update ckpt with 4ish epochs of training on a100
Browse files- config.json +1 -1
- latest +1 -1
- pytorch_model.bin +1 -1
- rng_state_0.pth +1 -1
- tokenizer_config.json +1 -1
- trainer_state.json +305 -188
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-
|
| 3 |
"architectures": [
|
| 4 |
"LongT5ForConditionalGeneration"
|
| 5 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP6",
|
| 3 |
"architectures": [
|
| 4 |
"LongT5ForConditionalGeneration"
|
| 5 |
],
|
latest
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
|
|
|
|
| 1 |
+
global_step150
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3132548907
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92ab44b991c09f6bc82409f7899997e00371195237de8016934fcb74aa027de4
|
| 3 |
size 3132548907
|
rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:661796353532b01dfcf9f907b7fc04fac2c5b189850da5882dad7779f8759631
|
| 3 |
size 14503
|
tokenizer_config.json
CHANGED
|
@@ -103,7 +103,7 @@
|
|
| 103 |
],
|
| 104 |
"eos_token": "</s>",
|
| 105 |
"extra_ids": 100,
|
| 106 |
-
"name_or_path": "pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-
|
| 107 |
"pad_token": "<pad>",
|
| 108 |
"special_tokens_map_file": null,
|
| 109 |
"tokenizer_class": "T5Tokenizer",
|
|
|
|
| 103 |
],
|
| 104 |
"eos_token": "</s>",
|
| 105 |
"extra_ids": 100,
|
| 106 |
+
"name_or_path": "pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP6",
|
| 107 |
"pad_token": "<pad>",
|
| 108 |
"special_tokens_map_file": null,
|
| 109 |
"tokenizer_class": "T5Tokenizer",
|
trainer_state.json
CHANGED
|
@@ -1,349 +1,466 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 1.
|
| 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":
|
| 14 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.07,
|
| 18 |
-
"learning_rate":
|
| 19 |
-
"loss":
|
| 20 |
"step": 6
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"epoch": 0.
|
| 24 |
-
"learning_rate":
|
| 25 |
-
"loss":
|
| 26 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.15,
|
| 30 |
-
"learning_rate":
|
| 31 |
-
"loss":
|
| 32 |
"step": 12
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch": 0.
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss":
|
| 38 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.22,
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss":
|
| 44 |
"step": 18
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"learning_rate":
|
| 49 |
-
"loss":
|
| 50 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.29,
|
| 54 |
-
"learning_rate":
|
| 55 |
-
"loss":
|
| 56 |
"step": 24
|
| 57 |
},
|
| 58 |
{
|
| 59 |
-
"epoch": 0.
|
| 60 |
-
"learning_rate":
|
| 61 |
-
"loss":
|
| 62 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 0.36,
|
| 66 |
-
"learning_rate":
|
| 67 |
-
"loss":
|
| 68 |
"step": 30
|
| 69 |
},
|
| 70 |
{
|
| 71 |
-
"epoch": 0.
|
| 72 |
-
"learning_rate":
|
| 73 |
-
"loss":
|
| 74 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.44,
|
| 78 |
-
"learning_rate":
|
| 79 |
-
"loss":
|
| 80 |
"step": 36
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"epoch": 0.
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss":
|
| 86 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.51,
|
| 90 |
-
"learning_rate":
|
| 91 |
-
"loss": 3.
|
| 92 |
"step": 42
|
| 93 |
},
|
| 94 |
{
|
| 95 |
-
"epoch": 0.
|
| 96 |
-
"learning_rate":
|
| 97 |
-
"loss": 3.
|
| 98 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 0.58,
|
| 102 |
-
"learning_rate":
|
| 103 |
-
"loss": 3.
|
| 104 |
"step": 48
|
| 105 |
},
|
| 106 |
{
|
| 107 |
-
"epoch": 0.
|
| 108 |
-
"learning_rate":
|
| 109 |
-
"loss": 3.
|
| 110 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 0.65,
|
| 114 |
-
"learning_rate":
|
| 115 |
-
"loss":
|
| 116 |
"step": 54
|
| 117 |
},
|
| 118 |
{
|
| 119 |
-
"epoch": 0.
