polejowska
commited on
Commit
•
5430b22
1
Parent(s):
c4e9ee8
End of training
Browse files- trainer_state.json +84 -14
trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 2.
|
3 |
-
"best_model_checkpoint": "cdetr-cd45rb-s/checkpoint-
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -78,18 +78,88 @@
|
|
78 |
"step": 1210
|
79 |
},
|
80 |
{
|
81 |
-
"epoch":
|
82 |
-
"
|
83 |
-
"
|
84 |
-
"
|
85 |
-
|
86 |
-
|
87 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
88 |
}
|
89 |
],
|
90 |
-
"max_steps":
|
91 |
-
"num_train_epochs":
|
92 |
-
"total_flos":
|
93 |
"trial_name": null,
|
94 |
"trial_params": null
|
95 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.0136280059814453,
|
3 |
+
"best_model_checkpoint": "cdetr-cd45rb-s/checkpoint-2420",
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 2420,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
78 |
"step": 1210
|
79 |
},
|
80 |
{
|
81 |
+
"epoch": 6.0,
|
82 |
+
"learning_rate": 4e-05,
|
83 |
+
"loss": 2.1588,
|
84 |
+
"step": 1452
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 6.0,
|
88 |
+
"eval_loss": 2.0859251022338867,
|
89 |
+
"eval_runtime": 17.1118,
|
90 |
+
"eval_samples_per_second": 5.844,
|
91 |
+
"eval_steps_per_second": 0.76,
|
92 |
+
"step": 1452
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 7.0,
|
96 |
+
"learning_rate": 3e-05,
|
97 |
+
"loss": 2.1731,
|
98 |
+
"step": 1694
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.0,
|
102 |
+
"eval_loss": 2.073065757751465,
|
103 |
+
"eval_runtime": 16.6383,
|
104 |
+
"eval_samples_per_second": 6.01,
|
105 |
+
"eval_steps_per_second": 0.781,
|
106 |
+
"step": 1694
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 8.0,
|
110 |
+
"learning_rate": 2e-05,
|
111 |
+
"loss": 2.1041,
|
112 |
+
"step": 1936
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 8.0,
|
116 |
+
"eval_loss": 2.1051650047302246,
|
117 |
+
"eval_runtime": 16.6295,
|
118 |
+
"eval_samples_per_second": 6.013,
|
119 |
+
"eval_steps_per_second": 0.782,
|
120 |
+
"step": 1936
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 9.0,
|
124 |
+
"learning_rate": 1e-05,
|
125 |
+
"loss": 2.0383,
|
126 |
+
"step": 2178
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 9.0,
|
130 |
+
"eval_loss": 2.037771463394165,
|
131 |
+
"eval_runtime": 17.1339,
|
132 |
+
"eval_samples_per_second": 5.836,
|
133 |
+
"eval_steps_per_second": 0.759,
|
134 |
+
"step": 2178
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 10.0,
|
138 |
+
"learning_rate": 0.0,
|
139 |
+
"loss": 1.967,
|
140 |
+
"step": 2420
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 10.0,
|
144 |
+
"eval_loss": 2.0136280059814453,
|
145 |
+
"eval_runtime": 16.8066,
|
146 |
+
"eval_samples_per_second": 5.95,
|
147 |
+
"eval_steps_per_second": 0.774,
|
148 |
+
"step": 2420
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 10.0,
|
152 |
+
"step": 2420,
|
153 |
+
"total_flos": 4.8214727269632e+18,
|
154 |
+
"train_loss": 1.0441367535551718,
|
155 |
+
"train_runtime": 1297.7653,
|
156 |
+
"train_samples_per_second": 7.444,
|
157 |
+
"train_steps_per_second": 1.865
|
158 |
}
|
159 |
],
|
160 |
+
"max_steps": 2420,
|
161 |
+
"num_train_epochs": 10,
|
162 |
+
"total_flos": 4.8214727269632e+18,
|
163 |
"trial_name": null,
|
164 |
"trial_params": null
|
165 |
}
|