pszemraj commited on
Commit
a0f8abb
·
verified ·
1 Parent(s): 633d6ae

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -37
README.md CHANGED
@@ -78,48 +78,13 @@ print("Sentence embeddings:")
78
  print(sentence_embeddings)
79
  ```
80
 
81
-
82
-
83
  ## Training
84
- The model was trained with the parameters:
85
-
86
- **DataLoader**:
87
 
88
- `sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader` of length 8663 with parameters:
89
- ```
90
- {'batch_size': 32}
91
- ```
92
 
93
  **Loss**:
94
 
95
  `sentence_transformers.losses.MatryoshkaLoss.MatryoshkaLoss` with parameters:
96
  ```
97
- {'loss': 'MultipleNegativesRankingLoss', 'matryoshka_dims': [768, 512, 256, 128, 64], 'matryoshka_weights': [1, 1, 1, 1, 1], 'n_dims_per_step': -1}
98
  ```
99
-
100
- Parameters of the fit()-Method:
101
- ```
102
- {
103
- "epochs": 1,
104
- "evaluation_steps": 216,
105
- "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
106
- "max_grad_norm": 1,
107
- "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
108
- "optimizer_params": {
109
- "lr": 2e-05
110
- },
111
- "scheduler": "WarmupLinear",
112
- "steps_per_epoch": null,
113
- "warmup_steps": 867,
114
- "weight_decay": 0.01
115
- }
116
- ```
117
-
118
-
119
- ## Full Model Architecture
120
- ```
121
- SentenceTransformer(
122
- (0): Transformer({'max_seq_length': 4096, 'do_lower_case': False}) with Transformer model: BertModel
123
- (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
124
- )
125
- ```
 
78
  print(sentence_embeddings)
79
  ```
80
 
 
 
81
  ## Training
 
 
 
82
 
83
+ The model was trained with the parameters:
 
 
 
84
 
85
  **Loss**:
86
 
87
  `sentence_transformers.losses.MatryoshkaLoss.MatryoshkaLoss` with parameters:
88
  ```
89
+ {'loss': 'CosineSimilarityLoss', 'matryoshka_dims': [768, 512, 256, 128, 64], 'matryoshka_weights': [1, 1, 1, 1, 1], 'n_dims_per_step': -1}
90
  ```