newmodel

README.md

@@ -0,0 +1,109 @@
+---
+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: 2404v7
+  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. -->
+
+# 2404v7
+
+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: 0.6435
+- Accuracy: 0.8487
+- Precision: 0.8488
+- Recall: 0.8487
+- F1: 0.8487
+- Ratio: 0.4916
+
+## 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: 3e-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: 10
+- label_smoothing_factor: 0.1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     | Ratio  |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|
+| 3.5609        | 0.2597 | 10   | 1.6738          | 0.5168   | 0.5191    | 0.5168 | 0.5020 | 0.3277 |
+| 1.4146        | 0.5195 | 20   | 0.9720          | 0.5294   | 0.5309    | 0.5294 | 0.5237 | 0.6092 |
+| 0.924         | 0.7792 | 30   | 0.9377          | 0.5      | 0.25      | 0.5    | 0.3333 | 1.0    |
+| 0.9189        | 1.0390 | 40   | 0.8705          | 0.5042   | 0.7511    | 0.5042 | 0.3426 | 0.0042 |
+| 0.8741        | 1.2987 | 50   | 0.8415          | 0.5      | 0.25      | 0.5    | 0.3333 | 1.0    |
+| 0.8001        | 1.5584 | 60   | 0.7613          | 0.7311   | 0.7640    | 0.7311 | 0.7224 | 0.6765 |
+| 0.7156        | 1.8182 | 70   | 0.6827          | 0.7773   | 0.8070    | 0.7773 | 0.7718 | 0.3445 |
+| 0.7028        | 2.0779 | 80   | 0.6722          | 0.7941   | 0.7967    | 0.7941 | 0.7937 | 0.4538 |
+| 0.5612        | 2.3377 | 90   | 0.6600          | 0.7689   | 0.7776    | 0.7689 | 0.7671 | 0.5882 |
+| 0.5967        | 2.5974 | 100  | 0.6264          | 0.8067   | 0.8075    | 0.8067 | 0.8066 | 0.5252 |
+| 0.6661        | 2.8571 | 110  | 0.6225          | 0.8193   | 0.8260    | 0.8193 | 0.8184 | 0.4286 |
+| 0.6454        | 3.1169 | 120  | 0.6108          | 0.8109   | 0.8336    | 0.8109 | 0.8077 | 0.6303 |
+| 0.541         | 3.3766 | 130  | 0.6002          | 0.8235   | 0.8311    | 0.8235 | 0.8225 | 0.4244 |
+| 0.538         | 3.6364 | 140  | 0.5880          | 0.8403   | 0.8428    | 0.8403 | 0.8401 | 0.5420 |
+| 0.5157        | 3.8961 | 150  | 0.5845          | 0.8529   | 0.8603    | 0.8529 | 0.8522 | 0.4286 |
+| 0.4868        | 4.1558 | 160  | 0.6059          | 0.8403   | 0.8548    | 0.8403 | 0.8387 | 0.6008 |
+| 0.4877        | 4.4156 | 170  | 0.5575          | 0.8571   | 0.8572    | 0.8571 | 0.8571 | 0.4916 |
+| 0.4758        | 4.6753 | 180  | 0.5656          | 0.8403   | 0.8403    | 0.8403 | 0.8403 | 0.5    |
+| 0.4686        | 4.9351 | 190  | 0.5736          | 0.8571   | 0.8581    | 0.8571 | 0.8571 | 0.5252 |
+| 0.4311        | 5.1948 | 200  | 0.5755          | 0.8571   | 0.8571    | 0.8571 | 0.8571 | 0.5    |
+| 0.4452        | 5.4545 | 210  | 0.6053          | 0.8487   | 0.8491    | 0.8487 | 0.8487 | 0.5168 |
+| 0.4396        | 5.7143 | 220  | 0.5726          | 0.8613   | 0.8614    | 0.8613 | 0.8613 | 0.4958 |
+| 0.4923        | 5.9740 | 230  | 0.5534          | 0.8487   | 0.8487    | 0.8487 | 0.8487 | 0.5    |
+| 0.4002        | 6.2338 | 240  | 0.5841          | 0.8445   | 0.8446    | 0.8445 | 0.8445 | 0.5042 |
+| 0.3887        | 6.4935 | 250  | 0.6092          | 0.8361   | 0.8402    | 0.8361 | 0.8356 | 0.5546 |
+| 0.402         | 6.7532 | 260  | 0.6164          | 0.8445   | 0.8446    | 0.8445 | 0.8445 | 0.4958 |
+| 0.4644        | 7.0130 | 270  | 0.6094          | 0.8571   | 0.8622    | 0.8571 | 0.8566 | 0.4412 |
+| 0.3905        | 7.2727 | 280  | 0.5938          | 0.8487   | 0.8503    | 0.8487 | 0.8486 | 0.5336 |
+| 0.3836        | 7.5325 | 290  | 0.6080          | 0.8487   | 0.8496    | 0.8487 | 0.8486 | 0.5252 |
+| 0.3781        | 7.7922 | 300  | 0.6193          | 0.8529   | 0.8530    | 0.8529 | 0.8529 | 0.4958 |
+| 0.4384        | 8.0519 | 310  | 0.6211          | 0.8529   | 0.8532    | 0.8529 | 0.8529 | 0.4874 |
+| 0.3324        | 8.3117 | 320  | 0.6312          | 0.8445   | 0.8446    | 0.8445 | 0.8445 | 0.4958 |
+| 0.3779        | 8.5714 | 330  | 0.6394          | 0.8529   | 0.8532    | 0.8529 | 0.8529 | 0.4874 |
+| 0.3772        | 8.8312 | 340  | 0.6415          | 0.8529   | 0.8530    | 0.8529 | 0.8529 | 0.4958 |
+| 0.3757        | 9.0909 | 350  | 0.6464          | 0.8403   | 0.8404    | 0.8403 | 0.8403 | 0.5084 |
+| 0.3742        | 9.3506 | 360  | 0.6441          | 0.8487   | 0.8487    | 0.8487 | 0.8487 | 0.5    |
+| 0.3647        | 9.6104 | 370  | 0.6437          | 0.8487   | 0.8488    | 0.8487 | 0.8487 | 0.4916 |
+| 0.3502        | 9.8701 | 380  | 0.6435          | 0.8487   | 0.8488    | 0.8487 | 0.8487 | 0.4916 |
+
+
+### 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 sha256:11facde7a1a11c693796174fc8a98d600c56279636205a01be07a7db589abcc2
+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 sha256:206a0b107dad8688332837f0c15021de9db0effaa9b54fa0c5ac35c97908498c
+size 4984