checkpoint-500

edit-qwen3.5-2b/{checkpoint-450 → checkpoint-500}/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:609465288589443a6141621f706d0e0a7a751a57dec19aa417f6718dabb20b6c
+oid sha256:c17cdaa323eca4ae4260265d7fd984189bc6d3cd705157fd83a1cdf98562cea2
 size 134604152

edit-qwen3.5-2b/{checkpoint-450 → checkpoint-500}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16bea85bbaa0c9c8182d7008601d4f963390a7785f4219c26dc827dae1d04e6d
+oid sha256:cf1b31ce1f39f00350ad9dddc6393fa1c148b7fb05eef9f00aa2f923ff01473f
 size 269426431

edit-qwen3.5-2b/{checkpoint-450 → checkpoint-500}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1416146577c55503c3516767da9d2425f2969f6e0ff823b8f246492379b4756
+oid sha256:189c9f75b7488d8f55f4a51eae65f911dfdd8e75a2d3bd2d43f548bfc5d580e9
 size 14645

edit-qwen3.5-2b/{checkpoint-450 → checkpoint-500}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f428fa345834e7d5a04466e8a86e74db282439f94f12e58c1904cbb0d1242e1a
+oid sha256:7ff0216cd99ce5cabe3bcec864f4244f481742d80e606b49df789f1f433da313
 size 1465

edit-qwen3.5-2b/{checkpoint-450 → checkpoint-500}/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": 2.5878962536023056,
+  "epoch": 2.8760806916426516,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -395,6 +395,49 @@
       "eval_samples_per_second": 56.456,
       "eval_steps_per_second": 14.114,
       "step": 450
+    },
+    {
+      "epoch": 2.6455331412103744,
+      "grad_norm": 3.9099183082580566,
+      "learning_rate": 1.2727272727272727e-05,
+      "loss": 0.45267200469970703,
+      "step": 460
+    },
+    {
+      "epoch": 2.7031700288184437,
+      "grad_norm": 4.078179359436035,
+      "learning_rate": 1.0707070707070708e-05,
+      "loss": 0.45285758972167967,
+      "step": 470
+    },
+    {
+      "epoch": 2.760806916426513,
+      "grad_norm": 4.219217300415039,
+      "learning_rate": 8.686868686868687e-06,
+      "loss": 0.3903587579727173,
+      "step": 480
+    },
+    {
+      "epoch": 2.8184438040345823,
+      "grad_norm": 3.370008945465088,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.6574668407440185,
+      "step": 490
+    },
+    {
+      "epoch": 2.8760806916426516,
+      "grad_norm": 3.4251184463500977,
+      "learning_rate": 4.646464646464647e-06,
+      "loss": 0.5324229717254638,
+      "step": 500
+    },
+    {
+      "epoch": 2.8760806916426516,
+      "eval_loss": 0.9864620566368103,
+      "eval_runtime": 2.5526,
+      "eval_samples_per_second": 56.413,
+      "eval_steps_per_second": 14.103,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -414,7 +457,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.991792883425024e+16,
+  "total_flos": 3.3232099729565184e+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:e9823821ec0ad20dd1affaf3ee846d1a3da597075cfabf570f720d6992122504
-size 17305
+oid sha256:cf99242dd6706d08d6e0335f3979b79d43d8e74d9b649e90800c72e2392ff4ab
+size 18631