haibotamiu
commited on
Commit
•
b02fd2a
1
Parent(s):
2fcf873
Model save
Browse files- README.md +4 -7
- added_tokens.json +5 -5
- config.json +21 -14
- pruning_config.json +1 -1
- pytorch_model.bin +2 -2
- raw_pytorch_model.bin +2 -2
- special_tokens_map.json +4 -2
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -12
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,11 +1,8 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
-
- question-answering
|
6 |
- generated_from_trainer
|
7 |
-
datasets:
|
8 |
-
- squad
|
9 |
model-index:
|
10 |
- name: out
|
11 |
results: []
|
@@ -16,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# out
|
18 |
|
19 |
-
This model is a fine-tuned version of [
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -36,12 +33,12 @@ More information needed
|
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
- learning_rate: 5e-05
|
39 |
-
- train_batch_size:
|
40 |
- eval_batch_size: 16
|
41 |
- seed: 42
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
-
- num_epochs:
|
45 |
|
46 |
### Training results
|
47 |
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: albert-base-v2
|
4 |
tags:
|
|
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
model-index:
|
7 |
- name: out
|
8 |
results: []
|
|
|
13 |
|
14 |
# out
|
15 |
|
16 |
+
This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the None dataset.
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
- learning_rate: 5e-05
|
36 |
+
- train_batch_size: 256
|
37 |
- eval_batch_size: 16
|
38 |
- seed: 42
|
39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
- lr_scheduler_type: linear
|
41 |
+
- num_epochs: 3.0
|
42 |
|
43 |
### Training results
|
44 |
|
added_tokens.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"[
|
5 |
-
"[
|
6 |
-
"[
|
7 |
}
|
|
|
1 |
{
|
2 |
+
"<pad>": 0,
|
3 |
+
"<unk>": 1,
|
4 |
+
"[CLS]": 2,
|
5 |
+
"[MASK]": 4,
|
6 |
+
"[SEP]": 3
|
7 |
}
|
config.json
CHANGED
@@ -1,26 +1,33 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"attention_probs_dropout_prob": 0
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
|
|
|
|
|
|
|
|
12 |
"initializer_range": 0.02,
|
13 |
-
"
|
|
|
14 |
"layer_norm_eps": 1e-12,
|
15 |
"max_position_embeddings": 512,
|
16 |
-
"model_type": "
|
17 |
-
"
|
18 |
-
"
|
|
|
|
|
|
|
19 |
"pad_token_id": 0,
|
20 |
"position_embedding_type": "absolute",
|
21 |
"torch_dtype": "float32",
|
22 |
"transformers_version": "4.35.0.dev0",
|
23 |
"type_vocab_size": 2,
|
24 |
-
"
|
25 |
-
"vocab_size": 30522
|
26 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "albert-base-v2",
|
3 |
"architectures": [
|
4 |
+
"AlbertForQuestionAnswering"
|
5 |
],
|
6 |
+
"attention_probs_dropout_prob": 0,
|
7 |
+
"bos_token_id": 2,
|
8 |
+
"classifier_dropout_prob": 0.1,
|
9 |
+
"down_scale_factor": 1,
|
10 |
+
"embedding_size": 128,
|
11 |
+
"eos_token_id": 3,
|
12 |
+
"gap_size": 0,
|
13 |
+
"hidden_act": "gelu_new",
|
14 |
+
"hidden_dropout_prob": 0,
|
15 |
+
"hidden_size": 768,
|
16 |
"initializer_range": 0.02,
|
17 |
+
"inner_group_num": 1,
|
18 |
+
"intermediate_size": 3072,
|
19 |
"layer_norm_eps": 1e-12,
|
20 |
"max_position_embeddings": 512,
|
21 |
+
"model_type": "albert",
|
22 |
+
"net_structure_type": 0,
|
23 |
+
"num_attention_heads": 12,
|
24 |
+
"num_hidden_groups": 1,
|
25 |
+
"num_hidden_layers": 12,
|
26 |
+
"num_memory_blocks": 0,
|
27 |
"pad_token_id": 0,
|
28 |
"position_embedding_type": "absolute",
|
29 |
"torch_dtype": "float32",
|
30 |
"transformers_version": "4.35.0.dev0",
|
31 |
"type_vocab_size": 2,
|
32 |
+
"vocab_size": 30000
|
|
|
33 |
}
|
pruning_config.json
CHANGED
@@ -18,7 +18,7 @@
|
|
18 |
},
|
19 |
"pruning_fn": "unstructured_magnitude",
|
20 |
"pruning_fn_default_kwargs": {
|
21 |
-
"target_sparsity": 0.
