quim-motger commited on
Commit
ce87de4
1 Parent(s): 4f33dc0

upload model files

Browse files
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-large-uncased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "B-feature",
15
+ "2": "I-feature"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
19
+ "label2id": {
20
+ "B-feature": 1,
21
+ "I-feature": 2,
22
+ "O": 0
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 16,
28
+ "num_hidden_layers": 24,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.30.2",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9576cd0dbd5f4c93b2be38fea11978b621a028486e6acc05c9d1257822f8627
3
+ size 2672992581
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a291b2e7d67d79083e86a0190590e2286dd80669c4ecf58fc2f5fd765e9662e5
3
+ size 1336519661
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:989474c474b2a7f63747f726408a1e702cf9862b4f2aac664325f5786914bd00
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30269608c9e0540a595d8484ff39d209fca7698cf0f2639d73b5d81109885fed
3
+ size 627
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "BertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0068976194597780704,
3
+ "best_model_checkpoint": "data/train-test///model/checkpoint-1676",
4
+ "epoch": 1.0,
5
+ "global_step": 1676,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.3,
12
+ "learning_rate": 1.7016706443914083e-05,
13
+ "loss": 0.0317,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.6,
18
+ "learning_rate": 1.4033412887828164e-05,
19
+ "loss": 0.0069,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.89,
24
+ "learning_rate": 1.1050119331742244e-05,
25
+ "loss": 0.0057,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 1.0,
30
+ "eval_accuracy": null,
31
+ "eval_f1": 0.9892573563755255,
32
+ "eval_loss": 0.0068976194597780704,
33
+ "eval_precision": 0.988795518207283,
34
+ "eval_recall": 0.9897196261682243,
35
+ "eval_runtime": 1.0104,
36
+ "eval_samples_per_second": 960.031,
37
+ "eval_steps_per_second": 60.373,
38
+ "step": 1676
39
+ }
40
+ ],
41
+ "max_steps": 3352,
42
+ "num_train_epochs": 2,
43
+ "total_flos": 2754552464105454.0,
44
+ "trial_name": null,
45
+ "trial_params": null
46
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcd4c8e96bb6df9697ffa863eba7f459db1f041b35419ef338624481154b1e20
3
+ size 3963
vocab.txt ADDED
The diff for this file is too large to render. See raw diff