videomae-base-finetuned-kinetics-finetuned-movienet-2-2/checkpoint-372
Browse files
all_results.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eval_accuracy": 0.7552083333333334,
|
3 |
+
"eval_loss": 1.4970475435256958
|
4 |
+
}
|
runs/Aug10_19-30-40_93e04ce25dfb/events.out.tfevents.1691695878.93e04ce25dfb.859.0
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:b05c51a745e07e69ebb320fb11e32ef64fa595138d81b4978a184fdb72f34dbd
|
3 |
+
size 24539
|
test_results.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eval_accuracy": 0.7552083333333334,
|
3 |
+
"eval_loss": 1.4970475435256958
|
4 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,754 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8351063829787234,
|
3 |
+
"best_model_checkpoint": "videomae-base-finetuned-kinetics-finetuned-movienet-2-2/checkpoint-372",
|
4 |
+
"epoch": 6.00054054054054,
|
5 |
+
"global_step": 1117,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.01,
|
12 |
+
"learning_rate": 5.405405405405406e-07,
|
13 |
+
"loss": 0.0001,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.01,
|
18 |
+
"learning_rate": 1.0810810810810812e-06,
|
19 |
+
"loss": 0.0009,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.02,
|
24 |
+
"learning_rate": 1.6216216216216219e-06,
|
25 |
+
"loss": 0.0003,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.02,
|
30 |
+
"learning_rate": 2.1621621621621623e-06,
|
31 |
+
"loss": 0.0002,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.03,
|
36 |
+
"learning_rate": 2.702702702702703e-06,
|
37 |
+
"loss": 0.0001,
|
38 |
+
"step": 50
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.03,
|
42 |
+
"learning_rate": 3.2432432432432437e-06,
|
43 |
+
"loss": 0.0001,
|
44 |
+
"step": 60
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.04,
|
48 |
+
"learning_rate": 3.783783783783784e-06,
|
49 |
+
"loss": 0.0033,
|
50 |
+
"step": 70
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.04,
|
54 |
+
"learning_rate": 4.324324324324325e-06,
|
55 |
+
"loss": 0.0003,
|
56 |
+
"step": 80
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.05,
|
60 |
+
"learning_rate": 4.864864864864866e-06,
|
61 |
+
"loss": 0.0001,
|
62 |
+
"step": 90
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.05,
|
66 |
+
"learning_rate": 5.405405405405406e-06,
|
67 |
+
"loss": 0.0001,
|
68 |
+
"step": 100
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.06,
|
72 |
+
"learning_rate": 5.945945945945946e-06,
|
73 |
+
"loss": 0.0001,
|
74 |
+
"step": 110
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.06,
|
78 |
+
"learning_rate": 6.486486486486487e-06,
|
79 |
+
"loss": 0.0001,
|
80 |
+
"step": 120
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.07,
|
84 |
+
"learning_rate": 7.027027027027028e-06,
|
85 |
+
"loss": 0.0,
|
86 |
+
"step": 130
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.08,
|
90 |
+
"learning_rate": 7.567567567567568e-06,
|
91 |
+
"loss": 0.0001,
|
92 |
+
"step": 140
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.08,
|
96 |
+
"learning_rate": 8.108108108108109e-06,
|
97 |
+
"loss": 0.0001,
|
98 |
+
"step": 150
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.09,
|
102 |
+
"learning_rate": 8.64864864864865e-06,
|
103 |
+
"loss": 0.0,
|
104 |
+
"step": 160
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.09,
|
108 |
+
"learning_rate": 9.18918918918919e-06,
|
109 |
+
"loss": 0.0007,
|
110 |
+
"step": 170
