End of training
Browse files- all_results.json +12 -12
- eval_results.json +7 -7
- train_results.json +6 -6
- trainer_state.json +91 -154
all_results.json
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_loss":
|
4 |
-
"eval_runtime":
|
5 |
-
"eval_samples":
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second":
|
8 |
-
"eval_wer":
|
9 |
-
"train_loss":
|
10 |
-
"train_runtime":
|
11 |
-
"train_samples":
|
12 |
-
"train_samples_per_second":
|
13 |
-
"train_steps_per_second": 0.
|
14 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_loss": 2.67260479927063,
|
4 |
+
"eval_runtime": 163.5078,
|
5 |
+
"eval_samples": 3659,
|
6 |
+
"eval_samples_per_second": 22.378,
|
7 |
+
"eval_steps_per_second": 1.401,
|
8 |
+
"eval_wer": 0.9814612868047983,
|
9 |
+
"train_loss": 14.438921352032104,
|
10 |
+
"train_runtime": 7245.592,
|
11 |
+
"train_samples": 11686,
|
12 |
+
"train_samples_per_second": 16.128,
|
13 |
+
"train_steps_per_second": 0.253
|
14 |
}
|
eval_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_loss":
|
4 |
-
"eval_runtime":
|
5 |
-
"eval_samples":
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second":
|
8 |
-
"eval_wer":
|
9 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_loss": 2.67260479927063,
|
4 |
+
"eval_runtime": 163.5078,
|
5 |
+
"eval_samples": 3659,
|
6 |
+
"eval_samples_per_second": 22.378,
|
7 |
+
"eval_steps_per_second": 1.401,
|
8 |
+
"eval_wer": 0.9814612868047983
|
9 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"train_loss":
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"train_loss": 14.438921352032104,
|
4 |
+
"train_runtime": 7245.592,
|
5 |
+
"train_samples": 11686,
|
6 |
+
"train_samples_per_second": 16.128,
|
7 |
+
"train_steps_per_second": 0.253
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,196 +1,133 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
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
|
12 |
-
"eval_loss":
|
13 |
-
"eval_runtime":
|
14 |
-
"eval_samples_per_second": 19.
|
15 |
-
"eval_steps_per_second":
|
16 |
-
"eval_wer": 1.0,
|
17 |
-
"step": 10
|
18 |
-
},
|
19 |
-
{
|
20 |
-
"epoch": 0.1,
|
21 |
-
"eval_loss": 235.82070922851562,
|
22 |
-
"eval_runtime": 27.9371,
|
23 |
-
"eval_samples_per_second": 19.794,
|
24 |
-
"eval_steps_per_second": 19.794,
|
25 |
-
"eval_wer": 1.0,
|
26 |
-
"step": 20
|
27 |
-
},
|
28 |
-
{
|
29 |
-
"epoch": 0.15,
|
30 |
-
"eval_loss": 226.90093994140625,
|
31 |
-
"eval_runtime": 27.8094,
|
32 |
-
"eval_samples_per_second": 19.885,
|
33 |
-
"eval_steps_per_second": 19.885,
|
34 |
-
"eval_wer": 1.0,
|
35 |
-
"step": 30
|
36 |
-
},
|
37 |
-
{
|
38 |
-
"epoch": 0.21,
|
39 |
-
"eval_loss": 198.07687377929688,
|
40 |
-
"eval_runtime": 27.9651,
|
41 |
-
"eval_samples_per_second": 19.775,
|
42 |
-
"eval_steps_per_second": 19.775,
|
43 |
-
"eval_wer": 1.0,
|
44 |
-
"step": 40
|
45 |
-
},
|
46 |
-
{
|
47 |
-
"epoch": 0.26,
|
48 |
-
"eval_loss": 166.6727752685547,
|
49 |
-
"eval_runtime": 28.4525,
|
50 |
-
"eval_samples_per_second": 19.436,
|
51 |
-
"eval_steps_per_second": 19.436,
|
52 |
-
"eval_wer": 1.0,
|
53 |
-
"step": 50
|
54 |
-
},
|
55 |
-
{
|
56 |
-
"epoch": 0.31,
|
57 |
-
"eval_loss": 149.14447021484375,
|
58 |
-
"eval_runtime": 27.248,
|
59 |
-
"eval_samples_per_second": 20.295,
|
60 |
-
"eval_steps_per_second": 20.295,
|
61 |
"eval_wer": 1.0,
|
62 |
-
"step":
|
63 |
},
|
64 |
{
|
65 |
-
"epoch": 0
|
66 |
-
"eval_loss":
|
67 |
-
"eval_runtime":
|
68 |
-
"eval_samples_per_second":
|
69 |
-
"eval_steps_per_second":
|
70 |
"eval_wer": 1.0,
|
71 |
-
"step":
|
72 |
},
|
73 |
{
|
74 |
-
"epoch":
|
75 |
-
"
|
76 |
-
"
|
77 |
-
"
|
78 |
-
"eval_steps_per_second": 19.614,
|
79 |
-
"eval_wer": 1.0,
|
80 |
-
"step": 80
|
81 |
},
|
82 |
{
|
83 |
-
"epoch": 0
|
84 |
-
"eval_loss":
|
85 |
-
"eval_runtime":
|
86 |
-
"eval_samples_per_second":
|
87 |
-
"eval_steps_per_second":
|
88 |
"eval_wer": 1.0,
|
89 |
-
"step":
|
90 |
},
|
91 |
{
|
92 |
-
"epoch": 0
|
93 |
-
"eval_loss":
|
94 |
-
"eval_runtime":
|
95 |
-
"eval_samples_per_second":
|
96 |
-
"eval_steps_per_second":
|
97 |
-
"eval_wer": 1.
