PereLluis13
commited on
Commit
•
2d36496
1
Parent(s):
dd93682
Training in progress, step 29000
Browse files- .ipynb_checkpoints/train_results-checkpoint.json +8 -0
- .ipynb_checkpoints/trainer_state-checkpoint.json +700 -0
- pytorch_model.bin +1 -1
- runs/Feb04_14-58-29_job-336a688f-553a-4e6e-83b3-ad5d10274b51/1643989411.4467487/events.out.tfevents.1643989411.job-336a688f-553a-4e6e-83b3-ad5d10274b51.728502.1 +3 -0
- runs/Feb04_14-58-29_job-336a688f-553a-4e6e-83b3-ad5d10274b51/events.out.tfevents.1643989411.job-336a688f-553a-4e6e-83b3-ad5d10274b51.728502.0 +3 -0
- special_tokens_map.json +1 -1
- training_args.bin +1 -1
.ipynb_checkpoints/train_results-checkpoint.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 12.0,
|
3 |
+
"train_loss": 0.5676147035501541,
|
4 |
+
"train_runtime": 172546.67,
|
5 |
+
"train_samples": 240334,
|
6 |
+
"train_samples_per_second": 16.714,
|
7 |
+
"train_steps_per_second": 0.131
|
8 |
+
}
|
.ipynb_checkpoints/trainer_state-checkpoint.json
ADDED
@@ -0,0 +1,700 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 11.999600585807482,
|
5 |
+
"global_step": 22524,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.09,
|
12 |
+
"learning_rate": 1.8712499999999997e-05,
|
13 |
+
"loss": 6.2099,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.09,
|
18 |
+
"eval_loss": 3.41253662109375,
|
19 |
+
"eval_runtime": 1358.074,
|
20 |
+
"eval_samples_per_second": 14.868,
|
21 |
+
"eval_steps_per_second": 0.465,
|
22 |
+
"eval_wer": 1.0,
|
23 |
+
"step": 500
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.18,
|
27 |
+
"learning_rate": 3.7462499999999996e-05,
|
28 |
+
"loss": 2.9961,
|
29 |
+
"step": 1000
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 0.18,
|
33 |
+
"eval_loss": 2.9223873615264893,
|
34 |
+
"eval_runtime": 1361.8836,
|
35 |
+
"eval_samples_per_second": 14.827,
|
36 |
+
"eval_steps_per_second": 0.463,
|
37 |
+
"eval_wer": 1.0,
|
38 |
+
"step": 1000
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.26,
|
42 |
+
"learning_rate": 5.62125e-05,
|
43 |
+
"loss": 2.2147,
|
44 |
+
"step": 1500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.26,
|
48 |
+
"eval_loss": 0.6520791053771973,
|
49 |
+
"eval_runtime": 1355.9385,
|
50 |
+
"eval_samples_per_second": 14.892,
|
51 |
+
"eval_steps_per_second": 0.465,
|
52 |
+
"eval_wer": 0.5567824255052013,
|
53 |
+
"step": 1500
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.35,
|
57 |
+
"learning_rate": 7.49625e-05,
|
58 |
+
"loss": 1.3017,
|
59 |
+
"step": 2000
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.35,
|
63 |
+
"eval_loss": 0.31525641679763794,
|
64 |
+
"eval_runtime": 1371.0684,
|
65 |
+
"eval_samples_per_second": 14.727,
|
66 |
+
"eval_steps_per_second": 0.46,
|
67 |
+
"eval_wer": 0.27607269814249236,
|
68 |
+
"step": 2000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.44,
|
72 |
+
"learning_rate": 7.431581352833637e-05,
|
73 |
+
"loss": 1.1196,
|
74 |
+
"step": 2500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.44,
|
78 |
+
"eval_loss": 0.24444133043289185,
|
79 |
+
"eval_runtime": 1363.4869,
|
80 |
+
"eval_samples_per_second": 14.809,
|
81 |
+
"eval_steps_per_second": 0.463,
|
82 |
+
"eval_wer": 0.23673497683411066,
|
83 |
+
"step": 2500
