End of training
Browse files- README.md +127 -0
- pytorch_model.bin +1 -1
README.md
ADDED
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: t5-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- glue
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: t5-base_sst2_dense_epochs-8
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Text Classification
|
15 |
+
type: text-classification
|
16 |
+
dataset:
|
17 |
+
name: glue
|
18 |
+
type: glue
|
19 |
+
config: sst2
|
20 |
+
split: validation
|
21 |
+
args: sst2
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.9346330275229358
|
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 |
+
# t5-base_sst2_dense_epochs-8
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the glue dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.2931
|
36 |
+
- Accuracy: 0.9346
|
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: 32
|
57 |
+
- eval_batch_size: 64
|
58 |
+
- seed: 0
|
59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
+
- lr_scheduler_type: linear
|
61 |
+
- lr_scheduler_warmup_steps: 20
|
62 |
+
- num_epochs: 8
|
63 |
+
|
64 |
+
### Training results
|
65 |
+
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
68 |
+
| 0.6552 | 0.02 | 50 | 0.6446 | 0.6193 |
|
69 |
+
| 0.3237 | 0.05 | 100 | 0.2756 | 0.9071 |
|
70 |
+
| 0.2725 | 0.07 | 150 | 0.2409 | 0.9151 |
|
71 |
+
| 0.2353 | 0.1 | 200 | 0.2526 | 0.9128 |
|
72 |
+
| 0.2342 | 0.12 | 250 | 0.2287 | 0.9174 |
|
73 |
+
| 0.2635 | 0.14 | 300 | 0.2342 | 0.9220 |
|
74 |
+
| 0.2534 | 0.17 | 350 | 0.2149 | 0.9255 |
|
75 |
+
| 0.2402 | 0.19 | 400 | 0.2160 | 0.9255 |
|
76 |
+
| 0.1857 | 0.21 | 450 | 0.2117 | 0.9243 |
|
77 |
+
| 0.1696 | 0.24 | 500 | 0.3351 | 0.9266 |
|
78 |
+
| 0.1504 | 0.26 | 550 | 0.2275 | 0.9209 |
|
79 |
+
| 0.2849 | 0.29 | 600 | 0.2301 | 0.9255 |
|
80 |
+
| 0.2336 | 0.31 | 650 | 0.2332 | 0.9220 |
|
81 |
+
| 0.1587 | 0.33 | 700 | 0.2158 | 0.9243 |
|
82 |
+
| 0.2645 | 0.36 | 750 | 0.2075 | 0.9300 |
|
83 |
+
| 0.1809 | 0.38 | 800 | 0.2060 | 0.9255 |
|
84 |
+
| 0.1088 | 0.4 | 850 | 0.3409 | 0.9255 |
|
85 |
+
| 0.1623 | 0.43 | 900 | 0.3342 | 0.9289 |
|
86 |
+
| 0.1987 | 0.45 | 950 | 0.2280 | 0.9278 |
|
87 |
+
| 0.2622 | 0.48 | 1000 | 0.3327 | 0.9243 |
|
88 |
+
| 0.1121 | 0.5 | 1050 | 0.3205 | 0.9289 |
|
89 |
+
| 0.1831 | 0.52 | 1100 | 0.4233 | 0.9243 |
|
90 |
+
| 0.2456 | 0.55 | 1150 | 0.5359 | 0.9335 |
|
91 |
+
| 0.0938 | 0.57 | 1200 | 0.1931 | 0.9358 |
|
92 |
+
| 0.1321 | 0.59 | 1250 | 0.4359 | 0.9323 |
|
93 |
+
| 0.1478 | 0.62 | 1300 | 0.3059 | 0.9346 |
|
94 |
+
| 0.1819 | 0.64 | 1350 | 0.4172 | 0.9358 |
|
95 |
+
| 0.1178 | 0.67 | 1400 | 0.2997 | 0.9358 |
|
96 |
+
| 0.1426 | 0.69 | 1450 | 0.5336 | 0.9346 |
|
97 |
+
| 0.1033 | 0.71 | 1500 | 0.4292 | 0.9300 |
|
98 |
+
| 0.1357 | 0.74 | 1550 | 0.4310 | 0.9369 |
|
99 |
+
| 0.1668 | 0.76 | 1600 | 0.5359 | 0.9358 |
|
100 |
+
| 0.1438 | 0.78 | 1650 | 0.3025 | 0.9381 |
|
101 |
+
| 0.2141 | 0.81 | 1700 | 0.4265 | 0.9323 |
|
102 |
+
| 0.0899 | 0.83 | 1750 | 0.4217 | 0.9323 |
|
103 |
+
| 0.1062 | 0.86 | 1800 | 0.4377 | 0.9289 |
|
104 |
+
| 0.1557 | 0.88 | 1850 | 0.3003 | 0.9323 |
|
105 |
+
| 0.1237 | 0.9 | 1900 | 0.3134 | 0.9358 |
|
106 |
+
| 0.1172 | 0.93 | 1950 | 0.3199 | 0.9312 |
|
107 |
+
| 0.1617 | 0.95 | 2000 | 0.2931 | 0.9346 |
|
108 |
+
| 0.1293 | 0.97 | 2050 | 0.2978 | 0.9381 |
|
109 |
+
| 0.1686 | 1.0 | 2100 | 0.2885 | 0.9369 |
|
110 |
+
| 0.7247 | 1.02 | 2150 | 0.7872 | 0.9300 |
|
111 |
+
| 0.0679 | 1.05 | 2200 | 0.3114 | 0.9404 |
|
112 |
+
| 0.0522 | 1.07 | 2250 | 0.2998 | 0.9346 |
|
113 |
+
| 0.078 | 1.09 | 2300 | 0.3418 | 0.9358 |
|
114 |
+
| 0.0749 | 1.12 | 2350 | 0.3248 | 0.9381 |
|
115 |
+
| 0.0483 | 1.14 | 2400 | 0.4340 | 0.9369 |
|
116 |
+
| 0.1534 | 1.16 | 2450 | 0.4428 | 0.9358 |
|
117 |
+
| 0.1007 | 1.19 | 2500 | 0.4344 | 0.9369 |
|
118 |
+
| 0.0655 | 1.21 | 2550 | 0.3215 | 0.9369 |
|
119 |
+
| 0.074 | 1.24 | 2600 | 0.3182 | 0.9404 |
|
120 |
+
|
121 |
+
|
122 |
+
### Framework versions
|
123 |
+
|
124 |
+
- Transformers 4.34.1
|
125 |
+
- Pytorch 2.0.1+cu117
|
126 |
+
- Datasets 2.9.0
|
127 |
+
- 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 894094241
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e04f1d277b87df0e736c67b7e23234f55885b3ceb0780d500b5e7514d90136bf
|
3 |
size 894094241
|