Commit
·
85f2d1c
1
Parent(s):
d3c8535
Update fine-tuned model
Browse files- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +727 -202
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -20,13 +20,13 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"k_proj",
|
| 24 |
-
"gate_proj",
|
| 25 |
"up_proj",
|
| 26 |
-
"
|
| 27 |
"down_proj",
|
| 28 |
"q_proj",
|
| 29 |
-
"
|
|
|
|
|
|
|
| 30 |
],
|
| 31 |
"task_type": " CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
|
|
|
|
|
| 23 |
"up_proj",
|
| 24 |
+
"v_proj",
|
| 25 |
"down_proj",
|
| 26 |
"q_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"gate_proj"
|
| 30 |
],
|
| 31 |
"task_type": " CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 159967880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8dc3526319616f564084803a55a4634c00e35413e9965c9cc8ea0d5da4e03d31
|
| 3 |
size 159967880
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 852876198
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e24dec637d4370a49253e03f0da5dfa9c777bfbeb86bfe5ba98c750ed05d739
|
| 3 |
size 852876198
|
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:a1e42b4ab9aefc741b06ae8d61682e61a1ced93aca1dc65b7a76e4f5950596de
|
| 3 |
size 14244
|
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 sha256:25c0243da09e051ffbb600413baac079966a139cd6939cbef7eb321283bd0767
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -3,364 +3,889 @@
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 5.0,
|
| 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,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch": 0.
|
| 13 |
-
"grad_norm": 0.
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss": 0.
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"grad_norm": 0.
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss": 0.
|
| 23 |
"step": 2
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"grad_norm": 0.
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 3
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch": 0.
|
| 34 |
-
"grad_norm": 0.
|
| 35 |
-
"learning_rate": 0.
|
| 36 |
-
"loss": 0.
|
| 37 |
"step": 4
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch": 0.
|
| 41 |
-
"grad_norm": 0.
|
| 42 |
-
"learning_rate": 0.
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 5
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"grad_norm": 0.
|
| 49 |
-
"learning_rate": 0.
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 6
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"grad_norm": 0.
|
| 56 |
-
"learning_rate": 0.
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 7
|
| 59 |
},
|
| 60 |
{
|
| 61 |
-
"epoch": 0.
|
| 62 |
-
"grad_norm": 0.
|
| 63 |
-
"learning_rate": 0.
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 8
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch": 0.
|
| 69 |
-
"grad_norm": 0.
|
| 70 |
-
"learning_rate": 0.
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 9
|
| 73 |
},
|
| 74 |
{
|
| 75 |
-
"epoch":
|
| 76 |
-
"grad_norm": 0.
|
| 77 |
-
"learning_rate": 0.
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 10
|
| 80 |
},
|
| 81 |
{
|
| 82 |
-
"epoch":
|
| 83 |
-
"grad_norm": 0.
|
| 84 |
-
"learning_rate": 0.
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 11
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch":
|
| 90 |
-
"grad_norm": 0.
|
| 91 |
-
"learning_rate": 0.
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 12
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch":
|
| 97 |
-
"grad_norm": 0.
|
| 98 |
-
"learning_rate": 0.
|
| 99 |
-
"loss": 0.
|
| 100 |
"step": 13
|
| 101 |
},
|
| 102 |
{
|
| 103 |
-
"epoch":
|
| 104 |
-
"grad_norm": 0.
|
| 105 |
-
"learning_rate": 0.
|
| 106 |
-
"loss": 0.
|
| 107 |
"step": 14
|
| 108 |
},
|
| 109 |
{
|
| 110 |
-
"epoch":
|
| 111 |
-
"grad_norm": 0.
|
| 112 |
-
"learning_rate": 0.
|
| 113 |
-
"loss": 0.
|
| 114 |
"step": 15
|
| 115 |
},
|
| 116 |
{
|
| 117 |
-
"epoch":
|
| 118 |
-
"grad_norm": 0.
|
| 119 |
-
"learning_rate": 0.
|
| 120 |
-
"loss": 0.
|
| 121 |
"step": 16
|
| 122 |
},
|
| 123 |
{
|
| 124 |
-
"epoch":
|
| 125 |
-
"grad_norm": 0.
|
| 126 |
-
"learning_rate": 0.
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 17
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch":
|
| 132 |
-
"grad_norm": 0.
|
| 133 |
-
"learning_rate": 0.
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 18
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch":
|
| 139 |
-
"grad_norm": 0.
|
| 140 |
-
"learning_rate": 0.
|
| 141 |
-
"loss": 0.
|
| 142 |
"step": 19
|
| 143 |
},
|
| 144 |
{
|
| 145 |
-
"epoch":
|
| 146 |
-
"grad_norm": 0.
|
| 147 |
-
"learning_rate": 0.
|
| 148 |
-
"loss": 0.
|
| 149 |
"step": 20
|
| 150 |
},
|
| 151 |
{
|
| 152 |
-
"epoch":
|
| 153 |
-
"grad_norm": 0.
|
| 154 |
-
"learning_rate": 0.
|
| 155 |
-
"loss": 0.
|
| 156 |
"step": 21
|
| 157 |
},
|
| 158 |
{
|
| 159 |
-
"epoch":
|
| 160 |
-
"grad_norm": 0.
|
| 161 |
-
"learning_rate": 0.
|
| 162 |
-
"loss": 0.
|
| 163 |
"step": 22
|
| 164 |
},
|
| 165 |
{
|
| 166 |
-
"epoch":
|
| 167 |
-
"grad_norm": 0.
|
| 168 |
-
"learning_rate": 0.
|
| 169 |
-
"loss": 0.
|
| 170 |
"step": 23
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"epoch":
|
| 174 |
-
"grad_norm": 0.
|
| 175 |
-
"learning_rate": 0.
