Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:826d12eea3bbee7ec77d12b1cda4900cb3a23e196f526b4d450def2246282fa2
+oid sha256:cfd6a21cebd0a82ed9a43f8a629fcc8064352b76f27c107e06c42b3fe55061db
 size 167832240

last-checkpoint/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db38cd9a27b6f8bf0e97fc1bbf5a8125ff6fd703ae2c800a8257c6a156ac146f
+oid sha256:f12dfd0fb885ae10cc96dc97b26dc1aef9e137c0ebd51efceb93f0d1d5282833
 size 335945362

last-checkpoint/pytorch_model_fsdp.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b9c18073a1d48d6a50bed942c1b1a021db57b53028945cf2331e397094db15d
+oid sha256:cb66c9d1334e455bfe642dae209bf3e27f59b032bf74afae2f46ed130bd70e7f
 size 167939550

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:337059d54254bc9389c938dc292312990ce226dd122bd2ed92af370c28fd9326
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.192,
+  "epoch": 0.21333333333333335,
   "eval_steps": 500,
-  "global_step": 27,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -413,6 +413,51 @@
       "rewards/margins": 5.356634140014648,
       "rewards/rejected": -8.09588623046875,
       "step": 27
+    },
+    {
+      "epoch": 0.1991111111111111,
+      "grad_norm": 1.7272309064865112,
+      "learning_rate": 7.022351411174866e-06,
+      "logits/chosen": -1.0286459922790527,
+      "logits/rejected": -1.320716142654419,
+      "logps/chosen": -98.15447235107422,
+      "logps/rejected": -169.14036560058594,
+      "loss": 0.2012,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": -2.8377060890197754,
+      "rewards/margins": 6.118044853210449,
+      "rewards/rejected": -8.955750465393066,
+      "step": 28
+    },
+    {
+      "epoch": 0.20622222222222222,
+      "grad_norm": 1.1793086528778076,
+      "learning_rate": 3.1416838871368924e-06,
+      "logits/chosen": -0.9110668897628784,
+      "logits/rejected": -1.2544306516647339,
+      "logps/chosen": -87.0140609741211,
+      "logps/rejected": -160.61866760253906,
+      "loss": 0.1207,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": -2.3407022953033447,
+      "rewards/margins": 6.302703380584717,
+      "rewards/rejected": -8.64340591430664,
+      "step": 29
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.6413570046424866,
+      "learning_rate": 7.885298685522235e-07,
+      "logits/chosen": -0.9873690605163574,
+      "logits/rejected": -1.3247737884521484,
+      "logps/chosen": -95.96586608886719,
+      "logps/rejected": -178.8674774169922,
+      "loss": 0.0721,
+      "rewards/accuracies": 0.984375,
+      "rewards/chosen": -2.3605031967163086,
+      "rewards/margins": 6.789929389953613,
+      "rewards/rejected": -9.150433540344238,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -427,7 +472,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }