kurosekurose
commited on
Commit
•
87d357a
1
Parent(s):
1dbc534
End of training
Browse files- pytorch_model.bin +1 -1
- trainer_state.json +224 -89
- training_args.bin +1 -1
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 379933779
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e8848c4dbe8d243b8bcf33ca12e6a97243231e706d3728ac5cd04aefa7ba673
|
3 |
size 379933779
|
trainer_state.json
CHANGED
@@ -1,190 +1,325 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint": "kurosekurose/wav2vec2-base-EMOPIA/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": 0.98,
|
12 |
-
"learning_rate":
|
13 |
-
"loss": 1.
|
14 |
"step": 41
|
15 |
},
|
16 |
{
|
17 |
"epoch": 0.98,
|
18 |
-
"eval_accuracy": 0.
|
19 |
-
"eval_loss": 1.
|
20 |
-
"eval_runtime":
|
21 |
-
"eval_samples_per_second": 1.
|
22 |
-
"eval_steps_per_second": 0.
|
23 |
"step": 41
|
24 |
},
|
25 |
{
|
26 |
"epoch": 1.98,
|
27 |
-
"learning_rate":
|
28 |
-
"loss":
|
29 |
"step": 82
|
30 |
},
|
31 |
{
|
32 |
"epoch": 1.98,
|
33 |
-
"eval_accuracy": 0.
|
34 |
-
"eval_loss": 1.
|
35 |
-
"eval_runtime":
|
36 |
-
"eval_samples_per_second": 1.
|
37 |
-
"eval_steps_per_second": 0.
|
38 |
"step": 82
|
39 |
},
|
40 |
{
|
41 |
"epoch": 2.98,
|
42 |
-
"learning_rate":
|
43 |
-
"loss":
|
44 |
"step": 123
|
45 |
},
|
46 |
{
|
47 |
"epoch": 2.98,
|
48 |
-
"eval_accuracy": 0.
|
49 |
-
"eval_loss": 1.
|
50 |
-
"eval_runtime":
|
51 |
-
"eval_samples_per_second": 1.
|
52 |
-
"eval_steps_per_second": 0.
|
53 |
"step": 123
|
54 |
},
|
55 |
{
|
56 |
"epoch": 3.98,
|
57 |
-
"learning_rate":
|
58 |
-
"loss":
|
59 |
"step": 164
|
60 |
},
|
61 |
{
|
62 |
"epoch": 3.98,
|
63 |
-
"eval_accuracy": 0.
|
64 |
-
"eval_loss": 1.
|
65 |
-
"eval_runtime":
|
66 |
-
"eval_samples_per_second": 1.
|
67 |
-
"eval_steps_per_second": 0.
|
68 |
"step": 164
|
69 |
},
|
70 |
{
|
71 |
"epoch": 4.98,
|
72 |
-
"learning_rate":
|
73 |
-
"loss": 0.
|
74 |
"step": 205
|
75 |
},
|
76 |
{
|
77 |
"epoch": 4.98,
|
78 |
-
"eval_accuracy": 0.
|
79 |
-
"eval_loss": 1.
|
80 |
-
"eval_runtime":
|
81 |
-
"eval_samples_per_second": 1.
|
82 |
-
"eval_steps_per_second": 0.
|
83 |
"step": 205
|
84 |
},
|
85 |
{
|
86 |
"epoch": 5.98,
|
87 |
-
"learning_rate":
|
88 |
-
"loss": 0.
|
89 |
"step": 246
|
90 |
},
|
91 |
{
|
92 |
"epoch": 5.98,
|
93 |
-
"eval_accuracy": 0.
|
94 |
-
"eval_loss": 1.
|
95 |
-
"eval_runtime":
|
96 |
-
"eval_samples_per_second": 1.
|
97 |
-
"eval_steps_per_second": 0.
|
98 |
"step": 246
|
99 |
},
|
100 |
{
|
101 |
"epoch": 6.98,
|
102 |
-
"learning_rate":
|
103 |
-
"loss": 0.
