Training in progress, epoch 1
Browse files- all_results.json +11 -11
- eval_results.json +6 -6
- pytorch_model.bin +1 -1
- train_results.json +6 -6
- trainer_state.json +250 -64
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,15 +1,15 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 1.
|
| 5 |
-
"eval_runtime": 0.
|
| 6 |
"eval_samples": 500,
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second":
|
| 9 |
-
"total_flos":
|
| 10 |
-
"train_loss": 1.
|
| 11 |
-
"train_runtime":
|
| 12 |
"train_samples": 4000,
|
| 13 |
-
"train_samples_per_second":
|
| 14 |
-
"train_steps_per_second":
|
| 15 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.27000001072883606,
|
| 4 |
+
"eval_loss": 1.60148286819458,
|
| 5 |
+
"eval_runtime": 0.3331,
|
| 6 |
"eval_samples": 500,
|
| 7 |
+
"eval_samples_per_second": 1501.132,
|
| 8 |
+
"eval_steps_per_second": 24.018,
|
| 9 |
+
"total_flos": 22540141814400.0,
|
| 10 |
+
"train_loss": 1.6052362956697979,
|
| 11 |
+
"train_runtime": 55.5553,
|
| 12 |
"train_samples": 4000,
|
| 13 |
+
"train_samples_per_second": 720.003,
|
| 14 |
+
"train_steps_per_second": 11.34
|
| 15 |
}
|
eval_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 1.
|
| 5 |
-
"eval_runtime": 0.
|
| 6 |
"eval_samples": 500,
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second":
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.27000001072883606,
|
| 4 |
+
"eval_loss": 1.60148286819458,
|
| 5 |
+
"eval_runtime": 0.3331,
|
| 6 |
"eval_samples": 500,
|
| 7 |
+
"eval_samples_per_second": 1501.132,
|
| 8 |
+
"eval_steps_per_second": 24.018
|
| 9 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 12755881
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0096f1a45fa31f275d0de57dd202bc75ce557882075f303de9bcaf314c72d4e
|
| 3 |
size 12755881
|
train_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 1.
|
| 5 |
-
"train_runtime":
|
| 6 |
"train_samples": 4000,
|
| 7 |
-
"train_samples_per_second":
|
| 8 |
-
"train_steps_per_second":
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 22540141814400.0,
|
| 4 |
+
"train_loss": 1.6052362956697979,
|
| 5 |
+
"train_runtime": 55.5553,
|
| 6 |
"train_samples": 4000,
|
| 7 |
+
"train_samples_per_second": 720.003,
|
| 8 |
+
"train_steps_per_second": 11.34
|
| 9 |
}
|
trainer_state.json
CHANGED
|
@@ -1,115 +1,301 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "chinese_roberta_L-2_H-128-finetuned-MC-hyper/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 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.
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss": 1.
|
| 14 |
"step": 20
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch": 0.
|
| 18 |
-
"learning_rate":
|
| 19 |
-
"loss": 1.
|
| 20 |
"step": 40
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"epoch": 0.
|
| 24 |
-
"learning_rate":
|
| 25 |
-
"loss": 1.
|
| 26 |
"step": 60
|
| 27 |
},
|
| 28 |
{
|
| 29 |
-
"epoch": 0
|
| 30 |
-
"
|
| 31 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
"step": 80
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch":
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss": 1.
|
| 38 |
"step": 100
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch":
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 1.
|
| 44 |
"step": 120
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch":
|
| 48 |
-
"eval_accuracy": 0.
|
| 49 |
-
"eval_loss": 1.
|
| 50 |
-
"eval_runtime": 0.
|
| 51 |
-
"eval_samples_per_second":
|
| 52 |
-
"eval_steps_per_second":
|
| 53 |
-
"step":
|
| 54 |
},
|
| 55 |
{
|
| 56 |
-
"epoch":
|
| 57 |
-
"learning_rate":
|
| 58 |
-
"loss": 1.
|
| 59 |
"step": 140
|
| 60 |
},
|
| 61 |
{
|
| 62 |
-
"epoch":
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss": 1.
|
| 65 |
"step": 160
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch":
|
| 69 |
-
"learning_rate":
|
| 70 |
-
"loss": 1.
