henryscheible
commited on
Commit
•
300084f
1
Parent(s):
8a629e6
update model card README.md
Browse files
README.md
CHANGED
@@ -2,9 +2,26 @@
|
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
5 |
model-index:
|
6 |
- name: t5-small_crows_pairs_finetuned
|
7 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
---
|
9 |
|
10 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -12,7 +29,14 @@ should probably proofread and complete it, then remove this comment. -->
|
|
12 |
|
13 |
# t5-small_crows_pairs_finetuned
|
14 |
|
15 |
-
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
|
17 |
## Model description
|
18 |
|
@@ -39,6 +63,59 @@ The following hyperparameters were used during training:
|
|
39 |
- lr_scheduler_type: linear
|
40 |
- num_epochs: 50
|
41 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
### Framework versions
|
43 |
|
44 |
- Transformers 4.26.1
|
|
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- crows_pairs
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
model-index:
|
10 |
- name: t5-small_crows_pairs_finetuned
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Sequence-to-sequence Language Modeling
|
14 |
+
type: text2text-generation
|
15 |
+
dataset:
|
16 |
+
name: crows_pairs
|
17 |
+
type: crows_pairs
|
18 |
+
config: crows_pairs
|
19 |
+
split: test
|
20 |
+
args: crows_pairs
|
21 |
+
metrics:
|
22 |
+
- name: Accuracy
|
23 |
+
type: accuracy
|
24 |
+
value: 0.49337748344370863
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
29 |
|
30 |
# t5-small_crows_pairs_finetuned
|
31 |
|
32 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the crows_pairs dataset.
|
33 |
+
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.3224
|
35 |
+
- Accuracy: 0.4934
|
36 |
+
- Tp: 0.4868
|
37 |
+
- Tn: 0.0066
|
38 |
+
- Fp: 0.5066
|
39 |
+
- Fn: 0.0
|
40 |
|
41 |
## Model description
|
42 |
|
|
|
63 |
- lr_scheduler_type: linear
|
64 |
- num_epochs: 50
|
65 |
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Tp | Tn | Fp | Fn |
|
69 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|
|
70 |
+
| 6.2415 | 1.05 | 20 | 5.3021 | 0.6689 | 0.4868 | 0.1821 | 0.3311 | 0.0 |
|
71 |
+
| 3.2024 | 2.11 | 40 | 2.0108 | 0.7119 | 0.3874 | 0.3245 | 0.1887 | 0.0993 |
|
72 |
+
| 1.0469 | 3.16 | 60 | 0.5733 | 0.5232 | 0.4868 | 0.0364 | 0.4768 | 0.0 |
|
73 |
+
| 0.4873 | 4.21 | 80 | 0.3613 | 0.4868 | 0.4868 | 0.0 | 0.5132 | 0.0 |
|
74 |
+
| 0.4485 | 5.26 | 100 | 0.3531 | 0.4868 | 0.4868 | 0.0 | 0.5132 | 0.0 |
|
75 |
+
| 0.4014 | 6.32 | 120 | 0.3609 | 0.4868 | 0.4868 | 0.0 | 0.5132 | 0.0 |
|
76 |
+
| 0.3846 | 7.37 | 140 | 0.3549 | 0.4868 | 0.4868 | 0.0 | 0.5132 | 0.0 |
|
77 |
+
| 0.4003 | 8.42 | 160 | 0.3539 | 0.4868 | 0.4868 | 0.0 | 0.5132 | 0.0 |
|
78 |
+
| 0.3725 | 9.47 | 180 | 0.3569 | 0.4868 | 0.4868 | 0.0 | 0.5132 | 0.0 |
|
79 |
+
| 0.3435 | 10.53 | 200 | 0.3544 | 0.4868 | 0.4868 | 0.0 | 0.5132 | 0.0 |
|
80 |
+
| 0.3467 | 11.58 | 220 | 0.3555 | 0.4868 | 0.4868 | 0.0 | 0.5132 | 0.0 |
|
81 |
+
| 0.3426 | 12.63 | 240 | 0.3528 | 0.4868 | 0.4868 | 0.0 | 0.5132 | 0.0 |