|
104 |
"step": 287
|
105 |
},
|
106 |
{
|
107 |
"epoch": 6.98,
|
108 |
-
"eval_accuracy": 0.
|
109 |
-
"eval_loss":
|
110 |
-
"eval_runtime":
|
111 |
-
"eval_samples_per_second": 1.
|
112 |
-
"eval_steps_per_second": 0.
|
113 |
"step": 287
|
114 |
},
|
115 |
{
|
116 |
"epoch": 7.98,
|
117 |
-
"learning_rate":
|
118 |
-
"loss": 0.
|
119 |
"step": 328
|
120 |
},
|
121 |
{
|
122 |
"epoch": 7.98,
|
123 |
"eval_accuracy": 0.6000000238418579,
|
124 |
-
"eval_loss":
|
125 |
-
"eval_runtime":
|
126 |
-
"eval_samples_per_second": 1.
|
127 |
-
"eval_steps_per_second": 0.
|
128 |
"step": 328
|
129 |
},
|
130 |
{
|
131 |
"epoch": 8.98,
|
132 |
-
"learning_rate":
|
133 |
-
"loss": 0.
|
134 |
"step": 369
|
135 |
},
|
136 |
{
|
137 |
"epoch": 8.98,
|
138 |
-
"eval_accuracy": 0.
|
139 |
-
"eval_loss": 1.
|
140 |
-
"eval_runtime":
|
141 |
-
"eval_samples_per_second": 1.
|
142 |
-
"eval_steps_per_second": 0.
|
143 |
"step": 369
|
144 |
},
|
145 |
{
|
146 |
"epoch": 9.98,
|
147 |
-
"learning_rate":
|
148 |
-
"loss": 0.
|
149 |
"step": 410
|
150 |
},
|
151 |
{
|
152 |
"epoch": 9.98,
|
153 |
"eval_accuracy": 0.6399999856948853,
|
154 |
-
"eval_loss":
|
155 |
-
"eval_runtime":
|
156 |
-
"eval_samples_per_second": 1.
|
157 |
-
"eval_steps_per_second": 0.
|
158 |
"step": 410
|
159 |
},
|
160 |
{
|
161 |
"epoch": 10.98,
|
162 |
-
"learning_rate":
|
163 |
-
"loss": 0.
|
164 |
"step": 451
|
165 |
},
|
166 |
{
|
167 |
"epoch": 10.98,
|
168 |
-
"eval_accuracy": 0.
|
169 |
-
"eval_loss": 1.
|
170 |
-
"eval_runtime":
|
171 |
-
"eval_samples_per_second": 1.
|
172 |
-
"eval_steps_per_second": 0.
|
173 |
"step": 451
|
174 |
},
|
175 |
{
|
176 |
-
"epoch":
|
177 |
-
"
|
178 |
-
"
|
179 |
-
"
|
180 |
-
|
181 |
-
|
182 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
183 |
}
|
184 |
],
|
185 |
-
"max_steps":
|
186 |
-
"num_train_epochs":
|
187 |
-
"total_flos":
|
188 |
"trial_name": null,
|
189 |
"trial_params": null
|
190 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9141282439231873,
|
3 |
+
"best_model_checkpoint": "kurosekurose/wav2vec2-base-EMOPIA/checkpoint-410",
|
4 |
+
"epoch": 19.984,
|
5 |
+
"global_step": 820,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
"epoch": 0.98,
|
12 |
+
"learning_rate": 1.3666666666666668e-06,
|
13 |
+
"loss": 1.4068,
|
14 |
"step": 41
|
15 |
},
|
16 |
{
|
17 |
"epoch": 0.98,
|
18 |
+
"eval_accuracy": 0.30000001192092896,
|
19 |
+
"eval_loss": 1.370680570602417,
|
20 |
+
"eval_runtime": 40.3938,
|
21 |
+
"eval_samples_per_second": 1.238,
|
22 |
+
"eval_steps_per_second": 0.322,
|
23 |
"step": 41
|
24 |
},
|
25 |
{
|
26 |
"epoch": 1.98,
|
27 |
+
"learning_rate": 2.7333333333333336e-06,
|
28 |
+
"loss": 1.3568,
|
29 |
"step": 82
|
30 |
},
|
31 |
{
|
32 |
"epoch": 1.98,
|
33 |
+
"eval_accuracy": 0.3199999928474426,
|
34 |
+
"eval_loss": 1.3092886209487915,
|
