Hugging Face's logo

davanstrien
/
fineweb-c-quality-reranker-v2

Text Ranking
sentence-transformers
Safetensors
multilingual
modernbert
cross-encoder
reranker
Generated from Trainer
dataset_size:9220
loss:BinaryCrossEntropyLoss
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
 Community
davanstrien HF Staff commited on
Commit
0fa9434
·
verified ·
1 Parent(s): 18fb71e

Training in progress, step 116

Browse files
Files changed (3) hide show
  1. README.md +29 -18
  2. eval/CrossEncoderClassificationEvaluator_fineweb_c_eval_results.csv +1 -0
  3. model.safetensors +1 -1
README.md CHANGED
@@ -31,25 +31,25 @@ model-index:
31
  type: fineweb_c_eval
32
  metrics:
33
  - type: accuracy
34
- value: 0.8369140625
35
  name: Accuracy
36
  - type: accuracy_threshold
37
- value: 0.8085842132568359
38
  name: Accuracy Threshold
39
  - type: f1
40
- value: 0.29916897506925205
41
  name: F1
42
  - type: f1_threshold
43
- value: 0.3967691659927368
44
  name: F1 Threshold
45
  - type: precision
46
- value: 0.1945945945945946
47
  name: Precision
48
  - type: recall
49
- value: 0.6467065868263473
50
  name: Recall
51
  - type: average_precision
52
- value: 0.22527425150874691
53
  name: Average Precision
54
  ---
55
 
@@ -110,7 +110,7 @@ pairs = [
110
  ]
111
  scores = model.predict(pairs)
112
  print(scores)
113
- # [0.2509 0.5293 0.6663 0.5265 0.2926]
114
 
115
  # Or rank different texts based on similarity to a single text
116
  ranks = model.rank(
@@ -161,13 +161,13 @@ You can finetune this model on your own dataset.
161
 
162
  | Metric | Value |
163
  |:----------------------|:-----------|
164
- | accuracy | 0.8369 |
165
- | accuracy_threshold | 0.8086 |
166
- | f1 | 0.2992 |
167
- | f1_threshold | 0.3968 |
168
- | precision | 0.1946 |
169
- | recall | 0.6467 |
170
- | **average_precision** | **0.2253** |
171
 
172
  <!--
173
  ## Bias, Risks and Limitations
@@ -370,12 +370,23 @@ You can finetune this model on your own dataset.
370
  | 0.1661 | 48 | 1.3934 | - | - |
371
  | 0.1869 | 54 | 1.1783 | - | - |
372
  | 0.2007 | 58 | - | 1.1506 | 0.2253 |
 
 
 
 
 
 
 
 
 
 
 
373
 
374
 
375
  ### Training Time
376
- - **Training**: 57.3 seconds
377
- - **Evaluation**: 20.6 seconds
378
- - **Total**: 1.3 minutes
379
 
380
  ### Framework Versions
381
  - Python: 3.12.12
 
31
  type: fineweb_c_eval
32
  metrics:
33
  - type: accuracy
34
+ value: 0.8388671875
35
  name: Accuracy
36
  - type: accuracy_threshold
37
+ value: 0.7548891305923462
38
  name: Accuracy Threshold
39
  - type: f1
40
+ value: 0.37500000000000006
41
  name: F1
42
  - type: f1_threshold
43
+ value: 0.49519360065460205
44
  name: F1 Threshold
45
  - type: precision
46
+ value: 0.3132530120481928
47
  name: Precision
48
  - type: recall
49
+ value: 0.46706586826347307
50
  name: Recall
51
  - type: average_precision
52
+ value: 0.296686339444048
53
  name: Average Precision
54
  ---
55
 
 
110
  ]
111
  scores = model.predict(pairs)
112
  print(scores)
113
+ # [0.094 0.6645 0.1461 0.2214 0.5059]
114
 
115
  # Or rank different texts based on similarity to a single text
116
  ranks = model.rank(
 
161
 
162
  | Metric | Value |
163
  |:----------------------|:-----------|
164
+ | accuracy | 0.8389 |
165
+ | accuracy_threshold | 0.7549 |
166
+ | f1 | 0.375 |
167
+ | f1_threshold | 0.4952 |
168
+ | precision | 0.3133 |
169
+ | recall | 0.4671 |
170
+ | **average_precision** | **0.2967** |
171
 
172
  <!--
173
  ## Bias, Risks and Limitations
 
370
  | 0.1661 | 48 | 1.3934 | - | - |
371
  | 0.1869 | 54 | 1.1783 | - | - |
372
  | 0.2007 | 58 | - | 1.1506 | 0.2253 |
373
+ | 0.2076 | 60 | 1.2396 | - | - |
374
+ | 0.2284 | 66 | 1.1510 | - | - |
375
+ | 0.2491 | 72 | 1.1545 | - | - |
376
+ | 0.2699 | 78 | 1.2084 | - | - |
377
+ | 0.2907 | 84 | 1.1823 | - | - |
378
+ | 0.3114 | 90 | 1.1707 | - | - |
379
+ | 0.3322 | 96 | 0.9403 | - | - |
380
+ | 0.3529 | 102 | 1.1831 | - | - |
381
+ | 0.3737 | 108 | 1.1537 | - | - |
382
+ | 0.3945 | 114 | 1.0772 | - | - |
383
+ | 0.4014 | 116 | - | 1.1264 | 0.2967 |
384
 
385
 
386
  ### Training Time
387
+ - **Training**: 1.8 minutes
388
+ - **Evaluation**: 41.5 seconds
389
+ - **Total**: 2.5 minutes
390
 
391
  ### Framework Versions
392
  - Python: 3.12.12
eval/CrossEncoderClassificationEvaluator_fineweb_c_eval_results.csv CHANGED
@@ -1,2 +1,3 @@
1
  epoch,steps,Accuracy,Accuracy_Threshold,F1,F1_Threshold,Precision,Recall,Average_Precision
2
  0.20069204152249134,58,0.8369140625,0.8085842,0.29916897506925205,0.39676917,0.1945945945945946,0.6467065868263473,0.22527425150874691
 
 
1
  epoch,steps,Accuracy,Accuracy_Threshold,F1,F1_Threshold,Precision,Recall,Average_Precision
2
  0.20069204152249134,58,0.8369140625,0.8085842,0.29916897506925205,0.39676917,0.1945945945945946,0.6467065868263473,0.22527425150874691
3
+ 0.4013840830449827,116,0.8388671875,0.75488913,0.37500000000000006,0.4951936,0.3132530120481928,0.46706586826347307,0.296686339444048
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1da53abc763ad0bb28a0f22a87a51d748a582a6647f6d6efd768188b4dd08c3e
3
  size 1230138348
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ea664b4ba0ae8596627ed5ef8736f276a4ef69c0948b6c038e76d549e9513f6
3
  size 1230138348