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 sha256:84d04ccc31489825558be8a180eaff4b3ba9223048b5cc47608b94cfca9862ad
|
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 sha256:3836ff494a03c7bc08d1a0d4006d1a487a927c9d3a5a8c271baefdb9d1e32ed8
|
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 sha256:44c0423e56847800b1af441d71079abfec9949c463147562f7e3cd89bd866525
|
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 sha256:55a7345a6cfdf75ebeb1c0e85b1873ad7e56a0d7bade2b30beaf421286538ddf
|
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": 1.7181818181818184e-06,
|
517 |
"loss": 0.0302,
|
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": 1.7181818181818184e-06,
|
517 |
"loss": 0.0302,
|
518 |
"step": 42500
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 0.58,
|
522 |
+
"learning_rate": 1.15e-06,
|
523 |
+
"loss": 0.0308,
|
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 sha256:3836ff494a03c7bc08d1a0d4006d1a487a927c9d3a5a8c271baefdb9d1e32ed8
|
3 |
size 551185105
|
runs/Oct19_12-48-30_40567d3bb726/events.out.tfevents.1666183950.40567d3bb726.23.0
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:f77f6ed342e1796ff327d9e432776581efb67f4f1514b66eb20f1a796bc2650c
|
3 |
+
size 59310
|