Training in progress, step 43000
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 1001681601
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8c387d1f618116a2d88801bc9cc6c4d7504d5277af93f6b007c47d2247542ad
|
3 |
size 1001681601
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 551185105
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f2e879ad81817b2f5162a22890ad784829fbae435ce67977e13e88a33d460e0
|
3 |
size 551185105
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38db93d04e7435809f2b90563dd7aafd4827e877fffeecabb0f1217b47849516
|
3 |
size 559
|
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:a222479049bc9f5bc593f20dae078ae63b08d00a6021d9c3814b19b4b39e494c
|
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": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -516,11 +516,17 @@
|
|
516 |
"learning_rate": 3.445454545454545e-09,
|
517 |
"loss": 0.0263,
|
518 |
"step": 42500
|
|
|
|
|
|
|
|
|
|
|
|
|
519 |
}
|
520 |
],
|
521 |
"max_steps": 44000,
|
522 |
"num_train_epochs": 1,
|
523 |
-
"total_flos": 4.
|
524 |
"trial_name": null,
|
525 |
"trial_params": null
|
526 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5833039420494316,
|
5 |
+
"global_step": 43000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
516 |
"learning_rate": 3.445454545454545e-09,
|
517 |
"loss": 0.0263,
|
518 |
"step": 42500
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 0.58,
|
522 |
+
"learning_rate": 2.309090909090909e-09,
|
523 |
+
"loss": 0.0257,
|
524 |
+
"step": 43000
|
525 |
}
|
526 |
],
|
527 |
"max_steps": 44000,
|
528 |
"num_train_epochs": 1,
|
529 |
+
"total_flos": 4.492971039994675e+16,
|
530 |
"trial_name": null,
|
531 |
"trial_params": null
|
532 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 551185105
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f2e879ad81817b2f5162a22890ad784829fbae435ce67977e13e88a33d460e0
|
3 |
size 551185105
|
runs/Oct24_08-39-52_00e58a194ed0/events.out.tfevents.1666601028.00e58a194ed0.23.0
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:f57a000308bcc2d338d5b5f6e8ab1b7e04f6e1ed6c7f65e86bf2deb198319048
|
3 |
+
size 59310
|