Upload folder using huggingface_hub
Browse files- config.json +1 -1
- latest +1 -0
- pytorch_model-00001-of-00002.bin +1 -1
- pytorch_model-00002-of-00002.bin +1 -1
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- rng_state_4.pth +3 -0
- rng_state_5.pth +3 -0
- rng_state_6.pth +3 -0
- rng_state_7.pth +3 -0
- trainer_state.json +379 -1516
- training_args.bin +1 -1
- zero_to_fp32.py +578 -0
config.json
CHANGED
|
@@ -26,7 +26,7 @@
|
|
| 26 |
"torch_dtype": "bfloat16",
|
| 27 |
"transformers_version": "4.31.0",
|
| 28 |
"tune_visual_abstractor": true,
|
| 29 |
-
"use_cache":
|
| 30 |
"visual_abstractor_lr": null,
|
| 31 |
"visual_config": {
|
| 32 |
"visual_abstractor": {
|
|
|
|
| 26 |
"torch_dtype": "bfloat16",
|
| 27 |
"transformers_version": "4.31.0",
|
| 28 |
"tune_visual_abstractor": true,
|
| 29 |
+
"use_cache": false,
|
| 30 |
"visual_abstractor_lr": null,
|
| 31 |
"visual_config": {
|
| 32 |
"visual_abstractor": {
|
latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step376
|
pytorch_model-00001-of-00002.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9991591698
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4d187bfd7ad6ece722f12446603cb507bdd45717e32726a12441bc737c35d1c
|
| 3 |
size 9991591698
|
pytorch_model-00002-of-00002.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6417830970
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56898eede94bfbe91688f02ab5a03758c695aae88dee17428f5a710a85841069
|
| 3 |
size 6417830970
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:569e3f96e00ce6f71c26359f4c3d353fdf576b977f9f1713b440b0de9fb09ce8
|
| 3 |
+
size 21687
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73d87b20a91ecef4d643e58a3fd10c41ff2bf9c4064b760dc40e29ace2e594e6
|
| 3 |
+
size 21687
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bcf53341194f948fcf9a3e26ad99832df1a48167bd687bf0a3c6c2a25771aa2
|
| 3 |
+
size 21687
|
rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b107a39e25d7ad4a8497408ddd779fafbe9135b11896245877b7a4b6c0d8d30
|
| 3 |
+
size 21687
|
rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34d3297c91cb02dc5bc5651ee04fcf26c836094e58aea2d90af5392c51300cb7
|
| 3 |
+
size 21687
|
rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:feaf8db8c36694d11d8c5ae2f94c53c602030053aab3bbe19182febea03576f6
|
| 3 |
+
size 21687
|
rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fe964ab071c98fecd13b4cc37d7060325abbdd909b545a66cf3beb9cda1c83b
|
| 3 |
+
size 21687
|
rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f6fda2084a2af7ecf370c6a8aa825344fa1aec4d118137a27a983dfc78aca36
|
| 3 |
+
size 21687
|
trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -10,3400 +10,2263 @@
|
|
| 10 |
{
|
| 11 |
"epoch": 0.01,
|
| 12 |
"learning_rate": 1.1764705882352942e-06,
|
| 13 |
-
"loss": 1.
|
| 14 |
"step": 1
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.01,
|
| 18 |
"learning_rate": 2.3529411764705885e-06,
|
| 19 |
-
"loss": 1.
|
| 20 |
"step": 2
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.02,
|
| 24 |
"learning_rate": 3.529411764705883e-06,
|
| 25 |
-
"loss": 1.
|
| 26 |
"step": 3
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.02,
|
| 30 |
"learning_rate": 4.705882352941177e-06,
|
| 31 |
-
"loss": 1.
|
| 32 |
"step": 4
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.03,
|
| 36 |
"learning_rate": 5.882352941176471e-06,
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 5
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.03,
|
| 42 |
"learning_rate": 7.058823529411766e-06,
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 6
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.04,
|
| 48 |
"learning_rate": 8.23529411764706e-06,
|
| 49 |
-
"loss": 0.
|
| 50 |
"step": 7
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.04,
|
| 54 |
"learning_rate": 9.411764705882354e-06,
|
| 55 |
-
"loss": 0.
|
| 56 |
"step": 8
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.05,
|
| 60 |
"learning_rate": 1.0588235294117648e-05,
|
| 61 |
-
"loss": 0.
|
| 62 |
"step": 9
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 0.05,
|
| 66 |
"learning_rate": 1.1764705882352942e-05,
|
| 67 |
-
"loss": 0.
|
| 68 |
"step": 10
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 0.06,
|
| 72 |
"learning_rate": 1.2941176470588238e-05,
|
| 73 |
-
"loss": 0.
|
| 74 |
"step": 11
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.06,
|
| 78 |
"learning_rate": 1.4117647058823532e-05,
|
| 79 |
-
"loss": 0.
|
| 80 |
"step": 12
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.07,
|
| 84 |
"learning_rate": 1.5294117647058822e-05,
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 13
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.07,
|
| 90 |
"learning_rate": 1.647058823529412e-05,
|
| 91 |
-
"loss": 0.
|
| 92 |
"step": 14
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 0.08,
|
| 96 |
"learning_rate": 1.7647058823529414e-05,
|
| 97 |
-
"loss": 0.
|
| 98 |
"step": 15
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 0.09,
|
| 102 |
"learning_rate": 1.8823529411764708e-05,
|
| 103 |
-
"loss": 0.
|
| 104 |
"step": 16
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 0.09,
|
| 108 |
"learning_rate": 2e-05,
|
| 109 |
-
"loss": 0.
|
| 110 |
"step": 17
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 0.1,
|
| 114 |
"learning_rate": 1.9999835072185805e-05,
|
| 115 |
-
"loss": 0.
|
| 116 |
"step": 18
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 0.1,
|
| 120 |
"learning_rate": 1.999934029418346e-05,
|
| 121 |
-
"loss": 0.
|
| 122 |
"step": 19
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.11,
|
| 126 |
"learning_rate": 1.9998515682313485e-05,
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 20
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.11,
|
| 132 |
"learning_rate": 1.999736126377618e-05,
|
| 133 |
-
"loss": 0.
|
| 134 |
"step": 21
|
| 135 |
},
|
| 136 |
{
|
| 137 |
"epoch": 0.12,
|
| 138 |
"learning_rate": 1.999587707665068e-05,
|
| 139 |
-
"loss": 0.
|
| 140 |
"step": 22
|
| 141 |
},
|
| 142 |
{
|
| 143 |
"epoch": 0.12,
|
| 144 |
"learning_rate": 1.999406316989374e-05,
|
| 145 |
-
"loss": 0.
|
| 146 |
"step": 23
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 0.13,
|
| 150 |
"learning_rate": 1.9991919603338088e-05,
|
| 151 |
-
"loss": 0.
|
| 152 |
"step": 24
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 0.13,
|
| 156 |
"learning_rate": 1.998944644769048e-05,
|
| 157 |
-
"loss": 0.
|
| 158 |
"step": 25
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 0.14,
|
| 162 |
"learning_rate": 1.9986643784529346e-05,
|
| 163 |
-
"loss": 0.
|
| 164 |
"step": 26
|
| 165 |
},
|
| 166 |
{
|
| 167 |
"epoch": 0.14,
|
| 168 |
"learning_rate": 1.9983511706302102e-05,
|
| 169 |
-
"loss": 0.
|
| 170 |
"step": 27
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.15,
|
| 174 |
"learning_rate": 1.9980050316322118e-05,
|
| 175 |
-
"loss": 0.
|
| 176 |
"step": 28
|
| 177 |
},
|
| 178 |
{
|
| 179 |
"epoch": 0.15,
|
| 180 |
"learning_rate": 1.997625972876529e-05,
|
| 181 |
-
"loss": 0.
|
| 182 |
"step": 29
|
| 183 |
},
|
| 184 |
{
|
| 185 |
"epoch": 0.16,
|
| 186 |
"learning_rate": 1.997214006866628e-05,
|
| 187 |
-
"loss": 0.
|
| 188 |
"step": 30
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 0.16,
|
| 192 |
"learning_rate": 1.9967691471914392e-05,
|
| 193 |
-
"loss": 0.
|
| 194 |
"step": 31
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 0.17,
|
| 198 |
"learning_rate": 1.99629140852491e-05,
|
| 199 |
-
"loss": 0.
|
| 200 |
"step": 32
|
| 201 |
},
|
| 202 |
{
|
| 203 |
"epoch": 0.18,
|
| 204 |
"learning_rate": 1.9957808066255187e-05,
|
| 205 |
-
"loss": 0.
|
| 206 |
"step": 33
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 0.18,
|
| 210 |
"learning_rate": 1.9952373583357566e-05,
|
| 211 |
-
"loss": 0.
|
| 212 |
"step": 34
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 0.19,
|
| 216 |
"learning_rate": 1.994661081581571e-05,
|
| 217 |
-
"loss": 0.
|
| 218 |
"step": 35
|
| 219 |
},
|
| 220 |
{
|
| 221 |
"epoch": 0.19,
|
| 222 |
"learning_rate": 1.9940519953717762e-05,
|
| 223 |
-
"loss": 0.
|
| 224 |
"step": 36
|
| 225 |
},
|
| 226 |
{
|
| 227 |
"epoch": 0.2,
|
| 228 |
"learning_rate": 1.993410119797422e-05,
|
| 229 |
-
"loss": 0.
|
| 230 |
"step": 37
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 0.2,
|
| 234 |
"learning_rate": 1.9927354760311365e-05,
|
| 235 |
-
"loss": 0.
|
| 236 |
"step": 38
|
| 237 |
},
|
| 238 |
{
|
| 239 |
"epoch": 0.21,
|
| 240 |
"learning_rate": 1.992028086326424e-05,
|
| 241 |
-
"loss": 0.
|
| 242 |
"step": 39
|
| 243 |
},
|
| 244 |
{
|
| 245 |
"epoch": 0.21,
|
| 246 |
"learning_rate": 1.991287974016932e-05,
|
| 247 |
-
"loss": 0.
|
| 248 |
"step": 40
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 0.22,
|
| 252 |
"learning_rate": 1.9905151635156813e-05,
|
| 253 |
-
"loss": 0.
|
| 254 |
"step": 41
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 0.22,
|
| 258 |
"learning_rate": 1.9897096803142616e-05,
|
| 259 |
-
"loss": 0.
|
| 260 |
"step": 42
|
| 261 |
},
|
| 262 |
{
|
| 263 |
"epoch": 0.23,
|
| 264 |
"learning_rate": 1.988871550981989e-05,
|
| 265 |
-
"loss": 0.
|
| 266 |
"step": 43
|
| 267 |
},
|
| 268 |
{
|
| 269 |
"epoch": 0.23,
|
| 270 |
"learning_rate": 1.988000803165032e-05,
|
| 271 |
-
"loss": 0.
|
| 272 |
"step": 44
|
| 273 |
},
|
| 274 |
{
|
| 275 |
"epoch": 0.24,
|
| 276 |
"learning_rate": 1.9870974655854974e-05,
|
| 277 |
-
"loss": 0.
|
| 278 |
"step": 45
|
| 279 |
},
|
| 280 |
{
|
| 281 |
"epoch": 0.24,
|
| 282 |
"learning_rate": 1.9861615680404833e-05,
|
| 283 |
-
"loss": 0.
|
| 284 |
"step": 46
|
| 285 |
},
|
| 286 |
{
|
| 287 |
"epoch": 0.25,
|
| 288 |
"learning_rate": 1.985193141401097e-05,
|
| 289 |
-
"loss": 0.
|
| 290 |
"step": 47
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 0.26,
|
| 294 |
"learning_rate": 1.9841922176114366e-05,
|
| 295 |
-
"loss": 0.
|
| 296 |
"step": 48
|
| 297 |
},
|
| 298 |
{
|
| 299 |
"epoch": 0.26,
|
| 300 |
"learning_rate": 1.9831588296875367e-05,
|
| 301 |
-
"loss": 0.
|
| 302 |
"step": 49
|
| 303 |
},
|
| 304 |
{
|
| 305 |
"epoch": 0.27,
|
| 306 |
"learning_rate": 1.982093011716279e-05,
|
| 307 |
-
"loss": 0.
|
| 308 |
"step": 50
|
| 309 |
},
|
| 310 |
{
|
| 311 |
"epoch": 0.27,
|
| 312 |
"learning_rate": 1.9809947988542696e-05,
|
| 313 |
-
"loss": 0.
|
| 314 |
"step": 51
|
| 315 |
},
|
| 316 |
{
|
| 317 |
"epoch": 0.28,
|
| 318 |
"learning_rate": 1.979864227326678e-05,
|
| 319 |
-
"loss": 0.
|
| 320 |
"step": 52
|
| 321 |
},
|
| 322 |
{
|
| 323 |
"epoch": 0.28,
|
| 324 |
"learning_rate": 1.9787013344260422e-05,
|
| 325 |
-
"loss": 0.
|
| 326 |
"step": 53
|
| 327 |
},
|
| 328 |
{
|
| 329 |
"epoch": 0.29,
|
| 330 |
"learning_rate": 1.9775061585110387e-05,
|
| 331 |
-
"loss": 0.
|
| 332 |
"step": 54
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 0.29,
|
| 336 |
"learning_rate": 1.976278739005218e-05,
|
| 337 |
-
"loss": 0.
|
| 338 |
"step": 55
|
| 339 |
},
|
| 340 |
{
|
| 341 |
"epoch": 0.3,
|
| 342 |
"learning_rate": 1.9750191163957042e-05,
|
| 343 |
-
"loss": 0.
|
| 344 |
"step": 56
|
| 345 |
},
|
| 346 |
{
|
| 347 |
"epoch": 0.3,
|
| 348 |
"learning_rate": 1.9737273322318565e-05,
|
| 349 |
-
"loss": 0.
|
| 350 |
"step": 57
|
| 351 |
},
|
| 352 |
{
|
| 353 |
"epoch": 0.31,
|
| 354 |
"learning_rate": 1.972403429123904e-05,
|
| 355 |
-
"loss": 0.
|
| 356 |
"step": 58
|
| 357 |
},
|
| 358 |
{
|
| 359 |
"epoch": 0.31,
|
| 360 |
"learning_rate": 1.971047450741535e-05,
|
| 361 |
-
"loss": 0.
|
| 362 |
"step": 59
|
| 363 |
},
|
| 364 |
{
|
| 365 |
"epoch": 0.32,
|
| 366 |
"learning_rate": 1.9696594418124598e-05,
|
| 367 |
-
"loss": 0.
|
| 368 |
"step": 60
|
| 369 |
},
|
| 370 |
{
|
| 371 |
"epoch": 0.32,
|
| 372 |
"learning_rate": 1.9682394481209338e-05,
|
| 373 |
-
"loss": 0.
|
| 374 |
"step": 61
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 0.33,
|
| 378 |
"learning_rate": 1.966787516506249e-05,
|
| 379 |
-
"loss": 0.
|
| 380 |
"step": 62
|
| 381 |
},
|
| 382 |
{
|
| 383 |
"epoch": 0.34,
|
| 384 |
"learning_rate": 1.9653036948611864e-05,
|
| 385 |
-
"loss": 0.
|
| 386 |
"step": 63
|
| 387 |
},
|
| 388 |
{
|
| 389 |
"epoch": 0.34,
|
| 390 |
"learning_rate": 1.9637880321304387e-05,
|
| 391 |
-
"loss": 0.
|
| 392 |
"step": 64
|
| 393 |
},
|
| 394 |
{
|
| 395 |
"epoch": 0.35,
|
| 396 |
"learning_rate": 1.962240578308993e-05,
|
| 397 |
-
"loss": 0.
|
| 398 |
"step": 65
|
| 399 |
},
|
| 400 |
{
|
| 401 |
"epoch": 0.35,
|
| 402 |
"learning_rate": 1.9606613844404853e-05,
|
| 403 |
-
"loss": 0.
|
| 404 |
"step": 66
|
| 405 |
},
|
| 406 |
{
|
| 407 |
"epoch": 0.36,
|
| 408 |
"learning_rate": 1.9590505026155146e-05,
|
| 409 |
-
"loss": 0.
|
| 410 |
"step": 67
|
| 411 |
},
|
| 412 |
{
|
| 413 |
"epoch": 0.36,
|
| 414 |
"learning_rate": 1.9574079859699236e-05,
|
| 415 |
-
"loss": 0.
|
| 416 |
"step": 68
|
| 417 |
},
|
| 418 |
{
|
| 419 |
"epoch": 0.37,
|
| 420 |
"learning_rate": 1.955733888683049e-05,
|
| 421 |
-
"loss": 0.
|
| 422 |
"step": 69
|
| 423 |
},
|
| 424 |
{
|
| 425 |
"epoch": 0.37,
|
| 426 |
"learning_rate": 1.9540282659759317e-05,
|
| 427 |
-
"loss": 0.
|
| 428 |
"step": 70
|
| 429 |
},
|
| 430 |
{
|
| 431 |
"epoch": 0.38,
|
| 432 |
"learning_rate": 1.9522911741094966e-05,
|
| 433 |
-
"loss": 0.
|
| 434 |
"step": 71
|
| 435 |
},
|
| 436 |
{
|
| 437 |
"epoch": 0.38,
|
| 438 |
"learning_rate": 1.9505226703826973e-05,
|
| 439 |
-
"loss": 0.
|
| 440 |
"step": 72
|
| 441 |
},
|
| 442 |
{
|
| 443 |
"epoch": 0.39,
|
| 444 |
"learning_rate": 1.948722813130624e-05,
|
| 445 |
-
"loss": 0.
|
| 446 |
"step": 73
|
| 447 |
},
|
| 448 |
{
|
| 449 |
"epoch": 0.39,
|
| 450 |
"learning_rate": 1.9468916617225814e-05,
|
| 451 |
-
"loss": 0.
|
| 452 |
"step": 74
|
| 453 |
},
|
| 454 |
{
|
| 455 |
"epoch": 0.4,
|
| 456 |
"learning_rate": 1.9450292765601287e-05,
|
| 457 |
-
"loss": 0.
|
| 458 |
"step": 75
|
| 459 |
},
|
| 460 |
{
|
| 461 |
"epoch": 0.4,
|
| 462 |
"learning_rate": 1.94313571907509e-05,
|
| 463 |
-
"loss": 0.
|
| 464 |
"step": 76
|
| 465 |
},
|
| 466 |
{
|
| 467 |
"epoch": 0.41,
|
| 468 |
"learning_rate": 1.941211051727524e-05,
|
| 469 |
-
"loss": 0.
|
| 470 |
"step": 77
|
| 471 |
},
|
| 472 |
{
|
| 473 |
"epoch": 0.41,
|
| 474 |
"learning_rate": 1.939255338003666e-05,
|
| 475 |
-
"loss": 0.
|
| 476 |
"step": 78
|
| 477 |
},
|
| 478 |
{
|
| 479 |
"epoch": 0.42,
|
| 480 |
"learning_rate": 1.937268642413835e-05,
|
| 481 |
-
"loss": 0.
|
| 482 |
"step": 79
|
| 483 |
},
|
| 484 |
{
|
| 485 |
"epoch": 0.43,
|
| 486 |
"learning_rate": 1.9352510304903017e-05,
|
| 487 |
-
"loss": 0.
|
| 488 |
"step": 80
|
| 489 |
},
|
| 490 |
{
|
| 491 |
"epoch": 0.43,
|
| 492 |
"learning_rate": 1.9332025687851325e-05,
|
| 493 |
-
"loss": 0.
|
| 494 |
"step": 81
|
| 495 |
},
|
| 496 |
{
|
| 497 |
"epoch": 0.44,
|
| 498 |
"learning_rate": 1.931123324867989e-05,
|
| 499 |
-
"loss": 0.
|
| 500 |
"step": 82
|
| 501 |
},
|
| 502 |
{
|
| 503 |
"epoch": 0.44,
|
| 504 |
"learning_rate": 1.929013367323902e-05,
|
| 505 |
-
"loss": 0.
|
| 506 |
"step": 83
|
| 507 |
},
|
| 508 |
{
|
| 509 |
"epoch": 0.45,
|
| 510 |
"learning_rate": 1.926872765751009e-05,
|
| 511 |
-
"loss": 0.
|
| 512 |
"step": 84
|
| 513 |
},
|
| 514 |
{
|
| 515 |
"epoch": 0.45,
|
| 516 |
"learning_rate": 1.9247015907582574e-05,
|
| 517 |
-
"loss": 0.
|
| 518 |
"step": 85
|
| 519 |
},
|
| 520 |
{
|
| 521 |
"epoch": 0.46,
|
| 522 |
"learning_rate": 1.9224999139630766e-05,
|
| 523 |
-
"loss": 0.
|
| 524 |
"step": 86
|
| 525 |
},
|
| 526 |
{
|
| 527 |
"epoch": 0.46,
|
| 528 |
"learning_rate": 1.920267807989015e-05,
|
| 529 |
-
"loss": 0.
|
| 530 |
"step": 87
|
| 531 |
},
|
| 532 |
{
|
| 533 |
"epoch": 0.47,
|
| 534 |
"learning_rate": 1.918005346463344e-05,
|
| 535 |
-
"loss": 0.
|
| 536 |
"step": 88
|
| 537 |
},
|
| 538 |
{
|
| 539 |
"epoch": 0.47,
|
| 540 |
"learning_rate": 1.9157126040146307e-05,
|
| 541 |
-
"loss": 0.
|
| 542 |
"step": 89
|
| 543 |
},
|
| 544 |
{
|
| 545 |
"epoch": 0.48,
|
| 546 |
"learning_rate": 1.9133896562702746e-05,
|
| 547 |
-
"loss": 0.
|
| 548 |
"step": 90
|
| 549 |
},
|
| 550 |
{
|
| 551 |
"epoch": 0.48,
|
| 552 |
"learning_rate": 1.911036579854016e-05,
|
| 553 |
-
"loss": 0.
|
| 554 |
"step": 91
|
| 555 |
},
|
| 556 |
{
|
| 557 |
"epoch": 0.49,
|
| 558 |
"learning_rate": 1.9086534523834032e-05,
|
| 559 |
-
"loss": 0.
|
| 560 |
"step": 92
|
| 561 |
},
|
| 562 |
{
|
| 563 |
"epoch": 0.49,
|
| 564 |
"learning_rate": 1.906240352467238e-05,
|
| 565 |
-
"loss": 0.
|
| 566 |
"step": 93
|
| 567 |
},
|
| 568 |
{
|
| 569 |
"epoch": 0.5,
|
| 570 |
"learning_rate": 1.9037973597029796e-05,
|
| 571 |
-
"loss": 0.
|
| 572 |
"step": 94
|
| 573 |
},
|
| 574 |
{
|
| 575 |
"epoch": 0.51,
|
| 576 |
"learning_rate": 1.901324554674119e-05,
|
| 577 |
-
"loss": 0.
|
| 578 |
"step": 95
|
| 579 |
},
|
| 580 |
{
|
| 581 |
"epoch": 0.51,
|
| 582 |
"learning_rate": 1.8988220189475216e-05,
|
| 583 |
-
"loss": 0.
|
| 584 |
"step": 96
|
| 585 |
},
|
| 586 |
{
|
| 587 |
"epoch": 0.52,
|
| 588 |
"learning_rate": 1.896289835070737e-05,
|
| 589 |
-
"loss": 0.
|
| 590 |
"step": 97
|
| 591 |
},
|
| 592 |
{
|
| 593 |
"epoch": 0.52,
|
| 594 |
"learning_rate": 1.893728086569276e-05,
|
| 595 |
-
"loss": 0.
|
| 596 |
"step": 98
|
| 597 |
},
|
| 598 |
{
|
| 599 |
"epoch": 0.53,
|
| 600 |
"learning_rate": 1.891136857943854e-05,
|
| 601 |
-
"loss": 0.
|
| 602 |
"step": 99
|
| 603 |
},
|
| 604 |
{
|
| 605 |
"epoch": 0.53,
|
| 606 |
"learning_rate": 1.8885162346676063e-05,
|
| 607 |
-
"loss": 0.
|
| 608 |
"step": 100
|
| 609 |
},
|
| 610 |
{
|
| 611 |
"epoch": 0.54,
|
| 612 |
"learning_rate": 1.8858663031832665e-05,
|
| 613 |
-
"loss": 0.
|
| 614 |
"step": 101
|
| 615 |
},
|
| 616 |
{
|
| 617 |
"epoch": 0.54,
|
| 618 |
"learning_rate": 1.8831871509003164e-05,
|
| 619 |
-
"loss": 0.
|
| 620 |
"step": 102
|
| 621 |
},
|
| 622 |
{
|
| 623 |
"epoch": 0.55,
|
| 624 |
"learning_rate": 1.8804788661921012e-05,
|
| 625 |
-
"loss": 0.
|
| 626 |
"step": 103
|
| 627 |
},
|
| 628 |
{
|
| 629 |
"epoch": 0.55,
|
| 630 |
"learning_rate": 1.877741538392917e-05,
|
| 631 |
-
"loss": 0.
|
| 632 |
"step": 104
|
| 633 |
},
|
| 634 |
{
|
| 635 |
"epoch": 0.56,
|
| 636 |
"learning_rate": 1.8749752577950614e-05,
|
| 637 |
-
"loss": 0.
|
| 638 |
"step": 105
|
| 639 |
},
|
| 640 |
{
|
| 641 |
"epoch": 0.56,
|
| 642 |
"learning_rate": 1.8721801156458573e-05,
|
| 643 |
-
"loss": 0.
|
| 644 |
"step": 106
|
| 645 |
},
|
| 646 |
{
|
| 647 |
"epoch": 0.57,
|
| 648 |
"learning_rate": 1.869356204144642e-05,
|
| 649 |
-
"loss": 0.
|
| 650 |
"step": 107
|
| 651 |
},
|
| 652 |
{
|
| 653 |
"epoch": 0.57,
|
| 654 |
"learning_rate": 1.866503616439725e-05,
|
| 655 |
-
"loss": 0.
|
| 656 |
"step": 108
|
| 657 |
},
|
| 658 |
{
|
| 659 |
"epoch": 0.58,
|
| 660 |
"learning_rate": 1.8636224466253177e-05,
|
| 661 |
-
"loss": 0.
|
| 662 |
"step": 109
|
| 663 |
},
|
| 664 |
{
|
| 665 |
"epoch": 0.59,
|
| 666 |
"learning_rate": 1.860712789738428e-05,
|
| 667 |
-
"loss": 0.
|
| 668 |
"step": 110
|
| 669 |
},
|
| 670 |
{
|
| 671 |
"epoch": 0.59,
|
| 672 |
"learning_rate": 1.857774741755726e-05,
|
| 673 |
-
"loss": 0.
|
| 674 |
"step": 111
|
| 675 |
},
|
| 676 |
{
|
| 677 |
"epoch": 0.6,
|
| 678 |
"learning_rate": 1.854808399590378e-05,
|
| 679 |
-
"loss": 0.
|
| 680 |
"step": 112
|
| 681 |
},
|
| 682 |
{
|
| 683 |
"epoch": 0.6,
|
| 684 |
"learning_rate": 1.8518138610888505e-05,
|
| 685 |
-
"loss": 0.
|
| 686 |
"step": 113
|
| 687 |
},
|
| 688 |
{
|
| 689 |
"epoch": 0.61,
|
| 690 |
"learning_rate": 1.8487912250276805e-05,
|
| 691 |
-
"loss": 0.
|
| 692 |
"step": 114
|
| 693 |
},
|
| 694 |
{
|
| 695 |
"epoch": 0.61,
|
| 696 |
"learning_rate": 1.8457405911102202e-05,
|
| 697 |
-
"loss": 0.
|
| 698 |
"step": 115
|
| 699 |
},
|
| 700 |
{
|
| 701 |
"epoch": 0.62,
|
| 702 |
"learning_rate": 1.8426620599633464e-05,
|
| 703 |
-
"loss": 0.
|
| 704 |
"step": 116
|
| 705 |
},
|
| 706 |
{
|
| 707 |
"epoch": 0.62,
|
| 708 |
"learning_rate": 1.8395557331341413e-05,
|
| 709 |
-
"loss": 0.
|
| 710 |
"step": 117
|
| 711 |
},
|
| 712 |
{
|
| 713 |
"epoch": 0.63,
|
| 714 |
"learning_rate": 1.836421713086544e-05,
|
| 715 |
-
"loss": 0.
|
| 716 |
"step": 118
|
| 717 |
},
|
| 718 |
{
|
| 719 |
"epoch": 0.63,
|
| 720 |
"learning_rate": 1.83326010319797e-05,
|
| 721 |
-
"loss": 0.
|
| 722 |
"step": 119
|
| 723 |
},
|
| 724 |
{
|
| 725 |
"epoch": 0.64,
|
| 726 |
"learning_rate": 1.830071007755901e-05,
|
| 727 |
-
"loss": 0.
|
| 728 |
"step": 120
|
| 729 |
},
|
| 730 |
{
|
| 731 |
"epoch": 0.64,
|
| 732 |
"learning_rate": 1.8268545319544443e-05,
|
| 733 |
-
"loss": 0.
|
| 734 |
"step": 121
|
| 735 |
},
|
| 736 |
{
|
| 737 |
"epoch": 0.65,
|
| 738 |
"learning_rate": 1.823610781890865e-05,
|
| 739 |
-
"loss": 0.
|
| 740 |
"step": 122
|
| 741 |
},
|
| 742 |
{
|
| 743 |
"epoch": 0.65,
|
| 744 |
"learning_rate": 1.820339864562085e-05,
|
| 745 |
-
"loss": 0.
|
| 746 |
"step": 123
|
| 747 |
},
|
| 748 |
{
|
| 749 |
"epoch": 0.66,
|
| 750 |
"learning_rate": 1.817041887861153e-05,
|
| 751 |
-
"loss": 0.
|
| 752 |
"step": 124
|
| 753 |
},
|
| 754 |
{
|
| 755 |
"epoch": 0.66,
|
| 756 |
"learning_rate": 1.8137169605736867e-05,
|
| 757 |
-
"loss": 0.
|
| 758 |
"step": 125
|
| 759 |
},
|
| 760 |
{
|
| 761 |
"epoch": 0.67,
|
| 762 |
"learning_rate": 1.8103651923742846e-05,
|
| 763 |
-
"loss": 0.
|
| 764 |
"step": 126
|
| 765 |
},
|
| 766 |
{
|
| 767 |
"epoch": 0.68,
|
| 768 |
"learning_rate": 1.8069866938229066e-05,
|
| 769 |
-
"loss": 0.
|
| 770 |
"step": 127
|
| 771 |
},
|
| 772 |
{
|
| 773 |
"epoch": 0.68,
|
| 774 |
"learning_rate": 1.8035815763612293e-05,
|
| 775 |
-
"loss": 0.
|
| 776 |
"step": 128
|
| 777 |
},
|
| 778 |
{
|
| 779 |
"epoch": 0.69,
|
| 780 |
"learning_rate": 1.8001499523089683e-05,
|
| 781 |
-
"loss": 0.
|
| 782 |
"step": 129
|
| 783 |
},
|
| 784 |
{
|
| 785 |
"epoch": 0.69,
|
| 786 |
"learning_rate": 1.7966919348601754e-05,
|
| 787 |
-
"loss": 0.
|
| 788 |
"step": 130
|
| 789 |
},
|
| 790 |
{
|
| 791 |
"epoch": 0.7,
|
| 792 |
"learning_rate": 1.7932076380795017e-05,
|
| 793 |
-
"loss": 0.
|
| 794 |
"step": 131
|
| 795 |
},
|
| 796 |
{
|
| 797 |
"epoch": 0.7,
|
| 798 |
"learning_rate": 1.7896971768984373e-05,
|
| 799 |
-
"loss": 0.
|
| 800 |
"step": 132
|
| 801 |
},
|
| 802 |
{
|
| 803 |
"epoch": 0.71,
|
| 804 |
"learning_rate": 1.7861606671115207e-05,
|
| 805 |
-
"loss": 0.
|
| 806 |
"step": 133
|
| 807 |
},
|
| 808 |
{
|
| 809 |
"epoch": 0.71,
|
| 810 |
"learning_rate": 1.7825982253725175e-05,
|
| 811 |
-
"loss": 0.
|
| 812 |
"step": 134
|
| 813 |
},
|
| 814 |
{
|
| 815 |
"epoch": 0.72,
|
| 816 |
"learning_rate": 1.7790099691905736e-05,
|
| 817 |
-
"loss": 0.
|
| 818 |
"step": 135
|
| 819 |
},
|
| 820 |
{
|
| 821 |
"epoch": 0.72,
|
| 822 |
"learning_rate": 1.7753960169263387e-05,
|
| 823 |
-
"loss": 0.
|
| 824 |
"step": 136
|
| 825 |
},
|
| 826 |
{
|
| 827 |
"epoch": 0.73,
|
| 828 |
"learning_rate": 1.7717564877880623e-05,
|
| 829 |
-
"loss": 0.
