checkpoint-450

edit-qwen3.5-2b/{checkpoint-400 → checkpoint-450}/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0de40c4432cd3c1bf14a3f38149584b15af1ede17906f76f4dd71b1249755da
+oid sha256:609465288589443a6141621f706d0e0a7a751a57dec19aa417f6718dabb20b6c
 size 134604152

edit-qwen3.5-2b/{checkpoint-400 → checkpoint-450}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6fba941b664b2ee77f60d5cd2884c4d7d320d4ba1fd46aa7ebd3aa17ae7cb85
+oid sha256:16bea85bbaa0c9c8182d7008601d4f963390a7785f4219c26dc827dae1d04e6d
 size 269426431

edit-qwen3.5-2b/{checkpoint-400 → checkpoint-450}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:480d7441c2e8f584c3db05ea6ab19542f9132f3782b5029d46b7c2f24752b3c6
+oid sha256:d1416146577c55503c3516767da9d2425f2969f6e0ff823b8f246492379b4756
 size 14645

edit-qwen3.5-2b/{checkpoint-400 → checkpoint-450}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d6935181675e1d1665ff39c91c33682acc867a658aded1287cdcaddd5b6d872
+oid sha256:f428fa345834e7d5a04466e8a86e74db282439f94f12e58c1904cbb0d1242e1a
 size 1465

edit-qwen3.5-2b/{checkpoint-400 → checkpoint-450}/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": 2.2997118155619596,
+  "epoch": 2.5878962536023056,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -352,6 +352,49 @@
       "eval_samples_per_second": 56.419,
       "eval_steps_per_second": 14.105,
       "step": 400
+    },
+    {
+      "epoch": 2.357348703170029,
+      "grad_norm": 4.348433971405029,
+      "learning_rate": 2.282828282828283e-05,
+      "loss": 0.586982011795044,
+      "step": 410
+    },
+    {
+      "epoch": 2.414985590778098,
+      "grad_norm": 3.5055832862854004,
+      "learning_rate": 2.080808080808081e-05,
+      "loss": 0.39878134727478026,
+      "step": 420
+    },
+    {
+      "epoch": 2.472622478386167,
+      "grad_norm": 4.1734747886657715,
+      "learning_rate": 1.878787878787879e-05,
+      "loss": 0.48946046829223633,
+      "step": 430
+    },
+    {
+      "epoch": 2.5302593659942363,
+      "grad_norm": 3.2713208198547363,
+      "learning_rate": 1.6767676767676768e-05,
+      "loss": 0.4852273941040039,
+      "step": 440
+    },
+    {
+      "epoch": 2.5878962536023056,
+      "grad_norm": 3.623262882232666,
+      "learning_rate": 1.4747474747474749e-05,
+      "loss": 0.6178666591644287,
+      "step": 450
+    },
+    {
+      "epoch": 2.5878962536023056,
+      "eval_loss": 1.0052427053451538,
+      "eval_runtime": 2.5507,
+      "eval_samples_per_second": 56.456,
+      "eval_steps_per_second": 14.114,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -371,7 +414,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.6578399898932224e+16,
+  "total_flos": 2.991792883425024e+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 sha256:733499a8a9725ec95a1a377a6fd52119a63f9d808ed75b32cb36935fab6e4e4f
-size 15979
+oid sha256:e9823821ec0ad20dd1affaf3ee846d1a3da597075cfabf570f720d6992122504
+size 17305