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 0.53,
|
87 |
+
"learning_rate": 7.363162705667275e-05,
|
88 |
+
"loss": 1.0712,
|
89 |
+
"step": 3000
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.53,
|
93 |
+
"eval_loss": 0.23236490786075592,
|
94 |
+
"eval_runtime": 1368.4487,
|
95 |
+
"eval_samples_per_second": 14.755,
|
96 |
+
"eval_steps_per_second": 0.461,
|
97 |
+
"eval_wer": 0.21321861436015543,
|
98 |
+
"step": 3000
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.62,
|
102 |
+
"learning_rate": 7.294606946983546e-05,
|
103 |
+
"loss": 1.052,
|
104 |
+
"step": 3500
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.62,
|
108 |
+
"eval_loss": 0.21734564006328583,
|
109 |
+
"eval_runtime": 1358.6503,
|
110 |
+
"eval_samples_per_second": 14.862,
|
111 |
+
"eval_steps_per_second": 0.464,
|
112 |
+
"eval_wer": 0.20317428528513493,
|
113 |
+
"step": 3500
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 2.13,
|
117 |
+
"learning_rate": 3.375103277334068e-05,
|
118 |
+
"loss": 1.2813,
|
119 |
+
"step": 4000
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 2.13,
|
123 |
+
"eval_loss": 0.332599401473999,
|
124 |
+
"eval_runtime": 393.989,
|
125 |
+
"eval_samples_per_second": 10.906,
|
126 |
+
"eval_steps_per_second": 0.343,
|
127 |
+
"eval_wer": 0.20989847979467358,
|
128 |
+
"step": 4000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 2.4,
|
132 |
+
"learning_rate": 2.3423299366565682e-05,
|
133 |
+
"loss": 1.2365,
|
134 |
+
"step": 4500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 2.4,
|
138 |
+
"eval_loss": 0.3223731815814972,
|
139 |
+
"eval_runtime": 391.7507,
|
140 |
+
"eval_samples_per_second": 10.969,
|
141 |
+
"eval_steps_per_second": 0.345,
|
142 |
+
"eval_wer": 0.2003283560376986,
|
143 |
+
"step": 4500
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 2.66,
|
147 |
+
"learning_rate": 1.309556595979069e-05,
|
148 |
+
"loss": 1.2193,
|
149 |
+
"step": 5000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 2.66,
|
153 |
+
"eval_loss": 0.31981074810028076,
|
154 |
+
"eval_runtime": 402.4439,
|
155 |
+
"eval_samples_per_second": 10.677,
|
156 |
+
"eval_steps_per_second": 0.335,
|
157 |
+
"eval_wer": 0.19565239980464894,
|
158 |
+
"step": 5000
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 2.93,
|
162 |
+
"learning_rate": 2.767832553015698e-06,
|
163 |
+
"loss": 1.2072,
|
164 |
+
"step": 5500
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 2.93,
|
168 |
+
"eval_loss": 0.3063456118106842,
|
169 |
+
"eval_runtime": 396.6525,
|
170 |
+
"eval_samples_per_second": 10.833,
|
171 |
+
"eval_steps_per_second": 0.34,
|
172 |
+
"eval_wer": 0.19327285763271923,
|
173 |
+
"step": 5500
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 3.2,
|
177 |
+
"learning_rate": 4.263388037141005e-05,
|
178 |
+
"loss": 1.213,
|
179 |
+
"step": 6000
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 3.2,
|
183 |
+
"eval_loss": 0.3051116168498993,
|
184 |
+
"eval_runtime": 371.5477,
|
185 |
+
"eval_samples_per_second": 11.565,
|
186 |
+
"eval_steps_per_second": 0.363,
|
187 |
+
"eval_wer": 0.19797998690732255,
|
188 |
+
"step": 6000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 3.46,
|
192 |
+
"learning_rate": 3.8585078816670256e-05,
|
193 |
+
"loss": 1.2074,
|
194 |
+
