polejowska commited on
Commit
103142b
1 Parent(s): 120a995

End of training

Browse files
Files changed (1) hide show
  1. trainer_state.json +165 -0
trainer_state.json ADDED
@@ -0,0 +1,165 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 4.372256755828857,
3
+ "best_model_checkpoint": "deta-cd45rb-4ah-4l\\checkpoint-46060",
4
+ "epoch": 10.0,
5
+ "global_step": 46060,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 9.00065132435953e-07,
13
+ "loss": 4.8838,
14
+ "step": 4606
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 5.58176851272583,
19
+ "eval_runtime": 290.9092,
20
+ "eval_samples_per_second": 6.122,
21
+ "eval_steps_per_second": 0.767,
22
+ "step": 4606
23
+ },
24
+ {
25
+ "epoch": 2.0,
26
+ "learning_rate": 8.001302648719061e-07,
27
+ "loss": 4.3326,
28
+ "step": 9212
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "eval_loss": 5.532724857330322,
33
+ "eval_runtime": 289.6139,
34
+ "eval_samples_per_second": 6.15,
35
+ "eval_steps_per_second": 0.77,
36
+ "step": 9212
37
+ },
38
+ {
39
+ "epoch": 3.0,
40
+ "learning_rate": 7.001519756838905e-07,
41
+ "loss": 4.3118,
42
+ "step": 13818
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "eval_loss": 5.353872776031494,
47
+ "eval_runtime": 289.091,
48
+ "eval_samples_per_second": 6.161,
49
+ "eval_steps_per_second": 0.771,
50
+ "step": 13818
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "learning_rate": 6.001953973078593e-07,
55
+ "loss": 4.1978,
56
+ "step": 18424
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "eval_loss": 5.155240058898926,
61
+ "eval_runtime": 288.8689,
62
+ "eval_samples_per_second": 6.165,
63
+ "eval_steps_per_second": 0.772,
64
+ "step": 18424
65
+ },
66
+ {
67
+ "epoch": 5.0,
68
+ "learning_rate": 5.002605297438124e-07,
69
+ "loss": 4.0235,
70
+ "step": 23030
71
+ },
72
+ {
73
+ "epoch": 5.0,
74
+ "eval_loss": 4.9679036140441895,
75
+ "eval_runtime": 288.4979,
76
+ "eval_samples_per_second": 6.173,
77
+ "eval_steps_per_second": 0.773,
78
+ "step": 23030
79
+ },
80
+ {
81
+ "epoch": 6.0,
82
+ "learning_rate": 4.003039513677811e-07,
83
+ "loss": 3.9038,
84
+ "step": 27636
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "eval_loss": 4.782414436340332,
89
+ "eval_runtime": 286.2672,
90
+ "eval_samples_per_second": 6.221,
91
+ "eval_steps_per_second": 0.779,
92
+ "step": 27636
93
+ },
94
+ {
95
+ "epoch": 7.0,
96
+ "learning_rate": 3.003256621797655e-07,
97
+ "loss": 3.8628,
98
+ "step": 32242
99
+ },
100
+ {
101
+ "epoch": 7.0,
102
+ "eval_loss": 4.591905117034912,
103
+ "eval_runtime": 286.8168,
104
+ "eval_samples_per_second": 6.21,
105
+ "eval_steps_per_second": 0.777,
106
+ "step": 32242
107
+ },
108
+ {
109
+ "epoch": 8.0,
110
+ "learning_rate": 2.0036908380373423e-07,
111
+ "loss": 3.7967,
112
+ "step": 36848
113
+ },
114
+ {
115
+ "epoch": 8.0,
116
+ "eval_loss": 4.441461563110352,
117
+ "eval_runtime": 286.3236,
118
+ "eval_samples_per_second": 6.22,
119
+ "eval_steps_per_second": 0.779,
120
+ "step": 36848
121
+ },
122
+ {
123
+ "epoch": 9.0,
124
+ "learning_rate": 1.0041250542770299e-07,
125
+ "loss": 3.7638,
126
+ "step": 41454
127
+ },
128
+ {
129
+ "epoch": 9.0,
130
+ "eval_loss": 4.400564670562744,
131
+ "eval_runtime": 286.0319,
132
+ "eval_samples_per_second": 6.227,
133
+ "eval_steps_per_second": 0.78,
134
+ "step": 41454
135
+ },
136
+ {
137
+ "epoch": 10.0,
138
+ "learning_rate": 4.5592705167173247e-10,
139
+ "loss": 3.7538,
140
+ "step": 46060
141
+ },
142
+ {
143
+ "epoch": 10.0,
144
+ "eval_loss": 4.372256755828857,
145
+ "eval_runtime": 285.8571,
146
+ "eval_samples_per_second": 6.23,
147
+ "eval_steps_per_second": 0.78,
148
+ "step": 46060
149
+ },
150
+ {
151
+ "epoch": 10.0,
152
+ "step": 46060,
153
+ "total_flos": 8.74966392383616e+19,
154
+ "train_loss": 4.083041820451585,
155
+ "train_runtime": 49819.081,
156
+ "train_samples_per_second": 3.698,
157
+ "train_steps_per_second": 0.925
158
+ }
159
+ ],
160
+ "max_steps": 46060,
161
+ "num_train_epochs": 10,
162
+ "total_flos": 8.74966392383616e+19,
163
+ "trial_name": null,
164
+ "trial_params": null
165
+ }