Commit
·
f869201
1
Parent(s):
edb375d
End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- train_results.json +8 -0
- trainer_state.json +928 -0
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 500.0,
|
3 |
+
"eval_loss": 0.6693080067634583,
|
4 |
+
"eval_runtime": 13.4537,
|
5 |
+
"eval_samples": 306,
|
6 |
+
"eval_samples_per_second": 22.745,
|
7 |
+
"eval_steps_per_second": 1.487,
|
8 |
+
"eval_wer": 0.592057761732852,
|
9 |
+
"train_loss": 1.1389288659529253,
|
10 |
+
"train_runtime": 23734.473,
|
11 |
+
"train_samples": 698,
|
12 |
+
"train_samples_per_second": 14.704,
|
13 |
+
"train_steps_per_second": 0.463
|
14 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 500.0,
|
3 |
+
"eval_loss": 0.6693080067634583,
|
4 |
+
"eval_runtime": 13.4537,
|
5 |
+
"eval_samples": 306,
|
6 |
+
"eval_samples_per_second": 22.745,
|
7 |
+
"eval_steps_per_second": 1.487,
|
8 |
+
"eval_wer": 0.592057761732852
|
9 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 500.0,
|
3 |
+
"train_loss": 1.1389288659529253,
|
4 |
+
"train_runtime": 23734.473,
|
5 |
+
"train_samples": 698,
|
6 |
+
"train_samples_per_second": 14.704,
|
7 |
+
"train_steps_per_second": 0.463
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,928 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 500.0,
|
5 |
+
"global_step": 11000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 4.55,
|
12 |
+
"learning_rate": 3.675e-06,
|
13 |
+
"loss": 15.8714,
|
14 |
+
"step": 100
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 9.09,
|
18 |
+
"learning_rate": 7.425e-06,
|
19 |
+
"loss": 8.905,
|
20 |
+
"step": 200
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 13.64,
|
24 |
+
"learning_rate": 1.1174999999999999e-05,
|
25 |
+
"loss": 5.8648,
|
26 |
+
"step": 300
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 18.18,
|
30 |
+
"learning_rate": 1.4925e-05,
|
31 |
+
"loss": 4.9504,
|
32 |
+
"step": 400
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 18.18,
|
36 |
+
"eval_loss": 4.673031330108643,
|
37 |
+
"eval_runtime": 13.8453,
|
38 |
+
"eval_samples_per_second": 22.101,
|
39 |
+
"eval_steps_per_second": 1.445,
|
40 |
+
"eval_wer": 1.0,
|
41 |
+
"step": 400
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 22.73,
|
45 |
+
"learning_rate": 1.8675e-05,
|
46 |
+
"loss": 4.2429,
|
47 |
+
"step": 500
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 27.27,
|
51 |
+
"learning_rate": 2.2424999999999996e-05,
|
52 |
+
"loss": 3.72,
|
53 |
+
"step": 600
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 31.82,
|
57 |
+
"learning_rate": 2.6174999999999996e-05,
|
58 |
+
"loss": 3.4596,
|
59 |
+
"step": 700
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 36.36,
|
63 |
+
"learning_rate": 2.9925e-05,
|
64 |
+
"loss": 3.3766,
|
65 |
+
"step": 800
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 36.36,
|
69 |
+
"eval_loss": 3.3464324474334717,
|
70 |
+
"eval_runtime": 13.5196,
|
71 |
+
"eval_samples_per_second": 22.634,
|
72 |
+
"eval_steps_per_second": 1.479,
|
73 |
+
"eval_wer": 1.0,
|
74 |
+
"step": 800
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 40.91,
|
78 |
+
"learning_rate": 3.3675e-05,
|
79 |
+
"loss": 3.3035,
|
80 |
+
"step": 900
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 45.45,
|
84 |
+
"learning_rate": 3.7424999999999995e-05,
|
85 |
+
"loss": 3.2559,
|
86 |
+
"step": 1000
