Training in progress, step 2073, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b3348347c5794cd8071f0cef1cc9e1495550a9f8017f064f8d08001da935de6
+oid sha256:84517c89bbc2c2f83f9f444f16ed2a673020e56dd03d58c4844ad9f53335dd4b
 size 232169792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6294f772f9da965b0dc3c23ee7713331071f97aea88c9f208bf5e6c9239b1585
+oid sha256:72c2efa3d285a9b7caff67d1688a851758f75b5b4d09323b03b14414d4e2a2b7
 size 117446154

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35f511fc6ceb095d52923c4d373851bf545d0c675a13d2bfda0c9c62cf0ead84
+oid sha256:6f613d7eac44061f59d135704a861e68edeb488d7abba16bc6b1ef32f2f4d7be
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.998078878969375,
+  "epoch": 2.999525370098316,
   "eval_steps": 500,
-  "global_step": 2072,
+  "global_step": 2073,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37303,6 +37303,24 @@
       "rewards/margins": 0.12131794542074203,
       "rewards/rejected": -0.2101914882659912,
       "step": 2072
+    },
+    {
+      "epoch": 2.999525370098316,
+      "grad_norm": 0.5511408448219299,
+      "learning_rate": 0.0,
+      "log_odds_chosen": 2.442730665206909,
+      "log_odds_ratio": -0.5054057240486145,
+      "logits/chosen": -1.783103346824646,
+      "logits/rejected": -1.5379068851470947,
+      "logps/chosen": -0.8532201051712036,
+      "logps/rejected": -2.985834836959839,
+      "loss": 1.0792,
+      "nll_loss": 1.0286327600479126,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.08532201498746872,
+      "rewards/margins": 0.2132614701986313,
+      "rewards/rejected": -0.2985834777355194,
+      "step": 2073
     }
   ],
   "logging_steps": 1,
@@ -37317,7 +37335,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }