🍻 cheers
Browse files- all_results.json +11 -11
- eval_results.json +6 -6
- runs/Jul18_23-44-46_052b66b80984/events.out.tfevents.1689724682.052b66b80984.308.1 +3 -0
- train_results.json +6 -6
- trainer_state.json +233 -71
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime": 2.
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second":
|
8 |
-
"total_flos":
|
9 |
-
"train_loss": 0.
|
10 |
-
"train_runtime":
|
11 |
-
"train_samples_per_second":
|
12 |
-
"train_steps_per_second": 0.
|
13 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 8.0,
|
3 |
+
"eval_accuracy": 0.6666666666666666,
|
4 |
+
"eval_loss": 0.7650650143623352,
|
5 |
+
"eval_runtime": 2.7569,
|
6 |
+
"eval_samples_per_second": 18.499,
|
7 |
+
"eval_steps_per_second": 2.539,
|
8 |
+
"total_flos": 5.945238728048148e+17,
|
9 |
+
"train_loss": 0.42277156077325345,
|
10 |
+
"train_runtime": 658.9186,
|
11 |
+
"train_samples_per_second": 11.643,
|
12 |
+
"train_steps_per_second": 0.728
|
13 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime": 2.
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 8.0,
|
3 |
+
"eval_accuracy": 0.6666666666666666,
|
4 |
+
"eval_loss": 0.7650650143623352,
|
5 |
+
"eval_runtime": 2.7569,
|
6 |
+
"eval_samples_per_second": 18.499,
|
7 |
+
"eval_steps_per_second": 2.539
|
8 |
}
|
runs/Jul18_23-44-46_052b66b80984/events.out.tfevents.1689724682.052b66b80984.308.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd87bd4a68f87e5f806f3a9bb4eecd67b2e6992b245e8c8d136418be84d14f74
|
3 |
+
size 411
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"total_flos":
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 8.0,
|
3 |
+
"total_flos": 5.945238728048148e+17,
|
4 |
+
"train_loss": 0.42277156077325345,
|
5 |
+
"train_runtime": 658.9186,
|
6 |
+
"train_samples_per_second": 11.643,
|
7 |
+
"train_steps_per_second": 0.728
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,187 +1,349 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "./vit-base-renovation/checkpoint-200",
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
"epoch": 0.17,
|
12 |
-
"learning_rate": 0.
|
13 |
-
"loss": 1.
|
14 |
"step": 10
|
15 |
},
|
16 |
{
|
17 |
"epoch": 0.33,
|
18 |
-
"learning_rate": 0.
|
19 |
-
"loss": 0.
|
20 |
"step": 20
|
21 |
},
|
22 |
{
|
23 |
"epoch": 0.5,
|
24 |
-
"learning_rate": 0.
|
25 |
-
"loss": 0.
|
26 |
"step": 30
|
27 |
},
|
28 |
{
|
29 |
"epoch": 0.67,
|
30 |
-
"learning_rate": 0.
|
31 |
-
"loss": 1.
|
32 |
"step": 40
|
33 |
},
|
34 |
{
|
35 |
"epoch": 0.83,
|
36 |
-
"learning_rate": 0.
|
37 |
-
"loss":
|
38 |
"step": 50
|
39 |
},
|
40 |
{
|
41 |
"epoch": 1.0,
|
42 |
-
"learning_rate": 0.
|
43 |
-
"loss": 1.
|
44 |
"step": 60
|
45 |
},
|
46 |
{
|
47 |
"epoch": 1.17,
|
48 |
-
"learning_rate": 0.
|
49 |
-
"loss": 0.
|
50 |
"step": 70
|
51 |
},
|
52 |
{
|
53 |
"epoch": 1.33,
|
54 |
-
"learning_rate": 0.
|
55 |
-
"loss": 0.
|
56 |
"step": 80
|
57 |
},
|
58 |
{
|
59 |
"epoch": 1.5,
|
60 |
-
"learning_rate": 0.
|
61 |
-
"loss": 0.
