End of training
Browse files
all_results.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eval_accuracy": 0.7864583333333334,
|
3 |
+
"eval_loss": 0.8737158179283142
|
4 |
+
}
|
runs/Aug10_06-11-57_115d31265f73/events.out.tfevents.1691648005.115d31265f73.353.0
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 sha256:24b1d1c0601b98e7c7b4ce5bc2adf2f12b71b83d5b57f0f1b96764abae2389d4
|
3 |
+
size 20989
|
test_results.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eval_accuracy": 0.7864583333333334,
|
3 |
+
"eval_loss": 0.8737158179283142
|
4 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,628 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8351063829787234,
|
3 |
+
"best_model_checkpoint": "videomae-base-finetuned-kinetics-finetuned-movienet/checkpoint-744",
|
4 |
+
"epoch": 4.100540540540541,
|
5 |
+
"global_step": 930,
|
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": 1.3513513513513515e-06,
|
13 |
+
"loss": 1.6108,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.01,
|
18 |
+
"learning_rate": 2.702702702702703e-06,
|
19 |
+
"loss": 1.6587,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.02,
|
24 |
+
"learning_rate": 4.0540540540540545e-06,
|
25 |
+
"loss": 1.6075,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.02,
|
30 |
+
"learning_rate": 5.405405405405406e-06,
|
31 |
+
"loss": 1.603,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.03,
|
36 |
+
"learning_rate": 6.7567567567567575e-06,
|
37 |
+
"loss": 1.5604,
|
38 |
+
"step": 50
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.03,
|
42 |
+
"learning_rate": 8.108108108108109e-06,
|
43 |
+
"loss": 1.494,
|
44 |
+
"step": 60
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.04,
|
48 |
+
"learning_rate": 9.45945945945946e-06,
|
49 |
+
"loss": 1.4524,
|
50 |
+
"step": 70
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.04,
|
54 |
+
"learning_rate": 1.0810810810810812e-05,
|
55 |
+
"loss": 1.4549,
|
56 |
+
"step": 80
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.05,
|
60 |
+
"learning_rate": 1.2162162162162164e-05,
|
61 |
+
"loss": 1.3249,
|
62 |
+
"step": 90
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.05,
|
66 |
+
"learning_rate": 1.3513513513513515e-05,
|
67 |
+
"loss": 1.2482,
|
68 |
+
"step": 100
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.06,
|
72 |
+
"learning_rate": 1.4864864864864867e-05,
|
73 |
+
"loss": 1.187,
|
74 |
+
"step": 110
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.06,
|
78 |
+
"learning_rate": 1.6216216216216218e-05,
|
79 |
+
"loss": 1.0783,
|
80 |
+
"step": 120
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.07,
|
84 |
+
"learning_rate": 1.756756756756757e-05,
|
85 |
+
"loss": 0.9135,
|
86 |
+
"step": 130
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.08,
|
90 |
+
"learning_rate": 1.891891891891892e-05,
|
91 |
+
"loss": 0.76,
|
92 |
+
"step": 140
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.08,
|
96 |
+
"learning_rate": 2.0270270270270273e-05,
|
97 |
+
"loss": 0.7138,
|
98 |
+
"step": 150
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.09,
|
102 |
+
"learning_rate": 2.1621621621621624e-05,
|
103 |
+
"loss": 0.5681,
|
104 |
+
"step": 160
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.09,
|
108 |
+
"learning_rate": 2.2972972972972976e-05,
|
109 |
+
"loss": 0.6388,
|
110 |
+
"step": 170
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.1,
|
114 |
+
"learning_rate": 2.4324324324324327e-05,
|
115 |
+
"loss": 0.7666,
|
116 |
+
"step": 180
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.1,
|
120 |
+
"eval_accuracy": 0.7021276595744681,
|
121 |
+
"eval_loss": 0.683621346950531,
|
122 |
+
"eval_runtime": 338.0924,
|
123 |
+
"eval_samples_per_second": 0.556,
|
124 |
+
"eval_steps_per_second": 0.071,
|
125 |
+
"step": 186
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 1.0,
|
129 |
+
"learning_rate": 2.5675675675675675e-05,
|
130 |
+
"loss": 0.5934,
|
131 |
+
"step": 190
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 1.01,
|
135 |
+
"learning_rate": 2.702702702702703e-05,
|
136 |
+
"loss": 0.5488,
|
137 |
+
"step": 200
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 1.01,
|
141 |
+
"learning_rate": 2.8378378378378378e-05,
|
142 |
+
"loss": 0.3927,
|
143 |
+
"step": 210
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 1.02,
|
