MaryaAI commited on
Commit
bc61a52
1 Parent(s): a494ec4
.gitignore ADDED
@@ -0,0 +1 @@
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - opus_wikipedia
6
+ model-index:
7
+ - name: opus-mt-ar-en-finetuned-ar-to-en
8
+ results:
9
+ - task:
10
+ name: Sequence-to-sequence Language Modeling
11
+ type: text2text-generation
12
+ dataset:
13
+ name: opus_wikipedia
14
+ type: opus_wikipedia
15
+ args: ar-en
16
+ ---
17
+
18
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
19
+ should probably proofread and complete it, then remove this comment. -->
20
+
21
+ # opus-mt-ar-en-finetuned-ar-to-en
22
+
23
+ This model is a fine-tuned version of [Helsinki-NLP/opus-mt-ar-en](https://huggingface.co/Helsinki-NLP/opus-mt-ar-en) on the opus_wikipedia dataset.
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 2e-05
43
+ - train_batch_size: 16
44
+ - eval_batch_size: 16
45
+ - seed: 42
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 1
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Framework versions
52
+
53
+ - Transformers 4.10.0
54
+ - Pytorch 1.9.0+cu102
55
+ - Datasets 1.11.0
56
+ - Tokenizers 0.10.3
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-ar-en",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "swish",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": false,
8
+ "architectures": [
9
+ "MarianMTModel"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bad_words_ids": [
13
+ [
14
+ 62833
15
+ ]
16
+ ],
17
+ "bos_token_id": 0,
18
+ "classif_dropout": 0.0,
19
+ "classifier_dropout": 0.0,
20
+ "d_model": 512,
21
+ "decoder_attention_heads": 8,
22
+ "decoder_ffn_dim": 2048,
23
+ "decoder_layerdrop": 0.0,
24
+ "decoder_layers": 6,
25
+ "decoder_start_token_id": 62833,
26
+ "dropout": 0.1,
27
+ "encoder_attention_heads": 8,
28
+ "encoder_ffn_dim": 2048,
29
+ "encoder_layerdrop": 0.0,
30
+ "encoder_layers": 6,
31
+ "eos_token_id": 0,
32
+ "forced_eos_token_id": 0,
33
+ "gradient_checkpointing": false,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1",
37
+ "2": "LABEL_2"
38
+ },
39
+ "init_std": 0.02,
40
+ "is_encoder_decoder": true,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1,
44
+ "LABEL_2": 2
45
+ },
46
+ "max_length": 512,
47
+ "max_position_embeddings": 512,
48
+ "model_type": "marian",
49
+ "normalize_before": false,
50
+ "normalize_embedding": false,
51
+ "num_beams": 4,
52
+ "num_hidden_layers": 6,
53
+ "pad_token_id": 62833,
54
+ "scale_embedding": true,
55
+ "static_position_embeddings": true,
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.10.0",
58
+ "use_cache": true,
59
+ "vocab_size": 62834
60
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:936dcb7d4c2eb0c6c495be3c4950b4fe7647673c821f536bf3785151dde61b8f
3
+ size 305573829
runs/Sep07_04-35-31_df95249aecf5/1630989499.1874473/events.out.tfevents.1630989499.df95249aecf5.77.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09dadd5a2dc0fefb1e6d3662cdf9aa9cc4551ce466ddf6869904cb7a831b5d3f
3
+ size 4452
runs/Sep07_04-35-31_df95249aecf5/events.out.tfevents.1630989499.df95249aecf5.77.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd8163ccf54e1162af2b97b2c37f34e6cd18701e88eff964551744280ab85344
3
+ size 6621
source.spm ADDED
Binary file (917 kB). View file
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
target.spm ADDED
Binary file (802 kB). View file
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"source_lang": "ar", "target_lang": "en", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "Helsinki-NLP/opus-mt-ar-en", "tokenizer_class": "MarianTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7e0e2dd97408b9ef7d4da52cf4b551049848990f858ddc33c5a23ede7567024
3
+ size 2799
vocab.json ADDED
The diff for this file is too large to render. See raw diff