Commit
•
448aff6
1
Parent(s):
e4aa045
Upload with huggingface_hub
Browse files- README.md +7 -7
- config.json +1 -1
- pytorch_model.bin +1 -1
- tokenizer_config.json +1 -1
README.md
CHANGED
@@ -28,7 +28,7 @@ Then you can use the model like this:
|
|
28 |
from sentence_transformers import SentenceTransformer
|
29 |
sentences = ["This is an example sentence", "Each sentence is converted"]
|
30 |
|
31 |
-
model = SentenceTransformer('
|
32 |
embeddings = model.encode(sentences)
|
33 |
print(embeddings)
|
34 |
```
|
@@ -85,22 +85,22 @@ The model was trained with the parameters:
|
|
85 |
|
86 |
**DataLoader**:
|
87 |
|
88 |
-
`torch.utils.data.dataloader.DataLoader` of length
|
89 |
```
|
90 |
-
{'batch_size':
|
91 |
```
|
92 |
|
93 |
**Loss**:
|
94 |
|
95 |
-
`sentence_transformers.losses.
|
96 |
```
|
97 |
-
{'
|
98 |
```
|
99 |
|
100 |
Parameters of the fit()-Method:
|
101 |
```
|
102 |
{
|
103 |
-
"epochs":
|
104 |
"evaluation_steps": 0,
|
105 |
"evaluator": "NoneType",
|
106 |
"max_grad_norm": 1,
|
@@ -110,7 +110,7 @@ Parameters of the fit()-Method:
|
|
110 |
},
|
111 |
"scheduler": "WarmupLinear",
|
112 |
"steps_per_epoch": null,
|
113 |
-
"warmup_steps":
|
114 |
"weight_decay": 0.01
|
115 |
}
|
116 |
```
|
|
|
28 |
from sentence_transformers import SentenceTransformer
|
29 |
sentences = ["This is an example sentence", "Each sentence is converted"]
|
30 |
|
31 |
+
model = SentenceTransformer('{MODEL_NAME}')
|
32 |
embeddings = model.encode(sentences)
|
33 |
print(embeddings)
|
34 |
```
|
|
|
85 |
|
86 |
**DataLoader**:
|
87 |
|
88 |
+
`torch.utils.data.dataloader.DataLoader` of length 5625 with parameters:
|
89 |
```
|
90 |
+
{'batch_size': 32, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
|
91 |
```
|
92 |
|
93 |
**Loss**:
|
94 |
|
95 |
+
`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
|
96 |
```
|
97 |
+
{'scale': 20.0, 'similarity_fct': 'cos_sim'}
|
98 |
```
|
99 |
|
100 |
Parameters of the fit()-Method:
|
101 |
```
|
102 |
{
|
103 |
+
"epochs": 2,
|
104 |
"evaluation_steps": 0,
|
105 |
"evaluator": "NoneType",
|
106 |
"max_grad_norm": 1,
|
|
|
110 |
},
|
111 |
"scheduler": "WarmupLinear",
|
112 |
"steps_per_epoch": null,
|
113 |
+
"warmup_steps": 1125,
|
114 |
"weight_decay": 0.01
|
115 |
}
|
116 |
```
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"RobertaModel"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/root/.cache/torch/sentence_transformers/reza-aditya_distilroberta-base-sentence-transformer/",
|
3 |
"architectures": [
|
4 |
"RobertaModel"
|
5 |
],
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 328511153
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:271865305016d69a973b13e425b956b4c301a4862d531320b8d1901b9b5a5fe9
|
3 |
size 328511153
|
tokenizer_config.json
CHANGED
@@ -6,7 +6,7 @@
|
|
6 |
"errors": "replace",
|
7 |
"mask_token": "<mask>",
|
8 |
"model_max_length": 512,
|
9 |
-
"name_or_path": "
|
10 |
"pad_token": "<pad>",
|
11 |
"sep_token": "</s>",
|
12 |
"special_tokens_map_file": null,
|
|
|
6 |
"errors": "replace",
|
7 |
"mask_token": "<mask>",
|
8 |
"model_max_length": 512,
|
9 |
+
"name_or_path": "/root/.cache/torch/sentence_transformers/reza-aditya_distilroberta-base-sentence-transformer/",
|
10 |
"pad_token": "<pad>",
|
11 |
"sep_token": "</s>",
|
12 |
"special_tokens_map_file": null,
|