End of training
Browse files- README.md +4 -36
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -22,7 +22,7 @@ model-index:
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
-
value: 0.
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
32 |
|
33 |
This model is a fine-tuned version of [t5-3b](https://huggingface.co/t5-3b) on the glue dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss:
|
36 |
-
- Accuracy: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -62,42 +62,10 @@ The following hyperparameters were used during training:
|
|
62 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
63 |
- lr_scheduler_type: linear
|
64 |
- lr_scheduler_warmup_steps: 20
|
65 |
-
- training_steps:
|
66 |
|
67 |
### Training results
|
68 |
|
69 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
70 |
-
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
71 |
-
| 0.7116 | 0.18 | 25 | 0.7078 | 0.4838 |
|
72 |
-
| 0.615 | 0.36 | 50 | 0.4571 | 0.8484 |
|
73 |
-
| 0.501 | 0.53 | 75 | 0.4176 | 0.8484 |
|
74 |
-
| 0.337 | 0.71 | 100 | 0.4462 | 0.8809 |
|
75 |
-
| 0.4199 | 0.89 | 125 | 0.4309 | 0.7942 |
|
76 |
-
| 0.2477 | 1.07 | 150 | 0.4325 | 0.8881 |
|
77 |
-
| 0.2253 | 1.25 | 175 | 0.4596 | 0.8845 |
|
78 |
-
| 0.214 | 1.42 | 200 | 0.9106 | 0.8736 |
|
79 |
-
| 0.2577 | 1.6 | 225 | 0.3652 | 0.9025 |
|
80 |
-
| 0.1966 | 1.78 | 250 | 0.3645 | 0.9097 |
|
81 |
-
| 0.2278 | 1.96 | 275 | 0.3337 | 0.9206 |
|
82 |
-
| 0.1221 | 2.14 | 300 | 1.2373 | 0.8881 |
|
83 |
-
| 0.3576 | 2.31 | 325 | 2.0514 | 0.8809 |
|
84 |
-
| 0.6186 | 2.49 | 350 | 3.9886 | 0.8809 |
|
85 |
-
| 1.0915 | 2.67 | 375 | 3.3403 | 0.8845 |
|
86 |
-
| 0.321 | 2.85 | 400 | 4.6906 | 0.8989 |
|
87 |
-
| 0.3969 | 3.02 | 425 | 1.2608 | 0.8736 |
|
88 |
-
| 0.026 | 3.2 | 450 | 4.4563 | 0.8809 |
|
89 |
-
| 0.0695 | 3.38 | 475 | 4.6858 | 0.8917 |
|
90 |
-
| 0.7626 | 3.56 | 500 | 4.7502 | 0.8917 |
|
91 |
-
| 0.2675 | 3.74 | 525 | 5.0576 | 0.9025 |
|
92 |
-
| 0.82 | 3.91 | 550 | 3.6297 | 0.9025 |
|
93 |
-
| 0.0011 | 4.09 | 575 | 5.7629 | 0.8989 |
|
94 |
-
| 0.3 | 4.27 | 600 | 2.3117 | 0.9097 |
|
95 |
-
| 0.0544 | 4.45 | 625 | 1.5657 | 0.9097 |
|
96 |
-
| 0.2907 | 4.63 | 650 | 2.6475 | 0.9025 |
|
97 |
-
| 0.2868 | 4.8 | 675 | 2.6720 | 0.8989 |
|
98 |
-
| 0.3191 | 4.98 | 700 | 2.8372 | 0.8773 |
|
99 |
-
| 0.0382 | 5.16 | 725 | 6.0565 | 0.9025 |
|
100 |
-
| 0.0297 | 5.34 | 750 | 4.1639 | 0.8736 |
|
101 |
|
102 |
|
103 |
### Framework versions
|
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.5020080321285141
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
32 |
|
33 |
This model is a fine-tuned version of [t5-3b](https://huggingface.co/t5-3b) on the glue dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.6987
|
36 |
+
- Accuracy: 0.5020
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
62 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
63 |
- lr_scheduler_type: linear
|
64 |
- lr_scheduler_warmup_steps: 20
|
65 |
+
- training_steps: 10
|
66 |
|
67 |
### Training results
|
68 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
69 |
|
70 |
|
71 |
### Framework versions
|
model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4998578592
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3d132e48c56c2a3c98b8dfd074a7331a4e8dd6c57d69d7b6e072d06b8b3c4f7
|
3 |
size 4998578592
|
model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 706803048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:997d238e64f55cead08bba494861ed782701a055e4de969fe113cf0117610683
|
3 |
size 706803048
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6264
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ccb5d413ce0fecdc6d74615b3d685925f0baebe79e635522159e089df01c44b
|
3 |
size 6264
|