|
62 |
"step": 90
|
63 |
},
|
64 |
{
|
65 |
"epoch": 1.67,
|
66 |
-
"learning_rate": 0.
|
67 |
-
"loss": 0.
|
68 |
"step": 100
|
69 |
},
|
70 |
{
|
71 |
"epoch": 1.67,
|
72 |
-
"eval_accuracy": 0.
|
73 |
-
"eval_loss": 0.
|
74 |
-
"eval_runtime": 2.
|
75 |
-
"eval_samples_per_second":
|
76 |
-
"eval_steps_per_second":
|
77 |
"step": 100
|
78 |
},
|
79 |
{
|
80 |
"epoch": 1.83,
|
81 |
-
"learning_rate": 0.
|
82 |
-
"loss":
|
83 |
"step": 110
|
84 |
},
|
85 |
{
|
86 |
"epoch": 2.0,
|
87 |
-
"learning_rate": 0.
|
88 |
-
"loss": 0.
|
89 |
"step": 120
|
90 |
},
|
91 |
{
|
92 |
"epoch": 2.17,
|
93 |
-
"learning_rate":
|
94 |
-
"loss": 0.
|
95 |
"step": 130
|
96 |
},
|
97 |
{
|
98 |
"epoch": 2.33,
|
99 |
-
"learning_rate":
|
100 |
-
"loss": 0.
|
101 |
"step": 140
|
102 |
},
|
103 |
{
|
104 |
"epoch": 2.5,
|
105 |
-
"learning_rate":
|
106 |
-
"loss": 0.
|
107 |
"step": 150
|
108 |
},
|
109 |
{
|
110 |
"epoch": 2.67,
|
111 |
-
"learning_rate":
|
112 |
-
"loss": 0.
|
113 |
"step": 160
|
114 |
},
|
115 |
{
|
116 |
"epoch": 2.83,
|
117 |
-
"learning_rate":
|
118 |
-
"loss": 0.
|
119 |
"step": 170
|
120 |
},
|
121 |
{
|
122 |
"epoch": 3.0,
|
123 |
-
"learning_rate":
|
124 |
-
"loss": 0.
|
125 |
"step": 180
|
126 |
},
|
127 |
{
|
128 |
"epoch": 3.17,
|
129 |
-
"learning_rate":
|
130 |
-
"loss": 0.
|
131 |
"step": 190
|
132 |
},
|
133 |
{
|
134 |
"epoch": 3.33,
|
135 |
-
"learning_rate":
|
136 |
-
"loss": 0.
|
137 |
"step": 200
|
138 |
},
|
139 |
{
|
140 |
"epoch": 3.33,
|
141 |
-
"eval_accuracy": 0.
|
142 |
-
"eval_loss": 0.
|
143 |
-
"eval_runtime":
|
144 |
-
"eval_samples_per_second": 21.
|
145 |
-
"eval_steps_per_second": 2.
|
146 |
"step": 200
|
147 |
},
|
148 |
{
|
149 |
"epoch": 3.5,
|
150 |
-
"learning_rate":
|
151 |
-
"loss": 0.
|
152 |
"step": 210
|
153 |
},
|
154 |
{
|
155 |
"epoch": 3.67,
|
156 |
-
"learning_rate":
|
157 |
-
"loss": 0.
|
158 |
"step": 220
|
159 |
},
|
160 |
{
|
161 |
"epoch": 3.83,
|
162 |
-
"learning_rate":
|
163 |
-
"loss": 0.
|
164 |
"step": 230
|
165 |
},
|
166 |
{
|
167 |
"epoch": 4.0,
|
168 |
-
"learning_rate":
|
169 |
-
"loss": 0.
|
170 |
"step": 240
|
171 |
},
|
172 |
{
|
173 |
-
"epoch": 4.
