DuongTrongChi
commited on
Commit
•
607684a
1
Parent(s):
6e13282
Training in progress, step 45, 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 100198584
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:672f916bebd7a5d3bc18cb32b38eef5409ec4970a4f0e264344d1d898aed73c7
|
3 |
size 100198584
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 50675156
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68ecb70cde7af6cfe8d984e2a09352a923bdbcdd1e80a416a9e4a53e0f1b6389
|
3 |
size 50675156
|
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 sha256:8cc121e67e70577df944161a080afe74f5e848cfee5c8b258778d6cec57833eb
|
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": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -315,6 +315,13 @@
|
|
315 |
"learning_rate": 8.800000000000001e-05,
|
316 |
"loss": 1.3378,
|
317 |
"step": 44
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
318 |
}
|
319 |
],
|
320 |
"logging_steps": 1,
|
@@ -334,7 +341,7 @@
|
|
334 |
"attributes": {}
|
335 |
}
|
336 |
},
|
337 |
-
"total_flos": 1.
|
338 |
"train_batch_size": 16,
|
339 |
"trial_name": null,
|
340 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.12345679012345678,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 45,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
315 |
"learning_rate": 8.800000000000001e-05,
|
316 |
"loss": 1.3378,
|
317 |
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.12345679012345678,
|
321 |
+
"grad_norm": 0.12385573983192444,
|
322 |
+
"learning_rate": 9e-05,
|
323 |
+
"loss": 1.2032,
|
324 |
+
"step": 45
|
325 |
}
|
326 |
],
|
327 |
"logging_steps": 1,
|
|
|
341 |
"attributes": {}
|
342 |
}
|
343 |
},
|
344 |
+
"total_flos": 1.279779880523858e+17,
|
345 |
"train_batch_size": 16,
|
346 |
"trial_name": null,
|
347 |
"trial_params": null
|