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.1,
|
114 |
+
"learning_rate": 9.729729729729732e-06,
|
115 |
+
"loss": 0.0006,
|
116 |
+
"step": 180
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.1,
|
120 |
+
"eval_accuracy": 0.7978723404255319,
|
121 |
+
"eval_loss": 1.0443280935287476,
|
122 |
+
"eval_runtime": 333.5702,
|
123 |
+
"eval_samples_per_second": 0.564,
|
124 |
+
"eval_steps_per_second": 0.072,
|
125 |
+
"step": 186
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 1.0,
|
129 |
+
"learning_rate": 1.0270270270270272e-05,
|
130 |
+
"loss": 0.0001,
|
131 |
+
"step": 190
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 1.01,
|
135 |
+
"learning_rate": 1.0810810810810812e-05,
|
136 |
+
"loss": 0.0003,
|
137 |
+
"step": 200
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 1.01,
|
141 |
+
"learning_rate": 1.1351351351351352e-05,
|
142 |
+
"loss": 0.0,
|
143 |
+
"step": 210
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 1.02,
|
147 |
+
"learning_rate": 1.1891891891891893e-05,
|
148 |
+
"loss": 0.0001,
|
149 |
+
"step": 220
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.02,
|
153 |
+
"learning_rate": 1.2432432432432435e-05,
|
154 |
+
"loss": 0.0001,
|
155 |
+
"step": 230
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 1.03,
|
159 |
+
"learning_rate": 1.2972972972972975e-05,
|
160 |
+
"loss": 0.0001,
|
161 |
+
"step": 240
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 1.03,
|
165 |
+
"learning_rate": 1.3513513513513515e-05,
|
166 |
+
"loss": 0.0,
|
167 |
+
"step": 250
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 1.04,
|
171 |
+
"learning_rate": 1.4054054054054055e-05,
|
172 |
+
"loss": 0.0,
|
173 |
+
"step": 260
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 1.05,
|
177 |
+
"learning_rate": 1.4594594594594596e-05,
|
178 |
+
"loss": 0.0,
|
179 |
+
"step": 270
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 1.05,
|
183 |
+
"learning_rate": 1.5135135135135136e-05,
|
184 |
+
"loss": 0.0001,
|
185 |
+
"step": 280
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 1.06,
|
189 |
+
"learning_rate": 1.5675675675675676e-05,
|
190 |
+
"loss": 0.0,
|
191 |
+
"step": 290
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 1.06,
|
195 |
+
"learning_rate": 1.6216216216216218e-05,
|
196 |
+
"loss": 0.0,
|
197 |
+
"step": 300
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 1.07,
|
201 |
+
"learning_rate": 1.675675675675676e-05,
|
202 |
+
"loss": 0.0,
|
203 |
+
"step": 310
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 1.07,
|
207 |
+
"learning_rate": 1.72972972972973e-05,
|
208 |
+
"loss": 0.0,
|
209 |
+
"step": 320
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 1.08,
|
213 |
+
"learning_rate": 1.783783783783784e-05,
|
214 |
+
"loss": 0.0,
|
215 |
+
"step": 330
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 1.08,
|
219 |
+
"learning_rate": 1.837837837837838e-05,
|
220 |
+
"loss": 0.0,
|
221 |
+
"step": 340
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 1.09,
|
225 |
+
"learning_rate": 1.891891891891892e-05,
|
226 |
+
"loss": 0.0,
|
227 |
+
"step": 350
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 1.09,
|
231 |
+
"learning_rate": 1.9459459459459463e-05,
|
232 |
+
"loss": 0.0001,
|
233 |
+
"step": 360
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.1,
|
237 |
+
"learning_rate": 2e-05,
|
238 |
+
"loss": 0.0,
|
239 |
+
"step": 370
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 1.1,
|
