ncduy commited on
Commit
b16ae62
1 Parent(s): 0c0686a

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-en-vi",
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
+ 53684
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": 53684,
25
+ "dropout": 0.1,
26
+ "encoder_attention_heads": 8,
27
+ "encoder_ffn_dim": 2048,
28
+ "encoder_layerdrop": 0.0,
29
+ "encoder_layers": 6,
30
+ "eos_token_id": 0,
31
+ "extra_pos_embeddings": 53685,
32
+ "forced_eos_token_id": 0,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1",
36
+ "2": "LABEL_2"
37
+ },
38
+ "init_std": 0.02,
39
+ "is_encoder_decoder": true,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1,
43
+ "LABEL_2": 2
44
+ },
45
+ "max_length": 512,
46
+ "max_position_embeddings": 512,
47
+ "model_type": "marian",
48
+ "normalize_before": false,
49
+ "normalize_embedding": false,
50
+ "num_beams": 4,
51
+ "num_hidden_layers": 6,
52
+ "pad_token_id": 53684,
53
+ "scale_embedding": true,
54
+ "static_position_embeddings": true,
55
+ "torch_dtype": "float32",
56
+ "transformers_version": "4.15.0",
57
+ "use_cache": true,
58
+ "vocab_size": 53685
59
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce0131c3196e31594834689b5a262e2190940419852cf0255b37971f7e019ccb
3
+ size 286809989
source.spm ADDED
Binary file (809 kB). View file
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
target.spm ADDED
Binary file (756 kB). View file
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"source_lang": "eng", "target_lang": "vie", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "Helsinki-NLP/opus-mt-en-vi", "tokenizer_class": "MarianTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4fe053707f09abfb057b1bc4ede85c7900c7f921e4be6fe8ae37a5a5060e626
3
+ size 3119
vocab.json ADDED
The diff for this file is too large to render. See raw diff