Training in progress, step 7, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f903071cb570bd7851966ec6fec44995d89982155ffda29cdb6967725c304a7d
+oid sha256:afe86c1030d85f487dbaa747f3184d5a685096b20446b3a5c415a5404c51be57
 size 13648432

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9e53fe451017a13010594dadfb5397d4346a7e0c68a800e93e1755de161d87a
+oid sha256:73437178095b577cbb6ccd45b95b4e2591fd14a3e216d879675222d8b32be866
 size 7309882

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a34833b1148ea746b3aaefd6499b7286814fc0502accf3a99066160145f0cf2
+oid sha256:5371e347fa271c949de68f5ea0cd89d44be17efe7025e824d262e6bcd68df751
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.061146496815286625,
+  "epoch": 0.07133757961783439,
   "eval_steps": 500,
-  "global_step": 6,
+  "global_step": 7,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -115,6 +115,24 @@
       "rewards/margins": 0.008565555326640606,
       "rewards/rejected": -0.2886205315589905,
       "step": 6
+    },
+    {
+      "epoch": 0.07133757961783439,
+      "grad_norm": 1.8428237438201904,
+      "learning_rate": 9.761904761904762e-05,
+      "log_odds_chosen": 0.03281838819384575,
+      "log_odds_ratio": -0.6809508800506592,
+      "logits/chosen": -0.5399191975593567,
+      "logits/rejected": -0.5274120569229126,
+      "logps/chosen": -2.9202024936676025,
+      "logps/rejected": -2.9510116577148438,
+      "loss": 3.3829,
+      "nll_loss": 3.314777374267578,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.2920202612876892,
+      "rewards/margins": 0.003080902621150017,
+      "rewards/rejected": -0.2951011657714844,
+      "step": 7
     }
   ],
   "logging_steps": 1,