Training in progress, epoch 1

adapter_config.json

@@ -1,19 +1,27 @@
 {
+  "alpha_pattern": {},
   "auto_mapping": null,
   "base_model_name_or_path": "distilbert-base-uncased",
+  "bias": "all",
   "fan_in_fan_out": false,
-  "feedforward_modules": [
-    "out_lin"
-  ],
   "inference_mode": true,
-  "init_ia3_weights": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
   "modules_to_save": null,
-  "peft_type": "IA3",
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "v_lin",
-    "out_lin",
     "q_lin"
   ],
-  "task_type": "TOKEN_CLS"
+  "task_type": "TOKEN_CLS",
+  "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:466df54b11ca25ae3078785da15ac1d6803410ce563c91a567dd1f679c68c8d8
-size 97916
+oid sha256:ce5d908338a60e44b334c1b371518df3656caa5e8c53746ce729d20dda1c3dae
+size 1436204

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea93d087351a7eb5db0a397a7530f8c091191fea6c6e33f04b2bbe82d0ba4f92
+oid sha256:0414562269dc94e3799256a6f6cc5d4f63a3c35221a42db870c751b8c1633f5f
 size 265503852

runs/Jan17_16-02-18_pjt20230003-aer2024010004-dp-5d9c8bc8b6-8b5n8/events.out.tfevents.1705474939.pjt20230003-aer2024010004-dp-5d9c8bc8b6-8b5n8.12086.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e32af352dd9676132187ee78f787ab87cb8a4fd04f903117bc20ee67afbc406f
+size 5385

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:344b72fb5e9829fed7ee71ede127d812b030bd1d8e6790269845dd68adb9c075
+oid sha256:25b06e0bbb36e59b8e2ed7534cba4fafc746124ed480e6d9594925bdbe320aa9
 size 4347