Training in progress, step 370000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +203 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 202194449
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8884578ecff20bdc143758e28e0d85c34dad8dbfa37132c1e5318c8f80a9a1be
|
3 |
size 202194449
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 102501541
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:797df8ba5787bd4a5fbf872ca4b3fe3fdb3db1dba64902a8c55adee164838ae0
|
3 |
size 102501541
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc84ada216c0172437f14147bb53f92637e055287492931833e7c516a6d9eed3
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc84ada216c0172437f14147bb53f92637e055287492931833e7c516a6d9eed3
|
3 |
size 14503
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc84ada216c0172437f14147bb53f92637e055287492931833e7c516a6d9eed3
|
3 |
size 14503
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc84ada216c0172437f14147bb53f92637e055287492931833e7c516a6d9eed3
|
3 |
size 14503
|
last-checkpoint/rng_state_4.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc84ada216c0172437f14147bb53f92637e055287492931833e7c516a6d9eed3
|
3 |
size 14503
|
last-checkpoint/rng_state_5.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc84ada216c0172437f14147bb53f92637e055287492931833e7c516a6d9eed3
|
3 |
size 14503
|
last-checkpoint/rng_state_6.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc84ada216c0172437f14147bb53f92637e055287492931833e7c516a6d9eed3
|
3 |
size 14503
|
last-checkpoint/rng_state_7.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc84ada216c0172437f14147bb53f92637e055287492931833e7c516a6d9eed3
|
3 |
size 14503
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:580594f4768ecd1bd92e87dca92e874365a397305161c1f8781b79f1f0b613ba
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 9.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -7206,11 +7206,211 @@
|
|
7206 |
"eval_samples_per_second": 733.817,
|
7207 |
"eval_steps_per_second": 11.741,
|
7208 |
"step": 360000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7209 |
}
|
7210 |
],
|
7211 |
"max_steps": 500000,
|
7212 |
"num_train_epochs": 13,
|
7213 |
-
"total_flos": 1.
|
7214 |
"trial_name": null,
|
7215 |
"trial_params": null
|
7216 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 9.429634537947909,
|
5 |
+
"global_step": 370000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
7206 |
"eval_samples_per_second": 733.817,
|
7207 |
"eval_steps_per_second": 11.741,
|
7208 |
"step": 360000
|
7209 |
+
},
|
7210 |
+
{
|
7211 |
+
"epoch": 9.19,
|
7212 |
+
"learning_rate": 6.746049527150238e-05,
|
7213 |
+
"loss": 0.276,
|
7214 |
+
"step": 360500
|
7215 |
+
},
|
7216 |
+
{
|
7217 |
+
"epoch": 9.2,
|
7218 |
+
"learning_rate": 6.707871421704209e-05,
|
7219 |
+
"loss": 0.2757,
|
7220 |
+
"step": 361000
|
7221 |
+
},
|
7222 |
+
{
|
7223 |
+
"epoch": 9.2,
|
7224 |
+
"eval_loss": 0.8061186075210571,
|
7225 |
+
"eval_runtime": 1.2926,
|
7226 |
+
"eval_samples_per_second": 773.629,
|
7227 |
+
"eval_steps_per_second": 12.378,
|
7228 |
+
"step": 361000
|
7229 |
+
},
|
7230 |
+
{
|
7231 |
+
"epoch": 9.21,
|
7232 |
+
"learning_rate": 6.669789465567683e-05,
|
7233 |
+
"loss": 0.2754,
|
7234 |
+
"step": 361500
|
7235 |
+
},
|
7236 |
+
{
|
7237 |
+
"epoch": 9.23,
|
7238 |
+
"learning_rate": 6.631804075198838e-05,
|
7239 |
+
"loss": 0.2754,
|
7240 |
+
"step": 362000
|
7241 |
+
},
|
7242 |
+
{
|
7243 |
+
"epoch": 9.23,
|
7244 |
+
"eval_loss": 0.8106433153152466,
|
7245 |
+
"eval_runtime": 1.3154,
|
7246 |
+
"eval_samples_per_second": 760.201,
|
7247 |
+
"eval_steps_per_second": 12.163,
|
7248 |
+
"step": 362000
|
7249 |
+
},
|
7250 |
+
{
|
7251 |
+
"epoch": 9.24,
|
7252 |
+
"learning_rate": 6.593915665999816e-05,
|
7253 |
+
"loss": 0.275,
|
7254 |
+
"step": 362500
|
7255 |
+
},
|
7256 |
+
{
|
7257 |
+
"epoch": 9.25,
|
7258 |
+
"learning_rate": 6.55612465231219e-05,
|
7259 |
+
"loss": 0.2755,
|
7260 |
+
"step": 363000
|
7261 |
+
},
|
7262 |
+
{
|
7263 |
+
"epoch": 9.25,
|
7264 |
+
"eval_loss": 0.8047894835472107,
|
7265 |
+
"eval_runtime": 1.3007,
|
7266 |
+
"eval_samples_per_second": 768.793,
|
7267 |
+
"eval_steps_per_second": 12.301,
|
7268 |
+
"step": 363000
|
7269 |
+
},
|
7270 |
+
{
|
7271 |
+
"epoch": 9.26,
|
7272 |
+
"learning_rate": 6.518431447412434e-05,
|
7273 |
+
"loss": 0.2754,
|
7274 |
+
"step": 363500
|
7275 |
+
},
|
7276 |
+
{
|
7277 |
+
"epoch": 9.28,
|
7278 |
+
"learning_rate": 6.480836463507392e-05,
|
7279 |
+
"loss": 0.2753,
|
7280 |
+
"step": 364000
|
7281 |
+
},
|
7282 |
+
{
|
7283 |
+
"epoch": 9.28,
|
7284 |
+
"eval_loss": 0.8103929758071899,
|
7285 |
+
"eval_runtime": 1.3172,
|
7286 |
+
"eval_samples_per_second": 759.199,
|
7287 |
+
"eval_steps_per_second": 12.147,
|
7288 |
+
"step": 364000
|
7289 |
+
},
|
7290 |
+
{
|
7291 |
+
"epoch": 9.29,
|
7292 |
+
"learning_rate": 6.443340111729786e-05,
|
7293 |
+
"loss": 0.2753,
|
7294 |
+
"step": 364500
|
7295 |
+
},
|
7296 |
+
{
|
7297 |
+
"epoch": 9.3,
|
7298 |
+
"learning_rate": 6.405942802133713e-05,
|
7299 |
+
"loss": 0.2753,
|
7300 |
+
"step": 365000
|
7301 |
+
},
|
7302 |
+
{
|
7303 |
+
"epoch": 9.3,
|
7304 |
+
"eval_loss": 0.8095191717147827,
|
7305 |
+
"eval_runtime": 1.3369,
|
7306 |
+
"eval_samples_per_second": 747.972,
|
7307 |
+
"eval_steps_per_second": 11.968,
|
7308 |
+
"step": 365000
|
7309 |
+
},
|
7310 |
+
{
|
7311 |
+
"epoch": 9.31,
|
7312 |
+
"learning_rate": 6.36864494369016e-05,
|
7313 |
+
"loss": 0.2754,
|
7314 |
+
"step": 365500
|
7315 |
+
},
|
7316 |
+
{
|
7317 |
+
"epoch": 9.33,
|
7318 |
+
"learning_rate": 6.331446944282534e-05,
|
7319 |
+
"loss": 0.2753,
|
7320 |
+
"step": 366000
|
7321 |
+
},
|
7322 |
+
{
|
7323 |
+
"epoch": 9.33,
