Training in progress, step 4500, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
|
@@ -23,13 +23,13 @@
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
|
|
|
| 26 |
"q_proj",
|
| 27 |
"v_proj",
|
| 28 |
-
"
|
| 29 |
-
"up_proj",
|
| 30 |
"down_proj",
|
| 31 |
-
"
|
| 32 |
-
"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
|
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
| 26 |
+
"gate_proj",
|
| 27 |
"q_proj",
|
| 28 |
"v_proj",
|
| 29 |
+
"o_proj",
|
|
|
|
| 30 |
"down_proj",
|
| 31 |
+
"k_proj",
|
| 32 |
+
"up_proj"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 161533160
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:caf08a37d467af8be6ee4d7f8398900235c664d83757737f8601af66dd61bee5
|
| 3 |
size 161533160
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 323292202
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f21859111603253f67b1ca4afa8ce4858e0978e5685b991a3d9c2883b821035
|
| 3 |
size 323292202
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:712366a72cf55e9140e7cb32d65c59ab0aec41cadb87ddf8db2ed2cbbb7181be
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 100,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -164,6 +164,496 @@
|
|
| 164 |
"learning_rate": 5.513245033112583e-05,
|
| 165 |
"loss": 0.7213,
|
| 166 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 167 |
}
|
| 168 |
],
|
| 169 |
"logging_steps": 50,
|
|
@@ -183,7 +673,7 @@
|
|
| 183 |
"attributes": {}
|
| 184 |
}
|
| 185 |
},
|
| 186 |
-
"total_flos":
|
| 187 |
"train_batch_size": 1,
|
| 188 |
"trial_name": null,
|
| 189 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7450331125827815,
|
| 6 |
"eval_steps": 100,
|
| 7 |
+
"global_step": 4500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 164 |
"learning_rate": 5.513245033112583e-05,
|
| 165 |
"loss": 0.7213,
|
| 166 |
"step": 1000
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.173841059602649,
|
| 170 |
+
"grad_norm": 1.8289754390716553,
|
| 171 |
+
"learning_rate": 5.789183222958058e-05,
|
| 172 |
+
"loss": 0.7335,
|
| 173 |
+
"step": 1050
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.18211920529801323,
|
| 177 |
+
"grad_norm": 1.4989681243896484,
|
| 178 |
+
"learning_rate": 6.065121412803533e-05,
|
| 179 |
+
"loss": 0.7326,
|
| 180 |
+
"step": 1100
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.19039735099337748,
|
| 184 |
+
"grad_norm": 1.5326098203659058,
|
| 185 |
+
"learning_rate": 6.341059602649006e-05,
|
| 186 |
+
"loss": 0.7311,
|
| 187 |
+
"step": 1150
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.1986754966887417,
|
| 191 |
+
"grad_norm": 1.4897147417068481,
|
| 192 |
+
"learning_rate": 6.616997792494481e-05,
|
| 193 |
+
"loss": 0.6918,
|
| 194 |
+
"step": 1200
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.20695364238410596,
|
| 198 |
+
"grad_norm": 1.634765863418579,
|
| 199 |
+
"learning_rate": 6.892935982339957e-05,
|
| 200 |
+
"loss": 0.7051,
|
| 201 |
+
"step": 1250
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.2152317880794702,
|
| 205 |
+
"grad_norm": 1.4463587999343872,
|
| 206 |
+
"learning_rate": 7.168874172185431e-05,
|
| 207 |
+
"loss": 0.6955,
|
| 208 |
+
"step": 1300
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.22350993377483444,
|
| 212 |
+
"grad_norm": 1.632133960723877,
|
| 213 |
+
"learning_rate": 7.444812362030905e-05,
|
| 214 |
+
"loss": 0.6901,
|
| 215 |
+
"step": 1350
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.23178807947019867,
|
| 219 |
+
"grad_norm": 1.4062328338623047,
|
| 220 |
+