|
| 71 |
"step": 180
|
| 72 |
},
|
| 73 |
{
|
| 74 |
-
"epoch":
|
| 75 |
-
"
|
| 76 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
"step": 200
|
| 78 |
},
|
| 79 |
{
|
| 80 |
-
"epoch":
|
| 81 |
-
"learning_rate":
|
| 82 |
-
"loss": 1.
|
| 83 |
"step": 220
|
| 84 |
},
|
| 85 |
{
|
| 86 |
-
"epoch":
|
| 87 |
-
"learning_rate":
|
| 88 |
-
"loss": 1.
|
| 89 |
"step": 240
|
| 90 |
},
|
| 91 |
{
|
| 92 |
-
"epoch":
|
| 93 |
-
"eval_accuracy": 0.
|
| 94 |
-
"eval_loss": 1.
|
| 95 |
-
"eval_runtime": 0.
|
| 96 |
-
"eval_samples_per_second":
|
| 97 |
-
"eval_steps_per_second":
|
| 98 |
-
"step":
|
| 99 |
},
|
| 100 |
{
|
| 101 |
-
"epoch":
|
| 102 |
-
"
|
| 103 |
-
"
|
| 104 |
-
"
|
| 105 |
-
|
| 106 |
-
|
| 107 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 108 |
}
|
| 109 |
],
|
| 110 |
-
"max_steps":
|
| 111 |
-
"num_train_epochs":
|
| 112 |
-
"total_flos":
|
| 113 |
"trial_name": null,
|
| 114 |
"trial_params": null
|
| 115 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.60148286819458,
|
| 3 |
+
"best_model_checkpoint": "chinese_roberta_L-2_H-128-finetuned-MC-hyper/checkpoint-630",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 630,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.32,
|
| 12 |
+
"learning_rate": 9.682539682539683e-06,
|
| 13 |
+
"loss": 1.6084,
|
| 14 |
"step": 20
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 0.63,
|
| 18 |
+
"learning_rate": 9.365079365079366e-06,
|
| 19 |
+
"loss": 1.6085,
|
| 20 |
"step": 40
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 0.95,
|
| 24 |
+
"learning_rate": 9.047619047619049e-06,
|
| 25 |
+
"loss": 1.6093,
|
| 26 |
"step": 60
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 1.0,
|
| 30 |
+
"eval_accuracy": 0.27799999713897705,
|
| 31 |
+
"eval_loss": 1.6079264879226685,
|
| 32 |
+
"eval_runtime": 0.3306,
|
| 33 |
+
"eval_samples_per_second": 1512.408,
|
| 34 |
+
"eval_steps_per_second": 24.199,
|
| 35 |
+
"step": 63
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 1.27,
|
| 39 |
+
"learning_rate": 8.730158730158731e-06,
|
| 40 |
+
"loss": 1.6092,
|
| 41 |
"step": 80
|
| 42 |
},
|
| 43 |
{
|
| 44 |
+
"epoch": 1.59,
|
| 45 |
+
"learning_rate": 8.412698412698414e-06,
|
| 46 |
+
"loss": 1.6084,
|
| 47 |
"step": 100
|
| 48 |
},
|
| 49 |
{
|
| 50 |
+
"epoch": 1.9,
|
| 51 |
+
"learning_rate": 8.095238095238097e-06,
|
| 52 |
+
"loss": 1.6083,
|
| 53 |
"step": 120
|
| 54 |
},
|
| 55 |
{
|
| 56 |
+
"epoch": 2.0,
|
| 57 |
+
"eval_accuracy": 0.27799999713897705,
|
| 58 |
+
"eval_loss": 1.6071099042892456,
|
| 59 |
+
"eval_runtime": 0.3325,
|
| 60 |
+
"eval_samples_per_second": 1503.597,
|
| 61 |
+
"eval_steps_per_second": 24.058,
|
| 62 |
+
"step": 126
|
| 63 |
},
|
| 64 |
{
|
| 65 |
+
"epoch": 2.22,
|
| 66 |
+
"learning_rate": 7.77777777777778e-06,
|
| 67 |
+
"loss": 1.6073,
|
| 68 |
"step": 140
|
| 69 |
},
|
| 70 |
{
|
| 71 |
+
"epoch": 2.54,
|
| 72 |
+
"learning_rate": 7.460317460317461e-06,
|
| 73 |
+
"loss": 1.6081,
|
| 74 |
"step": 160
|
| 75 |
},
|
| 76 |
{
|
| 77 |
+
"epoch": 2.86,
|
| 78 |
+
"learning_rate": 7.1428571428571436e-06,
|
| 79 |
+
"loss": 1.6077,
|
| 80 |
"step": 180
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 3.0,
|
| 84 |
+
"eval_accuracy": 0.28600001335144043,
|
| 85 |
+
"eval_loss": 1.6063222885131836,
|
