Commit
·
4993337
1
Parent(s):
939f636
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 +505 -155
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -23,13 +23,13 @@
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
| 26 |
-
"
|
| 27 |
-
"gate_proj",
|
| 28 |
"o_proj",
|
|
|
|
| 29 |
"v_proj",
|
| 30 |
"up_proj",
|
| 31 |
-
"
|
| 32 |
-
"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
|
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
| 26 |
+
"k_proj",
|
|
|
|
| 27 |
"o_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
"v_proj",
|
| 30 |
"up_proj",
|
| 31 |
+
"gate_proj",
|
| 32 |
+
"down_proj"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"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 sha256:0d57abfb1995626406e3aeee2635cbf7ef4de508d19400e9f935699650285534
|
| 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 sha256:914661d73dcb472dfac465b65b85ff1016e9cfd770b94d95e9ffab7bcfd0a48e
|
| 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 sha256:42d6261dada0cbb2e61bb4c36e57a1530b123b847a587188b0b247cf1f8b69e2
|
| 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 sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -1,368 +1,718 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 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": 0.02,
|
| 13 |
-
"grad_norm": 0.
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss": 0.
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.04,
|
| 20 |
-
"grad_norm": 0.
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss": 0.
|
| 23 |
"step": 2
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.06,
|
| 27 |
-
"grad_norm": 0.
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 3
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.08,
|
| 34 |
-
"grad_norm": 0.
|
| 35 |
-
"learning_rate":
|
| 36 |
-
"loss": 0.
|
| 37 |
"step": 4
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.1,
|
| 41 |
-
"grad_norm": 0.
|
| 42 |
-
"learning_rate": 0.
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 5
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.12,
|
| 48 |
-
"grad_norm": 0.
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 6
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.14,
|
| 55 |
-
"grad_norm": 0.
|
| 56 |
-
"learning_rate":
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 7
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.16,
|
| 62 |
-
"grad_norm": 0.
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 8
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.18,
|
| 69 |
-
"grad_norm": 0.
|
| 70 |
-
"learning_rate":
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 9
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.2,
|
| 76 |
-
"grad_norm": 0.
|
| 77 |
-
"learning_rate":
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 10
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.22,
|
| 83 |
-
"grad_norm": 0.
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 11
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.24,
|
| 90 |
-
"grad_norm": 0.
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 12
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.26,
|
| 97 |
-
"grad_norm": 0.
|
| 98 |
-
"learning_rate":
|
| 99 |
-
"loss": 0.
|
| 100 |
"step": 13
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.28,
|
| 104 |
-
"grad_norm": 0.
|
| 105 |
-
"learning_rate":
|
| 106 |
-
"loss": 0.
|
| 107 |
"step": 14
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.3,
|
| 111 |
-
"grad_norm": 0.
|
| 112 |
-
"learning_rate":
|
| 113 |
-
"loss": 0.
|
| 114 |
"step": 15
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.32,
|
| 118 |
-
"grad_norm": 0.
|
| 119 |
-
"learning_rate":
|
| 120 |
-
"loss": 0.
|
| 121 |
"step": 16
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.34,
|
| 125 |
-
"grad_norm": 0.
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 17
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.36,
|
| 132 |
-
"grad_norm": 0.
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 18
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.38,
|
| 139 |
-
"grad_norm": 0.
|
| 140 |
-
"learning_rate":
|
| 141 |
-
"loss": 0.
|
| 142 |
"step": 19
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.4,
|
| 146 |
-
"grad_norm": 0.
|
| 147 |
-
"learning_rate":
|
| 148 |
-
"loss": 0.
|
| 149 |
"step": 20
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.42,
|
| 153 |
-
"grad_norm": 0.
|
| 154 |
-
"learning_rate":
|
| 155 |
-
"loss": 0.
|
| 156 |
"step": 21
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 0.44,
|
| 160 |
-
"grad_norm": 0.
|
| 161 |
-
"learning_rate":
|
| 162 |
-
"loss": 0.
|
| 163 |
"step": 22
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 0.46,
|
| 167 |
-
"grad_norm": 0.
|
| 168 |
-
"learning_rate":
|
| 169 |
-
"loss": 0.
|
| 170 |
"step": 23
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.48,
|
| 174 |
-
"grad_norm": 0.
|
| 175 |
-
"learning_rate":
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 24
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.5,
|
| 181 |
-
"grad_norm": 0.
|
| 182 |
-
"learning_rate":
|
| 183 |
-
"loss": 0.
