dokyoungkim
commited on
Commit
•
d680405
1
Parent(s):
506e2ce
Training in progress, epoch 1
Browse files- config.json +48 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Mar19_13-34-11_gpusvr021320/events.out.tfevents.1710825165.gpusvr021320.1810604.0 +3 -0
- runs/Mar19_14-15-45_gpusvr021320/events.out.tfevents.1710826517.gpusvr021320.1864146.0 +3 -0
- runs/Mar19_14-37-27_gpusvr021320/events.out.tfevents.1710826660.gpusvr021320.1886221.0 +3 -0
- special_tokens_map.json +6 -0
- tokenizer_config.json +48 -0
- training_args.bin +3 -0
- vocab-src.json +0 -0
- vocab-tgt.json +0 -0
config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wmt19-de-en",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "relu",
|
5 |
+
"architectures": [
|
6 |
+
"FSMTForConditionalGeneration"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"d_model": 1024,
|
11 |
+
"decoder": {
|
12 |
+
"bos_token_id": 2,
|
13 |
+
"model_type": "fsmt_decoder",
|
14 |
+
"vocab_size": 42024
|
15 |
+
},
|
16 |
+
"decoder_attention_heads": 16,
|
17 |
+
"decoder_ffn_dim": 4096,
|
18 |
+
"decoder_layerdrop": 0,
|
19 |
+
"decoder_layers": 6,
|
20 |
+
"decoder_start_token_id": 2,
|
21 |
+
"dropout": 0.2,
|
22 |
+
"encoder_attention_heads": 16,
|
23 |
+
"encoder_ffn_dim": 8192,
|
24 |
+
"encoder_layerdrop": 0,
|
25 |
+
"encoder_layers": 6,
|
26 |
+
"eos_token_id": 2,
|
27 |
+
"forced_eos_token_id": 2,
|
28 |
+
"init_std": 0.02,
|
29 |
+
"is_encoder_decoder": true,
|
30 |
+
"langs": [
|
31 |
+
"de",
|
32 |
+
"en"
|
33 |
+
],
|
34 |
+
"length_penalty": 1.1,
|
35 |
+
"max_length": 200,
|
36 |
+
"max_position_embeddings": 1024,
|
37 |
+
"model_type": "fsmt",
|
38 |
+
"num_beams": 5,
|
39 |
+
"num_hidden_layers": 6,
|
40 |
+
"pad_token_id": 1,
|
41 |
+
"scale_embedding": true,
|
42 |
+
"src_vocab_size": 42024,
|
43 |
+
"tgt_vocab_size": 42024,
|
44 |
+
"tie_word_embeddings": true,
|
45 |
+
"torch_dtype": "float32",
|
46 |
+
"transformers_version": "4.37.2",
|
47 |
+
"use_cache": true
|
48 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ca4cc32206a5f9b36a29fd54b5b995601c60323e4f87ae89c46eed97f147d98
|
3 |
+
size 1087419504
|
runs/Mar19_13-34-11_gpusvr021320/events.out.tfevents.1710825165.gpusvr021320.1810604.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d80ac86e42c4067249e14c34d695fcd3b7c10370eb1ed71656e274eda4cd43c
|
3 |
+
size 342
|
runs/Mar19_14-15-45_gpusvr021320/events.out.tfevents.1710826517.gpusvr021320.1864146.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c596e3ca571175189d14028ba1445baf4ddaaf4379f557ee8ef7be492f3b8cce
|
3 |
+
size 342
|
runs/Mar19_14-37-27_gpusvr021320/events.out.tfevents.1710826660.gpusvr021320.1886221.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8f7e9367d209b09eac39f17a737492c05cb07cc88f260510bb2e9e1bf57d7eb
|
3 |
+
size 8620
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"pad_token": "<pad>",
|
4 |
+
"sep_token": "</s>",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"bos_token": "<s>",
|
37 |
+
"clean_up_tokenization_spaces": true,
|
38 |
+
"do_lower_case": false,
|
39 |
+
"langs": [
|
40 |
+
"de",
|
41 |
+
"en"
|
42 |
+
],
|
43 |
+
"model_max_length": 1024,
|
44 |
+
"pad_token": "<pad>",
|
45 |
+
"sep_token": "</s>",
|
46 |
+
"tokenizer_class": "FSMTTokenizer",
|
47 |
+
"unk_token": "<unk>"
|
48 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:120db0c847a72b5ee08ae720f24b69d8407507a0e26aca7c4d22408d49fcb433
|
3 |
+
size 4475
|
vocab-src.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
vocab-tgt.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|