|
| 830 |
"step": 137
|
| 831 |
},
|
| 832 |
{
|
| 833 |
"epoch": 0.73,
|
| 834 |
"learning_rate": 1.7680915018276613e-05,
|
| 835 |
-
"loss": 0.
|
| 836 |
"step": 138
|
| 837 |
},
|
| 838 |
{
|
| 839 |
"epoch": 0.74,
|
| 840 |
"learning_rate": 1.764401179936761e-05,
|
| 841 |
-
"loss": 0.
|
| 842 |
"step": 139
|
| 843 |
},
|
| 844 |
{
|
| 845 |
"epoch": 0.74,
|
| 846 |
"learning_rate": 1.7606856438427054e-05,
|
| 847 |
-
"loss": 0.
|
| 848 |
"step": 140
|
| 849 |
},
|
| 850 |
{
|
| 851 |
"epoch": 0.75,
|
| 852 |
"learning_rate": 1.7569450161045444e-05,
|
| 853 |
-
"loss": 0.
|
| 854 |
"step": 141
|
| 855 |
},
|
| 856 |
{
|
| 857 |
"epoch": 0.76,
|
| 858 |
"learning_rate": 1.7531794201089888e-05,
|
| 859 |
-
"loss": 0.
|
| 860 |
"step": 142
|
| 861 |
},
|
| 862 |
{
|
| 863 |
"epoch": 0.76,
|
| 864 |
"learning_rate": 1.749388980066342e-05,
|
| 865 |
-
"loss": 0.
|
| 866 |
"step": 143
|
| 867 |
},
|
| 868 |
{
|
| 869 |
"epoch": 0.77,
|
| 870 |
"learning_rate": 1.745573821006403e-05,
|
| 871 |
-
"loss": 0.
|
| 872 |
"step": 144
|
| 873 |
},
|
| 874 |
{
|
| 875 |
"epoch": 0.77,
|
| 876 |
"learning_rate": 1.7417340687743393e-05,
|
| 877 |
-
"loss": 0.
|
| 878 |
"step": 145
|
| 879 |
},
|
| 880 |
{
|
| 881 |
"epoch": 0.78,
|
| 882 |
"learning_rate": 1.7378698500265402e-05,
|
| 883 |
-
"loss": 0.
|
| 884 |
"step": 146
|
| 885 |
},
|
| 886 |
{
|
| 887 |
"epoch": 0.78,
|
| 888 |
"learning_rate": 1.7339812922264366e-05,
|
| 889 |
-
"loss": 0.
|
| 890 |
"step": 147
|
| 891 |
},
|
| 892 |
{
|
| 893 |
"epoch": 0.79,
|
| 894 |
"learning_rate": 1.730068523640295e-05,
|
| 895 |
-
"loss": 0.
|
| 896 |
"step": 148
|
| 897 |
},
|
| 898 |
{
|
| 899 |
"epoch": 0.79,
|
| 900 |
"learning_rate": 1.72613167333299e-05,
|
| 901 |
-
"loss": 0.
|
| 902 |
"step": 149
|
| 903 |
},
|
| 904 |
{
|
| 905 |
"epoch": 0.8,
|
| 906 |
"learning_rate": 1.7221708711637455e-05,
|
| 907 |
-
"loss": 0.
|
| 908 |
"step": 150
|
| 909 |
},
|
| 910 |
{
|
| 911 |
"epoch": 0.8,
|
| 912 |
"learning_rate": 1.718186247781849e-05,
|
| 913 |
-
"loss": 0.
|
| 914 |
"step": 151
|
| 915 |
},
|
| 916 |
{
|
| 917 |
"epoch": 0.81,
|
| 918 |
"learning_rate": 1.7141779346223465e-05,
|
| 919 |
-
"loss": 0.
|
| 920 |
"step": 152
|
| 921 |
},
|
| 922 |
{
|
| 923 |
"epoch": 0.81,
|
| 924 |
"learning_rate": 1.7101460639017034e-05,
|
| 925 |
-
"loss": 0.
|
| 926 |
"step": 153
|
| 927 |
},
|
| 928 |
{
|
| 929 |
"epoch": 0.82,
|
| 930 |
"learning_rate": 1.7060907686134445e-05,
|
| 931 |
-
"loss": 0.
|
| 932 |
"step": 154
|
| 933 |
},
|
| 934 |
{
|
| 935 |
"epoch": 0.82,
|
| 936 |
"learning_rate": 1.7020121825237672e-05,
|
| 937 |
-
"loss": 0.
|
| 938 |
"step": 155
|
| 939 |
},
|
| 940 |
{
|
| 941 |
"epoch": 0.83,
|
| 942 |
"learning_rate": 1.6979104401671296e-05,
|
| 943 |
-
"loss": 0.
|
| 944 |
"step": 156
|
| 945 |
},
|
| 946 |
{
|
| 947 |
"epoch": 0.84,
|
| 948 |
"learning_rate": 1.693785676841812e-05,
|
| 949 |
-
"loss": 0.
|
| 950 |
"step": 157
|
| 951 |
},
|
| 952 |
{
|
| 953 |
"epoch": 0.84,
|
| 954 |
"learning_rate": 1.6896380286054537e-05,
|
| 955 |
-
"loss": 0.
|
| 956 |
"step": 158
|
| 957 |
},
|
| 958 |
{
|
| 959 |
"epoch": 0.85,
|
| 960 |
"learning_rate": 1.6854676322705673e-05,
|
| 961 |
-
"loss": 0.
|
| 962 |
"step": 159
|
| 963 |
},
|
| 964 |
{
|
| 965 |
"epoch": 0.85,
|
| 966 |
"learning_rate": 1.6812746254000222e-05,
|
| 967 |
-
"loss": 0.
|
| 968 |
"step": 160
|
| 969 |
},
|
| 970 |
{
|
| 971 |
"epoch": 0.86,
|
| 972 |
"learning_rate": 1.67705914630251e-05,
|
| 973 |
-
"loss": 0.
|
| 974 |
"step": 161
|
| 975 |
},
|
| 976 |
{
|
| 977 |
"epoch": 0.86,
|
| 978 |
"learning_rate": 1.6728213340279822e-05,
|
| 979 |
-
"loss": 0.
|
| 980 |
"step": 162
|
| 981 |
},
|
| 982 |
{
|
| 983 |
"epoch": 0.87,
|
| 984 |
"learning_rate": 1.668561328363061e-05,
|
| 985 |
-
"loss": 0.
|
| 986 |
"step": 163
|
| 987 |
},
|
| 988 |
{
|
| 989 |
"epoch": 0.87,
|
| 990 |
"learning_rate": 1.6642792698264313e-05,
|
| 991 |
-
"loss": 0.
|
| 992 |
"step": 164
|
| 993 |
},
|
| 994 |
{
|
| 995 |
"epoch": 0.88,
|
| 996 |
"learning_rate": 1.6599752996642044e-05,
|
| 997 |
-
"loss": 0.
|
| 998 |
"step": 165
|
| 999 |
},
|
| 1000 |
{
|
| 1001 |
"epoch": 0.88,
|
| 1002 |
"learning_rate": 1.655649559845258e-05,
|
| 1003 |
-
"loss": 0.
|
| 1004 |
"step": 166
|
| 1005 |
},
|
| 1006 |
{
|
| 1007 |
"epoch": 0.89,
|
| 1008 |
"learning_rate": 1.651302193056555e-05,
|
| 1009 |
-
"loss": 0.
|
| 1010 |
"step": 167
|
| 1011 |
},
|
| 1012 |
{
|
| 1013 |
"epoch": 0.89,
|
| 1014 |
"learning_rate": 1.6469333426984357e-05,
|
| 1015 |
-
"loss": 0.
|
| 1016 |
"step": 168
|
| 1017 |
},
|
| 1018 |
{
|
| 1019 |
"epoch": 0.9,
|
| 1020 |
"learning_rate": 1.6425431528798883e-05,
|
| 1021 |
-
"loss": 0.
|
| 1022 |
"step": 169
|
| 1023 |
},
|
| 1024 |
{
|
| 1025 |
"epoch": 0.9,
|
| 1026 |
"learning_rate": 1.6381317684137946e-05,
|
| 1027 |
-
"loss": 0.
|
| 1028 |
"step": 170
|
| 1029 |
},
|
| 1030 |
{
|
| 1031 |
"epoch": 0.91,
|
| 1032 |
"learning_rate": 1.6336993348121543e-05,
|
| 1033 |
-
"loss": 0.
|
| 1034 |
"step": 171
|
| 1035 |
},
|
| 1036 |
{
|
| 1037 |
"epoch": 0.91,
|
| 1038 |
"learning_rate": 1.6292459982812845e-05,
|
| 1039 |
-
"loss": 0.
|
| 1040 |
"step": 172
|
| 1041 |
},
|
| 1042 |
{
|
| 1043 |
"epoch": 0.92,
|
| 1044 |
"learning_rate": 1.624771905716997e-05,
|
| 1045 |
-
"loss": 0.
|
| 1046 |
"step": 173
|
| 1047 |
},
|
| 1048 |
{
|
| 1049 |
"epoch": 0.93,
|
| 1050 |
"learning_rate": 1.620277204699754e-05,
|
| 1051 |
-
"loss": 0.
|
| 1052 |
"step": 174
|
| 1053 |
},
|
| 1054 |
{
|
| 1055 |
"epoch": 0.93,
|
| 1056 |
"learning_rate": 1.615762043489797e-05,
|
| 1057 |
-
"loss": 0.
|
| 1058 |
"step": 175
|
| 1059 |
},
|
| 1060 |
{
|
| 1061 |
"epoch": 0.94,
|
| 1062 |
"learning_rate": 1.611226571022261e-05,
|
| 1063 |
-
"loss": 0.
|
| 1064 |
"step": 176
|
| 1065 |
},
|
| 1066 |
{
|
| 1067 |
"epoch": 0.94,
|
| 1068 |
"learning_rate": 1.6066709369022576e-05,
|
| 1069 |
-
"loss": 0.
|
| 1070 |
"step": 177
|
| 1071 |
},
|
| 1072 |
{
|
| 1073 |
"epoch": 0.95,
|
| 1074 |
"learning_rate": 1.6020952913999423e-05,
|
| 1075 |
-
"loss": 0.
|
| 1076 |
"step": 178
|
| 1077 |
},
|
| 1078 |
{
|
| 1079 |
"epoch": 0.95,
|
| 1080 |
"learning_rate": 1.5974997854455575e-05,
|
| 1081 |
-
"loss": 0.
|
| 1082 |
"step": 179
|
| 1083 |
},
|
| 1084 |
{
|
| 1085 |
"epoch": 0.96,
|
| 1086 |
"learning_rate": 1.5928845706244537e-05,
|
| 1087 |
-
"loss": 0.
|
| 1088 |
"step": 180
|
| 1089 |
},
|
| 1090 |
{
|
| 1091 |
"epoch": 0.96,
|
| 1092 |
"learning_rate": 1.588249799172089e-05,
|
| 1093 |
-
"loss": 0.
|
| 1094 |
"step": 181
|
| 1095 |
},
|
| 1096 |
{
|
| 1097 |
"epoch": 0.97,
|
| 1098 |
"learning_rate": 1.583595623969009e-05,
|
| 1099 |
-
"loss": 0.
|
| 1100 |
"step": 182
|
| 1101 |
},
|
| 1102 |
{
|
| 1103 |
"epoch": 0.97,
|
| 1104 |
"learning_rate": 1.5789221985358017e-05,
|
| 1105 |
-
"loss": 0.
|
| 1106 |
"step": 183
|
| 1107 |
},
|
| 1108 |
{
|
| 1109 |
"epoch": 0.98,
|
| 1110 |
"learning_rate": 1.574229677028036e-05,
|
| 1111 |
-
"loss": 0.
|
| 1112 |
"step": 184
|
| 1113 |
},
|
| 1114 |
{
|
| 1115 |
"epoch": 0.98,
|
| 1116 |
"learning_rate": 1.5695182142311743e-05,
|
| 1117 |
-
"loss": 0.
|
| 1118 |
"step": 185
|
| 1119 |
},
|
| 1120 |
{
|
| 1121 |
"epoch": 0.99,
|
| 1122 |
"learning_rate": 1.564787965555469e-05,
|
| 1123 |
-
"loss": 0.
|
| 1124 |
"step": 186
|
| 1125 |
},
|
| 1126 |
{
|
| 1127 |
"epoch": 0.99,
|
| 1128 |
"learning_rate": 1.560039087030836e-05,
|
| 1129 |
-
"loss": 0.
|
| 1130 |
"step": 187
|
| 1131 |
},
|
| 1132 |
{
|
| 1133 |
"epoch": 1.0,
|
| 1134 |
"learning_rate": 1.5552717353017045e-05,
|
| 1135 |
-
"loss": 0.
|
| 1136 |
"step": 188
|
| 1137 |
},
|
| 1138 |
{
|
| 1139 |
"epoch": 1.01,
|
| 1140 |
"learning_rate": 1.5504860676218557e-05,
|
| 1141 |
-
"loss": 0.
|
| 1142 |
"step": 189
|
| 1143 |
},
|
| 1144 |
{
|
| 1145 |
"epoch": 1.01,
|
| 1146 |
"learning_rate": 1.5456822418492312e-05,
|
| 1147 |
-
"loss": 0.
|
| 1148 |
"step": 190
|
| 1149 |
},
|
| 1150 |
{
|
| 1151 |
"epoch": 1.02,
|
| 1152 |
"learning_rate": 1.540860416440728e-05,
|
| 1153 |
-
"loss": 0.
|
| 1154 |
"step": 191
|
| 1155 |
},
|
| 1156 |
{
|
| 1157 |
"epoch": 1.02,
|
| 1158 |
"learning_rate": 1.5360207504469715e-05,
|
| 1159 |
-
"loss": 0.
|
| 1160 |
"step": 192
|
| 1161 |
},
|
| 1162 |
{
|
| 1163 |
"epoch": 1.03,
|
| 1164 |
"learning_rate": 1.5311634035070678e-05,
|
| 1165 |
-
"loss": 0.
|
| 1166 |
"step": 193
|
| 1167 |
},
|
| 1168 |
{
|
| 1169 |
"epoch": 1.03,
|
| 1170 |
"learning_rate": 1.5262885358433404e-05,
|
| 1171 |
-
"loss": 0.
|
| 1172 |
"step": 194
|
| 1173 |
},
|
| 1174 |
{
|
| 1175 |
"epoch": 1.04,
|
| 1176 |
"learning_rate": 1.5213963082560424e-05,
|
| 1177 |
-
"loss": 0.
|
| 1178 |
"step": 195
|
| 1179 |
},
|
| 1180 |
{
|
| 1181 |
"epoch": 1.04,
|
| 1182 |
"learning_rate": 1.5164868821180538e-05,
|
| 1183 |
-
"loss": 0.
|
| 1184 |
"step": 196
|
| 1185 |
},
|
| 1186 |
{
|
| 1187 |
"epoch": 1.05,
|
| 1188 |
"learning_rate": 1.5115604193695599e-05,
|
| 1189 |
-
"loss": 0.
|
| 1190 |
"step": 197
|
| 1191 |
},
|
| 1192 |
{
|
| 1193 |
"epoch": 1.05,
|
| 1194 |
"learning_rate": 1.5066170825127069e-05,
|
| 1195 |
-
"loss": 0.
|
| 1196 |
"step": 198
|
| 1197 |
},
|
| 1198 |
{
|
| 1199 |
"epoch": 1.06,
|
| 1200 |
"learning_rate": 1.5016570346062432e-05,
|
| 1201 |
-
"loss": 0.
|
| 1202 |
"step": 199
|
| 1203 |
},
|
| 1204 |
{
|
| 1205 |
"epoch": 1.06,
|
| 1206 |
"learning_rate": 1.496680439260141e-05,
|
| 1207 |
-
"loss": 0.
|
| 1208 |
"step": 200
|
| 1209 |
},
|
| 1210 |
{
|
| 1211 |
"epoch": 1.07,
|
| 1212 |
"learning_rate": 1.4916874606301989e-05,
|
| 1213 |
-
"loss": 0.
|
| 1214 |
"step": 201
|
| 1215 |
},
|
| 1216 |
{
|
| 1217 |
"epoch": 1.07,
|
| 1218 |
"learning_rate": 1.4866782634126266e-05,
|
| 1219 |
-
"loss": 0.
|
| 1220 |
"step": 202
|
| 1221 |
},
|
| 1222 |
{
|
| 1223 |
"epoch": 1.08,
|
| 1224 |
"learning_rate": 1.4816530128386144e-05,
|
| 1225 |
-
"loss": 0.
|
| 1226 |
"step": 203
|
| 1227 |
},
|
| 1228 |
{
|
| 1229 |
"epoch": 1.09,
|
| 1230 |
"learning_rate": 1.4766118746688805e-05,
|
| 1231 |
-
"loss": 0.
|
| 1232 |
"step": 204
|
| 1233 |
},
|
| 1234 |
{
|
| 1235 |
"epoch": 1.09,
|
| 1236 |
"learning_rate": 1.471555015188205e-05,
|
| 1237 |
-
"loss": 0.
|
| 1238 |
"step": 205
|
| 1239 |
},
|
| 1240 |
{
|
| 1241 |
"epoch": 1.1,
|
| 1242 |
"learning_rate": 1.4664826011999436e-05,
|
| 1243 |
-
"loss": 0.
|
| 1244 |
"step": 206
|
| 1245 |
},
|
| 1246 |
{
|
| 1247 |
"epoch": 1.1,
|
| 1248 |
"learning_rate": 1.4613948000205272e-05,
|
| 1249 |
-
"loss": 0.
|
| 1250 |
"step": 207
|
| 1251 |
},
|
| 1252 |
{
|
| 1253 |
"epoch": 1.11,
|
| 1254 |
"learning_rate": 1.4562917794739412e-05,
|
| 1255 |
-
"loss": 0.
|
| 1256 |
"step": 208
|
| 1257 |
},
|
| 1258 |
{
|
| 1259 |
"epoch": 1.11,
|
| 1260 |
"learning_rate": 1.4511737078861903e-05,
|
| 1261 |
-
"loss": 0.
|
| 1262 |
"step": 209
|
| 1263 |
},
|
| 1264 |
{
|
| 1265 |
"epoch": 1.12,
|
| 1266 |
"learning_rate": 1.4460407540797467e-05,
|
| 1267 |
-
"loss": 0.
|
| 1268 |
"step": 210
|
| 1269 |
},
|
| 1270 |
{
|
| 1271 |
"epoch": 1.12,
|
| 1272 |
"learning_rate": 1.4408930873679805e-05,
|
| 1273 |
-
"loss": 0.
|
| 1274 |
"step": 211
|
| 1275 |
},
|
| 1276 |
{
|
| 1277 |
"epoch": 1.13,
|
| 1278 |
"learning_rate": 1.4357308775495757e-05,
|
| 1279 |
-
"loss": 0.
|
| 1280 |
"step": 212
|
| 1281 |
},
|
| 1282 |
{
|
| 1283 |
"epoch": 1.13,
|
| 1284 |
"learning_rate": 1.4305542949029286e-05,
|
| 1285 |
-
"loss": 0.
|
| 1286 |
"step": 213
|
| 1287 |
},
|
| 1288 |
{
|
| 1289 |
"epoch": 1.14,
|
| 1290 |
"learning_rate": 1.4253635101805313e-05,
|
| 1291 |
-
"loss": 0.
|
| 1292 |
"step": 214
|
| 1293 |
},
|
| 1294 |
{
|
| 1295 |
"epoch": 1.14,
|
| 1296 |
"learning_rate": 1.4201586946033397e-05,
|
| 1297 |
-
"loss": 0.
|
| 1298 |
"step": 215
|
| 1299 |
},
|
| 1300 |
{
|
| 1301 |
"epoch": 1.15,
|
| 1302 |
"learning_rate": 1.4149400198551247e-05,
|
| 1303 |
-
"loss": 0.
|
| 1304 |
"step": 216
|
| 1305 |
},
|
| 1306 |
{
|
| 1307 |
"epoch": 1.15,
|
| 1308 |
"learning_rate": 1.4097076580768103e-05,
|
| 1309 |
-
"loss": 0.
|
| 1310 |
"step": 217
|
| 1311 |
},
|
| 1312 |
{
|
| 1313 |
"epoch": 1.16,
|
| 1314 |
"learning_rate": 1.4044617818607949e-05,
|
| 1315 |
-
"loss": 0.
|
| 1316 |
"step": 218
|
| 1317 |
},
|
| 1318 |
{
|
| 1319 |
"epoch": 1.16,
|
| 1320 |
"learning_rate": 1.3992025642452579e-05,
|
| 1321 |
-
"loss": 0.
|
| 1322 |
"step": 219
|
| 1323 |
},
|
| 1324 |
{
|
| 1325 |
"epoch": 1.17,
|
| 1326 |
"learning_rate": 1.3939301787084522e-05,
|
| 1327 |
-
"loss": 0.
|
| 1328 |
"step": 220
|
| 1329 |
},
|
| 1330 |
{
|
| 1331 |
"epoch": 1.18,
|
| 1332 |
"learning_rate": 1.3886447991629828e-05,
|
| 1333 |
-
"loss": 0.
|
| 1334 |
"step": 221
|
| 1335 |
},
|
| 1336 |
{
|
| 1337 |
"epoch": 1.18,
|
| 1338 |
"learning_rate": 1.3833465999500689e-05,
|
| 1339 |
-
"loss": 0.
|
| 1340 |
"step": 222
|
| 1341 |
},
|
| 1342 |
{
|
| 1343 |
"epoch": 1.19,
|
| 1344 |
"learning_rate": 1.3780357558337927e-05,
|
| 1345 |
-
"loss": 0.
|
| 1346 |
"step": 223
|
| 1347 |
},
|
| 1348 |
{
|
| 1349 |
"epoch": 1.19,
|
| 1350 |
"learning_rate": 1.372712441995337e-05,
|
| 1351 |
-
"loss": 0.
|
| 1352 |
"step": 224
|
| 1353 |
},
|
| 1354 |
{
|
| 1355 |
"epoch": 1.2,
|
| 1356 |
"learning_rate": 1.3673768340272053e-05,
|
| 1357 |
-
"loss": 0.
|
| 1358 |
"step": 225
|
| 1359 |
},
|
| 1360 |
{
|
| 1361 |
"epoch": 1.2,
|
| 1362 |
"learning_rate": 1.362029107927429e-05,
|
| 1363 |
-
"loss": 0.
|
| 1364 |
"step": 226
|
| 1365 |
},
|
| 1366 |
{
|
| 1367 |
"epoch": 1.21,
|
| 1368 |
"learning_rate": 1.3566694400937635e-05,
|
| 1369 |
-
"loss": 0.
|
| 1370 |
"step": 227
|
| 1371 |
},
|
| 1372 |
{
|
| 1373 |
"epoch": 1.21,
|
| 1374 |
"learning_rate": 1.3512980073178693e-05,
|
| 1375 |
-
"loss": 0.
|
| 1376 |
"step": 228
|
| 1377 |
},
|
| 1378 |
{
|
| 1379 |
"epoch": 1.22,
|
| 1380 |
"learning_rate": 1.3459149867794794e-05,
|
| 1381 |
-
"loss": 0.
|
| 1382 |
"step": 229
|
| 1383 |
},
|
| 1384 |
{
|
| 1385 |
"epoch": 1.22,
|
| 1386 |
"learning_rate": 1.3405205560405558e-05,
|
| 1387 |
-
"loss": 0.
|
| 1388 |
"step": 230
|
| 1389 |
},
|
| 1390 |
{
|
| 1391 |
"epoch": 1.23,
|
| 1392 |
"learning_rate": 1.3351148930394333e-05,
|
| 1393 |
-
"loss": 0.
|
| 1394 |
"step": 231
|
| 1395 |
},
|
| 1396 |
{
|
| 1397 |
"epoch": 1.23,
|
| 1398 |
"learning_rate": 1.329698176084948e-05,
|
| 1399 |
-
"loss": 0.
|
| 1400 |
"step": 232
|
| 1401 |
},
|
| 1402 |
{
|
| 1403 |
"epoch": 1.24,
|
| 1404 |
"learning_rate": 1.3242705838505577e-05,
|
| 1405 |
-
"loss": 0.
|
| 1406 |
"step": 233
|
| 1407 |
},
|
| 1408 |
{
|
| 1409 |
"epoch": 1.24,
|
| 1410 |
"learning_rate": 1.3188322953684467e-05,
|
| 1411 |
-
"loss": 0.
|
| 1412 |
"step": 234
|
| 1413 |
},
|
| 1414 |
{
|
| 1415 |
"epoch": 1.25,
|
| 1416 |
"learning_rate": 1.3133834900236217e-05,
|
| 1417 |
-
"loss": 0.
|
| 1418 |
"step": 235
|
| 1419 |
},
|
| 1420 |
{
|
| 1421 |
"epoch": 1.26,
|
| 1422 |
"learning_rate": 1.3079243475479942e-05,
|
| 1423 |
-
"loss": 0.
|
| 1424 |
"step": 236
|
| 1425 |
},
|
| 1426 |
{
|
| 1427 |
"epoch": 1.26,
|
| 1428 |
"learning_rate": 1.3024550480144506e-05,
|
| 1429 |
-
"loss": 0.
|
| 1430 |
"step": 237
|
| 1431 |
},
|
| 1432 |
{
|
| 1433 |
"epoch": 1.27,
|
| 1434 |
"learning_rate": 1.296975771830915e-05,
|
| 1435 |
-
"loss": 0.
|
| 1436 |
"step": 238
|
| 1437 |
},
|
| 1438 |
{
|
| 1439 |
"epoch": 1.27,
|
| 1440 |
"learning_rate": 1.2914866997343957e-05,
|
| 1441 |
-
"loss": 0.
|
| 1442 |
"step": 239
|
| 1443 |
},
|
| 1444 |
{
|
| 1445 |
"epoch": 1.28,
|
| 1446 |
"learning_rate": 1.2859880127850258e-05,
|
| 1447 |
-
"loss": 0.
|
| 1448 |
"step": 240
|
| 1449 |
},
|
| 1450 |
{
|
| 1451 |
"epoch": 1.28,
|
| 1452 |
"learning_rate": 1.2804798923600888e-05,
|
| 1453 |
-
"loss": 0.
|
| 1454 |
"step": 241
|
| 1455 |
},
|
| 1456 |
{
|
| 1457 |
"epoch": 1.29,
|
| 1458 |
"learning_rate": 1.2749625201480375e-05,
|
| 1459 |
-
"loss": 0.
|
| 1460 |
"step": 242
|
| 1461 |
},
|
| 1462 |
{
|
| 1463 |
"epoch": 1.29,
|
| 1464 |
"learning_rate": 1.2694360781424994e-05,
|
| 1465 |
-
"loss": 0.
|
| 1466 |
"step": 243
|
| 1467 |
},
|
| 1468 |
{
|
| 1469 |
"epoch": 1.3,
|
| 1470 |
"learning_rate": 1.2639007486362745e-05,
|
| 1471 |
-
"loss": 0.
|
| 1472 |
"step": 244
|
| 1473 |
},
|
| 1474 |
{
|
| 1475 |
"epoch": 1.3,
|
| 1476 |
"learning_rate": 1.2583567142153224e-05,
|
| 1477 |
-
"loss": 0.
|
| 1478 |
"step": 245
|
| 1479 |
},
|
| 1480 |
{
|
| 1481 |
"epoch": 1.31,
|
| 1482 |
"learning_rate": 1.2528041577527384e-05,
|
| 1483 |
-
"loss": 0.
|
| 1484 |
"step": 246
|
| 1485 |
},
|
| 1486 |
{
|
| 1487 |
"epoch": 1.31,
|
| 1488 |
"learning_rate": 1.2472432624027228e-05,
|
| 1489 |
-
"loss": 0.
|
| 1490 |
"step": 247
|
| 1491 |
},
|
| 1492 |
{
|
| 1493 |
"epoch": 1.32,
|
| 1494 |
"learning_rate": 1.2416742115945391e-05,
|
| 1495 |
-
"loss": 0.
|
| 1496 |
"step": 248
|
| 1497 |
},
|
| 1498 |
{
|
| 1499 |
"epoch": 1.32,
|
| 1500 |
"learning_rate": 1.2360971890264621e-05,
|
| 1501 |
-
"loss": 0.
|
| 1502 |
"step": 249
|
| 1503 |
},
|
| 1504 |
{
|
| 1505 |
"epoch": 1.33,
|
| 1506 |
"learning_rate": 1.2305123786597202e-05,
|
| 1507 |
-
"loss": 0.
|
| 1508 |
"step": 250
|
| 1509 |
},
|
| 1510 |
{
|
| 1511 |
"epoch": 1.34,
|
| 1512 |
"learning_rate": 1.224919964712427e-05,
|
| 1513 |
-
"loss": 0.
|
| 1514 |
"step": 251
|
| 1515 |
},
|
| 1516 |
{
|
| 1517 |
"epoch": 1.34,
|
| 1518 |
"learning_rate": 1.219320131653504e-05,
|
| 1519 |
-
"loss": 0.
|
| 1520 |
"step": 252
|
| 1521 |
},
|
| 1522 |
{
|
| 1523 |
"epoch": 1.35,
|
| 1524 |
"learning_rate": 1.2137130641965964e-05,
|
| 1525 |
-
"loss": 0.
|
| 1526 |
"step": 253
|
| 1527 |
},
|
| 1528 |
{
|
| 1529 |
"epoch": 1.35,
|
| 1530 |
"learning_rate": 1.20809894729398e-05,
|
| 1531 |
-
"loss": 0.
|
| 1532 |
"step": 254
|
| 1533 |
},
|
| 1534 |
{
|
| 1535 |
"epoch": 1.36,
|
| 1536 |
"learning_rate": 1.2024779661304614e-05,
|
| 1537 |
-
"loss": 0.
|
| 1538 |
"step": 255
|
| 1539 |
},
|
| 1540 |
{
|
| 1541 |
"epoch": 1.36,
|
| 1542 |
"learning_rate": 1.1968503061172674e-05,
|
| 1543 |
-
"loss": 0.
|
| 1544 |
"step": 256
|
| 1545 |
},
|
| 1546 |
{
|
| 1547 |
"epoch": 1.37,
|
| 1548 |
"learning_rate": 1.1912161528859308e-05,
|
| 1549 |
-
"loss": 0.
|
| 1550 |
"step": 257
|
| 1551 |
},
|
| 1552 |
{
|
| 1553 |
"epoch": 1.37,
|
| 1554 |
"learning_rate": 1.1855756922821675e-05,
|
| 1555 |
-
"loss": 0.
|
| 1556 |
"step": 258
|
| 1557 |
},
|
| 1558 |
{
|
| 1559 |
"epoch": 1.38,
|
| 1560 |
"learning_rate": 1.179929110359745e-05,
|
| 1561 |
-
"loss": 0.
|
| 1562 |
"step": 259
|
| 1563 |
},
|
| 1564 |
{
|
| 1565 |
"epoch": 1.38,
|
| 1566 |
"learning_rate": 1.1742765933743459e-05,
|
| 1567 |
-
"loss": 0.
|
| 1568 |
"step": 260
|
| 1569 |
},
|
| 1570 |
{
|
| 1571 |
"epoch": 1.39,
|
| 1572 |
"learning_rate": 1.168618327777425e-05,
|
| 1573 |
-
"loss": 0.
|
| 1574 |
"step": 261
|
| 1575 |
},
|
| 1576 |
{
|
| 1577 |
"epoch": 1.39,
|
| 1578 |
"learning_rate": 1.1629545002100573e-05,
|
| 1579 |
-
"loss": 0.
|
| 1580 |
"step": 262
|
| 1581 |
},
|
| 1582 |
{
|
| 1583 |
"epoch": 1.4,
|
| 1584 |
"learning_rate": 1.157285297496783e-05,
|
| 1585 |
-
"loss": 0.
|
| 1586 |
"step": 263
|
| 1587 |
},
|
| 1588 |
{
|
| 1589 |
"epoch": 1.4,
|
| 1590 |
"learning_rate": 1.1516109066394445e-05,
|
| 1591 |
-
"loss": 0.
|
| 1592 |
"step": 264
|
| 1593 |
},
|
| 1594 |
{
|
| 1595 |
"epoch": 1.41,
|
| 1596 |
"learning_rate": 1.1459315148110179e-05,
|
| 1597 |
-
"loss": 0.
|
| 1598 |
"step": 265
|
| 1599 |
},
|
| 1600 |
{
|
| 1601 |
"epoch": 1.41,
|
| 1602 |
"learning_rate": 1.1402473093494395e-05,
|
| 1603 |
-
"loss": 0.
|
| 1604 |
"step": 266
|
| 1605 |
},
|
| 1606 |
{
|
| 1607 |
"epoch": 1.42,
|
| 1608 |
"learning_rate": 1.1345584777514253e-05,
|
| 1609 |
-
"loss": 0.
