kurosekurose
commited on
Commit
•
a546753
1
Parent(s):
a44511e
End of training
Browse files- pytorch_model.bin +1 -1
- trainer_state.json +139 -49
- 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 sha256:75add040323f286a5f487f8dee6385994c459945b3e78b3a1c4b144bc3fd6f70
|
3 |
size 379933779
|
trainer_state.json
CHANGED
@@ -1,100 +1,190 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
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": 8.
|
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": 0.
|
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": 0.
|
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":
|
87 |
-
"
|
88 |
-
"
|
89 |
-
"
|
90 |
-
|
91 |
-
|
92 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
93 |
}
|
94 |
],
|
95 |
-
"max_steps":
|
96 |
-
"num_train_epochs":
|
97 |
-
"total_flos":
|
98 |
"trial_name": null,
|
99 |
"trial_params": null
|
100 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.00103759765625,
|
3 |
+
"best_model_checkpoint": "kurosekurose/wav2vec2-base-EMOPIA/checkpoint-328",
|
4 |
+
"epoch": 10.984,
|
5 |
+
"global_step": 451,
|
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": 8.2e-05,
|
13 |
+
"loss": 1.1756,
|
14 |
"step": 41
|
15 |
},
|
16 |
{
|
17 |
"epoch": 0.98,
|
18 |
+
"eval_accuracy": 0.47999998927116394,
|
19 |
+
"eval_loss": 1.1352914571762085,
|
20 |
+
"eval_runtime": 38.9611,
|
21 |
+
"eval_samples_per_second": 1.283,
|
22 |
+
"eval_steps_per_second": 0.334,
|
23 |
"step": 41
|
24 |
},
|
25 |
{
|
26 |
"epoch": 1.98,
|
27 |
+
"learning_rate": 9.433628318584072e-05,
|
28 |
+
"loss": 0.9701,
|
29 |
"step": 82
|
30 |
},
|
31 |
{
|
32 |
"epoch": 1.98,
|
33 |
+
"eval_accuracy": 0.3799999952316284,
|
34 |
+
"eval_loss": 1.316631555557251,
|
35 |
+
"eval_runtime": 38.9776,
|
36 |
+
"eval_samples_per_second": 1.283,
|
37 |
+
"eval_steps_per_second": 0.334,
|
38 |
"step": 82
|
39 |
},
|
40 |
{
|
41 |
"epoch": 2.98,
|
42 |
+
"learning_rate": 8.725663716814159e-05,
|
43 |
+
"loss": 0.9071,
|
44 |
"step": 123
|
45 |
},
|
46 |
{
|
47 |
"epoch": 2.98,
|
48 |
+
"eval_accuracy": 0.5799999833106995,
|
49 |
+
"eval_loss": 1.0715261697769165,
|
50 |
+
"eval_runtime": 38.7598,
|
51 |
+
"eval_samples_per_second": 1.29,
|
52 |
+
"eval_steps_per_second": 0.335,
|
53 |
"step": 123
|
54 |
},
|
55 |
{
|
56 |
"epoch": 3.98,
|
57 |
+
"learning_rate": 8e-05,
|
58 |
+
"loss": 0.824,
|
59 |
"step": 164
|
60 |
},
|
61 |
{
|
62 |
"epoch": 3.98,
|
63 |
+
"eval_accuracy": 0.5400000214576721,
|
64 |
+
"eval_loss": 1.0068312883377075,
|
65 |
+
"eval_runtime": 39.0309,
|
66 |
+
"eval_samples_per_second": 1.281,
|
67 |
+
"eval_steps_per_second": 0.333,
|
68 |
"step": 164
|
69 |
},
|
70 |
{
|
71 |
"epoch": 4.98,
|
72 |
+
"learning_rate": 7.274336283185841e-05,
|
73 |
+
"loss": 0.792,
|
74 |
"step": 205
|
75 |
},
|
76 |
{
|
77 |
"epoch": 4.98,
|
78 |
+
"eval_accuracy": 0.5799999833106995,
|
79 |
+
"eval_loss": 1.12873375415802,
|
80 |
+
"eval_runtime": 38.9511,
|
81 |
+
"eval_samples_per_second": 1.284,
|
82 |
+
"eval_steps_per_second": 0.334,
|
83 |
"step": 205
|
84 |
},
|
85 |
{
|
86 |
+
"epoch": 5.98,
|
87 |
+
"learning_rate": 6.548672566371682e-05,
|
88 |
+
"loss": 0.766,
|
89 |
+
