Upload 11 files
Browse files- config.json +33 -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 +13 -0
- trainer_state.json +106 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
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": "NON-RELEVANT",
|
13 |
+
"1": "RELEVANT"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"label2id": {
|
17 |
+
"NON-RELEVANT": 0,
|
18 |
+
"RELEVANT": 1
|
19 |
+
},
|
20 |
+
"max_position_embeddings": 512,
|
21 |
+
"model_type": "distilbert",
|
22 |
+
"n_heads": 12,
|
23 |
+
"n_layers": 6,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"problem_type": "single_label_classification",
|
26 |
+
"qa_dropout": 0.1,
|
27 |
+
"seq_classif_dropout": 0.2,
|
28 |
+
"sinusoidal_pos_embds": false,
|
29 |
+
"tie_weights_": true,
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.28.1",
|
32 |
+
"vocab_size": 30522
|
33 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55ae65d7db77fc92f7064fbba38a79ffd5b5dd93d6e95b4ae4c1ef0338e1dbf2
|
3 |
+
size 535698053
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20d8eb2cb54d6cc7503fa4760822db643be2b886eda404d0e4abd6c3523f3bdd
|
3 |
+
size 267854125
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e24c70d52161dbcb5158286e2f42d69f37b0541ed2f096f42e1ed0d9806f122
|
3 |
+
size 13553
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2350d076c30f249d9133ba20b2ce1b6f0798c07ab6eeae44685b28b0e30d03d
|
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": "DistilBertTokenizer",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.4252347946166992,
|
3 |
+
"best_model_checkpoint": "/content/drive/My Drive/rele_model/checkpoint-50",
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 50,
|
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": 0.696969696969697,
|
13 |
+
"eval_loss": 0.6476646661758423,
|
14 |
+
"eval_runtime": 4.1809,
|
15 |
+
"eval_samples_per_second": 7.893,
|
16 |
+
"eval_steps_per_second": 0.718,
|
17 |
+
"step": 5
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 2.0,
|
21 |
+
"eval_accuracy": 0.696969696969697,
|
22 |
+
"eval_loss": 0.6051351428031921,
|
23 |
+
"eval_runtime": 3.7537,
|
24 |
+
"eval_samples_per_second": 8.791,
|
25 |
+
"eval_steps_per_second": 0.799,
|
26 |
+
"step": 10
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 3.0,
|
30 |
+
"eval_accuracy": 0.696969696969697,
|
31 |
+
"eval_loss": 0.5726537704467773,
|
32 |
+
"eval_runtime": 4.6254,
|
33 |
+
"eval_samples_per_second": 7.135,
|
34 |
+
"eval_steps_per_second": 0.649,
|
35 |
+
"step": 15
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 4.0,
|
39 |
+
"eval_accuracy": 0.696969696969697,
|
40 |
+
"eval_loss": 0.5456787943840027,
|
41 |
+
"eval_runtime": 4.55,
|
42 |
+
"eval_samples_per_second": 7.253,
|
43 |
+
"eval_steps_per_second": 0.659,
|
44 |
+
"step": 20
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 5.0,
|
48 |
+
"eval_accuracy": 0.7272727272727273,
|
49 |
+
"eval_loss": 0.5086619257926941,
|
50 |
+
"eval_runtime": 2.8705,
|
51 |
+
"eval_samples_per_second": 11.496,
|
52 |
+
"eval_steps_per_second": 1.045,
|
53 |
+
"step": 25
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 6.0,
|
57 |
+
"eval_accuracy": 0.8181818181818182,
|
58 |
+
"eval_loss": 0.4745181202888489,
|
59 |
+
"eval_runtime": 4.6427,
|
60 |
+
"eval_samples_per_second": 7.108,
|
61 |
+
"eval_steps_per_second": 0.646,
|
62 |
+
"step": 30
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 7.0,
|
66 |
+
"eval_accuracy": 0.8484848484848485,
|
67 |
+
"eval_loss": 0.4539332985877991,
|
68 |
+
"eval_runtime": 2.7782,
|
69 |
+
"eval_samples_per_second": 11.878,
|
70 |
+
"eval_steps_per_second": 1.08,
|
71 |
+
"step": 35
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 8.0,
|
75 |
+
"eval_accuracy": 0.9393939393939394,
|
76 |
+
"eval_loss": 0.43865931034088135,
|
77 |
+
"eval_runtime": 2.8349,
|
78 |
+
"eval_samples_per_second": 11.641,
|
79 |
+
"eval_steps_per_second": 1.058,
|
80 |
+
"step": 40
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 9.0,
|
84 |
+
"eval_accuracy": 0.9393939393939394,
|
85 |
+
"eval_loss": 0.4294145405292511,
|
86 |
+
"eval_runtime": 3.1828,
|
87 |
+
"eval_samples_per_second": 10.368,
|
88 |
+
"eval_steps_per_second": 0.943,
|
89 |
+
"step": 45
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 10.0,
|
93 |
+
"eval_accuracy": 0.9393939393939394,
|
94 |
+
"eval_loss": 0.4252347946166992,
|
95 |
+
"eval_runtime": 4.2614,
|
96 |
+
"eval_samples_per_second": 7.744,
|
97 |
+
"eval_steps_per_second": 0.704,
|
98 |
+
"step": 50
|
99 |
+
}
|
100 |
+
],
|
101 |
+
"max_steps": 50,
|
102 |
+
"num_train_epochs": 10,
|
103 |
+
"total_flos": 10996087715388.0,
|
104 |
+
"trial_name": null,
|
105 |
+
"trial_params": null
|
106 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22bad76bbfebbe226690d83db7e46d82fff50cca79c80218aa7f97c2c66946a3
|
3 |
+
size 3643
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|