kurosekurose
commited on
Commit
•
042a41a
1
Parent(s):
a7912e5
End of training
Browse files- pytorch_model.bin +1 -1
- trainer_state.json +48 -198
- 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:ff1c9c2ac0a09226468f470b3c2c47f05fd7560f181670ba0bb401ca1f4c1659
|
3 |
size 379933779
|
trainer_state.json
CHANGED
@@ -1,250 +1,100 @@
|
|
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": 40.
|
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": 1.
|
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": 0.
|
44 |
"step": 123
|
45 |
},
|
46 |
{
|
47 |
"epoch": 2.98,
|
48 |
-
"eval_accuracy": 0.
|
49 |
-
"eval_loss":
|
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": 0.
|
59 |
"step": 164
|
60 |
},
|
61 |
{
|
62 |
"epoch": 3.98,
|
63 |
-
"eval_accuracy": 0.
|
64 |
-
"eval_loss":
|
65 |
-
"eval_runtime": 40.
|
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":
|
80 |
-
"eval_runtime":
|
81 |
-
"eval_samples_per_second": 1.
|
82 |
-
"eval_steps_per_second": 0.
|
83 |
"step": 205
|
84 |
},
|
85 |
{
|
86 |
-
"epoch":
|
87 |
-
"
|
88 |
-
"
|
89 |
-
"
|
90 |
-
|
91 |
-
|
92 |
-
"epoch": 5.98,
|
93 |
-
"eval_accuracy": 0.7200000286102295,
|
94 |
-
"eval_loss": 0.841139554977417,
|
95 |
-
"eval_runtime": 40.6422,
|
96 |
-
"eval_samples_per_second": 1.23,
|
97 |
-
"eval_steps_per_second": 0.32,
|
98 |
-
"step": 246
|
99 |
-
},
|
100 |
-
{
|
101 |
-
"epoch": 6.98,
|
102 |
-
"learning_rate": 5.349593495934959e-06,
|
103 |
-
"loss": 0.6743,
|
104 |
-
"step": 287
|
105 |
-
},
|
106 |
-
{
|
107 |
-
"epoch": 6.98,
|
108 |
-
"eval_accuracy": 0.6200000047683716,
|
109 |
-
"eval_loss": 0.960402250289917,
|
110 |
-
"eval_runtime": 40.4332,
|
111 |
-
"eval_samples_per_second": 1.237,
|
112 |
-
"eval_steps_per_second": 0.322,
|
113 |
-
"step": 287
|
114 |
-
},
|
115 |
-
{
|
116 |
-
"epoch": 7.98,
|
117 |
-
"learning_rate": 4.682926829268293e-06,
|
118 |
-
"loss": 0.5737,
|
119 |
-
"step": 328
|
120 |
-
},
|
121 |
-
{
|
122 |
-
"epoch": 7.98,
|
123 |
-
"eval_accuracy": 0.699999988079071,
|
124 |
-
"eval_loss": 0.847145676612854,
|
125 |
-
"eval_runtime": 40.2368,
|
126 |
-
"eval_samples_per_second": 1.243,
|
127 |
-
"eval_steps_per_second": 0.323,
|
128 |
-
"step": 328
|
129 |
-
},
|
130 |
-
{
|
131 |
-
"epoch": 8.98,
|
132 |
-
"learning_rate": 4.0162601626016264e-06,
|
133 |
-
"loss": 0.5269,
|
134 |
-
"step": 369
|
135 |
-
},
|
136 |
-
{
|
137 |
-
"epoch": 8.98,
|
138 |
-
"eval_accuracy": 0.6000000238418579,
|
139 |
-
"eval_loss": 1.058085560798645,
|
140 |
-
"eval_runtime": 40.5212,
|
141 |
-
"eval_samples_per_second": 1.234,
|
142 |
-
"eval_steps_per_second": 0.321,
|
143 |
-
"step": 369
|
144 |
-
},
|
145 |
-
{
|
146 |
-
"epoch": 9.98,
|
147 |
-
"learning_rate": 3.3495934959349595e-06,
|
148 |
-
"loss": 0.4671,
|
149 |
-
"step": 410
|
150 |
-
},
|
151 |
-
{
|
152 |
-
