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:d685a967bc86ae20f1382db5639df4a2d1feb81ebcbc80e56f710245fb28bcc4
+oid sha256:1220dd5b71aec5e47e427ea99393be547330a8245b9ab3f19b2f1e9e0c774561
 size 167832240

last-checkpoint/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:488820cf9f4fcb25878ad6c8f53530a270146c4998c301d4663984a0e1b6b4e9
+oid sha256:b1fe4914eaeb1224a02a7d644147957cbdf2dc22b32253545179782b5756cd8d
 size 335945362

last-checkpoint/pytorch_model_fsdp.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d0b5aa7f1e225d59fb38ff0ac05e515eab33eafffc089dc2c7df7391a59518e
+oid sha256:79a3f0a243c448510d28953db06d91325ac0131a3005cdd3c71778e718d3542e
 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": 0.17482800485633346,
+  "epoch": 0.1942533387292594,
   "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": 28.954362869262695,
       "rewards/rejected": -33.52619552612305,
       "step": 27
+    },
+    {
+      "epoch": 0.1813031161473088,
+      "grad_norm": 6.979635713832977e-07,
+      "learning_rate": 7.022351411174866e-06,
+      "logits/chosen": -3.3811025619506836,
+      "logits/rejected": -3.2903144359588623,
+      "logps/chosen": -347.3415222167969,
+      "logps/rejected": -619.4091186523438,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -4.595226287841797,
+      "rewards/margins": 29.120075225830078,
+      "rewards/rejected": -33.715301513671875,
+      "step": 28
+    },
+    {
+      "epoch": 0.1877782274382841,
+      "grad_norm": 0.00033328495919704437,
+      "learning_rate": 3.1416838871368924e-06,
+      "logits/chosen": -3.442066192626953,
+      "logits/rejected": -3.2837891578674316,
+      "logps/chosen": -429.7748107910156,
+      "logps/rejected": -705.698486328125,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -6.5345988273620605,
+      "rewards/margins": 31.772361755371094,
+      "rewards/rejected": -38.30696105957031,
+      "step": 29
+    },
+    {
+      "epoch": 0.1942533387292594,
+      "grad_norm": 0.00010963407112285495,
+      "learning_rate": 7.885298685522235e-07,
+      "logits/chosen": -3.4091765880584717,
+      "logits/rejected": -3.3008341789245605,
+      "logps/chosen": -382.4224548339844,
+      "logps/rejected": -653.5609130859375,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -4.606748580932617,
+      "rewards/margins": 31.45462417602539,
+      "rewards/rejected": -36.06137466430664,
+      "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": {}
     }