kennethge123
commited on
Model save
Browse files- README.md +94 -0
- config.json +27 -0
- model.safetensors +3 -0
- runs/Mar22_22-14-30_dsail2/events.out.tfevents.1711160073.dsail2.27308.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: bert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- bigbench
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: bigbench_entailedpolarity-bert-base-uncased
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Text Classification
|
15 |
+
type: text-classification
|
16 |
+
dataset:
|
17 |
+
name: bigbench
|
18 |
+
type: bigbench
|
19 |
+
config: entailed_polarity
|
20 |
+
split: train
|
21 |
+
args: entailed_polarity
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.9583333333333334
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# bigbench_entailedpolarity-bert-base-uncased
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the bigbench dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.3706
|
36 |
+
- Accuracy: 0.9583
|
37 |
+
|
38 |
+
## Model description
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Intended uses & limitations
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training and evaluation data
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training procedure
|
51 |
+
|
52 |
+
### Training hyperparameters
|
53 |
+
|
54 |
+
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 5e-05
|
56 |
+
- train_batch_size: 4
|
57 |
+
- eval_batch_size: 32
|
58 |
+
- seed: 42
|
59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
+
- lr_scheduler_type: linear
|
61 |
+
- num_epochs: 20
|
62 |
+
|
63 |
+
### Training results
|
64 |
+
|
65 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
66 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
67 |
+
| No log | 1.0 | 24 | 0.5613 | 0.7917 |
|
68 |
+
| No log | 2.0 | 48 | 0.5337 | 0.7917 |
|
69 |
+
| No log | 3.0 | 72 | 0.3178 | 0.875 |
|
70 |
+
| No log | 4.0 | 96 | 0.1924 | 0.9167 |
|
71 |
+
| No log | 5.0 | 120 | 0.2007 | 0.9583 |
|
72 |
+
| No log | 6.0 | 144 | 0.2766 | 0.9583 |
|
73 |
+
| No log | 7.0 | 168 | 0.3031 | 0.9583 |
|
74 |
+
| No log | 8.0 | 192 | 0.3291 | 0.9583 |
|
75 |
+
| No log | 9.0 | 216 | 0.3381 | 0.9583 |
|
76 |
+
| No log | 10.0 | 240 | 0.3454 | 0.9583 |
|
77 |
+
| No log | 11.0 | 264 | 0.3508 | 0.9583 |
|
78 |
+
| No log | 12.0 | 288 | 0.3554 | 0.9583 |
|
79 |
+
| No log | 13.0 | 312 | 0.3592 | 0.9583 |
|
80 |
+
| No log | 14.0 | 336 | 0.3624 | 0.9583 |
|
81 |
+
| No log | 15.0 | 360 | 0.3650 | 0.9583 |
|
82 |
+
| No log | 16.0 | 384 | 0.3671 | 0.9583 |
|
83 |
+
| No log | 17.0 | 408 | 0.3686 | 0.9583 |
|
84 |
+
| No log | 18.0 | 432 | 0.3696 | 0.9583 |
|
85 |
+
| No log | 19.0 | 456 | 0.3704 | 0.9583 |
|
86 |
+
| No log | 20.0 | 480 | 0.3706 | 0.9583 |
|
87 |
+
|
88 |
+
|
89 |
+
### Framework versions
|
90 |
+
|
91 |
+
- Transformers 4.35.2
|
92 |
+
- Pytorch 1.10.1+cu102
|
93 |
+
- Datasets 2.15.0
|
94 |
+
- Tokenizers 0.15.0
|
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": "4.35.2",
|
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 sha256:53f3df42692fec5ee20e4168e47ea4057f122c99d937a15f1d964ba649cc8e7c
|
3 |
+
size 437958648
|
runs/Mar22_22-14-30_dsail2/events.out.tfevents.1711160073.dsail2.27308.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e22039e9c3341da2f98556fe221a332b86f211300c95c05ad52013185f4938e
|
3 |
+
size 11053
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48b3818370ff93c642d77d0a08849df6a0643f047221ea22db26ed9da8f13162
|
3 |
+
size 4271
|