|
98 |
-
"step":
|
99 |
},
|
100 |
{
|
101 |
-
"epoch": 0
|
102 |
-
"eval_loss":
|
103 |
-
"eval_runtime":
|
104 |
-
"eval_samples_per_second":
|
105 |
-
"eval_steps_per_second":
|
106 |
-
"eval_wer": 1.
|
107 |
-
"step":
|
108 |
},
|
109 |
{
|
110 |
-
"epoch":
|
111 |
-
"
|
112 |
-
"
|
113 |
-
"
|
114 |
-
"eval_steps_per_second": 20.484,
|
115 |
-
"eval_wer": 1.0,
|
116 |
-
"step": 120
|
117 |
},
|
118 |
{
|
119 |
-
"epoch": 0
|
120 |
-
"eval_loss":
|
121 |
-
"eval_runtime":
|
122 |
-
"eval_samples_per_second":
|
123 |
-
"eval_steps_per_second":
|
124 |
-
"eval_wer": 1.
|
125 |
-
"step":
|
126 |
},
|
127 |
{
|
128 |
-
"epoch": 0
|
129 |
-
"eval_loss":
|
130 |
-
"eval_runtime":
|
131 |
-
"eval_samples_per_second":
|
132 |
-
"eval_steps_per_second":
|
133 |
-
"eval_wer": 1.
|
134 |
-
"step":
|
135 |
},
|
136 |
{
|
137 |
-
"epoch": 0
|
138 |
-
"eval_loss":
|
139 |
-
"eval_runtime":
|
140 |
-
"eval_samples_per_second":
|
141 |
-
"eval_steps_per_second":
|
142 |
-
"eval_wer":
|
143 |
-
"step":
|
144 |
},
|
145 |
{
|
146 |
-
"epoch":
|
147 |
-
"
|
148 |
-
"
|
149 |
-
"
|
150 |
-
"eval_steps_per_second": 21.112,
|
151 |
-
"eval_wer": 1.0,
|
152 |
-
"step": 160
|
153 |
},
|
154 |
{
|
155 |
-
"epoch": 0
|
156 |
-
"eval_loss":
|
157 |
-
"eval_runtime":
|
158 |
-
"eval_samples_per_second":
|
159 |
-
"eval_steps_per_second":
|
160 |
-
"eval_wer":
|
161 |
-
"step":
|
162 |
},
|
163 |
{
|
164 |
-
"epoch": 0
|
165 |
-
"eval_loss":
|
166 |
-
"eval_runtime":
|
167 |
-
"eval_samples_per_second":
|
168 |
-
"eval_steps_per_second":
|
169 |
-
"eval_wer":
|
170 |
-
"step":
|
171 |
},
|
172 |
{
|
173 |
-
"epoch": 0
|
174 |
-
"
|
175 |
-
"
|
176 |
-
"
|
177 |
-
"
|
178 |
-
"
|
179 |
-
"
|
180 |
-
},
|
181 |
-
{
|
182 |
-
"epoch": 1.0,
|
183 |
-
"step": 195,
|
184 |
-
"total_flos": 2.4781601494187277e+17,
|
185 |
-
"train_loss": 109.71464342948718,
|
186 |
-
"train_runtime": 1380.1966,
|
187 |
-
"train_samples_per_second": 2.26,
|
188 |
-
"train_steps_per_second": 0.141
|
189 |
}
|
190 |
],
|
191 |
-
"max_steps":
|
192 |
-
"num_train_epochs":
|
193 |
-
"total_flos":
|
194 |
"trial_name": null,
|
195 |
"trial_params": null
|
196 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 1830,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"eval_loss": 47.84418869018555,
|
13 |
+
"eval_runtime": 186.8063,
|
14 |
+
"eval_samples_per_second": 19.587,
|
15 |
+
"eval_steps_per_second": 1.226,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
"eval_wer": 1.0,
|
17 |
+
"step": 183
|
18 |
},
|
19 |
{
|
20 |
+
"epoch": 2.0,
|
21 |
+
"eval_loss": 6.310945510864258,
|
22 |
+
"eval_runtime": 163.2985,
|
23 |
+
"eval_samples_per_second": 22.407,
|
24 |
+
"eval_steps_per_second": 1.402,
|
25 |
"eval_wer": 1.0,
|
26 |
+
"step": 366
|
27 |
},
|
28 |
{
|
29 |
+
"epoch": 2.73,
|
30 |
+
"learning_rate": 0.00029699999999999996,
|
31 |
+
"loss": 41.8902,
|
32 |
+
"step": 500
|
|
|
|
|
|
|
33 |
},
|
34 |
{
|
35 |
+
