End of training
Browse files- README.md +38 -22
- model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -6,7 +6,7 @@ tags:
|
|
6 |
metrics:
|
7 |
- bleu
|
8 |
model-index:
|
9 |
-
- name: ft-t5-small-on-info-lg
|
10 |
results: []
|
11 |
---
|
12 |
|
@@ -15,13 +15,14 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/asr-africa-research-team/huggingface/runs/ben1m3wk)
|
17 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/asr-africa-research-team/huggingface/runs/ben1m3wk)
|
18 |
-
|
|
|
19 |
|
20 |
-
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the
|
21 |
It achieves the following results on the evaluation set:
|
22 |
-
- Loss: 0.
|
23 |
-
- Bleu: 0.
|
24 |
-
- Gen Len: 15.
|
25 |
|
26 |
## Model description
|
27 |
|
@@ -46,27 +47,42 @@ The following hyperparameters were used during training:
|
|
46 |
- seed: 42
|
47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
- lr_scheduler_type: linear
|
49 |
-
- num_epochs:
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
|
55 |
-
| No log | 1.0 | 177 | 0.
|
56 |
-
| No log | 2.0 | 354 | 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
70 |
|
71 |
|
72 |
### Framework versions
|
|
|
6 |
metrics:
|
7 |
- bleu
|
8 |
model-index:
|
9 |
+
- name: ft-t5-small-on-info-lg-v1
|
10 |
results: []
|
11 |
---
|
12 |
|
|
|
15 |
|
16 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/asr-africa-research-team/huggingface/runs/ben1m3wk)
|
17 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/asr-africa-research-team/huggingface/runs/ben1m3wk)
|
18 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/asr-africa-research-team/huggingface/runs/ben1m3wk)
|
19 |
+
# ft-t5-small-on-info-lg-v1
|
20 |
|
21 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the Luganda Proverbs dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.5949
|
24 |
+
- Bleu: 0.2654
|
25 |
+
- Gen Len: 15.9299
|
26 |
|
27 |
## Model description
|
28 |
|
|
|
47 |
- seed: 42
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: linear
|
50 |
+
- num_epochs: 30
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
55 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
|
56 |
+
| No log | 1.0 | 177 | 0.5884 | 0.347 | 15.8567 |
|
57 |
+
| No log | 2.0 | 354 | 0.5872 | 0.3173 | 16.4809 |
|
58 |
+
| 0.5373 | 3.0 | 531 | 0.5877 | 0.3232 | 16.2389 |
|
59 |
+
| 0.5373 | 4.0 | 708 | 0.5878 | 0.3198 | 16.2803 |
|
60 |
+
| 0.5373 | 5.0 | 885 | 0.5886 | 0.2831 | 14.465 |
|
61 |
+
| 0.5202 | 6.0 | 1062 | 0.5889 | 0.3702 | 15.4076 |
|
62 |
+
| 0.5202 | 7.0 | 1239 | 0.5881 | 0.3095 | 16.2325 |
|
63 |
+
| 0.5202 | 8.0 | 1416 | 0.5880 | 0.2826 | 15.4045 |
|
64 |
+
| 0.5097 | 9.0 | 1593 | 0.5885 | 0.3264 | 15.9236 |
|
65 |
+
| 0.5097 | 10.0 | 1770 | 0.5886 | 0.3028 | 14.6592 |
|
66 |
+
| 0.5097 | 11.0 | 1947 | 0.5872 | 0.2958 | 15.0064 |
|
67 |
+
| 0.4995 | 12.0 | 2124 | 0.5882 | 0.22 | 14.8631 |
|
68 |
+
| 0.4995 | 13.0 | 2301 | 0.5876 | 0.2049 | 16.3726 |
|
69 |
+
| 0.4995 | 14.0 | 2478 | 0.5878 | 0.2635 | 15.8599 |
|
70 |
+
| 0.4921 | 15.0 | 2655 | 0.5892 | 0.3041 | 15.8248 |
|
71 |
+
| 0.4921 | 16.0 | 2832 | 0.5881 | 0.2746 | 15.8662 |
|
72 |
+
| 0.4838 | 17.0 | 3009 | 0.5909 | 0.2713 | 15.8121 |
|
73 |
+
| 0.4838 | 18.0 | 3186 | 0.5902 | 0.2587 | 15.4076 |
|
74 |
+
| 0.4838 | 19.0 | 3363 | 0.5917 | 0.3038 | 15.4331 |
|
75 |
+
| 0.4788 | 20.0 | 3540 | 0.5931 | 0.2837 | 15.3599 |
|
76 |
+
| 0.4788 | 21.0 | 3717 | 0.5930 | 0.306 | 15.0955 |
|
77 |
+
| 0.4788 | 22.0 | 3894 | 0.5940 | 0.2973 | 15.7229 |
|
78 |
+
| 0.4666 | 23.0 | 4071 | 0.5937 | 0.2458 | 16.0096 |
|
79 |
+
| 0.4666 | 24.0 | 4248 | 0.5936 | 0.2781 | 15.7389 |
|
80 |
+
| 0.4666 | 25.0 | 4425 | 0.5939 | 0.2998 | 15.5796 |
|
81 |
+
| 0.4643 | 26.0 | 4602 | 0.5943 | 0.2782 | 15.7293 |
|
82 |
+
| 0.4643 | 27.0 | 4779 | 0.5942 | 0.2685 | 15.5255 |
|
83 |
+
| 0.4643 | 28.0 | 4956 | 0.5948 | 0.2687 | 15.6815 |
|
84 |
+
| 0.4609 | 29.0 | 5133 | 0.5947 | 0.2658 | 15.9363 |
|
85 |
+
| 0.4609 | 30.0 | 5310 | 0.5949 | 0.2654 | 15.9299 |
|
86 |
|
87 |
|
88 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242041896
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56791b19d00f3226e1b26364deb9bd597ef6433cfa69de8933d57871df4b4ee1
|
3 |
size 242041896
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec30d8be119fdc691d79ecc75f5e0ed6661fa28f5d23df32441532788ccacae0
|
3 |
size 5240
|