Commit
•
831b887
1
Parent(s):
16a364f
ihebaker10/spark-name-ko-to-en
Browse files- README.md +57 -65
- config.json +61 -61
- generation_config.json +16 -16
- model.safetensors +1 -1
- special_tokens_map.json +23 -5
- tokenizer_config.json +38 -38
- training_args.bin +2 -2
- vocab.json +0 -0
README.md
CHANGED
@@ -1,65 +1,57 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
-
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
|
58 |
-
|
59 |
-
|
60 |
-
### Framework versions
|
61 |
-
|
62 |
-
- Transformers 4.41.0
|
63 |
-
- Pytorch 2.3.0+cu121
|
64 |
-
- Datasets 2.19.1
|
65 |
-
- Tokenizers 0.19.1
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: spark-name-ko-to-en
|
6 |
+
results: []
|
7 |
+
---
|
8 |
+
|
9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
10 |
+
should probably proofread and complete it, then remove this comment. -->
|
11 |
+
|
12 |
+
# spark-name-ko-to-en
|
13 |
+
|
14 |
+
This model was trained from scratch on an unknown dataset.
|
15 |
+
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 4.0402
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 2e-05
|
36 |
+
- train_batch_size: 16
|
37 |
+
- eval_batch_size: 16
|
38 |
+
- seed: 42
|
39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
+
- lr_scheduler_type: linear
|
41 |
+
- num_epochs: 3
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
46 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
47 |
+
| No log | 1.0 | 1 | 4.8571 |
|
48 |
+
| No log | 2.0 | 2 | 4.2938 |
|
49 |
+
| No log | 3.0 | 3 | 4.0402 |
|
50 |
+
|
51 |
+
|
52 |
+
### Framework versions
|
53 |
+
|
54 |
+
- Transformers 4.41.1
|
55 |
+
- Pytorch 2.0.1+cpu
|
56 |
+
- Datasets 2.19.1
|
57 |
+
- Tokenizers 0.19.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
CHANGED
@@ -1,61 +1,61 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "
|
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 |
-
65000
|
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": 65000,
|
25 |
-
"decoder_vocab_size": 65001,
|
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 |
-
"extra_pos_embeddings": 65001,
|
33 |
-
"forced_eos_token_id": 0,
|
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": 6,
|
52 |
-
"num_hidden_layers": 6,
|
53 |
-
"pad_token_id": 65000,
|
54 |
-
"scale_embedding": true,
|
55 |
-
"share_encoder_decoder_embeddings": true,
|
56 |
-
"static_position_embeddings": true,
|
57 |
-
"torch_dtype": "float32",
|
58 |
-
"transformers_version": "4.41.
|
59 |
-
"use_cache": true,
|
60 |
-
"vocab_size": 65001
|
61 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ihebaker10/spark-name-ko-to-en",
|
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 |
+
65000
|
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": 65000,
|
25 |
+
"decoder_vocab_size": 65001,
|
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 |
+
"extra_pos_embeddings": 65001,
|
33 |
+
"forced_eos_token_id": 0,
|
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": 6,
|
52 |
+
"num_hidden_layers": 6,
|
53 |
+
"pad_token_id": 65000,
|
54 |
+
"scale_embedding": true,
|
55 |
+
"share_encoder_decoder_embeddings": true,
|
56 |
+
"static_position_embeddings": true,
|
57 |
+
"torch_dtype": "float32",
|
58 |
+
"transformers_version": "4.41.1",
|
59 |
+
"use_cache": true,
|
60 |
+
"vocab_size": 65001
|
61 |
+
}
|
generation_config.json
CHANGED
@@ -1,16 +1,16 @@
|
|
1 |
-
{
|
2 |
-
"bad_words_ids": [
|
3 |
-
[
|
4 |
-
65000
|
5 |
-
]
|
6 |
-
],
|
7 |
-
"bos_token_id": 0,
|
8 |
-
"decoder_start_token_id": 65000,
|
9 |
-
"eos_token_id": 0,
|
10 |
-
"forced_eos_token_id": 0,
|
11 |
-
"max_length": 512,
|
12 |
-
"num_beams": 6,
|
13 |
-
"pad_token_id": 65000,
|
14 |
-
"renormalize_logits": true,
|
15 |
-
"transformers_version": "4.41.
|
16 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"bad_words_ids": [
|
3 |
+
[
|
4 |
+
65000
|
5 |
+
]
|
6 |
+
],
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"decoder_start_token_id": 65000,
|
9 |
+
"eos_token_id": 0,
|
10 |
+
"forced_eos_token_id": 0,
|
11 |
+
"max_length": 512,
|
12 |
+
"num_beams": 6,
|
13 |
+
"pad_token_id": 65000,
|
14 |
+
"renormalize_logits": true,
|
15 |
+
"transformers_version": "4.41.1"
|
16 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 309965092
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ce90a92a243e4a15df22fb16875efc4b68070d462a7f86ba81b025b79dd579e
|
3 |
size 309965092
|
special_tokens_map.json
CHANGED
@@ -1,5 +1,23 @@
|
|
1 |
-
{
|
2 |
-
"eos_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
}
|
tokenizer_config.json
CHANGED
@@ -1,38 +1,38 @@
|
|
1 |
-
{
|
2 |
-
"added_tokens_decoder": {
|
3 |
-
"0": {
|
4 |
-
"content": "</s>",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": false,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false,
|
9 |
-
"special": true
|
10 |
-
},
|
11 |
-
"1": {
|
12 |
-
"content": "<unk>",
|
13 |
-
"lstrip": false,
|
14 |
-
"normalized": false,
|
15 |
-
"rstrip": false,
|
16 |
-
"single_word": false,
|
17 |
-
"special": true
|
18 |
-
},
|
19 |
-
"65000": {
|
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": "kor",
|
34 |
-
"sp_model_kwargs": {},
|
35 |
-
"target_lang": "eng",
|
36 |
-
"tokenizer_class": "MarianTokenizer",
|
37 |
-
"unk_token": "<unk>"
|
38 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "</s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<unk>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"65000": {
|
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": "kor",
|
34 |
+
"sp_model_kwargs": {},
|
35 |
+
"target_lang": "eng",
|
36 |
+
"tokenizer_class": "MarianTokenizer",
|
37 |
+
"unk_token": "<unk>"
|
38 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:896545a35bd4b7a9bcdf4b0c8f808ecb974a2c3303f98efa77599e41c2437531
|
3 |
+
size 4795
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|