Zeref02210217-cst commited on
Commit
4e84240
·
verified ·
1 Parent(s): 824f284

Training in progress, step 500

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ source.spm filter=lfs diff=lfs merge=lfs -text
37
+ target.spm filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-tc-bible-big-mul-mul",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "MarianMTModel"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 0,
10
+ "classifier_dropout": 0.0,
11
+ "d_model": 1024,
12
+ "decoder_attention_heads": 16,
13
+ "decoder_ffn_dim": 4096,
14
+ "decoder_layerdrop": 0.0,
15
+ "decoder_layers": 6,
16
+ "decoder_start_token_id": 69666,
17
+ "decoder_vocab_size": 69667,
18
+ "dropout": 0.1,
19
+ "encoder_attention_heads": 16,
20
+ "encoder_ffn_dim": 4096,
21
+ "encoder_layerdrop": 0.0,
22
+ "encoder_layers": 6,
23
+ "eos_token_id": 524,
24
+ "forced_eos_token_id": null,
25
+ "init_std": 0.02,
26
+ "is_encoder_decoder": true,
27
+ "max_length": null,
28
+ "max_position_embeddings": 1024,
29
+ "model_type": "marian",
30
+ "normalize_embedding": false,
31
+ "num_beams": null,
32
+ "num_hidden_layers": 6,
33
+ "pad_token_id": 69666,
34
+ "scale_embedding": true,
35
+ "share_encoder_decoder_embeddings": true,
36
+ "static_position_embeddings": true,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.46.3",
39
+ "use_cache": true,
40
+ "vocab_size": 69667
41
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5627b7a6338f332f0198f61445a79fdaccf87e80e265f7b277f99b03adef5f62
3
+ size 991093820
source.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fcc8ca830e320086a44a4e9a1e611e1de4ac6e229fdd8fde8aaf5651c6fbdec
3
+ size 1315532
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 sha256:4fcc8ca830e320086a44a4e9a1e611e1de4ac6e229fdd8fde8aaf5651c6fbdec
3
+ size 1315532
tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "524": {
4
+ "content": "</s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "783": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "69666": {
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
+ "model_max_length": 512,
31
+ "pad_token": "<pad>",
32
+ "separate_vocabs": false,
33
+ "source_lang": "mul",
34
+ "sp_model_kwargs": {},
35
+ "target_lang": "mul",
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:e9e8c6973af39d2bac83ed769da9495e9ff23017fb94a8440c4aa4db96c227bd
3
+ size 5432
vocab.json ADDED
The diff for this file is too large to render. See raw diff