|
| 1610 |
"step": 267
|
| 1611 |
},
|
| 1612 |
{
|
| 1613 |
"epoch": 1.43,
|
| 1614 |
"learning_rate": 1.1288652076662878e-05,
|
| 1615 |
-
"loss": 0.
|
| 1616 |
"step": 268
|
| 1617 |
},
|
| 1618 |
{
|
| 1619 |
"epoch": 1.43,
|
| 1620 |
"learning_rate": 1.1231676868897452e-05,
|
| 1621 |
-
"loss": 0.
|
| 1622 |
"step": 269
|
| 1623 |
},
|
| 1624 |
{
|
| 1625 |
"epoch": 1.44,
|
| 1626 |
"learning_rate": 1.1174661033577267e-05,
|
| 1627 |
-
"loss": 0.
|
| 1628 |
"step": 270
|
| 1629 |
},
|
| 1630 |
{
|
| 1631 |
"epoch": 1.44,
|
| 1632 |
"learning_rate": 1.1117606451401745e-05,
|
| 1633 |
-
"loss": 0.
|
| 1634 |
"step": 271
|
| 1635 |
},
|
| 1636 |
{
|
| 1637 |
"epoch": 1.45,
|
| 1638 |
"learning_rate": 1.1060515004348394e-05,
|
| 1639 |
-
"loss": 0.
|
| 1640 |
"step": 272
|
| 1641 |
},
|
| 1642 |
{
|
| 1643 |
"epoch": 1.45,
|
| 1644 |
"learning_rate": 1.1003388575610724e-05,
|
| 1645 |
-
"loss": 0.
|
| 1646 |
"step": 273
|
| 1647 |
},
|
| 1648 |
{
|
| 1649 |
"epoch": 1.46,
|
| 1650 |
"learning_rate": 1.0946229049536136e-05,
|
| 1651 |
-
"loss": 0.
|
| 1652 |
"step": 274
|
| 1653 |
},
|
| 1654 |
{
|
| 1655 |
"epoch": 1.46,
|
| 1656 |
"learning_rate": 1.088903831156378e-05,
|
| 1657 |
-
"loss": 0.
|
| 1658 |
"step": 275
|
| 1659 |
},
|
| 1660 |
{
|
| 1661 |
"epoch": 1.47,
|
| 1662 |
"learning_rate": 1.0831818248162328e-05,
|
| 1663 |
-
"loss": 0.
|
| 1664 |
"step": 276
|
| 1665 |
},
|
| 1666 |
{
|
| 1667 |
"epoch": 1.47,
|
| 1668 |
"learning_rate": 1.0774570746767785e-05,
|
| 1669 |
-
"loss": 0.
|
| 1670 |
"step": 277
|
| 1671 |
},
|
| 1672 |
{
|
| 1673 |
"epoch": 1.48,
|
| 1674 |
"learning_rate": 1.0717297695721199e-05,
|
| 1675 |
-
"loss": 0.
|
| 1676 |
"step": 278
|
| 1677 |
},
|
| 1678 |
{
|
| 1679 |
"epoch": 1.48,
|
| 1680 |
"learning_rate": 1.0660000984206395e-05,
|
| 1681 |
-
"loss": 0.
|
| 1682 |
"step": 279
|
| 1683 |
},
|
| 1684 |
{
|
| 1685 |
"epoch": 1.49,
|
| 1686 |
"learning_rate": 1.0602682502187655e-05,
|
| 1687 |
-
"loss": 0.
|
| 1688 |
"step": 280
|
| 1689 |
},
|
| 1690 |
{
|
| 1691 |
"epoch": 1.49,
|
| 1692 |
"learning_rate": 1.0545344140347365e-05,
|
| 1693 |
-
"loss": 0.
|
| 1694 |
"step": 281
|
| 1695 |
},
|
| 1696 |
{
|
| 1697 |
"epoch": 1.5,
|
| 1698 |
"learning_rate": 1.0487987790023665e-05,
|
| 1699 |
-
"loss": 0.
|
| 1700 |
"step": 282
|
| 1701 |
},
|
| 1702 |
{
|
| 1703 |
"epoch": 1.51,
|
| 1704 |
"learning_rate": 1.0430615343148054e-05,
|
| 1705 |
-
"loss": 0.
|
| 1706 |
"step": 283
|
| 1707 |
},
|
| 1708 |
{
|
| 1709 |
"epoch": 1.51,
|
| 1710 |
"learning_rate": 1.0373228692182982e-05,
|
| 1711 |
-
"loss": 0.
|
| 1712 |
"step": 284
|
| 1713 |
},
|
| 1714 |
{
|
| 1715 |
"epoch": 1.52,
|
| 1716 |
"learning_rate": 1.031582973005943e-05,
|
| 1717 |
-
"loss": 0.
|
| 1718 |
"step": 285
|
| 1719 |
},
|
| 1720 |
{
|
| 1721 |
"epoch": 1.52,
|
| 1722 |
"learning_rate": 1.0258420350114473e-05,
|
| 1723 |
-
"loss": 0.
|
| 1724 |
"step": 286
|
| 1725 |
},
|
| 1726 |
{
|
| 1727 |
"epoch": 1.53,
|
| 1728 |
"learning_rate": 1.0201002446028815e-05,
|
| 1729 |
-
"loss": 0.
|
| 1730 |
"step": 287
|
| 1731 |
},
|
| 1732 |
{
|
| 1733 |
"epoch": 1.53,
|
| 1734 |
"learning_rate": 1.0143577911764341e-05,
|
| 1735 |
-
"loss": 0.
|
| 1736 |
"step": 288
|
| 1737 |
},
|
| 1738 |
{
|
| 1739 |
"epoch": 1.54,
|
| 1740 |
"learning_rate": 1.008614864150164e-05,
|
| 1741 |
-
"loss": 0.
|
| 1742 |
"step": 289
|
| 1743 |
},
|
| 1744 |
{
|
| 1745 |
"epoch": 1.54,
|
| 1746 |
"learning_rate": 1.002871652957751e-05,
|
| 1747 |
-
"loss": 0.
|
| 1748 |
"step": 290
|
| 1749 |
},
|
| 1750 |
{
|
| 1751 |
"epoch": 1.55,
|
| 1752 |
"learning_rate": 9.97128347042249e-06,
|
| 1753 |
-
"loss": 0.
|
| 1754 |
"step": 291
|
| 1755 |
},
|
| 1756 |
{
|
| 1757 |
"epoch": 1.55,
|
| 1758 |
"learning_rate": 9.91385135849836e-06,
|
| 1759 |
-
"loss": 0.
|
| 1760 |
"step": 292
|
| 1761 |
},
|
| 1762 |
{
|
| 1763 |
"epoch": 1.56,
|
| 1764 |
"learning_rate": 9.85642208823566e-06,
|
| 1765 |
-
"loss": 0.
|
| 1766 |
"step": 293
|
| 1767 |
},
|
| 1768 |
{
|
| 1769 |
"epoch": 1.56,
|
| 1770 |
"learning_rate": 9.79899755397119e-06,
|
| 1771 |
-
"loss": 0.
|
| 1772 |
"step": 294
|
| 1773 |
},
|
| 1774 |
{
|
| 1775 |
"epoch": 1.57,
|
| 1776 |
"learning_rate": 9.741579649885532e-06,
|
| 1777 |
-
"loss": 0.
|
| 1778 |
"step": 295
|
| 1779 |
},
|
| 1780 |
{
|
| 1781 |
"epoch": 1.57,
|
| 1782 |
"learning_rate": 9.684170269940573e-06,
|
| 1783 |
-
"loss": 0.
|
| 1784 |
"step": 296
|
| 1785 |
},
|
| 1786 |
{
|
| 1787 |
"epoch": 1.58,
|
| 1788 |
"learning_rate": 9.62677130781702e-06,
|
| 1789 |
-
"loss": 0.
|
| 1790 |
"step": 297
|
| 1791 |
},
|
| 1792 |
{
|
| 1793 |
"epoch": 1.59,
|
| 1794 |
"learning_rate": 9.569384656851948e-06,
|
| 1795 |
-
"loss": 0.
|
| 1796 |
"step": 298
|
| 1797 |
},
|
| 1798 |
{
|
| 1799 |
"epoch": 1.59,
|
| 1800 |
"learning_rate": 9.512012209976335e-06,
|
| 1801 |
-
"loss": 0.
|
| 1802 |
"step": 299
|
| 1803 |
},
|
| 1804 |
{
|
| 1805 |
"epoch": 1.6,
|
| 1806 |
"learning_rate": 9.454655859652637e-06,
|
| 1807 |
-
"loss": 0.
|
| 1808 |
"step": 300
|
| 1809 |
},
|
| 1810 |
{
|
| 1811 |
"epoch": 1.6,
|
| 1812 |
"learning_rate": 9.39731749781235e-06,
|
| 1813 |
-
"loss": 0.
|
| 1814 |
"step": 301
|
| 1815 |
},
|
| 1816 |
{
|
| 1817 |
"epoch": 1.61,
|
| 1818 |
"learning_rate": 9.339999015793606e-06,
|
| 1819 |
-
"loss": 0.
|
| 1820 |
"step": 302
|
| 1821 |
},
|
| 1822 |
{
|
| 1823 |
"epoch": 1.61,
|
| 1824 |
"learning_rate": 9.282702304278806e-06,
|
| 1825 |
-
"loss": 0.
|
| 1826 |
"step": 303
|
| 1827 |
},
|
| 1828 |
{
|
| 1829 |
"epoch": 1.62,
|
| 1830 |
"learning_rate": 9.225429253232218e-06,
|
| 1831 |
-
"loss": 0.
|
| 1832 |
"step": 304
|
| 1833 |
},
|
| 1834 |
{
|
| 1835 |
"epoch": 1.62,
|
| 1836 |
"learning_rate": 9.168181751837673e-06,
|
| 1837 |
-
"loss": 0.
|
| 1838 |
"step": 305
|
| 1839 |
},
|
| 1840 |
{
|
| 1841 |
"epoch": 1.63,
|
| 1842 |
"learning_rate": 9.110961688436222e-06,
|
| 1843 |
-
"loss": 0.
|
| 1844 |
"step": 306
|
| 1845 |
},
|
| 1846 |
{
|
| 1847 |
"epoch": 1.63,
|
| 1848 |
"learning_rate": 9.053770950463865e-06,
|
| 1849 |
-
"loss": 0.
|
| 1850 |
"step": 307
|
| 1851 |
},
|
| 1852 |
{
|
| 1853 |
"epoch": 1.64,
|
| 1854 |
"learning_rate": 8.996611424389283e-06,
|
| 1855 |
-
"loss": 0.
|
| 1856 |
"step": 308
|
| 1857 |
},
|
| 1858 |
{
|
| 1859 |
"epoch": 1.64,
|
| 1860 |
"learning_rate": 8.93948499565161e-06,
|
| 1861 |
-
"loss": 0.
|
| 1862 |
"step": 309
|
| 1863 |
},
|
| 1864 |
{
|
| 1865 |
"epoch": 1.65,
|
| 1866 |
"learning_rate": 8.882393548598258e-06,
|
| 1867 |
-
"loss": 0.
|
| 1868 |
"step": 310
|
| 1869 |
},
|
| 1870 |
{
|
| 1871 |
"epoch": 1.65,
|
| 1872 |
"learning_rate": 8.825338966422735e-06,
|
| 1873 |
-
"loss": 0.
|
| 1874 |
"step": 311
|
| 1875 |
},
|
| 1876 |
{
|
| 1877 |
"epoch": 1.66,
|
| 1878 |
"learning_rate": 8.768323131102552e-06,
|
| 1879 |
-
"loss": 0.
|
| 1880 |
"step": 312
|
| 1881 |
},
|
| 1882 |
{
|
| 1883 |
"epoch": 1.66,
|
| 1884 |
"learning_rate": 8.711347923337122e-06,
|
| 1885 |
-
"loss": 0.
|
| 1886 |
"step": 313
|
| 1887 |
},
|
| 1888 |
{
|
| 1889 |
"epoch": 1.67,
|
| 1890 |
"learning_rate": 8.65441522248575e-06,
|
| 1891 |
-
"loss": 0.
|
| 1892 |
"step": 314
|
| 1893 |
},
|
| 1894 |
{
|
| 1895 |
"epoch": 1.68,
|
| 1896 |
"learning_rate": 8.59752690650561e-06,
|
| 1897 |
-
"loss": 0.
|
| 1898 |
"step": 315
|
| 1899 |
},
|
| 1900 |
{
|
| 1901 |
"epoch": 1.68,
|
| 1902 |
"learning_rate": 8.540684851889823e-06,
|
| 1903 |
-
"loss": 0.
|
| 1904 |
"step": 316
|
| 1905 |
},
|
| 1906 |
{
|
| 1907 |
"epoch": 1.69,
|
| 1908 |
"learning_rate": 8.483890933605558e-06,
|
| 1909 |
-
"loss": 0.
|
| 1910 |
"step": 317
|
| 1911 |
},
|
| 1912 |
{
|
| 1913 |
"epoch": 1.69,
|
| 1914 |
"learning_rate": 8.427147025032171e-06,
|
| 1915 |
-
"loss": 0.
|
| 1916 |
"step": 318
|
| 1917 |
},
|
| 1918 |
{
|
| 1919 |
"epoch": 1.7,
|
| 1920 |
"learning_rate": 8.37045499789943e-06,
|
| 1921 |
-
"loss": 0.
|
| 1922 |
"step": 319
|
| 1923 |
},
|
| 1924 |
{
|
| 1925 |
"epoch": 1.7,
|
| 1926 |
"learning_rate": 8.313816722225751e-06,
|
| 1927 |
-
"loss": 0.
|
| 1928 |
"step": 320
|
| 1929 |
},
|
| 1930 |
{
|
| 1931 |
"epoch": 1.71,
|
| 1932 |
"learning_rate": 8.257234066256543e-06,
|
| 1933 |
-
"loss": 0.
|
| 1934 |
"step": 321
|
| 1935 |
},
|
| 1936 |
{
|
| 1937 |
"epoch": 1.71,
|
| 1938 |
"learning_rate": 8.200708896402557e-06,
|
| 1939 |
-
"loss": 0.
|
| 1940 |
"step": 322
|
| 1941 |
},
|
| 1942 |
{
|
| 1943 |
"epoch": 1.72,
|
| 1944 |
"learning_rate": 8.144243077178329e-06,
|
| 1945 |
-
"loss": 0.
|
| 1946 |
"step": 323
|
| 1947 |
},
|
| 1948 |
{
|
| 1949 |
"epoch": 1.72,
|
| 1950 |
"learning_rate": 8.087838471140696e-06,
|
| 1951 |
-
"loss": 0.
|
| 1952 |
"step": 324
|
| 1953 |
},
|
| 1954 |
{
|
| 1955 |
"epoch": 1.73,
|
| 1956 |
"learning_rate": 8.031496938827329e-06,
|
| 1957 |
-
"loss": 0.
|
| 1958 |
"step": 325
|
| 1959 |
},
|
| 1960 |
{
|
| 1961 |
"epoch": 1.73,
|
| 1962 |
"learning_rate": 7.97522033869539e-06,
|
| 1963 |
-
"loss": 0.
|
| 1964 |
"step": 326
|
| 1965 |
},
|
| 1966 |
{
|
| 1967 |
"epoch": 1.74,
|
| 1968 |
"learning_rate": 7.9190105270602e-06,
|
| 1969 |
-
"loss": 0.
|
| 1970 |
"step": 327
|
| 1971 |
},
|
| 1972 |
{
|
| 1973 |
"epoch": 1.74,
|
| 1974 |
"learning_rate": 7.86286935803404e-06,
|
| 1975 |
-
"loss": 0.
|
| 1976 |
"step": 328
|
| 1977 |
},
|
| 1978 |
{
|
| 1979 |
"epoch": 1.75,
|
| 1980 |
"learning_rate": 7.806798683464965e-06,
|
| 1981 |
-
"loss": 0.
|
| 1982 |
"step": 329
|
| 1983 |
},
|
| 1984 |
{
|
| 1985 |
"epoch": 1.76,
|
| 1986 |
"learning_rate": 7.750800352875734e-06,
|
| 1987 |
-
"loss": 0.
|
| 1988 |
"step": 330
|
| 1989 |
},
|
| 1990 |
{
|
| 1991 |
"epoch": 1.76,
|
| 1992 |
"learning_rate": 7.694876213402801e-06,
|
| 1993 |
-
"loss": 0.
|
| 1994 |
"step": 331
|
| 1995 |
},
|
| 1996 |
{
|
| 1997 |
"epoch": 1.77,
|
| 1998 |
"learning_rate": 7.63902810973538e-06,
|
| 1999 |
-
"loss": 0.
|
| 2000 |
"step": 332
|
| 2001 |
},
|
| 2002 |
{
|
| 2003 |
"epoch": 1.77,
|
| 2004 |
"learning_rate": 7.583257884054613e-06,
|
| 2005 |
-
"loss": 0.
|
| 2006 |
"step": 333
|
| 2007 |
},
|
| 2008 |
{
|
| 2009 |
"epoch": 1.78,
|
| 2010 |
"learning_rate": 7.527567375972772e-06,
|
| 2011 |
-
"loss": 0.
|
| 2012 |
"step": 334
|
| 2013 |
},
|
| 2014 |
{
|
| 2015 |
"epoch": 1.78,
|
| 2016 |
"learning_rate": 7.471958422472618e-06,
|
| 2017 |
-
"loss": 0.
|
| 2018 |
"step": 335
|
| 2019 |
},
|
| 2020 |
{
|
| 2021 |
"epoch": 1.79,
|
| 2022 |
"learning_rate": 7.416432857846783e-06,
|
| 2023 |
-
"loss": 0.
|
| 2024 |
"step": 336
|
| 2025 |
},
|
| 2026 |
{
|
| 2027 |
"epoch": 1.79,
|
| 2028 |
"learning_rate": 7.360992513637257e-06,
|
| 2029 |
-
"loss": 0.
|
| 2030 |
"step": 337
|
| 2031 |
},
|
| 2032 |
{
|
| 2033 |
"epoch": 1.8,
|
| 2034 |
"learning_rate": 7.305639218575009e-06,
|
| 2035 |
-
"loss": 0.
|
| 2036 |
"step": 338
|
| 2037 |
},
|
| 2038 |
{
|
| 2039 |
"epoch": 1.8,
|
| 2040 |
"learning_rate": 7.250374798519626e-06,
|
| 2041 |
-
"loss": 0.
|
| 2042 |
"step": 339
|
| 2043 |
},
|
| 2044 |
{
|
| 2045 |
"epoch": 1.81,
|
| 2046 |
"learning_rate": 7.1952010763991146e-06,
|
| 2047 |
-
"loss": 0.
|
| 2048 |
"step": 340
|
| 2049 |
},
|
| 2050 |
{
|
| 2051 |
"epoch": 1.81,
|
| 2052 |
"learning_rate": 7.140119872149743e-06,
|
| 2053 |
-
"loss": 0.
|
| 2054 |
"step": 341
|
| 2055 |
},
|
| 2056 |
{
|
| 2057 |
"epoch": 1.82,
|
| 2058 |
"learning_rate": 7.085133002656044e-06,
|
| 2059 |
-
"loss": 0.
|
| 2060 |
"step": 342
|
| 2061 |
},
|
| 2062 |
{
|
| 2063 |
"epoch": 1.82,
|
| 2064 |
"learning_rate": 7.030242281690856e-06,
|
| 2065 |
-
"loss": 0.
|
| 2066 |
"step": 343
|
| 2067 |
},
|
| 2068 |
{
|
| 2069 |
"epoch": 1.83,
|
| 2070 |
"learning_rate": 6.975449519855495e-06,
|
| 2071 |
-
"loss": 0.
|
| 2072 |
"step": 344
|
| 2073 |
},
|
| 2074 |
{
|
| 2075 |
"epoch": 1.84,
|
| 2076 |
"learning_rate": 6.9207565245200614e-06,
|
| 2077 |
-
"loss": 0.
|
| 2078 |
"step": 345
|
| 2079 |
},
|
| 2080 |
{
|
| 2081 |
"epoch": 1.84,
|
| 2082 |
"learning_rate": 6.866165099763782e-06,
|
| 2083 |
-
"loss": 0.
|
| 2084 |
"step": 346
|
| 2085 |
},
|
| 2086 |
{
|
| 2087 |
"epoch": 1.85,
|
| 2088 |
"learning_rate": 6.811677046315535e-06,
|
| 2089 |
-
"loss": 0.
|
| 2090 |
"step": 347
|
| 2091 |
},
|
| 2092 |
{
|
| 2093 |
"epoch": 1.85,
|
| 2094 |
"learning_rate": 6.757294161494426e-06,
|
| 2095 |
-
"loss": 0.
|
| 2096 |
"step": 348
|
| 2097 |
},
|
| 2098 |
{
|
| 2099 |
"epoch": 1.86,
|
| 2100 |
"learning_rate": 6.70301823915052e-06,
|
| 2101 |
-
"loss": 0.
|
| 2102 |
"step": 349
|
| 2103 |
},
|
| 2104 |
{
|
| 2105 |
"epoch": 1.86,
|
| 2106 |
"learning_rate": 6.64885106960567e-06,
|
| 2107 |
-
"loss": 0.
|
| 2108 |
"step": 350
|
| 2109 |
},
|
| 2110 |
{
|
| 2111 |
"epoch": 1.87,
|
| 2112 |
"learning_rate": 6.594794439594443e-06,
|
| 2113 |
-
"loss": 0.
|
| 2114 |
"step": 351
|
| 2115 |
},
|
| 2116 |
{
|
| 2117 |
"epoch": 1.87,
|
| 2118 |
"learning_rate": 6.54085013220521e-06,
|
| 2119 |
-
"loss": 0.
|
| 2120 |
"step": 352
|
| 2121 |
},
|
| 2122 |
{
|
| 2123 |
"epoch": 1.88,
|
| 2124 |
"learning_rate": 6.48701992682131e-06,
|
| 2125 |
-
"loss": 0.
|
| 2126 |
"step": 353
|
| 2127 |
},
|
| 2128 |
{
|
| 2129 |
"epoch": 1.88,
|
| 2130 |
"learning_rate": 6.4333055990623674e-06,
|
| 2131 |
-
"loss": 0.
|
| 2132 |
"step": 354
|
| 2133 |
},
|
| 2134 |
{
|
| 2135 |
"epoch": 1.89,
|
| 2136 |
"learning_rate": 6.379708920725713e-06,
|
| 2137 |
-
"loss": 0.
|
| 2138 |
"step": 355
|
| 2139 |
},
|
| 2140 |
{
|
| 2141 |
"epoch": 1.89,
|
| 2142 |
"learning_rate": 6.3262316597279506e-06,
|
| 2143 |
-
"loss": 0.
|
| 2144 |
"step": 356
|
| 2145 |
},
|
| 2146 |
{
|
| 2147 |
"epoch": 1.9,
|
| 2148 |
"learning_rate": 6.272875580046633e-06,
|
| 2149 |
-
"loss": 0.
|
| 2150 |
"step": 357
|
| 2151 |
},
|
| 2152 |
{
|
| 2153 |
"epoch": 1.9,
|
| 2154 |
"learning_rate": 6.219642441662077e-06,
|
| 2155 |
-
"loss": 0.
|
| 2156 |
"step": 358
|
| 2157 |
},
|
| 2158 |
{
|
| 2159 |
"epoch": 1.91,
|
| 2160 |
"learning_rate": 6.1665340004993164e-06,
|
| 2161 |
-
"loss": 0.
|
| 2162 |
"step": 359
|
| 2163 |
},
|
| 2164 |
{
|
| 2165 |
"epoch": 1.91,
|
| 2166 |
"learning_rate": 6.113552008370172e-06,
|
| 2167 |
-
"loss": 0.
|
| 2168 |
"step": 360
|
| 2169 |
},
|
| 2170 |
{
|
| 2171 |
"epoch": 1.92,
|
| 2172 |
"learning_rate": 6.06069821291548e-06,
|
| 2173 |
-
"loss": 0.
|
| 2174 |
"step": 361
|
| 2175 |
},
|
| 2176 |
{
|
| 2177 |
"epoch": 1.93,
|
| 2178 |
"learning_rate": 6.007974357547424e-06,
|
| 2179 |
-
"loss": 0.
|
| 2180 |
"step": 362
|
| 2181 |
},
|
| 2182 |
{
|
| 2183 |
"epoch": 1.93,
|
| 2184 |
"learning_rate": 5.9553821813920545e-06,
|
| 2185 |
-
"loss": 0.
|
| 2186 |
"step": 363
|
| 2187 |
},
|
| 2188 |
{
|
| 2189 |
"epoch": 1.94,
|
| 2190 |
"learning_rate": 5.902923419231902e-06,
|
| 2191 |
-
"loss": 0.
|
| 2192 |
"step": 364
|
| 2193 |
},
|
| 2194 |
{
|
| 2195 |
"epoch": 1.94,
|
| 2196 |
"learning_rate": 5.850599801448757e-06,
|
| 2197 |
-
"loss": 0.
|
| 2198 |
"step": 365
|
| 2199 |
},
|
| 2200 |
{
|
| 2201 |
"epoch": 1.95,
|
| 2202 |
"learning_rate": 5.798413053966607e-06,
|
| 2203 |
-
"loss": 0.
|
| 2204 |
"step": 366
|
| 2205 |
},
|
| 2206 |
{
|
| 2207 |
"epoch": 1.95,
|
| 2208 |
"learning_rate": 5.74636489819469e-06,
|
| 2209 |
-
"loss": 0.
|
| 2210 |
"step": 367
|
| 2211 |
},
|
| 2212 |
{
|
| 2213 |
"epoch": 1.96,
|
| 2214 |
"learning_rate": 5.6944570509707185e-06,
|
| 2215 |
-
"loss": 0.
|
| 2216 |
"step": 368
|
| 2217 |
},
|
| 2218 |
{
|
| 2219 |
"epoch": 1.96,
|
| 2220 |
"learning_rate": 5.6426912245042435e-06,
|
| 2221 |
-
"loss": 0.
|
| 2222 |
"step": 369
|
| 2223 |
},
|
| 2224 |
{
|
| 2225 |
"epoch": 1.97,
|
| 2226 |
"learning_rate": 5.5910691263201985e-06,
|
| 2227 |
-
"loss": 0.
|
| 2228 |
"step": 370
|
| 2229 |
},
|
| 2230 |
{
|
| 2231 |
"epoch": 1.97,
|
| 2232 |
"learning_rate": 5.5395924592025384e-06,
|
| 2233 |
-
"loss": 0.
|
| 2234 |
"step": 371
|
| 2235 |
},
|
| 2236 |
{
|
| 2237 |
"epoch": 1.98,
|
| 2238 |
"learning_rate": 5.488262921138098e-06,
|
| 2239 |
-
"loss": 0.
|
| 2240 |
"step": 372
|
| 2241 |
},
|
| 2242 |
{
|
| 2243 |
"epoch": 1.98,
|
| 2244 |
"learning_rate": 5.437082205260593e-06,
|
| 2245 |
-
"loss": 0.
|
| 2246 |
"step": 373
|
| 2247 |
},
|
| 2248 |
{
|
| 2249 |
"epoch": 1.99,
|
| 2250 |
"learning_rate": 5.3860519997947295e-06,
|
| 2251 |
-
"loss": 0.
|
| 2252 |
"step": 374
|
| 2253 |
},
|
| 2254 |
{
|
| 2255 |
"epoch": 1.99,
|
| 2256 |
"learning_rate": 5.335173988000566e-06,
|
| 2257 |
-
"loss": 0.
