Update README.md
Browse files
README.md
CHANGED
|
@@ -61,3 +61,22 @@ The following hyperparameters were used during training:
|
|
| 61 |
- Pytorch 2.3.1+cu121
|
| 62 |
- Datasets 2.21.0
|
| 63 |
- Tokenizers 0.19.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
- Pytorch 2.3.1+cu121
|
| 62 |
- Datasets 2.21.0
|
| 63 |
- Tokenizers 0.19.1
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
## Training Environment
|
| 67 |
+
|
| 68 |
+
This model was trained on a single A100 GPU machine in Google Cloud. Below are the machine specifications:
|
| 69 |
+
|
| 70 |
+
| Machine Type | GPU Count | GPU Memory (GB HBM2) | vCPU Count | VM Memory (GB) | Local SSD Supported | Max Network Bandwidth (Gbps) |
|
| 71 |
+
|:---------------:|:---------:|:--------------------:|:----------:|:--------------:|:-------------------:|:----------------------------:|
|
| 72 |
+
| a2-highgpu-1g | 1 | 40 | 12 | 85 | Yes | 24 |
|
| 73 |
+
|
| 74 |
+
You can find more details about the machine type [here](https://cloud.google.com/compute/docs/gpus#a100-gpus).
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
## Training Results
|
| 78 |
+
|
| 79 |
+
| Training Loss | Step | Validation Loss | Wer |
|
| 80 |
+
|:-------------:|:-----:|:---------------:|:---------:|
|
| 81 |
+
| 0.2128 | 1000 | 0.251406 | 17.495011 |
|
| 82 |
+
| 0.0270 | 2000 | 0.289191 | 17.921945 |
|