add model

README.md

@@ -0,0 +1,68 @@
+---
+license: apache-2.0
+tags:
+- generated_from_keras_callback
+model-index:
+- name: opus-mt-ar-en-finetunedTanzil-v6-ar-to-en
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# opus-mt-ar-en-finetunedTanzil-v6-ar-to-en
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-ar-en](https://huggingface.co/Helsinki-NLP/opus-mt-ar-en) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.8405
+- Validation Loss: 0.9594
+- Train Rouge1: 58.4345
+- Train Rouge2: 34.4502
+- Train Rougel: 54.6634
+- Train Rougelsum: 54.9469
+- Train Gen Len: 96.98
+- Epoch: 10
+
+## 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:
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Validation Loss | Train Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Train Gen Len | Epoch |
+|:----------:|:---------------:|:------------:|:------------:|:------------:|:---------------:|:-------------:|:-----:|
+| 1.7341     | 1.4426          | 55.0505      | 31.6295      | 51.3925      | 51.8558         | 76.44         | 0     |
+| 1.4329     | 1.2987          | 56.7672      | 33.8519      | 53.2796      | 53.6077         | 75.905        | 1     |
+| 1.2849     | 1.2132          | 59.1926      | 36.8577      | 55.8615      | 56.2321         | 94.415        | 2     |
+| 1.1854     | 1.1560          | 59.5654      | 36.0992      | 56.2438      | 56.6259         | 109.725       | 3     |
+| 1.1092     | 1.1101          | 59.2882      | 36.3247      | 56.1751      | 56.6098         | 110.7         | 4     |
+| 1.0478     | 1.0738          | 59.3702      | 35.9485      | 56.2157      | 56.6418         | 100.835       | 5     |
+| 0.9957     | 1.0464          | 59.3582      | 35.5831      | 55.8989      | 56.3337         | 103.575       | 6     |
+| 0.9503     | 1.0190          | 59.2327      | 35.7054      | 55.6769      | 56.0504         | 97.95         | 7     |
+| 0.9099     | 0.9959          | 58.9992      | 34.9965      | 55.5582      | 55.8486         | 97.05         | 8     |
+| 0.8735     | 0.9776          | 58.9665      | 35.1024      | 55.6433      | 55.8640         | 100.195       | 9     |
+| 0.8405     | 0.9594          | 58.4345      | 34.4502      | 54.6634      | 54.9469         | 96.98         | 10    |
+
+
+### Framework versions
+
+- Transformers 4.17.0.dev0
+- TensorFlow 2.7.0
+- Datasets 1.18.4.dev0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-ar-en",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      62833
+    ]
+  ],
+  "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": 62833,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "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": 512,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 62833,
+  "scale_embedding": true,
+  "static_position_embeddings": true,
+  "transformers_version": "4.17.0.dev0",
+  "use_cache": true,
+  "vocab_size": 62834
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c19e1e49298b8af0992b7c32715333deddba68431ee4ef674ec1fdc03bc111e
+size 307854560