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 50.0,
|
90 |
+
"learning_rate": 4.1175e-05,
|
91 |
+
"loss": 3.2202,
|
92 |
+
"step": 1100
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 54.55,
|
96 |
+
"learning_rate": 4.4924999999999994e-05,
|
97 |
+
"loss": 3.1128,
|
98 |
+
"step": 1200
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 54.55,
|
102 |
+
"eval_loss": 3.0176751613616943,
|
103 |
+
"eval_runtime": 13.6849,
|
104 |
+
"eval_samples_per_second": 22.36,
|
105 |
+
"eval_steps_per_second": 1.461,
|
106 |
+
"eval_wer": 0.9979943842759728,
|
107 |
+
"step": 1200
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 59.09,
|
111 |
+
"learning_rate": 4.8675e-05,
|
112 |
+
"loss": 2.9121,
|
113 |
+
"step": 1300
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 63.64,
|
117 |
+
"learning_rate": 5.2424999999999994e-05,
|
118 |
+
"loss": 2.4741,
|
119 |
+
"step": 1400
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 68.18,
|
123 |
+
"learning_rate": 5.6175e-05,
|
124 |
+
"loss": 2.0461,
|
125 |
+
"step": 1500
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 72.73,
|
129 |
+
"learning_rate": 5.9925e-05,
|
130 |
+
"loss": 1.7966,
|
131 |
+
"step": 1600
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 72.73,
|
135 |
+
"eval_loss": 0.8733049631118774,
|
136 |
+
"eval_runtime": 13.6227,
|
137 |
+
"eval_samples_per_second": 22.463,
|
138 |
+
"eval_steps_per_second": 1.468,
|
139 |
+
"eval_wer": 0.8038507821901324,
|
140 |
+
"step": 1600
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 77.27,
|
144 |
+
"learning_rate": 6.367499999999999e-05,
|
145 |
+
"loss": 1.6388,
|
146 |
+
"step": 1700
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 81.82,
|
150 |
+
"learning_rate": 6.7425e-05,
|
151 |
+
"loss": 1.5466,
|
152 |
+
"step": 1800
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 86.36,
|
156 |
+
"learning_rate": 7.1175e-05,
|
157 |
+
"loss": 1.461,
|
158 |
+
"step": 1900
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 90.91,
|
162 |
+
"learning_rate": 7.48875e-05,
|
163 |
+
"loss": 1.4085,
|
164 |
+
"step": 2000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 90.91,
|
168 |
+
"eval_loss": 0.5555232763290405,
|
169 |
+
"eval_runtime": 13.4681,
|
170 |
+
"eval_samples_per_second": 22.72,
|
171 |
+
"eval_steps_per_second": 1.485,
|
172 |
+
"eval_wer": 0.645808263136783,
|
173 |
+
"step": 2000
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 95.45,
|
177 |
+
"learning_rate": 7.419166666666666e-05,
|
178 |
+
"loss": 1.3233,
|
179 |
+
"step": 2100
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 100.0,
|
183 |
+
"learning_rate": 7.335833333333333e-05,
|
184 |
+
"loss": 1.2821,
|
185 |
+
"step": 2200
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 104.55,
|
189 |
+
"learning_rate": 7.252499999999999e-05,
|
190 |
+
"loss": 1.2194,
|
191 |
+
"step": 2300
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 109.09,
|
195 |
+
"learning_rate": 7.169166666666666e-05,
|
196 |
+
"loss": 1.1731,
|
197 |
+
"step": 2400
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 109.09,
|
201 |
+
"eval_loss": 0.4929651618003845,
|
202 |
+
"eval_runtime": 13.4716,
|
203 |
+
"eval_samples_per_second": 22.715,
|
204 |
+
"eval_steps_per_second": 1.485,
|
205 |
+
"eval_wer": 0.6438026474127557,
|
206 |
+
"step": 2400
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 113.64,
