Hugging Face's logo

semiotic
/
T5-3B-SynQL-Spider-All-Run-01

Text Generation
Transformers
PyTorch
English
t5
text2text-generation
code
text-generation-inference
Inference Endpoints
Model card Files Community
denverbaumgartner commited on
Commit
87e90f3
•
1 Parent(s): 7eaadcb

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +127 -0
trainer_state.json ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6992263056092843,
3
+ "best_model_checkpoint": "/train_synth_spider_sampled_all_01_run_01_train/checkpoint-392",
4
+ "epoch": 6.997668673231497,
5
+ "global_step": 392,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 0.0001,
13
+ "loss": 3.5409,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "learning_rate": 0.0001,
19
+ "loss": 0.5492,
20
+ "step": 56
21
+ },
22
+ {
23
+ "epoch": 1.0,
24
+ "eval_exact_match": 0.28336557059961315,
25
+ "eval_exec": 0.3365570599613153,
26
+ "eval_loss": 0.5485422015190125,
27
+ "eval_runtime": 18949.0472,
28
+ "eval_samples_per_second": 0.055,
29
+ "step": 56
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "learning_rate": 0.0001,
34
+ "loss": 0.1931,
35
+ "step": 112
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_exact_match": 0.30947775628626695,
40
+ "eval_exec": 0.5851063829787234,
41
+ "eval_loss": 0.5121298432350159,
42
+ "eval_runtime": 1802.6407,
43
+ "eval_samples_per_second": 0.574,
44
+ "step": 112
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "learning_rate": 0.0001,
49
+ "loss": 0.1547,
50
+ "step": 168
51
+ },
52
+ {
53
+ "epoch": 3.0,
54
+ "eval_exact_match": 0.3404255319148936,
55
+ "eval_exec": 0.6634429400386848,
56
+ "eval_loss": 0.47683650255203247,
57
+ "eval_runtime": 1827.0837,
58
+ "eval_samples_per_second": 0.566,
59
+ "step": 168
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "learning_rate": 0.0001,
64
+ "loss": 0.1342,
65
+ "step": 224
66
+ },
67
+ {
68
+ "epoch": 4.0,
69
+ "eval_exact_match": 0.3529980657640232,
70
+ "eval_exec": 0.6798839458413927,
71
+ "eval_loss": 0.5107799768447876,
72
+ "eval_runtime": 1921.6432,
73
+ "eval_samples_per_second": 0.538,
74
+ "step": 224
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "learning_rate": 0.0001,
79
+ "loss": 0.1199,
80
+ "step": 280
81
+ },
82
+ {
83
+ "epoch": 5.0,
84
+ "eval_exact_match": 0.3152804642166344,
85
+ "eval_exec": 0.6692456479690522,
86
+ "eval_loss": 0.5156922936439514,
87
+ "eval_runtime": 2316.9587,
88
+ "eval_samples_per_second": 0.446,
89
+ "step": 280
90
+ },
91
+ {
92
+ "epoch": 6.0,
93
+ "learning_rate": 0.0001,
94
+ "loss": 0.1102,
95
+ "step": 336
96
+ },
97
+ {
98
+ "epoch": 6.0,
99
+ "eval_exact_match": 0.30754352030947774,
100
+ "eval_exec": 0.6789168278529981,
101
+ "eval_loss": 0.5207614898681641,
102
+ "eval_runtime": 1852.842,
103
+ "eval_samples_per_second": 0.558,
104
+ "step": 336
105
+ },
106
+ {
107
+ "epoch": 7.0,
108
+ "learning_rate": 0.0001,
109
+ "loss": 0.1024,
110
+ "step": 392
111
+ },
112
+ {
113
+ "epoch": 7.0,
114
+ "eval_exact_match": 0.3355899419729207,
115
+ "eval_exec": 0.6992263056092843,
116
+ "eval_loss": 0.502002477645874,
117
+ "eval_runtime": 1897.7756,
118
+ "eval_samples_per_second": 0.545,
119
+ "step": 392
120
+ }
121
+ ],
122
+ "max_steps": 2800,
123
+ "num_train_epochs": 50,
124
+ "total_flos": 4.5786426052283474e+18,
125
+ "trial_name": null,
126
+ "trial_params": null
127
+ }