Upload folder using huggingface_hub
Browse files- model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +0 -0
- scheduler.pt +0 -0
- trainer_state.json +213 -3
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1426462208
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2ccb1201adc7ba3dce45c039a56a518750657ba48b9dc6407631be5a9ec0851
|
| 3 |
size 1426462208
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2853107898
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a11c2381fc62f5a000590233a5f5371a956d9b0994b73d666ec134c93e250cb3
|
| 3 |
size 2853107898
|
rng_state.pth
CHANGED
|
Binary files a/rng_state.pth and b/rng_state.pth differ
|
|
|
scheduler.pt
CHANGED
|
Binary files a/scheduler.pt and b/scheduler.pt differ
|
|
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -77,6 +77,216 @@
|
|
| 77 |
"learning_rate": 4.766941644720645e-05,
|
| 78 |
"loss": 2.9423,
|
| 79 |
"step": 100000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
}
|
| 81 |
],
|
| 82 |
"logging_steps": 10000,
|
|
@@ -96,7 +306,7 @@
|
|
| 96 |
"attributes": {}
|
| 97 |
}
|
| 98 |
},
|
| 99 |
-
"total_flos":
|
| 100 |
"train_batch_size": 4,
|
| 101 |
"trial_name": null,
|
| 102 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.18651009765668713,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 400000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 77 |
"learning_rate": 4.766941644720645e-05,
|
| 78 |
"loss": 2.9423,
|
| 79 |
"step": 100000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.051290276855588963,
|
| 83 |
+
"grad_norm": 1.2270045280456543,
|
| 84 |
+
"learning_rate": 4.7436372080184424e-05,
|
| 85 |
+
"loss": 2.9127,
|
| 86 |
+
"step": 110000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.05595302929700614,
|
| 90 |
+
"grad_norm": 1.0300427675247192,
|
| 91 |
+
"learning_rate": 4.7203327713162395e-05,
|
| 92 |
+
"loss": 2.8823,
|
| 93 |
+
"step": 120000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.060615781738423316,
|
| 97 |
+
"grad_norm": 0.8841068148612976,
|
| 98 |
+
"learning_rate": 4.6970283346140366e-05,
|
| 99 |
+
"loss": 2.8588,
|
| 100 |
+
"step": 130000
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.0652785341798405,
|
| 104 |
+
"grad_norm": 1.0524730682373047,
|
| 105 |
+
"learning_rate": 4.673721566535613e-05,
|
| 106 |
+
"loss": 2.8425,
|
| 107 |
+
"step": 140000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.06994128662125768,
|
| 111 |
+
"grad_norm": 0.9874018430709839,
|
| 112 |
+
"learning_rate": 4.650417129833409e-05,
|
| 113 |
+
"loss": 2.8257,
|
| 114 |
+
"step": 150000
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.07460403906267485,
|
| 118 |
+
"grad_norm": 0.9634119272232056,
|
| 119 |
+
"learning_rate": 4.6271126931312064e-05,
|
| 120 |
+
"loss": 2.8114,
|
| 121 |
+
"step": 160000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.07926679150409204,
|
| 125 |
+
"grad_norm": 0.885671854019165,
|
| 126 |
+
"learning_rate": 4.603808256429003e-05,
|
| 127 |
+
"loss": 2.7911,
|
| 128 |
+
"step": 170000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.08392954394550921,
|
| 132 |
+
"grad_norm": 1.0135940313339233,
|
| 133 |
+
"learning_rate": 4.58050148835058e-05,
|
| 134 |
+
"loss": 2.7786,
|
| 135 |
+
"step": 180000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.0885922963869264,
|
| 139 |
+
"grad_norm": 1.011932611465454,
|
| 140 |
+
"learning_rate": 4.557194720272156e-05,
|
| 141 |
+
"loss": 2.7636,
|
| 142 |
+
"step": 190000
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.09325504882834357,
|
| 146 |
+
"grad_norm": 0.7796096205711365,
|
| 147 |
+
"learning_rate": 4.533892614946173e-05,
|
| 148 |
+
"loss": 2.753,
|
| 149 |
+
"step": 200000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.09791780126976074,
|
| 153 |
+
"grad_norm": 1.1194034814834595,
|
| 154 |
+
"learning_rate": 4.5105858468677495e-05,
|
| 155 |
+
"loss": 2.7371,
|
| 156 |
+
"step": 210000
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.10258055371117793,
|
| 160 |
+
"grad_norm": 1.1135520935058594,
|
| 161 |
+
"learning_rate": 4.4872814101655467e-05,
|
| 162 |
+
"loss": 2.7285,
|
| 163 |
+
"step": 220000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.1072433061525951,
