checkpoint-580

verifier-qwen3.5-2b/{checkpoint-550 → checkpoint-580}/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef0112cb6279c64891c3fbf9781cf8622b95dea08147b9471db340793f655f04
+oid sha256:99a1adf34b419b08770096a8cad8175a7db1ec35acd939985822bd4472342f1a
 size 134604152

verifier-qwen3.5-2b/{checkpoint-550 → checkpoint-580}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f121469db57217ecf928bc063c038cca415ad05e9890e2d2afe74a62ad5e321
+oid sha256:5e47ab3963066bfad6aca98f360952d54b93a7146f3e3cc990bb8c5a6ccbf6ee
 size 269426431

verifier-qwen3.5-2b/{checkpoint-550 → checkpoint-580}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:018e1b2991d90390d6929314d9b73f53aa7497ae4a01cb66bd267cf827f1ee0b
+oid sha256:a4026b6791cdc7d63738e839ec3d5a24f797974b97b7b5abf96d65025ed5bcf5
 size 14645

verifier-qwen3.5-2b/{checkpoint-550 → checkpoint-580}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47c3044171b3cc0e1d0b2d397d52db31d03eb57daac247de8ff2404539a8e621
+oid sha256:7a6112fa30c5dbad7af1b976693a28071346fb21ab769e7a2fde80a53c550ea0
 size 1465

verifier-qwen3.5-2b/{checkpoint-550 → checkpoint-580}/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 250,
   "best_metric": 0.18705631792545319,
   "best_model_checkpoint": "./outputs/verifier-qwen3.5-2b/checkpoint-250",
-  "epoch": 1.8981001727115716,
+  "epoch": 2.0,
   "eval_steps": 50,
-  "global_step": 550,
+  "global_step": 580,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -481,6 +481,35 @@
       "eval_samples_per_second": 117.891,
       "eval_steps_per_second": 15.179,
       "step": 550
+    },
+    {
+      "epoch": 1.932642487046632,
+      "grad_norm": 2.636624813079834,
+      "learning_rate": 3.8112522686025406e-06,
+      "loss": 0.10344580411911011,
+      "step": 560
+    },
+    {
+      "epoch": 1.9671848013816926,
+      "grad_norm": 1.0986496210098267,
+      "learning_rate": 1.996370235934664e-06,
+      "loss": 0.06643763184547424,
+      "step": 570
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.666596531867981,
+      "learning_rate": 1.8148820326678765e-07,
+      "loss": 0.0791854977607727,
+      "step": 580
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.2300214171409607,
+      "eval_runtime": 1.9663,
+      "eval_samples_per_second": 118.496,
+      "eval_steps_per_second": 15.257,
+      "step": 580
     }
   ],
   "logging_steps": 10,
@@ -495,12 +524,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.7360364052276224e+16,
+  "total_flos": 1.826552114729933e+16,
   "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 sha256:57fb1d62c434a0f0ed3aeee625ad538fe3c3bc3a61caaf858986951f59986cde
-size 19961
+oid sha256:133b3f3b09c6455cd641e58a7fdd5984c0b953ca630662cc2b4101649f078729
+size 20865