Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df6ab6a60757df24462f3bd75fd1dfc82f78adf8612b5003984c90250fb8b620
+oid sha256:0067bf041abcc7f640b160e1e89e396eecd076d1fa103ca8aced3343ea31020e
 size 83115256

last-checkpoint/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4b621a709862532fab84bdd26da203fec37f54eec099a3c2722ae82b4558867
+oid sha256:196bef52b600c621ba1bc1b0c23bba01a60fd669d7849244954d82a09fccbec5
 size 166458326

last-checkpoint/pytorch_model_fsdp.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c890088ae0961b8cbdfa5dbeaa9ef1ff77c9568cb557d5d28606714d88add78b
+oid sha256:063ad7778a473e9ff3680c3427add129f7c79526e1b6f0c5ee9ff29d1378eaa0
 size 83202410

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9d306b0a206f0fc3110c9ad9c595fdedbab2f23084ce7c41e61873dac54abb7
+oid sha256:1e2ed9259304616a8ecebc61c5d000777b2978635f7a705b8d7081c480ce0bde
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08067226890756303,
+  "epoch": 0.0896358543417367,
   "eval_steps": 500,
-  "global_step": 18,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -278,6 +278,36 @@
       "rewards/margins": 7.247048854827881,
       "rewards/rejected": -8.813165664672852,
       "step": 18
+    },
+    {
+      "epoch": 0.08515406162464986,
+      "grad_norm": 1.9467198848724365,
+      "learning_rate": 8.645454235739903e-06,
+      "logits/chosen": -6.274759769439697,
+      "logits/rejected": -6.058895111083984,
+      "logps/chosen": -253.76348876953125,
+      "logps/rejected": -375.3273010253906,
+      "loss": 0.2131,
+      "rewards/accuracies": 0.921875,
+      "rewards/chosen": -0.9127716422080994,
+      "rewards/margins": 7.889276504516602,
+      "rewards/rejected": -8.802047729492188,
+      "step": 19
+    },
+    {
+      "epoch": 0.0896358543417367,
+      "grad_norm": 2.9522013664245605,
+      "learning_rate": 2.1852399266194314e-06,
+      "logits/chosen": -6.096031665802002,
+      "logits/rejected": -6.0123748779296875,
+      "logps/chosen": -293.298095703125,
+      "logps/rejected": -377.3089599609375,
+      "loss": 0.256,
+      "rewards/accuracies": 0.890625,
+      "rewards/chosen": -1.636772871017456,
+      "rewards/margins": 7.670954704284668,
+      "rewards/rejected": -9.307727813720703,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -292,7 +322,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }