Hugging Face's logo

violetar
/
Ner-model

Token Classification
Transformers
Safetensors
English
modernbert
named-entity-recognition
conll2003
Model card Files
xet
 Community
violetar commited on
Commit
3d341e3
·
verified ·
1 Parent(s): 8487335

Upload 8 files

Browse files
Files changed (8) hide show
  1. all_results.json +11 -0
  2. config.json +106 -0
  3. model.safetensors +3 -0
  4. test_results.json +11 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +17 -0
  7. trainer_state.json +135 -0
  8. training_args.bin +3 -0
all_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "test_accuracy": 0.9749472650041899,
4
+ "test_f1": 0.8915077989601387,
5
+ "test_loss": 0.30494070053100586,
6
+ "test_precision": 0.8730482009504412,
7
+ "test_recall": 0.9107648725212465,
8
+ "test_runtime": 201.6979,
9
+ "test_samples_per_second": 17.12,
10
+ "test_steps_per_second": 1.071
11
+ }
config.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForTokenClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
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": null,
18
+ "global_attn_every_n_layers": 3,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 1024,
22
+ "id2label": {
23
+ "0": "O",
24
+ "1": "B_PER",
25
+ "2": "I_PER",
26
+ "3": "B_ORG",
27
+ "4": "I_ORG",
28
+ "5": "B_LOC",
29
+ "6": "I_LOC",
30
+ "7": "B_MISC",
31
+ "8": "I_MISC"
32
+ },
33
+ "initializer_cutoff_factor": 2.0,
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 2624,
36
+ "label2id": {
37
+ "B_LOC": 5,
38
+ "B_MISC": 7,
39
+ "B_ORG": 3,
40
+ "B_PER": 1,
41
+ "I_LOC": 6,
42
+ "I_MISC": 8,
43
+ "I_ORG": 4,
44
+ "I_PER": 2,
45
+ "O": 0
46
+ },
47
+ "layer_norm_eps": 1e-05,
48
+ "layer_types": [
49
+ "full_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "full_attention",
53
+ "sliding_attention",
54
+ "sliding_attention",
55
+ "full_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "full_attention",
59
+ "sliding_attention",
60
+ "sliding_attention",
61
+ "full_attention",
62
+ "sliding_attention",
63
+ "sliding_attention",
64
+ "full_attention",
65
+ "sliding_attention",
66
+ "sliding_attention",
67
+ "full_attention",
68
+ "sliding_attention",
69
+ "sliding_attention",
70
+ "full_attention",
71
+ "sliding_attention",
72
+ "sliding_attention",
73
+ "full_attention",
74
+ "sliding_attention",
75
+ "sliding_attention",
76
+ "full_attention"
77
+ ],
78
+ "local_attention": 128,
79
+ "max_position_embeddings": 8192,
80
+ "mlp_bias": false,
81
+ "mlp_dropout": 0.0,
82
+ "model_type": "modernbert",
83
+ "norm_bias": false,
84
+ "norm_eps": 1e-05,
85
+ "num_attention_heads": 16,
86
+ "num_hidden_layers": 28,
87
+ "pad_token_id": 50283,
88
+ "position_embedding_type": "absolute",
89
+ "rope_parameters": {
90
+ "full_attention": {
91
+ "rope_theta": 160000.0,
92
+ "rope_type": "default"
93
+ },
94
+ "sliding_attention": {
95
+ "rope_theta": 10000.0,
96
+ "rope_type": "default"
97
+ }
98
+ },
99
+ "sep_token_id": 50282,
100
+ "sparse_pred_ignore_index": -100,
101
+ "sparse_prediction": false,
102
+ "tie_word_embeddings": true,
103
+ "transformers_version": "5.7.0",
104
+ "use_cache": false,
105
+ "vocab_size": 50368
106
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cae1813d7507c82e83ca0fe14cc1e66f5a42448cce4b1cde4e5a3fdfb56a7d33
3
+ size 1502347264
test_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "test_accuracy": 0.9749472650041899,
4
+ "test_f1": 0.8915077989601387,
5
+ "test_loss": 0.30494070053100586,
6
+ "test_precision": 0.8730482009504412,
7
+ "test_recall": 0.9107648725212465,
8
+ "test_runtime": 201.6979,
9
+ "test_samples_per_second": 17.12,
10
+ "test_steps_per_second": 1.071
11
+ }
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
+ }
