Training in progress, step 17, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40ae3564311bfbe49e68535b3496c99ce8072b21ad3b5839a07acab622564e8f
+oid sha256:2072e0c9e430cd9c1d1b0d97e0a2f69661beae4aae809f649487ba3a231006cc
 size 13648432

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cdc25067af02f302ae5f20feae9590d56ead7c091032508ad7b8f3cfd38e291
+oid sha256:edadc7bb3a3cf5f9e56c11af665611ed6af15aa65b8b091ca7262fb228f15b39
 size 7309882

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:397c58c95656820d3439e353b3be5fd82dca80421fee3f09e902bff4cb788a6b
+oid sha256:7c1ccdcfcaff5b9d27cc24fae538243e050f8af44531833539162f8573b512ec
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16305732484076432,
+  "epoch": 0.1732484076433121,
   "eval_steps": 500,
-  "global_step": 16,
+  "global_step": 17,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -295,6 +295,24 @@
       "rewards/margins": 0.007322215940803289,
       "rewards/rejected": -0.24865636229515076,
       "step": 16
+    },
+    {
+      "epoch": 0.1732484076433121,
+      "grad_norm": 3.263835906982422,
+      "learning_rate": 9.421768707482994e-05,
+      "log_odds_chosen": 0.12279009073972702,
+      "log_odds_ratio": -0.6375764608383179,
+      "logits/chosen": -0.5939255952835083,
+      "logits/rejected": -0.5961549878120422,
+      "logps/chosen": -2.3610243797302246,
+      "logps/rejected": -2.47149395942688,
+      "loss": 2.568,
+      "nll_loss": 2.5042312145233154,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.23610244691371918,
+      "rewards/margins": 0.011046944186091423,
+      "rewards/rejected": -0.24714939296245575,
+      "step": 17
     }
   ],
   "logging_steps": 1,