polejowska commited on
Commit
b36663a
·
1 Parent(s): 145d894

End of training

Browse files
Files changed (1) hide show
  1. trainer_state.json +84 -14
trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 1.6694599390029907,
3
- "best_model_checkpoint": "detr-r50-cd45rb-8ah-6l\\checkpoint-23030",
4
- "epoch": 5.0,
5
- "global_step": 23030,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -78,18 +78,88 @@
78
  "step": 23030
79
  },
80
  {
81
- "epoch": 5.0,
82
- "step": 23030,
83
- "total_flos": 4.401655508016e+19,
84
- "train_loss": 2.2335772548713635,
85
- "train_runtime": 14888.6441,
86
- "train_samples_per_second": 6.186,
87
- "train_steps_per_second": 1.547
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
  }
89
  ],
90
- "max_steps": 23030,
91
- "num_train_epochs": 5,
92
- "total_flos": 4.401655508016e+19,
93
  "trial_name": null,
94
  "trial_params": null
95
  }
 
1
  {
2
+ "best_metric": 1.631255865097046,
3
+ "best_model_checkpoint": "detr-r50-cd45rb-8ah-6l\\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,
 
78
  "step": 23030
79
  },
80
  {
81
+ "epoch": 6.0,
82
+ "learning_rate": 4.003907946157187e-06,
83
+ "loss": 2.1237,
84
+ "step": 27636
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "eval_loss": 1.6780959367752075,
89
+ "eval_runtime": 207.7036,
90
+ "eval_samples_per_second": 8.575,
91
+ "eval_steps_per_second": 1.074,
92
+ "step": 27636
93
+ },
94
+ {
95
+ "epoch": 7.0,
96
+ "learning_rate": 3.004342162396874e-06,
97
+ "loss": 2.1025,
98
+ "step": 32242
99
+ },
100
+ {
101
+ "epoch": 7.0,
102
+ "eval_loss": 1.6574461460113525,
103
+ "eval_runtime": 206.2072,
104
+ "eval_samples_per_second": 8.637,
105
+ "eval_steps_per_second": 1.081,
106
+ "step": 32242
107
+ },
108
+ {
109
+ "epoch": 8.0,
110
+ "learning_rate": 2.0043421623968738e-06,
111
+ "loss": 2.0796,
112
+ "step": 36848
113
+ },
114
+ {
115
+ "epoch": 8.0,
116
+ "eval_loss": 1.6417841911315918,
117
+ "eval_runtime": 206.3439,
118
+ "eval_samples_per_second": 8.631,
119
+ "eval_steps_per_second": 1.081,
120
+ "step": 36848
121
+ },
122
+ {
123
+ "epoch": 9.0,
124
+ "learning_rate": 1.0049934867564047e-06,
125
+ "loss": 2.0672,
126
+ "step": 41454
127
+ },
128
+ {
129
+ "epoch": 9.0,
130
+ "eval_loss": 1.6333234310150146,
131
+ "eval_runtime": 205.3701,
132
+ "eval_samples_per_second": 8.672,
133
+ "eval_steps_per_second": 1.086,
134
+ "step": 41454
135
+ },
136
+ {
137
+ "epoch": 10.0,
138
+ "learning_rate": 5.210594876248372e-09,
139
+ "loss": 2.0597,
140
+ "step": 46060
141
+ },
142
+ {
143
+ "epoch": 10.0,
144
+ "eval_loss": 1.631255865097046,
145
+ "eval_runtime": 206.8618,
146
+ "eval_samples_per_second": 8.61,
147
+ "eval_steps_per_second": 1.078,
148
+ "step": 46060
149
+ },
150
+ {
151
+ "epoch": 10.0,
152
+ "step": 46060,
153
+ "total_flos": 8.803311016032e+19,
154
+ "train_loss": 1.0432621427892965,
155
+ "train_runtime": 14963.7217,
156
+ "train_samples_per_second": 12.31,
157
+ "train_steps_per_second": 3.078
158
  }
159
  ],
160
+ "max_steps": 46060,
161
+ "num_train_epochs": 10,
162
+ "total_flos": 8.803311016032e+19,
163
  "trial_name": null,
164
  "trial_params": null
165
  }