Hugging Face's logo

ColeH0415
/
comp90042-crossencoder-factcheck

Text Ranking
sentence-transformers
Safetensors
deberta-v2
cross-encoder
reranker
Generated from Trainer
dataset_size:7419
loss:BinaryCrossEntropyLoss
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
 Community
ColeH0415 commited on
Commit
9fa97c3
·
verified ·
1 Parent(s): 672293b

CE fine-tuned epoch 3/3 best_val=0.6036

Browse files
Files changed (2) hide show
  1. README.md +18 -18
  2. model.safetensors +1 -1
README.md CHANGED
@@ -28,25 +28,25 @@ model-index:
28
  type: ce-val
29
  metrics:
30
  - type: accuracy
31
- value: 0.5733333333333334
32
  name: Accuracy
33
  - type: accuracy_threshold
34
- value: 0.5057904720306396
35
  name: Accuracy Threshold
36
  - type: f1
37
- value: 0.669374492282697
38
  name: F1
39
  - type: f1_threshold
40
- value: 0.45144930481910706
41
  name: F1 Threshold
42
  - type: precision
43
- value: 0.5036674816625917
44
  name: Precision
45
  - type: recall
46
- value: 0.9975786924939467
47
  name: Recall
48
  - type: average_precision
49
- value: 0.5550313029987005
50
  name: Average Precision
51
  ---
52
 
@@ -107,7 +107,7 @@ pairs = [
107
  ]
108
  scores = model.predict(pairs)
109
  print(scores)
110
- # [0.5149 0.4764 0.5282 0.5084 0.5007]
111
 
112
  # Or rank different texts based on similarity to a single text
113
  ranks = model.rank(
@@ -156,15 +156,15 @@ You can finetune this model on your own dataset.
156
  * Dataset: `ce-val`
157
  * Evaluated with [<code>CrossEncoderClassificationEvaluator</code>](https://sbert.net/docs/package_reference/cross_encoder/evaluation.html#sentence_transformers.cross_encoder.evaluation.CrossEncoderClassificationEvaluator)
158
 
159
- | Metric | Value |
160
- |:----------------------|:----------|
161
- | accuracy | 0.5733 |
162
- | accuracy_threshold | 0.5058 |
163
- | f1 | 0.6694 |
164
- | f1_threshold | 0.4514 |
165
- | precision | 0.5037 |
166
- | recall | 0.9976 |
167
- | **average_precision** | **0.555** |
168
 
169
  <!--
170
  ## Bias, Risks and Limitations
@@ -318,7 +318,7 @@ You can finetune this model on your own dataset.
318
  ### Training Logs
319
  | Epoch | Step | ce-val_average_precision |
320
  |:-----:|:----:|:------------------------:|
321
- | -1 | -1 | 0.5550 |
322
 
323
 
324
  ### Training Time
 
28
  type: ce-val
29
  metrics:
30
  - type: accuracy
31
+ value: 0.6036363636363636
32
  name: Accuracy
33
  - type: accuracy_threshold
34
+ value: 0.5116937160491943
35
  name: Accuracy Threshold
36
  - type: f1
37
+ value: 0.6751269035532994
38
  name: F1
39
  - type: f1_threshold
40
+ value: 0.4685322642326355
41
  name: F1 Threshold
42
  - type: precision
43
+ value: 0.5188556566970091
44
  name: Precision
45
  - type: recall
46
+ value: 0.9661016949152542
47
  name: Recall
48
  - type: average_precision
49
+ value: 0.5805485796313634
50
  name: Average Precision
51
  ---
52
 
 
107
  ]
108
  scores = model.predict(pairs)
109
  print(scores)
110
+ # [0.5664 0.4765 0.5621 0.5187 0.4973]
111
 
112
  # Or rank different texts based on similarity to a single text
113
  ranks = model.rank(
 
156
  * Dataset: `ce-val`
157
  * Evaluated with [<code>CrossEncoderClassificationEvaluator</code>](https://sbert.net/docs/package_reference/cross_encoder/evaluation.html#sentence_transformers.cross_encoder.evaluation.CrossEncoderClassificationEvaluator)
158
 
159
+ | Metric | Value |
160
+ |:----------------------|:-----------|
161
+ | accuracy | 0.6036 |
162
+ | accuracy_threshold | 0.5117 |
163
+ | f1 | 0.6751 |
164
+ | f1_threshold | 0.4685 |
165
+ | precision | 0.5189 |
166
+ | recall | 0.9661 |
167
+ | **average_precision** | **0.5805** |
168
 
169
  <!--
170
  ## Bias, Risks and Limitations
 
318
  ### Training Logs
319
  | Epoch | Step | ce-val_average_precision |
320
  |:-----:|:----:|:------------------------:|
321
+ | -1 | -1 | 0.5805 |
322
 
323
 
324
  ### Training Time
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c881c82d69a63589526eb988bc70667f516ac3a14e3d074e3d03833047c913b8
3
  size 737716172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb73cbc87aff97341c39cd6998abca49a89e0e0fa8e157eaf4e62b10dde088c6
3
  size 737716172