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 24
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch":
|
| 181 |
-
"grad_norm": 0.
|
| 182 |
-
"learning_rate": 0.
|
| 183 |
-
"loss": 0.
|
| 184 |
"step": 25
|
| 185 |
},
|
| 186 |
{
|
| 187 |
-
"epoch":
|
| 188 |
-
"grad_norm": 0.
|
| 189 |
-
"learning_rate": 0.
|
| 190 |
-
"loss": 0.
|
| 191 |
"step": 26
|
| 192 |
},
|
| 193 |
{
|
| 194 |
-
"epoch":
|
| 195 |
-
"grad_norm": 0.
|
| 196 |
-
"learning_rate":
|
| 197 |
-
"loss": 0.
|
| 198 |
"step": 27
|
| 199 |
},
|
| 200 |
{
|
| 201 |
-
"epoch":
|
| 202 |
-
"grad_norm": 0.
|
| 203 |
-
"learning_rate":
|
| 204 |
-
"loss": 0.
|
| 205 |
"step": 28
|
| 206 |
},
|
| 207 |
{
|
| 208 |
-
"epoch":
|
| 209 |
-
"grad_norm": 0.
|
| 210 |
-
"learning_rate":
|
| 211 |
-
"loss": 0.
|
| 212 |
"step": 29
|
| 213 |
},
|
| 214 |
{
|
| 215 |
-
"epoch":
|
| 216 |
-
"grad_norm": 0.
|
| 217 |
-
"learning_rate":
|
| 218 |
-
"loss": 0.
|
| 219 |
"step": 30
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch":
|
| 223 |
-
"grad_norm": 0.
|
| 224 |
-
"learning_rate":
|
| 225 |
-
"loss": 0.
|
| 226 |
"step": 31
|
| 227 |
},
|
| 228 |
{
|
| 229 |
-
"epoch":
|
| 230 |
-
"grad_norm": 0.
|
| 231 |
-
"learning_rate":
|
| 232 |
-
"loss": 0.
|
| 233 |
"step": 32
|
| 234 |
},
|
| 235 |
{
|
| 236 |
-
"epoch":
|
| 237 |
-
"grad_norm": 0.
|
| 238 |
-
"learning_rate":
|
| 239 |
-
"loss": 0.
|
| 240 |
"step": 33
|
| 241 |
},
|
| 242 |
{
|
| 243 |
-
"epoch":
|
| 244 |
-
"grad_norm": 0.
|
| 245 |
-
"learning_rate":
|
| 246 |
-
"loss": 0.
|
| 247 |
"step": 34
|
| 248 |
},
|
| 249 |
{
|
| 250 |
-
"epoch":
|
| 251 |
-
"grad_norm": 0.
|
| 252 |
-
"learning_rate":
|
| 253 |
-
"loss": 0.
|
| 254 |
"step": 35
|
| 255 |
},
|
| 256 |
{
|
| 257 |
-
"epoch":
|
| 258 |
-
"grad_norm": 0.
|
| 259 |
-
"learning_rate":
|
| 260 |
-
"loss": 0.
|
| 261 |
"step": 36
|
| 262 |
},
|
| 263 |
{
|
| 264 |
-
"epoch":
|
| 265 |
-
"grad_norm": 0.
|
| 266 |
-
"learning_rate":
|
| 267 |
-
"loss": 0.
|
| 268 |
"step": 37
|
| 269 |
},
|
| 270 |
{
|
| 271 |
-
"epoch":
|
| 272 |
-
"grad_norm": 0.
|
| 273 |
-
"learning_rate":
|
| 274 |
-
"loss": 0.
|
| 275 |
"step": 38
|
| 276 |
},
|
| 277 |
{
|
| 278 |
-
"epoch":
|
| 279 |
-
"grad_norm": 0.
|
| 280 |
-
"learning_rate":
|
| 281 |
-
"loss": 0.
|
| 282 |
"step": 39
|
| 283 |
},
|
| 284 |
{
|
| 285 |
-
"epoch":
|
| 286 |
-
"grad_norm": 0.
|
| 287 |
-
"learning_rate":
|
| 288 |
-
"loss": 0.
|
| 289 |
"step": 40
|
| 290 |
},
|
| 291 |
{
|
| 292 |
-
"epoch":
|
| 293 |
-
"grad_norm": 0.
|
| 294 |
-
"learning_rate":
|
| 295 |
-
"loss": 0.
|
| 296 |
"step": 41
|
| 297 |
},
|
| 298 |
{
|
| 299 |
-
"epoch":
|
| 300 |
-
"grad_norm": 0.
|
| 301 |
-
"learning_rate":
|
| 302 |
-
"loss": 0.
|
| 303 |
"step": 42
|
| 304 |
},
|
| 305 |
{
|
| 306 |
-
"epoch":
|
| 307 |
-
"grad_norm": 0.
|
| 308 |
-
"learning_rate":
|
| 309 |
-
"loss": 0.
|
| 310 |
"step": 43
|
| 311 |
},
|
| 312 |
{
|
| 313 |
-
"epoch":
|
| 314 |
-
"grad_norm": 0.
|
| 315 |
-
"learning_rate":
|
| 316 |
-
"loss": 0.
|
| 317 |
"step": 44
|
| 318 |
},
|
| 319 |
{
|
| 320 |
-
"epoch":
|
| 321 |
-
"grad_norm": 0.
|
| 322 |
-
"learning_rate":
|
| 323 |
-
"loss": 0.