|
| 120 |
-
"learning_rate":
|
| 121 |
-
"loss": 3.
|
| 122 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.73,
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss":
|
| 128 |
"step": 60
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch": 0.
|
| 132 |
-
"learning_rate":
|
| 133 |
-
"loss":
|
| 134 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 135 |
},
|
| 136 |
{
|
| 137 |
"epoch": 0.8,
|
| 138 |
-
"learning_rate":
|
| 139 |
-
"loss":
|
| 140 |
"step": 66
|
| 141 |
},
|
| 142 |
{
|
| 143 |
-
"epoch": 0.
|
| 144 |
-
"learning_rate":
|
| 145 |
-
"loss":
|
| 146 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 0.87,
|
| 150 |
-
"learning_rate":
|
| 151 |
-
"loss":
|
| 152 |
"step": 72
|
| 153 |
},
|
| 154 |
{
|
| 155 |
-
"epoch": 0.
|
| 156 |
-
"learning_rate":
|
| 157 |
-
"loss":
|
| 158 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 0.94,
|
| 162 |
-
"learning_rate":
|
| 163 |
-
"loss":
|
| 164 |
"step": 78
|
| 165 |
},
|
| 166 |
{
|
| 167 |
-
"epoch": 0.
|
| 168 |
-
"learning_rate":
|
| 169 |
-
"loss":
|
| 170 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 1.02,
|
| 174 |
-
"learning_rate":
|
| 175 |
-
"loss": 3.
|
| 176 |
"step": 84
|
| 177 |
},
|
| 178 |
{
|
| 179 |
-
"epoch": 1.
|
| 180 |
-
"learning_rate":
|
| 181 |
-
"loss":
|
| 182 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 183 |
},
|
| 184 |
{
|
| 185 |
"epoch": 1.1,
|
| 186 |
-
"learning_rate":
|
| 187 |
-
"loss":
|
| 188 |
"step": 90
|
| 189 |
},
|
| 190 |
{
|
| 191 |
-
"epoch": 1.
|
| 192 |
-
"learning_rate":
|
| 193 |
-
"loss":
|
| 194 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 1.17,
|
| 198 |
-
"learning_rate":
|
| 199 |
-
"loss":
|
| 200 |
"step": 96
|
| 201 |
},
|
| 202 |
{
|
| 203 |
-
"epoch": 1.
|
| 204 |
-
"learning_rate":
|
| 205 |
-
"loss":
|
| 206 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 1.24,
|
| 210 |
-
"learning_rate":
|
| 211 |
-
"loss":
|
| 212 |
"step": 102
|
| 213 |
},
|
| 214 |
{
|
| 215 |
-
"epoch": 1.
|
| 216 |
-
"learning_rate":
|
| 217 |
-
"loss":
|
| 218 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 219 |
},
|
| 220 |
{
|
| 221 |
"epoch": 1.31,
|
| 222 |
-
"learning_rate":
|
| 223 |
-
"loss":
|
| 224 |
"step": 108
|
| 225 |
},
|
| 226 |
{
|
| 227 |
-
"epoch": 1.
|
| 228 |
-
"learning_rate":
|
| 229 |
-
"loss":
|
| 230 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 1.39,
|
| 234 |
-
"learning_rate":
|
| 235 |
-
"loss":
|
| 236 |
"step": 114
|
| 237 |
},
|
| 238 |
{
|
| 239 |
-
"epoch": 1.
|
| 240 |
-
"learning_rate":
|
| 241 |
-
"loss":
|
| 242 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 243 |
},
|
| 244 |
{
|
| 245 |
"epoch": 1.46,
|
| 246 |
-
"learning_rate":
|
| 247 |
-
"loss":
|
| 248 |
"step": 120
|
| 249 |
},
|
| 250 |
{
|
| 251 |
-
"epoch": 1.
|
| 252 |
-
"learning_rate":
|
| 253 |
-
"loss":
|
| 254 |
-
"step":
|
| 255 |
},
|
| 256 |
{
|
| 257 |
-
"epoch": 1.
