_loss": 2.473806381225586,
|
| 47 |
+
"eval_runtime": 340.1389,
|
| 48 |
+
"eval_samples_per_second": 2.94,
|
| 49 |
+
"eval_steps_per_second": 0.094,
|
| 50 |
+
"step": 31
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.02,
|
| 54 |
+
"learning_rate": 2.857142857142857e-05,
|
| 55 |
+
"loss": 2.5835,
|
| 56 |
+
"step": 32
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.28,
|
| 60 |
+
"learning_rate": 3.571428571428572e-05,
|
| 61 |
+
"loss": 2.4181,
|
| 62 |
+
"step": 40
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.54,
|
| 66 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 67 |
+
"loss": 2.2732,
|
| 68 |
+
"step": 48
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.79,
|
| 72 |
+
"learning_rate": 5e-05,
|
| 73 |
+
"loss": 2.171,
|
| 74 |
+
"step": 56
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.98,
|
| 78 |
+
"eval_Macro F1": 0.39250727765144267,
|
| 79 |
+
"eval_Macro Precision": 0.4446397468859132,
|
| 80 |
+
"eval_Macro Recall": 0.42427064875651993,
|
| 81 |
+
"eval_Micro F1": 0.42299999999999993,
|
| 82 |
+
"eval_Micro Precision": 0.423,
|
| 83 |
+
"eval_Micro Recall": 0.423,
|
| 84 |
+
"eval_Weighted F1": 0.39356324128346765,
|
| 85 |
+
"eval_Weighted Precision": 0.45034474867370766,
|
| 86 |
+
"eval_Weighted Recall": 0.423,
|
| 87 |
+
"eval_accuracy": 0.423,
|
| 88 |
+
"eval_loss": 1.8510247468948364,
|
| 89 |
+
"eval_runtime": 23.3293,
|
| 90 |
+
"eval_samples_per_second": 42.864,
|
| 91 |
+
"eval_steps_per_second": 1.372,
|
| 92 |
+
"step": 62
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.05,
|
| 96 |
+
"learning_rate": 4.9203187250996016e-05,
|
| 97 |
+
"loss": 2.0057,
|
| 98 |
+
"step": 64
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.3,
|
| 102 |
+
"learning_rate": 4.840637450199204e-05,
|
| 103 |
+
"loss": 1.8883,
|
| 104 |
+
"step": 72
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.56,
|
| 108 |
+
"learning_rate": 4.760956175298805e-05,
|
| 109 |
+
"loss": 1.7538,
|
| 110 |
+
"step": 80
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.82,
|
| 114 |
+
"learning_rate": 4.6812749003984064e-05,
|
| 115 |
+
"loss": 1.6525,
|
| 116 |
+
"step": 88
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.98,
|
| 120 |
+
"eval_Macro F1": 0.5854998981328875,
|
| 121 |
+
"eval_Macro Precision": 0.6283041062692261,
|
| 122 |
+
"eval_Macro Recall": 0.6124154907646651,
|
| 123 |
+
"eval_Micro F1": 0.61,
|
| 124 |
+
"eval_Micro Precision": 0.61,
|
| 125 |
+
"eval_Micro Recall": 0.61,
|
| 126 |
+
"eval_Weighted F1": 0.5883778569595041,
|
| 127 |
+
"eval_Weighted Precision": 0.6376755054054996,
|
| 128 |
+
"eval_Weighted Recall": 0.61,
|
| 129 |
+
"eval_accuracy": 0.61,
|
| 130 |
+
"eval_loss": 1.2633185386657715,
|
| 131 |
+
"eval_runtime": 23.4866,
|
| 132 |
+
"eval_samples_per_second": 42.577,
|
| 133 |
+
"eval_steps_per_second": 1.362,
|
| 134 |
+
"step": 93
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 3.07,
|
| 138 |
+
"learning_rate": 4.601593625498008e-05,
