Training in progress, step 100, checkpoint
Browse files- last-checkpoint/model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +2 -2
- last-checkpoint/rng_state_1.pth +2 -2
- last-checkpoint/rng_state_2.pth +3 -0
- last-checkpoint/rng_state_3.pth +3 -0
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +51 -497
- last-checkpoint/training_args.bin +1 -1
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 136062744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08823db6e7d3f7ecebdb39fa2abc5545b00f017474fd1d822068d0885a26f95d
|
| 3 |
size 136062744
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 138234066
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e7d7dc966642f5cf110823004ec8a086c5b5536e976261bf7da9bb4f9cbd57d
|
| 3 |
size 138234066
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4651e32e118f1ea1a8e26dfbbe64298593e12e6a71bcd36cb77f04f86d3f86d
|
| 3 |
+
size 15024
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0c1eba909fbb51daca773a25c075f182b4096aff21c9b4ff19dbada2080ac99
|
| 3 |
+
size 15024
|
last-checkpoint/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28adb9f06e220aefdc723ea4380a84d42b8bfb87cc53ce65859d55ce1876f51c
|
| 3 |
+
size 15024
|
last-checkpoint/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:423c49ed521f6986d20d8b29112b383f4b0f3f2e228084ef82c2ad7dcd5d1de8
|
| 3 |
+
size 15024
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,543 +1,97 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"eval_steps":
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch": 0.
|
| 13 |
-
"eval_loss": 3.
|
| 14 |
-
"eval_runtime":
|
| 15 |
-
"eval_samples_per_second":
|
| 16 |
-
"eval_steps_per_second": 4.
|
| 17 |
"step": 1
|
| 18 |
},
|
| 19 |
{
|
| 20 |
-
"epoch":
|
| 21 |
-
"grad_norm": 1.
|
| 22 |
-
"learning_rate":
|
| 23 |
-
"loss": 3.
|
| 24 |
"step": 10
|
| 25 |
},
|
| 26 |
{
|
| 27 |
-
"epoch":
|
| 28 |
-
"grad_norm":
|
| 29 |
-
"learning_rate": 0.
|
| 30 |
-
"loss":
|
| 31 |
"step": 20
|
| 32 |
},
|
| 33 |
{
|
| 34 |
-
"epoch":
|
| 35 |
-
"grad_norm": 0.
|
| 36 |
-
"learning_rate": 0.
|
| 37 |
-
"loss": 2.
|
| 38 |
"step": 30
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch":
|
| 42 |
-
"grad_norm": 0.
|
| 43 |
-
"learning_rate": 0.
|
| 44 |
-
"loss": 2.
|
| 45 |
"step": 40
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch":
|
| 49 |
-
"grad_norm": 0.
|
| 50 |
-
"learning_rate": 0.
|
| 51 |
-
"loss": 2.
