Hugging Face's logo

andrewbawitlung
/
qwen3-asr-0.6b-mizonal3-E4-lus-v2026.06

Automatic Speech Recognition
TensorBoard
Safetensors
Lushai
qwen3_asr
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
andrewbawitlung commited on
Commit
a6aae33
·
verified ·
1 Parent(s): 08a379d

Add CER, hyperparameters, and training logs to README

Browse files
Files changed (1) hide show
  1. README.md +21 -21
README.md CHANGED
@@ -114,25 +114,25 @@ The following hyperparameters were used during training:
114
 
115
  | step | epoch | train_loss | eval_loss | eval_wer | eval_cer | learning_rate | grad_norm |
116
  | --- | --- | --- | --- | --- | --- | --- | --- |
117
- | 200 | 0.36 | 0.3447 | 0.5944 | 0.43 | 0.11 | 1.95e-05 | 27.88 |
118
- | 400 | 0.73 | 0.2183 | 0.3971 | 0.33 | 0.08 | 1.86e-05 | 9.94 |
119
- | 600 | 1.09 | 0.1382 | 0.3338 | 0.27 | 0.06 | 1.76e-05 | 9.44 |
120
- | 800 | 1.46 | 0.0984 | 0.3060 | 0.25 | 0.06 | 1.67e-05 | 4.19 |
121
- | 1000 | 1.82 | 0.1005 | 0.2859 | 0.23 | 0.05 | 1.58e-05 | 4.47 |
122
- | 1200 | 2.19 | 0.0763 | 0.2803 | 0.22 | 0.05 | 1.48e-05 | 6.12 |
123
- | 1400 | 2.55 | 0.0566 | 0.2762 | 0.21 | 0.05 | 1.39e-05 | 4.47 |
124
- | 1600 | 2.91 | 0.0576 | 0.2692 | 0.21 | 0.05 | 1.30e-05 | 4.25 |
125
- | 1800 | 3.28 | 0.0401 | 0.2816 | 0.21 | 0.05 | 1.20e-05 | 3.98 |
126
- | 2000 | 3.64 | 0.0317 | 0.2860 | 0.20 | 0.05 | 1.11e-05 | 6.34 |
127
- | 2200 | 4.01 | 0.0396 | 0.2856 | 0.21 | 0.05 | 1.02e-05 | 4.41 |
128
- | 2400 | 4.37 | 0.0219 | 0.3018 | 0.21 | 0.05 | 9.26e-06 | 4.47 |
129
- | 2600 | 4.74 | 0.0200 | 0.2963 | 0.21 | 0.05 | 8.33e-06 | 6.00 |
130
- | 2800 | 5.10 | 0.0109 | 0.3231 | 0.21 | 0.05 | 7.40e-06 | 2.19 |
131
- | 3000 | 5.46 | 0.0113 | 0.3205 | 0.21 | 0.05 | 6.47e-06 | 2.75 |
132
- | 3200 | 5.83 | 0.0100 | 0.3252 | 0.21 | 0.05 | 5.54e-06 | 1.66 |
133
- | 3400 | 6.19 | 0.0079 | 0.3390 | 0.21 | 0.05 | 4.61e-06 | 0.77 |
134
- | 3600 | 6.56 | 0.0084 | 0.3384 | 0.21 | 0.05 | 3.68e-06 | 1.29 |
135
- | 3800 | 6.92 | 0.0083 | 0.3375 | 0.21 | 0.05 | 2.76e-06 | 2.17 |
136
- | 4000 | 7.29 | 0.0087 | 0.3430 | 0.21 | 0.05 | 1.83e-06 | 2.41 |
137
- | 4200 | 7.65 | 0.0070 | 0.3444 | 0.21 | 0.05 | 8.97e-07 | 3.73 |
138
 
 
114
 
115
  | step | epoch | train_loss | eval_loss | eval_wer | eval_cer | learning_rate | grad_norm |
116
  | --- | --- | --- | --- | --- | --- | --- | --- |
117
+ | 200 | 0.36 | 0.3447 | 0.5944 | 43.21 | 11.49 | 1.95e-05 | 27.88 |
118
+ | 400 | 0.73 | 0.2183 | 0.3971 | 32.67 | 8.08 | 1.86e-05 | 9.94 |
119
+ | 600 | 1.09 | 0.1382 | 0.3338 | 27.18 | 6.40 | 1.76e-05 | 9.44 |
120
+ | 800 | 1.46 | 0.0984 | 0.3060 | 24.81 | 5.92 | 1.67e-05 | 4.19 |
121
+ | 1000 | 1.82 | 0.1005 | 0.2859 | 23.03 | 5.36 | 1.58e-05 | 4.47 |
122
+ | 1200 | 2.19 | 0.0763 | 0.2803 | 21.74 | 5.16 | 1.48e-05 | 6.12 |
123
+ | 1400 | 2.55 | 0.0566 | 0.2762 | 21.13 | 4.91 | 1.39e-05 | 4.47 |
124
+ | 1600 | 2.91 | 0.0576 | 0.2692 | 21.14 | 4.81 | 1.30e-05 | 4.25 |
125
+ | 1800 | 3.28 | 0.0401 | 0.2816 | 20.85 | 4.85 | 1.20e-05 | 3.98 |
126
+ | 2000 | 3.64 | 0.0317 | 0.2860 | 20.30 | 4.69 | 1.11e-05 | 6.34 |
127
+ | 2200 | 4.01 | 0.0396 | 0.2856 | 20.52 | 4.71 | 1.02e-05 | 4.41 |
128
+ | 2400 | 4.37 | 0.0219 | 0.3018 | 20.54 | 4.82 | 9.26e-06 | 4.47 |
129
+ | 2600 | 4.74 | 0.0200 | 0.2963 | 20.79 | 4.90 | 8.33e-06 | 6.00 |
130
+ | 2800 | 5.10 | 0.0109 | 0.3231 | 20.76 | 4.80 | 7.40e-06 | 2.19 |
131
+ | 3000 | 5.46 | 0.0113 | 0.3205 | 20.75 | 4.85 | 6.47e-06 | 2.75 |
132
+ | 3200 | 5.83 | 0.0100 | 0.3252 | 20.54 | 4.78 | 5.54e-06 | 1.66 |
133
+ | 3400 | 6.19 | 0.0079 | 0.3390 | 21.07 | 4.99 | 4.61e-06 | 0.77 |
134
+ | 3600 | 6.56 | 0.0084 | 0.3384 | 20.97 | 4.97 | 3.68e-06 | 1.29 |
135
+ | 3800 | 6.92 | 0.0083 | 0.3375 | 20.72 | 4.85 | 2.76e-06 | 2.17 |
136
+ | 4000 | 7.29 | 0.0087 | 0.3430 | 20.73 | 4.89 | 1.83e-06 | 2.41 |
137
+ | 4200 | 7.65 | 0.0070 | 0.3444 | 20.72 | 4.91 | 8.97e-07 | 3.73 |
138