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
d9f7c87
·
verified ·
1 Parent(s): 4f25141

Training in progress, step 83

Browse files
Files changed (11) hide show
  1. .gitattributes +1 -0
  2. README.md +0 -0
  3. config.json +85 -0
  4. config_sentence_transformers.json +11 -0
  5. eval/CrossEncoderClassificationEvaluator_fineweb_c_eval_results.csv +2 -0
  6. model.safetensors +3 -0
  7. modules.json +8 -0
  8. sentence_bert_config.json +10 -0
  9. tokenizer.json +3 -0
  10. tokenizer_config.json +25 -0
  11. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 2,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 1,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 1,
18
+ "global_attn_every_n_layers": 3,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 768,
22
+ "id2label": {
23
+ "0": "LABEL_0"
24
+ },
25
+ "initializer_cutoff_factor": 2.0,
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 1152,
28
+ "label2id": {
29
+ "LABEL_0": 0
30
+ },
31
+ "layer_norm_eps": 1e-05,
32
+ "layer_types": [
33
+ "full_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "full_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "full_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "full_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "full_attention",
46
+ "sliding_attention",
47
+ "sliding_attention",
48
+ "full_attention",
49
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "full_attention",
52
+ "sliding_attention",
53
+ "sliding_attention",
54
+ "full_attention"
55
+ ],
56
+ "local_attention": 128,
57
+ "mask_token_id": 4,
58
+ "max_position_embeddings": 8192,
59
+ "mlp_bias": false,
60
+ "mlp_dropout": 0.0,
61
+ "model_type": "modernbert",
62
+ "norm_bias": false,
63
+ "norm_eps": 1e-05,
64
+ "num_attention_heads": 12,
65
+ "num_hidden_layers": 22,
66
+ "pad_token_id": 0,
67
+ "position_embedding_type": "sans_pos",
68
+ "rope_parameters": {
69
+ "full_attention": {
70
+ "rope_theta": 160000,
71
+ "rope_type": "default"
72
+ },
73
+ "sliding_attention": {
74
+ "rope_theta": 160000,
75
+ "rope_type": "default"
76
+ }
77
+ },
78
+ "sep_token_id": 1,
79
+ "sparse_pred_ignore_index": -100,
80
+ "sparse_prediction": false,
81
+ "tie_word_embeddings": true,
82
+ "transformers_version": "5.8.1",
83
+ "use_cache": false,
84
+ "vocab_size": 256000
85
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "pytorch": "2.12.0+cu130",
4
+ "sentence_transformers": "5.5.0",
5
+ "transformers": "5.8.1"
6
+ },
7
+ "activation_fn": "torch.nn.modules.activation.Sigmoid",
8
+ "default_prompt_name": null,
9
+ "model_type": "CrossEncoder",
10
+ "prompts": {}
11
+ }
eval/CrossEncoderClassificationEvaluator_fineweb_c_eval_results.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ epoch,steps,Accuracy,Accuracy_Threshold,F1,F1_Threshold,Precision,Recall,Average_Precision
2
+ 0.2,83,0.8335597826086957,0.93439513,0.33268101761252444,0.69884336,0.21935483870967742,0.6882591093117408,0.2441194063501111
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e530136a08e1826eaf0bf913bf83a7e998dd2df53d492f794a427728a04b6902
3
+ size 1230138348
modules.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.base.modules.transformer.Transformer"
7
+ }
8
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "transformer_task": "sequence-classification",
3
+ "modality_config": {
4
+ "text": {
5
+ "method": "forward",
6
+ "method_output_name": "logits"
7
+ }
8
+ },
9
+ "module_output_name": "scores"
10
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17f7d8b9518c403d7429ad9eeeabb6eed49c8d3311de8ef4ed5ad811381a2ced
3
+ size 34363441
tokenizer_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<bos>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "cls_token": "<bos>",
6
+ "eos_token": "<eos>",
7
+ "extra_special_tokens": [
8
+ "<start_of_turn>",
9
+ "<end_of_turn>"
10
+ ],
11
+ "is_local": false,
12
+ "local_files_only": false,
13
+ "mask_token": "<mask>",
14
+ "model_input_names": [
15
+ "input_ids",
16
+ "attention_mask"
17
+ ],
18
+ "model_max_length": 512,
19
+ "pad_token": "<pad>",
20
+ "padding_side": "right",
21
+ "sep_token": "<eos>",
22
+ "spaces_between_special_tokens": false,
23
+ "tokenizer_class": "TokenizersBackend",
24
+ "unk_token": "<unk>"
25
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4de436e8a43b6d3dd72861b020e26944cccaec996a411245e6c37d0e5d728624
3
+ size 5713