|
| 324 |
"step": 45
|
| 325 |
},
|
| 326 |
{
|
| 327 |
-
"epoch":
|
| 328 |
-
"grad_norm": 0.
|
| 329 |
-
"learning_rate":
|
| 330 |
-
"loss": 0.
|
| 331 |
"step": 46
|
| 332 |
},
|
| 333 |
{
|
| 334 |
-
"epoch":
|
| 335 |
-
"grad_norm": 0.
|
| 336 |
-
"learning_rate":
|
| 337 |
-
"loss": 0.
|
| 338 |
"step": 47
|
| 339 |
},
|
| 340 |
{
|
| 341 |
-
"epoch":
|
| 342 |
-
"grad_norm": 0.
|
| 343 |
-
"learning_rate":
|
| 344 |
-
"loss": 0.
|
| 345 |
"step": 48
|
| 346 |
},
|
| 347 |
{
|
| 348 |
-
"epoch":
|
| 349 |
-
"grad_norm": 0.
|
| 350 |
-
"learning_rate":
|
| 351 |
-
"loss": 0.
|
| 352 |
"step": 49
|
| 353 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 354 |
{
|
| 355 |
"epoch": 5.0,
|
| 356 |
-
"grad_norm": 0.
|
| 357 |
"learning_rate": 0.0,
|
| 358 |
-
"loss": 0.
|
| 359 |
-
"step":
|
| 360 |
}
|
| 361 |
],
|
| 362 |
"logging_steps": 1,
|
| 363 |
-
"max_steps":
|
| 364 |
"num_input_tokens_seen": 0,
|
| 365 |
"num_train_epochs": 5,
|
| 366 |
"save_steps": 500,
|
|
@@ -376,7 +901,7 @@
|
|
| 376 |
"attributes": {}
|
| 377 |
}
|
| 378 |
},
|
| 379 |
-
"total_flos":
|
| 380 |
"train_batch_size": 1,
|
| 381 |
"trial_name": null,
|
| 382 |
"trial_params": null
|
|
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 5.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 125,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"grad_norm": 0.7209197878837585,
|
| 14 |
+
"learning_rate": 2.857142857142857e-05,
|
| 15 |
+
"loss": 0.8555,
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.08,
|
| 20 |
+
"grad_norm": 0.7282789945602417,
|
| 21 |
+
"learning_rate": 5.714285714285714e-05,
|
| 22 |
+
"loss": 0.8511,
|
| 23 |
"step": 2
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.12,
|
| 27 |
+
"grad_norm": 0.6870177984237671,
|
| 28 |
+
"learning_rate": 8.571428571428571e-05,
|
| 29 |
+
"loss": 0.8511,
|
| 30 |
"step": 3
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.16,
|
| 34 |
+
"grad_norm": 0.5710985660552979,
|
| 35 |
+
"learning_rate": 0.00011428571428571428,
|
| 36 |
+
"loss": 0.7533,
|
| 37 |
"step": 4
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.2,
|
| 41 |
+
"grad_norm": 0.4873427450656891,
|
| 42 |
+
"learning_rate": 0.00014285714285714287,
|
| 43 |
+
"loss": 0.7636,
|
| 44 |
"step": 5
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.24,
|
| 48 |
+
"grad_norm": 0.44160357117652893,
|
| 49 |
+
"learning_rate": 0.00017142857142857143,
|
| 50 |
+
"loss": 0.7484,
|
| 51 |
"step": 6
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.28,
|
| 55 |
+
"grad_norm": 0.38276153802871704,
|
| 56 |
+
"learning_rate": 0.0002,
|
| 57 |
+
"loss": 0.7157,
|
| 58 |
"step": 7
|
| 59 |
},
|
| 60 |
{
|
| 61 |
+
"epoch": 0.32,
|
| 62 |
+
"grad_norm": 0.3445475101470947,
|
| 63 |
+
"learning_rate": 0.00019996456111234527,
|
| 64 |
+
"loss": 0.7039,
|
| 65 |
"step": 8
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 0.36,
|
| 69 |
+
"grad_norm": 0.31933900713920593,
|
| 70 |
+
"learning_rate": 0.0001998582695676762,
|
| 71 |
+
"loss": 0.7062,
|
| 72 |
"step": 9
|
| 73 |
},
|
| 74 |
{
|
| 75 |
+
"epoch": 0.4,
|
| 76 |
+
"grad_norm": 0.3282822072505951,
|
| 77 |
+
"learning_rate": 0.000199681200703075,
|
| 78 |
+
"loss": 0.703,
|
| 79 |
"step": 10
|
| 80 |
},
|
| 81 |
{
|
| 82 |
+
"epoch": 0.44,
|
| 83 |
+
"grad_norm": 0.3057241439819336,
|
| 84 |
+
"learning_rate": 0.00019943348002101371,
|
| 85 |
+
"loss": 0.704,
|
| 86 |
"step": 11
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 0.48,
|
| 90 |
+
"grad_norm": 0.28319624066352844,
|
| 91 |
+
"learning_rate": 0.00019911528310040074,
|
| 92 |
+
"loss": 0.6743,
|
| 93 |
"step": 12
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.52,
|
| 97 |
+
"grad_norm": 0.2568361461162567,
|
| 98 |
+
"learning_rate": 0.00019872683547213446,
|
| 99 |
+
"loss": 0.6933,
|
| 100 |
"step": 13
|
| 101 |
},
|
| 102 |
{
|
| 103 |
+
"epoch": 0.56,
|
| 104 |
+
"grad_norm": 0.25777217745780945,
|
| 105 |
+
"learning_rate": 0.00019826841245925212,
|
| 106 |
+
"loss": 0.6664,
|
| 107 |
"step": 14
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 0.6,
|
| 111 |
+
"grad_norm": 0.2636028528213501,
|
| 112 |
+
"learning_rate": 0.00019774033898178667,
|
| 113 |
+
"loss": 0.6815,
|
| 114 |
"step": 15
|
| 115 |
},
|
| 116 |
{
|
| 117 |
+
"epoch": 0.64,
|
