Model save
Browse files- README.md +1 -1
- all_results.json +5 -5
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- train_results.json +5 -5
- trainer_state.json +1125 -789
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -35,7 +35,7 @@ The following hyperparameters were used during training:
|
|
| 35 |
- learning_rate: 1e-06
|
| 36 |
- train_batch_size: 2
|
| 37 |
- eval_batch_size: 8
|
| 38 |
-
- seed:
|
| 39 |
- distributed_type: multi-GPU
|
| 40 |
- num_devices: 8
|
| 41 |
- gradient_accumulation_steps: 8
|
|
|
|
| 35 |
- learning_rate: 1e-06
|
| 36 |
- train_batch_size: 2
|
| 37 |
- eval_batch_size: 8
|
| 38 |
+
- seed: 1
|
| 39 |
- distributed_type: multi-GPU
|
| 40 |
- num_devices: 8
|
| 41 |
- gradient_accumulation_steps: 8
|
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
+
"train_loss": 0.050850671487596796,
|
| 4 |
+
"train_runtime": 12712.7589,
|
| 5 |
+
"train_samples": 61134,
|
| 6 |
+
"train_samples_per_second": 9.618,
|
| 7 |
+
"train_steps_per_second": 0.075
|
| 8 |
}
|
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4976698672
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7618f7999999ef60b2bfe93ea1451f00269f72eacb4df7c6c113ae154adca33a
|
| 3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4999802720
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9e1ad781186cb8bf880a39e7274512b7b6981f9be52ef8007de07ccca61620c
|
| 3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915916176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2443b4320da98c5727b93698fb94167c01ff8f426fb8289a970af245b8f93022
|
| 3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1168138808
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f60ade571941bdba1e5f8c4d7b6dd59bc051248e9fca85c5e2cff4d393bd5ead
|
| 3 |
size 1168138808
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
+
"train_loss": 0.050850671487596796,
|
| 4 |
+
"train_runtime": 12712.7589,
|
| 5 |
+
"train_samples": 61134,
|
| 6 |
+
"train_samples_per_second": 9.618,
|
| 7 |
+
"train_steps_per_second": 0.075
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,1019 +1,1355 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 1.
|
| 5 |
"eval_steps": 10000,
|
| 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 |
-
"learning_rate": 1.
|
| 14 |
-
"logits/chosen":
|
| 15 |
-
"logits/rejected": 0.
|
| 16 |
-
"logps/chosen": -
|
| 17 |
-
"logps/rejected": -
|
| 18 |
-
"loss": 0.
|
| 19 |
-
"rewards/accuracies": 0.
|
| 20 |
-
"rewards/chosen": -
|
| 21 |
-
"rewards/margins":
|
| 22 |
-
"rewards/rejected": 0.
|
| 23 |
"step": 10
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"learning_rate": 2.
|
| 28 |
-
"logits/chosen":
|
| 29 |
-
"logits/rejected":
|
| 30 |
-
"logps/chosen": -
|
| 31 |
-
"logps/rejected": -
|
| 32 |
-
"loss": 0.
|
| 33 |
-
"rewards/accuracies": 0.
|
| 34 |
-
"rewards/chosen": 0.
|
| 35 |
-
"rewards/margins": 0.
|
| 36 |
-
"rewards/rejected": -0.
|
| 37 |
"step": 20
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch": 0.
|
| 41 |
-
"learning_rate":
|
| 42 |
-
"logits/chosen":
|
| 43 |
-
"logits/rejected": 0.
|
| 44 |
-
"logps/chosen": -
|
| 45 |
-
"logps/rejected": -
|
| 46 |
-
"loss": 0.
|
| 47 |
-
"rewards/accuracies": 0.
|
| 48 |
-
"rewards/chosen": -
|
| 49 |
-
"rewards/margins": 0.
|
| 50 |
-
"rewards/rejected": -0.
|
| 51 |
"step": 30
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"learning_rate":
|
| 56 |
-
"logits/chosen":
|
| 57 |
-
"logits/rejected": 0.
|
| 58 |
-
"logps/chosen": -
|
| 59 |
-
"logps/rejected": -
|
| 60 |
-
"loss": 0.
|
| 61 |
-
"rewards/accuracies": 0.
|
| 62 |
-
"rewards/chosen":
|
| 63 |
-
"rewards/margins": 0.
|
| 64 |
-
"rewards/rejected": -0.
|
| 65 |
"step": 40
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch": 0.
|
| 69 |
-
"learning_rate":
|
| 70 |
-
"logits/chosen": 0.
|
| 71 |
-
"logits/rejected": 0.
|
| 72 |
-
"logps/chosen": -
|
| 73 |
-
"logps/rejected": -
|
| 74 |
-
"loss": 0.
|
| 75 |
-
"rewards/accuracies": 0.
|
| 76 |
-
"rewards/chosen": -0.
|
| 77 |
-
"rewards/margins": 0.
|
| 78 |
-
"rewards/rejected": -0.
|
| 79 |
"step": 50
|
| 80 |
},
|
| 81 |
{
|
| 82 |
-
"epoch": 0.
|
| 83 |
-
"learning_rate":
|
| 84 |
-
"logits/chosen":
|
| 85 |
-
"logits/rejected": 0.
|
| 86 |
-
"logps/chosen": -
|
| 87 |
-
"logps/rejected": -
|
| 88 |
-
"loss": 0.
|
| 89 |
-
"rewards/accuracies": 0.
|
| 90 |
-
"rewards/chosen": -0.
|
| 91 |
-
"rewards/margins": 0.
|
| 92 |
-
"rewards/rejected": -0.
|
| 93 |
"step": 60
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 0.
|
| 97 |
-
"learning_rate":
|
| 98 |
-
"logits/chosen":
|
| 99 |
-
"logits/rejected":
|
| 100 |
-
"logps/chosen": -
|
| 101 |
-
"logps/rejected": -
|
| 102 |
-
"loss": 0.
|
| 103 |
-
"rewards/accuracies": 0.
|
| 104 |
-
"rewards/chosen": -0.
|
| 105 |
-
"rewards/margins": 0.
|
| 106 |
-
"rewards/rejected": -0.
|
| 107 |
"step": 70
|
| 108 |
},
|
| 109 |
{
|
| 110 |
-
"epoch": 0.
|
| 111 |
-
"learning_rate":
|
| 112 |
-
"logits/chosen": 0.
|
| 113 |
-
"logits/rejected": 0.
|
| 114 |
-
"logps/chosen": -
|
| 115 |
-
"logps/rejected": -
|
| 116 |
-
"loss": 0.
|
| 117 |
-
"rewards/accuracies": 0.
|
| 118 |
-
"rewards/chosen": -0.
|
| 119 |
-
"rewards/margins": 0.
|
| 120 |
-
"rewards/rejected": -0.
|
| 121 |
"step": 80
|
| 122 |
},
|
| 123 |
{
|
| 124 |
-
"epoch": 0.
|
| 125 |
-
"learning_rate": 9.
|
| 126 |
-
"logits/chosen":
|
| 127 |
-
"logits/rejected": 0.
|
| 128 |
-
"logps/chosen": -
|
| 129 |
-
"logps/rejected": -
|
| 130 |
-
"loss": 0.
|
| 131 |
-
"rewards/accuracies": 0.
|
| 132 |
-
"rewards/chosen": 0.
|
| 133 |
-
"rewards/margins": 0.
|
| 134 |
-
"rewards/rejected": -0.
|
| 135 |
"step": 90
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch": 0.
|
| 139 |
-
"learning_rate": 9.
|
| 140 |
-
"logits/chosen":
|
| 141 |
-
"logits/rejected": 0.
|
| 142 |
-
"logps/chosen": -
|
| 143 |
-
"logps/rejected": -
|
| 144 |
-
"loss": 0.
|
| 145 |
-
"rewards/accuracies": 0.
|
| 146 |
-
"rewards/chosen": 0.
|
| 147 |
-
"rewards/margins": 0.
|
| 148 |
-
"rewards/rejected": -0.
|
| 149 |
"step": 100
|
| 150 |
},
|
| 151 |
{
|
| 152 |
-
"epoch": 0.
|
| 153 |
-
"learning_rate": 9.
|
| 154 |
-
"logits/chosen":
|
| 155 |
-
"logits/rejected": 0.
|
| 156 |
-
"logps/chosen": -
|
| 157 |
-
"logps/rejected": -
|
| 158 |
-
"loss": 0.
|
| 159 |
-
"rewards/accuracies": 0.
|
| 160 |
-
"rewards/chosen": 0.
|
| 161 |
-
"rewards/margins": 0.
|
| 162 |
-
"rewards/rejected": -0.
|
| 163 |
"step": 110
|
| 164 |
},
|
| 165 |
{
|
| 166 |
-
"epoch": 0.
|
| 167 |
-
"learning_rate": 9.
|
| 168 |
-
"logits/chosen":
|
| 169 |
-
"logits/rejected":
|
| 170 |
-
"logps/chosen": -
|
| 171 |
-
"logps/rejected": -
|
| 172 |
-
"loss": 0.
|
| 173 |
-
"rewards/accuracies": 0.
|
| 174 |
-
"rewards/chosen": 0.
|
| 175 |
-
"rewards/margins": 0.
|
| 176 |
-
"rewards/rejected": -0.
|
| 177 |
"step": 120
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch": 0.
|
| 181 |
-
"learning_rate": 9.
|
| 182 |
-
"logits/chosen":
|
| 183 |
-
"logits/rejected":
|
| 184 |
-
"logps/chosen": -
|
| 185 |
-
"logps/rejected": -
|
| 186 |
-
"loss": 0.
|
| 187 |
-
"rewards/accuracies": 0.
|
| 188 |
-
"rewards/chosen": -0.
|
| 189 |
-
"rewards/margins": 0.
|
| 190 |
-
"rewards/rejected": -0.
|
| 191 |
"step": 130
|
| 192 |
},
|
| 193 |
{
|
| 194 |
-
"epoch": 0.
|
| 195 |
-
"learning_rate": 9.
|
| 196 |
-
"logits/chosen":
|
| 197 |
-
"logits/rejected":
|
| 198 |
-
"logps/chosen": -
|
| 199 |
-
"logps/rejected": -
|
| 200 |
-
"loss": 0.
|
| 201 |
-
"rewards/accuracies": 0.
|
| 202 |
-
"rewards/chosen": -0.
|
| 203 |
-
"rewards/margins": 0.
|
| 204 |
-
"rewards/rejected": -0.
|
| 205 |
"step": 140
|
| 206 |
},
|
| 207 |
{
|
| 208 |
-
"epoch": 0.
|
| 209 |
-
"learning_rate": 9.
|
| 210 |
-
"logits/chosen":
|
| 211 |
-
"logits/rejected":
|
| 212 |
-
"logps/chosen": -
|
| 213 |
-
"logps/rejected": -
|
| 214 |
-
"loss": 0.
|
| 215 |
-
"rewards/accuracies": 0.
|
| 216 |
-
"rewards/chosen": -0.
|
| 217 |
-
"rewards/margins": 0.
|
| 218 |
-
"rewards/rejected": -0.
|
| 219 |
"step": 150
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch": 0.
|
| 223 |
-
"learning_rate": 9.
|
| 224 |
-
"logits/chosen":
|
| 225 |
-
"logits/rejected":
|
| 226 |
-
"logps/chosen": -341.
|
| 227 |
-
"logps/rejected": -
|
| 228 |
-
"loss": 0.
|
| 229 |
-
"rewards/accuracies": 0.
|
| 230 |
-
"rewards/chosen": 0.
|
| 231 |
-
"rewards/margins": 0.
|
| 232 |
-
"rewards/rejected": -0.
|
| 233 |
"step": 160
|
| 234 |
},
|
| 235 |
{
|
| 236 |
-
"epoch": 0.
|
| 237 |
-
"learning_rate": 9.
|
| 238 |
-
"logits/chosen":
|
| 239 |
-
"logits/rejected":
|
| 240 |
-
"logps/chosen": -
|
| 241 |
-
"logps/rejected": -
|
| 242 |
-
"loss": 0.
|
| 243 |
-
"rewards/accuracies": 0.
|
| 244 |
-
"rewards/chosen": 0.
|
| 245 |
-
"rewards/margins": 0.
|
| 246 |
-
"rewards/rejected": -
|
| 247 |
"step": 170
|
| 248 |
},
|
| 249 |
{
|
| 250 |
-
"epoch": 0.
|
| 251 |
-
"learning_rate": 9.
|
| 252 |
-
"logits/chosen":
|
| 253 |
-
"logits/rejected": 0.
|
| 254 |
-
"logps/chosen": -
|
| 255 |
-
"logps/rejected": -
|
| 256 |
-
"loss": 0.
|
| 257 |
-
"rewards/accuracies": 0.
|
| 258 |
-
"rewards/chosen": -0.
|
| 259 |
-
"rewards/margins": 0.
|
| 260 |
-
"rewards/rejected": -
|
| 261 |
"step": 180
|
| 262 |
},
|
| 263 |
{
|
| 264 |
-
"epoch": 0.
|
| 265 |
-
"learning_rate": 9.
|
| 266 |
-
"logits/chosen":
|
| 267 |
-
"logits/rejected":
|
| 268 |
-
"logps/chosen": -
|
| 269 |
-
"logps/rejected": -
|
| 270 |
-
"loss": 0.
|
| 271 |
-
"rewards/accuracies": 0.
|
| 272 |
-
"rewards/chosen": -0.
|
| 273 |
-
"rewards/margins": 0.
|
| 274 |
-
"rewards/rejected": -
|
| 275 |
"step": 190
|
| 276 |
},
|
| 277 |
{
|
| 278 |
-
"epoch": 0.
|
| 279 |
-
"learning_rate": 9.
|
| 280 |
-
"logits/chosen":
|
| 281 |
-
"logits/rejected":
|
| 282 |
-
"logps/chosen": -
|
| 283 |
-
"logps/rejected": -
|
| 284 |
-
"loss": 0.
|
| 285 |
-
"rewards/accuracies": 0.
|
| 286 |
-
"rewards/chosen": -0.
|
| 287 |
-
"rewards/margins": 0.
|
| 288 |
-
"rewards/rejected": -
|
| 289 |
"step": 200
|
| 290 |
},
|
| 291 |
{
|
| 292 |
-
"epoch": 0.
|
| 293 |
-
"learning_rate":
|
| 294 |
-
"logits/chosen":
|
| 295 |
-
"logits/rejected":
|
| 296 |
-
"logps/chosen": -
|
| 297 |
-
"logps/rejected": -
|
| 298 |
-
"loss": 0.
|
| 299 |
-
"rewards/accuracies": 0.
|
| 300 |
-
"rewards/chosen": -0.
|
| 301 |
-
"rewards/margins": 0.
|
| 302 |
-
"rewards/rejected": -
|
| 303 |
"step": 210
|
| 304 |
},
|
| 305 |
{
|
| 306 |
-
"epoch": 0.
|
| 307 |
-
"learning_rate":
|
| 308 |
-
"logits/chosen":
|
| 309 |
-
"logits/rejected":
|
| 310 |
-
"logps/chosen": -
|
| 311 |
-
"logps/rejected": -
|
| 312 |
-
"loss": 0.
