checkpoint-522

edit-qwen3.5-2b/{checkpoint-500 → checkpoint-522}/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c17cdaa323eca4ae4260265d7fd984189bc6d3cd705157fd83a1cdf98562cea2
+oid sha256:5a131fb3173093e470e0ebf104035a1d8036da3476028965ffe8b4c29716abf5
 size 134604152

edit-qwen3.5-2b/{checkpoint-500 → checkpoint-522}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf1b31ce1f39f00350ad9dddc6393fa1c148b7fb05eef9f00aa2f923ff01473f
+oid sha256:16339f7d39dee8128ad4dad91ff053a817cadd0cd5175656d00073f85289b484
 size 269426431

edit-qwen3.5-2b/{checkpoint-500 → checkpoint-522}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:189c9f75b7488d8f55f4a51eae65f911dfdd8e75a2d3bd2d43f548bfc5d580e9
+oid sha256:e8da8f9385b4aef0617d60ce057ba8b334a00b95f8ef53b01233cb6867236f2f
 size 14645

edit-qwen3.5-2b/{checkpoint-500 → checkpoint-522}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ff0216cd99ce5cabe3bcec864f4244f481742d80e606b49df789f1f433da313
+oid sha256:57b1342a92a9abdc177d2ce815dae6b22c2b1803855905a8825da0b35bba438f
 size 1465

edit-qwen3.5-2b/{checkpoint-500 → checkpoint-522}/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 150,
   "best_metric": 0.9355365037918091,
   "best_model_checkpoint": "./outputs/edit-qwen3.5-2b/checkpoint-150",
-  "epoch": 2.8760806916426516,
+  "epoch": 3.0,
   "eval_steps": 50,
-  "global_step": 500,
+  "global_step": 522,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -438,6 +438,28 @@
       "eval_samples_per_second": 56.413,
       "eval_steps_per_second": 14.103,
       "step": 500
+    },
+    {
+      "epoch": 2.9337175792507204,
+      "grad_norm": 5.865486145019531,
+      "learning_rate": 2.6262626262626263e-06,
+      "loss": 0.3970566034317017,
+      "step": 510
+    },
+    {
+      "epoch": 2.9913544668587897,
+      "grad_norm": 0.623012363910675,
+      "learning_rate": 6.060606060606061e-07,
+      "loss": 0.2541007995605469,
+      "step": 520
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.9820418953895569,
+      "eval_runtime": 2.547,
+      "eval_samples_per_second": 56.538,
+      "eval_steps_per_second": 14.134,
+      "step": 522
     }
   ],
   "logging_steps": 10,
@@ -452,12 +474,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.3232099729565184e+16,
+  "total_flos": 3.448892658042317e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

edit-qwen3.5-2b/tb/events.out.tfevents.1790604388.9b7939721266.4215.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf99242dd6706d08d6e0335f3979b79d43d8e74d9b649e90800c72e2392ff4ab
-size 18631
+oid sha256:ef4878f89b7d5d077edeb7c9bce5f060004e2d63825b1031c34f943ff92d62d0
+size 19324