Training in progress, step 11, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe2e764601139447b09b1940cad4fcd131d157b3e2784066a3141e9bfbdee2e4
+oid sha256:cd5001970a94c1aeb2be404f63b934153c6a8afecd421ffb89f6ae43dfb02029
 size 13648432

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cd62999c0283cf985daa9ac4c15a5bad20101c134a614f464395a815e2f477f
+oid sha256:b961d010e7b252944302920bab7291331927a0492c9deec402fe522402693a0c
 size 7309882

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a02099495f1ee0f69345f2400d62a00da3dfa60ed976e72211dd9b267ea7c6f
+oid sha256:e23ccafad489da96357ee6455b0c6b7c38f2cddbd7f8464d5fb60ce0c29726cc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10191082802547771,
+  "epoch": 0.11210191082802548,
   "eval_steps": 500,
-  "global_step": 10,
+  "global_step": 11,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,24 @@
       "rewards/margins": 0.004964826162904501,
       "rewards/rejected": -0.27728739380836487,
       "step": 10
+    },
+    {
+      "epoch": 0.11210191082802548,
+      "grad_norm": 2.745220422744751,
+      "learning_rate": 9.625850340136054e-05,
+      "log_odds_chosen": 0.0562276728451252,
+      "log_odds_ratio": -0.6704986095428467,
+      "logits/chosen": -0.5921126008033752,
+      "logits/rejected": -0.5893128514289856,
+      "logps/chosen": -2.645206928253174,
+      "logps/rejected": -2.696500539779663,
+      "loss": 3.0034,
+      "nll_loss": 2.936365842819214,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.26452070474624634,
+      "rewards/margins": 0.005129385739564896,
+      "rewards/rejected": -0.26965007185935974,
+      "step": 11
     }
   ],
   "logging_steps": 1,