przybytniowska
commited on
Commit
•
7ef0024
1
Parent(s):
f3f21d9
Training complete
Browse files- README.md +52 -0
- pytorch_model.bin +1 -1
- test_metrics.json +3 -0
- train_losses.csv +33 -0
README.md
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: FacebookAI/roberta-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: roberta_base_TextClass_IMDB_adafactor
|
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 |
+
# roberta_base_TextClass_IMDB_adafactor
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset.
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 2e-05
|
36 |
+
- train_batch_size: 8
|
37 |
+
- eval_batch_size: 8
|
38 |
+
- seed: 42
|
39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
+
- lr_scheduler_type: linear
|
41 |
+
- num_epochs: 5
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
|
46 |
+
|
47 |
+
### Framework versions
|
48 |
+
|
49 |
+
- Transformers 4.34.1
|
50 |
+
- Pytorch 2.3.0+cu118
|
51 |
+
- Datasets 2.19.0
|
52 |
+
- Tokenizers 0.14.1
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 498658094
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cb8fd062124d3de8ea642f2a404d76bcfd627beae78fabb52b4a79e78bdb20f
|
3 |
size 498658094
|
test_metrics.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"test_accuracy": 0.95448
|
3 |
+
}
|
train_losses.csv
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
loss,epoch
|
2 |
+
0.3771,0.16
|
3 |
+
0.2988,0.32
|
4 |
+
0.3083,0.48
|
5 |
+
0.2859,0.64
|
6 |
+
0.2674,0.8
|
7 |
+
0.2695,0.96
|
8 |
+
0.1869,1.12
|
9 |
+
0.1987,1.28
|
10 |
+
0.2158,1.44
|
11 |
+
0.1779,1.6
|
12 |
+
0.1949,1.76
|
13 |
+
0.1896,1.92
|
14 |
+
0.1317,2.08
|
15 |
+
0.116,2.24
|
16 |
+
0.1082,2.4
|
17 |
+
0.0951,2.56
|
18 |
+
0.1068,2.72
|
19 |
+
0.1222,2.88
|
20 |
+
0.0989,3.04
|
21 |
+
0.0626,3.2
|
22 |
+
0.0675,3.36
|
23 |
+
0.0425,3.52
|
24 |
+
0.0506,3.68
|
25 |
+
0.0608,3.84
|
26 |
+
0.04,4.0
|
27 |
+
0.0306,4.16
|
28 |
+
0.0474,4.32
|
29 |
+
0.0273,4.48
|
30 |
+
0.0317,4.64
|
31 |
+
0.0433,4.8
|
32 |
+
0.0296,4.96
|
33 |
+
0.13712727940368652,5.0
|