checkpoint-350

edit-qwen3.5-2b/{checkpoint-300 → checkpoint-350}/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb8b1146b9f6f2ab245c4a7915693bcdc7bc275ede46e0dcf0c25ffd99a8f47e
+oid sha256:615027d4316ae38d0bd9a05f6f73a58a48f0a41299020c158d699dd2506e0333
 size 134604152

edit-qwen3.5-2b/{checkpoint-300 → checkpoint-350}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0bf3ae236b3fb3f1a313d130212811110b1aed4eeec3e4954922b0f1f59f836
+oid sha256:e6a507dfe8a03d18a13d4e3ea82211fa095887561c48bfb931cbb41ae7118ee4
 size 269426431

edit-qwen3.5-2b/{checkpoint-300 → checkpoint-350}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4db15b331dc121cabbbdc8caf7b9d6dce32e716cfc423688abeb7d5224297e6f
+oid sha256:fb0cc07bf8584542fc3e445215bf5f344f42ca1fd0358903763df928113fd0ad
 size 14645

edit-qwen3.5-2b/{checkpoint-300 → checkpoint-350}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edcf8aad81b9757527dfc94cf931298c7f5301b1b302bc98028445b6f5d61e52
+oid sha256:06d22c6a60fc2beed1e26cbe201ba98f53ea7e3c9a4142c6b073b11a4a68afe7
 size 1465

edit-qwen3.5-2b/{checkpoint-300 → checkpoint-350}/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": 1.7262247838616713,
+  "epoch": 2.011527377521614,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -266,6 +266,49 @@
       "eval_samples_per_second": 56.498,
       "eval_steps_per_second": 14.124,
       "step": 300
+    },
+    {
+      "epoch": 1.7838616714697406,
+      "grad_norm": 4.792970657348633,
+      "learning_rate": 4.303030303030303e-05,
+      "loss": 0.7996978282928466,
+      "step": 310
+    },
+    {
+      "epoch": 1.84149855907781,
+      "grad_norm": 3.7477433681488037,
+      "learning_rate": 4.101010101010101e-05,
+      "loss": 1.0061834335327149,
+      "step": 320
+    },
+    {
+      "epoch": 1.899135446685879,
+      "grad_norm": 5.449916839599609,
+      "learning_rate": 3.898989898989899e-05,
+      "loss": 0.702385139465332,
+      "step": 330
+    },
+    {
+      "epoch": 1.956772334293948,
+      "grad_norm": 4.3524322509765625,
+      "learning_rate": 3.6969696969696974e-05,
+      "loss": 0.7624853610992431,
+      "step": 340
+    },
+    {
+      "epoch": 2.011527377521614,
+      "grad_norm": 3.221466064453125,
+      "learning_rate": 3.494949494949495e-05,
+      "loss": 0.624992036819458,
+      "step": 350
+    },
+    {
+      "epoch": 2.011527377521614,
+      "eval_loss": 0.9362655282020569,
+      "eval_runtime": 2.554,
+      "eval_samples_per_second": 56.383,
+      "eval_steps_per_second": 14.096,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -285,7 +328,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9895526504301056e+16,
+  "total_flos": 2.3177856345391104e+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:a120065397e08a6d467934d96155e37488f19b2b1f224a89b2c286d2d3200f00
-size 13327
+oid sha256:f9d7ad78e505fdfa48ca2010e6c24e3fa64a2b5f3c46e84ca6ef4021bab3e48b
+size 14653