Training in progress, step 1000000
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 893441093
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a41c0cfdbba59adb55e48f4497cb58e6acc6b3452b49124d5a5f0fe8e60c1ed5
|
3 |
size 893441093
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 449474181
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c27f116a4294f22674c90e68e437b33583a613d34e7b53d5073c3c54064bc66c
|
3 |
size 449474181
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 17641
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ff52e12d1ecb30cb53f7d49f3e0645dc2a062bffe7e31ad2d54f6553c1e3bcf
|
3 |
size 17641
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00fbdf9131638fc1a94afc0c7252f3e83640538433d010f21c313201f00efd8a
|
3 |
size 627
|
last-checkpoint/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,
|
@@ -7332,11 +7332,85 @@
|
|
7332 |
"eval_samples_per_second": 167.016,
|
7333 |
"eval_steps_per_second": 5.221,
|
7334 |
"step": 990000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7335 |
}
|
7336 |
],
|
7337 |
"max_steps": 1000000,
|
7338 |
"num_train_epochs": 72,
|
7339 |
-
"total_flos": 3.
|
7340 |
"trial_name": null,
|
7341 |
"trial_params": null
|
7342 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 71.11363959607452,
|
5 |
+
"global_step": 1000000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
7332 |
"eval_samples_per_second": 167.016,
|
7333 |
"eval_steps_per_second": 5.221,
|
7334 |
"step": 990000
|
7335 |
+
},
|
7336 |
+
{
|
7337 |
+
"epoch": 70.47,
|
7338 |
+
"learning_rate": 1.001439324972257e-05,
|
7339 |
+
"loss": 0.1073,
|
7340 |
+
"step": 991000
|
7341 |
+
},
|
7342 |
+
{
|
7343 |
+
"epoch": 70.54,
|
7344 |
+
"learning_rate": 1.0011372620416e-05,
|
7345 |
+
"loss": 0.1072,
|
7346 |
+
"step": 992000
|
7347 |
+
},
|
7348 |
+
{
|
7349 |
+
"epoch": 70.62,
|
7350 |
+
"learning_rate": 1.0008707281533315e-05,
|
7351 |
+
"loss": 0.1071,
|
7352 |
+
"step": 993000
|
7353 |
+
},
|
7354 |
+
{
|
7355 |
+
"epoch": 70.69,
|
7356 |
+
"learning_rate": 1.0006397262222235e-05,
|
7357 |
+
"loss": 0.1071,
|
7358 |
+
"step": 994000
|
7359 |
+
},
|
7360 |
+
{
|
7361 |
+
"epoch": 70.76,
|
7362 |
+
"learning_rate": 1.0004442587744758e-05,
|
7363 |
+
"loss": 0.107,
|
7364 |
+
"step": 995000
|
7365 |
+
},
|
7366 |
+
{
|
7367 |
+
"epoch": 70.76,
|
7368 |
+
"eval_runtime": 521.8934,
|
7369 |
+
"eval_samples_per_second": 168.45,
|
7370 |
+
"eval_steps_per_second": 5.265,
|
7371 |
+
"step": 995000
|
7372 |
+
},
|
7373 |
+
{
|
7374 |
+
"epoch": 70.83,
|
7375 |
+
"learning_rate": 1.0002843279476897e-05,
|
7376 |
+
"loss": 0.1068,
|
7377 |
+
"step": 996000
|
7378 |
+
},
|
7379 |
+
{
|
7380 |
+
"epoch": 70.9,
|
7381 |
+
"learning_rate": 1.0001599354908423e-05,
|
7382 |
+
"loss": 0.1071,
|
7383 |
+
"step": 997000
|
7384 |
+
},
|
7385 |
+
{
|
7386 |
+
"epoch": 70.97,
|
7387 |
+
"learning_rate": 1.0000710827642701e-05,
|
7388 |
+
"loss": 0.1072,
|
7389 |
+
"step": 998000
|
7390 |
+
},
|
7391 |
+
{
|
7392 |
+
"epoch": 71.04,
|
7393 |
+
"learning_rate": 1.0000177707396518e-05,
|
7394 |
+
"loss": 0.1068,
|
7395 |
+
"step": 999000
|
7396 |
+
},
|
7397 |
+
{
|
7398 |
+
"epoch": 71.11,
|
7399 |
+
"learning_rate": 1e-05,
|
7400 |
+
"loss": 0.1067,
|
7401 |
+
"step": 1000000
|
7402 |
+
},
|
7403 |
+
{
|
7404 |
+
"epoch": 71.11,
|
7405 |
+
"eval_runtime": 522.5962,
|
7406 |
+
"eval_samples_per_second": 168.224,
|
7407 |
+
"eval_steps_per_second": 5.258,
|
7408 |
+
"step": 1000000
|
7409 |
}
|
7410 |
],
|
7411 |
"max_steps": 1000000,
|
7412 |
"num_train_epochs": 72,
|
7413 |
+
"total_flos": 3.504995597979001e+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 449474181
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c27f116a4294f22674c90e68e437b33583a613d34e7b53d5073c3c54064bc66c
|
3 |
size 449474181
|