End of training
Browse files- README.md +2 -23
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -3,9 +3,6 @@ license: mit
|
|
3 |
base_model: microsoft/git-base
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
-
metrics:
|
7 |
-
- wer
|
8 |
-
- rouge
|
9 |
model-index:
|
10 |
- name: git-base-env
|
11 |
results: []
|
@@ -17,13 +14,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
# git-base-env
|
18 |
|
19 |
This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
|
20 |
-
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 8.4059
|
22 |
-
- Wer: 59.0853
|
23 |
-
- Rouge1: 1.86
|
24 |
-
- Rouge2: 0.57
|
25 |
-
- Rougel: 1.63
|
26 |
-
- Rougelsum: 1.63
|
27 |
|
28 |
## Model description
|
29 |
|
@@ -42,24 +32,13 @@ More information needed
|
|
42 |
### Training hyperparameters
|
43 |
|
44 |
The following hyperparameters were used during training:
|
45 |
-
- learning_rate: 5e-
|
46 |
- train_batch_size: 1
|
47 |
- eval_batch_size: 1
|
48 |
- seed: 42
|
49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
- lr_scheduler_type: linear
|
51 |
-
- num_epochs:
|
52 |
-
|
53 |
-
### Training results
|
54 |
-
|
55 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
56 |
-
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:------:|:------:|:---------:|
|
57 |
-
| 8.6175 | 0.6 | 30 | 8.4884 | 59.0612 | 1.84 | 0.5 | 1.56 | 1.56 |
|
58 |
-
| 8.5757 | 1.2 | 60 | 8.4512 | 58.9443 | 1.81 | 0.53 | 1.57 | 1.57 |
|
59 |
-
| 8.541 | 1.8 | 90 | 8.4258 | 59.2653 | 1.86 | 0.56 | 1.62 | 1.62 |
|
60 |
-
| 8.5196 | 2.4 | 120 | 8.4114 | 58.9926 | 1.84 | 0.57 | 1.62 | 1.62 |
|
61 |
-
| 8.5091 | 3.0 | 150 | 8.4059 | 59.0853 | 1.86 | 0.57 | 1.63 | 1.63 |
|
62 |
-
|
63 |
|
64 |
### Framework versions
|
65 |
|
|
|
3 |
base_model: microsoft/git-base
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
|
|
6 |
model-index:
|
7 |
- name: git-base-env
|
8 |
results: []
|
|
|
14 |
# git-base-env
|
15 |
|
16 |
This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
32 |
### Training hyperparameters
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 5e-05
|
36 |
- train_batch_size: 1
|
37 |
- eval_batch_size: 1
|
38 |
- seed: 42
|
39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
- lr_scheduler_type: linear
|
41 |
+
- num_epochs: 5
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
|
43 |
### Framework versions
|
44 |
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 706584273
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bb19154d60ae63b3c0f48b8bba14ade2d67ace854ee6b7101f0d428c35d9946
|
3 |
size 706584273
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4027
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa9fbc2bc75f566f204e7b3a142a4d8b40f24d65a9cb39b7cfe674c3aef4e23b
|
3 |
size 4027
|