|
| 2258 |
"step": 375
|
| 2259 |
},
|
| 2260 |
{
|
| 2261 |
"epoch": 2.0,
|
| 2262 |
"learning_rate": 5.284449848117954e-06,
|
| 2263 |
-
"loss": 0.0577,
|
| 2264 |
-
"step": 376
|
| 2265 |
-
},
|
| 2266 |
-
{
|
| 2267 |
-
"epoch": 2.01,
|
| 2268 |
-
"learning_rate": 5.233881253311197e-06,
|
| 2269 |
-
"loss": 0.0506,
|
| 2270 |
-
"step": 377
|
| 2271 |
-
},
|
| 2272 |
-
{
|
| 2273 |
-
"epoch": 2.01,
|
| 2274 |
-
"learning_rate": 5.183469871613858e-06,
|
| 2275 |
-
"loss": 0.0447,
|
| 2276 |
-
"step": 378
|
| 2277 |
-
},
|
| 2278 |
-
{
|
| 2279 |
-
"epoch": 2.02,
|
| 2280 |
-
"learning_rate": 5.133217365873736e-06,
|
| 2281 |
-
"loss": 0.0408,
|
| 2282 |
-
"step": 379
|
| 2283 |
-
},
|
| 2284 |
-
{
|
| 2285 |
-
"epoch": 2.02,
|
| 2286 |
-
"learning_rate": 5.083125393698015e-06,
|
| 2287 |
-
"loss": 0.0478,
|
| 2288 |
-
"step": 380
|
| 2289 |
-
},
|
| 2290 |
-
{
|
| 2291 |
-
"epoch": 2.03,
|
| 2292 |
-
"learning_rate": 5.0331956073985885e-06,
|
| 2293 |
-
"loss": 0.0379,
|
| 2294 |
-
"step": 381
|
| 2295 |
-
},
|
| 2296 |
-
{
|
| 2297 |
-
"epoch": 2.03,
|
| 2298 |
-
"learning_rate": 4.98342965393757e-06,
|
| 2299 |
-
"loss": 0.0392,
|
| 2300 |
-
"step": 382
|
| 2301 |
-
},
|
| 2302 |
-
{
|
| 2303 |
-
"epoch": 2.04,
|
| 2304 |
-
"learning_rate": 4.933829174872932e-06,
|
| 2305 |
-
"loss": 0.0471,
|
| 2306 |
-
"step": 383
|
| 2307 |
-
},
|
| 2308 |
-
{
|
| 2309 |
-
"epoch": 2.04,
|
| 2310 |
-
"learning_rate": 4.884395806304402e-06,
|
| 2311 |
-
"loss": 0.0493,
|
| 2312 |
-
"step": 384
|
| 2313 |
-
},
|
| 2314 |
-
{
|
| 2315 |
-
"epoch": 2.05,
|
| 2316 |
-
"learning_rate": 4.835131178819467e-06,
|
| 2317 |
-
"loss": 0.0427,
|
| 2318 |
-
"step": 385
|
| 2319 |
-
},
|
| 2320 |
-
{
|
| 2321 |
-
"epoch": 2.05,
|
| 2322 |
-
"learning_rate": 4.78603691743958e-06,
|
| 2323 |
-
"loss": 0.0322,
|
| 2324 |
-
"step": 386
|
| 2325 |
-
},
|
| 2326 |
-
{
|
| 2327 |
-
"epoch": 2.06,
|
| 2328 |
-
"learning_rate": 4.737114641566598e-06,
|
| 2329 |
-
"loss": 0.0477,
|
| 2330 |
-
"step": 387
|
| 2331 |
-
},
|
| 2332 |
-
{
|
| 2333 |
-
"epoch": 2.06,
|
| 2334 |
-
"learning_rate": 4.688365964929321e-06,
|
| 2335 |
-
"loss": 0.0275,
|
| 2336 |
-
"step": 388
|
| 2337 |
-
},
|
| 2338 |
-
{
|
| 2339 |
-
"epoch": 2.07,
|
| 2340 |
-
"learning_rate": 4.639792495530286e-06,
|
| 2341 |
-
"loss": 0.0483,
|
| 2342 |
-
"step": 389
|
| 2343 |
-
},
|
| 2344 |
-
{
|
| 2345 |
-
"epoch": 2.07,
|
| 2346 |
-
"learning_rate": 4.59139583559272e-06,
|
| 2347 |
-
"loss": 0.0356,
|
| 2348 |
-
"step": 390
|
| 2349 |
-
},
|
| 2350 |
-
{
|
| 2351 |
-
"epoch": 2.08,
|
| 2352 |
-
"learning_rate": 4.54317758150769e-06,
|
| 2353 |
-
"loss": 0.0397,
|
| 2354 |
-
"step": 391
|
| 2355 |
-
},
|
| 2356 |
-
{
|
| 2357 |
-
"epoch": 2.09,
|
| 2358 |
-
"learning_rate": 4.495139323781448e-06,
|
| 2359 |
-
"loss": 0.0418,
|
| 2360 |
-
"step": 392
|
| 2361 |
-
},
|
| 2362 |
-
{
|
| 2363 |
-
"epoch": 2.09,
|
| 2364 |
-
"learning_rate": 4.447282646982961e-06,
|
| 2365 |
-
"loss": 0.0356,
|
| 2366 |
-
"step": 393
|
| 2367 |
-
},
|
| 2368 |
-
{
|
| 2369 |
-
"epoch": 2.1,
|
| 2370 |
-
"learning_rate": 4.399609129691649e-06,
|
| 2371 |
-
"loss": 0.0396,
|
| 2372 |
-
"step": 394
|
| 2373 |
-
},
|
| 2374 |
-
{
|
| 2375 |
-
"epoch": 2.1,
|
| 2376 |
-
"learning_rate": 4.352120344445308e-06,
|
| 2377 |
-
"loss": 0.0396,
|
| 2378 |
-
"step": 395
|
| 2379 |
-
},
|
| 2380 |
-
{
|
| 2381 |
-
"epoch": 2.11,
|
| 2382 |
-
"learning_rate": 4.304817857688262e-06,
|
| 2383 |
-
"loss": 0.0341,
|
| 2384 |
-
"step": 396
|
| 2385 |
-
},
|
| 2386 |
-
{
|
| 2387 |
-
"epoch": 2.11,
|
| 2388 |
-
"learning_rate": 4.257703229719643e-06,
|
| 2389 |
-
"loss": 0.0419,
|
| 2390 |
-
"step": 397
|
| 2391 |
-
},
|
| 2392 |
-
{
|
| 2393 |
-
"epoch": 2.12,
|
| 2394 |
-
"learning_rate": 4.210778014641984e-06,
|
| 2395 |
-
"loss": 0.0446,
|
| 2396 |
-
"step": 398
|
| 2397 |
-
},
|
| 2398 |
-
{
|
| 2399 |
-
"epoch": 2.12,
|
| 2400 |
-
"learning_rate": 4.164043760309916e-06,
|
| 2401 |
-
"loss": 0.042,
|
| 2402 |
-
"step": 399
|
| 2403 |
-
},
|
| 2404 |
-
{
|
| 2405 |
-
"epoch": 2.13,
|
| 2406 |
-
"learning_rate": 4.1175020082791105e-06,
|
| 2407 |
-
"loss": 0.0386,
|
| 2408 |
-
"step": 400
|
| 2409 |
-
},
|
| 2410 |
-
{
|
| 2411 |
-
"epoch": 2.13,
|
| 2412 |
-
"learning_rate": 4.071154293755465e-06,
|
| 2413 |
-
"loss": 0.0376,
|
| 2414 |
-
"step": 401
|
| 2415 |
-
},
|
| 2416 |
-
{
|
| 2417 |
-
"epoch": 2.14,
|
| 2418 |
-
"learning_rate": 4.025002145544426e-06,
|
| 2419 |
-
"loss": 0.0425,
|
| 2420 |
-
"step": 402
|
| 2421 |
-
},
|
| 2422 |
-
{
|
| 2423 |
-
"epoch": 2.14,
|
| 2424 |
-
"learning_rate": 3.979047086000579e-06,
|
| 2425 |
-
"loss": 0.0389,
|
| 2426 |
-
"step": 403
|
| 2427 |
-
},
|
| 2428 |
-
{
|
| 2429 |
-
"epoch": 2.15,
|
| 2430 |
-
"learning_rate": 3.933290630977426e-06,
|
| 2431 |
-
"loss": 0.0352,
|
| 2432 |
-
"step": 404
|
| 2433 |
-
},
|
| 2434 |
-
{
|
| 2435 |
-
"epoch": 2.15,
|
| 2436 |
-
"learning_rate": 3.887734289777393e-06,
|
| 2437 |
-
"loss": 0.0294,
|
| 2438 |
-
"step": 405
|
| 2439 |
-
},
|
| 2440 |
-
{
|
| 2441 |
-
"epoch": 2.16,
|
| 2442 |
-
"learning_rate": 3.842379565102032e-06,
|
| 2443 |
-
"loss": 0.046,
|
| 2444 |
-
"step": 406
|
| 2445 |
-
},
|
| 2446 |
-
{
|
| 2447 |
-
"epoch": 2.16,
|
| 2448 |
-
"learning_rate": 3.797227953002466e-06,
|
| 2449 |
-
"loss": 0.0474,
|
| 2450 |
-
"step": 407
|
| 2451 |
-
},
|
| 2452 |
-
{
|
| 2453 |
-
"epoch": 2.17,
|
| 2454 |
-
"learning_rate": 3.7522809428300323e-06,
|
| 2455 |
-
"loss": 0.04,
|
| 2456 |
-
"step": 408
|
| 2457 |
-
},
|
| 2458 |
-
{
|
| 2459 |
-
"epoch": 2.18,
|
| 2460 |
-
"learning_rate": 3.707540017187157e-06,
|
| 2461 |
-
"loss": 0.036,
|
| 2462 |
-
"step": 409
|
| 2463 |
-
},
|
| 2464 |
-
{
|
| 2465 |
-
"epoch": 2.18,
|
| 2466 |
-
"learning_rate": 3.6630066518784625e-06,
|
| 2467 |
-
"loss": 0.0417,
|
| 2468 |
-
"step": 410
|
| 2469 |
-
},
|
| 2470 |
-
{
|
| 2471 |
-
"epoch": 2.19,
|
| 2472 |
-
"learning_rate": 3.6186823158620564e-06,
|
| 2473 |
-
"loss": 0.0359,
|
| 2474 |
-
"step": 411
|
| 2475 |
-
},
|
| 2476 |
-
{
|
| 2477 |
-
"epoch": 2.19,
|
| 2478 |
-
"learning_rate": 3.5745684712011196e-06,
|
| 2479 |
-
"loss": 0.0388,
|
| 2480 |
-
"step": 412
|
| 2481 |
-
},
|
| 2482 |
-
{
|
| 2483 |
-
"epoch": 2.2,
|
| 2484 |
-
"learning_rate": 3.5306665730156486e-06,
|
| 2485 |
-
"loss": 0.0422,
|
| 2486 |
-
"step": 413
|
| 2487 |
-
},
|
| 2488 |
-
{
|
| 2489 |
-
"epoch": 2.2,
|
| 2490 |
-
"learning_rate": 3.4869780694344523e-06,
|
| 2491 |
-
"loss": 0.0422,
|
| 2492 |
-
"step": 414
|
| 2493 |
-
},
|
| 2494 |
-
{
|
| 2495 |
-
"epoch": 2.21,
|
| 2496 |
-
"learning_rate": 3.4435044015474216e-06,
|
| 2497 |
-
"loss": 0.0492,
|
| 2498 |
-
"step": 415
|
| 2499 |
-
},
|
| 2500 |
-
{
|
| 2501 |
-
"epoch": 2.21,
|
| 2502 |
-
"learning_rate": 3.4002470033579582e-06,
|
| 2503 |
-
"loss": 0.0328,
|
| 2504 |
-
"step": 416
|
| 2505 |
-
},
|
| 2506 |
-
{
|
| 2507 |
-
"epoch": 2.22,
|
| 2508 |
-
"learning_rate": 3.357207301735688e-06,
|
| 2509 |
-
"loss": 0.0351,
|
| 2510 |
-
"step": 417
|
| 2511 |
-
},
|
| 2512 |
-
{
|
| 2513 |
-
"epoch": 2.22,
|
| 2514 |
-
"learning_rate": 3.3143867163693933e-06,
|
| 2515 |
-
"loss": 0.0608,
|
| 2516 |
-
"step": 418
|
| 2517 |
-
},
|
| 2518 |
-
{
|
| 2519 |
-
"epoch": 2.23,
|
| 2520 |
-
"learning_rate": 3.271786659720182e-06,
|
| 2521 |
-
"loss": 0.0444,
|
| 2522 |
-
"step": 419
|
| 2523 |
-
},
|
| 2524 |
-
{
|
| 2525 |
-
"epoch": 2.23,
|
| 2526 |
-
"learning_rate": 3.229408536974902e-06,
|
| 2527 |
-
"loss": 0.0417,
|
| 2528 |
-
"step": 420
|
| 2529 |
-
},
|
| 2530 |
-
{
|
| 2531 |
-
"epoch": 2.24,
|
| 2532 |
-
"learning_rate": 3.1872537459997833e-06,
|
| 2533 |
-
"loss": 0.0542,
|
| 2534 |
-
"step": 421
|
| 2535 |
-
},
|
| 2536 |
-
{
|
| 2537 |
-
"epoch": 2.24,
|
| 2538 |
-
"learning_rate": 3.1453236772943317e-06,
|
| 2539 |
-
"loss": 0.0332,
|
| 2540 |
-
"step": 422
|
| 2541 |
-
},
|
| 2542 |
-
{
|
| 2543 |
-
"epoch": 2.25,
|
| 2544 |
-
"learning_rate": 3.1036197139454604e-06,
|
| 2545 |
-
"loss": 0.037,
|
| 2546 |
-
"step": 423
|
| 2547 |
-
},
|
| 2548 |
-
{
|
| 2549 |
-
"epoch": 2.26,
|
| 2550 |
-
"learning_rate": 3.0621432315818846e-06,
|
| 2551 |
-
"loss": 0.0366,
|
| 2552 |
-
"step": 424
|
| 2553 |
-
},
|
| 2554 |
-
{
|
| 2555 |
-
"epoch": 2.26,
|
| 2556 |
-
"learning_rate": 3.0208955983287035e-06,
|
| 2557 |
-
"loss": 0.0487,
|
| 2558 |
-
"step": 425
|
| 2559 |
-
},
|
| 2560 |
-
{
|
| 2561 |
-
"epoch": 2.27,
|
| 2562 |
-
"learning_rate": 2.9798781747623282e-06,
|
| 2563 |
-
"loss": 0.0393,
|
| 2564 |
-
"step": 426
|
| 2565 |
-
},
|
| 2566 |
-
{
|
| 2567 |
-
"epoch": 2.27,
|
| 2568 |
-
"learning_rate": 2.9390923138655604e-06,
|
| 2569 |
-
"loss": 0.0392,
|
| 2570 |
-
"step": 427
|
| 2571 |
-
},
|
| 2572 |
-
{
|
| 2573 |
-
"epoch": 2.28,
|
| 2574 |
-
"learning_rate": 2.898539360982968e-06,
|
| 2575 |
-
"loss": 0.0409,
|
| 2576 |
-
"step": 428
|
| 2577 |
-
},
|
| 2578 |
-
{
|
| 2579 |
-
"epoch": 2.28,
|
| 2580 |
-
"learning_rate": 2.8582206537765355e-06,
|
| 2581 |
-
"loss": 0.0409,
|
| 2582 |
-
"step": 429
|
| 2583 |
-
},
|
| 2584 |
-
{
|
| 2585 |
-
"epoch": 2.29,
|
| 2586 |
-
"learning_rate": 2.81813752218151e-06,
|
| 2587 |
-
"loss": 0.03,
|
| 2588 |
-
"step": 430
|
| 2589 |
-
},
|
| 2590 |
-
{
|
| 2591 |
-
"epoch": 2.29,
|
| 2592 |
-
"learning_rate": 2.778291288362549e-06,
|
| 2593 |
-
"loss": 0.0422,
|
| 2594 |
-
"step": 431
|
| 2595 |
-
},
|
| 2596 |
-
{
|
| 2597 |
-
"epoch": 2.3,
|
| 2598 |
-
"learning_rate": 2.7386832666701003e-06,
|
| 2599 |
-
"loss": 0.0391,
|
| 2600 |
-
"step": 432
|
| 2601 |
-
},
|
| 2602 |
-
{
|
| 2603 |
-
"epoch": 2.3,
|
| 2604 |
-
"learning_rate": 2.6993147635970528e-06,
|
| 2605 |
-
"loss": 0.058,
|
| 2606 |
-
"step": 433
|
| 2607 |
-
},
|
| 2608 |
-
{
|
| 2609 |
-
"epoch": 2.31,
|
| 2610 |
-
"learning_rate": 2.6601870777356396e-06,
|
| 2611 |
-
"loss": 0.0386,
|
| 2612 |
-
"step": 434
|
| 2613 |
-
},
|
| 2614 |
-
{
|
| 2615 |
-
"epoch": 2.31,
|
| 2616 |
-
"learning_rate": 2.6213014997345997e-06,
|
| 2617 |
-
"loss": 0.0403,
|
| 2618 |
-
"step": 435
|
| 2619 |
-
},
|
| 2620 |
-
{
|
| 2621 |
-
"epoch": 2.32,
|
| 2622 |
-
"learning_rate": 2.5826593122566112e-06,
|
| 2623 |
-
"loss": 0.0449,
|
| 2624 |
-
"step": 436
|
| 2625 |
-
},
|
| 2626 |
-
{
|
| 2627 |
-
"epoch": 2.32,
|
| 2628 |
-
"learning_rate": 2.5442617899359732e-06,
|
| 2629 |
-
"loss": 0.036,
|
| 2630 |
-
"step": 437
|
| 2631 |
-
},
|
| 2632 |
-
{
|
| 2633 |
-
"epoch": 2.33,
|
| 2634 |
-
"learning_rate": 2.506110199336581e-06,
|
| 2635 |
-
"loss": 0.038,
|
| 2636 |
-
"step": 438
|
| 2637 |
-
},
|
| 2638 |
-
{
|
| 2639 |
-
"epoch": 2.34,
|
| 2640 |
-
"learning_rate": 2.4682057989101115e-06,
|
| 2641 |
-
"loss": 0.0503,
|
| 2642 |
-
"step": 439
|
| 2643 |
-
},
|
| 2644 |
-
{
|
| 2645 |
-
"epoch": 2.34,
|
| 2646 |
-
"learning_rate": 2.4305498389545566e-06,
|
| 2647 |
-
"loss": 0.0294,
|
| 2648 |
-
"step": 440
|
| 2649 |
-
},
|
| 2650 |
-
{
|
| 2651 |
-
"epoch": 2.35,
|
| 2652 |
-
"learning_rate": 2.3931435615729483e-06,
|
| 2653 |
-
"loss": 0.037,
|
| 2654 |
-
"step": 441
|
| 2655 |
-
},
|
| 2656 |
-
{
|
| 2657 |
-
"epoch": 2.35,
|
| 2658 |
-
"learning_rate": 2.355988200632391e-06,
|
| 2659 |
-
"loss": 0.0335,
|
| 2660 |
-
"step": 442
|
| 2661 |
-
},
|
| 2662 |
-
{
|
| 2663 |
-
"epoch": 2.36,
|
| 2664 |
-
"learning_rate": 2.319084981723386e-06,
|
| 2665 |
-
"loss": 0.0334,
|
| 2666 |
-
"step": 443
|
| 2667 |
-
},
|
| 2668 |
-
{
|
| 2669 |
-
"epoch": 2.36,
|
| 2670 |
-
"learning_rate": 2.2824351221193796e-06,
|
| 2671 |
-
"loss": 0.038,
|
| 2672 |
-
"step": 444
|
| 2673 |
-
},
|
| 2674 |
-
{
|
| 2675 |
-
"epoch": 2.37,
|
| 2676 |
-
"learning_rate": 2.246039830736616e-06,
|
| 2677 |
-
"loss": 0.04,
|
| 2678 |
-
"step": 445
|
| 2679 |
-
},
|
| 2680 |
-
{
|
| 2681 |
-
"epoch": 2.37,
|
| 2682 |
-
"learning_rate": 2.209900308094265e-06,
|
| 2683 |
-
"loss": 0.0488,
|
| 2684 |
-
"step": 446
|
| 2685 |
-
},
|
| 2686 |
-
{
|
| 2687 |
-
"epoch": 2.38,
|
| 2688 |
-
"learning_rate": 2.174017746274828e-06,
|
| 2689 |
-
"loss": 0.0369,
|
| 2690 |
-
"step": 447
|
| 2691 |
-
},
|
| 2692 |
-
{
|
| 2693 |
-
"epoch": 2.38,
|
| 2694 |
-
"learning_rate": 2.1383933288847967e-06,
|
| 2695 |
-
"loss": 0.0404,
|
| 2696 |
-
"step": 448
|
| 2697 |
-
},
|
| 2698 |
-
{
|
| 2699 |
-
"epoch": 2.39,
|
| 2700 |
-
"learning_rate": 2.1030282310156282e-06,
|
| 2701 |
-
"loss": 0.0475,
|
| 2702 |
-
"step": 449
|
| 2703 |
-
},
|
| 2704 |
-
{
|
| 2705 |
-
"epoch": 2.39,
|
| 2706 |
-
"learning_rate": 2.067923619204989e-06,
|
| 2707 |
-
"loss": 0.0383,
|
| 2708 |
-
"step": 450
|
| 2709 |
-
},
|
| 2710 |
-
{
|
| 2711 |
-
"epoch": 2.4,
|
| 2712 |
-
"learning_rate": 2.033080651398248e-06,
|
| 2713 |
-
"loss": 0.0302,
|
| 2714 |
-
"step": 451
|
| 2715 |
-
},
|
| 2716 |
-
{
|
| 2717 |
-
"epoch": 2.4,
|
| 2718 |
-
"learning_rate": 1.9985004769103157e-06,
|
| 2719 |
-
"loss": 0.0369,
|
| 2720 |
-
"step": 452
|
| 2721 |
-
},
|
| 2722 |
-
{
|
| 2723 |
-
"epoch": 2.41,
|
| 2724 |
-
"learning_rate": 1.9641842363877096e-06,
|
| 2725 |
-
"loss": 0.0426,
|
| 2726 |
-
"step": 453
|
| 2727 |
-
},
|
| 2728 |
-
{
|
| 2729 |
-
"epoch": 2.41,
|
| 2730 |
-
"learning_rate": 1.930133061770936e-06,
|
| 2731 |
-
"loss": 0.036,
|
| 2732 |
-
"step": 454
|
| 2733 |
-
},
|
| 2734 |
-
{
|
| 2735 |
-
"epoch": 2.42,
|
| 2736 |
-
"learning_rate": 1.8963480762571563e-06,
|
| 2737 |
-
"loss": 0.0308,
|
| 2738 |
-
"step": 455
|
| 2739 |
-
},
|
| 2740 |
-
{
|
| 2741 |
-
"epoch": 2.43,
|
| 2742 |
-
"learning_rate": 1.8628303942631332e-06,
|
| 2743 |
-
"loss": 0.0483,
|
| 2744 |
-
"step": 456
|
| 2745 |
-
},
|
| 2746 |
-
{
|
| 2747 |
-
"epoch": 2.43,
|
| 2748 |
-
"learning_rate": 1.8295811213884729e-06,
|
| 2749 |
-
"loss": 0.0416,
|
| 2750 |
-
"step": 457
|
| 2751 |
-
},
|
| 2752 |
-
{
|
| 2753 |
-
"epoch": 2.44,
|
| 2754 |
-
"learning_rate": 1.7966013543791528e-06,
|
| 2755 |
-
"loss": 0.047,
|
| 2756 |
-
"step": 458
|
| 2757 |
-
},
|
| 2758 |
-
{
|
| 2759 |
-
"epoch": 2.44,
|
| 2760 |
-
"learning_rate": 1.7638921810913524e-06,
|
| 2761 |
-
"loss": 0.0348,
|
| 2762 |
-
"step": 459
|
| 2763 |
-
},
|
| 2764 |
-
{
|
| 2765 |
-
"epoch": 2.45,
|
| 2766 |
-
"learning_rate": 1.73145468045556e-06,
|
| 2767 |
"loss": 0.052,
|
| 2768 |
-
"step":
|
| 2769 |
-
},
|
| 2770 |
-
{
|
| 2771 |
-
"epoch": 2.45,
|
| 2772 |
-
"learning_rate": 1.6992899224409965e-06,
|
| 2773 |
-
"loss": 0.0423,
|
| 2774 |
-
"step": 461
|
| 2775 |
-
},
|
| 2776 |
-
{
|
| 2777 |
-
"epoch": 2.46,
|
| 2778 |
-
"learning_rate": 1.667398968020303e-06,
|
| 2779 |
-
"loss": 0.0534,
|
| 2780 |
-
"step": 462
|
| 2781 |
-
},
|
| 2782 |
-
{
|
| 2783 |
-
"epoch": 2.46,
|
| 2784 |
-
"learning_rate": 1.6357828691345602e-06,
|
| 2785 |
-
"loss": 0.0544,
|
| 2786 |
-
"step": 463
|
| 2787 |
-
},
|
| 2788 |
-
{
|
| 2789 |
-
"epoch": 2.47,
|
| 2790 |
-
"learning_rate": 1.6044426686585912e-06,
|
| 2791 |
-
"loss": 0.0401,
|
| 2792 |
-
"step": 464
|
| 2793 |
-
},
|
| 2794 |
-
{
|
| 2795 |
-
"epoch": 2.47,
|
| 2796 |
-
"learning_rate": 1.5733794003665392e-06,
|
| 2797 |
-
"loss": 0.0529,
|
| 2798 |
-
"step": 465
|
| 2799 |
-
},
|
| 2800 |
-
{
|
| 2801 |
-
"epoch": 2.48,
|
| 2802 |
-
"learning_rate": 1.5425940888978007e-06,
|
| 2803 |
-
"loss": 0.0445,
|
| 2804 |
-
"step": 466
|
| 2805 |
-
},
|
| 2806 |
-
{
|
| 2807 |
-
"epoch": 2.48,
|
| 2808 |
-
"learning_rate": 1.5120877497231968e-06,
|
| 2809 |
-
"loss": 0.0397,
|
| 2810 |
-
"step": 467
|
| 2811 |
-
},
|
| 2812 |
-
{
|
| 2813 |
-
"epoch": 2.49,
|
| 2814 |
-
"learning_rate": 1.4818613891114975e-06,
|
| 2815 |
-
"loss": 0.0441,
|
| 2816 |
-
"step": 468
|
| 2817 |
-
},
|
| 2818 |
-
{
|
| 2819 |
-
"epoch": 2.49,
|
| 2820 |
-
"learning_rate": 1.4519160040962188e-06,
|
| 2821 |
-
"loss": 0.0448,
|
| 2822 |
-
"step": 469
|
| 2823 |
-
},
|
| 2824 |
-
{
|
| 2825 |
-
"epoch": 2.5,
|
| 2826 |
-
"learning_rate": 1.4222525824427414e-06,
|
| 2827 |
-
"loss": 0.0397,
|
| 2828 |
-
"step": 470
|
| 2829 |
-
},
|
| 2830 |
-
{
|
| 2831 |
-
"epoch": 2.51,
|
| 2832 |
-
"learning_rate": 1.392872102615722e-06,
|
| 2833 |
-
"loss": 0.0509,
|
| 2834 |
-
"step": 471
|
| 2835 |
-
},
|
| 2836 |
-
{
|
| 2837 |
-
"epoch": 2.51,
|
| 2838 |
-
"learning_rate": 1.3637755337468262e-06,
|
| 2839 |
-
"loss": 0.0457,
|
| 2840 |
-
"step": 472
|
| 2841 |
-
},
|
| 2842 |
-
{
|
| 2843 |
-
"epoch": 2.52,
|
| 2844 |
-
"learning_rate": 1.3349638356027539e-06,
|
| 2845 |
-
"loss": 0.0476,
|
| 2846 |
-
"step": 473
|
| 2847 |
-
},
|
| 2848 |
-
{
|
| 2849 |
-
"epoch": 2.52,
|
| 2850 |
-
"learning_rate": 1.3064379585535847e-06,
|
| 2851 |
-
"loss": 0.0296,
|
| 2852 |
-
"step": 474
|
| 2853 |
-
},
|
| 2854 |
-
{
|
| 2855 |
-
"epoch": 2.53,
|
| 2856 |
-
"learning_rate": 1.2781988435414284e-06,
|
| 2857 |
-
"loss": 0.0304,
|
| 2858 |
-
"step": 475
|
| 2859 |
-
},
|
| 2860 |
-
{
|
| 2861 |
-
"epoch": 2.53,
|
| 2862 |
-
"learning_rate": 1.2502474220493888e-06,
|
| 2863 |
-
"loss": 0.0309,
|
| 2864 |
-
"step": 476
|
| 2865 |
-
},
|
| 2866 |
-
{
|
| 2867 |
-
"epoch": 2.54,
|
| 2868 |
-
"learning_rate": 1.2225846160708332e-06,
|
| 2869 |
-
"loss": 0.0425,
|
| 2870 |
-
"step": 477
|
| 2871 |
-
},
|
| 2872 |
-
{
|
| 2873 |
-
"epoch": 2.54,
|
| 2874 |
-
"learning_rate": 1.195211338078992e-06,
|
| 2875 |
-
"loss": 0.0392,
|
| 2876 |
-
"step": 478
|
| 2877 |
-
},
|
| 2878 |
-
{
|
| 2879 |
-
"epoch": 2.55,
|
| 2880 |
-
"learning_rate": 1.1681284909968393e-06,
|
| 2881 |
-
"loss": 0.0414,
|
| 2882 |
-
"step": 479
|
| 2883 |
-
},
|
| 2884 |
-
{
|
| 2885 |
-
"epoch": 2.55,
|
| 2886 |
-
"learning_rate": 1.1413369681673348e-06,
|
| 2887 |
-
"loss": 0.0421,
|
| 2888 |
-
"step": 480
|
| 2889 |
-
},
|
| 2890 |
-
{
|
| 2891 |
-
"epoch": 2.56,
|
| 2892 |
-
"learning_rate": 1.114837653323939e-06,
|
| 2893 |
-
"loss": 0.0382,
|
| 2894 |
-
"step": 481
|
| 2895 |
-
},
|
| 2896 |
-
{
|
| 2897 |
-
"epoch": 2.56,
|
| 2898 |
-
"learning_rate": 1.0886314205614612e-06,
|
| 2899 |
-
"loss": 0.0442,
|
| 2900 |
-
"step": 482
|
| 2901 |
-
},
|
| 2902 |
-
{
|
| 2903 |
-
"epoch": 2.57,
|
| 2904 |
-
"learning_rate": 1.062719134307244e-06,
|
| 2905 |
-
"loss": 0.0404,
|
| 2906 |
-
"step": 483
|
| 2907 |
-
},
|
| 2908 |
-
{
|
| 2909 |
-
"epoch": 2.57,
|
| 2910 |
-
"learning_rate": 1.0371016492926322e-06,
|
| 2911 |
-
"loss": 0.0427,
|
| 2912 |
-
"step": 484
|
| 2913 |
-
},
|
| 2914 |
-
{
|
| 2915 |
-
"epoch": 2.58,
|
| 2916 |
-
"learning_rate": 1.0117798105247867e-06,
|
| 2917 |
-
"loss": 0.0446,
|
| 2918 |
-
"step": 485
|
| 2919 |
-
},
|
| 2920 |
-
{
|
| 2921 |
-
"epoch": 2.59,
|
| 2922 |
-
"learning_rate": 9.867544532588135e-07,
|
| 2923 |
-
"loss": 0.0371,
|
| 2924 |
-
"step": 486
|
| 2925 |
-
},
|
| 2926 |
-
{
|
| 2927 |
-
"epoch": 2.59,
|
| 2928 |
-
"learning_rate": 9.620264029702054e-07,
|
| 2929 |
-
"loss": 0.0393,
|
| 2930 |
-
"step": 487
|
| 2931 |
-
},
|
| 2932 |
-
{
|
| 2933 |
-
"epoch": 2.6,
|
| 2934 |
-
"learning_rate": 9.375964753276201e-07,
|
| 2935 |
-
"loss": 0.0405,
|
| 2936 |
-
"step": 488
|
| 2937 |
-
},
|
| 2938 |
-
{
|
| 2939 |
-
"epoch": 2.6,
|
| 2940 |
-
"learning_rate": 9.1346547616597e-07,
|
| 2941 |
-
"loss": 0.0469,
|
| 2942 |
-
"step": 489
|
| 2943 |
-
},
|
| 2944 |
-
{
|
| 2945 |
-
"epoch": 2.61,
|
| 2946 |
-
"learning_rate": 8.896342014598458e-07,
|
| 2947 |
-
"loss": 0.0479,
|
| 2948 |
-
"step": 490
|
| 2949 |
-
},
|
| 2950 |
-
{
|
| 2951 |
-
"epoch": 2.61,
|
| 2952 |
-
"learning_rate": 8.661034372972532e-07,
|
| 2953 |
-
"loss": 0.0499,
|
| 2954 |
-
"step": 491
|
| 2955 |
-
},
|
| 2956 |
-
{
|
| 2957 |
-
"epoch": 2.62,
|
| 2958 |
-
"learning_rate": 8.428739598536995e-07,
|
| 2959 |
-
"loss": 0.0389,
|
| 2960 |
-
"step": 492
|
| 2961 |
-
},
|
| 2962 |
-
{
|
| 2963 |
-
"epoch": 2.62,
|
| 2964 |
-
"learning_rate": 8.199465353665637e-07,
|
| 2965 |
-
"loss": 0.0333,
|
| 2966 |
-
"step": 493
|
| 2967 |
-
},
|
| 2968 |
-
{
|
| 2969 |
-
"epoch": 2.63,
|
| 2970 |
-
"learning_rate": 7.973219201098537e-07,
|
| 2971 |
-
"loss": 0.0455,
|
| 2972 |
-
"step": 494
|
| 2973 |
-
},
|
| 2974 |
-
{
|
| 2975 |
-
"epoch": 2.63,
|
| 2976 |
-
"learning_rate": 7.750008603692372e-07,
|
| 2977 |
-
"loss": 0.0394,
|
| 2978 |
-
"step": 495
|
| 2979 |
-
},
|
| 2980 |
-
{
|
| 2981 |
-
"epoch": 2.64,
|
| 2982 |
-
"learning_rate": 7.52984092417427e-07,
|
| 2983 |
-
"loss": 0.0344,
|
| 2984 |
-
"step": 496
|
| 2985 |
-
},
|
| 2986 |
-
{
|
| 2987 |
-
"epoch": 2.64,
|
| 2988 |
-
"learning_rate": 7.312723424899115e-07,
|
| 2989 |
-
"loss": 0.053,
|
| 2990 |
-
"step": 497
|
| 2991 |
-
},
|
| 2992 |
-
{
|
| 2993 |
-
"epoch": 2.65,
|
| 2994 |
-
"learning_rate": 7.098663267609818e-07,
|
| 2995 |
-
"loss": 0.0356,
|
| 2996 |
-
"step": 498
|
| 2997 |
-
},
|
| 2998 |
-
{
|
| 2999 |
-
"epoch": 2.65,
|
| 3000 |
-
"learning_rate": 6.887667513201135e-07,
|
| 3001 |
-
"loss": 0.0396,
|
| 3002 |
-
"step": 499
|
| 3003 |
-
},
|
| 3004 |
-
{
|
| 3005 |
-
"epoch": 2.66,
|
| 3006 |
-
"learning_rate": 6.679743121486759e-07,
|
| 3007 |
-
"loss": 0.0342,
|
| 3008 |
-
"step": 500
|
| 3009 |
-
},
|
| 3010 |
-
{
|
| 3011 |
-
"epoch": 2.66,
|
| 3012 |
-
"learning_rate": 6.474896950969845e-07,
|
| 3013 |
-
"loss": 0.0365,
|
| 3014 |
-
"step": 501
|
| 3015 |
-
},
|
| 3016 |
-
{
|
| 3017 |
-
"epoch": 2.67,
|
| 3018 |
-
"learning_rate": 6.273135758616567e-07,
|
| 3019 |
-
"loss": 0.0413,
|
| 3020 |
-
"step": 502
|
| 3021 |
-
},
|
| 3022 |
-
{
|
| 3023 |
-
"epoch": 2.68,
|
| 3024 |
-
"learning_rate": 6.074466199633411e-07,
|
| 3025 |
-
"loss": 0.0353,
|
| 3026 |
-
"step": 503
|
| 3027 |
-
},
|
| 3028 |
-
{
|
| 3029 |
-
"epoch": 2.68,
|
| 3030 |
-
"learning_rate": 5.87889482724765e-07,
|
| 3031 |
-
"loss": 0.0384,
|
| 3032 |
-
"step": 504
|
| 3033 |
-
},
|
| 3034 |
-
{
|
| 3035 |
-
"epoch": 2.69,
|
| 3036 |
-
"learning_rate": 5.686428092491014e-07,
|
| 3037 |
-
"loss": 0.0402,
|
| 3038 |
-
"step": 505
|
| 3039 |
-
},
|
| 3040 |
-
{
|
| 3041 |
-
"epoch": 2.69,
|
| 3042 |
-
"learning_rate": 5.497072343987131e-07,
|
| 3043 |
-
"loss": 0.0457,
|
| 3044 |
-
"step": 506
|
| 3045 |
-
},
|
| 3046 |
-
{
|
| 3047 |
-
"epoch": 2.7,
|
| 3048 |
-
"learning_rate": 5.310833827741912e-07,
|
| 3049 |
-
"loss": 0.0324,
|
| 3050 |
-
"step": 507
|
| 3051 |
-
},
|
| 3052 |
-
{
|
| 3053 |
-
"epoch": 2.7,
|
| 3054 |
-
"learning_rate": 5.127718686937644e-07,
|
| 3055 |
-
"loss": 0.0424,
|
| 3056 |
-
"step": 508
|
| 3057 |
-
},
|
| 3058 |
-
{
|
| 3059 |
-
"epoch": 2.71,
|
| 3060 |
-
"learning_rate": 4.9477329617303e-07,
|
| 3061 |
-
"loss": 0.0326,
|
| 3062 |
-
"step": 509
|
| 3063 |
-
},
|
| 3064 |
-
{
|
| 3065 |
-
"epoch": 2.71,
|
| 3066 |
-
"learning_rate": 4.770882589050351e-07,
|
| 3067 |
-
"loss": 0.0358,
|
| 3068 |
-
"step": 510
|
| 3069 |
-
},
|
| 3070 |
-
{
|
| 3071 |
-
"epoch": 2.72,
|
| 3072 |
-
"learning_rate": 4.5971734024068735e-07,
|
| 3073 |
-
"loss": 0.0375,
|
| 3074 |
-
"step": 511
|
| 3075 |
-
