JEdward7777
commited on
Commit
•
e33d59c
1
Parent(s):
70a3e24
End of training
Browse files- all_results.json +11 -6
- eval_results.json +8 -0
- runs/Aug30_11-16-42_7497dc661104/events.out.tfevents.1661859013.7497dc661104.71.2 +3 -0
- train_results.json +6 -6
- trainer_state.json +346 -64
all_results.json
CHANGED
@@ -1,8 +1,13 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
|
|
|
|
|
|
|
|
|
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 40.0,
|
3 |
+
"eval_accuracy": 0.8571428571428571,
|
4 |
+
"eval_loss": 0.703612744808197,
|
5 |
+
"eval_runtime": 0.6018,
|
6 |
+
"eval_samples_per_second": 11.631,
|
7 |
+
"eval_steps_per_second": 1.662,
|
8 |
+
"total_flos": 6.164974248394752e+16,
|
9 |
+
"train_loss": 0.3415180742740631,
|
10 |
+
"train_runtime": 367.0026,
|
11 |
+
"train_samples_per_second": 6.757,
|
12 |
+
"train_steps_per_second": 0.109
|
13 |
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 40.0,
|
3 |
+
"eval_accuracy": 0.8571428571428571,
|
4 |
+
"eval_loss": 0.703612744808197,
|
5 |
+
"eval_runtime": 0.6018,
|
6 |
+
"eval_samples_per_second": 11.631,
|
7 |
+
"eval_steps_per_second": 1.662
|
8 |
+
}
|
runs/Aug30_11-16-42_7497dc661104/events.out.tfevents.1661859013.7497dc661104.71.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90fb26c741cce9302f79a4655e927e9be8ee7af38941eb96b24721abb4955556
|
3 |
+
size 357
|
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": 40.0,
|
3 |
+
"total_flos": 6.164974248394752e+16,
|
4 |
+
"train_loss": 0.3415180742740631,
|
5 |
+
"train_runtime": 367.0026,
|
6 |
+
"train_samples_per_second": 6.757,
|
7 |
+
"train_steps_per_second": 0.109
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,115 +1,397 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "
|
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": 1.0,
|
12 |
-
"eval_accuracy": 0.
|
13 |
-
"eval_loss": 1.
|
14 |
-
"eval_runtime": 0.
|
15 |
-
"eval_samples_per_second":
|
16 |
-
"eval_steps_per_second":
|
17 |
"step": 1
|
18 |
},
|
19 |
{
|
20 |
"epoch": 2.0,
|
21 |
-
"eval_accuracy": 0.
|
22 |
-
"eval_loss": 1.
|
23 |
-
"eval_runtime": 0.
|
24 |
-
"eval_samples_per_second":
|
25 |
-
"eval_steps_per_second":
|
26 |
"step": 2
|
27 |
},
|
28 |
{
|
29 |
"epoch": 3.0,
|
30 |
-
"eval_accuracy": 0.
|
31 |
-
"eval_loss": 1.
|
32 |
-
"eval_runtime": 0.
|
33 |
-
"eval_samples_per_second":
|
34 |
-
"eval_steps_per_second":
|
35 |
"step": 3
|
36 |
},
|
37 |
{
|
38 |
"epoch": 4.0,
|
39 |
-
"eval_accuracy": 0.
|
40 |
-
"eval_loss": 1.
|
41 |
-
"eval_runtime": 0.
|
42 |
-
"eval_samples_per_second":
|
43 |
-
"eval_steps_per_second":
|
44 |
"step": 4
|
45 |
},
|
46 |
{
|
47 |
"epoch": 5.0,
|
48 |
-
"eval_accuracy": 0.
|
49 |
-
"eval_loss": 1.
|
50 |
-
"eval_runtime": 0.
|
51 |
-
"eval_samples_per_second":
|
52 |
-
"eval_steps_per_second":
|
53 |
"step": 5
|
54 |
},
|
55 |
{
|
56 |
"epoch": 6.0,
|
57 |
-
"eval_accuracy": 0.
|
58 |
-
"eval_loss": 1.
|
59 |
-
"eval_runtime": 0.
|
60 |
-
"eval_samples_per_second":
|
61 |
-
"eval_steps_per_second":
|
62 |
"step": 6
|
63 |
},
|
64 |
{
|
65 |
"epoch": 7.0,
|
66 |
-
"eval_accuracy": 0.
|
67 |
-
"eval_loss": 1.
|
68 |
-
"eval_runtime": 0.