"step": 6500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 3.46,
|
198 |
+
"eval_loss": 0.3011966645717621,
|
199 |
+
"eval_runtime": 372.0587,
|
200 |
+
"eval_samples_per_second": 11.549,
|
201 |
+
"eval_steps_per_second": 0.363,
|
202 |
+
"eval_wer": 0.18792148549934018,
|
203 |
+
"step": 6500
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 3.73,
|
207 |
+
"learning_rate": 3.4536277261930465e-05,
|
208 |
+
"loss": 1.1918,
|
209 |
+
"step": 7000
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 3.73,
|
213 |
+
"eval_loss": 0.29471954703330994,
|
214 |
+
"eval_runtime": 372.8767,
|
215 |
+
"eval_samples_per_second": 11.524,
|
216 |
+
"eval_steps_per_second": 0.362,
|
217 |
+
"eval_wer": 0.18287145276764655,
|
218 |
+
"step": 7000
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 4.0,
|
222 |
+
"learning_rate": 3.0487475707190668e-05,
|
223 |
+
"loss": 1.1893,
|
224 |
+
"step": 7500
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 4.0,
|
228 |
+
"eval_loss": 0.28953900933265686,
|
229 |
+
"eval_runtime": 372.4558,
|
230 |
+
"eval_samples_per_second": 11.537,
|
231 |
+
"eval_steps_per_second": 0.362,
|
232 |
+
"eval_wer": 0.1807205129004437,
|
233 |
+
"step": 7500
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 4.26,
|
237 |
+
"learning_rate": 2.643867415245087e-05,
|
238 |
+
"loss": 1.1751,
|
239 |
+
"step": 8000
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 4.26,
|
243 |
+
"eval_loss": 0.2877567410469055,
|
244 |
+
"eval_runtime": 371.9244,
|
245 |
+
"eval_samples_per_second": 11.553,
|
246 |
+
"eval_steps_per_second": 0.363,
|
247 |
+
"eval_wer": 0.17759281773122604,
|
248 |
+
"step": 8000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 4.53,
|
252 |
+
"learning_rate": 2.2389872597711073e-05,
|
253 |
+
"loss": 1.1628,
|
254 |
+
"step": 8500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 4.53,
|
258 |
+
"eval_loss": 0.28352275490760803,
|
259 |
+
"eval_runtime": 373.4388,
|
260 |
+
"eval_samples_per_second": 11.507,
|
261 |
+
"eval_steps_per_second": 0.362,
|
262 |
+
"eval_wer": 0.1730727267059447,
|
263 |
+
"step": 8500
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 4.79,
|
267 |
+
"learning_rate": 1.834107104297128e-05,
|
268 |
+
"loss": 1.1577,
|
269 |
+
"step": 9000
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 4.79,
|
273 |
+
"eval_loss": 0.28156954050064087,
|
274 |
+
"eval_runtime": 371.5997,
|
275 |
+
"eval_samples_per_second": 11.564,
|
276 |
+
"eval_steps_per_second": 0.363,
|
277 |
+
"eval_wer": 0.17605494768124527,
|
278 |
+
"step": 9000
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 5.06,
|
282 |
+
"learning_rate": 1.4300367091340963e-05,
|
283 |
+
"loss": 1.1448,
|
284 |
+
"step": 9500
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 5.06,
|
288 |
+
"eval_loss": 0.2757455110549927,
|
289 |
+
"eval_runtime": 373.7148,
|
290 |
+
"eval_samples_per_second": 11.498,
|
291 |
+
"eval_steps_per_second": 0.361,
|
292 |
+
"eval_wer": 0.17397674491100096,
|
293 |
+
"step": 9500
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 5.33,
|
297 |
+
"learning_rate": 1.0251565536601165e-05,
|
298 |
+
"loss": 1.1407,
|
299 |
+
"step": 10000
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 5.33,
|
303 |
+
"eval_loss": 0.2768358588218689,
|
304 |
+
"eval_runtime": 373.2273,
|
305 |
+
"eval_samples_per_second": 11.513,
|
306 |
+
"eval_steps_per_second": 0.362,
|
307 |
+
"eval_wer": 0.17976453962613131,
|
308 |
+
"step": 10000
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 5.59,
|
312 |
+
"learning_rate": 6.202763981861369e-06,
|
313 |
+
"loss": 1.1401,
|
314 |
+
"step": 10500
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 5.59,
|
318 |
+
"eval_loss": 0.2780420780181885,
|
319 |
+
"eval_runtime": 375.3753,
|
320 |
+
"eval_samples_per_second": 11.447,
|
321 |
+
"eval_steps_per_second": 0.36,
|
322 |
+
"eval_wer": 0.18160374907779753,
|
323 |
+
"step": 10500
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 5.86,
|
327 |
+
"learning_rate": 2.153962427121572e-06,
|
328 |
+
"loss": 1.1333,
|
329 |
+
"step": 11000
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 5.86,
|
333 |
+
"eval_loss": 0.2748132646083832,
|
334 |
+
"eval_runtime": 371.6352,
|
335 |
+
"eval_samples_per_second": 11.562,
|
336 |
+
"eval_steps_per_second": 0.363,
|
337 |
+
"eval_wer": 0.17495350021301578,
|
338 |
+
"step": 11000
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 6.13,
|
342 |
+
"learning_rate": 4.029916195673358e-05,
|
343 |
+
"loss": 1.1571,
|
344 |
+
"step": 11500
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 6.13,
|
348 |
+
"eval_loss": 0.2807982861995697,
|
349 |
+
"eval_runtime": 393.9701,
|
350 |
+
"eval_samples_per_second": 10.907,
|
351 |
+
"eval_steps_per_second": 0.343,
|
352 |
+
"eval_wer": 0.17083865872793208,
|
353 |
+
"step": 11500
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 6.39,
|
357 |
+
"learning_rate": 3.8472032742155524e-05,
|
358 |
+
"loss": 1.1505,
|
359 |
+
"step": 12000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 6.39,
|
363 |
+
"eval_loss": 0.27258625626564026,
|
364 |
+
"eval_runtime": 389.5937,
|
365 |
+
"eval_samples_per_second": 11.029,
|
366 |
+
"eval_steps_per_second": 0.347,
|
367 |
+
"eval_wer": 0.16920726955329032,
|
368 |
+
"step": 12000
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 6.66,
|
372 |
+
"learning_rate": 3.6648557786006625e-05,
|
373 |
+
"loss": 1.1519,
|
374 |
+
"step": 12500
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 6.66,
|
378 |
+
"eval_loss": 0.2748955190181732,
|
379 |
+
"eval_runtime": 387.583,
|
380 |
+
"eval_samples_per_second": 11.087,
|
381 |
+
"eval_steps_per_second": 0.348,
|
382 |
+
"eval_wer": 0.16539376746989204,
|
383 |
+
"step": 12500
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 6.93,
|
387 |
+
"learning_rate": 3.482142857142857e-05,
|
388 |
+
"loss": 1.136,
|
389 |
+
"step": 13000
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 6.93,
|
393 |
+
"eval_loss": 0.276467502117157,
|
394 |
+
"eval_runtime": 393.6733,
|
395 |
+
"eval_samples_per_second": 10.915,
|
396 |
+
"eval_steps_per_second": 0.343,
|
397 |
+
"eval_wer": 0.16425075594625768,
|
398 |
+
"step": 13000
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 7.19,
|
402 |
+
"learning_rate": 3.299429935685051e-05,
|
403 |
+
"loss": 1.1326,
|
404 |
+
"step": 13500
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 7.19,
|
408 |
+
"eval_loss": 0.27056241035461426,
|
409 |
+
"eval_runtime": 391.6082,
|
410 |
+
"eval_samples_per_second": 10.973,