"learning_rate": 7.72075055187638e-05,
|
| 221 |
+
"loss": 0.6833,
|
| 222 |
+
"step": 1400
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.24006622516556292,
|
| 226 |
+
"grad_norm": 1.2914466857910156,
|
| 227 |
+
"learning_rate": 7.996688741721855e-05,
|
| 228 |
+
"loss": 0.6663,
|
| 229 |
+
"step": 1450
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.24834437086092714,
|
| 233 |
+
"grad_norm": 1.4995919466018677,
|
| 234 |
+
"learning_rate": 8.272626931567329e-05,
|
| 235 |
+
"loss": 0.6959,
|
| 236 |
+
"step": 1500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.25662251655629137,
|
| 240 |
+
"grad_norm": 1.1299749612808228,
|
| 241 |
+
"learning_rate": 8.548565121412803e-05,
|
| 242 |
+
"loss": 0.6685,
|
| 243 |
+
"step": 1550
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.26490066225165565,
|
| 247 |
+
"grad_norm": 1.329004168510437,
|
| 248 |
+
"learning_rate": 8.824503311258279e-05,
|
| 249 |
+
"loss": 0.6678,
|
| 250 |
+
"step": 1600
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.2731788079470199,
|
| 254 |
+
"grad_norm": 1.5191948413848877,
|
| 255 |
+
"learning_rate": 9.100441501103754e-05,
|
| 256 |
+
"loss": 0.6731,
|
| 257 |
+
"step": 1650
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.2814569536423841,
|
| 261 |
+
"grad_norm": 1.739169716835022,
|
| 262 |
+
"learning_rate": 9.376379690949227e-05,
|
| 263 |
+
"loss": 0.6691,
|
| 264 |
+
"step": 1700
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.2897350993377483,
|
| 268 |
+
"grad_norm": 1.2906118631362915,
|
| 269 |
+
"learning_rate": 9.652317880794703e-05,
|
| 270 |
+
"loss": 0.6718,
|
| 271 |
+
"step": 1750
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.2980132450331126,
|
| 275 |
+
"grad_norm": 1.289502501487732,
|
| 276 |
+
"learning_rate": 9.928256070640178e-05,
|
| 277 |
+
"loss": 0.6581,
|
| 278 |
+
"step": 1800
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.30629139072847683,
|
| 282 |
+
"grad_norm": 1.3923128843307495,
|
| 283 |
+
"learning_rate": 9.999872989402833e-05,
|
| 284 |
+
"loss": 0.6589,
|
| 285 |
+
"step": 1850
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.31456953642384106,
|
| 289 |
+
"grad_norm": 1.1048816442489624,
|
| 290 |
+
"learning_rate": 9.999297790520483e-05,
|
| 291 |
+
"loss": 0.6341,
|
| 292 |
+
"step": 1900
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.3228476821192053,
|
| 296 |
+
"grad_norm": 1.3568603992462158,
|
| 297 |
+
"learning_rate": 9.998258777484084e-05,
|
| 298 |
+
"loss": 0.6318,
|
| 299 |
+
"step": 1950
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.33112582781456956,
|
| 303 |
+
"grad_norm": 0.923786997795105,
|
| 304 |
+
"learning_rate": 9.996756046688961e-05,
|
| 305 |
+
"loss": 0.6318,
|
| 306 |
+
"step": 2000
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.3394039735099338,
|
| 310 |
+
"grad_norm": 1.102367877960205,
|
| 311 |
+
"learning_rate": 9.994789737552259e-05,
|
| 312 |
+
"loss": 0.6193,
|
| 313 |
+
"step": 2050
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.347682119205298,
|
| 317 |
+
"grad_norm": 1.0738896131515503,
|
| 318 |
+
"learning_rate": 9.992360032500001e-05,
|
| 319 |
+
"loss": 0.6184,
|
| 320 |
+
"step": 2100
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.35596026490066224,
|
| 324 |
+
"grad_norm": 1.279288649559021,
|
| 325 |
+
"learning_rate": 9.98946715695016e-05,
|
| 326 |
+
"loss": 0.626,
|
| 327 |
+
"step": 2150
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.36423841059602646,
|
| 331 |
+
"grad_norm": 1.2009036540985107,
|
| 332 |
+
"learning_rate": 9.986111379291759e-05,
|
| 333 |
+
"loss": 0.6305,
|
| 334 |
+
"step": 2200
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 0.37251655629139074,
|
| 338 |
+
"grad_norm": 0.8177038431167603,
|
| 339 |
+
"learning_rate": 9.982293010859955e-05,
|
| 340 |
+
"loss": 0.6266,
|
| 341 |
+
"step": 2250
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 0.38079470198675497,
|
| 345 |
+
"grad_norm": 1.2464983463287354,
|
| 346 |
+
"learning_rate": 9.978012405907165e-05,
|
| 347 |
+
"loss": 0.6148,
|
| 348 |
+
"step": 2300
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.3890728476821192,
|
| 352 |
+
"grad_norm": 1.2841860055923462,
|
| 353 |
+
"learning_rate": 9.973269961570195e-05,
|
| 354 |
+
"loss": 0.5946,
|
| 355 |
+
"step": 2350
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 0.3973509933774834,
|
| 359 |
+
"grad_norm": 1.2200431823730469,
|
| 360 |
+
"learning_rate": 9.968066117833401e-05,
|
| 361 |
+
"loss": 0.6166,
|
| 362 |
+
"step": 2400
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.4056291390728477,
|
| 366 |
+
"grad_norm": 1.128247857093811,
|
| 367 |
+
"learning_rate": 9.962401357487863e-05,
|
| 368 |
+
"loss": 0.5992,
|
| 369 |
+
"step": 2450
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.4139072847682119,
|
| 373 |
+
"grad_norm": 1.0683091878890991,
|
| 374 |
+
"learning_rate": 9.956276206086597e-05,
|
| 375 |
+
"loss": 0.6048,
|
| 376 |
+
"step": 2500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.42218543046357615,
|
| 380 |
+
"grad_norm": 1.1819758415222168,
|
| 381 |
+
"learning_rate": 9.949691231895791e-05,
|
| 382 |
+
"loss": 0.5944,
|
| 383 |
+
"step": 2550
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.4304635761589404,
|
| 387 |
+
"grad_norm": 1.0043411254882812,
|
| 388 |
+
"learning_rate": 9.942647045842095e-05,
|
| 389 |
+
"loss": 0.5962,
|
| 390 |
+
"step": 2600
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.43874172185430466,
|
| 394 |
+
"grad_norm": 1.0588668584823608,
|
| 395 |
+
"learning_rate": 9.93514430145593e-05,
|
| 396 |
+
"loss": 0.6067,
|
| 397 |
+
"step": 2650
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.4470198675496689,
|
| 401 |
+
"grad_norm": 0.9364084601402283,
|
| 402 |
+
"learning_rate": 9.927183694810862e-05,
|
| 403 |
+
"loss": 0.5928,
|
| 404 |
+
"step": 2700
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.4552980132450331,
|
| 408 |
+
"grad_norm": 1.155172348022461,
|
| 409 |
+
"learning_rate": 9.918765964459022e-05,
|
| 410 |
+
"loss": 0.5987,
|
| 411 |
+
"step": 2750
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.46357615894039733,
|
| 415 |
+
"grad_norm": 1.1639224290847778,
|
| 416 |
+
"learning_rate": 9.909891891362587e-05,
|
| 417 |
+
"loss": 0.5745,
|
| 418 |
+
"step": 2800
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.4718543046357616,
|
| 422 |
+
"grad_norm": 0.9658174514770508,
|
| 423 |
+
"learning_rate": 9.900562298821323e-05,
|
| 424 |
+
"loss": 0.5825,
|
| 425 |
+
"step": 2850
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.48013245033112584,
|
| 429 |
+
"grad_norm": 1.118033766746521,
|
| 430 |
+
"learning_rate": 9.890778052396205e-05,
|
| 431 |
+
"loss": 0.5806,
|
| 432 |
+
"step": 2900
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.48841059602649006,
|
| 436 |
+
"grad_norm": 0.9781912565231323,
|
| 437 |
+
"learning_rate": 9.880540059829115e-05,
|
| 438 |
+
"loss": 0.5712,
|
| 439 |
+
"step": 2950
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.4966887417218543,
|
| 443 |
+
"grad_norm": 1.2145684957504272,
|
| 444 |
+