},
|
| 3076 |
-
{
|
| 3077 |
-
"epoch": 2.72,
|
| 3078 |
-
"learning_rate": 4.426611131695147e-07,
|
| 3079 |
-
"loss": 0.0402,
|
| 3080 |
-
"step": 512
|
| 3081 |
-
},
|
| 3082 |
-
{
|
| 3083 |
-
"epoch": 2.73,
|
| 3084 |
-
"learning_rate": 4.2592014030076734e-07,
|
| 3085 |
-
"loss": 0.0382,
|
| 3086 |
-
"step": 513
|
| 3087 |
-
},
|
| 3088 |
-
{
|
| 3089 |
-
"epoch": 2.73,
|
| 3090 |
-
"learning_rate": 4.0949497384485727e-07,
|
| 3091 |
-
"loss": 0.0446,
|
| 3092 |
-
"step": 514
|
| 3093 |
-
},
|
| 3094 |
-
{
|
| 3095 |
-
"epoch": 2.74,
|
| 3096 |
-
"learning_rate": 3.933861555951468e-07,
|
| 3097 |
-
"loss": 0.0432,
|
| 3098 |
-
"step": 515
|
| 3099 |
-
},
|
| 3100 |
-
{
|
| 3101 |
-
"epoch": 2.74,
|
| 3102 |
-
"learning_rate": 3.7759421691007213e-07,
|
| 3103 |
-
"loss": 0.0382,
|
| 3104 |
-
"step": 516
|
| 3105 |
-
},
|
| 3106 |
-
{
|
| 3107 |
-
"epoch": 2.75,
|
| 3108 |
-
"learning_rate": 3.6211967869561603e-07,
|
| 3109 |
-
"loss": 0.049,
|
| 3110 |
-
"step": 517
|
| 3111 |
-
},
|
| 3112 |
-
{
|
| 3113 |
-
"epoch": 2.76,
|
| 3114 |
-
"learning_rate": 3.4696305138813504e-07,
|
| 3115 |
-
"loss": 0.0452,
|
| 3116 |
-
"step": 518
|
| 3117 |
-
},
|
| 3118 |
-
{
|
| 3119 |
-
"epoch": 2.76,
|
| 3120 |
-
"learning_rate": 3.3212483493750946e-07,
|
| 3121 |
-
"loss": 0.0382,
|
| 3122 |
-
"step": 519
|
| 3123 |
-
},
|
| 3124 |
-
{
|
| 3125 |
-
"epoch": 2.77,
|
| 3126 |
-
"learning_rate": 3.1760551879066125e-07,
|
| 3127 |
-
"loss": 0.0337,
|
| 3128 |
-
"step": 520
|
| 3129 |
-
},
|
| 3130 |
-
{
|
| 3131 |
-
"epoch": 2.77,
|
| 3132 |
-
"learning_rate": 3.034055818754056e-07,
|
| 3133 |
-
"loss": 0.0269,
|
| 3134 |
-
"step": 521
|
| 3135 |
-
},
|
| 3136 |
-
{
|
| 3137 |
-
"epoch": 2.78,
|
| 3138 |
-
"learning_rate": 2.8952549258465356e-07,
|
| 3139 |
-
"loss": 0.0404,
|
| 3140 |
-
"step": 522
|
| 3141 |
-
},
|
| 3142 |
-
{
|
| 3143 |
-
"epoch": 2.78,
|
| 3144 |
-
"learning_rate": 2.759657087609624e-07,
|
| 3145 |
-
"loss": 0.0344,
|
| 3146 |
-
"step": 523
|
| 3147 |
-
},
|
| 3148 |
-
{
|
| 3149 |
-
"epoch": 2.79,
|
| 3150 |
-
"learning_rate": 2.6272667768143413e-07,
|
| 3151 |
-
"loss": 0.0375,
|
| 3152 |
-
"step": 524
|
| 3153 |
-
},
|
| 3154 |
-
{
|
| 3155 |
-
"epoch": 2.79,
|
| 3156 |
-
"learning_rate": 2.498088360429607e-07,
|
| 3157 |
-
"loss": 0.0464,
|
| 3158 |
-
"step": 525
|
| 3159 |
-
},
|
| 3160 |
-
{
|
| 3161 |
-
"epoch": 2.8,
|
| 3162 |
-
"learning_rate": 2.372126099478178e-07,
|
| 3163 |
-
"loss": 0.0409,
|
| 3164 |
-
"step": 526
|
| 3165 |
-
},
|
| 3166 |
-
{
|
| 3167 |
-
"epoch": 2.8,
|
| 3168 |
-
"learning_rate": 2.2493841488961387e-07,
|
| 3169 |
-
"loss": 0.0319,
|
| 3170 |
-
"step": 527
|
| 3171 |
-
},
|
| 3172 |
-
{
|
| 3173 |
-
"epoch": 2.81,
|
| 3174 |
-
"learning_rate": 2.12986655739581e-07,
|
| 3175 |
-
"loss": 0.039,
|
| 3176 |
-
"step": 528
|
| 3177 |
-
},
|
| 3178 |
-
{
|
| 3179 |
-
"epoch": 2.81,
|
| 3180 |
-
"learning_rate": 2.013577267332223e-07,
|
| 3181 |
-
"loss": 0.0386,
|
| 3182 |
-
"step": 529
|
| 3183 |
-
},
|
| 3184 |
-
{
|
| 3185 |
-
"epoch": 2.82,
|
| 3186 |
-
"learning_rate": 1.9005201145730568e-07,
|
| 3187 |
-
"loss": 0.0355,
|
| 3188 |
-
"step": 530
|
| 3189 |
-
},
|
| 3190 |
-
{
|
| 3191 |
-
"epoch": 2.82,
|
| 3192 |
-
"learning_rate": 1.7906988283721173e-07,
|
| 3193 |
-
"loss": 0.0299,
|
| 3194 |
-
"step": 531
|
| 3195 |
-
},
|
| 3196 |
-
{
|
| 3197 |
-
"epoch": 2.83,
|
| 3198 |
-
"learning_rate": 1.6841170312463684e-07,
|
| 3199 |
-
"loss": 0.041,
|
| 3200 |
-
"step": 532
|
| 3201 |
-
},
|
| 3202 |
-
{
|
| 3203 |
-
"epoch": 2.84,
|
| 3204 |
-
"learning_rate": 1.5807782388563509e-07,
|
| 3205 |
-
"loss": 0.0355,
|
| 3206 |
-
"step": 533
|
| 3207 |
-
},
|
| 3208 |
-
{
|
| 3209 |
-
"epoch": 2.84,
|
| 3210 |
-
"learning_rate": 1.4806858598903075e-07,
|
| 3211 |
-
"loss": 0.0307,
|
| 3212 |
-
"step": 534
|
| 3213 |
-
},
|
| 3214 |
-
{
|
| 3215 |
-
"epoch": 2.85,
|
| 3216 |
-
"learning_rate": 1.3838431959516952e-07,
|
| 3217 |
-
"loss": 0.0478,
|
| 3218 |
-
"step": 535
|
| 3219 |
-
},
|
| 3220 |
-
{
|
| 3221 |
-
"epoch": 2.85,
|
| 3222 |
-
"learning_rate": 1.2902534414502843e-07,
|
| 3223 |
-
"loss": 0.0248,
|
| 3224 |
-
"step": 536
|
| 3225 |
-
},
|
| 3226 |
-
{
|
| 3227 |
-
"epoch": 2.86,
|
| 3228 |
-
"learning_rate": 1.1999196834968085e-07,
|
| 3229 |
-
"loss": 0.0314,
|
| 3230 |
-
"step": 537
|
| 3231 |
-
},
|
| 3232 |
-
{
|
| 3233 |
-
"epoch": 2.86,
|
| 3234 |
-
"learning_rate": 1.1128449018011134e-07,
|
| 3235 |
-
"loss": 0.0403,
|
| 3236 |
-
"step": 538
|
| 3237 |
-
},
|
| 3238 |
-
{
|
| 3239 |
-
"epoch": 2.87,
|
| 3240 |
-
"learning_rate": 1.0290319685738793e-07,
|
| 3241 |
-
"loss": 0.0344,
|
| 3242 |
-
"step": 539
|
| 3243 |
-
},
|
| 3244 |
-
{
|
| 3245 |
-
"epoch": 2.87,
|
| 3246 |
-
"learning_rate": 9.484836484318971e-08,
|
| 3247 |
-
"loss": 0.0341,
|
| 3248 |
-
"step": 540
|
| 3249 |
-
},
|
| 3250 |
-
{
|
| 3251 |
-
"epoch": 2.88,
|
| 3252 |
-
"learning_rate": 8.712025983068196e-08,
|
| 3253 |
-
"loss": 0.0358,
|
| 3254 |
-
"step": 541
|
| 3255 |
-
},
|
| 3256 |
-
{
|
| 3257 |
-
"epoch": 2.88,
|
| 3258 |
-
"learning_rate": 7.97191367357597e-08,
|
| 3259 |
-
"loss": 0.0414,
|
| 3260 |
-
"step": 542
|
| 3261 |
-
},
|
| 3262 |
-
{
|
| 3263 |
-
"epoch": 2.89,
|
| 3264 |
-
"learning_rate": 7.264523968863458e-08,
|
| 3265 |
-
"loss": 0.0339,
|
| 3266 |
-
"step": 543
|
| 3267 |
-
},
|
| 3268 |
-
{
|
| 3269 |
-
"epoch": 2.89,
|
| 3270 |
-
"learning_rate": 6.589880202578003e-08,
|
| 3271 |
-
"loss": 0.038,
|
| 3272 |
-
"step": 544
|
| 3273 |
-
},
|
| 3274 |
-
{
|
| 3275 |
-
"epoch": 2.9,
|
| 3276 |
-
"learning_rate": 5.948004628224091e-08,
|
| 3277 |
-
"loss": 0.0414,
|
| 3278 |
-
"step": 545
|
| 3279 |
-
},
|
| 3280 |
-
{
|
| 3281 |
-
"epoch": 2.9,
|
| 3282 |
-
"learning_rate": 5.338918418428929e-08,
|
| 3283 |
-
"loss": 0.0441,
|
| 3284 |
-
"step": 546
|
| 3285 |
-
},
|
| 3286 |
-
{
|
| 3287 |
-
"epoch": 2.91,
|
| 3288 |
-
"learning_rate": 4.7626416642436724e-08,
|
| 3289 |
-
"loss": 0.0348,
|
| 3290 |
-
"step": 547
|
| 3291 |
-
},
|
| 3292 |
-
{
|
| 3293 |
-
"epoch": 2.91,
|
| 3294 |
-
"learning_rate": 4.2191933744815116e-08,
|
| 3295 |
-
"loss": 0.0346,
|
| 3296 |
-
"step": 548
|
| 3297 |
-
},
|
| 3298 |
-
{
|
| 3299 |
-
"epoch": 2.92,
|
| 3300 |
-
"learning_rate": 3.708591475090284e-08,
|
| 3301 |
-
"loss": 0.0418,
|
| 3302 |
-
"step": 549
|
| 3303 |
-
},
|
| 3304 |
-
{
|
| 3305 |
-
"epoch": 2.93,
|
| 3306 |
-
"learning_rate": 3.230852808561058e-08,
|
| 3307 |
-
"loss": 0.0399,
|
| 3308 |
-
"step": 550
|
| 3309 |
-
},
|
| 3310 |
-
{
|
| 3311 |
-
"epoch": 2.93,
|
| 3312 |
-
"learning_rate": 2.7859931333723557e-08,
|
| 3313 |
-
"loss": 0.0279,
|
| 3314 |
-
"step": 551
|
| 3315 |
-
},
|
| 3316 |
-
{
|
| 3317 |
-
"epoch": 2.94,
|
| 3318 |
-
"learning_rate": 2.3740271234712343e-08,
|
| 3319 |
-
"loss": 0.0445,
|
| 3320 |
-
"step": 552
|
| 3321 |
-
},
|
| 3322 |
-
{
|
| 3323 |
-
"epoch": 2.94,
|
| 3324 |
-
"learning_rate": 1.9949683677882302e-08,
|
| 3325 |
-
"loss": 0.0381,
|
| 3326 |
-
"step": 553
|
| 3327 |
-
},
|
| 3328 |
-
{
|
| 3329 |
-
"epoch": 2.95,
|
| 3330 |
-
"learning_rate": 1.6488293697898284e-08,
|
| 3331 |
-
"loss": 0.0321,
|
| 3332 |
-
"step": 554
|
| 3333 |
-
},
|
| 3334 |
-
{
|
| 3335 |
-
"epoch": 2.95,
|
| 3336 |
-
"learning_rate": 1.3356215470656797e-08,
|
| 3337 |
-
"loss": 0.0417,
|
| 3338 |
-
"step": 555
|
| 3339 |
-
},
|
| 3340 |
-
{
|
| 3341 |
-
"epoch": 2.96,
|
| 3342 |
-
"learning_rate": 1.0553552309521265e-08,
|
| 3343 |
-
"loss": 0.0329,
|
| 3344 |
-
"step": 556
|
| 3345 |
-
},
|
| 3346 |
-
{
|
| 3347 |
-
"epoch": 2.96,
|
| 3348 |
-
"learning_rate": 8.080396661913626e-09,
|
| 3349 |
-
"loss": 0.0435,
|
| 3350 |
-
"step": 557
|
| 3351 |
-
},
|
| 3352 |
-
{
|
| 3353 |
-
"epoch": 2.97,
|
| 3354 |
-
"learning_rate": 5.936830106263447e-09,
|
| 3355 |
-
"loss": 0.0405,
|
| 3356 |
-
"step": 558
|
| 3357 |
-
},
|
| 3358 |
-
{
|
| 3359 |
-
"epoch": 2.97,
|
| 3360 |
-
"learning_rate": 4.1229233493222945e-09,
|
| 3361 |
-
"loss": 0.0302,
|
| 3362 |
-
"step": 559
|
| 3363 |
-
},
|
| 3364 |
-
{
|
| 3365 |
-
"epoch": 2.98,
|
| 3366 |
-
"learning_rate": 2.6387362238233794e-09,
|
| 3367 |
-
"loss": 0.0311,
|
| 3368 |
-
"step": 560
|
| 3369 |
-
},
|
| 3370 |
-
{
|
| 3371 |
-
"epoch": 2.98,
|
| 3372 |
-
"learning_rate": 1.4843176865153575e-09,
|
| 3373 |
-
"loss": 0.0425,
|
| 3374 |
-
"step": 561
|
| 3375 |
-
},
|
| 3376 |
-
{
|
| 3377 |
-
"epoch": 2.99,
|
| 3378 |
-
"learning_rate": 6.597058165436209e-10,
|
| 3379 |
-
"loss": 0.0497,
|
| 3380 |
-
"step": 562
|
| 3381 |
-
},
|
| 3382 |
-
{
|
| 3383 |
-
"epoch": 2.99,
|
| 3384 |
-
"learning_rate": 1.6492781419574778e-10,
|
| 3385 |
-
"loss": 0.0391,
|
| 3386 |
-
"step": 563
|
| 3387 |
-
},
|
| 3388 |
-
{
|
| 3389 |
-
"epoch": 3.0,
|
| 3390 |
-
"learning_rate": 0.0,
|
| 3391 |
-
"loss": 0.0382,
|
| 3392 |
-
"step": 564
|
| 3393 |
-
},
|
| 3394 |
-
{
|
| 3395 |
-
"epoch": 3.0,
|
| 3396 |
-
"step": 564,
|
| 3397 |
-
"total_flos": 30619220115456.0,
|
| 3398 |
-
"train_loss": 0.07966609711342669,
|
| 3399 |
-
"train_runtime": 1503.8031,
|
| 3400 |
-
"train_samples_per_second": 47.926,
|
| 3401 |
-
"train_steps_per_second": 0.375
|
| 3402 |
}
|
| 3403 |
],
|
| 3404 |
"max_steps": 564,
|
| 3405 |
"num_train_epochs": 3,
|
| 3406 |
-
"total_flos":
|
| 3407 |
"trial_name": null,
|
| 3408 |
"trial_params": null
|
| 3409 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 376,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 10 |
{
|
| 11 |
"epoch": 0.01,
|
| 12 |
"learning_rate": 1.1764705882352942e-06,
|
| 13 |
+
"loss": 1.3193,
|
| 14 |
"step": 1
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.01,
|
| 18 |
"learning_rate": 2.3529411764705885e-06,
|
| 19 |
+
"loss": 1.2891,
|
| 20 |
"step": 2
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.02,
|
| 24 |
"learning_rate": 3.529411764705883e-06,
|
| 25 |
+
"loss": 1.3105,
|
| 26 |
"step": 3
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.02,
|
| 30 |
"learning_rate": 4.705882352941177e-06,
|
| 31 |
+
"loss": 1.2383,
|
| 32 |
"step": 4
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.03,
|
| 36 |
"learning_rate": 5.882352941176471e-06,
|
| 37 |
+
"loss": 0.8359,
|
| 38 |
"step": 5
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.03,
|
| 42 |
"learning_rate": 7.058823529411766e-06,
|
| 43 |
+
"loss": 0.49,
|
| 44 |
"step": 6
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.04,
|
| 48 |
"learning_rate": 8.23529411764706e-06,
|
| 49 |
+
"loss": 0.1881,
|
| 50 |
"step": 7
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.04,
|
| 54 |
"learning_rate": 9.411764705882354e-06,
|
| 55 |
+
"loss": 0.2035,
|
| 56 |
"step": 8
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.05,
|
| 60 |
"learning_rate": 1.0588235294117648e-05,
|
| 61 |
+
"loss": 0.1893,
|
| 62 |
"step": 9
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 0.05,
|
| 66 |
"learning_rate": 1.1764705882352942e-05,
|
| 67 |
+
"loss": 0.2448,
|
| 68 |
"step": 10
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 0.06,
|
| 72 |
"learning_rate": 1.2941176470588238e-05,
|
| 73 |
+
"loss": 0.1973,
|
| 74 |
"step": 11
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.06,
|
| 78 |
"learning_rate": 1.4117647058823532e-05,
|
| 79 |
+
"loss": 0.2133,
|
| 80 |
"step": 12
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.07,
|
| 84 |
"learning_rate": 1.5294117647058822e-05,
|
| 85 |
+
"loss": 0.2087,
|
| 86 |
"step": 13
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.07,
|
| 90 |
"learning_rate": 1.647058823529412e-05,
|
| 91 |
+
"loss": 0.2408,
|
| 92 |
"step": 14
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 0.08,
|
| 96 |
"learning_rate": 1.7647058823529414e-05,
|
| 97 |
+
"loss": 0.1686,
|
| 98 |
"step": 15
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 0.09,
|
| 102 |
"learning_rate": 1.8823529411764708e-05,
|
| 103 |
+
"loss": 0.1917,
|
| 104 |
"step": 16
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 0.09,
|
| 108 |
"learning_rate": 2e-05,
|
| 109 |
+
"loss": 0.2241,
|
| 110 |
"step": 17
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 0.1,
|
| 114 |
"learning_rate": 1.9999835072185805e-05,
|
| 115 |
+
"loss": 0.2195,
|
| 116 |
"step": 18
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 0.1,
|
| 120 |
"learning_rate": 1.999934029418346e-05,
|
| 121 |
+
"loss": 0.1847,
|
| 122 |
"step": 19
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.11,
|
| 126 |
"learning_rate": 1.9998515682313485e-05,
|
| 127 |
+
"loss": 0.1765,
|
| 128 |
"step": 20
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.11,
|
| 132 |
"learning_rate": 1.999736126377618e-05,
|
| 133 |
+
"loss": 0.1572,
|
| 134 |
"step": 21
|
| 135 |
},
|
| 136 |
{
|
| 137 |
"epoch": 0.12,
|
| 138 |
"learning_rate": 1.999587707665068e-05,
|
| 139 |
+
"loss": 0.1677,
|
| 140 |
"step": 22
|
| 141 |
},
|
| 142 |
{
|
| 143 |
"epoch": 0.12,
|
| 144 |
"learning_rate": 1.999406316989374e-05,
|
| 145 |
+
"loss": 0.1906,
|
| 146 |
"step": 23
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 0.13,
|
| 150 |
"learning_rate": 1.9991919603338088e-05,
|
| 151 |
+
"loss": 0.153,
|
| 152 |
"step": 24
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 0.13,
|
| 156 |
"learning_rate": 1.998944644769048e-05,
|
| 157 |
+
"loss": 0.1473,
|
| 158 |
"step": 25
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 0.14,
|
| 162 |
"learning_rate": 1.9986643784529346e-05,
|
| 163 |
+
"loss": 0.1345,
|
| 164 |
"step": 26
|
| 165 |
},
|
| 166 |
{
|
| 167 |
"epoch": 0.14,
|
| 168 |
"learning_rate": 1.9983511706302102e-05,
|
| 169 |
+
"loss": 0.1476,
|
| 170 |
"step": 27
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.15,
|
| 174 |
"learning_rate": 1.9980050316322118e-05,
|
| 175 |
+
"loss": 0.1219,
|
| 176 |
"step": 28
|
| 177 |
},
|
| 178 |
{
|
| 179 |
"epoch": 0.15,
|
| 180 |
"learning_rate": 1.997625972876529e-05,
|
| 181 |
+
"loss": 0.1336,
|
| 182 |
"step": 29
|
| 183 |
},
|
| 184 |
{
|
| 185 |
"epoch": 0.16,
|
| 186 |
"learning_rate": 1.997214006866628e-05,
|
| 187 |
+
"loss": 0.1133,
|
| 188 |
"step": 30
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 0.16,
|
| 192 |
"learning_rate": 1.9967691471914392e-05,
|
| 193 |
+
"loss": 0.1424,
|
| 194 |
"step": 31
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 0.17,
|
| 198 |
"learning_rate": 1.99629140852491e-05,
|
| 199 |
+
"loss": 0.123,
|
| 200 |
"step": 32
|
| 201 |
},
|
| 202 |
{
|
| 203 |
"epoch": 0.18,
|
| 204 |
"learning_rate": 1.9957808066255187e-05,
|
| 205 |
+
"loss": 0.1199,
|
| 206 |
"step": 33
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 0.18,
|
| 210 |
"learning_rate": 1.9952373583357566e-05,
|
| 211 |
+
"loss": 0.1308,
|
| 212 |
"step": 34
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 0.19,
|
| 216 |
"learning_rate": 1.994661081581571e-05,
|
| 217 |
+
"loss": 0.1172,
|
| 218 |
"step": 35
|
| 219 |
},
|
| 220 |
{
|
| 221 |
"epoch": 0.19,
|
| 222 |
"learning_rate": 1.9940519953717762e-05,
|
| 223 |
+
"loss": 0.1299,
|
| 224 |
"step": 36
|
| 225 |
},
|
| 226 |
{
|
| 227 |
"epoch": 0.2,
|
| 228 |
"learning_rate": 1.993410119797422e-05,
|
| 229 |
+
"loss": 0.1358,
|
| 230 |
"step": 37
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 0.2,
|
| 234 |
"learning_rate": 1.9927354760311365e-05,
|
| 235 |
+
"loss": 0.121,
|
| 236 |
"step": 38
|
| 237 |
},
|
| 238 |
{
|
| 239 |
"epoch": 0.21,
|
| 240 |
"learning_rate": 1.992028086326424e-05,
|
| 241 |
+
"loss": 0.1273,
|
| 242 |
"step": 39
|
| 243 |
},
|
| 244 |
{
|
| 245 |
"epoch": 0.21,
|
| 246 |
"learning_rate": 1.991287974016932e-05,
|
| 247 |
+
"loss": 0.1215,
|
| 248 |
"step": 40
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 0.22,
|
| 252 |
"learning_rate": 1.9905151635156813e-05,
|
| 253 |
+
"loss": 0.1239,
|
| 254 |
"step": 41
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 0.22,
|
| 258 |
"learning_rate": 1.9897096803142616e-05,
|
| 259 |
+
"loss": 0.1178,
|
| 260 |
"step": 42
|
| 261 |
},
|
| 262 |
{
|
| 263 |
"epoch": 0.23,
|
| 264 |
"learning_rate": 1.988871550981989e-05,
|
| 265 |
+
"loss": 0.1135,
|
| 266 |
"step": 43
|
| 267 |
},
|
| 268 |
{
|
| 269 |
"epoch": 0.23,
|
| 270 |
"learning_rate": 1.988000803165032e-05,
|
| 271 |
+
"loss": 0.1103,
|
| 272 |
"step": 44
|
| 273 |
},
|
| 274 |
{
|
| 275 |
"epoch": 0.24,
|
| 276 |
"learning_rate": 1.9870974655854974e-05,
|
| 277 |
+
"loss": 0.124,
|
| 278 |
"step": 45
|
| 279 |
},
|
| 280 |
{
|
| 281 |
"epoch": 0.24,
|
| 282 |
"learning_rate": 1.9861615680404833e-05,
|
| 283 |
+
"loss": 0.1031,
|
| 284 |
"step": 46
|
| 285 |
},
|
| 286 |
{
|
| 287 |
"epoch": 0.25,
|
| 288 |
"learning_rate": 1.985193141401097e-05,
|
| 289 |
+
"loss": 0.1032,
|
| 290 |
"step": 47
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 0.26,
|
| 294 |
"learning_rate": 1.9841922176114366e-05,
|
| 295 |
+
"loss": 0.1151,
|
| 296 |
"step": 48
|
| 297 |
},
|
| 298 |
{
|
| 299 |
"epoch": 0.26,
|
| 300 |
"learning_rate": 1.9831588296875367e-05,
|
| 301 |
+
"loss": 0.1061,
|
| 302 |
"step": 49
|
| 303 |
},
|
| 304 |
{
|
| 305 |
"epoch": 0.27,
|
| 306 |
"learning_rate": 1.982093011716279e-05,
|
| 307 |
+
"loss": 0.1019,
|
| 308 |
"step": 50
|
| 309 |
},
|
| 310 |
{
|
| 311 |
"epoch": 0.27,
|
| 312 |
"learning_rate": 1.9809947988542696e-05,
|
| 313 |
+
"loss": 0.1004,
|
| 314 |
"step": 51
|
| 315 |
},
|
| 316 |
{
|
| 317 |
"epoch": 0.28,
|
| 318 |
"learning_rate": 1.979864227326678e-05,
|
| 319 |
+
"loss": 0.0971,
|
| 320 |
"step": 52
|
| 321 |
},
|
| 322 |
{
|
| 323 |
"epoch": 0.28,
|
| 324 |
"learning_rate": 1.9787013344260422e-05,
|
| 325 |
+
"loss": 0.1137,
|
| 326 |
"step": 53
|
| 327 |
},
|
| 328 |
{
|
| 329 |
"epoch": 0.29,
|
| 330 |
"learning_rate": 1.9775061585110387e-05,
|
| 331 |
+
"loss": 0.1052,
|
| 332 |
"step": 54
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 0.29,
|
| 336 |
"learning_rate": 1.976278739005218e-05,
|
| 337 |
+
"loss": 0.1034,
|
| 338 |
"step": 55
|
| 339 |
},
|
| 340 |
{
|
| 341 |
"epoch": 0.3,
|
| 342 |
"learning_rate": 1.9750191163957042e-05,
|
| 343 |
+
"loss": 0.0911,
|
| 344 |
"step": 56
|
| 345 |
},
|
| 346 |
{
|
| 347 |
"epoch": 0.3,
|
| 348 |
"learning_rate": 1.9737273322318565e-05,
|
| 349 |
+
"loss": 0.1107,
|
| 350 |
"step": 57
|
| 351 |
},
|
| 352 |
{
|
| 353 |
"epoch": 0.31,
|
| 354 |
"learning_rate": 1.972403429123904e-05,
|
| 355 |
+
"loss": 0.1055,
|
| 356 |
"step": 58
|
| 357 |
},
|
| 358 |
{
|
| 359 |
"epoch": 0.31,
|
| 360 |
"learning_rate": 1.971047450741535e-05,
|
| 361 |
+
"loss": 0.106,
|
| 362 |
"step": 59
|
| 363 |
},
|
| 364 |
{
|
| 365 |
"epoch": 0.32,
|
| 366 |
"learning_rate": 1.9696594418124598e-05,
|
| 367 |
+
"loss": 0.0934,
|
| 368 |
"step": 60
|
| 369 |
},
|
| 370 |
{
|
| 371 |
"epoch": 0.32,
|
| 372 |
"learning_rate": 1.9682394481209338e-05,
|
| 373 |
+
"loss": 0.0986,
|
| 374 |
"step": 61
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 0.33,
|
| 378 |
"learning_rate": 1.966787516506249e-05,
|
| 379 |
+
"loss": 0.1112,
|
| 380 |
"step": 62
|
| 381 |
},
|
| 382 |
{
|
| 383 |
"epoch": 0.34,
|
| 384 |
"learning_rate": 1.9653036948611864e-05,
|
| 385 |
+
"loss": 0.1075,
|
| 386 |
"step": 63
|
| 387 |
},
|
| 388 |
{
|
| 389 |
"epoch": 0.34,
|
| 390 |
"learning_rate": 1.9637880321304387e-05,
|
| 391 |
+
"loss": 0.1089,
|
| 392 |
"step": 64
|
| 393 |
},
|
| 394 |
{
|
| 395 |
"epoch": 0.35,
|
| 396 |
"learning_rate": 1.962240578308993e-05,
|
| 397 |
+
"loss": 0.0972,
|
| 398 |
"step": 65
|
| 399 |
},
|
| 400 |
{
|
| 401 |
"epoch": 0.35,
|
| 402 |
"learning_rate": 1.9606613844404853e-05,
|
| 403 |
+
"loss": 0.0898,
|
| 404 |
"step": 66
|
| 405 |
},
|
| 406 |
{
|
| 407 |
"epoch": 0.36,
|
| 408 |
"learning_rate": 1.9590505026155146e-05,
|
| 409 |
+
"loss": 0.088,
|
| 410 |
"step": 67
|
| 411 |
},
|
| 412 |
{
|
| 413 |
"epoch": 0.36,
|
| 414 |
"learning_rate": 1.9574079859699236e-05,
|
| 415 |
+
"loss": 0.1041,
|
| 416 |
"step": 68
|
| 417 |
},
|
| 418 |
{
|
| 419 |
"epoch": 0.37,
|
| 420 |
"learning_rate": 1.955733888683049e-05,
|
| 421 |
+
"loss": 0.1028,
|
| 422 |
"step": 69
|
| 423 |
},
|
| 424 |
{
|
| 425 |
"epoch": 0.37,
|
| 426 |
"learning_rate": 1.9540282659759317e-05,
|
| 427 |
+
"loss": 0.0876,
|
| 428 |
"step": 70
|
| 429 |
},
|
| 430 |
{
|
| 431 |
"epoch": 0.38,
|
| 432 |
"learning_rate": 1.9522911741094966e-05,
|
| 433 |
+
"loss": 0.088,
|
| 434 |
"step": 71
|
| 435 |
},
|
| 436 |
{
|
| 437 |
"epoch": 0.38,
|
| 438 |
"learning_rate": 1.9505226703826973e-05,
|
| 439 |
+
"loss": 0.0905,
|
| 440 |
"step": 72
|
| 441 |
},
|
| 442 |
{
|
| 443 |
"epoch": 0.39,
|
| 444 |
"learning_rate": 1.948722813130624e-05,
|
| 445 |
+
"loss": 0.0945,
|
| 446 |
"step": 73
|
| 447 |
},
|
| 448 |
{
|
| 449 |
"epoch": 0.39,
|
| 450 |
"learning_rate": 1.9468916617225814e-05,
|
| 451 |
+
"loss": 0.0978,
|
| 452 |
"step": 74
|
| 453 |
},
|
| 454 |
{
|
| 455 |
"epoch": 0.4,
|
| 456 |
"learning_rate": 1.9450292765601287e-05,
|
| 457 |
+
"loss": 0.1132,
|
| 458 |
"step": 75
|
| 459 |
},
|
| 460 |
{
|
| 461 |
"epoch": 0.4,
|
| 462 |
"learning_rate": 1.94313571907509e-05,
|
| 463 |
+
"loss": 0.0826,
|
| 464 |
"step": 76
|
| 465 |
},
|
| 466 |
{
|
| 467 |
"epoch": 0.41,
|
| 468 |
"learning_rate": 1.941211051727524e-05,
|
| 469 |
+
"loss": 0.1053,
|
| 470 |
"step": 77
|
| 471 |
},
|
| 472 |
{
|
| 473 |
"epoch": 0.41,
|
| 474 |
"learning_rate": 1.939255338003666e-05,
|
| 475 |
+
"loss": 0.1049,
|
| 476 |
"step": 78
|
| 477 |
},
|
| 478 |
{
|
| 479 |
"epoch": 0.42,
|
| 480 |
"learning_rate": 1.937268642413835e-05,
|
| 481 |
+
"loss": 0.1079,
|
| 482 |
"step": 79
|
| 483 |
},
|
| 484 |
{
|
| 485 |
"epoch": 0.43,
|
| 486 |
"learning_rate": 1.9352510304903017e-05,
|
| 487 |
+
"loss": 0.1078,
|
| 488 |
"step": 80
|
| 489 |
},
|
| 490 |
{
|
| 491 |
"epoch": 0.43,
|
| 492 |
"learning_rate": 1.9332025687851325e-05,
|
| 493 |
+
"loss": 0.0937,
|
| 494 |
"step": 81
|
| 495 |
},
|
| 496 |
{
|
| 497 |
"epoch": 0.44,
|
| 498 |
"learning_rate": 1.931123324867989e-05,
|
| 499 |
+
"loss": 0.0822,
|
| 500 |
"step": 82
|
| 501 |
},
|
| 502 |
{
|
| 503 |
"epoch": 0.44,
|
| 504 |
"learning_rate": 1.929013367323902e-05,
|
| 505 |
+
"loss": 0.1162,
|
| 506 |
"step": 83
|
| 507 |
},
|
| 508 |
{
|
| 509 |
"epoch": 0.45,
|
| 510 |
"learning_rate": 1.926872765751009e-05,
|
| 511 |
+
"loss": 0.0896,
|
| 512 |
"step": 84
|
| 513 |
},
|
| 514 |
{
|
| 515 |
"epoch": 0.45,
|
| 516 |
"learning_rate": 1.9247015907582574e-05,
|
| 517 |
+
"loss": 0.1021,
|
| 518 |
"step": 85
|
| 519 |
},
|
| 520 |
{
|
| 521 |
"epoch": 0.46,
|
| 522 |
"learning_rate": 1.9224999139630766e-05,
|
| 523 |
+
"loss": 0.1036,
|
| 524 |
"step": 86
|
| 525 |
},
|
| 526 |
{
|
| 527 |
"epoch": 0.46,
|
| 528 |
"learning_rate": 1.920267807989015e-05,
|
| 529 |
+
"loss": 0.0952,
|
| 530 |
"step": 87
