ckartal commited on
Commit
74d946d
1 Parent(s): 06fed42

Training in progress, epoch 1

Browse files
README.md ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-4.0
3
+ base_model: Helsinki-NLP/opus-mt-tc-big-en-tr
4
+ tags:
5
+ - translation
6
+ - generated_from_trainer
7
+ datasets:
8
+ - tatoeba
9
+ metrics:
10
+ - bleu
11
+ model-index:
12
+ - name: opus-mt-tc-big-en-tr
13
+ results:
14
+ - task:
15
+ name: Sequence-to-sequence Language Modeling
16
+ type: text2text-generation
17
+ dataset:
18
+ name: tatoeba
19
+ type: tatoeba
20
+ config: en-tr
21
+ split: train
22
+ args: en-tr
23
+ metrics:
24
+ - name: Bleu
25
+ type: bleu
26
+ value: 54.405510741899164
27
+ ---
28
+
29
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
30
+ should probably proofread and complete it, then remove this comment. -->
31
+
32
+ # opus-mt-tc-big-en-tr
33
+
34
+ This model is a fine-tuned version of [Helsinki-NLP/opus-mt-tc-big-en-tr](https://huggingface.co/Helsinki-NLP/opus-mt-tc-big-en-tr) on the tatoeba dataset.
35
+ It achieves the following results on the evaluation set:
36
+ - Loss: 0.5573
37
+ - Bleu: 54.4055
38
+
39
+ ## Model description
40
+
41
+ More information needed
42
+
43
+ ## Intended uses & limitations
44
+
45
+ More information needed
46
+
47
+ ## Training and evaluation data
48
+
49
+ More information needed
50
+
51
+ ## Training procedure
52
+
53
+ ### Training hyperparameters
54
+
55
+ The following hyperparameters were used during training:
56
+ - learning_rate: 2e-05
57
+ - train_batch_size: 32
58
+ - eval_batch_size: 64
59
+ - seed: 42
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - num_epochs: 3
63
+
64
+ ### Training results
65
+
66
+
67
+
68
+ ### Framework versions
69
+
70
+ - Transformers 4.38.2
71
+ - Pytorch 2.2.1+cu121
72
+ - Datasets 2.18.0
73
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-tc-big-en-tr",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "MarianMTModel"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bad_words_ids": [
10
+ [
11
+ 57059
12
+ ]
13
+ ],
14
+ "bos_token_id": 0,
15
+ "classifier_dropout": 0.0,
16
+ "d_model": 1024,
17
+ "decoder_attention_heads": 16,
18
+ "decoder_ffn_dim": 4096,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 6,
21
+ "decoder_start_token_id": 57059,
22
+ "decoder_vocab_size": 57060,
23
+ "dropout": 0.1,
24
+ "encoder_attention_heads": 16,
25
+ "encoder_ffn_dim": 4096,
26
+ "encoder_layerdrop": 0.0,
27
+ "encoder_layers": 6,
28
+ "eos_token_id": 43741,
29
+ "forced_eos_token_id": 43741,
30
+ "init_std": 0.02,
31
+ "is_encoder_decoder": true,
32
+ "max_length": 512,
33
+ "max_position_embeddings": 1024,
34
+ "model_type": "marian",
35
+ "normalize_embedding": false,
36
+ "num_beams": 4,
37
+ "num_hidden_layers": 6,
38
+ "pad_token_id": 57059,
39
+ "scale_embedding": true,
40
+ "share_encoder_decoder_embeddings": true,
41
+ "static_position_embeddings": true,
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.38.2",
44
+ "use_cache": true,
45
+ "vocab_size": 57060
46
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 57059
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 57059,
9
+ "eos_token_id": 43741,
10
+ "forced_eos_token_id": 43741,
11
+ "max_length": 512,
12
+ "num_beams": 4,
13
+ "pad_token_id": 57059,
14
+ "renormalize_logits": true,
15
+ "transformers_version": "4.38.2"
16
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15f12709fcd158c4a5d85b4afbccd861cf99db69082b04992e147ea0d1bdd4b6
3
+ size 939405120
runs/Mar30_20-38-13_5cae252bde23/events.out.tfevents.1711831210.5cae252bde23.1389.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe88fcd974a9b7fa5436545a30709070b767995263d45d8eacf5c1d478213a97
3
+ size 5810
runs/Mar30_20-38-13_5cae252bde23/events.out.tfevents.1711833332.5cae252bde23.1389.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77baf753e4955fcbbc88a09e41a23b6463ba707b08bb35958b9303339f4225e3
3
+ size 401
runs/Mar30_21-16-42_5cae252bde23/events.out.tfevents.1711833603.5cae252bde23.1389.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d96acbc68572899e75585f8fc1e0d337eaec10b320c0020b4a9e5b7d3a16143
3
+ size 5810
runs/Mar30_21-16-42_5cae252bde23/events.out.tfevents.1711837307.5cae252bde23.1389.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d68f6e4a02f29d6bd0c7eab039037be2a9dc8a9fe8709393d9196e17f62e38b
3
+ size 401
runs/Mar30_22-26-03_5cae252bde23/events.out.tfevents.1711837656.5cae252bde23.1389.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db3844b6c83546a4d930e46d090498ea6c3e99e1336275502e4a7c248d2ed64c
3
+ size 5810
runs/Mar30_22-26-03_5cae252bde23/events.out.tfevents.1711839515.5cae252bde23.1389.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:090f0a2f4a7a8fcbb8d922a1f4e9f72d3dfd1489776cdb17fe34ab9e2c208158
3
+ size 401
runs/Mar30_23-19-56_5cae252bde23/events.out.tfevents.1711841011.5cae252bde23.1389.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed8eb6ed922ba0b60a247ff9359d5ac719b8ada7ae12606d99b7dd4acf181a63
3
+ size 5462
source.spm ADDED
Binary file (797 kB). View file
 
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
target.spm ADDED
Binary file (833 kB). View file
 
tokenizer_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "43741": {
4
+ "content": "</s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "52508": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "57059": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "clean_up_tokenization_spaces": true,
29
+ "eos_token": "</s>",
30
+ "model_max_length": 512,
31
+ "pad_token": "<pad>",
32
+ "return_tensors": "pt",
33
+ "separate_vocabs": false,
34
+ "source_lang": "en",
35
+ "sp_model_kwargs": {},
36
+ "target_lang": "tr",
37
+ "tokenizer_class": "MarianTokenizer",
38
+ "unk_token": "<unk>"
39
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97859b17d5b9b2d376dd2aeefa2b0b350adc607c0dd2d80b98bd5ebd8515d954
3
+ size 5048
vocab.json ADDED
The diff for this file is too large to render. See raw diff