|
| 139 |
+
"loss": 1.4741,
|
| 140 |
+
"step": 96
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 3.33,
|
| 144 |
+
"learning_rate": 4.52191235059761e-05,
|
| 145 |
+
"loss": 1.4995,
|
| 146 |
+
"step": 104
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 3.58,
|
| 150 |
+
"learning_rate": 4.442231075697211e-05,
|
| 151 |
+
"loss": 1.3476,
|
| 152 |
+
"step": 112
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.84,
|
| 156 |
+
"learning_rate": 4.362549800796813e-05,
|
| 157 |
+
"loss": 1.346,
|
| 158 |
+
"step": 120
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 4.0,
|
| 162 |
+
"eval_Macro F1": 0.6991540885965197,
|
| 163 |
+
"eval_Macro Precision": 0.7033970309397422,
|
| 164 |
+
"eval_Macro Recall": 0.705813786350264,
|
| 165 |
+
"eval_Micro F1": 0.706,
|
| 166 |
+
"eval_Micro Precision": 0.706,
|
| 167 |
+
"eval_Micro Recall": 0.706,
|
| 168 |
+
"eval_Weighted F1": 0.7023066954415087,
|
| 169 |
+
"eval_Weighted Precision": 0.7095418750091215,
|
| 170 |
+
"eval_Weighted Recall": 0.706,
|
| 171 |
+
"eval_accuracy": 0.706,
|
| 172 |
+
"eval_loss": 1.025865077972412,
|
| 173 |
+
"eval_runtime": 25.2258,
|
| 174 |
+
"eval_samples_per_second": 39.642,
|
| 175 |
+
"eval_steps_per_second": 1.269,
|
| 176 |
+
"step": 125
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 4.1,
|
| 180 |
+
"learning_rate": 4.2828685258964146e-05,
|
| 181 |
+
"loss": 1.361,
|
| 182 |
+
"step": 128
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 4.35,
|
| 186 |
+
"learning_rate": 4.203187250996016e-05,
|
| 187 |
+
"loss": 1.2724,
|
| 188 |
+
"step": 136
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 4.61,
|
| 192 |
+
"learning_rate": 4.123505976095618e-05,
|
| 193 |
+
"loss": 1.2634,
|
| 194 |
+
"step": 144
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 4.86,
|
| 198 |
+
"learning_rate": 4.043824701195219e-05,
|
| 199 |
+
"loss": 1.253,
|
| 200 |
+
"step": 152
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 4.99,
|
| 204 |
+
"eval_Macro F1": 0.7239315752163233,
|
| 205 |
+
"eval_Macro Precision": 0.7261038012066161,
|
| 206 |
+
"eval_Macro Recall": 0.7290773391581917,
|
| 207 |
+
"eval_Micro F1": 0.729,
|
| 208 |
+
"eval_Micro Precision": 0.729,
|
| 209 |
+
"eval_Micro Recall": 0.729,
|
| 210 |
+
"eval_Weighted F1": 0.7276898829930567,
|
| 211 |
+
"eval_Weighted Precision": 0.7340103739336716,
|
| 212 |
+
"eval_Weighted Recall": 0.729,
|
| 213 |
+
"eval_accuracy": 0.729,
|
| 214 |
+
"eval_loss": 0.9180329442024231,
|
| 215 |
+
"eval_runtime": 24.244,
|
| 216 |
+
"eval_samples_per_second": 41.247,
|
| 217 |
+
"eval_steps_per_second": 1.32,
|
| 218 |
+
"step": 156
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 5.12,
|
| 222 |
+
"learning_rate": 3.964143426294821e-05,
|
| 223 |
+
"loss": 1.1127,
|
| 224 |
+
"step": 160
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 5.38,
|
| 228 |
+
"learning_rate": 3.884462151394422e-05,
|
| 229 |
+
"loss": 1.2072,
|
| 230 |
+
"step": 168