35 |
+
"eval_runtime": 40.4466,
|
36 |
+
"eval_samples_per_second": 1.236,
|
37 |
+
"eval_steps_per_second": 0.321,
|
38 |
"step": 82
|
39 |
},
|
40 |
{
|
41 |
"epoch": 2.98,
|
42 |
+
"learning_rate": 4.1e-06,
|
43 |
+
"loss": 1.2503,
|
44 |
"step": 123
|
45 |
},
|
46 |
{
|
47 |
"epoch": 2.98,
|
48 |
+
"eval_accuracy": 0.46000000834465027,
|
49 |
+
"eval_loss": 1.178250789642334,
|
50 |
+
"eval_runtime": 40.4213,
|
51 |
+
"eval_samples_per_second": 1.237,
|
52 |
+
"eval_steps_per_second": 0.322,
|
53 |
"step": 123
|
54 |
},
|
55 |
{
|
56 |
"epoch": 3.98,
|
57 |
+
"learning_rate": 5.466666666666667e-06,
|
58 |
+
"loss": 1.1088,
|
59 |
"step": 164
|
60 |
},
|
61 |
{
|
62 |
"epoch": 3.98,
|
63 |
+
"eval_accuracy": 0.41999998688697815,
|
64 |
+
"eval_loss": 1.16064453125,
|
65 |
+
"eval_runtime": 40.5701,
|
66 |
+
"eval_samples_per_second": 1.232,
|
67 |
+
"eval_steps_per_second": 0.32,
|
68 |
"step": 164
|
69 |
},
|
70 |
{
|
71 |
"epoch": 4.98,
|
72 |
+
"learning_rate": 6.833333333333334e-06,
|
73 |
+
"loss": 0.9996,
|
74 |
"step": 205
|
75 |
},
|
76 |
{
|
77 |
"epoch": 4.98,
|
78 |
+
"eval_accuracy": 0.5400000214576721,
|
79 |
+
"eval_loss": 1.027118444442749,
|
80 |
+
"eval_runtime": 40.2938,
|
81 |
+
"eval_samples_per_second": 1.241,
|
82 |
+
"eval_steps_per_second": 0.323,
|
83 |
"step": 205
|
84 |
},
|
85 |
{
|
86 |
"epoch": 5.98,
|
87 |
+
"learning_rate": 8.2e-06,
|
88 |
+
"loss": 0.924,
|
89 |
"step": 246
|
90 |
},
|
91 |
{
|
92 |
"epoch": 5.98,
|
93 |
+
"eval_accuracy": 0.5799999833106995,
|
94 |
+
"eval_loss": 1.009319543838501,
|
95 |
+
"eval_runtime": 40.7551,
|
96 |
+
"eval_samples_per_second": 1.227,
|
97 |
+
"eval_steps_per_second": 0.319,
|
98 |
"step": 246
|
99 |
},
|
100 |
{
|
101 |
"epoch": 6.98,
|
102 |
+
"learning_rate": 9.566666666666668e-06,
|
103 |
+
"loss": 0.8449,
|
104 |
"step": 287
|
105 |
},
|
106 |
{
|
107 |
"epoch": 6.98,
|
108 |
+
"eval_accuracy": 0.5799999833106995,
|
109 |
+
"eval_loss": 0.961348295211792,
|
110 |
+
"eval_runtime": 40.5666,
|
111 |
+
"eval_samples_per_second": 1.233,
|
112 |
+
"eval_steps_per_second": 0.32,
|
113 |
"step": 287
|
114 |
},
|
115 |
{
|
116 |
"epoch": 7.98,
|
117 |
+
"learning_rate": 9.461538461538463e-06,
|
118 |
+
"loss": 0.7559,
|
119 |
"step": 328
|
120 |
},
|
121 |
{
|
122 |
"epoch": 7.98,
|
123 |
"eval_accuracy": 0.6000000238418579,
|
124 |
+
"eval_loss": 0.937028169631958,
|
125 |
+
"eval_runtime": 40.5792,
|
126 |
+
"eval_samples_per_second": 1.232,
|
127 |
+
"eval_steps_per_second": 0.32,
|
128 |
"step": 328
|
129 |
},
|
130 |
{
|
131 |
"epoch": 8.98,
|
132 |
+
"learning_rate": 8.673076923076924e-06,
|
133 |
+
"loss": 0.7744,
|
134 |
"step": 369
|
135 |
},
|
136 |
{
|
137 |
"epoch": 8.98,
|
138 |
+
"eval_accuracy": 0.5600000023841858,
|
139 |
+
"eval_loss": 1.0094345808029175,
|
140 |
+
"eval_runtime": 40.4365,