|
| 167 |
+
"grad_norm": 0.7772097587585449,
|
| 168 |
+
"learning_rate": 4.463976973463344e-05,
|
| 169 |
+
"loss": 2.7173,
|
| 170 |
+
"step": 230000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.11190605859401229,
|
| 174 |
+
"grad_norm": 1.096358299255371,
|
| 175 |
+
"learning_rate": 4.44067020538492e-05,
|
| 176 |
+
"loss": 2.7141,
|
| 177 |
+
"step": 240000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.11656881103542946,
|
| 181 |
+
"grad_norm": 0.8112640380859375,
|
| 182 |
+
"learning_rate": 4.417363437306496e-05,
|
| 183 |
+
"loss": 2.7073,
|
| 184 |
+
"step": 250000
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.12123156347684663,
|
| 188 |
+
"grad_norm": 1.0931545495986938,
|
| 189 |
+
"learning_rate": 4.394059000604293e-05,
|
| 190 |
+
"loss": 2.6931,
|
| 191 |
+
"step": 260000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.1258943159182638,
|
| 195 |
+
"grad_norm": 1.1369918584823608,
|
| 196 |
+
"learning_rate": 4.37075456390209e-05,
|
| 197 |
+
"loss": 2.6824,
|
| 198 |
+
"step": 270000
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.130557068359681,
|
| 202 |
+
"grad_norm": 1.258300542831421,
|
| 203 |
+
"learning_rate": 4.347450127199887e-05,
|
| 204 |
+
"loss": 2.6741,
|
| 205 |
+
"step": 280000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.13521982080109818,
|
| 209 |
+
"grad_norm": 0.9752686023712158,
|
| 210 |
+
"learning_rate": 4.324143359121463e-05,
|
| 211 |
+
"loss": 2.6645,
|
| 212 |
+
"step": 290000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.13988257324251535,
|
| 216 |
+
"grad_norm": 1.0001367330551147,
|
| 217 |
+
"learning_rate": 4.3008412537954805e-05,
|
| 218 |
+
"loss": 2.6592,
|
| 219 |
+
"step": 300000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.14454532568393252,
|
| 223 |
+
"grad_norm": 1.0314422845840454,
|
| 224 |
+
"learning_rate": 4.277534485717057e-05,
|
| 225 |
+
"loss": 2.6523,
|
| 226 |
+
"step": 310000
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.1492080781253497,
|
| 230 |
+
"grad_norm": 0.9287506937980652,
|
| 231 |
+
"learning_rate": 4.254230049014854e-05,
|
| 232 |
+
"loss": 2.6503,
|
| 233 |
+
"step": 320000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.1538708305667669,
|
| 237 |
+
"grad_norm": 0.8209073543548584,
|
| 238 |
+
"learning_rate": 4.23092328093643e-05,
|
| 239 |
+
"loss": 2.6379,
|
| 240 |
+
"step": 330000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.15853358300818407,
|
| 244 |
+
"grad_norm": 0.8727386593818665,
|
| 245 |
+
"learning_rate": 4.207618844234227e-05,
|
| 246 |
+
"loss": 2.6332,
|
| 247 |
+
"step": 340000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.16319633544960124,
|
| 251 |
+
"grad_norm": 0.9841961860656738,
|
| 252 |
+
"learning_rate": 4.184314407532024e-05,
|
| 253 |
+
"loss": 2.6279,
|
| 254 |
+
"step": 350000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.16785908789101842,
|
| 258 |
+
"grad_norm": 0.7831237316131592,
|
| 259 |
+
"learning_rate": 4.1610099708298214e-05,
|
| 260 |
+
"loss": 2.6237,
|
| 261 |
+
"step": 360000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.1725218403324356,
|
| 265 |
+
"grad_norm": 0.9184048175811768,
|
| 266 |
+
"learning_rate": 4.137707865503839e-05,
|
| 267 |
+
"loss": 2.6167,
|
| 268 |
+
"step": 370000
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.1771845927738528,
|
| 272 |
+
"grad_norm": 0.9598727822303772,
|
| 273 |
+
"learning_rate": 4.114401097425415e-05,
|
| 274 |
+
"loss": 2.6082,
|
| 275 |
+
"step": 380000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.18184734521526996,
|
| 279 |
+
"grad_norm": 0.8814136981964111,
|
| 280 |
+
"learning_rate": 4.0910966607232115e-05,
|
| 281 |
+
"loss": 2.6027,
|
| 282 |
+
"step": 390000
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.18651009765668713,
|
| 286 |
+
"grad_norm": 0.9080318212509155,
|
| 287 |
+
"learning_rate": 4.067789892644788e-05,
|
| 288 |
+
"loss": 2.6014,
|
| 289 |
+
"step": 400000
|
| 290 |
}
|
| 291 |
],
|
| 292 |
"logging_steps": 10000,
|
|
|
|
| 306 |
"attributes": {}
|
| 307 |
}
|
| 308 |
},
|
| 309 |
+
"total_flos": 9.86304678504589e+18,
|
| 310 |
"train_batch_size": 4,
|
| 311 |
"trial_name": null,
|
| 312 |
"trial_params": null
|