Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2072e0c9e430cd9c1d1b0d97e0a2f69661beae4aae809f649487ba3a231006cc
+oid sha256:0c1c2f9eb3807f15e5202c65322a8f3cfb134e7beab87fc2ec60ec7ce25d0220
 size 13648432

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edadc7bb3a3cf5f9e56c11af665611ed6af15aa65b8b091ca7262fb228f15b39
+oid sha256:d199b5dd209fd16b98226e0bfe983b172dc1010aece87d4e191d13daf3612235
 size 7309882

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c1ccdcfcaff5b9d27cc24fae538243e050f8af44531833539162f8573b512ec
+oid sha256:523fdd0b639a62e85034051de84a610796befa0fd6e94d6a020f84859b31247b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1732484076433121,
+  "epoch": 0.18343949044585986,
   "eval_steps": 500,
-  "global_step": 17,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -313,6 +313,24 @@
       "rewards/margins": 0.011046944186091423,
       "rewards/rejected": -0.24714939296245575,
       "step": 17
+    },
+    {
+      "epoch": 0.18343949044585986,
+      "grad_norm": 2.0416226387023926,
+      "learning_rate": 9.387755102040817e-05,
+      "log_odds_chosen": 0.1555405557155609,
+      "log_odds_ratio": -0.6227366328239441,
+      "logits/chosen": -0.586774468421936,
+      "logits/rejected": -0.6310256123542786,
+      "logps/chosen": -2.2520110607147217,
+      "logps/rejected": -2.390634775161743,
+      "loss": 2.4749,
+      "nll_loss": 2.412618637084961,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": -0.22520111501216888,
+      "rewards/margins": 0.013862377032637596,
+      "rewards/rejected": -0.23906347155570984,
+      "step": 18
     }
   ],
   "logging_steps": 1,