Training in progress, step 16, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ef7cbd8c6f20311732aef5070bb43ca5e8012ce0013335f2e94d5bd8e85c56e
+oid sha256:40ae3564311bfbe49e68535b3496c99ce8072b21ad3b5839a07acab622564e8f
 size 13648432

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:568e1e6f9a75fe7d912123661bcb4d4b277b1ea7fc0276a156d8360c3005786a
+oid sha256:7cdc25067af02f302ae5f20feae9590d56ead7c091032508ad7b8f3cfd38e291
 size 7309882

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6994cb487905172b0ba255400eaecb8aa47a01b2c6f61db8cf605bf89aaea0f
+oid sha256:397c58c95656820d3439e353b3be5fd82dca80421fee3f09e902bff4cb788a6b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15286624203821655,
+  "epoch": 0.16305732484076432,
   "eval_steps": 500,
-  "global_step": 15,
+  "global_step": 16,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -277,6 +277,24 @@
       "rewards/margins": 0.011246275156736374,
       "rewards/rejected": -0.25726398825645447,
       "step": 15
+    },
+    {
+      "epoch": 0.16305732484076432,
+      "grad_norm": 3.213852882385254,
+      "learning_rate": 9.455782312925171e-05,
+      "log_odds_chosen": 0.0818968415260315,
+      "log_odds_ratio": -0.6613866090774536,
+      "logits/chosen": -0.5976958274841309,
+      "logits/rejected": -0.6143887639045715,
+      "logps/chosen": -2.413341522216797,
+      "logps/rejected": -2.4865636825561523,
+      "loss": 2.6428,
+      "nll_loss": 2.5766918659210205,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.24133417010307312,
+      "rewards/margins": 0.007322215940803289,
+      "rewards/rejected": -0.24865636229515076,
+      "step": 16
     }
   ],
   "logging_steps": 1,