147 |
+
"learning_rate": 2.9729729729729733e-05,
|
148 |
+
"loss": 0.4944,
|
149 |
+
"step": 220
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.02,
|
153 |
+
"learning_rate": 3.108108108108108e-05,
|
154 |
+
"loss": 0.5078,
|
155 |
+
"step": 230
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 1.03,
|
159 |
+
"learning_rate": 3.2432432432432436e-05,
|
160 |
+
"loss": 0.5674,
|
161 |
+
"step": 240
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 1.03,
|
165 |
+
"learning_rate": 3.3783783783783784e-05,
|
166 |
+
"loss": 0.4871,
|
167 |
+
"step": 250
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 1.04,
|
171 |
+
"learning_rate": 3.513513513513514e-05,
|
172 |
+
"loss": 0.6036,
|
173 |
+
"step": 260
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 1.05,
|
177 |
+
"learning_rate": 3.648648648648649e-05,
|
178 |
+
"loss": 0.447,
|
179 |
+
"step": 270
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 1.05,
|
183 |
+
"learning_rate": 3.783783783783784e-05,
|
184 |
+
"loss": 0.4363,
|
185 |
+
"step": 280
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 1.06,
|
189 |
+
"learning_rate": 3.918918918918919e-05,
|
190 |
+
"loss": 0.472,
|
191 |
+
"step": 290
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 1.06,
|
195 |
+
"learning_rate": 4.0540540540540545e-05,
|
196 |
+
"loss": 0.3898,
|
197 |
+
"step": 300
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 1.07,
|
201 |
+
"learning_rate": 4.189189189189189e-05,
|
202 |
+
"loss": 0.3694,
|
203 |
+
"step": 310
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 1.07,
|
207 |
+
"learning_rate": 4.324324324324325e-05,
|
208 |
+
"loss": 0.5361,
|
209 |
+
"step": 320
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 1.08,
|
213 |
+
"learning_rate": 4.4594594594594596e-05,
|
214 |
+
"loss": 0.4282,
|
215 |
+
"step": 330
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 1.08,
|
219 |
+
"learning_rate": 4.594594594594595e-05,
|
220 |
+
"loss": 0.4951,
|
221 |
+
"step": 340
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 1.09,
|
225 |
+
"learning_rate": 4.72972972972973e-05,
|
226 |
+
"loss": 0.4869,
|
227 |
+
"step": 350
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 1.09,
|
231 |
+
"learning_rate": 4.8648648648648654e-05,
|
232 |
+
"loss": 0.5659,
|
233 |
+
"step": 360
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.1,
|
237 |
+
"learning_rate": 5e-05,
|
238 |
+
"loss": 0.5221,
|
239 |
+
"step": 370
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 1.1,
|
243 |
+
"eval_accuracy": 0.8191489361702128,
|
244 |
+
"eval_loss": 0.45883435010910034,
|
245 |
+
"eval_runtime": 177.7151,
|
246 |
+
"eval_samples_per_second": 1.058,
|
247 |
+
"eval_steps_per_second": 0.135,
|
248 |
+
"step": 372
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 2.0,
|
252 |
+
"learning_rate": 4.9662162162162164e-05,
|
253 |
+
"loss": 0.4096,
|
254 |
+
"step": 380
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 2.01,
|
258 |
+
"learning_rate": 4.9324324324324325e-05,
|
259 |
+
"loss": 0.2432,
|
260 |
+
"step": 390
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 2.02,
|
264 |
+
"learning_rate": 4.8986486486486486e-05,
|
265 |
+
"loss": 0.3223,
|
266 |
+
"step": 400
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 2.02,
|
270 |
+
"learning_rate": 4.8648648648648654e-05,
|
271 |
+
"loss": 0.2595,
|
272 |
+
"step": 410
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 2.03,
|
276 |
+
"learning_rate": 4.8310810810810816e-05,
|
277 |
+
"loss": 0.2677,
|
278 |
+
"step": 420
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 2.03,
|
282 |
+
"learning_rate": 4.797297297297298e-05,
|
283 |
+
"loss": 0.1923,
|
284 |
+
"step": 430
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 2.04,
|
288 |
+
"learning_rate": 4.763513513513514e-05,
|
289 |
+
"loss": 0.2242,
|
290 |
+
"step": 440
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 2.04,
|
294 |
+
"learning_rate": 4.72972972972973e-05,
|
295 |
+
"loss": 0.2813,
|
296 |
+
"step": 450
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 2.05,
|
300 |
+
"learning_rate": 4.695945945945946e-05,
|
301 |
+
"loss": 0.1839,
|
302 |
+
"step": 460
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 2.05,
|
306 |
+
"learning_rate": 4.662162162162162e-05,
|
307 |
+
"loss": 0.1759,
|
308 |
+
"step": 470
