Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +34 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +20 -0
- tokenizer_config.json +25 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "uclanlp/plbart-base",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"architectures": [
|
6 |
+
"PLBartForConditionalGeneration"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"classifier_dropout": 0.0,
|
11 |
+
"d_model": 768,
|
12 |
+
"decoder_attention_heads": 12,
|
13 |
+
"decoder_ffn_dim": 3072,
|
14 |
+
"decoder_layerdrop": 0.0,
|
15 |
+
"decoder_layers": 6,
|
16 |
+
"dropout": 0.1,
|
17 |
+
"encoder_attention_heads": 12,
|
18 |
+
"encoder_ffn_dim": 3072,
|
19 |
+
"encoder_layerdrop": 0.0,
|
20 |
+
"encoder_layers": 6,
|
21 |
+
"eos_token_id": 2,
|
22 |
+
"forced_eos_token_id": 2,
|
23 |
+
"init_std": 0.02,
|
24 |
+
"is_encoder_decoder": true,
|
25 |
+
"max_position_embeddings": 1024,
|
26 |
+
"model_type": "plbart",
|
27 |
+
"num_hidden_layers": 6,
|
28 |
+
"pad_token_id": 1,
|
29 |
+
"scale_embedding": true,
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.30.2",
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 50005
|
34 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c35887c1b384b12fcfa586d2b93c9ae23d40c585a1898910f959732a5fed70f
|
3 |
+
size 557171485
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f72f5d040a176945623a255484d24066f8c0da89a294359154e226efbe494b80
|
3 |
+
size 985833
|
special_tokens_map.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"__java__",
|
4 |
+
"__python__",
|
5 |
+
"__en_XX__"
|
6 |
+
],
|
7 |
+
"bos_token": "<s>",
|
8 |
+
"cls_token": "<s>",
|
9 |
+
"eos_token": "</s>",
|
10 |
+
"mask_token": {
|
11 |
+
"content": "<mask>",
|
12 |
+
"lstrip": true,
|
13 |
+
"normalized": true,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
},
|
17 |
+
"pad_token": "<pad>",
|
18 |
+
"sep_token": "</s>",
|
19 |
+
"unk_token": "<unk>"
|
20 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": null,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"cls_token": "<s>",
|
6 |
+
"eos_token": "</s>",
|
7 |
+
"language_codes": "base",
|
8 |
+
"mask_token": {
|
9 |
+
"__type": "AddedToken",
|
10 |
+
"content": "<mask>",
|
11 |
+
"lstrip": true,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"model_max_length": 1024,
|
17 |
+
"pad_token": "<pad>",
|
18 |
+
"return_tensors": "pt",
|
19 |
+
"sep_token": "</s>",
|
20 |
+
"sp_model_kwargs": {},
|
21 |
+
"src_lang": null,
|
22 |
+
"tgt_lang": null,
|
23 |
+
"tokenizer_class": "PLBartTokenizer",
|
24 |
+
"unk_token": "<unk>"
|
25 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ac0e209c5fd26ed794437674c3855045ce772f4019e0d95d3d14343ff3f916c
|
3 |
+
size 4091
|