Add new SentenceTransformer model.
Browse files- README.md +3 -6
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -195,8 +195,6 @@ You can finetune this model on your own dataset.
|
|
| 195 |
- `eval_strategy`: steps
|
| 196 |
- `per_device_train_batch_size`: 32
|
| 197 |
- `per_device_eval_batch_size`: 32
|
| 198 |
-
- `learning_rate`: 5e-06
|
| 199 |
-
- `num_train_epochs`: 5
|
| 200 |
- `warmup_ratio`: 0.01
|
| 201 |
|
| 202 |
#### All Hyperparameters
|
|
@@ -213,13 +211,13 @@ You can finetune this model on your own dataset.
|
|
| 213 |
- `gradient_accumulation_steps`: 1
|
| 214 |
- `eval_accumulation_steps`: None
|
| 215 |
- `torch_empty_cache_steps`: None
|
| 216 |
-
- `learning_rate`: 5e-
|
| 217 |
- `weight_decay`: 0.0
|
| 218 |
- `adam_beta1`: 0.9
|
| 219 |
- `adam_beta2`: 0.999
|
| 220 |
- `adam_epsilon`: 1e-08
|
| 221 |
- `max_grad_norm`: 1.0
|
| 222 |
-
- `num_train_epochs`:
|
| 223 |
- `max_steps`: -1
|
| 224 |
- `lr_scheduler_type`: linear
|
| 225 |
- `lr_scheduler_kwargs`: {}
|
|
@@ -323,8 +321,7 @@ You can finetune this model on your own dataset.
|
|
| 323 |
### Training Logs
|
| 324 |
| Epoch | Step | Training Loss | Validation Loss |
|
| 325 |
|:------:|:----:|:-------------:|:---------------:|
|
| 326 |
-
| 2.3256 | 100 |
|
| 327 |
-
| 4.6512 | 200 | 2.8868 | 2.8038 |
|
| 328 |
|
| 329 |
|
| 330 |
### Framework Versions
|
|
|
|
| 195 |
- `eval_strategy`: steps
|
| 196 |
- `per_device_train_batch_size`: 32
|
| 197 |
- `per_device_eval_batch_size`: 32
|
|
|
|
|
|
|
| 198 |
- `warmup_ratio`: 0.01
|
| 199 |
|
| 200 |
#### All Hyperparameters
|
|
|
|
| 211 |
- `gradient_accumulation_steps`: 1
|
| 212 |
- `eval_accumulation_steps`: None
|
| 213 |
- `torch_empty_cache_steps`: None
|
| 214 |
+
- `learning_rate`: 5e-05
|
| 215 |
- `weight_decay`: 0.0
|
| 216 |
- `adam_beta1`: 0.9
|
| 217 |
- `adam_beta2`: 0.999
|
| 218 |
- `adam_epsilon`: 1e-08
|
| 219 |
- `max_grad_norm`: 1.0
|
| 220 |
+
- `num_train_epochs`: 3
|
| 221 |
- `max_steps`: -1
|
| 222 |
- `lr_scheduler_type`: linear
|
| 223 |
- `lr_scheduler_kwargs`: {}
|
|
|
|
| 321 |
### Training Logs
|
| 322 |
| Epoch | Step | Training Loss | Validation Loss |
|
| 323 |
|:------:|:----:|:-------------:|:---------------:|
|
| 324 |
+
| 2.3256 | 100 | 2.6739 | 2.4339 |
|
|
|
|
| 325 |
|
| 326 |
|
| 327 |
### Framework Versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 90864192
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffeadbd82ea53b1744fce6df91cafe86a7abfe7dd412e3c2c1ab377fbefbd7bc
|
| 3 |
size 90864192
|