xlm-roberta-meta4types-ft-ES

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,77 @@
+---
+base_model: cardiffnlp/twitter-xlm-roberta-base-sentiment
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+model-index:
+- name: xlm-roberta-meta4types-ft
+  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. -->
+
+# xlm-roberta-meta4types-ft
+
+This model is a fine-tuned version of [cardiffnlp/twitter-xlm-roberta-base-sentiment](https://huggingface.co/cardiffnlp/twitter-xlm-roberta-base-sentiment) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8324
+- Roc Auc: 0.7122
+- Hamming Loss: 0.2261
+- F1 Score: 0.6089
+- Accuracy: 0.5528
+- Precision: 0.6081
+- Recall: 0.6436
+- Per Label: {'f1_score': 0.608905822183525, 'precision': 0.6080571799870046, 'recall': 0.6435841440010588, 'support': 235}
+
+## 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: 4
+- eval_batch_size: 4
+- 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: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Roc Auc | Hamming Loss | F1 Score | Accuracy | Precision | Recall | Per Label                                                                                                         |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:------------:|:--------:|:--------:|:---------:|:------:|:-----------------------------------------------------------------------------------------------------------------:|
+| 0.4279        | 1.0   | 199  | 0.5287          | 0.4967  | 0.2496       | 0.3209   | 0.5276   | 0.6759    | 0.3575 | {'f1_score': 0.3208852937872149, 'precision': 0.6759286629224553, 'recall': 0.35748792270531404, 'support': 235}  |
+| 0.4609        | 2.0   | 398  | 0.5076          | 0.5276  | 0.2245       | 0.3757   | 0.5779   | 0.8026    | 0.3913 | {'f1_score': 0.3757246741060956, 'precision': 0.8025944726452341, 'recall': 0.3913043478260869, 'support': 235}   |
+| 0.5875        | 3.0   | 597  | 0.5463          | 0.5557  | 0.2127       | 0.4232   | 0.6080   | 0.6653    | 0.4153 | {'f1_score': 0.42320834457332973, 'precision': 0.6653348029760265, 'recall': 0.41534974521871487, 'support': 235} |
+| 0.493         | 4.0   | 796  | 0.5526          | 0.6428  | 0.2077       | 0.5744   | 0.6080   | 0.6577    | 0.5455 | {'f1_score': 0.5744086944086945, 'precision': 0.6577216876443267, 'recall': 0.5455495996294091, 'support': 235}   |
+| 0.3519        | 5.0   | 995  | 0.6760          | 0.6795  | 0.2161       | 0.5809   | 0.5879   | 0.6192    | 0.5961 | {'f1_score': 0.5809003977320809, 'precision': 0.6191632544737641, 'recall': 0.5960790152868771, 'support': 235}   |
+| 0.2451        | 6.0   | 1194 | 0.7729          | 0.7046  | 0.2312       | 0.6045   | 0.5578   | 0.6161    | 0.6045 | {'f1_score': 0.6045152483631816, 'precision': 0.6161038489469862, 'recall': 0.6044603269141685, 'support': 235}   |
+| 0.0608        | 7.0   | 1393 | 0.7616          | 0.6942  | 0.2127       | 0.6060   | 0.5779   | 0.6221    | 0.6095 | {'f1_score': 0.6060266030810951, 'precision': 0.6220689655172414, 'recall': 0.6094566871815233, 'support': 235}   |
+| 0.0859        | 8.0   | 1592 | 0.8324          | 0.7122  | 0.2261       | 0.6089   | 0.5528   | 0.6081    | 0.6436 | {'f1_score': 0.608905822183525, 'precision': 0.6080571799870046, 'recall': 0.6435841440010588, 'support': 235}    |
+| 0.0767        | 9.0   | 1791 | 0.8192          | 0.6950  | 0.2127       | 0.6004   | 0.5578   | 0.6086    | 0.6073 | {'f1_score': 0.6003549503292779, 'precision': 0.6086247086247086, 'recall': 0.6072827741380452, 'support': 235}   |
+| 0.0221        | 10.0  | 1990 | 0.8094          | 0.6975  | 0.2077       | 0.6135   | 0.5578   | 0.6116    | 0.6215 | {'f1_score': 0.6135398054397458, 'precision': 0.6116043923140263, 'recall': 0.6215108199324995, 'support': 235}   |
+
+
+### Framework versions
+
+- Transformers 4.43.1
+- Pytorch 1.13.1+cu116
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "cardiffnlp/twitter-xlm-roberta-base-sentiment",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "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": "negative",
+    "1": "neutral",
+    "2": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "neutral": 1,
+    "positive": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bde1611e66e9dadf639c0f6edd76f8f85fc1957a76d5c3d5e35c56fa1deb023a
+size 1112208084

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:349ddbc97c4742ad2a4f2da1ecf985a03c45bff47d712556b3a73db66512977a
+size 17098516

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3dfa6174dc02addb7d04e1947a4128eef7770fcd47845520edad2d61567a1c4
+size 4731