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 2964338224
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1a32e202d6a9986f8af91d48a45dcc68c8af86d7d0ac1bb171c1f9857f327da
|
3 |
size 2964338224
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1485440604
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1c3442ba049accf431a05b91c06b929128705beea2e7eb357461e740a7a49fc
|
3 |
size 1485440604
|
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 sha256:2bd1dee7deec1e95b1dc9de02b0106495e9ca2b8592662bdafb66ff8d2e738e9
|
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:e3af4895ee60a6cf3967bedfe8b1f52d2a28f2e3bbcaf5bdf959ed76cea26519
|
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":
|
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,
|
@@ -231,6 +231,34 @@
|
|
231 |
"learning_rate": 2.2132914365039993e-05,
|
232 |
"loss": 2.0105,
|
233 |
"step": 32
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
234 |
}
|
235 |
],
|
236 |
"logging_steps": 1,
|
@@ -250,7 +278,7 @@
|
|
250 |
"attributes": {}
|
251 |
}
|
252 |
},
|
253 |
-
"total_flos": 2.
|
254 |
"train_batch_size": 2,
|
255 |
"trial_name": null,
|
256 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.068222621184919,
|
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,
|
|
|
231 |
"learning_rate": 2.2132914365039993e-05,
|
232 |
"loss": 2.0105,
|
233 |
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.895870736086176,
|
237 |
+
"grad_norm": 1.2399568557739258,
|
238 |
+
"learning_rate": 2.0240222270883288e-05,
|
239 |
+
"loss": 2.0335,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 1.9533213644524237,
|
244 |
+
"grad_norm": 1.1331653594970703,
|
245 |
+
"learning_rate": 1.8375462445083464e-05,
|
246 |
+
"loss": 2.0217,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 2.0107719928186714,
|
251 |
+
"grad_norm": 1.219581961631775,
|
252 |
+
"learning_rate": 1.6549578039787436e-05,
|
253 |
+
"loss": 2.0096,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 2.068222621184919,
|
258 |
+
"grad_norm": 1.239498257637024,
|
259 |
+
"learning_rate": 1.4773284070716503e-05,
|
260 |
+
"loss": 2.0598,
|
261 |
+
"step": 36
|
262 |
}
|
263 |
],
|
264 |
"logging_steps": 1,
|
|
|
278 |
"attributes": {}
|
279 |
}
|
280 |
},
|
281 |
+
"total_flos": 2.4592295975399424e+16,
|
282 |
"train_batch_size": 2,
|
283 |
"trial_name": null,
|
284 |
"trial_params": null
|