|
| 184 |
"step": 25
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"epoch": 0.52,
|
| 188 |
-
"grad_norm": 0.
|
| 189 |
-
"learning_rate":
|
| 190 |
-
"loss": 0.
|
| 191 |
"step": 26
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 0.54,
|
| 195 |
-
"grad_norm": 0.
|
| 196 |
-
"learning_rate":
|
| 197 |
-
"loss": 0.
|
| 198 |
"step": 27
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 0.56,
|
| 202 |
-
"grad_norm": 0.
|
| 203 |
-
"learning_rate": 8.
|
| 204 |
-
"loss": 0.
|
| 205 |
"step": 28
|
| 206 |
},
|
| 207 |
{
|
| 208 |
"epoch": 0.58,
|
| 209 |
-
"grad_norm": 0.
|
| 210 |
-
"learning_rate": 8.
|
| 211 |
-
"loss": 0.
|
| 212 |
"step": 29
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 0.6,
|
| 216 |
-
"grad_norm": 0.
|
| 217 |
-
"learning_rate":
|
| 218 |
-
"loss": 0.
|
| 219 |
"step": 30
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.62,
|
| 223 |
-
"grad_norm": 0.
|
| 224 |
-
"learning_rate":
|
| 225 |
-
"loss": 0.
|
| 226 |
"step": 31
|
| 227 |
},
|
| 228 |
{
|
| 229 |
"epoch": 0.64,
|
| 230 |
-
"grad_norm": 0.
|
| 231 |
-
"learning_rate":
|
| 232 |
-
"loss": 0.
|
| 233 |
"step": 32
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 0.66,
|
| 237 |
-
"grad_norm": 0.
|
| 238 |
-
"learning_rate":
|
| 239 |
-
"loss": 0.
|
| 240 |
"step": 33
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 0.68,
|
| 244 |
-
"grad_norm": 0.
|
| 245 |
-
"learning_rate":
|
| 246 |
-
"loss": 0.
|
| 247 |
"step": 34
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"epoch": 0.7,
|
| 251 |
-
"grad_norm": 0.
|
| 252 |
-
"learning_rate":
|
| 253 |
-
"loss": 0.
|
| 254 |
"step": 35
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 0.72,
|
| 258 |
-
"grad_norm": 0.
|
| 259 |
-
"learning_rate":
|
| 260 |
-
"loss": 0.
|
| 261 |
"step": 36
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 0.74,
|
| 265 |
-
"grad_norm": 0.
|
| 266 |
-
"learning_rate":
|
| 267 |
-
"loss": 0.
|
| 268 |
"step": 37
|
| 269 |
},
|
| 270 |
{
|
| 271 |
"epoch": 0.76,
|
| 272 |
-
"grad_norm": 0.
|
| 273 |
-
"learning_rate":
|
| 274 |
-
"loss": 0.
|
| 275 |
"step": 38
|
| 276 |
},
|
| 277 |
{
|
| 278 |
"epoch": 0.78,
|
| 279 |
-
"grad_norm": 0.
|
| 280 |
-
"learning_rate":
|
| 281 |
-
"loss": 0.
|
| 282 |
"step": 39
|
| 283 |
},
|
| 284 |
{
|
| 285 |
"epoch": 0.8,
|
| 286 |
-
"grad_norm": 0.
|
| 287 |
-
"learning_rate":
|
| 288 |
-
"loss": 0.
|
| 289 |
"step": 40
|
| 290 |
},
|
| 291 |
{
|
| 292 |
"epoch": 0.82,
|
| 293 |
-
"grad_norm": 0.
|
| 294 |
-
"learning_rate":
|
| 295 |
-
"loss": 0.
|
| 296 |
"step": 41
|
| 297 |
},
|
| 298 |
{
|
| 299 |
"epoch": 0.84,
|
| 300 |
-
"grad_norm": 0.
|
| 301 |
-
"learning_rate":
|
| 302 |
-
"loss": 0.
|
| 303 |
"step": 42
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 0.86,
|
| 307 |
-
"grad_norm": 0.
|
| 308 |
-
"learning_rate":
|
| 309 |
-
"loss": 0.
|
| 310 |
"step": 43
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"epoch": 0.88,
|
| 314 |
-
"grad_norm": 0.
|
| 315 |
-
"learning_rate":
|
| 316 |
-
"loss": 0.
|
| 317 |
"step": 44
|
| 318 |
},
|
| 319 |
{
|
| 320 |
"epoch": 0.9,
|
| 321 |
-
"grad_norm": 0.
|
| 322 |
-
"learning_rate":
|
| 323 |
-
"loss": 0.
|
| 324 |
"step": 45
|
| 325 |
},
|
| 326 |
{
|
| 327 |
"epoch": 0.92,
|
| 328 |
-
"grad_norm": 0.
|
| 329 |
-
"learning_rate":
|
| 330 |
-
"loss": 0.
|
| 331 |
"step": 46
|
| 332 |
},
|
| 333 |
{
|
| 334 |
"epoch": 0.94,
|
| 335 |
-
"grad_norm": 0.
|
| 336 |
-
"learning_rate":
|
| 337 |
-
"loss": 0.
|
| 338 |
"step": 47
|
| 339 |
},
|
| 340 |
{
|
| 341 |
"epoch": 0.96,
|
| 342 |
-
"grad_norm": 0.
|
| 343 |
-
"learning_rate":
|
| 344 |
-
"loss": 0.
|
| 345 |
"step": 48
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 0.98,
|
| 349 |
-
"grad_norm": 0.
|
| 350 |
-
"learning_rate":
|
| 351 |
-
"loss": 0.
|
| 352 |
"step": 49
|
| 353 |
},
|
| 354 |
{
|
| 355 |
"epoch": 1.0,
|
| 356 |
-
"grad_norm": 0.
|
| 357 |
-
"learning_rate":
|
| 358 |
-
"loss": 0.
|
| 359 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 360 |
}
|
| 361 |
],
|
| 362 |
"logging_steps": 1,
|
| 363 |
-
"max_steps":
|
| 364 |
"num_input_tokens_seen": 0,
|
| 365 |
-
"num_train_epochs":
|
| 366 |
"save_steps": 500,
|
| 367 |
"stateful_callbacks": {
|
| 368 |
"TrainerControl": {
|
|
@@ -376,7 +726,7 @@
|
|
| 376 |
"attributes": {}
|
| 377 |
}
|
| 378 |
},
|
| 379 |
-
"total_flos":
|
| 380 |
"train_batch_size": 1,
|
| 381 |
"trial_name": null,
|
| 382 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.02,
|
| 13 |
+
"grad_norm": 0.3624022305011749,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 0.5345,
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.04,
|
| 20 |
+
"grad_norm": 0.3736283481121063,
|
| 21 |
+
"learning_rate": 4e-05,
|
| 22 |
+
"loss": 0.5545,
|
| 23 |
"step": 2
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.06,
|
| 27 |
+
"grad_norm": 0.3715187907218933,
|
| 28 |
+
"learning_rate": 6e-05,
|
| 29 |
+
"loss": 0.5167,
|
| 30 |
"step": 3
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.08,
|
| 34 |
+
"grad_norm": 0.3104977607727051,
|
| 35 |
+
"learning_rate": 8e-05,
|
| 36 |
+
"loss": 0.4994,
|
| 37 |
"step": 4
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.1,
|
| 41 |
+
"grad_norm": 0.3549410104751587,
|
| 42 |
+
"learning_rate": 0.0001,
|
| 43 |
+
"loss": 0.5208,
|
| 44 |
"step": 5
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.12,
|
| 48 |
+
"grad_norm": 0.41164880990982056,
|
| 49 |
+
"learning_rate": 9.997266286704631e-05,
|
| 50 |
+
"loss": 0.528,
|
| 51 |
"step": 6
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.14,
|
| 55 |
+
"grad_norm": 0.4071100354194641,
|
| 56 |
+
"learning_rate": 9.989068136093873e-05,
|
| 57 |
+
"loss": 0.5083,
|
| 58 |
"step": 7
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.16,
|
| 62 |
+
"grad_norm": 0.42801719903945923,
|
| 63 |
+
"learning_rate": 9.975414512725057e-05,
|
| 64 |
+
"loss": 0.5336,
|
| 65 |
"step": 8
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.18,
|
| 69 |
+
"grad_norm": 0.43720319867134094,
|
| 70 |
+
"learning_rate": 9.956320346634876e-05,
|
| 71 |
+
"loss": 0.5478,
|
| 72 |
"step": 9
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.2,
|
| 76 |
+
"grad_norm": 0.39605292677879333,
|
| 77 |
+
"learning_rate": 9.931806517013612e-05,
|
| 78 |
+
"loss": 0.5509,
|
| 79 |
"step": 10
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.22,
|
| 83 |
+
"grad_norm": 0.4373878240585327,
|
| 84 |
+
"learning_rate": 9.901899829374047e-05,
|
| 85 |
+
"loss": 0.4953,
|
| 86 |
"step": 11
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.24,
|
| 90 |
+
"grad_norm": 0.3865221440792084,
|
| 91 |
+
