Steve Chiou
commited on
Commit
•
ffa6cfb
1
Parent(s):
0460b78
End of training
Browse files- all_results.json +8 -0
- test_results.json +8 -0
- trainer_state.json +211 -0
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.24,
|
3 |
+
"eval_accuracy": 0.475,
|
4 |
+
"eval_loss": 1.5633509159088135,
|
5 |
+
"eval_runtime": 62.0235,
|
6 |
+
"eval_samples_per_second": 1.29,
|
7 |
+
"eval_steps_per_second": 0.322
|
8 |
+
}
|
test_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.24,
|
3 |
+
"eval_accuracy": 0.475,
|
4 |
+
"eval_loss": 1.5633509159088135,
|
5 |
+
"eval_runtime": 62.0235,
|
6 |
+
"eval_samples_per_second": 1.29,
|
7 |
+
"eval_steps_per_second": 0.322
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,211 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.475,
|
3 |
+
"best_model_checkpoint": "videomae-base-finetuned-engine-subset/checkpoint-224",
|
4 |
+
"epoch": 3.236607142857143,
|
5 |
+
"global_step": 224,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.04,
|
12 |
+
"learning_rate": 2.173913043478261e-05,
|
13 |
+
"loss": 2.8816,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.09,
|
18 |
+
"learning_rate": 4.347826086956522e-05,
|
19 |
+
"loss": 2.8286,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.13,
|
24 |
+
"learning_rate": 4.82587064676617e-05,
|
25 |
+
"loss": 2.6244,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.18,
|
30 |
+
"learning_rate": 4.577114427860697e-05,
|
31 |
+
"loss": 2.3974,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.22,
|
36 |
+
"learning_rate": 4.328358208955224e-05,
|
37 |
+
"loss": 2.6687,
|
38 |
+
"step": 50
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.25,
|
42 |
+
"eval_accuracy": 0.15,
|
43 |
+
"eval_loss": 2.5947723388671875,
|
44 |
+
"eval_runtime": 65.3974,
|
45 |
+
"eval_samples_per_second": 1.223,
|
46 |
+
"eval_steps_per_second": 0.306,
|
47 |
+
"step": 57
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 1.01,
|
51 |
+
"learning_rate": 4.079601990049751e-05,
|
52 |
+
"loss": 2.6448,
|
53 |
+
"step": 60
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 1.06,
|
57 |
+
"learning_rate": 3.830845771144278e-05,
|
58 |
+
"loss": 2.5092,
|
59 |
+
"step": 70
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 1.1,
|
63 |
+
"learning_rate": 3.582089552238806e-05,
|
64 |
+
"loss": 2.4746,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.15,
|
69 |
+
"learning_rate": 3.3333333333333335e-05,
|
70 |
+
"loss": 2.5698,
|
71 |
+
"step": 90
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 1.19,
|
75 |
+
"learning_rate": 3.084577114427861e-05,
|
76 |
+
"loss": 2.3483,
|
77 |
+
"step": 100
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 1.24,
|
81 |
+
"learning_rate": 2.835820895522388e-05,
|
82 |
+
"loss": 2.3001,
|
83 |
+
"step": 110
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 1.25,
|
87 |
+
"eval_accuracy": 0.175,
|
88 |
+
"eval_loss": 2.2452101707458496,
|
89 |
+
"eval_runtime": 61.8887,
|
90 |
+
"eval_samples_per_second": 1.293,
|
91 |
+
"eval_steps_per_second": 0.323,
|
92 |
+
"step": 114
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 2.03,
|
96 |
+
"learning_rate": 2.5870646766169153e-05,
|
97 |
+
"loss": 2.0974,
|
98 |
+
"step": 120
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 2.07,
|
102 |
+
"learning_rate": 2.338308457711443e-05,
|
103 |
+
"loss": 2.0862,
|
104 |
+
"step": 130
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 2.12,
|
108 |
+
"learning_rate": 2.0895522388059702e-05,
|
109 |
+
"loss": 2.0094,
|
110 |
+
"step": 140
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 2.16,
|
114 |
+
"learning_rate": 1.8407960199004975e-05,
|
115 |
+
"loss": 2.0335,
|
116 |
+
"step": 150
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 2.21,
|
120 |
+
"learning_rate": 1.592039800995025e-05,
|
121 |
+
"loss": 1.761,
|
122 |
+
"step": 160
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 2.25,
|
126 |
+
"learning_rate": 1.3432835820895523e-05,
|
127 |
+
"loss": 2.1531,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 2.25,
|
132 |
+
"eval_accuracy": 0.3875,
|
133 |
+
"eval_loss": 1.91796875,
|
134 |
+
"eval_runtime": 61.6028,
|
135 |
+
"eval_samples_per_second": 1.299,
|
136 |
+
"eval_steps_per_second": 0.325,
|
137 |
+
"step": 171
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 3.04,
|
141 |
+
"learning_rate": 1.0945273631840796e-05,
|
142 |
+
"loss": 1.7171,
|
143 |
+
"step": 180
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 3.08,
|
147 |
+
"learning_rate": 8.45771144278607e-06,
|
148 |
+
"loss": 1.7341,
|
149 |
+
"step": 190
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 3.13,
|
153 |
+
"learning_rate": 5.970149253731343e-06,
|
154 |
+
"loss": 1.711,
|
155 |
+
"step": 200
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 3.17,
|
159 |
+
"learning_rate": 3.482587064676617e-06,
|
160 |
+
"loss": 1.6104,
|
161 |
+
"step": 210
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 3.22,
|
165 |
+
"learning_rate": 9.950248756218907e-07,
|
166 |
+
"loss": 1.6332,
|
167 |
+
"step": 220
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 3.24,
|
171 |
+
"eval_accuracy": 0.475,
|
172 |
+
"eval_loss": 1.5633509159088135,
|
173 |
+
"eval_runtime": 61.4445,
|
174 |
+
"eval_samples_per_second": 1.302,
|
175 |
+
"eval_steps_per_second": 0.325,
|
176 |
+
"step": 224
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 3.24,
|
180 |
+
"step": 224,
|
181 |
+
"total_flos": 1.1053874300107162e+18,
|
182 |
+
"train_loss": 2.2049321063927243,
|
183 |
+
"train_runtime": 1138.2528,
|
184 |
+
"train_samples_per_second": 0.787,
|
185 |
+
"train_steps_per_second": 0.197
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 3.24,
|
189 |
+
"eval_accuracy": 0.475,
|
190 |
+
"eval_loss": 1.5633509159088135,
|
191 |
+
"eval_runtime": 63.8635,
|
192 |
+
"eval_samples_per_second": 1.253,
|
193 |
+
"eval_steps_per_second": 0.313,
|
194 |
+
"step": 224
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 3.24,
|
198 |
+
"eval_accuracy": 0.475,
|
199 |
+
"eval_loss": 1.5633509159088135,
|
200 |
+
"eval_runtime": 62.0235,
|
201 |
+
"eval_samples_per_second": 1.29,
|
202 |
+
"eval_steps_per_second": 0.322,
|
203 |
+
"step": 224
|
204 |
+
}
|
205 |
+
],
|
206 |
+
"max_steps": 224,
|
207 |
+
"num_train_epochs": 9223372036854775807,
|
208 |
+
"total_flos": 1.1053874300107162e+18,
|
209 |
+
"trial_name": null,
|
210 |
+
"trial_params": null
|
211 |
+
}
|