newmodel

README.md

@@ -0,0 +1,86 @@
+---
+license: apache-2.0
+base_model: projecte-aina/roberta-base-ca-v2-cased-te
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: 2404v6
+  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. -->
+
+# 2404v6
+
+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: 0.5736
+- Accuracy: 0.8487
+- Precision: 0.8491
+- Recall: 0.8487
+- F1: 0.8487
+- Ratio: 0.4832
+
+## 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: 16
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.06
+- lr_scheduler_warmup_steps: 4
+- num_epochs: 4
+- label_smoothing_factor: 0.1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     | Ratio  |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|
+| 3.6992        | 0.2597 | 10   | 1.6456          | 0.5378   | 0.5416    | 0.5378 | 0.5270 | 0.3487 |
+| 1.4527        | 0.5195 | 20   | 1.1248          | 0.5336   | 0.5398    | 0.5336 | 0.5147 | 0.6975 |
+| 0.9494        | 0.7792 | 30   | 0.9286          | 0.5756   | 0.6051    | 0.5756 | 0.5437 | 0.7647 |
+| 0.9076        | 1.0390 | 40   | 0.8154          | 0.6849   | 0.6855    | 0.6849 | 0.6846 | 0.5294 |
+| 0.8356        | 1.2987 | 50   | 0.7335          | 0.7647   | 0.7659    | 0.7647 | 0.7644 | 0.5336 |
+| 0.7475        | 1.5584 | 60   | 0.7286          | 0.7437   | 0.7803    | 0.7437 | 0.7350 | 0.6807 |
+| 0.7234        | 1.8182 | 70   | 0.6457          | 0.8025   | 0.8027    | 0.8025 | 0.8025 | 0.4874 |
+| 0.67          | 2.0779 | 80   | 0.6208          | 0.8025   | 0.8043    | 0.8025 | 0.8022 | 0.5378 |
+| 0.5994        | 2.3377 | 90   | 0.6106          | 0.8235   | 0.8236    | 0.8235 | 0.8235 | 0.4916 |
+| 0.666         | 2.5974 | 100  | 0.5912          | 0.8361   | 0.8363    | 0.8361 | 0.8361 | 0.5126 |
+| 0.6142        | 2.8571 | 110  | 0.5853          | 0.8319   | 0.8320    | 0.8319 | 0.8319 | 0.5084 |
+| 0.6181        | 3.1169 | 120  | 0.5866          | 0.8361   | 0.8373    | 0.8361 | 0.8360 | 0.5294 |
+| 0.5555        | 3.3766 | 130  | 0.5762          | 0.8487   | 0.8496    | 0.8487 | 0.8486 | 0.4748 |
+| 0.5658        | 3.6364 | 140  | 0.5751          | 0.8487   | 0.8496    | 0.8487 | 0.8486 | 0.4748 |
+| 0.5777        | 3.8961 | 150  | 0.5736          | 0.8487   | 0.8491    | 0.8487 | 0.8487 | 0.4832 |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,40 @@
+{
+  "_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": "ENTAILMENT",
+    "1": "NEUTRAL",
+    "2": "CONTRADICTION"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "CONTRADICTION": 2,
+    "ENTAILMENT": 0,
+    "NEUTRAL": 1
+  },
+  "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 sha256:6a14e08c43481a416874d634b9cf786eff8c3441e29edefcc9c8db7fa24bae7f
+size 498606684

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 sha256:7b1ed6ff99e97de233b2b831905d93aa8da062ed2fe31189c313cf244d4814ec
+size 4920