| 118 |
+
"grad_norm": 0.2726347744464874,
|
| 119 |
+
"learning_rate": 0.00019714298932647098,
|
| 120 |
+
"loss": 0.6769,
|
| 121 |
"step": 16
|
| 122 |
},
|
| 123 |
{
|
| 124 |
+
"epoch": 0.68,
|
| 125 |
+
"grad_norm": 0.2455451488494873,
|
| 126 |
+
"learning_rate": 0.0001964767868814516,
|
| 127 |
+
"loss": 0.6499,
|
| 128 |
"step": 17
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 0.72,
|
| 132 |
+
"grad_norm": 0.2470139116048813,
|
| 133 |
+
"learning_rate": 0.00019574220383620055,
|
| 134 |
+
"loss": 0.6729,
|
| 135 |
"step": 18
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 0.76,
|
| 139 |
+
"grad_norm": 0.2509821057319641,
|
| 140 |
+
"learning_rate": 0.00019493976084683813,
|
| 141 |
+
"loss": 0.6548,
|
| 142 |
"step": 19
|
| 143 |
},
|
| 144 |
{
|
| 145 |
+
"epoch": 0.8,
|
| 146 |
+
"grad_norm": 0.2554020583629608,
|
| 147 |
+
"learning_rate": 0.00019407002666710336,
|
| 148 |
+
"loss": 0.6156,
|
| 149 |
"step": 20
|
| 150 |
},
|
| 151 |
{
|
| 152 |
+
"epoch": 0.84,
|
| 153 |
+
"grad_norm": 0.26096639037132263,
|
| 154 |
+
"learning_rate": 0.00019313361774523385,
|
| 155 |
+
"loss": 0.6278,
|
| 156 |
"step": 21
|
| 157 |
},
|
| 158 |
{
|
| 159 |
+
"epoch": 0.88,
|
| 160 |
+
"grad_norm": 0.25810953974723816,
|
| 161 |
+
"learning_rate": 0.00019213119778704128,
|
| 162 |
+
"loss": 0.6334,
|
| 163 |
"step": 22
|
| 164 |
},
|
| 165 |
{
|
| 166 |
+
"epoch": 0.92,
|
| 167 |
+
"grad_norm": 0.24838820099830627,
|
| 168 |
+
"learning_rate": 0.00019106347728549135,
|
| 169 |
+
"loss": 0.6238,
|
| 170 |
"step": 23
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"epoch": 0.96,
|
| 174 |
+
"grad_norm": 0.2597545385360718,
|
| 175 |
+
"learning_rate": 0.00018993121301712193,
|
| 176 |
+
"loss": 0.6083,
|
| 177 |
"step": 24
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 1.0,
|
| 181 |
+
"grad_norm": 0.2563561797142029,
|
| 182 |
+
"learning_rate": 0.00018873520750565718,
|
| 183 |
+
"loss": 0.632,
|
| 184 |
"step": 25
|
| 185 |
},
|
| 186 |
{
|
| 187 |
+
"epoch": 1.04,
|
| 188 |
+
"grad_norm": 0.2539364993572235,
|
| 189 |
+
"learning_rate": 0.00018747630845319612,
|
| 190 |
+
"loss": 0.53,
|
| 191 |
"step": 26
|
| 192 |
},
|
| 193 |
{
|
| 194 |
+
"epoch": 1.08,
|
| 195 |
+
"grad_norm": 0.27705103158950806,
|
| 196 |
+
"learning_rate": 0.0001861554081393806,
|
| 197 |
+
"loss": 0.5125,
|
| 198 |
"step": 27
|
| 199 |
},
|
| 200 |
{
|
| 201 |
+
"epoch": 1.12,
|
| 202 |
+
"grad_norm": 0.2639136016368866,
|
| 203 |
+
"learning_rate": 0.0001847734427889671,
|
| 204 |
+
"loss": 0.514,
|
| 205 |
"step": 28
|
| 206 |
},
|
| 207 |
{
|
| 208 |
+
"epoch": 1.16,
|
| 209 |
+
"grad_norm": 0.24399739503860474,
|
| 210 |
+
"learning_rate": 0.0001833313919082515,
|
| 211 |
+
"loss": 0.5203,
|
| 212 |
"step": 29
|
| 213 |
},
|
| 214 |
{
|
| 215 |
+
"epoch": 1.2,
|
| 216 |
+
"grad_norm": 0.24673549830913544,
|
| 217 |
+
"learning_rate": 0.0001818302775908169,
|
| 218 |
+
"loss": 0.4994,
|
| 219 |
"step": 30
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 1.24,
|
| 223 |
+
"grad_norm": 0.24222399294376373,
|
| 224 |
+
"learning_rate": 0.00018027116379309638,
|
| 225 |
+
"loss": 0.5129,
|
| 226 |
"step": 31
|
| 227 |
},
|
| 228 |
{
|
| 229 |
+
"epoch": 1.28,
|
| 230 |
+
"grad_norm": 0.23906999826431274,
|
| 231 |
+
"learning_rate": 0.00017865515558026428,
|
| 232 |
+
"loss": 0.4904,
|
| 233 |
"step": 32
|
| 234 |
},
|
| 235 |
{
|
| 236 |
+
"epoch": 1.32,
|
| 237 |
+
"grad_norm": 0.2312118262052536,
|
| 238 |
+
"learning_rate": 0.00017698339834299061,
|
| 239 |
+
"loss": 0.4781,
|
| 240 |
"step": 33
|
| 241 |
},
|
| 242 |
{
|
| 243 |
+
"epoch": 1.3599999999999999,
|
| 244 |
+
"grad_norm": 0.24449752271175385,
|
| 245 |
+
"learning_rate": 0.00017525707698561385,
|
| 246 |
+
"loss": 0.4928,
|
| 247 |
"step": 34
|
| 248 |
},
|
| 249 |
{
|
| 250 |
+
"epoch": 1.4,
|
| 251 |
+
"grad_norm": 0.24433298408985138,
|
| 252 |
+
"learning_rate": 0.00017347741508630672,
|
| 253 |
+
"loss": 0.4916,
|
| 254 |
"step": 35
|
| 255 |
},
|
| 256 |
{
|
| 257 |
+
"epoch": 1.44,
|
| 258 |
+
"grad_norm": 0.25431713461875916,
|
| 259 |
+
"learning_rate": 0.00017164567402983152,
|
| 260 |
+
"loss": 0.47,
|
| 261 |
"step": 36
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 1.48,
|
| 265 |
+
"grad_norm": 0.25172215700149536,
