Commit
•
e25e764
1
Parent(s):
1d624d1
Training in progress, step 14000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1715561468
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba212990d194dca4f44ced4ca63ccf9ef184764cc7f8172c878fbac719c06d49
|
| 3 |
size 1715561468
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3431474364
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aaf08772128513652918e0bba4e572e2c66384e3a11c4c8c40940608c79e2518
|
| 3 |
size 3431474364
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:811402e95375709703215e6c97e1c03c4e9ff165e81e964713fe6305f44ed804
|
| 3 |
size 14244
|
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 sha256:1f2d0d921e9513c8f152071073b4ae78b683c89f70f41659678cef15c9b0b508
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 1000,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -121,6 +121,494 @@
|
|
| 121 |
"learning_rate": 4.999922185102915e-05,
|
| 122 |
"loss": 1.0514,
|
| 123 |
"step": 2800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 124 |
}
|
| 125 |
],
|
| 126 |
"logging_steps": 200,
|
|
@@ -140,7 +628,7 @@
|
|
| 140 |
"attributes": {}
|
| 141 |
}
|
| 142 |
},
|
| 143 |
-
"total_flos":
|
| 144 |
"train_batch_size": 6,
|
| 145 |
"trial_name": null,
|
| 146 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.6289873303980591,
|
| 5 |
"eval_steps": 1000,
|
| 6 |
+
"global_step": 14000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 121 |
"learning_rate": 4.999922185102915e-05,
|
| 122 |
"loss": 1.0514,
|
| 123 |
"step": 2800
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.13478299937101268,
|
| 127 |
+
"grad_norm": 2.352109432220459,
|
| 128 |
+
"learning_rate": 4.9999106504350065e-05,
|
| 129 |
+
"loss": 1.0327,
|
| 130 |
+
"step": 3000
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.13478299937101268,
|
| 134 |
+
"eval_loss": 3.369852066040039,
|
| 135 |
+
"eval_runtime": 1064.8233,
|
| 136 |
+
"eval_samples_per_second": 9.301,
|
| 137 |
+
"eval_steps_per_second": 0.146,
|
| 138 |
+
"step": 3000
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.14376853266241352,
|
| 142 |
+
"grad_norm": 0.7272612452507019,
|
| 143 |
+
"learning_rate": 4.999898318918469e-05,
|
| 144 |
+
"loss": 1.0379,
|
| 145 |
+
"step": 3200
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.15275406595381436,
|
| 149 |
+
"grad_norm": 1.021616816520691,
|
| 150 |
+
"learning_rate": 4.999885190557234e-05,
|
| 151 |
+
"loss": 1.0416,
|
| 152 |
+
"step": 3400
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.1617395992452152,
|
| 156 |
+
"grad_norm": 2.4565377235412598,
|
| 157 |
+
"learning_rate": 4.999871265355485e-05,
|
| 158 |
+
"loss": 1.0212,
|
| 159 |
+
"step": 3600
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.17072513253661606,
|
| 163 |
+
"grad_norm": 20.56285858154297,
|
| 164 |
+
"learning_rate": 4.9998565433176624e-05,
|
| 165 |
+
"loss": 1.0219,
|
| 166 |
+
"step": 3800
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.1797106658280169,
|
| 170 |
+
"grad_norm": 0.7909038662910461,
|
| 171 |
+
"learning_rate": 4.9998410244484574e-05,
|
| 172 |
+
"loss": 1.0075,
|
| 173 |
+
"step": 4000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.1797106658280169,
|
| 177 |
+
"eval_loss": 3.339078903198242,
|
| 178 |
+
"eval_runtime": 1066.4833,
|
| 179 |
+
"eval_samples_per_second": 9.287,
|
| 180 |
+
"eval_steps_per_second": 0.145,
|
| 181 |
+
"step": 4000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.18869619911941773,
|
| 185 |
+
"grad_norm": 2.09454607963562,
|