|
| 52 |
-
"step": 50
|
| 53 |
-
},
|
| 54 |
-
{
|
| 55 |
-
"epoch": 3.8461538461538463,
|
| 56 |
-
"eval_loss": 2.814912796020508,
|
| 57 |
-
"eval_runtime": 5.762,
|
| 58 |
-
"eval_samples_per_second": 260.499,
|
| 59 |
-
"eval_steps_per_second": 4.165,
|
| 60 |
"step": 50
|
| 61 |
},
|
| 62 |
-
{
|
| 63 |
-
"epoch": 4.615384615384615,
|
| 64 |
-
"grad_norm": 0.71484375,
|
| 65 |
-
"learning_rate": 0.00019863613034027224,
|
| 66 |
-
"loss": 2.4698,
|
| 67 |
-
"step": 60
|
| 68 |
-
},
|
| 69 |
-
{
|
| 70 |
-
"epoch": 5.384615384615385,
|
| 71 |
-
"grad_norm": 0.7734375,
|
| 72 |
-
"learning_rate": 0.00019757963826274357,
|
| 73 |
-
"loss": 2.3909,
|
| 74 |
-
"step": 70
|
| 75 |
-
},
|
| 76 |
-
{
|
| 77 |
-
"epoch": 6.153846153846154,
|
| 78 |
-
"grad_norm": 0.765625,
|
| 79 |
-
"learning_rate": 0.00019622680003092503,
|
| 80 |
-
"loss": 2.2723,
|
| 81 |
-
"step": 80
|
| 82 |
-
},
|
| 83 |
-
{
|
| 84 |
-
"epoch": 6.923076923076923,
|
| 85 |
-
"grad_norm": 0.796875,
|
| 86 |
-
"learning_rate": 0.00019458172417006347,
|
| 87 |
-
"loss": 2.1816,
|
| 88 |
-
"step": 90
|
| 89 |
-
},
|
| 90 |
-
{
|
| 91 |
-
"epoch": 7.6923076923076925,
|
| 92 |
-
"grad_norm": 0.8203125,
|
| 93 |
-
"learning_rate": 0.00019264940672148018,
|
| 94 |
-
"loss": 2.0808,
|
| 95 |
-
"step": 100
|
| 96 |
-
},
|
| 97 |
-
{
|
| 98 |
-
"epoch": 7.6923076923076925,
|
| 99 |
-
"eval_loss": 2.966378927230835,
|
| 100 |
-
"eval_runtime": 5.6204,
|
| 101 |
-
"eval_samples_per_second": 267.064,
|
| 102 |
-
"eval_steps_per_second": 4.27,
|
| 103 |
-
"step": 100
|
| 104 |
-
},
|
| 105 |
-
{
|
| 106 |
-
"epoch": 8.461538461538462,
|
| 107 |
-
"grad_norm": 0.83984375,
|
| 108 |
-
"learning_rate": 0.00019043571606975777,
|
| 109 |
-
"loss": 1.9902,
|
| 110 |
-
"step": 110
|
| 111 |
-
},
|
| 112 |
-
{
|
| 113 |
-
"epoch": 9.23076923076923,
|
| 114 |
-
"grad_norm": 0.99609375,
|
| 115 |
-
"learning_rate": 0.0001879473751206489,
|
| 116 |
-
"loss": 1.9033,
|
| 117 |
-
"step": 120
|
| 118 |
-
},
|
| 119 |
{
|
| 120 |
"epoch": 10.0,
|
| 121 |
-
"grad_norm": 0.
|
| 122 |
-
"learning_rate": 0.00018519194088383273,
|
| 123 |
-
"loss": 1.8173,
|
| 124 |
-
"step": 130
|
| 125 |
-
},
|
| 126 |
-
{
|
| 127 |
-
"epoch": 10.76923076923077,
|
| 128 |
-
"grad_norm": 0.87890625,
|
| 129 |
-
"learning_rate": 0.0001821777815225245,
|
| 130 |
-
"loss": 1.7058,
|
| 131 |
-
"step": 140
|
| 132 |
-
},
|
| 133 |
-
{
|
| 134 |
-
"epoch": 11.538461538461538,
|
| 135 |
-
"grad_norm": 0.9296875,
|
| 136 |
-
"learning_rate": 0.00017891405093963938,
|
| 137 |
-
"loss": 1.6294,
|
| 138 |
-
"step": 150
|
| 139 |
-
},
|
| 140 |
-
{
|
| 141 |
-
"epoch": 11.538461538461538,
|
| 142 |
-
"eval_loss": 3.233675003051758,
|
| 143 |
-
"eval_runtime": 5.5692,
|
| 144 |
-
"eval_samples_per_second": 269.517,
|
| 145 |
-
"eval_steps_per_second": 4.309,
|
| 146 |
-
"step": 150
|
| 147 |
-
},
|
| 148 |
-
{
|
| 149 |
-
"epoch": 12.307692307692308,
|
| 150 |
-
"grad_norm": 0.9921875,
|
| 151 |
-
"learning_rate": 0.00017541066097768963,
|
| 152 |
-
"loss": 1.5563,
|
| 153 |
-
"step": 160
|
| 154 |
-
},
|
| 155 |
-
{
|
| 156 |
-
"epoch": 13.076923076923077,
|
| 157 |
-
"grad_norm": 1.0546875,
|
| 158 |
-
"learning_rate": 0.00017167825131684513,
|
| 159 |
-
"loss": 1.4865,
|
| 160 |
-
"step": 170
|
| 161 |
-
},
|
| 162 |
-
{
|
| 163 |
-
"epoch": 13.846153846153847,
|
| 164 |
-
"grad_norm": 0.94921875,
|
| 165 |
-
"learning_rate": 0.00016772815716257412,
|
| 166 |
-
"loss": 1.3938,
|
| 167 |
-
"step": 180
|
| 168 |
-
},
|
| 169 |
-
{
|
| 170 |
-
"epoch": 14.615384615384615,
|
| 171 |
-
"grad_norm": 0.90625,
|
| 172 |
-
"learning_rate": 0.00016357237482099684,
|
| 173 |
-
"loss": 1.3247,
|
| 174 |
-
"step": 190
|
| 175 |
-
},
|
| 176 |
-
{
|
| 177 |
-
"epoch": 15.384615384615385,
|
| 178 |
-
"grad_norm": 0.99609375,
|
| 179 |
-
"learning_rate": 0.00015922352526649803,
|
| 180 |
-
"loss": 1.2699,
|
| 181 |
-
"step": 200
|
| 182 |
-
},
|
| 183 |
-
{
|
| 184 |
-
"epoch": 15.384615384615385,
|
| 185 |
-
"eval_loss": 3.521737813949585,
|
| 186 |
-
"eval_runtime": 5.6468,
|
| 187 |
-
"eval_samples_per_second": 265.815,
|
| 188 |
-
"eval_steps_per_second": 4.25,
|
| 189 |
-
"step": 200
|
| 190 |
-
},
|
| 191 |
-
{
|
| 192 |
-
"epoch": 16.153846153846153,
|
| 193 |
-
"grad_norm": 0.95703125,
|
| 194 |
-
"learning_rate": 0.00015469481581224272,
|
| 195 |
-
"loss": 1.2117,
|
| 196 |
-
"step": 210
|
| 197 |
-
},
|
| 198 |
-
{
|
| 199 |
-
"epoch": 16.923076923076923,
|
| 200 |
-
"grad_norm": 1.0390625,
|
| 201 |
-
"learning_rate": 0.00015000000000000001,
|
| 202 |
-
"loss": 1.1498,
|
| 203 |
-
"step": 220
|
| 204 |
-
},
|
| 205 |
-
{
|
| 206 |
-
"epoch": 17.692307692307693,
|
| 207 |
-
"grad_norm": 1.0078125,
|
| 208 |
-
"learning_rate": 0.00014515333583108896,
|
| 209 |
-
"loss": 1.0864,
|
| 210 |
-
"step": 230
|
| 211 |
-
},
|
| 212 |
-
{
|
| 213 |
-