|
| 313 |
-
"rewards/accuracies": 0.
|
| 314 |
-
"rewards/chosen": -0.
|
| 315 |
-
"rewards/margins": 0.
|
| 316 |
-
"rewards/rejected": -
|
| 317 |
"step": 220
|
| 318 |
},
|
| 319 |
{
|
| 320 |
-
"epoch": 0.
|
| 321 |
-
"learning_rate":
|
| 322 |
-
"logits/chosen":
|
| 323 |
-
"logits/rejected":
|
| 324 |
-
"logps/chosen": -
|
| 325 |
-
"logps/rejected": -
|
| 326 |
-
"loss": 0.
|
| 327 |
-
"rewards/accuracies": 0.
|
| 328 |
-
"rewards/chosen": -0.
|
| 329 |
-
"rewards/margins": 0.
|
| 330 |
-
"rewards/rejected": -
|
| 331 |
"step": 230
|
| 332 |
},
|
| 333 |
{
|
| 334 |
-
"epoch": 0.
|
| 335 |
-
"learning_rate":
|
| 336 |
-
"logits/chosen":
|
| 337 |
-
"logits/rejected":
|
| 338 |
-
"logps/chosen": -
|
| 339 |
-
"logps/rejected": -
|
| 340 |
-
"loss": 0.
|
| 341 |
-
"rewards/accuracies": 0.
|
| 342 |
-
"rewards/chosen": -0.
|
| 343 |
-
"rewards/margins": 0.
|
| 344 |
-
"rewards/rejected": -
|
| 345 |
"step": 240
|
| 346 |
},
|
| 347 |
{
|
| 348 |
-
"epoch": 0.
|
| 349 |
-
"learning_rate":
|
| 350 |
-
"logits/chosen":
|
| 351 |
-
"logits/rejected":
|
| 352 |
-
"logps/chosen": -
|
| 353 |
-
"logps/rejected": -
|
| 354 |
-
"loss": 0.
|
| 355 |
-
"rewards/accuracies": 0.
|
| 356 |
-
"rewards/chosen": -0.
|
| 357 |
-
"rewards/margins": 0.
|
| 358 |
-
"rewards/rejected": -
|
| 359 |
"step": 250
|
| 360 |
},
|
| 361 |
{
|
| 362 |
-
"epoch": 0.
|
| 363 |
-
"learning_rate":
|
| 364 |
-
"logits/chosen":
|
| 365 |
-
"logits/rejected":
|
| 366 |
-
"logps/chosen": -
|
| 367 |
-
"logps/rejected": -
|
| 368 |
-
"loss": 0.
|
| 369 |
-
"rewards/accuracies": 0.
|
| 370 |
-
"rewards/chosen": -0.
|
| 371 |
-
"rewards/margins": 0.
|
| 372 |
-
"rewards/rejected": -
|
| 373 |
"step": 260
|
| 374 |
},
|
| 375 |
{
|
| 376 |
-
"epoch": 0.
|
| 377 |
-
"learning_rate":
|
| 378 |
-
"logits/chosen":
|
| 379 |
-
"logits/rejected": 0.
|
| 380 |
-
"logps/chosen": -
|
| 381 |
-
"logps/rejected": -
|
| 382 |
-
"loss": 0.
|
| 383 |
-
"rewards/accuracies": 0.
|
| 384 |
-
"rewards/chosen": -0.
|
| 385 |
-
"rewards/margins": 0.
|
| 386 |
-
"rewards/rejected": -
|
| 387 |
"step": 270
|
| 388 |
},
|
| 389 |
{
|
| 390 |
-
"epoch": 0.
|
| 391 |
-
"learning_rate":
|
| 392 |
-
"logits/chosen":
|
| 393 |
-
"logits/rejected":
|
| 394 |
-
"logps/chosen": -
|
| 395 |
-
"logps/rejected": -
|
| 396 |
-
"loss": 0.
|
| 397 |
-
"rewards/accuracies": 0.
|
| 398 |
-
"rewards/chosen": -0.
|
| 399 |
-
"rewards/margins": 0.
|
| 400 |
-
"rewards/rejected": -
|
| 401 |
"step": 280
|
| 402 |
},
|
| 403 |
{
|
| 404 |
-
"epoch": 0.
|
| 405 |
-
"learning_rate":
|
| 406 |
-
"logits/chosen":
|
| 407 |
-
"logits/rejected":
|
| 408 |
-
"logps/chosen": -
|
| 409 |
-
"logps/rejected": -
|
| 410 |
-
"loss": 0.
|
| 411 |
-
"rewards/accuracies": 0.
|
| 412 |
-
"rewards/chosen": -0.
|
| 413 |
-
"rewards/margins": 0.
|
| 414 |
-
"rewards/rejected": -
|
| 415 |
"step": 290
|
| 416 |
},
|
| 417 |
{
|
| 418 |
-
"epoch": 0.
|
| 419 |
-
"learning_rate":
|
| 420 |
-
"logits/chosen":
|
| 421 |
-
"logits/rejected":
|
| 422 |
-
"logps/chosen": -
|
| 423 |
-
"logps/rejected": -
|
| 424 |
-
"loss": 0.
|
| 425 |
-
"rewards/accuracies": 0.
|
| 426 |
-
"rewards/chosen": -0.
|
| 427 |
-
"rewards/margins": 0.
|
| 428 |
-
"rewards/rejected": -
|
| 429 |
"step": 300
|
| 430 |
},
|
| 431 |
{
|
| 432 |
-
"epoch": 0.
|
| 433 |
-
"learning_rate":
|
| 434 |
-
"logits/chosen":
|
| 435 |
-
"logits/rejected":
|
| 436 |
-
"logps/chosen": -
|
| 437 |
-
"logps/rejected": -
|
| 438 |
-
"loss": 0.
|
| 439 |
-
"rewards/accuracies": 0.
|
| 440 |
-
"rewards/chosen": -0.
|
| 441 |
-
"rewards/margins": 0.
|
| 442 |
-
"rewards/rejected": -
|
| 443 |
"step": 310
|
| 444 |
},
|
| 445 |
{
|
| 446 |
-
"epoch": 0.
|
| 447 |
-
"learning_rate":
|
| 448 |
-
"logits/chosen":
|
| 449 |
-
"logits/rejected":
|
| 450 |
-
"logps/chosen": -
|
| 451 |
-
"logps/rejected": -
|
| 452 |
-
"loss": 0.
|
| 453 |
-
"rewards/accuracies": 0.
|
| 454 |
-
"rewards/chosen": -0.
|
| 455 |
-
"rewards/margins": 0.
|
| 456 |
-
"rewards/rejected": -
|
| 457 |
"step": 320
|
| 458 |
},
|
| 459 |
{
|
| 460 |
-
"epoch": 0.
|
| 461 |
-
"learning_rate":
|
| 462 |
-
"logits/chosen":
|
| 463 |
-
"logits/rejected":
|
| 464 |
-
"logps/chosen": -
|
| 465 |
-
"logps/rejected": -
|
| 466 |
-
"loss": 0.
|
| 467 |
-
"rewards/accuracies": 0.
|
| 468 |
-
"rewards/chosen": -0.
|
| 469 |
-
"rewards/margins": 0.
|
| 470 |
-
"rewards/rejected": -
|
| 471 |
"step": 330
|
| 472 |
},
|
| 473 |
{
|
| 474 |
-
"epoch": 0.
|
| 475 |
-
"learning_rate":
|
| 476 |
-
"logits/chosen":
|
| 477 |
-
"logits/rejected":
|
| 478 |
-
"logps/chosen": -
|
| 479 |
-
"logps/rejected": -
|
| 480 |
-
"loss": 0.
|
| 481 |
-
"rewards/accuracies": 0.
|
| 482 |
-
"rewards/chosen": -0.
|
| 483 |
-
"rewards/margins": 0.
|
| 484 |
-
"rewards/rejected": -
|
| 485 |
"step": 340
|
| 486 |
},
|
| 487 |
{
|
| 488 |
-
"epoch": 0.
|
| 489 |
-
"learning_rate":
|
| 490 |
-
"logits/chosen":
|
| 491 |
-
"logits/rejected":
|
| 492 |
-
"logps/chosen": -
|
| 493 |
-
"logps/rejected": -
|
| 494 |
-
"loss": 0.
|
| 495 |
-
"rewards/accuracies": 0.
|
| 496 |
-
"rewards/chosen": -0.
|
| 497 |
-
"rewards/margins": 0.
|
| 498 |
-
"rewards/rejected": -
|
| 499 |
"step": 350
|
| 500 |
},
|
| 501 |
{
|
| 502 |
-
"epoch":
|
| 503 |
-
"learning_rate":
|
| 504 |
-
"logits/chosen":
|
| 505 |
-
"logits/rejected":
|
| 506 |
-
"logps/chosen": -
|
| 507 |
-
"logps/rejected": -
|
| 508 |
-
"loss": 0.
|
| 509 |
-
"rewards/accuracies": 0.
|
| 510 |
-
"rewards/chosen": -0.
|
| 511 |
-
"rewards/margins": 0.
|
| 512 |
-
"rewards/rejected": -
|
| 513 |
"step": 360
|
| 514 |
},
|
| 515 |
{
|
| 516 |
-
"epoch":
|
| 517 |
-
"learning_rate":
|
| 518 |
-
"logits/chosen":
|
| 519 |
-
"logits/rejected":
|
| 520 |
-
"logps/chosen": -
|
| 521 |
-
"logps/rejected": -
|
| 522 |
-
"loss": 0.
|
| 523 |
-
"rewards/accuracies": 0.
|
| 524 |
-
"rewards/chosen": -0.
|
| 525 |
-
"rewards/margins": 0.
|
| 526 |
-
"rewards/rejected": -1.
|
| 527 |
"step": 370
|
| 528 |
},
|
| 529 |
{
|
| 530 |
-
"epoch":
|
| 531 |
-
"learning_rate":
|
| 532 |
-
"logits/chosen":
|
| 533 |
-
"logits/rejected": 0.
|
| 534 |
-
"logps/chosen": -
|
| 535 |
-
"logps/rejected": -
|
| 536 |
-
"loss": 0.
|
| 537 |
-
"rewards/accuracies": 0.
|
| 538 |
-
"rewards/chosen": -0.
|
| 539 |
-
"rewards/margins": 0.
|
| 540 |
-
"rewards/rejected": -1.
|
| 541 |
"step": 380
|
| 542 |
},
|
| 543 |
{
|
| 544 |
-
"epoch":
|
| 545 |
-
"learning_rate":
|
| 546 |
-
"logits/chosen": -0.
|
| 547 |
-
"logits/rejected":
|
| 548 |
-
"logps/chosen": -
|
| 549 |
-
"logps/rejected": -
|
| 550 |
-
"loss": 0.
|
| 551 |
-
"rewards/accuracies": 0.
|
| 552 |
-
"rewards/chosen": -
|
| 553 |
-
"rewards/margins": 0.
|
| 554 |
-
"rewards/rejected": -1.
|
| 555 |
"step": 390
|
| 556 |
},
|
| 557 |
{
|
| 558 |
-
"epoch":
|
| 559 |
-
"learning_rate":
|
| 560 |
-
"logits/chosen":
|
| 561 |
-
"logits/rejected":
|
| 562 |
-
"logps/chosen": -
|
| 563 |
-
"logps/rejected": -
|
| 564 |
-
"loss": 0.
|
| 565 |
-
"rewards/accuracies": 0.
|
| 566 |
-
"rewards/chosen": -
|
| 567 |
-
"rewards/margins": 0.
|
| 568 |
-
"rewards/rejected": -1.
|
| 569 |
"step": 400
|
| 570 |
},
|
| 571 |
{
|
| 572 |
-
"epoch":
|
| 573 |
-
"learning_rate":
|
| 574 |
-
"logits/chosen": -0.
|
| 575 |
-
"logits/rejected":
|
| 576 |
-
"logps/chosen": -394.
|
| 577 |
-
"logps/rejected": -
|
| 578 |
-
"loss": 0.
|
| 579 |
-
"rewards/accuracies": 0.
|
| 580 |
-
"rewards/chosen": -
|
| 581 |
-
"rewards/margins": 0.
|
| 582 |
-
"rewards/rejected": -1.
|
| 583 |
"step": 410
|
| 584 |
},
|
| 585 |
{
|
| 586 |
-
"epoch":
|
| 587 |
-
"learning_rate":
|
| 588 |
-
"logits/chosen":
|
| 589 |
-
"logits/rejected":
|
| 590 |
-
"logps/chosen": -
|
| 591 |
-
"logps/rejected": -
|
| 592 |
-
"loss": 0.
|
| 593 |
-
"rewards/accuracies": 0.
|
| 594 |
-
"rewards/chosen": -0.
|
| 595 |
-
"rewards/margins": 0.
|
| 596 |
-
"rewards/rejected": -1.
|
| 597 |
"step": 420
|
| 598 |
},
|
| 599 |
{
|
| 600 |
-
"epoch":
|
| 601 |
-
"learning_rate":
|
| 602 |
-
"logits/chosen":
|
| 603 |
-
"logits/rejected":
|
| 604 |
-
"logps/chosen": -
|
| 605 |
-
"logps/rejected": -
|
| 606 |
-
"loss": 0.
|
| 607 |
-
"rewards/accuracies": 0.
|
| 608 |
-
"rewards/chosen": -
|
| 609 |
-
"rewards/margins": 0.
|
| 610 |
-
"rewards/rejected": -1.
|
| 611 |
"step": 430
|
| 612 |
},
|
| 613 |
{
|
| 614 |
-
"epoch":
|
| 615 |
-
"learning_rate":
|
| 616 |
-
"logits/chosen":
|
| 617 |
-
"logits/rejected":
|
| 618 |
-
"logps/chosen": -
|
| 619 |
-
"logps/rejected": -
|
| 620 |
-
"loss": 0.
|
| 621 |
-
"rewards/accuracies": 0.
|
| 622 |
-
"rewards/chosen": -
|
| 623 |
-
"rewards/margins": 0.
|
| 624 |
-
"rewards/rejected": -1.
|
| 625 |
"step": 440
|
| 626 |
},
|
| 627 |
{
|
| 628 |
-
"epoch":
|
| 629 |
-
"learning_rate":
|
| 630 |
-
"logits/chosen":
|
| 631 |
-
"logits/rejected":
|
| 632 |
-
"logps/chosen": -
|
| 633 |
-
"logps/rejected": -
|
| 634 |
-
"loss": 0.
|
| 635 |
-
"rewards/accuracies": 0.
|
| 636 |
-
"rewards/chosen": -
|
| 637 |
-
"rewards/margins": 0.
|
| 638 |
-
"rewards/rejected": -1.
|
| 639 |
"step": 450
|
| 640 |
},
|
| 641 |
{
|
| 642 |
-
"epoch":
|
| 643 |
-
"learning_rate":
|
| 644 |
-
"logits/chosen":
|
| 645 |
-
"logits/rejected":
|
| 646 |
-
"logps/chosen": -
|
| 647 |
-
"logps/rejected": -
|
| 648 |
-
"loss": 0.
|
| 649 |
-
"rewards/accuracies": 0.
|
| 650 |
-
"rewards/chosen": -
|
| 651 |
-
"rewards/margins": 0.