|
141 |
+
"eval_samples_per_second": 1.237,
|
142 |
+
"eval_steps_per_second": 0.321,
|
143 |
"step": 369
|
144 |
},
|
145 |
{
|
146 |
"epoch": 9.98,
|
147 |
+
"learning_rate": 7.884615384615384e-06,
|
148 |
+
"loss": 0.6745,
|
149 |
"step": 410
|
150 |
},
|
151 |
{
|
152 |
"epoch": 9.98,
|
153 |
"eval_accuracy": 0.6399999856948853,
|
154 |
+
"eval_loss": 0.9141282439231873,
|
155 |
+
"eval_runtime": 40.471,
|
156 |
+
"eval_samples_per_second": 1.235,
|
157 |
+
"eval_steps_per_second": 0.321,
|
158 |
"step": 410
|
159 |
},
|
160 |
{
|
161 |
"epoch": 10.98,
|
162 |
+
"learning_rate": 7.096153846153847e-06,
|
163 |
+
"loss": 0.6245,
|
164 |
"step": 451
|
165 |
},
|
166 |
{
|
167 |
"epoch": 10.98,
|
168 |
+
"eval_accuracy": 0.5,
|
169 |
+
"eval_loss": 1.1951998472213745,
|
170 |
+
"eval_runtime": 40.6687,
|
171 |
+
"eval_samples_per_second": 1.229,
|
172 |
+
"eval_steps_per_second": 0.32,
|
173 |
"step": 451
|
174 |
},
|
175 |
{
|
176 |
+
"epoch": 11.98,
|
177 |
+
"learning_rate": 6.307692307692308e-06,
|
178 |
+
"loss": 0.5174,
|
179 |
+
"step": 492
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 11.98,
|
183 |
+
"eval_accuracy": 0.6600000262260437,
|
184 |
+
"eval_loss": 0.9249220490455627,
|
185 |
+
"eval_runtime": 40.488,
|
186 |
+
"eval_samples_per_second": 1.235,
|
187 |
+
"eval_steps_per_second": 0.321,
|
188 |
+
"step": 492
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 12.98,
|
192 |
+
"learning_rate": 5.5192307692307705e-06,
|
193 |
+
"loss": 0.5091,
|
194 |
+
"step": 533
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 12.98,
|
198 |
+
"eval_accuracy": 0.7200000286102295,
|
199 |
+
"eval_loss": 0.9292579293251038,
|
200 |
+
"eval_runtime": 40.6346,
|
201 |
+
"eval_samples_per_second": 1.23,
|
202 |
+
"eval_steps_per_second": 0.32,
|
203 |
+
"step": 533
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 13.98,
|
207 |
+
"learning_rate": 4.730769230769231e-06,
|
208 |
+
"loss": 0.391,
|
209 |
+
"step": 574
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 13.98,
|
213 |
+
"eval_accuracy": 0.6600000262260437,
|
214 |
+
"eval_loss": 0.9355679750442505,
|
215 |
+
"eval_runtime": 40.4106,
|
216 |
+
"eval_samples_per_second": 1.237,
|
217 |
+
"eval_steps_per_second": 0.322,
|
218 |
+
"step": 574
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 14.98,
|
222 |
+
"learning_rate": 3.961538461538462e-06,
|
223 |
+
"loss": 0.3689,
|
224 |
+
"step": 615
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 14.98,
|
228 |
+
"eval_accuracy": 0.6200000047683716,
|
229 |
+
"eval_loss": 1.0244715213775635,
|
230 |
+
"eval_runtime": 40.302,
|
231 |
+
"eval_samples_per_second": 1.241,
|
232 |
+
"eval_steps_per_second": 0.323,
|
233 |
+
"step": 615
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 15.98,
|
237 |
+
"learning_rate": 3.1730769230769233e-06,
|