"learning_rate": 9.86663298624003e-05,
|
| 92 |
+
"loss": 0.5273,
|
| 93 |
"step": 12
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.26,
|
| 97 |
+
"grad_norm": 0.3498033881187439,
|
| 98 |
+
"learning_rate": 9.826044551386744e-05,
|
| 99 |
+
"loss": 0.5626,
|
| 100 |
"step": 13
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.28,
|
| 104 |
+
"grad_norm": 0.33049601316452026,
|
| 105 |
+
"learning_rate": 9.780178907671789e-05,
|
| 106 |
+
"loss": 0.5252,
|
| 107 |
"step": 14
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.3,
|
| 111 |
+
"grad_norm": 0.3525201082229614,
|
| 112 |
+
"learning_rate": 9.729086208503174e-05,
|
| 113 |
+
"loss": 0.5433,
|
| 114 |
"step": 15
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.32,
|
| 118 |
+
"grad_norm": 0.3323298990726471,
|
| 119 |
+
"learning_rate": 9.672822322997305e-05,
|
| 120 |
+
"loss": 0.5371,
|
| 121 |
"step": 16
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.34,
|
| 125 |
+
"grad_norm": 0.34475523233413696,
|
| 126 |
+
"learning_rate": 9.611448774886924e-05,
|
| 127 |
+
"loss": 0.5273,
|
| 128 |
"step": 17
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.36,
|
| 132 |
+
"grad_norm": 0.33978456258773804,
|
| 133 |
+
"learning_rate": 9.545032675245813e-05,
|
| 134 |
+
"loss": 0.5377,
|
| 135 |
"step": 18
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.38,
|
| 139 |
+
"grad_norm": 0.32446014881134033,
|
| 140 |
+
"learning_rate": 9.473646649103818e-05,
|
| 141 |
+
"loss": 0.5321,
|
| 142 |
"step": 19
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.4,
|
| 146 |
+
"grad_norm": 0.32642048597335815,
|
| 147 |
+
"learning_rate": 9.397368756032445e-05,
|
| 148 |
+
"loss": 0.5134,
|
| 149 |
"step": 20
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.42,
|
| 153 |
+
"grad_norm": 0.32789453864097595,
|
| 154 |
+
"learning_rate": 9.316282404787871e-05,
|
| 155 |
+
"loss": 0.5516,
|
| 156 |
"step": 21
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 0.44,
|
| 160 |
+
"grad_norm": 0.33384475111961365,
|
| 161 |
+
"learning_rate": 9.230476262104677e-05,
|
| 162 |
+
"loss": 0.5656,
|
| 163 |
"step": 22
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 0.46,
|
| 167 |
+
"grad_norm": 0.3290055990219116,
|
| 168 |
+
"learning_rate": 9.140044155740101e-05,
|
| 169 |
+
"loss": 0.5809,
|
| 170 |
"step": 23
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.48,
|
| 174 |
+
"grad_norm": 0.3402266204357147,
|
| 175 |
+
"learning_rate": 9.045084971874738e-05,
|
| 176 |
+
"loss": 0.5617,
|
| 177 |
"step": 24
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.5,
|
| 181 |
+
"grad_norm": 0.33358535170555115,
|
| 182 |
+
"learning_rate": 8.945702546981969e-05,
|
| 183 |
+
"loss": 0.5357,
|
| 184 |
"step": 25
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"epoch": 0.52,
|
| 188 |
+
"grad_norm": 0.33832627534866333,
|
| 189 |
+
"learning_rate": 8.842005554284296e-05,
|
| 190 |
+
"loss": 0.5587,
|
| 191 |
"step": 26
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 0.54,
|
| 195 |
+
"grad_norm": 0.3213883638381958,
|
| 196 |
+
"learning_rate": 8.73410738492077e-05,
|
| 197 |
+
"loss": 0.5697,
|
| 198 |
"step": 27
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 0.56,
|
| 202 |
+
"grad_norm": 0.34648266434669495,
|
| 203 |
+
"learning_rate": 8.622126023955446e-05,
|
| 204 |
+
"loss": 0.522,
|
| 205 |
"step": 28
|
| 206 |
},
|
| 207 |
{
|
| 208 |
"epoch": 0.58,
|
| 209 |
+
"grad_norm": 0.3362743854522705,
|
| 210 |
+
"learning_rate": 8.506183921362443e-05,
|
| 211 |
+
