Hugging Face's logo

Chathuri-bhagya
/
text_to_sql_model

Safetensors
t5
Model card Files
xet
Community
Chathuri-bhagya commited on
Commit
bd54e9f
·
verified ·
1 Parent(s): e33fc18

Upload trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +183 -0
trainer_state.json ADDED
@@ -0,0 +1,183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 8.475200957036577e-06,
3
+ "best_model_checkpoint": "./t5_sql_model/checkpoint-1000",
4
+ "epoch": 10.0,
5
+ "eval_steps": 100,
6
+ "global_step": 1000,
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
+ "grad_norm": 0.19069062173366547,
14
+ "learning_rate": 4.5050000000000004e-05,
15
+ "loss": 0.0952,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_loss": 0.01930948905646801,
21
+ "eval_runtime": 4.2969,
22
+ "eval_samples_per_second": 46.545,
23
+ "eval_steps_per_second": 23.273,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "grad_norm": 0.11524572968482971,
29
+ "learning_rate": 4.0050000000000004e-05,
30
+ "loss": 0.0134,
31
+ "step": 200
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_loss": 0.00038512772880494595,
36
+ "eval_runtime": 4.2896,
37
+ "eval_samples_per_second": 46.624,
38
+ "eval_steps_per_second": 23.312,
39
+ "step": 200
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "grad_norm": 0.08386600762605667,
44
+ "learning_rate": 3.505e-05,
45
+ "loss": 0.0035,
46
+ "step": 300
47
+ },
48
+ {
49
+ "epoch": 3.0,
50
+ "eval_loss": 7.71833147155121e-05,
51
+ "eval_runtime": 4.2776,
52
+ "eval_samples_per_second": 46.755,
53
+ "eval_steps_per_second": 23.377,
54
+ "step": 300
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "grad_norm": 0.04387281462550163,
59
+ "learning_rate": 3.0050000000000002e-05,
60
+ "loss": 0.0018,
61
+ "step": 400
62
+ },
63
+ {
64
+ "epoch": 4.0,
65
+ "eval_loss": 3.606174868764356e-05,
66
+ "eval_runtime": 4.288,
67
+ "eval_samples_per_second": 46.642,
68
+ "eval_steps_per_second": 23.321,
69
+ "step": 400
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "grad_norm": 0.02179218828678131,
74
+ "learning_rate": 2.5050000000000002e-05,
75
+ "loss": 0.0011,
76
+ "step": 500
77
+ },
78
+ {
79
+ "epoch": 5.0,
80
+ "eval_loss": 1.9488097677822225e-05,
81
+ "eval_runtime": 4.2812,
82
+ "eval_samples_per_second": 46.715,
83
+ "eval_steps_per_second": 23.358,
84
+ "step": 500
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "grad_norm": 0.02126687951385975,
89
+ "learning_rate": 2.0050000000000003e-05,
90
+ "loss": 0.001,
91
+ "step": 600
92
+ },
93
+ {
94
+ "epoch": 6.0,
95
+ "eval_loss": 1.42730787047185e-05,
96
+ "eval_runtime": 4.3012,
97
+ "eval_samples_per_second": 46.498,
98
+ "eval_steps_per_second": 23.249,
99
+ "step": 600
100
+ },
101
+ {
102
+ "epoch": 7.0,
103
+ "grad_norm": 0.03087877482175827,
104
+ "learning_rate": 1.505e-05,
105
+ "loss": 0.0007,
106
+ "step": 700
107
+ },
108
+ {
109
+ "epoch": 7.0,
110
+ "eval_loss": 1.0926911272690631e-05,
111
+ "eval_runtime": 4.2954,
112
+ "eval_samples_per_second": 46.561,
113
+ "eval_steps_per_second": 23.281,
114
+ "step": 700
115
+ },
116
+ {
117
+ "epoch": 8.0,
118
+ "grad_norm": 0.015643499791622162,
119
+ "learning_rate": 1.005e-05,
120
+ "loss": 0.0006,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 8.0,
125
+ "eval_loss": 9.499091902398504e-06,
126
+ "eval_runtime": 4.2684,
127
+ "eval_samples_per_second": 46.857,
128
+ "eval_steps_per_second": 23.428,
129
+ "step": 800
130
+ },
131
+ {
132
+ "epoch": 9.0,
133
+ "grad_norm": 0.020900582894682884,
134
+ "learning_rate": 5.050000000000001e-06,
135
+ "loss": 0.0005,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 9.0,
140
+ "eval_loss": 8.78215996635845e-06,
141
+ "eval_runtime": 4.2696,
142
+ "eval_samples_per_second": 46.843,
143
+ "eval_steps_per_second": 23.422,
144
+ "step": 900
145
+ },
146
+ {
147
+ "epoch": 10.0,
148
+ "grad_norm": 0.00630880007520318,
149
+ "learning_rate": 5.0000000000000004e-08,
150
+ "loss": 0.0005,
151
+ "step": 1000
152
+ },
153
+ {
154
+ "epoch": 10.0,
155
+ "eval_loss": 8.475200957036577e-06,
156
+ "eval_runtime": 4.2698,
157
+ "eval_samples_per_second": 46.841,
158
+ "eval_steps_per_second": 23.42,
159
+ "step": 1000
160
+ }
161
+ ],
162
+ "logging_steps": 100,
163
+ "max_steps": 1000,
164
+ "num_input_tokens_seen": 0,
165
+ "num_train_epochs": 10,
166
+ "save_steps": 100,
167
+ "stateful_callbacks": {
168
+ "TrainerControl": {
169
+ "args": {
170
+ "should_epoch_stop": false,
171
+ "should_evaluate": false,
172
+ "should_log": false,
173
+ "should_save": true,
174
+ "should_training_stop": true
175
+ },
176
+ "attributes": {}
177
+ }
178
+ },
179
+ "total_flos": 1082734411776000.0,
180
+ "train_batch_size": 1,
181
+ "trial_name": null,
182
+ "trial_params": null
183
+ }