Training in progress, step 12, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd5001970a94c1aeb2be404f63b934153c6a8afecd421ffb89f6ae43dfb02029
+oid sha256:a02e3260ee9d062c315bc654bc3b6ea88b9c6010da782a47c8833c40c4de4572
 size 13648432

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b961d010e7b252944302920bab7291331927a0492c9deec402fe522402693a0c
+oid sha256:0626c259fd2ef9911b97f6e7245714e0c7b47939414128b3839167e3cc8351ab
 size 7309882

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e23ccafad489da96357ee6455b0c6b7c38f2cddbd7f8464d5fb60ce0c29726cc
+oid sha256:97f1945a3cd3872f925c6c28b703dcb3b39023385486b89709dc5e08cdba61de
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.11210191082802548,
+  "epoch": 0.12229299363057325,
   "eval_steps": 500,
-  "global_step": 11,
+  "global_step": 12,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -205,6 +205,24 @@
       "rewards/margins": 0.005129385739564896,
       "rewards/rejected": -0.26965007185935974,
       "step": 11
+    },
+    {
+      "epoch": 0.12229299363057325,
+      "grad_norm": 1.8458824157714844,
+      "learning_rate": 9.591836734693878e-05,
+      "log_odds_chosen": -0.026220712810754776,
+      "log_odds_ratio": -0.7125887870788574,
+      "logits/chosen": -0.5802856087684631,
+      "logits/rejected": -0.6202648878097534,
+      "logps/chosen": -2.6887969970703125,
+      "logps/rejected": -2.6625289916992188,
+      "loss": 3.0166,
+      "nll_loss": 2.945356845855713,
+      "rewards/accuracies": 0.40625,
+      "rewards/chosen": -0.2688797116279602,
+      "rewards/margins": -0.0026267748326063156,
+      "rewards/rejected": -0.26625293493270874,
+      "step": 12
     }
   ],
   "logging_steps": 1,