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 5.63,
|
| 234 |
+
"learning_rate": 3.804780876494024e-05,
|
| 235 |
+
"loss": 1.1051,
|
| 236 |
+
"step": 176
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 5.89,
|
| 240 |
+
"learning_rate": 3.7250996015936256e-05,
|
| 241 |
+
"loss": 1.0975,
|
| 242 |
+
"step": 184
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 5.98,
|
| 246 |
+
"eval_Macro F1": 0.7437283226344332,
|
| 247 |
+
"eval_Macro Precision": 0.7525965488125351,
|
| 248 |
+
"eval_Macro Recall": 0.7471731443855207,
|
| 249 |
+
"eval_Micro F1": 0.747,
|
| 250 |
+
"eval_Micro Precision": 0.747,
|
| 251 |
+
"eval_Micro Recall": 0.747,
|
| 252 |
+
"eval_Weighted F1": 0.7479974803294792,
|
| 253 |
+
"eval_Weighted Precision": 0.7608663358741853,
|
| 254 |
+
"eval_Weighted Recall": 0.747,
|
| 255 |
+
"eval_accuracy": 0.747,
|
| 256 |
+
"eval_loss": 0.8858795166015625,
|
| 257 |
+
"eval_runtime": 24.5565,
|
| 258 |
+
"eval_samples_per_second": 40.722,
|
| 259 |
+
"eval_steps_per_second": 1.303,
|
| 260 |
+
"step": 187
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 6.14,
|
| 264 |
+
"learning_rate": 3.6454183266932277e-05,
|
| 265 |
+
"loss": 1.0922,
|
| 266 |
+
"step": 192
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 6.4,
|
| 270 |
+
"learning_rate": 3.565737051792829e-05,
|
| 271 |
+
"loss": 1.0797,
|
| 272 |
+
"step": 200
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 6.66,
|
| 276 |
+
"learning_rate": 3.4860557768924304e-05,
|
| 277 |
+
"loss": 1.0066,
|
| 278 |
+
"step": 208
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 6.91,
|
| 282 |
+
"learning_rate": 3.406374501992032e-05,
|
| 283 |
+
"loss": 1.1122,
|
| 284 |
+
"step": 216
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 6.98,
|
| 288 |
+
"eval_Macro F1": 0.7577762006111012,
|
| 289 |
+
"eval_Macro Precision": 0.7726630864911376,
|
| 290 |
+
"eval_Macro Recall": 0.7594437988791525,
|
| 291 |
+
"eval_Micro F1": 0.76,
|
| 292 |
+
"eval_Micro Precision": 0.76,
|
| 293 |
+
"eval_Micro Recall": 0.76,
|
| 294 |
+
"eval_Weighted F1": 0.7606134776349917,
|
| 295 |
+
"eval_Weighted Precision": 0.7772442524935343,
|
| 296 |
+
"eval_Weighted Recall": 0.76,
|
| 297 |
+
"eval_accuracy": 0.76,
|
| 298 |
+
"eval_loss": 0.8269779086112976,
|
| 299 |
+
"eval_runtime": 24.3399,
|
| 300 |
+
"eval_samples_per_second": 41.085,
|
| 301 |
+
"eval_steps_per_second": 1.315,
|
| 302 |
+
"step": 218
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 7.17,
|
| 306 |
+
"learning_rate": 3.326693227091633e-05,
|
| 307 |
+
"loss": 0.988,
|
| 308 |
+
"step": 224
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 7.42,
|
| 312 |
+
"learning_rate": 3.247011952191235e-05,
|
| 313 |
+
"loss": 1.0301,
|
| 314 |
+
"step": 232
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 7.68,
|
| 318 |
+
"learning_rate": 3.1673306772908366e-05,
|
| 319 |
+
"loss": 0.9724,
|
| 320 |
+
"step": 240
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 7.94,
