BrandonC8310
commited on
Commit
•
70c46f7
1
Parent(s):
db48488
delete
Browse files- README.md +0 -69
- all_results.json +0 -8
- config.json +0 -27
- pytorch_model.bin +0 -3
- special_tokens_map.json +0 -7
- tokenizer.json +0 -0
- tokenizer_config.json +0 -14
- train_results.json +0 -8
- training_args.bin +0 -3
- vocab.txt +0 -0
README.md
DELETED
@@ -1,69 +0,0 @@
|
|
1 |
-
---
|
2 |
-
tags:
|
3 |
-
- generated_from_trainer
|
4 |
-
model-index:
|
5 |
-
- name: bert-base-uncased-bert-base-uncased-finetuned-mbti-0905
|
6 |
-
results: []
|
7 |
-
---
|
8 |
-
|
9 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
10 |
-
should probably proofread and complete it, then remove this comment. -->
|
11 |
-
|
12 |
-
# bert-base-uncased-bert-base-uncased-finetuned-mbti-0905
|
13 |
-
|
14 |
-
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
|
15 |
-
It achieves the following results on the evaluation set:
|
16 |
-
- Loss: 2.1300
|
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: 2e-05
|
36 |
-
- train_batch_size: 4
|
37 |
-
- eval_batch_size: 8
|
38 |
-
- seed: 42
|
39 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
-
- lr_scheduler_type: linear
|
41 |
-
- num_epochs: 15
|
42 |
-
|
43 |
-
### Training results
|
44 |
-
|
45 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
46 |
-
|:-------------:|:-----:|:-----:|:---------------:|
|
47 |
-
| 6.1123 | 1.0 | 1735 | 5.8687 |
|
48 |
-
| 5.7296 | 2.0 | 3470 | 5.7366 |
|
49 |
-
| 5.4171 | 3.0 | 5205 | 5.7069 |
|
50 |
-
| 5.1515 | 4.0 | 6940 | 5.7513 |
|
51 |
-
| 4.972 | 5.0 | 8675 | 5.7805 |
|
52 |
-
| 4.8949 | 6.0 | 10410 | 5.5448 |
|
53 |
-
| 4.2657 | 7.0 | 12145 | 4.9113 |
|
54 |
-
| 3.6447 | 8.0 | 13880 | 4.1228 |
|
55 |
-
| 3.0587 | 9.0 | 15615 | 3.6803 |
|
56 |
-
| 2.8321 | 10.0 | 17350 | 3.4982 |
|
57 |
-
| 2.5816 | 11.0 | 19085 | 2.8572 |
|
58 |
-
| 1.9901 | 12.0 | 20820 | 2.4997 |
|
59 |
-
| 1.5719 | 13.0 | 22555 | 2.2799 |
|
60 |
-
| 1.2894 | 14.0 | 24290 | 2.1577 |
|
61 |
-
| 1.1245 | 15.0 | 26025 | 2.1300 |
|
62 |
-
|
63 |
-
|
64 |
-
### Framework versions
|
65 |
-
|
66 |
-
- Transformers 4.21.2
|
67 |
-
- Pytorch 1.12.1
|
68 |
-
- Datasets 2.4.0
|
69 |
-
- Tokenizers 0.12.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
all_results.json
DELETED
@@ -1,8 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"epoch": 10.0,
|
3 |
-
"total_flos": 2.4440047552512e+16,
|
4 |
-
"train_loss": 0.0,
|
5 |
-
"train_runtime": 0.0636,
|
6 |
-
"train_samples_per_second": 1090977.125,
|
7 |
-
"train_steps_per_second": 272744.281
|
8 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
DELETED
@@ -1,27 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "bert-base-uncased",
|
3 |
-
"architectures": [
|
4 |
-
"BertLMHeadModel"
|
5 |
-
],
|
6 |
-
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"classifier_dropout": null,
|
8 |
-
"gradient_checkpointing": false,
|
9 |
-
"hidden_act": "gelu",
|
10 |
-
"hidden_dropout_prob": 0.1,
|
11 |
-
"hidden_size": 768,
|
12 |
-
"initializer_range": 0.02,
|
13 |
-
"intermediate_size": 3072,
|
14 |
-
"is_decoder": true,
|
15 |
-
"layer_norm_eps": 1e-12,
|
16 |
-
"max_position_embeddings": 512,
|
17 |
-
"model_type": "bert",
|
18 |
-
"num_attention_heads": 12,
|
19 |
-
"num_hidden_layers": 12,
|
20 |
-
"pad_token_id": 0,
|
21 |
-
"position_embedding_type": "absolute",
|
22 |
-
"torch_dtype": "float32",
|
23 |
-
"transformers_version": "4.21.2",
|
24 |
-
"type_vocab_size": 2,
|
25 |
-
"use_cache": true,
|
26 |
-
"vocab_size": 30522
|
27 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:5effbedba4f5c9e07bfab9da4e091dbeceed3d6ccec82d46859b57e3769316fd
|
3 |
-
size 554035445
|
|
|
|
|
|
|
|
special_tokens_map.json
DELETED
@@ -1,7 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"cls_token": "[CLS]",
|
3 |
-
"mask_token": "[MASK]",
|
4 |
-
"pad_token": "[PAD]",
|
5 |
-
"sep_token": "[SEP]",
|
6 |
-
"unk_token": "[UNK]"
|
7 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
DELETED
@@ -1,14 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"cls_token": "[CLS]",
|
3 |
-
"do_lower_case": true,
|
4 |
-
"mask_token": "[MASK]",
|
5 |
-
"model_max_length": 512,
|
6 |
-
"name_or_path": "bert-base-uncased",
|
7 |
-
"pad_token": "[PAD]",
|
8 |
-
"sep_token": "[SEP]",
|
9 |
-
"special_tokens_map_file": null,
|
10 |
-
"strip_accents": null,
|
11 |
-
"tokenize_chinese_chars": true,
|
12 |
-
"tokenizer_class": "BertTokenizer",
|
13 |
-
"unk_token": "[UNK]"
|
14 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
train_results.json
DELETED
@@ -1,8 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"epoch": 10.0,
|
3 |
-
"total_flos": 2.4440047552512e+16,
|
4 |
-
"train_loss": 0.0,
|
5 |
-
"train_runtime": 0.0636,
|
6 |
-
"train_samples_per_second": 1090977.125,
|
7 |
-
"train_steps_per_second": 272744.281
|
8 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:89a540841fda3f6392292e2684856d19b90f4c59e7bdc789705efb8bf6c001c0
|
3 |
-
size 3311
|
|
|
|
|
|
|
|
vocab.txt
DELETED
The diff for this file is too large to render.
See raw diff
|
|