"learning_rate": 9.869849270958622e-05,
|
| 445 |
+
"loss": 0.5855,
|
| 446 |
+
"step": 3000
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.5049668874172185,
|
| 450 |
+
"grad_norm": 0.999279260635376,
|
| 451 |
+
"learning_rate": 9.858706677631862e-05,
|
| 452 |
+
"loss": 0.5843,
|
| 453 |
+
"step": 3050
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.5132450331125827,
|
| 457 |
+
"grad_norm": 1.098258137702942,
|
| 458 |
+
"learning_rate": 9.847113313612517e-05,
|
| 459 |
+
"loss": 0.5605,
|
| 460 |
+
"step": 3100
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.5215231788079471,
|
| 464 |
+
"grad_norm": 0.627949059009552,
|
| 465 |
+
"learning_rate": 9.835070254484912e-05,
|
| 466 |
+
"loss": 0.5538,
|
| 467 |
+
"step": 3150
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.5298013245033113,
|
| 471 |
+
"grad_norm": 1.0991902351379395,
|
| 472 |
+
"learning_rate": 9.822578617554219e-05,
|
| 473 |
+
"loss": 0.5555,
|
| 474 |
+
"step": 3200
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.5380794701986755,
|
| 478 |
+
"grad_norm": 0.9670843482017517,
|
| 479 |
+
"learning_rate": 9.8096395617428e-05,
|
| 480 |
+
"loss": 0.5647,
|
| 481 |
+
"step": 3250
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.5463576158940397,
|
| 485 |
+
"grad_norm": 0.9838133454322815,
|
| 486 |
+
"learning_rate": 9.796254287482693e-05,
|
| 487 |
+
"loss": 0.5561,
|
| 488 |
+
"step": 3300
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.554635761589404,
|
| 492 |
+
"grad_norm": 1.1465744972229004,
|
| 493 |
+
"learning_rate": 9.782424036604234e-05,
|
| 494 |
+
"loss": 0.559,
|
| 495 |
+
"step": 3350
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.5629139072847682,
|
| 499 |
+
"grad_norm": 1.1423758268356323,
|
| 500 |
+
"learning_rate": 9.768150092220849e-05,
|
| 501 |
+
"loss": 0.5517,
|
| 502 |
+
"step": 3400
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.5711920529801324,
|
| 506 |
+
"grad_norm": 1.1365066766738892,
|
| 507 |
+
"learning_rate": 9.753433778610008e-05,
|
| 508 |
+
"loss": 0.5464,
|
| 509 |
+
"step": 3450
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.5794701986754967,
|
| 513 |
+
"grad_norm": 0.81045001745224,
|
| 514 |
+
"learning_rate": 9.738276461090371e-05,
|
| 515 |
+
"loss": 0.5493,
|
| 516 |
+
"step": 3500
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.5877483443708609,
|
| 520 |
+
"grad_norm": 1.0236687660217285,
|
| 521 |
+
"learning_rate": 9.72267954589511e-05,
|
| 522 |
+
"loss": 0.567,
|
| 523 |
+
"step": 3550
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.5960264900662252,
|
| 527 |
+
"grad_norm": 0.9495602250099182,
|
| 528 |
+
"learning_rate": 9.706644480041455e-05,
|
| 529 |
+
"loss": 0.5474,
|
| 530 |
+
"step": 3600
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.6043046357615894,
|
| 534 |
+
"grad_norm": 0.960738480091095,
|
| 535 |
+
"learning_rate": 9.690172751196437e-05,
|
| 536 |
+
"loss": 0.5238,
|
| 537 |
+
"step": 3650
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.6125827814569537,
|
| 541 |
+
"grad_norm": 1.0488675832748413,
|
| 542 |
+
"learning_rate": 9.67326588753887e-05,
|
| 543 |
+
"loss": 0.521,
|
| 544 |
+
"step": 3700
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.6208609271523179,
|
| 548 |
+
"grad_norm": 0.8753538727760315,
|
| 549 |
+
"learning_rate": 9.65592545761758e-05,
|
| 550 |
+
"loss": 0.5232,
|
| 551 |
+
"step": 3750
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.6291390728476821,
|
| 555 |
+
"grad_norm": 1.0551217794418335,
|
| 556 |
+