| 86 |
+
"eval_runtime": 0.3267,
|
| 87 |
+
"eval_samples_per_second": 1530.439,
|
| 88 |
+
"eval_steps_per_second": 24.487,
|
| 89 |
+
"step": 189
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 3.17,
|
| 93 |
+
"learning_rate": 6.825396825396826e-06,
|
| 94 |
+
"loss": 1.6061,
|
| 95 |
"step": 200
|
| 96 |
},
|
| 97 |
{
|
| 98 |
+
"epoch": 3.49,
|
| 99 |
+
"learning_rate": 6.507936507936509e-06,
|
| 100 |
+
"loss": 1.6081,
|
| 101 |
"step": 220
|
| 102 |
},
|
| 103 |
{
|
| 104 |
+
"epoch": 3.81,
|
| 105 |
+
"learning_rate": 6.1904761904761914e-06,
|
| 106 |
+
"loss": 1.6078,
|
| 107 |
"step": 240
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 4.0,
|
| 111 |
+
"eval_accuracy": 0.2919999957084656,
|
| 112 |
+
"eval_loss": 1.605468511581421,
|
| 113 |
+
"eval_runtime": 0.391,
|
| 114 |
+
"eval_samples_per_second": 1278.612,
|
| 115 |
+
"eval_steps_per_second": 20.458,
|
| 116 |
+
"step": 252
|
| 117 |
},
|
| 118 |
{
|
| 119 |
+
"epoch": 4.13,
|
| 120 |
+
"learning_rate": 5.873015873015874e-06,
|
| 121 |
+
"loss": 1.606,
|
| 122 |
+
"step": 260
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 4.44,
|
| 126 |
+
"learning_rate": 5.555555555555557e-06,
|
| 127 |
+
"loss": 1.6059,
|
| 128 |
+
"step": 280
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 4.76,
|
| 132 |
+
"learning_rate": 5.2380952380952384e-06,
|
| 133 |
+
"loss": 1.6047,
|
| 134 |
+
"step": 300
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 5.0,
|
| 138 |
+
"eval_accuracy": 0.28200000524520874,
|
| 139 |
+
"eval_loss": 1.6045148372650146,
|
| 140 |
+
"eval_runtime": 0.3348,
|
| 141 |
+
"eval_samples_per_second": 1493.284,
|
| 142 |
+
"eval_steps_per_second": 23.893,
|
| 143 |
+
"step": 315
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 5.08,
|
| 147 |
+
"learning_rate": 4.920634920634921e-06,
|
| 148 |
+
"loss": 1.6059,
|
| 149 |
+
"step": 320
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 5.4,
|
| 153 |
+
"learning_rate": 4.603174603174604e-06,
|
| 154 |
+
"loss": 1.6057,
|
| 155 |
+
"step": 340
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 5.71,
|
| 159 |
+
"learning_rate": 4.2857142857142855e-06,
|
| 160 |
+
"loss": 1.6042,
|
| 161 |
+
"step": 360
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 6.0,
|
| 165 |
+
"eval_accuracy": 0.27799999713897705,
|
| 166 |
+
"eval_loss": 1.60362708568573,
|
| 167 |
+
"eval_runtime": 0.3262,
|
| 168 |
+
"eval_samples_per_second": 1532.953,
|
| 169 |
+
"eval_steps_per_second": 24.527,
|
| 170 |
+
"step": 378
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 6.03,
|
| 174 |
+
"learning_rate": 3.968253968253968e-06,
|
| 175 |
+
"loss": 1.6031,
|
| 176 |
+
"step": 380
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 6.35,
|
| 180 |
+
"learning_rate": 3.6507936507936507e-06,
|
| 181 |
+
"loss": 1.6043,
|
| 182 |
+
"step": 400
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 6.67,
|
| 186 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 187 |
+
"loss": 1.604,
|
| 188 |
+
"step": 420
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 6.98,
|
| 192 |
+
"learning_rate": 3.015873015873016e-06,
|
| 193 |
+
"loss": 1.6029,
|
| 194 |
+
"step": 440
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 7.0,
|
| 198 |
+
"eval_accuracy": 0.27399998903274536,
|
| 199 |
+