|
| 258 |
-
"learning_rate":
|
| 259 |
-
"loss":
|
| 260 |
-
"step":
|
| 261 |
},
|
| 262 |
{
|
| 263 |
-
"epoch": 1.
|
| 264 |
-
"learning_rate":
|
| 265 |
-
"loss":
|
| 266 |
-
"step":
|
| 267 |
},
|
| 268 |
{
|
| 269 |
-
"epoch": 1.
|
| 270 |
-
"learning_rate":
|
| 271 |
-
"loss":
|
| 272 |
-
"step":
|
| 273 |
},
|
| 274 |
{
|
| 275 |
-
"epoch": 1.
|
| 276 |
-
"learning_rate":
|
| 277 |
-
"loss":
|
| 278 |
-
"step":
|
| 279 |
},
|
| 280 |
{
|
| 281 |
-
"epoch": 1.
|
| 282 |
-
"learning_rate":
|
| 283 |
-
"loss":
|
| 284 |
-
"step":
|
| 285 |
},
|
| 286 |
{
|
| 287 |
-
"epoch": 1.
|
| 288 |
-
"learning_rate":
|
| 289 |
-
"loss":
|
| 290 |
-
"step":
|
| 291 |
},
|
| 292 |
{
|
| 293 |
-
"epoch": 1.
|
| 294 |
-
"learning_rate":
|
| 295 |
-
"loss":
|
| 296 |
-
"step":
|
| 297 |
},
|
| 298 |
{
|
| 299 |
-
"epoch": 1.
|
| 300 |
-
"learning_rate":
|
| 301 |
-
"loss":
|
| 302 |
-
"step":
|
| 303 |
},
|
| 304 |
{
|
| 305 |
-
"epoch": 1.
|
| 306 |
-
"learning_rate":
|
| 307 |
-
"loss":
|
| 308 |
-
"step":
|
| 309 |
},
|
| 310 |
{
|
| 311 |
-
"epoch": 1.
|
| 312 |
-
"learning_rate":
|
| 313 |
-
"loss":
|
| 314 |
-
"step":
|
| 315 |
},
|
| 316 |
{
|
| 317 |
-
"epoch": 1.
|
| 318 |
-
"learning_rate":
|
| 319 |
-
"loss":
|
| 320 |
-
"step":
|
| 321 |
},
|
| 322 |
{
|
| 323 |
-
"epoch": 1.
|
| 324 |
-
"learning_rate":
|
| 325 |
-
"loss":
|
| 326 |
-
"step":
|
| 327 |
},
|
| 328 |
{
|
| 329 |
-
"epoch": 1.
|
| 330 |
-
"learning_rate":
|
| 331 |
-
"loss":
|
| 332 |
-
"step":
|
| 333 |
},
|
| 334 |
{
|
| 335 |
-
"epoch": 1.
|
| 336 |
-
"
|
| 337 |
-
"
|
| 338 |
-
"
|
| 339 |
-
"train_runtime": 68661.2713,
|
| 340 |
-
"train_samples_per_second": 0.308,
|
| 341 |
-
"train_steps_per_second": 0.002
|
| 342 |
}
|
| 343 |
],
|
| 344 |
-
"max_steps":
|
| 345 |
-
"num_train_epochs":
|
| 346 |
-
"total_flos": 1.
