fresh-2-layer-mmlu_EVAL_mmlu
Browse files- README.md +78 -0
- config.json +24 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
metrics:
|
5 |
+
- accuracy
|
6 |
+
model-index:
|
7 |
+
- name: fresh-2-layer-mmlu_EVAL_mmlu
|
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 |
+
# fresh-2-layer-mmlu_EVAL_mmlu
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.0196
|
19 |
+
- Accuracy: 0.9942
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 0.0005
|
39 |
+
- train_batch_size: 32
|
40 |
+
- eval_batch_size: 32
|
41 |
+
- seed: 321
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- lr_scheduler_warmup_steps: 500
|
45 |
+
- num_epochs: 20
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
50 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
51 |
+
| No log | 1.0 | 439 | 1.1960 | 0.518 |
|
52 |
+
| 1.2946 | 2.0 | 878 | 0.9728 | 0.61 |
|
53 |
+
| 1.1382 | 3.0 | 1317 | 0.6014 | 0.796 |
|
54 |
+
| 0.8904 | 4.0 | 1756 | 0.3594 | 0.88 |
|
55 |
+
| 0.5997 | 5.0 | 2195 | 0.2266 | 0.932 |
|
56 |
+
| 0.413 | 6.0 | 2634 | 0.1883 | 0.936 |
|
57 |
+
| 0.2801 | 7.0 | 3073 | 0.1547 | 0.95 |
|
58 |
+
| 0.2194 | 8.0 | 3512 | 0.1150 | 0.952 |
|
59 |
+
| 0.2194 | 9.0 | 3951 | 0.0860 | 0.974 |
|
60 |
+
| 0.1697 | 10.0 | 4390 | 0.0870 | 0.974 |
|
61 |
+
| 0.134 | 11.0 | 4829 | 0.0561 | 0.98 |
|
62 |
+
| 0.1098 | 12.0 | 5268 | 0.0450 | 0.99 |
|
63 |
+
| 0.0908 | 13.0 | 5707 | 0.0301 | 0.988 |
|
64 |
+
| 0.0771 | 14.0 | 6146 | 0.0229 | 0.992 |
|
65 |
+
| 0.0618 | 15.0 | 6585 | 0.0174 | 0.996 |
|
66 |
+
| 0.0482 | 16.0 | 7024 | 0.0107 | 0.998 |
|
67 |
+
| 0.0482 | 17.0 | 7463 | 0.0060 | 0.996 |
|
68 |
+
| 0.0418 | 18.0 | 7902 | 0.0037 | 0.998 |
|
69 |
+
| 0.0289 | 19.0 | 8341 | 0.0031 | 0.998 |
|
70 |
+
| 0.0242 | 20.0 | 8780 | 0.0029 | 0.998 |
|
71 |
+
|
72 |
+
|
73 |
+
### Framework versions
|
74 |
+
|
75 |
+
- Transformers 4.34.0.dev0
|
76 |
+
- Pytorch 2.0.1+cu117
|
77 |
+
- Datasets 2.14.5
|
78 |
+
- Tokenizers 0.14.0
|
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BertForMultipleChoice"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"classifier_dropout": null,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 512,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 3072,
|
12 |
+
"layer_norm_eps": 1e-12,
|
13 |
+
"max_position_embeddings": 512,
|
14 |
+
"model_type": "bert",
|
15 |
+
"num_attention_heads": 8,
|
16 |
+
"num_hidden_layers": 2,
|
17 |
+
"pad_token_id": 0,
|
18 |
+
"position_embedding_type": "absolute",
|
19 |
+
"torch_dtype": "float32",
|
20 |
+
"transformers_version": "4.34.0.dev0",
|
21 |
+
"type_vocab_size": 2,
|
22 |
+
"use_cache": true,
|
23 |
+
"vocab_size": 30522
|
24 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c09c58ee946d740a285bb800242dfa74da21c27c60215468220b49ddd17ca7d0
|
3 |
+
size 98247916
|
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": "BertTokenizer",
|
55 |
+
"unk_token": "[UNK]"
|
56 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9073375bbdecef6460350c1694620c9bf8b1818d7426b2fcef94be0e20171b2
|
3 |
+
size 4027
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|