MohamedAhmedAE
commited on
Commit
•
2ec4c28
1
Parent(s):
205392b
Training in progress, step 8800, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0be03972159ec159a56e3e77ca8d38e2168af9dcdd4df0d68963ed1c60e6965
|
3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 84581014
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9dd5bd046dc3465f6df5b72e0a2552c5b0fda402004d2a228232c184835c93f0
|
3 |
size 84581014
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85904f7c1b5e0d81333d46dd0befeb978507214982bf15efdfa380ed0f5f6789
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a757a49f50d9542b04e522a04786aa578e7821acc2014c546ec09d428c28168
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 2000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -308,6 +308,13 @@
|
|
308 |
"learning_rate": 1.99999194681957e-05,
|
309 |
"loss": 1.5581,
|
310 |
"step": 8600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
311 |
}
|
312 |
],
|
313 |
"logging_steps": 200,
|
@@ -315,7 +322,7 @@
|
|
315 |
"num_input_tokens_seen": 0,
|
316 |
"num_train_epochs": 5,
|
317 |
"save_steps": 200,
|
318 |
-
"total_flos": 1.
|
319 |
"train_batch_size": 1,
|
320 |
"trial_name": null,
|
321 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.006544234938034276,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 8800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
308 |
"learning_rate": 1.99999194681957e-05,
|
309 |
"loss": 1.5581,
|
310 |
"step": 8600
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.01,
|
314 |
+
"grad_norm": 2.273376703262329,
|
315 |
+
"learning_rate": 1.9999915674072735e-05,
|
316 |
+
"loss": 1.6099,
|
317 |
+
"step": 8800
|
318 |
}
|
319 |
],
|
320 |
"logging_steps": 200,
|
|
|
322 |
"num_input_tokens_seen": 0,
|
323 |
"num_train_epochs": 5,
|
324 |
"save_steps": 200,
|
325 |
+
"total_flos": 1.1521698789135974e+17,
|
326 |
"train_batch_size": 1,
|
327 |
"trial_name": null,
|
328 |
"trial_params": null
|