willherbert27
commited on
Commit
•
451c7ca
1
Parent(s):
406e19d
willherbert27/bert-combined-no-context-textbook
Browse files- README.md +76 -0
- config.json +26 -0
- generation_config.json +5 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google-bert/bert-base-cased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: bert-finetuned-combo-textbook-no-context
|
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 |
+
# bert-finetuned-combo-textbook-no-context
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 1.6241
|
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: 0.0001
|
38 |
+
- train_batch_size: 16
|
39 |
+
- eval_batch_size: 8
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 20
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
49 |
+
| 2.4652 | 1.0 | 2444 | 2.2878 |
|
50 |
+
| 2.2439 | 2.0 | 4888 | 2.2005 |
|
51 |
+
| 2.1422 | 3.0 | 7332 | 2.1331 |
|
52 |
+
| 2.0527 | 4.0 | 9776 | 2.0734 |
|
53 |
+
| 1.9734 | 5.0 | 12220 | 2.0488 |
|
54 |
+
| 1.8752 | 6.0 | 14664 | 1.9844 |
|
55 |
+
| 1.7757 | 7.0 | 17108 | 1.9257 |
|
56 |
+
| 1.7478 | 8.0 | 19552 | 1.8901 |
|
57 |
+
| 1.6469 | 9.0 | 21996 | 1.8797 |
|
58 |
+
| 1.5894 | 10.0 | 24440 | 1.8198 |
|
59 |
+
| 1.5341 | 11.0 | 26884 | 1.7803 |
|
60 |
+
| 1.4563 | 12.0 | 29328 | 1.7602 |
|
61 |
+
| 1.4385 | 13.0 | 31772 | 1.7663 |
|
62 |
+
| 1.3534 | 14.0 | 34216 | 1.7007 |
|
63 |
+
| 1.3007 | 15.0 | 36660 | 1.6705 |
|
64 |
+
| 1.2689 | 16.0 | 39104 | 1.6996 |
|
65 |
+
| 1.2268 | 17.0 | 41548 | 1.6319 |
|
66 |
+
| 1.2152 | 18.0 | 43992 | 1.6599 |
|
67 |
+
| 1.1317 | 19.0 | 46436 | 1.6433 |
|
68 |
+
| 1.1133 | 20.0 | 48880 | 1.6241 |
|
69 |
+
|
70 |
+
|
71 |
+
### Framework versions
|
72 |
+
|
73 |
+
- Transformers 4.38.2
|
74 |
+
- Pytorch 1.13.1+cu116
|
75 |
+
- Datasets 2.18.0
|
76 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForMaskedLM"
|
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 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.38.2",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 28996
|
26 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"pad_token_id": 0,
|
4 |
+
"transformers_version": "4.38.2"
|
5 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8aa2f143825eed75d9ccffefc75df09a3e2e885e471f4a0c63c7eedbf404a34b
|
3 |
+
size 433386912
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bee92089cc496f0c0135ccfe8da85932e68c1312461e5e4e4d9ccfcc2c5c67eb
|
3 |
+
size 4475
|