Sebastian Alejandro Donoso Bustos commited on
Commit
1a794e4
1 Parent(s): 865cd03

adding model finetuned on NER

Browse files
all_results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.9592208294396288,
4
+ "eval_f1": 0.7977113603854551,
5
+ "eval_loss": 0.142496719956398,
6
+ "eval_precision": 0.7950180072028812,
7
+ "eval_recall": 0.8004230246260764,
8
+ "eval_runtime": 1.7114,
9
+ "eval_samples": 1916,
10
+ "eval_samples_per_second": 1119.532,
11
+ "eval_steps_per_second": 35.058,
12
+ "train_loss": 0.1423617688175362,
13
+ "train_runtime": 34.8094,
14
+ "train_samples": 8324,
15
+ "train_samples_per_second": 717.393,
16
+ "train_steps_per_second": 22.494
17
+ }
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "CenIA/distillbert-base-spanish-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForTokenClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "finetuning_task": "ner",
11
+ "hidden_dim": 3072,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "label2id": {
25
+ "LABEL_0": 0,
26
+ "LABEL_1": 1,
27
+ "LABEL_2": 2,
28
+ "LABEL_3": 3,
29
+ "LABEL_4": 4,
30
+ "LABEL_5": 5,
31
+ "LABEL_6": 6,
32
+ "LABEL_7": 7,
33
+ "LABEL_8": 8
34
+ },
35
+ "max_position_embeddings": 512,
36
+ "model_type": "distilbert",
37
+ "n_heads": 12,
38
+ "n_layers": 6,
39
+ "pad_token_id": 0,
40
+ "qa_dropout": 0.1,
41
+ "seq_classif_dropout": 0.2,
42
+ "sinusoidal_pos_embds": true,
43
+ "tie_weights_": true,
44
+ "torch_dtype": "float32",
45
+ "transformers_version": "4.12.5",
46
+ "vocab_size": 31002
47
+ }
eval_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.9592208294396288,
4
+ "eval_f1": 0.7977113603854551,
5
+ "eval_loss": 0.142496719956398,
6
+ "eval_precision": 0.7950180072028812,
7
+ "eval_recall": 0.8004230246260764,
8
+ "eval_runtime": 1.7114,
9
+ "eval_samples": 1916,
10
+ "eval_samples_per_second": 1119.532,
11
+ "eval_steps_per_second": 35.058
12
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ed4d302c84626a363602f463b093875bd7710cc9602a0041a24818e4d153fd9
3
+ size 266993141
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "do_basic_tokenize": true, "never_split": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "CenIA/distillbert-base-spanish-uncased", "tokenizer_class": "DistilBertTokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.1423617688175362,
4
+ "train_runtime": 34.8094,
5
+ "train_samples": 8324,
6
+ "train_samples_per_second": 717.393,
7
+ "train_steps_per_second": 22.494
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 783,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.92,
12
+ "learning_rate": 1.826309067688378e-05,
13
+ "loss": 0.1857,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 3.0,
18
+ "step": 783,
19
+ "total_flos": 630881172395712.0,
20
+ "train_loss": 0.1423617688175362,
21
+ "train_runtime": 34.8094,
22
+ "train_samples_per_second": 717.393,
23
+ "train_steps_per_second": 22.494
24
+ }
25
+ ],
26
+ "max_steps": 783,
27
+ "num_train_epochs": 3,
28
+ "total_flos": 630881172395712.0,
29
+ "trial_name": null,
30
+ "trial_params": null
31
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebf6ad43cabf28d1f8700d1ffd4838c62088e573fc3604d73ed8c5c09ca6fa79
3
+ size 2863
vocab.txt ADDED
The diff for this file is too large to render. See raw diff