Model save
Browse files- README.md +6 -7
- config.json +25 -52
- generation_config.json +4 -3
- pytorch_model.bin +2 -2
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +13 -100
- tokenizer_config.json +17 -106
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,6 +1,5 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
base_model: t5-small
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
@@ -13,7 +12,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# folder
|
15 |
|
16 |
-
This model is a fine-tuned version of [
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -33,15 +32,15 @@ More information needed
|
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
- learning_rate: 5e-05
|
36 |
-
- train_batch_size:
|
37 |
-
- eval_batch_size:
|
38 |
- seed: 42
|
39 |
- gradient_accumulation_steps: 16
|
40 |
-
- total_train_batch_size:
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
- lr_scheduler_warmup_steps: 500
|
44 |
-
- num_epochs:
|
45 |
|
46 |
### Training results
|
47 |
|
|
|
1 |
---
|
2 |
+
base_model: uclanlp/plbart-base
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
model-index:
|
|
|
12 |
|
13 |
# folder
|
14 |
|
15 |
+
This model is a fine-tuned version of [uclanlp/plbart-base](https://huggingface.co/uclanlp/plbart-base) on an unknown dataset.
|
16 |
|
17 |
## Model description
|
18 |
|
|
|
32 |
|
33 |
The following hyperparameters were used during training:
|
34 |
- learning_rate: 5e-05
|
35 |
+
- train_batch_size: 8
|
36 |
+
- eval_batch_size: 8
|
37 |
- seed: 42
|
38 |
- gradient_accumulation_steps: 16
|
39 |
+
- total_train_batch_size: 128
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: linear
|
42 |
- lr_scheduler_warmup_steps: 500
|
43 |
+
- num_epochs: 1
|
44 |
|
45 |
### Training results
|
46 |
|
config.json
CHANGED
@@ -1,61 +1,34 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
|
|
|
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
|
|
|
|
6 |
"classifier_dropout": 0.0,
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
12 |
-
"
|
13 |
-
"
|
14 |
-
"
|
15 |
-
"
|
|
|
|
|
|
|
|
|
16 |
"is_encoder_decoder": true,
|
17 |
-
"
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"num_heads": 8,
|
23 |
-
"num_layers": 6,
|
24 |
-
"output_past": true,
|
25 |
-
"pad_token_id": 0,
|
26 |
-
"relative_attention_max_distance": 128,
|
27 |
-
"relative_attention_num_buckets": 32,
|
28 |
-
"task_specific_params": {
|
29 |
-
"summarization": {
|
30 |
-
"early_stopping": true,
|
31 |
-
"length_penalty": 2.0,
|
32 |
-
"max_length": 200,
|
33 |
-
"min_length": 30,
|
34 |
-
"no_repeat_ngram_size": 3,
|
35 |
-
"num_beams": 4,
|
36 |
-
"prefix": "summarize: "
|
37 |
-
},
|
38 |
-
"translation_en_to_de": {
|
39 |
-
"early_stopping": true,
|
40 |
-
"max_length": 300,
|
41 |
-
"num_beams": 4,
|
42 |
-
"prefix": "translate English to German: "
|
43 |
-
},
|
44 |
-
"translation_en_to_fr": {
|
45 |
-
"early_stopping": true,
|
46 |
-
"max_length": 300,
|
47 |
-
"num_beams": 4,
|
48 |
-
"prefix": "translate English to French: "
|
49 |
-
},
|
50 |
-
"translation_en_to_ro": {
|
51 |
-
"early_stopping": true,
|
52 |
-
"max_length": 300,
|
53 |
-
"num_beams": 4,
|
54 |
-
"prefix": "translate English to Romanian: "
|
55 |
-
}
|
56 |
-
},
|
57 |
"torch_dtype": "float32",
|
58 |
"transformers_version": "4.32.0",
|
59 |
"use_cache": true,
|
60 |
-
"vocab_size":
|
61 |
}
|
|
|