243 |
+
"eval_accuracy": 0.8351063829787234,
|
244 |
+
"eval_loss": 1.0924887657165527,
|
245 |
+
"eval_runtime": 177.4121,
|
246 |
+
"eval_samples_per_second": 1.06,
|
247 |
+
"eval_steps_per_second": 0.135,
|
248 |
+
"step": 372
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 2.0,
|
252 |
+
"learning_rate": 2.0540540540540544e-05,
|
253 |
+
"loss": 0.0001,
|
254 |
+
"step": 380
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 2.01,
|
258 |
+
"learning_rate": 2.1081081081081082e-05,
|
259 |
+
"loss": 0.0,
|
260 |
+
"step": 390
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 2.02,
|
264 |
+
"learning_rate": 2.1621621621621624e-05,
|
265 |
+
"loss": 0.0,
|
266 |
+
"step": 400
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 2.02,
|
270 |
+
"learning_rate": 2.2162162162162166e-05,
|
271 |
+
"loss": 0.0,
|
272 |
+
"step": 410
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 2.03,
|
276 |
+
"learning_rate": 2.2702702702702705e-05,
|
277 |
+
"loss": 0.0,
|
278 |
+
"step": 420
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 2.03,
|
282 |
+
"learning_rate": 2.3243243243243247e-05,
|
283 |
+
"loss": 0.0,
|
284 |
+
"step": 430
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 2.04,
|
288 |
+
"learning_rate": 2.3783783783783785e-05,
|
289 |
+
"loss": 0.0,
|
290 |
+
"step": 440
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 2.04,
|
294 |
+
"learning_rate": 2.4324324324324327e-05,
|
295 |
+
"loss": 0.0,
|
296 |
+
"step": 450
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 2.05,
|
300 |
+
"learning_rate": 2.486486486486487e-05,
|
301 |
+
"loss": 0.0,
|
302 |
+
"step": 460
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 2.05,
|
306 |
+
"learning_rate": 2.5405405405405408e-05,
|
307 |
+
"loss": 0.0,
|
308 |
+
"step": 470
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 2.06,
|
312 |
+
"learning_rate": 2.594594594594595e-05,
|
313 |
+
"loss": 0.0,
|
314 |
+
"step": 480
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 2.06,
|
318 |
+
"learning_rate": 2.6486486486486488e-05,
|
319 |
+
"loss": 0.0,
|
320 |
+
"step": 490
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 2.07,
|
324 |
+
"learning_rate": 2.702702702702703e-05,
|
325 |
+
"loss": 0.0,
|
326 |
+
"step": 500
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 2.07,
|
330 |
+
"learning_rate": 2.7567567567567572e-05,
|
331 |
+
"loss": 0.0,
|
332 |
+
"step": 510
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 2.08,
|
336 |
+
"learning_rate": 2.810810810810811e-05,
|
337 |
+
"loss": 0.0,
|
338 |
+
"step": 520
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 2.09,
|
342 |
+
"learning_rate": 2.8648648648648653e-05,
|
343 |
+
"loss": 0.0,
|
344 |
+
"step": 530
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 2.09,
|
348 |
+
"learning_rate": 2.918918918918919e-05,
|
349 |
+
"loss": 0.0332,
|
350 |
+
"step": 540
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 2.1,
|
354 |
+
"learning_rate": 2.9729729729729733e-05,
|
355 |
+
"loss": 0.0005,
|
356 |
+
"step": 550
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 2.1,
|
360 |
+
"eval_accuracy": 0.7925531914893617,
|
361 |
+
"eval_loss": 1.8252729177474976,
|
362 |
+
"eval_runtime": 119.7198,
|
363 |
+
"eval_samples_per_second": 1.57,
|
364 |
+
"eval_steps_per_second": 0.2,
|
365 |
+
"step": 558
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 3.0,
|
369 |
+
"learning_rate": 3.0270270270270272e-05,