|
7324 |
+
"eval_loss": 0.8096633553504944,
|
7325 |
+
"eval_runtime": 1.2639,
|
7326 |
+
"eval_samples_per_second": 791.187,
|
7327 |
+
"eval_steps_per_second": 12.659,
|
7328 |
+
"step": 366000
|
7329 |
+
},
|
7330 |
+
{
|
7331 |
+
"epoch": 9.34,
|
7332 |
+
"learning_rate": 6.294349210702188e-05,
|
7333 |
+
"loss": 0.2748,
|
7334 |
+
"step": 366500
|
7335 |
+
},
|
7336 |
+
{
|
7337 |
+
"epoch": 9.35,
|
7338 |
+
"learning_rate": 6.257352148643998e-05,
|
7339 |
+
"loss": 0.2752,
|
7340 |
+
"step": 367000
|
7341 |
+
},
|
7342 |
+
{
|
7343 |
+
"epoch": 9.35,
|
7344 |
+
"eval_loss": 0.808983564376831,
|
7345 |
+
"eval_runtime": 1.349,
|
7346 |
+
"eval_samples_per_second": 741.265,
|
7347 |
+
"eval_steps_per_second": 11.86,
|
7348 |
+
"step": 367000
|
7349 |
+
},
|
7350 |
+
{
|
7351 |
+
"epoch": 9.37,
|
7352 |
+
"learning_rate": 6.220456162701908e-05,
|
7353 |
+
"loss": 0.2751,
|
7354 |
+
"step": 367500
|
7355 |
+
},
|
7356 |
+
{
|
7357 |
+
"epoch": 9.38,
|
7358 |
+
"learning_rate": 6.183661656364515e-05,
|
7359 |
+
"loss": 0.2749,
|
7360 |
+
"step": 368000
|
7361 |
+
},
|
7362 |
+
{
|
7363 |
+
"epoch": 9.38,
|
7364 |
+
"eval_loss": 0.8059231638908386,
|
7365 |
+
"eval_runtime": 1.3338,
|
7366 |
+
"eval_samples_per_second": 749.736,
|
7367 |
+
"eval_steps_per_second": 11.996,
|
7368 |
+
"step": 368000
|
7369 |
+
},
|
7370 |
+
{
|
7371 |
+
"epoch": 9.39,
|
7372 |
+
"learning_rate": 6.146969032010631e-05,
|
7373 |
+
"loss": 0.2747,
|
7374 |
+
"step": 368500
|
7375 |
+
},
|
7376 |
+
{
|
7377 |
+
"epoch": 9.4,
|
7378 |
+
"learning_rate": 6.110378690904928e-05,
|
7379 |
+
"loss": 0.2749,
|
7380 |
+
"step": 369000
|
7381 |
+
},
|
7382 |
+
{
|
7383 |
+
"epoch": 9.4,
|
7384 |
+
"eval_loss": 0.8113678097724915,
|
7385 |
+
"eval_runtime": 1.2927,
|
7386 |
+
"eval_samples_per_second": 773.561,
|
7387 |
+
"eval_steps_per_second": 12.377,
|
7388 |
+
"step": 369000
|
7389 |
+
},
|
7390 |
+
{
|
7391 |
+
"epoch": 9.42,
|
7392 |
+
"learning_rate": 6.073891033193507e-05,
|
7393 |
+
"loss": 0.2749,
|
7394 |
+
"step": 369500
|
7395 |
+
},
|
7396 |
+
{
|
7397 |
+
"epoch": 9.43,
|
7398 |
+
"learning_rate": 6.037506457899553e-05,
|
7399 |
+
"loss": 0.2747,
|
7400 |
+
"step": 370000
|
7401 |
+
},
|
7402 |
+
{
|
7403 |
+
"epoch": 9.43,
|
7404 |
+
"eval_loss": 0.8089262843132019,
|
7405 |
+
"eval_runtime": 1.3047,
|
7406 |
+
"eval_samples_per_second": 766.44,
|
7407 |
+
"eval_steps_per_second": 12.263,
|
7408 |
+
"step": 370000
|
7409 |
}
|
7410 |
],
|
7411 |
"max_steps": 500000,
|
7412 |
"num_train_epochs": 13,
|
7413 |
+
"total_flos": 1.1820902824439095e+22,
|
7414 |
"trial_name": null,
|
7415 |
"trial_params": null
|
7416 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 102501541
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:797df8ba5787bd4a5fbf872ca4b3fe3fdb3db1dba64902a8c55adee164838ae0
|
3 |
size 102501541
|