Training in progress, step 14, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57af3ec9e9bc0bac55cf64ba5e1fb08de9d2ede3096818555088a2ff7e428ead
+oid sha256:524a0383464ed8233cb5c31d43fcca20d30f68bf78f3883d33c20e2d06688be7
 size 13648432

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:953e63cc83c713f7f7e9059f9fc5c9822da1756e40eb6fe9357c73ea034a8a54
+oid sha256:94b41fee192042a9231bc1472a99b2509e0ba0e5a7d8421a95fe0b306e7e49dd
 size 7309882

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74e03bb177867092e474fff4d24dc38255337f57b1a5894b05877f1068f78f43
+oid sha256:f895ebca9457e7f3dcd70f61f7e4463c2de0333085250ad5b62167b24f32b158
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.13248407643312102,
+  "epoch": 0.14267515923566879,
   "eval_steps": 500,
-  "global_step": 13,
+  "global_step": 14,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -241,6 +241,24 @@
       "rewards/margins": 0.008943157270550728,
       "rewards/rejected": -0.26839813590049744,
       "step": 13
+    },
+    {
+      "epoch": 0.14267515923566879,
+      "grad_norm": 1.9950586557388306,
+      "learning_rate": 9.523809523809524e-05,
+      "log_odds_chosen": 0.07333967834711075,
+      "log_odds_ratio": -0.6641579270362854,
+      "logits/chosen": -0.5741627812385559,
+      "logits/rejected": -0.6016291379928589,
+      "logps/chosen": -2.556469678878784,
+      "logps/rejected": -2.6230132579803467,
+      "loss": 2.8169,
+      "nll_loss": 2.7504758834838867,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.2556469738483429,
+      "rewards/margins": 0.006654377095401287,
+      "rewards/rejected": -0.26230132579803467,
+      "step": 14
     }
   ],
   "logging_steps": 1,