Training in progress, step 32000
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:efa456da4f36fe45ddc2ba315e5270c5efc83b7c9794b86b7d435735e0f11209
|
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 sha256:9e4c77d18a75f347704dfbf96b41fdcccddd7bca28245235d9e205cbd34e8ea7
|
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 sha256:9bb51c392fda29e22cba18ab8cd576d658276c1e17efe6e379f584c00eca6b3a
|
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 sha256:083bfd8359291fd5c10363ff17a4a14307aa1f9a2672d4435db6f274991a6e6e
|
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,
|
@@ -384,11 +384,17 @@
|
|
384 |
"learning_rate": 1.4214772727272727e-05,
|
385 |
"loss": 0.0324,
|
386 |
"step": 31500
|
|
|
|
|
|
|
|
|
|
|
|
|
387 |
}
|
388 |
],
|
389 |
"max_steps": 44000,
|
390 |
"num_train_epochs": 1,
|
391 |
-
"total_flos": 3.
|
392 |
"trial_name": null,
|
393 |
"trial_params": null
|
394 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4340866545484142,
|
5 |
+
"global_step": 32000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
384 |
"learning_rate": 1.4214772727272727e-05,
|
385 |
"loss": 0.0324,
|
386 |
"step": 31500
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 0.43,
|
390 |
+
"learning_rate": 1.364659090909091e-05,
|
391 |
+
"loss": 0.0312,
|
392 |
+
"step": 32000
|
393 |
}
|
394 |
],
|
395 |
"max_steps": 44000,
|
396 |
"num_train_epochs": 1,
|
397 |
+
"total_flos": 3.343659811681075e+16,
|
398 |
"trial_name": null,
|
399 |
"trial_params": null
|
400 |
}
|
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 sha256:9e4c77d18a75f347704dfbf96b41fdcccddd7bca28245235d9e205cbd34e8ea7
|
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 sha256:31ccf4b3723335f1d1a28c8de45453f20dd60d27af0c84d7c7985c961421acb5
|
3 |
+
size 55790
|