|
69 |
-
"eval_samples_per_second":
|
70 |
-
"eval_steps_per_second":
|
71 |
"step": 7
|
72 |
},
|
73 |
{
|
74 |
"epoch": 8.0,
|
75 |
-
"eval_accuracy": 0.
|
76 |
-
"eval_loss": 1.
|
77 |
-
"eval_runtime": 0.
|
78 |
-
"eval_samples_per_second":
|
79 |
-
"eval_steps_per_second":
|
80 |
"step": 8
|
81 |
},
|
82 |
{
|
83 |
"epoch": 9.0,
|
84 |
-
"eval_accuracy": 0.
|
85 |
-
"eval_loss": 1.
|
86 |
-
"eval_runtime": 0.
|
87 |
-
"eval_samples_per_second":
|
88 |
-
"eval_steps_per_second": 1.
|
89 |
"step": 9
|
90 |
},
|
91 |
{
|
92 |
"epoch": 10.0,
|
93 |
-
"eval_accuracy": 0.
|
94 |
-
"eval_loss": 1.
|
95 |
-
"eval_runtime": 0.
|
96 |
-
"eval_samples_per_second":
|
97 |
-
"eval_steps_per_second":
|
98 |
"step": 10
|
99 |
},
|
100 |
{
|
101 |
-
"epoch":
|
102 |
-
"
|
103 |
-
"
|
104 |
-
"
|
105 |
-
"
|
106 |
-
"
|
107 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
108 |
}
|
109 |
],
|
110 |
-
"max_steps":
|
111 |
-
"num_train_epochs":
|
112 |
-
"total_flos":
|
113 |
"trial_name": null,
|
114 |
"trial_params": null
|
115 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.8571428571428571,
|
3 |
+
"best_model_checkpoint": "delivery_truck_classification/checkpoint-27",
|
4 |
+
"epoch": 40.0,
|
5 |
+
"global_step": 40,
|
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 |
+
"eval_accuracy": 0.14285714285714285,
|
13 |
+
"eval_loss": 1.9874809980392456,
|
14 |
+
"eval_runtime": 0.555,
|
15 |
+
"eval_samples_per_second": 12.612,
|
16 |
+
"eval_steps_per_second": 1.802,
|
17 |
"step": 1
|
18 |
},
|
19 |
{
|
20 |
"epoch": 2.0,
|
21 |
+
"eval_accuracy": 0.14285714285714285,
|
22 |
+
"eval_loss": 1.9131802320480347,
|
23 |
+
"eval_runtime": 0.612,
|
24 |
+
"eval_samples_per_second": 11.438,
|
25 |
+
"eval_steps_per_second": 1.634,
|
26 |
"step": 2
|
27 |
},
|
28 |
{
|
29 |
"epoch": 3.0,
|
30 |
+
"eval_accuracy": 0.42857142857142855,
|
31 |
+
"eval_loss": 1.7584645748138428,
|
32 |
+
"eval_runtime": 0.6123,
|
33 |
+
"eval_samples_per_second": 11.432,
|
34 |
+
"eval_steps_per_second": 1.633,
|
35 |
"step": 3
|
36 |
},
|
37 |
{
|
38 |
"epoch": 4.0,
|
39 |
+
"eval_accuracy": 0.42857142857142855,
|
40 |
+
"eval_loss": 1.5935114622116089,
|
41 |
+
"eval_runtime": 0.6224,
|
42 |
+
"eval_samples_per_second": 11.247,
|
43 |
+
"eval_steps_per_second": 1.607,
|
44 |
"step": 4
|
45 |
},
|
46 |
{
|
47 |
"epoch": 5.0,
|
48 |
+
"eval_accuracy": 0.42857142857142855,
|
49 |
+
"eval_loss": 1.5026111602783203,
|
50 |
+
"eval_runtime": 0.5902,
|
51 |
+
"eval_samples_per_second": 11.86,
|
52 |
+
"eval_steps_per_second": 1.694,
|
53 |
"step": 5
|
54 |
},
|
55 |
{
|
56 |
"epoch": 6.0,
|
57 |
+
"eval_accuracy": 0.42857142857142855,
|
58 |
+
"eval_loss": 1.4698925018310547,
|
59 |
+
"eval_runtime": 0.6228,
|
60 |
+
"eval_samples_per_second": 11.239,
|
61 |
+
"eval_steps_per_second": 1.606,
|
62 |
"step": 6
|
63 |
},
|
64 |
{
|
65 |
"epoch": 7.0,
|
66 |
+
"eval_accuracy": 0.42857142857142855,
|
67 |
+
"eval_loss": 1.4360735416412354,
|
68 |
+
"eval_runtime": 0.5993,
|
69 |
+
"eval_samples_per_second": 11.681,
|
70 |
+
"eval_steps_per_second": 1.669,
|
71 |
"step": 7
|
72 |
},
|
73 |
{
|
74 |
"epoch": 8.0,
|
75 |
+
"eval_accuracy": 0.42857142857142855,
|
76 |
+
"eval_loss": 1.3962326049804688,
|
77 |
+
"eval_runtime": 0.6058,
|
78 |
+
"eval_samples_per_second": 11.555,
|
79 |
+
"eval_steps_per_second": 1.651,
|
80 |
