End of training

README.md

@@ -0,0 +1,71 @@
+---
+license: apache-2.0
+base_model: projecte-aina/roberta-base-ca-v2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: fm-tc-authentic
+  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. -->
+
+# fm-tc-authentic
+
+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 None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2183
+- Accuracy: 0.684
+- Precision: 0.4290
+- Recall: 0.4443
+- F1: 0.4224
+
+## 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
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 2.2298        | 1.0   | 568  | 1.5513          | 0.576    | 0.2101    | 0.2781 | 0.2186 |
+| 1.4142        | 2.0   | 1136 | 1.2728          | 0.652    | 0.3275    | 0.3903 | 0.3517 |
+| 1.1276        | 3.0   | 1704 | 1.2183          | 0.684    | 0.4290    | 0.4443 | 0.4224 |
+| 0.8384        | 4.0   | 2272 | 1.2388          | 0.672    | 0.5085    | 0.4718 | 0.4609 |
+| 0.6867        | 5.0   | 2840 | 1.2870          | 0.674    | 0.5075    | 0.4686 | 0.4597 |
+
+
+### Framework versions
+
+- Transformers 4.41.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,51 @@
+{
+  "_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": "Aig\u00fces",
+    "1": "Consum, comer\u00e7 i mercats",
+    "2": "Cultura",
+    "3": "Economia",
+    "4": "Educaci\u00f3",
+    "5": "Enllumenat p\u00fablic",
+    "6": "Esports",
+    "7": "Habitatge",
+    "8": "Horta",
+    "9": "Informaci\u00f3 general",
+    "10": "Inform\u00e0tica",
+    "11": "Joventut",
+    "12": "Medi ambient",
+    "13": "Neteja de la via p\u00fablica",
+    "14": "Salut p\u00fablica i Cementiri",
+    "15": "Seguretat",
+    "16": "Serveis socials",
+    "17": "Tramitacions",
+    "18": "Urbanisme",
+    "19": "Via p\u00fablica i mobilitat"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.41.0",
+  "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:c9719a973ac90f6cb3dd9e7d483d6b3a5d7bbde8f1cc9ccb2bf2882d9cfa3991
+size 498658976

runs/May28_06-51-05_f9a3c78db310/events.out.tfevents.1716879070.f9a3c78db310.342.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c447e45938e22d89c58aa3ebe94e100913d5bf9fb8bcf883e5cc041bfce09b06
+size 9219

runs/May28_06-51-05_f9a3c78db310/events.out.tfevents.1716880383.f9a3c78db310.342.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fe6c9fc57810fa608f3a7d519de16005b86e85e89c8e3c7dbc2a2d859884b16
+size 560

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:abf9a1c735feb5f260a1326f4b7333ccef38bbb70e2c66166c5561de12fa4ce9
+size 5112