Hugging Face's logo

Saddammm
/
T5_model_1

Transformers
t5
text2text-generation
Model card Files
xet
Community
Saddammm commited on
Commit
79fb73f
·
1 Parent(s): 61e90eb

Upload trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +184 -0
trainer_state.json ADDED
@@ -0,0 +1,184 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.345794392523365,
5
+ "global_step": 1000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.93,
12
+ "learning_rate": 0.0002719626168224299,
13
+ "loss": 2.3351,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 1.9539090394973755,
19
+ "eval_rouge1": 0.3928238565889721,
20
+ "eval_rouge2": 0.24457675199617848,
21
+ "eval_rougeL": 0.34443833165269067,
22
+ "eval_rougeLsum": 0.35377968284169653,
23
+ "eval_runtime": 113.4757,
24
+ "eval_samples_per_second": 2.503,
25
+ "eval_steps_per_second": 0.626,
26
+ "step": 107
27
+ },
28
+ {
29
+ "epoch": 1.87,
30
+ "learning_rate": 0.0002439252336448598,
31
+ "loss": 1.8616,
32
+ "step": 200
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_loss": 1.8454691171646118,
37
+ "eval_rouge1": 0.40135907614173977,
38
+ "eval_rouge2": 0.2537731004498688,
39
+ "eval_rougeL": 0.3517340305952086,
40
+ "eval_rougeLsum": 0.3599553733909089,
41
+ "eval_runtime": 90.5265,
42
+ "eval_samples_per_second": 3.137,
43
+ "eval_steps_per_second": 0.784,
44
+ "step": 214
45
+ },
46
+ {
47
+ "epoch": 2.8,
48
+ "learning_rate": 0.0002158878504672897,
49
+ "loss": 1.5474,
50
+ "step": 300
51
+ },
52
+ {
53
+ "epoch": 3.0,
54
+ "eval_loss": 1.7911098003387451,
55
+ "eval_rouge1": 0.40516907769034227,
56
+ "eval_rouge2": 0.2571882790410479,
57
+ "eval_rougeL": 0.3551430134650718,
58
+ "eval_rougeLsum": 0.3650237424768551,
59
+ "eval_runtime": 89.8747,
60
+ "eval_samples_per_second": 3.16,
61
+ "eval_steps_per_second": 0.79,
62
+ "step": 321
63
+ },
64
+ {
65
+ "epoch": 3.74,
66
+ "learning_rate": 0.0001878504672897196,
67
+ "loss": 1.3416,
68
+ "step": 400
69
+ },
70
+ {
71
+ "epoch": 4.0,
72
+ "eval_loss": 1.7877225875854492,
73
+ "eval_rouge1": 0.39727138204448276,
74
+ "eval_rouge2": 0.2553111741867333,
75
+ "eval_rougeL": 0.35344418510391534,
76
+ "eval_rougeLsum": 0.3624411592522736,
77
+ "eval_runtime": 91.2462,
78
+ "eval_samples_per_second": 3.112,
79
+ "eval_steps_per_second": 0.778,
80
+ "step": 428
81
+ },
82
+ {
83
+ "epoch": 4.67,
84
+ "learning_rate": 0.0001598130841121495,
85
+ "loss": 1.1667,
86
+ "step": 500
87
+ },
88
+ {
89
+ "epoch": 5.0,
90
+ "eval_loss": 1.8065179586410522,
91
+ "eval_rouge1": 0.40226039832787347,
92
+ "eval_rouge2": 0.25889093132847524,
93
+ "eval_rougeL": 0.3547361470543734,
94
+ "eval_rougeLsum": 0.3642271784388902,
95
+ "eval_runtime": 88.6588,
96
+ "eval_samples_per_second": 3.203,
97
+ "eval_steps_per_second": 0.801,
98
+ "step": 535
99
+ },
100
+ {
101
+ "epoch": 5.61,
102
+ "learning_rate": 0.0001317757009345794,
103
+ "loss": 1.0582,
104
+ "step": 600
105
+ },
106
+ {
107
+ "epoch": 6.0,
108
+ "eval_loss": 1.8586112260818481,
109
+ "eval_rouge1": 0.3957092352506892,
110
+ "eval_rouge2": 0.2538965597420449,
111
+ "eval_rougeL": 0.34916932912187554,
112
+ "eval_rougeLsum": 0.3576929636444268,
113
+ "eval_runtime": 95.986,
114
+ "eval_samples_per_second": 2.959,
115
+ "eval_steps_per_second": 0.74,
116
+ "step": 642
117
+ },
118
+ {
119
+ "epoch": 6.54,
120
+ "learning_rate": 0.00010373831775700933,
121
+ "loss": 0.9202,
122
+ "step": 700
123
+ },
124
+ {
125
+ "epoch": 7.0,
126
+ "eval_loss": 1.8837732076644897,
127
+ "eval_rouge1": 0.40251597070955947,
128
+ "eval_rouge2": 0.2583209858085714,
129
+ "eval_rougeL": 0.3540804774162999,
130
+ "eval_rougeLsum": 0.36370971781604133,
131
+ "eval_runtime": 94.4477,
132
+ "eval_samples_per_second": 3.007,
133
+ "eval_steps_per_second": 0.752,
134
+ "step": 749
135
+ },
136
+ {
137
+ "epoch": 7.48,
138
+ "learning_rate": 7.570093457943924e-05,
139
+ "loss": 0.8575,
140
+ "step": 800
141
+ },
142
+ {
143
+ "epoch": 8.0,
144
+ "eval_loss": 1.9066342115402222,
145
+ "eval_rouge1": 0.39449493230029453,
146
+ "eval_rouge2": 0.2549659416128175,
147
+ "eval_rougeL": 0.348120528239499,
148
+ "eval_rougeLsum": 0.3568722790464366,
149
+ "eval_runtime": 82.6343,
150
+ "eval_samples_per_second": 3.437,
151
+ "eval_steps_per_second": 0.859,
152
+ "step": 856
153
+ },
154
+ {
155
+ "epoch": 8.41,
156
+ "learning_rate": 4.766355140186915e-05,
157
+ "loss": 0.7691,
158
+ "step": 900
159
+ },
160
+ {
161
+ "epoch": 9.0,
162
+ "eval_loss": 1.970426321029663,
163
+ "eval_rouge1": 0.393735400589476,
164
+ "eval_rouge2": 0.25521942254430097,
165
+ "eval_rougeL": 0.34772527093463,
166
+ "eval_rougeLsum": 0.356885126635194,
167
+ "eval_runtime": 88.6133,
168
+ "eval_samples_per_second": 3.205,
169
+ "eval_steps_per_second": 0.801,
170
+ "step": 963
171
+ },
172
+ {
173
+ "epoch": 9.35,
174
+ "learning_rate": 1.9626168224299062e-05,
175
+ "loss": 0.7361,
176
+ "step": 1000
177
+ }
178
+ ],
179
+ "max_steps": 1070,
180
+ "num_train_epochs": 10,
181
+ "total_flos": 370753309016064.0,
182
+ "trial_name": null,
183
+ "trial_params": null
184
+ }