checkpoint-200

verifier-qwen3.5-2b/{checkpoint-100 → checkpoint-200}/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:625f49fe7483fc760ce2c7907172fd27f5c59740f99290e87e5ea43593164db0
+oid sha256:bf59e7241b6d9f9d5521691a4dbb76d67ca51d0facb7c81f605a0471a6ecf570
 size 134604152

verifier-qwen3.5-2b/{checkpoint-100 → checkpoint-200}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da497bbf805a89c06a400d77de2daae67e63fa26110df86266fe4a0c4348a093
+oid sha256:f5b725bc74a325a963e4de2c61eb69793de9a80c5bd4ca2b705f7493b6e0a694
 size 269426431

verifier-qwen3.5-2b/{checkpoint-100 → checkpoint-200}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a52348434bd4d91caa1c184d161d03e578e0f98d142e50f3bf3cd374e72062f
+oid sha256:7f9197cb2325b9b47e226057dae57f81670041e1727b4f5c0693aca5457b601e
 size 14645

verifier-qwen3.5-2b/{checkpoint-100 → checkpoint-200}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac1bbdd3ce0af473d9ef76003e81bfacae2facea6fc38fa9562dacede3c723e4
+oid sha256:4d39e1efc00e6fe7a440b3b47997a336e3ba2211044f8a50e0a9d6394db6f64c
 size 1465

verifier-qwen3.5-2b/{checkpoint-100 → checkpoint-200}/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 100,
-  "best_metric": 0.2274889498949051,
-  "best_model_checkpoint": "./outputs/verifier-qwen3.5-2b/checkpoint-100",
-  "epoch": 0.3454231433506045,
+  "best_global_step": 200,
+  "best_metric": 0.20766094326972961,
+  "best_model_checkpoint": "./outputs/verifier-qwen3.5-2b/checkpoint-200",
+  "epoch": 0.690846286701209,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -94,6 +94,92 @@
       "eval_samples_per_second": 119.096,
       "eval_steps_per_second": 15.334,
       "step": 100
+    },
+    {
+      "epoch": 0.3799654576856649,
+      "grad_norm": 1.6563022136688232,
+      "learning_rate": 8.5480943738657e-05,
+      "loss": 0.2126215696334839,
+      "step": 110
+    },
+    {
+      "epoch": 0.41450777202072536,
+      "grad_norm": 1.256416916847229,
+      "learning_rate": 8.366606170598912e-05,
+      "loss": 0.1954953193664551,
+      "step": 120
+    },
+    {
+      "epoch": 0.44905008635578586,
+      "grad_norm": 1.5402225255966187,
+      "learning_rate": 8.185117967332124e-05,
+      "loss": 0.18174756765365602,
+      "step": 130
+    },
+    {
+      "epoch": 0.4835924006908463,
+      "grad_norm": 1.518054723739624,
+      "learning_rate": 8.003629764065335e-05,
+      "loss": 0.1569438695907593,
+      "step": 140
+    },
+    {
+      "epoch": 0.5181347150259067,
+      "grad_norm": 1.6671258211135864,
+      "learning_rate": 7.822141560798548e-05,
+      "loss": 0.19996687173843383,
+      "step": 150
+    },
+    {
+      "epoch": 0.5181347150259067,
+      "eval_loss": 0.22001148760318756,
+      "eval_runtime": 1.9657,
+      "eval_samples_per_second": 118.534,
+      "eval_steps_per_second": 15.262,
+      "step": 150
+    },
+    {
+      "epoch": 0.5526770293609672,
+      "grad_norm": 1.7403196096420288,
+      "learning_rate": 7.640653357531761e-05,
+      "loss": 0.16722545623779297,
+      "step": 160
+    },
+    {
+      "epoch": 0.5872193436960277,
+      "grad_norm": 1.5578631162643433,
+      "learning_rate": 7.459165154264974e-05,
+      "loss": 0.1962692379951477,
+      "step": 170
+    },
+    {
+      "epoch": 0.6217616580310881,
+      "grad_norm": 1.2932735681533813,
+      "learning_rate": 7.277676950998185e-05,
+      "loss": 0.18478379249572754,
+      "step": 180
+    },
+    {
+      "epoch": 0.6563039723661486,
+      "grad_norm": 1.350063443183899,
+      "learning_rate": 7.096188747731398e-05,
+      "loss": 0.18056931495666503,
+      "step": 190
+    },
+    {
+      "epoch": 0.690846286701209,
+      "grad_norm": 1.4605202674865723,
+      "learning_rate": 6.914700544464611e-05,
+      "loss": 0.19524022340774536,
+      "step": 200
+    },
+    {
+      "epoch": 0.690846286701209,
+      "eval_loss": 0.20766094326972961,
+      "eval_runtime": 1.9685,
+      "eval_samples_per_second": 118.366,
+      "eval_steps_per_second": 15.24,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -113,7 +199,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3152905916547072.0,
+  "total_flos": 6313645475278848.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

verifier-qwen3.5-2b/tb/events.out.tfevents.1790667609.02b48645612f.2184.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b07a76a9793f1fa59fbaf62500ac8628582631ee8d915790a0901da4e2e953b
-size 9353
+oid sha256:bb1a368d629d0a116e90b00ab92ccd6a23c7e08074d897f352f0eebf3db850c2
+size 10679