|
| 324 |
+
"learning_rate": 3.0876494023904386e-05,
|
| 325 |
+
"loss": 1.0365,
|
| 326 |
+
"step": 248
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 8.0,
|
| 330 |
+
"eval_Macro F1": 0.7730173451661722,
|
| 331 |
+
"eval_Macro Precision": 0.7919871344293006,
|
| 332 |
+
"eval_Macro Recall": 0.7734992733449892,
|
| 333 |
+
"eval_Micro F1": 0.775,
|
| 334 |
+
"eval_Micro Precision": 0.775,
|
| 335 |
+
"eval_Micro Recall": 0.775,
|
| 336 |
+
"eval_Weighted F1": 0.7759067917731501,
|
| 337 |
+
"eval_Weighted Precision": 0.7957122736768526,
|
| 338 |
+
"eval_Weighted Recall": 0.775,
|
| 339 |
+
"eval_accuracy": 0.775,
|
| 340 |
+
"eval_loss": 0.7806075215339661,
|
| 341 |
+
"eval_runtime": 23.5653,
|
| 342 |
+
"eval_samples_per_second": 42.435,
|
| 343 |
+
"eval_steps_per_second": 1.358,
|
| 344 |
+
"step": 250
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 8.19,
|
| 348 |
+
"learning_rate": 3.00796812749004e-05,
|
| 349 |
+
"loss": 0.9482,
|
| 350 |
+
"step": 256
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 8.45,
|
| 354 |
+
"learning_rate": 2.9282868525896417e-05,
|
| 355 |
+
"loss": 0.9364,
|
| 356 |
+
"step": 264
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 8.7,
|
| 360 |
+
"learning_rate": 2.8486055776892434e-05,
|
| 361 |
+
"loss": 0.9417,
|
| 362 |
+
"step": 272
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 8.96,
|
| 366 |
+
"learning_rate": 2.7689243027888445e-05,
|
| 367 |
+
"loss": 1.004,
|
| 368 |
+
"step": 280
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 8.99,
|
| 372 |
+
"eval_Macro F1": 0.7956663948657638,
|
| 373 |
+
"eval_Macro Precision": 0.8150981558104353,
|
| 374 |
+
"eval_Macro Recall": 0.7955573765342054,
|
| 375 |
+
"eval_Micro F1": 0.796,
|
| 376 |
+
"eval_Micro Precision": 0.796,
|
| 377 |
+
"eval_Micro Recall": 0.796,
|
| 378 |
+
"eval_Weighted F1": 0.7977477337842563,
|
| 379 |
+
"eval_Weighted Precision": 0.8193174046095921,
|
| 380 |
+
"eval_Weighted Recall": 0.796,
|
| 381 |
+
"eval_accuracy": 0.796,
|
| 382 |
+
"eval_loss": 0.7471871972084045,
|
| 383 |
+
"eval_runtime": 24.2779,
|
| 384 |
+
"eval_samples_per_second": 41.19,
|
| 385 |
+
"eval_steps_per_second": 1.318,
|
| 386 |
+
"step": 281
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 9.22,
|
| 390 |
+
"learning_rate": 2.6892430278884462e-05,
|
| 391 |
+
"loss": 0.8964,
|
| 392 |
+
"step": 288
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 9.47,
|
| 396 |
+
"learning_rate": 2.609561752988048e-05,
|
| 397 |
+
"loss": 0.9098,
|
| 398 |
+
"step": 296
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 9.73,
|
| 402 |
+
"learning_rate": 2.5298804780876496e-05,
|
| 403 |
+
"loss": 0.9576,
|
| 404 |
+
"step": 304
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 9.98,
|
| 408 |
+
"learning_rate": 2.4501992031872513e-05,
|
| 409 |
+
"loss": 0.9278,
|
| 410 |
+
"step": 312
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 9.98,
|
| 414 |
+
"eval_Macro F1": 0.7956928280629123,