|
| 652 |
-
"rewards/rejected": -1.
|
| 653 |
"step": 460
|
| 654 |
},
|
| 655 |
{
|
| 656 |
-
"epoch":
|
| 657 |
-
"learning_rate":
|
| 658 |
-
"logits/chosen":
|
| 659 |
-
"logits/rejected":
|
| 660 |
-
"logps/chosen": -
|
| 661 |
-
"logps/rejected": -
|
| 662 |
-
"loss": 0.
|
| 663 |
-
"rewards/accuracies": 0.
|
| 664 |
-
"rewards/chosen": -1.
|
| 665 |
-
"rewards/margins": 0.
|
| 666 |
-
"rewards/rejected": -
|
| 667 |
"step": 470
|
| 668 |
},
|
| 669 |
{
|
| 670 |
-
"epoch": 1.
|
| 671 |
-
"learning_rate":
|
| 672 |
-
"logits/chosen":
|
| 673 |
-
"logits/rejected": 0.
|
| 674 |
-
"logps/chosen": -
|
| 675 |
-
"logps/rejected": -
|
| 676 |
-
"loss": 0.
|
| 677 |
-
"rewards/accuracies": 0.
|
| 678 |
-
"rewards/chosen": -
|
| 679 |
-
"rewards/margins":
|
| 680 |
-
"rewards/rejected": -
|
| 681 |
"step": 480
|
| 682 |
},
|
| 683 |
{
|
| 684 |
-
"epoch": 1.
|
| 685 |
-
"learning_rate":
|
| 686 |
-
"logits/chosen": -0.
|
| 687 |
-
"logits/rejected": 0.
|
| 688 |
-
"logps/chosen": -
|
| 689 |
-
"logps/rejected": -
|
| 690 |
-
"loss": 0.
|
| 691 |
-
"rewards/accuracies": 0.
|
| 692 |
-
"rewards/chosen": -1.
|
| 693 |
-
"rewards/margins":
|
| 694 |
-
"rewards/rejected": -2.
|
| 695 |
"step": 490
|
| 696 |
},
|
| 697 |
{
|
| 698 |
-
"epoch": 1.
|
| 699 |
-
"learning_rate":
|
| 700 |
-
"logits/chosen": 0.
|
| 701 |
-
"logits/rejected": 0.
|
| 702 |
-
"logps/chosen": -
|
| 703 |
-
"logps/rejected": -
|
| 704 |
-
"loss": 0.
|
| 705 |
-
"rewards/accuracies": 0.
|
| 706 |
-
"rewards/chosen": -1.
|
| 707 |
-
"rewards/margins":
|
| 708 |
-
"rewards/rejected": -
|
| 709 |
"step": 500
|
| 710 |
},
|
| 711 |
{
|
| 712 |
-
"epoch": 1.
|
| 713 |
-
"learning_rate":
|
| 714 |
-
"logits/chosen": 0.
|
| 715 |
-
"logits/rejected": 0.
|
| 716 |
-
"logps/chosen": -
|
| 717 |
-
"logps/rejected": -
|
| 718 |
-
"loss": 0.
|
| 719 |
-
"rewards/accuracies": 0.
|
| 720 |
-
"rewards/chosen": -1.
|
| 721 |
-
"rewards/margins":
|
| 722 |
-
"rewards/rejected": -
|
| 723 |
"step": 510
|
| 724 |
},
|
| 725 |
{
|
| 726 |
-
"epoch": 1.
|
| 727 |
-
"learning_rate":
|
| 728 |
-
"logits/chosen": 0.
|
| 729 |
-
"logits/rejected": 0.
|
| 730 |
-
"logps/chosen": -
|
| 731 |
-
"logps/rejected": -
|
| 732 |
-
"loss": 0.
|
| 733 |
-
"rewards/accuracies": 0.
|
| 734 |
-
"rewards/chosen": -
|
| 735 |
-
"rewards/margins":
|
| 736 |
-
"rewards/rejected": -
|
| 737 |
"step": 520
|
| 738 |
},
|
| 739 |
{
|
| 740 |
-
"epoch": 1.
|
| 741 |
-
"learning_rate":
|
| 742 |
-
"logits/chosen": 0.
|
| 743 |
-
"logits/rejected": 0.
|
| 744 |
-
"logps/chosen": -
|
| 745 |
-
"logps/rejected": -
|
| 746 |
-
"loss": 0.
|
| 747 |
-
"rewards/accuracies": 0.
|
| 748 |
-
"rewards/chosen": -1.
|
| 749 |
-
"rewards/margins":
|
| 750 |
-
"rewards/rejected": -2.
|
| 751 |
"step": 530
|
| 752 |
},
|
| 753 |
{
|
| 754 |
-
"epoch": 1.
|
| 755 |
-
"learning_rate":
|
| 756 |
-
"logits/chosen": 0.
|
| 757 |
-
"logits/rejected": 0.
|
| 758 |
-
"logps/chosen": -
|
| 759 |
-
"logps/rejected": -
|
| 760 |
-
"loss": 0.
|
| 761 |
-
"rewards/accuracies": 0.
|
| 762 |
-
"rewards/chosen": -1.
|
| 763 |
-
"rewards/margins":
|
| 764 |
-
"rewards/rejected": -2.
|
| 765 |
"step": 540
|
| 766 |
},
|
| 767 |
{
|
| 768 |
-
"epoch": 1.
|
| 769 |
-
"learning_rate":
|
| 770 |
-
"logits/chosen": 0.
|
| 771 |
-
"logits/rejected": 0.
|
| 772 |
-
"logps/chosen": -
|
| 773 |
-
"logps/rejected": -
|
| 774 |
-
"loss": 0.
|
| 775 |
-
"rewards/accuracies": 0.
|
| 776 |
-
"rewards/chosen": -1.
|
| 777 |
-
"rewards/margins":
|
| 778 |
-
"rewards/rejected": -
|
| 779 |
"step": 550
|
| 780 |
},
|
| 781 |
{
|
| 782 |
-
"epoch": 1.
|
| 783 |
-
"learning_rate":
|
| 784 |
-
"logits/chosen": 0.
|
| 785 |
-
"logits/rejected": 0.
|
| 786 |
-
"logps/chosen": -
|
| 787 |
-
"logps/rejected": -
|
| 788 |
-
"loss": 0.
|
| 789 |
-
"rewards/accuracies": 0.
|
| 790 |
-
"rewards/chosen": -1.
|
| 791 |
-
"rewards/margins":
|
| 792 |
-
"rewards/rejected": -2.
|
| 793 |
"step": 560
|
| 794 |
},
|
| 795 |
{
|
| 796 |
-
"epoch": 1.
|
| 797 |
-
"learning_rate":
|
| 798 |
-
"logits/chosen": 0.
|
| 799 |
-
"logits/rejected": 0.
|
| 800 |
-
"logps/chosen": -
|
| 801 |
-
"logps/rejected": -
|
| 802 |
-
"loss": 0.
|
| 803 |
-
"rewards/accuracies": 0.
|
| 804 |
-
"rewards/chosen": -1.
|
| 805 |
-
"rewards/margins": 1.
|
| 806 |
-
"rewards/rejected": -
|
| 807 |
"step": 570
|
| 808 |
},
|
| 809 |
{
|
| 810 |
-
"epoch": 1.
|
| 811 |
-
"learning_rate":
|
| 812 |
-
"logits/chosen": 0.
|
| 813 |
-
"logits/rejected": 0.
|
| 814 |
-
"logps/chosen": -
|
| 815 |
-
"logps/rejected": -
|
| 816 |
-
"loss": 0.
|
| 817 |
-
"rewards/accuracies": 0.
|
| 818 |
-
"rewards/chosen": -1.
|
| 819 |
-
"rewards/margins":
|
| 820 |
-
"rewards/rejected": -
|
| 821 |
"step": 580
|
| 822 |
},
|
| 823 |
{
|
| 824 |
-
"epoch": 1.
|
| 825 |
-
"learning_rate":
|
| 826 |
-
"logits/chosen": 0.
|
| 827 |
-
"logits/rejected": 0.
|
| 828 |
-
"logps/chosen": -
|
| 829 |
-
"logps/rejected": -
|
| 830 |
-
"loss": 0.
|
| 831 |
-
"rewards/accuracies": 0.
|
| 832 |
-
"rewards/chosen": -1.
|
| 833 |
-
"rewards/margins":
|
| 834 |
-
"rewards/rejected": -
|
| 835 |
"step": 590
|
| 836 |
},
|
| 837 |
{
|
| 838 |
-
"epoch": 1.
|
| 839 |
-
"learning_rate":
|
| 840 |
-
"logits/chosen": 0.
|
| 841 |
-
"logits/rejected": 0.
|
| 842 |
-
"logps/chosen": -
|
| 843 |
-
"logps/rejected": -
|
| 844 |
-
"loss": 0.
|
| 845 |
-
"rewards/accuracies": 0.
|
| 846 |
-
"rewards/chosen": -1.
|
| 847 |
-
"rewards/margins": 1.
|
| 848 |
-
"rewards/rejected": -
|
| 849 |
"step": 600
|
| 850 |
},
|
| 851 |
{
|
| 852 |
-
"epoch": 1.
|
| 853 |
-
"learning_rate":
|
| 854 |
-
"logits/chosen": 0.
|
| 855 |
-
"logits/rejected": 0.
|
| 856 |
-
"logps/chosen": -
|
| 857 |
-
"logps/rejected": -
|
| 858 |
-
"loss": 0.
|
| 859 |
-
"rewards/accuracies": 0.
|
| 860 |
-
"rewards/chosen": -1.
|
| 861 |
-
"rewards/margins": 1.
|
| 862 |
-
"rewards/rejected": -
|
| 863 |
"step": 610
|
| 864 |
},
|
| 865 |
{
|
| 866 |
-
"epoch": 1.
|
| 867 |
-
"learning_rate":
|
| 868 |
-
"logits/chosen": 0.
|
| 869 |
-
"logits/rejected": 0.
|
| 870 |
-
"logps/chosen": -
|
| 871 |
-
"logps/rejected": -
|
| 872 |
-
"loss": 0.
|
| 873 |
-
"rewards/accuracies": 0.
|
| 874 |
-
"rewards/chosen": -1.
|
| 875 |
-
"rewards/margins":
|
| 876 |
-
"rewards/rejected": -
|
| 877 |
"step": 620
|
| 878 |
},
|
| 879 |
{
|
| 880 |
-
"epoch": 1.
|
| 881 |
-
"learning_rate": 3.
|
| 882 |
-
"logits/chosen": 0.
|
| 883 |
-
"logits/rejected": 0.
|
| 884 |
-
"logps/chosen": -
|
| 885 |
-
"logps/rejected": -
|
| 886 |
-
"loss": 0.
|
| 887 |
-
"rewards/accuracies": 0.
|
| 888 |
-
"rewards/chosen": -1.
|
| 889 |
-
"rewards/margins":
|
| 890 |
-
"rewards/rejected": -
|
| 891 |
"step": 630
|
| 892 |
},
|
| 893 |
{
|
| 894 |
-
"epoch": 1.
|
| 895 |
-
"learning_rate": 2.
|
| 896 |
-
"logits/chosen": 0.
|
| 897 |
-
"logits/rejected": 0.
|
| 898 |
-
"logps/chosen": -
|
| 899 |
-
"logps/rejected": -
|
| 900 |
-
"loss": 0.
|
| 901 |
-
"rewards/accuracies": 0.
|
| 902 |
-
"rewards/chosen": -1.
|
| 903 |
-
"rewards/margins": 1.
|
| 904 |
-
"rewards/rejected": -
|
| 905 |
"step": 640
|
| 906 |
},
|
| 907 |
{
|
| 908 |
-
"epoch": 1.
|
| 909 |
-
"learning_rate": 2.
|
| 910 |
-
"logits/chosen": 0.
|
| 911 |
-
"logits/rejected": 0.
|
| 912 |
-
"logps/chosen": -
|
| 913 |
-
"logps/rejected": -
|
| 914 |
-
"loss": 0.
|
| 915 |
-
"rewards/accuracies": 0.
|
| 916 |
-
"rewards/chosen": -1.
|
| 917 |
-
"rewards/margins":
|
| 918 |
-
"rewards/rejected": -
|
| 919 |
"step": 650
|
| 920 |
},
|
| 921 |
{
|
| 922 |
-
"epoch": 1.
|
| 923 |
-
"learning_rate":
|
| 924 |
-
"logits/chosen": 0.
|
| 925 |
-
"logits/rejected": 0.
|
| 926 |
-
"logps/chosen": -
|
| 927 |
-
"logps/rejected": -
|
| 928 |
-
"loss": 0.
|
| 929 |
-
"rewards/accuracies": 0.
|
| 930 |
-
"rewards/chosen": -1.
|
| 931 |
-
"rewards/margins": 1.
|
| 932 |
-
"rewards/rejected": -
|
| 933 |
"step": 660
|
| 934 |
},
|
| 935 |
{
|
| 936 |
-
"epoch": 1.
|
| 937 |
-
"learning_rate":
|
| 938 |
-
"logits/chosen": 0.
|
| 939 |
-
"logits/rejected": 0.
|
| 940 |
-
"logps/chosen": -
|
| 941 |
-
"logps/rejected": -
|
| 942 |
-
"loss": 0.
|
| 943 |
-
"rewards/accuracies": 0.
|
| 944 |
-
"rewards/chosen": -1.
|
| 945 |
-
"rewards/margins":
|
| 946 |
-
"rewards/rejected": -
|
| 947 |
"step": 670
|
| 948 |
},
|
| 949 |
{
|
| 950 |
-
"epoch": 1.
|
| 951 |
-
"learning_rate":
|
| 952 |
-
"logits/chosen": 0.
|
| 953 |
-
"logits/rejected": 0.
|
| 954 |
-
"logps/chosen": -
|
| 955 |
-
"logps/rejected": -
|
| 956 |
-
"loss": 0.
|
| 957 |
-
"rewards/accuracies": 0.
|
| 958 |
-
"rewards/chosen": -
|
| 959 |
-
"rewards/margins": 1.
|
| 960 |
-
"rewards/rejected": -
|
| 961 |
"step": 680
|
| 962 |
},
|
| 963 |
{
|
| 964 |
-
"epoch": 1.
|
| 965 |
-
"learning_rate": 2.
|
| 966 |
-
"logits/chosen": 0.
|
| 967 |
-
"logits/rejected": 0.
|
| 968 |
-
"logps/chosen": -
|
| 969 |
-
"logps/rejected": -
|
| 970 |
-
"loss": 0.
|
| 971 |
-
"rewards/accuracies": 0.
|
| 972 |
-
"rewards/chosen": -
|
| 973 |
-
"rewards/margins": 1.
|
| 974 |
-
"rewards/rejected": -
|
| 975 |
"step": 690
|
| 976 |
},
|
| 977 |
{
|
| 978 |
-
"epoch": 1.
|
| 979 |
-
"learning_rate":
|
| 980 |
-
"logits/chosen": 0.
|
| 981 |
-
"logits/rejected": 0.
|
| 982 |
-
"logps/chosen": -
|
| 983 |
-
"logps/rejected": -
|
| 984 |
-
"loss": 0.
