Hugging Face's logo

cwchang
/
summarization_model_billsum

Text2Text Generation
Transformers
TensorBoard
Safetensors
mt5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
cwchang commited on
Commit
a7dd059
•
1 Parent(s): 52e3c68

End of training

Browse files
Files changed (3) hide show
  1. all_results.json +8 -0
  2. train_results.json +8 -0
  3. trainer_state.json +197 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 2.0746695444824423,
4
+ "train_runtime": 9365.9127,
5
+ "train_samples": 18949,
6
+ "train_samples_per_second": 6.07,
7
+ "train_steps_per_second": 1.518
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 2.0746695444824423,
4
+ "train_runtime": 9365.9127,
5
+ "train_samples": 18949,
6
+ "train_samples_per_second": 6.07,
7
+ "train_steps_per_second": 1.518
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,197 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 14214,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.11,
13
+ "learning_rate": 4.8241170676797525e-05,
14
+ "loss": 5.1993,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.21,
19
+ "learning_rate": 4.648234135359505e-05,
20
+ "loss": 2.7321,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.32,
25
+ "learning_rate": 4.472351203039257e-05,
26
+ "loss": 2.4547,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.42,
31
+ "learning_rate": 4.2964682707190094e-05,
32
+ "loss": 2.3454,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.53,
37
+ "learning_rate": 4.120585338398762e-05,
38
+ "loss": 2.2375,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.63,
43
+ "learning_rate": 3.944702406078514e-05,
44
+ "loss": 2.1503,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.74,
49
+ "learning_rate": 3.768819473758266e-05,
50
+ "loss": 2.0775,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.84,
55
+ "learning_rate": 3.592936541438019e-05,
56
+ "loss": 2.0802,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.95,
61
+ "learning_rate": 3.4170536091177716e-05,
62
+ "loss": 2.0028,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 1.06,
67
+ "learning_rate": 3.241170676797524e-05,
68
+ "loss": 1.9862,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 1.16,
73
+ "learning_rate": 3.065287744477276e-05,
74
+ "loss": 1.95,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 1.27,
79
+ "learning_rate": 2.8894048121570285e-05,
80
+ "loss": 1.9279,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 1.37,
85
+ "learning_rate": 2.7135218798367808e-05,
86
+ "loss": 1.8896,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 1.48,
91
+ "learning_rate": 2.537638947516533e-05,
92
+ "loss": 1.8719,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 1.58,
97
+ "learning_rate": 2.3617560151962857e-05,
98
+ "loss": 1.8719,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 1.69,
103
+ "learning_rate": 2.185873082876038e-05,
104
+ "loss": 1.8422,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 1.79,
109
+ "learning_rate": 2.0099901505557903e-05,
110
+ "loss": 1.8601,
111
+ "step": 8500
112
+ },
113
+ {
114
+ "epoch": 1.9,
115
+ "learning_rate": 1.8341072182355426e-05,
116
+ "loss": 1.8463,
117
+ "step": 9000
118
+ },
119
+ {
120
+ "epoch": 2.01,
121
+ "learning_rate": 1.658224285915295e-05,
122
+ "loss": 1.8008,
123
+ "step": 9500
124
+ },
125
+ {
126
+ "epoch": 2.11,
127
+ "learning_rate": 1.4823413535950473e-05,
128
+ "loss": 1.812,
129
+ "step": 10000
130
+ },
131
+ {
132
+ "epoch": 2.22,
133
+ "learning_rate": 1.3064584212747996e-05,
134
+ "loss": 1.7943,
135
+ "step": 10500
136
+ },
137
+ {
138
+ "epoch": 2.32,
139
+ "learning_rate": 1.130575488954552e-05,
140
+ "loss": 1.7935,
141
+ "step": 11000
142
+ },
143
+ {
144
+ "epoch": 2.43,
145
+ "learning_rate": 9.546925566343042e-06,
146
+ "loss": 1.782,
147
+ "step": 11500
148
+ },
149
+ {
150
+ "epoch": 2.53,
151
+ "learning_rate": 7.788096243140567e-06,
152
+ "loss": 1.7745,
153
+ "step": 12000
154
+ },
155
+ {
156
+ "epoch": 2.64,
157
+ "learning_rate": 6.02926691993809e-06,
158
+ "loss": 1.7724,
159
+ "step": 12500
160
+ },
161
+ {
162
+ "epoch": 2.74,
163
+ "learning_rate": 4.270437596735613e-06,
164
+ "loss": 1.7846,
165
+ "step": 13000
166
+ },
167
+ {
168
+ "epoch": 2.85,
169
+ "learning_rate": 2.5116082735331366e-06,
170
+ "loss": 1.7903,
171
+ "step": 13500
172
+ },
173
+ {
174
+ "epoch": 2.95,
175
+ "learning_rate": 7.5277895033066e-07,
176
+ "loss": 1.763,
177
+ "step": 14000
178
+ },
179
+ {
180
+ "epoch": 3.0,
181
+ "step": 14214,
182
+ "total_flos": 6.011566735491072e+16,
183
+ "train_loss": 2.0746695444824423,
184
+ "train_runtime": 9365.9127,
185
+ "train_samples_per_second": 6.07,
186
+ "train_steps_per_second": 1.518
187
+ }
188
+ ],
189
+ "logging_steps": 500,
190
+ "max_steps": 14214,
191
+ "num_input_tokens_seen": 0,
192
+ "num_train_epochs": 3,
193
+ "save_steps": 500,
194
+ "total_flos": 6.011566735491072e+16,
195
+ "trial_name": null,
196
+ "trial_params": null
197
+ }