End of training
Browse files
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.25,
|
3 |
+
"eval_accuracy": 0.8903225806451613,
|
4 |
+
"eval_loss": 0.2866836190223694,
|
5 |
+
"eval_runtime": 45.388,
|
6 |
+
"eval_samples_per_second": 3.415,
|
7 |
+
"eval_steps_per_second": 0.859
|
8 |
+
}
|
runs/Jan06_18-15-38_ef6056a5ed87/events.out.tfevents.1704565899.ef6056a5ed87.13843.1
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fe7d8f0b04c518d91825a261b34c811a49b1449574b679ac9f74a45115b004c
|
3 |
+
size 734
|
test_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.25,
|
3 |
+
"eval_accuracy": 0.8903225806451613,
|
4 |
+
"eval_loss": 0.2866836190223694,
|
5 |
+
"eval_runtime": 45.388,
|
6 |
+
"eval_samples_per_second": 3.415,
|
7 |
+
"eval_steps_per_second": 0.859
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,262 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9428571428571428,
|
3 |
+
"best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-300",
|
4 |
+
"epoch": 3.25,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 300,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.03,
|
13 |
+
"learning_rate": 1.6666666666666667e-05,
|
14 |
+
"loss": 2.3616,
|
15 |
+
"step": 10
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.07,
|
19 |
+
"learning_rate": 3.3333333333333335e-05,
|
20 |
+
"loss": 2.2311,
|
21 |
+
"step": 20
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.1,
|
25 |
+
"learning_rate": 5e-05,
|
26 |
+
"loss": 2.2097,
|
27 |
+
"step": 30
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.13,
|
31 |
+
"learning_rate": 4.814814814814815e-05,
|
32 |
+
"loss": 2.0667,
|
33 |
+
"step": 40
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.17,
|
37 |
+
"learning_rate": 4.62962962962963e-05,
|
38 |
+
"loss": 2.0458,
|
39 |
+
"step": 50
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.2,
|
43 |
+
"learning_rate": 4.4444444444444447e-05,
|
44 |
+
"loss": 1.9547,
|
45 |
+
"step": 60
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.23,
|
49 |
+
"learning_rate": 4.259259259259259e-05,
|
50 |
+
"loss": 1.9487,
|
51 |
+
"step": 70
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.25,
|
55 |
+
"eval_accuracy": 0.32857142857142857,
|
56 |
+
"eval_loss": 1.7081499099731445,
|
57 |
+
"eval_runtime": 23.0243,
|
58 |
+
"eval_samples_per_second": 3.04,
|
59 |
+
"eval_steps_per_second": 0.782,
|
60 |
+
"step": 75
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 1.02,
|
64 |
+
"learning_rate": 4.074074074074074e-05,
|
65 |
+
"loss": 1.4841,
|
66 |
+
"step": 80
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 1.05,
|
70 |
+
"learning_rate": 3.888888888888889e-05,
|
71 |
+
"loss": 1.3976,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 1.08,
|
76 |
+
"learning_rate": 3.7037037037037037e-05,
|
77 |
+
"loss": 1.2798,
|
78 |
+
"step": 100
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 1.12,
|
82 |
+
"learning_rate": 3.518518518518519e-05,
|
83 |
+
"loss": 0.9707,
|
84 |
+
"step": 110
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 1.15,
|
88 |
+
"learning_rate": 3.3333333333333335e-05,
|
89 |
+
"loss": 0.9494,
|
90 |
+
"step": 120
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 1.18,
|
94 |
+
"learning_rate": 3.148148148148148e-05,
|
95 |
+
"loss": 0.6656,
|
96 |
+
"step": 130
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 1.22,
|
100 |
+
"learning_rate": 2.962962962962963e-05,
|
101 |
+
"loss": 0.6657,
|
102 |
+
"step": 140
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 1.25,
|
106 |
+
"learning_rate": 2.777777777777778e-05,
|
107 |
+
"loss": 0.9701,
|
108 |
+
"step": 150
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 1.25,
|
112 |
+
"eval_accuracy": 0.8285714285714286,
|
113 |
+
"eval_loss": 0.5870282053947449,
|
114 |
+
"eval_runtime": 22.0061,
|
115 |
+
"eval_samples_per_second": 3.181,
|
116 |
+
"eval_steps_per_second": 0.818,
|
117 |
+
"step": 150
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 2.03,
|
121 |
+
"learning_rate": 2.5925925925925925e-05,
|
122 |
+
"loss": 0.3559,
|
123 |
+
"step": 160
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 2.07,
|
127 |
+
"learning_rate": 2.4074074074074074e-05,
|
128 |
+
"loss": 0.4951,
|
129 |
+
"step": 170
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 2.1,
|
133 |
+
"learning_rate": 2.2222222222222223e-05,
|
134 |
+
"loss": 0.3375,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 2.13,
|
139 |
+
"learning_rate": 2.037037037037037e-05,
|
140 |
+
"loss": 0.4615,
|
141 |
+
"step": 190
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 2.17,
|
145 |
+
"learning_rate": 1.8518518518518518e-05,
|
146 |
+
"loss": 0.3499,
|
147 |
+
"step": 200
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 2.2,
|
151 |
+
"learning_rate": 1.6666666666666667e-05,
|
152 |
+
"loss": 0.2213,
|
153 |
+
"step": 210
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 2.23,
|
157 |
+
"learning_rate": 1.4814814814814815e-05,
|
158 |
+
"loss": 0.3204,
|
159 |
+
"step": 220
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 2.25,
|
163 |
+
"eval_accuracy": 0.8571428571428571,
|
164 |
+
"eval_loss": 0.3159988224506378,
|
165 |
+
"eval_runtime": 22.4412,
|
166 |
+
"eval_samples_per_second": 3.119,
|
167 |
+
"eval_steps_per_second": 0.802,
|
168 |
+
"step": 225
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 3.02,
|
172 |
+
"learning_rate": 1.2962962962962962e-05,
|
173 |
+
"loss": 0.2408,
|
174 |
+
"step": 230
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 3.05,
|
178 |
+
"learning_rate": 1.1111111111111112e-05,
|
179 |
+
"loss": 0.1195,
|
180 |
+
"step": 240
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 3.08,
|
184 |
+
"learning_rate": 9.259259259259259e-06,
|
185 |
+
"loss": 0.154,
|
186 |
+
"step": 250
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 3.12,
|
190 |
+
"learning_rate": 7.4074074074074075e-06,
|
191 |
+
"loss": 0.1484,
|
192 |
+
"step": 260
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 3.15,
|
196 |
+
"learning_rate": 5.555555555555556e-06,
|
197 |
+
"loss": 0.129,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 3.18,
|
202 |
+
"learning_rate": 3.7037037037037037e-06,
|
203 |
+
"loss": 0.1952,
|
204 |
+
"step": 280
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 3.22,
|
208 |
+
"learning_rate": 1.8518518518518519e-06,
|
209 |
+
"loss": 0.1787,
|
210 |
+
"step": 290
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 3.25,
|
214 |
+
"learning_rate": 0.0,
|
215 |
+
"loss": 0.2186,
|
216 |
+
"step": 300
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 3.25,
|
220 |
+
"eval_accuracy": 0.9428571428571428,
|
221 |
+
"eval_loss": 0.19522547721862793,
|
222 |
+
"eval_runtime": 21.9526,
|
223 |
+
"eval_samples_per_second": 3.189,
|
224 |
+
"eval_steps_per_second": 0.82,
|
225 |
+
"step": 300
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 3.25,
|
229 |
+
"step": 300,
|
230 |
+
"total_flos": 1.495384188125184e+18,
|
231 |
+
"train_loss": 0.9042303419113159,
|
232 |
+
"train_runtime": 866.4529,
|
233 |
+
"train_samples_per_second": 1.385,
|
234 |
+
"train_steps_per_second": 0.346
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 3.25,
|
238 |
+
"eval_accuracy": 0.8903225806451613,
|
239 |
+
"eval_loss": 0.2866836190223694,
|
240 |
+
"eval_runtime": 46.2249,
|
241 |
+
"eval_samples_per_second": 3.353,
|
242 |
+
"eval_steps_per_second": 0.844,
|
243 |
+
"step": 300
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 3.25,
|
247 |
+
"eval_accuracy": 0.8903225806451613,
|
248 |
+
"eval_loss": 0.2866836190223694,
|
249 |
+
"eval_runtime": 45.388,
|
250 |
+
"eval_samples_per_second": 3.415,
|
251 |
+
"eval_steps_per_second": 0.859,
|
252 |
+
"step": 300
|
253 |
+
}
|
254 |
+
],
|
255 |
+
"logging_steps": 10,
|
256 |
+
"max_steps": 300,
|
257 |
+
"num_train_epochs": 9223372036854775807,
|
258 |
+
"save_steps": 500,
|
259 |
+
"total_flos": 1.495384188125184e+18,
|
260 |
+
"trial_name": null,
|
261 |
+
"trial_params": null
|
262 |
+
}
|