Training in progress, step 22, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f3c8bba520e1d372ac5c43cfe6df92fe739c300b664bf3e62a928931065c617
+oid sha256:6791720c9aa9c10c0568940fec77bac6fe57789cb506b6bf8f90b278076c3fa4
 size 13648432

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b270b42ded6c82b839854d38f85a2b525d7d9dffcaf59d2f277f3b4ed376988
+oid sha256:7c545ee2ffb67a6c2534ea61c1c1928696d9df7cb25d0c8dbcaea709f4e639ed
 size 7309882

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20d18db6d6c57ecdaee77f0983f58f8567b939678e8b514c7925344ebf41e7d2
+oid sha256:94f2c5eeed509221b8c2053b245533d211927aa85e1cc04b3def4c4f33595da6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2140127388535032,
+  "epoch": 0.22420382165605096,
   "eval_steps": 500,
-  "global_step": 21,
+  "global_step": 22,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -385,6 +385,24 @@
       "rewards/margins": 0.01174245961010456,
       "rewards/rejected": -0.22161263227462769,
       "step": 21
+    },
+    {
+      "epoch": 0.22420382165605096,
+      "grad_norm": 2.6400585174560547,
+      "learning_rate": 9.25170068027211e-05,
+      "log_odds_chosen": 0.0851236879825592,
+      "log_odds_ratio": -0.6567416191101074,
+      "logits/chosen": -0.6978996992111206,
+      "logits/rejected": -0.7123661041259766,
+      "logps/chosen": -2.0720839500427246,
+      "logps/rejected": -2.1482036113739014,
+      "loss": 2.2512,
+      "nll_loss": 2.1855506896972656,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.20720840990543365,
+      "rewards/margins": 0.007611965760588646,
+      "rewards/rejected": -0.21482038497924805,
+      "step": 22
     }
   ],
   "logging_steps": 1,