Training in progress, step 275, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7e059af2fa1682f997e031ec3ea16d4b7f1a901f0a40a963cb0c2bf88a6dcc6
+oid sha256:4b4a21428d6c7636bb544f872b5623df6e884e7437687862a5f3d04f923b6d48
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab6fd2dd4d4671d2a95fba6147743f118484bc79d3ce4925e5e5ad064766fc4a
+oid sha256:e508ee4172c367fc5f059f559b7960256770a6c6ad6409ef65eb2f354d318ca6
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c41acd26c86d70d331c5563ab0c5313662afe31133e12a8b590736afe2c91d4c
+oid sha256:da9a63ca771fcdbabf21b707c3680464f1a559a6fb7c42095ebd8941c7fa90b5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d1617b580f1638489e3c8c2c28b0fae6efb39474b08ccf2fbee4f3c8bf63bcd
+oid sha256:373aad709c251f92b29c15e15959fdc2aaf4ffb38eba8495b44748a1f4d8fb58
 size 1064

last-checkpoint/tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
-size 11422063
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001991064104299902,
+  "epoch": 0.0021901705147298924,
   "eval_steps": 500,
-  "global_step": 250,
+  "global_step": 275,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -307,6 +307,30 @@
       "reward_std": 0.24264758601784706,
       "rewards/custom_reward_simplified_v7_dblog": 0.6875,
       "step": 250
+    },
+    {
+      "completion_length": 731.66875,
+      "epoch": 0.002070706668471898,
+      "grad_norm": 0.1944543570280075,
+      "kl": 0.001084678602637723,
+      "learning_rate": 4.998942375205502e-06,
+      "loss": 0.0,
+      "reward": 0.796875,
+      "reward_std": 0.31279500126838683,
+      "rewards/custom_reward_simplified_v7_dblog": 0.796875,
+      "step": 260
+    },
+    {
+      "completion_length": 770.69375,
+      "epoch": 0.0021503492326438944,
+      "grad_norm": 0.10904921591281891,
+      "kl": 0.0012701354396995157,
+      "learning_rate": 4.997620553954645e-06,
+      "loss": 0.0001,
+      "reward": 0.653125,
+      "reward_std": 0.1583670809864998,
+      "rewards/custom_reward_simplified_v7_dblog": 0.653125,
+      "step": 270
     }
   ],
   "logging_steps": 10,