Upload folder using huggingface_hub

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c95fd793fc0337979ec6c4129a6080db38f5dbe61244bcc458cca5dc773ea2c
+oid sha256:48fc89abd90a21ef7b36e2b1f8fbb4476ac359132a337229fa6f31e81625e032
 size 264308896

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbf558869a3675275ba8ba849ee958ef7d45c6303085d6c7a7ab1e5d746ef26a
+oid sha256:682da4dd151c64857eabf99f9fbc7c7e767ac42a1b626f95f3f9abc1cabd7582
 size 136089907

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02b05853d6fc885b4edf189843dd1363333f7b7831d00142f0b849df78b46cdd
+oid sha256:88dc39fe998588d5850095831bc034e4ff1606c17e9a23c7c4eb6652f638f52f
 size 14645

scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc0fa4ae2cdc54c52e59725723f1bf62720aad412266cfb060da831da5d7b169
+oid sha256:473fb6db6e2b1e587cd461a781ffd1335528b38f4ac58fcad263180181c9f9f5
 size 1383

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f85084d35070cb6a6db912f297b8d1016ee4f73d52182deee9f152e602928a16
+oid sha256:9bfc4cf403bbe48b7708cd2f91056532b3ac5b91e064eba6cfc7c555597c4bde
 size 1465

trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6072067115940035,
+  "epoch": 0.6078943749140421,
   "eval_steps": 500,
-  "global_step": 8830,
+  "global_step": 8840,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -24732,11 +24732,39 @@
       "rewards/match_format_exactly/mean": 1.0,
       "rewards/match_format_exactly/std": 0.0,
       "step": 8830
+    },
+    {
+      "completion_length": 23.075,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 57.9,
+      "completions/max_terminated_length": 57.9,
+      "completions/mean_length": 23.075,
+      "completions/mean_terminated_length": 23.075,
+      "completions/min_length": 9.7,
+      "completions/min_terminated_length": 9.7,
+      "epoch": 0.6078943749140421,
+      "frac_reward_zero_std": 0.9,
+      "grad_norm": 0.004883910529315472,
+      "kl": 1.190100622177124,
+      "learning_rate": 1.6284444444444448e-06,
+      "loss": 0.0012,
+      "num_tokens": 11018086.0,
+      "reward": 5.95,
+      "reward_std": 0.1,
+      "rewards/check_coherence/mean": 1.475,
+      "rewards/check_coherence/std": 0.05,
+      "rewards/check_response_quality/mean": 2.4875,
+      "rewards/check_response_quality/std": 0.025,
+      "rewards/match_format_approximately/mean": 0.9875,
+      "rewards/match_format_approximately/std": 0.025,
+      "rewards/match_format_exactly/mean": 1.0,
+      "rewards/match_format_exactly/std": 0.0,
+      "step": 8840
     }
   ],
   "logging_steps": 10,
   "max_steps": 12500,
-  "num_input_tokens_seen": 11005827,
+  "num_input_tokens_seen": 11018086,
   "num_train_epochs": 1,
   "save_steps": 10,
   "stateful_callbacks": {