Training in progress, step 2300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea4152a2ecb2a36c2f03c57c1af9834e82d74af2d98b546ef377df84e9217079
+oid sha256:51607906ace2c98e569d183ab45677434a935eac30550ca59fcf7e6b0aa28ecc
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3b771aa162d23f5298ffa3d4a7478a5f8ca06ca450f343b659dff96388c05cc
+oid sha256:9808d74ff94c8178a179d50be213199f49e72f74fef5bb8d5f22f51d5b64db0e
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4ce68317885d0fab0d249ff862a16f04f6bddc55d10bc7c8820876e15315633
+oid sha256:2e5009569494f30f2940455df04e4f5368d219ec998b9ebf88b01d9bbb842107
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:578d6fda5043112e1e2d7094db2258c237f4222eb739591bdc6ff4137fd79fa1
+oid sha256:16e85494c48f97d81e46f2565e394f0b90477ea8854b7c074fd4e2bd18c4915c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.018118683349129108,
+  "epoch": 0.018317789759559097,
   "eval_steps": 500,
-  "global_step": 2275,
+  "global_step": 2300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2731,6 +2731,42 @@
       "reward_std": 0.3084723956882954,
       "rewards/custom_reward_simplified_v7_dblog": 0.959375,
       "step": 2270
+    },
+    {
+      "completion_length": 662.05625,
+      "epoch": 0.018158504631215107,
+      "grad_norm": 0.153013676404953,
+      "kl": 0.017893880722112954,
+      "learning_rate": 3.798061746947995e-08,
+      "loss": 0.0007,
+      "reward": 0.753125,
+      "reward_std": 0.2308400221168995,
+      "rewards/custom_reward_simplified_v7_dblog": 0.753125,
+      "step": 2280
+    },
+    {
+      "completion_length": 615.55,
+      "epoch": 0.018238147195387102,
+      "grad_norm": 0.2853679060935974,
+      "kl": 0.0166370629100129,
+      "learning_rate": 3.1927217206564884e-08,
+      "loss": 0.0007,
+      "reward": 0.74375,
+      "reward_std": 0.25018117427825926,
+      "rewards/custom_reward_simplified_v7_dblog": 0.74375,
+      "step": 2290
+    },
+    {
+      "completion_length": 710.45,
+      "epoch": 0.018317789759559097,
+      "grad_norm": 0.011245607398450375,
+      "kl": 0.01835272475145757,
+      "learning_rate": 2.6395903547638825e-08,
+      "loss": 0.0007,
+      "reward": 0.78125,
+      "reward_std": 0.2881218962371349,
+      "rewards/custom_reward_simplified_v7_dblog": 0.78125,
+      "step": 2300
     }
   ],
   "logging_steps": 10,