Upload 4 files
Browse files- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +442 -0
- training_args.bin +3 -0
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96d83cd43847eca5f45ca3f1e6451b2eae9fdb0057abcba1b323cd40fce51ef3
|
| 3 |
+
size 13990
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8a9e6f64ecccf0b02087978dc28d8f7ec65ca88c5f388b9356e5c192850c88e
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,442 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.12,
|
| 5 |
+
"eval_steps": 20,
|
| 6 |
+
"global_step": 1140,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.16,
|
| 13 |
+
"learning_rate": 2.9520000000000002e-05,
|
| 14 |
+
"loss": 0.675,
|
| 15 |
+
"step": 20
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.32,
|
| 19 |
+
"learning_rate": 2.904e-05,
|
| 20 |
+
"loss": 0.6234,
|
| 21 |
+
"step": 40
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.48,
|
| 25 |
+
"learning_rate": 2.856e-05,
|
| 26 |
+
"loss": 0.4842,
|
| 27 |
+
"step": 60
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.64,
|
| 31 |
+
"learning_rate": 2.8080000000000002e-05,
|
| 32 |
+
"loss": 0.3626,
|
| 33 |
+
"step": 80
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.8,
|
| 37 |
+
"learning_rate": 2.7600000000000003e-05,
|
| 38 |
+
"loss": 0.3259,
|
| 39 |
+
"step": 100
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.96,
|
| 43 |
+
"learning_rate": 2.712e-05,
|
| 44 |
+
"loss": 0.2786,
|
| 45 |
+
"step": 120
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.0,
|
| 49 |
+
"eval_accuracy": 0.6135040521621704,
|
| 50 |
+
"eval_loss": 1.1749801635742188,
|
| 51 |
+
"eval_runtime": 4843.6207,
|
| 52 |
+
"eval_samples_per_second": 0.887,
|
| 53 |
+
"eval_steps_per_second": 0.028,
|
| 54 |
+
"step": 125
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.12,
|
| 58 |
+
"learning_rate": 2.6640000000000002e-05,
|
| 59 |
+
"loss": 0.231,
|
| 60 |
+
"step": 140
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.28,
|
| 64 |
+
"learning_rate": 2.616e-05,
|
| 65 |
+
"loss": 0.2978,
|
| 66 |
+
"step": 160
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.44,
|
| 70 |
+
"learning_rate": 2.568e-05,
|
| 71 |
+
"loss": 0.2383,
|
| 72 |
+
"step": 180
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.6,
|
| 76 |
+
"learning_rate": 2.52e-05,
|
| 77 |
+
"loss": 0.2364,
|
| 78 |
+
"step": 200
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 1.76,
|
| 82 |
+
"learning_rate": 2.472e-05,
|
| 83 |
+
"loss": 0.2186,
|
| 84 |
+
"step": 220
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.92,
|
| 88 |
+
"learning_rate": 2.4240000000000002e-05,
|
| 89 |
+
"loss": 0.1869,
|
| 90 |
+
"step": 240
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 2.0,
|
| 94 |
+
"eval_accuracy": 0.6817229390144348,
|
| 95 |
+
"eval_loss": 0.9132505655288696,
|
| 96 |
+
"eval_runtime": 4886.8402,
|
| 97 |
+
"eval_samples_per_second": 0.879,
|
| 98 |
+
"eval_steps_per_second": 0.028,
|
| 99 |
+
"step": 250
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.08,
|
| 103 |
+
"learning_rate": 2.3760000000000003e-05,
|
| 104 |
+
"loss": 0.1656,
|
| 105 |
+
"step": 260
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.24,
|
| 109 |
+
"learning_rate": 2.328e-05,
|
| 110 |
+
"loss": 0.1846,
|
| 111 |
+
"step": 280
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.4,
|
| 115 |
+
"learning_rate": 2.2800000000000002e-05,
|
| 116 |
+
"loss": 0.1609,
|
| 117 |
+
"step": 300
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 2.56,
|
| 121 |
+
"learning_rate": 2.232e-05,
|
| 122 |
+
"loss": 0.1497,
|
| 123 |
+
"step": 320
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.72,
|
| 127 |
+
"learning_rate": 2.184e-05,
|
| 128 |
+
"loss": 0.1564,
|
| 129 |
+
"step": 340
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 2.88,
|
| 133 |
+
"learning_rate": 2.136e-05,
|
| 134 |
+
"loss": 0.1409,
|
| 135 |
+
"step": 360
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 3.0,
|
| 139 |
+
"eval_accuracy": 0.6696158051490784,
|
| 140 |
+
"eval_loss": 0.9002014398574829,
|
| 141 |
+
"eval_runtime": 4890.7807,
|
| 142 |
+
"eval_samples_per_second": 0.878,
|
| 143 |
+
"eval_steps_per_second": 0.028,
