Training in progress, step 25500
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:c994645db6d5d599fcef94036912b7e487c1c03515a1a9751d4b72357a5b6b43
|
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 sha256:10b0ba5e55b025622252c015b4d6a75b940bc980ccd844fa8541f73bf0ee3aa3
|
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 sha256:3b51a2c12aa5e5c5bb8ad4bad155d4836ecb099e0fb15393e5dbcd575b8f505b
|
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:d545287429cb3322d6a13141eeda62ee7d1dca530ea52e59079ed5d3bb68ec63
|
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,
|
@@ -306,11 +306,17 @@
|
|
306 |
"learning_rate": 2.1598863636363635e-05,
|
307 |
"loss": 0.0327,
|
308 |
"step": 25000
|
|
|
|
|
|
|
|
|
|
|
|
|
309 |
}
|
310 |
],
|
311 |
"max_steps": 44000,
|
312 |
"num_train_epochs": 1,
|
313 |
-
"total_flos": 2.
|
314 |
"trial_name": null,
|
315 |
"trial_params": null
|
316 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.3459128028432676,
|
5 |
+
"global_step": 25500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
306 |
"learning_rate": 2.1598863636363635e-05,
|
307 |
"loss": 0.0327,
|
308 |
"step": 25000
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.35,
|
312 |
+
"learning_rate": 2.103068181818182e-05,
|
313 |
+
"loss": 0.0303,
|
314 |
+
"step": 25500
|
315 |
}
|
316 |
],
|
317 |
"max_steps": 44000,
|
318 |
"num_train_epochs": 1,
|
319 |
+
"total_flos": 2.664521358586675e+16,
|
320 |
"trial_name": null,
|
321 |
"trial_params": null
|
322 |
}
|
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 sha256:10b0ba5e55b025622252c015b4d6a75b940bc980ccd844fa8541f73bf0ee3aa3
|
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:cac71812d6feb03eed0c56f168dbead49de17ebfa3c53c63744c6ad623321380
|
3 |
+
size 53710
|