Training in progress, step 8, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afe86c1030d85f487dbaa747f3184d5a685096b20446b3a5c415a5404c51be57
+oid sha256:8398c0e5bddec9eb883e0399f65b755d78d063f3b9ecbe58f175f44f364cc7e9
 size 13648432

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73437178095b577cbb6ccd45b95b4e2591fd14a3e216d879675222d8b32be866
+oid sha256:35967646370f39bc8adcdeb6bb4be3fa34ef34aa59b57e6a7303e7a39ef1094c
 size 7309882

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5371e347fa271c949de68f5ea0cd89d44be17efe7025e824d262e6bcd68df751
+oid sha256:600149e975d1bacd170387afa159597e660c1a6e94a6b29b69de17c6162d48a4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07133757961783439,
+  "epoch": 0.08152866242038216,
   "eval_steps": 500,
-  "global_step": 7,
+  "global_step": 8,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,24 @@
       "rewards/margins": 0.003080902621150017,
       "rewards/rejected": -0.2951011657714844,
       "step": 7
+    },
+    {
+      "epoch": 0.08152866242038216,
+      "grad_norm": 1.8741809129714966,
+      "learning_rate": 9.727891156462585e-05,
+      "log_odds_chosen": 0.09863043576478958,
+      "log_odds_ratio": -0.6496734619140625,
+      "logits/chosen": -0.5901607275009155,
+      "logits/rejected": -0.5661267042160034,
+      "logps/chosen": -2.7296760082244873,
+      "logps/rejected": -2.8212223052978516,
+      "loss": 3.1928,
+      "nll_loss": 3.1278655529022217,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.2729676365852356,
+      "rewards/margins": 0.009154656901955605,
+      "rewards/rejected": -0.28212225437164307,
+      "step": 8
     }
   ],
   "logging_steps": 1,