End of training

README.md

@@ -0,0 +1,81 @@
+---
+license: apache-2.0
+base_model: projecte-aina/roberta-base-ca-v2
+tags:
+- generated_from_trainer
+datasets:
+- wiki_cat_ca
+metrics:
+- accuracy
+- f1
+model-index:
+- name: activitat-finetuned-wikicat
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: projecte-aina/WikiCAT_ca
+      type: wiki_cat_ca
+      config: wikiCAT_ca
+      split: validation
+      args: wikiCAT_ca
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.504
+    - name: F1
+      type: f1
+      value: 0.42287883344725447
+---
+
+<!-- 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. -->
+
+# activitat-finetuned-wikicat
+
+This model is a fine-tuned version of [projecte-aina/roberta-base-ca-v2](https://huggingface.co/projecte-aina/roberta-base-ca-v2) on the projecte-aina/WikiCAT_ca dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.1061
+- Accuracy: 0.504
+- F1: 0.4229
+
+## 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: 2e-05
+- train_batch_size: 5
+- eval_batch_size: 5
+- 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     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| No log        | 1.0   | 100  | 2.2088          | 0.392    | 0.2614 |
+| No log        | 2.0   | 200  | 2.1061          | 0.504    | 0.4229 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "projecte-aina/roberta-base-ca-v2",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Ci\u00e8ncia_i_Tecnologia",
+    "1": "Dret",
+    "2": "Economia",
+    "3": "Enginyeria",
+    "4": "Entreteniment",
+    "5": "Esport",
+    "6": "Filosofia",
+    "7": "Hist\u00f2ria",
+    "8": "Humanitats",
+    "9": "Matem\u00e0tiques",
+    "10": "M\u00fasica",
+    "11": "Pol\u00edtica",
+    "12": "Religi\u00f3"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Ci\u00e8ncia_i_Tecnologia": 0,
+    "Dret": 1,
+    "Economia": 2,
+    "Enginyeria": 3,
+    "Entreteniment": 4,
+    "Esport": 5,
+    "Filosofia": 6,
+    "Hist\u00f2ria": 7,
+    "Humanitats": 8,
+    "Matem\u00e0tiques": 9,
+    "M\u00fasica": 10,
+    "Pol\u00edtica": 11,
+    "Religi\u00f3": 12
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e36fa375860a6fd47a75b067977e1510580a8f42ec467740c86fff2b4465da3
+size 498637444

runs/Mar24_07-29-32_111eecf27792/events.out.tfevents.1711265411.111eecf27792.25102.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b34e57889553c05dfe307ca4423232819e3ab885f0e0a214dba922fc609e7f28
+size 5402

runs/Mar24_07-29-32_111eecf27792/events.out.tfevents.1711266933.111eecf27792.25102.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a1307802c5ae16abf78708da17d258fb46ad9a456017f22e78f77a36aa6d816
+size 6487

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_len": 512,
+  "model_max_length": 512,
+  "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 sha256:09a3b72a20690120cd7ea74b3cc01090a5a192dc4e86003bdc69c551f26e5a8b
+size 4920