Training in progress, step 500
Browse files- config.json +56 -0
- model.safetensors +3 -0
- source.spm +0 -0
- target.spm +0 -0
- tokenizer_config.json +3 -3
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "MubarakB/Helsinki_lg_inf_en",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "swish",
|
6 |
+
"add_bias_logits": false,
|
7 |
+
"add_final_layer_norm": false,
|
8 |
+
"architectures": [
|
9 |
+
"MarianMTModel"
|
10 |
+
],
|
11 |
+
"attention_dropout": 0.0,
|
12 |
+
"bos_token_id": 0,
|
13 |
+
"classif_dropout": 0.0,
|
14 |
+
"classifier_dropout": 0.0,
|
15 |
+
"d_model": 512,
|
16 |
+
"decoder_attention_heads": 8,
|
17 |
+
"decoder_ffn_dim": 2048,
|
18 |
+
"decoder_layerdrop": 0.0,
|
19 |
+
"decoder_layers": 6,
|
20 |
+
"decoder_start_token_id": 60446,
|
21 |
+
"decoder_vocab_size": 60447,
|
22 |
+
"dropout": 0.1,
|
23 |
+
"encoder_attention_heads": 8,
|
24 |
+
"encoder_ffn_dim": 2048,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 6,
|
27 |
+
"eos_token_id": 0,
|
28 |
+
"forced_eos_token_id": 0,
|
29 |
+
"id2label": {
|
30 |
+
"0": "LABEL_0",
|
31 |
+
"1": "LABEL_1",
|
32 |
+
"2": "LABEL_2"
|
33 |
+
},
|
34 |
+
"init_std": 0.02,
|
35 |
+
"is_encoder_decoder": true,
|
36 |
+
"label2id": {
|
37 |
+
"LABEL_0": 0,
|
38 |
+
"LABEL_1": 1,
|
39 |
+
"LABEL_2": 2
|
40 |
+
},
|
41 |
+
"max_length": null,
|
42 |
+
"max_position_embeddings": 512,
|
43 |
+
"model_type": "marian",
|
44 |
+
"normalize_before": false,
|
45 |
+
"normalize_embedding": false,
|
46 |
+
"num_beams": null,
|
47 |
+
"num_hidden_layers": 6,
|
48 |
+
"pad_token_id": 60446,
|
49 |
+
"scale_embedding": true,
|
50 |
+
"share_encoder_decoder_embeddings": true,
|
51 |
+
"static_position_embeddings": true,
|
52 |
+
"torch_dtype": "float32",
|
53 |
+
"transformers_version": "4.45.1",
|
54 |
+
"use_cache": true,
|
55 |
+
"vocab_size": 60447
|
56 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5cf780865dafdcf688cc825109cebc84bcf16b105897f8766c4862726960a2b
|
3 |
+
size 300620284
|
source.spm
CHANGED
Binary files a/source.spm and b/source.spm differ
|
|
target.spm
CHANGED
Binary files a/target.spm and b/target.spm differ
|
|
tokenizer_config.json
CHANGED
@@ -16,7 +16,7 @@
|
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
"content": "<pad>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
@@ -30,9 +30,9 @@
|
|
30 |
"model_max_length": 512,
|
31 |
"pad_token": "<pad>",
|
32 |
"separate_vocabs": false,
|
33 |
-
"source_lang": "
|
34 |
"sp_model_kwargs": {},
|
35 |
-
"target_lang": "
|
36 |
"tokenizer_class": "MarianTokenizer",
|
37 |
"unk_token": "<unk>"
|
38 |
}
|
|
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
+
"60446": {
|
20 |
"content": "<pad>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
|
|
30 |
"model_max_length": 512,
|
31 |
"pad_token": "<pad>",
|
32 |
"separate_vocabs": false,
|
33 |
+
"source_lang": "lg",
|
34 |
"sp_model_kwargs": {},
|
35 |
+
"target_lang": "en",
|
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:b1886968a32e7e762e9c4393128b9be5597f9f57cdbbbeb04f480bee148e7040
|
3 |
+
size 5432
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|