Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9591d33d66a228df18f40bf825bff99e72c5c3fdd285bcba0bc42330ed2316a
+oid sha256:fe2e764601139447b09b1940cad4fcd131d157b3e2784066a3141e9bfbdee2e4
 size 13648432

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f044fa49bfb4d2bbfcec57213268099d307fbc95f23e06ec1b2719c4ce4e5ff
+oid sha256:0cd62999c0283cf985daa9ac4c15a5bad20101c134a614f464395a815e2f477f
 size 7309882

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43add00f7e103ff8ae7c8e9ba6ae78e3693180f4799be0f85468cd77804118b2
+oid sha256:9a02099495f1ee0f69345f2400d62a00da3dfa60ed976e72211dd9b267ea7c6f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09171974522292993,
+  "epoch": 0.10191082802547771,
   "eval_steps": 500,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -169,6 +169,24 @@
       "rewards/margins": 0.005067505408078432,
       "rewards/rejected": -0.27393460273742676,
       "step": 9
+    },
+    {
+      "epoch": 0.10191082802547771,
+      "grad_norm": 3.7560782432556152,
+      "learning_rate": 9.659863945578231e-05,
+      "log_odds_chosen": 0.05389935150742531,
+      "log_odds_ratio": -0.6712656617164612,
+      "logits/chosen": -0.5685052871704102,
+      "logits/rejected": -0.5835959911346436,
+      "logps/chosen": -2.7232255935668945,
+      "logps/rejected": -2.772873878479004,
+      "loss": 3.1185,
+      "nll_loss": 3.0513598918914795,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.27232253551483154,
+      "rewards/margins": 0.004964826162904501,
+      "rewards/rejected": -0.27728739380836487,
+      "step": 10
     }
   ],
   "logging_steps": 1,