|
411 |
+
"eval_steps_per_second": 0.345,
|
412 |
+
"eval_wer": 0.1668277273813606,
|
413 |
+
"step": 13500
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 7.46,
|
417 |
+
"learning_rate": 3.116717014227246e-05,
|
418 |
+
"loss": 1.1342,
|
419 |
+
"step": 14000
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 7.46,
|
423 |
+
"eval_loss": 0.26654428243637085,
|
424 |
+
"eval_runtime": 388.567,
|
425 |
+
"eval_samples_per_second": 11.059,
|
426 |
+
"eval_steps_per_second": 0.347,
|
427 |
+
"eval_wer": 0.1638247243783576,
|
428 |
+
"step": 14000
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 7.72,
|
432 |
+
"learning_rate": 2.9340040927694404e-05,
|
433 |
+
"loss": 1.1286,
|
434 |
+
"step": 14500
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 7.72,
|
438 |
+
"eval_loss": 0.2668865919113159,
|
439 |
+
"eval_runtime": 384.4478,
|
440 |
+
"eval_samples_per_second": 11.177,
|
441 |
+
"eval_steps_per_second": 0.351,
|
442 |
+
"eval_wer": 0.1635857310597795,
|
443 |
+
"step": 14500
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 7.99,
|
447 |
+
"learning_rate": 2.7516565971545504e-05,
|
448 |
+
"loss": 1.1243,
|
449 |
+
"step": 15000
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 7.99,
|
453 |
+
"eval_loss": 0.2619013488292694,
|
454 |
+
"eval_runtime": 392.1143,
|
455 |
+
"eval_samples_per_second": 10.959,
|
456 |
+
"eval_steps_per_second": 0.344,
|
457 |
+
"eval_wer": 0.16234920041148415,
|
458 |
+
"step": 15000
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 8.26,
|
462 |
+
"learning_rate": 2.5689436756967453e-05,
|
463 |
+
"loss": 1.1173,
|
464 |
+
"step": 15500
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 8.26,
|
468 |
+
"eval_loss": 0.2651631236076355,
|
469 |
+
"eval_runtime": 388.7223,
|
470 |
+
"eval_samples_per_second": 11.054,
|
471 |
+
"eval_steps_per_second": 0.347,
|
472 |
+
"eval_wer": 0.16037490777975208,
|
473 |
+
"step": 15500
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 8.52,
|
477 |
+
"learning_rate": 2.3862307542389395e-05,
|
478 |
+
"loss": 1.1129,
|
479 |
+
"step": 16000
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 8.52,
|
483 |
+
"eval_loss": 0.26095372438430786,
|
484 |
+
"eval_runtime": 387.1141,
|
485 |
+
"eval_samples_per_second": 11.1,
|
486 |
+
"eval_steps_per_second": 0.349,
|
487 |
+
"eval_wer": 0.1597514469486788,
|
488 |
+
"step": 16000
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 8.79,
|
492 |
+
"learning_rate": 2.203517832781134e-05,
|
493 |
+
"loss": 1.1091,
|
494 |
+
"step": 16500
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 8.79,
|
498 |
+
"eval_loss": 0.2608127295970917,
|
499 |
+
"eval_runtime": 386.5271,
|
500 |
+
"eval_samples_per_second": 11.117,
|
501 |
+
"eval_steps_per_second": 0.349,
|
502 |
+
"eval_wer": 0.15837983312031756,
|
503 |
+
"step": 16500
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 9.06,
|
507 |
+
"learning_rate": 2.0208049113233286e-05,
|
508 |
+
"loss": 1.1053,
|
509 |
+
"step": 17000
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 9.06,
|
513 |
+
"eval_loss": 0.2632738947868347,
|
514 |
+
"eval_runtime": 389.2784,
|
515 |
+
"eval_samples_per_second": 11.038,
|
516 |
+
"eval_steps_per_second": 0.347,
|
517 |
+
"eval_wer": 0.1664016958134605,
|
518 |
+
"step": 17000
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 9.32,
|
522 |
+
"learning_rate": 1.8384574157084387e-05,
|
523 |
+
"loss": 1.1004,
|
524 |
+
"step": 17500
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 9.32,
|
528 |
+
"eval_loss": 0.2594461441040039,
|
529 |
+
"eval_runtime": 388.9349,
|
530 |
+
"eval_samples_per_second": 11.048,
|
531 |
+
"eval_steps_per_second": 0.347,
|
532 |
+
"eval_wer": 0.16618348452258486,
|
533 |
+
"step": 17500
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 9.59,
|
537 |
+
"learning_rate": 1.6557444942506332e-05,
|
538 |
+
"loss": 1.0995,
|
539 |
+
"step": 18000
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 9.59,
|
543 |
+
"eval_loss": 0.26234543323516846,
|
544 |
+
"eval_runtime": 383.4387,
|
545 |
+
"eval_samples_per_second": 11.206,
|
546 |
+
"eval_steps_per_second": 0.352,
|
547 |
+
"eval_wer": 0.15694587320884898,
|
548 |
+
"step": 18000
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 9.86,
|
552 |
+
"learning_rate": 1.4730315727928276e-05,
|
553 |
+
"loss": 1.0964,
|
554 |
+
"step": 18500
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 9.86,
|
558 |
+
"eval_loss": 0.26244357228279114,
|
559 |
+
"eval_runtime": 384.9493,
|
560 |
+
"eval_samples_per_second": 11.163,
|
561 |
+
"eval_steps_per_second": 0.351,
|
562 |
+
"eval_wer": 0.15968910086557145,
|
563 |
+
"step": 18500
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 10.12,
|
567 |
+
"learning_rate": 1.2903186513350224e-05,
|
568 |
+
"loss": 1.09,
|
569 |
+
"step": 19000
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 10.12,
|
573 |
+
"eval_loss": 0.2576591968536377,
|
574 |
+
"eval_runtime": 391.5397,
|
575 |
+
"eval_samples_per_second": 10.975,
|
576 |
+
"eval_steps_per_second": 0.345,
|
577 |
+
"eval_wer": 0.15782910938620281,
|
578 |
+
"step": 19000
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 10.39,
|
582 |
+
"learning_rate": 1.108336581563048e-05,
|
583 |
+
"loss": 1.089,
|
584 |
+
"step": 19500
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 10.39,
|
588 |
+
"eval_loss": 0.25744903087615967,
|
589 |
+
"eval_runtime": 384.7348,
|
590 |
+
"eval_samples_per_second": 11.169,
|
591 |
+
"eval_steps_per_second": 0.351,
|
592 |
+
"eval_wer": 0.1531219801115995,
|
593 |
+
"step": 19500
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 10.66,
|
597 |
+
"learning_rate": 9.256236601052426e-06,
|
598 |
+
"loss": 1.0864,
|
599 |
+
"step": 20000
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 10.66,
|
603 |
+
"eval_loss": 0.2556162476539612,
|
604 |
+
"eval_runtime": 391.8515,
|
605 |
+
"eval_samples_per_second": 10.966,
|
606 |
+
"eval_steps_per_second": 0.345,
|
607 |
+
"eval_wer": 0.15464945914772904,
|
608 |
+
"step": 20000
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 10.92,
|
612 |
+
"learning_rate": 7.429107386474371e-06,
|
613 |
+
"loss": 1.0806,
|
614 |
+
"step": 20500
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 10.92,
|
618 |
+
"eval_loss": 0.2548317313194275,
|
619 |
+
"eval_runtime": 384.3272,
|
620 |
+
"eval_samples_per_second": 11.181,
|
621 |
+
"eval_steps_per_second": 0.351,
|
622 |
+
"eval_wer": 0.1583174870372102,
|
623 |
+
"step": 20500
|
624 |
+
},
|
625 |
+
{
|
626 |
+
