End of training

README.md

@@ -0,0 +1,96 @@
+---
+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: 2504v2
+  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. -->
+
+# 2504v2
+
+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: 0.6769
+- Accuracy: 0.8655
+- Precision: 0.8660
+- Recall: 0.8655
+- F1: 0.8655
+- Ratio: 0.5168
+
+## 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: 1e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 3
+- total_train_batch_size: 48
+- 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: 10
+- label_smoothing_factor: 0.2
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     | Ratio  |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|
+| 4.1824        | 0.3896 | 10   | 2.4179          | 0.5084   | 0.3727    | 0.3389 | 0.3212 | 0.7479 |
+| 1.997         | 0.7792 | 20   | 1.6877          | 0.5462   | 0.5489    | 0.5462 | 0.5398 | 0.3824 |
+| 1.4096        | 1.1688 | 30   | 1.2832          | 0.5924   | 0.5939    | 0.5924 | 0.5908 | 0.5630 |
+| 1.1296        | 1.5584 | 40   | 1.1040          | 0.6176   | 0.6187    | 0.6176 | 0.6168 | 0.5462 |
+| 1.0408        | 1.9481 | 50   | 0.9666          | 0.7227   | 0.7292    | 0.7227 | 0.7207 | 0.5840 |
+| 0.9242        | 2.3377 | 60   | 0.8829          | 0.7815   | 0.7816    | 0.7815 | 0.7815 | 0.4916 |
+| 0.8948        | 2.7273 | 70   | 0.8146          | 0.7899   | 0.7940    | 0.7899 | 0.7892 | 0.4412 |
+| 0.842         | 3.1169 | 80   | 0.7745          | 0.7941   | 0.8101    | 0.7941 | 0.7914 | 0.6134 |
+| 0.7715        | 3.5065 | 90   | 0.7244          | 0.8277   | 0.8279    | 0.8277 | 0.8277 | 0.4874 |
+| 0.7361        | 3.8961 | 100  | 0.7224          | 0.8151   | 0.8243    | 0.8151 | 0.8138 | 0.5840 |
+| 0.7115        | 4.2857 | 110  | 0.7004          | 0.8403   | 0.8407    | 0.8403 | 0.8403 | 0.5168 |
+| 0.7076        | 4.6753 | 120  | 0.6940          | 0.8403   | 0.8407    | 0.8403 | 0.8403 | 0.4832 |
+| 0.7026        | 5.0649 | 130  | 0.6936          | 0.8487   | 0.8491    | 0.8487 | 0.8487 | 0.5168 |
+| 0.6717        | 5.4545 | 140  | 0.6912          | 0.8571   | 0.8581    | 0.8571 | 0.8571 | 0.4748 |
+| 0.7166        | 5.8442 | 150  | 0.6867          | 0.8571   | 0.8575    | 0.8571 | 0.8571 | 0.5168 |
+| 0.6606        | 6.2338 | 160  | 0.6812          | 0.8613   | 0.8616    | 0.8613 | 0.8613 | 0.4874 |
+| 0.6939        | 6.6234 | 170  | 0.6747          | 0.8613   | 0.8614    | 0.8613 | 0.8613 | 0.4958 |
+| 0.6609        | 7.0130 | 180  | 0.6744          | 0.8613   | 0.8616    | 0.8613 | 0.8613 | 0.5126 |
+| 0.6388        | 7.4026 | 190  | 0.6790          | 0.8529   | 0.8532    | 0.8529 | 0.8529 | 0.5126 |
+| 0.6435        | 7.7922 | 200  | 0.6840          | 0.8571   | 0.8572    | 0.8571 | 0.8571 | 0.5084 |
+| 0.6534        | 8.1818 | 210  | 0.6828          | 0.8571   | 0.8571    | 0.8571 | 0.8571 | 0.5    |
+| 0.6552        | 8.5714 | 220  | 0.6818          | 0.8655   | 0.8660    | 0.8655 | 0.8655 | 0.5168 |
+| 0.646         | 8.9610 | 230  | 0.6788          | 0.8655   | 0.8660    | 0.8655 | 0.8655 | 0.5168 |
+| 0.6443        | 9.3506 | 240  | 0.6770          | 0.8655   | 0.8660    | 0.8655 | 0.8655 | 0.5168 |
+| 0.6418        | 9.7403 | 250  | 0.6769          | 0.8655   | 0.8660    | 0.8655 | 0.8655 | 0.5168 |
+
+
+### 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:ae4698a3afc903c76062b27aca8876509b3d46ce6cc6db0b8462f57af7146ec4
+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 sha256:7f2f2a8ecfccc85c81bf080e8110106c7c65a7c02f6ce042e7e733d68d0132e8
+size 4984