Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8398c0e5bddec9eb883e0399f65b755d78d063f3b9ecbe58f175f44f364cc7e9
+oid sha256:a9591d33d66a228df18f40bf825bff99e72c5c3fdd285bcba0bc42330ed2316a
 size 13648432

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35967646370f39bc8adcdeb6bb4be3fa34ef34aa59b57e6a7303e7a39ef1094c
+oid sha256:9f044fa49bfb4d2bbfcec57213268099d307fbc95f23e06ec1b2719c4ce4e5ff
 size 7309882

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:600149e975d1bacd170387afa159597e660c1a6e94a6b29b69de17c6162d48a4
+oid sha256:43add00f7e103ff8ae7c8e9ba6ae78e3693180f4799be0f85468cd77804118b2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08152866242038216,
+  "epoch": 0.09171974522292993,
   "eval_steps": 500,
-  "global_step": 8,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -151,6 +151,24 @@
       "rewards/margins": 0.009154656901955605,
       "rewards/rejected": -0.28212225437164307,
       "step": 8
+    },
+    {
+      "epoch": 0.09171974522292993,
+      "grad_norm": 1.9783447980880737,
+      "learning_rate": 9.693877551020408e-05,
+      "log_odds_chosen": 0.05389028042554855,
+      "log_odds_ratio": -0.6711492538452148,
+      "logits/chosen": -0.5444136261940002,
+      "logits/rejected": -0.564105212688446,
+      "logps/chosen": -2.688671112060547,
+      "logps/rejected": -2.7393460273742676,
+      "loss": 3.1182,
+      "nll_loss": 3.051093101501465,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.2688670754432678,
+      "rewards/margins": 0.005067505408078432,
+      "rewards/rejected": -0.27393460273742676,
+      "step": 9
     }
   ],
   "logging_steps": 1,