Training in progress, epoch 1

adapter_config.json

@@ -1,19 +1,29 @@
 {
+  "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,
-  "modules_to_save": null,
-  "peft_type": "IA3",
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "decode_head"
+  ],
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "q_lin",
-    "out_lin",
     "v_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:cea5e36c867c40a591a3a8e465a423c5bfd282289531bc9c7012d19f15c529af
-size 97916
+oid sha256:4f9edad28f47dc82fbf47a5fcb3638eeec3fdd3f8d48c4f3b8d4be3ae25389d6
+size 9127116

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d90ae2bc7f4c20a6325dda4073c8da18f5a4b0bef8996e8fb5f1aaebab4c5ac
+oid sha256:e48352b277b1a62d7c98973d50f068a55966ca8b9f3556a1a8fcb5ed3543302b
 size 265503852

runs/Jan17_14-06-47_pjt20230003-aer2024010004-dp-5d9c8bc8b6-8b5n8/events.out.tfevents.1705468008.pjt20230003-aer2024010004-dp-5d9c8bc8b6-8b5n8.10521.16

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e875ededd38880555645e336a1c521b2d9664373914952a50a01fac320496805
+size 5319

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7730d61e56cbee18eb2c2420e4576b02989e6e736eabd518f24c972fe9b1dee2
+oid sha256:3ee3074c5ce4c152a66b27dd6155bb364d5b9928f88b0d2595cb2d1c2788a1d4
 size 4283