|
210 |
+
"learning_rate": 7.085833333333333e-05,
|
211 |
+
"loss": 1.135,
|
212 |
+
"step": 2500
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 118.18,
|
216 |
+
"learning_rate": 7.0025e-05,
|
217 |
+
"loss": 1.1009,
|
218 |
+
"step": 2600
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 122.73,
|
222 |
+
"learning_rate": 6.919166666666666e-05,
|
223 |
+
"loss": 1.0712,
|
224 |
+
"step": 2700
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 127.27,
|
228 |
+
"learning_rate": 6.835833333333332e-05,
|
229 |
+
"loss": 1.0271,
|
230 |
+
"step": 2800
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 127.27,
|
234 |
+
"eval_loss": 0.47801950573921204,
|
235 |
+
"eval_runtime": 13.4955,
|
236 |
+
"eval_samples_per_second": 22.674,
|
237 |
+
"eval_steps_per_second": 1.482,
|
238 |
+
"eval_wer": 0.6093060569594866,
|
239 |
+
"step": 2800
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 131.82,
|
243 |
+
"learning_rate": 6.753333333333333e-05,
|
244 |
+
"loss": 1.0016,
|
245 |
+
"step": 2900
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 136.36,
|
249 |
+
"learning_rate": 6.67e-05,
|
250 |
+
"loss": 0.9638,
|
251 |
+
"step": 3000
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 140.91,
|
255 |
+
"learning_rate": 6.586666666666666e-05,
|
256 |
+
"loss": 0.9327,
|
257 |
+
"step": 3100
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 145.45,
|
261 |
+
"learning_rate": 6.503333333333333e-05,
|
262 |
+
"loss": 0.9045,
|
263 |
+
"step": 3200
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 145.45,
|
267 |
+
"eval_loss": 0.46472442150115967,
|
268 |
+
"eval_runtime": 13.3444,
|
269 |
+
"eval_samples_per_second": 22.931,
|
270 |
+
"eval_steps_per_second": 1.499,
|
271 |
+
"eval_wer": 0.6578419574809466,
|
272 |
+
"step": 3200
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 150.0,
|
276 |
+
"learning_rate": 6.419999999999999e-05,
|
277 |
+
"loss": 0.8865,
|
278 |
+
"step": 3300
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 154.55,
|
282 |
+
"learning_rate": 6.336666666666666e-05,
|
283 |
+
"loss": 0.8703,
|
284 |
+
"step": 3400
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 159.09,
|
288 |
+
"learning_rate": 6.253333333333333e-05,
|
289 |
+
"loss": 0.8379,
|
290 |
+
"step": 3500
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 163.64,
|
294 |
+
"learning_rate": 6.17e-05,
|
295 |
+
"loss": 0.807,
|
296 |
+
"step": 3600
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 163.64,
|
300 |
+
"eval_loss": 0.4505322575569153,
|
301 |
+
"eval_runtime": 13.3663,
|
302 |
+
"eval_samples_per_second": 22.893,
|
303 |
+
"eval_steps_per_second": 1.496,
|
304 |
+
"eval_wer": 0.5924588848776574,
|
305 |
+
"step": 3600
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 168.18,
|
309 |
+
"learning_rate": 6.0866666666666664e-05,
|
310 |
+
"loss": 0.805,
|
311 |
+
"step": 3700
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 172.73,
|
315 |
+
"learning_rate": 6.003333333333333e-05,
|
316 |
+
"loss": 0.7889,
|
317 |
+
"step": 3800
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 177.27,
|
321 |
+
"learning_rate": 5.9199999999999996e-05,
|
322 |
+
"loss": 0.764,
|
323 |
+
"step": 3900
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 181.82,
|
327 |
+
"learning_rate": 5.8366666666666665e-05,
|
328 |
+
"loss": 0.741,
|
329 |
+
