Hugging Face's logo

wybxc
/
danmaku-spam

Text Classification
Transformers
TensorBoard
ONNX
Safetensors
Chinese
bert
Inference Endpoints
Model card Files Metrics Community
wybxc commited on
Commit
72e79ec
•
1 Parent(s): a6db6ca

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +105 -0
trainer_state.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.35069674253463745,
3
+ "best_model_checkpoint": "danmaku-spam/checkpoint-192",
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 256,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.7799607072691552,
14
+ "eval_loss": 0.4711815118789673,
15
+ "eval_runtime": 0.3379,
16
+ "eval_samples_per_second": 1506.525,
17
+ "eval_steps_per_second": 23.678,
18
+ "step": 32
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.8271119842829077,
23
+ "eval_loss": 0.3976481258869171,
24
+ "eval_runtime": 0.3122,
25
+ "eval_samples_per_second": 1630.28,
26
+ "eval_steps_per_second": 25.623,
27
+ "step": 64
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.8428290766208252,
32
+ "eval_loss": 0.3673166036605835,
33
+ "eval_runtime": 0.3056,
34
+ "eval_samples_per_second": 1665.848,
35
+ "eval_steps_per_second": 26.182,
36
+ "step": 96
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_accuracy": 0.8212180746561886,
41
+ "eval_loss": 0.389240026473999,
42
+ "eval_runtime": 0.3579,
43
+ "eval_samples_per_second": 1422.305,
44
+ "eval_steps_per_second": 22.354,
45
+ "step": 128
46
+ },
47
+ {
48
+ "epoch": 5.0,
49
+ "eval_accuracy": 0.8605108055009824,
50
+ "eval_loss": 0.3535878360271454,
51
+ "eval_runtime": 0.31,
52
+ "eval_samples_per_second": 1641.821,
53
+ "eval_steps_per_second": 25.805,
54
+ "step": 160
55
+ },
56
+ {
57
+ "epoch": 6.0,
58
+ "eval_accuracy": 0.8506876227897839,
59
+ "eval_loss": 0.35069674253463745,
60
+ "eval_runtime": 0.3173,
61
+ "eval_samples_per_second": 1604.32,
62
+ "eval_steps_per_second": 25.215,
63
+ "step": 192
64
+ },
65
+ {
66
+ "epoch": 7.0,
67
+ "eval_accuracy": 0.8506876227897839,
68
+ "eval_loss": 0.37072867155075073,
69
+ "eval_runtime": 0.3565,
70
+ "eval_samples_per_second": 1427.644,
71
+ "eval_steps_per_second": 22.438,
72
+ "step": 224
73
+ },
74
+ {
75
+ "epoch": 8.0,
76
+ "eval_accuracy": 0.8467583497053045,
77
+ "eval_loss": 0.37388625741004944,
78
+ "eval_runtime": 0.3195,
79
+ "eval_samples_per_second": 1593.016,
80
+ "eval_steps_per_second": 25.038,
81
+ "step": 256
82
+ }
83
+ ],
84
+ "logging_steps": 500,
85
+ "max_steps": 640,
86
+ "num_input_tokens_seen": 0,
87
+ "num_train_epochs": 20,
88
+ "save_steps": 500,
89
+ "stateful_callbacks": {
90
+ "TrainerControl": {
91
+ "args": {
92
+ "should_epoch_stop": false,
93
+ "should_evaluate": false,
94
+ "should_log": false,
95
+ "should_save": true,
96
+ "should_training_stop": false
97
+ },
98
+ "attributes": {}
99
+ }
100
+ },
101
+ "total_flos": 83359892998512.0,
102
+ "train_batch_size": 64,
103
+ "trial_name": null,
104
+ "trial_params": null
105
+ }