checkpoint-300

edit-qwen3.5-2b/{checkpoint-250 → checkpoint-300}/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f335ac58ef7285c169a541a936deaa09de5a4bc337fc5a658163e8e56fecf5a
+oid sha256:cb8b1146b9f6f2ab245c4a7915693bcdc7bc275ede46e0dcf0c25ffd99a8f47e
 size 134604152

edit-qwen3.5-2b/{checkpoint-250 → checkpoint-300}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe247bb153f5e48a6347f7acd41b9583dc3dfb20f84f4de68a89222466c464bf
+oid sha256:d0bf3ae236b3fb3f1a313d130212811110b1aed4eeec3e4954922b0f1f59f836
 size 269426431

edit-qwen3.5-2b/{checkpoint-250 → checkpoint-300}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a9bb72a4281afdaa85d24b988cedaad2e7575e9088aa3ae95e536cd421d4b51
+oid sha256:4db15b331dc121cabbbdc8caf7b9d6dce32e716cfc423688abeb7d5224297e6f
 size 14645

edit-qwen3.5-2b/{checkpoint-250 → checkpoint-300}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97887b03ed5ddb9fb30ec5a630828d150a649222e1efaf740f45334b4842e9f4
+oid sha256:edcf8aad81b9757527dfc94cf931298c7f5301b1b302bc98028445b6f5d61e52
 size 1465

edit-qwen3.5-2b/{checkpoint-250 → checkpoint-300}/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": 1.4380403458213258,
+  "epoch": 1.7262247838616713,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -223,6 +223,49 @@
       "eval_samples_per_second": 56.413,
       "eval_steps_per_second": 14.103,
       "step": 250
+    },
+    {
+      "epoch": 1.4956772334293948,
+      "grad_norm": 2.263134002685547,
+      "learning_rate": 5.313131313131313e-05,
+      "loss": 0.49338202476501464,
+      "step": 260
+    },
+    {
+      "epoch": 1.553314121037464,
+      "grad_norm": 3.2704994678497314,
+      "learning_rate": 5.111111111111111e-05,
+      "loss": 1.0119559288024902,
+      "step": 270
+    },
+    {
+      "epoch": 1.6109510086455332,
+      "grad_norm": 4.177541732788086,
+      "learning_rate": 4.909090909090909e-05,
+      "loss": 0.8234881401062012,
+      "step": 280
+    },
+    {
+      "epoch": 1.6685878962536023,
+      "grad_norm": 4.183651924133301,
+      "learning_rate": 4.7070707070707074e-05,
+      "loss": 0.6315438747406006,
+      "step": 290
+    },
+    {
+      "epoch": 1.7262247838616713,
+      "grad_norm": 3.0654070377349854,
+      "learning_rate": 4.5050505050505056e-05,
+      "loss": 0.6100435256958008,
+      "step": 300
+    },
+    {
+      "epoch": 1.7262247838616713,
+      "eval_loss": 0.9526227116584778,
+      "eval_runtime": 2.5488,
+      "eval_samples_per_second": 56.498,
+      "eval_steps_per_second": 14.124,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -242,7 +285,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6731342844263936e+16,
+  "total_flos": 1.9895526504301056e+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:b5312debb0485f92b7b7650e1f23a4dff3d3a6eac45b6c9317518cb14d07641a
-size 12001
+oid sha256:a120065397e08a6d467934d96155e37488f19b2b1f224a89b2c286d2d3200f00
+size 13327