Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:524a0383464ed8233cb5c31d43fcca20d30f68bf78f3883d33c20e2d06688be7
+oid sha256:2ef7cbd8c6f20311732aef5070bb43ca5e8012ce0013335f2e94d5bd8e85c56e
 size 13648432

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94b41fee192042a9231bc1472a99b2509e0ba0e5a7d8421a95fe0b306e7e49dd
+oid sha256:568e1e6f9a75fe7d912123661bcb4d4b277b1ea7fc0276a156d8360c3005786a
 size 7309882

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f895ebca9457e7f3dcd70f61f7e4463c2de0333085250ad5b62167b24f32b158
+oid sha256:b6994cb487905172b0ba255400eaecb8aa47a01b2c6f61db8cf605bf89aaea0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14267515923566879,
+  "epoch": 0.15286624203821655,
   "eval_steps": 500,
-  "global_step": 14,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -259,6 +259,24 @@
       "rewards/margins": 0.006654377095401287,
       "rewards/rejected": -0.26230132579803467,
       "step": 14
+    },
+    {
+      "epoch": 0.15286624203821655,
+      "grad_norm": 2.0696280002593994,
+      "learning_rate": 9.489795918367348e-05,
+      "log_odds_chosen": 0.12293906509876251,
+      "log_odds_ratio": -0.6370925903320312,
+      "logits/chosen": -0.5484431385993958,
+      "logits/rejected": -0.5725057721138,
+      "logps/chosen": -2.460176944732666,
+      "logps/rejected": -2.5726397037506104,
+      "loss": 2.7249,
+      "nll_loss": 2.661222219467163,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": -0.2460177093744278,
+      "rewards/margins": 0.011246275156736374,
+      "rewards/rejected": -0.25726398825645447,
+      "step": 15
     }
   ],
   "logging_steps": 1,