Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80db105b009fb93114803e32f31508f0e1c0ec28079143f026961c4f4cf3e469
+oid sha256:7d841bdf6b4728ba25ddfa075a6ecf7ffcd91ad64f151f5984cfdb0fb36616e2
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3477641575947a2ff6bc25fe793ce5f3806bb14bd921d11e487d3914218af487
+oid sha256:b591aa40759fbc489d41cede5b6d509cefae3af7c306b30fa1e6a7a4b8ec4837
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e41038421362cc3793a0cf8f1bb2ecf0a45df92fe445e455ba3ea3ee170030cb
+oid sha256:b9ffa2392d644ba2690b0835df4eac79e599506fd693b988dfb49d247c7e500c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae04182ae51e8bdccafb7cc0327b07cc7bf010fe19276cd2a27aeb0d48ae0ab7
+oid sha256:0119210f3709b267b1dcdc2165f2b55aac98c420d5275ee5428e502b1f632094
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.015729406423969226,
+  "epoch": 0.015928512834399215,
   "eval_steps": 500,
-  "global_step": 1975,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2371,6 +2371,42 @@
       "reward_std": 0.2198973834514618,
       "rewards/custom_reward_simplified_v7_dblog": 0.715625,
       "step": 1970
+    },
+    {
+      "completion_length": 641.45,
+      "epoch": 0.015769227706055225,
+      "grad_norm": 0.23187489807605743,
+      "kl": 0.017989515024237335,
+      "learning_rate": 4.5211988927752026e-07,
+      "loss": 0.0007,
+      "reward": 0.7875,
+      "reward_std": 0.24450960606336594,
+      "rewards/custom_reward_simplified_v7_dblog": 0.7875,
+      "step": 1980
+    },
+    {
+      "completion_length": 643.6375,
+      "epoch": 0.01584887027022722,
+      "grad_norm": 0.235895574092865,
+      "kl": 0.015841626143082977,
+      "learning_rate": 4.3148139714622365e-07,
+      "loss": 0.0006,
+      "reward": 0.896875,
+      "reward_std": 0.26189937368035315,
+      "rewards/custom_reward_simplified_v7_dblog": 0.896875,
+      "step": 1990
+    },
+    {
+      "completion_length": 629.60625,
+      "epoch": 0.015928512834399215,
+      "grad_norm": 0.2776155471801758,
+      "kl": 0.015184593386948109,
+      "learning_rate": 4.1128047146765936e-07,
+      "loss": 0.0006,
+      "reward": 0.921875,
+      "reward_std": 0.23378355875611306,
+      "rewards/custom_reward_simplified_v7_dblog": 0.921875,
+      "step": 2000
     }
   ],
   "logging_steps": 10,