End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,102 @@
+---
+license: mit
+base_model: FacebookAI/xlm-roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: XMLRoberta_Dataset59KBoDuoi
+  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. -->
+
+# XMLRoberta_Dataset59KBoDuoi
+
+This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4792
+- Accuracy: 0.8964
+- F1: 0.8969
+
+## 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
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 128
+- 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     |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|
+| No log        | 0.5115  | 200  | 0.4025          | 0.8084   | 0.8111 |
+| No log        | 1.0230  | 400  | 0.3500          | 0.8424   | 0.8451 |
+| No log        | 1.5345  | 600  | 0.3312          | 0.8637   | 0.8612 |
+| 0.4018        | 2.0460  | 800  | 0.3394          | 0.8580   | 0.8610 |
+| 0.4018        | 2.5575  | 1000 | 0.2938          | 0.8747   | 0.8760 |
+| 0.4018        | 3.0691  | 1200 | 0.2903          | 0.8829   | 0.8841 |
+| 0.4018        | 3.5806  | 1400 | 0.2871          | 0.8854   | 0.8859 |
+| 0.2576        | 4.0921  | 1600 | 0.2955          | 0.8864   | 0.8873 |
+| 0.2576        | 4.6036  | 1800 | 0.2831          | 0.8887   | 0.8894 |
+| 0.2576        | 5.1151  | 2000 | 0.2952          | 0.8885   | 0.8898 |
+| 0.2576        | 5.6266  | 2200 | 0.2947          | 0.8872   | 0.8881 |
+| 0.2036        | 6.1381  | 2400 | 0.3086          | 0.8887   | 0.8902 |
+| 0.2036        | 6.6496  | 2600 | 0.2939          | 0.8924   | 0.8931 |
+| 0.2036        | 7.1611  | 2800 | 0.3368          | 0.8879   | 0.8895 |
+| 0.2036        | 7.6726  | 3000 | 0.3162          | 0.8924   | 0.8932 |
+| 0.1616        | 8.1841  | 3200 | 0.3423          | 0.8909   | 0.8919 |
+| 0.1616        | 8.6957  | 3400 | 0.3475          | 0.8940   | 0.8945 |
+| 0.1616        | 9.2072  | 3600 | 0.3546          | 0.8914   | 0.8923 |
+| 0.1616        | 9.7187  | 3800 | 0.3505          | 0.8941   | 0.8947 |
+| 0.1291        | 10.2302 | 4000 | 0.3850          | 0.8934   | 0.8941 |
+| 0.1291        | 10.7417 | 4200 | 0.3718          | 0.8957   | 0.8963 |
+| 0.1291        | 11.2532 | 4400 | 0.3893          | 0.8916   | 0.8924 |
+| 0.1291        | 11.7647 | 4600 | 0.3923          | 0.8949   | 0.8955 |
+| 0.1047        | 12.2762 | 4800 | 0.4213          | 0.8959   | 0.8968 |
+| 0.1047        | 12.7877 | 5000 | 0.3877          | 0.8951   | 0.8961 |
+| 0.1047        | 13.2992 | 5200 | 0.3972          | 0.8990   | 0.8992 |
+| 0.1047        | 13.8107 | 5400 | 0.3896          | 0.8928   | 0.8937 |
+| 0.0865        | 14.3223 | 5600 | 0.4290          | 0.8961   | 0.8964 |
+| 0.0865        | 14.8338 | 5800 | 0.4360          | 0.8977   | 0.8979 |
+| 0.0865        | 15.3453 | 6000 | 0.4398          | 0.8958   | 0.8963 |
+| 0.0865        | 15.8568 | 6200 | 0.4357          | 0.8951   | 0.8955 |
+| 0.0726        | 16.3683 | 6400 | 0.4662          | 0.8952   | 0.8953 |
+| 0.0726        | 16.8798 | 6600 | 0.4608          | 0.8945   | 0.8955 |
+| 0.0726        | 17.3913 | 6800 | 0.4714          | 0.8952   | 0.8954 |
+| 0.0726        | 17.9028 | 7000 | 0.4638          | 0.8967   | 0.8971 |
+| 0.0612        | 18.4143 | 7200 | 0.4783          | 0.8969   | 0.8971 |
+| 0.0612        | 18.9258 | 7400 | 0.4856          | 0.8962   | 0.8967 |
+| 0.0612        | 19.4373 | 7600 | 0.4779          | 0.8958   | 0.8963 |
+| 0.0612        | 19.9488 | 7800 | 0.4792          | 0.8964   | 0.8969 |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.1.2
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "FacebookAI/xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "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": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:257f9895de92a8002f9c24b141fdd27ae59e2da2b84973ed2c9551268d038c0b
+size 1112205008

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1742a608da1249ee2a11741fd2fdb9bc0c4ec18330f7ec4e863ba7cc6e4185ac
+size 17082986

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
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "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": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ed465a09c095c743a37b4f465f0cc99f5560849cb6ea6b32b0ca1b7f17801cd
+size 5048