trainer_state.json ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 440,
3
+ "best_metric": 0.9371466577984703,
4
+ "best_model_checkpoint": "ner_model/trial_0/checkpoint-440",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 440,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.22779043280182232,
14
+ "grad_norm": 21.80908203125,
15
+ "learning_rate": 3.899594554207158e-05,
16
+ "loss": 4.429600219726563,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.45558086560364464,
21
+ "grad_norm": 12.349945068359375,
22
+ "learning_rate": 3.4009251738737616e-05,
23
+ "loss": 0.8959714508056641,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.683371298405467,
28
+ "grad_norm": 7.801368236541748,
29
+ "learning_rate": 2.9022557935403655e-05,
30
+ "loss": 0.6988069152832032,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.9111617312072893,
35
+ "grad_norm": 8.062862396240234,
36
+ "learning_rate": 2.4035864132069692e-05,
37
+ "loss": 0.4868038177490234,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 1.0,
42
+ "eval_accuracy": 0.9839882395009735,
43
+ "eval_f1": 0.9144043171440432,
44
+ "eval_loss": 0.12814635038375854,
45
+ "eval_precision": 0.9023431099459283,
46
+ "eval_recall": 0.9267923258162235,
47
+ "eval_runtime": 214.1736,
48
+ "eval_samples_per_second": 15.175,
49
+ "eval_steps_per_second": 0.952,
50
+ "step": 220
51
+ },
52
+ {
53
+ "epoch": 1.1366742596810935,
54
+ "grad_norm": 10.9319486618042,
55
+ "learning_rate": 1.904917032873573e-05,
56
+ "loss": 0.37126468658447265,
57
+ "step": 250
58
+ },
59
+ {
60
+ "epoch": 1.3644646924829158,
61
+ "grad_norm": 7.102725505828857,
62
+ "learning_rate": 1.406247652540177e-05,
63
+ "loss": 0.2684678649902344,
64
+ "step": 300
65
+ },
66
+ {
67
+ "epoch": 1.592255125284738,
68
+ "grad_norm": 15.202373504638672,
69
+ "learning_rate": 9.07578272206781e-06,
70
+ "loss": 0.2503110694885254,
71
+ "step": 350
72
+ },
73
+ {
74
+ "epoch": 1.8200455580865604,
75
+ "grad_norm": 8.701669692993164,
76
+ "learning_rate": 4.089088918733848e-06,
77
+ "loss": 0.17738252639770508,
78
+ "step": 400
79
+ },
80
+ {
81
+ "epoch": 2.0,
82
+ "eval_accuracy": 0.9879746248692174,
83
+ "eval_f1": 0.9371466577984703,
84
+ "eval_loss": 0.09272900968790054,
85
+ "eval_precision": 0.9260598093986198,
86
+ "eval_recall": 0.9485021878155503,
87
+ "eval_runtime": 233.7442,
88
+ "eval_samples_per_second": 13.904,
89
+ "eval_steps_per_second": 0.873,
90
+ "step": 440
91
+ },
92
+ {
93
+ "epoch": 2.0,
94
+ "step": 440,
95
+ "total_flos": 3263842854590472.0,
96
+ "train_loss": 0.8773450081998652,
97
+ "train_runtime": 3811.6545,
98
+ "train_samples_per_second": 7.367,
99
+ "train_steps_per_second": 0.115
100
+ },
101
+ {
102
+ "epoch": 2.0,
103
+ "step": 440,
104
+ "test_accuracy": 0.9749472650041899,
105
+ "test_f1": 0.8915077989601387,
106
+ "test_loss": 0.30494070053100586,
107
+ "test_precision": 0.8730482009504412,
108
+ "test_recall": 0.9107648725212465,
109
+ "test_runtime": 201.6979,
110
+ "test_samples_per_second": 17.12,
111
+ "test_steps_per_second": 1.071
112
+ }
113
+ ],
114
+ "logging_steps": 50,
115
+ "max_steps": 440,
116
+ "num_input_tokens_seen": 0,
117
+ "num_train_epochs": 2,
118
+ "save_steps": 500,
119
+ "stateful_callbacks": {
120
+ "TrainerControl": {
121
+ "args": {
122
+ "should_epoch_stop": false,
123
+ "should_evaluate": false,
124
+ "should_log": false,
125
+ "should_save": true,
126
+ "should_training_stop": true
127
+ },
128
+ "attributes": {}
129
+ }
130
+ },
131
+ "total_flos": 3263842854590472.0,
132
+ "train_batch_size": 16,
133
+ "trial_name": null,
134
+ "trial_params": null
135
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73d85baf25e9df26706b163ba73ddd6fff6a3cbcced0845174bd510dfbdfeb80
3
+ size 5265