Conrad747 commited on
Commit
97cfc0a
1 Parent(s): 5569281

End of training

Browse files
.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 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "AI-Lab-Makerere/lg_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
+ 64171
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": 64171,
25
+ "decoder_vocab_size": 64172,
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": 64172,
33
+ "forced_eos_token_id": 0,
34
+ "gradient_checkpointing": false,
35
+ "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "max_length": 512,
38
+ "max_position_embeddings": 512,
39
+ "model_type": "marian",
40
+ "normalize_before": false,
41
+ "normalize_embedding": false,
42
+ "num_beams": 6,
43
+ "num_hidden_layers": 6,
44
+ "pad_token_id": 64171,
45
+ "scale_embedding": true,
46
+ "share_encoder_decoder_embeddings": true,
47
+ "static_position_embeddings": true,
48
+ "torch_dtype": "float32",
49
+ "transformers_version": "4.22.2",
50
+ "use_cache": true,
51
+ "vocab_size": 64172
52
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b29690ba9e7c961a264bf4d74844f4621fbee1ae2be3f1620b0c6f7797d61eb
3
+ size 308319365
source.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4a99ea3602b29fbf901ade8b93a45efa3d7c64eab8fc5fa812383efa327a87d
3
+ size 706917
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:c6dce5fa58fcd7dde9e81e279b8c075bf42ee558278f73d6fb48e342029d7f19
3
+ size 791194
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "model_max_length": 512,
4
+ "name_or_path": "AI-Lab-Makerere/lg_en",
5
+ "pad_token": "<pad>",
6
+ "separate_vocabs": false,
7
+ "source_lang": "mul",
8
+ "sp_model_kwargs": {},
9
+ "special_tokens_map_file": null,
10
+ "target_lang": "eng",
11
+ "tokenizer_class": "MarianTokenizer",
12
+ "tokenizer_file": null,
13
+ "unk_token": "<unk>"
14
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f08717700e7b07ce50bc8fae46a74929040d4154d857e996b6e474e4751fc91
3
+ size 3503
vocab.json ADDED
The diff for this file is too large to render. See raw diff