"step": 8
|
81 |
},
|
82 |
{
|
83 |
"epoch": 9.0,
|
84 |
+
"eval_accuracy": 0.42857142857142855,
|
85 |
+
"eval_loss": 1.3457258939743042,
|
86 |
+
"eval_runtime": 0.6198,
|
87 |
+
"eval_samples_per_second": 11.293,
|
88 |
+
"eval_steps_per_second": 1.613,
|
89 |
"step": 9
|
90 |
},
|
91 |
{
|
92 |
"epoch": 10.0,
|
93 |
+
"eval_accuracy": 0.42857142857142855,
|
94 |
+
"eval_loss": 1.2874202728271484,
|
95 |
+
"eval_runtime": 0.6157,
|
96 |
+
"eval_samples_per_second": 11.369,
|
97 |
+
"eval_steps_per_second": 1.624,
|
98 |
"step": 10
|
99 |
},
|
100 |
{
|
101 |
+
"epoch": 11.0,
|
102 |
+
"eval_accuracy": 0.42857142857142855,
|
103 |
+
"eval_loss": 1.2239570617675781,
|
104 |
+
"eval_runtime": 0.6193,
|
105 |
+
"eval_samples_per_second": 11.304,
|
106 |
+
"eval_steps_per_second": 1.615,
|
107 |
+
"step": 11
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 12.0,
|
111 |
+
"eval_accuracy": 0.42857142857142855,
|
112 |
+
"eval_loss": 1.1642504930496216,
|
113 |
+
"eval_runtime": 0.6288,
|
114 |
+
"eval_samples_per_second": 11.132,
|
115 |
+
"eval_steps_per_second": 1.59,
|
116 |
+
"step": 12
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 13.0,
|
120 |
+
"eval_accuracy": 0.5714285714285714,
|
121 |
+
"eval_loss": 1.101585030555725,
|
122 |
+
"eval_runtime": 0.6087,
|
123 |
+
"eval_samples_per_second": 11.5,
|
124 |
+
"eval_steps_per_second": 1.643,
|
125 |
+
"step": 13
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 14.0,
|
129 |
+
"eval_accuracy": 0.5714285714285714,
|
130 |
+
"eval_loss": 1.0355511903762817,
|
131 |
+
"eval_runtime": 0.5997,
|
132 |
+
"eval_samples_per_second": 11.673,
|
133 |
+
"eval_steps_per_second": 1.668,
|
134 |
+
"step": 14
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 15.0,
|
138 |
+
"eval_accuracy": 0.7142857142857143,
|
139 |
+
"eval_loss": 0.9718684554100037,
|
140 |
+
"eval_runtime": 0.5696,
|
141 |
+
"eval_samples_per_second": 12.29,
|
142 |
+
"eval_steps_per_second": 1.756,
|
143 |
+
"step": 15
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 16.0,
|
147 |
+
"eval_accuracy": 0.7142857142857143,
|
148 |
+
"eval_loss": 0.91197669506073,
|
149 |
+
"eval_runtime": 0.6278,
|
150 |
+
"eval_samples_per_second": 11.15,
|
151 |
+
"eval_steps_per_second": 1.593,
|
152 |
+
"step": 16
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 17.0,
|
156 |
+
"eval_accuracy": 0.7142857142857143,
|
157 |
+
"eval_loss": 0.8606060743331909,
|
158 |
+
"eval_runtime": 0.6159,
|
159 |
+
"eval_samples_per_second": 11.365,
|
160 |
+
"eval_steps_per_second": 1.624,
|
161 |
+
"step": 17
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 18.0,
|
165 |
+
"eval_accuracy": 0.7142857142857143,
|
166 |
+
"eval_loss": 0.8117322325706482,
|
167 |
+
"eval_runtime": 0.628,
|
168 |
+
"eval_samples_per_second": 11.147,
|
169 |
+
"eval_steps_per_second": 1.592,
|
170 |
+
"step": 18
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 19.0,
|
174 |
+
"eval_accuracy": 0.7142857142857143,
|
175 |
+
"eval_loss": 0.7706560492515564,
|
176 |
+
"eval_runtime": 0.6266,
|
177 |
+
"eval_samples_per_second": 11.171,
|
178 |
+
"eval_steps_per_second": 1.596,
|
179 |
+
"step": 19
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 20.0,
|
183 |
+
"learning_rate": 2.777777777777778e-05,
|
184 |
+
"loss": 0.5111,
|
185 |
+
"step": 20
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 20.0,
