End of training
Browse files- all_results.json +15 -0
- eval_results.json +10 -0
- train_results.json +8 -0
- trainer_state.json +517 -0
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.6156604453386092,
|
| 4 |
+
"eval_loss": 2.101821184158325,
|
| 5 |
+
"eval_runtime": 86.7273,
|
| 6 |
+
"eval_samples": 541,
|
| 7 |
+
"eval_samples_per_second": 6.238,
|
| 8 |
+
"eval_steps_per_second": 3.125,
|
| 9 |
+
"perplexity": 8.181055562487236,
|
| 10 |
+
"train_loss": 1.970301656346572,
|
| 11 |
+
"train_runtime": 9467.2073,
|
| 12 |
+
"train_samples": 4881,
|
| 13 |
+
"train_samples_per_second": 2.062,
|
| 14 |
+
"train_steps_per_second": 0.016
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.6156604453386092,
|
| 4 |
+
"eval_loss": 2.101821184158325,
|
| 5 |
+
"eval_runtime": 86.7273,
|
| 6 |
+
"eval_samples": 541,
|
| 7 |
+
"eval_samples_per_second": 6.238,
|
| 8 |
+
"eval_steps_per_second": 3.125,
|
| 9 |
+
"perplexity": 8.181055562487236
|
| 10 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"train_loss": 1.970301656346572,
|
| 4 |
+
"train_runtime": 9467.2073,
|
| 5 |
+
"train_samples": 4881,
|
| 6 |
+
"train_samples_per_second": 2.062,
|
| 7 |
+
"train_steps_per_second": 0.016
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,517 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6156604453386092,
|
| 3 |
+
"best_model_checkpoint": "./runtime-ar/checkpoint-152",
|
| 4 |
+
"epoch": 3.9950900163666123,
|
| 5 |
+
"global_step": 152,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 5e-05,
|
| 13 |
+
"loss": 3.3108,
|
| 14 |
+
"step": 2
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.1,
|
| 18 |
+
"learning_rate": 0.0001,
|
| 19 |
+
"loss": 4.8935,
|
| 20 |
+
"step": 4
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.16,
|
| 24 |
+
"learning_rate": 0.00015000000000000001,
|
| 25 |
+
"loss": 3.6355,
|
| 26 |
+
"step": 6
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.21,
|
| 30 |
+
"learning_rate": 0.0002,
|
| 31 |
+
"loss": 3.4513,
|
| 32 |
+
"step": 8
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.26,
|
| 36 |
+
"learning_rate": 0.0001999048221581858,
|
| 37 |
+
"loss": 3.2178,
|
| 38 |
+
"step": 10
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.31,
|
| 42 |
+
"learning_rate": 0.00019961946980917456,
|
| 43 |
+
"loss": 3.0584,
|
| 44 |
+
"step": 12
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.37,
|
| 48 |
+
"learning_rate": 0.00019914448613738106,
|
| 49 |
+
"loss": 2.908,
|
| 50 |
+
"step": 14
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.42,
|
| 54 |
+
"learning_rate": 0.00019848077530122083,
|
| 55 |
+
"loss": 2.7828,
|
| 56 |
+
"step": 16
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.47,
|
| 60 |
+
"learning_rate": 0.00019762960071199333,
|
| 61 |
+
"loss": 2.6914,
|
| 62 |
+
"step": 18
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.52,
|
| 66 |
+
"learning_rate": 0.00019659258262890683,
|
| 67 |
+
"loss": 2.6232,
|
| 68 |
+
"step": 20
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.58,
|
| 72 |
+
"learning_rate": 0.0001953716950748227,
|
| 73 |
+
"loss": 2.5839,
|
| 74 |
+
"step": 22
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.63,
|
| 78 |
+
"learning_rate": 0.00019396926207859084,
|
| 79 |
+
"loss": 2.5405,
|
| 80 |
+
"step": 24
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.68,
|
| 84 |
+
"learning_rate": 0.0001923879532511287,
|
| 85 |
+
"loss": 2.4946,
|
| 86 |
+
"step": 26
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.73,
|
| 90 |
+
"learning_rate": 0.000190630778703665,
|
| 91 |
+
"loss": 2.4245,
|
| 92 |
+
"step": 28
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.79,
|
| 96 |
+
"learning_rate": 0.00018870108331782217,
|
| 97 |
+
"loss": 2.4099,
|
| 98 |
+
"step": 30
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.84,
|
| 102 |
+
