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: 0.8892
+- Loss: 0.4907
 
 ## Model description
 
@@ -45,8 +46,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 7    | 0.9168          |
-| No log        | 2.0   | 14   | 0.8892          |
+| No log        | 1.0   | 7    | 0.4933          |
+| No log        | 2.0   | 14   | 0.4907          |
 
 
 ### 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
 }

evaluation_report.json

@@ -0,0 +1,27 @@
+{
+    "0": {
+        "precision": 0.7205882352941176,
+        "recall": 0.8032786885245902,
+        "f1-score": 0.7596899224806202,
+        "support": 61.0
+    },
+    "1": {
+        "precision": 0.625,
+        "recall": 0.5128205128205128,
+        "f1-score": 0.5633802816901409,
+        "support": 39.0
+    },
+    "accuracy": 0.69,
+    "macro avg": {
+        "precision": 0.6727941176470589,
+        "recall": 0.6580496006725515,
+        "f1-score": 0.6615351020853806,
+        "support": 100.0
+    },
+    "weighted avg": {
+        "precision": 0.6833088235294117,
+        "recall": 0.69,
+        "f1-score": 0.6831291625723332,
+        "support": 100.0
+    }
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce410972ea7b8b4331d14ae05f474f38ae47dda3452c467b3707e4bd4b49e30f
-size 439039996
+oid sha256:ec3d9d8da48972921b1f7421cec164719ca1b8e9372149c40daf8f5da257d8b6
+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 sha256:9e16bdafd3627cef8d379918048882bd0dca5ece55f00090dc9ac9f56b518d54
+oid sha256:455187f5fd122b9776f18c65dc3e1c1a293babd5d5418037f9c25194c5b75bbc
 size 4984