basakdemirok commited on
Commit
ffdcd7b
1 Parent(s): b53be10

Training complete

Browse files
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-4.0
3
+ base_model: Helsinki-NLP/opus-mt-tc-big-tr-en
4
+ tags:
5
+ - translation
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: nmt_v0123_head10k
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # nmt_v0123_head10k
16
+
17
+ This model is a fine-tuned version of [Helsinki-NLP/opus-mt-tc-big-tr-en](https://huggingface.co/Helsinki-NLP/opus-mt-tc-big-tr-en) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - eval_loss: 1.4075
20
+ - eval_bleu: 29.7605
21
+ - eval_runtime: 575.4386
22
+ - eval_samples_per_second: 5.226
23
+ - eval_steps_per_second: 2.614
24
+ - step: 0
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 2e-05
44
+ - train_batch_size: 2
45
+ - eval_batch_size: 2
46
+ - seed: 42
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - num_epochs: 3
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Framework versions
53
+
54
+ - Transformers 4.41.2
55
+ - Pytorch 2.3.0+cu118
56
+ - Datasets 2.4.0
57
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-tc-big-tr-en",
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": "4.41.2",
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": "4.41.2"
16
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:359068cb19e13ee0ceba05cea425467bc6fc86f394cae37ef631d3e137b48d3c
3
+ size 939405120
runs/Jun02_22-22-03_tm211pc/events.out.tfevents.1717356745.tm211pc.708150.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f022aba3e8ab28c41a87082efaa60d64edecbaa5f5860b3a6ed184a89d2cc2d6
3
+ size 596
source.spm ADDED
Binary file (833 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 (797 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": "tr",
35
+ "sp_model_kwargs": {},
36
+ "target_lang": "en",
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 sha256:6a19eb209ff92c69ae5d3f757bb426687df7e826732b27c732dc0831998c8752
3
+ size 5304
vocab.json ADDED
The diff for this file is too large to render. See raw diff