cwchang commited on
Commit
73c9c5c
1 Parent(s): ca6e4c6

End of training

Browse files
README.md ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: distilbert-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - conll2003
8
+ model-index:
9
+ - name: ner_model
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # ner_model
17
+
18
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the conll2003 dataset.
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
+ - train_batch_size: 8
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 3.0
44
+
45
+ ### Framework versions
46
+
47
+ - Transformers 4.36.0.dev0
48
+ - Pytorch 2.1.0+cu118
49
+ - Datasets 2.15.0
50
+ - Tokenizers 0.15.0
all_results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.9877146528561972,
4
+ "eval_f1": 0.9397145256087323,
5
+ "eval_loss": 0.055851779878139496,
6
+ "eval_precision": 0.9376675603217158,
7
+ "eval_recall": 0.9417704476607203,
8
+ "eval_runtime": 7.0625,
9
+ "eval_samples": 3250,
10
+ "eval_samples_per_second": 460.177,
11
+ "eval_steps_per_second": 57.628,
12
+ "train_loss": 0.044327347904964204,
13
+ "train_runtime": 311.2643,
14
+ "train_samples": 14041,
15
+ "train_samples_per_second": 135.329,
16
+ "train_steps_per_second": 16.925
17
+ }
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-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": "O",
14
+ "1": "B-PER",
15
+ "2": "I-PER",
16
+ "3": "B-ORG",
17
+ "4": "I-ORG",
18
+ "5": "B-LOC",
19
+ "6": "I-LOC",
20
+ "7": "B-MISC",
21
+ "8": "I-MISC"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "label2id": {
25
+ "B-LOC": 5,
26
+ "B-MISC": 7,
27
+ "B-ORG": 3,
28
+ "B-PER": 1,
29
+ "I-LOC": 6,
30
+ "I-MISC": 8,
31
+ "I-ORG": 4,
32
+ "I-PER": 2,
33
+ "O": 0
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": false,
43
+ "tie_weights_": true,
44
+ "torch_dtype": "float32",
45
+ "transformers_version": "4.36.0.dev0",
46
+ "vocab_size": 30522
47
+ }
eval_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.9877146528561972,
4
+ "eval_f1": 0.9397145256087323,
5
+ "eval_loss": 0.055851779878139496,
6
+ "eval_precision": 0.9376675603217158,
7
+ "eval_recall": 0.9417704476607203,
8
+ "eval_runtime": 7.0625,
9
+ "eval_samples": 3250,
10
+ "eval_samples_per_second": 460.177,
11
+ "eval_steps_per_second": 57.628
12
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73b49b372a7d4625a2ad7b5422e68f321560e0c5187572781660f59e92250f5c
3
+ size 265491548
runs/Dec04_10-18-50_1261423ab883/events.out.tfevents.1701685157.1261423ab883.2501.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7976538e51c739926823f6bf5a334d5c4746654a2d29ae369c48de489d03c758
3
+ size 6515
runs/Dec04_10-18-50_1261423ab883/events.out.tfevents.1701685476.1261423ab883.2501.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c455c5f9960a9949417678d0668861d4a1057b4457a520ac3a98b211e7fa1dc
3
+ size 560
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.044327347904964204,
4
+ "train_runtime": 311.2643,
5
+ "train_samples": 14041,
6
+ "train_samples_per_second": 135.329,
7
+ "train_steps_per_second": 16.925
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5268,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.28,
13
+ "learning_rate": 4.525436598329537e-05,
14
+ "loss": 0.1662,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.57,
19
+ "learning_rate": 4.050873196659074e-05,
20
+ "loss": 0.0736,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.85,
25
+ "learning_rate": 3.5763097949886106e-05,
26
+ "loss": 0.0629,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 1.14,
31
+ "learning_rate": 3.1017463933181475e-05,
32
+ "loss": 0.042,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.42,
37
+ "learning_rate": 2.6271829916476843e-05,
38
+ "loss": 0.028,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 1.71,
43
+ "learning_rate": 2.152619589977221e-05,
44
+ "loss": 0.0283,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 1.99,
49
+ "learning_rate": 1.678056188306758e-05,
50
+ "loss": 0.0244,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 2.28,
55
+ "learning_rate": 1.2034927866362947e-05,
56
+ "loss": 0.012,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 2.56,
61
+ "learning_rate": 7.289293849658315e-06,
62
+ "loss": 0.0112,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 2.85,
67
+ "learning_rate": 2.5436598329536827e-06,
68
+ "loss": 0.0135,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 3.0,
73
+ "step": 5268,
74
+ "total_flos": 445788652997016.0,
75
+ "train_loss": 0.044327347904964204,
76
+ "train_runtime": 311.2643,
77
+ "train_samples_per_second": 135.329,
78
+ "train_steps_per_second": 16.925
79
+ }
80
+ ],
81
+ "logging_steps": 500,
82
+ "max_steps": 5268,
83
+ "num_input_tokens_seen": 0,
84
+ "num_train_epochs": 3,
85
+ "save_steps": 500,
86
+ "total_flos": 445788652997016.0,
87
+ "trial_name": null,
88
+ "trial_params": null
89
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a07260d95fd4eb5e3b6cd7b3391b25472cfa0b15a613ca8e828a9e11bbcd89d
3
+ size 4728
vocab.txt ADDED
The diff for this file is too large to render. See raw diff