Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee2b96db0e93a6619b3d097c0eaa3469c2afb27d62591810323a83dec110bd9b
+oid sha256:cfb728383d3bee7b9c748607471f87f0ee294a0d8cc43a21cae0f2196449db97
 size 13648432

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b46d0c54c243567a411320a64dbdd49c36fb7c2b1172c52baee8ca31cea57ffe
+oid sha256:76fe498e55b46d16ac7fb6f0b17696cb151a98e43481d5de152b791bc92ba88a
 size 7309882

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78a1dc42ca905df9cb387c589e1dae74e503f3621933abeafd9d287290af6058
+oid sha256:c69cc92a81dedf50e82a2e8116edb54160d7b181c612e013d15766f2d25acd0b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.19363057324840766,
+  "epoch": 0.20382165605095542,
   "eval_steps": 500,
-  "global_step": 19,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -349,6 +349,24 @@
       "rewards/margins": 0.012145599350333214,
       "rewards/rejected": -0.23428542912006378,
       "step": 19
+    },
+    {
+      "epoch": 0.20382165605095542,
+      "grad_norm": 1.9783782958984375,
+      "learning_rate": 9.319727891156463e-05,
+      "log_odds_chosen": 0.09560593217611313,
+      "log_odds_ratio": -0.6527409553527832,
+      "logits/chosen": -0.6574750542640686,
+      "logits/rejected": -0.6695252656936646,
+      "logps/chosen": -2.228286027908325,
+      "logps/rejected": -2.3149209022521973,
+      "loss": 2.4197,
+      "nll_loss": 2.3543879985809326,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.22282862663269043,
+      "rewards/margins": 0.008663482964038849,
+      "rewards/rejected": -0.23149211704730988,
+      "step": 20
     }
   ],
   "logging_steps": 1,