"epoch": 18.46153846153846,
|
| 214 |
-
"grad_norm": 0.81640625,
|
| 215 |
-
"learning_rate": 0.00014016954246529696,
|
| 216 |
-
"loss": 1.0441,
|
| 217 |
-
"step": 240
|
| 218 |
-
},
|
| 219 |
-
{
|
| 220 |
-
"epoch": 19.23076923076923,
|
| 221 |
-
"grad_norm": 0.98828125,
|
| 222 |
-
"learning_rate": 0.00013506375551927547,
|
| 223 |
-
"loss": 1.0092,
|
| 224 |
-
"step": 250
|
| 225 |
-
},
|
| 226 |
-
{
|
| 227 |
-
"epoch": 19.23076923076923,
|
| 228 |
-
"eval_loss": 3.726165533065796,
|
| 229 |
-
"eval_runtime": 5.8207,
|
| 230 |
-
"eval_samples_per_second": 257.872,
|
| 231 |
-
"eval_steps_per_second": 4.123,
|
| 232 |
-
"step": 250
|
| 233 |
-
},
|
| 234 |
-
{
|
| 235 |
-
"epoch": 20.0,
|
| 236 |
-
"grad_norm": 0.8359375,
|
| 237 |
-
"learning_rate": 0.00012985148110016947,
|
| 238 |
-
"loss": 0.9671,
|
| 239 |
-
"step": 260
|
| 240 |
-
},
|
| 241 |
-
{
|
| 242 |
-
"epoch": 20.76923076923077,
|
| 243 |
-
"grad_norm": 0.8203125,
|
| 244 |
-
"learning_rate": 0.00012454854871407994,
|
| 245 |
-
"loss": 0.9182,
|
| 246 |
-
"step": 270
|
| 247 |
-
},
|
| 248 |
-
{
|
| 249 |
-
"epoch": 21.53846153846154,
|
| 250 |
-
"grad_norm": 0.796875,
|
| 251 |
-
"learning_rate": 0.00011917106319237386,
|
| 252 |
-
"loss": 0.8857,
|
| 253 |
-
"step": 280
|
| 254 |
-
},
|
| 255 |
-
{
|
| 256 |
-
"epoch": 22.307692307692307,
|
| 257 |
-
"grad_norm": 0.79296875,
|
| 258 |
-
"learning_rate": 0.00011373535578184082,
|
| 259 |
-
"loss": 0.8623,
|
| 260 |
-
"step": 290
|
| 261 |
-
},
|
| 262 |
-
{
|
| 263 |
-
"epoch": 23.076923076923077,
|
| 264 |
-
"grad_norm": 0.7421875,
|
| 265 |
-
"learning_rate": 0.00010825793454723325,
|
| 266 |
-
"loss": 0.8392,
|
| 267 |
-
"step": 300
|
| 268 |
-
},
|
| 269 |
-
{
|
| 270 |
-
"epoch": 23.076923076923077,
|
| 271 |
-
"eval_loss": 3.868284225463867,
|
| 272 |
-
"eval_runtime": 5.7191,
|
| 273 |
-
"eval_samples_per_second": 262.455,
|
| 274 |
-
"eval_steps_per_second": 4.196,
|
| 275 |
-
"step": 300
|
| 276 |
-
},
|
| 277 |
-
{
|
| 278 |
-
"epoch": 23.846153846153847,
|
| 279 |
-
"grad_norm": 0.75,
|
| 280 |
-
"learning_rate": 0.00010275543423681621,
|
| 281 |
-
"loss": 0.8103,
|
| 282 |
-
"step": 310
|
| 283 |
-
},
|
| 284 |
-
{
|
| 285 |
-
"epoch": 24.615384615384617,
|
| 286 |
-
"grad_norm": 0.75390625,
|
| 287 |
-
"learning_rate": 9.724456576318381e-05,
|
| 288 |
-
"loss": 0.7828,
|
| 289 |
-
"step": 320
|
| 290 |
-
},
|
| 291 |
-
{
|
| 292 |
-