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 2.06,
|
312 |
+
"learning_rate": 4.628378378378378e-05,
|
313 |
+
"loss": 0.3216,
|
314 |
+
"step": 480
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 2.06,
|
318 |
+
"learning_rate": 4.594594594594595e-05,
|
319 |
+
"loss": 0.4189,
|
320 |
+
"step": 490
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 2.07,
|
324 |
+
"learning_rate": 4.560810810810811e-05,
|
325 |
+
"loss": 0.3461,
|
326 |
+
"step": 500
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 2.07,
|
330 |
+
"learning_rate": 4.5270270270270274e-05,
|
331 |
+
"loss": 0.3762,
|
332 |
+
"step": 510
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 2.08,
|
336 |
+
"learning_rate": 4.4932432432432435e-05,
|
337 |
+
"loss": 0.274,
|
338 |
+
"step": 520
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 2.09,
|
342 |
+
"learning_rate": 4.4594594594594596e-05,
|
343 |
+
"loss": 0.2273,
|
344 |
+
"step": 530
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 2.09,
|
348 |
+
"learning_rate": 4.425675675675676e-05,
|
349 |
+
"loss": 0.3088,
|
350 |
+
"step": 540
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 2.1,
|
354 |
+
"learning_rate": 4.391891891891892e-05,
|
355 |
+
"loss": 0.2842,
|
356 |
+
"step": 550
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 2.1,
|
360 |
+
"eval_accuracy": 0.7872340425531915,
|
361 |
+
"eval_loss": 0.7170040011405945,
|
362 |
+
"eval_runtime": 129.3008,
|
363 |
+
"eval_samples_per_second": 1.454,
|
364 |
+
"eval_steps_per_second": 0.186,
|
365 |
+
"step": 558
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 3.0,
|
369 |
+
"learning_rate": 4.358108108108108e-05,
|
370 |
+
"loss": 0.4734,
|
371 |
+
"step": 560
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 3.01,
|
375 |
+
"learning_rate": 4.324324324324325e-05,
|
376 |
+
"loss": 0.1211,
|
377 |
+
"step": 570
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 3.01,
|
381 |
+
"learning_rate": 4.290540540540541e-05,
|
382 |
+
"loss": 0.2635,
|
383 |
+
"step": 580
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 3.02,
|
387 |
+
"learning_rate": 4.256756756756757e-05,
|
388 |
+
"loss": 0.1709,
|
389 |
+
"step": 590
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 3.02,
|
393 |
+
"learning_rate": 4.222972972972973e-05,
|
394 |
+
"loss": 0.1331,
|
395 |
+
"step": 600
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 3.03,
|
399 |
+
"learning_rate": 4.189189189189189e-05,
|
400 |
+
"loss": 0.2039,
|
401 |
+
"step": 610
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 3.03,
|
405 |
+
"learning_rate": 4.1554054054054055e-05,
|
406 |
+
"loss": 0.1331,
|
407 |
+
"step": 620
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 3.04,
|
411 |
+
"learning_rate": 4.1216216216216216e-05,
|
412 |
+
"loss": 0.0862,
|
413 |
+
"step": 630
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 3.04,
|
417 |
+
"learning_rate": 4.087837837837838e-05,
|
418 |
+
"loss": 0.0994,
|
419 |
+
"step": 640
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 3.05,
|
423 |
+
"learning_rate": 4.0540540540540545e-05,
|
424 |
+
"loss": 0.0995,
|
425 |
+
"step": 650
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 3.06,
|
429 |
+
"learning_rate": 4.0202702702702707e-05,
|
430 |
+
"loss": 0.1932,
|
431 |
+
"step": 660
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 3.06,
|
435 |
+
"learning_rate": 3.986486486486487e-05,
|
436 |
+
"loss": 0.1393,
|
437 |
+
"step": 670
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 3.07,
|
441 |
+
"learning_rate": 3.952702702702703e-05,
|
442 |
+
"loss": 0.2566,
|
443 |
+
"step": 680
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 3.07,
|
447 |
+
"learning_rate": 3.918918918918919e-05,
|
448 |
+
"loss": 0.1237,
|
449 |
+
"step": 690
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 3.08,
|
453 |
+
"learning_rate": 3.885135135135135e-05,
|
454 |
+
"loss": 0.3312,
|
455 |
+
"step": 700
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 3.08,
|
459 |
+
"learning_rate": 3.851351351351351e-05,
|
460 |
+
"loss": 0.1597,
|
461 |
+
"step": 710
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 3.09,
|
465 |
+
"learning_rate": 3.8175675675675674e-05,
|
466 |
+
"loss": 0.2005,
|
467 |
+
"step": 720
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 3.09,
|
471 |
+
