Commit
•
4ad283e
1
Parent(s):
b810492
End of training
Browse files
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.05,
|
3 |
+
"eval_loss": 0.18787039816379547,
|
4 |
+
"eval_runtime": 2754.7233,
|
5 |
+
"eval_samples_per_second": 3.682,
|
6 |
+
"eval_steps_per_second": 0.23,
|
7 |
+
"eval_wer": 10.503340419070756,
|
8 |
+
"train_loss": 0.14094245743751527,
|
9 |
+
"train_runtime": 15142.1641,
|
10 |
+
"train_samples_per_second": 4.227,
|
11 |
+
"train_steps_per_second": 0.066
|
12 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.05,
|
3 |
+
"eval_loss": 0.18787039816379547,
|
4 |
+
"eval_runtime": 2754.7233,
|
5 |
+
"eval_samples_per_second": 3.682,
|
6 |
+
"eval_steps_per_second": 0.23,
|
7 |
+
"eval_wer": 10.503340419070756
|
8 |
+
}
|
runs/Dec07_17-25-52_129-154-231-61/events.out.tfevents.1670452253.129-154-231-61.428224.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e51721345e2bded455bbff4ca1b6b39601325324c122355479fa515e86657049
|
3 |
+
size 358
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.05,
|
3 |
+
"train_loss": 0.14094245743751527,
|
4 |
+
"train_runtime": 15142.1641,
|
5 |
+
"train_samples_per_second": 4.227,
|
6 |
+
"train_steps_per_second": 0.066
|
7 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,274 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 10.503340419070756,
|
3 |
+
"best_model_checkpoint": "./checkpoint-1000",
|
4 |
+
"epoch": 3.052,
|
5 |
+
"global_step": 1000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.03,
|
12 |
+
"learning_rate": 4.6000000000000004e-07,
|
13 |
+
"loss": 1.0986,
|
14 |
+
"step": 25
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.05,
|
18 |
+
"learning_rate": 9.600000000000001e-07,
|
19 |
+
"loss": 0.8438,
|
20 |
+
"step": 50
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.07,
|
24 |
+
"learning_rate": 1.46e-06,
|
25 |
+
"loss": 0.2768,
|
26 |
+
"step": 75
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.1,
|
30 |
+
"learning_rate": 1.9600000000000003e-06,
|
31 |
+
"loss": 0.1883,
|
32 |
+
"step": 100
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.12,
|
36 |
+
"learning_rate": 2.46e-06,
|
37 |
+
"loss": 0.1602,
|
38 |
+
"step": 125
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.15,
|
42 |
+
"learning_rate": 2.96e-06,
|
43 |
+
"loss": 0.1401,
|
44 |
+
"step": 150
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.17,
|
48 |
+
"learning_rate": 3.46e-06,
|
49 |
+
"loss": 0.1456,
|
50 |
+
"step": 175
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.2,
|
54 |
+
"learning_rate": 3.96e-06,
|
55 |
+
"loss": 0.1446,
|
56 |
+
"step": 200
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.23,
|
60 |
+
"learning_rate": 4.4600000000000005e-06,
|
61 |
+
"loss": 0.1658,
|
62 |
+
"step": 225
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.25,
|
66 |
+
"learning_rate": 4.960000000000001e-06,
|
67 |
+
"loss": 0.1517,
|
68 |
+
"step": 250
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.28,
|
72 |
+
"learning_rate": 5.460000000000001e-06,
|
73 |
+
"loss": 0.1521,
|
74 |
+
"step": 275
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.3,
|
78 |
+
"learning_rate": 5.9600000000000005e-06,
|
79 |
+
"loss": 0.1309,
|
80 |
+
"step": 300
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 1.01,
|
84 |
+
"learning_rate": 6.460000000000001e-06,
|
85 |
+
"loss": 0.1455,
|
86 |
+
"step": 325
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.03,
|
90 |
+
"learning_rate": 6.96e-06,
|
91 |
+
"loss": 0.1544,
|
92 |
+
"step": 350
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 1.06,
|
96 |
+
"learning_rate": 7.4600000000000006e-06,
|
97 |
+
"loss": 0.1497,
|
98 |
+
"step": 375
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 1.08,
|
102 |
+
"learning_rate": 7.960000000000002e-06,
|
103 |
+
"loss": 0.1058,
|
104 |
+
"step": 400
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 1.11,
|
108 |
+
"learning_rate": 8.46e-06,
|
109 |
+
"loss": 0.0996,
|
110 |
+
"step": 425
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 1.13,
|
114 |
+
"learning_rate": 8.96e-06,
|
115 |
+
"loss": 0.0982,
|
116 |
+
"step": 450