|
370 |
+
"loss": 0.2088,
|
371 |
+
"step": 560
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 3.01,
|
375 |
+
"learning_rate": 3.081081081081082e-05,
|
376 |
+
"loss": 0.3743,
|
377 |
+
"step": 570
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 3.01,
|
381 |
+
"learning_rate": 3.135135135135135e-05,
|
382 |
+
"loss": 0.5181,
|
383 |
+
"step": 580
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 3.02,
|
387 |
+
"learning_rate": 3.1891891891891894e-05,
|
388 |
+
"loss": 0.694,
|
389 |
+
"step": 590
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 3.02,
|
393 |
+
"learning_rate": 3.2432432432432436e-05,
|
394 |
+
"loss": 0.0207,
|
395 |
+
"step": 600
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 3.03,
|
399 |
+
"learning_rate": 3.297297297297298e-05,
|
400 |
+
"loss": 0.0749,
|
401 |
+
"step": 610
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 3.03,
|
405 |
+
"learning_rate": 3.351351351351352e-05,
|
406 |
+
"loss": 0.0858,
|
407 |
+
"step": 620
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 3.04,
|
411 |
+
"learning_rate": 3.4054054054054055e-05,
|
412 |
+
"loss": 0.2189,
|
413 |
+
"step": 630
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 3.04,
|
417 |
+
"learning_rate": 3.45945945945946e-05,
|
418 |
+
"loss": 0.0966,
|
419 |
+
"step": 640
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 3.05,
|
423 |
+
"learning_rate": 3.513513513513514e-05,
|
424 |
+
"loss": 0.0286,
|
425 |
+
"step": 650
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 3.06,
|
429 |
+
"learning_rate": 3.567567567567568e-05,
|
430 |
+
"loss": 0.1632,
|
431 |
+
"step": 660
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 3.06,
|
435 |
+
"learning_rate": 3.621621621621622e-05,
|
436 |
+
"loss": 0.1709,
|
437 |
+
"step": 670
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 3.07,
|
441 |
+
"learning_rate": 3.675675675675676e-05,
|
442 |
+
"loss": 0.1024,
|
443 |
+
"step": 680
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 3.07,
|
447 |
+
"learning_rate": 3.72972972972973e-05,
|
448 |
+
"loss": 0.0277,
|
449 |
+
"step": 690
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 3.08,
|
453 |
+
"learning_rate": 3.783783783783784e-05,
|
454 |
+
"loss": 0.1365,
|
455 |
+
"step": 700
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 3.08,
|
459 |
+
"learning_rate": 3.8378378378378384e-05,
|
460 |
+
"loss": 0.0059,
|
461 |
+
"step": 710
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 3.09,
|
465 |
+
"learning_rate": 3.8918918918918926e-05,
|
466 |
+
"loss": 0.1678,
|
467 |
+
"step": 720
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 3.09,
|
471 |
+
"learning_rate": 3.945945945945946e-05,
|
472 |
+
"loss": 0.0807,
|
473 |
+
"step": 730
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 3.1,
|
477 |
+
"learning_rate": 4e-05,
|
478 |
+
"loss": 0.1005,
|
479 |
+
"step": 740
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 3.1,
|
483 |
+
"eval_accuracy": 0.776595744680851,
|
484 |
+
"eval_loss": 1.4864708185195923,
|
485 |
+
"eval_runtime": 144.0436,
|
486 |
+
"eval_samples_per_second": 1.305,
|
487 |
+
"eval_steps_per_second": 0.167,
|
488 |
+
"step": 744
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 4.0,
|
492 |
+
"learning_rate": 4.0540540540540545e-05,
|
493 |
+
"loss": 0.0011,
|
494 |
+
"step": 750
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 4.01,
|
498 |
+
"learning_rate": 4.108108108108109e-05,