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": "4.32.0",
|
32 |
"use_cache": true,
|
33 |
+
"vocab_size": 50005
|
34 |
}
|
generation_config.json
CHANGED
@@ -1,7 +1,8 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
-
"
|
4 |
-
"eos_token_id":
|
5 |
-
"
|
|
|
6 |
"transformers_version": "4.32.0"
|
7 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"forced_eos_token_id": 2,
|
6 |
+
"pad_token_id": 1,
|
7 |
"transformers_version": "4.32.0"
|
8 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f97e5ae0dba4396aa7a10a14a8e6ef75c8546f9c9ca346ff7ff70f2b7051b03
|
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
CHANGED
@@ -1,107 +1,20 @@
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"<extra_id_3>",
|
7 |
-
"<extra_id_4>",
|
8 |
-
"<extra_id_5>",
|
9 |
-
"<extra_id_6>",
|
10 |
-
"<extra_id_7>",
|
11 |
-
"<extra_id_8>",
|
12 |
-
"<extra_id_9>",
|
13 |
-
"<extra_id_10>",
|
14 |
-
"<extra_id_11>",
|
15 |
-
"<extra_id_12>",
|
16 |
-
"<extra_id_13>",
|
17 |
-
"<extra_id_14>",
|
18 |
-
"<extra_id_15>",
|
19 |
-
"<extra_id_16>",
|
20 |
-
"<extra_id_17>",
|
21 |
-
"<extra_id_18>",
|
22 |
-
"<extra_id_19>",
|
23 |
-
"<extra_id_20>",
|
24 |
-
"<extra_id_21>",
|
25 |
-
"<extra_id_22>",
|
26 |
-
"<extra_id_23>",
|
27 |
-
"<extra_id_24>",
|
28 |
-
"<extra_id_25>",
|
29 |
-
"<extra_id_26>",
|
30 |
-
"<extra_id_27>",
|
31 |
-
"<extra_id_28>",
|
32 |
-
"<extra_id_29>",
|
33 |
-
"<extra_id_30>",
|
34 |
-
"<extra_id_31>",
|
35 |
-
"<extra_id_32>",
|
36 |
-
"<extra_id_33>",
|
37 |
-
"<extra_id_34>",
|
38 |
-
"<extra_id_35>",
|
39 |
-
"<extra_id_36>",
|
40 |
-
"<extra_id_37>",
|
41 |
-
"<extra_id_38>",
|
42 |
-
"<extra_id_39>",
|
43 |
-
"<extra_id_40>",
|
44 |
-
"<extra_id_41>",
|
45 |
-
"<extra_id_42>",
|
46 |
-
"<extra_id_43>",
|
47 |
-
"<extra_id_44>",
|
48 |
-
"<extra_id_45>",
|
49 |
-
"<extra_id_46>",
|
50 |
-
"<extra_id_47>",
|
51 |
-
"<extra_id_48>",
|
52 |
-
"<extra_id_49>",
|
53 |
-
"<extra_id_50>",
|
54 |
-
"<extra_id_51>",
|
55 |
-
"<extra_id_52>",
|
56 |
-
"<extra_id_53>",
|
57 |
-
"<extra_id_54>",
|
58 |
-
"<extra_id_55>",
|
59 |
-
"<extra_id_56>",
|
60 |
-
"<extra_id_57>",
|
61 |
-
"<extra_id_58>",
|
62 |
-
"<extra_id_59>",
|
63 |
-
"<extra_id_60>",
|
64 |
-
"<extra_id_61>",
|
65 |
-
"<extra_id_62>",
|
66 |
-
"<extra_id_63>",
|
67 |
-
"<extra_id_64>",
|
68 |
-
"<extra_id_65>",
|
69 |
-
"<extra_id_66>",
|
70 |
-
"<extra_id_67>",
|
71 |
-
"<extra_id_68>",
|
72 |
-
"<extra_id_69>",
|
73 |
-
"<extra_id_70>",
|
74 |
-
"<extra_id_71>",
|
75 |
-
"<extra_id_72>",
|
76 |
-
"<extra_id_73>",
|
77 |
-
"<extra_id_74>",
|
78 |
-
"<extra_id_75>",
|
79 |
-
"<extra_id_76>",
|
80 |
-
"<extra_id_77>",
|
81 |
-
"<extra_id_78>",
|
82 |
-
"<extra_id_79>",
|
83 |
-
"<extra_id_80>",
|
84 |
-
"<extra_id_81>",
|
85 |
-
"<extra_id_82>",
|
86 |
-
"<extra_id_83>",
|
87 |
-
"<extra_id_84>",
|
88 |
-
"<extra_id_85>",
|
89 |
-
"<extra_id_86>",
|
90 |
-
"<extra_id_87>",
|
91 |
-
"<extra_id_88>",
|
92 |
-
"<extra_id_89>",
|
93 |
-
"<extra_id_90>",
|
94 |
-
"<extra_id_91>",
|
95 |
-
"<extra_id_92>",
|
96 |
-
"<extra_id_93>",
|
97 |
-
"<extra_id_94>",
|
98 |
-
"<extra_id_95>",
|
99 |
-
"<extra_id_96>",
|
100 |
-
"<extra_id_97>",
|
101 |
-
"<extra_id_98>",
|
102 |
-
"<extra_id_99>"
|
103 |
],
|
|
|
|
|
104 |
"eos_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
105 |
"pad_token": "<pad>",
|
|
|
106 |
"unk_token": "<unk>"
|
107 |
}
|
|
|
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
