mhr2004/bert-base-uncased-pp-1000-1e-06-8
Browse files- README.md +78 -0
- config.json +27 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-pp-1000-1e-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-pp-1000-1e-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: 0.6942
|
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 | 32 | 0.7053 |
|
51 |
+
| No log | 2.0 | 64 | 0.7014 |
|
52 |
+
| No log | 3.0 | 96 | 0.6994 |
|
53 |
+
| No log | 4.0 | 128 | 0.6983 |
|
54 |
+
| No log | 5.0 | 160 | 0.6972 |
|
55 |
+
| No log | 6.0 | 192 | 0.6967 |
|
56 |
+
| 0.6995 | 7.0 | 224 | 0.6959 |
|
57 |
+
| 0.6995 | 8.0 | 256 | 0.6955 |
|
58 |
+
| 0.6995 | 9.0 | 288 | 0.6953 |
|
59 |
+
| 0.6995 | 10.0 | 320 | 0.6951 |
|
60 |
+
| 0.6995 | 11.0 | 352 | 0.6949 |
|
61 |
+
| 0.6995 | 12.0 | 384 | 0.6948 |
|
62 |
+
| 0.69 | 13.0 | 416 | 0.6946 |
|
63 |
+
| 0.69 | 14.0 | 448 | 0.6945 |
|
64 |
+
| 0.69 | 15.0 | 480 | 0.6945 |
|
65 |
+
| 0.69 | 16.0 | 512 | 0.6944 |
|
66 |
+
| 0.69 | 17.0 | 544 | 0.6943 |
|
67 |
+
| 0.69 | 18.0 | 576 | 0.6942 |
|
68 |
+
| 0.6839 | 19.0 | 608 | 0.6943 |
|
69 |
+
| 0.6839 | 20.0 | 640 | 0.6943 |
|
70 |
+
| 0.6839 | 21.0 | 672 | 0.6943 |
|
71 |
+
|
72 |
+
|
73 |
+
### Framework versions
|
74 |
+
|
75 |
+
- Transformers 4.44.2
|
76 |
+
- Pytorch 2.4.0+cu121
|
77 |
+
- Datasets 2.21.0
|
78 |
+
- 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:a62f5de2e66ef72620f17924ea1c16966f995e6b9bd7a5253e6a9e7a3f0c1760
|
3 |
+
size 437958648
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e94789ff3c44b56811c0d3d1c5ac5df44466b203379ccaa89ed62020be33f919
|
3 |
+
size 5176
|