"learning_rate": 3.783783783783784e-05,
|
472 |
+
"loss": 0.1036,
|
473 |
+
"step": 730
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 3.1,
|
477 |
+
"learning_rate": 3.7500000000000003e-05,
|
478 |
+
"loss": 0.2556,
|
479 |
+
"step": 740
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 3.1,
|
483 |
+
"eval_accuracy": 0.8351063829787234,
|
484 |
+
"eval_loss": 0.5215957164764404,
|
485 |
+
"eval_runtime": 162.9032,
|
486 |
+
"eval_samples_per_second": 1.154,
|
487 |
+
"eval_steps_per_second": 0.147,
|
488 |
+
"step": 744
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 4.0,
|
492 |
+
"learning_rate": 3.7162162162162165e-05,
|
493 |
+
"loss": 0.0293,
|
494 |
+
"step": 750
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 4.01,
|
498 |
+
"learning_rate": 3.6824324324324326e-05,
|
499 |
+
"loss": 0.0963,
|
500 |
+
"step": 760
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 4.01,
|
504 |
+
"learning_rate": 3.648648648648649e-05,
|
505 |
+
"loss": 0.0378,
|
506 |
+
"step": 770
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 4.02,
|
510 |
+
"learning_rate": 3.6148648648648655e-05,
|
511 |
+
"loss": 0.0574,
|
512 |
+
"step": 780
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 4.02,
|
516 |
+
"learning_rate": 3.581081081081081e-05,
|
517 |
+
"loss": 0.0259,
|
518 |
+
"step": 790
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 4.03,
|
522 |
+
"learning_rate": 3.547297297297297e-05,
|
523 |
+
"loss": 0.1403,
|
524 |
+
"step": 800
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 4.04,
|
528 |
+
"learning_rate": 3.513513513513514e-05,
|
529 |
+
"loss": 0.0184,
|
530 |
+
"step": 810
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 4.04,
|
534 |
+
"learning_rate": 3.47972972972973e-05,
|
535 |
+
"loss": 0.18,
|
536 |
+
"step": 820
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 4.05,
|
540 |
+
"learning_rate": 3.445945945945946e-05,
|
541 |
+
"loss": 0.0206,
|
542 |
+
"step": 830
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 4.05,
|
546 |
+
"learning_rate": 3.412162162162162e-05,
|
547 |
+
"loss": 0.0274,
|
548 |
+
"step": 840
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 4.06,
|
552 |
+
"learning_rate": 3.3783783783783784e-05,
|
553 |
+
"loss": 0.0834,
|
554 |
+
"step": 850
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 4.06,
|
558 |
+
"learning_rate": 3.344594594594595e-05,
|
559 |
+
"loss": 0.1082,
|
560 |
+
"step": 860
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 4.07,
|
564 |
+
"learning_rate": 3.310810810810811e-05,
|
565 |
+
"loss": 0.0765,
|
566 |
+
"step": 870
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 4.07,
|
570 |
+
"learning_rate": 3.277027027027027e-05,
|
571 |
+
"loss": 0.0635,
|
572 |
+
"step": 880
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 4.08,
|
576 |
+
"learning_rate": 3.2432432432432436e-05,
|
577 |
+
"loss": 0.0918,
|
578 |
+
"step": 890
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 4.08,
|
582 |
+
"learning_rate": 3.20945945945946e-05,
|
583 |
+
"loss": 0.1317,
|
584 |
+
"step": 900
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 4.09,
|
588 |
+
"learning_rate": 3.175675675675676e-05,
|
589 |
+
"loss": 0.0651,
|
590 |
+
"step": 910
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 4.1,
|
594 |
+
"learning_rate": 3.141891891891892e-05,
|
595 |
+
"loss": 0.0477,
|
596 |
+
"step": 920
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 4.1,
|
600 |
+
"learning_rate": 3.108108108108108e-05,
|
601 |
+
"loss": 0.0356,
|
602 |
+
"step": 930
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 4.1,
|
606 |
+
"eval_accuracy": 0.7864583333333334,
|
607 |
+
"eval_loss": 0.8737158179283142,
|
608 |
+
"eval_runtime": 287.7784,
|
609 |
+
"eval_samples_per_second": 0.667,
|
610 |
+
"eval_steps_per_second": 0.083,
|
611 |
+
"step": 930
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 4.1,
|
615 |
+
"eval_accuracy": 0.7864583333333334,
|
616 |
+
"eval_loss": 0.8737158179283142,
|
617 |
+
"eval_runtime": 124.9385,
|
618 |
+
"eval_samples_per_second": 1.537,
|
619 |
+
"eval_steps_per_second": 0.192,
|
620 |
+
"step": 930
|
621 |
+
}
|
622 |
+
],
|
623 |
+
"max_steps": 1850,
|
624 |
+
"num_train_epochs": 9223372036854775807,
|
625 |
+
"total_flos": 9.227355150982349e+18,
|
626 |
+
"trial_name": null,
|
627 |
+
"trial_params": null
|
628 |
+
}
|