Hugging Face's logo

luismond
/
tm2tb

Transformers
Safetensors
t5
text2text-generation
text-generation-inference
Model card Files
xet
 Community
luismond commited on
Commit
a655628
·
1 Parent(s): 98264bf

Delete trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +0 -215
trainer_state.json DELETED
@@ -1,215 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 2.840909090909091,
5
- "eval_steps": 500,
6
- "global_step": 15000,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 0.09,
13
- "learning_rate": 0.000968560606060606,
14
- "loss": 1.2526,
15
- "step": 500
16
- },
17
- {
18
- "epoch": 0.19,
19
- "learning_rate": 0.0009369949494949496,
20
- "loss": 1.0002,
21
- "step": 1000
22
- },
23
- {
24
- "epoch": 0.28,
25
- "learning_rate": 0.000905429292929293,
26
- "loss": 0.948,
27
- "step": 1500
28
- },
29
- {
30
- "epoch": 0.38,
31
- "learning_rate": 0.0008738636363636364,
32
- "loss": 0.9093,
33
- "step": 2000
34
- },
35
- {
36
- "epoch": 0.47,
37
- "learning_rate": 0.0008422979797979798,
38
- "loss": 0.8866,
39
- "step": 2500
40
- },
41
- {
42
- "epoch": 0.57,
43
- "learning_rate": 0.0008107323232323233,
44
- "loss": 0.8698,
45
- "step": 3000
46
- },
47
- {
48
- "epoch": 0.66,
49
- "learning_rate": 0.0007791666666666667,
50
- "loss": 0.8519,
51
- "step": 3500
52
- },
53
- {
54
- "epoch": 0.76,
55
- "learning_rate": 0.0007476010101010101,
56
- "loss": 0.8349,
57
- "step": 4000
58
- },
59
- {
60
- "epoch": 0.85,
61
- "learning_rate": 0.0007160353535353535,
62
- "loss": 0.8212,
63
- "step": 4500
64
- },
65
- {
66
- "epoch": 0.95,
67
- "learning_rate": 0.000684469696969697,
68
- "loss": 0.8139,
69
- "step": 5000
70
- },
71
- {
72
- "epoch": 1.0,
73
- "eval_loss": 0.7459572553634644,
74
- "eval_runtime": 61.4124,
75
- "eval_samples_per_second": 458.507,
76
- "eval_steps_per_second": 28.659,
77
- "step": 5280
78
- },
79
- {
80
- "epoch": 1.04,
81
- "learning_rate": 0.0006529040404040404,
82
- "loss": 0.7987,
83
- "step": 5500
84
- },
85
- {
86
- "epoch": 1.14,
87
- "learning_rate": 0.0006213383838383839,
88
- "loss": 0.7816,
89
- "step": 6000
90
- },
91
- {
92
- "epoch": 1.23,
93
- "learning_rate": 0.0005897727272727272,
94
- "loss": 0.7777,
95
- "step": 6500
96
- },
97
- {
98
- "epoch": 1.33,
99
- "learning_rate": 0.0005582070707070706,
100
- "loss": 0.7748,
101
- "step": 7000
102
- },
103
- {
104
- "epoch": 1.42,
105
- "learning_rate": 0.0005267045454545455,
106
- "loss": 0.766,
107
- "step": 7500
108
- },
109
- {
110
- "epoch": 1.52,
111
- "learning_rate": 0.0004951388888888889,
112
- "loss": 0.7622,
113
- "step": 8000
114
- },
115
- {
116
- "epoch": 1.61,
117
- "learning_rate": 0.0004635732323232323,
118
- "loss": 0.7607,
119
- "step": 8500
120
- },
121
- {
122
- "epoch": 1.7,
123
- "learning_rate": 0.00043200757575757577,
124
- "loss": 0.754,
125
- "step": 9000
126
- },
127
- {
128
- "epoch": 1.8,
129
- "learning_rate": 0.00040050505050505056,
130
- "loss": 0.7475,
131
- "step": 9500
132
- },
133
- {
134
- "epoch": 1.89,
135
- "learning_rate": 0.00036893939393939395,
136
- "loss": 0.7465,
137
- "step": 10000
138
- },
139
- {
140
- "epoch": 1.99,
141
- "learning_rate": 0.0003373737373737374,
142
- "loss": 0.743,
143
- "step": 10500
144
- },
145
- {
146
- "epoch": 2.0,
147
- "eval_loss": 0.6981947422027588,
148
- "eval_runtime": 60.7826,
149
- "eval_samples_per_second": 463.257,
150
- "eval_steps_per_second": 28.956,
151
- "step": 10560
152
- },
153
- {
154
- "epoch": 2.08,
155
- "learning_rate": 0.0003058080808080808,
156
- "loss": 0.724,
157
- "step": 11000
158
- },
159
- {
160
- "epoch": 2.18,
161
- "learning_rate": 0.00027424242424242424,
162
- "loss": 0.7173,
163
- "step": 11500
164
- },
165
- {
166
- "epoch": 2.27,
167
- "learning_rate": 0.0002426767676767677,
168
- "loss": 0.7174,
169
- "step": 12000
170
- },
171
- {
172
- "epoch": 2.37,
173
- "learning_rate": 0.0002111111111111111,
174
- "loss": 0.7177,
175
- "step": 12500
176
- },
177
- {
178
- "epoch": 2.46,
179
- "learning_rate": 0.00017954545454545453,
180
- "loss": 0.7146,
181
- "step": 13000
182
- },
183
- {
184
- "epoch": 2.56,
185
- "learning_rate": 0.0001480429292929293,
186
- "loss": 0.7116,
187
- "step": 13500
188
- },
189
- {
190
- "epoch": 2.65,
191
- "learning_rate": 0.00011647727272727272,
192
- "loss": 0.7044,
193
- "step": 14000
194
- },
195
- {
196
- "epoch": 2.75,
197
- "learning_rate": 8.491161616161616e-05,
198
- "loss": 0.7072,
199
- "step": 14500
200
- },
201
- {
202
- "epoch": 2.84,
203
- "learning_rate": 5.3345959595959597e-05,
204
- "loss": 0.7067,
205
- "step": 15000
206
- }
207
- ],
208
- "logging_steps": 500,
209
- "max_steps": 15840,
210
- "num_train_epochs": 3,
211
- "save_steps": 1000,
212
- "total_flos": 2.090004984181555e+16,
213
- "trial_name": null,
214
- "trial_params": null
215
- }