araT5-Rajhi-Intent-T5ForSequenceClassification-NewData-8-1-2024-V4

README.md

@@ -0,0 +1,69 @@
+---
+base_model: UBC-NLP/AraT5v2-base-1024
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: results2
+  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. -->
+
+# results2
+
+This model is a fine-tuned version of [UBC-NLP/AraT5v2-base-1024](https://huggingface.co/UBC-NLP/AraT5v2-base-1024) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1770
+- F1: 0.9794
+
+## 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: 16
+- 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 | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 3.0825        | 1.0   | 543  | 2.9025          | 0.1075 |
+| 2.4749        | 2.0   | 1086 | 1.4022          | 0.4926 |
+| 0.8659        | 3.0   | 1629 | 0.3157          | 0.8640 |
+| 0.3053        | 4.0   | 2172 | 0.2107          | 0.9415 |
+| 0.1425        | 5.0   | 2715 | 0.1161          | 0.9794 |
+| 0.073         | 6.0   | 3258 | 0.1695          | 0.9794 |
+| 0.0444        | 7.0   | 3801 | 0.1721          | 0.9794 |
+| 0.0441        | 8.0   | 4344 | 0.1719          | 0.9794 |
+| 0.0265        | 9.0   | 4887 | 0.1819          | 0.9794 |
+| 0.0252        | 10.0  | 5430 | 0.1770          | 0.9794 |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.0.1
+- Datasets 2.16.1
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,86 @@
+{
+  "_name_or_path": "UBC-NLP/AraT5v2-base-1024",
+  "architectures": [
+    "T5ForSequenceClassification"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23"
+  },
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 110208
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f605831ff5e2f1369258bc00c225e52fed31ecc8fa9d48d589093b06c346e868
+size 1133949480

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08d2f7cc518db3bc553794122bc5afe13f28fac21e130c32de72848eeea27aa3
+size 4155