|
| 985 |
-
"rewards/accuracies": 0.
|
| 986 |
-
"rewards/chosen": -
|
| 987 |
-
"rewards/margins":
|
| 988 |
-
"rewards/rejected": -
|
| 989 |
"step": 700
|
| 990 |
},
|
| 991 |
{
|
| 992 |
-
"epoch":
|
| 993 |
-
"learning_rate":
|
| 994 |
-
"logits/chosen": 0.
|
| 995 |
-
"logits/rejected": 0.
|
| 996 |
-
"logps/chosen": -
|
| 997 |
-
"logps/rejected": -
|
| 998 |
-
"loss": 0.
|
| 999 |
-
"rewards/accuracies": 0.
|
| 1000 |
-
"rewards/chosen": -1.
|
| 1001 |
-
"rewards/margins":
|
| 1002 |
-
"rewards/rejected": -
|
| 1003 |
"step": 710
|
| 1004 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1005 |
{
|
| 1006 |
"epoch": 2.0,
|
| 1007 |
-
"step":
|
| 1008 |
"total_flos": 0.0,
|
| 1009 |
-
"train_loss": 0.
|
| 1010 |
-
"train_runtime":
|
| 1011 |
-
"train_samples_per_second":
|
| 1012 |
-
"train_steps_per_second": 0.
|
| 1013 |
}
|
| 1014 |
],
|
| 1015 |
"logging_steps": 10,
|
| 1016 |
-
"max_steps":
|
| 1017 |
"num_train_epochs": 2,
|
| 1018 |
"save_steps": 10000,
|
| 1019 |
"total_flos": 0.0,
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9973828840617638,
|
| 5 |
"eval_steps": 10000,
|
| 6 |
+
"global_step": 954,
|
| 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 |
+
"learning_rate": 1.0416666666666667e-07,
|
| 14 |
+
"logits/chosen": 0.17704486846923828,
|
| 15 |
+
"logits/rejected": 0.25409135222435,
|
| 16 |
+
"logps/chosen": -354.4068603515625,
|
| 17 |
+
"logps/rejected": -305.2366638183594,
|
| 18 |
+
"loss": 0.1821,
|
| 19 |
+
"rewards/accuracies": 0.4312500059604645,
|
| 20 |
+
"rewards/chosen": -6.60312725813128e-05,
|
| 21 |
+
"rewards/margins": 0.00012125837383791804,
|
| 22 |
+
"rewards/rejected": -0.00018728969735093415,
|
| 23 |
"step": 10
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.04,
|
| 27 |
+
"learning_rate": 2.0833333333333333e-07,
|
| 28 |
+
"logits/chosen": 0.07091161608695984,
|
| 29 |
+
"logits/rejected": 0.1985362321138382,
|
| 30 |
+
"logps/chosen": -316.65069580078125,
|
| 31 |
+
"logps/rejected": -276.1200866699219,
|
| 32 |
+
"loss": 0.182,
|
| 33 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 34 |
+
"rewards/chosen": 0.0008458361262455583,
|
| 35 |
+
"rewards/margins": 0.0016920112539082766,
|
| 36 |
+
"rewards/rejected": -0.0008461751276627183,
|
| 37 |
"step": 20
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.06,
|
| 41 |
+
"learning_rate": 3.1249999999999997e-07,
|
| 42 |
+
"logits/chosen": 0.17787829041481018,
|
| 43 |
+
"logits/rejected": 0.2488478720188141,
|
| 44 |
+
"logps/chosen": -294.9706115722656,
|
| 45 |
+
"logps/rejected": -298.59521484375,
|
| 46 |
+
"loss": 0.1822,
|
| 47 |
+
"rewards/accuracies": 0.625,
|
| 48 |
+
"rewards/chosen": -3.700423985719681e-05,
|
| 49 |
+
"rewards/margins": 0.0029355171136558056,
|
| 50 |
+
"rewards/rejected": -0.0029725211206823587,
|
| 51 |
"step": 30
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.08,
|
| 55 |
+
"learning_rate": 4.1666666666666667e-07,
|
| 56 |
+
"logits/chosen": 0.09609868377447128,
|
| 57 |
+
"logits/rejected": 0.21795693039894104,
|
| 58 |
+
"logps/chosen": -347.44097900390625,
|
| 59 |
+
"logps/rejected": -320.9972839355469,
|
| 60 |
+
"loss": 0.1877,
|
| 61 |
+
"rewards/accuracies": 0.643750011920929,
|
| 62 |
+
"rewards/chosen": 0.0013125470140948892,
|
| 63 |
+
"rewards/margins": 0.00661453977227211,
|
| 64 |
+
"rewards/rejected": -0.005301993805915117,
|
| 65 |
"step": 40
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 0.1,
|
| 69 |
+
"learning_rate": 5.208333333333334e-07,
|
| 70 |
+
"logits/chosen": 0.1497882902622223,
|
| 71 |
+
"logits/rejected": 0.240590900182724,
|
| 72 |
+
"logps/chosen": -311.1229553222656,
|
| 73 |
+
"logps/rejected": -286.51702880859375,
|
| 74 |
+
"loss": 0.1814,
|
| 75 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 76 |
+
"rewards/chosen": -0.005703258328139782,
|
| 77 |
+
"rewards/margins": 0.022644545882940292,
|
| 78 |
+
"rewards/rejected": -0.02834780514240265,
|
| 79 |
"step": 50
|
| 80 |
},
|
| 81 |
{
|
| 82 |
+
"epoch": 0.13,
|
| 83 |
+
"learning_rate": 6.249999999999999e-07,
|
| 84 |
+
"logits/chosen": 0.13869214057922363,
|
| 85 |
+
"logits/rejected": 0.28307411074638367,
|
| 86 |
+
"logps/chosen": -295.9754638671875,
|
| 87 |
+
"logps/rejected": -281.43798828125,
|
| 88 |
+
"loss": 0.1766,
|
| 89 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 90 |
+
"rewards/chosen": -0.03096725046634674,
|
| 91 |
+
"rewards/margins": 0.028959080576896667,
|
| 92 |
+
"rewards/rejected": -0.059926338493824005,
|
| 93 |
"step": 60
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.15,
|
| 97 |
+
"learning_rate": 7.291666666666666e-07,
|
| 98 |
+
"logits/chosen": 0.18460798263549805,
|
| 99 |
+
"logits/rejected": 0.2718513607978821,
|
| 100 |
+
"logps/chosen": -335.46148681640625,
|
| 101 |
+
"logps/rejected": -330.33404541015625,
|
| 102 |
+
"loss": 0.174,
|
| 103 |
+
"rewards/accuracies": 0.59375,
|
| 104 |
+
"rewards/chosen": -0.057377688586711884,
|
| 105 |
+
"rewards/margins": 0.05648452043533325,
|
| 106 |
+
"rewards/rejected": -0.11386220157146454,
|
| 107 |
"step": 70
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 0.17,
|
| 111 |
+
"learning_rate": 8.333333333333333e-07,
|
| 112 |
+
"logits/chosen": 0.29816848039627075,
|
| 113 |
+
"logits/rejected": 0.4011983871459961,
|
| 114 |
+
"logps/chosen": -330.4580383300781,
|
| 115 |
+
"logps/rejected": -311.96490478515625,
|
| 116 |
+
"loss": 0.159,
|
| 117 |
+
"rewards/accuracies": 0.731249988079071,
|
| 118 |
+
"rewards/chosen": -0.11794394254684448,
|
| 119 |
+
"rewards/margins": 0.13102997839450836,
|
| 120 |
+
"rewards/rejected": -0.24897389113903046,
|
| 121 |
"step": 80
|
| 122 |
},
|
| 123 |
{
|
| 124 |
+
"epoch": 0.19,
|
| 125 |
+
"learning_rate": 9.374999999999999e-07,
|
| 126 |
+
"logits/chosen": 0.2283201515674591,
|
| 127 |
+
"logits/rejected": 0.37335914373397827,
|
| 128 |
+
"logps/chosen": -358.6737365722656,
|
| 129 |
+
"logps/rejected": -304.0804138183594,
|
| 130 |
+
"loss": 0.1421,
|
| 131 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 132 |
+
"rewards/chosen": -0.21732211112976074,
|
| 133 |
+
"rewards/margins": 0.15273679792881012,
|
| 134 |
+
"rewards/rejected": -0.37005892395973206,
|
| 135 |
"step": 90
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 0.21,
|
| 139 |
+
"learning_rate": 9.999463737538052e-07,
|
| 140 |
+
"logits/chosen": 0.2938156723976135,
|
| 141 |
+
"logits/rejected": 0.46553492546081543,
|
| 142 |
+
"logps/chosen": -361.78338623046875,
|
| 143 |
+
"logps/rejected": -343.25750732421875,
|
| 144 |
+
"loss": 0.1217,
|
| 145 |
+
"rewards/accuracies": 0.668749988079071,
|
| 146 |
+
"rewards/chosen": -0.27221935987472534,
|
| 147 |
+
"rewards/margins": 0.23653486371040344,
|
| 148 |
+
"rewards/rejected": -0.5087541937828064,
|
| 149 |
"step": 100
|
| 150 |
},
|
| 151 |
{
|
| 152 |
+
"epoch": 0.23,
|
| 153 |
+
"learning_rate": 9.993432105822034e-07,
|
| 154 |
+
"logits/chosen": 0.31155580282211304,
|
| 155 |
+
"logits/rejected": 0.3508353531360626,
|
| 156 |
+
"logps/chosen": -353.184814453125,
|
| 157 |
+
"logps/rejected": -366.32720947265625,
|
| 158 |
+
"loss": 0.106,
|
| 159 |
+
"rewards/accuracies": 0.6312500238418579,
|
| 160 |
+
"rewards/chosen": -0.40565404295921326,
|
| 161 |
+
"rewards/margins": 0.2631165683269501,
|
| 162 |
+
"rewards/rejected": -0.6687706708908081,
|
| 163 |
"step": 110
|
| 164 |
},
|
| 165 |
{
|
| 166 |
+
"epoch": 0.25,
|
| 167 |
+
"learning_rate": 9.980706626858607e-07,
|
| 168 |
+
"logits/chosen": 0.26659709215164185,
|
| 169 |
+
"logits/rejected": 0.3288796842098236,
|
| 170 |
+
"logps/chosen": -374.50274658203125,
|
| 171 |
+
"logps/rejected": -403.8424377441406,
|
| 172 |
+
"loss": 0.0951,
|
| 173 |
+
"rewards/accuracies": 0.625,
|
| 174 |
+
"rewards/chosen": -0.5394914150238037,
|
| 175 |
+
"rewards/margins": 0.28696924448013306,
|
| 176 |
+
"rewards/rejected": -0.8264607191085815,
|
| 177 |
"step": 120
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 0.27,
|
| 181 |
+
"learning_rate": 9.961304359538434e-07,
|
| 182 |
+
"logits/chosen": 0.1616436094045639,
|
| 183 |
+
"logits/rejected": 0.2970871031284332,
|
| 184 |
+
"logps/chosen": -396.555419921875,
|
| 185 |
+
"logps/rejected": -362.3848876953125,
|
| 186 |
+
"loss": 0.0934,
|
| 187 |
+
"rewards/accuracies": 0.625,
|
| 188 |
+
"rewards/chosen": -0.5805934071540833,
|
| 189 |
+
"rewards/margins": 0.19475166499614716,
|
| 190 |
+
"rewards/rejected": -0.775344967842102,
|
| 191 |
"step": 130
|
| 192 |
},
|
| 193 |
{
|
| 194 |
+
"epoch": 0.29,
|
| 195 |
+
"learning_rate": 9.935251313189563e-07,
|
| 196 |
+
"logits/chosen": 0.1485656201839447,
|
| 197 |
+
"logits/rejected": 0.2714545428752899,
|
| 198 |
+
"logps/chosen": -384.0659484863281,
|
| 199 |
+
"logps/rejected": -346.6048278808594,
|
| 200 |
+
"loss": 0.0933,
|
| 201 |
+
"rewards/accuracies": 0.59375,
|
| 202 |
+
"rewards/chosen": -0.5202253460884094,
|
| 203 |
+
"rewards/margins": 0.24675369262695312,
|
| 204 |
+
"rewards/rejected": -0.766978919506073,
|
| 205 |
"step": 140
|
| 206 |
},
|
| 207 |
{
|
| 208 |
+
"epoch": 0.31,
|
| 209 |
+
"learning_rate": 9.902582412711118e-07,
|
| 210 |
+
"logits/chosen": 0.12988325953483582,
|
| 211 |
+
"logits/rejected": 0.1523539423942566,
|
| 212 |
+
"logps/chosen": -379.16839599609375,
|
| 213 |
+
"logps/rejected": -395.9466552734375,
|
| 214 |
+
"loss": 0.1019,
|
| 215 |
+
"rewards/accuracies": 0.6875,
|
| 216 |
+
"rewards/chosen": -0.4386775493621826,
|
| 217 |
+
"rewards/margins": 0.37129276990890503,
|
| 218 |
+
"rewards/rejected": -0.8099702596664429,
|
| 219 |
"step": 150
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 0.33,
|
| 223 |
+
"learning_rate": 9.86334145175542e-07,
|
| 224 |
+
"logits/chosen": 0.06655962765216827,
|
| 225 |
+
"logits/rejected": 0.09024105966091156,
|
| 226 |
+
"logps/chosen": -341.7105407714844,
|
| 227 |
+
"logps/rejected": -360.19805908203125,
|
| 228 |
+
"loss": 0.0937,
|
| 229 |
+
"rewards/accuracies": 0.699999988079071,
|
| 230 |
+
"rewards/chosen": -0.3964901566505432,
|
| 231 |
+
"rewards/margins": 0.3985019028186798,
|
| 232 |
+
"rewards/rejected": -0.7949920892715454,
|
| 233 |
"step": 160
|
| 234 |
},
|
| 235 |
{
|
| 236 |
+
"epoch": 0.36,
|
| 237 |
+
"learning_rate": 9.817581034021272e-07,
|
| 238 |
+
"logits/chosen": 0.16973164677619934,
|
| 239 |
+
"logits/rejected": 0.21836213767528534,
|
| 240 |
+
"logps/chosen": -398.22369384765625,
|
| 241 |
+
"logps/rejected": -417.8206481933594,
|
| 242 |
+
"loss": 0.081,
|
| 243 |
+
"rewards/accuracies": 0.675000011920929,
|
| 244 |
+
"rewards/chosen": -0.6185532808303833,
|
| 245 |
+
"rewards/margins": 0.4811604917049408,
|
| 246 |
+
"rewards/rejected": -1.0997138023376465,
|
| 247 |
"step": 170
|
| 248 |
},
|
| 249 |
{
|
| 250 |
+
"epoch": 0.38,
|
| 251 |
+
"learning_rate": 9.765362502737097e-07,
|
| 252 |
+
"logits/chosen": 0.09212584793567657,
|
| 253 |
+
"logits/rejected": 0.23974208533763885,
|
| 254 |
+
"logps/chosen": -388.64910888671875,
|
| 255 |
+
"logps/rejected": -411.5782775878906,
|
| 256 |
+
"loss": 0.0713,
|
| 257 |
+
"rewards/accuracies": 0.706250011920929,
|
| 258 |
+
"rewards/chosen": -0.6261709928512573,
