Training in progress, epoch 1

README.md

@@ -0,0 +1,74 @@
+---
+license: mit
+base_model: PORTULAN/albertina-100m-portuguese-ptpt-encoder
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: LVI_albertina-100m-portuguese-ptpt-encoder
+  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. -->
+
+# LVI_albertina-100m-portuguese-ptpt-encoder
+
+This model is a fine-tuned version of [PORTULAN/albertina-100m-portuguese-ptpt-encoder](https://huggingface.co/PORTULAN/albertina-100m-portuguese-ptpt-encoder) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1867
+- Accuracy: 0.9802
+- F1: 0.9800
+- Precision: 0.9905
+- Recall: 0.9696
+
+## 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-06
+- 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: 10
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 0.1284        | 1.0   | 3217  | 0.1454          | 0.9581   | 0.9567 | 0.9882    | 0.9272 |
+| 0.0946        | 2.0   | 6434  | 0.1211          | 0.9737   | 0.9734 | 0.9864    | 0.9607 |
+| 0.0575        | 3.0   | 9651  | 0.1087          | 0.9776   | 0.9774 | 0.9892    | 0.9659 |
+| 0.0374        | 4.0   | 12868 | 0.1033          | 0.981    | 0.9809 | 0.9854    | 0.9765 |
+| 0.0311        | 5.0   | 16085 | 0.1154          | 0.981    | 0.9808 | 0.9896    | 0.9722 |
+| 0.0125        | 6.0   | 19302 | 0.1143          | 0.9830   | 0.9830 | 0.9833    | 0.9826 |
+| 0.0107        | 7.0   | 22519 | 0.1562          | 0.9807   | 0.9805 | 0.9910    | 0.9702 |
+| 0.0032        | 8.0   | 25736 | 0.1711          | 0.9808   | 0.9806 | 0.9892    | 0.9721 |
+| 0.0036        | 9.0   | 28953 | 0.1867          | 0.9802   | 0.9800 | 0.9905    | 0.9696 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "PORTULAN/albertina-900m-portuguese-ptpt-encoder",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_head_size": 64,
+  "attention_probs_dropout_prob": 0.1,
+  "conv_act": "gelu",
+  "conv_kernel_size": 3,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1536,
+  "id2label": {
+    "0": "PT-PT",
+    "1": "PT-BR"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "label2id": {
+    "PT-BR": 1,
+    "PT-PT": 0
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1536,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3ff4c9238f90645375d55f78199db30f85210160c88a738b418567dea8df155
+size 3547878120

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "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 +1,59 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "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
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98dba147a521d306ae9efe98c37cfcba4dd621d3f67b2a55fc71af2eb37ec508
+size 5048