Training in progress, step 23, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6791720c9aa9c10c0568940fec77bac6fe57789cb506b6bf8f90b278076c3fa4
+oid sha256:c7da29b3c527f6adfa53cbea2d9f62ad4836f417c6e209d1b791700873e15b72
 size 13648432

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c545ee2ffb67a6c2534ea61c1c1928696d9df7cb25d0c8dbcaea709f4e639ed
+oid sha256:9e842bafd437b9c9bd87fe315b19b648d03282bedf2a026f6d1e5f6384398121
 size 7309882

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94f2c5eeed509221b8c2053b245533d211927aa85e1cc04b3def4c4f33595da6
+oid sha256:078374aaaf0ef6477f920c224c32134039e8f06ec3f7925b56035828b5c37d05
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.22420382165605096,
+  "epoch": 0.23439490445859873,
   "eval_steps": 500,
-  "global_step": 22,
+  "global_step": 23,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -403,6 +403,24 @@
       "rewards/margins": 0.007611965760588646,
       "rewards/rejected": -0.21482038497924805,
       "step": 22
+    },
+    {
+      "epoch": 0.23439490445859873,
+      "grad_norm": 3.0456278324127197,
+      "learning_rate": 9.217687074829933e-05,
+      "log_odds_chosen": 0.12218278646469116,
+      "log_odds_ratio": -0.639614462852478,
+      "logits/chosen": -0.6912589073181152,
+      "logits/rejected": -0.7216678261756897,
+      "logps/chosen": -1.9978296756744385,
+      "logps/rejected": -2.103085517883301,
+      "loss": 2.1711,
+      "nll_loss": 2.1071152687072754,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.19978296756744385,
+      "rewards/margins": 0.010525593534111977,
+      "rewards/rejected": -0.21030855178833008,
+      "step": 23
     }
   ],
   "logging_steps": 1,