"epoch": 11.19,
|
627 |
+
"learning_rate": 5.6019781718963155e-06,
|
628 |
+
"loss": 1.0842,
|
629 |
+
"step": 21000
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 11.19,
|
633 |
+
"eval_loss": 0.25501224398612976,
|
634 |
+
"eval_runtime": 383.8764,
|
635 |
+
"eval_samples_per_second": 11.194,
|
636 |
+
"eval_steps_per_second": 0.352,
|
637 |
+
"eval_wer": 0.1542026455521265,
|
638 |
+
"step": 21000
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 11.45,
|
642 |
+
"learning_rate": 3.774848957318261e-06,
|
643 |
+
"loss": 1.0805,
|
644 |
+
"step": 21500
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 11.45,
|
648 |
+
"eval_loss": 0.25607678294181824,
|
649 |
+
"eval_runtime": 388.7678,
|
650 |
+
"eval_samples_per_second": 11.053,
|
651 |
+
"eval_steps_per_second": 0.347,
|
652 |
+
"eval_wer": 0.15236343610046033,
|
653 |
+
"step": 21500
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 11.72,
|
657 |
+
"learning_rate": 1.9477197427402063e-06,
|
658 |
+
"loss": 1.0722,
|
659 |
+
"step": 22000
|
660 |
+
},
|
661 |
+
{
|
662 |
+
"epoch": 11.72,
|
663 |
+
"eval_loss": 0.25402259826660156,
|
664 |
+
"eval_runtime": 385.5053,
|
665 |
+
"eval_samples_per_second": 11.146,
|
666 |
+
"eval_steps_per_second": 0.35,
|
667 |
+
"eval_wer": 0.1565614056963538,
|
668 |
+
"step": 22000
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 11.99,
|
672 |
+
"learning_rate": 1.2059052816215163e-07,
|
673 |
+
"loss": 1.0763,
|
674 |
+
"step": 22500
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 11.99,
|
678 |
+
"eval_loss": 0.2549177408218384,
|
679 |
+
"eval_runtime": 379.953,
|
680 |
+
"eval_samples_per_second": 11.309,
|
681 |
+
"eval_steps_per_second": 0.355,
|
682 |
+
"eval_wer": 0.15720564855512953,
|
683 |
+
"step": 22500
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 12.0,
|
687 |
+
"step": 22524,
|
688 |
+
"total_flos": 6.281601139352125e+20,
|
689 |
+
"train_loss": 0.5676147035501541,
|
690 |
+
"train_runtime": 172546.67,
|
691 |
+
"train_samples_per_second": 16.714,
|
692 |
+
"train_steps_per_second": 0.131
|
693 |
+
}
|
694 |
+
],
|
695 |
+
"max_steps": 22524,
|
696 |
+
"num_train_epochs": 12,
|
697 |
+
"total_flos": 6.281601139352125e+20,
|
698 |
+
"trial_name": null,
|
699 |
+
"trial_params": null
|
700 |
+
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262112241
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39fa76fb2ec03774fc8c4aa8489fca5d270344d70cfc1d74df96b2737119bfde
|
3 |
size 1262112241
|
runs/Feb04_14-58-29_job-336a688f-553a-4e6e-83b3-ad5d10274b51/1643989411.4467487/events.out.tfevents.1643989411.job-336a688f-553a-4e6e-83b3-ad5d10274b51.728502.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a74d331c074b656f428d24db8dce4efbe1b7f1dde7e244fac7207dc29ae942c3
|
3 |
+
size 4814
|
runs/Feb04_14-58-29_job-336a688f-553a-4e6e-83b3-ad5d10274b51/events.out.tfevents.1643989411.job-336a688f-553a-4e6e-83b3-ad5d10274b51.728502.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c4c8c21717b713877aa8ac7a90603991568c4a02c47c28cd84f8cc50ba68e7e
|
3 |
+
size 5233
|
special_tokens_map.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
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:eb4880e33458fbd00defffaa2d4a3e6ec806898ed51633382a67c03e0088e649
|
3 |
size 3055
|