Update README.md
Browse files
README.md
CHANGED
|
@@ -54,6 +54,41 @@ The following hyperparameters were used during training:
|
|
| 54 |
- training_steps: 3000
|
| 55 |
- mixed_precision_training: Native AMP
|
| 56 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
### Framework versions
|
| 58 |
|
| 59 |
- Transformers 4.41.2
|
|
|
|
| 54 |
- training_steps: 3000
|
| 55 |
- mixed_precision_training: Native AMP
|
| 56 |
|
| 57 |
+
### Training results
|
| 58 |
+
|
| 59 |
+
| **Step** | **Training Loss** | **Validation Loss** | **Bleu** | **Chrf** | **Wer** |
|
| 60 |
+
|---------:|------------------:|--------------------:|----------:|----------:|-----------:|
|
| 61 |
+
| 100 | 2.351300 | 1.908078 | 6.230000 | 21.980000 | 117.424584 |
|
| 62 |
+
| 200 | 1.831200 | 1.567262 | 10.800000 | 30.010000 | 109.770374 |
|
| 63 |
+
| 300 | 1.494100 | 1.421244 | 13.550000 | 33.480000 | 120.306168 |
|
| 64 |
+
| 400 | 1.309900 | 1.326882 | 19.540000 | 41.060000 | 77.217470 |
|
| 65 |
+
| 500 | 1.069600 | 1.285087 | 19.100000 | 40.230000 | 95.767672 |
|
| 66 |
+
| 600 | 0.889600 | 1.255216 | 16.450000 | 38.590000 | 110.445745 |
|
| 67 |
+
| 700 | 0.783700 | 1.204875 | 30.430000 | 47.940000 | 63.574966 |
|
| 68 |
+
| 800 | 0.653300 | 1.213243 | 24.280000 | 43.240000 | 72.219721 |
|
| 69 |
+
| 900 | 0.585300 | 1.246309 | 29.130000 | 44.890000 | 64.295362 |
|
| 70 |
+
| 1000 | 0.471100 | 1.236493 | 26.550000 | 45.000000 | 70.688879 |
|
| 71 |
+
| 1100 | 0.228500 | 1.271864 | 26.430000 | 45.950000 | 73.525439 |
|
| 72 |
+
| 1200 | 0.213200 | 1.297864 | 28.940000 | 45.720000 | 65.736155 |
|
| 73 |
+
| 1300 | 0.184800 | 1.262461 | 27.330000 | 46.820000 | 72.264746 |
|
| 74 |
+
| 1400 | 0.195100 | 1.283275 | 29.740000 | 46.850000 | 64.745610 |
|
| 75 |
+
| 1500 | 0.172600 | 1.252396 | 29.330000 | 46.390000 | 64.655561 |
|
| 76 |
+
| 1600 | 0.164400 | 1.295237 | 25.880000 | 45.290000 | 74.110761 |
|
| 77 |
+
| 1700 | 0.144700 | 1.291115 | 24.490000 | 44.950000 | 71.994597 |
|
| 78 |
+
| 1800 | 0.148200 | 1.260603 | 29.300000 | 46.220000 | 63.935164 |
|
| 79 |
+
| 1900 | 0.115800 | 1.292712 | 29.480000 | 46.770000 | 63.980189 |
|
| 80 |
+
| 2000 | 0.105900 | 1.293839 | 29.150000 | 47.870000 | 67.086898 |
|
| 81 |
+
| 2100 | 0.086100 | 1.295070 | 28.820000 | 47.200000 | 64.700585 |
|
| 82 |
+
| 2200 | 0.035700 | 1.303162 | 30.170000 | 47.570000 | 64.745610 |
|
| 83 |
+
| 2300 | 0.032700 | 1.324677 | 27.020000 | 45.370000 | 73.075191 |
|
| 84 |
+
| 2400 | 0.031700 | 1.286437 | 30.480000 | 48.450000 | 63.619991 |
|
| 85 |
+
| 2500 | 0.031200 | 1.305244 | 32.510000 | 49.490000 | 61.278703 |
|
| 86 |
+
| 2600 | 0.027300 | 1.306147 | 31.860000 | 49.900000 | 63.124719 |
|
| 87 |
+
| 2700 | 0.027000 | 1.321022 | 32.000000 | 49.300000 | 63.124719 |
|
| 88 |
+
| 2800 | 0.023100 | 1.305768 | 32.190000 | 49.760000 | 61.413778 |
|
| 89 |
+
| 2900 | 0.020800 | 1.319407 | 32.070000 | 48.470000 | 62.179199 |
|
| 90 |
+
| 3000 | 0.022800 | 1.318355 | 32.150000 | 48.490000 | 61.638901 |
|
| 91 |
+
|
| 92 |
### Framework versions
|
| 93 |
|
| 94 |
- Transformers 4.41.2
|