"learning_rate": 9.638153070205871e-05,
|
| 557 |
+
"loss": 0.5432,
|
| 558 |
+
"step": 3800
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.6374172185430463,
|
| 562 |
+
"grad_norm": 1.158676028251648,
|
| 563 |
+
"learning_rate": 9.619950374152278e-05,
|
| 564 |
+
"loss": 0.5416,
|
| 565 |
+
"step": 3850
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 0.6456953642384106,
|
| 569 |
+
"grad_norm": 1.0036752223968506,
|
| 570 |
+
"learning_rate": 9.601319058227589e-05,
|
| 571 |
+
"loss": 0.5496,
|
| 572 |
+
"step": 3900
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.6539735099337748,
|
| 576 |
+
"grad_norm": 0.8905594348907471,
|
| 577 |
+
"learning_rate": 9.58226085096817e-05,
|
| 578 |
+
"loss": 0.5335,
|
| 579 |
+
"step": 3950
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.6622516556291391,
|
| 583 |
+
"grad_norm": 0.9868190884590149,
|
| 584 |
+
"learning_rate": 9.562777520515598e-05,
|
| 585 |
+
"loss": 0.5094,
|
| 586 |
+
"step": 4000
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.6705298013245033,
|
| 590 |
+
"grad_norm": 0.9672690629959106,
|
| 591 |
+
"learning_rate": 9.542870874452618e-05,
|
| 592 |
+
"loss": 0.5061,
|
| 593 |
+
"step": 4050
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.6788079470198676,
|
| 597 |
+
"grad_norm": 1.044123888015747,
|
| 598 |
+
"learning_rate": 9.52254275963545e-05,
|
| 599 |
+
"loss": 0.5253,
|
| 600 |
+
"step": 4100
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.6870860927152318,
|
| 604 |
+
"grad_norm": 1.0346958637237549,
|
| 605 |
+
"learning_rate": 9.501795062022434e-05,
|
| 606 |
+
"loss": 0.5149,
|
| 607 |
+
"step": 4150
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 0.695364238410596,
|
| 611 |
+
"grad_norm": 1.0799248218536377,
|
| 612 |
+
"learning_rate": 9.48062970649907e-05,
|
| 613 |
+
"loss": 0.5207,
|
| 614 |
+
"step": 4200
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.7036423841059603,
|
| 618 |
+
"grad_norm": 0.9847925901412964,
|
| 619 |
+
"learning_rate": 9.459048656699427e-05,
|
| 620 |
+
"loss": 0.531,
|
| 621 |
+
"step": 4250
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.7119205298013245,
|
| 625 |
+
"grad_norm": 1.134179949760437,
|
| 626 |
+
"learning_rate": 9.43705391482397e-05,
|
| 627 |
+
"loss": 0.5202,
|
| 628 |
+
"step": 4300
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 0.7201986754966887,
|
| 632 |
+
"grad_norm": 0.9750307202339172,
|
| 633 |
+
"learning_rate": 9.414647521453798e-05,
|
| 634 |
+
"loss": 0.5183,
|
| 635 |
+
"step": 4350
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 0.7284768211920529,
|
| 639 |
+
"grad_norm": 1.372010350227356,
|
| 640 |
+
"learning_rate": 9.391831555361341e-05,
|
| 641 |
+
"loss": 0.5203,
|
| 642 |
+
"step": 4400
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.7367549668874173,
|
| 646 |
+
"grad_norm": 0.9671643376350403,
|
| 647 |
+
"learning_rate": 9.36860813331748e-05,
|
| 648 |
+
"loss": 0.5313,
|
| 649 |
+
"step": 4450
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.7450331125827815,
|
| 653 |
+
"grad_norm": 1.270264983177185,
|
| 654 |
+
"learning_rate": 9.344979409895178e-05,
|
| 655 |
+
"loss": 0.5236,
|
| 656 |
+
"step": 4500
|
| 657 |
}
|
| 658 |
],
|
| 659 |
"logging_steps": 50,
|
|
|
|
| 673 |
"attributes": {}
|
| 674 |
}
|
| 675 |
},
|
| 676 |
+
"total_flos": 3.5270617397723136e+16,
|
| 677 |
"train_batch_size": 1,
|
| 678 |
"trial_name": null,
|
| 679 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2543e07a37d2c3de3cd8e1d682eb10ddfc7a8cf84209a331e0b0e44870af81c3
|
| 3 |
size 5752
|