End of training
Browse files- README.md +25 -39
- 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 |
|
@@ -16,13 +16,14 @@ should probably proofread and complete it, then remove this comment. -->
|
|
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 |
-
|
|
|
20 |
|
21 |
-
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the Luganda
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 0.
|
24 |
-
- Bleu:
|
25 |
-
- Gen Len:
|
26 |
|
27 |
## Model description
|
28 |
|
@@ -47,42 +48,27 @@ The following hyperparameters were used during training:
|
|
47 |
- seed: 42
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: linear
|
50 |
-
- num_epochs:
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
-
| Training Loss | Epoch | Step
|
55 |
-
|
56 |
-
|
|
57 |
-
|
|
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 |
-
| 0.
|
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
|
|
|
6 |
metrics:
|
7 |
- bleu
|
8 |
model-index:
|
9 |
+
- name: ft-t5-small-on-info-lg-formal
|
10 |
results: []
|
11 |
---
|
12 |
|
|
|
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 |
+
[<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)
|
20 |
+
# ft-t5-small-on-info-lg-formal
|
21 |
|
22 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the Luganda Formal Data dataset.
|
23 |
It achieves the following results on the evaluation set:
|
24 |
+
- Loss: 0.1997
|
25 |
+
- Bleu: 15.1631
|
26 |
+
- Gen Len: 12.3001
|
27 |
|
28 |
## Model description
|
29 |
|
|
|
48 |
- seed: 42
|
49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
- lr_scheduler_type: linear
|
51 |
+
- num_epochs: 15
|
52 |
|
53 |
### Training results
|
54 |
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
56 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
|
57 |
+
| 0.5515 | 1.0 | 846 | 0.3160 | 1.5468 | 12.8596 |
|
58 |
+
| 0.3157 | 2.0 | 1692 | 0.2813 | 3.6176 | 13.2076 |
|
59 |
+
| 0.2801 | 3.0 | 2538 | 0.2576 | 5.4512 | 12.9075 |
|
60 |
+
| 0.2655 | 4.0 | 3384 | 0.2432 | 7.2817 | 12.6248 |
|
61 |
+
| 0.2468 | 5.0 | 4230 | 0.2307 | 8.9484 | 12.6766 |
|
62 |
+
| 0.2339 | 6.0 | 5076 | 0.2228 | 10.7122 | 12.475 |
|
63 |
+
| 0.225 | 7.0 | 5922 | 0.2165 | 11.5595 | 12.4025 |
|
64 |
+
| 0.2152 | 8.0 | 6768 | 0.2119 | 12.6485 | 12.3446 |
|
65 |
+
| 0.2094 | 9.0 | 7614 | 0.2079 | 12.9033 | 12.5243 |
|
66 |
+
| 0.2053 | 10.0 | 8460 | 0.2048 | 13.9509 | 12.4165 |
|
67 |
+
| 0.2019 | 11.0 | 9306 | 0.2033 | 14.4313 | 12.2947 |
|
68 |
+
| 0.1975 | 12.0 | 10152 | 0.2014 | 14.6399 | 12.2768 |
|
69 |
+
| 0.195 | 13.0 | 10998 | 0.2004 | 14.9622 | 12.3094 |
|
70 |
+
| 0.1927 | 14.0 | 11844 | 0.2000 | 14.8282 | 12.3087 |
|
71 |
+
| 0.1917 | 15.0 | 12690 | 0.1997 | 15.1631 | 12.3001 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
72 |
|
73 |
|
74 |
### 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 sha256:67a3da3450b18b1ac896739d00b18f12cc3a19f613f8a8a1718d2f5eef3cba1c
|
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 sha256:952ea275baecca372ce298c1bcdbb8afbbd5ad787e37799a00eed7443d0ef7cb
|
3 |
size 5240
|