|
| 415 |
+
"eval_Macro Precision": 0.8114507473411248,
|
| 416 |
+
"eval_Macro Recall": 0.7953090431389529,
|
| 417 |
+
"eval_Micro F1": 0.795,
|
| 418 |
+
"eval_Micro Precision": 0.795,
|
| 419 |
+
"eval_Micro Recall": 0.795,
|
| 420 |
+
"eval_Weighted F1": 0.7974177696936208,
|
| 421 |
+
"eval_Weighted Precision": 0.8157219938612603,
|
| 422 |
+
"eval_Weighted Recall": 0.795,
|
| 423 |
+
"eval_accuracy": 0.795,
|
| 424 |
+
"eval_loss": 0.7296148538589478,
|
| 425 |
+
"eval_runtime": 24.012,
|
| 426 |
+
"eval_samples_per_second": 41.646,
|
| 427 |
+
"eval_steps_per_second": 1.333,
|
| 428 |
+
"step": 312
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 10.24,
|
| 432 |
+
"learning_rate": 2.3705179282868527e-05,
|
| 433 |
+
"loss": 0.8623,
|
| 434 |
+
"step": 320
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 10.5,
|
| 438 |
+
"learning_rate": 2.290836653386454e-05,
|
| 439 |
+
"loss": 0.9,
|
| 440 |
+
"step": 328
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 10.75,
|
| 444 |
+
"learning_rate": 2.2111553784860558e-05,
|
| 445 |
+
"loss": 0.8767,
|
| 446 |
+
"step": 336
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 10.98,
|
| 450 |
+
"eval_Macro F1": 0.8077597575155505,
|
| 451 |
+
"eval_Macro Precision": 0.8135983545887402,
|
| 452 |
+
"eval_Macro Recall": 0.8090640618814349,
|
| 453 |
+
"eval_Micro F1": 0.809,
|
| 454 |
+
"eval_Micro Precision": 0.809,
|
| 455 |
+
"eval_Micro Recall": 0.809,
|
| 456 |
+
"eval_Weighted F1": 0.8101031910520137,
|
| 457 |
+
"eval_Weighted Precision": 0.8181958157506283,
|
| 458 |
+
"eval_Weighted Recall": 0.809,
|
| 459 |
+
"eval_accuracy": 0.809,
|
| 460 |
+
"eval_loss": 0.7256603240966797,
|
| 461 |
+
"eval_runtime": 23.8159,
|
| 462 |
+
"eval_samples_per_second": 41.989,
|
| 463 |
+
"eval_steps_per_second": 1.344,
|
| 464 |
+
"step": 343
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 11.01,
|
| 468 |
+
"learning_rate": 2.1314741035856575e-05,
|
| 469 |
+
"loss": 0.9239,
|
| 470 |
+
"step": 344
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 11.26,
|
| 474 |
+
"learning_rate": 2.0517928286852592e-05,
|
| 475 |
+
"loss": 0.8971,
|
| 476 |
+
"step": 352
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 11.52,
|
| 480 |
+
"learning_rate": 1.9721115537848606e-05,
|
| 481 |
+
"loss": 0.9387,
|
| 482 |
+
"step": 360
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 11.78,
|
| 486 |
+
"learning_rate": 1.8924302788844623e-05,
|
| 487 |
+
"loss": 0.8656,
|
| 488 |
+
"step": 368
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 12.0,
|
| 492 |
+
"eval_Macro F1": 0.8106317572025369,
|
| 493 |
+
"eval_Macro Precision": 0.8164411111931356,
|
| 494 |
+
"eval_Macro Recall": 0.812159053433045,
|
| 495 |
+
"eval_Micro F1": 0.8140000000000001,
|
| 496 |
+
"eval_Micro Precision": 0.814,
|
| 497 |
+
"eval_Micro Recall": 0.814,
|
| 498 |
+
"eval_Weighted F1": 0.813675273019787,
|
| 499 |
+
"eval_Weighted Precision": 0.8206734023674667,
|
| 500 |
+
