Hugging Face's logo

tuenguyen
/
token_classification_model

Token Classification
Transformers
Safetensors
roberta
Inference Endpoints
Model card Files Community
tuenguyen commited on
Commit
5b0850b
•
1 Parent(s): f6feaf0

Upload 8 files

Browse files
Files changed (8) hide show
  1. config.json +53 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +15 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +57 -0
  7. trainer_state.json +57 -0
  8. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "FacebookAI/roberta-base",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 3072,
28
+ "label2id": {
29
+ "LABEL_0": 0,
30
+ "LABEL_1": 1,
31
+ "LABEL_10": 10,
32
+ "LABEL_2": 2,
33
+ "LABEL_3": 3,
34
+ "LABEL_4": 4,
35
+ "LABEL_5": 5,
36
+ "LABEL_6": 6,
37
+ "LABEL_7": 7,
38
+ "LABEL_8": 8,
39
+ "LABEL_9": 9
40
+ },
41
+ "layer_norm_eps": 1e-05,
42
+ "max_position_embeddings": 514,
43
+ "model_type": "roberta",
44
+ "num_attention_heads": 12,
45
+ "num_hidden_layers": 12,
46
+ "pad_token_id": 1,
47
+ "position_embedding_type": "absolute",
48
+ "torch_dtype": "float32",
49
+ "transformers_version": "4.37.2",
50
+ "type_vocab_size": 1,
51
+ "use_cache": true,
52
+ "vocab_size": 50265
53
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57dd0480847948812b93bf9ec79718747b38af04f20204330cebc052335d1286
3
+ size 496277924
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "</s>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "</s>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
trainer_state.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 314,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "learning_rate": 6.254980079681275e-05,
14
+ "loss": 0.3437,
15
+ "step": 157
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.9989770448872703,
20
+ "eval_f1": 0.9949637636653974,
21
+ "eval_loss": 0.0055595990270376205,
22
+ "eval_precision": 0.995085995085995,
23
+ "eval_recall": 0.9948415622697127,
24
+ "eval_runtime": 3.3496,
25
+ "eval_samples_per_second": 298.841,
26
+ "eval_steps_per_second": 2.388,
27
+ "step": 157
28
+ },
29
+ {
30
+ "epoch": 2.0,
31
+ "learning_rate": 0.0,
32
+ "loss": 0.0042,
33
+ "step": 314
34
+ },
35
+ {
36
+ "epoch": 2.0,
37
+ "eval_accuracy": 0.9994271451368714,
38
+ "eval_f1": 0.9968066814050602,
39
+ "eval_loss": 0.0035066502168774605,
40
+ "eval_precision": 0.9968066814050602,
41
+ "eval_recall": 0.9968066814050602,
42
+ "eval_runtime": 4.8918,
43
+ "eval_samples_per_second": 204.63,
44
+ "eval_steps_per_second": 1.635,
45
+ "step": 314
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 314,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 2,
52
+ "save_steps": 500,
53
+ "total_flos": 449632356350856.0,
54
+ "train_batch_size": 64,
55
+ "trial_name": null,
56
+ "trial_params": null
57
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff