Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2964054f1ce3e570a5a5925bda48122ddbb54f44b42b96aedd7cdbdff7c2ac52
+oid sha256:f903071cb570bd7851966ec6fec44995d89982155ffda29cdb6967725c304a7d
 size 13648432

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6ba377c6ceb87dee6a4489a116fa7c780de61cb21f836c5d771a22552c4b568
+oid sha256:45b69b38f30c9123191de0b8828377ed369b0f837f3773e9ff0d96384f02ce82
 size 6979130

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:132d841d6075a4630b10f974a8eec92787f412f6496d65f09d0ed31599e2fe94
+oid sha256:5a97cec4ccaf7b86834a2fdb06e10135db381a62fd0dc050dc49420427220909
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04076433121019108,
+  "epoch": 0.050955414012738856,
   "eval_steps": 500,
-  "global_step": 4,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -79,6 +79,24 @@
       "rewards/margins": 0.011471111327409744,
       "rewards/rejected": -0.2936646640300751,
       "step": 4
+    },
+    {
+      "epoch": 0.050955414012738856,
+      "grad_norm": 2.1892218589782715,
+      "learning_rate": 0.0,
+      "log_odds_chosen": 0.06512074917554855,
+      "log_odds_ratio": -0.6671069860458374,
+      "logits/chosen": -0.5229994654655457,
+      "logits/rejected": -0.5436381697654724,
+      "logps/chosen": -2.7552542686462402,
+      "logps/rejected": -2.816582679748535,
+      "loss": 3.2584,
+      "nll_loss": 3.191640615463257,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.27552542090415955,
+      "rewards/margins": 0.006132860202342272,
+      "rewards/rejected": -0.2816582918167114,
+      "step": 5
     }
   ],
   "logging_steps": 1,
@@ -93,7 +111,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }