test444

README.md

@@ -0,0 +1,81 @@
+---
+license: apache-2.0
+base_model: projecte-aina/roberta-base-ca-v2-cased-te
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: modelofinenew
+  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. -->
+
+# modelofinenew
+
+This model is a fine-tuned version of [projecte-aina/roberta-base-ca-v2-cased-te](https://huggingface.co/projecte-aina/roberta-base-ca-v2-cased-te) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.2185
+- Accuracy: 0.5126
+- F1: 0.5338
+
+## 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: 20
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 30
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|
+| 1.9546        | 1.6129  | 50   | 2.5028          | 0.2101   | 0.2019 |
+| 1.7901        | 3.2258  | 100  | 2.6787          | 0.1849   | 0.1805 |
+| 1.6177        | 4.8387  | 150  | 2.3416          | 0.3445   | 0.3332 |
+| 1.2977        | 6.4516  | 200  | 2.0729          | 0.4202   | 0.4060 |
+| 0.9411        | 8.0645  | 250  | 1.9746          | 0.4706   | 0.4583 |
+| 0.595         | 9.6774  | 300  | 1.8840          | 0.5126   | 0.5167 |
+| 0.3374        | 11.2903 | 350  | 1.8955          | 0.4958   | 0.4977 |
+| 0.1974        | 12.9032 | 400  | 1.9658          | 0.5378   | 0.5169 |
+| 0.0981        | 14.5161 | 450  | 2.2185          | 0.5126   | 0.5338 |
+| 0.05          | 16.1290 | 500  | 2.3554          | 0.5042   | 0.5096 |
+| 0.0312        | 17.7419 | 550  | 2.4366          | 0.5294   | 0.5289 |
+| 0.0235        | 19.3548 | 600  | 2.5235          | 0.5210   | 0.5181 |
+| 0.0194        | 20.9677 | 650  | 2.5713          | 0.5294   | 0.5289 |
+| 0.0166        | 22.5806 | 700  | 2.6188          | 0.5294   | 0.5289 |
+| 0.0148        | 24.1935 | 750  | 2.6473          | 0.5294   | 0.5289 |
+| 0.0136        | 25.8065 | 800  | 2.6742          | 0.5210   | 0.5218 |
+| 0.013         | 27.4194 | 850  | 2.6920          | 0.5210   | 0.5218 |
+| 0.0129        | 29.0323 | 900  | 2.6961          | 0.5210   | 0.5218 |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.1.0+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,68 @@
+{
+  "_name_or_path": "projecte-aina/roberta-base-ca-v2-cased-te",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "mnli",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Aigua",
+    "1": "Consum, comer\u00e7 i mercats",
+    "2": "Cultura",
+    "3": "Economia",
+    "4": "Educaci\u00f3",
+    "5": "Enllumenat p\u00fablic",
+    "6": "Esports",
+    "7": "Habitatge",
+    "8": "Horta",
+    "9": "Medi ambient i jardins",
+    "10": "Neteja de la via p\u00fablica",
+    "11": "Salut p\u00fablica",
+    "12": "Seguretat ciutadana i incivisme",
+    "13": "Serveis socials",
+    "14": "Tr\u00e0mits",
+    "15": "Urbanisme",
+    "16": "Via p\u00fablica i mobilitat"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Aigua": 0,
+    "Consum, comer\u00e7 i mercats": 1,
+    "Cultura": 2,
+    "Economia": 3,
+    "Educaci\u00f3": 4,
+    "Enllumenat p\u00fablic": 5,
+    "Esports": 6,
+    "Habitatge": 7,
+    "Horta": 8,
+    "Medi ambient i jardins": 9,
+    "Neteja de la via p\u00fablica": 10,
+    "Salut p\u00fablica": 11,
+    "Seguretat ciutadana i incivisme": 12,
+    "Serveis socials": 13,
+    "Tr\u00e0mits": 14,
+    "Urbanisme": 15,
+    "Via p\u00fablica i mobilitat": 16
+  },
+  "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": "4.40.0",
+  "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:e9144548ce1a4e025c2f0d08abf81b165296f0e99bc25d9e8131a4ba261a8f45
+size 498649748

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 +1,65 @@
+{
+  "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,
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "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 sha256:6a54cbd8df69f708873c6c52004f3ddbd3d3e6ad799cec62345d370c994497ed
+size 4920