End of training

README.md

@@ -0,0 +1,70 @@
+---
+base_model: vinai/phobert-base-v2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: phobert_55k_bo_vn
+ 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. -->
+
+# phobert_55k_bo_vn
+
+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: 0.2688
+- Accuracy: 0.9534
+- F1: 0.9536
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine_with_restarts
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
+| 0.211 | 1.0 | 1719 | 0.1383 | 0.9485 | 0.9487 |
+| 0.1376 | 2.0 | 3438 | 0.1373 | 0.9521 | 0.9523 |
+| 0.1105 | 3.0 | 5157 | 0.1431 | 0.9522 | 0.9527 |
+| 0.0889 | 4.0 | 6876 | 0.1649 | 0.9534 | 0.9537 |
+| 0.0715 | 5.0 | 8595 | 0.1770 | 0.9549 | 0.9548 |
+| 0.0561 | 6.0 | 10314 | 0.1937 | 0.9533 | 0.9536 |
+| 0.0443 | 7.0 | 12033 | 0.2260 | 0.9530 | 0.9533 |
+| 0.0367 | 8.0 | 13752 | 0.2664 | 0.9529 | 0.9531 |
+| 0.0327 | 9.0 | 15471 | 0.2663 | 0.9532 | 0.9534 |
+| 0.0298 | 10.0 | 17190 | 0.2688 | 0.9534 | 0.9536 |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.1.2
+- Datasets 2.19.1
+- Tokenizers 0.19.1

added_tokens.json

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

config.json

@@ -0,0 +1,29 @@
+{
+ "_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,
+ "initializer_range": 0.02,
+ "intermediate_size": 3072,
+ "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": "4.41.2",
+ "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 sha256:668bef5ca8315d2f358e2db371b8d306b47ae83d64bbc172365034414a1ef093
+size 540023384

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 sha256:283f28d7e697afbabdf7e12b052e5180cd7da208d3972b7d963d19de51ec0ab6
+size 5112