|
| 266 |
+
"learning_rate": 0.0001697631521134985,
|
| 267 |
+
"loss": 0.4794,
|
| 268 |
"step": 37
|
| 269 |
},
|
| 270 |
{
|
| 271 |
+
"epoch": 1.52,
|
| 272 |
+
"grad_norm": 0.25659480690956116,
|
| 273 |
+
"learning_rate": 0.00016783118362696163,
|
| 274 |
+
"loss": 0.4773,
|
| 275 |
"step": 38
|
| 276 |
},
|
| 277 |
{
|
| 278 |
+
"epoch": 1.56,
|
| 279 |
+
"grad_norm": 0.2669978141784668,
|
| 280 |
+
"learning_rate": 0.00016585113790650388,
|
| 281 |
+
"loss": 0.4634,
|
| 282 |
"step": 39
|
| 283 |
},
|
| 284 |
{
|
| 285 |
+
"epoch": 1.6,
|
| 286 |
+
"grad_norm": 0.26926499605178833,
|
| 287 |
+
"learning_rate": 0.00016382441836448202,
|
| 288 |
+
"loss": 0.4416,
|
| 289 |
"step": 40
|
| 290 |
},
|
| 291 |
{
|
| 292 |
+
"epoch": 1.6400000000000001,
|
| 293 |
+
"grad_norm": 0.26841145753860474,
|
| 294 |
+
"learning_rate": 0.0001617524614946192,
|
| 295 |
+
"loss": 0.4492,
|
| 296 |
"step": 41
|
| 297 |
},
|
| 298 |
{
|
| 299 |
+
"epoch": 1.6800000000000002,
|
| 300 |
+
"grad_norm": 0.26070988178253174,
|
| 301 |
+
"learning_rate": 0.00015963673585385016,
|
| 302 |
+
"loss": 0.4316,
|
| 303 |
"step": 42
|
| 304 |
},
|
| 305 |
{
|
| 306 |
+
"epoch": 1.72,
|
| 307 |
+
"grad_norm": 0.2793709337711334,
|
| 308 |
+
"learning_rate": 0.0001574787410214407,
|
| 309 |
+
"loss": 0.4443,
|
| 310 |
"step": 43
|
| 311 |
},
|
| 312 |
{
|
| 313 |
+
"epoch": 1.76,
|
| 314 |
+
"grad_norm": 0.2722426652908325,
|
| 315 |
+
"learning_rate": 0.00015528000653611935,
|
| 316 |
+
"loss": 0.4469,
|
| 317 |
"step": 44
|
| 318 |
},
|
| 319 |
{
|
| 320 |
+
"epoch": 1.8,
|
| 321 |
+
"grad_norm": 0.2657548487186432,
|
| 322 |
+
"learning_rate": 0.00015304209081197425,
|
| 323 |
+
"loss": 0.4456,
|
| 324 |
"step": 45
|
| 325 |
},
|
| 326 |
{
|
| 327 |
+
"epoch": 1.8399999999999999,
|
| 328 |
+
"grad_norm": 0.28950250148773193,
|
| 329 |
+
"learning_rate": 0.000150766580033884,
|
| 330 |
+
"loss": 0.4388,
|
| 331 |
"step": 46
|
| 332 |
},
|
| 333 |
{
|
| 334 |
+
"epoch": 1.88,
|
| 335 |
+
"grad_norm": 0.2785035967826843,
|
| 336 |
+
"learning_rate": 0.00014845508703326504,
|
| 337 |
+
"loss": 0.4269,
|
| 338 |
"step": 47
|
| 339 |
},
|
| 340 |
{
|
| 341 |
+
"epoch": 1.92,
|
| 342 |
+
"grad_norm": 0.2793751060962677,
|
| 343 |
+
"learning_rate": 0.0001461092501449326,
|
| 344 |
+
"loss": 0.4182,
|
| 345 |
"step": 48
|
| 346 |
},
|
| 347 |
{
|
| 348 |
+
"epoch": 1.96,
|
| 349 |
+
"grad_norm": 0.28629055619239807,
|
| 350 |
+
"learning_rate": 0.00014373073204588556,
|
| 351 |
+
"loss": 0.4433,
|
| 352 |
"step": 49
|
| 353 |
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.0,
|
| 356 |
+
"grad_norm": 0.2770131528377533,
|
| 357 |
+
"learning_rate": 0.00014132121857683783,
|
| 358 |
+
"loss": 0.4447,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.04,
|
| 363 |
+
"grad_norm": 0.2512931823730469,
|
| 364 |
+
"learning_rate": 0.00013888241754733208,
|
| 365 |
+
"loss": 0.3446,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.08,
|
| 370 |
+
"grad_norm": 0.25569790601730347,
|
| 371 |
+
"learning_rate": 0.00013641605752528224,
|
| 372 |
+
"loss": 0.385,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 2.12,
|
| 377 |
+
"grad_norm": 0.2556793689727783,
|
| 378 |
+
"learning_rate": 0.00013392388661180303,
|
| 379 |
+
"loss": 0.3545,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.16,
|
| 384 |
+
"grad_norm": 0.2621767818927765,
|
| 385 |
+
"learning_rate": 0.0001314076712021949,
|
| 386 |
+
"loss": 0.3555,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.2,
|
| 391 |
+
"grad_norm": 0.2598123550415039,
|
| 392 |
+
"learning_rate": 0.0001288691947339621,
|
| 393 |
+
"loss": 0.3403,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 2.24,
|
| 398 |
+
"grad_norm": 0.26771417260169983,
|
| 399 |
+
"learning_rate": 0.00012631025642275212,
|
| 400 |
+
"loss": 0.3244,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.2800000000000002,
|
| 405 |
+
"grad_norm": 0.27799421548843384,
|
| 406 |
+
"learning_rate": 0.0001237326699871115,
|
| 407 |
+
"loss": 0.3281,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.32,
|
| 412 |
+
"grad_norm": 0.2827088534832001,
|
| 413 |
+
"learning_rate": 0.00012113826236296244,
|
| 414 |
+
"loss": 0.3308,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 2.36,
|
| 419 |
+