"step": 4000
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 181.82,
|
333 |
+
"eval_loss": 0.4745561182498932,
|
334 |
+
"eval_runtime": 13.2681,
|
335 |
+
"eval_samples_per_second": 23.063,
|
336 |
+
"eval_steps_per_second": 1.507,
|
337 |
+
"eval_wer": 0.6024869634977938,
|
338 |
+
"step": 4000
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 186.36,
|
342 |
+
"learning_rate": 5.753333333333333e-05,
|
343 |
+
"loss": 0.7192,
|
344 |
+
"step": 4100
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 190.91,
|
348 |
+
"learning_rate": 5.6699999999999996e-05,
|
349 |
+
"loss": 0.6977,
|
350 |
+
"step": 4200
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 195.45,
|
354 |
+
"learning_rate": 5.5866666666666665e-05,
|
355 |
+
"loss": 0.6882,
|
356 |
+
"step": 4300
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 200.0,
|
360 |
+
"learning_rate": 5.503333333333333e-05,
|
361 |
+
"loss": 0.6706,
|
362 |
+
"step": 4400
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 200.0,
|
366 |
+
"eval_loss": 0.5003653168678284,
|
367 |
+
"eval_runtime": 13.3324,
|
368 |
+
"eval_samples_per_second": 22.952,
|
369 |
+
"eval_steps_per_second": 1.5,
|
370 |
+
"eval_wer": 0.5844364219815483,
|
371 |
+
"step": 4400
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 204.55,
|
375 |
+
"learning_rate": 5.4199999999999996e-05,
|
376 |
+
"loss": 0.6627,
|
377 |
+
"step": 4500
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 209.09,
|
381 |
+
"learning_rate": 5.3366666666666665e-05,
|
382 |
+
"loss": 0.6453,
|
383 |
+
"step": 4600
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 213.64,
|
387 |
+
"learning_rate": 5.253333333333333e-05,
|
388 |
+
"loss": 0.6311,
|
389 |
+
"step": 4700
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 218.18,
|
393 |
+
"learning_rate": 5.1699999999999996e-05,
|
394 |
+
"loss": 0.6186,
|
395 |
+
"step": 4800
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 218.18,
|
399 |
+
"eval_loss": 0.4983522891998291,
|
400 |
+
"eval_runtime": 13.4916,
|
401 |
+
"eval_samples_per_second": 22.681,
|
402 |
+
"eval_steps_per_second": 1.482,
|
403 |
+
"eval_wer": 0.5996791014841556,
|
404 |
+
"step": 4800
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 222.73,
|
408 |
+
"learning_rate": 5.086666666666666e-05,
|
409 |
+
"loss": 0.5976,
|
410 |
+
"step": 4900
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 227.27,
|
414 |
+
"learning_rate": 5.003333333333333e-05,
|
415 |
+
"loss": 0.5832,
|
416 |
+
"step": 5000
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 231.82,
|
420 |
+
"learning_rate": 4.9199999999999997e-05,
|
421 |
+
"loss": 0.5663,
|
422 |
+
"step": 5100
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 236.36,
|
426 |
+
"learning_rate": 4.836666666666666e-05,
|
427 |
+
"loss": 0.5508,
|
428 |
+
"step": 5200
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 236.36,
|
432 |
+
"eval_loss": 0.5298363566398621,
|
433 |
+
"eval_runtime": 13.4008,
|
434 |
+
"eval_samples_per_second": 22.834,
|
435 |
+
"eval_steps_per_second": 1.492,
|
436 |
+
"eval_wer": 0.5635780184516647,
|
437 |
+
"step": 5200
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 240.91,
|
441 |
+
"learning_rate": 4.753333333333333e-05,
|
442 |
+
"loss": 0.554,
|
443 |
+
"step": 5300
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 245.45,
|
447 |
+
"learning_rate": 4.67e-05,
