End of training

README.md

@@ -0,0 +1,73 @@
+---
+base_model: vinai/phobert-base-v2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: metadata-cls-no-gov-8k-v3
+ results: []
+---
+
+<!-- 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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/nguyenducbao/huggingface/runs/gi7dm5g5)
+# metadata-cls-no-gov-8k-v3
+
+This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3064
+- Accuracy: 0.9515
+- F1: 0.8155
+
+## 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: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|
+| 0.5565 | 1.6393 | 200 | 0.1942 | 0.9472 | 0.7911 |
+| 0.1619 | 3.2787 | 400 | 0.1935 | 0.9404 | 0.7817 |
+| 0.1275 | 4.9180 | 600 | 0.1903 | 0.9430 | 0.8019 |
+| 0.0768 | 6.5574 | 800 | 0.2192 | 0.9489 | 0.8016 |
+| 0.0579 | 8.1967 | 1000 | 0.2350 | 0.9455 | 0.7866 |
+| 0.0477 | 9.8361 | 1200 | 0.2572 | 0.9498 | 0.7952 |
+| 0.0358 | 11.4754 | 1400 | 0.2823 | 0.9413 | 0.7938 |
+| 0.0277 | 13.1148 | 1600 | 0.2704 | 0.9464 | 0.8096 |
+| 0.0233 | 14.7541 | 1800 | 0.2868 | 0.9481 | 0.7951 |
+| 0.0139 | 16.3934 | 2000 | 0.3026 | 0.9438 | 0.7965 |
+| 0.0125 | 18.0328 | 2200 | 0.3034 | 0.9489 | 0.8035 |
+| 0.0085 | 19.6721 | 2400 | 0.3064 | 0.9515 | 0.8155 |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.1.2
+- Datasets 2.20.0
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+ "<mask>": 64000
+}

config.json

@@ -0,0 +1,43 @@
+{
+ "_name_or_path": "vinai/phobert-base-v2",
+ "architectures": [
+ "RobertaForSequenceClassification"
+ ],
+ "attention_probs_dropout_prob": 0.1,
+ "bos_token_id": 0,
+ "classifier_dropout": null,
+ "eos_token_id": 2,
+ "hidden_act": "gelu",
+ "hidden_dropout_prob": 0.1,
+ "hidden_size": 768,
+ "id2label": {
+ "0": "LABEL_0",
+ "1": "LABEL_1",
+ "2": "LABEL_2",
+ "3": "LABEL_3",
+ "4": "LABEL_4"
+ },
+ "initializer_range": 0.02,
+ "intermediate_size": 3072,
+ "label2id": {
+ "LABEL_0": 0,
+ "LABEL_1": 1,
+ "LABEL_2": 2,
+ "LABEL_3": 3,
+ "LABEL_4": 4
+ },
+ "layer_norm_eps": 1e-05,
+ "max_position_embeddings": 258,
+ "model_type": "roberta",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 12,
+ "pad_token_id": 1,
+ "position_embedding_type": "absolute",
+ "problem_type": "single_label_classification",
+ "tokenizer_class": "PhobertTokenizer",
+ "torch_dtype": "float32",
+ "transformers_version": "4.42.4",
+ "type_vocab_size": 1,
+ "use_cache": true,
+ "vocab_size": 64001
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9c7e769f1d2885854836ae7890e309e1ff06d9a3e28f4eb4e322dd3f6b2c2ba
+size 540032612

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+ "bos_token": "<s>",
+ "cls_token": "<s>",
+ "eos_token": "</s>",
+ "mask_token": "<mask>",
+ "pad_token": "<pad>",
+ "sep_token": "</s>",
+ "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+ "added_tokens_decoder": {
+ "0": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "<pad>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "3": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "64000": {
+ "content": "<mask>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "<s>",
+ "clean_up_tokenization_spaces": true,
+ "cls_token": "<s>",
+ "eos_token": "</s>",
+ "mask_token": "<mask>",
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "<pad>",
+ "sep_token": "</s>",
+ "tokenizer_class": "PhobertTokenizer",
+ "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d812ecc61a6e51b1a8c3ec01d51cb6380f8ed559ffcedf7f2e9cbb39042faec1
+size 5112