Training in progress, step 21, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfb728383d3bee7b9c748607471f87f0ee294a0d8cc43a21cae0f2196449db97
+oid sha256:1f3c8bba520e1d372ac5c43cfe6df92fe739c300b664bf3e62a928931065c617
 size 13648432

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76fe498e55b46d16ac7fb6f0b17696cb151a98e43481d5de152b791bc92ba88a
+oid sha256:9b270b42ded6c82b839854d38f85a2b525d7d9dffcaf59d2f277f3b4ed376988
 size 7309882

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c69cc92a81dedf50e82a2e8116edb54160d7b181c612e013d15766f2d25acd0b
+oid sha256:20d18db6d6c57ecdaee77f0983f58f8567b939678e8b514c7925344ebf41e7d2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.20382165605095542,
+  "epoch": 0.2140127388535032,
   "eval_steps": 500,
-  "global_step": 20,
+  "global_step": 21,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -367,6 +367,24 @@
       "rewards/margins": 0.008663482964038849,
       "rewards/rejected": -0.23149211704730988,
       "step": 20
+    },
+    {
+      "epoch": 0.2140127388535032,
+      "grad_norm": 2.270171880722046,
+      "learning_rate": 9.285714285714286e-05,
+      "log_odds_chosen": 0.13292132318019867,
+      "log_odds_ratio": -0.6331073641777039,
+      "logits/chosen": -0.6325170993804932,
+      "logits/rejected": -0.6448156237602234,
+      "logps/chosen": -2.0987019538879395,
+      "logps/rejected": -2.2161264419555664,
+      "loss": 2.2766,
+      "nll_loss": 2.2132651805877686,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": -0.20987018942832947,
+      "rewards/margins": 0.01174245961010456,
+      "rewards/rejected": -0.22161263227462769,
+      "step": 21
     }
   ],
   "logging_steps": 1,