P0u4a commited on
Commit
7dba3cd
·
verified ·
1 Parent(s): d3907a7

End of training

Browse files
Files changed (6) hide show
  1. README.md +72 -0
  2. config.json +86 -0
  3. model.safetensors +3 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +17 -0
  6. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: answerdotai/ModernBERT-base
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - f1
9
+ - precision
10
+ - recall
11
+ - accuracy
12
+ model-index:
13
+ - name: ModernBERT-bash-classifier
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # ModernBERT-bash-classifier
21
+
22
+ This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on an unknown dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.2624
25
+ - F1: 0.9515
26
+ - Precision: 0.9608
27
+ - Recall: 0.9423
28
+ - Accuracy: 0.9864
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 2e-05
48
+ - train_batch_size: 16
49
+ - eval_batch_size: 16
50
+ - seed: 42
51
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
+ - lr_scheduler_type: linear
53
+ - num_epochs: 5
54
+ - mixed_precision_training: Native AMP
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall | Accuracy |
59
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|:------:|:--------:|
60
+ | 0.1074 | 1.0 | 184 | 0.0978 | 0.9074 | 0.875 | 0.9423 | 0.9728 |
61
+ | 0.0633 | 2.0 | 368 | 0.0335 | 0.9808 | 0.9808 | 0.9808 | 0.9946 |
62
+ | 0.0267 | 3.0 | 552 | 0.0268 | 0.9903 | 1.0 | 0.9808 | 0.9973 |
63
+ | 0.0000 | 4.0 | 736 | 0.0636 | 0.9804 | 1.0 | 0.9615 | 0.9946 |
64
+ | 0.0000 | 5.0 | 920 | 0.0677 | 0.9804 | 1.0 | 0.9615 | 0.9946 |
65
+
66
+
67
+ ### Framework versions
68
+
69
+ - Transformers 5.10.2
70
+ - Pytorch 2.11.0+cu128
71
+ - Datasets 4.0.0
72
+ - Tokenizers 0.22.2
config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 768,
22
+ "id2label": {
23
+ "0": "unsafe",
24
+ "1": "safe"
25
+ },
26
+ "initializer_cutoff_factor": 2.0,
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 1152,
29
+ "label2id": {
30
+ "safe": 1,
31
+ "unsafe": 0
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "layer_types": [
35
+ "full_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "full_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "full_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "full_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "full_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "full_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "full_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "full_attention"
57
+ ],
58
+ "local_attention": 128,
59
+ "max_position_embeddings": 8192,
60
+ "mlp_bias": false,
61
+ "mlp_dropout": 0.0,
62
+ "model_type": "modernbert",
63
+ "norm_bias": false,
64
+ "norm_eps": 1e-05,
65
+ "num_attention_heads": 12,
66
+ "num_hidden_layers": 22,
67
+ "pad_token_id": 50283,
68
+ "position_embedding_type": "absolute",
69
+ "rope_parameters": {
70
+ "full_attention": {
71
+ "rope_theta": 160000.0,
72
+ "rope_type": "default"
73
+ },
74
+ "sliding_attention": {
75
+ "rope_theta": 10000.0,
76
+ "rope_type": "default"
77
+ }
78
+ },
79
+ "sep_token_id": 50282,
80
+ "sparse_pred_ignore_index": -100,
81
+ "sparse_prediction": false,
82
+ "tie_word_embeddings": true,
83
+ "transformers_version": "5.10.2",
84
+ "use_cache": false,
85
+ "vocab_size": 50368
86
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4a71c385cd467a9b581d5aed55e161579142bc82587a8db2658666096f7cb12
3
+ size 598439784
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "is_local": false,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "model_input_names": [
9
+ "input_ids",
10
+ "attention_mask"
11
+ ],
12
+ "model_max_length": 8192,
13
+ "pad_token": "[PAD]",
14
+ "sep_token": "[SEP]",
15
+ "tokenizer_class": "TokenizersBackend",
16
+ "unk_token": "[UNK]"
17
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4671cf7ebca0be3e532eff7bdebbef504abf9d245eaaf4371ea6224fcbf2c0f4
3
+ size 5201