Training in progress, step 6300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3679f487a29a66a28f7e38cfb4a58312820967a2b855198e16727c550fe3afd3
+oid sha256:f17501ff264f2f69aeebf03d6193fa59ef60e903b393d074668303cb68739293
 size 3424816

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7912ee99d02acbf74c5095cc093aa7b282ac9bb4b9317bdd53e915fc0dcc9750
+oid sha256:6fe730bbc6ae39067cc12154a4b4b7e10e6f3eaf5249f633ac442bfa80e15708
 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:d7b663c5ef2e9deb31c2106da816f19be00858604173d9e70e5a468f851d333d
+oid sha256:8a4e845a5abfbbcaeeb1729f67c9dc13e95e9d503cb9b8dfb91b1697fdaf6ebd
 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": 450,
-  "global_step": 5850,
+  "global_step": 6300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -425,6 +425,37 @@
       "eval_samples_per_second": 1.674,
       "eval_steps_per_second": 0.107,
       "step": 5850
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 16.75,
+      "learning_rate": 6.89655172413793e-08,
+      "logits/chosen": -3.2184925079345703,
+      "logits/rejected": -3.238489866256714,
+      "logps/chosen": -167.82688903808594,
+      "logps/rejected": -119.77684020996094,
+      "loss": 0.6852,
+      "rewards/accuracies": 0.5600000023841858,
+      "rewards/chosen": 0.0775378867983818,
+      "rewards/margins": 0.05544096976518631,
+      "rewards/rejected": 0.022096913307905197,
+      "step": 6300
+    },
+    {
+      "epoch": 2.8,
+      "eval_logits/chosen": -3.0090227127075195,
+      "eval_logits/rejected": -3.036957025527954,
+      "eval_logps/chosen": -161.59054565429688,
+      "eval_logps/rejected": -117.90101623535156,
+      "eval_loss": 0.6878227591514587,
+      "eval_rewards/accuracies": 0.5546875,
+      "eval_rewards/chosen": 0.06660065799951553,
+      "eval_rewards/margins": 0.05401822179555893,
+      "eval_rewards/rejected": 0.012582436203956604,
+      "eval_runtime": 299.1701,
+      "eval_samples_per_second": 1.671,
+      "eval_steps_per_second": 0.107,
+      "step": 6300
     }
   ],
   "logging_steps": 450,