|
22 |
},
|
23 |
"pruning_frequency": 100,
|
24 |
"scheduler": "iterative",
|
|
|
18 |
},
|
19 |
"pruning_fn": "unstructured_magnitude",
|
20 |
"pruning_fn_default_kwargs": {
|
21 |
+
"target_sparsity": 0.85
|
22 |
},
|
23 |
"pruning_frequency": 100,
|
24 |
"scheduler": "iterative",
|
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 sha256:59c8b45d58cc16f8be68b58c766c18149b106ba6c63923e4e660069e34e7fff0
|
3 |
+
size 44387257
|
raw_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 sha256:990d6dcf19e7b47d49c419810e1b5a77fcafce7f87a95dd98a00357b924f9eda
|
3 |
+
size 73096798
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,9 @@
|
|
1 |
{
|
|
|
2 |
"cls_token": "[CLS]",
|
|
|
3 |
"mask_token": "[MASK]",
|
4 |
-
"pad_token": "
|
5 |
"sep_token": "[SEP]",
|
6 |
-
"unk_token": "
|
7 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "<pad>",
|
7 |
"sep_token": "[SEP]",
|
8 |
+
"unk_token": "<unk>"
|
9 |
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
|
3 |
+
size 760289
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,22 +1,22 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
-
"content": "
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
-
"
|
12 |
-
"content": "
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
"content": "[CLS]",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
@@ -24,7 +24,7 @@
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
"content": "[SEP]",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
@@ -32,9 +32,9 @@
|
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
-
"
|
36 |
"content": "[MASK]",
|
37 |
-
"lstrip":
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
@@ -42,15 +42,17 @@
|
|
42 |
}
|
43 |
},
|
44 |
"additional_special_tokens": [],
|
|
|
45 |
"clean_up_tokenization_spaces": true,
|
46 |
"cls_token": "[CLS]",
|
47 |
"do_lower_case": true,
|
|
|
|
|
48 |
"mask_token": "[MASK]",
|
49 |
"model_max_length": 512,
|
50 |
-
"pad_token": "
|
|
|
51 |
"sep_token": "[SEP]",
|
52 |
-
"
|
53 |
-
"
|
54 |
-
"tokenizer_class": "BertTokenizer",
|
55 |
-
"unk_token": "[UNK]"
|
56 |
}
|
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
+
"content": "<pad>",
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
+
"1": {
|
12 |
+
"content": "<unk>",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
+
"2": {
|
20 |
"content": "[CLS]",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
+
"3": {
|
28 |
"content": "[SEP]",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
|
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
+
"4": {
|
36 |
"content": "[MASK]",
|
37 |
+
"lstrip": true,
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
|
|
42 |
}
|
43 |
},
|
44 |
"additional_special_tokens": [],
|
45 |
+
"bos_token": "[CLS]",
|
46 |
"clean_up_tokenization_spaces": true,
|
47 |
"cls_token": "[CLS]",
|
48 |
"do_lower_case": true,
|
49 |
+
"eos_token": "[SEP]",
|
50 |
+
"keep_accents": false,
|
51 |
"mask_token": "[MASK]",
|
52 |
"model_max_length": 512,
|
53 |
+
"pad_token": "<pad>",
|
54 |
+
"remove_space": true,
|
55 |
"sep_token": "[SEP]",
|
56 |
+
"tokenizer_class": "AlbertTokenizer",
|
57 |
+
"unk_token": "<unk>"
|
|
|
|
|
58 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9322bc2bcb7a8886f68ebf17e543e082e1598e8a1909dedfcca9c382180b7d8c
|
3 |
size 4664
|