"grad_norm": 0.28123676776885986,
|
| 420 |
+
"learning_rate": 0.00011852887240871145,
|
| 421 |
+
"loss": 0.3267,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.4,
|
| 426 |
+
"grad_norm": 0.30861011147499084,
|
| 427 |
+
"learning_rate": 0.00011590634960190721,
|
| 428 |
+
"loss": 0.32,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.44,
|
| 433 |
+
"grad_norm": 0.29810547828674316,
|
| 434 |
+
"learning_rate": 0.00011327255272837221,
|
| 435 |
+
"loss": 0.3283,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 2.48,
|
| 440 |
+
"grad_norm": 0.296453058719635,
|
| 441 |
+
"learning_rate": 0.00011062934856473655,
|
| 442 |
+
"loss": 0.3302,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 2.52,
|
| 447 |
+
"grad_norm": 0.32325005531311035,
|
| 448 |
+
"learning_rate": 0.00010797861055530831,
|
| 449 |
+
"loss": 0.3381,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.56,
|
| 454 |
+
"grad_norm": 0.29035669565200806,
|
| 455 |
+
"learning_rate": 0.00010532221748421787,
|
| 456 |
+
"loss": 0.3189,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 2.6,
|
| 461 |
+
"grad_norm": 0.3050059974193573,
|
| 462 |
+
"learning_rate": 0.00010266205214377748,
|
| 463 |
+
"loss": 0.3047,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.64,
|
| 468 |
+
"grad_norm": 0.30324605107307434,
|
| 469 |
+
"learning_rate": 0.0001,
|
| 470 |
+
"loss": 0.3054,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.68,
|
| 475 |
+
"grad_norm": 0.3131050169467926,
|
| 476 |
+
"learning_rate": 9.733794785622253e-05,
|
| 477 |
+
"loss": 0.3238,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 2.7199999999999998,
|
| 482 |
+
"grad_norm": 0.3103804886341095,
|
| 483 |
+
"learning_rate": 9.467778251578217e-05,
|
| 484 |
+
"loss": 0.336,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 2.76,
|
| 489 |
+
"grad_norm": 0.3039088845252991,
|
| 490 |
+
"learning_rate": 9.202138944469168e-05,
|
| 491 |
+
"loss": 0.3304,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.8,
|
| 496 |
+
"grad_norm": 0.3010499179363251,
|
| 497 |
+
"learning_rate": 8.937065143526347e-05,
|
| 498 |
+
"loss": 0.3126,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 2.84,
|
| 503 |
+
"grad_norm": 0.2960353195667267,
|
| 504 |
+
"learning_rate": 8.672744727162781e-05,
|
| 505 |
+
"loss": 0.3201,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.88,
|
| 510 |
+
"grad_norm": 0.2927502393722534,
|
| 511 |
+
"learning_rate": 8.409365039809281e-05,
|
| 512 |
+
"loss": 0.307,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.92,
|
| 517 |
+
"grad_norm": 0.29815661907196045,
|
| 518 |
+
"learning_rate": 8.147112759128859e-05,
|
| 519 |
+
"loss": 0.313,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 2.96,
|
| 524 |
+
"grad_norm": 0.2862599790096283,
|
| 525 |
+
"learning_rate": 7.886173763703757e-05,
|
| 526 |
+
"loss": 0.3216,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 3.0,
|
| 531 |
+
"grad_norm": 0.28218919038772583,
|
| 532 |
+
"learning_rate": 7.626733001288851e-05,
|
| 533 |
+
"loss": 0.3021,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 3.04,
|
| 538 |
+
"grad_norm": 0.29704561829566956,
|
| 539 |
+
"learning_rate": 7.368974357724789e-05,
|
| 540 |
+
"loss": 0.2639,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 3.08,
|
| 545 |
+
"grad_norm": 0.2927261292934418,
|
| 546 |
+
"learning_rate": 7.113080526603792e-05,
|
| 547 |
+
"loss": 0.2633,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 3.12,
|
| 552 |
+
"grad_norm": 0.2776476740837097,
|
| 553 |
+
"learning_rate": 6.859232879780515e-05,
|
| 554 |
+
"loss": 0.2565,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 3.16,
|
| 559 |
+
"grad_norm": 0.27619966864585876,
|
| 560 |
+
"learning_rate": 6.607611338819697e-05,
|
| 561 |
+
"loss": 0.2528,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 3.2,
|
| 566 |
+
"grad_norm": 0.27579841017723083,
|
| 567 |
+
"learning_rate": 6.358394247471778e-05,
|
| 568 |
+
"loss": 0.2512,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 3.24,
|
| 573 |
+
"grad_norm": 0.2667072117328644,
|
| 574 |
+
"learning_rate": 6.111758245266794e-05,
|
| 575 |
+
"loss": 0.2543,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 3.2800000000000002,
|
| 580 |
+
"grad_norm": 0.2724190056324005,
|
| 581 |
+
