Training in progress, step 16, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d49859a687f5bcf62f01bc8c9be1882fef9ff208931820730895575f61667169
+oid sha256:d322779a1186df23a7829764fb627209b085bd4b77e86bd6f3bdfa609e642671
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29c35731a9801a0d6782d07ac7c7beaaec9504135a62fbfbd41a6f5842ef98a5
+oid sha256:6d29cd0557a9a0f1041cf54c528dc5a0159d59a6be759a390a397c8f1ca1a6c1
 size 42545748

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6dc9dacb9cf3beacf8a1b58112bb95fab90581585484c32e86dfb3d4ea057b6
+oid sha256:45ce84522eef25e960ae0873f5accbfd9cd132c499be9678ea6d0f7d9ef1f2d4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.244663905702453,
+  "epoch": 0.326218540936604,
   "eval_steps": 500,
-  "global_step": 12,
+  "global_step": 16,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -223,6 +223,78 @@
       "rewards/margins": 0.007394128944724798,
       "rewards/rejected": -0.16955989599227905,
       "step": 12
+    },
+    {
+      "epoch": 0.26505256451099074,
+      "grad_norm": 2.420715093612671,
+      "learning_rate": 9.230769230769232e-05,
+      "log_odds_chosen": 0.10657332092523575,
+      "log_odds_ratio": -0.6556077599525452,
+      "logits/chosen": -2.683443784713745,
+      "logits/rejected": -2.6935503482818604,
+      "logps/chosen": -1.4284594058990479,
+      "logps/rejected": -1.508366584777832,
+      "loss": 1.7205,
+      "nll_loss": 1.654909372329712,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.14284594357013702,
+      "rewards/margins": 0.007990704849362373,
+      "rewards/rejected": -0.15083666145801544,
+      "step": 13
+    },
+    {
+      "epoch": 0.28544122331952854,
+      "grad_norm": 2.851985216140747,
+      "learning_rate": 8.974358974358975e-05,
+      "log_odds_chosen": 0.156551793217659,
+      "log_odds_ratio": -0.6308416128158569,
+      "logits/chosen": -2.6921679973602295,
+      "logits/rejected": -2.6880078315734863,
+      "logps/chosen": -1.332141637802124,
+      "logps/rejected": -1.4488908052444458,
+      "loss": 1.5952,
+      "nll_loss": 1.5321555137634277,
+      "rewards/accuracies": 0.671875,
+      "rewards/chosen": -0.13321417570114136,
+      "rewards/margins": 0.01167491264641285,
+      "rewards/rejected": -0.14488908648490906,
+      "step": 14
+    },
+    {
+      "epoch": 0.3058298821280663,
+      "grad_norm": 2.4120404720306396,
+      "learning_rate": 8.717948717948718e-05,
+      "log_odds_chosen": 0.0856461226940155,
+      "log_odds_ratio": -0.6610275506973267,
+      "logits/chosen": -2.6284494400024414,
+      "logits/rejected": -2.6575706005096436,
+      "logps/chosen": -1.342667579650879,
+      "logps/rejected": -1.4053808450698853,
+      "loss": 1.5791,
+      "nll_loss": 1.5130078792572021,
+      "rewards/accuracies": 0.671875,
+      "rewards/chosen": -0.13426676392555237,
+      "rewards/margins": 0.006271325517445803,
+      "rewards/rejected": -0.1405380815267563,
+      "step": 15
+    },
+    {
+      "epoch": 0.326218540936604,
+      "grad_norm": 2.2445013523101807,
+      "learning_rate": 8.461538461538461e-05,
+      "log_odds_chosen": 0.18759144842624664,
+      "log_odds_ratio": -0.617063045501709,
+      "logits/chosen": -2.574859857559204,
+      "logits/rejected": -2.5844004154205322,
+      "logps/chosen": -1.24087393283844,
+      "logps/rejected": -1.3730320930480957,
+      "loss": 1.5016,
+      "nll_loss": 1.439911127090454,
+      "rewards/accuracies": 0.703125,
+      "rewards/chosen": -0.1240873858332634,
+      "rewards/margins": 0.013215810991823673,
+      "rewards/rejected": -0.1373032033443451,
+      "step": 16
     }
   ],
   "logging_steps": 1,