Upload 8 files

README.md

@@ -1,22 +1,60 @@
 ---
-license: apache-2.0
-language:
-- vi
+base_model: FPTAI/vibert-base-cased
+tags:
+- generated_from_trainer
 metrics:
 - accuracy
-library_name: transformers
-pipeline_tag: text-classification
-tags:
-- finance
+model-index:
+- name: vi-fin-news
+  results: []
 ---
-Model for financial news
 
----
-language:
-- vi
-metrics:
-- accuracy
-pipeline_tag: text-classification
-tags:
-- finance
----
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# vi-fin-news
+
+This model is a fine-tuned version of [FPTAI/vibert-base-cased](https://huggingface.co/FPTAI/vibert-base-cased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4509
+- Accuracy: 0.9136
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.1176        | 1.0   | 1150 | 0.3566          | 0.9181   |
+| 0.0582        | 2.0   | 2300 | 0.4509          | 0.9136   |
+
+
+### Framework versions
+
+- Transformers 4.32.1
+- Pytorch 2.1.2
+- Datasets 2.12.0
+- Tokenizers 0.13.3

config.json

@@ -11,12 +11,14 @@
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "LABEL_0"
+    "0": "irrelevant",
+    "1": "relevant"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "LABEL_0": 0
+    "irrelevant": 0,
+    "relevant": 1
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
@@ -31,7 +33,7 @@
   "pooler_size_per_head": 128,
   "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
-  "problem_type": "regression",
+  "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.32.1",
   "type_vocab_size": 2,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fa16f1a4b9148c93ac67a3c9fd9e85828b4e31083c18d6463e3d6e193ce8f49
-size 461489390
+oid sha256:8ec9d1faf60f6576fcdb1491a99e05bf0939bc07b69cc6ac4805c6c4bfc7f15e
+size 461492462

tokenizer.json

@@ -54,7 +54,7 @@
     "clean_text": true,
     "handle_chinese_chars": true,
     "strip_accents": null,
-    "lowercase": false
+    "lowercase": true
   },
   "pre_tokenizer": {
     "type": "BertPreTokenizer"

tokenizer_config.json

@@ -2,7 +2,7 @@
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
-  "do_lower_case": false,
+  "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
   "never_split": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78a062a52576017395f1fa007b88b6a50afbb37ae4f122636f2a56ab111b559e
-size 3640
+oid sha256:4c73d7d65b16a3bdd605616b54598a62789f030b081da49b7be85ceb3906f010
+size 4536