Training in progress, step 300
Browse files- README.md +9 -10
- config.json +3 -3
- pytorch_model.bin +2 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [ad019el/tamasheq-99-1](https://huggingface.co/ad019el/tamasheq-99-1) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss:
|
21 |
-
- Wer: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -46,23 +46,22 @@ The following hyperparameters were used during training:
|
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
48 |
- lr_scheduler_warmup_steps: 500
|
49 |
-
- num_epochs:
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
55 |
-
|
|
56 |
-
|
|
57 |
-
|
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.5422 | 47.37 | 1800 | 1.3783 | 0.8147 |
|
61 |
|
62 |
|
63 |
### Framework versions
|
64 |
|
65 |
-
- Transformers 4.
|
66 |
- Pytorch 2.0.1+cu118
|
67 |
- Datasets 2.14.4
|
68 |
- Tokenizers 0.13.3
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [ad019el/tamasheq-99-1](https://huggingface.co/ad019el/tamasheq-99-1) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.3479
|
21 |
+
- Wer: 0.4957
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
48 |
- lr_scheduler_warmup_steps: 500
|
49 |
+
- num_epochs: 30
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
55 |
+
| 4.3118 | 6.0 | 300 | 0.8477 | 0.8593 |
|
56 |
+
| 0.4823 | 12.0 | 600 | 0.3741 | 0.5064 |
|
57 |
+
| 0.2054 | 18.0 | 900 | 0.3855 | 0.5027 |
|
58 |
+
| 0.1798 | 24.0 | 1200 | 0.3700 | 0.5023 |
|
59 |
+
| 0.2097 | 30.0 | 1500 | 0.3479 | 0.4957 |
|
|
|
60 |
|
61 |
|
62 |
### Framework versions
|
63 |
|
64 |
+
- Transformers 4.31.0
|
65 |
- Pytorch 2.0.1+cu118
|
66 |
- Datasets 2.14.4
|
67 |
- Tokenizers 0.13.3
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_dropout": 0.05,
|
4 |
"adapter_attn_dim": null,
|
5 |
"adapter_kernel_size": 3,
|
@@ -85,7 +85,7 @@
|
|
85 |
"num_hidden_layers": 24,
|
86 |
"num_negatives": 100,
|
87 |
"output_hidden_size": 1024,
|
88 |
-
"pad_token_id":
|
89 |
"proj_codevector_dim": 256,
|
90 |
"tdnn_dilation": [
|
91 |
1,
|
@@ -111,6 +111,6 @@
|
|
111 |
"torch_dtype": "float32",
|
112 |
"transformers_version": "4.32.1",
|
113 |
"use_weighted_layer_sum": false,
|
114 |
-
"vocab_size":
|
115 |
"xvector_output_dim": 512
|
116 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/content/tamasheq-99-2",
|
3 |
"activation_dropout": 0.05,
|
4 |
"adapter_attn_dim": null,
|
5 |
"adapter_kernel_size": 3,
|
|
|
85 |
"num_hidden_layers": 24,
|
86 |
"num_negatives": 100,
|
87 |
"output_hidden_size": 1024,
|
88 |
+
"pad_token_id": 43,
|
89 |
"proj_codevector_dim": 256,
|
90 |
"tdnn_dilation": [
|
91 |
1,
|
|
|
111 |
"torch_dtype": "float32",
|
112 |
"transformers_version": "4.32.1",
|
113 |
"use_weighted_layer_sum": false,
|
114 |
+
"vocab_size": 44,
|
115 |
"xvector_output_dim": 512
|
116 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4d0fcb51f2e603b102e660dea05870208f71f1eac2f418643e3652cef2e3a29
|
3 |
+
size 1262082221
|
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:ad6c7003da7fe6691dd038465b0e03ae7c241e32bc2461e2ac611d3d835b8a3c
|
3 |
size 4027
|