Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e69d7e83124273cbe9fc42d38f6f941fb08e1b210d75bedd2b52599c302c41a
+oid sha256:1ee8890e9470e703f434146247aadbad651bce325e9e0207ae8f609bd4d2d1a9
 size 78480072

last-checkpoint/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7d114c0d46b857cedf71faee614496722cc1b2b8487c5b5a97383baff8725f3
+oid sha256:c5cd07b367454e817f1900454a269308e24e8a0c8f66c9724b3dba995669162f
 size 157117882

last-checkpoint/pytorch_model_fsdp.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:938415b6ea3f8296cec18b712c1570bec37b36f6a258d2312edd5c22f27b12b4
+oid sha256:bf0e5fce8fcc55d510afe38fac54e277069b2cc6db5c6aef8c003e5c456113a4
 size 78540410

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": 0.006689170357065437,
+  "epoch": 0.007432411507850485,
   "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": 35.485843658447266,
       "rewards/rejected": -52.94690704345703,
       "step": 27
+    },
+    {
+      "epoch": 0.006936917407327119,
+      "grad_norm": 0.0011011986061930656,
+      "learning_rate": 7.022351411174866e-06,
+      "logits/chosen": -10.881973266601562,
+      "logits/rejected": -10.674958229064941,
+      "logps/chosen": -437.04595947265625,
+      "logps/rejected": -733.4830322265625,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -17.543977737426758,
+      "rewards/margins": 33.01079559326172,
+      "rewards/rejected": -50.554771423339844,
+      "step": 28
+    },
+    {
+      "epoch": 0.007184664457588802,
+      "grad_norm": 2.7401858460507356e-05,
+      "learning_rate": 3.1416838871368924e-06,
+      "logits/chosen": -10.476828575134277,
+      "logits/rejected": -9.965253829956055,
+      "logps/chosen": -504.1549072265625,
+      "logps/rejected": -879.5731201171875,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -19.05587387084961,
+      "rewards/margins": 41.9334831237793,
+      "rewards/rejected": -60.98935317993164,
+      "step": 29
+    },
+    {
+      "epoch": 0.007432411507850485,
+      "grad_norm": 1.9023595086764544e-05,
+      "learning_rate": 7.885298685522235e-07,
+      "logits/chosen": -10.411879539489746,
+      "logits/rejected": -9.946537017822266,
+      "logps/chosen": -505.53265380859375,
+      "logps/rejected": -847.1196899414062,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -20.327346801757812,
+      "rewards/margins": 37.78123092651367,
+      "rewards/rejected": -58.10857391357422,
+      "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": {}
     }