End of training

README.md

@@ -0,0 +1,65 @@
+---
+base_model: cardiffnlp/twitter-xlm-roberta-base-sentiment-multilingual
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: sentiment_analysis_model_rpsi
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/themohal/huggingface/runs/ddp65niu)
+# sentiment_analysis_model_rpsi
+
+This model is a fine-tuned version of [cardiffnlp/twitter-xlm-roberta-base-sentiment-multilingual](https://huggingface.co/cardiffnlp/twitter-xlm-roberta-base-sentiment-multilingual) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5686
+- Accuracy: 0.8018
+
+## 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: 6
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.7314        | 1.0   | 3378  | 0.6028          | 0.7367   |
+| 0.563         | 2.0   | 6756  | 0.5503          | 0.7646   |
+| 0.4859        | 3.0   | 10134 | 0.5316          | 0.7847   |
+| 0.421         | 4.0   | 13512 | 0.5223          | 0.7954   |
+| 0.3668        | 5.0   | 16890 | 0.5514          | 0.7973   |
+| 0.3266        | 6.0   | 20268 | 0.5686          | 0.8018   |
+
+
+### Framework versions
+
+- Transformers 4.42.3
+- Pytorch 2.1.2
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "cardiffnlp/twitter-xlm-roberta-base-sentiment-multilingual",
+  "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": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "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:b737fb5ec232da426a77e6de2289926e88ed31df3c51ff9f12f05691c29a9da5
+size 1112208084

runs/Aug27_23-13-35_90dd27a1bf53/events.out.tfevents.1724800424.90dd27a1bf53.23.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34020973aada3f3fab71e0db5985fa1015757cbeb6f2b59329a4eab52415f1dc
+size 8825

runs/Aug27_23-13-35_90dd27a1bf53/events.out.tfevents.1724841990.90dd27a1bf53.23.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21fb489170f34e9fc19494dab78b5ac18a40e1532cf157ee1f4b468e72b13d27
+size 417

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "105": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "lowercase": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecf6a568b6b5944afdceac716cdd38ccab70f9ee5c8fe701313eed7ba31fa558
+size 5176