|
| 531 |
},
|
| 532 |
{
|
| 533 |
"epoch": 0.47,
|
| 534 |
"learning_rate": 1.918005346463344e-05,
|
| 535 |
+
"loss": 0.0869,
|
| 536 |
"step": 88
|
| 537 |
},
|
| 538 |
{
|
| 539 |
"epoch": 0.47,
|
| 540 |
"learning_rate": 1.9157126040146307e-05,
|
| 541 |
+
"loss": 0.0923,
|
| 542 |
"step": 89
|
| 543 |
},
|
| 544 |
{
|
| 545 |
"epoch": 0.48,
|
| 546 |
"learning_rate": 1.9133896562702746e-05,
|
| 547 |
+
"loss": 0.0983,
|
| 548 |
"step": 90
|
| 549 |
},
|
| 550 |
{
|
| 551 |
"epoch": 0.48,
|
| 552 |
"learning_rate": 1.911036579854016e-05,
|
| 553 |
+
"loss": 0.1044,
|
| 554 |
"step": 91
|
| 555 |
},
|
| 556 |
{
|
| 557 |
"epoch": 0.49,
|
| 558 |
"learning_rate": 1.9086534523834032e-05,
|
| 559 |
+
"loss": 0.0901,
|
| 560 |
"step": 92
|
| 561 |
},
|
| 562 |
{
|
| 563 |
"epoch": 0.49,
|
| 564 |
"learning_rate": 1.906240352467238e-05,
|
| 565 |
+
"loss": 0.0774,
|
| 566 |
"step": 93
|
| 567 |
},
|
| 568 |
{
|
| 569 |
"epoch": 0.5,
|
| 570 |
"learning_rate": 1.9037973597029796e-05,
|
| 571 |
+
"loss": 0.0863,
|
| 572 |
"step": 94
|
| 573 |
},
|
| 574 |
{
|
| 575 |
"epoch": 0.51,
|
| 576 |
"learning_rate": 1.901324554674119e-05,
|
| 577 |
+
"loss": 0.0906,
|
| 578 |
"step": 95
|
| 579 |
},
|
| 580 |
{
|
| 581 |
"epoch": 0.51,
|
| 582 |
"learning_rate": 1.8988220189475216e-05,
|
| 583 |
+
"loss": 0.11,
|
| 584 |
"step": 96
|
| 585 |
},
|
| 586 |
{
|
| 587 |
"epoch": 0.52,
|
| 588 |
"learning_rate": 1.896289835070737e-05,
|
| 589 |
+
"loss": 0.1056,
|
| 590 |
"step": 97
|
| 591 |
},
|
| 592 |
{
|
| 593 |
"epoch": 0.52,
|
| 594 |
"learning_rate": 1.893728086569276e-05,
|
| 595 |
+
"loss": 0.0897,
|
| 596 |
"step": 98
|
| 597 |
},
|
| 598 |
{
|
| 599 |
"epoch": 0.53,
|
| 600 |
"learning_rate": 1.891136857943854e-05,
|
| 601 |
+
"loss": 0.0954,
|
| 602 |
"step": 99
|
| 603 |
},
|
| 604 |
{
|
| 605 |
"epoch": 0.53,
|
| 606 |
"learning_rate": 1.8885162346676063e-05,
|
| 607 |
+
"loss": 0.095,
|
| 608 |
"step": 100
|
| 609 |
},
|
| 610 |
{
|
| 611 |
"epoch": 0.54,
|
| 612 |
"learning_rate": 1.8858663031832665e-05,
|
| 613 |
+
"loss": 0.0786,
|
| 614 |
"step": 101
|
| 615 |
},
|
| 616 |
{
|
| 617 |
"epoch": 0.54,
|
| 618 |
"learning_rate": 1.8831871509003164e-05,
|
| 619 |
+
"loss": 0.0933,
|
| 620 |
"step": 102
|
| 621 |
},
|
| 622 |
{
|
| 623 |
"epoch": 0.55,
|
| 624 |
"learning_rate": 1.8804788661921012e-05,
|
| 625 |
+
"loss": 0.0833,
|
| 626 |
"step": 103
|
| 627 |
},
|
| 628 |
{
|
| 629 |
"epoch": 0.55,
|
| 630 |
"learning_rate": 1.877741538392917e-05,
|
| 631 |
+
"loss": 0.0784,
|
| 632 |
"step": 104
|
| 633 |
},
|
| 634 |
{
|
| 635 |
"epoch": 0.56,
|
| 636 |
"learning_rate": 1.8749752577950614e-05,
|
| 637 |
+
"loss": 0.0851,
|
| 638 |
"step": 105
|
| 639 |
},
|
| 640 |
{
|
| 641 |
"epoch": 0.56,
|
| 642 |
"learning_rate": 1.8721801156458573e-05,
|
| 643 |
+
"loss": 0.0891,
|
| 644 |
"step": 106
|
| 645 |
},
|
| 646 |
{
|
| 647 |
"epoch": 0.57,
|
| 648 |
"learning_rate": 1.869356204144642e-05,
|
| 649 |
+
"loss": 0.0812,
|
| 650 |
"step": 107
|
| 651 |
},
|
| 652 |
{
|
| 653 |
"epoch": 0.57,
|
| 654 |
"learning_rate": 1.866503616439725e-05,
|
| 655 |
+
"loss": 0.1109,
|
| 656 |
"step": 108
|
| 657 |
},
|
| 658 |
{
|
| 659 |
"epoch": 0.58,
|
| 660 |
"learning_rate": 1.8636224466253177e-05,
|
| 661 |
+
"loss": 0.0948,
|
| 662 |
"step": 109
|
| 663 |
},
|
| 664 |
{
|
| 665 |
"epoch": 0.59,
|
| 666 |
"learning_rate": 1.860712789738428e-05,
|
| 667 |
+
"loss": 0.0933,
|
| 668 |
"step": 110
|
| 669 |
},
|
| 670 |
{
|
| 671 |
"epoch": 0.59,
|
| 672 |
"learning_rate": 1.857774741755726e-05,
|
| 673 |
+
"loss": 0.0872,
|
| 674 |
"step": 111
|
| 675 |
},
|
| 676 |
{
|
| 677 |
"epoch": 0.6,
|
| 678 |
"learning_rate": 1.854808399590378e-05,
|
| 679 |
+
"loss": 0.0995,
|
| 680 |
"step": 112
|
| 681 |
},
|
| 682 |
{
|
| 683 |
"epoch": 0.6,
|
| 684 |
"learning_rate": 1.8518138610888505e-05,
|
| 685 |
+
"loss": 0.0862,
|
| 686 |
"step": 113
|
| 687 |
},
|
| 688 |
{
|
| 689 |
"epoch": 0.61,
|
| 690 |
"learning_rate": 1.8487912250276805e-05,
|
| 691 |
+
"loss": 0.0716,
|
| 692 |
"step": 114
|
| 693 |
},
|
| 694 |
{
|
| 695 |
"epoch": 0.61,
|
| 696 |
"learning_rate": 1.8457405911102202e-05,
|
| 697 |
+
"loss": 0.0977,
|
| 698 |
"step": 115
|
| 699 |
},
|
| 700 |
{
|
| 701 |
"epoch": 0.62,
|
| 702 |
"learning_rate": 1.8426620599633464e-05,
|
| 703 |
+
"loss": 0.0782,
|
| 704 |
"step": 116
|
| 705 |
},
|
| 706 |
{
|
| 707 |
"epoch": 0.62,
|
| 708 |
"learning_rate": 1.8395557331341413e-05,
|
| 709 |
+
"loss": 0.0891,
|
| 710 |
"step": 117
|
| 711 |
},
|
| 712 |
{
|
| 713 |
"epoch": 0.63,
|
| 714 |
"learning_rate": 1.836421713086544e-05,
|
| 715 |
+
"loss": 0.096,
|
| 716 |
"step": 118
|
| 717 |
},
|
| 718 |
{
|
| 719 |
"epoch": 0.63,
|
| 720 |
"learning_rate": 1.83326010319797e-05,
|
| 721 |
+
"loss": 0.0912,
|
| 722 |
"step": 119
|
| 723 |
},
|
| 724 |
{
|
| 725 |
"epoch": 0.64,
|
| 726 |
"learning_rate": 1.830071007755901e-05,
|
| 727 |
+
"loss": 0.0807,
|
| 728 |
"step": 120
|
| 729 |
},
|
| 730 |
{
|
| 731 |
"epoch": 0.64,
|
| 732 |
"learning_rate": 1.8268545319544443e-05,
|
| 733 |
+
"loss": 0.092,
|
| 734 |
"step": 121
|
| 735 |
},
|
| 736 |
{
|
| 737 |
"epoch": 0.65,
|
| 738 |
"learning_rate": 1.823610781890865e-05,
|
| 739 |
+
"loss": 0.0931,
|
| 740 |
"step": 122
|
| 741 |
},
|
| 742 |
{
|
| 743 |
"epoch": 0.65,
|
| 744 |
"learning_rate": 1.820339864562085e-05,
|
| 745 |
+
"loss": 0.0859,
|
| 746 |
"step": 123
|
| 747 |
},
|
| 748 |
{
|
| 749 |
"epoch": 0.66,
|
| 750 |
"learning_rate": 1.817041887861153e-05,
|
| 751 |
+
"loss": 0.089,
|
| 752 |
"step": 124
|
| 753 |
},
|
| 754 |
{
|
| 755 |
"epoch": 0.66,
|
| 756 |
"learning_rate": 1.8137169605736867e-05,
|
| 757 |
+
"loss": 0.0991,
|
| 758 |
"step": 125
|
| 759 |
},
|
| 760 |
{
|
| 761 |
"epoch": 0.67,
|
| 762 |
"learning_rate": 1.8103651923742846e-05,
|
| 763 |
+
"loss": 0.0741,
|
| 764 |
"step": 126
|
| 765 |
},
|
| 766 |
{
|
| 767 |
"epoch": 0.68,
|
| 768 |
"learning_rate": 1.8069866938229066e-05,
|
| 769 |
+
"loss": 0.087,
|
| 770 |
"step": 127
|
| 771 |
},
|
| 772 |
{
|
| 773 |
"epoch": 0.68,
|
| 774 |
"learning_rate": 1.8035815763612293e-05,
|
| 775 |
+
"loss": 0.0969,
|
| 776 |
"step": 128
|
| 777 |
},
|
| 778 |
{
|
| 779 |
"epoch": 0.69,
|
| 780 |
"learning_rate": 1.8001499523089683e-05,
|
| 781 |
+
"loss": 0.071,
|
| 782 |
"step": 129
|
| 783 |
},
|
| 784 |
{
|
| 785 |
"epoch": 0.69,
|
| 786 |
"learning_rate": 1.7966919348601754e-05,
|
| 787 |
+
"loss": 0.0804,
|
| 788 |
"step": 130
|
| 789 |
},
|
| 790 |
{
|
| 791 |
"epoch": 0.7,
|
| 792 |
"learning_rate": 1.7932076380795017e-05,
|
| 793 |
+
"loss": 0.0895,
|
| 794 |
"step": 131
|
| 795 |
},
|
| 796 |
{
|
| 797 |
"epoch": 0.7,
|
| 798 |
"learning_rate": 1.7896971768984373e-05,
|
| 799 |
+
"loss": 0.085,
|
| 800 |
"step": 132
|
| 801 |
},
|
| 802 |
{
|
| 803 |
"epoch": 0.71,
|
| 804 |
"learning_rate": 1.7861606671115207e-05,
|
| 805 |
+
"loss": 0.1048,
|
| 806 |
"step": 133
|
| 807 |
},
|
| 808 |
{
|
| 809 |
"epoch": 0.71,
|
| 810 |
"learning_rate": 1.7825982253725175e-05,
|
| 811 |
+
"loss": 0.0858,
|
| 812 |
"step": 134
|
| 813 |
},
|
| 814 |
{
|
| 815 |
"epoch": 0.72,
|
| 816 |
"learning_rate": 1.7790099691905736e-05,
|
| 817 |
+
"loss": 0.1055,
|
| 818 |
"step": 135
|
| 819 |
},
|
| 820 |
{
|
| 821 |
"epoch": 0.72,
|
| 822 |
"learning_rate": 1.7753960169263387e-05,
|
| 823 |
+
"loss": 0.0835,
|
| 824 |
"step": 136
|
| 825 |
},
|
| 826 |
{
|
| 827 |
"epoch": 0.73,
|
| 828 |
"learning_rate": 1.7717564877880623e-05,
|
| 829 |
+
"loss": 0.0967,
|
| 830 |
"step": 137
|
| 831 |
},
|
| 832 |
{
|
| 833 |
"epoch": 0.73,
|
| 834 |
"learning_rate": 1.7680915018276613e-05,
|
| 835 |
+
"loss": 0.0972,
|
| 836 |
"step": 138
|
| 837 |
},
|
| 838 |
{
|
| 839 |
"epoch": 0.74,
|
| 840 |
"learning_rate": 1.764401179936761e-05,
|
| 841 |
+
"loss": 0.0823,
|
| 842 |
"step": 139
|
| 843 |
},
|
| 844 |
{
|
| 845 |
"epoch": 0.74,
|
| 846 |
"learning_rate": 1.7606856438427054e-05,
|
| 847 |
+
"loss": 0.0803,
|
| 848 |
"step": 140
|
| 849 |
},
|
| 850 |
{
|
| 851 |
"epoch": 0.75,
|
| 852 |
"learning_rate": 1.7569450161045444e-05,
|
| 853 |
+
"loss": 0.0926,
|
| 854 |
"step": 141
|
| 855 |
},
|
| 856 |
{
|
| 857 |
"epoch": 0.76,
|
| 858 |
"learning_rate": 1.7531794201089888e-05,
|
| 859 |
+
"loss": 0.11,
|
| 860 |
"step": 142
|
| 861 |
},
|
| 862 |
{
|
| 863 |
"epoch": 0.76,
|
| 864 |
"learning_rate": 1.749388980066342e-05,
|
| 865 |
+
"loss": 0.0889,
|
| 866 |
"step": 143
|
| 867 |
},
|
| 868 |
{
|
| 869 |
"epoch": 0.77,
|
| 870 |
"learning_rate": 1.745573821006403e-05,
|
| 871 |
+
"loss": 0.093,
|
| 872 |
"step": 144
|
| 873 |
},
|
| 874 |
{
|
| 875 |
"epoch": 0.77,
|
| 876 |
"learning_rate": 1.7417340687743393e-05,
|
| 877 |
+
"loss": 0.0857,
|
| 878 |
"step": 145
|
| 879 |
},
|
| 880 |
{
|
| 881 |
"epoch": 0.78,
|
| 882 |
"learning_rate": 1.7378698500265402e-05,
|
| 883 |
+
"loss": 0.0871,
|
| 884 |
"step": 146
|
| 885 |
},
|
| 886 |
{
|
| 887 |
"epoch": 0.78,
|
| 888 |
"learning_rate": 1.7339812922264366e-05,
|
| 889 |
+
"loss": 0.0911,
|
| 890 |
"step": 147
|
| 891 |
},
|
| 892 |
{
|
| 893 |
"epoch": 0.79,
|
| 894 |
"learning_rate": 1.730068523640295e-05,
|
| 895 |
+
"loss": 0.0938,
|
| 896 |
"step": 148
|
| 897 |
},
|
| 898 |
{
|
| 899 |
"epoch": 0.79,
|
| 900 |
"learning_rate": 1.72613167333299e-05,
|
| 901 |
+
"loss": 0.0883,
|
| 902 |
"step": 149
|
| 903 |
},
|
| 904 |
{
|
| 905 |
"epoch": 0.8,
|
| 906 |
"learning_rate": 1.7221708711637455e-05,
|
| 907 |
+
"loss": 0.0897,
|
| 908 |
"step": 150
|
| 909 |
},
|
| 910 |
{
|
| 911 |
"epoch": 0.8,
|
| 912 |
"learning_rate": 1.718186247781849e-05,
|
| 913 |
+
"loss": 0.0814,
|
| 914 |
"step": 151
|
| 915 |
},
|
| 916 |
{
|
| 917 |
"epoch": 0.81,
|
| 918 |
"learning_rate": 1.7141779346223465e-05,
|
| 919 |
+
"loss": 0.0793,
|
| 920 |
"step": 152
|
| 921 |
},
|
| 922 |
{
|
| 923 |
"epoch": 0.81,
|
| 924 |
"learning_rate": 1.7101460639017034e-05,
|
| 925 |
+
"loss": 0.0717,
|
| 926 |
"step": 153
|
| 927 |
},
|
| 928 |
{
|
| 929 |
"epoch": 0.82,
|
| 930 |
"learning_rate": 1.7060907686134445e-05,
|
| 931 |
+
"loss": 0.0847,
|
| 932 |
"step": 154
|
| 933 |
},
|
| 934 |
{
|
| 935 |
"epoch": 0.82,
|
| 936 |
"learning_rate": 1.7020121825237672e-05,
|
| 937 |
+
"loss": 0.0798,
|
| 938 |
"step": 155
|
| 939 |
},
|
| 940 |
{
|
| 941 |
"epoch": 0.83,
|
| 942 |
"learning_rate": 1.6979104401671296e-05,
|
| 943 |
+
"loss": 0.0865,
|
| 944 |
"step": 156
|
| 945 |
},
|
| 946 |
{
|
| 947 |
"epoch": 0.84,
|
| 948 |
"learning_rate": 1.693785676841812e-05,
|
| 949 |
+
"loss": 0.0914,
|
| 950 |
"step": 157
|
| 951 |
},
|
| 952 |
{
|
| 953 |
"epoch": 0.84,
|
| 954 |
"learning_rate": 1.6896380286054537e-05,
|
| 955 |
+
"loss": 0.0797,
|
| 956 |
"step": 158
|
| 957 |
},
|
| 958 |
{
|
| 959 |
"epoch": 0.85,
|
| 960 |
"learning_rate": 1.6854676322705673e-05,
|
| 961 |
+
"loss": 0.0736,
|
| 962 |
"step": 159
|
| 963 |
},
|
| 964 |
{
|
| 965 |
"epoch": 0.85,
|
| 966 |
"learning_rate": 1.6812746254000222e-05,
|
| 967 |
+
"loss": 0.0765,
|
| 968 |
"step": 160
|
| 969 |
},
|
| 970 |
{
|
| 971 |
"epoch": 0.86,
|
| 972 |
"learning_rate": 1.67705914630251e-05,
|
| 973 |
+
"loss": 0.0843,
|
| 974 |
"step": 161
|
| 975 |
},
|
| 976 |
{
|
| 977 |
"epoch": 0.86,
|
| 978 |
"learning_rate": 1.6728213340279822e-05,
|
| 979 |
+
"loss": 0.0772,
|
| 980 |
"step": 162
|
| 981 |
},
|
| 982 |
{
|
| 983 |
"epoch": 0.87,
|
| 984 |
"learning_rate": 1.668561328363061e-05,
|
| 985 |
+
"loss": 0.0944,
|
| 986 |
"step": 163
|
| 987 |
},
|
| 988 |
{
|
| 989 |
"epoch": 0.87,
|
| 990 |
"learning_rate": 1.6642792698264313e-05,
|
| 991 |
+
"loss": 0.0915,
|
| 992 |
"step": 164
|
| 993 |
},
|
| 994 |
{
|
| 995 |
"epoch": 0.88,
|
| 996 |
"learning_rate": 1.6599752996642044e-05,
|
| 997 |
+
"loss": 0.0805,
|
| 998 |
"step": 165
|
| 999 |
},
|
| 1000 |
{
|
| 1001 |
"epoch": 0.88,
|
| 1002 |
"learning_rate": 1.655649559845258e-05,
|
| 1003 |
+
"loss": 0.0925,
|
| 1004 |
"step": 166
|
| 1005 |
},
|
| 1006 |
{
|
| 1007 |
"epoch": 0.89,
|
| 1008 |
"learning_rate": 1.651302193056555e-05,
|
| 1009 |
+
"loss": 0.0811,
|
| 1010 |
"step": 167
|
| 1011 |
},
|
| 1012 |
{
|
| 1013 |
"epoch": 0.89,
|
| 1014 |
"learning_rate": 1.6469333426984357e-05,
|
| 1015 |
+
"loss": 0.0787,
|
| 1016 |
"step": 168
|
| 1017 |
},
|
| 1018 |
{
|
| 1019 |
"epoch": 0.9,
|
| 1020 |
"learning_rate": 1.6425431528798883e-05,
|
| 1021 |
+
"loss": 0.0858,
|
| 1022 |
"step": 169
|
| 1023 |
},
|
| 1024 |
{
|
| 1025 |
"epoch": 0.9,
|
| 1026 |
"learning_rate": 1.6381317684137946e-05,
|
| 1027 |
+
"loss": 0.0768,
|
| 1028 |
"step": 170
|
| 1029 |
},
|
| 1030 |
{
|
| 1031 |
"epoch": 0.91,
|
| 1032 |
"learning_rate": 1.6336993348121543e-05,
|
| 1033 |
+
"loss": 0.0818,
|
| 1034 |
"step": 171
|
| 1035 |
},
|
| 1036 |
{
|
| 1037 |
"epoch": 0.91,
|
| 1038 |
"learning_rate": 1.6292459982812845e-05,
|
| 1039 |
+
"loss": 0.0868,
|
| 1040 |
"step": 172
|
| 1041 |
},
|
| 1042 |
{
|
| 1043 |
"epoch": 0.92,
|
| 1044 |
"learning_rate": 1.624771905716997e-05,
|
| 1045 |
+
"loss": 0.0828,
|
| 1046 |
"step": 173
|
| 1047 |
},
|
| 1048 |
{
|
| 1049 |
"epoch": 0.93,
|
| 1050 |
"learning_rate": 1.620277204699754e-05,
|
| 1051 |
+
"loss": 0.0821,
|
| 1052 |
"step": 174
|
| 1053 |
},
|
| 1054 |
{
|
| 1055 |
"epoch": 0.93,
|
| 1056 |
"learning_rate": 1.615762043489797e-05,
|
| 1057 |
+
"loss": 0.0858,
|
| 1058 |
"step": 175
|
| 1059 |
},
|
| 1060 |
{
|
| 1061 |
"epoch": 0.94,
|
| 1062 |
"learning_rate": 1.611226571022261e-05,
|
| 1063 |
+
"loss": 0.0711,
|
| 1064 |
"step": 176
|
| 1065 |
},
|
| 1066 |
{
|
| 1067 |
"epoch": 0.94,
|
| 1068 |
"learning_rate": 1.6066709369022576e-05,
|
| 1069 |
+
"loss": 0.0771,
|
| 1070 |
"step": 177
|
| 1071 |
},
|
| 1072 |
{
|
| 1073 |
"epoch": 0.95,
|
| 1074 |
"learning_rate": 1.6020952913999423e-05,
|
| 1075 |
+
"loss": 0.0788,
|
| 1076 |
"step": 178
|
| 1077 |
},
|
| 1078 |
{
|
| 1079 |
"epoch": 0.95,
|
| 1080 |
"learning_rate": 1.5974997854455575e-05,
|
| 1081 |
+
"loss": 0.0716,
|
| 1082 |
"step": 179
|
| 1083 |
},
|
| 1084 |
{
|
| 1085 |
"epoch": 0.96,
|
| 1086 |
"learning_rate": 1.5928845706244537e-05,
|
| 1087 |
+
"loss": 0.0894,
|
| 1088 |
"step": 180
|
| 1089 |
},
|
| 1090 |
{
|
| 1091 |
"epoch": 0.96,
|
| 1092 |
"learning_rate": 1.588249799172089e-05,
|
| 1093 |
+
"loss": 0.085,
|
| 1094 |
"step": 181
|
| 1095 |
},
|
| 1096 |
{
|
| 1097 |
"epoch": 0.97,
|
| 1098 |
"learning_rate": 1.583595623969009e-05,
|
| 1099 |
+
"loss": 0.0832,
|
| 1100 |
"step": 182
|
| 1101 |
},
|
| 1102 |
{
|
| 1103 |
"epoch": 0.97,
|
| 1104 |
"learning_rate": 1.5789221985358017e-05,
|
| 1105 |
+
"loss": 0.0787,
|
| 1106 |
"step": 183
|
| 1107 |
},
|
| 1108 |
{
|
| 1109 |
"epoch": 0.98,
|
| 1110 |
"learning_rate": 1.574229677028036e-05,
|
| 1111 |
+
"loss": 0.0792,
|
| 1112 |
"step": 184
|
| 1113 |
},
|
| 1114 |
{
|
| 1115 |
"epoch": 0.98,
|
| 1116 |
"learning_rate": 1.5695182142311743e-05,
|
| 1117 |
+
"loss": 0.0798,
|
| 1118 |
"step": 185
|
| 1119 |
},
|
| 1120 |
{
|
| 1121 |
"epoch": 0.99,
|
| 1122 |
"learning_rate": 1.564787965555469e-05,
|
| 1123 |
+
"loss": 0.0978,
|
| 1124 |
"step": 186
|
| 1125 |
},
|
| 1126 |
{
|
| 1127 |
"epoch": 0.99,
|
| 1128 |
"learning_rate": 1.560039087030836e-05,
|
| 1129 |
+
"loss": 0.0909,
|
| 1130 |
"step": 187
|
| 1131 |
},
|
| 1132 |
{
|
| 1133 |
"epoch": 1.0,
|
| 1134 |
"learning_rate": 1.5552717353017045e-05,
|
| 1135 |
+
"loss": 0.0749,
|
| 1136 |
"step": 188
|
| 1137 |
},
|
| 1138 |
{
|
| 1139 |
"epoch": 1.01,
|
| 1140 |
"learning_rate": 1.5504860676218557e-05,
|
| 1141 |
+
"loss": 0.0788,
|
| 1142 |
"step": 189
|
| 1143 |
},
|
| 1144 |
{
|
| 1145 |
"epoch": 1.01,
|
| 1146 |
"learning_rate": 1.5456822418492312e-05,
|
| 1147 |
+
"loss": 0.07,
|
| 1148 |
"step": 190
|
| 1149 |
},
|
| 1150 |
{
|
| 1151 |
"epoch": 1.02,
|
| 1152 |
"learning_rate": 1.540860416440728e-05,
|
| 1153 |
+
"loss": 0.073,
|
| 1154 |
"step": 191
|
| 1155 |
},
|
| 1156 |
{
|
| 1157 |
"epoch": 1.02,
|
| 1158 |
"learning_rate": 1.5360207504469715e-05,
|
| 1159 |
+
"loss": 0.0621,
|
| 1160 |
"step": 192
|
| 1161 |
},
|
| 1162 |
{
|
| 1163 |
"epoch": 1.03,
|
| 1164 |
"learning_rate": 1.5311634035070678e-05,
|
| 1165 |
+
"loss": 0.0738,
|
| 1166 |
"step": 193
|
| 1167 |
},
|
| 1168 |
{
|
| 1169 |
"epoch": 1.03,
|
| 1170 |
"learning_rate": 1.5262885358433404e-05,
|
| 1171 |
+
"loss": 0.0698,
|
| 1172 |
"step": 194
|
| 1173 |
},
|
| 1174 |
{
|
| 1175 |
"epoch": 1.04,
|
| 1176 |
"learning_rate": 1.5213963082560424e-05,
|
| 1177 |
+
"loss": 0.0666,
|
| 1178 |
"step": 195
|
| 1179 |
},
|
| 1180 |
{
|
| 1181 |
"epoch": 1.04,
|
| 1182 |
"learning_rate": 1.5164868821180538e-05,
|
| 1183 |
+
"loss": 0.0663,
|
| 1184 |
"step": 196
|
| 1185 |
},
|
| 1186 |
{
|
| 1187 |
"epoch": 1.05,
|
| 1188 |
"learning_rate": 1.5115604193695599e-05,
|
| 1189 |
+
"loss": 0.0686,
|
| 1190 |
"step": 197
|
| 1191 |
},
|
| 1192 |
{
|
| 1193 |
"epoch": 1.05,
|
| 1194 |
"learning_rate": 1.5066170825127069e-05,
|
| 1195 |
+
"loss": 0.0612,
|
| 1196 |
"step": 198
|
| 1197 |
},
|
| 1198 |
{
|
| 1199 |
"epoch": 1.06,
|
| 1200 |
"learning_rate": 1.5016570346062432e-05,
|
| 1201 |
+
"loss": 0.0657,
|
| 1202 |
"step": 199
|
| 1203 |
},
|
| 1204 |
{
|
| 1205 |
"epoch": 1.06,
|
| 1206 |
"learning_rate": 1.496680439260141e-05,
|
| 1207 |
+
"loss": 0.0626,
|
| 1208 |
"step": 200
|
| 1209 |
},
|
| 1210 |
{
|
| 1211 |
"epoch": 1.07,
|
| 1212 |
"learning_rate": 1.4916874606301989e-05,
|
| 1213 |
+
"loss": 0.068,
|
| 1214 |
"step": 201
|
| 1215 |
},
|
| 1216 |
{
|
| 1217 |
"epoch": 1.07,
|
| 1218 |
"learning_rate": 1.4866782634126266e-05,
|
| 1219 |
+
"loss": 0.0637,
|
| 1220 |
"step": 202
|
| 1221 |
},
|
| 1222 |
{
|
| 1223 |
"epoch": 1.08,
|
| 1224 |
"learning_rate": 1.4816530128386144e-05,
|
| 1225 |
+
"loss": 0.0698,
|
| 1226 |
"step": 203
|
| 1227 |
},
|
| 1228 |
{
|
| 1229 |
"epoch": 1.09,
|
| 1230 |
"learning_rate": 1.4766118746688805e-05,
|
| 1231 |
+
"loss": 0.0714,
|
| 1232 |
"step": 204
|
| 1233 |
},
|
| 1234 |
{
|
| 1235 |
"epoch": 1.09,
|
| 1236 |
"learning_rate": 1.471555015188205e-05,
|
| 1237 |
+
"loss": 0.061,
|
| 1238 |
"step": 205
|
| 1239 |
},
|
| 1240 |
{
|
| 1241 |
"epoch": 1.1,
|
| 1242 |
"learning_rate": 1.4664826011999436e-05,
|
| 1243 |
+
"loss": 0.0645,
|
| 1244 |
"step": 206
|
| 1245 |
},
|
| 1246 |
{
|
| 1247 |
"epoch": 1.1,
|
| 1248 |
"learning_rate": 1.4613948000205272e-05,
|
| 1249 |
+
"loss": 0.0714,
|
| 1250 |
"step": 207
|
| 1251 |
},
|
| 1252 |
{
|
| 1253 |
"epoch": 1.11,
|
| 1254 |
"learning_rate": 1.4562917794739412e-05,
|
| 1255 |
+
"loss": 0.0583,
|
| 1256 |
"step": 208
|
| 1257 |
},
|
| 1258 |
{
|
| 1259 |
"epoch": 1.11,
|
| 1260 |
"learning_rate": 1.4511737078861903e-05,
|
| 1261 |
+
"loss": 0.0609,
|
| 1262 |
"step": 209
|
| 1263 |
},
|
| 1264 |
{
|
| 1265 |
"epoch": 1.12,
|
| 1266 |
"learning_rate": 1.4460407540797467e-05,
|
| 1267 |
+
"loss": 0.0695,
|
| 1268 |
"step": 210
|
| 1269 |
},
|
| 1270 |
{
|
| 1271 |
"epoch": 1.12,
|
| 1272 |
"learning_rate": 1.4408930873679805e-05,
|
| 1273 |
+
"loss": 0.0824,
|
| 1274 |
"step": 211
|
| 1275 |
},
|
| 1276 |
{
|
| 1277 |
"epoch": 1.13,
|
| 1278 |
"learning_rate": 1.4357308775495757e-05,
|
| 1279 |
+
"loss": 0.0541,
|
| 1280 |
"step": 212
|
| 1281 |
},
|
| 1282 |
{
|
| 1283 |
"epoch": 1.13,
|
| 1284 |
"learning_rate": 1.4305542949029286e-05,
|
| 1285 |
+
"loss": 0.0706,
|
| 1286 |
"step": 213
|
| 1287 |
},
|
| 1288 |
{
|
| 1289 |
"epoch": 1.14,
|
| 1290 |
"learning_rate": 1.4253635101805313e-05,
|
| 1291 |
+
"loss": 0.0812,
|
| 1292 |
"step": 214
|
| 1293 |
},
|
| 1294 |
{
|
| 1295 |
"epoch": 1.14,
|
| 1296 |
"learning_rate": 1.4201586946033397e-05,
|
| 1297 |
+
"loss": 0.0605,
|
| 1298 |
"step": 215
|
| 1299 |
},
|
| 1300 |
{
|
| 1301 |
"epoch": 1.15,
|
| 1302 |
"learning_rate": 1.4149400198551247e-05,
|
| 1303 |
+
"loss": 0.0674,
|
| 1304 |
"step": 216
|
| 1305 |
},
|
| 1306 |
{
|
| 1307 |
"epoch": 1.15,
|
| 1308 |
"learning_rate": 1.4097076580768103e-05,
|
| 1309 |
+
"loss": 0.0709,
|
| 1310 |
"step": 217
|
| 1311 |
},
|
| 1312 |
{
|
| 1313 |
"epoch": 1.16,
|
| 1314 |
"learning_rate": 1.4044617818607949e-05,
|
| 1315 |
+
"loss": 0.0727,
|
| 1316 |
"step": 218
|
| 1317 |
},
|
| 1318 |
{
|
| 1319 |
"epoch": 1.16,
|
| 1320 |
"learning_rate": 1.3992025642452579e-05,
|
| 1321 |
+
"loss": 0.0734,
|
| 1322 |
"step": 219
|
| 1323 |
},
|
| 1324 |
{
|
| 1325 |
"epoch": 1.17,
|
| 1326 |
"learning_rate": 1.3939301787084522e-05,
|
| 1327 |
+
"loss": 0.0593,
|
| 1328 |
"step": 220
|
| 1329 |
},
|
| 1330 |
{
|
| 1331 |
"epoch": 1.18,
|
| 1332 |
"learning_rate": 1.3886447991629828e-05,
|
| 1333 |
+
"loss": 0.0762,
|
| 1334 |
"step": 221
|
| 1335 |
},
|
| 1336 |
{
|
| 1337 |
"epoch": 1.18,
|
| 1338 |
"learning_rate": 1.3833465999500689e-05,
|
| 1339 |
+
"loss": 0.0668,
|
| 1340 |
"step": 222
|
| 1341 |
},
|
| 1342 |
{
|
| 1343 |
"epoch": 1.19,
|
| 1344 |
"learning_rate": 1.3780357558337927e-05,
|
| 1345 |
+
"loss": 0.0658,
|
| 1346 |
"step": 223
|
| 1347 |
},
|
| 1348 |
{
|
| 1349 |
"epoch": 1.19,
|
| 1350 |
"learning_rate": 1.372712441995337e-05,
|
| 1351 |
+
"loss": 0.0823,
|
| 1352 |
"step": 224
|
| 1353 |
},
|
| 1354 |
{
|
| 1355 |
"epoch": 1.2,
|
| 1356 |
"learning_rate": 1.3673768340272053e-05,
|
| 1357 |
+
"loss": 0.066,
|
| 1358 |
"step": 225
|
| 1359 |
},
|
| 1360 |
{
|
| 1361 |
"epoch": 1.2,
|
| 1362 |
"learning_rate": 1.362029107927429e-05,
|
| 1363 |
+
"loss": 0.0658,
|
| 1364 |
"step": 226
|
| 1365 |
},
|
| 1366 |
{
|
| 1367 |
"epoch": 1.21,
|
| 1368 |
"learning_rate": 1.3566694400937635e-05,
|
| 1369 |
+
"loss": 0.0618,
|
| 1370 |
"step": 227
|
| 1371 |
},
|
| 1372 |
{
|
| 1373 |
"epoch": 1.21,
|
| 1374 |
"learning_rate": 1.3512980073178693e-05,
|
| 1375 |
+
"loss": 0.0536,
|
| 1376 |
"step": 228
|
| 1377 |
},
|
| 1378 |
{
|
| 1379 |
"epoch": 1.22,
|
| 1380 |
"learning_rate": 1.3459149867794794e-05,
|
| 1381 |
+
"loss": 0.0676,
|
| 1382 |
"step": 229
|
| 1383 |
},
|
| 1384 |
{
|
| 1385 |
"epoch": 1.22,
|
| 1386 |
"learning_rate": 1.3405205560405558e-05,
|
| 1387 |
+
"loss": 0.0597,
|
| 1388 |
"step": 230
|
| 1389 |
},
|
| 1390 |
{
|
| 1391 |
"epoch": 1.23,
|
| 1392 |
"learning_rate": 1.3351148930394333e-05,
|
| 1393 |
+
"loss": 0.0618,
|
| 1394 |
"step": 231
|
| 1395 |
},
|
| 1396 |
{
|
| 1397 |
"epoch": 1.23,
|
| 1398 |
"learning_rate": 1.329698176084948e-05,
|
| 1399 |
+
"loss": 0.0642,
|
| 1400 |
"step": 232
|
| 1401 |
},
|
| 1402 |
{
|
| 1403 |
"epoch": 1.24,
|
| 1404 |
"learning_rate": 1.3242705838505577e-05,
|
| 1405 |
+
"loss": 0.0508,
|
| 1406 |
"step": 233
|
| 1407 |
},
|
| 1408 |
{
|
| 1409 |
"epoch": 1.24,
|
| 1410 |
"learning_rate": 1.3188322953684467e-05,
|
| 1411 |
+
"loss": 0.0688,
|
| 1412 |
"step": 234
|
| 1413 |
},
|
| 1414 |
{
|
| 1415 |
"epoch": 1.25,
|
| 1416 |
"learning_rate": 1.3133834900236217e-05,
