checkpoint-150

edit-qwen3.5-2b/{checkpoint-50 → checkpoint-150}/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d832f0e7028771fce609568a9b4f180a858cb814f73d1e7249b02440397241f0
+oid sha256:c1728f9a704086e3589352b594b5e256dd7ff4e42ba8b23422f3b074bc59efce
 size 134604152

edit-qwen3.5-2b/{checkpoint-50 → checkpoint-150}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f35d00ee693c59692701624c37870bc1ac1fce5d3db9ccf3b386afab0acab59
+oid sha256:e1efdf3478d02050b220c46304cd72273ec6e592db8814768b70d6527ad63ce1
 size 269426431

edit-qwen3.5-2b/{checkpoint-50 → checkpoint-150}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8106c15826296de5d71c00671c582d299e589cc9f7689d0cd37d905ba9ea5c6d
+oid sha256:529f17025d0b7da5a0551fca62e4565a474ea67e2881c757146f59a354c567f9
 size 14645

edit-qwen3.5-2b/{checkpoint-50 → checkpoint-150}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:466b26b2fb2e52bf171794d0d11032cdaddebdfd2afd0dcc0ab4252a3aa9acd2
+oid sha256:78a8f80c807aa6a675c92ce4dd0be216c722daa1274f4adbc86cde14a2254e40
 size 1465

edit-qwen3.5-2b/{checkpoint-50 → checkpoint-150}/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 50,
-  "best_metric": 1.1613417863845825,
-  "best_model_checkpoint": "./outputs/edit-qwen3.5-2b/checkpoint-50",
-  "epoch": 0.2881844380403458,
+  "best_global_step": 150,
+  "best_metric": 0.9355365037918091,
+  "best_model_checkpoint": "./outputs/edit-qwen3.5-2b/checkpoint-150",
+  "epoch": 0.8645533141210374,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -51,6 +51,92 @@
       "eval_samples_per_second": 56.853,
       "eval_steps_per_second": 14.213,
       "step": 50
+    },
+    {
+      "epoch": 0.345821325648415,
+      "grad_norm": 3.6900596618652344,
+      "learning_rate": 9.353535353535354e-05,
+      "loss": 1.2613624572753905,
+      "step": 60
+    },
+    {
+      "epoch": 0.4034582132564842,
+      "grad_norm": 3.4724302291870117,
+      "learning_rate": 9.151515151515152e-05,
+      "loss": 0.9937849044799805,
+      "step": 70
+    },
+    {
+      "epoch": 0.4610951008645533,
+      "grad_norm": 3.44368052482605,
+      "learning_rate": 8.94949494949495e-05,
+      "loss": 1.165354347229004,
+      "step": 80
+    },
+    {
+      "epoch": 0.5187319884726225,
+      "grad_norm": 3.752511739730835,
+      "learning_rate": 8.747474747474747e-05,
+      "loss": 0.9866464614868165,
+      "step": 90
+    },
+    {
+      "epoch": 0.5763688760806917,
+      "grad_norm": 3.243701934814453,
+      "learning_rate": 8.545454545454545e-05,
+      "loss": 1.2611675262451172,
+      "step": 100
+    },
+    {
+      "epoch": 0.5763688760806917,
+      "eval_loss": 0.9719823002815247,
+      "eval_runtime": 2.5438,
+      "eval_samples_per_second": 56.607,
+      "eval_steps_per_second": 14.152,
+      "step": 100
+    },
+    {
+      "epoch": 0.6340057636887608,
+      "grad_norm": 5.817702293395996,
+      "learning_rate": 8.343434343434344e-05,
+      "loss": 1.1399730682373046,
+      "step": 110
+    },
+    {
+      "epoch": 0.69164265129683,
+      "grad_norm": 4.230010509490967,
+      "learning_rate": 8.141414141414141e-05,
+      "loss": 1.022247314453125,
+      "step": 120
+    },
+    {
+      "epoch": 0.7492795389048992,
+      "grad_norm": 5.1941914558410645,
+      "learning_rate": 7.93939393939394e-05,
+      "loss": 0.7813982009887696,
+      "step": 130
+    },
+    {
+      "epoch": 0.8069164265129684,
+      "grad_norm": 2.836448907852173,
+      "learning_rate": 7.737373737373738e-05,
+      "loss": 1.296474075317383,
+      "step": 140
+    },
+    {
+      "epoch": 0.8645533141210374,
+      "grad_norm": 4.288060188293457,
+      "learning_rate": 7.535353535353536e-05,
+      "loss": 1.1853026390075683,
+      "step": 150
+    },
+    {
+      "epoch": 0.8645533141210374,
+      "eval_loss": 0.9355365037918091,
+      "eval_runtime": 2.5492,
+      "eval_samples_per_second": 56.488,
+      "eval_steps_per_second": 14.122,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -70,7 +156,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3421478286965760.0,
+  "total_flos": 1.0098881638347264e+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:fa80a216c44b3ebde978198a5d88f07e7e3e839c246b6c2ba25e8ca1e5572d96
-size 8031
+oid sha256:ff0b233bc0fa1c0b505edf088c3b3cf7dc519f375840228353d9368d4e3f697c
+size 9349