|
499 |
+
"loss": 0.0026,
|
500 |
+
"step": 760
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 4.01,
|
504 |
+
"learning_rate": 4.162162162162163e-05,
|
505 |
+
"loss": 0.0969,
|
506 |
+
"step": 770
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 4.02,
|
510 |
+
"learning_rate": 4.2162162162162164e-05,
|
511 |
+
"loss": 0.0021,
|
512 |
+
"step": 780
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 4.02,
|
516 |
+
"learning_rate": 4.2702702702702706e-05,
|
517 |
+
"loss": 0.1575,
|
518 |
+
"step": 790
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 4.03,
|
522 |
+
"learning_rate": 4.324324324324325e-05,
|
523 |
+
"loss": 0.1013,
|
524 |
+
"step": 800
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 4.04,
|
528 |
+
"learning_rate": 4.378378378378379e-05,
|
529 |
+
"loss": 0.107,
|
530 |
+
"step": 810
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 4.04,
|
534 |
+
"learning_rate": 4.432432432432433e-05,
|
535 |
+
"loss": 0.1215,
|
536 |
+
"step": 820
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 4.05,
|
540 |
+
"learning_rate": 4.486486486486487e-05,
|
541 |
+
"loss": 0.1436,
|
542 |
+
"step": 830
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 4.05,
|
546 |
+
"learning_rate": 4.540540540540541e-05,
|
547 |
+
"loss": 0.1396,
|
548 |
+
"step": 840
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 4.06,
|
552 |
+
"learning_rate": 4.594594594594595e-05,
|
553 |
+
"loss": 0.1465,
|
554 |
+
"step": 850
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 4.06,
|
558 |
+
"learning_rate": 4.648648648648649e-05,
|
559 |
+
"loss": 0.1406,
|
560 |
+
"step": 860
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 4.07,
|
564 |
+
"learning_rate": 4.7027027027027035e-05,
|
565 |
+
"loss": 0.0622,
|
566 |
+
"step": 870
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 4.07,
|
570 |
+
"learning_rate": 4.756756756756757e-05,
|
571 |
+
"loss": 0.1626,
|
572 |
+
"step": 880
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 4.08,
|
576 |
+
"learning_rate": 4.810810810810811e-05,
|
577 |
+
"loss": 0.0762,
|
578 |
+
"step": 890
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 4.08,
|
582 |
+
"learning_rate": 4.8648648648648654e-05,
|
583 |
+
"loss": 0.3711,
|
584 |
+
"step": 900
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 4.09,
|
588 |
+
"learning_rate": 4.9189189189189196e-05,
|
589 |
+
"loss": 0.0856,
|
590 |
+
"step": 910
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 4.1,
|
594 |
+
"learning_rate": 4.972972972972974e-05,
|
595 |
+
"loss": 0.1893,
|
596 |
+
"step": 920
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 4.1,
|
600 |
+
"learning_rate": 4.972972972972974e-05,
|
601 |
+
"loss": 0.0775,
|
602 |
+
"step": 930
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 4.1,
|
606 |
+
"eval_accuracy": 0.7819148936170213,
|
607 |
+
"eval_loss": 1.3223650455474854,
|
608 |
+
"eval_runtime": 128.5188,
|
609 |
+
"eval_samples_per_second": 1.463,
|
610 |
+
"eval_steps_per_second": 0.187,
|
611 |
+
"step": 930
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 5.01,
|
615 |
+
"learning_rate": 4.9189189189189196e-05,
|
616 |
+
"loss": 0.0432,
|
617 |
+
"step": 940
|
618 |
+
},
|
619 |
+
{
|
620 |
+
"epoch": 5.01,
|
621 |
+
"learning_rate": 4.8648648648648654e-05,
|
622 |
+
"loss": 0.0816,
|
623 |
+
"step": 950
|
624 |
+
},
|
625 |
+
{
|
626 |
+
"epoch": 5.02,
|
627 |
+
"learning_rate": 4.810810810810811e-05,
|
