Training in progress, step 19, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c1c2f9eb3807f15e5202c65322a8f3cfb134e7beab87fc2ec60ec7ce25d0220
+oid sha256:ee2b96db0e93a6619b3d097c0eaa3469c2afb27d62591810323a83dec110bd9b
 size 13648432

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d199b5dd209fd16b98226e0bfe983b172dc1010aece87d4e191d13daf3612235
+oid sha256:b46d0c54c243567a411320a64dbdd49c36fb7c2b1172c52baee8ca31cea57ffe
 size 7309882

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:523fdd0b639a62e85034051de84a610796befa0fd6e94d6a020f84859b31247b
+oid sha256:78a1dc42ca905df9cb387c589e1dae74e503f3621933abeafd9d287290af6058
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18343949044585986,
+  "epoch": 0.19363057324840766,
   "eval_steps": 500,
-  "global_step": 18,
+  "global_step": 19,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -331,6 +331,24 @@
       "rewards/margins": 0.013862377032637596,
       "rewards/rejected": -0.23906347155570984,
       "step": 18
+    },
+    {
+      "epoch": 0.19363057324840766,
+      "grad_norm": 1.8552919626235962,
+      "learning_rate": 9.35374149659864e-05,
+      "log_odds_chosen": 0.1357956975698471,
+      "log_odds_ratio": -0.6316878199577332,
+      "logits/chosen": -0.6498819589614868,
+      "logits/rejected": -0.6668039560317993,
+      "logps/chosen": -2.22139835357666,
+      "logps/rejected": -2.3428542613983154,
+      "loss": 2.3994,
+      "nll_loss": 2.336277723312378,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.22213983535766602,
+      "rewards/margins": 0.012145599350333214,
+      "rewards/rejected": -0.23428542912006378,
+      "step": 19
     }
   ],
   "logging_steps": 1,