Training in progress, epoch 1
Browse files- .gitattributes +2 -0
- .gitignore +1 -0
- config.json +46 -0
- pytorch_model.bin +3 -0
- runs/Sep27_09-18-20_338561d404fd/1664270319.4013343/events.out.tfevents.1664270319.338561d404fd.67.1 +3 -0
- runs/Sep27_09-18-20_338561d404fd/events.out.tfevents.1664270319.338561d404fd.67.0 +3 -0
- source.spm +3 -0
- special_tokens_map.json +5 -0
- target.spm +3 -0
- tokenizer_config.json +15 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -30,3 +30,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
30 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
31 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
32 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
30 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
31 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
32 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
33 |
+
source.spm filter=lfs diff=lfs merge=lfs -text
|
34 |
+
target.spm filter=lfs diff=lfs merge=lfs -text
|
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Hoax0930/kyoto_marian_mod_2_0",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "swish",
|
5 |
+
"architectures": [
|
6 |
+
"MarianMTModel"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"bad_words_ids": [
|
10 |
+
[
|
11 |
+
65000
|
12 |
+
]
|
13 |
+
],
|
14 |
+
"bos_token_id": 0,
|
15 |
+
"classifier_dropout": 0.0,
|
16 |
+
"d_model": 512,
|
17 |
+
"decoder_attention_heads": 8,
|
18 |
+
"decoder_ffn_dim": 2048,
|
19 |
+
"decoder_layerdrop": 0.0,
|
20 |
+
"decoder_layers": 6,
|
21 |
+
"decoder_start_token_id": 65000,
|
22 |
+
"decoder_vocab_size": 65001,
|
23 |
+
"dropout": 0.1,
|
24 |
+
"encoder_attention_heads": 8,
|
25 |
+
"encoder_ffn_dim": 2048,
|
26 |
+
"encoder_layerdrop": 0.0,
|
27 |
+
"encoder_layers": 6,
|
28 |
+
"eos_token_id": 0,
|
29 |
+
"forced_eos_token_id": 0,
|
30 |
+
"init_std": 0.02,
|
31 |
+
"is_encoder_decoder": true,
|
32 |
+
"max_length": 512,
|
33 |
+
"max_position_embeddings": 512,
|
34 |
+
"model_type": "marian",
|
35 |
+
"normalize_embedding": false,
|
36 |
+
"num_beams": 6,
|
37 |
+
"num_hidden_layers": 6,
|
38 |
+
"pad_token_id": 65000,
|
39 |
+
"scale_embedding": true,
|
40 |
+
"share_encoder_decoder_embeddings": true,
|
41 |
+
"static_position_embeddings": true,
|
42 |
+
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.22.1",
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 65001
|
46 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3db05b1f6ab9687a2ab932f72e8a93b396fb8a347f9d4781605096277266f4b3
|
3 |
+
size 310020485
|
runs/Sep27_09-18-20_338561d404fd/1664270319.4013343/events.out.tfevents.1664270319.338561d404fd.67.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83d11ee816dca776b48fba4d688428dc06e79e7b8cbbfb4aaa9a1de1661e5356
|
3 |
+
size 5743
|
runs/Sep27_09-18-20_338561d404fd/events.out.tfevents.1664270319.338561d404fd.67.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e886c3217ef042fc01851137ad5a50fffc07265f1d6598e0c5ff48fd6298a89
|
3 |
+
size 5247
|
source.spm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3fd0f2a618eaf9d0216d869b5904af7af2db87d2c561745f4cc21e363be4a75
|
3 |
+
size 807923
|
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
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c157a6b3846478cfbf2b1e2f652e6b62b6f0e9c667fda108ba8bf0ff67d75317
|
3 |
+
size 834449
|
tokenizer_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "</s>",
|
3 |
+
"model_max_length": 512,
|
4 |
+
"name_or_path": "Helsinki-NLP/opus-tatoeba-en-ja",
|
5 |
+
"pad_token": "<pad>",
|
6 |
+
"return_tensors": "pt",
|
7 |
+
"separate_vocabs": false,
|
8 |
+
"source_lang": "eng",
|
9 |
+
"sp_model_kwargs": {},
|
10 |
+
"special_tokens_map_file": null,
|
11 |
+
"target_lang": "jpn",
|
12 |
+
"tokenizer_class": "MarianTokenizer",
|
13 |
+
"tokenizer_file": null,
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b331d1b52e0e575e5f949518903fd48941254c48a60aec7acbfe4ff87af68d6b
|
3 |
+
size 3503
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|