Training in progress, step 12600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bc4ea4e83e24743f6ed00f142c8816faed4479ba2f5990b21043ab2925c5f16
+oid sha256:c02df1845fa9dd645c303520d4ca01928b45d9afe4205811ef3eaeecc9cf9dea
 size 3424816

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:358d107562a13aa9382425ce0af610ebb9eb465faafab68b36de0b7ee29c8b3e
+oid sha256:59710797fdbcc44b6a2af90614284740a92e6ffda2ec5aa2056c1e30df2c536b
 size 3447162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52cca5856c568bc52c683b690919168fa27bfbdfefc6e0a62355afa6011157c3
+oid sha256:c3fcb8b7132fdda989f7bbb14a5bf464435849629fe731ccbc64c4724068a57e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bcf513d5bff4d94c470a7d32357260ec2da198c18c2b52a4683b938e78fdb30
+oid sha256:d4280930a39a9bc68d11760521afcfbc98f92d3d0361616a4bf1913be5b2f748
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.6,
+  "epoch": 2.8,
   "eval_steps": 900,
-  "global_step": 11700,
+  "global_step": 12600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -425,6 +425,37 @@
       "eval_samples_per_second": 1.622,
       "eval_steps_per_second": 0.102,
       "step": 11700
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 6.9375,
+      "learning_rate": 6.89655172413793e-08,
+      "logits/chosen": -3.2290825843811035,
+      "logits/rejected": -3.238609552383423,
+      "logps/chosen": -155.42266845703125,
+      "logps/rejected": -132.62841796875,
+      "loss": 0.6884,
+      "rewards/accuracies": 0.5483333468437195,
+      "rewards/chosen": 0.03833283483982086,
+      "rewards/margins": 0.018470091745257378,
+      "rewards/rejected": 0.019862744957208633,
+      "step": 12600
+    },
+    {
+      "epoch": 2.8,
+      "eval_logits/chosen": -3.013180732727051,
+      "eval_logits/rejected": -3.0272974967956543,
+      "eval_logps/chosen": -157.42144775390625,
+      "eval_logps/rejected": -134.997314453125,
+      "eval_loss": 0.6886058449745178,
+      "eval_rewards/accuracies": 0.54067462682724,
+      "eval_rewards/chosen": 0.041760578751564026,
+      "eval_rewards/margins": 0.018192334100604057,
+      "eval_rewards/rejected": 0.02356824465095997,
+      "eval_runtime": 617.3224,
+      "eval_samples_per_second": 1.62,
+      "eval_steps_per_second": 0.102,
+      "step": 12600
     }
   ],
   "logging_steps": 900,