Upload 11 files
Browse files- config.json +75 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- trainer_state.json +25 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/content/event_cat/checkpoint-300",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "A party",
|
13 |
+
"1": "Birthday party",
|
14 |
+
"2": "Boarding fees",
|
15 |
+
"3": "Charity",
|
16 |
+
"4": "Coffee outing",
|
17 |
+
"5": "Dentist appointment",
|
18 |
+
"6": "Dinner or lunch out",
|
19 |
+
"7": "Doctor appointment",
|
20 |
+
"8": "Exams",
|
21 |
+
"9": "Get together",
|
22 |
+
"10": "Grocery shopping",
|
23 |
+
"11": "Haircut",
|
24 |
+
"12": "Health checkup",
|
25 |
+
"13": "Movie night",
|
26 |
+
"14": "Musical show",
|
27 |
+
"15": "Other",
|
28 |
+
"16": "Saloon appointment",
|
29 |
+
"17": "Shopping outing",
|
30 |
+
"18": "Trips",
|
31 |
+
"19": "Virtual event",
|
32 |
+
"20": "Visit grand parents",
|
33 |
+
"21": "Wedding",
|
34 |
+
"22": "Workouts or Gym"
|
35 |
+
},
|
36 |
+
"initializer_range": 0.02,
|
37 |
+
"label2id": {
|
38 |
+
"A party": 0,
|
39 |
+
"Birthday party": 1,
|
40 |
+
"Boarding fees": 2,
|
41 |
+
"Charity": 3,
|
42 |
+
"Coffee outing": 4,
|
43 |
+
"Dentist appointment": 5,
|
44 |
+
"Dinner or lunch out": 6,
|
45 |
+
"Doctor appointment": 7,
|
46 |
+
"Exams": 8,
|
47 |
+
"Get together": 9,
|
48 |
+
"Grocery shopping": 10,
|
49 |
+
"Haircut": 11,
|
50 |
+
"Health checkup": 12,
|
51 |
+
"Movie night": 13,
|
52 |
+
"Musical show": 14,
|
53 |
+
"Other": 15,
|
54 |
+
"Saloon appointment": 16,
|
55 |
+
"Shopping outing": 17,
|
56 |
+
"Trips": 18,
|
57 |
+
"Virtual event": 19,
|
58 |
+
"Visit grand parents": 20,
|
59 |
+
"Wedding": 21,
|
60 |
+
"Workouts or Gym": 22
|
61 |
+
},
|
62 |
+
"max_position_embeddings": 512,
|
63 |
+
"model_type": "distilbert",
|
64 |
+
"n_heads": 12,
|
65 |
+
"n_layers": 6,
|
66 |
+
"pad_token_id": 0,
|
67 |
+
"problem_type": "single_label_classification",
|
68 |
+
"qa_dropout": 0.1,
|
69 |
+
"seq_classif_dropout": 0.2,
|
70 |
+
"sinusoidal_pos_embds": false,
|
71 |
+
"tie_weights_": true,
|
72 |
+
"torch_dtype": "float32",
|
73 |
+
"transformers_version": "4.26.1",
|
74 |
+
"vocab_size": 30522
|
75 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cf3ed28b904a2dd6e18542f30fcbe9e65a3d14297596d7529eb59d1058cbf90
|
3 |
+
size 535830085
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a47c242ecda63cb680ab79aace290709ac7e00c44487824e13eb17e4e393b12a
|
3 |
+
size 267920109
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb4c0b3ca9337c0758f0bae7c439f633b168f835815677040a91f5b5d654ea7a
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abd65622b00542a2477df9109020601f2870ab1b29de07c6f9f157414e14cf56
|
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 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_lower_case": true,
|
4 |
+
"mask_token": "[MASK]",
|
5 |
+
"model_max_length": 512,
|
6 |
+
"name_or_path": "/content/event_cat/checkpoint-300",
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"special_tokens_map_file": null,
|
10 |
+
"strip_accents": null,
|
11 |
+
"tokenize_chinese_chars": true,
|
12 |
+
"tokenizer_class": "DistilBertTokenizer",
|
13 |
+
"unk_token": "[UNK]"
|
14 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.681374192237854,
|
3 |
+
"best_model_checkpoint": "event_cat/checkpoint-30",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 30,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"eval_accuracy": 0.92,
|
13 |
+
"eval_loss": 0.681374192237854,
|
14 |
+
"eval_runtime": 0.3288,
|
15 |
+
"eval_samples_per_second": 152.084,
|
16 |
+
"eval_steps_per_second": 12.167,
|
17 |
+
"step": 30
|
18 |
+
}
|
19 |
+
],
|
20 |
+
"max_steps": 600,
|
21 |
+
"num_train_epochs": 20,
|
22 |
+
"total_flos": 28528168388886.0,
|
23 |
+
"trial_name": null,
|
24 |
+
"trial_params": null
|
25 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47c03206a00743ffbef8921ebe29f8e2490b036bd1383cf9f15a66135c8643c3
|
3 |
+
size 3451
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|