haibotamiu
commited on
Commit
•
262245a
1
Parent(s):
cfc5aca
Model save
Browse files- README.md +52 -0
- added_tokens.json +7 -0
- all_results.json +8 -0
- args.bin +3 -0
- config.json +24 -0
- pruning_config.json +26 -0
- pytorch_model.bin +3 -0
- raw_pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- train_results.json +8 -0
- trainer_state.json +28 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilbert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: out
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# out
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
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 |
+
|
45 |
+
|
46 |
+
|
47 |
+
### Framework versions
|
48 |
+
|
49 |
+
- Transformers 4.35.0.dev0
|
50 |
+
- Pytorch 2.1.0+cu118
|
51 |
+
- Datasets 2.10.1
|
52 |
+
- Tokenizers 0.14.1
|
added_tokens.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[CLS]": 101,
|
3 |
+
"[MASK]": 103,
|
4 |
+
"[PAD]": 0,
|
5 |
+
"[SEP]": 102,
|
6 |
+
"[UNK]": 100
|
7 |
+
}
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 2.116673701227048,
|
4 |
+
"train_runtime": 309.01,
|
5 |
+
"train_samples": 30000,
|
6 |
+
"train_samples_per_second": 291.253,
|
7 |
+
"train_steps_per_second": 1.146
|
8 |
+
}
|
args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84681b490574eec665dd628028717bdc85fbdb7ad3d54c8ed025f6816f1b69f3
|
3 |
+
size 5652
|
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"QuantizedDistilBertForQuestionAnswering"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"qa_dropout": 0.1,
|
18 |
+
"seq_classif_dropout": 0.2,
|
19 |
+
"sinusoidal_pos_embds": false,
|
20 |
+
"tie_weights_": true,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.35.0.dev0",
|
23 |
+
"vocab_size": 30522
|
24 |
+
}
|
pruning_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"begin_pruning_step": 1400,
|
3 |
+
"end_pruning_step": 12000,
|
4 |
+
"explicit_prune": {},
|
5 |
+
"init_strategy": "uniform",
|
6 |
+
"initial_step": 0,
|
7 |
+
"not_to_prune": [
|
8 |
+
"qa_outputs",
|
9 |
+
"pooler",
|
10 |
+
"teacher"
|
11 |
+
],
|
12 |
+
"policy_begin_step": 1400,
|
13 |
+
"policy_end_step": 10000,
|
14 |
+
"prune_layer_types": {
|
15 |
+
"Linear": {
|
16 |
+
"name": "weight"
|
17 |
+
}
|
18 |
+
},
|
19 |
+
"pruning_fn": "unstructured_magnitude",
|
20 |
+
"pruning_fn_default_kwargs": {
|
21 |
+
"target_sparsity": 0.85
|
22 |
+
},
|
23 |
+
"pruning_frequency": 100,
|
24 |
+
"scheduler": "iterative",
|
25 |
+
"weight_sparsity_map": {}
|
26 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3ef050729f0931a1ab4b251d4ccc9bd10abefc57d7de8209769201e2e17232c
|
3 |
+
size 265832945
|
raw_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1f0839ac6d21be64cac0d009add03e24b92d8146d213fbb1f1473a3a4c3ea9e
|
3 |
+
size 265864653
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
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": "[PAD]",
|
51 |
+
"sep_token": "[SEP]",
|
52 |
+
"strip_accents": null,
|
53 |
+
"tokenize_chinese_chars": true,
|
54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
55 |
+
"unk_token": "[UNK]"
|
56 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 2.116673701227048,
|
4 |
+
"train_runtime": 309.01,
|
5 |
+
"train_samples": 30000,
|
6 |
+
"train_samples_per_second": 291.253,
|
7 |
+
"train_steps_per_second": 1.146
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 354,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 3.0,
|
13 |
+
"step": 354,
|
14 |
+
"total_flos": 8819084252160000.0,
|
15 |
+
"train_loss": 2.116673701227048,
|
16 |
+
"train_runtime": 309.01,
|
17 |
+
"train_samples_per_second": 291.253,
|
18 |
+
"train_steps_per_second": 1.146
|
19 |
+
}
|
20 |
+
],
|
21 |
+
"logging_steps": 500,
|
22 |
+
"max_steps": 354,
|
23 |
+
"num_train_epochs": 3,
|
24 |
+
"save_steps": 500,
|
25 |
+
"total_flos": 8819084252160000.0,
|
26 |
+
"trial_name": null,
|
27 |
+
"trial_params": null
|
28 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed62376ecc90c8a01bbc2f29b3d92d6ab6a87975e9b65b07bf2310214f6493ce
|
3 |
+
size 4664
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|