End of training
Browse files
all_results.json
CHANGED
@@ -1,8 +1,13 @@
|
|
1 |
{
|
2 |
"epoch": 1.94,
|
|
|
|
|
|
|
|
|
|
|
3 |
"total_flos": 8.866156938264576e+16,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second": 13.
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.94,
|
3 |
+
"eval_accuracy": 0.9659090909090909,
|
4 |
+
"eval_loss": 0.08971412479877472,
|
5 |
+
"eval_runtime": 1.6502,
|
6 |
+
"eval_samples_per_second": 53.328,
|
7 |
+
"eval_steps_per_second": 6.666,
|
8 |
"total_flos": 8.866156938264576e+16,
|
9 |
+
"train_loss": 0.16435068647842854,
|
10 |
+
"train_runtime": 116.6536,
|
11 |
+
"train_samples_per_second": 13.476,
|
12 |
+
"train_steps_per_second": 0.411
|
13 |
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.94,
|
3 |
+
"eval_accuracy": 0.9659090909090909,
|
4 |
+
"eval_loss": 0.08971412479877472,
|
5 |
+
"eval_runtime": 1.6502,
|
6 |
+
"eval_samples_per_second": 53.328,
|
7 |
+
"eval_steps_per_second": 6.666
|
8 |
+
}
|
runs/Jul31_02-11-10_4d8ae2de2193/events.out.tfevents.1690769648.4d8ae2de2193.4377.13
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7262d1183ec1467e8c7c8f0e3163849dd4454abfc151a376b96c891027df3ae0
|
3 |
+
size 405
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.94,
|
3 |
"total_flos": 8.866156938264576e+16,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second": 13.
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.94,
|
3 |
"total_flos": 8.866156938264576e+16,
|
4 |
+
"train_loss": 0.16435068647842854,
|
5 |
+
"train_runtime": 116.6536,
|
6 |
+
"train_samples_per_second": 13.476,
|
7 |
+
"train_steps_per_second": 0.411
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "focal-patacotron/checkpoint-48",
|
4 |
"epoch": 1.9393939393939394,
|
5 |
"global_step": 48,
|
@@ -10,173 +10,173 @@
|
|
10 |
{
|
11 |
"epoch": 0.08,
|
12 |
"learning_rate": 2e-05,
|
13 |
-
"loss": 0.
|
14 |
"step": 2
|
15 |
},
|
16 |
{
|
17 |
"epoch": 0.16,
|
18 |
"learning_rate": 4e-05,
|
19 |
-
"loss": 0.
|
20 |
"step": 4
|
21 |
},
|
22 |
{
|
23 |
"epoch": 0.24,
|
24 |
"learning_rate": 4.883720930232558e-05,
|
25 |
-
"loss": 0.
|
26 |
"step": 6
|
27 |
},
|
28 |
{
|
29 |
"epoch": 0.32,
|
30 |
"learning_rate": 4.651162790697675e-05,
|
31 |
-
"loss": 0.
|
32 |
"step": 8
|
33 |
},
|
34 |
{
|
35 |
"epoch": 0.4,
|
36 |
"learning_rate": 4.418604651162791e-05,
|
37 |
-
"loss": 0.
|
38 |
"step": 10
|
39 |
},
|
40 |
{
|
41 |
"epoch": 0.48,
|
42 |
"learning_rate": 4.186046511627907e-05,
|
43 |
-
"loss": 0.
|
44 |
"step": 12
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.57,
|
48 |
"learning_rate": 3.953488372093023e-05,
|
49 |
-
"loss": 0.
|
50 |
"step": 14
|
51 |
},
|
52 |
{
|
53 |
"epoch": 0.65,
|
54 |
"learning_rate": 3.7209302325581394e-05,
|
55 |
-
"loss": 0.
|
56 |
"step": 16
|
57 |
},
|
58 |
{
|
59 |
"epoch": 0.73,
|
60 |
"learning_rate": 3.488372093023256e-05,
|
61 |
-
"loss": 0.
|
62 |
"step": 18
|
63 |
},
|
64 |
{
|
65 |
"epoch": 0.81,
|
66 |
"learning_rate": 3.2558139534883724e-05,
|
67 |
-
"loss": 0.
|
68 |
"step": 20
|
69 |
},
|
70 |
{
|
71 |
"epoch": 0.89,
|
72 |
"learning_rate": 3.0232558139534883e-05,
|
73 |
-
"loss": 0.
|
74 |
"step": 22
|
75 |
},
|
76 |
{
|
77 |
"epoch": 0.97,
|
78 |
"learning_rate": 2.7906976744186048e-05,
|
79 |
-
"loss": 0.
|
80 |
"step": 24
|
81 |
},
|
82 |
{
|
83 |
"epoch": 0.97,
|
84 |
-
"eval_accuracy": 0.
|
85 |
-
"eval_loss": 0.
|
86 |
-
"eval_runtime": 1.
|
87 |
-
"eval_samples_per_second":
|
88 |
-
"eval_steps_per_second": 6.
|
89 |
"step": 24
|
90 |
},
|
91 |
{
|
92 |
"epoch": 1.05,
|
93 |
"learning_rate": 2.5581395348837212e-05,
|
94 |
-
"loss": 0.
|
95 |
"step": 26
|
96 |
},
|
97 |
{
|
98 |
"epoch": 1.13,
|
99 |
"learning_rate": 2.3255813953488374e-05,
|
100 |
-
"loss": 0.
|
101 |
"step": 28
|
102 |
},
|
103 |
{
|
104 |
"epoch": 1.21,
|
105 |
"learning_rate": 2.0930232558139536e-05,
|
106 |
-
"loss": 0.
|
107 |
"step": 30
|
108 |
},
|
109 |
{
|
110 |
"epoch": 1.29,
|
111 |
"learning_rate": 1.8604651162790697e-05,
|
112 |
-
"loss": 0.
|
113 |
"step": 32
|
114 |
},
|
115 |
{
|
116 |
"epoch": 1.37,
|
117 |
"learning_rate": 1.6279069767441862e-05,
|
118 |
-
"loss": 0.
|
119 |
"step": 34
|
120 |
},
|
121 |
{
|
122 |
"epoch": 1.45,
|
123 |
"learning_rate": 1.3953488372093024e-05,
|
124 |
-
"loss": 0.
|
125 |
"step": 36
|
126 |
},
|
127 |
{
|
128 |
"epoch": 1.54,
|
129 |
"learning_rate": 1.1627906976744187e-05,
|
130 |
-
"loss": 0.
|
131 |
"step": 38
|
132 |
},
|
133 |
{
|
134 |
"epoch": 1.62,
|
135 |
"learning_rate": 9.302325581395349e-06,
|
136 |
-
"loss": 0.
|
137 |
"step": 40
|
138 |
},
|
139 |
{
|
140 |
"epoch": 1.7,
|
141 |
"learning_rate": 6.976744186046512e-06,
|
142 |
-
"loss": 0.
|
143 |
"step": 42
|
144 |
},
|
145 |
{
|
146 |
"epoch": 1.78,
|
147 |
"learning_rate": 4.651162790697674e-06,
|
148 |
-
"loss": 0.
|
149 |
"step": 44
|
150 |
},
|
151 |
{
|
152 |
"epoch": 1.86,
|
153 |
"learning_rate": 2.325581395348837e-06,
|
154 |
-
"loss": 0.
|
155 |
"step": 46
|
156 |
},
|
157 |
{
|
158 |
"epoch": 1.94,
|
159 |
"learning_rate": 0.0,
|
160 |
-
"loss": 0.
|
161 |
"step": 48
|
162 |
},
|
163 |
{
|
164 |
"epoch": 1.94,
|
165 |
-
"eval_accuracy": 0.
|
166 |
-
"eval_loss": 0.
|
167 |
-
"eval_runtime": 1.
|
168 |
-
"eval_samples_per_second":
|
169 |
-
"eval_steps_per_second":
|
170 |
"step": 48
|
171 |
},
|
172 |
{
|
173 |
"epoch": 1.94,
|
174 |
"step": 48,
|
175 |
"total_flos": 8.866156938264576e+16,
|
176 |
-
"train_loss": 0.
|
177 |
-
"train_runtime":
|
178 |
-
"train_samples_per_second": 13.
|
179 |
-
"train_steps_per_second": 0.
|
180 |
}
|
181 |
],
|
182 |
"max_steps": 48,
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9659090909090909,
|
3 |
"best_model_checkpoint": "focal-patacotron/checkpoint-48",
|
4 |
"epoch": 1.9393939393939394,
|
5 |
"global_step": 48,
|
|
|
10 |
{
|
11 |
"epoch": 0.08,
|
12 |
"learning_rate": 2e-05,
|
13 |
+
"loss": 0.6836,
|
14 |
"step": 2
|
15 |
},
|
16 |
{
|
17 |
"epoch": 0.16,
|
18 |
"learning_rate": 4e-05,
|
19 |
+
"loss": 0.5915,
|
20 |
"step": 4
|
21 |
},
|
22 |
{
|
23 |
"epoch": 0.24,
|
24 |
"learning_rate": 4.883720930232558e-05,
|
25 |
+
"loss": 0.4642,
|
26 |
"step": 6
|
27 |
},
|
28 |
{
|
29 |
"epoch": 0.32,
|
30 |
"learning_rate": 4.651162790697675e-05,
|
31 |
+
"loss": 0.3705,
|
32 |
"step": 8
|
33 |
},
|
34 |
{
|
35 |
"epoch": 0.4,
|
36 |
"learning_rate": 4.418604651162791e-05,
|
37 |
+
"loss": 0.185,
|
38 |
"step": 10
|
39 |
},
|
40 |
{
|
41 |
"epoch": 0.48,
|
42 |
"learning_rate": 4.186046511627907e-05,
|
43 |
+
"loss": 0.1973,
|
44 |
"step": 12
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.57,
|
48 |
"learning_rate": 3.953488372093023e-05,
|
49 |
+
"loss": 0.1505,
|
