Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cefcc76bd22e9fee6d3b5fa1a0402ceea19d51f3133c4634afe75a33d7de4171
+oid sha256:1e69d7e83124273cbe9fc42d38f6f941fb08e1b210d75bedd2b52599c302c41a
 size 78480072

last-checkpoint/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce34ea9ebe5c47350f6022d4feac6275e99b60013b08ceb20b87ae9ecd507728
+oid sha256:e7d114c0d46b857cedf71faee614496722cc1b2b8487c5b5a97383baff8725f3
 size 157117882

last-checkpoint/pytorch_model_fsdp.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe4e6d35e1d1e34312ba914236936ccb07642bc14574830c07612c300ee593a3
+oid sha256:938415b6ea3f8296cec18b712c1570bec37b36f6a258d2312edd5c22f27b12b4
 size 78540410

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:859214dc387eb3e62419c68b424697c31e86f60684ce969a4432863354d30aa8
+oid sha256:337059d54254bc9389c938dc292312990ce226dd122bd2ed92af370c28fd9326
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005945929206280388,
+  "epoch": 0.006689170357065437,
   "eval_steps": 500,
-  "global_step": 24,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -368,6 +368,51 @@
       "rewards/margins": 42.09270477294922,
       "rewards/rejected": -59.91984558105469,
       "step": 24
+    },
+    {
+      "epoch": 0.006193676256542071,
+      "grad_norm": 0.00013728135672863573,
+      "learning_rate": 2.7103137257858868e-05,
+      "logits/chosen": -10.484910011291504,
+      "logits/rejected": -10.038405418395996,
+      "logps/chosen": -470.36724853515625,
+      "logps/rejected": -829.9815063476562,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -18.556917190551758,
+      "rewards/margins": 40.350582122802734,
+      "rewards/rejected": -58.907501220703125,
+      "step": 25
+    },
+    {
+      "epoch": 0.006441423306803753,
+      "grad_norm": 1.0545077202550601e-05,
+      "learning_rate": 1.9098300562505266e-05,
+      "logits/chosen": -10.911032676696777,
+      "logits/rejected": -10.46043586730957,
+      "logps/chosen": -463.2617492675781,
+      "logps/rejected": -793.1405639648438,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -17.526235580444336,
+      "rewards/margins": 37.045745849609375,
+      "rewards/rejected": -54.57197952270508,
+      "step": 26
+    },
+    {
+      "epoch": 0.006689170357065437,
+      "grad_norm": 0.00020930655591655523,
+      "learning_rate": 1.2369331995613665e-05,
+      "logits/chosen": -10.635181427001953,
+      "logits/rejected": -10.339822769165039,
+      "logps/chosen": -446.2877197265625,
+      "logps/rejected": -769.8375244140625,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -17.4610595703125,
+      "rewards/margins": 35.485843658447266,
+      "rewards/rejected": -52.94690704345703,
+      "step": 27
     }
   ],
   "logging_steps": 1,