Training in progress, step 27500
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 sha256:9a2b98efdf1cf2e63bd3a7637e763bc4a9c4911a3b814d096182f0fa150f2a0d
|
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 sha256:44a2b8d9a599359b00e747730cd1665872fdb98e6218c96ba987585dd9ba73c2
|
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 sha256:7a1346239025060fcc17f30ecb28384f79c7cc4e7c861714d542800e3acb0fb0
|
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 sha256:7891b57b3cb8df38800764b8bcbf3ca1a2a82de00c931905e25fba7619593b0f
|
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,
|
@@ -330,11 +330,17 @@
|
|
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.
|
338 |
"trial_name": null,
|
339 |
"trial_params": null
|
340 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.3730432187525435,
|
5 |
+
"global_step": 27500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
330 |
"learning_rate": 1.9327272727272728e-05,
|
331 |
"loss": 0.0327,
|
332 |
"step": 27000
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.37,
|
336 |
+
"learning_rate": 1.8759090909090908e-05,
|
337 |
+
"loss": 0.0326,
|
338 |
+
"step": 27500
|
339 |
}
|
340 |
],
|
341 |
"max_steps": 44000,
|
342 |
"num_train_epochs": 1,
|
343 |
+
"total_flos": 2.873487036461875e+16,
|
344 |
"trial_name": null,
|
345 |
"trial_params": null
|
346 |
}
|
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 sha256:44a2b8d9a599359b00e747730cd1665872fdb98e6218c96ba987585dd9ba73c2
|
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 sha256:16eeffa4d93e8effad14a9ce69822361e2937048e71b662703d22045b6f78d59
|
3 |
+
size 54350
|