sapadev13/SAPA_model_case_v1

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
-license: apache-2.0
-base_model: distilbert-base-uncased
+license: mit
+base_model: microsoft/deberta-v3-small
 tags:
 - generated_from_trainer
 metrics:
@@ -19,13 +19,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-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-small](https://huggingface.co/microsoft/deberta-v3-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1950
-- Accuracy: 0.9279
-- Precision: 0.9366
-- Recall: 0.918
-- F1: 0.9272
+- Loss: 0.1435
+- Accuracy: 0.9485
+- Precision: 0.9559
+- Recall: 0.9405
+- F1: 0.9481
 
 ## Model description
 
@@ -58,10 +58,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| 0.3973        | 1.0   | 782  | 0.2365          | 0.9059   | 0.9528    | 0.8541 | 0.9007 |
-| 0.1701        | 2.0   | 1564 | 0.1950          | 0.9279   | 0.9366    | 0.918  | 0.9272 |
-| 0.1073        | 3.0   | 2346 | 0.2522          | 0.9319   | 0.9358    | 0.9274 | 0.9316 |
-| 0.0574        | 4.0   | 3128 | 0.2988          | 0.9301   | 0.9278    | 0.9328 | 0.9303 |
+| 0.344         | 1.0   | 782  | 0.1528          | 0.9438   | 0.9444    | 0.9430 | 0.9437 |
+| 0.1362        | 2.0   | 1564 | 0.1435          | 0.9485   | 0.9559    | 0.9405 | 0.9481 |
+| 0.1           | 3.0   | 2346 | 0.1799          | 0.9503   | 0.9533    | 0.9470 | 0.9501 |
+| 0.0574        | 4.0   | 3128 | 0.2148          | 0.9516   | 0.9511    | 0.9521 | 0.9516 |
 
 
 ### Framework versions

config.json

@@ -1,24 +1,35 @@
 {
-  "activation": "gelu",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "DebertaV2ForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
   "pad_token_id": 0,
-  "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
   "torch_dtype": "float32",
   "transformers_version": "4.50.3",
-  "vocab_size": 30522
+  "type_vocab_size": 0,
+  "vocab_size": 128100
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7e0136aea2542c637d994bd82c73bb7486cfb11a3033dcb06c2df4d77e205e5
-size 267832560
+oid sha256:956446865b7811afc97cace808a8c2a819f45ea2d6c9fca3644bce7602d40baa
+size 567598552

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
+  }
 }

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,
@@ -41,16 +41,19 @@
       "special": true
     }
   },
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
   "extra_special_tokens": {},
   "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"
 }