Hugging Face's logo

davanstrien
/
fineweb-c-quality-reranker-v1

Text Ranking
sentence-transformers
Safetensors
multilingual
modernbert
cross-encoder
reranker
Generated from Trainer
dataset_size:13249
loss:BinaryCrossEntropyLoss
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
 Community
davanstrien HF Staff commited on
Commit
6bca37b
·
verified ·
1 Parent(s): 2a50617

Training in progress, step 747

Browse files
Files changed (3) hide show
  1. README.md +28 -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: 0.9130434782608695
35
  name: Accuracy
36
  - type: accuracy_threshold
37
- value: 0.8539100885391235
38
  name: Accuracy Threshold
39
  - type: f1
40
- value: 0.7319778188539743
41
  name: F1
42
  - type: f1_threshold
43
- value: 0.5879430174827576
44
  name: F1 Threshold
45
  - type: precision
46
- value: 0.673469387755102
47
  name: Precision
48
  - type: recall
49
- value: 0.8016194331983806
50
  name: Recall
51
  - type: average_precision
52
- value: 0.8063402291784638
53
  name: Average Precision
54
  ---
55
 
@@ -110,7 +110,7 @@ pairs = [
110
  ]
111
  scores = model.predict(pairs)
112
  print(scores)
113
- # [0.044 0.1645 0.0029 0.6868 0.9974]
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 | 0.913 |
165
- | accuracy_threshold | 0.8539 |
166
- | f1 | 0.732 |
167
- | f1_threshold | 0.5879 |
168
- | precision | 0.6735 |
169
- | recall | 0.8016 |
170
- | **average_precision** | **0.8063** |
171
 
172
  <!--
173
  ## Bias, Risks and Limitations
@@ -441,12 +441,22 @@ You can finetune this model on your own dataset.
441
  | 1.5614 | 648 | 0.4039 | - | - |
442
  | 1.5831 | 657 | 0.3553 | - | - |
443
  | 1.6 | 664 | - | 0.5771 | 0.8063 |
 
 
 
 
 
 
 
 
 
 
444
 
445
 
446
  ### Training Time
447
- - **Training**: 9.9 minutes
448
- - **Evaluation**: 4.8 minutes
449
- - **Total**: 14.7 minutes
450
 
451
  ### Framework Versions
452
  - Python: 3.12.12
 
31
  type: fineweb_c_eval
32
  metrics:
33
  - type: accuracy
34
+ value: 0.9164402173913043
35
  name: Accuracy
36
  - type: accuracy_threshold
37
+ value: 0.926296591758728
38
  name: Accuracy Threshold
39
  - type: f1
40
+ value: 0.7514910536779323
41
  name: F1
42
  - type: f1_threshold
43
+ value: 0.7859656810760498
44
  name: F1 Threshold
45
  - type: precision
46
+ value: 0.73828125
47
  name: Precision
48
  - type: recall
49
+ value: 0.7651821862348178
50
  name: Recall
51
  - type: average_precision
52
+ value: 0.8143721445987863
53
  name: Average Precision
54
  ---
55
 
 
110
  ]
111
  scores = model.predict(pairs)
112
  print(scores)
113
+ # [0.0362 0.2744 0.0054 0.5936 0.9971]
114
 
115
  # Or rank different texts based on similarity to a single text
116
  ranks = model.rank(
 
161
 
162
  | Metric | Value |
163
  |:----------------------|:-----------|
164
+ | accuracy | 0.9164 |
165
+ | accuracy_threshold | 0.9263 |
166
+ | f1 | 0.7515 |
167
+ | f1_threshold | 0.786 |
168
+ | precision | 0.7383 |
169
+ | recall | 0.7652 |
170
+ | **average_precision** | **0.8144** |
171
 
172
  <!--
173
  ## Bias, Risks and Limitations
 
441
  | 1.5614 | 648 | 0.4039 | - | - |
442
  | 1.5831 | 657 | 0.3553 | - | - |
443
  | 1.6 | 664 | - | 0.5771 | 0.8063 |
444
+ | 1.6048 | 666 | 0.3838 | - | - |
445
+ | 1.6265 | 675 | 0.3185 | - | - |
446
+ | 1.6482 | 684 | 0.4768 | - | - |
447
+ | 1.6699 | 693 | 0.4672 | - | - |
448
+ | 1.6916 | 702 | 0.3107 | - | - |
449
+ | 1.7133 | 711 | 0.4545 | - | - |
450
+ | 1.7349 | 720 | 0.4031 | - | - |
451
+ | 1.7566 | 729 | 0.2858 | - | - |
452
+ | 1.7783 | 738 | 0.5050 | - | - |
453
+ | 1.8 | 747 | 0.5735 | 0.5351 | 0.8144 |
454
 
455
 
456
  ### Training Time
457
+ - **Training**: 11.3 minutes
458
+ - **Evaluation**: 5.3 minutes
459
+ - **Total**: 16.6 minutes
460
 
461
  ### Framework Versions
462
  - Python: 3.12.12
eval/CrossEncoderClassificationEvaluator_fineweb_c_eval_results.csv CHANGED
@@ -7,3 +7,4 @@ epoch,steps,Accuracy,Accuracy_Threshold,F1,F1_Threshold,Precision,Recall,Average
7
  1.2,498,0.8947010869565217,0.80193585,0.642570281124498,0.6293162,0.6374501992031872,0.6477732793522267,0.7075905295332267
8
  1.4,581,0.9110054347826086,0.8187252,0.70509977827051,0.7655752,0.7794117647058824,0.6437246963562753,0.7665107869533287
9
  1.6,664,0.9130434782608695,0.8539101,0.7319778188539743,0.587943,0.673469387755102,0.8016194331983806,0.8063402291784638
 
 
7
  1.2,498,0.8947010869565217,0.80193585,0.642570281124498,0.6293162,0.6374501992031872,0.6477732793522267,0.7075905295332267
8
  1.4,581,0.9110054347826086,0.8187252,0.70509977827051,0.7655752,0.7794117647058824,0.6437246963562753,0.7665107869533287
9
  1.6,664,0.9130434782608695,0.8539101,0.7319778188539743,0.587943,0.673469387755102,0.8016194331983806,0.8063402291784638
10
+ 1.8,747,0.9164402173913043,0.9262966,0.7514910536779323,0.7859657,0.73828125,0.7651821862348178,0.8143721445987863
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbf1890c2bc36b7ef4fef48d5f2da2c9fd5fe802745d42efe4b5733d42205c49
3
  size 1230138348
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a82f1846201e2050a813612992edc07c69e8cde5534cfdbf3f60ab005722889
3
  size 1230138348