|
174 |
-
"
|
175 |
-
"
|
176 |
-
"
|
177 |
-
|
178 |
-
|
179 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
180 |
}
|
181 |
],
|
182 |
-
"max_steps":
|
183 |
-
"num_train_epochs":
|
184 |
-
"total_flos":
|
185 |
"trial_name": null,
|
186 |
"trial_params": null
|
187 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7650650143623352,
|
3 |
"best_model_checkpoint": "./vit-base-renovation/checkpoint-200",
|
4 |
+
"epoch": 8.0,
|
5 |
+
"global_step": 480,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
"epoch": 0.17,
|
12 |
+
"learning_rate": 0.00019583333333333334,
|
13 |
+
"loss": 1.0402,
|
14 |
"step": 10
|
15 |
},
|
16 |
{
|
17 |
"epoch": 0.33,
|
18 |
+
"learning_rate": 0.00019166666666666667,
|
19 |
+
"loss": 0.9827,
|
20 |
"step": 20
|
21 |
},
|
22 |
{
|
23 |
"epoch": 0.5,
|
24 |
+
"learning_rate": 0.0001875,
|
25 |
+
"loss": 0.9183,
|
26 |
"step": 30
|
27 |
},
|
28 |
{
|
29 |
"epoch": 0.67,
|
30 |
+
"learning_rate": 0.00018333333333333334,
|
31 |
+
"loss": 1.0276,
|
32 |
"step": 40
|
33 |
},
|
34 |
{
|
35 |
"epoch": 0.83,
|
36 |
+
"learning_rate": 0.0001791666666666667,
|
37 |
+
"loss": 1.0298,
|
38 |
"step": 50
|
39 |
},
|
40 |
{
|
41 |
"epoch": 1.0,
|
42 |
+
"learning_rate": 0.000175,
|
43 |
+
"loss": 1.0427,
|
44 |
"step": 60
|
45 |
},
|
46 |
{
|
47 |
"epoch": 1.17,
|
48 |
+
"learning_rate": 0.00017083333333333333,
|
49 |
+
"loss": 0.9752,
|
50 |
"step": 70
|
51 |
},
|
52 |
{
|
53 |
"epoch": 1.33,
|
54 |
+
"learning_rate": 0.0001666666666666667,
|
55 |
+
"loss": 0.9352,
|
56 |
"step": 80
|
57 |
},
|
58 |
{
|
59 |
"epoch": 1.5,
|
60 |
+
"learning_rate": 0.00016250000000000002,
|
61 |
+
"loss": 0.9524,
|
62 |
"step": 90
|
63 |
},
|
64 |
{
|
65 |
"epoch": 1.67,
|
66 |
+
"learning_rate": 0.00015833333333333332,
|
67 |
+
"loss": 0.9092,
|
68 |
"step": 100
|
69 |
},
|
70 |
{
|
71 |
"epoch": 1.67,
|
72 |
+
"eval_accuracy": 0.5686274509803921,
|
73 |
+
"eval_loss": 0.828122615814209,
|
74 |
+
"eval_runtime": 2.4102,
|
75 |
+
"eval_samples_per_second": 21.16,
|
76 |
+
"eval_steps_per_second": 2.904,
|
77 |
"step": 100
|
78 |
},
|
79 |
{
|
80 |
"epoch": 1.83,
|
81 |
+
"learning_rate": 0.00015416666666666668,
|
82 |
+
"loss": 1.0012,
|
83 |
"step": 110
|
84 |
},
|
85 |
{
|
86 |
"epoch": 2.0,
|
87 |
+
"learning_rate": 0.00015000000000000001,
|
88 |
+
"loss": 0.8633,
|
89 |
"step": 120
|
90 |
},
|
91 |
{
|
92 |
"epoch": 2.17,
|
93 |
+
"learning_rate": 0.00014625,
|
94 |
+
"loss": 0.8039,
|
95 |
"step": 130
|
96 |
},
|
97 |
{
|
98 |
"epoch": 2.33,
|
99 |
+
"learning_rate": 0.00014208333333333334,
|
100 |
+
"loss": 0.6671,
|
101 |
"step": 140
|
102 |
},
|
103 |
{
|
104 |
"epoch": 2.5,
|
105 |
+
"learning_rate": 0.00013791666666666667,
|
106 |
+
"loss": 0.7614,
|
107 |
"step": 150
|
108 |
},
|
109 |
{
|
110 |
"epoch": 2.67,
|
111 |
+
"learning_rate": 0.00013375,
|
112 |
+
"loss": 0.7356,
|
113 |
"step": 160
|
114 |
},
|
115 |
{
|
116 |
"epoch": 2.83,
|
117 |
+
"learning_rate": 0.00012958333333333336,
|
118 |
+
"loss": 0.7792,
|
119 |
"step": 170
|
120 |
},
|
121 |
