allistair99
commited on
Commit
•
3481e1f
1
Parent(s):
76bf8ce
BiLSTM test 1
Browse files- README.md +58 -0
- config.json +33 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: csarron/mobilebert-uncased-squad-v1
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: MobileBERT-uncased-squad-v1-BiLSTM-finetuned-squad-fc1-resize-dropout
|
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 |
+
# MobileBERT-uncased-squad-v1-BiLSTM-finetuned-squad-fc1-resize-dropout
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [csarron/mobilebert-uncased-squad-v1](https://huggingface.co/csarron/mobilebert-uncased-squad-v1) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 1.0322
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 3e-05
|
38 |
+
- train_batch_size: 6
|
39 |
+
- eval_batch_size: 60
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 2
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
49 |
+
| 0.5688 | 1.0 | 14619 | 1.0454 |
|
50 |
+
| 0.5474 | 2.0 | 29238 | 1.0322 |
|
51 |
+
|
52 |
+
|
53 |
+
### Framework versions
|
54 |
+
|
55 |
+
- Transformers 4.40.0
|
56 |
+
- Pytorch 2.4.0+cu121
|
57 |
+
- Datasets 2.21.0
|
58 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "csarron/mobilebert-uncased-squad-v1",
|
3 |
+
"architectures": [
|
4 |
+
"MobileBertForQuestionAnswering1"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_activation": false,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"embedding_size": 128,
|
10 |
+
"hidden_act": "relu",
|
11 |
+
"hidden_dropout_prob": 0.0,
|
12 |
+
"hidden_size": 512,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 512,
|
15 |
+
"intra_bottleneck_size": 128,
|
16 |
+
"key_query_shared_bottleneck": true,
|
17 |
+
"layer_norm_eps": 1e-12,
|
18 |
+
"max_position_embeddings": 512,
|
19 |
+
"model_type": "mobilebert",
|
20 |
+
"normalization_type": "no_norm",
|
21 |
+
"num_attention_heads": 4,
|
22 |
+
"num_feedforward_networks": 4,
|
23 |
+
"num_hidden_layers": 24,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.40.0",
|
27 |
+
"trigram_input": true,
|
28 |
+
"true_hidden_size": 128,
|
29 |
+
"type_vocab_size": 2,
|
30 |
+
"use_bottleneck": true,
|
31 |
+
"use_bottleneck_attention": false,
|
32 |
+
"vocab_size": 30522
|
33 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a7732f81b52d823ce659f7930fdd90b19e570aab74b6ee98009b87715d57049
|
3 |
+
size 117380688
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac5651ee2ce138a3e687899386388e11357cbfa0a0695687a09040a2eb1358a7
|
3 |
+
size 4984
|