CuATR-distilbert-LoRA

README.md

@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6921
-- Accuracy: 0.6087
-- F1: 0.7429
+- Loss: 0.6857
+- Accuracy: 0.5652
+- F1: 0.7222
 
 ## Model description
 
@@ -54,9 +54,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.6915        | 0.67  | 1    | 0.6924          | 0.5652   | 0.7222 |
-| 0.7001        | 2.0   | 3    | 0.6922          | 0.6087   | 0.7429 |
-| 0.6993        | 2.67  | 4    | 0.6921          | 0.6087   | 0.7429 |
+| 0.6809        | 0.67  | 1    | 0.6860          | 0.5652   | 0.7222 |
+| 0.6938        | 2.0   | 3    | 0.6857          | 0.5652   | 0.7222 |
+| 0.6844        | 2.67  | 4    | 0.6857          | 0.5652   | 0.7222 |
 
 
 ### Framework versions

adapter_config.json

@@ -12,13 +12,13 @@
   "lora_dropout": 0.05,
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_lin",
     "q_lin",
-    "v_lin",
-    "k_lin"
+    "v_lin"
   ],
   "task_type": "TOKEN_CLS"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8d037a6b4dfa12a6ca0bc76220db3586d6cb71dae9e2d5b7fcc888ea2e45c1e
-size 889912
+oid sha256:a10fb40b919c270ce46691352cd62ec5656c4fbb4af0ee161e2aa1286bb5166f
+size 1774720

tokenizer.json

@@ -1,19 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": "BatchLongest",
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:941b8aadd8869ecaa167c9e829d0d115b6664dcefd00b0d94a1c1a5a35f01100
+oid sha256:27caa59b4a51fd997f8759f82e5995b0c2c2b266fb9c9393b5c953d8c650c159
 size 4600