End of training

.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 +1,76 @@
+---
+base_model: cardiffnlp/twitter-xlm-roberta-base-sentiment
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+model-index:
+- name: xlm-roberta-meta4types-ft-2.0
+  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-2.0
+
+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: 1.0008
+- Roc Auc: 0.6612
+- Hamming Loss: 0.2239
+- F1 Score: 0.5943
+- Accuracy: 0.5392
+- Precision: 0.5798
+- Recall: 0.6121
+
+## 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: 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 |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:------------:|:--------:|:--------:|:---------:|:------:|
+| No log        | 1.0   | 204  | 0.5010          | 0.4988  | 0.2042       | 0.2930   | 0.6127   | 0.5948    | 0.3333 |
+| No log        | 2.0   | 408  | 0.5433          | 0.5027  | 0.2010       | 0.3038   | 0.6176   | 0.9281    | 0.3388 |
+| 0.4958        | 3.0   | 612  | 0.5013          | 0.5043  | 0.2010       | 0.3139   | 0.6127   | 0.8170    | 0.3443 |
+| 0.4958        | 4.0   | 816  | 0.6563          | 0.6108  | 0.2190       | 0.5211   | 0.5686   | 0.6488    | 0.4799 |
+| 0.3484        | 5.0   | 1020 | 0.6404          | 0.6444  | 0.1912       | 0.5645   | 0.5980   | 0.6014    | 0.5386 |
+| 0.3484        | 6.0   | 1224 | 0.9555          | 0.6520  | 0.2614       | 0.5559   | 0.5196   | 0.5889    | 0.5417 |
+| 0.3484        | 7.0   | 1428 | 0.7919          | 0.6202  | 0.2222       | 0.5417   | 0.5392   | 0.5743    | 0.5297 |
+| 0.1644        | 8.0   | 1632 | 0.8959          | 0.6389  | 0.2157       | 0.5551   | 0.5539   | 0.5823    | 0.5515 |
+| 0.1644        | 9.0   | 1836 | 1.0008          | 0.6612  | 0.2239       | 0.5943   | 0.5392   | 0.5798    | 0.6121 |
+| 0.0611        | 10.0  | 2040 | 0.9594          | 0.6452  | 0.2141       | 0.5822   | 0.5294   | 0.5757    | 0.5893 |
+
+
+### Framework versions
+
+- Transformers 4.43.3
+- Pytorch 2.3.1+cu121
+- 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": "4.43.3",
+  "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 sha256:6d05f207664c49f487f9fbf1b00166e62037e77b485b3d4517f8f2dbb2e70d22
+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 sha256:18c627ab81818311c0fe2cdff9513205bf80e28f6b5d501fd1222714b4e7a084
+size 5176