| 186 |
+
"learning_rate": 4.999824708752817e-05,
|
| 187 |
+
"loss": 0.9825,
|
| 188 |
+
"step": 4200
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.19768173241081857,
|
| 192 |
+
"grad_norm": 2.223658323287964,
|
| 193 |
+
"learning_rate": 4.999807596235943e-05,
|
| 194 |
+
"loss": 0.9851,
|
| 195 |
+
"step": 4400
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.20666726570221944,
|
| 199 |
+
"grad_norm": 1.121969223022461,
|
| 200 |
+
"learning_rate": 4.999789686903289e-05,
|
| 201 |
+
"loss": 1.0041,
|
| 202 |
+
"step": 4600
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.21565279899362028,
|
| 206 |
+
"grad_norm": 4.0251312255859375,
|
| 207 |
+
"learning_rate": 4.9997709807605626e-05,
|
| 208 |
+
"loss": 0.9841,
|
| 209 |
+
"step": 4800
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.22463833228502111,
|
| 213 |
+
"grad_norm": 1.6437472105026245,
|
| 214 |
+
"learning_rate": 4.9997514778137275e-05,
|
| 215 |
+
"loss": 0.9483,
|
| 216 |
+
"step": 5000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.22463833228502111,
|
| 220 |
+
"eval_loss": 3.2980644702911377,
|
| 221 |
+
"eval_runtime": 1067.9785,
|
| 222 |
+
"eval_samples_per_second": 9.274,
|
| 223 |
+
"eval_steps_per_second": 0.145,
|
| 224 |
+
"step": 5000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.23362386557642195,
|
| 228 |
+
"grad_norm": 0.8991021513938904,
|
| 229 |
+
"learning_rate": 4.999731178069001e-05,
|
| 230 |
+
"loss": 0.9541,
|
| 231 |
+
"step": 5200
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.24260939886782282,
|
| 235 |
+
"grad_norm": 3.1451597213745117,
|
| 236 |
+
"learning_rate": 4.999710081532853e-05,
|
| 237 |
+
"loss": 0.9589,
|
| 238 |
+
"step": 5400
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.2515949321592236,
|
| 242 |
+
"grad_norm": 2.142390489578247,
|
| 243 |
+
"learning_rate": 4.999688188212007e-05,
|
| 244 |
+
"loss": 0.9677,
|
| 245 |
+
"step": 5600
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.2605804654506245,
|
| 249 |
+
"grad_norm": 2.2872331142425537,
|
| 250 |
+
"learning_rate": 4.999665498113444e-05,
|
| 251 |
+
"loss": 0.962,
|
| 252 |
+
"step": 5800
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.26956599874202536,
|
| 256 |
+
"grad_norm": 2.730259418487549,
|
| 257 |
+
"learning_rate": 4.999642011244394e-05,
|
| 258 |
+
"loss": 0.9581,
|
| 259 |
+
"step": 6000
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.26956599874202536,
|
| 263 |
+
"eval_loss": 3.3341598510742188,
|
| 264 |
+
"eval_runtime": 1066.5406,
|
| 265 |
+
"eval_samples_per_second": 9.286,
|
| 266 |
+
"eval_steps_per_second": 0.145,
|
| 267 |
+
"step": 6000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.2785515320334262,
|
| 271 |
+
"grad_norm": 2.8416945934295654,
|
| 272 |
+
"learning_rate": 4.999617727612344e-05,
|
| 273 |
+
"loss": 0.9675,
|
| 274 |
+
"step": 6200
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.28753706532482703,
|
| 278 |
+
"grad_norm": 2.8148677349090576,
|
| 279 |
+
"learning_rate": 4.9995926472250356e-05,
|
| 280 |
+
"loss": 0.9411,
|
| 281 |
+
"step": 6400
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.2965225986162279,
|
| 285 |
+
"grad_norm": 1.3317234516143799,
|
| 286 |
+
"learning_rate": 4.999566770090462e-05,
|
| 287 |
+
"loss": 0.9279,
|
| 288 |
+
"step": 6600
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.3055081319076287,
|
| 292 |
+
"grad_norm": 3.403902053833008,
|
| 293 |
+
"learning_rate": 4.999540096216872e-05,
|
| 294 |
+
"loss": 0.9293,
|
| 295 |
+
"step": 6800
