Add model documentation
Browse files- README_model.md +3 -3
README_model.md
CHANGED
|
@@ -32,11 +32,11 @@ effectively predict anomalies. We will then attempt build a model that is more
|
|
| 32 |
## Training Details
|
| 33 |
- Base model: EleutherAI/pythia-70m
|
| 34 |
- Dataset: https://zenodo.org/records/8196385/files/HDFS_v1.zip?download=1 + preprocessed data at honicky/log-analysis-hdfs-preprocessed
|
| 35 |
-
- Batch size:
|
| 36 |
- Max sequence length: 405
|
| 37 |
- Learning rate: 0.0001
|
| 38 |
-
- Training steps:
|
| 39 |
-
- Weights and Biases run: https://wandb.ai/honicky/log-analysis-pythia/runs/
|
| 40 |
|
| 41 |
|
| 42 |
## Special Tokens
|
|
|
|
| 32 |
## Training Details
|
| 33 |
- Base model: EleutherAI/pythia-70m
|
| 34 |
- Dataset: https://zenodo.org/records/8196385/files/HDFS_v1.zip?download=1 + preprocessed data at honicky/log-analysis-hdfs-preprocessed
|
| 35 |
+
- Batch size: 32
|
| 36 |
- Max sequence length: 405
|
| 37 |
- Learning rate: 0.0001
|
| 38 |
+
- Training steps: 16000
|
| 39 |
+
- Weights and Biases run: https://wandb.ai/honicky/log-analysis-pythia/runs/dwb96ojk
|
| 40 |
|
| 41 |
|
| 42 |
## Special Tokens
|