Hugging Face's logo

LamaDiab
/
V7MiniLM-Synonyms-SemanticEngine

Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
dense
Generated from Trainer
dataset_size:683
loss:MultipleNegativesSymmetricRankingLoss
text-embeddings-inference
Model card Files
xet
 Community
LamaDiab commited on
Commit
aa4e1ba
·
verified ·
1 Parent(s): 8c4ae35

Training in progress, epoch 1

Browse files
Files changed (4) hide show
  1. final/README.md +9 -9
  2. final/model.safetensors +1 -1
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
final/README.md CHANGED
@@ -98,9 +98,9 @@ print(embeddings.shape)
98
  # Get the similarity scores for the embeddings
99
  similarities = model.similarity(embeddings, embeddings)
100
  print(similarities)
101
- # tensor([[1.0000, 0.8999, 0.4346],
102
- # [0.8999, 1.0000, 0.4347],
103
- # [0.4346, 0.4347, 1.0000]])
104
  ```
105
 
106
  <!--
@@ -172,7 +172,7 @@ You can finetune this model on your own dataset.
172
 
173
  - `per_device_train_batch_size`: 32
174
  - `per_device_eval_batch_size`: 16
175
- - `learning_rate`: 1e-05
176
  - `weight_decay`: 0.001
177
  - `num_train_epochs`: 4
178
  - `warmup_ratio`: 0.2
@@ -199,7 +199,7 @@ You can finetune this model on your own dataset.
199
  - `gradient_accumulation_steps`: 1
200
  - `eval_accumulation_steps`: None
201
  - `torch_empty_cache_steps`: None
202
- - `learning_rate`: 1e-05
203
  - `weight_decay`: 0.001
204
  - `adam_beta1`: 0.9
205
  - `adam_beta2`: 0.999
@@ -312,10 +312,10 @@ You can finetune this model on your own dataset.
312
  | Epoch | Step | Training Loss |
313
  |:------:|:----:|:-------------:|
314
  | 0.0455 | 1 | 3.3947 |
315
- | 1.0 | 22 | 2.9858 |
316
- | 2.0 | 44 | 2.9203 |
317
- | 3.0 | 66 | 2.8467 |
318
- | 4.0 | 88 | 2.772 |
319
 
320
 
321
  ### Framework Versions
 
98
  # Get the similarity scores for the embeddings
99
  similarities = model.similarity(embeddings, embeddings)
100
  print(similarities)
101
+ # tensor([[1.0000, 0.8991, 0.4566],
102
+ # [0.8991, 1.0000, 0.4530],
103
+ # [0.4566, 0.4530, 1.0000]])
104
  ```
105
 
106
  <!--
 
172
 
173
  - `per_device_train_batch_size`: 32
174
  - `per_device_eval_batch_size`: 16
175
+ - `learning_rate`: 2e-05
176
  - `weight_decay`: 0.001
177
  - `num_train_epochs`: 4
178
  - `warmup_ratio`: 0.2
 
199
  - `gradient_accumulation_steps`: 1
200
  - `eval_accumulation_steps`: None
201
  - `torch_empty_cache_steps`: None
202
+ - `learning_rate`: 2e-05
203
  - `weight_decay`: 0.001
204
  - `adam_beta1`: 0.9
205
  - `adam_beta2`: 0.999
 
312
  | Epoch | Step | Training Loss |
313
  |:------:|:----:|:-------------:|
314
  | 0.0455 | 1 | 3.3947 |
315
+ | 1.0 | 22 | 2.9599 |
316
+ | 2.0 | 44 | 2.7929 |
317
+ | 3.0 | 66 | 2.6597 |
318
+ | 4.0 | 88 | 2.5617 |
319
 
320
 
321
  ### Framework Versions
final/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:293545b11a01048bbe67423c177a2ce3d5791796a1d3230a1f2b1d57a2324131
3
  size 90864192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86df2550396444a8a4c8956321efa49bf3a49624e2f4c8366d26f5e8c81dbb18
3
  size 90864192
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86df2550396444a8a4c8956321efa49bf3a49624e2f4c8366d26f5e8c81dbb18
3
  size 90864192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3ffef6305a3c11e58526fb71b67320f9a25ebd402f9bfc8faa86d74662a744c
3
  size 90864192
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0918c5fd5b70657b6953b33311bee05533810127029f097a8f57f51d4a043b8c
3
  size 5752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0110283e5edb1e35b9e0be5e96c585f900a35198f2392bd1ba1fa0e1bcc011f
3
  size 5752