IParraMartin/XLM-EusBERTa-topic-classification

README.md

@@ -0,0 +1,110 @@
+---
+license: cc-by-sa-4.0
+base_model: ClassCat/roberta-small-basque
+tags:
+- generated_from_trainer
+datasets:
+- basque_glue
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: XLM-EusBERTa-topic-classification
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: basque_glue
+      type: basque_glue
+      config: bhtc
+      split: validation
+      args: bhtc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6494345718901454
+    - name: F1
+      type: f1
+      value: 0.6432667195761544
+    - name: Precision
+      type: precision
+      value: 0.6447174737999963
+    - name: Recall
+      type: recall
+      value: 0.6494345718901454
+---
+
+<!-- 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. -->
+
+# XLM-EusBERTa-topic-classification
+
+This model is a fine-tuned version of [ClassCat/roberta-small-basque](https://huggingface.co/ClassCat/roberta-small-basque) on the basque_glue dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.2158
+- Accuracy: 0.6494
+- F1: 0.6433
+- Precision: 0.6447
+- Recall: 0.6494
+
+## 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: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 1.2439        | 1.0   | 1074  | 1.1310          | 0.6581   | 0.6316 | 0.6139    | 0.6581 |
+| 0.9539        | 2.0   | 2148  | 1.3019          | 0.6117   | 0.6034 | 0.6465    | 0.6117 |
+| 0.579         | 3.0   | 3222  | 1.5533          | 0.6645   | 0.6524 | 0.6661    | 0.6645 |
+| 0.3766        | 4.0   | 4296  | 2.3287          | 0.6381   | 0.6283 | 0.6590    | 0.6381 |
+| 0.2641        | 5.0   | 5370  | 2.2805          | 0.6597   | 0.6515 | 0.6707    | 0.6597 |
+| 0.1707        | 6.0   | 6444  | 2.6621          | 0.6397   | 0.6399 | 0.6581    | 0.6397 |
+| 0.1537        | 7.0   | 7518  | 2.9116          | 0.6408   | 0.6336 | 0.6452    | 0.6408 |
+| 0.0867        | 8.0   | 8592  | 3.1775          | 0.6344   | 0.6337 | 0.6531    | 0.6344 |
+| 0.0779        | 9.0   | 9666  | 3.2514          | 0.6543   | 0.6471 | 0.6593    | 0.6543 |
+| 0.0587        | 10.0  | 10740 | 3.3244          | 0.6457   | 0.6424 | 0.6488    | 0.6457 |
+| 0.0322        | 11.0  | 11814 | 3.8090          | 0.6214   | 0.6244 | 0.6488    | 0.6214 |
+| 0.0139        | 12.0  | 12888 | 3.8642          | 0.6247   | 0.6176 | 0.6424    | 0.6247 |
+| 0.0256        | 13.0  | 13962 | 3.8734          | 0.6419   | 0.6327 | 0.6398    | 0.6419 |
+| 0.0046        | 14.0  | 15036 | 4.0934          | 0.6365   | 0.6330 | 0.6463    | 0.6365 |
+| 0.0036        | 15.0  | 16110 | 4.0890          | 0.6484   | 0.6416 | 0.6469    | 0.6484 |
+| 0.0023        | 16.0  | 17184 | 4.0978          | 0.6505   | 0.6440 | 0.6470    | 0.6505 |
+| 0.0008        | 17.0  | 18258 | 4.1709          | 0.6478   | 0.6418 | 0.6449    | 0.6478 |
+| 0.0014        | 18.0  | 19332 | 4.1715          | 0.6505   | 0.6446 | 0.6458    | 0.6505 |
+| 0.0007        | 19.0  | 20406 | 4.2158          | 0.6489   | 0.6427 | 0.6443    | 0.6489 |
+| 0.0039        | 20.0  | 21480 | 4.2158          | 0.6494   | 0.6433 | 0.6447    | 0.6494 |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "ClassCat/roberta-small-basque",
+  "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": 512,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1c90c88cc00fee77ece92d1435225091f6ec43ca36d2d666fd3319e8a132d79
+size 205426744

runs/Dec27_20-11-14_b2521899950f/events.out.tfevents.1703707874.b2521899950f.3997.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e3db4a266524fa4cfd169e52f347adc4ee04430ef20c0cd486e5bab34b1cf18
+size 21276

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "</s>",
+      "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>",
+  "errors": "replace",
+  "keep_accents": true,
+  "mask_token": "<mask>",
+  "max_len": 50,
+  "model_max_length": 50,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8f6a3ad7f1673b3014bb19a19bca01499d2adf5ebc56de02f7ccd35a930f17c
+size 4600