|
| 347 |
"trial_name": null,
|
| 348 |
"trial_params": null
|
| 349 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.8219074598677998,
|
| 5 |
+
"global_step": 150,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 0.0004,
|
| 13 |
+
"loss": 2.8174,
|
| 14 |
+
"step": 2
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"learning_rate": 0.0008,
|
| 19 |
+
"loss": 2.8801,
|
| 20 |
+
"step": 4
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.07,
|
| 24 |
+
"learning_rate": 0.0009999575185316995,
|
| 25 |
+
"loss": 2.8676,
|
| 26 |
"step": 6
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 0.1,
|
| 30 |
+
"learning_rate": 0.0009996177100962712,
|
| 31 |
+
"loss": 2.8733,
|
| 32 |
+
"step": 8
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.12,
|
| 36 |
+
"learning_rate": 0.000998938324184584,
|
| 37 |
+
"loss": 2.9105,
|
| 38 |
+
"step": 10
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.15,
|
| 42 |
+
"learning_rate": 0.0009979198225579969,
|
| 43 |
+
"loss": 2.9035,
|
| 44 |
"step": 12
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.17,
|
| 48 |
+
"learning_rate": 0.0009965628974662145,
|
| 49 |
+
"loss": 2.8884,
|
| 50 |
+
"step": 14
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.19,
|
| 54 |
+
"learning_rate": 0.00099486847117678,
|
| 55 |
+
"loss": 2.879,
|
| 56 |
+
"step": 16
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.22,
|
| 60 |
+
"learning_rate": 0.0009928376953482344,
|
| 61 |
+
"loss": 2.9521,
|
| 62 |
"step": 18
|
| 63 |
},
|
| 64 |
{
|
| 65 |
+
"epoch": 0.24,
|
| 66 |
+
"learning_rate": 0.0009904719502473634,
|
| 67 |
+
"loss": 2.9526,
|
| 68 |
+
"step": 20
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.27,
|
| 72 |
+
"learning_rate": 0.0009877728438110645,
|
| 73 |
+
"loss": 2.9211,
|
| 74 |
+
"step": 22
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.29,
|
| 78 |
+
"learning_rate": 0.0009847422105534738,
|
| 79 |
+
"loss": 2.8804,
|
| 80 |
"step": 24
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 0.31,
|
| 84 |
+
"learning_rate": 0.000981382110319093,
|
| 85 |
+
"loss": 2.9045,
|
| 86 |
+
"step": 26
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.34,
|
| 90 |
+
"learning_rate": 0.0009776948268827657,
|
| 91 |
+
"loss": 2.9369,
|
| 92 |
+
"step": 28
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 0.36,
|
| 96 |
+
"learning_rate": 0.0009736828663974526,
|
| 97 |
+
"loss": 2.9049,
|
| 98 |
"step": 30
|
| 99 |
},
|
| 100 |
{
|
| 101 |
+
"epoch": 0.39,
|
| 102 |
+
"learning_rate": 0.0009693489556908641,
|
| 103 |
+
"loss": 2.9069,
|
| 104 |
+
"step": 32
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.41,
|
| 108 |
+
"learning_rate": 0.0009646960404121041,
|
| 109 |
+
"loss": 2.9257,
|
| 110 |
+
"step": 34
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 0.44,
|
| 114 |
+
"learning_rate": 0.0009597272830295876,
|
| 115 |
+
"loss": 2.8909,
|
| 116 |
"step": 36
|
| 117 |
},
|
| 118 |
{
|
| 119 |
+
"epoch": 0.46,
|
| 120 |
+
"learning_rate": 0.00095444606068159,
|
| 121 |
+
"loss": 2.9512,
|
| 122 |
+
"step": 38