|
| 144 |
+
"step": 375
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.04,
|
| 148 |
+
"learning_rate": 2.088e-05,
|
| 149 |
+
"loss": 0.1441,
|
| 150 |
+
"step": 380
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 3.2,
|
| 154 |
+
"learning_rate": 2.04e-05,
|
| 155 |
+
"loss": 0.1179,
|
| 156 |
+
"step": 400
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 3.36,
|
| 160 |
+
"learning_rate": 1.9920000000000002e-05,
|
| 161 |
+
"loss": 0.1467,
|
| 162 |
+
"step": 420
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 3.52,
|
| 166 |
+
"learning_rate": 1.944e-05,
|
| 167 |
+
"loss": 0.1311,
|
| 168 |
+
"step": 440
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 3.68,
|
| 172 |
+
"learning_rate": 1.896e-05,
|
| 173 |
+
"loss": 0.1261,
|
| 174 |
+
"step": 460
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 3.84,
|
| 178 |
+
"learning_rate": 1.848e-05,
|
| 179 |
+
"loss": 0.1533,
|
| 180 |
+
"step": 480
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 4.0,
|
| 184 |
+
"learning_rate": 1.8e-05,
|
| 185 |
+
"loss": 0.1296,
|
| 186 |
+
"step": 500
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 4.0,
|
| 190 |
+
"eval_accuracy": 0.7143189907073975,
|
| 191 |
+
"eval_loss": 0.8478733897209167,
|
| 192 |
+
"eval_runtime": 4805.5106,
|
| 193 |
+
"eval_samples_per_second": 0.894,
|
| 194 |
+
"eval_steps_per_second": 0.028,
|
| 195 |
+
"step": 500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 4.16,
|
| 199 |
+
"learning_rate": 1.7519999999999998e-05,
|
| 200 |
+
"loss": 0.1276,
|
| 201 |
+
"step": 520
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 4.32,
|
| 205 |
+
"learning_rate": 1.704e-05,
|
| 206 |
+
"loss": 0.1259,
|
| 207 |
+
"step": 540
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 4.48,
|
| 211 |
+
"learning_rate": 1.656e-05,
|
| 212 |
+
"loss": 0.1175,
|
| 213 |
+
"step": 560
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 4.64,
|
| 217 |
+
"learning_rate": 1.6080000000000002e-05,
|
| 218 |
+
"loss": 0.1392,
|
| 219 |
+
"step": 580
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 4.8,
|
| 223 |
+
"learning_rate": 1.56e-05,
|
| 224 |
+
"loss": 0.113,
|
| 225 |
+
"step": 600
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 4.96,
|
| 229 |
+
"learning_rate": 1.5120000000000001e-05,
|
| 230 |
+
"loss": 0.1139,
|
| 231 |
+
"step": 620
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 5.0,
|
| 235 |
+
"eval_accuracy": 0.7427241206169128,
|
| 236 |
+
"eval_loss": 0.8348045349121094,
|
| 237 |
+
"eval_runtime": 4819.2179,
|
| 238 |
+
"eval_samples_per_second": 0.891,
|
| 239 |
+
"eval_steps_per_second": 0.028,
|
| 240 |
+
"step": 625
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 5.12,
|
| 244 |
+
"learning_rate": 1.464e-05,
|
| 245 |
+
"loss": 0.1246,
|
| 246 |
+
"step": 640
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 5.28,
|
| 250 |
+
"learning_rate": 1.416e-05,
|
| 251 |
+
"loss": 0.1313,
|
| 252 |
+
"step": 660
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 5.44,
|
| 256 |
+
"learning_rate": 1.3680000000000001e-05,
|
| 257 |
+
"loss": 0.1175,
|
| 258 |
+
"step": 680
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 5.6,
|
| 262 |
+
"learning_rate": 1.32e-05,
|
| 263 |
+
"loss": 0.1205,
|
| 264 |
+
"step": 700
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 5.76,
|
| 268 |
+
"learning_rate": 1.272e-05,
|
| 269 |
+
"loss": 0.1015,
|
| 270 |
+
"step": 720
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 5.92,
|
| 274 |
+
"learning_rate": 1.224e-05,
|
| 275 |
+
"loss": 0.0941,
|
| 276 |
+
"step": 740
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 6.0,
|
| 280 |
+
"eval_accuracy": 0.7427241206169128,
|
| 281 |
+
"eval_loss": 0.830384373664856,
|
| 282 |
+
"eval_runtime": 4804.5403,
|
| 283 |
+
"eval_samples_per_second": 0.894,
|
| 284 |
+
"eval_steps_per_second": 0.028,
|
| 285 |
+
"step": 750
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 6.08,
|
| 289 |
+
"learning_rate": 1.1760000000000001e-05,
|
| 290 |
+
"loss": 0.1224,
|
| 291 |
+
"step": 760
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 6.24,
|
| 295 |
+
"learning_rate": 1.128e-05,
