Upload 8 files
Browse files- config.json +62 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- trainer_state.json +75 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "O",
|
13 |
+
"1": "LDEMO",
|
14 |
+
"2": "LB",
|
15 |
+
"3": "VBA",
|
16 |
+
"4": "LGROUND",
|
17 |
+
"5": "LBALL",
|
18 |
+
"6": "LSP",
|
19 |
+
"7": "VSPEED",
|
20 |
+
"8": "LD",
|
21 |
+
"9": "VDIR",
|
22 |
+
"10": "LBRAKE",
|
23 |
+
"11": "LSTE",
|
24 |
+
"12": "VSTEER",
|
25 |
+
"13": "LTHROT",
|
26 |
+
"14": "VTHROTTLE",
|
27 |
+
"15": "LBOOST",
|
28 |
+
"16": "LPOS"
|
29 |
+
},
|
30 |
+
"initializer_range": 0.02,
|
31 |
+
"label2id": {
|
32 |
+
"LB": 2,
|
33 |
+
"LBALL": 5,
|
34 |
+
"LBOOST": 15,
|
35 |
+
"LBRAKE": 10,
|
36 |
+
"LD": 8,
|
37 |
+
"LDEMO": 1,
|
38 |
+
"LGROUND": 4,
|
39 |
+
"LPOS": 16,
|
40 |
+
"LSP": 6,
|
41 |
+
"LSTE": 11,
|
42 |
+
"LTHROT": 13,
|
43 |
+
"O": 0,
|
44 |
+
"VBA": 3,
|
45 |
+
"VDIR": 9,
|
46 |
+
"VSPEED": 7,
|
47 |
+
"VSTEER": 12,
|
48 |
+
"VTHROTTLE": 14
|
49 |
+
},
|
50 |
+
"max_position_embeddings": 512,
|
51 |
+
"model_type": "distilbert",
|
52 |
+
"n_heads": 12,
|
53 |
+
"n_layers": 6,
|
54 |
+
"pad_token_id": 0,
|
55 |
+
"qa_dropout": 0.1,
|
56 |
+
"seq_classif_dropout": 0.2,
|
57 |
+
"sinusoidal_pos_embds": false,
|
58 |
+
"tie_weights_": true,
|
59 |
+
"torch_dtype": "float32",
|
60 |
+
"transformers_version": "4.44.2",
|
61 |
+
"vocab_size": 30522
|
62 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d52c709be5268db5b43986f1c4a7b04a3e5a1e251fc16318e82b148b3293e5d5
|
3 |
+
size 265516156
|
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 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 170,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.29411764705882354,
|
13 |
+
"grad_norm": 0.6570231914520264,
|
14 |
+
"learning_rate": 1.4117647058823532e-05,
|
15 |
+
"loss": 1.7885,
|
16 |
+
"step": 50
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.5882352941176471,
|
20 |
+
"grad_norm": 0.4875588119029999,
|
21 |
+
"learning_rate": 8.23529411764706e-06,
|
22 |
+
"loss": 1.1021,
|
23 |
+
"step": 100
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.8823529411764706,
|
27 |
+
"grad_norm": 0.49891045689582825,
|
28 |
+
"learning_rate": 2.3529411764705885e-06,
|
29 |
+
"loss": 0.8354,
|
30 |
+
"step": 150
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 1.0,
|
34 |
+
"eval_accuracy": 0.6922833279324294,
|
35 |
+
"eval_f1": 0.3653082805262036,
|
36 |
+
"eval_loss": 0.7156894207000732,
|
37 |
+
"eval_precision": 0.5395248279438931,
|
38 |
+
"eval_recall": 0.2761404816941317,
|
39 |
+
"eval_runtime": 44.3167,
|
40 |
+
"eval_samples_per_second": 557.894,
|
41 |
+
"eval_steps_per_second": 1.106,
|
42 |
+
"step": 170
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 1.0,
|
46 |
+
"step": 170,
|
47 |
+
"total_flos": 1540622822358936.0,
|
48 |
+
"train_loss": 1.187572114607867,
|
49 |
+
"train_runtime": 230.4334,
|
50 |
+
"train_samples_per_second": 375.523,
|
51 |
+
"train_steps_per_second": 0.738
|
52 |
+
}
|
53 |
+
],
|
54 |
+
"logging_steps": 50,
|
55 |
+
"max_steps": 170,
|
56 |
+
"num_input_tokens_seen": 0,
|
57 |
+
"num_train_epochs": 1,
|
58 |
+
"save_steps": 50,
|
59 |
+
"stateful_callbacks": {
|
60 |
+
"TrainerControl": {
|
61 |
+
"args": {
|
62 |
+
"should_epoch_stop": false,
|
63 |
+
"should_evaluate": false,
|
64 |
+
"should_log": false,
|
65 |
+
"should_save": true,
|
66 |
+
"should_training_stop": true
|
67 |
+
},
|
68 |
+
"attributes": {}
|
69 |
+
}
|
70 |
+
},
|
71 |
+
"total_flos": 1540622822358936.0,
|
72 |
+
"train_batch_size": 512,
|
73 |
+
"trial_name": null,
|
74 |
+
"trial_params": null
|
75 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6361cd3ff4a0f8e4f2f367517713478416342f5ccec8908600f242cebd18e1f9
|
3 |
+
size 5176
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|