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 +1,78 @@
+---
+license: mit
+base_model: xlm-roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: FULL-12epoch-XLMRoBERTa-finetuned-CEFR_ner-60000news
+ 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. -->
+
+# FULL-12epoch-XLMRoBERTa-finetuned-CEFR_ner-60000news
+
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0687
+- Accuracy: 0.3222
+- Precision: 0.6358
+- Recall: 0.8475
+- F1: 0.6074
+
+## 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: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 12
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.087 | 1.0 | 1563 | 0.0917 | 0.3188 | 0.7203 | 0.8273 | 0.6562 |
+| 0.08 | 2.0 | 3126 | 0.0747 | 0.3204 | 0.7147 | 0.8331 | 0.6569 |
+| 0.0666 | 3.0 | 4689 | 0.0691 | 0.3211 | 0.7195 | 0.8376 | 0.6624 |
+| 0.0583 | 4.0 | 6252 | 0.0667 | 0.3213 | 0.6889 | 0.8419 | 0.6433 |
+| 0.0514 | 5.0 | 7815 | 0.0650 | 0.3216 | 0.7043 | 0.8433 | 0.6543 |
+| 0.0463 | 6.0 | 9378 | 0.0642 | 0.3219 | 0.6780 | 0.8444 | 0.6362 |
+| 0.0421 | 7.0 | 10941 | 0.0635 | 0.3220 | 0.6759 | 0.8458 | 0.6354 |
+| 0.0385 | 8.0 | 12504 | 0.0644 | 0.3220 | 0.6330 | 0.8470 | 0.6066 |
+| 0.0358 | 9.0 | 14067 | 0.0670 | 0.3221 | 0.6368 | 0.8467 | 0.6068 |
+| 0.0331 | 10.0 | 15630 | 0.0676 | 0.3222 | 0.6442 | 0.8468 | 0.6130 |
+| 0.0309 | 11.0 | 17193 | 0.0680 | 0.3222 | 0.6377 | 0.8472 | 0.6092 |
+| 0.0298 | 12.0 | 18756 | 0.0687 | 0.3222 | 0.6358 | 0.8475 | 0.6074 |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.2.1
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,46 @@
+{
+ "_name_or_path": "xlm-roberta-base",
+ "architectures": [
+ "XLMRobertaForTokenClassification"
+ ],
+ "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": "0",
+ "1": "A1",
+ "2": "A2",
+ "3": "B1",
+ "4": "B2",
+ "5": "C1",
+ "6": "C2"
+ },
+ "initializer_range": 0.02,
+ "intermediate_size": 3072,
+ "label2id": {
+ "0": 0,
+ "A1": 1,
+ "A2": 2,
+ "B1": 3,
+ "B2": 4,
+ "C1": 5,
+ "C2": 6
+ },
+ "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",
+ "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 sha256:09a3aac86fc61ab296d2757e627ca444478c5a93721302505e1ae51320a20b21
+size 1109857804

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 sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

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 sha256:0a9afdc8cc0f5d3193a38b747da3191e78c20d0a2204fa8d112a2b9bf1bea31a
+size 5176