SciRoBERTa-ES-TweetAreas

README.md

@@ -0,0 +1,76 @@
+---
+license: mit
+base_model: xlm-roberta-large
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+model-index:
+- name: results_RoBERTa
+  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. -->
+
+# results_RoBERTa
+
+This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1365
+- Roc Auc: 0.8669
+- Hamming Loss: 0.0454
+- F1 Score: 0.7761
+- Accuracy: 0.4712
+- Precision: 0.7977
+- Recall: 0.7665
+
+## 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: 5e-05
+- 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: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Roc Auc | Hamming Loss | F1 Score | Accuracy | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:------------:|:--------:|:--------:|:---------:|:------:|
+| No log        | 1.0   | 374  | 0.1904          | 0.6981  | 0.0674       | 0.4749   | 0.3440   | 0.7840    | 0.4297 |
+| 0.2476        | 2.0   | 748  | 0.1674          | 0.7439  | 0.0612       | 0.5672   | 0.3802   | 0.8482    | 0.5228 |
+| 0.1597        | 3.0   | 1122 | 0.1512          | 0.7955  | 0.0545       | 0.6516   | 0.4163   | 0.8172    | 0.6218 |
+| 0.1597        | 4.0   | 1496 | 0.1414          | 0.8087  | 0.0511       | 0.6736   | 0.4324   | 0.8251    | 0.6535 |
+| 0.1222        | 5.0   | 1870 | 0.1395          | 0.8344  | 0.0490       | 0.7153   | 0.4378   | 0.8190    | 0.7038 |
+| 0.09          | 6.0   | 2244 | 0.1385          | 0.8485  | 0.0477       | 0.7552   | 0.4645   | 0.8182    | 0.7315 |
+| 0.0663        | 7.0   | 2618 | 0.1391          | 0.8544  | 0.0466       | 0.7617   | 0.4712   | 0.7936    | 0.7401 |
+| 0.0663        | 8.0   | 2992 | 0.1365          | 0.8669  | 0.0454       | 0.7761   | 0.4712   | 0.7977    | 0.7665 |
+| 0.0461        | 9.0   | 3366 | 0.1375          | 0.8617  | 0.0460       | 0.7711   | 0.4699   | 0.7956    | 0.7569 |
+| 0.0293        | 10.0  | 3740 | 0.1388          | 0.8636  | 0.0448       | 0.7736   | 0.4926   | 0.7953    | 0.7592 |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,69 @@
+{
+  "_name_or_path": "xlm-roberta-large",
+  "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": 1024,
+  "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",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "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": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "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 sha256:8be011924d7322e2554e7bc4a5b68d0355f20613392a27af38625e9577cfdc10
+size 2239684272

runs/Jul18_23-28-54_344887fdfbf3/events.out.tfevents.1721345359.344887fdfbf3.2513.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5923360c4e1e2cb5d435ef85ddfba07fe36e9cc12c8947374beecd0d5951e303
+size 13361

runs/Jul18_23-28-54_344887fdfbf3/events.out.tfevents.1721350438.344887fdfbf3.2513.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ff45775a3ff72df892fedb2513f23b9011d62eb6901e6e9da0702269c5a2c66
+size 673

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_config.json

@@ -0,0 +1,55 @@
+{
+  "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>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4ca9799dc32e881c1a4ed1664c0d299df33df6dfa77582c5e345bb86f6f0461
+size 5112