|
| 259 |
+
"rewards/margins": 0.4908596873283386,
|
| 260 |
+
"rewards/rejected": -1.1170307397842407,
|
| 261 |
"step": 180
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 0.4,
|
| 265 |
+
"learning_rate": 9.706755858428485e-07,
|
| 266 |
+
"logits/chosen": 0.1811675727367401,
|
| 267 |
+
"logits/rejected": 0.27236208319664,
|
| 268 |
+
"logps/chosen": -419.11376953125,
|
| 269 |
+
"logps/rejected": -437.33843994140625,
|
| 270 |
+
"loss": 0.0681,
|
| 271 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 272 |
+
"rewards/chosen": -0.8445426225662231,
|
| 273 |
+
"rewards/margins": 0.4015916883945465,
|
| 274 |
+
"rewards/rejected": -1.2461342811584473,
|
| 275 |
"step": 190
|
| 276 |
},
|
| 277 |
{
|
| 278 |
+
"epoch": 0.42,
|
| 279 |
+
"learning_rate": 9.641839665080363e-07,
|
| 280 |
+
"logits/chosen": 0.14256766438484192,
|
| 281 |
+
"logits/rejected": 0.2711044251918793,
|
| 282 |
+
"logps/chosen": -414.55975341796875,
|
| 283 |
+
"logps/rejected": -416.9037170410156,
|
| 284 |
+
"loss": 0.0675,
|
| 285 |
+
"rewards/accuracies": 0.6875,
|
| 286 |
+
"rewards/chosen": -0.7406997680664062,
|
| 287 |
+
"rewards/margins": 0.48706990480422974,
|
| 288 |
+
"rewards/rejected": -1.2277696132659912,
|
| 289 |
"step": 200
|
| 290 |
},
|
| 291 |
{
|
| 292 |
+
"epoch": 0.44,
|
| 293 |
+
"learning_rate": 9.570700944819582e-07,
|
| 294 |
+
"logits/chosen": 0.23208096623420715,
|
| 295 |
+
"logits/rejected": 0.35697174072265625,
|
| 296 |
+
"logps/chosen": -382.19970703125,
|
| 297 |
+
"logps/rejected": -386.50701904296875,
|
| 298 |
+
"loss": 0.0708,
|
| 299 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 300 |
+
"rewards/chosen": -0.6804240942001343,
|
| 301 |
+
"rewards/margins": 0.48590850830078125,
|
| 302 |
+
"rewards/rejected": -1.166332721710205,
|
| 303 |
"step": 210
|
| 304 |
},
|
| 305 |
{
|
| 306 |
+
"epoch": 0.46,
|
| 307 |
+
"learning_rate": 9.493435061259129e-07,
|
| 308 |
+
"logits/chosen": 0.13639363646507263,
|
| 309 |
+
"logits/rejected": 0.23731064796447754,
|
| 310 |
+
"logps/chosen": -382.42022705078125,
|
| 311 |
+
"logps/rejected": -369.6554870605469,
|
| 312 |
+
"loss": 0.0763,
|
| 313 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 314 |
+
"rewards/chosen": -0.6574115753173828,
|
| 315 |
+
"rewards/margins": 0.40243881940841675,
|
| 316 |
+
"rewards/rejected": -1.0598504543304443,
|
| 317 |
"step": 220
|
| 318 |
},
|
| 319 |
{
|
| 320 |
+
"epoch": 0.48,
|
| 321 |
+
"learning_rate": 9.4101455916603e-07,
|
| 322 |
+
"logits/chosen": 0.1799091249704361,
|
| 323 |
+
"logits/rejected": 0.2304597645998001,
|
| 324 |
+
"logps/chosen": -416.672607421875,
|
| 325 |
+
"logps/rejected": -420.39862060546875,
|
| 326 |
+
"loss": 0.0668,
|
| 327 |
+
"rewards/accuracies": 0.643750011920929,
|
| 328 |
+
"rewards/chosen": -0.9061130285263062,
|
| 329 |
+
"rewards/margins": 0.46666598320007324,
|
| 330 |
+
"rewards/rejected": -1.3727790117263794,
|
| 331 |
"step": 230
|
| 332 |
},
|
| 333 |
{
|
| 334 |
+
"epoch": 0.5,
|
| 335 |
+
"learning_rate": 9.320944188084241e-07,
|
| 336 |
+
"logits/chosen": 0.08318189531564713,
|
| 337 |
+
"logits/rejected": 0.13486048579216003,
|
| 338 |
+
"logps/chosen": -408.77545166015625,
|
| 339 |
+
"logps/rejected": -427.9566345214844,
|
| 340 |
+
"loss": 0.0639,
|
| 341 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 342 |
+
"rewards/chosen": -0.968237042427063,
|
| 343 |
+
"rewards/margins": 0.2922549843788147,
|
| 344 |
+
"rewards/rejected": -1.260491967201233,
|
| 345 |
"step": 240
|
| 346 |
},
|
| 347 |
{
|
| 348 |
+
"epoch": 0.52,
|
| 349 |
+
"learning_rate": 9.225950427718974e-07,
|
| 350 |
+
"logits/chosen": 0.051157813519239426,
|
| 351 |
+
"logits/rejected": 0.1319509893655777,
|
| 352 |
+
"logps/chosen": -385.2474670410156,
|
| 353 |
+
"logps/rejected": -402.11126708984375,
|
| 354 |
+
"loss": 0.0631,
|
| 355 |
+
"rewards/accuracies": 0.668749988079071,
|
| 356 |
+
"rewards/chosen": -0.7319932579994202,
|
| 357 |
+
"rewards/margins": 0.468679815530777,
|
| 358 |
+
"rewards/rejected": -1.2006731033325195,
|
| 359 |
"step": 250
|
| 360 |
},
|
| 361 |
{
|
| 362 |
+
"epoch": 0.54,
|
| 363 |
+
"learning_rate": 9.125291652582547e-07,
|
| 364 |
+
"logits/chosen": 0.013853952288627625,
|
| 365 |
+
"logits/rejected": 0.10071275383234024,
|
| 366 |
+
"logps/chosen": -445.53607177734375,
|
| 367 |
+
"logps/rejected": -434.2711486816406,
|
| 368 |
+
"loss": 0.0641,
|
| 369 |
+
"rewards/accuracies": 0.612500011920929,
|
| 370 |
+
"rewards/chosen": -0.9089228510856628,
|
| 371 |
+
"rewards/margins": 0.4331666827201843,
|
| 372 |
+
"rewards/rejected": -1.3420894145965576,
|
| 373 |
"step": 260
|
| 374 |
},
|
| 375 |
{
|
| 376 |
+
"epoch": 0.57,
|
| 377 |
+
"learning_rate": 9.019102798817195e-07,
|
| 378 |
+
"logits/chosen": 0.1297096163034439,
|
| 379 |
+
"logits/rejected": 0.1613592505455017,
|
| 380 |
+
"logps/chosen": -403.47393798828125,
|
| 381 |
+
"logps/rejected": -446.1951599121094,
|
| 382 |
+
"loss": 0.0685,
|
| 383 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 384 |
+
"rewards/chosen": -0.7434005737304688,
|
| 385 |
+
"rewards/margins": 0.6140644550323486,
|
| 386 |
+
"rewards/rejected": -1.357465147972107,
|
| 387 |
"step": 270
|
| 388 |
},
|
| 389 |
{
|
| 390 |
+
"epoch": 0.59,
|
| 391 |
+
"learning_rate": 8.90752621580335e-07,
|
| 392 |
+
"logits/chosen": 0.16231071949005127,
|
| 393 |
+
"logits/rejected": 0.1873283088207245,
|
| 394 |
+
"logps/chosen": -362.4006652832031,
|
| 395 |
+
"logps/rejected": -398.279296875,
|
| 396 |
+
"loss": 0.0751,
|
| 397 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 398 |
+
"rewards/chosen": -0.6591774225234985,
|
| 399 |
+
"rewards/margins": 0.41294485330581665,
|
| 400 |
+
"rewards/rejected": -1.07212233543396,
|
| 401 |
"step": 280
|
| 402 |
},
|
| 403 |
{
|
| 404 |
+
"epoch": 0.61,
|
| 405 |
+
"learning_rate": 8.79071147533597e-07,
|
| 406 |
+
"logits/chosen": 0.14204099774360657,
|
| 407 |
+
"logits/rejected": 0.20997166633605957,
|
| 408 |
+
"logps/chosen": -424.5856018066406,
|
| 409 |
+
"logps/rejected": -456.9698181152344,
|
| 410 |
+
"loss": 0.0642,
|
| 411 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 412 |
+
"rewards/chosen": -0.7815448045730591,
|
| 413 |
+
"rewards/margins": 0.5602203011512756,
|
| 414 |
+
"rewards/rejected": -1.34176504611969,
|
| 415 |
"step": 290
|
| 416 |
},
|
| 417 |
{
|
| 418 |
+
"epoch": 0.63,
|
| 419 |
+
"learning_rate": 8.668815171119019e-07,
|
| 420 |
+
"logits/chosen": 0.2026984989643097,
|
| 421 |
+
"logits/rejected": 0.23374077677726746,
|
| 422 |
+
"logps/chosen": -380.8060607910156,
|
| 423 |
+
"logps/rejected": -468.7802734375,
|
| 424 |
+
"loss": 0.0554,
|
| 425 |
+
"rewards/accuracies": 0.699999988079071,
|
| 426 |
+
"rewards/chosen": -0.8905105590820312,
|
| 427 |
+
"rewards/margins": 0.5638677477836609,
|
| 428 |
+
"rewards/rejected": -1.454378366470337,
|
| 429 |
"step": 300
|
| 430 |
},
|
| 431 |
{
|
| 432 |
+
"epoch": 0.65,
|
| 433 |
+
"learning_rate": 8.54200070884685e-07,
|
| 434 |
+
"logits/chosen": 0.23336808383464813,
|
| 435 |
+
"logits/rejected": 0.25176650285720825,
|
| 436 |
+
"logps/chosen": -385.24676513671875,
|
| 437 |
+
"logps/rejected": -462.87322998046875,
|
| 438 |
+
"loss": 0.0565,
|
| 439 |
+
"rewards/accuracies": 0.706250011920929,
|
| 440 |
+
"rewards/chosen": -0.8951492309570312,
|
| 441 |
+
"rewards/margins": 0.6165014505386353,
|
| 442 |
+
"rewards/rejected": -1.5116506814956665,
|
| 443 |
"step": 310
|
| 444 |
},
|
| 445 |
{
|
| 446 |
+
"epoch": 0.67,
|
| 447 |
+
"learning_rate": 8.410438087153911e-07,
|
| 448 |
+
"logits/chosen": 0.22913236916065216,
|
| 449 |
+
"logits/rejected": 0.3360585570335388,
|
| 450 |
+
"logps/chosen": -383.767578125,
|
| 451 |
+
"logps/rejected": -424.25067138671875,
|
| 452 |
+
"loss": 0.0641,
|
| 453 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 454 |
+
"rewards/chosen": -0.6813658475875854,
|
| 455 |
+
"rewards/margins": 0.6591276526451111,
|
| 456 |
+
"rewards/rejected": -1.3404934406280518,
|
| 457 |
"step": 320
|
| 458 |
},
|
| 459 |
{
|
| 460 |
+
"epoch": 0.69,
|
| 461 |
+
"learning_rate": 8.274303669726426e-07,
|
| 462 |
+
"logits/chosen": 0.22990348935127258,
|
| 463 |
+
"logits/rejected": 0.3006184697151184,
|
| 464 |
+
"logps/chosen": -366.43499755859375,
|
| 465 |
+
"logps/rejected": -444.06536865234375,
|
| 466 |
+
"loss": 0.0636,
|
| 467 |
+
"rewards/accuracies": 0.675000011920929,
|
| 468 |
+
"rewards/chosen": -0.6766657829284668,
|
| 469 |
+
"rewards/margins": 0.6564770936965942,
|
| 470 |
+
"rewards/rejected": -1.333142876625061,
|
| 471 |
"step": 330
|
| 472 |
},
|
| 473 |
{
|
| 474 |
+
"epoch": 0.71,
|
| 475 |
+
"learning_rate": 8.133779948881513e-07,
|
| 476 |
+
"logits/chosen": 0.22257550060749054,
|
| 477 |
+
"logits/rejected": 0.3241097033023834,
|
| 478 |
+
"logps/chosen": -360.141845703125,
|
| 479 |
+
"logps/rejected": -405.85711669921875,
|
| 480 |
+
"loss": 0.0662,
|
| 481 |
+
"rewards/accuracies": 0.78125,
|
| 482 |
+
"rewards/chosen": -0.7344536781311035,
|
| 483 |
+
"rewards/margins": 0.7157880067825317,
|
| 484 |
+
"rewards/rejected": -1.4502416849136353,
|
| 485 |
"step": 340
|
| 486 |
},
|
| 487 |
{
|
| 488 |
+
"epoch": 0.73,
|
| 489 |
+
"learning_rate": 7.989055300930704e-07,
|
| 490 |
+
"logits/chosen": 0.1499968320131302,
|
| 491 |
+
"logits/rejected": 0.15372925996780396,
|
| 492 |
+
"logps/chosen": -388.67559814453125,
|
| 493 |
+
"logps/rejected": -462.0445251464844,
|
| 494 |
+
"loss": 0.0644,
|
| 495 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 496 |
+
"rewards/chosen": -0.8717344403266907,
|
| 497 |
+
"rewards/margins": 0.6429644227027893,
|
| 498 |
+
"rewards/rejected": -1.51469886302948,
|
| 499 |
"step": 350
|
| 500 |
},
|
| 501 |
{
|
| 502 |
+
"epoch": 0.75,
|
| 503 |
+
"learning_rate": 7.840323733655778e-07,
|
| 504 |
+
"logits/chosen": 0.08885981142520905,
|
| 505 |
+
"logits/rejected": 0.19541098177433014,
|
| 506 |
+
"logps/chosen": -407.87286376953125,
|
| 507 |
+
"logps/rejected": -420.4515686035156,
|
| 508 |
+
"loss": 0.0583,
|
| 509 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 510 |
+
"rewards/chosen": -0.797155499458313,
|
| 511 |
+
"rewards/margins": 0.5855330228805542,
|
| 512 |
+
"rewards/rejected": -1.3826884031295776,
|
| 513 |
"step": 360
|
| 514 |
},
|
| 515 |
{
|
| 516 |
+
"epoch": 0.77,
|
| 517 |
+
"learning_rate": 7.687784626235447e-07,
|
| 518 |
+
"logits/chosen": 0.05912008136510849,
|
| 519 |
+
"logits/rejected": 0.17702099680900574,
|
| 520 |
+
"logps/chosen": -428.82354736328125,
|
| 521 |
+
"logps/rejected": -466.0895080566406,
|
| 522 |
+
"loss": 0.0599,
|
| 523 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 524 |
+
"rewards/chosen": -0.803920567035675,
|
| 525 |
+
"rewards/margins": 0.7507921457290649,
|
| 526 |
+
"rewards/rejected": -1.5547125339508057,
|
| 527 |
"step": 370
|
| 528 |
},
|
| 529 |
{
|
| 530 |
+
"epoch": 0.8,
|
| 531 |
+
"learning_rate": 7.531642461971514e-07,
|
| 532 |
+
"logits/chosen": 0.11388075351715088,
|
| 533 |
+
"logits/rejected": 0.1931450068950653,
|
| 534 |
+
"logps/chosen": -388.9282531738281,
|
| 535 |
+
"logps/rejected": -427.1614685058594,
|
| 536 |
+
"loss": 0.0578,
|
| 537 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 538 |
+
"rewards/chosen": -0.9585503339767456,
|
| 539 |
+
"rewards/margins": 0.5912213325500488,
|
| 540 |
+
"rewards/rejected": -1.5497716665267944,
|
| 541 |
"step": 380
|
| 542 |
},
|
| 543 |
{
|
| 544 |
+
"epoch": 0.82,
|
| 545 |
+
"learning_rate": 7.372106554172801e-07,
|
| 546 |
+
"logits/chosen": -0.049389470368623734,
|
| 547 |
+
"logits/rejected": 0.10218650102615356,
|
| 548 |
+
"logps/chosen": -443.7737731933594,
|
| 549 |
+
"logps/rejected": -484.5735778808594,
|
| 550 |
+
"loss": 0.0446,
|
| 551 |
+
"rewards/accuracies": 0.731249988079071,
|
| 552 |
+
"rewards/chosen": -1.0208237171173096,
|
| 553 |
+
"rewards/margins": 0.8150562047958374,
|
| 554 |
+
"rewards/rejected": -1.835879921913147,
|
| 555 |
"step": 390
|
| 556 |
},
|
| 557 |
{
|
| 558 |
+
"epoch": 0.84,
|
| 559 |
+
"learning_rate": 7.209390765564318e-07,
|
| 560 |
+
"logits/chosen": 0.07526848465204239,
|
| 561 |
+
"logits/rejected": 0.1457681804895401,
|
| 562 |
+
"logps/chosen": -430.77130126953125,
|
| 563 |
+
"logps/rejected": -478.53118896484375,
|
| 564 |
+
"loss": 0.0488,
|
| 565 |
+
"rewards/accuracies": 0.706250011920929,
|
| 566 |
+
"rewards/chosen": -1.137662410736084,
|
| 567 |
+
"rewards/margins": 0.6997725963592529,
|
| 568 |
+
"rewards/rejected": -1.837435007095337,
|
| 569 |
"step": 400
|
| 570 |
},
|
| 571 |
{
|
| 572 |
+
"epoch": 0.86,
|
| 573 |
+
"learning_rate": 7.043713221597773e-07,
|
| 574 |
+
"logits/chosen": -0.014962440356612206,
|
| 575 |
+
"logits/rejected": 0.049673158675432205,
|
| 576 |
+
"logps/chosen": -394.35980224609375,
|
| 577 |
+
"logps/rejected": -455.79168701171875,
|
| 578 |
+
"loss": 0.0469,
|
| 579 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 580 |
+
"rewards/chosen": -1.0516221523284912,
|
| 581 |
+
"rewards/margins": 0.6002627015113831,
|
| 582 |
+
"rewards/rejected": -1.65188467502594,
|
| 583 |
"step": 410
|
| 584 |
},
|
| 585 |
{
|
| 586 |
+
"epoch": 0.88,
|
| 587 |
+
"learning_rate": 6.875296018047809e-07,
|
| 588 |
+
"logits/chosen": 0.1113734096288681,
|
| 589 |
+
"logits/rejected": 0.17297616600990295,
|
| 590 |
+
"logps/chosen": -371.1769104003906,
|
| 591 |
+
"logps/rejected": -433.82763671875,
|
| 592 |
+
"loss": 0.057,
|
| 593 |
+
"rewards/accuracies": 0.731249988079071,
|
| 594 |
+
"rewards/chosen": -0.7784308791160583,
|
| 595 |
+
"rewards/margins": 0.7032991647720337,
|
| 596 |
+
"rewards/rejected": -1.4817302227020264,
|
| 597 |
"step": 420
|
| 598 |
},
|
| 599 |
{
|
| 600 |
+
"epoch": 0.9,
|
| 601 |
+
"learning_rate": 6.704364923285857e-07,
|
| 602 |
+
"logits/chosen": 0.08021976053714752,
|
| 603 |
+
"logits/rejected": 0.09611347317695618,
|
| 604 |
+
"logps/chosen": -433.26898193359375,
|
| 605 |
+
"logps/rejected": -482.2544860839844,
|
| 606 |
+
"loss": 0.0623,
|
| 607 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 608 |
+
"rewards/chosen": -0.9919212460517883,
|
| 609 |
+
"rewards/margins": 0.5928072333335876,
|
| 610 |
+
"rewards/rejected": -1.584728479385376,
|
| 611 |
"step": 430
|
| 612 |
},
|
| 613 |
{
|
| 614 |
+
"epoch": 0.92,
|
| 615 |
+
"learning_rate": 6.531149075630796e-07,
|
| 616 |
+
"logits/chosen": 0.06492827087640762,
|
| 617 |
+
"logits/rejected": 0.09372309595346451,
|
| 618 |
+
"logps/chosen": -369.0657958984375,
|
| 619 |
+
"logps/rejected": -427.1637268066406,
|
| 620 |
+
"loss": 0.0602,
|
| 621 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 622 |
+
"rewards/chosen": -0.8450859785079956,
|
| 623 |
+
"rewards/margins": 0.6487796902656555,
|
| 624 |
+
"rewards/rejected": -1.4938656091690063,
|
| 625 |
"step": 440
|
| 626 |
},
|
| 627 |
{
|
| 628 |
+
"epoch": 0.94,
|
| 629 |
+
"learning_rate": 6.355880676182085e-07,
|
| 630 |
+
"logits/chosen": 0.015085640363395214,
|
| 631 |
+
"logits/rejected": 0.1697283238172531,
|
| 632 |
+
"logps/chosen": -454.42071533203125,
|
| 633 |
+
"logps/rejected": -461.6656799316406,
|
| 634 |
+
"loss": 0.0537,
|
| 635 |
+
"rewards/accuracies": 0.699999988079071,
|
| 636 |
+
"rewards/chosen": -1.0446925163269043,
|
| 637 |
+
"rewards/margins": 0.7324589490890503,
|
| 638 |
+
"rewards/rejected": -1.7771514654159546,
|
| 639 |
"step": 450
|
| 640 |
},
|
| 641 |
{
|
| 642 |
+
"epoch": 0.96,
|
| 643 |
+
"learning_rate": 6.178794677547137e-07,
|
| 644 |
+
"logits/chosen": 0.052903078496456146,
|
| 645 |
+
"logits/rejected": 0.21909013390541077,
|
| 646 |
+
"logps/chosen": -389.771728515625,
|
| 647 |
+
"logps/rejected": -432.63311767578125,
|
| 648 |
+
"loss": 0.0475,
|
| 649 |
+
"rewards/accuracies": 0.71875,
|
| 650 |
+
"rewards/chosen": -0.918341338634491,
|
| 651 |
+
"rewards/margins": 0.7504295706748962,
|
| 652 |
+
"rewards/rejected": -1.6687707901000977,
|
| 653 |
"step": 460
|
| 654 |
},
|
| 655 |
{
|
| 656 |
+
"epoch": 0.98,
|
| 657 |
+
"learning_rate": 6.000128468880222e-07,
|
| 658 |
+
"logits/chosen": 0.0020152360666543245,
|
| 659 |
+
"logits/rejected": 0.10528425872325897,
|
| 660 |
+
"logps/chosen": -439.73016357421875,
|
| 661 |
+
"logps/rejected": -486.3055114746094,
|
| 662 |
+
"loss": 0.0531,
|
| 663 |
+
"rewards/accuracies": 0.75,
|
| 664 |
+
"rewards/chosen": -1.0058103799819946,
|
| 665 |
+
"rewards/margins": 0.8824182748794556,
|
| 666 |
+
"rewards/rejected": -1.8882286548614502,
|
| 667 |
"step": 470
|
| 668 |
},
|
| 669 |
{
|
| 670 |
+
"epoch": 1.0,
|
| 671 |
+
"learning_rate": 5.820121557655108e-07,
|
| 672 |
+
"logits/chosen": 0.03267590329051018,
|
| 673 |
+
"logits/rejected": 0.10403893887996674,
|
| 674 |
+
"logps/chosen": -426.3312072753906,
|
| 675 |
+
"logps/rejected": -521.575439453125,
|
| 676 |
+
"loss": 0.0497,
|
| 677 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 678 |
+
"rewards/chosen": -0.897496223449707,
|
| 679 |
+
"rewards/margins": 1.0473217964172363,
|
| 680 |
+
"rewards/rejected": -1.9448179006576538,
|
| 681 |
"step": 480
|
| 682 |
},
|
| 683 |
{
|
| 684 |
+
"epoch": 1.03,
|
| 685 |
+
"learning_rate": 5.639015248598023e-07,
|
| 686 |
+
"logits/chosen": -0.05066138505935669,
|
| 687 |
+
"logits/rejected": 0.0016520231729373336,
|
| 688 |
+
"logps/chosen": -459.2066955566406,
|
| 689 |
+
"logps/rejected": -572.3805541992188,
|
| 690 |
+
"loss": 0.0254,
|
| 691 |
+
"rewards/accuracies": 0.768750011920929,
|
| 692 |
+
"rewards/chosen": -1.404326319694519,
|
| 693 |
+
"rewards/margins": 1.2682745456695557,
|
| 694 |
+
"rewards/rejected": -2.6726012229919434,
|
| 695 |
"step": 490
|
| 696 |
},
|
| 697 |
{
|
| 698 |
+
"epoch": 1.05,
|
| 699 |
+
"learning_rate": 5.457052320211339e-07,
|
| 700 |
+
"logits/chosen": 0.10663177818059921,
|
| 701 |
+
"logits/rejected": 0.143524631857872,
|
| 702 |
+
"logps/chosen": -454.5547790527344,
|
| 703 |
+
"logps/rejected": -574.3235473632812,
|
| 704 |
+
"loss": 0.0198,
|
| 705 |
+
"rewards/accuracies": 0.71875,
|
| 706 |
+
"rewards/chosen": -1.592284083366394,
|
| 707 |
+
"rewards/margins": 1.2184875011444092,
|
| 708 |
+
"rewards/rejected": -2.8107717037200928,
|
| 709 |
"step": 500
|
| 710 |
},
|
| 711 |
{
|
| 712 |
+
"epoch": 1.07,
|
| 713 |
+
"learning_rate": 5.274476699321637e-07,
|
| 714 |
+
"logits/chosen": -0.019788045436143875,
|
| 715 |
+
"logits/rejected": 0.12656378746032715,
|
| 716 |
+
"logps/chosen": -488.24627685546875,
|
| 717 |
+
"logps/rejected": -596.00537109375,
|
| 718 |
+
"loss": 0.015,
|
| 719 |
+
"rewards/accuracies": 0.800000011920929,
|
| 720 |
+
"rewards/chosen": -1.8213142156600952,
|
| 721 |
+
"rewards/margins": 1.3653538227081299,
|
| 722 |
+
"rewards/rejected": -3.1866683959960938,
|
| 723 |
"step": 510
|
| 724 |
},
|
| 725 |
{
|
| 726 |
+
"epoch": 1.09,
|
| 727 |
+
"learning_rate": 5.091533134088387e-07,
|
| 728 |
+
"logits/chosen": -0.0814504474401474,
|
| 729 |
+
"logits/rejected": 0.05524957925081253,
|
| 730 |
+
"logps/chosen": -552.7730712890625,
|
| 731 |
+
"logps/rejected": -634.5548095703125,
|
| 732 |
+
"loss": 0.0147,
|
| 733 |
+
"rewards/accuracies": 0.731249988079071,
|
| 734 |
+
"rewards/chosen": -2.0995850563049316,
|
| 735 |
+
"rewards/margins": 1.1655638217926025,
|
| 736 |
+
"rewards/rejected": -3.2651493549346924,
|
| 737 |
"step": 520
|
| 738 |
},
|
| 739 |
{
|
| 740 |
+
"epoch": 1.11,
|
| 741 |
+
"learning_rate": 4.908466865911614e-07,
|
| 742 |
+
"logits/chosen": 0.03363295644521713,
|
| 743 |
+
"logits/rejected": 0.043015364557504654,
|
| 744 |
+
"logps/chosen": -468.89593505859375,
|
| 745 |
+
"logps/rejected": -560.2864990234375,
|
| 746 |
+
"loss": 0.0174,
|
| 747 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 748 |
+
"rewards/chosen": -1.5512639284133911,
|
| 749 |
+
"rewards/margins": 1.2513355016708374,
|
| 750 |
+
"rewards/rejected": -2.8025994300842285,
|
| 751 |
"step": 530
|
| 752 |
},
|
| 753 |
{
|
| 754 |
+
"epoch": 1.13,
|
| 755 |
+
"learning_rate": 4.7255233006783624e-07,
|
| 756 |
+
"logits/chosen": -0.03754299506545067,
|
| 757 |
+
"logits/rejected": 0.08725563436746597,
|
| 758 |
+
"logps/chosen": -456.68243408203125,
|
| 759 |
+
"logps/rejected": -549.9105224609375,
|
| 760 |
+
"loss": 0.0178,
|
| 761 |
+
"rewards/accuracies": 0.706250011920929,
|
| 762 |
+
"rewards/chosen": -1.657478928565979,
|
| 763 |
+
"rewards/margins": 1.0530353784561157,
|
| 764 |
+
"rewards/rejected": -2.7105140686035156,
|
| 765 |
"step": 540
|
| 766 |
},
|
| 767 |
{
|
| 768 |
+
"epoch": 1.15,
|
| 769 |
+
"learning_rate": 4.5429476797886617e-07,
|
| 770 |
+
"logits/chosen": 0.0340617299079895,
|
| 771 |
+
"logits/rejected": 0.1264275759458542,
|
| 772 |
+
"logps/chosen": -469.5687561035156,
|
| 773 |
+
"logps/rejected": -592.4705810546875,
|
| 774 |
+
"loss": 0.0185,
|
| 775 |
+
"rewards/accuracies": 0.800000011920929,
|
| 776 |
+
"rewards/chosen": -1.408406138420105,
|
| 777 |
+
"rewards/margins": 1.4667712450027466,
|
| 778 |
+
"rewards/rejected": -2.8751769065856934,
|
| 779 |
"step": 550
|
| 780 |
},
|
| 781 |
{
|
| 782 |
+
"epoch": 1.17,
|
| 783 |
+
"learning_rate": 4.3609847514019763e-07,
|
| 784 |
+
"logits/chosen": 0.0167356226593256,
|
| 785 |
+
"logits/rejected": 0.032135289162397385,
|
| 786 |
+
"logps/chosen": -480.41278076171875,
|
| 787 |
+
"logps/rejected": -577.2174072265625,
|
| 788 |
+
"loss": 0.0165,
|
| 789 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 790 |
+
"rewards/chosen": -1.5578255653381348,
|
| 791 |
+
"rewards/margins": 1.0947318077087402,
|
| 792 |
+
"rewards/rejected": -2.652557611465454,
|
| 793 |
"step": 560
|
| 794 |
},
|
| 795 |
{
|
| 796 |
+
"epoch": 1.19,
|
| 797 |
+
"learning_rate": 4.179878442344892e-07,
|
| 798 |
+
"logits/chosen": 0.10041844844818115,
|
| 799 |
+
"logits/rejected": 0.16732005774974823,
|
| 800 |
+
"logps/chosen": -453.9161071777344,
|
| 801 |
+
"logps/rejected": -615.6796875,
|
| 802 |
+
"loss": 0.0153,
|
| 803 |
+
"rewards/accuracies": 0.762499988079071,
|
| 804 |
+
"rewards/chosen": -1.7070415019989014,
|
| 805 |
+
"rewards/margins": 1.4755295515060425,
|
| 806 |
+
"rewards/rejected": -3.1825711727142334,
|
| 807 |
"step": 570
|
| 808 |
},
|
| 809 |
{
|
| 810 |
+
"epoch": 1.21,
|
| 811 |
+
"learning_rate": 3.9998715311197783e-07,
|
| 812 |
+
"logits/chosen": 0.1310591995716095,
|
| 813 |
+