"learning_rate": 5.867878142316221e-05,
|
| 582 |
+
"loss": 0.2619,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 3.32,
|
| 587 |
+
"grad_norm": 0.2652760446071625,
|
| 588 |
+
"learning_rate": 5.626926795411447e-05,
|
| 589 |
+
"loss": 0.2402,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 3.36,
|
| 594 |
+
"grad_norm": 0.27490079402923584,
|
| 595 |
+
"learning_rate": 5.38907498550674e-05,
|
| 596 |
+
"loss": 0.2363,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 3.4,
|
| 601 |
+
"grad_norm": 0.280770480632782,
|
| 602 |
+
"learning_rate": 5.1544912966734994e-05,
|
| 603 |
+
"loss": 0.2517,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 3.44,
|
| 608 |
+
"grad_norm": 0.3093857169151306,
|
| 609 |
+
"learning_rate": 4.9233419966116036e-05,
|
| 610 |
+
"loss": 0.2593,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 3.48,
|
| 615 |
+
"grad_norm": 0.2780980169773102,
|
| 616 |
+
"learning_rate": 4.695790918802576e-05,
|
| 617 |
+
"loss": 0.2355,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 3.52,
|
| 622 |
+
"grad_norm": 0.2719030976295471,
|
| 623 |
+
"learning_rate": 4.47199934638807e-05,
|
| 624 |
+
"loss": 0.2305,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 3.56,
|
| 629 |
+
"grad_norm": 0.3024630546569824,
|
| 630 |
+
"learning_rate": 4.252125897855932e-05,
|
| 631 |
+
"loss": 0.2359,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 3.6,
|
| 636 |
+
"grad_norm": 0.27690544724464417,
|
| 637 |
+
"learning_rate": 4.036326414614985e-05,
|
| 638 |
+
"loss": 0.245,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 3.64,
|
| 643 |
+
"grad_norm": 0.27956703305244446,
|
| 644 |
+
"learning_rate": 3.824753850538082e-05,
|
| 645 |
+
"loss": 0.2247,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 3.68,
|
| 650 |
+
"grad_norm": 0.28436169028282166,
|
| 651 |
+
"learning_rate": 3.617558163551802e-05,
|
| 652 |
+
"loss": 0.2467,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 3.7199999999999998,
|
| 657 |
+
"grad_norm": 0.28021368384361267,
|
| 658 |
+
"learning_rate": 3.414886209349615e-05,
|
| 659 |
+
"loss": 0.2435,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 3.76,
|
| 664 |
+
"grad_norm": 0.3015545904636383,
|
| 665 |
+
"learning_rate": 3.216881637303839e-05,
|
| 666 |
+
"loss": 0.2437,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 3.8,
|
| 671 |
+
"grad_norm": 0.28339913487434387,
|
| 672 |
+
"learning_rate": 3.0236847886501542e-05,
|
| 673 |
+
"loss": 0.2509,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 3.84,
|
| 678 |
+
"grad_norm": 0.3016417324542999,
|
| 679 |
+
"learning_rate": 2.8354325970168484e-05,
|
| 680 |
+
"loss": 0.2596,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 3.88,
|
| 685 |
+
"grad_norm": 0.284646213054657,
|
| 686 |
+
"learning_rate": 2.6522584913693294e-05,
|
| 687 |
+
"loss": 0.2343,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 3.92,
|
| 692 |
+
"grad_norm": 0.30606040358543396,
|
| 693 |
+
"learning_rate": 2.4742923014386156e-05,
|
| 694 |
+
"loss": 0.2486,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 3.96,
|
| 699 |
+
"grad_norm": 0.28671491146087646,
|
| 700 |
+
"learning_rate": 2.301660165700936e-05,
|
| 701 |
+
"loss": 0.2265,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 4.0,
|
| 706 |
+
"grad_norm": 0.2809029519557953,
|
| 707 |
+
"learning_rate": 2.1344844419735755e-05,
|
| 708 |
+
"loss": 0.2378,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 4.04,
|
| 713 |
+
"grad_norm": 0.2681520879268646,
|
| 714 |
+
"learning_rate": 1.9728836206903656e-05,
|
| 715 |
+
"loss": 0.2296,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 4.08,
|
| 720 |
+
"grad_norm": 0.2830915153026581,
|
| 721 |
+
"learning_rate": 1.8169722409183097e-05,
|
| 722 |
+
"loss": 0.2207,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 4.12,
|
| 727 |
+
"grad_norm": 0.2674114406108856,
|
| 728 |
+
"learning_rate": 1.6668608091748495e-05,
|
| 729 |
+
"loss": 0.2273,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 4.16,
|
| 734 |
+
"grad_norm": 0.26131343841552734,
|
| 735 |
+
"learning_rate": 1.522655721103291e-05,
|
| 736 |
+
"loss": 0.2048,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 4.2,
|
| 741 |
+
"grad_norm": 0.26205572485923767,
|
| 742 |
+
"learning_rate": 1.3844591860619383e-05,
|