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 1.16,
|
120 |
+
"learning_rate": 9.460000000000001e-06,
|
121 |
+
"loss": 0.0868,
|
122 |
+
"step": 475
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 1.18,
|
126 |
+
"learning_rate": 9.960000000000001e-06,
|
127 |
+
"loss": 0.0915,
|
128 |
+
"step": 500
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.21,
|
132 |
+
"learning_rate": 9.54e-06,
|
133 |
+
"loss": 0.0926,
|
134 |
+
"step": 525
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 1.23,
|
138 |
+
"learning_rate": 9.040000000000002e-06,
|
139 |
+
"loss": 0.0926,
|
140 |
+
"step": 550
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 1.26,
|
144 |
+
"learning_rate": 8.540000000000001e-06,
|
145 |
+
"loss": 0.0792,
|
146 |
+
"step": 575
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 1.28,
|
150 |
+
"learning_rate": 8.040000000000001e-06,
|
151 |
+
"loss": 0.0802,
|
152 |
+
"step": 600
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 1.31,
|
156 |
+
"learning_rate": 7.540000000000001e-06,
|
157 |
+
"loss": 0.0754,
|
158 |
+
"step": 625
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 2.02,
|
162 |
+
"learning_rate": 7.04e-06,
|
163 |
+
"loss": 0.0741,
|
164 |
+
"step": 650
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 2.04,
|
168 |
+
"learning_rate": 6.540000000000001e-06,
|
169 |
+
"loss": 0.075,
|
170 |
+
"step": 675
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 2.07,
|
174 |
+
"learning_rate": 6.040000000000001e-06,
|
175 |
+
"loss": 0.0645,
|
176 |
+
"step": 700
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 2.09,
|
180 |
+
"learning_rate": 5.540000000000001e-06,
|
181 |
+
"loss": 0.055,
|
182 |
+
"step": 725
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 2.12,
|
186 |
+
"learning_rate": 5.04e-06,
|
187 |
+
"loss": 0.0482,
|
188 |
+
"step": 750
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 2.14,
|
192 |
+
"learning_rate": 4.540000000000001e-06,
|
193 |
+
"loss": 0.0415,
|
194 |
+
"step": 775
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 2.17,
|
198 |
+
"learning_rate": 4.04e-06,
|
199 |
+
"loss": 0.0442,
|
200 |
+
"step": 800
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 2.19,
|
204 |
+
"learning_rate": 3.54e-06,
|
205 |
+
"loss": 0.0441,
|
206 |
+
"step": 825
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 2.22,
|
210 |
+
"learning_rate": 3.04e-06,
|
211 |
+
"loss": 0.0415,
|
212 |
+
"step": 850
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 2.24,
|
216 |
+
"learning_rate": 2.5400000000000002e-06,
|
217 |
+
"loss": 0.0356,
|
218 |
+
"step": 875
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 2.27,
|
222 |
+
"learning_rate": 2.04e-06,
|
223 |
+
"loss": 0.0306,
|
224 |
+
"step": 900
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 2.29,
|
228 |
+
"learning_rate": 1.54e-06,
|
229 |
+
"loss": 0.0317,
|
230 |
+
"step": 925
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 3.0,
|
234 |
+
"learning_rate": 1.04e-06,
|
235 |
+
"loss": 0.0348,
|
236 |
+
"step": 950
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 3.03,
|
240 |
+
"learning_rate": 5.4e-07,
|
241 |
+
"loss": 0.0322,
|
242 |
+
"step": 975
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 3.05,
|
246 |
+
"learning_rate": 4e-08,
|
247 |
+
"loss": 0.0348,
|
248 |
+
"step": 1000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 3.05,
|
252 |
+
"eval_loss": 0.18787039816379547,
|
253 |
+
"eval_runtime": 2768.6707,
|
254 |
+
"eval_samples_per_second": 3.663,
|
255 |
+
"eval_steps_per_second": 0.229,
|
256 |
+
"eval_wer": 10.503340419070756,
|
257 |
+
"step": 1000
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 3.05,
|
261 |
+
"step": 1000,
|
262 |
+
"total_flos": 6.54105685229568e+19,
|
263 |
+
"train_loss": 0.14094245743751527,
|
264 |
+
"train_runtime": 15142.1641,
|
265 |
+
"train_samples_per_second": 4.227,
|
266 |
+
"train_steps_per_second": 0.066
|
267 |
+
}
|
268 |
+
],
|
269 |
+
"max_steps": 1000,
|
270 |
+
"num_train_epochs": 9223372036854775807,
|
271 |
+
"total_flos": 6.54105685229568e+19,
|
272 |
+
"trial_name": null,
|
273 |
+
"trial_params": null
|
274 |
+
}
|