adediu25/implicit-debertav3-all

README.md

@@ -1,11 +1,11 @@
 ---
-license: apache-2.0
+license: mit
 library_name: peft
 tags:
 - generated_from_trainer
 metrics:
 - accuracy
-base_model: distilbert-base-uncased
+base_model: microsoft/deberta-v3-base
 model-index:
 - name: trainer
   results: []
@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # trainer
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6720
-- Accuracy: {'accuracy': 0.7188000915960614}
+- Loss: 0.5146
+- Accuracy: {'accuracy': 0.8154339363407374}
 
 ## Model description
 
@@ -50,10 +50,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Accuracy                         |
 |:-------------:|:-----:|:-----:|:---------------:|:--------------------------------:|
-| 0.5412        | 1.0   | 2772  | 0.7622          | {'accuracy': 0.6675062972292192} |
-| 0.487         | 2.0   | 5544  | 0.7221          | {'accuracy': 0.6936111747194871} |
-| 0.4486        | 3.0   | 8316  | 0.6913          | {'accuracy': 0.7105564460728189} |
-| 0.4463        | 4.0   | 11088 | 0.6720          | {'accuracy': 0.7188000915960614} |
+| 0.3938        | 1.0   | 2772  | 0.5646          | {'accuracy': 0.7842912754751545} |
+| 0.3103        | 2.0   | 5544  | 0.5375          | {'accuracy': 0.7945958323792077} |
+| 0.2796        | 3.0   | 8316  | 0.5112          | {'accuracy': 0.8124570643462331} |
+| 0.2611        | 4.0   | 11088 | 0.5146          | {'accuracy': 0.8154339363407374} |
 
 
 ### Framework versions

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": null,
+  "base_model_name_or_path": "microsoft/deberta-v3-base",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,7 +20,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_lin"
+    "key_proj",
+    "query_proj",
+    "value_proj",
+    "classifier",
+    "dense"
   ],
   "task_type": "SEQ_CLS",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d424fe6766c67c4dd10cd3fd38e39a5785b36a33f08513614fef4bbec25875b
-size 2669460
+oid sha256:34b3e7a18d001089251e2e2cef126b2aaafb6b73b7f16fd7d399459f32c444ad
+size 5462676

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

runs/Apr16_23-54-21_0dafd0179a67/events.out.tfevents.1713311667.0dafd0179a67.1311.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefbb2337116ebe509971039b67861f9712d98069772d5241342009df381ef8a
+size 10916

special_tokens_map.json

@@ -1,7 +1,15 @@
 {
+  "bos_token": "[CLS]",
   "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
   "mask_token": "[MASK]",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -8,31 +8,31 @@
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
-      "content": "[CLS]",
+    "2": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[SEP]",
+    "3": {
+      "content": "[UNK]",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
+    "128000": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
@@ -41,15 +41,18 @@
       "special": true
     }
   },
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
-  "unk_token": "[UNK]"
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65ce3a7a97684427bc85f4d0111668fb23ab0e9c616537d6875f075dabe150c7
+oid sha256:9137612d3c6735586176c8ca4b89907557fddf395a5286a996f11876025bb30b
 size 4856