"step": 246
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 5.98,
|
93 |
+
"eval_accuracy": 0.6000000238418579,
|
94 |
+
"eval_loss": 1.004433274269104,
|
95 |
+
"eval_runtime": 39.052,
|
96 |
+
"eval_samples_per_second": 1.28,
|
97 |
+
"eval_steps_per_second": 0.333,
|
98 |
+
"step": 246
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 6.98,
|
102 |
+
"learning_rate": 5.823008849557522e-05,
|
103 |
+
"loss": 0.6868,
|
104 |
+
"step": 287
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 6.98,
|
108 |
+
"eval_accuracy": 0.47999998927116394,
|
109 |
+
"eval_loss": 1.3310095071792603,
|
110 |
+
"eval_runtime": 39.0925,
|
111 |
+
"eval_samples_per_second": 1.279,
|
112 |
+
"eval_steps_per_second": 0.333,
|
113 |
+
"step": 287
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 7.98,
|
117 |
+
"learning_rate": 5.097345132743363e-05,
|
118 |
+
"loss": 0.5697,
|
119 |
+
"step": 328
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 7.98,
|
123 |
+
"eval_accuracy": 0.6000000238418579,
|
124 |
+
"eval_loss": 1.00103759765625,
|
125 |
+
"eval_runtime": 39.0178,
|
126 |
+
"eval_samples_per_second": 1.281,
|
127 |
+
"eval_steps_per_second": 0.333,
|
128 |
+
"step": 328
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 8.98,
|
132 |
+
"learning_rate": 4.371681415929203e-05,
|
133 |
+
"loss": 0.5018,
|
134 |
+
"step": 369
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 8.98,
|
138 |
+
"eval_accuracy": 0.6200000047683716,
|
139 |
+
"eval_loss": 1.2707340717315674,
|
140 |
+
"eval_runtime": 38.9236,
|
141 |
+
"eval_samples_per_second": 1.285,
|
142 |
+
"eval_steps_per_second": 0.334,
|
143 |
+
"step": 369
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 9.98,
|
147 |
+
"learning_rate": 3.646017699115045e-05,
|
148 |
+
"loss": 0.4066,
|
149 |
+
"step": 410
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 9.98,
|
153 |
+
"eval_accuracy": 0.6399999856948853,
|
154 |
+
"eval_loss": 1.0768933296203613,
|
155 |
+
"eval_runtime": 39.038,
|
156 |
+
"eval_samples_per_second": 1.281,
|
157 |
+
"eval_steps_per_second": 0.333,
|
158 |
+
"step": 410
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 10.98,
|
162 |
+
"learning_rate": 2.9203539823008852e-05,
|
163 |
+
"loss": 0.3536,
|
164 |
+
"step": 451
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 10.98,
|
168 |
+
"eval_accuracy": 0.5400000214576721,
|
169 |
+
"eval_loss": 1.5523918867111206,
|
170 |
+
"eval_runtime": 38.8373,
|
171 |
+
"eval_samples_per_second": 1.287,
|
172 |
+
"eval_steps_per_second": 0.335,
|
173 |
+
"step": 451
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 10.98,
|
177 |
+
"step": 451,
|
178 |
+
"total_flos": 3.1483778529632256e+18,
|
179 |
+
"train_loss": 0.723032221825847,
|
180 |
+
"train_runtime": 12293.1978,
|
181 |
+
"train_samples_per_second": 0.61,
|
182 |
+
"train_steps_per_second": 0.05
|
183 |
}
|
184 |
],
|
185 |
+
"max_steps": 615,
|
186 |
+
"num_train_epochs": 15,
|
187 |
+
"total_flos": 3.1483778529632256e+18,
|
188 |
"trial_name": null,
|
189 |
"trial_params": null
|
190 |
}
|
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 sha256:77de735cd6b55073fc5ab87db28cef98a20c15253a704c429229dac427654822
|
3 |
size 3055
|