checkpoint-200

edit-qwen3.5-2b/{checkpoint-100 → checkpoint-200}/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26615955e4c50eac12e067b6c66d2621a63ef5a1ad8391830f76735bf6f51d86
+oid sha256:7c7b2139bfa85954ecc4ddf56d29a80db597a7a2c1d04b75ae74e41688d0b1dc
 size 134604152

edit-qwen3.5-2b/{checkpoint-100 → checkpoint-200}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2cfcfdc39eefed5ed00251eea8e942e7cad96886796c2faf482220a5e0a5bdd
+oid sha256:04141f72da7ba24f697adc74fc80fee14be14daf03dc8f6325eeae461a3f9374
 size 269426431

edit-qwen3.5-2b/{checkpoint-100 → checkpoint-200}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ba260817a557eb13476c1337b4391ca536c4d3a8b23bbe340e326650dd8dc6a
+oid sha256:bcc015c243960e175ce6ad5a0955ff172eaeeb5aac901582b5cc34830cc6bc24
 size 14645

edit-qwen3.5-2b/{checkpoint-100 → checkpoint-200}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18b962f0602a95b7f2ce81b7d2790c79b7334efadc529c67c355419631109139
+oid sha256:4c2f4641c0edb2bfb241fbdc1196c117a5f1697dbfac8e5dc6f94774f897bc32
 size 1465

edit-qwen3.5-2b/{checkpoint-100 → checkpoint-200}/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 100,
-  "best_metric": 0.9719823002815247,
-  "best_model_checkpoint": "./outputs/edit-qwen3.5-2b/checkpoint-100",
-  "epoch": 0.5763688760806917,
+  "best_global_step": 150,
+  "best_metric": 0.9355365037918091,
+  "best_model_checkpoint": "./outputs/edit-qwen3.5-2b/checkpoint-150",
+  "epoch": 1.1498559077809798,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -94,6 +94,92 @@
       "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
+    },
+    {
+      "epoch": 0.9221902017291066,
+      "grad_norm": 4.369518280029297,
+      "learning_rate": 7.333333333333333e-05,
+      "loss": 0.786583948135376,
+      "step": 160
+    },
+    {
+      "epoch": 0.9798270893371758,
+      "grad_norm": 3.0574004650115967,
+      "learning_rate": 7.131313131313132e-05,
+      "loss": 0.7988658428192139,
+      "step": 170
+    },
+    {
+      "epoch": 1.0345821325648414,
+      "grad_norm": 2.3126754760742188,
+      "learning_rate": 6.92929292929293e-05,
+      "loss": 0.9892278671264648,
+      "step": 180
+    },
+    {
+      "epoch": 1.0922190201729107,
+      "grad_norm": 3.308208703994751,
+      "learning_rate": 6.727272727272727e-05,
+      "loss": 0.9979540824890136,
+      "step": 190
+    },
+    {
+      "epoch": 1.1498559077809798,
+      "grad_norm": 2.233207941055298,
+      "learning_rate": 6.525252525252525e-05,
+      "loss": 0.6490315914154052,
+      "step": 200
+    },
+    {
+      "epoch": 1.1498559077809798,
+      "eval_loss": 0.9719119668006897,
+      "eval_runtime": 2.5517,
+      "eval_samples_per_second": 56.433,
+      "eval_steps_per_second": 14.108,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -113,7 +199,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6761209816478208.0,
+  "total_flos": 1.3413018767963136e+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:ff0b233bc0fa1c0b505edf088c3b3cf7dc519f375840228353d9368d4e3f697c
-size 9349
+oid sha256:4d9f66376a79084a22812581ddac3f00d23fc4c6c331bb0a0745865773d1563f
+size 10675