Training in progress, step 13500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c02df1845fa9dd645c303520d4ca01928b45d9afe4205811ef3eaeecc9cf9dea
+oid sha256:7e114d1cf986fb612752ba70fb0ea17cb79352616af50e33cfc89ace788d3b72
 size 3424816

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59710797fdbcc44b6a2af90614284740a92e6ffda2ec5aa2056c1e30df2c536b
+oid sha256:6163818d4bd20de9be429c12036c9bb1da392b50e19a30f533745961246d38f4
 size 3447162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3fcb8b7132fdda989f7bbb14a5bf464435849629fe731ccbc64c4724068a57e
+oid sha256:adbac4581908b419c3039e502a4aacf8ebe77d7c5097a659c9e661f2ab321b78
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4280930a39a9bc68d11760521afcfbc98f92d3d0361616a4bf1913be5b2f748
+oid sha256:7eeb85a3c5947dca7875fa9a54d0371a562d757985dcc841d33c689ef8bd64c7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.8,
+  "epoch": 3.0,
   "eval_steps": 900,
-  "global_step": 12600,
+  "global_step": 13500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -456,6 +456,37 @@
       "eval_samples_per_second": 1.62,
       "eval_steps_per_second": 0.102,
       "step": 12600
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 5.375,
+      "learning_rate": 0.0,
+      "logits/chosen": -3.2291133403778076,
+      "logits/rejected": -3.2376110553741455,
+      "logps/chosen": -156.7918701171875,
+      "logps/rejected": -134.85708618164062,
+      "loss": 0.6898,
+      "rewards/accuracies": 0.527222216129303,
+      "rewards/chosen": 0.03252815455198288,
+      "rewards/margins": 0.01564921624958515,
+      "rewards/rejected": 0.016878938302397728,
+      "step": 13500
+    },
+    {
+      "epoch": 3.0,
+      "eval_logits/chosen": -3.013054370880127,
+      "eval_logits/rejected": -3.0272860527038574,
+      "eval_logps/chosen": -157.42190551757812,
+      "eval_logps/rejected": -135.01458740234375,
+      "eval_loss": 0.6845603585243225,
+      "eval_rewards/accuracies": 0.5476190447807312,
+      "eval_rewards/chosen": 0.04152738302946091,
+      "eval_rewards/margins": 0.026597492396831512,
+      "eval_rewards/rejected": 0.014929892495274544,
+      "eval_runtime": 616.7592,
+      "eval_samples_per_second": 1.621,
+      "eval_steps_per_second": 0.102,
+      "step": 13500
     }
   ],
   "logging_steps": 900,