|
| 296 |
+
"loss": 0.105,
|
| 297 |
+
"step": 780
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 6.4,
|
| 301 |
+
"learning_rate": 1.08e-05,
|
| 302 |
+
"loss": 0.122,
|
| 303 |
+
"step": 800
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 6.56,
|
| 307 |
+
"learning_rate": 1.032e-05,
|
| 308 |
+
"loss": 0.1044,
|
| 309 |
+
"step": 820
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 6.72,
|
| 313 |
+
"learning_rate": 9.84e-06,
|
| 314 |
+
"loss": 0.1077,
|
| 315 |
+
"step": 840
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 6.88,
|
| 319 |
+
"learning_rate": 9.36e-06,
|
| 320 |
+
"loss": 0.1075,
|
| 321 |
+
"step": 860
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 7.0,
|
| 325 |
+
"eval_accuracy": 0.6938300132751465,
|
| 326 |
+
"eval_loss": 0.8423438668251038,
|
| 327 |
+
"eval_runtime": 4824.348,
|
| 328 |
+
"eval_samples_per_second": 0.89,
|
| 329 |
+
"eval_steps_per_second": 0.028,
|
| 330 |
+
"step": 875
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 7.04,
|
| 334 |
+
"learning_rate": 8.88e-06,
|
| 335 |
+
"loss": 0.0951,
|
| 336 |
+
"step": 880
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 7.2,
|
| 340 |
+
"learning_rate": 8.400000000000001e-06,
|
| 341 |
+
"loss": 0.1229,
|
| 342 |
+
"step": 900
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 7.36,
|
| 346 |
+
"learning_rate": 7.92e-06,
|
| 347 |
+
"loss": 0.1171,
|
| 348 |
+
"step": 920
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 7.52,
|
| 352 |
+
"learning_rate": 7.44e-06,
|
| 353 |
+
"loss": 0.0955,
|
| 354 |
+
"step": 940
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 7.68,
|
| 358 |
+
"learning_rate": 6.96e-06,
|
| 359 |
+
"loss": 0.1139,
|
| 360 |
+
"step": 960
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 7.84,
|
| 364 |
+
"learning_rate": 6.48e-06,
|
| 365 |
+
"loss": 0.1051,
|
| 366 |
+
"step": 980
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 8.0,
|
| 370 |
+
"learning_rate": 6e-06,
|
| 371 |
+
"loss": 0.1011,
|
| 372 |
+
"step": 1000
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 8.0,
|
| 376 |
+
"eval_accuracy": 0.7236321568489075,
|
| 377 |
+
"eval_loss": 0.8057857155799866,
|
| 378 |
+
"eval_runtime": 4915.4234,
|
| 379 |
+
"eval_samples_per_second": 0.874,
|
| 380 |
+
"eval_steps_per_second": 0.027,
|
| 381 |
+
"step": 1000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 8.16,
|
| 385 |
+
"learning_rate": 5.52e-06,
|
| 386 |
+
"loss": 0.0976,
|
| 387 |
+
"step": 1020
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 8.32,
|
| 391 |
+
"learning_rate": 5.04e-06,
|
| 392 |
+
"loss": 0.1008,
|
| 393 |
+
"step": 1040
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 8.48,
|
| 397 |
+
"learning_rate": 4.56e-06,
|
| 398 |
+
"loss": 0.1066,
|
| 399 |
+
"step": 1060
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 8.64,
|
| 403 |
+
"learning_rate": 4.080000000000001e-06,
|
| 404 |
+
"loss": 0.1038,
|
| 405 |
+
"step": 1080
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 8.8,
|
| 409 |
+
"learning_rate": 3.6e-06,
|
| 410 |
+
"loss": 0.1044,
|
| 411 |
+
"step": 1100
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 8.96,
|
| 415 |
+
"learning_rate": 3.1199999999999998e-06,
|
| 416 |
+
"loss": 0.1015,
|
| 417 |
+
"step": 1120
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 9.0,
|
| 421 |
+
"eval_accuracy": 0.7201396822929382,
|
| 422 |
+
"eval_loss": 0.7934114336967468,
|
| 423 |
+
"eval_runtime": 4842.9757,
|
| 424 |
+
"eval_samples_per_second": 0.887,
|
| 425 |
+
"eval_steps_per_second": 0.028,
|
| 426 |
+
"step": 1125
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 9.12,
|
| 430 |
+
"learning_rate": 2.6399999999999997e-06,
|
| 431 |
+
"loss": 0.1091,
|
| 432 |
+
"step": 1140
|
| 433 |
+
}
|
| 434 |
+
],
|
| 435 |
+
"logging_steps": 20,
|
| 436 |
+
"max_steps": 1250,
|
| 437 |
+
"num_train_epochs": 10,
|
| 438 |
+
"save_steps": 20,
|
| 439 |
+
"total_flos": 4.43240458915968e+19,
|
| 440 |
+
"trial_name": null,
|
| 441 |
+
"trial_params": null
|
| 442 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18ccc8a6cb4ea2b5071107bfaaeddbde9cb6df895e3fd9d248ea483f24fe97dc
|
| 3 |
+
size 4536
|