{
|
122 |
"epoch": 3.0,
|
123 |
+
"learning_rate": 0.00012541666666666666,
|
124 |
+
"loss": 0.7458,
|
125 |
"step": 180
|
126 |
},
|
127 |
{
|
128 |
"epoch": 3.17,
|
129 |
+
"learning_rate": 0.00012124999999999999,
|
130 |
+
"loss": 0.5359,
|
131 |
"step": 190
|
132 |
},
|
133 |
{
|
134 |
"epoch": 3.33,
|
135 |
+
"learning_rate": 0.00011708333333333335,
|
136 |
+
"loss": 0.3809,
|
137 |
"step": 200
|
138 |
},
|
139 |
{
|
140 |
"epoch": 3.33,
|
141 |
+
"eval_accuracy": 0.6666666666666666,
|
142 |
+
"eval_loss": 0.7650650143623352,
|
143 |
+
"eval_runtime": 2.3488,
|
144 |
+
"eval_samples_per_second": 21.713,
|
145 |
+
"eval_steps_per_second": 2.98,
|
146 |
"step": 200
|
147 |
},
|
148 |
{
|
149 |
"epoch": 3.5,
|
150 |
+
"learning_rate": 0.00011291666666666667,
|
151 |
+
"loss": 0.3832,
|
152 |
"step": 210
|
153 |
},
|
154 |
{
|
155 |
"epoch": 3.67,
|
156 |
+
"learning_rate": 0.00010875,
|
157 |
+
"loss": 0.4645,
|
158 |
"step": 220
|
159 |
},
|
160 |
{
|
161 |
"epoch": 3.83,
|
162 |
+
"learning_rate": 0.00010458333333333335,
|
163 |
+
"loss": 0.4131,
|
164 |
"step": 230
|
165 |
},
|
166 |
{
|
167 |
"epoch": 4.0,
|
168 |
+
"learning_rate": 0.00010041666666666666,
|
169 |
+
"loss": 0.5098,
|
170 |
"step": 240
|
171 |
},
|
172 |
{
|
173 |
+
"epoch": 4.17,
|
174 |
+
"learning_rate": 9.625000000000001e-05,
|
175 |
+
"loss": 0.2046,
|
176 |
+
"step": 250
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 4.33,
|
180 |
+
"learning_rate": 9.208333333333333e-05,
|
181 |
+
"loss": 0.1603,
|
182 |
+
"step": 260
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 4.5,
|
186 |
+
"learning_rate": 8.791666666666667e-05,
|
187 |
+
"loss": 0.1362,
|
188 |
+
"step": 270
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 4.67,
|
192 |
+
"learning_rate": 8.375e-05,
|
193 |
+
"loss": 0.1255,
|
194 |
+
"step": 280
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 4.83,
|
198 |
+
"learning_rate": 7.958333333333333e-05,
|
199 |
+
"loss": 0.1471,
|
200 |
+
"step": 290
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 5.0,
|
204 |
+
"learning_rate": 7.541666666666667e-05,
|
205 |
+
"loss": 0.1873,
|
206 |
+
"step": 300
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 5.0,
|
210 |
+
"eval_accuracy": 0.6666666666666666,
|
211 |
+
"eval_loss": 1.0181704759597778,
|
212 |
+
"eval_runtime": 2.4305,
|
213 |
+
"eval_samples_per_second": 20.983,
|
214 |
+
"eval_steps_per_second": 2.88,
|
215 |
+
"step": 300
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 5.17,
|
219 |
+
"learning_rate": 7.125000000000001e-05,
|
220 |
+
"loss": 0.0605,
|
221 |
+
"step": 310
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 5.33,
|
225 |
+
"learning_rate": 6.708333333333333e-05,
|
226 |
+
"loss": 0.0432,
|
227 |
+
"step": 320
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 5.5,
|
231 |
+
"learning_rate": 6.291666666666667e-05,
|
232 |
+
"loss": 0.0339,
|
233 |
+
"step": 330
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 5.67,
|
237 |
+
"learning_rate": 5.8750000000000005e-05,