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.31449366519902955,
|
| 299 |
+
"grad_norm": 1.70892333984375,
|
| 300 |
+
"learning_rate": 4.9995126256127675e-05,
|
| 301 |
+
"loss": 0.9475,
|
| 302 |
+
"step": 7000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.31449366519902955,
|
| 306 |
+
"eval_loss": 3.238970994949341,
|
| 307 |
+
"eval_runtime": 1068.527,
|
| 308 |
+
"eval_samples_per_second": 9.269,
|
| 309 |
+
"eval_steps_per_second": 0.145,
|
| 310 |
+
"step": 7000
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.3234791984904304,
|
| 314 |
+
"grad_norm": 3.11971378326416,
|
| 315 |
+
"learning_rate": 4.999484358286907e-05,
|
| 316 |
+
"loss": 0.9465,
|
| 317 |
+
"step": 7200
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.3324647317818312,
|
| 321 |
+
"grad_norm": 1.395370364189148,
|
| 322 |
+
"learning_rate": 4.9994552942482975e-05,
|
| 323 |
+
"loss": 0.9445,
|
| 324 |
+
"step": 7400
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.3414502650732321,
|
| 328 |
+
"grad_norm": 6.5639424324035645,
|
| 329 |
+
"learning_rate": 4.999425433506204e-05,
|
| 330 |
+
"loss": 0.9263,
|
| 331 |
+
"step": 7600
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.35043579836463296,
|
| 335 |
+
"grad_norm": 2.2011075019836426,
|
| 336 |
+
"learning_rate": 4.999394776070146e-05,
|
| 337 |
+
"loss": 0.9193,
|
| 338 |
+
"step": 7800
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.3594213316560338,
|
| 342 |
+
"grad_norm": 2.9525458812713623,
|
| 343 |
+
"learning_rate": 4.999363321949895e-05,
|
| 344 |
+
"loss": 0.9405,
|
| 345 |
+
"step": 8000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.3594213316560338,
|
| 349 |
+
"eval_loss": 3.2370519638061523,
|
| 350 |
+
"eval_runtime": 1068.6545,
|
| 351 |
+
"eval_samples_per_second": 9.268,
|
| 352 |
+
"eval_steps_per_second": 0.145,
|
| 353 |
+
"step": 8000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.36840686494743463,
|
| 357 |
+
"grad_norm": 4.726866245269775,
|
| 358 |
+
"learning_rate": 4.999331071155477e-05,
|
| 359 |
+
"loss": 0.9391,
|
| 360 |
+
"step": 8200
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.37739239823883547,
|
| 364 |
+
"grad_norm": 2.23179292678833,
|
| 365 |
+
"learning_rate": 4.9992980236971723e-05,
|
| 366 |
+
"loss": 0.9352,
|
| 367 |
+
"step": 8400
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.3863779315302363,
|
| 371 |
+
"grad_norm": 2.175626516342163,
|
| 372 |
+
"learning_rate": 4.9992641795855134e-05,
|
| 373 |
+
"loss": 0.9359,
|
| 374 |
+
"step": 8600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.39536346482163714,
|
| 378 |
+
"grad_norm": 5.489994525909424,
|
| 379 |
+
"learning_rate": 4.9992295388312895e-05,
|
| 380 |
+
"loss": 0.918,
|
| 381 |
+
"step": 8800
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.404348998113038,
|
| 385 |
+
"grad_norm": 1.484823226928711,
|
| 386 |
+
"learning_rate": 4.9991941014455414e-05,
|
| 387 |
+
"loss": 0.9075,
|
| 388 |
+
"step": 9000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.404348998113038,
|
| 392 |
+
"eval_loss": 3.1722910404205322,
|
| 393 |
+
"eval_runtime": 1070.0307,
|
| 394 |
+
"eval_samples_per_second": 9.256,
|
| 395 |
+
"eval_steps_per_second": 0.145,
|
| 396 |
+
"step": 9000
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.4133345314044389,
|
| 400 |
+
"grad_norm": 1.1743195056915283,
|
| 401 |
+
"learning_rate": 4.9991578674395656e-05,
|
| 402 |
+
"loss": 0.9116,
|
| 403 |
+
"step": 9200
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.4223200646958397,
