checkpoint-250

edit-qwen3.5-2b/{checkpoint-200 → checkpoint-250}/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c7b2139bfa85954ecc4ddf56d29a80db597a7a2c1d04b75ae74e41688d0b1dc
+oid sha256:0f335ac58ef7285c169a541a936deaa09de5a4bc337fc5a658163e8e56fecf5a
 size 134604152

edit-qwen3.5-2b/{checkpoint-200 → checkpoint-250}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04141f72da7ba24f697adc74fc80fee14be14daf03dc8f6325eeae461a3f9374
+oid sha256:fe247bb153f5e48a6347f7acd41b9583dc3dfb20f84f4de68a89222466c464bf
 size 269426431

edit-qwen3.5-2b/{checkpoint-200 → checkpoint-250}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcc015c243960e175ce6ad5a0955ff172eaeeb5aac901582b5cc34830cc6bc24
+oid sha256:6a9bb72a4281afdaa85d24b988cedaad2e7575e9088aa3ae95e536cd421d4b51
 size 14645

edit-qwen3.5-2b/{checkpoint-200 → checkpoint-250}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c2f4641c0edb2bfb241fbdc1196c117a5f1697dbfac8e5dc6f94774f897bc32
+oid sha256:97887b03ed5ddb9fb30ec5a630828d150a649222e1efaf740f45334b4842e9f4
 size 1465

edit-qwen3.5-2b/{checkpoint-200 → checkpoint-250}/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": 1.1498559077809798,
+  "epoch": 1.4380403458213258,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -180,6 +180,49 @@
       "eval_samples_per_second": 56.433,
       "eval_steps_per_second": 14.108,
       "step": 200
+    },
+    {
+      "epoch": 1.207492795389049,
+      "grad_norm": 2.812197208404541,
+      "learning_rate": 6.323232323232323e-05,
+      "loss": 0.5693333625793457,
+      "step": 210
+    },
+    {
+      "epoch": 1.2651296829971181,
+      "grad_norm": 3.991762161254883,
+      "learning_rate": 6.121212121212121e-05,
+      "loss": 0.7459357261657715,
+      "step": 220
+    },
+    {
+      "epoch": 1.3227665706051872,
+      "grad_norm": 2.750476360321045,
+      "learning_rate": 5.91919191919192e-05,
+      "loss": 0.8752019882202149,
+      "step": 230
+    },
+    {
+      "epoch": 1.3804034582132565,
+      "grad_norm": 3.3135452270507812,
+      "learning_rate": 5.717171717171717e-05,
+      "loss": 0.7731741428375244,
+      "step": 240
+    },
+    {
+      "epoch": 1.4380403458213258,
+      "grad_norm": 4.044683933258057,
+      "learning_rate": 5.5151515151515156e-05,
+      "loss": 0.6258707046508789,
+      "step": 250
+    },
+    {
+      "epoch": 1.4380403458213258,
+      "eval_loss": 0.9547940492630005,
+      "eval_runtime": 2.5526,
+      "eval_samples_per_second": 56.413,
+      "eval_steps_per_second": 14.103,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -199,7 +242,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3413018767963136e+16,
+  "total_flos": 1.6731342844263936e+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 sha256:4d9f66376a79084a22812581ddac3f00d23fc4c6c331bb0a0745865773d1563f
-size 10675
+oid sha256:b5312debb0485f92b7b7650e1f23a4dff3d3a6eac45b6c9317518cb14d07641a
+size 12001