Training in progress, step 34000
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 sha256:9e2b0d7cefc425b3d7ba009dd1956ce75392b4667d1594eeb2397364bce8786a
|
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:a68d868dc3356a39282bd9e275365276ba9d6e04fc6a4a3a578025091d482c8b
|
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 sha256:249921c436c614149e5ab4a65621e75fe44abaa9e917306092c1b315a658722b
|
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:a5494c0bb5ab81adc18595af621da437a192bbd71d0d2c225fc7f8164b54c484
|
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,
|
@@ -408,11 +408,17 @@
|
|
408 |
"learning_rate": 1.1942045454545455e-05,
|
409 |
"loss": 0.0303,
|
410 |
"step": 33500
|
|
|
|
|
|
|
|
|
|
|
|
|
411 |
}
|
412 |
],
|
413 |
"max_steps": 44000,
|
414 |
"num_train_epochs": 1,
|
415 |
-
"total_flos": 3.
|
416 |
"trial_name": null,
|
417 |
"trial_params": null
|
418 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4612170704576901,
|
5 |
+
"global_step": 34000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
408 |
"learning_rate": 1.1942045454545455e-05,
|
409 |
"loss": 0.0303,
|
410 |
"step": 33500
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.46,
|
414 |
+
"learning_rate": 1.1373863636363637e-05,
|
415 |
+
"loss": 0.0295,
|
416 |
+
"step": 34000
|
417 |
}
|
418 |
],
|
419 |
"max_steps": 44000,
|
420 |
"num_train_epochs": 1,
|
421 |
+
"total_flos": 3.552625489556275e+16,
|
422 |
"trial_name": null,
|
423 |
"trial_params": null
|
424 |
}
|
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:a68d868dc3356a39282bd9e275365276ba9d6e04fc6a4a3a578025091d482c8b
|
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:bd860af2ad229cae00be2a346432d0aa4f453bde9b8c9d6aa6b49d8b068fc092
|
3 |
+
size 56430
|