checkpoint-400

edit-qwen3.5-2b/{checkpoint-350 → checkpoint-400}/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:615027d4316ae38d0bd9a05f6f73a58a48f0a41299020c158d699dd2506e0333
+oid sha256:d0de40c4432cd3c1bf14a3f38149584b15af1ede17906f76f4dd71b1249755da
 size 134604152

edit-qwen3.5-2b/{checkpoint-350 → checkpoint-400}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6a507dfe8a03d18a13d4e3ea82211fa095887561c48bfb931cbb41ae7118ee4
+oid sha256:b6fba941b664b2ee77f60d5cd2884c4d7d320d4ba1fd46aa7ebd3aa17ae7cb85
 size 269426431

edit-qwen3.5-2b/{checkpoint-350 → checkpoint-400}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb0cc07bf8584542fc3e445215bf5f344f42ca1fd0358903763df928113fd0ad
+oid sha256:480d7441c2e8f584c3db05ea6ab19542f9132f3782b5029d46b7c2f24752b3c6
 size 14645

edit-qwen3.5-2b/{checkpoint-350 → checkpoint-400}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06d22c6a60fc2beed1e26cbe201ba98f53ea7e3c9a4142c6b073b11a4a68afe7
+oid sha256:0d6935181675e1d1665ff39c91c33682acc867a658aded1287cdcaddd5b6d872
 size 1465

edit-qwen3.5-2b/{checkpoint-350 → checkpoint-400}/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": 2.011527377521614,
+  "epoch": 2.2997118155619596,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -309,6 +309,49 @@
       "eval_samples_per_second": 56.383,
       "eval_steps_per_second": 14.096,
       "step": 350
+    },
+    {
+      "epoch": 2.069164265129683,
+      "grad_norm": 2.879030466079712,
+      "learning_rate": 3.292929292929293e-05,
+      "loss": 0.6604353904724121,
+      "step": 360
+    },
+    {
+      "epoch": 2.126801152737752,
+      "grad_norm": 3.0312411785125732,
+      "learning_rate": 3.090909090909091e-05,
+      "loss": 0.4823118209838867,
+      "step": 370
+    },
+    {
+      "epoch": 2.1844380403458215,
+      "grad_norm": 3.097743034362793,
+      "learning_rate": 2.8888888888888888e-05,
+      "loss": 0.4382351875305176,
+      "step": 380
+    },
+    {
+      "epoch": 2.2420749279538903,
+      "grad_norm": 2.786288261413574,
+      "learning_rate": 2.686868686868687e-05,
+      "loss": 0.3148329734802246,
+      "step": 390
+    },
+    {
+      "epoch": 2.2997118155619596,
+      "grad_norm": 3.8189518451690674,
+      "learning_rate": 2.4848484848484847e-05,
+      "loss": 0.7436184883117676,
+      "step": 400
+    },
+    {
+      "epoch": 2.2997118155619596,
+      "eval_loss": 1.0097650289535522,
+      "eval_runtime": 2.5523,
+      "eval_samples_per_second": 56.419,
+      "eval_steps_per_second": 14.105,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -328,7 +371,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.3177856345391104e+16,
+  "total_flos": 2.6578399898932224e+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:f9d7ad78e505fdfa48ca2010e6c24e3fa64a2b5f3c46e84ca6ef4021bab3e48b
-size 14653
+oid sha256:733499a8a9725ec95a1a377a6fd52119a63f9d808ed75b32cb36935fab6e4e4f
+size 15979