oddadmix/English-To-EgyptianArabic-Translator

README.md

@@ -0,0 +1,78 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Helsinki-NLP/opus-mt-en-ar
+tags:
+- generated_from_trainer
+model-index:
+- name: English-To-EgyptianArabic-Translator
+  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. -->
+
+# English-To-EgyptianArabic-Translator
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-ar](https://huggingface.co/Helsinki-NLP/opus-mt-en-ar) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.8722
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 1.5425        | 1.0   | 4701  | 1.9165          |
+| 1.4814        | 2.0   | 9402  | 1.8411          |
+| 1.3308        | 3.0   | 14103 | 1.8098          |
+| 1.2401        | 4.0   | 18804 | 1.7975          |
+| 1.1253        | 5.0   | 23505 | 1.7835          |
+| 1.02          | 6.0   | 28206 | 1.7948          |
+| 0.9592        | 7.0   | 32907 | 1.8001          |
+| 0.8913        | 8.0   | 37608 | 1.8011          |
+| 0.808         | 9.0   | 42309 | 1.8004          |
+| 0.7824        | 10.0  | 47010 | 1.8144          |
+| 0.7382        | 11.0  | 51711 | 1.8230          |
+| 0.6639        | 12.0  | 56412 | 1.8272          |
+| 0.6307        | 13.0  | 61113 | 1.8363          |
+| 0.6096        | 14.0  | 65814 | 1.8416          |
+| 0.5885        | 15.0  | 70515 | 1.8533          |
+| 0.549         | 16.0  | 75216 | 1.8609          |
+| 0.5113        | 17.0  | 79917 | 1.8633          |
+| 0.5041        | 18.0  | 84618 | 1.8700          |
+| 0.4829        | 19.0  | 89319 | 1.8681          |
+| 0.4847        | 20.0  | 94020 | 1.8722          |
+
+
+### Framework versions
+
+- Transformers 4.46.3
+- Pytorch 2.1.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-en-ar",
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 62801,
+  "decoder_vocab_size": 62802,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "extra_pos_embeddings": 62802,
+  "forced_eos_token_id": 0,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 62801,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 62802
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      62801
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 62801,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 62801,
+  "renormalize_logits": true,
+  "transformers_version": "4.46.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4b20d99c54d0029ab228cdd38f00a09dab9d09383a37ca723f6ccda3eee4de4
+size 305452744

runs/Nov20_21-51-23_n11x8j43o5/events.out.tfevents.1732139483.n11x8j43o5.352.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1ccc52eca5dc23839d8e68ca8281b50da68b52c6bd1d9dd806fa21633fcf4e8
+size 52113

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "62801": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "eng",
+  "sp_model_kwargs": {},
+  "target_lang": "ara",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92ca6446b8cc346e932f0f3283826b9a02f12b82d001aadc1cce060b893485a2
+size 5496