Noor0/XLM_RoBERTa_Twitter_eng_ar_sentiment

README.md

@@ -1,6 +1,5 @@
 ---
-license: mit
-base_model: xlm-roberta-base
+base_model: cardiffnlp/twitter-xlm-roberta-base-sentiment
 tags:
 - generated_from_trainer
 metrics:
@@ -15,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # result
 
-This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
+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: 0.8753
-- Accuracy: 0.7905
+- Loss: 0.5662
+- Accuracy: 0.8065
 
 ## Model description
 
@@ -38,22 +37,21 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | Accuracy |
 |:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 0.5769        | 1.0   | 12925 | 0.6333          | 0.7682   |
-| 0.4925        | 2.0   | 25850 | 0.5946          | 0.7824   |
-| 0.43          | 3.0   | 38775 | 0.5930          | 0.7864   |
-| 0.3766        | 4.0   | 51700 | 0.6989          | 0.7905   |
-| 0.3333        | 5.0   | 64625 | 0.8753          | 0.7905   |
+| 0.5234        | 1.0   | 6463  | 0.5311          | 0.7852   |
+| 0.4135        | 2.0   | 12926 | 0.5020          | 0.8039   |
+| 0.3246        | 3.0   | 19389 | 0.5662          | 0.8065   |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "xlm-roberta-base",
+  "_name_or_path": "cardiffnlp/twitter-xlm-roberta-base-sentiment",
   "architectures": [
     "XLMRobertaForSequenceClassification"
   ],
@@ -7,20 +7,21 @@
   "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": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
+    "0": "negative",
+    "1": "neutral",
+    "2": "positive"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
+    "negative": 0,
+    "neutral": 1,
+    "positive": 2
   },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05dfdd4e783bfc719e99edc9e3d8194c8d5a6ae765a8f535f12f1bfaa19f1033
+oid sha256:6de7a3825d55ff3eaa6f08a0f9aa3a481f38ec1ec4a0cd483ff4225cae180a6a
 size 1112208084

runs/Dec06_03-15-23_0f41a1620a98/events.out.tfevents.1701832679.0f41a1620a98.47.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1968e7ee7350232949419098cfb5839f8375db5e30a36a7ee16011685edab1d6
+size 11795

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c4147c7d8584d679fcabb10e7c63ac96de865feb8a5e2b6bc9308acf93cacdb
-size 17082953
+oid sha256:b0ebf3e7cfe6347b0b6b82a19702f2f60528b0653b70195c4093b3cb3bcb8cd7
+size 17098361

tokenizer_config.json

@@ -46,9 +46,10 @@
   "cls_token": "<s>",
   "eos_token": "</s>",
   "mask_token": "<mask>",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "sep_token": "</s>",
+  "sp_model_kwargs": {},
   "tokenizer_class": "XLMRobertaTokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4839b97df1775501c504ea2360c9bcd5949b53b46cb79e91efe2df8b9d40fd55
+oid sha256:a40590a3260ce5f4807be95baf1d0ce597013250f0bc6e673dee2f053f04db34
 size 4155