Training in progress, step 27000
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 sha256:34d175ceeb60089ae591f15c4b744f6579eeafea76ffb227ae2bdbaf726e0060
|
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 sha256:7a7835ef7e3313d361291f104ab9cd8713ad97d972993c99dfde1b63e42d2b29
|
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 sha256:622cbe0fdcc45c7d55b7d02cb0e754bb7b8ccf9bb05cc6397ae4a14e2e372cc5
|
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:e5506114f96050eac236e76ed0c9f8e3296a268f48a496ff81995a444664e23c
|
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,
|
@@ -324,11 +324,17 @@
|
|
324 |
"learning_rate": 1.9895454545454548e-05,
|
325 |
"loss": 0.0316,
|
326 |
"step": 26500
|
|
|
|
|
|
|
|
|
|
|
|
|
327 |
}
|
328 |
],
|
329 |
"max_steps": 44000,
|
330 |
"num_train_epochs": 1,
|
331 |
-
"total_flos": 2.
|
332 |
"trial_name": null,
|
333 |
"trial_params": null
|
334 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.3662606147752245,
|
5 |
+
"global_step": 27000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
324 |
"learning_rate": 1.9895454545454548e-05,
|
325 |
"loss": 0.0316,
|
326 |
"step": 26500
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.37,
|
330 |
+
"learning_rate": 1.9327272727272728e-05,
|
331 |
+
"loss": 0.0327,
|
332 |
+
"step": 27000
|
333 |
}
|
334 |
],
|
335 |
"max_steps": 44000,
|
336 |
"num_train_epochs": 1,
|
337 |
+
"total_flos": 2.821245616993075e+16,
|
338 |
"trial_name": null,
|
339 |
"trial_params": null
|
340 |
}
|
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 sha256:7a7835ef7e3313d361291f104ab9cd8713ad97d972993c99dfde1b63e42d2b29
|
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:fe22113a9dcb97d953935ed4c1f8030beaef530ec0909559f4d794af98e18992
|
3 |
+
size 54190
|