mhr2004/bert-base-uncased-nsp-5000-1e-06-8
Browse files- README.md +87 -0
- config.json +27 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
base_model: bert-base-uncased
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
model-index:
|
8 |
+
- name: bert-base-uncased-nsp-5000-1e-06-8
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# bert-base-uncased-nsp-5000-1e-06-8
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.4119
|
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: 1e-06
|
39 |
+
- train_batch_size: 32
|
40 |
+
- eval_batch_size: 1024
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 30
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| No log | 1.0 | 157 | 0.6923 |
|
51 |
+
| 0.6979 | 2.0 | 314 | 0.6900 |
|
52 |
+
| 0.6928 | 3.0 | 471 | 0.6867 |
|
53 |
+
| 0.6891 | 4.0 | 628 | 0.6805 |
|
54 |
+
| 0.6891 | 5.0 | 785 | 0.6697 |
|
55 |
+
| 0.6805 | 6.0 | 942 | 0.6527 |
|
56 |
+
| 0.6637 | 7.0 | 1099 | 0.6301 |
|
57 |
+
| 0.6388 | 8.0 | 1256 | 0.6087 |
|
58 |
+
| 0.6103 | 9.0 | 1413 | 0.5909 |
|
59 |
+
| 0.6103 | 10.0 | 1570 | 0.5760 |
|
60 |
+
| 0.5846 | 11.0 | 1727 | 0.5624 |
|
61 |
+
| 0.5665 | 12.0 | 1884 | 0.5438 |
|
62 |
+
| 0.5322 | 13.0 | 2041 | 0.5249 |
|
63 |
+
| 0.5322 | 14.0 | 2198 | 0.5029 |
|
64 |
+
| 0.5096 | 15.0 | 2355 | 0.4886 |
|
65 |
+
| 0.4759 | 16.0 | 2512 | 0.4672 |
|
66 |
+
| 0.4457 | 17.0 | 2669 | 0.4581 |
|
67 |
+
| 0.4306 | 18.0 | 2826 | 0.4493 |
|
68 |
+
| 0.4306 | 19.0 | 2983 | 0.4413 |
|
69 |
+
| 0.4073 | 20.0 | 3140 | 0.4331 |
|
70 |
+
| 0.3974 | 21.0 | 3297 | 0.4267 |
|
71 |
+
| 0.3789 | 22.0 | 3454 | 0.4252 |
|
72 |
+
| 0.3615 | 23.0 | 3611 | 0.4200 |
|
73 |
+
| 0.3615 | 24.0 | 3768 | 0.4183 |
|
74 |
+
| 0.356 | 25.0 | 3925 | 0.4164 |
|
75 |
+
| 0.3588 | 26.0 | 4082 | 0.4152 |
|
76 |
+
| 0.3465 | 27.0 | 4239 | 0.4146 |
|
77 |
+
| 0.3465 | 28.0 | 4396 | 0.4133 |
|
78 |
+
| 0.3431 | 29.0 | 4553 | 0.4123 |
|
79 |
+
| 0.3451 | 30.0 | 4710 | 0.4119 |
|
80 |
+
|
81 |
+
|
82 |
+
### Framework versions
|
83 |
+
|
84 |
+
- Transformers 4.44.2
|
85 |
+
- Pytorch 2.4.0+cu121
|
86 |
+
- Datasets 2.21.0
|
87 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
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 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"problem_type": "single_label_classification",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.44.2",
|
24 |
+
"type_vocab_size": 2,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 30522
|
27 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:140ee23b6043965730fc9d3eba5745046cfaf08f2e34a76e6ada487bb4967dda
|
3 |
+
size 437958648
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:519f07488259e50c9ae517bb396afa5cbf4a6209556d000728d087e82df7e9fb
|
3 |
+
size 5176
|