"epoch": 25.384615384615383,
|
| 293 |
-
"grad_norm": 0.7265625,
|
| 294 |
-
"learning_rate": 9.174206545276677e-05,
|
| 295 |
-
"loss": 0.7749,
|
| 296 |
-
"step": 330
|
| 297 |
-
},
|
| 298 |
-
{
|
| 299 |
-
"epoch": 26.153846153846153,
|
| 300 |
-
"grad_norm": 0.74609375,
|
| 301 |
-
"learning_rate": 8.626464421815919e-05,
|
| 302 |
-
"loss": 0.7574,
|
| 303 |
-
"step": 340
|
| 304 |
-
},
|
| 305 |
-
{
|
| 306 |
-
"epoch": 26.923076923076923,
|
| 307 |
-
"grad_norm": 0.6875,
|
| 308 |
-
"learning_rate": 8.082893680762619e-05,
|
| 309 |
-
"loss": 0.7428,
|
| 310 |
-
"step": 350
|
| 311 |
-
},
|
| 312 |
-
{
|
| 313 |
-
"epoch": 26.923076923076923,
|
| 314 |
-
"eval_loss": 3.9434773921966553,
|
| 315 |
-
"eval_runtime": 5.6325,
|
| 316 |
-
"eval_samples_per_second": 266.49,
|
| 317 |
-
"eval_steps_per_second": 4.261,
|
| 318 |
-
"step": 350
|
| 319 |
-
},
|
| 320 |
-
{
|
| 321 |
-
"epoch": 27.692307692307693,
|
| 322 |
-
"grad_norm": 0.6953125,
|
| 323 |
"learning_rate": 7.54514512859201e-05,
|
| 324 |
-
"loss":
|
| 325 |
-
"step":
|
| 326 |
-
},
|
| 327 |
-
{
|
| 328 |
-
"epoch": 28.46153846153846,
|
| 329 |
-
"grad_norm": 0.66015625,
|
| 330 |
-
"learning_rate": 7.014851889983057e-05,
|
| 331 |
-
"loss": 0.7167,
|
| 332 |
-
"step": 370
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 29.23076923076923,
|
| 336 |
-
"grad_norm": 0.65625,
|
| 337 |
-
"learning_rate": 6.493624448072457e-05,
|
| 338 |
-
"loss": 0.7147,
|
| 339 |
-
"step": 380
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 30.0,
|
| 343 |
-
"grad_norm": 0.69140625,
|
| 344 |
-
"learning_rate": 5.983045753470308e-05,
|
| 345 |
-
"loss": 0.7019,
|
| 346 |
-
"step": 390
|
| 347 |
-
},
|
| 348 |
-
{
|
| 349 |
-
"epoch": 30.76923076923077,
|
| 350 |
-
"grad_norm": 0.66796875,
|
| 351 |
-
"learning_rate": 5.484666416891109e-05,
|
| 352 |
-
"loss": 0.6952,
|
| 353 |
-
"step": 400
|
| 354 |
-
},
|
| 355 |
-
{
|
| 356 |
-
"epoch": 30.76923076923077,
|
| 357 |
-
"eval_loss": 3.985978841781616,
|
| 358 |
-
"eval_runtime": 5.6438,
|
| 359 |
-
"eval_samples_per_second": 265.955,
|
| 360 |
-
"eval_steps_per_second": 4.252,
|
| 361 |
-
"step": 400
|
| 362 |
-
},
|
| 363 |
-
{
|
| 364 |
-
"epoch": 31.53846153846154,
|
| 365 |
-
"grad_norm": 0.6484375,
|
| 366 |
-
"learning_rate": 5.000000000000002e-05,
|
| 367 |
-
"loss": 0.6901,
|
| 368 |
-
"step": 410
|
| 369 |
},
|
| 370 |
{
|
| 371 |
-
"epoch":
|
| 372 |
-
"grad_norm": 0.