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.48,
|
| 126 |
+
"learning_rate": 0.0009488559628808938,
|
| 127 |
+
"loss": 3.0004,
|
| 128 |
+
"step": 40
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.51,
|
| 132 |
+
"learning_rate": 0.0009429607890750862,
|
| 133 |
+
"loss": 3.1118,
|
| 134 |
"step": 42
|
| 135 |
},
|
| 136 |
{
|
| 137 |
+
"epoch": 0.53,
|
| 138 |
+
"learning_rate": 0.0009367645460641715,
|
| 139 |
+
"loss": 3.082,
|
| 140 |
+
"step": 44
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.56,
|
| 144 |
+
"learning_rate": 0.0009302714452772515,
|
| 145 |
+
"loss": 3.0348,
|
| 146 |
+
"step": 46
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 0.58,
|
| 150 |
+
"learning_rate": 0.0009234858999101231,
|
| 151 |
+
"loss": 3.0918,
|
| 152 |
"step": 48
|
| 153 |
},
|
| 154 |
{
|
| 155 |
+
"epoch": 0.6,
|
| 156 |
+
"learning_rate": 0.0009164125219257418,
|
| 157 |
+
"loss": 3.0042,
|
| 158 |
+
"step": 50
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.63,
|
| 162 |
+
"learning_rate": 0.000909056118919587,
|
| 163 |
+
"loss": 2.971,
|
| 164 |
+
"step": 52
|
| 165 |
},
|
| 166 |
{
|
| 167 |
"epoch": 0.65,
|
| 168 |
+
"learning_rate": 0.0009014216908520619,
|
| 169 |
+
"loss": 2.9717,
|
| 170 |
"step": 54
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"epoch": 0.68,
|
| 174 |
+
"learning_rate": 0.0008935144266501469,
|
| 175 |
+
"loss": 3.0012,
|
| 176 |
+
"step": 56
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.7,
|
| 180 |
+
"learning_rate": 0.0008853397006806182,
|
| 181 |
+
"loss": 2.9478,
|
| 182 |
+
"step": 58
|
| 183 |
},
|
| 184 |
{
|
| 185 |
"epoch": 0.73,
|
| 186 |
+
"learning_rate": 0.0008769030690972262,
|
| 187 |
+
"loss": 2.9312,
|
| 188 |
"step": 60
|
| 189 |
},
|
| 190 |
{
|
| 191 |
+
"epoch": 0.75,
|
| 192 |
+
"learning_rate": 0.0008682102660643197,
|
| 193 |
+
"loss": 2.898,
|
| 194 |
+
"step": 62
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.77,
|
| 198 |
+
"learning_rate": 0.0008592671998594795,
|
| 199 |
+
"loss": 2.8673,
|
| 200 |
+
"step": 64
|
| 201 |
},
|
| 202 |
{
|
| 203 |
"epoch": 0.8,
|
| 204 |
+
"learning_rate": 0.0008500799488578119,
|
| 205 |
+
"loss": 2.8984,
|
| 206 |
"step": 66
|
| 207 |
},
|
| 208 |
{
|
| 209 |
+
"epoch": 0.82,
|
| 210 |
+
"learning_rate": 0.0008406547574006325,
|
| 211 |
+
"loss": 2.8778,
|
| 212 |
+
"step": 68
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.85,
|
| 216 |
+
"learning_rate": 0.0008309980315513443,
|
| 217 |
+
"loss": 2.8978,
|
| 218 |
+
"step": 70
|
| 219 |
},
|
| 220 |
{
|
| 221 |
"epoch": 0.87,
|
| 222 |
+
"learning_rate": 0.0008211163347414004,
|
| 223 |
+
"loss": 2.8657,
|
| 224 |
"step": 72
|
| 225 |
},
|
| 226 |
{
|
| 227 |
+
"epoch": 0.89,
|
| 228 |
+
"learning_rate": 0.0008110163833093049,
|
| 229 |
+
"loss": 2.881,
|
| 230 |
+
"step": 74
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.92,
|
| 234 |
+
"learning_rate": 0.0008007050419356898,
|
| 235 |
+
"loss": 2.8425,
|
| 236 |
+
"step": 76
|
| 237 |
},
|
| 238 |
{
|
| 239 |
"epoch": 0.94,
|
| 240 |
+