|
189 |
+
"eval_accuracy": 0.7142857142857143,
|
190 |
+
"eval_loss": 0.7366718649864197,
|
191 |
+
"eval_runtime": 0.601,
|
192 |
+
"eval_samples_per_second": 11.646,
|
193 |
+
"eval_steps_per_second": 1.664,
|
194 |
+
"step": 20
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 21.0,
|
198 |
+
"eval_accuracy": 0.7142857142857143,
|
199 |
+
"eval_loss": 0.7156747579574585,
|
200 |
+
"eval_runtime": 0.619,
|
201 |
+
"eval_samples_per_second": 11.308,
|
202 |
+
"eval_steps_per_second": 1.615,
|
203 |
+
"step": 21
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 22.0,
|
207 |
+
"eval_accuracy": 0.7142857142857143,
|
208 |
+
"eval_loss": 0.706693172454834,
|
209 |
+
"eval_runtime": 0.6179,
|
210 |
+
"eval_samples_per_second": 11.329,
|
211 |
+
"eval_steps_per_second": 1.618,
|
212 |
+
"step": 22
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 23.0,
|
216 |
+
"eval_accuracy": 0.7142857142857143,
|
217 |
+
"eval_loss": 0.7012028098106384,
|
218 |
+
"eval_runtime": 0.6214,
|
219 |
+
"eval_samples_per_second": 11.265,
|
220 |
+
"eval_steps_per_second": 1.609,
|
221 |
+
"step": 23
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 24.0,
|
225 |
+
"eval_accuracy": 0.7142857142857143,
|
226 |
+
"eval_loss": 0.697659432888031,
|
227 |
+
"eval_runtime": 0.6273,
|
228 |
+
"eval_samples_per_second": 11.16,
|
229 |
+
"eval_steps_per_second": 1.594,
|
230 |
+
"step": 24
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 25.0,
|
234 |
+
"eval_accuracy": 0.7142857142857143,
|
235 |
+
"eval_loss": 0.6974306106567383,
|
236 |
+
"eval_runtime": 0.6326,
|
237 |
+
"eval_samples_per_second": 11.065,
|
238 |
+
"eval_steps_per_second": 1.581,
|
239 |
+
"step": 25
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 26.0,
|
243 |
+
"eval_accuracy": 0.7142857142857143,
|
244 |
+
"eval_loss": 0.6976919770240784,
|
245 |
+
"eval_runtime": 0.6266,
|
246 |
+
"eval_samples_per_second": 11.171,
|
247 |
+
"eval_steps_per_second": 1.596,
|
248 |
+
"step": 26
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 27.0,
|
252 |
+
"eval_accuracy": 0.8571428571428571,
|
253 |
+
"eval_loss": 0.703612744808197,
|
254 |
+
"eval_runtime": 0.626,
|
255 |
+
"eval_samples_per_second": 11.182,
|
256 |
+
"eval_steps_per_second": 1.597,
|
257 |
+
"step": 27
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 28.0,
|
261 |
+
"eval_accuracy": 0.8571428571428571,
|
262 |
+
"eval_loss": 0.7074456810951233,
|
263 |
+
"eval_runtime": 0.624,
|
264 |
+
"eval_samples_per_second": 11.218,
|
265 |
+
"eval_steps_per_second": 1.603,
|
266 |
+
"step": 28
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 29.0,
|
270 |
+
"eval_accuracy": 0.8571428571428571,
|
271 |
+
"eval_loss": 0.7061924338340759,
|
272 |
+
"eval_runtime": 0.5569,
|
273 |
+
"eval_samples_per_second": 12.569,
|
274 |
+
"eval_steps_per_second": 1.796,
|
275 |
+
"step": 29
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 30.0,
|
279 |
+
"eval_accuracy": 0.8571428571428571,
|
280 |
+
"eval_loss": 0.7056497931480408,
|
281 |
+
"eval_runtime": 0.6221,
|
282 |
+
"eval_samples_per_second": 11.252,
|
283 |
+
"eval_steps_per_second": 1.607,
|
284 |
+
"step": 30
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 31.0,
|
288 |
+
"eval_accuracy": 0.8571428571428571,
|
289 |
+
"eval_loss": 0.7049512267112732,
|
290 |
+
"eval_runtime": 0.6315,
|
291 |
+