CHANGED
@@ -1,113 +1,24 @@
|
|
1 |
{
|
2 |
-
"additional_special_tokens":
|
3 |
-
|
4 |
-
"<extra_id_1>",
|
5 |
-
"<extra_id_2>",
|
6 |
-
"<extra_id_3>",
|
7 |
-
"<extra_id_4>",
|
8 |
-
"<extra_id_5>",
|
9 |
-
"<extra_id_6>",
|
10 |
-
"<extra_id_7>",
|
11 |
-
"<extra_id_8>",
|
12 |
-
"<extra_id_9>",
|
13 |
-
"<extra_id_10>",
|
14 |
-
"<extra_id_11>",
|
15 |
-
"<extra_id_12>",
|
16 |
-
"<extra_id_13>",
|
17 |
-
"<extra_id_14>",
|
18 |
-
"<extra_id_15>",
|
19 |
-
"<extra_id_16>",
|
20 |
-
"<extra_id_17>",
|
21 |
-
"<extra_id_18>",
|
22 |
-
"<extra_id_19>",
|
23 |
-
"<extra_id_20>",
|
24 |
-
"<extra_id_21>",
|
25 |
-
"<extra_id_22>",
|
26 |
-
"<extra_id_23>",
|
27 |
-
"<extra_id_24>",
|
28 |
-
"<extra_id_25>",
|
29 |
-
"<extra_id_26>",
|
30 |
-
"<extra_id_27>",
|
31 |
-
"<extra_id_28>",
|
32 |
-
"<extra_id_29>",
|
33 |
-
"<extra_id_30>",
|
34 |
-
"<extra_id_31>",
|
35 |
-
"<extra_id_32>",
|
36 |
-
"<extra_id_33>",
|
37 |
-
"<extra_id_34>",
|
38 |
-
"<extra_id_35>",
|
39 |
-
"<extra_id_36>",
|
40 |
-
"<extra_id_37>",
|
41 |
-
"<extra_id_38>",
|
42 |
-
"<extra_id_39>",
|
43 |
-
"<extra_id_40>",
|
44 |
-
"<extra_id_41>",
|
45 |
-
"<extra_id_42>",
|
46 |
-
"<extra_id_43>",
|
47 |
-
"<extra_id_44>",
|
48 |
-
"<extra_id_45>",
|
49 |
-
"<extra_id_46>",
|
50 |
-
"<extra_id_47>",
|
51 |
-
"<extra_id_48>",
|
52 |
-
"<extra_id_49>",
|
53 |
-
"<extra_id_50>",
|
54 |
-
"<extra_id_51>",
|
55 |
-
"<extra_id_52>",
|
56 |
-
"<extra_id_53>",
|
57 |
-
"<extra_id_54>",
|
58 |
-
"<extra_id_55>",
|
59 |
-
"<extra_id_56>",
|
60 |
-
"<extra_id_57>",
|
61 |
-
"<extra_id_58>",
|
62 |
-
"<extra_id_59>",
|
63 |
-
"<extra_id_60>",
|
64 |
-
"<extra_id_61>",
|
65 |
-
"<extra_id_62>",
|
66 |
-
"<extra_id_63>",
|
67 |
-
"<extra_id_64>",
|
68 |
-
"<extra_id_65>",
|
69 |
-
"<extra_id_66>",
|
70 |
-
"<extra_id_67>",
|
71 |
-
"<extra_id_68>",
|
72 |
-
"<extra_id_69>",
|
73 |
-
"<extra_id_70>",
|
74 |
-
"<extra_id_71>",
|
75 |
-
"<extra_id_72>",
|
76 |
-
"<extra_id_73>",
|
77 |
-
"<extra_id_74>",
|
78 |
-
"<extra_id_75>",
|
79 |
-
"<extra_id_76>",
|
80 |
-
"<extra_id_77>",
|
81 |
-
"<extra_id_78>",
|
82 |
-
"<extra_id_79>",
|
83 |
-
"<extra_id_80>",
|
84 |
-
"<extra_id_81>",
|
85 |
-
"<extra_id_82>",
|
86 |
-
"<extra_id_83>",
|
87 |
-
"<extra_id_84>",
|
88 |
-
"<extra_id_85>",
|
89 |
-
"<extra_id_86>",
|
90 |
-
"<extra_id_87>",
|
91 |
-
"<extra_id_88>",
|
92 |
-
"<extra_id_89>",
|
93 |
-
"<extra_id_90>",
|
94 |
-
"<extra_id_91>",
|
95 |
-
"<extra_id_92>",
|
96 |
-
"<extra_id_93>",
|
97 |
-
"<extra_id_94>",
|
98 |
-
"<extra_id_95>",
|
99 |
-
"<extra_id_96>",
|
100 |
-
"<extra_id_97>",
|
101 |
-
"<extra_id_98>",
|
102 |
-
"<extra_id_99>"
|
103 |
-
],
|
104 |
"clean_up_tokenization_spaces": true,
|
|
|
105 |
"eos_token": "</s>",
|
106 |
-
"
|
107 |
-
"
|
108 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
109 |
"pad_token": "<pad>",
|
|
|
110 |
"sp_model_kwargs": {},
|
111 |
-
"
|
|
|
|
|
112 |
"unk_token": "<unk>"
|
113 |
}
|
|
|
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 |
+
"sep_token": "</s>",
|
19 |
"sp_model_kwargs": {},
|
20 |
+
"src_lang": null,
|
21 |
+
"tgt_lang": null,
|
22 |
+
"tokenizer_class": "PLBartTokenizer",
|
23 |
"unk_token": "<unk>"
|
24 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4027
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52cd1d4dfcee3823c8a0517f153e1dc335d64b7f2371b91b71ef3d1fb42da4b7
|
3 |
size 4027
|