Training in progress, step 22, 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 sha256:6791720c9aa9c10c0568940fec77bac6fe57789cb506b6bf8f90b278076c3fa4
|
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 sha256:7c545ee2ffb67a6c2534ea61c1c1928696d9df7cb25d0c8dbcaea709f4e639ed
|
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 sha256:94f2c5eeed509221b8c2053b245533d211927aa85e1cc04b3def4c4f33595da6
|
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,
|
@@ -385,6 +385,24 @@
|
|
385 |
"rewards/margins": 0.01174245961010456,
|
386 |
"rewards/rejected": -0.22161263227462769,
|
387 |
"step": 21
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
388 |
}
|
389 |
],
|
390 |
"logging_steps": 1,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.22420382165605096,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 22,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
385 |
"rewards/margins": 0.01174245961010456,
|
386 |
"rewards/rejected": -0.22161263227462769,
|
387 |
"step": 21
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.22420382165605096,
|
391 |
+
"grad_norm": 2.6400585174560547,
|
392 |
+
"learning_rate": 9.25170068027211e-05,
|
393 |
+
"log_odds_chosen": 0.0851236879825592,
|
394 |
+
"log_odds_ratio": -0.6567416191101074,
|
395 |
+
"logits/chosen": -0.6978996992111206,
|
396 |
+
"logits/rejected": -0.7123661041259766,
|
397 |
+
"logps/chosen": -2.0720839500427246,
|
398 |
+
"logps/rejected": -2.1482036113739014,
|
399 |
+
"loss": 2.2512,
|
400 |
+
"nll_loss": 2.1855506896972656,
|
401 |
+
"rewards/accuracies": 0.6875,
|
402 |
+
"rewards/chosen": -0.20720840990543365,
|
403 |
+
"rewards/margins": 0.007611965760588646,
|
404 |
+
"rewards/rejected": -0.21482038497924805,
|
405 |
+
"step": 22
|
406 |
}
|
407 |
],
|
408 |
"logging_steps": 1,
|