"loss": 0.5572,
|
| 212 |
"step": 29
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 0.6,
|
| 216 |
+
"grad_norm": 0.3271280825138092,
|
| 217 |
+
"learning_rate": 8.386407858128706e-05,
|
| 218 |
+
"loss": 0.514,
|
| 219 |
"step": 30
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.62,
|
| 223 |
+
"grad_norm": 0.334176629781723,
|
| 224 |
+
"learning_rate": 8.262928807620843e-05,
|
| 225 |
+
"loss": 0.5092,
|
| 226 |
"step": 31
|
| 227 |
},
|
| 228 |
{
|
| 229 |
"epoch": 0.64,
|
| 230 |
+
"grad_norm": 0.33813613653182983,
|
| 231 |
+
"learning_rate": 8.135881792367686e-05,
|
| 232 |
+
"loss": 0.57,
|
| 233 |
"step": 32
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 0.66,
|
| 237 |
+
"grad_norm": 0.3526760935783386,
|
| 238 |
+
"learning_rate": 8.005405736415126e-05,
|
| 239 |
+
"loss": 0.5737,
|
| 240 |
"step": 33
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 0.68,
|
| 244 |
+
"grad_norm": 0.3210213780403137,
|
| 245 |
+
"learning_rate": 7.871643313414718e-05,
|
| 246 |
+
"loss": 0.5444,
|
| 247 |
"step": 34
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"epoch": 0.7,
|
| 251 |
+
"grad_norm": 0.3287356197834015,
|
| 252 |
+
"learning_rate": 7.734740790612136e-05,
|
| 253 |
+
"loss": 0.5188,
|
| 254 |
"step": 35
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 0.72,
|
| 258 |
+
"grad_norm": 0.3406030535697937,
|
| 259 |
+
"learning_rate": 7.594847868906076e-05,
|
| 260 |
+
"loss": 0.5491,
|
| 261 |
"step": 36
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 0.74,
|
| 265 |
+
"grad_norm": 0.3229946792125702,
|
| 266 |
+
"learning_rate": 7.452117519152542e-05,
|
| 267 |
+
"loss": 0.5309,
|
| 268 |
"step": 37
|
| 269 |
},
|
| 270 |
{
|
| 271 |
"epoch": 0.76,
|
| 272 |
+
"grad_norm": 0.31070253252983093,
|
| 273 |
+
"learning_rate": 7.30670581489344e-05,
|
| 274 |
+
"loss": 0.5348,
|
| 275 |
"step": 38
|
| 276 |
},
|
| 277 |
{
|
| 278 |
"epoch": 0.78,
|
| 279 |
+
"grad_norm": 0.31888288259506226,
|
| 280 |
+
"learning_rate": 7.158771761692464e-05,
|
| 281 |
+
"loss": 0.5598,
|
| 282 |
"step": 39
|
| 283 |
},
|
| 284 |
{
|
| 285 |
"epoch": 0.8,
|
| 286 |
+
"grad_norm": 0.3222619295120239,
|
| 287 |
+
"learning_rate": 7.008477123264848e-05,
|
| 288 |
+
"loss": 0.5674,
|
| 289 |
"step": 40
|
| 290 |
},
|
| 291 |
{
|
| 292 |
"epoch": 0.82,
|
| 293 |
+
"grad_norm": 0.3319852352142334,
|
| 294 |
+
"learning_rate": 6.855986244591104e-05,
|
| 295 |
+
"loss": 0.5371,
|
| 296 |
"step": 41
|
| 297 |
},
|
| 298 |
{
|
| 299 |
"epoch": 0.84,
|
| 300 |
+
"grad_norm": 0.30418190360069275,
|
| 301 |
+
"learning_rate": 6.701465872208216e-05,
|
| 302 |
+
"loss": 0.5104,
|
| 303 |
"step": 42
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 0.86,
|
| 307 |
+
"grad_norm": 0.3073510229587555,
|
| 308 |
+
"learning_rate": 6.545084971874738e-05,
|
| 309 |
+
"loss": 0.5359,
|
| 310 |
"step": 43
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"epoch": 0.88,
|
| 314 |
+
"grad_norm": 0.3012188673019409,
|
| 315 |
+
"learning_rate": 6.387014543809223e-05,
|
| 316 |
+
"loss": 0.5341,
|
| 317 |
"step": 44
|
| 318 |
},
|
| 319 |
{
|
| 320 |
"epoch": 0.9,
|
| 321 |
+
"grad_norm": 0.2977622151374817,
|
| 322 |
+
"learning_rate": 6.227427435703997e-05,
|
| 323 |
+
"loss": 0.5448,
|
| 324 |
"step": 45
|
| 325 |
},
|
| 326 |
{
|
| 327 |
"epoch": 0.92,
|
| 328 |
+
"grad_norm": 0.312294065952301,
|
| 329 |
+
"learning_rate": 6.066498153718735e-05,
|
| 330 |
+
"loss": 0.5421,
|
| 331 |
"step": 46
|
| 332 |
},
|
| 333 |
{
|
| 334 |
"epoch": 0.94,
|
| 335 |