| 743 |
+
"loss": 0.2012,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 4.24,
|
| 748 |
+
"grad_norm": 0.2575109302997589,
|
| 749 |
+
"learning_rate": 1.2523691546803873e-05,
|
| 750 |
+
"loss": 0.2011,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 4.28,
|
| 755 |
+
"grad_norm": 0.25955626368522644,
|
| 756 |
+
"learning_rate": 1.1264792494342857e-05,
|
| 757 |
+
"loss": 0.1869,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 4.32,
|
| 762 |
+
"grad_norm": 0.2660517692565918,
|
| 763 |
+
"learning_rate": 1.0068786982878087e-05,
|
| 764 |
+
"loss": 0.218,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 4.36,
|
| 769 |
+
"grad_norm": 0.2595648765563965,
|
| 770 |
+
"learning_rate": 8.936522714508678e-06,
|
| 771 |
+
"loss": 0.218,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 4.4,
|
| 776 |
+
"grad_norm": 0.2599768042564392,
|
| 777 |
+
"learning_rate": 7.868802212958703e-06,
|
| 778 |
+
"loss": 0.199,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 4.44,
|
| 783 |
+
"grad_norm": 0.26886242628097534,
|
| 784 |
+
"learning_rate": 6.866382254766157e-06,
|
| 785 |
+
"loss": 0.2137,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 4.48,
|
| 790 |
+
"grad_norm": 0.2693222165107727,
|
| 791 |
+
"learning_rate": 5.929973332896677e-06,
|
| 792 |
+
"loss": 0.1991,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 4.52,
|
| 797 |
+
"grad_norm": 0.2585678994655609,
|
| 798 |
+
"learning_rate": 5.060239153161872e-06,
|
| 799 |
+
"loss": 0.2072,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 4.5600000000000005,
|
| 804 |
+
"grad_norm": 0.26331010460853577,
|
| 805 |
+
"learning_rate": 4.257796163799455e-06,
|
| 806 |
+
"loss": 0.2093,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 4.6,
|
| 811 |
+
"grad_norm": 0.2705547511577606,
|
| 812 |
+
"learning_rate": 3.5232131185484076e-06,
|
| 813 |
+
"loss": 0.2187,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 4.64,
|
| 818 |
+
"grad_norm": 0.2604030668735504,
|
| 819 |
+
"learning_rate": 2.857010673529015e-06,
|
| 820 |
+
"loss": 0.2081,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 4.68,
|
| 825 |
+
"grad_norm": 0.2516978681087494,
|
| 826 |
+
"learning_rate": 2.259661018213333e-06,
|
| 827 |
+
"loss": 0.2049,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 4.72,
|
| 832 |
+
"grad_norm": 0.2609613239765167,
|
| 833 |
+
"learning_rate": 1.7315875407479032e-06,
|
| 834 |
+
"loss": 0.2193,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 4.76,
|
| 839 |
+
"grad_norm": 0.25738459825515747,
|
| 840 |
+
"learning_rate": 1.2731645278655445e-06,
|
| 841 |
+
"loss": 0.1945,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 4.8,
|
| 846 |
+
"grad_norm": 0.2718040347099304,
|
| 847 |
+
"learning_rate": 8.847168995992916e-07,
|
| 848 |
+
"loss": 0.2248,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 4.84,
|
| 853 |
+
"grad_norm": 0.26361677050590515,
|
| 854 |
+
"learning_rate": 5.665199789862907e-07,
|
| 855 |
+
"loss": 0.2188,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 4.88,
|
| 860 |
+
"grad_norm": 0.2609327435493469,
|
| 861 |
+
"learning_rate": 3.1879929692498757e-07,
|
| 862 |
+
"loss": 0.1975,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 4.92,
|
| 867 |
+
"grad_norm": 0.2681811451911926,
|
| 868 |
+
"learning_rate": 1.4173043232380557e-07,
|
| 869 |
+
"loss": 0.2177,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 4.96,
|
| 874 |
+
"grad_norm": 0.25932785868644714,
|
| 875 |
+
"learning_rate": 3.5438887654737355e-08,
|
| 876 |
+
"loss": 0.2266,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
{
|
| 880 |
"epoch": 5.0,
|
| 881 |
+
"grad_norm": 0.26163730025291443,
|
| 882 |
"learning_rate": 0.0,
|
| 883 |
+
"loss": 0.2116,
|
| 884 |
+
"step": 125
|
| 885 |
}
|
| 886 |
],
|
| 887 |
"logging_steps": 1,
|
| 888 |
+
"max_steps": 125,
|
| 889 |
"num_input_tokens_seen": 0,
|
| 890 |
"num_train_epochs": 5,
|
| 891 |
"save_steps": 500,
|
|
|
|
| 901 |
"attributes": {}
|
| 902 |
}
|
| 903 |
},
|
| 904 |
+
"total_flos": 1.8787073669726208e+17,
|
| 905 |
"train_batch_size": 1,
|
| 906 |
"trial_name": null,
|
| 907 |
"trial_params": null
|
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 sha256:4114bcdcd5ee84b4b6297142cec343da8142ccd3caff500bedf3bed40df3d2fa
|
| 3 |
size 5240
|