Model save

README.md

@@ -1,5 +1,6 @@
 ---
-base_model: yiyanghkust/finbert-fls
+license: apache-2.0
+base_model: distilbert/distilbert-base-uncased
 tags:
 - generated_from_trainer
 model-index:
@@ -12,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # my_fancy_model
 
-This model is a fine-tuned version of [yiyanghkust/finbert-fls](https://huggingface.co/yiyanghkust/finbert-fls) on an unknown dataset.
+This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4101
+- Loss: 0.4597
 
 ## Model description
 
@@ -45,8 +46,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 32   | 0.4455          |
-| No log        | 2.0   | 64   | 0.4101          |
+| No log        | 1.0   | 32   | 0.4597          |
+| No log        | 2.0   | 64   | 0.4772          |
 
 
 ### Framework versions

config.json

@@ -1,37 +1,25 @@
 {
-  "_name_or_path": "yiyanghkust/finbert-fls",
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "BertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "id2label": {
-    "0": "Not FLS",
-    "1": "Non-specific FLS",
-    "2": "Specific FLS"
-  },
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "label2id": {
-    "Non-specific FLS": 1,
-    "Not FLS": 0,
-    "Specific FLS": 2
-  },
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.38.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30873
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:092069ae18671d95f4237c52d4cba3661a0a76da22ed868f0c75e54c2a5b6387
-size 439039996
+oid sha256:f0ddfa6f42b7fd1fd1cd7711f38020f3a5d1b4a11e9c4d92a89dec034c60f776
+size 267832560

tokenizer_config.json

@@ -8,7 +8,7 @@
       "single_word": false,
       "special": true
     },
-    "2": {
+    "100": {
       "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": true
     },
-    "3": {
+    "101": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "4": {
+    "102": {
       "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
@@ -32,7 +32,7 @@
       "single_word": false,
       "special": true
     },
-    "5": {
+    "103": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
@@ -43,15 +43,13 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49106e3271a81a0e8ba6fd355381d6f90b04ae16401fb3a9622152e880bef41d
+oid sha256:99ab5c42657123c290d98ea1fca5c995694310d8e9d869ec054ccf2dbe2487e7
 size 4984