Training in progress, step 13, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a02e3260ee9d062c315bc654bc3b6ea88b9c6010da782a47c8833c40c4de4572
+oid sha256:57af3ec9e9bc0bac55cf64ba5e1fb08de9d2ede3096818555088a2ff7e428ead
 size 13648432

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0626c259fd2ef9911b97f6e7245714e0c7b47939414128b3839167e3cc8351ab
+oid sha256:953e63cc83c713f7f7e9059f9fc5c9822da1756e40eb6fe9357c73ea034a8a54
 size 7309882

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97f1945a3cd3872f925c6c28b703dcb3b39023385486b89709dc5e08cdba61de
+oid sha256:74e03bb177867092e474fff4d24dc38255337f57b1a5894b05877f1068f78f43
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12229299363057325,
+  "epoch": 0.13248407643312102,
   "eval_steps": 500,
-  "global_step": 12,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -223,6 +223,24 @@
       "rewards/margins": -0.0026267748326063156,
       "rewards/rejected": -0.26625293493270874,
       "step": 12
+    },
+    {
+      "epoch": 0.13248407643312102,
+      "grad_norm": 1.8597255945205688,
+      "learning_rate": 9.557823129251701e-05,
+      "log_odds_chosen": 0.0966324731707573,
+      "log_odds_ratio": -0.6508103013038635,
+      "logits/chosen": -0.5836719274520874,
+      "logits/rejected": -0.6042653322219849,
+      "logps/chosen": -2.5945496559143066,
+      "logps/rejected": -2.6839816570281982,
+      "loss": 2.891,
+      "nll_loss": 2.8259291648864746,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.25945499539375305,
+      "rewards/margins": 0.008943157270550728,
+      "rewards/rejected": -0.26839813590049744,
+      "step": 13
     }
   ],
   "logging_steps": 1,