tatiana-merz
commited on
Commit
•
f903855
1
Parent(s):
6295b3c
End of training
Browse files- .gitignore +1 -0
- config.json +37 -0
- generation_config.json +10 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Jun29_15-10-40_3a5fd2ebcb1b/events.out.tfevents.1688051453.3a5fd2ebcb1b.8726.0 +3 -0
- runs/Jun29_15-14-46_3a5fd2ebcb1b/events.out.tfevents.1688051695.3a5fd2ebcb1b.8726.1 +3 -0
- special_tokens_map.json +20 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/m2m100_418M",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "relu",
|
5 |
+
"architectures": [
|
6 |
+
"M2M100ForConditionalGeneration"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"d_model": 1024,
|
11 |
+
"decoder_attention_heads": 16,
|
12 |
+
"decoder_ffn_dim": 4096,
|
13 |
+
"decoder_layerdrop": 0.05,
|
14 |
+
"decoder_layers": 12,
|
15 |
+
"decoder_start_token_id": 2,
|
16 |
+
"dropout": 0.1,
|
17 |
+
"early_stopping": true,
|
18 |
+
"encoder_attention_heads": 16,
|
19 |
+
"encoder_ffn_dim": 4096,
|
20 |
+
"encoder_layerdrop": 0.05,
|
21 |
+
"encoder_layers": 12,
|
22 |
+
"eos_token_id": 2,
|
23 |
+
"gradient_checkpointing": false,
|
24 |
+
"init_std": 0.02,
|
25 |
+
"is_encoder_decoder": true,
|
26 |
+
"max_length": 200,
|
27 |
+
"max_position_embeddings": 1024,
|
28 |
+
"model_type": "m2m_100",
|
29 |
+
"num_beams": 5,
|
30 |
+
"num_hidden_layers": 12,
|
31 |
+
"pad_token_id": 1,
|
32 |
+
"scale_embedding": true,
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.30.2",
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 128112
|
37 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 0,
|
3 |
+
"decoder_start_token_id": 2,
|
4 |
+
"early_stopping": true,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"max_length": 200,
|
7 |
+
"num_beams": 5,
|
8 |
+
"pad_token_id": 1,
|
9 |
+
"transformers_version": "4.30.2"
|
10 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87f9332a3e45d9f4d7d744439ee6d2aba4a51a0b939911a4f4f22d5cc3cdc96c
|
3 |
+
size 1944201353
|
runs/Jun29_15-10-40_3a5fd2ebcb1b/events.out.tfevents.1688051453.3a5fd2ebcb1b.8726.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:955b0ce44aa9de7b1b08af3a0c333582d8308b3338946340926327a996492fb6
|
3 |
+
size 5185
|
runs/Jun29_15-14-46_3a5fd2ebcb1b/events.out.tfevents.1688051695.3a5fd2ebcb1b.8726.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc2508c20c632310e91d2f02c09e2c988da1533d8819cdba582edb12ae1e4a26
|
3 |
+
size 8494
|
special_tokens_map.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<special0>",
|
4 |
+
"<special1>",
|
5 |
+
"<special2>",
|
6 |
+
"<special3>",
|
7 |
+
"<special4>",
|
8 |
+
"<special5>",
|
9 |
+
"<special6>",
|
10 |
+
"<special7>",
|
11 |
+
"<special8>",
|
12 |
+
"<special9>"
|
13 |
+
],
|
14 |
+
"bos_token": "<s>",
|
15 |
+
"cls_token": "</s>",
|
16 |
+
"mask_token": "<special1>",
|
17 |
+
"pad_token": "<pad>",
|
18 |
+
"sep_token": "</s>",
|
19 |
+
"unk_token": "<unk>"
|
20 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<special0>",
|
4 |
+
"<special1>",
|
5 |
+
"<special2>",
|
6 |
+
"<special3>",
|
7 |
+
"<special4>",
|
8 |
+
"<special5>",
|
9 |
+
"<special6>",
|
10 |
+
"<special7>",
|
11 |
+
"<special8>",
|
12 |
+
"<special9>"
|
13 |
+
],
|
14 |
+
"bos_token": "<s>",
|
15 |
+
"clean_up_tokenization_spaces": true,
|
16 |
+
"cls_token": "</s>",
|
17 |
+
"do_lowercase_and_remove_accent": true,
|
18 |
+
"id2lang": {
|
19 |
+
"0": "ar",
|
20 |
+
"1": "bg",
|
21 |
+
"10": "th",
|
22 |
+
"11": "tr",
|
23 |
+
"12": "ur",
|
24 |
+
"13": "vi",
|
25 |
+
"14": "zh",
|
26 |
+
"2": "de",
|
27 |
+
"3": "el",
|
28 |
+
"4": "en",
|
29 |
+
"5": "es",
|
30 |
+
"6": "fr",
|
31 |
+
"7": "hi",
|
32 |
+
"8": "ru",
|
33 |
+
"9": "sw"
|
34 |
+
},
|
35 |
+
"lang2id": {
|
36 |
+
"ar": 0,
|
37 |
+
"bg": 1,
|
38 |
+
"de": 2,
|
39 |
+
"el": 3,
|
40 |
+
"en": 4,
|
41 |
+
"es": 5,
|
42 |
+
"fr": 6,
|
43 |
+
"hi": 7,
|
44 |
+
"ru": 8,
|
45 |
+
"sw": 9,
|
46 |
+
"th": 10,
|
47 |
+
"tr": 11,
|
48 |
+
"ur": 12,
|
49 |
+
"vi": 13,
|
50 |
+
"zh": 14
|
51 |
+
},
|
52 |
+
"mask_token": "<special1>",
|
53 |
+
"model_max_length": 512,
|
54 |
+
"pad_token": "<pad>",
|
55 |
+
"sep_token": "</s>",
|
56 |
+
"tokenizer_class": "XLMTokenizer",
|
57 |
+
"unk_token": "<unk>"
|
58 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29f4d74d4938e2d88cb67433a47c55ecc4e076f435997d7b03ddaa267cd0a8c2
|
3 |
+
size 4091
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|