"learning_rate": 0.00018660254037844388,
|
| 103 |
+
"loss": 2.3972,
|
| 104 |
+
"step": 32
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.89,
|
| 108 |
+
"learning_rate": 0.0001843391445812886,
|
| 109 |
+
"loss": 2.3371,
|
| 110 |
+
"step": 34
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.94,
|
| 114 |
+
"learning_rate": 0.0001819152044288992,
|
| 115 |
+
"loss": 2.276,
|
| 116 |
+
"step": 36
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.0,
|
| 120 |
+
"learning_rate": 0.00017933533402912354,
|
| 121 |
+
"loss": 2.3067,
|
| 122 |
+
"step": 38
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.0,
|
| 126 |
+
"eval_accuracy": 0.5594373263429553,
|
| 127 |
+
"eval_loss": 2.3559441566467285,
|
| 128 |
+
"eval_runtime": 87.3704,
|
| 129 |
+
"eval_samples_per_second": 6.192,
|
| 130 |
+
"eval_steps_per_second": 3.102,
|
| 131 |
+
"step": 38
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.05,
|
| 135 |
+
"learning_rate": 0.0001766044443118978,
|
| 136 |
+
"loss": 2.3629,
|
| 137 |
+
"step": 40
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.1,
|
| 141 |
+
"learning_rate": 0.0001737277336810124,
|
| 142 |
+
"loss": 2.0942,
|
| 143 |
+
"step": 42
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.16,
|
| 147 |
+
"learning_rate": 0.00017071067811865476,
|
| 148 |
+
"loss": 2.0975,
|
| 149 |
+
"step": 44
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.21,
|
| 153 |
+
"learning_rate": 0.00016755902076156604,
|
| 154 |
+
"loss": 2.0554,
|
| 155 |
+
"step": 46
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.26,
|
| 159 |
+
"learning_rate": 0.00016427876096865394,
|
| 160 |
+
"loss": 2.0336,
|
| 161 |
+
"step": 48
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.31,
|
| 165 |
+
"learning_rate": 0.00016087614290087208,
|
| 166 |
+
"loss": 2.0584,
|
| 167 |
+
"step": 50
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.37,
|
| 171 |
+
"learning_rate": 0.0001573576436351046,
|
| 172 |
+
"loss": 1.9959,
|
| 173 |
+
"step": 52
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.42,
|
| 177 |
+
"learning_rate": 0.0001537299608346824,
|
| 178 |
+
"loss": 1.9855,
|
| 179 |
+
"step": 54
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.47,
|
| 183 |
+
"learning_rate": 0.00015000000000000001,
|
| 184 |
+
"loss": 1.9941,
|
| 185 |
+
"step": 56
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.52,
|
| 189 |
+
"learning_rate": 0.00014617486132350343,
|
| 190 |
+
"loss": 1.9589,
|
| 191 |
+
"step": 58
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.58,
|
| 195 |
+
"learning_rate": 0.00014226182617406996,
|
| 196 |
+
"loss": 1.9918,
|
| 197 |
+
"step": 60
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.63,
|
| 201 |
+
"learning_rate": 0.000138268343236509,
|
| 202 |
+
"loss": 1.9673,
|
| 203 |
+
"step": 62
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.68,
|
| 207 |
+
"learning_rate": 0.00013420201433256689,
|
| 208 |
+
"loss": 1.9626,
|
| 209 |
+
"step": 64
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.73,
|
| 213 |
+
"learning_rate": 0.00013007057995042732,
|
| 214 |
+
"loss": 1.9327,
|
| 215 |
+
"step": 66
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.79,
|
| 219 |
+
"learning_rate": 0.00012588190451025207,
|
| 220 |
+
"loss": 1.9334,
|
| 221 |
+
"step": 68
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.84,
|
| 225 |
+
"learning_rate": 0.00012164396139381029,
|
| 226 |
+
"loss": 1.9405,
|
| 227 |
+
"step": 70
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.89,
|
| 231 |
+
"learning_rate": 0.00011736481776669306,
|
| 232 |
+
"loss": 1.8394,
|
| 233 |
+
"step": 72
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.94,
|
| 237 |
+
"learning_rate": 0.00011305261922200519,
|
| 238 |
+
"loss": 1.9284,
|
| 239 |
+
"step": 74
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.0,
|
| 243 |
