End of training
Browse files- README.md +74 -0
- config.json +5 -8
- events.out.tfevents.1700918845.a0539e9e3983.5718.0 +3 -0
- model.safetensors +3 -0
- runs/Nov25_13-27-31_a0539e9e3983/events.out.tfevents.1700918902.a0539e9e3983.5718.1 +3 -0
- runs/Nov25_13-27-31_a0539e9e3983/events.out.tfevents.1700918902.a0539e9e3983.5718.2 +3 -0
- runs/Nov25_13-33-33_a0539e9e3983/events.out.tfevents.1700919218.a0539e9e3983.5718.3 +3 -0
- runs/Nov25_13-33-33_a0539e9e3983/events.out.tfevents.1700919218.a0539e9e3983.5718.4 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: prajjwal1/bert-tiny
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: BP-test1
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# BP-test1
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.2385
|
21 |
+
- Accuracy: 0.93
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 2e-05
|
41 |
+
- train_batch_size: 16
|
42 |
+
- eval_batch_size: 16
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 10
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
+
| No log | 0.01 | 50 | 0.6925 | 0.45 |
|
53 |
+
| No log | 0.02 | 100 | 0.6758 | 0.62 |
|
54 |
+
| No log | 0.03 | 150 | 0.6384 | 0.66 |
|
55 |
+
| No log | 0.04 | 200 | 0.6241 | 0.66 |
|
56 |
+
| No log | 0.05 | 250 | 0.6081 | 0.66 |
|
57 |
+
| No log | 0.06 | 300 | 0.5643 | 0.87 |
|
58 |
+
| No log | 0.07 | 350 | 0.5200 | 0.87 |
|
59 |
+
| No log | 0.08 | 400 | 0.4989 | 0.81 |
|
60 |
+
| No log | 0.09 | 450 | 0.4370 | 0.87 |
|
61 |
+
| 0.6058 | 0.1 | 500 | 0.3298 | 0.94 |
|
62 |
+
| 0.6058 | 0.11 | 550 | 0.2876 | 0.94 |
|
63 |
+
| 0.6058 | 0.12 | 600 | 0.2701 | 0.93 |
|
64 |
+
| 0.6058 | 0.13 | 650 | 0.2533 | 0.93 |
|
65 |
+
| 0.6058 | 0.14 | 700 | 0.2452 | 0.93 |
|
66 |
+
| 0.6058 | 0.15 | 750 | 0.2385 | 0.93 |
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- Transformers 4.35.2
|
72 |
+
- Pytorch 2.1.0+cu118
|
73 |
+
- Datasets 2.15.0
|
74 |
+
- Tokenizers 0.15.0
|
config.json
CHANGED
@@ -1,20 +1,15 @@
|
|
1 |
{
|
2 |
"_name_or_path": "prajjwal1/bert-tiny",
|
|
|
|
|
|
|
3 |
"attention_probs_dropout_prob": 0.1,
|
4 |
"classifier_dropout": null,
|
5 |
"hidden_act": "gelu",
|
6 |
"hidden_dropout_prob": 0.1,
|
7 |
"hidden_size": 128,
|
8 |
-
"id2label": {
|
9 |
-
"0": "Taken",
|
10 |
-
"1": "Not Taken"
|
11 |
-
},
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 512,
|
14 |
-
"label2id": {
|
15 |
-
"Not Taken": 1,
|
16 |
-
"Taken": 0
|
17 |
-
},
|
18 |
"layer_norm_eps": 1e-12,
|
19 |
"max_position_embeddings": 512,
|
20 |
"model_type": "bert",
|
@@ -22,6 +17,8 @@
|
|
22 |
"num_hidden_layers": 2,
|
23 |
"pad_token_id": 0,
|
24 |
"position_embedding_type": "absolute",
|
|
|
|
|
25 |
"transformers_version": "4.35.2",
|
26 |
"type_vocab_size": 2,
|
27 |
"use_cache": true,
|
|
|
1 |
{
|
2 |
"_name_or_path": "prajjwal1/bert-tiny",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"classifier_dropout": null,
|
8 |
"hidden_act": "gelu",
|
9 |
"hidden_dropout_prob": 0.1,
|
10 |
"hidden_size": 128,
|
|
|
|
|
|
|
|
|
11 |
"initializer_range": 0.02,
|
12 |
"intermediate_size": 512,
|
|
|
|
|
|
|
|
|
13 |
"layer_norm_eps": 1e-12,
|
14 |
"max_position_embeddings": 512,
|
15 |
"model_type": "bert",
|
|
|
17 |
"num_hidden_layers": 2,
|
18 |
"pad_token_id": 0,
|
19 |
"position_embedding_type": "absolute",
|
20 |
+
"problem_type": "single_label_classification",
|
21 |
+
"torch_dtype": "float32",
|
22 |
"transformers_version": "4.35.2",
|
23 |
"type_vocab_size": 2,
|
24 |
"use_cache": true,
|
events.out.tfevents.1700918845.a0539e9e3983.5718.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a0869641fa9b2cccafe445be67a807fbbe2cc4eba2158fe38c0e0e41452d230
|
3 |
+
size 748
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e1fce89abd544540d6e725d80059f55b8c70ae3fe9839010a91ddd685c3dd7c
|
3 |
+
size 17549312
|
runs/Nov25_13-27-31_a0539e9e3983/events.out.tfevents.1700918902.a0539e9e3983.5718.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ffb116a2a61dd94af5fa5345eea1a3fbe7c3bbebd897a1f4554c83e53217cd1d
|
3 |
+
size 4096
|
runs/Nov25_13-27-31_a0539e9e3983/events.out.tfevents.1700918902.a0539e9e3983.5718.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ccdacae6edb7f9f10f903dab8333e9c2f06e74725e06d930b291d235472ccca
|
3 |
+
size 4096
|
runs/Nov25_13-33-33_a0539e9e3983/events.out.tfevents.1700919218.a0539e9e3983.5718.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebebc32ec35adf37f74626936b9fcb275128a7b547014abb52af50dd0cf91133
|
3 |
+
size 9440
|
runs/Nov25_13-33-33_a0539e9e3983/events.out.tfevents.1700919218.a0539e9e3983.5718.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b1b0574fe5b427e1bec02b5f77b1bdf955afa0d6f59383b84496e84559cb092
|
3 |
+
size 9440
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3a82be5472588eaffa660e0852fc31ee46a8f50d05e5a6f334bd141aee41524
|
3 |
+
size 4536
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|