"eval_loss": 1.6027634143829346,
|
| 200 |
+
"eval_runtime": 0.3276,
|
| 201 |
+
"eval_samples_per_second": 1526.145,
|
| 202 |
+
"eval_steps_per_second": 24.418,
|
| 203 |
+
"step": 441
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 7.3,
|
| 207 |
+
"learning_rate": 2.6984126984126986e-06,
|
| 208 |
+
"loss": 1.6022,
|
| 209 |
+
"step": 460
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 7.62,
|
| 213 |
+
"learning_rate": 2.380952380952381e-06,
|
| 214 |
+
"loss": 1.6041,
|
| 215 |
+
"step": 480
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 7.94,
|
| 219 |
+
"learning_rate": 2.0634920634920634e-06,
|
| 220 |
+
"loss": 1.6007,
|
| 221 |
+
"step": 500
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 8.0,
|
| 225 |
+
"eval_accuracy": 0.27000001072883606,
|
| 226 |
+
"eval_loss": 1.6020437479019165,
|
| 227 |
+
"eval_runtime": 0.3322,
|
| 228 |
+
"eval_samples_per_second": 1505.137,
|
| 229 |
+
"eval_steps_per_second": 24.082,
|
| 230 |
+
"step": 504
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 8.25,
|
| 234 |
+
"learning_rate": 1.746031746031746e-06,
|
| 235 |
+
"loss": 1.6023,
|
| 236 |
+
"step": 520
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 8.57,
|
| 240 |
+
"learning_rate": 1.4285714285714286e-06,
|
| 241 |
+
"loss": 1.6026,
|
| 242 |
+
"step": 540
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 8.89,
|
| 246 |
+
"learning_rate": 1.111111111111111e-06,
|
| 247 |
+
"loss": 1.6015,
|
| 248 |
+
"step": 560
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 9.0,
|
| 252 |
+
"eval_accuracy": 0.27000001072883606,
|
| 253 |
+
"eval_loss": 1.6016141176223755,
|
| 254 |
+
"eval_runtime": 0.3269,
|
| 255 |
+
"eval_samples_per_second": 1529.374,
|
| 256 |
+
"eval_steps_per_second": 24.47,
|
| 257 |
+
"step": 567
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 9.21,
|
| 261 |
+
"learning_rate": 7.936507936507937e-07,
|
| 262 |
+
"loss": 1.6016,
|
| 263 |
+
"step": 580
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 9.52,
|
| 267 |
+
"learning_rate": 4.7619047619047623e-07,
|
| 268 |
+
"loss": 1.6024,
|
| 269 |
+
"step": 600
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 9.84,
|
| 273 |
+
"learning_rate": 1.5873015873015874e-07,
|
| 274 |
+
"loss": 1.6017,
|
| 275 |
+
"step": 620
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 10.0,
|
| 279 |
+
"eval_accuracy": 0.27000001072883606,
|
| 280 |
+
"eval_loss": 1.60148286819458,
|
| 281 |
+
"eval_runtime": 0.3257,
|
| 282 |
+
"eval_samples_per_second": 1535.263,
|
| 283 |
+
"eval_steps_per_second": 24.564,
|
| 284 |
+
"step": 630
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 10.0,
|
| 288 |
+
"step": 630,
|
| 289 |
+
"total_flos": 22540141814400.0,
|
| 290 |
+
"train_loss": 1.6052362956697979,
|
| 291 |
+
"train_runtime": 55.5553,
|
| 292 |
+
"train_samples_per_second": 720.003,
|
| 293 |
+
"train_steps_per_second": 11.34
|
| 294 |
}
|
| 295 |
],
|
| 296 |
+
"max_steps": 630,
|
| 297 |
+
"num_train_epochs": 10,
|
| 298 |
+
"total_flos": 22540141814400.0,
|
| 299 |
"trial_name": null,
|
| 300 |
"trial_params": null
|
| 301 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2799
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:369f79da83f13b5b29eb52d0370d4338999b9bc2fbbcd98395648ddfc7a6d687
|
| 3 |
size 2799
|