Update README.md
Browse files
README.md
CHANGED
@@ -120,26 +120,9 @@ This model has been trained on news articles only. Hence, it might not perform a
|
|
120 |
|
121 |
#### Training Hyperparameters
|
122 |
|
123 |
-
|
124 |
-
|
125 |
-
|
126 |
-
--train_file /srv/scratch2/grosjean/Masterarbeit/data_subsets \
|
127 |
-
--output_dir /srv/scratch2/grosjean/Masterarbeit/model \
|
128 |
-
--overwrite_output_dir \
|
129 |
-
--save_strategy no \
|
130 |
-
--do_train \
|
131 |
-
--num_train_epochs 1 \
|
132 |
-
--learning_rate 1e-5 \
|
133 |
-
--per_device_train_batch_size 4 \
|
134 |
-
--gradient_accumulation_steps 128 \
|
135 |
-
--max_seq_length 512 \
|
136 |
-
--overwrite_cache \
|
137 |
-
--pooler_type avg \
|
138 |
-
--pad_to_max_length \
|
139 |
-
--temp 0.05 \
|
140 |
-
--fp16 <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
141 |
-
|
142 |
-
[More Information Needed]
|
143 |
|
144 |
## Evaluation
|
145 |
|
@@ -190,35 +173,3 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
190 |
### Model Architecture and Objective
|
191 |
|
192 |
[More Information Needed]
|
193 |
-
|
194 |
-
## Citation [optional]
|
195 |
-
|
196 |
-
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
197 |
-
|
198 |
-
**BibTeX:**
|
199 |
-
|
200 |
-
[More Information Needed]
|
201 |
-
|
202 |
-
**APA:**
|
203 |
-
|
204 |
-
[More Information Needed]
|
205 |
-
|
206 |
-
## Glossary [optional]
|
207 |
-
|
208 |
-
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
209 |
-
|
210 |
-
[More Information Needed]
|
211 |
-
|
212 |
-
## More Information [optional]
|
213 |
-
|
214 |
-
[More Information Needed]
|
215 |
-
|
216 |
-
## Model Card Authors [optional]
|
217 |
-
|
218 |
-
[More Information Needed]
|
219 |
-
|
220 |
-
## Model Card Contact
|
221 |
-
|
222 |
-
[More Information Needed]
|
223 |
-
|
224 |
-
|
|
|
120 |
|
121 |
#### Training Hyperparameters
|
122 |
|
123 |
+
Number of epochs: 1
|
124 |
+
Learning rate: 1e-5
|
125 |
+
Batch size: 512
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
126 |
|
127 |
## Evaluation
|
128 |
|
|
|
173 |
### Model Architecture and Objective
|
174 |
|
175 |
[More Information Needed]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|