"logits/rejected": 0.20585906505584717,
|
| 814 |
+
"logps/chosen": -493.8118591308594,
|
| 815 |
+
"logps/rejected": -631.4963989257812,
|
| 816 |
+
"loss": 0.015,
|
| 817 |
+
"rewards/accuracies": 0.731249988079071,
|
| 818 |
+
"rewards/chosen": -1.7850983142852783,
|
| 819 |
+
"rewards/margins": 1.443263292312622,
|
| 820 |
+
"rewards/rejected": -3.228361129760742,
|
| 821 |
"step": 580
|
| 822 |
},
|
| 823 |
{
|
| 824 |
+
"epoch": 1.24,
|
| 825 |
+
"learning_rate": 3.821205322452863e-07,
|
| 826 |
+
"logits/chosen": 0.22954685986042023,
|
| 827 |
+
"logits/rejected": 0.2483092099428177,
|
| 828 |
+
"logps/chosen": -473.4378967285156,
|
| 829 |
+
"logps/rejected": -605.134033203125,
|
| 830 |
+
"loss": 0.0149,
|
| 831 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 832 |
+
"rewards/chosen": -1.700280785560608,
|
| 833 |
+
"rewards/margins": 1.460669755935669,
|
| 834 |
+
"rewards/rejected": -3.1609506607055664,
|
| 835 |
"step": 590
|
| 836 |
},
|
| 837 |
{
|
| 838 |
+
"epoch": 1.26,
|
| 839 |
+
"learning_rate": 3.6441193238179146e-07,
|
| 840 |
+
"logits/chosen": 0.13607949018478394,
|
| 841 |
+
"logits/rejected": 0.1680508852005005,
|
| 842 |
+
"logps/chosen": -451.55340576171875,
|
| 843 |
+
"logps/rejected": -627.7686157226562,
|
| 844 |
+
"loss": 0.0147,
|
| 845 |
+
"rewards/accuracies": 0.75,
|
| 846 |
+
"rewards/chosen": -1.6148862838745117,
|
| 847 |
+
"rewards/margins": 1.678989052772522,
|
| 848 |
+
"rewards/rejected": -3.2938759326934814,
|
| 849 |
"step": 600
|
| 850 |
},
|
| 851 |
{
|
| 852 |
+
"epoch": 1.28,
|
| 853 |
+
"learning_rate": 3.4688509243692034e-07,
|
| 854 |
+
"logits/chosen": 0.04345204681158066,
|
| 855 |
+
"logits/rejected": 0.13040025532245636,
|
| 856 |
+
"logps/chosen": -461.54095458984375,
|
| 857 |
+
"logps/rejected": -684.9581909179688,
|
| 858 |
+
"loss": 0.0153,
|
| 859 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 860 |
+
"rewards/chosen": -1.6480602025985718,
|
| 861 |
+
"rewards/margins": 1.6946277618408203,
|
| 862 |
+
"rewards/rejected": -3.3426880836486816,
|
| 863 |
"step": 610
|
| 864 |
},
|
| 865 |
{
|
| 866 |
+
"epoch": 1.3,
|
| 867 |
+
"learning_rate": 3.295635076714144e-07,
|
| 868 |
+
"logits/chosen": 0.18233785033226013,
|
| 869 |
+
"logits/rejected": 0.19972297549247742,
|
| 870 |
+
"logps/chosen": -408.9209899902344,
|
| 871 |
+
"logps/rejected": -547.9658813476562,
|
| 872 |
+
"loss": 0.0143,
|
| 873 |
+
"rewards/accuracies": 0.75,
|
| 874 |
+
"rewards/chosen": -1.6356074810028076,
|
| 875 |
+
"rewards/margins": 1.3703811168670654,
|
| 876 |
+
"rewards/rejected": -3.005988597869873,
|
| 877 |
"step": 620
|
| 878 |
},
|
| 879 |
{
|
| 880 |
+
"epoch": 1.32,
|
| 881 |
+
"learning_rate": 3.12470398195219e-07,
|
| 882 |
+
"logits/chosen": 0.15017299354076385,
|
| 883 |
+
"logits/rejected": 0.07167269289493561,
|
| 884 |
+
"logps/chosen": -474.58172607421875,
|
| 885 |
+
"logps/rejected": -649.4796142578125,
|
| 886 |
+
"loss": 0.0129,
|
| 887 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 888 |
+
"rewards/chosen": -1.6831333637237549,
|
| 889 |
+
"rewards/margins": 1.4837870597839355,
|
| 890 |
+
"rewards/rejected": -3.1669201850891113,
|
| 891 |
"step": 630
|
| 892 |
},
|
| 893 |
{
|
| 894 |
+
"epoch": 1.34,
|
| 895 |
+
"learning_rate": 2.956286778402226e-07,
|
| 896 |
+
"logits/chosen": 0.03866753727197647,
|
| 897 |
+
"logits/rejected": 0.20129835605621338,
|
| 898 |
+
"logps/chosen": -546.3468017578125,
|
| 899 |
+
"logps/rejected": -608.462646484375,
|
| 900 |
+
"loss": 0.0126,
|
| 901 |
+
"rewards/accuracies": 0.75,
|
| 902 |
+
"rewards/chosen": -1.7091865539550781,
|
| 903 |
+
"rewards/margins": 1.3178246021270752,
|
| 904 |
+
"rewards/rejected": -3.0270111560821533,
|
| 905 |
"step": 640
|
| 906 |
},
|
| 907 |
{
|
| 908 |
+
"epoch": 1.36,
|
| 909 |
+
"learning_rate": 2.7906092344356826e-07,
|
| 910 |
+
"logits/chosen": 0.2127591073513031,
|
| 911 |
+
"logits/rejected": 0.24179625511169434,
|
| 912 |
+
"logps/chosen": -462.47412109375,
|
| 913 |
+
"logps/rejected": -581.084228515625,
|
| 914 |
+
"loss": 0.014,
|
| 915 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 916 |
+
"rewards/chosen": -1.751960039138794,
|
| 917 |
+
"rewards/margins": 1.4448457956314087,
|
| 918 |
+
"rewards/rejected": -3.196805953979492,
|
| 919 |
"step": 650
|
| 920 |
},
|
| 921 |
{
|
| 922 |
+
"epoch": 1.38,
|
| 923 |
+
"learning_rate": 2.6278934458271996e-07,
|
| 924 |
+
"logits/chosen": 0.09269841015338898,
|
| 925 |
+
"logits/rejected": 0.2964209318161011,
|
| 926 |
+
"logps/chosen": -479.434326171875,
|
| 927 |
+
"logps/rejected": -605.9524536132812,
|
| 928 |
+
"loss": 0.0123,
|
| 929 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 930 |
+
"rewards/chosen": -1.8022867441177368,
|
| 931 |
+
"rewards/margins": 1.3753817081451416,
|
| 932 |
+
"rewards/rejected": -3.177668333053589,
|
| 933 |
"step": 660
|
| 934 |
},
|
| 935 |
{
|
| 936 |
+
"epoch": 1.4,
|
| 937 |
+
"learning_rate": 2.468357538028487e-07,
|
| 938 |
+
"logits/chosen": 0.16141146421432495,
|
| 939 |
+
"logits/rejected": 0.18542757630348206,
|
| 940 |
+
"logps/chosen": -487.90277099609375,
|
| 941 |
+
"logps/rejected": -652.5034790039062,
|
| 942 |
+
"loss": 0.0107,
|
| 943 |
+
"rewards/accuracies": 0.75,
|
| 944 |
+
"rewards/chosen": -1.9332258701324463,
|
| 945 |
+
"rewards/margins": 1.736053705215454,
|
| 946 |
+
"rewards/rejected": -3.6692795753479004,
|
| 947 |
"step": 670
|
| 948 |
},
|
| 949 |
{
|
| 950 |
+
"epoch": 1.42,
|
| 951 |
+
"learning_rate": 2.312215373764551e-07,
|
| 952 |
+
"logits/chosen": 0.07799498736858368,
|
| 953 |
+
"logits/rejected": 0.17718131840229034,
|
| 954 |
+
"logps/chosen": -603.2567138671875,
|
| 955 |
+
"logps/rejected": -699.2156372070312,
|
| 956 |
+
"loss": 0.0101,
|
| 957 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 958 |
+
"rewards/chosen": -2.1482930183410645,
|
| 959 |
+
"rewards/margins": 1.3787685632705688,
|
| 960 |
+
"rewards/rejected": -3.5270614624023438,
|
| 961 |
"step": 680
|
| 962 |
},
|
| 963 |
{
|
| 964 |
+
"epoch": 1.44,
|
| 965 |
+
"learning_rate": 2.1596762663442213e-07,
|
| 966 |
+
"logits/chosen": 0.2014874666929245,
|
| 967 |
+
"logits/rejected": 0.3246391713619232,
|
| 968 |
+
"logps/chosen": -489.08349609375,
|
| 969 |
+
"logps/rejected": -607.5847778320312,
|
| 970 |
+
"loss": 0.0096,
|
| 971 |
+
"rewards/accuracies": 0.762499988079071,
|
| 972 |
+
"rewards/chosen": -2.083740711212158,
|
| 973 |
+
"rewards/margins": 1.446257472038269,
|
| 974 |
+
"rewards/rejected": -3.5299980640411377,
|
| 975 |
"step": 690
|
| 976 |
},
|
| 977 |
{
|
| 978 |
+
"epoch": 1.47,
|
| 979 |
+
"learning_rate": 2.0109446990692963e-07,
|
| 980 |
+
"logits/chosen": 0.09734896570444107,
|
| 981 |
+
"logits/rejected": 0.16283641755580902,
|
| 982 |
+
"logps/chosen": -540.1688232421875,
|
| 983 |
+
"logps/rejected": -701.462890625,
|
| 984 |
+
"loss": 0.0094,
|
| 985 |
+
"rewards/accuracies": 0.8125,
|
| 986 |
+
"rewards/chosen": -2.07643985748291,
|
| 987 |
+
"rewards/margins": 1.7090556621551514,
|
| 988 |
+
"rewards/rejected": -3.7854957580566406,
|
| 989 |
"step": 700
|
| 990 |
},
|
| 991 |
{
|
| 992 |
+
"epoch": 1.49,
|
| 993 |
+
"learning_rate": 1.8662200511184872e-07,
|
| 994 |
+
"logits/chosen": 0.07912759482860565,
|
| 995 |
+
"logits/rejected": 0.19963078200817108,
|
| 996 |
+
"logps/chosen": -491.30426025390625,
|
| 997 |
+
"logps/rejected": -630.0563354492188,
|
| 998 |
+
"loss": 0.0099,
|
| 999 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1000 |
+
"rewards/chosen": -1.9977525472640991,
|
| 1001 |
+
"rewards/margins": 1.5802443027496338,
|
| 1002 |
+
"rewards/rejected": -3.5779967308044434,
|
| 1003 |
"step": 710
|
| 1004 |
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 1.51,
|
| 1007 |
+
"learning_rate": 1.725696330273575e-07,
|
| 1008 |
+
"logits/chosen": 0.14783975481987,
|
| 1009 |
+
"logits/rejected": 0.27563345432281494,
|
| 1010 |
+
"logps/chosen": -530.8796997070312,
|
| 1011 |
+
"logps/rejected": -640.3440551757812,
|
| 1012 |
+
"loss": 0.0107,
|
| 1013 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1014 |
+
"rewards/chosen": -2.036653518676758,
|
| 1015 |
+
"rewards/margins": 1.323557734489441,
|
| 1016 |
+
"rewards/rejected": -3.3602116107940674,
|
| 1017 |
+
"step": 720
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.53,
|
| 1021 |
+
"learning_rate": 1.589561912846089e-07,
|
| 1022 |
+
"logits/chosen": 0.16717246174812317,
|
| 1023 |
+
"logits/rejected": 0.2920343279838562,
|
| 1024 |
+
"logps/chosen": -499.3802795410156,
|
| 1025 |
+
"logps/rejected": -612.64892578125,
|
| 1026 |
+
"loss": 0.012,
|
| 1027 |
+
"rewards/accuracies": 0.731249988079071,
|
| 1028 |
+
"rewards/chosen": -2.0618550777435303,
|
| 1029 |
+
"rewards/margins": 1.435462236404419,
|
| 1030 |
+
"rewards/rejected": -3.4973175525665283,
|
| 1031 |
+
"step": 730
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 1.55,
|
| 1035 |
+
"learning_rate": 1.4579992911531496e-07,
|
| 1036 |
+
"logits/chosen": 0.1249130517244339,
|
| 1037 |
+
"logits/rejected": 0.23616066575050354,
|
| 1038 |
+
"logps/chosen": -575.0750732421875,
|
| 1039 |
+
"logps/rejected": -649.9669189453125,
|
| 1040 |
+
"loss": 0.0106,
|
| 1041 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1042 |
+
"rewards/chosen": -2.2815146446228027,
|
| 1043 |
+
"rewards/margins": 1.226216197013855,
|
| 1044 |
+
"rewards/rejected": -3.5077309608459473,
|
| 1045 |
+
"step": 740
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 1.57,
|
| 1049 |
+
"learning_rate": 1.3311848288809813e-07,
|
| 1050 |
+
"logits/chosen": 0.21837782859802246,
|
| 1051 |
+
"logits/rejected": 0.31546956300735474,
|
| 1052 |
+
"logps/chosen": -510.7059020996094,
|
| 1053 |
+
"logps/rejected": -609.2933959960938,
|
| 1054 |
+
"loss": 0.0119,
|
| 1055 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1056 |
+
"rewards/chosen": -1.790372610092163,
|
| 1057 |
+
"rewards/margins": 1.2426694631576538,
|
| 1058 |
+
"rewards/rejected": -3.0330421924591064,
|
| 1059 |
+
"step": 750
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.59,
|
| 1063 |
+
"learning_rate": 1.209288524664029e-07,
|
| 1064 |
+
"logits/chosen": 0.14562873542308807,
|
| 1065 |
+
"logits/rejected": 0.3084864318370819,
|
| 1066 |
+
"logps/chosen": -622.6912841796875,
|
| 1067 |
+
"logps/rejected": -749.8731689453125,
|
| 1068 |
+
"loss": 0.0131,
|
| 1069 |
+
"rewards/accuracies": 0.71875,
|
| 1070 |
+
"rewards/chosen": -2.2252538204193115,
|
| 1071 |
+
"rewards/margins": 1.5818650722503662,
|
| 1072 |
+
"rewards/rejected": -3.8071188926696777,
|
| 1073 |
+
"step": 760
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 1.61,
|
| 1077 |
+
"learning_rate": 1.0924737841966497e-07,
|
| 1078 |
+
"logits/chosen": 0.1799144446849823,
|
| 1079 |
+
"logits/rejected": 0.354133278131485,
|
| 1080 |
+
"logps/chosen": -585.0472412109375,
|
| 1081 |
+
"logps/rejected": -712.3133544921875,
|
| 1082 |
+
"loss": 0.0107,
|
| 1083 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1084 |
+
"rewards/chosen": -2.1570990085601807,
|
| 1085 |
+
"rewards/margins": 1.6586040258407593,
|
| 1086 |
+
"rewards/rejected": -3.8157036304473877,
