add model
Browse files- README.md +57 -0
- config.json +58 -0
- tf_model.h5 +3 -0
README.md
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_keras_callback
|
5 |
+
model-index:
|
6 |
+
- name: opus-mt-en-ar-finetunedSTEM-v5-en-to-ar
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
11 |
+
probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# opus-mt-en-ar-finetunedSTEM-v5-en-to-ar
|
14 |
+
|
15 |
+
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.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 0.0921
|
18 |
+
- Validation Loss: 8.1798
|
19 |
+
- Epoch: 4
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- 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}
|
39 |
+
- training_precision: float32
|
40 |
+
|
41 |
+
### Training results
|
42 |
+
|
43 |
+
| Train Loss | Validation Loss | Epoch |
|
44 |
+
|:----------:|:---------------:|:-----:|
|
45 |
+
| 0.1178 | 7.5286 | 0 |
|
46 |
+
| 0.1103 | 7.7336 | 1 |
|
47 |
+
| 0.1028 | 7.6719 | 2 |
|
48 |
+
| 0.0976 | 8.1806 | 3 |
|
49 |
+
| 0.0921 | 8.1798 | 4 |
|
50 |
+
|
51 |
+
|
52 |
+
### Framework versions
|
53 |
+
|
54 |
+
- Transformers 4.17.0.dev0
|
55 |
+
- TensorFlow 2.7.0
|
56 |
+
- Datasets 1.18.4.dev0
|
57 |
+
- Tokenizers 0.10.3
|
config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Helsinki-NLP/opus-mt-en-ar",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "swish",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"MarianMTModel"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"bad_words_ids": [
|
12 |
+
[
|
13 |
+
62801
|
14 |
+
]
|
15 |
+
],
|
16 |
+
"bos_token_id": 0,
|
17 |
+
"classif_dropout": 0.0,
|
18 |
+
"classifier_dropout": 0.0,
|
19 |
+
"d_model": 512,
|
20 |
+
"decoder_attention_heads": 8,
|
21 |
+
"decoder_ffn_dim": 2048,
|
22 |
+
"decoder_layerdrop": 0.0,
|
23 |
+
"decoder_layers": 6,
|
24 |
+
"decoder_start_token_id": 62801,
|
25 |
+
"dropout": 0.1,
|
26 |
+
"encoder_attention_heads": 8,
|
27 |
+
"encoder_ffn_dim": 2048,
|
28 |
+
"encoder_layerdrop": 0.0,
|
29 |
+
"encoder_layers": 6,
|
30 |
+
"eos_token_id": 0,
|
31 |
+
"extra_pos_embeddings": 62802,
|
32 |
+
"forced_eos_token_id": 0,
|
33 |
+
"id2label": {
|
34 |
+
"0": "LABEL_0",
|
35 |
+
"1": "LABEL_1",
|
36 |
+
"2": "LABEL_2"
|
37 |
+
},
|
38 |
+
"init_std": 0.02,
|
39 |
+
"is_encoder_decoder": true,
|
40 |
+
"label2id": {
|
41 |
+
"LABEL_0": 0,
|
42 |
+
"LABEL_1": 1,
|
43 |
+
"LABEL_2": 2
|
44 |
+
},
|
45 |
+
"max_length": 512,
|
46 |
+
"max_position_embeddings": 512,
|
47 |
+
"model_type": "marian",
|
48 |
+
"normalize_before": false,
|
49 |
+
"normalize_embedding": false,
|
50 |
+
"num_beams": 4,
|
51 |
+
"num_hidden_layers": 6,
|
52 |
+
"pad_token_id": 62801,
|
53 |
+
"scale_embedding": true,
|
54 |
+
"static_position_embeddings": true,
|
55 |
+
"transformers_version": "4.17.0.dev0",
|
56 |
+
"use_cache": true,
|
57 |
+
"vocab_size": 62802
|
58 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8325d07b49a20c98ec3c9ed1cf3d4c258a9526d24e14cdfd47522fafa6aa407f
|
3 |
+
size 307788896
|