|
448 |
+
"loss": 0.543,
|
449 |
+
"step": 5400
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 250.0,
|
453 |
+
"learning_rate": 4.586666666666666e-05,
|
454 |
+
"loss": 0.5221,
|
455 |
+
"step": 5500
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 254.55,
|
459 |
+
"learning_rate": 4.503333333333333e-05,
|
460 |
+
"loss": 0.5123,
|
461 |
+
"step": 5600
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 254.55,
|
465 |
+
"eval_loss": 0.5410219430923462,
|
466 |
+
"eval_runtime": 13.3891,
|
467 |
+
"eval_samples_per_second": 22.854,
|
468 |
+
"eval_steps_per_second": 1.494,
|
469 |
+
"eval_wer": 0.51103088648215,
|
470 |
+
"step": 5600
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 259.09,
|
474 |
+
"learning_rate": 4.42e-05,
|
475 |
+
"loss": 0.5023,
|
476 |
+
"step": 5700
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 263.64,
|
480 |
+
"learning_rate": 4.336666666666666e-05,
|
481 |
+
"loss": 0.4854,
|
482 |
+
"step": 5800
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 268.18,
|
486 |
+
"learning_rate": 4.253333333333333e-05,
|
487 |
+
"loss": 0.4795,
|
488 |
+
"step": 5900
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 272.73,
|
492 |
+
"learning_rate": 4.17e-05,
|
493 |
+
"loss": 0.4623,
|
494 |
+
"step": 6000
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 272.73,
|
498 |
+
"eval_loss": 0.5591160655021667,
|
499 |
+
"eval_runtime": 13.3234,
|
500 |
+
"eval_samples_per_second": 22.967,
|
501 |
+
"eval_steps_per_second": 1.501,
|
502 |
+
"eval_wer": 0.538307260328921,
|
503 |
+
"step": 6000
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 277.27,
|
507 |
+
"learning_rate": 4.086666666666666e-05,
|
508 |
+
"loss": 0.4593,
|
509 |
+
"step": 6100
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 281.82,
|
513 |
+
"learning_rate": 4.003333333333333e-05,
|
514 |
+
"loss": 0.4435,
|
515 |
+
"step": 6200
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 286.36,
|
519 |
+
"learning_rate": 3.919999999999999e-05,
|
520 |
+
"loss": 0.4432,
|
521 |
+
"step": 6300
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 290.91,
|
525 |
+
"learning_rate": 3.836666666666666e-05,
|
526 |
+
"loss": 0.4281,
|
527 |
+
"step": 6400
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 290.91,
|
531 |
+
"eval_loss": 0.5775493383407593,
|
532 |
+
"eval_runtime": 13.3759,
|
533 |
+
"eval_samples_per_second": 22.877,
|
534 |
+
"eval_steps_per_second": 1.495,
|
535 |
+
"eval_wer": 0.5599679101484155,
|
536 |
+
"step": 6400
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 295.45,
|
540 |
+
"learning_rate": 3.753333333333333e-05,
|
541 |
+
"loss": 0.4264,
|
542 |
+
"step": 6500
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 300.0,
|
546 |
+
"learning_rate": 3.67e-05,
|
547 |
+
"loss": 0.4187,
|
548 |
+
"step": 6600
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 304.55,
|
552 |
+
"learning_rate": 3.586666666666666e-05,
|
553 |
+
"loss": 0.3965,
|
554 |
+
"step": 6700
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 309.09,
|
558 |
+
"learning_rate": 3.503333333333333e-05,
|
559 |
+
"loss": 0.4045,
|
560 |
+
"step": 6800
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 309.09,
|
564 |
+
"eval_loss": 0.5923808217048645,
|
565 |
+
"eval_runtime": 13.6647,
|
566 |
+
"eval_samples_per_second": 22.394,
|
567 |
+
"eval_steps_per_second": 1.464,
|
568 |
+
"eval_wer": 0.5579622944243883,
|
569 |
+
"step": 6800
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 313.64,
|
573 |
+
"learning_rate": 3.42e-05,
|
574 |
+
"loss": 0.3857,
|
575 |
+
"step": 6900
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 318.18,
|
579 |
+
"learning_rate": 3.336666666666667e-05,
|
580 |
+
"loss": 0.373,
|
581 |
+
"step": 7000
|
582 |
+
},
|
583 |
+
{
|
584 |
+
"epoch": 322.73,
|
585 |
+
"learning_rate": 3.253333333333333e-05,
|
586 |
+
"loss": 0.3752,
|
587 |
+
"step": 7100
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 327.27,
|
591 |
+
"learning_rate": 3.17e-05,
|
592 |
+
"loss": 0.3651,
|
593 |
+
"step": 7200
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 327.27,
|
597 |
+
"eval_loss": 0.567070484161377,
|
598 |
+
"eval_runtime": 13.4998,
|
599 |
+
"eval_samples_per_second": 22.667,
|
600 |
+
"eval_steps_per_second": 1.482,
|
601 |
+
"eval_wer": 0.5683914961893302,
|
602 |
+
"step": 7200
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 331.82,
|
606 |
+
"learning_rate": 3.086666666666667e-05,
|
607 |
+
"loss": 0.3567,
|
608 |
+
"step": 7300
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 336.36,
|
612 |
+
"learning_rate": 3.003333333333333e-05,
|
613 |
+
"loss": 0.3551,
|
614 |
+
"step": 7400
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 340.91,
|
618 |
+
"learning_rate": 2.9199999999999995e-05,
|
619 |
+
"loss": 0.351,
|
620 |
+
"step": 7500
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 345.45,
|
624 |
+
"learning_rate": 2.8366666666666664e-05,
|
625 |
+
"loss": 0.343,
|
626 |
+
"step": 7600
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 345.45,
|
630 |
+
"eval_loss": 0.6082874536514282,
|
631 |
+
"eval_runtime": 13.5565,
|
632 |
+
"eval_samples_per_second": 22.572,
|
633 |
+
"eval_steps_per_second": 1.475,
|
634 |
+
"eval_wer": 0.5944645006016848,
|
635 |
+
"step": 7600
|
636 |
+
},
|
637 |
+
{
|
638 |
+
"epoch": 350.0,
|
639 |
+
"learning_rate": 2.7541666666666664e-05,
|
640 |
+
"loss": 0.3379,
|
641 |
+
"step": 7700
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 354.55,
|
645 |
+
"learning_rate": 2.6716666666666664e-05,
|
646 |
+
"loss": 0.3257,
|
647 |
+
"step": 7800
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 359.09,
|
651 |
+
"learning_rate": 2.588333333333333e-05,
|
652 |
+
"loss": 0.3285,
|
653 |
+
"step": 7900
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 363.64,
|
657 |
+
"learning_rate": 2.505e-05,
|
658 |
+
"loss": 0.3085,
|
659 |
+
"step": 8000
|
660 |
+
},
|
661 |
+
{
|
662 |
+
"epoch": 363.64,
|
663 |
+
"eval_loss": 0.6242865324020386,
|
664 |
+
"eval_runtime": 13.4343,
|
665 |
+
"eval_samples_per_second": 22.778,
|
666 |
+
"eval_steps_per_second": 1.489,
|
667 |
+
"eval_wer": 0.5728038507821901,
|
668 |
+
"step": 8000
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 368.18,
|
672 |
+
"learning_rate": 2.4216666666666665e-05,
|
673 |
+
"loss": 0.3127,
|
674 |
+
"step": 8100
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 372.73,
|
678 |
+
"learning_rate": 2.338333333333333e-05,
|
679 |
+
"loss": 0.3149,
|
680 |
+
"step": 8200
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 377.27,
|
684 |
+
"learning_rate": 2.255e-05,
|
685 |
+
"loss": 0.307,
|
686 |
+
"step": 8300
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 381.82,
|
690 |
+