|
| 407 |
+
"grad_norm": 4.027889728546143,
|
| 408 |
+
"learning_rate": 4.999120836824912e-05,
|
| 409 |
+
"loss": 0.9023,
|
| 410 |
+
"step": 9400
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.43130559798724055,
|
| 414 |
+
"grad_norm": 3.1647088527679443,
|
| 415 |
+
"learning_rate": 4.9990830096133826e-05,
|
| 416 |
+
"loss": 0.8992,
|
| 417 |
+
"step": 9600
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.4402911312786414,
|
| 421 |
+
"grad_norm": 1.6494026184082031,
|
| 422 |
+
"learning_rate": 4.9990443858170366e-05,
|
| 423 |
+
"loss": 0.8881,
|
| 424 |
+
"step": 9800
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.44927666457004223,
|
| 428 |
+
"grad_norm": 2.5967679023742676,
|
| 429 |
+
"learning_rate": 4.999004965448184e-05,
|
| 430 |
+
"loss": 0.8889,
|
| 431 |
+
"step": 10000
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.44927666457004223,
|
| 435 |
+
"eval_loss": 3.1767914295196533,
|
| 436 |
+
"eval_runtime": 1067.4091,
|
| 437 |
+
"eval_samples_per_second": 9.279,
|
| 438 |
+
"eval_steps_per_second": 0.145,
|
| 439 |
+
"step": 10000
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.45826219786144307,
|
| 443 |
+
"grad_norm": 2.703774929046631,
|
| 444 |
+
"learning_rate": 4.998964748519391e-05,
|
| 445 |
+
"loss": 0.8845,
|
| 446 |
+
"step": 10200
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.4672477311528439,
|
| 450 |
+
"grad_norm": 5.934618949890137,
|
| 451 |
+
"learning_rate": 4.998923735043477e-05,
|
| 452 |
+
"loss": 0.899,
|
| 453 |
+
"step": 10400
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.47623326444424474,
|
| 457 |
+
"grad_norm": 7.952963352203369,
|
| 458 |
+
"learning_rate": 4.9988819250335136e-05,
|
| 459 |
+
"loss": 0.8968,
|
| 460 |
+
"step": 10600
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.48521879773564563,
|
| 464 |
+
"grad_norm": 3.2846908569335938,
|
| 465 |
+
"learning_rate": 4.99883931850283e-05,
|
| 466 |
+
"loss": 0.8687,
|
| 467 |
+
"step": 10800
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.4942043310270465,
|
| 471 |
+
"grad_norm": 1.9633086919784546,
|
| 472 |
+
"learning_rate": 4.998795915465005e-05,
|
| 473 |
+
"loss": 0.8537,
|
| 474 |
+
"step": 11000
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.4942043310270465,
|
| 478 |
+
"eval_loss": 3.1828198432922363,
|
| 479 |
+
"eval_runtime": 1068.8128,
|
| 480 |
+
"eval_samples_per_second": 9.266,
|
| 481 |
+
"eval_steps_per_second": 0.145,
|
| 482 |
+
"step": 11000
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.5031898643184473,
|
| 486 |
+
"grad_norm": 6.807458400726318,
|
| 487 |
+
"learning_rate": 4.9987517159338744e-05,
|
| 488 |
+
"loss": 0.8482,
|
| 489 |
+
"step": 11200
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.5121753976098481,
|
| 493 |
+
"grad_norm": 2.9921388626098633,
|
| 494 |
+
"learning_rate": 4.998706719923526e-05,
|
| 495 |
+
"loss": 0.8662,
|
| 496 |
+
"step": 11400
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.521160930901249,
|
| 500 |
+
"grad_norm": 0.7828212380409241,
|
| 501 |
+
"learning_rate": 4.998660927448304e-05,
|
| 502 |
+
"loss": 0.88,
|
| 503 |
+
"step": 11600
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.5301464641926499,
|
| 507 |
+
"grad_norm": 3.1086294651031494,
|
| 508 |
+
"learning_rate": 4.9986143385228026e-05,
|
| 509 |
+
"loss": 0.8536,
|
| 510 |
+
"step": 11800
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.5391319974840507,
|
| 514 |
+
"grad_norm": 3.759007453918457,
|
| 515 |
+
"learning_rate": 4.998566953161874e-05,