"epoch": 9.98,
|
153 |
-
"eval_accuracy": 0.6399999856948853,
|
154 |
-
"eval_loss": 1.0365118980407715,
|
155 |
-
"eval_runtime": 40.1443,
|
156 |
-
"eval_samples_per_second": 1.246,
|
157 |
-
"eval_steps_per_second": 0.324,
|
158 |
-
"step": 410
|
159 |
-
},
|
160 |
-
{
|
161 |
-
"epoch": 10.98,
|
162 |
-
"learning_rate": 2.682926829268293e-06,
|
163 |
-
"loss": 0.4227,
|
164 |
-
"step": 451
|
165 |
-
},
|
166 |
-
{
|
167 |
-
"epoch": 10.98,
|
168 |
-
"eval_accuracy": 0.6000000238418579,
|
169 |
-
"eval_loss": 1.099373459815979,
|
170 |
-
"eval_runtime": 40.7426,
|
171 |
-
"eval_samples_per_second": 1.227,
|
172 |
-
"eval_steps_per_second": 0.319,
|
173 |
-
"step": 451
|
174 |
-
},
|
175 |
-
{
|
176 |
-
"epoch": 11.98,
|
177 |
-
"learning_rate": 2.016260162601626e-06,
|
178 |
-
"loss": 0.3688,
|
179 |
-
"step": 492
|
180 |
-
},
|
181 |
-
{
|
182 |
-
"epoch": 11.98,
|
183 |
-
"eval_accuracy": 0.5799999833106995,
|
184 |
-
"eval_loss": 1.0964391231536865,
|
185 |
-
"eval_runtime": 40.5324,
|
186 |
-
"eval_samples_per_second": 1.234,
|
187 |
-
"eval_steps_per_second": 0.321,
|
188 |
-
"step": 492
|
189 |
-
},
|
190 |
-
{
|
191 |
-
"epoch": 12.98,
|
192 |
-
"learning_rate": 1.3495934959349594e-06,
|
193 |
-
"loss": 0.355,
|
194 |
-
"step": 533
|
195 |
-
},
|
196 |
-
{
|
197 |
-
"epoch": 12.98,
|
198 |
-
"eval_accuracy": 0.5799999833106995,
|
199 |
-
"eval_loss": 1.058560848236084,
|
200 |
-
"eval_runtime": 40.3075,
|
201 |
-
"eval_samples_per_second": 1.24,
|
202 |
-
"eval_steps_per_second": 0.323,
|
203 |
-
"step": 533
|
204 |
-
},
|
205 |
-
{
|
206 |
-
"epoch": 13.98,
|
207 |
-
"learning_rate": 6.829268292682928e-07,
|
208 |
-
"loss": 0.3232,
|
209 |
-
"step": 574
|
210 |
-
},
|
211 |
-
{
|
212 |
-
"epoch": 13.98,
|
213 |
-
"eval_accuracy": 0.6000000238418579,
|
214 |
-
"eval_loss": 1.041379451751709,
|
215 |
-
"eval_runtime": 40.2153,
|
216 |
-
"eval_samples_per_second": 1.243,
|
217 |
-
"eval_steps_per_second": 0.323,
|
218 |
-
"step": 574
|
219 |
-
},
|
220 |
-
{
|
221 |
-
"epoch": 14.98,
|
222 |
-
"learning_rate": 1.626016260162602e-08,
|
223 |
-
"loss": 0.3045,
|
224 |
-
"step": 615
|
225 |
-
},
|
226 |
-
{
|
227 |
-
"epoch": 14.98,
|
228 |
-
"eval_accuracy": 0.6200000047683716,
|
229 |
-
"eval_loss": 1.028589129447937,
|
230 |
-
"eval_runtime": 40.5756,
|
231 |
-
"eval_samples_per_second": 1.232,
|
232 |
-
"eval_steps_per_second": 0.32,
|
233 |
-
"step": 615
|
234 |
-
},
|
235 |
-
{
|
236 |
-
"epoch": 14.98,
|
237 |
-
"step": 615,
|
238 |
-
"total_flos": 4.289632004627067e+18,
|
239 |
-
"train_loss": 0.6339288587492656,
|
240 |
-
"train_runtime": 16994.3858,
|
241 |
-
"train_samples_per_second": 0.441,
|
242 |
"train_steps_per_second": 0.036
|
243 |
}
|
244 |
],
|
245 |
-
"max_steps":
|
246 |
-
"num_train_epochs":
|
247 |
-
"total_flos":
|
248 |
"trial_name": null,
|
249 |