|
| 373 |
"learning_rate": 4.530518418775733e-05,
|
| 374 |
-
"loss":
|
| 375 |
-
"step":
|
| 376 |
-
},
|
| 377 |
-
{
|
| 378 |
-
"epoch": 33.07692307692308,
|
| 379 |
-
"grad_norm": 0.62890625,
|
| 380 |
-
"learning_rate": 4.077647473350201e-05,
|
| 381 |
-
"loss": 0.6851,
|
| 382 |
-
"step": 430
|
| 383 |
-
},
|
| 384 |
-
{
|
| 385 |
-
"epoch": 33.84615384615385,
|
| 386 |
-
"grad_norm": 0.62109375,
|
| 387 |
-
"learning_rate": 3.642762517900322e-05,
|
| 388 |
-
"loss": 0.6782,
|
| 389 |
-
"step": 440
|
| 390 |
-
},
|
| 391 |
-
{
|
| 392 |
-
"epoch": 34.61538461538461,
|
| 393 |
-
"grad_norm": 0.6171875,
|
| 394 |
-
"learning_rate": 3.227184283742591e-05,
|
| 395 |
-
"loss": 0.6762,
|
| 396 |
-
"step": 450
|
| 397 |
-
},
|
| 398 |
-
{
|
| 399 |
-
"epoch": 34.61538461538461,
|
| 400 |
-
"eval_loss": 3.998966932296753,
|
| 401 |
-
"eval_runtime": 5.7156,
|
| 402 |
-
"eval_samples_per_second": 262.613,
|
| 403 |
-
"eval_steps_per_second": 4.199,
|
| 404 |
-
"step": 450
|
| 405 |
-
},
|
| 406 |
-
{
|
| 407 |
-
"epoch": 35.38461538461539,
|
| 408 |
-
"grad_norm": 0.62109375,
|
| 409 |
-
"learning_rate": 2.8321748683154893e-05,
|
| 410 |
-
"loss": 0.6742,
|
| 411 |
-
"step": 460
|
| 412 |
-
},
|
| 413 |
-
{
|
| 414 |
-
"epoch": 36.15384615384615,
|
| 415 |
-
"grad_norm": 0.6171875,
|
| 416 |
-
"learning_rate": 2.4589339022310386e-05,
|
| 417 |
-
"loss": 0.674,
|
| 418 |
-
"step": 470
|
| 419 |
},
|
| 420 |
{
|
| 421 |
-
"epoch":
|
| 422 |
-
"grad_norm": 0.
|
| 423 |
"learning_rate": 2.1085949060360654e-05,
|
| 424 |
-
"loss":
|
| 425 |
-
"step":
|
| 426 |
-
},
|
| 427 |
-
{
|
| 428 |
-
"epoch": 37.69230769230769,
|
| 429 |
-
"grad_norm": 0.6171875,
|
| 430 |
-
"learning_rate": 1.7822218477475494e-05,
|
| 431 |
-
"loss": 0.6681,
|
| 432 |
-
"step": 490
|
| 433 |
-
},
|
| 434 |
-
{
|
| 435 |
-
"epoch": 38.46153846153846,
|
| 436 |
-
"grad_norm": 0.62109375,
|
| 437 |
-
"learning_rate": 1.4808059116167305e-05,
|
| 438 |
-
"loss": 0.6739,
|
| 439 |
-
"step": 500
|
| 440 |
-
},
|
| 441 |
-
{
|
| 442 |
-
"epoch": 38.46153846153846,
|
| 443 |
-
"eval_loss": 4.016704559326172,
|
| 444 |
-
"eval_runtime": 5.9697,
|
| 445 |
-
"eval_samples_per_second": 251.437,
|
| 446 |
-
"eval_steps_per_second": 4.02,
|
| 447 |
-
"step": 500
|
| 448 |
-
},
|
| 449 |
-
{
|
| 450 |
-
"epoch": 39.23076923076923,
|
| 451 |
-
"grad_norm": 0.61328125,
|
| 452 |
-
"learning_rate": 1.2052624879351104e-05,
|
| 453 |
-
"loss": 0.6685,
|
| 454 |
-
"step": 510
|
| 455 |
-
},
|
| 456 |
-
{
|
| 457 |
-
"epoch": 40.0,
|
| 458 |
-
"grad_norm": 0.625,
|
| 459 |
-
"learning_rate": 9.564283930242257e-06,
|
| 460 |
-
"loss": 0.6697,
|
| 461 |
-
"step": 520
|
| 462 |
-
},
|
| 463 |
-
{
|
| 464 |
-
"epoch": 40.76923076923077,
|
| 465 |
-
"grad_norm": 0.60546875,
|
| 466 |
-
"learning_rate": 7.350593278519824e-06,
|
| 467 |
-
"loss": 0.6691,
|
| 468 |
-
"step": 530
|
| 469 |
},
|
| 470 |
{
|
| 471 |
-
"epoch":
|
| 472 |
-
"grad_norm": 0.