"learning_rate": 0.0007901893189775639,
|
| 241 |
+
"loss": 2.899,
|
| 242 |
"step": 78
|
| 243 |
},
|
| 244 |
{
|
| 245 |
+
"epoch": 0.97,
|
| 246 |
+
"learning_rate": 0.0007794763617049123,
|
| 247 |
+
"loss": 2.8116,
|
| 248 |
+
"step": 80
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.99,
|
| 252 |
+
"learning_rate": 0.0007685734514428766,
|
| 253 |
+
"loss": 2.8995,
|
| 254 |
+
"step": 82
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 1.02,
|
| 258 |
+
"learning_rate": 0.0007574879986228245,
|
| 259 |
+
"loss": 3.874,
|
| 260 |
"step": 84
|
| 261 |
},
|
| 262 |
{
|
| 263 |
+
"epoch": 1.05,
|
| 264 |
+
"learning_rate": 0.000746227537745667,
|
| 265 |
+
"loss": 2.7812,
|
| 266 |
+
"step": 86
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.07,
|
| 270 |
+
"learning_rate": 0.0007347997222608493,
|
| 271 |
+
"loss": 2.7706,
|
| 272 |
+
"step": 88
|
| 273 |
},
|
| 274 |
{
|
| 275 |
"epoch": 1.1,
|
| 276 |
+
"learning_rate": 0.0007232123193644956,
|
| 277 |
+
"loss": 2.727,
|
| 278 |
"step": 90
|
| 279 |
},
|
| 280 |
{
|
| 281 |
+
"epoch": 1.12,
|
| 282 |
+
"learning_rate": 0.0007114732047202433,
|
| 283 |
+
"loss": 2.7466,
|
| 284 |
+
"step": 92
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.15,
|
| 288 |
+
"learning_rate": 0.000699590357106354,
|
| 289 |
+
"loss": 2.7615,
|
| 290 |
+
"step": 94
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 1.17,
|
| 294 |
+
"learning_rate": 0.0006875718529927403,
|
| 295 |
+
"loss": 2.7312,
|
| 296 |
"step": 96
|
| 297 |
},
|
| 298 |
{
|
| 299 |
+
"epoch": 1.19,
|
| 300 |
+
"learning_rate": 0.0006754258610515948,
|
| 301 |
+
"loss": 2.7192,
|
| 302 |
+
"step": 98
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.22,
|
| 306 |
+
"learning_rate": 0.0006631606366053507,
|
| 307 |
+
"loss": 2.7178,
|
| 308 |
+
"step": 100
|
| 309 |
},
|
| 310 |
{
|
| 311 |
"epoch": 1.24,
|
| 312 |
+
"learning_rate": 0.0006507845160157477,
|
| 313 |
+
"loss": 2.7426,
|
| 314 |
"step": 102
|
| 315 |
},
|
| 316 |
{
|
| 317 |
+
"epoch": 1.27,
|
| 318 |
+
"learning_rate": 0.0006383059110178205,
|
| 319 |
+
"loss": 2.78,
|
| 320 |
+
"step": 104
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.29,
|
| 324 |
+
"learning_rate": 0.0006257333030026537,
|
| 325 |
+
"loss": 2.801,
|
| 326 |
+
"step": 106
|
| 327 |
},
|
| 328 |
{
|
| 329 |
"epoch": 1.31,
|
| 330 |
+
"learning_rate": 0.0006130752372527982,
|
| 331 |
+
"loss": 2.8101,
|
| 332 |
"step": 108
|
| 333 |
},
|
| 334 |
{
|
| 335 |
+
"epoch": 1.34,
|
| 336 |
+
"learning_rate": 0.0006003403171342563,
|
| 337 |
+
"loss": 2.8212,
|
| 338 |
+
"step": 110
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.36,
|
| 342 |
+
"learning_rate": 0.0005875371982489958,
|
| 343 |
+
"loss": 2.8073,
|
| 344 |
+
"step": 112
|
| 345 |
},
|
| 346 |
{
|
| 347 |
"epoch": 1.39,
|
| 348 |
+
"learning_rate": 0.0005746745825519538,
|
| 349 |
+
"loss": 2.7252,
|
| 350 |
"step": 114
|
| 351 |
},
|
| 352 |
{
|
| 353 |
+
"epoch": 1.41,
|
| 354 |
+
"learning_rate": 0.0005617612124365409,
|
| 355 |
+
"loss": 2.783,
|
| 356 |
+
"step": 116