+
"learning_rate": 0.00010871557427476583,
|
| 244 |
+
"loss": 1.9243,
|
| 245 |
+
"step": 76
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 2.0,
|
| 249 |
+
"eval_accuracy": 0.5974633090939628,
|
| 250 |
+
"eval_loss": 2.1282806396484375,
|
| 251 |
+
"eval_runtime": 88.3059,
|
| 252 |
+
"eval_samples_per_second": 6.126,
|
| 253 |
+
"eval_steps_per_second": 3.069,
|
| 254 |
+
"step": 76
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.05,
|
| 258 |
+
"learning_rate": 0.00010436193873653361,
|
| 259 |
+
"loss": 1.8745,
|
| 260 |
+
"step": 78
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.1,
|
| 264 |
+
"learning_rate": 0.0001,
|
| 265 |
+
"loss": 1.6456,
|
| 266 |
+
"step": 80
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.16,
|
| 270 |
+
"learning_rate": 9.563806126346642e-05,
|
| 271 |
+
"loss": 1.6496,
|
| 272 |
+
"step": 82
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.21,
|
| 276 |
+
"learning_rate": 9.128442572523417e-05,
|
| 277 |
+
"loss": 1.6571,
|
| 278 |
+
"step": 84
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.26,
|
| 282 |
+
"learning_rate": 8.694738077799488e-05,
|
| 283 |
+
"loss": 1.6366,
|
| 284 |
+
"step": 86
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.31,
|
| 288 |
+
"learning_rate": 8.263518223330697e-05,
|
| 289 |
+
"loss": 1.6033,
|
| 290 |
+
"step": 88
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.37,
|
| 294 |
+
"learning_rate": 7.835603860618972e-05,
|
| 295 |
+
"loss": 1.6042,
|
| 296 |
+
"step": 90
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.42,
|
| 300 |
+
"learning_rate": 7.411809548974792e-05,
|
| 301 |
+
"loss": 1.6111,
|
| 302 |
+
"step": 92
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.47,
|
| 306 |
+
"learning_rate": 6.992942004957271e-05,
|
| 307 |
+
"loss": 1.6058,
|
| 308 |
+
"step": 94
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.52,
|
| 312 |
+
"learning_rate": 6.579798566743314e-05,
|
| 313 |
+
"loss": 1.6079,
|
| 314 |
+
"step": 96
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.58,
|
| 318 |
+
"learning_rate": 6.173165676349103e-05,
|
| 319 |
+
"loss": 1.5789,
|
| 320 |
+
"step": 98
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.63,
|
| 324 |
+
"learning_rate": 5.773817382593008e-05,
|
| 325 |
+
"loss": 1.6267,
|
| 326 |
+
"step": 100
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.68,
|
| 330 |
+
"learning_rate": 5.382513867649663e-05,
|
| 331 |
+
"loss": 1.5811,
|
| 332 |
+
"step": 102
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.73,
|
| 336 |
+
"learning_rate": 5.000000000000002e-05,
|
| 337 |
+
"loss": 1.5605,
|
| 338 |
+
"step": 104
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.79,
|
| 342 |
+
"learning_rate": 4.6270039165317605e-05,
|
| 343 |
+
"loss": 1.5828,
|
| 344 |
+
"step": 106
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.84,
|
| 348 |
+
"learning_rate": 4.264235636489542e-05,
|
| 349 |
+
"loss": 1.5579,
|
| 350 |
+
"step": 108
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.89,
|
| 354 |
+
"learning_rate": 3.9123857099127936e-05,
|
| 355 |
+
"loss": 1.5991,
|
| 356 |
+
"step": 110
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.94,
|
| 360 |
+
"learning_rate": 3.5721239031346066e-05,
|
| 361 |
+
"loss": 1.5641,
|
| 362 |
+
"step": 112
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 3.0,
|
| 366 |
+
"learning_rate": 3.244097923843398e-05,
|
| 367 |
+
"loss": 1.5971,
|
| 368 |
+
"step": 114
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 3.0,
|
| 372 |
+
"eval_accuracy": 0.6139908093264839,
|
| 373 |
+
"eval_loss": 2.075925827026367,
|
| 374 |
+
"eval_runtime": 88.4185,
|
| 375 |
+
"eval_samples_per_second": 6.119,
|
| 376 |
+
"eval_steps_per_second": 3.065,
|
| 377 |
+
"step": 114
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.05,
|
| 381 |
+