|
| 1087 |
+
"step": 770
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.63,
|
| 1091 |
+
"learning_rate": 9.808972011828054e-08,
|
| 1092 |
+
"logits/chosen": 0.20896565914154053,
|
| 1093 |
+
"logits/rejected": 0.1832619458436966,
|
| 1094 |
+
"logps/chosen": -474.9366149902344,
|
| 1095 |
+
"logps/rejected": -665.3892822265625,
|
| 1096 |
+
"loss": 0.0099,
|
| 1097 |
+
"rewards/accuracies": 0.8125,
|
| 1098 |
+
"rewards/chosen": -1.9308887720108032,
|
| 1099 |
+
"rewards/margins": 1.5281493663787842,
|
| 1100 |
+
"rewards/rejected": -3.459038257598877,
|
| 1101 |
+
"step": 780
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.65,
|
| 1105 |
+
"learning_rate": 8.747083474174527e-08,
|
| 1106 |
+
"logits/chosen": 0.25221484899520874,
|
| 1107 |
+
"logits/rejected": 0.3025228679180145,
|
| 1108 |
+
"logps/chosen": -486.76678466796875,
|
| 1109 |
+
"logps/rejected": -610.9810791015625,
|
| 1110 |
+
"loss": 0.01,
|
| 1111 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1112 |
+
"rewards/chosen": -1.9139289855957031,
|
| 1113 |
+
"rewards/margins": 1.4173685312271118,
|
| 1114 |
+
"rewards/rejected": -3.3312973976135254,
|
| 1115 |
+
"step": 790
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.67,
|
| 1119 |
+
"learning_rate": 7.740495722810269e-08,
|
| 1120 |
+
"logits/chosen": 0.12703558802604675,
|
| 1121 |
+
"logits/rejected": 0.25433093309402466,
|
| 1122 |
+
"logps/chosen": -528.8013916015625,
|
| 1123 |
+
"logps/rejected": -645.4374389648438,
|
| 1124 |
+
"loss": 0.01,
|
| 1125 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1126 |
+
"rewards/chosen": -2.129984140396118,
|
| 1127 |
+
"rewards/margins": 1.322923183441162,
|
| 1128 |
+
"rewards/rejected": -3.452907085418701,
|
| 1129 |
+
"step": 800
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.7,
|
| 1133 |
+
"learning_rate": 6.790558119157597e-08,
|
| 1134 |
+
"logits/chosen": 0.1941952407360077,
|
| 1135 |
+
"logits/rejected": 0.36538344621658325,
|
| 1136 |
+
"logps/chosen": -536.0458374023438,
|
| 1137 |
+
"logps/rejected": -630.6697387695312,
|
| 1138 |
+
"loss": 0.0111,
|
| 1139 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 1140 |
+
"rewards/chosen": -1.9618316888809204,
|
| 1141 |
+
"rewards/margins": 1.3840124607086182,
|
| 1142 |
+
"rewards/rejected": -3.34584379196167,
|
| 1143 |
+
"step": 810
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.72,
|
| 1147 |
+
"learning_rate": 5.898544083397e-08,
|
| 1148 |
+
"logits/chosen": 0.1936766654253006,
|
| 1149 |
+
"logits/rejected": 0.22626741230487823,
|
| 1150 |
+
"logps/chosen": -482.18902587890625,
|
| 1151 |
+
"logps/rejected": -640.9258422851562,
|
| 1152 |
+
"loss": 0.0113,
|
| 1153 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1154 |
+
"rewards/chosen": -1.822951078414917,
|
| 1155 |
+
"rewards/margins": 1.679091215133667,
|
| 1156 |
+
"rewards/rejected": -3.502042055130005,
|
| 1157 |
+
"step": 820
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.74,
|
| 1161 |
+
"learning_rate": 5.065649387408705e-08,
|
| 1162 |
+
"logits/chosen": 0.16037659347057343,
|
| 1163 |
+
"logits/rejected": 0.23867423832416534,
|
| 1164 |
+
"logps/chosen": -536.796630859375,
|
| 1165 |
+
"logps/rejected": -645.6795654296875,
|
| 1166 |
+
"loss": 0.0119,
|
| 1167 |
+
"rewards/accuracies": 0.7562500238418579,
|
| 1168 |
+
"rewards/chosen": -2.09273624420166,
|
| 1169 |
+
"rewards/margins": 1.3475998640060425,
|
| 1170 |
+
"rewards/rejected": -3.440336227416992,
|
| 1171 |
+
"step": 830
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.76,
|
| 1175 |
+
"learning_rate": 4.292990551804171e-08,
|
| 1176 |
+
"logits/chosen": 0.11955185234546661,
|
| 1177 |
+
"logits/rejected": 0.2987907826900482,
|
| 1178 |
+
"logps/chosen": -521.8675537109375,
|
| 1179 |
+
"logps/rejected": -622.3560791015625,
|
| 1180 |
+
"loss": 0.0115,
|
| 1181 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1182 |
+
"rewards/chosen": -1.9727070331573486,
|
| 1183 |
+
"rewards/margins": 1.207002878189087,
|
| 1184 |
+
"rewards/rejected": -3.1797099113464355,
|
| 1185 |
+
"step": 840
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.78,
|
| 1189 |
+
"learning_rate": 3.581603349196371e-08,
|
| 1190 |
+
"logits/chosen": 0.12183141708374023,
|
| 1191 |
+
"logits/rejected": 0.24950018525123596,
|
| 1192 |
+
"logps/chosen": -529.2427978515625,
|
| 1193 |
+
"logps/rejected": -662.9299926757812,
|
| 1194 |
+
"loss": 0.0112,
|
| 1195 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 1196 |
+
"rewards/chosen": -2.024509906768799,
|
| 1197 |
+
"rewards/margins": 1.5907318592071533,
|
| 1198 |
+
"rewards/rejected": -3.615241289138794,
|
| 1199 |
+
"step": 850
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.8,
|
| 1203 |
+
"learning_rate": 2.9324414157151367e-08,
|
| 1204 |
+
"logits/chosen": 0.11247365176677704,
|
| 1205 |
+
"logits/rejected": 0.28803473711013794,
|
| 1206 |
+
"logps/chosen": -538.6015625,
|
| 1207 |
+
"logps/rejected": -616.6097412109375,
|
| 1208 |
+
"loss": 0.0105,
|
| 1209 |
+
"rewards/accuracies": 0.7437499761581421,
|
| 1210 |
+
"rewards/chosen": -2.005286693572998,
|
| 1211 |
+
"rewards/margins": 1.320533037185669,
|
| 1212 |
+
"rewards/rejected": -3.325819492340088,
|
| 1213 |
+
"step": 860
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.82,
|
| 1217 |
+
"learning_rate": 2.3463749726290284e-08,
|
| 1218 |
+
"logits/chosen": 0.09726160764694214,
|
| 1219 |
+
"logits/rejected": 0.3085189759731293,
|
| 1220 |
+
"logps/chosen": -527.7420043945312,
|
| 1221 |
+
"logps/rejected": -666.7064208984375,
|
| 1222 |
+
"loss": 0.0114,
|
| 1223 |
+
"rewards/accuracies": 0.78125,
|
| 1224 |
+
"rewards/chosen": -1.963595986366272,
|
| 1225 |
+
"rewards/margins": 1.6061077117919922,
|
| 1226 |
+
"rewards/rejected": -3.5697035789489746,
|
| 1227 |
+
"step": 870
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.84,
|
| 1231 |
+
"learning_rate": 1.824189659787284e-08,
|
| 1232 |
+
"logits/chosen": 0.19652321934700012,
|
| 1233 |
+
"logits/rejected": 0.2885872423648834,
|
| 1234 |
+
"logps/chosen": -515.560546875,
|
| 1235 |
+
"logps/rejected": -641.10791015625,
|
| 1236 |
+
"loss": 0.0111,
|
| 1237 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1238 |
+
"rewards/chosen": -1.9605176448822021,
|
| 1239 |
+
"rewards/margins": 1.3721264600753784,
|
| 1240 |
+
"rewards/rejected": -3.33264422416687,
|
| 1241 |
+
"step": 880
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.86,
|
| 1245 |
+
"learning_rate": 1.3665854824458035e-08,
|
| 1246 |
+
"logits/chosen": 0.16733339428901672,
|
| 1247 |
+
"logits/rejected": 0.3634529113769531,
|
| 1248 |
+
"logps/chosen": -542.18505859375,
|
| 1249 |
+
"logps/rejected": -629.7310791015625,
|
| 1250 |
+
"loss": 0.0115,
|
| 1251 |
+
"rewards/accuracies": 0.768750011920929,
|
| 1252 |
+
"rewards/chosen": -2.0391831398010254,
|
| 1253 |
+
"rewards/margins": 1.1835925579071045,
|
| 1254 |
+
"rewards/rejected": -3.2227752208709717,
|
| 1255 |
+
"step": 890
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.88,
|
| 1259 |
+
"learning_rate": 9.741758728888217e-09,
|
| 1260 |
+
"logits/chosen": 0.08950433880090714,
|
| 1261 |
+
"logits/rejected": 0.2665843069553375,
|
| 1262 |
+
"logps/chosen": -533.1641845703125,
|
| 1263 |
+
"logps/rejected": -621.0523681640625,
|
| 1264 |
+
"loss": 0.0113,
|
| 1265 |
+
"rewards/accuracies": 0.675000011920929,
|
| 1266 |
+
"rewards/chosen": -1.9605424404144287,
|
| 1267 |
+
"rewards/margins": 1.1125773191452026,
|
| 1268 |
+
"rewards/rejected": -3.073119640350342,
|
| 1269 |
+
"step": 900
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.91,
|
| 1273 |
+
"learning_rate": 6.474868681043577e-09,
|
| 1274 |
+
"logits/chosen": 0.13345034420490265,
|
| 1275 |
+
"logits/rejected": 0.2458508014678955,
|
| 1276 |
+
"logps/chosen": -523.0572509765625,
|
| 1277 |
+
"logps/rejected": -666.5548706054688,
|
| 1278 |
+
"loss": 0.0107,
|
| 1279 |
+
"rewards/accuracies": 0.75,
|
| 1280 |
+
"rewards/chosen": -2.094968557357788,
|
| 1281 |
+
"rewards/margins": 1.4136923551559448,
|
| 1282 |
+
"rewards/rejected": -3.5086607933044434,
|
| 1283 |
+
"step": 910
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.93,
|
| 1287 |
+
"learning_rate": 3.869564046156459e-09,
|
| 1288 |
+
"logits/chosen": 0.17636564373970032,
|
| 1289 |
+
"logits/rejected": 0.24904970824718475,
|
| 1290 |
+
"logps/chosen": -521.7586669921875,
|
| 1291 |
+
"logps/rejected": -661.547119140625,
|
| 1292 |
+
"loss": 0.0115,
|
| 1293 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 1294 |
+
"rewards/chosen": -2.0953400135040283,
|
| 1295 |
+
"rewards/margins": 1.3953152894973755,
|
| 1296 |
+
"rewards/rejected": -3.4906551837921143,
|
| 1297 |
+
"step": 920
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.95,
|
| 1301 |
+
"learning_rate": 1.929337314139412e-09,
|
| 1302 |
+
"logits/chosen": 0.1708141714334488,
|
| 1303 |
+
"logits/rejected": 0.2874212861061096,
|
| 1304 |
+
"logps/chosen": -481.3929138183594,
|
| 1305 |
+
"logps/rejected": -591.492431640625,
|
| 1306 |
+
"loss": 0.0107,
|
| 1307 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1308 |
+
"rewards/chosen": -1.8482071161270142,
|
| 1309 |
+
"rewards/margins": 1.3176212310791016,
|
| 1310 |
+
"rewards/rejected": -3.165828227996826,
|
| 1311 |
+
"step": 930
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.97,
|
| 1315 |
+
"learning_rate": 6.567894177967325e-10,
|
| 1316 |
+
"logits/chosen": 0.1810809224843979,
|
| 1317 |
+
"logits/rejected": 0.3499010503292084,
|
| 1318 |
+
"logps/chosen": -509.21966552734375,
|
| 1319 |
+
"logps/rejected": -619.0591430664062,
|
| 1320 |
+
"loss": 0.0119,
|
| 1321 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1322 |
+
"rewards/chosen": -1.7878868579864502,
|
| 1323 |
+
"rewards/margins": 1.3797376155853271,
|
| 1324 |
+
"rewards/rejected": -3.1676242351531982,
|
| 1325 |
+
"step": 940
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.99,
|
| 1329 |
+
"learning_rate": 5.3626246194704575e-11,
|
| 1330 |
+
"logits/chosen": 0.12432925403118134,
|
| 1331 |
+
"logits/rejected": 0.1847553700208664,
|
| 1332 |
+
"logps/chosen": -471.4737854003906,
|
| 1333 |
+
"logps/rejected": -620.7115478515625,
|
| 1334 |
+
"loss": 0.0121,
|
| 1335 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1336 |
+
"rewards/chosen": -1.8229620456695557,
|
| 1337 |
+
"rewards/margins": 1.5415856838226318,
|
| 1338 |
+
"rewards/rejected": -3.3645477294921875,
|
| 1339 |
+
"step": 950
|
| 1340 |
+
},
|
| 1341 |
{
|
| 1342 |
"epoch": 2.0,
|
| 1343 |
+
"step": 954,
|
| 1344 |
"total_flos": 0.0,
|
| 1345 |
+
"train_loss": 0.050850671487596796,
|
| 1346 |
+
"train_runtime": 12712.7589,
|
| 1347 |
+
"train_samples_per_second": 9.618,
|
| 1348 |
+
"train_steps_per_second": 0.075
|
| 1349 |
}
|
| 1350 |
],
|
| 1351 |
"logging_steps": 10,
|
| 1352 |
+
"max_steps": 954,
|
| 1353 |
"num_train_epochs": 2,
|
| 1354 |
"save_steps": 10000,
|
| 1355 |
"total_flos": 0.0,
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6648
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1bcefccada842dee8d69c04461efc22f005902c17e1d735f351279d99f9c2e09
|
| 3 |
size 6648
|