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.44,
|
| 360 |
+
"learning_rate": 0.0005488058647926577,
|
| 361 |
+
"loss": 2.7034,
|
| 362 |
+
"step": 118
|
| 363 |
},
|
| 364 |
{
|
| 365 |
"epoch": 1.46,
|
| 366 |
+
"learning_rate": 0.0005358173450412649,
|
| 367 |
+
"loss": 2.7864,
|
| 368 |
"step": 120
|
| 369 |
},
|
| 370 |
{
|
| 371 |
+
"epoch": 1.48,
|
| 372 |
+
"learning_rate": 0.0005228044811495631,
|
| 373 |
+
"loss": 2.7136,
|
| 374 |
+
"step": 122
|
| 375 |
},
|
| 376 |
{
|
| 377 |
+
"epoch": 1.51,
|
| 378 |
+
"learning_rate": 0.0005097761176308471,
|
| 379 |
+
"loss": 2.762,
|
| 380 |
+
"step": 124
|
| 381 |
},
|
| 382 |
{
|
| 383 |
+
"epoch": 1.53,
|
| 384 |
+
"learning_rate": 0.0004967411095331149,
|
| 385 |
+
"loss": 2.7633,
|
| 386 |
+
"step": 126
|
| 387 |
},
|
| 388 |
{
|
| 389 |
+
"epoch": 1.56,
|
| 390 |
+
"learning_rate": 0.0004837083164205159,
|
| 391 |
+
"loss": 2.7863,
|
| 392 |
+
"step": 128
|
| 393 |
},
|
| 394 |
{
|
| 395 |
+
"epoch": 1.58,
|
| 396 |
+
"learning_rate": 0.00047068659635173026,
|
| 397 |
+
"loss": 2.7523,
|
| 398 |
+
"step": 130
|
| 399 |
},
|
| 400 |
{
|
| 401 |
+
"epoch": 1.6,
|
| 402 |
+
"learning_rate": 0.00045768479985937196,
|
| 403 |
+
"loss": 2.6834,
|
| 404 |
+
"step": 132
|
| 405 |
},
|
| 406 |
{
|
| 407 |
+
"epoch": 1.63,
|
| 408 |
+
"learning_rate": 0.0004447117639345052,
|
| 409 |
+
"loss": 2.7107,
|
| 410 |
+
"step": 134
|
| 411 |
},
|
| 412 |
{
|
| 413 |
+
"epoch": 1.65,
|
| 414 |
+
"learning_rate": 0.0004317763060203664,
|
| 415 |
+
"loss": 2.7554,
|
| 416 |
+
"step": 136
|
| 417 |
},
|
| 418 |
{
|
| 419 |
+
"epoch": 1.68,
|
| 420 |
+
"learning_rate": 0.0004188872180193723,
|
| 421 |
+
"loss": 2.7709,
|
| 422 |
+
"step": 138
|
| 423 |
},
|
| 424 |
{
|
| 425 |
+
"epoch": 1.7,
|
| 426 |
+
"learning_rate": 0.00040605326031748645,
|
| 427 |
+
"loss": 2.7199,
|
| 428 |
+
"step": 140
|
| 429 |
},
|
| 430 |
{
|
| 431 |
+
"epoch": 1.73,
|
| 432 |
+
"learning_rate": 0.0003932831558300074,
|
| 433 |
+
"loss": 2.702,
|
| 434 |
+
"step": 142
|
| 435 |
},
|
| 436 |
{
|
| 437 |
+
"epoch": 1.75,
|
| 438 |
+
"learning_rate": 0.0003805855840728246,
|
| 439 |
+
"loss": 2.7447,
|
| 440 |
+
"step": 144
|
| 441 |
},
|
| 442 |
{
|
| 443 |
+
"epoch": 1.77,
|
| 444 |
+
"learning_rate": 0.00036796917526317154,
|
| 445 |
+
"loss": 2.7329,
|
| 446 |
+
"step": 146
|
| 447 |
},
|
| 448 |
{
|
| 449 |
+
"epoch": 1.8,
|
| 450 |
+
"learning_rate": 0.0003554425044538868,
|
| 451 |
+
"loss": 2.7188,
|
| 452 |
+
"step": 148
|
| 453 |
},
|
| 454 |
{
|
| 455 |
+
"epoch": 1.82,
|
| 456 |
+
"learning_rate": 0.00034301408570516746,
|
| 457 |
+
"loss": 2.7646,
|
| 458 |
+
"step": 150
|
|
|
|
|
|
|
|
|
|
| 459 |
}
|
| 460 |
],
|
| 461 |
+
"max_steps": 246,
|
| 462 |
+
"num_train_epochs": 3,
|
| 463 |
+
"total_flos": 1.4229744023408476e+18,
|
| 464 |
"trial_name": null,
|
| 465 |
"trial_params": null
|
| 466 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4527
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69a6570fe353bddee22ecfde7f0ce22259d3ebe6bcb4e301b37e008be4d9697d
|
| 3 |
size 4527
|