"learning_rate": 2.1716666666666665e-05,
|
691 |
+
"loss": 0.2941,
|
692 |
+
"step": 8400
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 381.82,
|
696 |
+
"eval_loss": 0.6244971752166748,
|
697 |
+
"eval_runtime": 13.5184,
|
698 |
+
"eval_samples_per_second": 22.636,
|
699 |
+
"eval_steps_per_second": 1.479,
|
700 |
+
"eval_wer": 0.5579622944243883,
|
701 |
+
"step": 8400
|
702 |
+
},
|
703 |
+
{
|
704 |
+
"epoch": 386.36,
|
705 |
+
"learning_rate": 2.088333333333333e-05,
|
706 |
+
"loss": 0.295,
|
707 |
+
"step": 8500
|
708 |
+
},
|
709 |
+
{
|
710 |
+
"epoch": 390.91,
|
711 |
+
"learning_rate": 2.0049999999999996e-05,
|
712 |
+
"loss": 0.2842,
|
713 |
+
"step": 8600
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 395.45,
|
717 |
+
"learning_rate": 1.9216666666666665e-05,
|
718 |
+
"loss": 0.2817,
|
719 |
+
"step": 8700
|
720 |
+
},
|
721 |
+
{
|
722 |
+
"epoch": 400.0,
|
723 |
+
"learning_rate": 1.838333333333333e-05,
|
724 |
+
"loss": 0.2735,
|
725 |
+
"step": 8800
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 400.0,
|
729 |
+
"eval_loss": 0.6457676291465759,
|
730 |
+
"eval_runtime": 13.5206,
|
731 |
+
"eval_samples_per_second": 22.632,
|
732 |
+
"eval_steps_per_second": 1.479,
|
733 |
+
"eval_wer": 0.5804251905334937,
|
734 |
+
"step": 8800
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 404.55,
|
738 |
+
"learning_rate": 1.755e-05,
|
739 |
+
"loss": 0.2786,
|
740 |
+
"step": 8900
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 409.09,
|
744 |
+
"learning_rate": 1.6716666666666665e-05,
|
745 |
+
"loss": 0.2708,
|
746 |
+
"step": 9000
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 413.64,
|
750 |
+
"learning_rate": 1.5883333333333334e-05,
|
751 |
+
"loss": 0.2661,
|
752 |
+
"step": 9100
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 418.18,
|
756 |
+
"learning_rate": 1.5049999999999998e-05,
|
757 |
+
"loss": 0.262,
|
758 |
+
"step": 9200
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 418.18,
|
762 |
+
"eval_loss": 0.656562328338623,
|
763 |
+
"eval_runtime": 13.3117,
|
764 |
+
"eval_samples_per_second": 22.987,
|
765 |
+
"eval_steps_per_second": 1.502,
|
766 |
+
"eval_wer": 0.5824308062575211,
|
767 |
+
"step": 9200
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 422.73,
|
771 |
+
"learning_rate": 1.4216666666666666e-05,
|
772 |
+
"loss": 0.2577,
|
773 |
+
"step": 9300
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 427.27,
|
777 |
+
"learning_rate": 1.3383333333333331e-05,
|
778 |
+
"loss": 0.2576,
|
779 |
+
"step": 9400
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 431.82,
|
783 |
+
"learning_rate": 1.2549999999999998e-05,
|
784 |
+
"loss": 0.2573,
|
785 |
+
"step": 9500
|
786 |
+
},
|
787 |
+
{
|
788 |
+
"epoch": 436.36,
|
789 |
+
"learning_rate": 1.1716666666666666e-05,
|
790 |
+
"loss": 0.2578,
|
791 |
+
"step": 9600
|
792 |
+
},
|
793 |
+
{
|
794 |
+
"epoch": 436.36,
|
795 |
+
"eval_loss": 0.6557896733283997,
|
796 |
+
"eval_runtime": 13.599,
|
797 |
+
"eval_samples_per_second": 22.502,
|
798 |
+
"eval_steps_per_second": 1.471,
|
799 |
+
"eval_wer": 0.596470116325712,
|
800 |
+
"step": 9600
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 440.91,
|
804 |
+
"learning_rate": 1.0883333333333331e-05,
|
805 |
+
"loss": 0.2445,
|
806 |
+
"step": 9700
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 445.45,
|
810 |