"eval_Weighted Recall": 0.814,
|
| 501 |
+
"eval_accuracy": 0.814,
|
| 502 |
+
"eval_loss": 0.687544584274292,
|
| 503 |
+
"eval_runtime": 24.187,
|
| 504 |
+
"eval_samples_per_second": 41.344,
|
| 505 |
+
"eval_steps_per_second": 1.323,
|
| 506 |
+
"step": 375
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 12.03,
|
| 510 |
+
"learning_rate": 1.812749003984064e-05,
|
| 511 |
+
"loss": 0.8568,
|
| 512 |
+
"step": 376
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 12.29,
|
| 516 |
+
"learning_rate": 1.7330677290836657e-05,
|
| 517 |
+
"loss": 0.9105,
|
| 518 |
+
"step": 384
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 12.54,
|
| 522 |
+
"learning_rate": 1.653386454183267e-05,
|
| 523 |
+
"loss": 0.7687,
|
| 524 |
+
"step": 392
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 12.8,
|
| 528 |
+
"learning_rate": 1.5737051792828685e-05,
|
| 529 |
+
"loss": 0.7905,
|
| 530 |
+
"step": 400
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 12.99,
|
| 534 |
+
"eval_Macro F1": 0.807144557531445,
|
| 535 |
+
"eval_Macro Precision": 0.8145226206650988,
|
| 536 |
+
"eval_Macro Recall": 0.8067641953560594,
|
| 537 |
+
"eval_Micro F1": 0.808,
|
| 538 |
+
"eval_Micro Precision": 0.808,
|
| 539 |
+
"eval_Micro Recall": 0.808,
|
| 540 |
+
"eval_Weighted F1": 0.8093388838073848,
|
| 541 |
+
"eval_Weighted Precision": 0.8181875581570741,
|
| 542 |
+
"eval_Weighted Recall": 0.808,
|
| 543 |
+
"eval_accuracy": 0.808,
|
| 544 |
+
"eval_loss": 0.7060463428497314,
|
| 545 |
+
"eval_runtime": 23.4383,
|
| 546 |
+
"eval_samples_per_second": 42.665,
|
| 547 |
+
"eval_steps_per_second": 1.365,
|
| 548 |
+
"step": 406
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 13.06,
|
| 552 |
+
"learning_rate": 1.4940239043824702e-05,
|
| 553 |
+
"loss": 0.8453,
|
| 554 |
+
"step": 408
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 13.31,
|
| 558 |
+
"learning_rate": 1.4143426294820719e-05,
|
| 559 |
+
"loss": 0.7926,
|
| 560 |
+
"step": 416
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 13.57,
|
| 564 |
+
"learning_rate": 1.3346613545816733e-05,
|
| 565 |
+
"loss": 0.8721,
|
| 566 |
+
"step": 424
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 13.82,
|
| 570 |
+
"learning_rate": 1.254980079681275e-05,
|
| 571 |
+
"loss": 0.8804,
|
| 572 |
+
"step": 432
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 13.98,
|
| 576 |
+
"eval_Macro F1": 0.8182926573190057,
|
| 577 |
+
"eval_Macro Precision": 0.8215050680984892,
|
| 578 |
+
"eval_Macro Recall": 0.8183483781309105,
|
| 579 |
+
"eval_Micro F1": 0.82,
|
| 580 |
+
"eval_Micro Precision": 0.82,
|
| 581 |
+
"eval_Micro Recall": 0.82,
|
| 582 |
+
"eval_Weighted F1": 0.8213528638428045,
|
| 583 |
+
"eval_Weighted Precision": 0.8260224129157536,
|
| 584 |
+
"eval_Weighted Recall": 0.82,
|
| 585 |
+
"eval_accuracy": 0.82,
|
| 586 |
+
"eval_loss": 0.6848881244659424,
|
| 587 |
+
"eval_runtime": 24.2686,
|
| 588 |
+
"eval_samples_per_second": 41.206,
|
| 589 |
+