|
| 473 |
"learning_rate": 5.418275829936537e-06,
|
| 474 |
-
"loss":
|
| 475 |
-
"step":
|
| 476 |
-
},
|
| 477 |
-
{
|
| 478 |
-
"epoch": 42.30769230769231,
|
| 479 |
-
"grad_norm": 0.62109375,
|
| 480 |
-
"learning_rate": 3.7731999690749585e-06,
|
| 481 |
-
"loss": 0.6691,
|
| 482 |
-
"step": 550
|
| 483 |
-
},
|
| 484 |
-
{
|
| 485 |
-
"epoch": 42.30769230769231,
|
| 486 |
-
"eval_loss": 4.020811080932617,
|
| 487 |
-
"eval_runtime": 5.6558,
|
| 488 |
-
"eval_samples_per_second": 265.392,
|
| 489 |
-
"eval_steps_per_second": 4.243,
|
| 490 |
-
"step": 550
|
| 491 |
-
},
|
| 492 |
-
{
|
| 493 |
-
"epoch": 43.07692307692308,
|
| 494 |
-
"grad_norm": 0.61328125,
|
| 495 |
-
"learning_rate": 2.420361737256438e-06,
|
| 496 |
-
"loss": 0.6671,
|
| 497 |
-
"step": 560
|
| 498 |
-
},
|
| 499 |
-
{
|
| 500 |
-
"epoch": 43.84615384615385,
|
| 501 |
-
"grad_norm": 0.62890625,
|
| 502 |
-
"learning_rate": 1.3638696597277679e-06,
|
| 503 |
-
"loss": 0.6683,
|
| 504 |
-
"step": 570
|
| 505 |
-
},
|
| 506 |
-
{
|
| 507 |
-
"epoch": 44.61538461538461,
|
| 508 |
-
"grad_norm": 0.59375,
|
| 509 |
-
"learning_rate": 6.069322682050516e-07,
|
| 510 |
-
"loss": 0.6714,
|
| 511 |
-
"step": 580
|
| 512 |
-
},
|
| 513 |
-
{
|
| 514 |
-
"epoch": 45.38461538461539,
|
| 515 |
-
"grad_norm": 0.6015625,
|
| 516 |
-
"learning_rate": 1.518483566683826e-07,
|
| 517 |
-
"loss": 0.6695,
|
| 518 |
-
"step": 590
|
| 519 |
},
|
| 520 |
{
|
| 521 |
-
"epoch":
|
| 522 |
-
"grad_norm": 0.
|
| 523 |
"learning_rate": 0.0,
|
| 524 |
-
"loss":
|
| 525 |
-
"step":
|
| 526 |
-
},
|
| 527 |
-
{
|
| 528 |
-
"epoch": 46.15384615384615,
|
| 529 |
-
"eval_loss": 4.010259628295898,
|
| 530 |
-
"eval_runtime": 5.6787,
|
| 531 |
-
"eval_samples_per_second": 264.32,
|
| 532 |
-
"eval_steps_per_second": 4.226,
|
| 533 |
-
"step": 600
|
| 534 |
}
|
| 535 |
],
|
| 536 |
"logging_steps": 10,
|
| 537 |
-
"max_steps":
|
| 538 |
"num_input_tokens_seen": 0,
|
| 539 |
-
"num_train_epochs":
|
| 540 |
-
"save_steps":
|
| 541 |
"stateful_callbacks": {
|
| 542 |
"TrainerControl": {
|
| 543 |
"args": {
|
|
@@ -550,7 +104,7 @@
|
|
| 550 |
"attributes": {}
|
| 551 |
}
|
| 552 |
},
|
| 553 |
-
"total_flos":
|
| 554 |
"train_batch_size": 32,
|
| 555 |
"trial_name": null,
|
| 556 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 16.666666666666668,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.16666666666666666,
|
| 13 |
+
"eval_loss": 3.9322755336761475,
|
| 14 |
+
"eval_runtime": 2.5681,
|
| 15 |
+
"eval_samples_per_second": 584.476,
|
| 16 |
+
"eval_steps_per_second": 4.673,
|
| 17 |
"step": 1
|
| 18 |
},
|
| 19 |
{
|
| 20 |
+
"epoch": 1.6666666666666665,
|
| 21 |
+
"grad_norm": 1.1328125,
|
| 22 |
+
"learning_rate": 0.00019863613034027224,
