Training in progress, step 500
Browse files- config.json +46 -0
- model.safetensors +3 -0
- runs/Nov17_13-59-42_DESKTOP-F8GLMQP/events.out.tfevents.1731841229.DESKTOP-F8GLMQP.21844.0 +3 -0
- source.spm +0 -0
- special_tokens_map.json +23 -0
- target.spm +0 -0
- tokenizer_config.json +38 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ilhami/AcademicTranslation2024_v2-tr-to-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": "4.37.2",
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 57060
|
46 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4b1a11b81293c03bd45827ec4c1dbc4a1a68e8deef89ab79e869e3e9c5f6f50
|
3 |
+
size 939405120
|
runs/Nov17_13-59-42_DESKTOP-F8GLMQP/events.out.tfevents.1731841229.DESKTOP-F8GLMQP.21844.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de676ba8d58d934411b705aa5f7e549b90efa582260eb5d58b4ca62ec48df737
|
3 |
+
size 5113
|
source.spm
ADDED
Binary file (833 kB). View file
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": {
|
3 |
+
"content": "</s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"pad_token": {
|
10 |
+
"content": "<pad>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
target.spm
ADDED
Binary file (797 kB). View file
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"separate_vocabs": false,
|
33 |
+
"source_lang": "tr",
|
34 |
+
"sp_model_kwargs": {},
|
35 |
+
"target_lang": "en",
|
36 |
+
"tokenizer_class": "MarianTokenizer",
|
37 |
+
"unk_token": "<unk>"
|
38 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0688ec99dfa32bb5832a4bd751ecd197e1c7523e3f04a3b2c830ebd7398adc08
|
3 |
+
size 4411
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|