Training in progress, step 44, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d8660ac4f46748d4fea7d183b030ee476ead541262b87e9cd468abd5cf2fd3f
+oid sha256:0b692fb3e97cf7d7f117b648d2d9d5c6cb4303fed1b353b124d68b9bae0ce7af
 size 590925768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:893d356ba86f8ffdcdcad783cb3fa0c7a7eac39b12a727448815b1cd1e8d5645
+oid sha256:e8e2c889141e437e95e4167240260c77a3c831959e07afd53c0a940b120467aa
 size 296481140

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:280dd73179115c4c161606f8d4213df78626a76fac949f56bf41551396432bdf
+oid sha256:9a33d7ef10436adaddd7a5b0ae02a851e8464f7fece53aa135a75d0095ea5afe
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05844348560600872,
+  "epoch": 0.06428783416660959,
   "eval_steps": 500,
-  "global_step": 40,
+  "global_step": 44,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -727,6 +727,78 @@
       "rewards/margins": -0.0024731969460844994,
       "rewards/rejected": -0.13805550336837769,
       "step": 40
+    },
+    {
+      "epoch": 0.059904572746158936,
+      "grad_norm": 0.5273575186729431,
+      "learning_rate": 9.937896060529485e-06,
+      "log_odds_chosen": -0.08113294094800949,
+      "log_odds_ratio": -0.7743253707885742,
+      "logits/chosen": -1.9785962104797363,
+      "logits/rejected": -1.9705551862716675,
+      "logps/chosen": -1.2821004390716553,
+      "logps/rejected": -1.208033561706543,
+      "loss": 1.5836,
+      "nll_loss": 1.5061376094818115,
+      "rewards/accuracies": 0.234375,
+      "rewards/chosen": -0.12821003794670105,
+      "rewards/margins": -0.007406666409224272,
+      "rewards/rejected": -0.12080337107181549,
+      "step": 41
+    },
+    {
+      "epoch": 0.061365659886309154,
+      "grad_norm": 0.5236508250236511,
+      "learning_rate": 9.934197316154721e-06,
+      "log_odds_chosen": -0.13003796339035034,
+      "log_odds_ratio": -0.7939882278442383,
+      "logits/chosen": -1.9101815223693848,
+      "logits/rejected": -1.943664312362671,
+      "logps/chosen": -1.155348777770996,
+      "logps/rejected": -1.0918152332305908,
+      "loss": 1.4569,
+      "nll_loss": 1.377458095550537,
+      "rewards/accuracies": 0.328125,
+      "rewards/chosen": -0.11553487926721573,
+      "rewards/margins": -0.006353363860398531,
+      "rewards/rejected": -0.10918151587247849,
+      "step": 42
+    },
+    {
+      "epoch": 0.06282674702645938,
+      "grad_norm": 0.4699207842350006,
+      "learning_rate": 9.9303923195285e-06,
+      "log_odds_chosen": -0.041184213012456894,
+      "log_odds_ratio": -0.7406144142150879,
+      "logits/chosen": -1.9506869316101074,
+      "logits/rejected": -1.9735560417175293,
+      "logps/chosen": -1.2942121028900146,
+      "logps/rejected": -1.2584986686706543,
+      "loss": 1.5464,
+      "nll_loss": 1.4723409414291382,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.12942121922969818,
+      "rewards/margins": -0.0035713440738618374,
+      "rewards/rejected": -0.1258498728275299,
+      "step": 43
+    },
+    {
+      "epoch": 0.06428783416660959,
+      "grad_norm": 0.5235589742660522,
+      "learning_rate": 9.92648115258704e-06,
+      "log_odds_chosen": 0.04650488868355751,
+      "log_odds_ratio": -0.7010443806648254,
+      "logits/chosen": -1.9501118659973145,
+      "logits/rejected": -1.9561800956726074,
+      "logps/chosen": -1.1499981880187988,
+      "logps/rejected": -1.1835464239120483,
+      "loss": 1.4224,
+      "nll_loss": 1.3523142337799072,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.11499983072280884,
+      "rewards/margins": 0.003354821354150772,
+      "rewards/rejected": -0.11835464835166931,
+      "step": 44
     }
   ],
   "logging_steps": 1.0,