|
| 516 |
+
"loss": 0.8321,
|
| 517 |
+
"step": 12000
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 0.5391319974840507,
|
| 521 |
+
"eval_loss": 3.1765565872192383,
|
| 522 |
+
"eval_runtime": 1069.9445,
|
| 523 |
+
"eval_samples_per_second": 9.257,
|
| 524 |
+
"eval_steps_per_second": 0.145,
|
| 525 |
+
"step": 12000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.5481175307754516,
|
| 529 |
+
"grad_norm": 4.347619533538818,
|
| 530 |
+
"learning_rate": 4.9985187713806206e-05,
|
| 531 |
+
"loss": 0.8713,
|
| 532 |
+
"step": 12200
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.5571030640668524,
|
| 536 |
+
"grad_norm": 2.748655080795288,
|
| 537 |
+
"learning_rate": 4.9984697931944024e-05,
|
| 538 |
+
"loss": 0.8457,
|
| 539 |
+
"step": 12400
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.5660885973582532,
|
| 543 |
+
"grad_norm": 2.891540288925171,
|
| 544 |
+
"learning_rate": 4.998420018618829e-05,
|
| 545 |
+
"loss": 0.8212,
|
| 546 |
+
"step": 12600
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.5750741306496541,
|
| 550 |
+
"grad_norm": 4.089766025543213,
|
| 551 |
+
"learning_rate": 4.998369447669768e-05,
|
| 552 |
+
"loss": 0.8288,
|
| 553 |
+
"step": 12800
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.5840596639410549,
|
| 557 |
+
"grad_norm": 4.722995758056641,
|
| 558 |
+
"learning_rate": 4.9983180803633376e-05,
|
| 559 |
+
"loss": 0.8757,
|
| 560 |
+
"step": 13000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.5840596639410549,
|
| 564 |
+
"eval_loss": 3.168459892272949,
|
| 565 |
+
"eval_runtime": 1070.7464,
|
| 566 |
+
"eval_samples_per_second": 9.25,
|
| 567 |
+
"eval_steps_per_second": 0.145,
|
| 568 |
+
"step": 13000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.5930451972324557,
|
| 572 |
+
"grad_norm": 7.390491008758545,
|
| 573 |
+
"learning_rate": 4.998265916715912e-05,
|
| 574 |
+
"loss": 0.8477,
|
| 575 |
+
"step": 13200
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.6020307305238566,
|
| 579 |
+
"grad_norm": 2.4633262157440186,
|
| 580 |
+
"learning_rate": 4.9982129567441185e-05,
|
| 581 |
+
"loss": 0.8415,
|
| 582 |
+
"step": 13400
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 0.6110162638152574,
|
| 586 |
+
"grad_norm": 5.4892473220825195,
|
| 587 |
+
"learning_rate": 4.998159200464837e-05,
|
| 588 |
+
"loss": 0.8176,
|
| 589 |
+
"step": 13600
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.6200017971066583,
|
| 593 |
+
"grad_norm": 4.862381458282471,
|
| 594 |
+
"learning_rate": 4.998104647895203e-05,
|
| 595 |
+
"loss": 0.8336,
|
| 596 |
+
"step": 13800
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.6289873303980591,
|
| 600 |
+
"grad_norm": 8.079172134399414,
|
| 601 |
+
"learning_rate": 4.998049299052606e-05,
|
| 602 |
+
"loss": 0.8147,
|
| 603 |
+
"step": 14000
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.6289873303980591,
|
| 607 |
+
"eval_loss": 3.1354148387908936,
|
| 608 |
+
"eval_runtime": 1070.1274,
|
| 609 |
+
"eval_samples_per_second": 9.255,
|
| 610 |
+
"eval_steps_per_second": 0.145,
|
| 611 |
+
"step": 14000
|
| 612 |
}
|
| 613 |
],
|
| 614 |
"logging_steps": 200,
|
|
|
|
| 628 |
"attributes": {}
|
| 629 |
}
|
| 630 |
},
|
| 631 |
+
"total_flos": 2.00704631758848e+17,
|
| 632 |
"train_batch_size": 6,
|
| 633 |
"trial_name": null,
|
| 634 |
"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 5240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:befd02aaf8966ad3b2e0325fdff20577e54e5843141cd14048ed8a8fb00ce681
|
| 3 |
size 5240
|