+
"grad_norm": 0.33205491304397583,
|
| 336 |
+
"learning_rate": 5.90440267166055e-05,
|
| 337 |
+
"loss": 0.5841,
|
| 338 |
"step": 47
|
| 339 |
},
|
| 340 |
{
|
| 341 |
"epoch": 0.96,
|
| 342 |
+
"grad_norm": 0.31330958008766174,
|
| 343 |
+
"learning_rate": 5.74131823855921e-05,
|
| 344 |
+
"loss": 0.5344,
|
| 345 |
"step": 48
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 0.98,
|
| 349 |
+
"grad_norm": 0.32422611117362976,
|
| 350 |
+
"learning_rate": 5.577423184847932e-05,
|
| 351 |
+
"loss": 0.5277,
|
| 352 |
"step": 49
|
| 353 |
},
|
| 354 |
{
|
| 355 |
"epoch": 1.0,
|
| 356 |
+
"grad_norm": 0.3156668245792389,
|
| 357 |
+
"learning_rate": 5.4128967273616625e-05,
|
| 358 |
+
"loss": 0.5454,
|
| 359 |
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.02,
|
| 363 |
+
"grad_norm": 0.3290346562862396,
|
| 364 |
+
"learning_rate": 5.247918773366112e-05,
|
| 365 |
+
"loss": 0.4873,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.04,
|
| 370 |
+
"grad_norm": 0.3424556255340576,
|
| 371 |
+
"learning_rate": 5.0826697238317935e-05,
|
| 372 |
+
"loss": 0.4639,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.06,
|
| 377 |
+
"grad_norm": 0.31981292366981506,
|
| 378 |
+
"learning_rate": 4.917330276168208e-05,
|
| 379 |
+
"loss": 0.459,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.08,
|
| 384 |
+
"grad_norm": 0.3340217173099518,
|
| 385 |
+
"learning_rate": 4.7520812266338885e-05,
|
| 386 |
+
"loss": 0.4981,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.1,
|
| 391 |
+
"grad_norm": 0.3345750868320465,
|
| 392 |
+
"learning_rate": 4.5871032726383386e-05,
|
| 393 |
+
"loss": 0.4898,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.12,
|
| 398 |
+
"grad_norm": 0.2998408079147339,
|
| 399 |
+
"learning_rate": 4.4225768151520694e-05,
|
| 400 |
+
"loss": 0.4329,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.1400000000000001,
|
| 405 |
+
"grad_norm": 0.33386602997779846,
|
| 406 |
+
"learning_rate": 4.2586817614407895e-05,
|
| 407 |
+
"loss": 0.43,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.16,
|
| 412 |
+
"grad_norm": 0.3249485492706299,
|
| 413 |
+
"learning_rate": 4.095597328339452e-05,
|
| 414 |
+
"loss": 0.4762,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.18,
|
| 419 |
+
"grad_norm": 0.32801133394241333,
|
| 420 |
+
"learning_rate": 3.933501846281267e-05,
|
| 421 |
+
"loss": 0.4514,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.2,
|
| 426 |
+
"grad_norm": 0.32089194655418396,
|
| 427 |
+
"learning_rate": 3.772572564296005e-05,
|
| 428 |
+
"loss": 0.4206,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.22,
|
| 433 |
+
"grad_norm": 0.32813841104507446,
|
| 434 |
+
"learning_rate": 3.612985456190778e-05,
|
| 435 |
+
"loss": 0.4853,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.24,
|
| 440 |
+
"grad_norm": 0.33598625659942627,
|
| 441 |
+
"learning_rate": 3.4549150281252636e-05,
|
| 442 |
+
"loss": 0.4334,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.26,
|
| 447 |
+
"grad_norm": 0.3225085139274597,
|
| 448 |
+
"learning_rate": 3.298534127791785e-05,
|
| 449 |
+
"loss": 0.4479,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.28,
|
| 454 |
+
"grad_norm": 0.3295815885066986,
|
| 455 |
+
"learning_rate": 3.144013755408895e-05,
|
| 456 |
+
"loss": 0.4739,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.3,
|
| 461 |
+
"grad_norm": 0.3391561508178711,
|
| 462 |
+
"learning_rate": 2.991522876735154e-05,
|
| 463 |
+
"loss": 0.4211,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.32,