"eval_samples_per_second": 11.084,
|
292 |
+
"eval_steps_per_second": 1.583,
|
293 |
+
"step": 31
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 32.0,
|
297 |
+
"eval_accuracy": 0.8571428571428571,
|
298 |
+
"eval_loss": 0.7050389647483826,
|
299 |
+
"eval_runtime": 0.6239,
|
300 |
+
"eval_samples_per_second": 11.22,
|
301 |
+
"eval_steps_per_second": 1.603,
|
302 |
+
"step": 32
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 33.0,
|
306 |
+
"eval_accuracy": 0.8571428571428571,
|
307 |
+
"eval_loss": 0.703091025352478,
|
308 |
+
"eval_runtime": 0.633,
|
309 |
+
"eval_samples_per_second": 11.058,
|
310 |
+
"eval_steps_per_second": 1.58,
|
311 |
+
"step": 33
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 34.0,
|
315 |
+
"eval_accuracy": 0.8571428571428571,
|
316 |
+
"eval_loss": 0.7015966773033142,
|
317 |
+
"eval_runtime": 0.6318,
|
318 |
+
"eval_samples_per_second": 11.079,
|
319 |
+
"eval_steps_per_second": 1.583,
|
320 |
+
"step": 34
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 35.0,
|
324 |
+
"eval_accuracy": 0.8571428571428571,
|
325 |
+
"eval_loss": 0.6995734572410583,
|
326 |
+
"eval_runtime": 0.6327,
|
327 |
+
"eval_samples_per_second": 11.064,
|
328 |
+
"eval_steps_per_second": 1.581,
|
329 |
+
"step": 35
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 36.0,
|
333 |
+
"eval_accuracy": 0.8571428571428571,
|
334 |
+
"eval_loss": 0.6970993280410767,
|
335 |
+
"eval_runtime": 0.6284,
|
336 |
+
"eval_samples_per_second": 11.139,
|
337 |
+
"eval_steps_per_second": 1.591,
|
338 |
+
"step": 36
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 37.0,
|
342 |
+
"eval_accuracy": 0.8571428571428571,
|
343 |
+
"eval_loss": 0.6953268647193909,
|
344 |
+
"eval_runtime": 0.6135,
|
345 |
+
"eval_samples_per_second": 11.41,
|
346 |
+
"eval_steps_per_second": 1.63,
|
347 |
+
"step": 37
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 38.0,
|
351 |
+
"eval_accuracy": 0.8571428571428571,
|
352 |
+
"eval_loss": 0.6938610672950745,
|
353 |
+
"eval_runtime": 0.7702,
|
354 |
+
"eval_samples_per_second": 9.089,
|
355 |
+
"eval_steps_per_second": 1.298,
|
356 |
+
"step": 38
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 39.0,
|
360 |
+
"eval_accuracy": 0.8571428571428571,
|
361 |
+
"eval_loss": 0.6938490867614746,
|
362 |
+
"eval_runtime": 0.6214,
|
363 |
+
"eval_samples_per_second": 11.265,
|
364 |
+
"eval_steps_per_second": 1.609,
|
365 |
+
"step": 39
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 40.0,
|
369 |
+
"learning_rate": 0.0,
|
370 |
+
"loss": 0.1719,
|
371 |
+
"step": 40
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 40.0,
|
375 |
+
"eval_accuracy": 0.8571428571428571,
|
376 |
+
"eval_loss": 0.6936034560203552,
|
377 |
+
"eval_runtime": 0.6132,
|
378 |
+
"eval_samples_per_second": 11.416,
|
379 |
+
"eval_steps_per_second": 1.631,
|
380 |
+
"step": 40
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 40.0,
|
384 |
+
"step": 40,
|
385 |
+
"total_flos": 6.164974248394752e+16,
|
386 |
+
"train_loss": 0.3415180742740631,
|
387 |
+
"train_runtime": 367.0026,
|
388 |
+
"train_samples_per_second": 6.757,
|
389 |
+
"train_steps_per_second": 0.109
|
390 |
}
|
391 |
],
|
392 |
+
"max_steps": 40,
|
393 |
+
"num_train_epochs": 40,
|
394 |
+
"total_flos": 6.164974248394752e+16,
|
395 |
"trial_name": null,
|
396 |
"trial_params": null
|
397 |
}
|