SciBERT-ES-TweetAreas

README.md

@@ -0,0 +1,76 @@
+---
+license: apache-2.0
+base_model: google-bert/bert-base-multilingual-cased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+model-index:
+- name: results
+  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
+
+This model is a fine-tuned version of [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1516
+- Roc Auc: 0.8130
+- Hamming Loss: 0.0509
+- F1 Score: 0.6969
+- Accuracy: 0.4418
+- Precision: 0.8279
+- Recall: 0.6583
+
+## 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  | 0.2285          | 0.6386  | 0.0822       | 0.3390   | 0.2731   | 0.8932    | 0.3080 |
+| 0.2678        | 2.0   | 748  | 0.1870          | 0.7175  | 0.0679       | 0.5123   | 0.3481   | 0.7842    | 0.4679 |
+| 0.1722        | 3.0   | 1122 | 0.1727          | 0.7839  | 0.0607       | 0.6116   | 0.3949   | 0.7611    | 0.6096 |
+| 0.1722        | 4.0   | 1496 | 0.1577          | 0.7865  | 0.0545       | 0.6408   | 0.4137   | 0.8178    | 0.6096 |
+| 0.1236        | 5.0   | 1870 | 0.1537          | 0.8055  | 0.0523       | 0.6798   | 0.4230   | 0.8250    | 0.6423 |
+| 0.0847        | 6.0   | 2244 | 0.1570          | 0.8069  | 0.0541       | 0.6695   | 0.4297   | 0.7839    | 0.6503 |
+| 0.063         | 7.0   | 2618 | 0.1516          | 0.8130  | 0.0509       | 0.6969   | 0.4418   | 0.8279    | 0.6583 |
+| 0.063         | 8.0   | 2992 | 0.1531          | 0.8147  | 0.0512       | 0.6856   | 0.4458   | 0.7982    | 0.6622 |
+| 0.0465        | 9.0   | 3366 | 0.1526          | 0.8427  | 0.0489       | 0.7544   | 0.4565   | 0.8190    | 0.7174 |
+| 0.0349        | 10.0  | 3740 | 0.1534          | 0.8349  | 0.0498       | 0.7414   | 0.4431   | 0.8212    | 0.7023 |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,72 @@
+{
+  "_name_or_path": "google-bert/bert-base-multilingual-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "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": 3072,
+  "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-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a15eaac42f47a1b3a75009ca8f6713d16bbe27a5ffacf7d071ef49cb7d38a73
+size 711492680

runs/Jul11_23-37-46_afc9b30540b0/events.out.tfevents.1720741072.afc9b30540b0.4048.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f4644e407c37d0cd5f824758163cae88c25cb581892c51efd03f8175d54467d
+size 13472

runs/Jul11_23-37-46_afc9b30540b0/events.out.tfevents.1720742156.afc9b30540b0.4048.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2c04e137841c64b7960f12c1aedac55d837f91c2e465841c01ceb4fd80d0ed6
+size 673

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4069abb263512571b59cc84c2bd716ec30f5f67c713116335f02dc2af2783ee0
+size 5112