Training in progress, step 69
Browse files- config.json +3 -9
- model.safetensors +3 -0
- tokenizer_config.json +28 -1
- training_args.bin +2 -2
config.json
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "Helsinki-NLP/opus-mt-ja-en",
|
3 |
"_num_labels": 3,
|
4 |
"activation_dropout": 0.0,
|
5 |
"activation_function": "swish",
|
@@ -9,11 +8,6 @@
|
|
9 |
"MarianMTModel"
|
10 |
],
|
11 |
"attention_dropout": 0.0,
|
12 |
-
"bad_words_ids": [
|
13 |
-
[
|
14 |
-
60715
|
15 |
-
]
|
16 |
-
],
|
17 |
"bos_token_id": 0,
|
18 |
"classif_dropout": 0.0,
|
19 |
"classifier_dropout": 0.0,
|
@@ -43,19 +37,19 @@
|
|
43 |
"LABEL_1": 1,
|
44 |
"LABEL_2": 2
|
45 |
},
|
46 |
-
"max_length":
|
47 |
"max_position_embeddings": 512,
|
48 |
"model_type": "marian",
|
49 |
"normalize_before": false,
|
50 |
"normalize_embedding": false,
|
51 |
-
"num_beams":
|
52 |
"num_hidden_layers": 6,
|
53 |
"pad_token_id": 60715,
|
54 |
"scale_embedding": true,
|
55 |
"share_encoder_decoder_embeddings": true,
|
56 |
"static_position_embeddings": true,
|
57 |
"torch_dtype": "float32",
|
58 |
-
"transformers_version": "4.
|
59 |
"use_cache": true,
|
60 |
"vocab_size": 60716
|
61 |
}
|
|
|
1 |
{
|
|
|
2 |
"_num_labels": 3,
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "swish",
|
|
|
8 |
"MarianMTModel"
|
9 |
],
|
10 |
"attention_dropout": 0.0,
|
|
|
|
|
|
|
|
|
|
|
11 |
"bos_token_id": 0,
|
12 |
"classif_dropout": 0.0,
|
13 |
"classifier_dropout": 0.0,
|
|
|
37 |
"LABEL_1": 1,
|
38 |
"LABEL_2": 2
|
39 |
},
|
40 |
+
"max_length": null,
|
41 |
"max_position_embeddings": 512,
|
42 |
"model_type": "marian",
|
43 |
"normalize_before": false,
|
44 |
"normalize_embedding": false,
|
45 |
+
"num_beams": null,
|
46 |
"num_hidden_layers": 6,
|
47 |
"pad_token_id": 60715,
|
48 |
"scale_embedding": true,
|
49 |
"share_encoder_decoder_embeddings": true,
|
50 |
"static_position_embeddings": true,
|
51 |
"torch_dtype": "float32",
|
52 |
+
"transformers_version": "4.51.3",
|
53 |
"use_cache": true,
|
54 |
"vocab_size": 60716
|
55 |
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15412e10ff3da1ec76baf6d36092fc79caf20623a38631667aad9dabee82589d
|
3 |
+
size 301172272
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,33 @@
|
|
1 |
{
|
2 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"eos_token": "</s>",
|
|
|
4 |
"model_max_length": 512,
|
5 |
"pad_token": "<pad>",
|
6 |
"separate_vocabs": false,
|
|
|
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 |
+
"60715": {
|
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": false,
|
29 |
"eos_token": "</s>",
|
30 |
+
"extra_special_tokens": {},
|
31 |
"model_max_length": 512,
|
32 |
"pad_token": "<pad>",
|
33 |
"separate_vocabs": false,
|
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 sha256:330966ff420af90e7d3105954d455e789fc4ec8fd964592c296f32c13c52e1f9
|
3 |
+
size 5496
|