|
| 1417 |
+
"loss": 0.0589,
|
| 1418 |
"step": 235
|
| 1419 |
},
|
| 1420 |
{
|
| 1421 |
"epoch": 1.26,
|
| 1422 |
"learning_rate": 1.3079243475479942e-05,
|
| 1423 |
+
"loss": 0.0569,
|
| 1424 |
"step": 236
|
| 1425 |
},
|
| 1426 |
{
|
| 1427 |
"epoch": 1.26,
|
| 1428 |
"learning_rate": 1.3024550480144506e-05,
|
| 1429 |
+
"loss": 0.0825,
|
| 1430 |
"step": 237
|
| 1431 |
},
|
| 1432 |
{
|
| 1433 |
"epoch": 1.27,
|
| 1434 |
"learning_rate": 1.296975771830915e-05,
|
| 1435 |
+
"loss": 0.0652,
|
| 1436 |
"step": 238
|
| 1437 |
},
|
| 1438 |
{
|
| 1439 |
"epoch": 1.27,
|
| 1440 |
"learning_rate": 1.2914866997343957e-05,
|
| 1441 |
+
"loss": 0.0654,
|
| 1442 |
"step": 239
|
| 1443 |
},
|
| 1444 |
{
|
| 1445 |
"epoch": 1.28,
|
| 1446 |
"learning_rate": 1.2859880127850258e-05,
|
| 1447 |
+
"loss": 0.0629,
|
| 1448 |
"step": 240
|
| 1449 |
},
|
| 1450 |
{
|
| 1451 |
"epoch": 1.28,
|
| 1452 |
"learning_rate": 1.2804798923600888e-05,
|
| 1453 |
+
"loss": 0.0704,
|
| 1454 |
"step": 241
|
| 1455 |
},
|
| 1456 |
{
|
| 1457 |
"epoch": 1.29,
|
| 1458 |
"learning_rate": 1.2749625201480375e-05,
|
| 1459 |
+
"loss": 0.0688,
|
| 1460 |
"step": 242
|
| 1461 |
},
|
| 1462 |
{
|
| 1463 |
"epoch": 1.29,
|
| 1464 |
"learning_rate": 1.2694360781424994e-05,
|
| 1465 |
+
"loss": 0.0623,
|
| 1466 |
"step": 243
|
| 1467 |
},
|
| 1468 |
{
|
| 1469 |
"epoch": 1.3,
|
| 1470 |
"learning_rate": 1.2639007486362745e-05,
|
| 1471 |
+
"loss": 0.0948,
|
| 1472 |
"step": 244
|
| 1473 |
},
|
| 1474 |
{
|
| 1475 |
"epoch": 1.3,
|
| 1476 |
"learning_rate": 1.2583567142153224e-05,
|
| 1477 |
+
"loss": 0.0744,
|
| 1478 |
"step": 245
|
| 1479 |
},
|
| 1480 |
{
|
| 1481 |
"epoch": 1.31,
|
| 1482 |
"learning_rate": 1.2528041577527384e-05,
|
| 1483 |
+
"loss": 0.0526,
|
| 1484 |
"step": 246
|
| 1485 |
},
|
| 1486 |
{
|
| 1487 |
"epoch": 1.31,
|
| 1488 |
"learning_rate": 1.2472432624027228e-05,
|
| 1489 |
+
"loss": 0.0624,
|
| 1490 |
"step": 247
|
| 1491 |
},
|
| 1492 |
{
|
| 1493 |
"epoch": 1.32,
|
| 1494 |
"learning_rate": 1.2416742115945391e-05,
|
| 1495 |
+
"loss": 0.0732,
|
| 1496 |
"step": 248
|
| 1497 |
},
|
| 1498 |
{
|
| 1499 |
"epoch": 1.32,
|
| 1500 |
"learning_rate": 1.2360971890264621e-05,
|
| 1501 |
+
"loss": 0.0645,
|
| 1502 |
"step": 249
|
| 1503 |
},
|
| 1504 |
{
|
| 1505 |
"epoch": 1.33,
|
| 1506 |
"learning_rate": 1.2305123786597202e-05,
|
| 1507 |
+
"loss": 0.0678,
|
| 1508 |
"step": 250
|
| 1509 |
},
|
| 1510 |
{
|
| 1511 |
"epoch": 1.34,
|
| 1512 |
"learning_rate": 1.224919964712427e-05,
|
| 1513 |
+
"loss": 0.0802,
|
| 1514 |
"step": 251
|
| 1515 |
},
|
| 1516 |
{
|
| 1517 |
"epoch": 1.34,
|
| 1518 |
"learning_rate": 1.219320131653504e-05,
|
| 1519 |
+
"loss": 0.0568,
|
| 1520 |
"step": 252
|
| 1521 |
},
|
| 1522 |
{
|
| 1523 |
"epoch": 1.35,
|
| 1524 |
"learning_rate": 1.2137130641965964e-05,
|
| 1525 |
+
"loss": 0.0526,
|
| 1526 |
"step": 253
|
| 1527 |
},
|
| 1528 |
{
|
| 1529 |
"epoch": 1.35,
|
| 1530 |
"learning_rate": 1.20809894729398e-05,
|
| 1531 |
+
"loss": 0.0632,
|
| 1532 |
"step": 254
|
| 1533 |
},
|
| 1534 |
{
|
| 1535 |
"epoch": 1.36,
|
| 1536 |
"learning_rate": 1.2024779661304614e-05,
|
| 1537 |
+
"loss": 0.0667,
|
| 1538 |
"step": 255
|
| 1539 |
},
|
| 1540 |
{
|
| 1541 |
"epoch": 1.36,
|
| 1542 |
"learning_rate": 1.1968503061172674e-05,
|
| 1543 |
+
"loss": 0.0727,
|
| 1544 |
"step": 256
|
| 1545 |
},
|
| 1546 |
{
|
| 1547 |
"epoch": 1.37,
|
| 1548 |
"learning_rate": 1.1912161528859308e-05,
|
| 1549 |
+
"loss": 0.0641,
|
| 1550 |
"step": 257
|
| 1551 |
},
|
| 1552 |
{
|
| 1553 |
"epoch": 1.37,
|
| 1554 |
"learning_rate": 1.1855756922821675e-05,
|
| 1555 |
+
"loss": 0.0522,
|
| 1556 |
"step": 258
|
| 1557 |
},
|
| 1558 |
{
|
| 1559 |
"epoch": 1.38,
|
| 1560 |
"learning_rate": 1.179929110359745e-05,
|
| 1561 |
+
"loss": 0.0599,
|
| 1562 |
"step": 259
|
| 1563 |
},
|
| 1564 |
{
|
| 1565 |
"epoch": 1.38,
|
| 1566 |
"learning_rate": 1.1742765933743459e-05,
|
| 1567 |
+
"loss": 0.0681,
|
| 1568 |
"step": 260
|
| 1569 |
},
|
| 1570 |
{
|
| 1571 |
"epoch": 1.39,
|
| 1572 |
"learning_rate": 1.168618327777425e-05,
|
| 1573 |
+
"loss": 0.0576,
|
| 1574 |
"step": 261
|
| 1575 |
},
|
| 1576 |
{
|
| 1577 |
"epoch": 1.39,
|
| 1578 |
"learning_rate": 1.1629545002100573e-05,
|
| 1579 |
+
"loss": 0.0647,
|
| 1580 |
"step": 262
|
| 1581 |
},
|
| 1582 |
{
|
| 1583 |
"epoch": 1.4,
|
| 1584 |
"learning_rate": 1.157285297496783e-05,
|
| 1585 |
+
"loss": 0.0646,
|
| 1586 |
"step": 263
|
| 1587 |
},
|
| 1588 |
{
|
| 1589 |
"epoch": 1.4,
|
| 1590 |
"learning_rate": 1.1516109066394445e-05,
|
| 1591 |
+
"loss": 0.0587,
|
| 1592 |
"step": 264
|
| 1593 |
},
|
| 1594 |
{
|
| 1595 |
"epoch": 1.41,
|
| 1596 |
"learning_rate": 1.1459315148110179e-05,
|
| 1597 |
+
"loss": 0.064,
|
| 1598 |
"step": 265
|
| 1599 |
},
|
| 1600 |
{
|
| 1601 |
"epoch": 1.41,
|
| 1602 |
"learning_rate": 1.1402473093494395e-05,
|
| 1603 |
+
"loss": 0.0677,
|
| 1604 |
"step": 266
|
| 1605 |
},
|
| 1606 |
{
|
| 1607 |
"epoch": 1.42,
|
| 1608 |
"learning_rate": 1.1345584777514253e-05,
|
| 1609 |
+
"loss": 0.0599,
|
| 1610 |
"step": 267
|
| 1611 |
},
|
| 1612 |
{
|
| 1613 |
"epoch": 1.43,
|
| 1614 |
"learning_rate": 1.1288652076662878e-05,
|
| 1615 |
+
"loss": 0.0674,
|
| 1616 |
"step": 268
|
| 1617 |
},
|
| 1618 |
{
|
| 1619 |
"epoch": 1.43,
|
| 1620 |
"learning_rate": 1.1231676868897452e-05,
|
| 1621 |
+
"loss": 0.0716,
|
| 1622 |
"step": 269
|
| 1623 |
},
|
| 1624 |
{
|
| 1625 |
"epoch": 1.44,
|
| 1626 |
"learning_rate": 1.1174661033577267e-05,
|
| 1627 |
+
"loss": 0.0797,
|
| 1628 |
"step": 270
|
| 1629 |
},
|
| 1630 |
{
|
| 1631 |
"epoch": 1.44,
|
| 1632 |
"learning_rate": 1.1117606451401745e-05,
|
| 1633 |
+
"loss": 0.0577,
|
| 1634 |
"step": 271
|
| 1635 |
},
|
| 1636 |
{
|
| 1637 |
"epoch": 1.45,
|
| 1638 |
"learning_rate": 1.1060515004348394e-05,
|
| 1639 |
+
"loss": 0.0643,
|
| 1640 |
"step": 272
|
| 1641 |
},
|
| 1642 |
{
|
| 1643 |
"epoch": 1.45,
|
| 1644 |
"learning_rate": 1.1003388575610724e-05,
|
| 1645 |
+
"loss": 0.0735,
|
| 1646 |
"step": 273
|
| 1647 |
},
|
| 1648 |
{
|
| 1649 |
"epoch": 1.46,
|
| 1650 |
"learning_rate": 1.0946229049536136e-05,
|
| 1651 |
+
"loss": 0.0619,
|
| 1652 |
"step": 274
|
| 1653 |
},
|
| 1654 |
{
|
| 1655 |
"epoch": 1.46,
|
| 1656 |
"learning_rate": 1.088903831156378e-05,
|
| 1657 |
+
"loss": 0.0667,
|
| 1658 |
"step": 275
|
| 1659 |
},
|
| 1660 |
{
|
| 1661 |
"epoch": 1.47,
|
| 1662 |
"learning_rate": 1.0831818248162328e-05,
|
| 1663 |
+
"loss": 0.0721,
|
| 1664 |
"step": 276
|
| 1665 |
},
|
| 1666 |
{
|
| 1667 |
"epoch": 1.47,
|
| 1668 |
"learning_rate": 1.0774570746767785e-05,
|
| 1669 |
+
"loss": 0.0646,
|
| 1670 |
"step": 277
|
| 1671 |
},
|
| 1672 |
{
|
| 1673 |
"epoch": 1.48,
|
| 1674 |
"learning_rate": 1.0717297695721199e-05,
|
| 1675 |
+
"loss": 0.0604,
|
| 1676 |
"step": 278
|
| 1677 |
},
|
| 1678 |
{
|
| 1679 |
"epoch": 1.48,
|
| 1680 |
"learning_rate": 1.0660000984206395e-05,
|
| 1681 |
+
"loss": 0.0623,
|
| 1682 |
"step": 279
|
| 1683 |
},
|
| 1684 |
{
|
| 1685 |
"epoch": 1.49,
|
| 1686 |
"learning_rate": 1.0602682502187655e-05,
|
| 1687 |
+
"loss": 0.0648,
|
| 1688 |
"step": 280
|
| 1689 |
},
|
| 1690 |
{
|
| 1691 |
"epoch": 1.49,
|
| 1692 |
"learning_rate": 1.0545344140347365e-05,
|
| 1693 |
+
"loss": 0.0605,
|
| 1694 |
"step": 281
|
| 1695 |
},
|
| 1696 |
{
|
| 1697 |
"epoch": 1.5,
|
| 1698 |
"learning_rate": 1.0487987790023665e-05,
|
| 1699 |
+
"loss": 0.0667,
|
| 1700 |
"step": 282
|
| 1701 |
},
|
| 1702 |
{
|
| 1703 |
"epoch": 1.51,
|
| 1704 |
"learning_rate": 1.0430615343148054e-05,
|
| 1705 |
+
"loss": 0.0638,
|
| 1706 |
"step": 283
|
| 1707 |
},
|
| 1708 |
{
|
| 1709 |
"epoch": 1.51,
|
| 1710 |
"learning_rate": 1.0373228692182982e-05,
|
| 1711 |
+
"loss": 0.0598,
|
| 1712 |
"step": 284
|
| 1713 |
},
|
| 1714 |
{
|
| 1715 |
"epoch": 1.52,
|
| 1716 |
"learning_rate": 1.031582973005943e-05,
|
| 1717 |
+
"loss": 0.0805,
|
| 1718 |
"step": 285
|
| 1719 |
},
|
| 1720 |
{
|
| 1721 |
"epoch": 1.52,
|
| 1722 |
"learning_rate": 1.0258420350114473e-05,
|
| 1723 |
+
"loss": 0.0682,
|
| 1724 |
"step": 286
|
| 1725 |
},
|
| 1726 |
{
|
| 1727 |
"epoch": 1.53,
|
| 1728 |
"learning_rate": 1.0201002446028815e-05,
|
| 1729 |
+
"loss": 0.059,
|
| 1730 |
"step": 287
|
| 1731 |
},
|
| 1732 |
{
|
| 1733 |
"epoch": 1.53,
|
| 1734 |
"learning_rate": 1.0143577911764341e-05,
|
| 1735 |
+
"loss": 0.0558,
|
| 1736 |
"step": 288
|
| 1737 |
},
|
| 1738 |
{
|
| 1739 |
"epoch": 1.54,
|
| 1740 |
"learning_rate": 1.008614864150164e-05,
|
| 1741 |
+
"loss": 0.0685,
|
| 1742 |
"step": 289
|
| 1743 |
},
|
| 1744 |
{
|
| 1745 |
"epoch": 1.54,
|
| 1746 |
"learning_rate": 1.002871652957751e-05,
|
| 1747 |
+
"loss": 0.0539,
|
| 1748 |
"step": 290
|
| 1749 |
},
|
| 1750 |
{
|
| 1751 |
"epoch": 1.55,
|
| 1752 |
"learning_rate": 9.97128347042249e-06,
|
| 1753 |
+
"loss": 0.0588,
|
| 1754 |
"step": 291
|
| 1755 |
},
|
| 1756 |
{
|
| 1757 |
"epoch": 1.55,
|
| 1758 |
"learning_rate": 9.91385135849836e-06,
|
| 1759 |
+
"loss": 0.0513,
|
| 1760 |
"step": 292
|
| 1761 |
},
|
| 1762 |
{
|
| 1763 |
"epoch": 1.56,
|
| 1764 |
"learning_rate": 9.85642208823566e-06,
|
| 1765 |
+
"loss": 0.0616,
|
| 1766 |
"step": 293
|
| 1767 |
},
|
| 1768 |
{
|
| 1769 |
"epoch": 1.56,
|
| 1770 |
"learning_rate": 9.79899755397119e-06,
|
| 1771 |
+
"loss": 0.0588,
|
| 1772 |
"step": 294
|
| 1773 |
},
|
| 1774 |
{
|
| 1775 |
"epoch": 1.57,
|
| 1776 |
"learning_rate": 9.741579649885532e-06,
|
| 1777 |
+
"loss": 0.0645,
|
| 1778 |
"step": 295
|
| 1779 |
},
|
| 1780 |
{
|
| 1781 |
"epoch": 1.57,
|
| 1782 |
"learning_rate": 9.684170269940573e-06,
|
| 1783 |
+
"loss": 0.0644,
|
| 1784 |
"step": 296
|
| 1785 |
},
|
| 1786 |
{
|
| 1787 |
"epoch": 1.58,
|
| 1788 |
"learning_rate": 9.62677130781702e-06,
|
| 1789 |
+
"loss": 0.0638,
|
| 1790 |
"step": 297
|
| 1791 |
},
|
| 1792 |
{
|
| 1793 |
"epoch": 1.59,
|
| 1794 |
"learning_rate": 9.569384656851948e-06,
|
| 1795 |
+
"loss": 0.085,
|
| 1796 |
"step": 298
|
| 1797 |
},
|
| 1798 |
{
|
| 1799 |
"epoch": 1.59,
|
| 1800 |
"learning_rate": 9.512012209976335e-06,
|
| 1801 |
+
"loss": 0.0567,
|
| 1802 |
"step": 299
|
| 1803 |
},
|
| 1804 |
{
|
| 1805 |
"epoch": 1.6,
|
| 1806 |
"learning_rate": 9.454655859652637e-06,
|
| 1807 |
+
"loss": 0.0639,
|
| 1808 |
"step": 300
|
| 1809 |
},
|
| 1810 |
{
|
| 1811 |
"epoch": 1.6,
|
| 1812 |
"learning_rate": 9.39731749781235e-06,
|
| 1813 |
+
"loss": 0.073,
|
| 1814 |
"step": 301
|
| 1815 |
},
|
| 1816 |
{
|
| 1817 |
"epoch": 1.61,
|
| 1818 |
"learning_rate": 9.339999015793606e-06,
|
| 1819 |
+
"loss": 0.0703,
|
| 1820 |
"step": 302
|
| 1821 |
},
|
| 1822 |
{
|
| 1823 |
"epoch": 1.61,
|
| 1824 |
"learning_rate": 9.282702304278806e-06,
|
| 1825 |
+
"loss": 0.0711,
|
| 1826 |
"step": 303
|
| 1827 |
},
|
| 1828 |
{
|
| 1829 |
"epoch": 1.62,
|
| 1830 |
"learning_rate": 9.225429253232218e-06,
|
| 1831 |
+
"loss": 0.0641,
|
| 1832 |
"step": 304
|
| 1833 |
},
|
| 1834 |
{
|
| 1835 |
"epoch": 1.62,
|
| 1836 |
"learning_rate": 9.168181751837673e-06,
|
| 1837 |
+
"loss": 0.0591,
|
| 1838 |
"step": 305
|
| 1839 |
},
|
| 1840 |
{
|
| 1841 |
"epoch": 1.63,
|
| 1842 |
"learning_rate": 9.110961688436222e-06,
|
| 1843 |
+
"loss": 0.0684,
|
| 1844 |
"step": 306
|
| 1845 |
},
|
| 1846 |
{
|
| 1847 |
"epoch": 1.63,
|
| 1848 |
"learning_rate": 9.053770950463865e-06,
|
| 1849 |
+
"loss": 0.0775,
|
| 1850 |
"step": 307
|
| 1851 |
},
|
| 1852 |
{
|
| 1853 |
"epoch": 1.64,
|
| 1854 |
"learning_rate": 8.996611424389283e-06,
|
| 1855 |
+
"loss": 0.0688,
|
| 1856 |
"step": 308
|
| 1857 |
},
|
| 1858 |
{
|
| 1859 |
"epoch": 1.64,
|
| 1860 |
"learning_rate": 8.93948499565161e-06,
|
| 1861 |
+
"loss": 0.0785,
|
| 1862 |
"step": 309
|
| 1863 |
},
|
| 1864 |
{
|
| 1865 |
"epoch": 1.65,
|
| 1866 |
"learning_rate": 8.882393548598258e-06,
|
| 1867 |
+
"loss": 0.0737,
|
| 1868 |
"step": 310
|
| 1869 |
},
|
| 1870 |
{
|
| 1871 |
"epoch": 1.65,
|
| 1872 |
"learning_rate": 8.825338966422735e-06,
|
| 1873 |
+
"loss": 0.062,
|
| 1874 |
"step": 311
|
| 1875 |
},
|
| 1876 |
{
|
| 1877 |
"epoch": 1.66,
|
| 1878 |
"learning_rate": 8.768323131102552e-06,
|
| 1879 |
+
"loss": 0.0685,
|
| 1880 |
"step": 312
|
| 1881 |
},
|
| 1882 |
{
|
| 1883 |
"epoch": 1.66,
|
| 1884 |
"learning_rate": 8.711347923337122e-06,
|
| 1885 |
+
"loss": 0.0618,
|
| 1886 |
"step": 313
|
| 1887 |
},
|
| 1888 |
{
|
| 1889 |
"epoch": 1.67,
|
| 1890 |
"learning_rate": 8.65441522248575e-06,
|
| 1891 |
+
"loss": 0.0728,
|
| 1892 |
"step": 314
|
| 1893 |
},
|
| 1894 |
{
|
| 1895 |
"epoch": 1.68,
|
| 1896 |
"learning_rate": 8.59752690650561e-06,
|
| 1897 |
+
"loss": 0.0562,
|
| 1898 |
"step": 315
|
| 1899 |
},
|
| 1900 |
{
|
| 1901 |
"epoch": 1.68,
|
| 1902 |
"learning_rate": 8.540684851889823e-06,
|
| 1903 |
+
"loss": 0.0772,
|
| 1904 |
"step": 316
|
| 1905 |
},
|
| 1906 |
{
|
| 1907 |
"epoch": 1.69,
|
| 1908 |
"learning_rate": 8.483890933605558e-06,
|
| 1909 |
+
"loss": 0.0711,
|
| 1910 |
"step": 317
|
| 1911 |
},
|
| 1912 |
{
|
| 1913 |
"epoch": 1.69,
|
| 1914 |
"learning_rate": 8.427147025032171e-06,
|
| 1915 |
+
"loss": 0.0579,
|
| 1916 |
"step": 318
|
| 1917 |
},
|
| 1918 |
{
|
| 1919 |
"epoch": 1.7,
|
| 1920 |
"learning_rate": 8.37045499789943e-06,
|
| 1921 |
+
"loss": 0.0607,
|
| 1922 |
"step": 319
|
| 1923 |
},
|
| 1924 |
{
|
| 1925 |
"epoch": 1.7,
|
| 1926 |
"learning_rate": 8.313816722225751e-06,
|
| 1927 |
+
"loss": 0.0692,
|
| 1928 |
"step": 320
|
| 1929 |
},
|
| 1930 |
{
|
| 1931 |
"epoch": 1.71,
|
| 1932 |
"learning_rate": 8.257234066256543e-06,
|
| 1933 |
+
"loss": 0.0632,
|
| 1934 |
"step": 321
|
| 1935 |
},
|
| 1936 |
{
|
| 1937 |
"epoch": 1.71,
|
| 1938 |
"learning_rate": 8.200708896402557e-06,
|
| 1939 |
+
"loss": 0.0706,
|
| 1940 |
"step": 322
|
| 1941 |
},
|
| 1942 |
{
|
| 1943 |
"epoch": 1.72,
|
| 1944 |
"learning_rate": 8.144243077178329e-06,
|
| 1945 |
+
"loss": 0.0612,
|
| 1946 |
"step": 323
|
| 1947 |
},
|
| 1948 |
{
|
| 1949 |
"epoch": 1.72,
|
| 1950 |
"learning_rate": 8.087838471140696e-06,
|
| 1951 |
+
"loss": 0.0684,
|
| 1952 |
"step": 324
|
| 1953 |
},
|
| 1954 |
{
|
| 1955 |
"epoch": 1.73,
|
| 1956 |
"learning_rate": 8.031496938827329e-06,
|
| 1957 |
+
"loss": 0.0712,
|
| 1958 |
"step": 325
|
| 1959 |
},
|
| 1960 |
{
|
| 1961 |
"epoch": 1.73,
|
| 1962 |
"learning_rate": 7.97522033869539e-06,
|
| 1963 |
+
"loss": 0.0676,
|
| 1964 |
"step": 326
|
| 1965 |
},
|
| 1966 |
{
|
| 1967 |
"epoch": 1.74,
|
| 1968 |
"learning_rate": 7.9190105270602e-06,
|
| 1969 |
+
"loss": 0.0643,
|
| 1970 |
"step": 327
|
| 1971 |
},
|
| 1972 |
{
|
| 1973 |
"epoch": 1.74,
|
| 1974 |
"learning_rate": 7.86286935803404e-06,
|
| 1975 |
+
"loss": 0.0602,
|
| 1976 |
"step": 328
|
| 1977 |
},
|
| 1978 |
{
|
| 1979 |
"epoch": 1.75,
|
| 1980 |
"learning_rate": 7.806798683464965e-06,
|
| 1981 |
+
"loss": 0.0594,
|
| 1982 |
"step": 329
|
| 1983 |
},
|
| 1984 |
{
|
| 1985 |
"epoch": 1.76,
|
| 1986 |
"learning_rate": 7.750800352875734e-06,
|
| 1987 |
+
"loss": 0.0677,
|
| 1988 |
"step": 330
|
| 1989 |
},
|
| 1990 |
{
|
| 1991 |
"epoch": 1.76,
|
| 1992 |
"learning_rate": 7.694876213402801e-06,
|
| 1993 |
+
"loss": 0.0684,
|
| 1994 |
"step": 331
|
| 1995 |
},
|
| 1996 |
{
|
| 1997 |
"epoch": 1.77,
|
| 1998 |
"learning_rate": 7.63902810973538e-06,
|
| 1999 |
+
"loss": 0.0599,
|
| 2000 |
"step": 332
|
| 2001 |
},
|
| 2002 |
{
|
| 2003 |
"epoch": 1.77,
|
| 2004 |
"learning_rate": 7.583257884054613e-06,
|
| 2005 |
+
"loss": 0.0711,
|
| 2006 |
"step": 333
|
| 2007 |
},
|
| 2008 |
{
|
| 2009 |
"epoch": 1.78,
|
| 2010 |
"learning_rate": 7.527567375972772e-06,
|
| 2011 |
+
"loss": 0.0724,
|
| 2012 |
"step": 334
|
| 2013 |
},
|
| 2014 |
{
|
| 2015 |
"epoch": 1.78,
|
| 2016 |
"learning_rate": 7.471958422472618e-06,
|
| 2017 |
+
"loss": 0.0579,
|
| 2018 |
"step": 335
|
| 2019 |
},
|
| 2020 |
{
|
| 2021 |
"epoch": 1.79,
|
| 2022 |
"learning_rate": 7.416432857846783e-06,
|
| 2023 |
+
"loss": 0.0544,
|
| 2024 |
"step": 336
|
| 2025 |
},
|
| 2026 |
{
|
| 2027 |
"epoch": 1.79,
|
| 2028 |
"learning_rate": 7.360992513637257e-06,
|
| 2029 |
+
"loss": 0.0559,
|
| 2030 |
"step": 337
|
| 2031 |
},
|
| 2032 |
{
|
| 2033 |
"epoch": 1.8,
|
| 2034 |
"learning_rate": 7.305639218575009e-06,
|
| 2035 |
+
"loss": 0.0681,
|
| 2036 |
"step": 338
|
| 2037 |
},
|
| 2038 |
{
|
| 2039 |
"epoch": 1.8,
|
| 2040 |
"learning_rate": 7.250374798519626e-06,
|
| 2041 |
+
"loss": 0.0668,
|
| 2042 |
"step": 339
|
| 2043 |
},
|
| 2044 |
{
|
| 2045 |
"epoch": 1.81,
|
| 2046 |
"learning_rate": 7.1952010763991146e-06,
|
| 2047 |
+
"loss": 0.0787,
|
| 2048 |
"step": 340
|
| 2049 |
},
|
| 2050 |
{
|
| 2051 |
"epoch": 1.81,
|
| 2052 |
"learning_rate": 7.140119872149743e-06,
|
| 2053 |
+
"loss": 0.0739,
|
| 2054 |
"step": 341
|
| 2055 |
},
|
| 2056 |
{
|
| 2057 |
"epoch": 1.82,
|
| 2058 |
"learning_rate": 7.085133002656044e-06,
|
| 2059 |
+
"loss": 0.0616,
|
| 2060 |
"step": 342
|
| 2061 |
},
|
| 2062 |
{
|
| 2063 |
"epoch": 1.82,
|
| 2064 |
"learning_rate": 7.030242281690856e-06,
|
| 2065 |
+
"loss": 0.052,
|
| 2066 |
"step": 343
|
| 2067 |
},
|
| 2068 |
{
|
| 2069 |
"epoch": 1.83,
|
| 2070 |
"learning_rate": 6.975449519855495e-06,
|
| 2071 |
+
"loss": 0.0676,
|
| 2072 |
"step": 344
|
| 2073 |
},
|
| 2074 |
{
|
| 2075 |
"epoch": 1.84,
|
| 2076 |
"learning_rate": 6.9207565245200614e-06,
|
| 2077 |
+
"loss": 0.0576,
|
| 2078 |
"step": 345
|
| 2079 |
},
|
| 2080 |
{
|
| 2081 |
"epoch": 1.84,
|
| 2082 |
"learning_rate": 6.866165099763782e-06,
|
| 2083 |
+
"loss": 0.0547,
|
| 2084 |
"step": 346
|
| 2085 |
},
|
| 2086 |
{
|
| 2087 |
"epoch": 1.85,
|
| 2088 |
"learning_rate": 6.811677046315535e-06,
|
| 2089 |
+
"loss": 0.0615,
|
| 2090 |
"step": 347
|
| 2091 |
},
|
| 2092 |
{
|
| 2093 |
"epoch": 1.85,
|
| 2094 |
"learning_rate": 6.757294161494426e-06,
|
| 2095 |
+
"loss": 0.0533,
|
| 2096 |
"step": 348
|
| 2097 |
},
|
| 2098 |
{
|
| 2099 |
"epoch": 1.86,
|
| 2100 |
"learning_rate": 6.70301823915052e-06,
|
| 2101 |
+
"loss": 0.0654,
|
| 2102 |
"step": 349
|
| 2103 |
},
|
| 2104 |
{
|
| 2105 |
"epoch": 1.86,
|
| 2106 |
"learning_rate": 6.64885106960567e-06,
|
| 2107 |
+
"loss": 0.0616,
|
| 2108 |
"step": 350
|
| 2109 |
},
|
| 2110 |
{
|
| 2111 |
"epoch": 1.87,
|
| 2112 |
"learning_rate": 6.594794439594443e-06,
|
| 2113 |
+
"loss": 0.0602,
|
| 2114 |
"step": 351
|
| 2115 |
},
|
| 2116 |
{
|
| 2117 |
"epoch": 1.87,
|
| 2118 |
"learning_rate": 6.54085013220521e-06,
|
| 2119 |
+
"loss": 0.0565,
|
| 2120 |
"step": 352
|
| 2121 |
},
|
| 2122 |
{
|
| 2123 |
"epoch": 1.88,
|
| 2124 |
"learning_rate": 6.48701992682131e-06,
|
| 2125 |
+
"loss": 0.0481,
|
| 2126 |
"step": 353
|
| 2127 |
},
|
| 2128 |
{
|
| 2129 |
"epoch": 1.88,
|
| 2130 |
"learning_rate": 6.4333055990623674e-06,
|
| 2131 |
+
"loss": 0.0583,
|
| 2132 |
"step": 354
|
| 2133 |
},
|
| 2134 |
{
|
| 2135 |
"epoch": 1.89,
|
| 2136 |
"learning_rate": 6.379708920725713e-06,
|
| 2137 |
+
"loss": 0.0598,
|
| 2138 |
"step": 355
|
| 2139 |
},
|
| 2140 |
{
|
| 2141 |
"epoch": 1.89,
|
| 2142 |
"learning_rate": 6.3262316597279506e-06,
|
| 2143 |
+
"loss": 0.0565,
|
| 2144 |
"step": 356
|
| 2145 |
},
|
| 2146 |
{
|
| 2147 |
"epoch": 1.9,
|
| 2148 |
"learning_rate": 6.272875580046633e-06,
|
| 2149 |
+
"loss": 0.0684,
|
| 2150 |
"step": 357
|
| 2151 |
},
|
| 2152 |
{
|
| 2153 |
"epoch": 1.9,
|
| 2154 |
"learning_rate": 6.219642441662077e-06,
|
| 2155 |
+
"loss": 0.0593,
|
| 2156 |
"step": 358
|
| 2157 |
},
|
| 2158 |
{
|
| 2159 |
"epoch": 1.91,
|
| 2160 |
"learning_rate": 6.1665340004993164e-06,
|
| 2161 |
+
"loss": 0.0567,
|
| 2162 |
"step": 359
|
| 2163 |
},
|
| 2164 |
{
|
| 2165 |
"epoch": 1.91,
|
| 2166 |
"learning_rate": 6.113552008370172e-06,
|
| 2167 |
+
"loss": 0.064,
|
| 2168 |
"step": 360
|
| 2169 |
},
|
| 2170 |
{
|
| 2171 |
"epoch": 1.92,
|
| 2172 |
"learning_rate": 6.06069821291548e-06,
|
| 2173 |
+
"loss": 0.0613,
|
| 2174 |
"step": 361
|
| 2175 |
},
|
| 2176 |
{
|
| 2177 |
"epoch": 1.93,
|
| 2178 |
"learning_rate": 6.007974357547424e-06,
|
| 2179 |
+
"loss": 0.0671,
|
| 2180 |
"step": 362
|
| 2181 |
},
|
| 2182 |
{
|
| 2183 |
"epoch": 1.93,
|
| 2184 |
"learning_rate": 5.9553821813920545e-06,
|
| 2185 |
+
"loss": 0.0572,
|
| 2186 |
"step": 363
|
| 2187 |
},
|
| 2188 |
{
|
| 2189 |
"epoch": 1.94,
|
| 2190 |
"learning_rate": 5.902923419231902e-06,
|
| 2191 |
+
"loss": 0.0432,
|
| 2192 |
"step": 364
|
| 2193 |
},
|
| 2194 |
{
|
| 2195 |
"epoch": 1.94,
|
| 2196 |
"learning_rate": 5.850599801448757e-06,
|
| 2197 |
+
"loss": 0.0624,
|
| 2198 |
"step": 365
|
| 2199 |
},
|
| 2200 |
{
|
| 2201 |
"epoch": 1.95,
|
| 2202 |
"learning_rate": 5.798413053966607e-06,
|
| 2203 |
+
"loss": 0.0717,
|
| 2204 |
"step": 366
|
| 2205 |
},
|
| 2206 |
{
|
| 2207 |
"epoch": 1.95,
|
| 2208 |
"learning_rate": 5.74636489819469e-06,
|
| 2209 |
+
"loss": 0.064,
|
| 2210 |
"step": 367
|
| 2211 |
},
|
| 2212 |
{
|
| 2213 |
"epoch": 1.96,
|
| 2214 |
"learning_rate": 5.6944570509707185e-06,
|
| 2215 |
+
"loss": 0.0546,
|
| 2216 |
"step": 368
|
| 2217 |
},
|
| 2218 |
{
|
| 2219 |
"epoch": 1.96,
|
| 2220 |
"learning_rate": 5.6426912245042435e-06,
|
| 2221 |
+
"loss": 0.0653,
|
| 2222 |
"step": 369
|
| 2223 |
},
|
| 2224 |
{
|
| 2225 |
"epoch": 1.97,
|
| 2226 |
"learning_rate": 5.5910691263201985e-06,
|
| 2227 |
+
"loss": 0.0492,
|
| 2228 |
"step": 370
|
| 2229 |
},
|
| 2230 |
{
|
| 2231 |
"epoch": 1.97,
|
| 2232 |
"learning_rate": 5.5395924592025384e-06,
|
| 2233 |
+
"loss": 0.0595,
|
| 2234 |
"step": 371
|
| 2235 |
},
|
| 2236 |
{
|
| 2237 |
"epoch": 1.98,
|
| 2238 |
"learning_rate": 5.488262921138098e-06,
|
| 2239 |
+
"loss": 0.0607,
|
| 2240 |
"step": 372
|
| 2241 |
},
|
| 2242 |
{
|
| 2243 |
"epoch": 1.98,
|
| 2244 |
"learning_rate": 5.437082205260593e-06,
|
| 2245 |
+
"loss": 0.0571,
|
| 2246 |
"step": 373
|
| 2247 |
},
|
| 2248 |
{
|
| 2249 |
"epoch": 1.99,
|
| 2250 |
"learning_rate": 5.3860519997947295e-06,
|
| 2251 |
+
"loss": 0.0818,
|
| 2252 |
"step": 374
|
| 2253 |
},
|
| 2254 |
{
|
| 2255 |
"epoch": 1.99,
|
| 2256 |
"learning_rate": 5.335173988000566e-06,
|
| 2257 |
+
"loss": 0.0599,
|
| 2258 |
"step": 375
|
| 2259 |
},
|
| 2260 |
{
|
| 2261 |
"epoch": 2.0,
|
| 2262 |
"learning_rate": 5.284449848117954e-06,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2263 |
"loss": 0.052,
|
| 2264 |
+
"step": 376
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2265 |
}
|
| 2266 |
],
|
| 2267 |
"max_steps": 564,
|
| 2268 |
"num_train_epochs": 3,
|
| 2269 |
+
"total_flos": 20423908786176.0,
|
| 2270 |
"trial_name": null,
|
| 2271 |
"trial_params": null
|
| 2272 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5819
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fad8848292df93b3a6ec679f158060cf333018cc301781c08a0eee936fbb2a15
|
| 3 |
size 5819
|
zero_to_fp32.py
ADDED
|
