Training in progress, epoch 1

README.md

@@ -0,0 +1,67 @@
+---
+license: mit
+base_model: xlm-roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+model-index:
+- name: xlm-roberta-base-finetuned-detests-wandb24
+  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. -->
+
+# xlm-roberta-base-finetuned-detests-wandb24
+
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4371
+- Accuracy: 0.7938
+- F1-score: 0.7241
+- Precision: 0.7136
+- Recall: 0.7396
+- Auc: 0.7396
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1-score | Precision | Recall | Auc    |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------:|:------:|:------:|
+| 0.458         | 1.0   | 153  | 0.4512          | 0.7725   | 0.4358   | 0.3863    | 0.5    | 0.5    |
+| 0.4262        | 2.0   | 306  | 0.4371          | 0.7938   | 0.7241   | 0.7136    | 0.7396 | 0.7396 |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.1

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "@usuario": 31002,
+  "emoji": 31005,
+  "hashtag": 31004,
+  "url": 31003
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "finiteautomata/beto-sentiment-analysis",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "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": "4.37.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31006
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:560de303b35b30b7d2b03c5cfa4e6492dba58ffe136838d84325966e23a4e340
+size 439445496

runs/Feb12_09-39-40_93f51a08e000/events.out.tfevents.1707730980.93f51a08e000.1197.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29e970fcaa23ba6488b071bda1f199569abf6140cb145bbc03cb1d64fa21d0bc
+size 7049

runs/Feb12_09-48-09_93f51a08e000/events.out.tfevents.1707731299.93f51a08e000.1197.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccb3aa453258cabb6f8fc87ccff9813ae003ee2066763ac5fdb8595d0ba11f74
+size 7099

runs/Feb12_09-52-39_93f51a08e000/events.out.tfevents.1707731565.93f51a08e000.1197.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13b21529e804a993e9128799476e28f9f5b9d862cd1da89cde3d95a066f3e9f0
+size 7026

runs/Feb12_09-57-03_93f51a08e000/events.out.tfevents.1707731829.93f51a08e000.1197.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e94493558f1ef8006fd3dcd25367220f38ba6b4b82e4dca7200d736eb9f01f3
+size 7099

runs/Feb12_10-02-09_93f51a08e000/events.out.tfevents.1707732135.93f51a08e000.1197.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1797a15649ac7456a4cc9448d9d174e1e0cf5900ffdd63f1bd819c33a964e53
+size 7049

runs/Feb12_10-06-36_93f51a08e000/events.out.tfevents.1707732411.93f51a08e000.1197.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cac9fc0cea880fe529e712c64cb99c5c05eb90c4011eebf2e4536e6c1d797c5
+size 7055

runs/Feb12_10-15-15_93f51a08e000/events.out.tfevents.1707732920.93f51a08e000.1197.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbfa6a168f0fd8b786bc799a646063315b96e8528c40fc8d1ca3aae720c82860
+size 6375

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 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,93 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[MASK]",
+      "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
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "31002": {
+      "content": "@usuario",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31003": {
+      "content": "url",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31004": {
+      "content": "hashtag",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31005": {
+      "content": "emoji",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef7e15e5fc18349d3871ab6e2436ca32b9e187d7656ed9621c41bb156385ec5c
+size 4728