Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +114 -0
- pytorch_model.bin +3 -0
- runs/Mar29_15-46-53_602bea06de11/1680104825.2226512/events.out.tfevents.1680104825.602bea06de11.198.5 +3 -0
- runs/Mar29_15-46-53_602bea06de11/events.out.tfevents.1680104825.602bea06de11.198.4 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "elastic/distilbert-base-cased-finetuned-conll03-english",
|
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": "B-BUT",
|
14 |
+
"1": "I-BUT",
|
15 |
+
"2": "B-CALM_DOWN",
|
16 |
+
"3": "I-CALM_DOWN",
|
17 |
+
"4": "B-COME_ON",
|
18 |
+
"5": "I-COME_ON",
|
19 |
+
"6": "B-EMPHATIC",
|
20 |
+
"7": "I-EMPHATIC",
|
21 |
+
"8": "B-ENTHUSIASTIC",
|
22 |
+
"9": "I-ENTHUSIASTIC",
|
23 |
+
"10": "B-EXPLAIN",
|
24 |
+
"11": "I-EXPLAIN",
|
25 |
+
"12": "B-FRONT",
|
26 |
+
"13": "I-FRONT",
|
27 |
+
"14": "B-GREET",
|
28 |
+
"15": "I-GREET",
|
29 |
+
"16": "B-ITERATE",
|
30 |
+
"17": "I-ITERATE",
|
31 |
+
"18": "B-NEUTRAL",
|
32 |
+
"19": "I-NEUTRAL",
|
33 |
+
"20": "B-NO",
|
34 |
+
"21": "I-NO",
|
35 |
+
"22": "B-NO_GESTURE",
|
36 |
+
"23": "I-NO_GESTURE",
|
37 |
+
"24": "B-OTHER_PEER",
|
38 |
+
"25": "I-OTHER_PEER",
|
39 |
+
"26": "B-PLEASE",
|
40 |
+
"27": "I-PLEASE",
|
41 |
+
"28": "B-QUESTION",
|
42 |
+
"29": "I-QUESTION",
|
43 |
+
"30": "B-SELF",
|
44 |
+
"31": "I-SELF",
|
45 |
+
"32": "B-SORRY",
|
46 |
+
"33": "I-SORRY",
|
47 |
+
"34": "B-THANKS",
|
48 |
+
"35": "I-THANKS",
|
49 |
+
"36": "B-THINKING",
|
50 |
+
"37": "I-THINKING",
|
51 |
+
"38": "B-THIRD_PERSON",
|
52 |
+
"39": "I-THIRD_PERSON",
|
53 |
+
"40": "B-YES",
|
54 |
+
"41": "I-YES"
|
55 |
+
},
|
56 |
+
"initializer_range": 0.02,
|
57 |
+
"label2id": {
|
58 |
+
"B-BUT": 0,
|
59 |
+
"B-CALM_DOWN": 2,
|
60 |
+
"B-COME_ON": 4,
|
61 |
+
"B-EMPHATIC": 6,
|
62 |
+
"B-ENTHUSIASTIC": 8,
|
63 |
+
"B-EXPLAIN": 10,
|
64 |
+
"B-FRONT": 12,
|
65 |
+
"B-GREET": 14,
|
66 |
+
"B-ITERATE": 16,
|
67 |
+
"B-NEUTRAL": 18,
|
68 |
+
"B-NO": 20,
|
69 |
+
"B-NO_GESTURE": 22,
|
70 |
+
"B-OTHER_PEER": 24,
|
71 |
+
"B-PLEASE": 26,
|
72 |
+
"B-QUESTION": 28,
|
73 |
+
"B-SELF": 30,
|
74 |
+
"B-SORRY": 32,
|
75 |
+
"B-THANKS": 34,
|
76 |
+
"B-THINKING": 36,
|
77 |
+
"B-THIRD_PERSON": 38,
|
78 |
+
"B-YES": 40,
|
79 |
+
"I-BUT": 1,
|
80 |
+
"I-CALM_DOWN": 3,
|
81 |
+
"I-COME_ON": 5,
|
82 |
+
"I-EMPHATIC": 7,
|
83 |
+
"I-ENTHUSIASTIC": 9,
|
84 |
+
"I-EXPLAIN": 11,
|
85 |
+
"I-FRONT": 13,
|
86 |
+
"I-GREET": 15,
|
87 |
+
"I-ITERATE": 17,
|
88 |
+
"I-NEUTRAL": 19,
|
89 |
+
"I-NO": 21,
|
90 |
+
"I-NO_GESTURE": 23,
|
91 |
+
"I-OTHER_PEER": 25,
|
92 |
+
"I-PLEASE": 27,
|
93 |
+
"I-QUESTION": 29,
|
94 |
+
"I-SELF": 31,
|
95 |
+
"I-SORRY": 33,
|
96 |
+
"I-THANKS": 35,
|
97 |
+
"I-THINKING": 37,
|
98 |
+
"I-THIRD_PERSON": 39,
|
99 |
+
"I-YES": 41
|
100 |
+
},
|
101 |
+
"max_position_embeddings": 512,
|
102 |
+
"model_type": "distilbert",
|
103 |
+
"n_heads": 12,
|
104 |
+
"n_layers": 6,
|
105 |
+
"output_past": true,
|
106 |
+
"pad_token_id": 0,
|
107 |
+
"qa_dropout": 0.1,
|
108 |
+
"seq_classif_dropout": 0.2,
|
109 |
+
"sinusoidal_pos_embds": false,
|
110 |
+
"tie_weights_": true,
|
111 |
+
"torch_dtype": "float32",
|
112 |
+
"transformers_version": "4.27.3",
|
113 |
+
"vocab_size": 28996
|
114 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbc125954e7b5055593d79e7b8c802836521292383cfe9f42c229a345a9504a8
|
3 |
+
size 260927653
|
runs/Mar29_15-46-53_602bea06de11/1680104825.2226512/events.out.tfevents.1680104825.602bea06de11.198.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:632dd504a0a956f9cf29f54e8884316d7b561fa37b04452377041dabb3ccac5e
|
3 |
+
size 5910
|
runs/Mar29_15-46-53_602bea06de11/events.out.tfevents.1680104825.602bea06de11.198.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fde98ba8e50e2d3bf6bdc064dd67acd19e217269e7a3bf49fa7654eac1651a3
|
3 |
+
size 6498
|
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 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_basic_tokenize": true,
|
5 |
+
"do_lower_case": false,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"model_max_length": 512,
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--elastic--distilbert-base-cased-finetuned-conll03-english/snapshots/feacb62c370dc6cc1cf311a423881e5f3473f92c/special_tokens_map.json",
|
12 |
+
"strip_accents": null,
|
13 |
+
"tokenize_chinese_chars": true,
|
14 |
+
"tokenizer_class": "DistilBertTokenizer",
|
15 |
+
"unk_token": "[UNK]"
|
16 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18696ba4a9520f654bbc31743b3e5cedbd974c9b1d55b340560e5d8d1348f363
|
3 |
+
size 3643
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|