DuongTrongChi
commited on
Commit
•
784802f
1
Parent(s):
d75cbaf
Training in progress, step 35, 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 sha256:92ec7b0d148cabae94bf355a3171875f492bcba9a4ba1e447dca12c104746eef
|
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:d0c1c682e6e5a5603c0576b994f13008bef21f4d49721578dc361dc4265d85d4
|
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:af67e9e5c8e6cf58e25d32243548a1daefe99b687ecc48520798924fe992214b
|
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,
|
@@ -245,6 +245,13 @@
|
|
245 |
"learning_rate": 6.800000000000001e-05,
|
246 |
"loss": 1.4967,
|
247 |
"step": 34
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
248 |
}
|
249 |
],
|
250 |
"logging_steps": 1,
|
@@ -264,7 +271,7 @@
|
|
264 |
"attributes": {}
|
265 |
}
|
266 |
},
|
267 |
-
"total_flos": 9.
|
268 |
"train_batch_size": 16,
|
269 |
"trial_name": null,
|
270 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.09602194787379972,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 35,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
245 |
"learning_rate": 6.800000000000001e-05,
|
246 |
"loss": 1.4967,
|
247 |
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.09602194787379972,
|
251 |
+
"grad_norm": 0.5295405983924866,
|
252 |
+
"learning_rate": 7e-05,
|
253 |
+
"loss": 1.4445,
|
254 |
+
"step": 35
|
255 |
}
|
256 |
],
|
257 |
"logging_steps": 1,
|
|
|
271 |
"attributes": {}
|
272 |
}
|
273 |
},
|
274 |
+
"total_flos": 9.98748058276823e+16,
|
275 |
"train_batch_size": 16,
|
276 |
"trial_name": null,
|
277 |
"trial_params": null
|