+
"learning_rate": 1.005e-05,
|
811 |
+
"loss": 0.2422,
|
812 |
+
"step": 9800
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 450.0,
|
816 |
+
"learning_rate": 9.216666666666666e-06,
|
817 |
+
"loss": 0.2481,
|
818 |
+
"step": 9900
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 454.55,
|
822 |
+
"learning_rate": 8.383333333333333e-06,
|
823 |
+
"loss": 0.2388,
|
824 |
+
"step": 10000
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 454.55,
|
828 |
+
"eval_loss": 0.659763514995575,
|
829 |
+
"eval_runtime": 13.4458,
|
830 |
+
"eval_samples_per_second": 22.758,
|
831 |
+
"eval_steps_per_second": 1.487,
|
832 |
+
"eval_wer": 0.5992779783393501,
|
833 |
+
"step": 10000
|
834 |
+
},
|
835 |
+
{
|
836 |
+
"epoch": 459.09,
|
837 |
+
"learning_rate": 7.55e-06,
|
838 |
+
"loss": 0.2362,
|
839 |
+
"step": 10100
|
840 |
+
},
|
841 |
+
{
|
842 |
+
"epoch": 463.64,
|
843 |
+
"learning_rate": 6.716666666666666e-06,
|
844 |
+
"loss": 0.2374,
|
845 |
+
"step": 10200
|
846 |
+
},
|
847 |
+
{
|
848 |
+
"epoch": 468.18,
|
849 |
+
"learning_rate": 5.883333333333333e-06,
|
850 |
+
"loss": 0.2352,
|
851 |
+
"step": 10300
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 472.73,
|
855 |
+
"learning_rate": 5.049999999999999e-06,
|
856 |
+
"loss": 0.2328,
|
857 |
+
"step": 10400
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 472.73,
|
861 |
+
"eval_loss": 0.6699528694152832,
|
862 |
+
"eval_runtime": 13.3932,
|
863 |
+
"eval_samples_per_second": 22.847,
|
864 |
+
"eval_steps_per_second": 1.493,
|
865 |
+
"eval_wer": 0.6040914560770156,
|
866 |
+
"step": 10400
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 477.27,
|
870 |
+
"learning_rate": 4.216666666666666e-06,
|
871 |
+
"loss": 0.2286,
|
872 |
+
"step": 10500
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 481.82,
|
876 |
+
"learning_rate": 3.3916666666666662e-06,
|
877 |
+
"loss": 0.232,
|
878 |
+
"step": 10600
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 486.36,
|
882 |
+
"learning_rate": 2.558333333333333e-06,
|
883 |
+
"loss": 0.2323,
|
884 |
+
"step": 10700
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 490.91,
|
888 |
+
"learning_rate": 1.7249999999999998e-06,
|
889 |
+
"loss": 0.2286,
|
890 |
+
"step": 10800
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 490.91,
|
894 |
+
"eval_loss": 0.6684302091598511,
|
895 |
+
"eval_runtime": 13.5254,
|
896 |
+
"eval_samples_per_second": 22.624,
|
897 |
+
"eval_steps_per_second": 1.479,
|
898 |
+
"eval_wer": 0.5956678700361011,
|
899 |
+
"step": 10800
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 495.45,
|
903 |
+
"learning_rate": 8.916666666666666e-07,
|
904 |
+
"loss": 0.229,
|
905 |
+
"step": 10900
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 500.0,
|
909 |
+
"learning_rate": 5.8333333333333326e-08,
|
910 |
+
"loss": 0.2255,
|
911 |
+
"step": 11000
|
912 |
+
},
|
913 |
+
{
|
914 |
+
"epoch": 500.0,
|
915 |
+
"step": 11000,
|
916 |
+
"total_flos": 6.534167693112984e+19,
|
917 |
+
"train_loss": 1.1389288659529253,
|
918 |
+
"train_runtime": 23734.473,
|
919 |
+
"train_samples_per_second": 14.704,
|
920 |
+
"train_steps_per_second": 0.463
|
921 |
+
}
|
922 |
+
],
|
923 |
+
"max_steps": 11000,
|
924 |
+
"num_train_epochs": 500,
|
925 |
+
"total_flos": 6.534167693112984e+19,
|
926 |
+
"trial_name": null,
|
927 |
+
"trial_params": null
|
928 |
+
}
|