Hugging Face's logo

semiotic
/
T5-3B-SynQL-Spider-Train-Run-00

Text Generation
Transformers
PyTorch
English
t5
text2text-generation
code
text-generation-inference
Inference Endpoints
Model card Files Community
denverbaumgartner commited on
Commit
6bcc944
•
1 Parent(s): f4c3104

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +112 -0
trainer_state.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7021276595744681,
3
+ "best_model_checkpoint": "/train_synth_spider_sampled_all_01_run_00_train/checkpoint-336",
4
+ "epoch": 5.997668673231497,
5
+ "global_step": 336,
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": 3.5417,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "learning_rate": 0.0001,
19
+ "loss": 0.5468,
20
+ "step": 56
21
+ },
22
+ {
23
+ "epoch": 1.0,
24
+ "eval_exact_match": 0.281431334622824,
25
+ "eval_exec": 0.4951644100580271,
26
+ "eval_loss": 0.5159241557121277,
27
+ "eval_runtime": 1406.1616,
28
+ "eval_samples_per_second": 0.735,
29
+ "step": 56
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "learning_rate": 0.0001,
34
+ "loss": 0.1933,
35
+ "step": 112
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_exact_match": 0.3317214700193424,
40
+ "eval_exec": 0.6363636363636364,
41
+ "eval_loss": 0.518136203289032,
42
+ "eval_runtime": 2302.9263,
43
+ "eval_samples_per_second": 0.449,
44
+ "step": 112
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "learning_rate": 0.0001,
49
+ "loss": 0.1528,
50
+ "step": 168
51
+ },
52
+ {
53
+ "epoch": 3.0,
54
+ "eval_exact_match": 0.3181818181818182,
55
+ "eval_exec": 0.6344294003868471,
56
+ "eval_loss": 0.4836026132106781,
57
+ "eval_runtime": 1889.4185,
58
+ "eval_samples_per_second": 0.547,
59
+ "step": 168
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "learning_rate": 0.0001,
64
+ "loss": 0.1327,
65
+ "step": 224
66
+ },
67
+ {
68
+ "epoch": 4.0,
69
+ "eval_exact_match": 0.3607350096711799,
70
+ "eval_exec": 0.6847195357833655,
71
+ "eval_loss": 0.498320996761322,
72
+ "eval_runtime": 1664.6976,
73
+ "eval_samples_per_second": 0.621,
74
+ "step": 224
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "learning_rate": 0.0001,
79
+ "loss": 0.12,
80
+ "step": 280
81
+ },
82
+ {
83
+ "epoch": 5.0,
84
+ "eval_exact_match": 0.31431334622823986,
85
+ "eval_exec": 0.6731141199226306,
86
+ "eval_loss": 0.5015786290168762,
87
+ "eval_runtime": 2255.9177,
88
+ "eval_samples_per_second": 0.458,
89
+ "step": 280
90
+ },
91
+ {
92
+ "epoch": 6.0,
93
+ "learning_rate": 0.0001,
94
+ "loss": 0.1106,
95
+ "step": 336
96
+ },
97
+ {
98
+ "epoch": 6.0,
99
+ "eval_exact_match": 0.32495164410058025,
100
+ "eval_exec": 0.7021276595744681,
101
+ "eval_loss": 0.5117971301078796,
102
+ "eval_runtime": 1729.5329,
103
+ "eval_samples_per_second": 0.598,
104
+ "step": 336
105
+ }
106
+ ],
107
+ "max_steps": 2800,
108
+ "num_train_epochs": 50,
109
+ "total_flos": 3.9251496697240044e+18,
110
+ "trial_name": null,
111
+ "trial_params": null
112
+ }