Training in progress, step 58, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf42019408e16e6c794697c7ac5c5efb23ce2fb1345896c31731c25ddd73266f
+oid sha256:99db89048811aeca193ff41f8d47cac443599a280416659f90b0bd7b15000675
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8309df69f11eca58a323a366d91ae8910c463affa6aefa6af51884a035087797
+oid sha256:1cc7023852cac4d43ecd10f780743c0055f402685fbc515280c67435510fcd24
 size 42033220

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b12cf3d06a90f38b5514cf6e5bc966f40e7acb9dc02ece4ffbc7baf3786fc8f
+oid sha256:f268b0e33016b436f8c315b966b7e2ba418b82eb64cd83a4ed4e1f4db2c9125a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5810767760433259,
+  "epoch": 0.5912711054475948,
   "eval_steps": 500,
-  "global_step": 57,
+  "global_step": 58,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1033,6 +1033,24 @@
       "rewards/margins": 0.05135873705148697,
       "rewards/rejected": -0.11398905515670776,
       "step": 57
+    },
+    {
+      "epoch": 0.5912711054475948,
+      "grad_norm": 0.5601215958595276,
+      "learning_rate": 0.00013636363636363634,
+      "log_odds_chosen": 0.9498623609542847,
+      "log_odds_ratio": -0.35345450043678284,
+      "logits/chosen": -6.869694709777832,
+      "logits/rejected": -6.53272819519043,
+      "logps/chosen": -0.7229388356208801,
+      "logps/rejected": -1.3177077770233154,
+      "loss": 0.8727,
+      "nll_loss": 0.8374002575874329,
+      "rewards/accuracies": 0.96875,
+      "rewards/chosen": -0.07229389250278473,
+      "rewards/margins": 0.05947688966989517,
+      "rewards/rejected": -0.1317707896232605,
+      "step": 58
     }
   ],
   "logging_steps": 1,