|
| 23 |
+
"loss": 3.2122,
|
| 24 |
"step": 10
|
| 25 |
},
|
| 26 |
{
|
| 27 |
+
"epoch": 3.3333333333333335,
|
| 28 |
+
"grad_norm": 0.671875,
|
| 29 |
+
"learning_rate": 0.0001879473751206489,
|
| 30 |
+
"loss": 2.8046,
|
| 31 |
"step": 20
|
| 32 |
},
|
| 33 |
{
|
| 34 |
+
"epoch": 5.0,
|
| 35 |
+
"grad_norm": 0.5078125,
|
| 36 |
+
"learning_rate": 0.00016772815716257412,
|
| 37 |
+
"loss": 2.6022,
|
| 38 |
"step": 30
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 6.666666666666667,
|
| 42 |
+
"grad_norm": 0.482421875,
|
| 43 |
+
"learning_rate": 0.00014016954246529696,
|
| 44 |
+
"loss": 2.4584,
|
| 45 |
"step": 40
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 8.333333333333334,
|
| 49 |
+
"grad_norm": 0.439453125,
|
| 50 |
+
"learning_rate": 0.00010825793454723325,
|
| 51 |
+
"loss": 2.3679,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
"step": 50
|
| 53 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
{
|
| 55 |
"epoch": 10.0,
|
| 56 |
+
"grad_norm": 0.423828125,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
"learning_rate": 7.54514512859201e-05,
|
| 58 |
+
"loss": 2.3013,
|
| 59 |
+
"step": 60
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
},
|
| 61 |
{
|
| 62 |
+
"epoch": 11.666666666666666,
|
| 63 |
+
"grad_norm": 0.40625,
|
| 64 |
"learning_rate": 4.530518418775733e-05,
|
| 65 |
+
"loss": 2.2634,
|
| 66 |
+
"step": 70
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
},
|
| 68 |
{
|
| 69 |
+
"epoch": 13.333333333333334,
|
| 70 |
+
"grad_norm": 0.392578125,
|
| 71 |
"learning_rate": 2.1085949060360654e-05,
|
| 72 |
+
"loss": 2.252,
|
| 73 |
+
"step": 80
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 74 |
},
|
| 75 |
{
|
| 76 |
+
"epoch": 15.0,
|
| 77 |
+
"grad_norm": 0.392578125,
|
| 78 |
"learning_rate": 5.418275829936537e-06,
|
| 79 |
+
"loss": 2.2463,
|
| 80 |
+
"step": 90
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 16.666666666666668,
|
| 84 |
+
"grad_norm": 0.396484375,
|
| 85 |
"learning_rate": 0.0,
|
| 86 |
+
"loss": 2.2461,
|
| 87 |
+
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 88 |
}
|
| 89 |
],
|
| 90 |
"logging_steps": 10,
|
| 91 |
+
"max_steps": 100,
|
| 92 |
"num_input_tokens_seen": 0,
|
| 93 |
+
"num_train_epochs": 17,
|
| 94 |
+
"save_steps": 200,
|
| 95 |
"stateful_callbacks": {
|
| 96 |
"TrainerControl": {
|
| 97 |
"args": {
|
|
|
|
| 104 |
"attributes": {}
|
| 105 |
}
|
| 106 |
},
|
| 107 |
+
"total_flos": 6834755941171200.0,
|
| 108 |
"train_batch_size": 32,
|
| 109 |
"trial_name": null,
|
| 110 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6840
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c99f76655201d3a5e646acd9bbe970d07860ce4d230a73ef72b05ccbd756ed49
|
| 3 |
size 6840
|