Training in progress, step 21, 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 13648432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f3c8bba520e1d372ac5c43cfe6df92fe739c300b664bf3e62a928931065c617
|
3 |
size 13648432
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7309882
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b270b42ded6c82b839854d38f85a2b525d7d9dffcaf59d2f277f3b4ed376988
|
3 |
size 7309882
|
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 sha256:20d18db6d6c57ecdaee77f0983f58f8567b939678e8b514c7925344ebf41e7d2
|
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,
|
@@ -367,6 +367,24 @@
|
|
367 |
"rewards/margins": 0.008663482964038849,
|
368 |
"rewards/rejected": -0.23149211704730988,
|
369 |
"step": 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
370 |
}
|
371 |
],
|
372 |
"logging_steps": 1,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2140127388535032,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 21,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
367 |
"rewards/margins": 0.008663482964038849,
|
368 |
"rewards/rejected": -0.23149211704730988,
|
369 |
"step": 20
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.2140127388535032,
|
373 |
+
"grad_norm": 2.270171880722046,
|
374 |
+
"learning_rate": 9.285714285714286e-05,
|
375 |
+
"log_odds_chosen": 0.13292132318019867,
|
376 |
+
"log_odds_ratio": -0.6331073641777039,
|
377 |
+
"logits/chosen": -0.6325170993804932,
|
378 |
+
"logits/rejected": -0.6448156237602234,
|
379 |
+
"logps/chosen": -2.0987019538879395,
|
380 |
+
"logps/rejected": -2.2161264419555664,
|
381 |
+
"loss": 2.2766,
|
382 |
+
"nll_loss": 2.2132651805877686,
|
383 |
+
"rewards/accuracies": 0.84375,
|
384 |
+
"rewards/chosen": -0.20987018942832947,
|
385 |
+
"rewards/margins": 0.01174245961010456,
|
386 |
+
"rewards/rejected": -0.22161263227462769,
|
387 |
+
"step": 21
|
388 |
}
|
389 |
],
|
390 |
"logging_steps": 1,
|