Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86088744fc73991dbad542cb575e003e003845f7733294f33cccef3a4ea00bab
+oid sha256:41ae7286c40588b294347e621f3f7922d9cae9f17cf8be88a08a31ca42c6f611
 size 167832240

last-checkpoint/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16a17ae578843264458af1825dd54e9b6c49feedf8389be152d73b055998d99d
+oid sha256:0e753c1af6536086e024a95f9e9040c56d624df01c7c4dd8c6e0a2d36ca535f1
 size 335945362

last-checkpoint/pytorch_model_fsdp.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cc3acd79ef21a0c8cfd24a04c27cc1b761922190e7386ae99698fbbdb092058
+oid sha256:d62d52efb7db5eaea077122373b0d6b82ed50899a7a69891600bd5c7866c19ea
 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": 0.04870898635697373,
+  "epoch": 0.054121095952193034,
   "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": 2.055999279022217,
       "rewards/rejected": -6.28859281539917,
       "step": 27
+    },
+    {
+      "epoch": 0.050513022888713496,
+      "grad_norm": 2.2822930812835693,
+      "learning_rate": 7.022351411174866e-06,
+      "logits/chosen": -0.9451706409454346,
+      "logits/rejected": -0.9948737025260925,
+      "logps/chosen": -71.27719116210938,
+      "logps/rejected": -111.13409423828125,
+      "loss": 0.3123,
+      "rewards/accuracies": 0.859375,
+      "rewards/chosen": -3.154958486557007,
+      "rewards/margins": 2.582075357437134,
+      "rewards/rejected": -5.737033843994141,
+      "step": 28
+    },
+    {
+      "epoch": 0.05231705942045326,
+      "grad_norm": 1.710213541984558,
+      "learning_rate": 3.1416838871368924e-06,
+      "logits/chosen": -1.023850679397583,
+      "logits/rejected": -1.0052146911621094,
+      "logps/chosen": -70.90506744384766,
+      "logps/rejected": -106.48423767089844,
+      "loss": 0.3029,
+      "rewards/accuracies": 0.859375,
+      "rewards/chosen": -2.946613311767578,
+      "rewards/margins": 2.681060314178467,
+      "rewards/rejected": -5.627673625946045,
+      "step": 29
+    },
+    {
+      "epoch": 0.054121095952193034,
+      "grad_norm": 1.7251282930374146,
+      "learning_rate": 7.885298685522235e-07,
+      "logits/chosen": -0.9415796399116516,
+      "logits/rejected": -1.002912163734436,
+      "logps/chosen": -76.29087829589844,
+      "logps/rejected": -120.40290832519531,
+      "loss": 0.258,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": -3.300144672393799,
+      "rewards/margins": 3.0684115886688232,
+      "rewards/rejected": -6.368556022644043,
+      "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": {}
     }