628 |
+
"loss": 0.1708,
|
629 |
+
"step": 960
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 5.02,
|
633 |
+
"learning_rate": 4.756756756756757e-05,
|
634 |
+
"loss": 0.239,
|
635 |
+
"step": 970
|
636 |
+
},
|
637 |
+
{
|
638 |
+
"epoch": 5.03,
|
639 |
+
"learning_rate": 4.7027027027027035e-05,
|
640 |
+
"loss": 0.3324,
|
641 |
+
"step": 980
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 5.03,
|
645 |
+
"learning_rate": 4.648648648648649e-05,
|
646 |
+
"loss": 0.0658,
|
647 |
+
"step": 990
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 5.04,
|
651 |
+
"learning_rate": 4.594594594594595e-05,
|
652 |
+
"loss": 0.1028,
|
653 |
+
"step": 1000
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 5.04,
|
657 |
+
"learning_rate": 4.540540540540541e-05,
|
658 |
+
"loss": 0.0007,
|
659 |
+
"step": 1010
|
660 |
+
},
|
661 |
+
{
|
662 |
+
"epoch": 5.05,
|
663 |
+
"learning_rate": 4.486486486486487e-05,
|
664 |
+
"loss": 0.0467,
|
665 |
+
"step": 1020
|
666 |
+
},
|
667 |
+
{
|
668 |
+
"epoch": 5.05,
|
669 |
+
"learning_rate": 4.432432432432433e-05,
|
670 |
+
"loss": 0.1297,
|
671 |
+
"step": 1030
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 5.06,
|
675 |
+
"learning_rate": 4.378378378378379e-05,
|
676 |
+
"loss": 0.1153,
|
677 |
+
"step": 1040
|
678 |
+
},
|
679 |
+
{
|
680 |
+
"epoch": 5.06,
|
681 |
+
"learning_rate": 4.324324324324325e-05,
|
682 |
+
"loss": 0.0932,
|
683 |
+
"step": 1050
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 5.07,
|
687 |
+
"learning_rate": 4.2702702702702706e-05,
|
688 |
+
"loss": 0.0055,
|
689 |
+
"step": 1060
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 5.08,
|
693 |
+
"learning_rate": 4.2162162162162164e-05,
|
694 |
+
"loss": 0.0069,
|
695 |
+
"step": 1070
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 5.08,
|
699 |
+
"learning_rate": 4.162162162162163e-05,
|
700 |
+
"loss": 0.2046,
|
701 |
+
"step": 1080
|
702 |
+
},
|
703 |
+
{
|
704 |
+
"epoch": 5.09,
|
705 |
+
"learning_rate": 4.108108108108109e-05,
|
706 |
+
"loss": 0.0671,
|
707 |
+
"step": 1090
|
708 |
+
},
|
709 |
+
{
|
710 |
+
"epoch": 5.09,
|
711 |
+
"learning_rate": 4.0540540540540545e-05,
|
712 |
+
"loss": 0.0448,
|
713 |
+
"step": 1100
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 5.1,
|
717 |
+
"learning_rate": 4e-05,
|
718 |
+
"loss": 0.224,
|
719 |
+
"step": 1110
|
720 |
+
},
|
721 |
+
{
|
722 |
+
"epoch": 5.1,
|
723 |
+
"eval_accuracy": 0.75,
|
724 |
+
"eval_loss": 1.1644213199615479,
|
725 |
+
"eval_runtime": 165.0141,
|
726 |
+
"eval_samples_per_second": 1.139,
|
727 |
+
"eval_steps_per_second": 0.145,
|
728 |
+
"step": 1116
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 6.0,
|
732 |
+
"eval_accuracy": 0.7552083333333334,
|
733 |
+
"eval_loss": 1.4970475435256958,
|
734 |
+
"eval_runtime": 328.5593,
|
735 |
+
"eval_samples_per_second": 0.584,
|
736 |
+
"eval_steps_per_second": 0.073,
|
737 |
+
"step": 1117
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 6.0,
|
741 |
+
"eval_accuracy": 0.7552083333333334,
|
742 |
+
"eval_loss": 1.4970475435256958,
|
743 |
+
"eval_runtime": 166.7089,
|
744 |
+
"eval_samples_per_second": 1.152,
|
745 |
+
"eval_steps_per_second": 0.144,
|
746 |
+
"step": 1117
|
747 |
+
}
|
748 |
+
],
|
749 |
+
"max_steps": 1850,
|
750 |
+
"num_train_epochs": 9223372036854775807,
|
751 |
+
"total_flos": 1.1072826181178819e+19,
|
752 |
+
"trial_name": null,
|
753 |
+
"trial_params": null
|
754 |
+
}
|