@@ -0,0 +1,578 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python
|
| 2 |
+
|
| 3 |
+
# Copyright (c) Microsoft Corporation.
|
| 4 |
+
# SPDX-License-Identifier: Apache-2.0
|
| 5 |
+
|
| 6 |
+
# DeepSpeed Team
|
| 7 |
+
|
| 8 |
+
# This script extracts fp32 consolidated weights from a zero 2 and 3 DeepSpeed checkpoints. It gets
|
| 9 |
+
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
| 10 |
+
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
| 11 |
+
# application.
|
| 12 |
+
#
|
| 13 |
+
# example: python zero_to_fp32.py . pytorch_model.bin
|
| 14 |
+
|
| 15 |
+
import argparse
|
| 16 |
+
import torch
|
| 17 |
+
import glob
|
| 18 |
+
import math
|
| 19 |
+
import os
|
| 20 |
+
import re
|
| 21 |
+
from collections import OrderedDict
|
| 22 |
+
from dataclasses import dataclass
|
| 23 |
+
|
| 24 |
+
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
| 25 |
+
# DeepSpeed data structures it has to be available in the current python environment.
|
| 26 |
+
from deepspeed.utils import logger
|
| 27 |
+
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
| 28 |
+
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
| 29 |
+
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
@dataclass
|
| 33 |
+
class zero_model_state:
|
| 34 |
+
buffers: dict()
|
| 35 |
+
param_shapes: dict()
|
| 36 |
+
shared_params: list
|
| 37 |
+
ds_version: int
|
| 38 |
+
frozen_param_shapes: dict()
|
| 39 |
+
frozen_param_fragments: dict()
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
debug = 0
|
| 43 |
+
|
| 44 |
+
# load to cpu
|
| 45 |
+
device = torch.device('cpu')
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
def atoi(text):
|
| 49 |
+
return int(text) if text.isdigit() else text
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
def natural_keys(text):
|
| 53 |
+
'''
|
| 54 |
+
alist.sort(key=natural_keys) sorts in human order
|
| 55 |
+
http://nedbatchelder.com/blog/200712/human_sorting.html
|
| 56 |
+
(See Toothy's implementation in the comments)
|
| 57 |
+
'''
|
| 58 |
+
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
def get_model_state_file(checkpoint_dir, zero_stage):
|
| 62 |
+
if not os.path.isdir(checkpoint_dir):
|
| 63 |
+
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
| 64 |
+
|
| 65 |
+
# there should be only one file
|
| 66 |
+
if zero_stage == 2:
|
| 67 |
+
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
| 68 |
+
elif zero_stage == 3:
|
| 69 |
+
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
| 70 |
+
|
| 71 |
+
if not os.path.exists(file):
|
| 72 |
+
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
| 73 |
+
|
| 74 |
+
return file
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
| 78 |
+
# XXX: need to test that this simple glob rule works for multi-node setup too
|
| 79 |
+
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
| 80 |
+
|
| 81 |
+
if len(ckpt_files) == 0:
|
| 82 |
+
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
| 83 |
+
|
| 84 |
+
return ckpt_files
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
def get_optim_files(checkpoint_dir):
|
| 88 |
+
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
def get_model_state_files(checkpoint_dir):
|
| 92 |
+
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
| 93 |
+
|
| 94 |
+
|
| 95 |
+
def parse_model_states(files):
|
| 96 |
+
zero_model_states = []
|
| 97 |
+
for file in files:
|
| 98 |
+
state_dict = torch.load(file, map_location=device)
|
| 99 |
+
|
| 100 |
+
if BUFFER_NAMES not in state_dict:
|
| 101 |
+
raise ValueError(f"{file} is not a model state checkpoint")
|
| 102 |
+
buffer_names = state_dict[BUFFER_NAMES]
|
| 103 |
+
if debug:
|
| 104 |
+
print("Found buffers:", buffer_names)
|
| 105 |
+
|
| 106 |
+
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
| 107 |
+
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
| 108 |
+
param_shapes = state_dict[PARAM_SHAPES]
|
| 109 |
+
|
| 110 |
+
# collect parameters that are included in param_shapes
|
| 111 |
+
param_names = []
|
| 112 |
+
for s in param_shapes:
|
| 113 |
+
for name in s.keys():
|
| 114 |
+
param_names.append(name)
|
| 115 |
+
|
| 116 |
+
# update with frozen parameters
|
| 117 |
+
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
| 118 |
+
if frozen_param_shapes is not None:
|
| 119 |
+
if debug:
|
| 120 |
+
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
| 121 |
+
param_names += list(frozen_param_shapes.keys())
|
| 122 |
+
|
| 123 |
+
# handle shared params
|
| 124 |
+
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
| 125 |
+
|
| 126 |
+
ds_version = state_dict.get(DS_VERSION, None)
|
| 127 |
+
|
| 128 |
+
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
| 129 |
+
|
| 130 |
+
z_model_state = zero_model_state(buffers=buffers,
|
| 131 |
+
param_shapes=param_shapes,
|
| 132 |
+
shared_params=shared_params,
|
| 133 |
+
ds_version=ds_version,
|
| 134 |
+
frozen_param_shapes=frozen_param_shapes,
|
| 135 |
+
frozen_param_fragments=frozen_param_fragments)
|
| 136 |
+
zero_model_states.append(z_model_state)
|
| 137 |
+
|
| 138 |
+
return zero_model_states
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
def parse_optim_states(files, ds_checkpoint_dir):
|
| 142 |
+
|
| 143 |
+
total_files = len(files)
|
| 144 |
+
state_dicts = []
|
| 145 |
+
for f in files:
|
| 146 |
+
state_dicts.append(torch.load(f, map_location=device))
|
| 147 |
+
|
| 148 |
+
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
| 149 |
+
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
| 150 |
+
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
| 151 |
+
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
| 152 |
+
|
| 153 |
+
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
| 154 |
+
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
| 155 |
+
# use the max of the partition_count to get the dp world_size.
|
| 156 |
+
|
| 157 |
+
if type(world_size) is list:
|
| 158 |
+
world_size = max(world_size)
|
| 159 |
+
|
| 160 |
+
if world_size != total_files:
|
| 161 |
+
raise ValueError(
|
| 162 |
+
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
| 163 |
+
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
| 164 |
+
)
|
| 165 |
+
|
| 166 |
+
# the groups are named differently in each stage
|
| 167 |
+
if zero_stage == 2:
|
| 168 |
+
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
| 169 |
+
elif zero_stage == 3:
|
| 170 |
+
fp32_groups_key = FP32_FLAT_GROUPS
|
| 171 |
+
else:
|
| 172 |
+
raise ValueError(f"unknown zero stage {zero_stage}")
|
| 173 |
+
|
| 174 |
+
if zero_stage == 2:
|
| 175 |
+
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
| 176 |
+
elif zero_stage == 3:
|
| 177 |
+
# if there is more than one param group, there will be multiple flattened tensors - one
|
| 178 |
+
# flattened tensor per group - for simplicity merge them into a single tensor
|
| 179 |
+
#
|
| 180 |
+
# XXX: could make the script more memory efficient for when there are multiple groups - it
|
| 181 |
+
# will require matching the sub-lists of param_shapes for each param group flattened tensor
|
| 182 |
+
|
| 183 |
+
fp32_flat_groups = [
|
| 184 |
+
torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
|
| 185 |
+
]
|
| 186 |
+
|
| 187 |
+
return zero_stage, world_size, fp32_flat_groups
|
| 188 |
+
|
| 189 |
+
|
| 190 |
+
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
|
| 191 |
+
"""
|
| 192 |
+
Returns fp32 state_dict reconstructed from ds checkpoint
|
| 193 |
+
|
| 194 |
+
Args:
|
| 195 |
+
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
| 196 |
+
|
| 197 |
+
"""
|
| 198 |
+
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
| 199 |
+
|
| 200 |
+
optim_files = get_optim_files(ds_checkpoint_dir)
|
| 201 |
+
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
| 202 |
+
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
| 203 |
+
|
| 204 |
+
model_files = get_model_state_files(ds_checkpoint_dir)
|
| 205 |
+
|
| 206 |
+
zero_model_states = parse_model_states(model_files)
|
| 207 |
+
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
| 208 |
+
|
| 209 |
+
if zero_stage == 2:
|
| 210 |
+
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states)
|
| 211 |
+
elif zero_stage == 3:
|
| 212 |
+
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
|
| 213 |
+
|
| 214 |
+
|
| 215 |
+
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
| 216 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 217 |
+
return
|
| 218 |
+
|
| 219 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 220 |
+
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
| 221 |
+
|
| 222 |
+
if debug:
|
| 223 |
+
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
| 224 |
+
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 225 |
+
|
| 226 |
+
wanted_params = len(frozen_param_shapes)
|
| 227 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 228 |
+
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
| 229 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 230 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 231 |
+
|
| 232 |
+
total_params = 0
|
| 233 |
+
total_numel = 0
|
| 234 |
+
for name, shape in frozen_param_shapes.items():
|
| 235 |
+
total_params += 1
|
| 236 |
+
unpartitioned_numel = shape.numel()
|
| 237 |
+
total_numel += unpartitioned_numel
|
| 238 |
+
|
| 239 |
+
state_dict[name] = frozen_param_fragments[name]
|
| 240 |
+
|
| 241 |
+
if debug:
|
| 242 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 243 |
+
|
| 244 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 245 |
+
|
| 246 |
+
|
| 247 |
+
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 248 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 249 |
+
|
| 250 |
+
# Reconstruction protocol:
|
| 251 |
+
#
|
| 252 |
+
# XXX: document this
|
| 253 |
+
|
| 254 |
+
if debug:
|
| 255 |
+
for i in range(world_size):
|
| 256 |
+
for j in range(len(fp32_flat_groups[0])):
|
| 257 |
+
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
| 258 |
+
|
| 259 |
+
# XXX: memory usage doubles here (zero2)
|
| 260 |
+
num_param_groups = len(fp32_flat_groups[0])
|
| 261 |
+
merged_single_partition_of_fp32_groups = []
|
| 262 |
+
for i in range(num_param_groups):
|
| 263 |
+
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
| 264 |
+
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
| 265 |
+
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
| 266 |
+
avail_numel = sum(
|
| 267 |
+
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
| 268 |
+
|
| 269 |
+
if debug:
|
| 270 |
+
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
| 271 |
+
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
| 272 |
+
# not asserting if there is a mismatch due to possible padding
|
| 273 |
+
print(f"Have {avail_numel} numels to process.")
|
| 274 |
+
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
| 275 |
+
|
| 276 |
+
# params
|
| 277 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 278 |
+
# out-of-core computing solution
|
| 279 |
+
total_numel = 0
|
| 280 |
+
total_params = 0
|
| 281 |
+
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
| 282 |
+
offset = 0
|
| 283 |
+
avail_numel = full_single_fp32_vector.numel()
|
| 284 |
+
for name, shape in shapes.items():
|
| 285 |
+
|
| 286 |
+
unpartitioned_numel = shape.numel()
|
| 287 |
+
total_numel += unpartitioned_numel
|
| 288 |
+
total_params += 1
|
| 289 |
+
|
| 290 |
+
if debug:
|
| 291 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 292 |
+
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
| 293 |
+
offset += unpartitioned_numel
|
| 294 |
+
|
| 295 |
+
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
| 296 |
+
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
| 297 |
+
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
| 298 |
+
# live optimizer object, so we are checking that the numbers are within the right range
|
| 299 |
+
align_to = 2 * world_size
|
| 300 |
+
|
| 301 |
+
def zero2_align(x):
|
| 302 |
+
return align_to * math.ceil(x / align_to)
|
| 303 |
+
|
| 304 |
+
if debug:
|
| 305 |
+
print(f"original offset={offset}, avail_numel={avail_numel}")
|
| 306 |
+
|
| 307 |
+
offset = zero2_align(offset)
|
| 308 |
+
avail_numel = zero2_align(avail_numel)
|
| 309 |
+
|
| 310 |
+
if debug:
|
| 311 |
+
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
| 312 |
+
|
| 313 |
+
# Sanity check
|
| 314 |
+
if offset != avail_numel:
|
| 315 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 316 |
+
|
| 317 |
+
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
| 318 |
+
|
| 319 |
+
|
| 320 |
+
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states):
|
| 321 |
+
state_dict = OrderedDict()
|
| 322 |
+
|
| 323 |
+
# buffers
|
| 324 |
+
buffers = zero_model_states[0].buffers
|
| 325 |
+
state_dict.update(buffers)
|
| 326 |
+
if debug:
|
| 327 |
+
print(f"added {len(buffers)} buffers")
|
| 328 |
+
|
| 329 |
+
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
| 330 |
+
|
| 331 |
+
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 332 |
+
|
| 333 |
+
# recover shared parameters
|
| 334 |
+
for pair in zero_model_states[0].shared_params:
|
| 335 |
+
if pair[1] in state_dict:
|
| 336 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 337 |
+
|
| 338 |
+
return state_dict
|
| 339 |
+
|
| 340 |
+
|
| 341 |
+
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
| 342 |
+
remainder = unpartitioned_numel % world_size
|
| 343 |
+
padding_numel = (world_size - remainder) if remainder else 0
|
| 344 |
+
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
| 345 |
+
return partitioned_numel, padding_numel
|
| 346 |
+
|
| 347 |
+
|
| 348 |
+
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
| 349 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 350 |
+
return
|
| 351 |
+
|
| 352 |
+
if debug:
|
| 353 |
+
for i in range(world_size):
|
| 354 |
+
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
| 355 |
+
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 356 |
+
|
| 357 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 358 |
+
wanted_params = len(frozen_param_shapes)
|
| 359 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 360 |
+
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
| 361 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 362 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 363 |
+
|
| 364 |
+
total_params = 0
|
| 365 |
+
total_numel = 0
|
| 366 |
+
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
| 367 |
+
total_params += 1
|
| 368 |
+
unpartitioned_numel = shape.numel()
|
| 369 |
+
total_numel += unpartitioned_numel
|
| 370 |
+
|
| 371 |
+
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
| 372 |
+
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 373 |
+
|
| 374 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 375 |
+
|
| 376 |
+
if debug:
|
| 377 |
+
print(
|
| 378 |
+
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 379 |
+
)
|
| 380 |
+
|
| 381 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 382 |
+
|
| 383 |
+
|
| 384 |
+
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 385 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 386 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 387 |
+
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
| 388 |
+
# param, re-consolidating each param, while dealing with padding if any
|
| 389 |
+
|
| 390 |
+
# merge list of dicts, preserving order
|
| 391 |
+
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
| 392 |
+
|
| 393 |
+
if debug:
|
| 394 |
+
for i in range(world_size):
|
| 395 |
+
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
| 396 |
+
|
| 397 |
+
wanted_params = len(param_shapes)
|
| 398 |
+
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
| 399 |
+
# not asserting if there is a mismatch due to possible padding
|
| 400 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 401 |
+
print(f"Trainable params: Have {avail_numel} numels to process.")
|
| 402 |
+
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
| 403 |
+
|
| 404 |
+
# params
|
| 405 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 406 |
+
# out-of-core computing solution
|
| 407 |
+
offset = 0
|
| 408 |
+
total_numel = 0
|
| 409 |
+
total_params = 0
|
| 410 |
+
for name, shape in param_shapes.items():
|
| 411 |
+
|
| 412 |
+
unpartitioned_numel = shape.numel()
|
| 413 |
+
total_numel += unpartitioned_numel
|
| 414 |
+
total_params += 1
|
| 415 |
+
|
| 416 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 417 |
+
|
| 418 |
+
if debug:
|
| 419 |
+
print(
|
| 420 |
+
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 421 |
+
)
|
| 422 |
+
|
| 423 |
+
# XXX: memory usage doubles here
|
| 424 |
+
state_dict[name] = torch.cat(
|
| 425 |
+
tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
|
| 426 |
+
0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 427 |
+
offset += partitioned_numel
|
| 428 |
+
|
| 429 |
+
offset *= world_size
|
| 430 |
+
|
| 431 |
+
# Sanity check
|
| 432 |
+
if offset != avail_numel:
|
| 433 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 434 |
+
|
| 435 |
+
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
| 436 |
+
|
| 437 |
+
|
| 438 |
+
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
|
| 439 |
+
state_dict = OrderedDict()
|
| 440 |
+
|
| 441 |
+
# buffers
|
| 442 |
+
buffers = zero_model_states[0].buffers
|
| 443 |
+
state_dict.update(buffers)
|
| 444 |
+
if debug:
|
| 445 |
+
print(f"added {len(buffers)} buffers")
|
| 446 |
+
|
| 447 |
+
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
| 448 |
+
|
| 449 |
+
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 450 |
+
|
| 451 |
+
# recover shared parameters
|
| 452 |
+
for pair in zero_model_states[0].shared_params:
|
| 453 |
+
if pair[1] in state_dict:
|
| 454 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 455 |
+
|
| 456 |
+
return state_dict
|
| 457 |
+
|
| 458 |
+
|
| 459 |
+
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
|
| 460 |
+
"""
|
| 461 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
| 462 |
+
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
| 463 |
+
via a model hub.
|
| 464 |
+
|
| 465 |
+
Args:
|
| 466 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder
|
| 467 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
| 468 |
+
|
| 469 |
+
Returns:
|
| 470 |
+
- pytorch ``state_dict``
|
| 471 |
+
|
| 472 |
+
Note: this approach may not work if your application doesn't have sufficient free CPU memory and
|
| 473 |
+
you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
| 474 |
+
the checkpoint.
|
| 475 |
+
|
| 476 |
+
A typical usage might be ::
|
| 477 |
+
|
| 478 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 479 |
+
# do the training and checkpoint saving
|
| 480 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
| 481 |
+
model = model.cpu() # move to cpu
|
| 482 |
+
model.load_state_dict(state_dict)
|
| 483 |
+
# submit to model hub or save the model to share with others
|
| 484 |
+
|
| 485 |
+
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
| 486 |
+
application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 487 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 488 |
+
|
| 489 |
+
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
| 490 |
+
|
| 491 |
+
"""
|
| 492 |
+
if tag is None:
|
| 493 |
+
latest_path = os.path.join(checkpoint_dir, 'latest')
|
| 494 |
+
if os.path.isfile(latest_path):
|
| 495 |
+
with open(latest_path, 'r') as fd:
|
| 496 |
+
tag = fd.read().strip()
|
| 497 |
+
else:
|
| 498 |
+
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
| 499 |
+
|
| 500 |
+
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
| 501 |
+
|
| 502 |
+
if not os.path.isdir(ds_checkpoint_dir):
|
| 503 |
+
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
| 504 |
+
|
| 505 |
+
return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
|
| 506 |
+
|
| 507 |
+
|
| 508 |
+
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
|
| 509 |
+
"""
|
| 510 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
| 511 |
+
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
| 512 |
+
|
| 513 |
+
Args:
|
| 514 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 515 |
+
- ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
|
| 516 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 517 |
+
"""
|
| 518 |
+
|
| 519 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
| 520 |
+
print(f"Saving fp32 state dict to {output_file}")
|
| 521 |
+
torch.save(state_dict, output_file)
|
| 522 |
+
|
| 523 |
+
|
| 524 |
+
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
| 525 |
+
"""
|
| 526 |
+
1. Put the provided model to cpu
|
| 527 |
+
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
| 528 |
+
3. Load it into the provided model
|
| 529 |
+
|
| 530 |
+
Args:
|
| 531 |
+
- ``model``: the model object to update
|
| 532 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 533 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 534 |
+
|
| 535 |
+
Returns:
|
| 536 |
+
- ``model`: modified model
|
| 537 |
+
|
| 538 |
+
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
| 539 |
+
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
| 540 |
+
conveniently placed for you in the checkpoint folder.
|
| 541 |
+
|
| 542 |
+
A typical usage might be ::
|
| 543 |
+
|
| 544 |
+
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
| 545 |
+
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
| 546 |
+
# submit to model hub or save the model to share with others
|
| 547 |
+
|
| 548 |
+
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
| 549 |
+
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 550 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 551 |
+
|
| 552 |
+
"""
|
| 553 |
+
logger.info(f"Extracting fp32 weights")
|
| 554 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
| 555 |
+
|
| 556 |
+
logger.info(f"Overwriting model with fp32 weights")
|
| 557 |
+
model = model.cpu()
|
| 558 |
+
model.load_state_dict(state_dict, strict=False)
|
| 559 |
+
|
| 560 |
+
return model
|
| 561 |
+
|
| 562 |
+
|
| 563 |
+
if __name__ == "__main__":
|
| 564 |
+
|
| 565 |
+
parser = argparse.ArgumentParser()
|
| 566 |
+
parser.add_argument("checkpoint_dir",
|
| 567 |
+
type=str,
|
| 568 |
+
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
| 569 |
+
parser.add_argument(
|
| 570 |
+
"output_file",
|
| 571 |
+
type=str,
|
| 572 |
+
help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
|
| 573 |
+
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
| 574 |
+
args = parser.parse_args()
|
| 575 |
+
|
| 576 |
+
debug = args.debug
|
| 577 |
+
|
| 578 |
+
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file)
|