|
82 |
+
| 0.346 | 13.68 | 260 | 0.3499 | 0.4868 | 0.4868 | 0.0 | 0.5132 | 0.0 |
|
83 |
+
| 0.338 | 14.74 | 280 | 0.3464 | 0.4868 | 0.4868 | 0.0 | 0.5132 | 0.0 |
|
84 |
+
| 0.3233 | 15.79 | 300 | 0.3489 | 0.4868 | 0.4868 | 0.0 | 0.5132 | 0.0 |
|
85 |
+
| 0.3283 | 16.84 | 320 | 0.3413 | 0.4868 | 0.4868 | 0.0 | 0.5132 | 0.0 |
|
86 |
+
| 0.3079 | 17.89 | 340 | 0.3408 | 0.4868 | 0.4868 | 0.0 | 0.5132 | 0.0 |
|
87 |
+
| 0.3099 | 18.95 | 360 | 0.3339 | 0.4868 | 0.4868 | 0.0 | 0.5132 | 0.0 |
|
88 |
+
| 0.2912 | 20.0 | 380 | 0.3296 | 0.4868 | 0.4868 | 0.0 | 0.5132 | 0.0 |
|
89 |
+
| 0.2864 | 21.05 | 400 | 0.3224 | 0.4868 | 0.4868 | 0.0 | 0.5132 | 0.0 |
|
90 |
+
| 0.2821 | 22.11 | 420 | 0.3200 | 0.4868 | 0.4868 | 0.0 | 0.5132 | 0.0 |
|
91 |
+
| 0.2753 | 23.16 | 440 | 0.3140 | 0.4901 | 0.4868 | 0.0033 | 0.5099 | 0.0 |
|
92 |
+
| 0.2531 | 24.21 | 460 | 0.3110 | 0.4901 | 0.4868 | 0.0033 | 0.5099 | 0.0 |
|
93 |
+
| 0.2637 | 25.26 | 480 | 0.3115 | 0.4901 | 0.4868 | 0.0033 | 0.5099 | 0.0 |
|
94 |
+
| 0.2624 | 26.32 | 500 | 0.3090 | 0.4901 | 0.4868 | 0.0033 | 0.5099 | 0.0 |
|
95 |
+
| 0.233 | 27.37 | 520 | 0.3056 | 0.4901 | 0.4868 | 0.0033 | 0.5099 | 0.0 |
|
96 |
+
| 0.2402 | 28.42 | 540 | 0.3037 | 0.4901 | 0.4868 | 0.0033 | 0.5099 | 0.0 |
|
97 |
+
| 0.2448 | 29.47 | 560 | 0.3081 | 0.4901 | 0.4868 | 0.0033 | 0.5099 | 0.0 |
|
98 |
+
| 0.248 | 30.53 | 580 | 0.3064 | 0.4901 | 0.4868 | 0.0033 | 0.5099 | 0.0 |
|
99 |
+
| 0.2184 | 31.58 | 600 | 0.3066 | 0.4901 | 0.4868 | 0.0033 | 0.5099 | 0.0 |
|
100 |
+
| 0.2278 | 32.63 | 620 | 0.3075 | 0.4901 | 0.4868 | 0.0033 | 0.5099 | 0.0 |
|
101 |
+
| 0.2158 | 33.68 | 640 | 0.3076 | 0.4901 | 0.4868 | 0.0033 | 0.5099 | 0.0 |
|
102 |
+
| 0.222 | 34.74 | 660 | 0.3107 | 0.4901 | 0.4868 | 0.0033 | 0.5099 | 0.0 |
|
103 |
+
| 0.2142 | 35.79 | 680 | 0.3128 | 0.4901 | 0.4868 | 0.0033 | 0.5099 | 0.0 |
|
104 |
+
| 0.2166 | 36.84 | 700 | 0.3117 | 0.4901 | 0.4868 | 0.0033 | 0.5099 | 0.0 |
|
105 |
+
| 0.1967 | 37.89 | 720 | 0.3157 | 0.4901 | 0.4868 | 0.0033 | 0.5099 | 0.0 |
|
106 |
+
| 0.201 | 38.95 | 740 | 0.3155 | 0.4901 | 0.4868 | 0.0033 | 0.5099 | 0.0 |
|
107 |
+
| 0.1984 | 40.0 | 760 | 0.3166 | 0.4934 | 0.4868 | 0.0066 | 0.5066 | 0.0 |
|
108 |
+
| 0.1968 | 41.05 | 780 | 0.3191 | 0.4934 | 0.4868 | 0.0066 | 0.5066 | 0.0 |
|
109 |
+
| 0.1777 | 42.11 | 800 | 0.3199 | 0.4934 | 0.4868 | 0.0066 | 0.5066 | 0.0 |
|
110 |
+
| 0.2044 | 43.16 | 820 | 0.3203 | 0.4934 | 0.4868 | 0.0066 | 0.5066 | 0.0 |
|
111 |
+
| 0.1915 | 44.21 | 840 | 0.3210 | 0.4934 | 0.4868 | 0.0066 | 0.5066 | 0.0 |
|
112 |
+
| 0.1998 | 45.26 | 860 | 0.3214 | 0.4934 | 0.4868 | 0.0066 | 0.5066 | 0.0 |
|
113 |
+
| 0.1956 | 46.32 | 880 | 0.3214 | 0.4934 | 0.4868 | 0.0066 | 0.5066 | 0.0 |
|
114 |
+
| 0.1908 | 47.37 | 900 | 0.3223 | 0.4934 | 0.4868 | 0.0066 | 0.5066 | 0.0 |
|
115 |
+
| 0.1992 | 48.42 | 920 | 0.3224 | 0.4934 | 0.4868 | 0.0066 | 0.5066 | 0.0 |
|
116 |
+
| 0.2 | 49.47 | 940 | 0.3224 | 0.4934 | 0.4868 | 0.0066 | 0.5066 | 0.0 |
|
117 |
+
|
118 |
+
|
119 |
### Framework versions
|
120 |
|
121 |
- Transformers 4.26.1
|