|
238 |
+
"loss": 0.0386,
|
239 |
+
"step": 340
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 5.83,
|
243 |
+
"learning_rate": 5.458333333333333e-05,
|
244 |
+
"loss": 0.0371,
|
245 |
+
"step": 350
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 6.0,
|
249 |
+
"learning_rate": 5.041666666666667e-05,
|
250 |
+
"loss": 0.0353,
|
251 |
+
"step": 360
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 6.17,
|
255 |
+
"learning_rate": 4.6250000000000006e-05,
|
256 |
+
"loss": 0.0223,
|
257 |
+
"step": 370
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 6.33,
|
261 |
+
"learning_rate": 4.208333333333334e-05,
|
262 |
+
"loss": 0.0215,
|
263 |
+
"step": 380
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 6.5,
|
267 |
+
"learning_rate": 3.791666666666667e-05,
|
268 |
+
"loss": 0.0214,
|
269 |
+
"step": 390
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 6.67,
|
273 |
+
"learning_rate": 3.375000000000001e-05,
|
274 |
+
"loss": 0.019,
|
275 |
+
"step": 400
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 6.67,
|
279 |
+
"eval_accuracy": 0.6470588235294118,
|
280 |
+
"eval_loss": 1.2346100807189941,
|
281 |
+
"eval_runtime": 2.3302,
|
282 |
+
"eval_samples_per_second": 21.886,
|
283 |
+
"eval_steps_per_second": 3.004,
|
284 |
+
"step": 400
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 6.83,
|
288 |
+
"learning_rate": 2.9583333333333335e-05,
|
289 |
+
"loss": 0.0191,
|
290 |
+
"step": 410
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 7.0,
|
294 |
+
"learning_rate": 2.5416666666666667e-05,
|
295 |
+
"loss": 0.0189,
|
296 |
+
"step": 420
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 7.17,
|
300 |
+
"learning_rate": 2.125e-05,
|
301 |
+
"loss": 0.0179,
|
302 |
+
"step": 430
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 7.33,
|
306 |
+
"learning_rate": 1.7083333333333333e-05,
|
307 |
+
"loss": 0.0174,
|
308 |
+
"step": 440
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 7.5,
|
312 |
+
"learning_rate": 1.2916666666666668e-05,
|
313 |
+
"loss": 0.0173,
|
314 |
+
"step": 450
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 7.67,
|
318 |
+
"learning_rate": 8.75e-06,
|
319 |
+
"loss": 0.017,
|
320 |
+
"step": 460
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 7.83,
|
324 |
+
"learning_rate": 4.583333333333333e-06,
|
325 |
+
"loss": 0.0168,
|
326 |
+
"step": 470
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 8.0,
|
330 |
+
"learning_rate": 4.1666666666666667e-07,
|
331 |
+
"loss": 0.0168,
|
332 |
+
"step": 480
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 8.0,
|
336 |
+
"step": 480,
|
337 |
+
"total_flos": 5.945238728048148e+17,
|
338 |
+
"train_loss": 0.42277156077325345,
|
339 |
+
"train_runtime": 658.9186,
|
340 |
+
"train_samples_per_second": 11.643,
|
341 |
+
"train_steps_per_second": 0.728
|
342 |
}
|
343 |
],
|
344 |
+
"max_steps": 480,
|
345 |
+
"num_train_epochs": 8,
|
346 |
+
"total_flos": 5.945238728048148e+17,
|
347 |
"trial_name": null,
|
348 |
"trial_params": null
|
349 |
}
|