DuongTrongChi
commited on
Commit
•
9437f05
1
Parent(s):
ef4f15d
Training in progress, step 36, 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 sha256:3c4c2c5b373f6a50d462b25c2a377562f91b4389f0e2d101d2feb433346495d8
|
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:f9a26df27a852fcc25a43cec6ed5388e796c14c8dee9596a8fd6a85722b9a531
|
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:cc45c09e66fd942f81d3e1a2a005793e3b66657aac967cab369d222230d52fd0
|
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,
|
@@ -252,6 +252,13 @@
|
|
252 |
"learning_rate": 7e-05,
|
253 |
"loss": 1.4445,
|
254 |
"step": 35
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
255 |
}
|
256 |
],
|
257 |
"logging_steps": 1,
|
@@ -271,7 +278,7 @@
|
|
271 |
"attributes": {}
|
272 |
}
|
273 |
},
|
274 |
-
"total_flos":
|
275 |
"train_batch_size": 16,
|
276 |
"trial_name": null,
|
277 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.09876543209876543,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 36,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
252 |
"learning_rate": 7e-05,
|
253 |
"loss": 1.4445,
|
254 |
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.09876543209876543,
|
258 |
+
"grad_norm": 0.3918333351612091,
|
259 |
+
"learning_rate": 7.2e-05,
|
260 |
+
"loss": 1.3956,
|
261 |
+
"step": 36
|
262 |
}
|
263 |
],
|
264 |
"logging_steps": 1,
|
|
|
278 |
"attributes": {}
|
279 |
}
|
280 |
},
|
281 |
+
"total_flos": 1.029250509239255e+17,
|
282 |
"train_batch_size": 16,
|
283 |
"trial_name": null,
|
284 |
"trial_params": null
|