"trial_params": null
|
250 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.0591806173324585,
|
3 |
+
"best_model_checkpoint": "kurosekurose/wav2vec2-base-EMOPIA/checkpoint-205",
|
4 |
+
"epoch": 4.984,
|
5 |
+
"global_step": 205,
|
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": 8.000000000000001e-06,
|
13 |
+
"loss": 1.2789,
|
14 |
"step": 41
|
15 |
},
|
16 |
{
|
17 |
"epoch": 0.98,
|
18 |
+
"eval_accuracy": 0.4000000059604645,
|
19 |
+
"eval_loss": 1.201923131942749,
|
20 |
+
"eval_runtime": 40.4421,
|
21 |
+
"eval_samples_per_second": 1.236,
|
22 |
+
"eval_steps_per_second": 0.321,
|
23 |
"step": 41
|
24 |
},
|
25 |
{
|
26 |
"epoch": 1.98,
|
27 |
+
"learning_rate": 6e-06,
|
28 |
+
"loss": 1.0522,
|
29 |
"step": 82
|
30 |
},
|
31 |
{
|
32 |
"epoch": 1.98,
|
33 |
+
"eval_accuracy": 0.4000000059604645,
|
34 |
+
"eval_loss": 1.1521090269088745,
|
35 |
+
"eval_runtime": 39.8895,
|
36 |
+
"eval_samples_per_second": 1.253,
|
37 |
+
"eval_steps_per_second": 0.326,
|
38 |
"step": 82
|
39 |
},
|
40 |
{
|
41 |
"epoch": 2.98,
|
42 |
+
"learning_rate": 4.000000000000001e-06,
|
43 |
+
"loss": 0.957,
|
44 |
"step": 123
|
45 |
},
|
46 |
{
|
47 |
"epoch": 2.98,
|
48 |
+
"eval_accuracy": 0.5199999809265137,
|
49 |
+
"eval_loss": 1.0672701597213745,
|
50 |
+
"eval_runtime": 40.1526,
|
51 |
+
"eval_samples_per_second": 1.245,
|
52 |
+
"eval_steps_per_second": 0.324,
|
53 |
"step": 123
|
54 |
},
|
55 |
{
|
56 |
"epoch": 3.98,
|
57 |
+
"learning_rate": 2.0000000000000003e-06,
|
58 |
+
"loss": 0.87,
|
59 |
"step": 164
|
60 |
},
|
61 |
{
|
62 |
"epoch": 3.98,
|
63 |
+
"eval_accuracy": 0.5,
|
64 |
+
"eval_loss": 1.09552001953125,
|
65 |
+
"eval_runtime": 40.1131,
|
66 |
+
"eval_samples_per_second": 1.246,
|
67 |
+
"eval_steps_per_second": 0.324,
|
68 |
"step": 164
|
69 |
},
|
70 |
{
|
71 |
"epoch": 4.98,
|
72 |
+
"learning_rate": 0.0,
|
73 |
+
"loss": 0.8053,
|
74 |
"step": 205
|
75 |
},
|
76 |
{
|
77 |
"epoch": 4.98,
|
78 |
+
"eval_accuracy": 0.5199999809265137,
|
79 |
+
"eval_loss": 1.0591806173324585,
|
80 |
+
"eval_runtime": 39.9652,
|
81 |
+
"eval_samples_per_second": 1.251,
|
82 |
+
"eval_steps_per_second": 0.325,
|
83 |
"step": 205
|
84 |
},
|
85 |
{
|
86 |
+
"epoch": 4.98,
|
87 |
+
"step": 205,
|
88 |
+
"total_flos": 1.4276872903849574e+18,
|
89 |
+
"train_loss": 0.992677939810404,
|
90 |
+
"train_runtime": 5632.3881,
|
91 |
+
"train_samples_per_second": 0.444,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
92 |
"train_steps_per_second": 0.036
|
93 |
}
|
94 |
],
|
95 |
+
"max_steps": 205,
|
96 |
+
"num_train_epochs": 5,
|
97 |
+
"total_flos": 1.4276872903849574e+18,
|
98 |
"trial_name": null,
|
99 |
"trial_params": null
|
100 |
}
|
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 sha256:9c1fa44bc78763d5540c7a35a8fda1d2b0ddc9ebf97518fe45dbeb21beb2a65c
|
3 |
size 3055
|