50 |
"step": 14
|
51 |
},
|
52 |
{
|
53 |
"epoch": 0.65,
|
54 |
"learning_rate": 3.7209302325581394e-05,
|
55 |
+
"loss": 0.1137,
|
56 |
"step": 16
|
57 |
},
|
58 |
{
|
59 |
"epoch": 0.73,
|
60 |
"learning_rate": 3.488372093023256e-05,
|
61 |
+
"loss": 0.094,
|
62 |
"step": 18
|
63 |
},
|
64 |
{
|
65 |
"epoch": 0.81,
|
66 |
"learning_rate": 3.2558139534883724e-05,
|
67 |
+
"loss": 0.0736,
|
68 |
"step": 20
|
69 |
},
|
70 |
{
|
71 |
"epoch": 0.89,
|
72 |
"learning_rate": 3.0232558139534883e-05,
|
73 |
+
"loss": 0.0946,
|
74 |
"step": 22
|
75 |
},
|
76 |
{
|
77 |
"epoch": 0.97,
|
78 |
"learning_rate": 2.7906976744186048e-05,
|
79 |
+
"loss": 0.0575,
|
80 |
"step": 24
|
81 |
},
|
82 |
{
|
83 |
"epoch": 0.97,
|
84 |
+
"eval_accuracy": 0.9545454545454546,
|
85 |
+
"eval_loss": 0.12081997096538544,
|
86 |
+
"eval_runtime": 1.7666,
|
87 |
+
"eval_samples_per_second": 49.813,
|
88 |
+
"eval_steps_per_second": 6.227,
|
89 |
"step": 24
|
90 |
},
|
91 |
{
|
92 |
"epoch": 1.05,
|
93 |
"learning_rate": 2.5581395348837212e-05,
|
94 |
+
"loss": 0.0139,
|
95 |
"step": 26
|
96 |
},
|
97 |
{
|
98 |
"epoch": 1.13,
|
99 |
"learning_rate": 2.3255813953488374e-05,
|
100 |
+
"loss": 0.0574,
|
101 |
"step": 28
|
102 |
},
|
103 |
{
|
104 |
"epoch": 1.21,
|
105 |
"learning_rate": 2.0930232558139536e-05,
|
106 |
+
"loss": 0.1247,
|
107 |
"step": 30
|
108 |
},
|
109 |
{
|
110 |
"epoch": 1.29,
|
111 |
"learning_rate": 1.8604651162790697e-05,
|
112 |
+
"loss": 0.0401,
|
113 |
"step": 32
|
114 |
},
|
115 |
{
|
116 |
"epoch": 1.37,
|
117 |
"learning_rate": 1.6279069767441862e-05,
|
118 |
+
"loss": 0.2808,
|
119 |
"step": 34
|
120 |
},
|
121 |
{
|
122 |
"epoch": 1.45,
|
123 |
"learning_rate": 1.3953488372093024e-05,
|
124 |
+
"loss": 0.0545,
|
125 |
"step": 36
|
126 |
},
|
127 |
{
|
128 |
"epoch": 1.54,
|
129 |
"learning_rate": 1.1627906976744187e-05,
|
130 |
+
"loss": 0.0295,
|
131 |
"step": 38
|
132 |
},
|
133 |
{
|
134 |
"epoch": 1.62,
|
135 |
"learning_rate": 9.302325581395349e-06,
|
136 |
+
"loss": 0.0947,
|
137 |
"step": 40
|
138 |
},
|
139 |
{
|
140 |
"epoch": 1.7,
|
141 |
"learning_rate": 6.976744186046512e-06,
|
142 |
+
"loss": 0.0312,
|
143 |
"step": 42
|
144 |
},
|
145 |
{
|
146 |
"epoch": 1.78,
|
147 |
"learning_rate": 4.651162790697674e-06,
|
148 |
+
"loss": 0.1001,
|
149 |
"step": 44
|
150 |
},
|
151 |
{
|
152 |
"epoch": 1.86,
|
153 |
"learning_rate": 2.325581395348837e-06,
|
154 |
+
"loss": 0.014,
|
155 |
"step": 46
|
156 |
},
|
157 |
{
|
158 |
"epoch": 1.94,
|
159 |
"learning_rate": 0.0,
|
160 |
+
"loss": 0.0275,
|
161 |
"step": 48
|
162 |
},
|
163 |
{
|
164 |
"epoch": 1.94,
|
165 |
+
"eval_accuracy": 0.9659090909090909,
|
166 |
+
"eval_loss": 0.08971412479877472,
|
167 |
+
"eval_runtime": 1.8839,
|
168 |
+
"eval_samples_per_second": 46.711,
|
169 |
+
"eval_steps_per_second": 5.839,
|
170 |
"step": 48
|
171 |
},
|
172 |
{
|
173 |
"epoch": 1.94,
|
174 |
"step": 48,
|
175 |
"total_flos": 8.866156938264576e+16,
|
176 |
+
"train_loss": 0.16435068647842854,
|
177 |
+
"train_runtime": 116.6536,
|
178 |
+
"train_samples_per_second": 13.476,
|
179 |
+
"train_steps_per_second": 0.411
|
180 |
}
|
181 |
],
|
182 |
"max_steps": 48,
|