"epoch": 3.0,
|
36 |
+
"eval_loss": 6.239192008972168,
|
37 |
+
"eval_runtime": 163.0201,
|
38 |
+
"eval_samples_per_second": 22.445,
|
39 |
+
"eval_steps_per_second": 1.405,
|
40 |
"eval_wer": 1.0,
|
41 |
+
"step": 549
|
42 |
},
|
43 |
{
|
44 |
+
"epoch": 4.0,
|
45 |
+
"eval_loss": 5.973925590515137,
|
46 |
+
"eval_runtime": 163.0214,
|
47 |
+
"eval_samples_per_second": 22.445,
|
48 |
+
"eval_steps_per_second": 1.405,
|
49 |
+
"eval_wer": 1.1123227917121048,
|
50 |
+
"step": 732
|
51 |
},
|
52 |
{
|
53 |
+
"epoch": 5.0,
|
54 |
+
"eval_loss": 4.901411056518555,
|
55 |
+
"eval_runtime": 162.8715,
|
56 |
+
"eval_samples_per_second": 22.466,
|
57 |
+
"eval_steps_per_second": 1.406,
|
58 |
+
"eval_wer": 1.9473827699018538,
|
59 |
+
"step": 915
|
60 |
},
|
61 |
{
|
62 |
+
"epoch": 5.46,
|
63 |
+
"learning_rate": 0.00018834586466165413,
|
64 |
+
"loss": 5.5817,
|
65 |
+
"step": 1000
|
|
|
|
|
|
|
66 |
},
|
67 |
{
|
68 |
+
"epoch": 6.0,
|
69 |
+
"eval_loss": 3.9892334938049316,
|
70 |
+
"eval_runtime": 163.2053,
|
71 |
+
"eval_samples_per_second": 22.42,
|
72 |
+
"eval_steps_per_second": 1.403,
|
73 |
+
"eval_wer": 1.0188113413304254,
|
74 |
+
"step": 1098
|
75 |
},
|
76 |
{
|
77 |
+
"epoch": 7.0,
|
78 |
+
"eval_loss": 3.5080456733703613,
|
79 |
+
"eval_runtime": 162.7362,
|
80 |
+
"eval_samples_per_second": 22.484,
|
81 |
+
"eval_steps_per_second": 1.407,
|
82 |
+
"eval_wer": 1.0103598691384952,
|
83 |
+
"step": 1281
|
84 |
},
|
85 |
{
|
86 |
+
"epoch": 8.0,
|
87 |
+
"eval_loss": 3.0796852111816406,
|
88 |
+
"eval_runtime": 164.2666,
|
89 |
+
"eval_samples_per_second": 22.275,
|
90 |
+
"eval_steps_per_second": 1.394,
|
91 |
+
"eval_wer": 0.9904580152671756,
|
92 |
+
"step": 1464
|
93 |
},
|
94 |
{
|
95 |
+
"epoch": 8.2,
|
96 |
+
"learning_rate": 7.556390977443609e-05,
|
97 |
+
"loss": 3.5579,
|
98 |
+
"step": 1500
|
|
|
|
|
|
|
99 |
},
|
100 |
{
|
101 |
+
"epoch": 9.0,
|
102 |
+
"eval_loss": 2.8110806941986084,
|
103 |
+
"eval_runtime": 168.541,
|
104 |
+
"eval_samples_per_second": 21.71,
|
105 |
+
"eval_steps_per_second": 1.359,
|
106 |
+
"eval_wer": 0.9836423118865867,
|
107 |
+
"step": 1647
|
108 |
},
|
109 |
{
|
110 |
+
"epoch": 10.0,
|
111 |
+
"eval_loss": 2.67260479927063,
|
112 |
+
"eval_runtime": 165.7448,
|
113 |
+
"eval_samples_per_second": 22.076,
|
114 |
+
"eval_steps_per_second": 1.382,
|
115 |
+
"eval_wer": 0.9814612868047983,
|
116 |
+
"step": 1830
|
117 |
},
|
118 |
{
|
119 |
+
"epoch": 10.0,
|
120 |
+
"step": 1830,
|
121 |
+
"total_flos": 1.3577354977100892e+19,
|
122 |
+
"train_loss": 14.438921352032104,
|
123 |
+
"train_runtime": 7245.592,
|
124 |
+
"train_samples_per_second": 16.128,
|
125 |
+
"train_steps_per_second": 0.253
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
126 |
}
|
127 |
],
|
128 |
+
"max_steps": 1830,
|
129 |
+
"num_train_epochs": 10,
|
130 |
+
"total_flos": 1.3577354977100892e+19,
|
131 |
"trial_name": null,
|
132 |
"trial_params": null
|
133 |
}
|