Training in progress, step 38, 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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b1d58814f9249322fd686abf6d8b35569e37c7d3ace969e7544a8c91b395f8e
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37430836
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3425991f31429ae03ba06ff22235bb60e270e7cfa141bfbaec537483296eb76f
|
3 |
size 37430836
|
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 sha256:8716ebd4f58a4256f1770cba51ce3345df43367e84204568d19ce91d08e1a9b7
|
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,
|
@@ -266,6 +266,13 @@
|
|
266 |
"learning_rate": 7.4e-05,
|
267 |
"loss": 1.4451,
|
268 |
"step": 37
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
269 |
}
|
270 |
],
|
271 |
"logging_steps": 1,
|
@@ -285,7 +292,7 @@
|
|
285 |
"attributes": {}
|
286 |
}
|
287 |
},
|
288 |
-
"total_flos": 4.
|
289 |
"train_batch_size": 4,
|
290 |
"trial_name": null,
|
291 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.10425240054869685,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 38,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
266 |
"learning_rate": 7.4e-05,
|
267 |
"loss": 1.4451,
|
268 |
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.10425240054869685,
|
272 |
+
"grad_norm": 0.24707239866256714,
|
273 |
+
"learning_rate": 7.6e-05,
|
274 |
+
"loss": 1.3434,
|
275 |
+
"step": 38
|
276 |
}
|
277 |
],
|
278 |
"logging_steps": 1,
|
|
|
292 |
"attributes": {}
|
293 |
}
|
294 |
},
|
295 |
+
"total_flos": 4.687294560414106e+16,
|
296 |
"train_batch_size": 4,
|
297 |
"trial_name": null,
|
298 |
"trial_params": null
|