Training in progress, step 28500
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 sha256:40d7d6b4b24f7fc8cfbbadb3fc2a9b48c1679659e12b1ea7b977e9b412e8263c
|
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:e04274160d28650504ae69301f85e020a624c7b2c374399dd44235507a417ff1
|
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 sha256:76032163bdf981961aec2cc48085e7f7bc06d6f12f77dabe1586dea6b171945c
|
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:cb6486a869809777a873ef786105b2ce740463493d6cb1e4bc60cbe50f0921bd
|
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,
|
@@ -342,11 +342,17 @@
|
|
342 |
"learning_rate": 1.8192045454545457e-05,
|
343 |
"loss": 0.038,
|
344 |
"step": 28000
|
|
|
|
|
|
|
|
|
|
|
|
|
345 |
}
|
346 |
],
|
347 |
"max_steps": 44000,
|
348 |
"num_train_epochs": 1,
|
349 |
-
"total_flos": 2.
|
350 |
"trial_name": null,
|
351 |
"trial_params": null
|
352 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.38660842670718143,
|
5 |
+
"global_step": 28500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
342 |
"learning_rate": 1.8192045454545457e-05,
|
343 |
"loss": 0.038,
|
344 |
"step": 28000
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 0.39,
|
348 |
+
"learning_rate": 1.7623863636363637e-05,
|
349 |
+
"loss": 0.0298,
|
350 |
+
"step": 28500
|
351 |
}
|
352 |
],
|
353 |
"max_steps": 44000,
|
354 |
"num_train_epochs": 1,
|
355 |
+
"total_flos": 2.977969875399475e+16,
|
356 |
"trial_name": null,
|
357 |
"trial_params": null
|
358 |
}
|
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:e04274160d28650504ae69301f85e020a624c7b2c374399dd44235507a417ff1
|
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:d8d84b939646f97f8e0ebb3c9864761fb943d745ff5d0295ba6ec03e7a05b9e8
|
3 |
+
size 54670
|