|
| 468 |
+
"grad_norm": 0.3367979824542999,
|
| 469 |
+
"learning_rate": 2.8412282383075363e-05,
|
| 470 |
+
"loss": 0.4502,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.34,
|
| 475 |
+
"grad_norm": 0.3409813344478607,
|
| 476 |
+
"learning_rate": 2.693294185106562e-05,
|
| 477 |
+
"loss": 0.4886,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.3599999999999999,
|
| 482 |
+
"grad_norm": 0.33046984672546387,
|
| 483 |
+
"learning_rate": 2.547882480847461e-05,
|
| 484 |
+
"loss": 0.4142,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.38,
|
| 489 |
+
"grad_norm": 0.3314824104309082,
|
| 490 |
+
"learning_rate": 2.405152131093926e-05,
|
| 491 |
+
"loss": 0.4535,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.4,
|
| 496 |
+
"grad_norm": 0.34188470244407654,
|
| 497 |
+
"learning_rate": 2.2652592093878666e-05,
|
| 498 |
+
"loss": 0.4525,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.42,
|
| 503 |
+
"grad_norm": 0.3405551612377167,
|
| 504 |
+
"learning_rate": 2.128356686585282e-05,
|
| 505 |
+
"loss": 0.4306,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.44,
|
| 510 |
+
"grad_norm": 0.34439051151275635,
|
| 511 |
+
"learning_rate": 1.9945942635848748e-05,
|
| 512 |
+
"loss": 0.4849,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.46,
|
| 517 |
+
"grad_norm": 0.33053305745124817,
|
| 518 |
+
"learning_rate": 1.8641182076323148e-05,
|
| 519 |
+
"loss": 0.4395,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.48,
|
| 524 |
+
"grad_norm": 0.3231377601623535,
|
| 525 |
+
"learning_rate": 1.7370711923791567e-05,
|
| 526 |
+
"loss": 0.4461,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.5,
|
| 531 |
+
"grad_norm": 0.3283744752407074,
|
| 532 |
+
"learning_rate": 1.6135921418712956e-05,
|
| 533 |
+
"loss": 0.4322,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.52,
|
| 538 |
+
"grad_norm": 0.3327557146549225,
|
| 539 |
+
"learning_rate": 1.4938160786375572e-05,
|
| 540 |
+
"loss": 0.4796,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.54,
|
| 545 |
+
"grad_norm": 0.3517839312553406,
|
| 546 |
+
"learning_rate": 1.3778739760445552e-05,
|
| 547 |
+
"loss": 0.4617,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.56,
|
| 552 |
+
"grad_norm": 0.3397415578365326,
|
| 553 |
+
"learning_rate": 1.2658926150792322e-05,
|
| 554 |
+
"loss": 0.4561,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.58,
|
| 559 |
+
"grad_norm": 0.32547858357429504,
|
| 560 |
+
"learning_rate": 1.157994445715706e-05,
|
| 561 |
+
"loss": 0.4522,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.6,
|
| 566 |
+
"grad_norm": 0.322001576423645,
|
| 567 |
+
"learning_rate": 1.0542974530180327e-05,
|
| 568 |
+
"loss": 0.4275,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.62,
|
| 573 |
+
"grad_norm": 0.32253459095954895,
|
| 574 |
+
"learning_rate": 9.549150281252633e-06,
|
| 575 |
+
"loss": 0.4388,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.6400000000000001,
|
| 580 |
+
"grad_norm": 0.33204764127731323,
|
| 581 |
+
"learning_rate": 8.599558442598998e-06,
|
| 582 |
+
"loss": 0.4317,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.6600000000000001,
|
| 587 |
+
"grad_norm": 0.32604044675827026,
|
| 588 |
+
"learning_rate": 7.695237378953223e-06,
|
| 589 |
+
"loss": 0.4357,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.6800000000000002,
|
| 594 |
+
"grad_norm": 0.34298455715179443,
|
| 595 |
+
"learning_rate": 6.837175952121306e-06,
|
| 596 |
+
"loss": 0.442,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.7,
