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 +1,79 @@
+---
+base_model: cardiffnlp/twitter-xlm-roberta-base-sentiment
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: fineTuningXLMRoberta-TokenClassification-Spacy
+  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. -->
+
+# fineTuningXLMRoberta-TokenClassification-Spacy
+
+This model is a fine-tuned version of [cardiffnlp/twitter-xlm-roberta-base-sentiment](https://huggingface.co/cardiffnlp/twitter-xlm-roberta-base-sentiment) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8479
+- Precision: 0.2076
+- Recall: 0.2102
+- F1: 0.2089
+- Accuracy: 0.6718
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 31   | 0.7433          | 0.2164    | 0.1421 | 0.1716 | 0.6557   |
+| No log        | 2.0   | 62   | 0.7177          | 0.2275    | 0.1848 | 0.2039 | 0.6727   |
+| No log        | 3.0   | 93   | 0.7054          | 0.1719    | 0.1949 | 0.1827 | 0.6637   |
+| No log        | 4.0   | 124  | 0.7148          | 0.1823    | 0.1919 | 0.1869 | 0.6628   |
+| No log        | 5.0   | 155  | 0.7018          | 0.2063    | 0.2061 | 0.2062 | 0.6853   |
+| No log        | 6.0   | 186  | 0.7310          | 0.1866    | 0.1919 | 0.1892 | 0.6711   |
+| No log        | 7.0   | 217  | 0.7272          | 0.2150    | 0.2071 | 0.2110 | 0.6897   |
+| No log        | 8.0   | 248  | 0.7878          | 0.1758    | 0.1848 | 0.1802 | 0.6582   |
+| No log        | 9.0   | 279  | 0.7727          | 0.2080    | 0.2071 | 0.2075 | 0.6814   |
+| No log        | 10.0  | 310  | 0.8099          | 0.1969    | 0.1959 | 0.1964 | 0.6688   |
+| No log        | 11.0  | 341  | 0.8119          | 0.2062    | 0.2030 | 0.2046 | 0.6766   |
+| No log        | 12.0  | 372  | 0.8227          | 0.2105    | 0.2112 | 0.2108 | 0.6770   |
+| No log        | 13.0  | 403  | 0.8300          | 0.2008    | 0.2051 | 0.2029 | 0.6744   |
+| No log        | 14.0  | 434  | 0.8409          | 0.2064    | 0.2081 | 0.2073 | 0.6739   |
+| No log        | 15.0  | 465  | 0.8479          | 0.2076    | 0.2102 | 0.2089 | 0.6718   |
+
+
+### Framework versions
+
+- Transformers 4.44.0
+- Pytorch 2.4.0
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "cardiffnlp/twitter-xlm-roberta-base-sentiment",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "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": "positive",
+    "2": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "O": 2,
+    "negative": 0,
+    "positive": 1
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0",
+  "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 sha256:02a33a53f6ef9ddfff457d26c37476d4cc00f81baa0887e3c877fe0b3fccda6e
+size 1109845500

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:b74659c780d49afad7a7b9799868f75cbd3014fb6c34956e85a793028d38094a
+size 17098251

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 sha256:912d0dd936dbe15184f05c3170b044cb28e74459e157238cc7ca734a69d687bf
+size 5240