"eval_steps_per_second": 1.319,
|
| 590 |
+
"step": 437
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 14.08,
|
| 594 |
+
"learning_rate": 1.1752988047808767e-05,
|
| 595 |
+
"loss": 0.8041,
|
| 596 |
+
"step": 440
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 14.34,
|
| 600 |
+
"learning_rate": 1.095617529880478e-05,
|
| 601 |
+
"loss": 0.8291,
|
| 602 |
+
"step": 448
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 14.59,
|
| 606 |
+
"learning_rate": 1.0159362549800798e-05,
|
| 607 |
+
"loss": 0.8109,
|
| 608 |
+
"step": 456
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 14.85,
|
| 612 |
+
"learning_rate": 9.362549800796813e-06,
|
| 613 |
+
"loss": 0.8265,
|
| 614 |
+
"step": 464
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 14.98,
|
| 618 |
+
"eval_Macro F1": 0.814299562240979,
|
| 619 |
+
"eval_Macro Precision": 0.8205669101031257,
|
| 620 |
+
"eval_Macro Recall": 0.8141933591904861,
|
| 621 |
+
"eval_Micro F1": 0.816,
|
| 622 |
+
"eval_Micro Precision": 0.816,
|
| 623 |
+
"eval_Micro Recall": 0.816,
|
| 624 |
+
"eval_Weighted F1": 0.8171172793618807,
|
| 625 |
+
"eval_Weighted Precision": 0.8242012281620977,
|
| 626 |
+
"eval_Weighted Recall": 0.816,
|
| 627 |
+
"eval_accuracy": 0.816,
|
| 628 |
+
"eval_loss": 0.6820688247680664,
|
| 629 |
+
"eval_runtime": 24.1434,
|
| 630 |
+
"eval_samples_per_second": 41.419,
|
| 631 |
+
"eval_steps_per_second": 1.325,
|
| 632 |
+
"step": 468
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 15.1,
|
| 636 |
+
"learning_rate": 8.565737051792829e-06,
|
| 637 |
+
"loss": 0.7845,
|
| 638 |
+
"step": 472
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 15.36,
|
| 642 |
+
"learning_rate": 7.768924302788846e-06,
|
| 643 |
+
"loss": 0.8545,
|
| 644 |
+
"step": 480
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 15.62,
|
| 648 |
+
"learning_rate": 6.97211155378486e-06,
|
| 649 |
+
"loss": 0.7685,
|
| 650 |
+
"step": 488
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 15.87,
|
| 654 |
+
"learning_rate": 6.175298804780877e-06,
|
| 655 |
+
"loss": 0.7929,
|
| 656 |
+
"step": 496
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 16.0,
|
| 660 |
+
"eval_Macro F1": 0.8151613063095204,
|
| 661 |
+
"eval_Macro Precision": 0.818634892770315,
|
| 662 |
+
"eval_Macro Recall": 0.8167488060127654,
|
| 663 |
+
"eval_Micro F1": 0.818,
|
| 664 |
+
"eval_Micro Precision": 0.818,
|
| 665 |
+
"eval_Micro Recall": 0.818,
|
| 666 |
+
"eval_Weighted F1": 0.8184268497331145,
|
| 667 |
+
"eval_Weighted Precision": 0.8239745058078853,
|
| 668 |
+
"eval_Weighted Recall": 0.818,
|
| 669 |
+
"eval_accuracy": 0.818,
|
| 670 |
+
"eval_loss": 0.6877326369285583,
|
| 671 |
+
"eval_runtime": 23.4065,
|
| 672 |
+
"eval_samples_per_second": 42.723,
|
| 673 |
+
"eval_steps_per_second": 1.367,
|
| 674 |
+
"step": 500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 16.13,
|
| 678 |
+
"learning_rate": 5.378486055776893e-06,
|
| 679 |
+
"loss": 0.8338,
|
| 680 |
+
"step": 504
