Training in progress, step 49, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3b9052f10d018a0db2660eaa5f127e76f6f6767fcf20c15c57a23f60d95695b
+oid sha256:61c4aef52327b74e276194084cea23c87f6341f1f7b52a3cefd75fcaf48183e5
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ffd4b8d2bcfd1c78297f63b2d538b9b190d18e7c357b463b7792462af296554
+oid sha256:298622a49610be57349874e2523642fc0a004bb3569dff87441b2022830a345f
 size 20359034

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2fb311d43c732630c9c38144204d369cab84f4088b1165920818e91a4205052
+oid sha256:25704ee5478cd4521ee5db3e9e14050e9c72edebe1088acf05e49ba2bb8ed7fb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.978655622809812,
+  "epoch": 0.9990442816183498,
   "eval_steps": 500,
-  "global_step": 48,
+  "global_step": 49,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -871,6 +871,24 @@
       "rewards/margins": 0.01552429050207138,
       "rewards/rejected": -0.22111549973487854,
       "step": 48
+    },
+    {
+      "epoch": 0.9990442816183498,
+      "grad_norm": 4.174467086791992,
+      "learning_rate": 0.0,
+      "log_odds_chosen": 0.19606728851795197,
+      "log_odds_ratio": -0.6126885414123535,
+      "logits/chosen": -21.158491134643555,
+      "logits/rejected": -21.405784606933594,
+      "logps/chosen": -2.048922538757324,
+      "logps/rejected": -2.2221457958221436,
+      "loss": 2.4451,
+      "nll_loss": 2.3838396072387695,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.20489224791526794,
+      "rewards/margins": 0.017322326079010963,
+      "rewards/rejected": -0.22221459448337555,
+      "step": 49
     }
   ],
   "logging_steps": 1,
@@ -885,7 +903,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }