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:f0dda1b3a74879de59b8a3a38cf543baa4c978fe5106b3ebf47e2acf49cbb0f9
+oid sha256:70082a784b3a40b80eef4107594f9ad4aa081bd6d9f8c106958c2ea614d54277
 size 590925768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6ca5950cdfcfe617c06d832f8c9bdcc2c48f0bb3ac300b66428443eee871b99
+oid sha256:7a32692aa2cd37cdb83fa8f39f049e7c3266de86872bd53e275966d8eba7e480
 size 296481140

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec8b93ce75495f1e8832c6df04d7fb196a5e52bb09b8a3c23a2b12a44245658a
+oid sha256:85789d24a030dd0676934dfc35b17ca73a64f42fa104badf9fe0a48fd11a328f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.017533045681802615,
+  "epoch": 0.02337739424240349,
   "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": -0.0014716808218508959,
       "rewards/rejected": -0.13422170281410217,
       "step": 12
+    },
+    {
+      "epoch": 0.018994132821952833,
+      "grad_norm": 0.7423222064971924,
+      "learning_rate": 9.998062075464943e-06,
+      "log_odds_chosen": -0.11804741621017456,
+      "log_odds_ratio": -0.7873090505599976,
+      "logits/chosen": -2.200981616973877,
+      "logits/rejected": -2.1934943199157715,
+      "logps/chosen": -1.2868025302886963,
+      "logps/rejected": -1.2002918720245361,
+      "loss": 1.6073,
+      "nll_loss": 1.5285530090332031,
+      "rewards/accuracies": 0.3125,
+      "rewards/chosen": -0.1286802589893341,
+      "rewards/margins": -0.008651047013700008,
+      "rewards/rejected": -0.12002921104431152,
+      "step": 13
+    },
+    {
+      "epoch": 0.020455219962103054,
+      "grad_norm": 0.6683437824249268,
+      "learning_rate": 9.997362330917032e-06,
+      "log_odds_chosen": -0.012934267520904541,
+      "log_odds_ratio": -0.7275698184967041,
+      "logits/chosen": -2.1948914527893066,
+      "logits/rejected": -2.200413227081299,
+      "logps/chosen": -1.3400592803955078,
+      "logps/rejected": -1.3343003988265991,
+      "loss": 1.6521,
+      "nll_loss": 1.5793243646621704,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.13400591909885406,
+      "rewards/margins": -0.0005758859915658832,
+      "rewards/rejected": -0.13343004882335663,
+      "step": 14
+    },
+    {
+      "epoch": 0.02191630710225327,
+      "grad_norm": 0.6963202357292175,
+      "learning_rate": 9.996554973931884e-06,
+      "log_odds_chosen": -0.11072862148284912,
+      "log_odds_ratio": -0.7919189929962158,
+      "logits/chosen": -2.1773252487182617,
+      "logits/rejected": -2.162838935852051,
+      "logps/chosen": -1.305843710899353,
+      "logps/rejected": -1.2427345514297485,
+      "loss": 1.6167,
+      "nll_loss": 1.5374785661697388,
+      "rewards/accuracies": 0.359375,
+      "rewards/chosen": -0.13058437407016754,
+      "rewards/margins": -0.006310915574431419,
+      "rewards/rejected": -0.12427344918251038,
+      "step": 15
+    },
+    {
+      "epoch": 0.02337739424240349,
+      "grad_norm": 0.6812885999679565,
+      "learning_rate": 9.995640021894996e-06,
+      "log_odds_chosen": -0.03462236002087593,
+      "log_odds_ratio": -0.7293962836265564,
+      "logits/chosen": -2.1697518825531006,
+      "logits/rejected": -2.1682655811309814,
+      "logps/chosen": -1.2563740015029907,
+      "logps/rejected": -1.2293565273284912,
+      "loss": 1.5666,
+      "nll_loss": 1.4936596155166626,
+      "rewards/accuracies": 0.40625,
+      "rewards/chosen": -0.12563739717006683,
+      "rewards/margins": -0.0027017316315323114,
+      "rewards/rejected": -0.12293566763401031,
+      "step": 16
     }
   ],
   "logging_steps": 1.0,