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 16.38,
|
| 684 |
+
"learning_rate": 4.581673306772908e-06,
|
| 685 |
+
"loss": 0.8154,
|
| 686 |
+
"step": 512
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 16.64,
|
| 690 |
+
"learning_rate": 3.7848605577689246e-06,
|
| 691 |
+
"loss": 0.8054,
|
| 692 |
+
"step": 520
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 16.9,
|
| 696 |
+
"learning_rate": 2.9880478087649404e-06,
|
| 697 |
+
"loss": 0.7993,
|
| 698 |
+
"step": 528
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 16.99,
|
| 702 |
+
"eval_Macro F1": 0.8233893661888394,
|
| 703 |
+
"eval_Macro Precision": 0.8281793690152945,
|
| 704 |
+
"eval_Macro Recall": 0.822655931109436,
|
| 705 |
+
"eval_Micro F1": 0.825,
|
| 706 |
+
"eval_Micro Precision": 0.825,
|
| 707 |
+
"eval_Micro Recall": 0.825,
|
| 708 |
+
"eval_Weighted F1": 0.8258766455781327,
|
| 709 |
+
"eval_Weighted Precision": 0.8305915821251276,
|
| 710 |
+
"eval_Weighted Recall": 0.825,
|
| 711 |
+
"eval_accuracy": 0.825,
|
| 712 |
+
"eval_loss": 0.6717957854270935,
|
| 713 |
+
"eval_runtime": 24.415,
|
| 714 |
+
"eval_samples_per_second": 40.958,
|
| 715 |
+
"eval_steps_per_second": 1.311,
|
| 716 |
+
"step": 531
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 17.15,
|
| 720 |
+
"learning_rate": 2.1912350597609563e-06,
|
| 721 |
+
"loss": 0.7572,
|
| 722 |
+
"step": 536
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 17.41,
|
| 726 |
+
"learning_rate": 1.3944223107569721e-06,
|
| 727 |
+
"loss": 0.8022,
|
| 728 |
+
"step": 544
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 17.66,
|
| 732 |
+
"learning_rate": 5.976095617529881e-07,
|
| 733 |
+
"loss": 0.7954,
|
| 734 |
+
"step": 552
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 17.86,
|
| 738 |
+
"eval_Macro F1": 0.8242217019056312,
|
| 739 |
+
"eval_Macro Precision": 0.8293094252297472,
|
| 740 |
+
"eval_Macro Recall": 0.8236754312981294,
|
| 741 |
+
"eval_Micro F1": 0.826,
|
| 742 |
+
"eval_Micro Precision": 0.826,
|
| 743 |
+
"eval_Micro Recall": 0.826,
|
| 744 |
+
"eval_Weighted F1": 0.827162008102242,
|
| 745 |
+
"eval_Weighted Precision": 0.8326500761444383,
|
| 746 |
+
"eval_Weighted Recall": 0.826,
|
| 747 |
+
"eval_accuracy": 0.826,
|
| 748 |
+
"eval_loss": 0.6715443134307861,
|
| 749 |
+
"eval_runtime": 24.1692,
|
| 750 |
+
"eval_samples_per_second": 41.375,
|
| 751 |
+
"eval_steps_per_second": 1.324,
|
| 752 |
+
"step": 558
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 17.86,
|
| 756 |
+
"step": 558,
|
| 757 |
+
"total_flos": 5.536126404560683e+18,
|
| 758 |
+
"train_loss": 1.1784635154149865,
|
| 759 |
+
"train_runtime": 5483.2083,
|
| 760 |
+
"train_samples_per_second": 13.131,
|
| 761 |
+
"train_steps_per_second": 0.102
|
| 762 |
+
}
|
| 763 |
+
],
|
| 764 |
+
"max_steps": 558,
|
| 765 |
+
"num_train_epochs": 18,
|
| 766 |
+
"total_flos": 5.536126404560683e+18,
|
| 767 |
+
"trial_name": null,
|
| 768 |
+
"trial_params": null
|
| 769 |
+
}
|