|
| 601 |
+
"grad_norm": 0.3202356994152069,
|
| 602 |
+
"learning_rate": 6.026312439675552e-06,
|
| 603 |
+
"loss": 0.4342,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.72,
|
| 608 |
+
"grad_norm": 0.3258272409439087,
|
| 609 |
+
"learning_rate": 5.263533508961827e-06,
|
| 610 |
+
"loss": 0.4348,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.74,
|
| 615 |
+
"grad_norm": 0.3249031901359558,
|
| 616 |
+
"learning_rate": 4.549673247541875e-06,
|
| 617 |
+
"loss": 0.4093,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.76,
|
| 622 |
+
"grad_norm": 0.32874855399131775,
|
| 623 |
+
"learning_rate": 3.885512251130763e-06,
|
| 624 |
+
"loss": 0.4076,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.78,
|
| 629 |
+
"grad_norm": 0.33212965726852417,
|
| 630 |
+
"learning_rate": 3.271776770026963e-06,
|
| 631 |
+
"loss": 0.4426,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.8,
|
| 636 |
+
"grad_norm": 0.32816311717033386,
|
| 637 |
+
"learning_rate": 2.7091379149682685e-06,
|
| 638 |
+
"loss": 0.4422,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.8199999999999998,
|
| 643 |
+
"grad_norm": 0.333683580160141,
|
| 644 |
+
"learning_rate": 2.1982109232821178e-06,
|
| 645 |
+
"loss": 0.4619,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.8399999999999999,
|
| 650 |
+
"grad_norm": 0.3273014724254608,
|
| 651 |
+
"learning_rate": 1.7395544861325718e-06,
|
| 652 |
+
"loss": 0.4662,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.8599999999999999,
|
| 657 |
+
"grad_norm": 0.33303171396255493,
|
| 658 |
+
"learning_rate": 1.333670137599713e-06,
|
| 659 |
+
"loss": 0.4467,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.88,
|
| 664 |
+
"grad_norm": 0.3208991587162018,
|
| 665 |
+
"learning_rate": 9.810017062595322e-07,
|
| 666 |
+
"loss": 0.4459,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.9,
|
| 671 |
+
"grad_norm": 0.3281053304672241,
|
| 672 |
+
"learning_rate": 6.819348298638839e-07,
|
| 673 |
+
"loss": 0.4471,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.92,
|
| 678 |
+
"grad_norm": 0.31943386793136597,
|
| 679 |
+
"learning_rate": 4.367965336512403e-07,
|
| 680 |
+
"loss": 0.4342,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.94,
|
| 685 |
+
"grad_norm": 0.3442579507827759,
|
| 686 |
+
"learning_rate": 2.458548727494292e-07,
|
| 687 |
+
"loss": 0.454,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.96,
|
| 692 |
+
"grad_norm": 0.3283260762691498,
|
| 693 |
+
"learning_rate": 1.0931863906127327e-07,
|
| 694 |
+
"loss": 0.4328,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.98,
|
| 699 |
+
"grad_norm": 0.33244219422340393,
|
| 700 |
+
"learning_rate": 2.7337132953697554e-08,
|
| 701 |
+
"loss": 0.4145,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 2.0,
|
| 706 |
+
"grad_norm": 0.3326053321361542,
|
| 707 |
+
"learning_rate": 0.0,
|
| 708 |
+
"loss": 0.4836,
|
| 709 |
+
"step": 100
|
| 710 |
}
|
| 711 |
],
|
| 712 |
"logging_steps": 1,
|
| 713 |
+
"max_steps": 100,
|
| 714 |
"num_input_tokens_seen": 0,
|
| 715 |
+
"num_train_epochs": 2,
|
| 716 |
"save_steps": 500,
|
| 717 |
"stateful_callbacks": {
|
| 718 |
"TrainerControl": {
|
|
|
|
| 726 |
"attributes": {}
|
| 727 |
}
|
| 728 |
},
|
| 729 |
+
"total_flos": 1.211706059414569e+17,
|
| 730 |
"train_batch_size": 1,
|
| 731 |
"trial_name": null,
|
| 732 |
"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 sha256:3991df946dfe0faf0ca3dbffd32bec5aefcf4baf342b73addfac6fc0a9b22d2f
|
| 3 |
size 5240
|