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
3c79fcd
·
verified ·
1 Parent(s): 2f751f4

CE fine-tuned epoch 3/3 best_val=0.6388

Browse files
Files changed (2) hide show
  1. README.md +20 -16
  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: 0.6
32
  name: Accuracy
33
  - type: accuracy_threshold
34
- value: 0.5077031850814819
35
  name: Accuracy Threshold
36
  - type: f1
37
- value: 0.6791489361702127
38
  name: F1
39
  - type: f1_threshold
40
- value: 0.4203318953514099
41
  name: F1 Threshold
42
  - type: precision
43
- value: 0.5236220472440944
44
  name: Precision
45
  - type: recall
46
- value: 0.9661016949152542
47
  name: Recall
48
  - type: average_precision
49
- value: 0.6083361348816916
50
  name: Average Precision
51
  ---
52
 
@@ -107,7 +107,7 @@ pairs = [
107
  ]
108
  scores = model.predict(pairs)
109
  print(scores)
110
- # [0.6799 0.5912 0.5 0.4181 0.4313]
111
 
112
  # Or rank different texts based on similarity to a single text
113
  ranks = model.rank(
@@ -158,13 +158,13 @@ You can finetune this model on your own dataset.
158
 
159
  | Metric | Value |
160
  |:----------------------|:-----------|
161
- | accuracy | 0.6 |
162
- | accuracy_threshold | 0.5077 |
163
- | f1 | 0.6791 |
164
- | f1_threshold | 0.4203 |
165
- | precision | 0.5236 |
166
- | recall | 0.9661 |
167
- | **average_precision** | **0.6083** |
168
 
169
  <!--
170
  ## Bias, Risks and Limitations
@@ -326,10 +326,14 @@ You can finetune this model on your own dataset.
326
  | 0.5391 | 1000 | 0.6840 | - |
327
  | 0.8086 | 1500 | 0.6848 | - |
328
  | -1 | -1 | - | 0.6083 |
 
 
 
 
329
 
330
 
331
  ### Training Time
332
- - **Training**: 7.2 minutes
333
 
334
  ### Framework Versions
335
  - Python: 3.12.13
 
28
  type: ce-val
29
  metrics:
30
  - type: accuracy
31
+ value: 0.6387878787878788
32
  name: Accuracy
33
  - type: accuracy_threshold
34
+ value: 0.47375625371932983
35
  name: Accuracy Threshold
36
  - type: f1
37
+ value: 0.6906474820143886
38
  name: F1
39
  - type: f1_threshold
40
+ value: 0.3463754653930664
41
  name: F1 Threshold
42
  - type: precision
43
+ value: 0.5493562231759657
44
  name: Precision
45
  - type: recall
46
+ value: 0.9297820823244553
47
  name: Recall
48
  - type: average_precision
49
+ value: 0.6675220045050669
50
  name: Average Precision
51
  ---
52
 
 
107
  ]
108
  scores = model.predict(pairs)
109
  print(scores)
110
+ # [0.7955 0.4447 0.5575 0.3427 0.3421]
111
 
112
  # Or rank different texts based on similarity to a single text
113
  ranks = model.rank(
 
158
 
159
  | Metric | Value |
160
  |:----------------------|:-----------|
161
+ | accuracy | 0.6388 |
162
+ | accuracy_threshold | 0.4738 |
163
+ | f1 | 0.6906 |
164
+ | f1_threshold | 0.3464 |
165
+ | precision | 0.5494 |
166
+ | recall | 0.9298 |
167
+ | **average_precision** | **0.6675** |
168
 
169
  <!--
170
  ## Bias, Risks and Limitations
 
326
  | 0.5391 | 1000 | 0.6840 | - |
327
  | 0.8086 | 1500 | 0.6848 | - |
328
  | -1 | -1 | - | 0.6083 |
329
+ | 0.2695 | 500 | 0.6379 | - |
330
+ | 0.5391 | 1000 | 0.6424 | - |
331
+ | 0.8086 | 1500 | 0.6501 | - |
332
+ | -1 | -1 | - | 0.6675 |
333
 
334
 
335
  ### Training Time
336
+ - **Training**: 7.1 minutes
337
 
338
  ### Framework Versions
339
  - Python: 3.12.13
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97b936db2695b03518b21df64ef8888ab2b08529a82fbaff59162c06c34daf7f
3
  size 737716172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a2701e5f38f5d50dbd4c46ce52b54e777353e7acb8e142bd9753b4caa41bf8c
3
  size 737716172