238 |
+
"loss": 0.2816,
|
239 |
+
"step": 656
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 15.98,
|
243 |
+
"eval_accuracy": 0.6600000262260437,
|
244 |
+
"eval_loss": 1.0420873165130615,
|
245 |
+
"eval_runtime": 40.6297,
|
246 |
+
"eval_samples_per_second": 1.231,
|
247 |
+
"eval_steps_per_second": 0.32,
|
248 |
+
"step": 656
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 16.98,
|
252 |
+
"learning_rate": 2.384615384615385e-06,
|
253 |
+
"loss": 0.3003,
|
254 |
+
"step": 697
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 16.98,
|
258 |
+
"eval_accuracy": 0.6399999856948853,
|
259 |
+
"eval_loss": 1.042699933052063,
|
260 |
+
"eval_runtime": 40.2488,
|
261 |
+
"eval_samples_per_second": 1.242,
|
262 |
+
"eval_steps_per_second": 0.323,
|
263 |
+
"step": 697
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 17.98,
|
267 |
+
"learning_rate": 1.596153846153846e-06,
|
268 |
+
"loss": 0.2495,
|
269 |
+
"step": 738
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 17.98,
|
273 |
+
"eval_accuracy": 0.6600000262260437,
|
274 |
+
"eval_loss": 1.095711350440979,
|
275 |
+
"eval_runtime": 40.5759,
|
276 |
+
"eval_samples_per_second": 1.232,
|
277 |
+
"eval_steps_per_second": 0.32,
|
278 |
+
"step": 738
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 18.98,
|
282 |
+
"learning_rate": 8.076923076923078e-07,
|
283 |
+
"loss": 0.2269,
|
284 |
+
"step": 779
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 18.98,
|
288 |
+
"eval_accuracy": 0.6600000262260437,
|
289 |
+
"eval_loss": 1.05389404296875,
|
290 |
+
"eval_runtime": 40.5913,
|
291 |
+
"eval_samples_per_second": 1.232,
|
292 |
+
"eval_steps_per_second": 0.32,
|
293 |
+
"step": 779
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 19.98,
|
297 |
+
"learning_rate": 1.9230769230769234e-08,
|
298 |
+
"loss": 0.2055,
|
299 |
+
"step": 820
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 19.98,
|
303 |
+
"eval_accuracy": 0.6800000071525574,
|
304 |
+
"eval_loss": 1.062558650970459,
|
305 |
+
"eval_runtime": 40.7382,
|
306 |
+
"eval_samples_per_second": 1.227,
|
307 |
+
"eval_steps_per_second": 0.319,
|
308 |
+
"step": 820
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 19.98,
|
312 |
+
"step": 820,
|
313 |
+
"total_flos": 5.721848459887288e+18,
|
314 |
+
"train_loss": 0.6885371266341791,
|
315 |
+
"train_runtime": 22708.6522,
|
316 |
+
"train_samples_per_second": 0.44,
|
317 |
+
"train_steps_per_second": 0.036
|
318 |
}
|
319 |
],
|
320 |
+
"max_steps": 820,
|
321 |
+
"num_train_epochs": 20,
|
322 |
+
"total_flos": 5.721848459887288e+18,
|
323 |
"trial_name": null,
|
324 |
"trial_params": null
|
325 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3055
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ccf48c4a0d78c84d927241619accb6e146ed3470c5f78ef19ec300caa18ccaa
|
3 |
size 3055
|