"learning_rate": 2.9289321881345254e-05,
|
| 382 |
+
"loss": 1.5486,
|
| 383 |
+
"step": 116
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 3.1,
|
| 387 |
+
"learning_rate": 2.6272266318987603e-05,
|
| 388 |
+
"loss": 1.4341,
|
| 389 |
+
"step": 118
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.16,
|
| 393 |
+
"learning_rate": 2.339555568810221e-05,
|
| 394 |
+
"loss": 1.4085,
|
| 395 |
+
"step": 120
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 3.21,
|
| 399 |
+
"learning_rate": 2.0664665970876496e-05,
|
| 400 |
+
"loss": 1.3819,
|
| 401 |
+
"step": 122
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 3.26,
|
| 405 |
+
"learning_rate": 1.808479557110081e-05,
|
| 406 |
+
"loss": 1.3935,
|
| 407 |
+
"step": 124
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 3.31,
|
| 411 |
+
"learning_rate": 1.566085541871145e-05,
|
| 412 |
+
"loss": 1.4073,
|
| 413 |
+
"step": 126
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 3.37,
|
| 417 |
+
"learning_rate": 1.339745962155613e-05,
|
| 418 |
+
"loss": 1.419,
|
| 419 |
+
"step": 128
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 3.42,
|
| 423 |
+
"learning_rate": 1.129891668217783e-05,
|
| 424 |
+
"loss": 1.3807,
|
| 425 |
+
"step": 130
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 3.47,
|
| 429 |
+
"learning_rate": 9.369221296335006e-06,
|
| 430 |
+
"loss": 1.3881,
|
| 431 |
+
"step": 132
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 3.52,
|
| 435 |
+
"learning_rate": 7.612046748871327e-06,
|
| 436 |
+
"loss": 1.3674,
|
| 437 |
+
"step": 134
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 3.58,
|
| 441 |
+
"learning_rate": 6.030737921409169e-06,
|
| 442 |
+
"loss": 1.3847,
|
| 443 |
+
"step": 136
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 3.63,
|
| 447 |
+
"learning_rate": 4.628304925177318e-06,
|
| 448 |
+
"loss": 1.3734,
|
| 449 |
+
"step": 138
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 3.68,
|
| 453 |
+
"learning_rate": 3.40741737109318e-06,
|
| 454 |
+
"loss": 1.3969,
|
| 455 |
+
"step": 140
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 3.73,
|
| 459 |
+
"learning_rate": 2.3703992880066638e-06,
|
| 460 |
+
"loss": 1.3544,
|
| 461 |
+
"step": 142
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 3.79,
|
| 465 |
+
"learning_rate": 1.5192246987791981e-06,
|
| 466 |
+
"loss": 1.4021,
|
| 467 |
+
"step": 144
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 3.84,
|
| 471 |
+
"learning_rate": 8.555138626189618e-07,
|
| 472 |
+
"loss": 1.4061,
|
| 473 |
+
"step": 146
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 3.89,
|
| 477 |
+
"learning_rate": 3.805301908254455e-07,
|
| 478 |
+
"loss": 1.3621,
|
| 479 |
+
"step": 148
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 3.94,
|
| 483 |
+
"learning_rate": 9.517784181422019e-08,
|
| 484 |
+
"loss": 1.3759,
|
| 485 |
+
"step": 150
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 4.0,
|
| 489 |
+
"learning_rate": 0.0,
|
| 490 |
+
"loss": 1.4139,
|
| 491 |
+
"step": 152
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 4.0,
|
| 495 |
+
"eval_accuracy": 0.6156604453386092,
|
| 496 |
+
"eval_loss": 2.101821184158325,
|
| 497 |
+
"eval_runtime": 88.2947,
|
| 498 |
+
"eval_samples_per_second": 6.127,
|
| 499 |
+
"eval_steps_per_second": 3.069,
|
| 500 |
+
"step": 152
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 4.0,
|
| 504 |
+
"step": 152,
|
| 505 |
+
"total_flos": 8.481201929060352e+16,
|
| 506 |
+
"train_loss": 1.970301656346572,
|
| 507 |
+
"train_runtime": 9467.2073,
|
| 508 |
+
"train_samples_per_second": 2.062,
|
| 509 |
+
"train_steps_per_second": 0.016
|
| 510 |
+
}
|
| 511 |
+
],
|
| 512 |
+
"max_steps": 152,
|
| 513 |
+
"num_train_epochs": 4,
|
| 514 |
+
"total_flos": 8.481201929060352e+16,
|
| 515 |
+
"trial_name": null,
|
| 516 |
+
"trial_params": null
|
| 517 |
+
}
|