Update README.md
Browse files
README.md
CHANGED
|
@@ -23,19 +23,6 @@ metrics:
|
|
| 23 |
- accuracy
|
| 24 |
model-index:
|
| 25 |
- name: pixel-base-finetuned-xnli-translate-train-all
|
| 26 |
-
results:
|
| 27 |
-
- task:
|
| 28 |
-
name: Text Classification
|
| 29 |
-
type: text-classification
|
| 30 |
-
dataset:
|
| 31 |
-
name: XNLI
|
| 32 |
-
type: xnli
|
| 33 |
-
args: xnli
|
| 34 |
-
metrics:
|
| 35 |
-
- name: Accuracy
|
| 36 |
-
type: accuracy
|
| 37 |
-
value: 0.6254886211512718
|
| 38 |
-
---
|
| 39 |
|
| 40 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 41 |
should probably proofread and complete it, then remove this comment. -->
|
|
@@ -43,9 +30,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 43 |
# pixel-base-finetuned-xnli-translate-train-all
|
| 44 |
|
| 45 |
This model is a fine-tuned version of [Team-PIXEL/pixel-base](https://huggingface.co/Team-PIXEL/pixel-base) on the XNLI dataset.
|
| 46 |
-
It achieves the following results on the evaluation set:
|
| 47 |
-
- Loss: 0.8312
|
| 48 |
-
- Accuracy: 0.6255
|
| 49 |
|
| 50 |
## Model description
|
| 51 |
|
|
@@ -74,62 +58,6 @@ The following hyperparameters were used during training:
|
|
| 74 |
- training_steps: 50000
|
| 75 |
- mixed_precision_training: Apex, opt level O1
|
| 76 |
|
| 77 |
-
### Training results
|
| 78 |
-
|
| 79 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 80 |
-
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 81 |
-
| 1.0422 | 0.04 | 1000 | 1.0647 | 0.4250 |
|
| 82 |
-
| 0.9622 | 0.09 | 2000 | 1.0015 | 0.5051 |
|
| 83 |
-
| 0.93 | 0.13 | 3000 | 0.9750 | 0.5285 |
|
| 84 |
-
| 0.9126 | 0.17 | 4000 | 0.9396 | 0.5488 |
|
| 85 |
-
| 0.9033 | 0.22 | 5000 | 0.9353 | 0.5603 |
|
| 86 |
-
| 0.8861 | 0.26 | 6000 | 0.9369 | 0.5606 |
|
| 87 |
-
| 0.8799 | 0.3 | 7000 | 0.9407 | 0.5575 |
|
| 88 |
-
| 0.8627 | 0.35 | 8000 | 0.9079 | 0.5774 |
|
| 89 |
-
| 0.8658 | 0.39 | 9000 | 0.9110 | 0.5711 |
|
| 90 |
-
| 0.8521 | 0.43 | 10000 | 0.8945 | 0.5837 |
|
| 91 |
-
| 0.8562 | 0.48 | 11000 | 0.8818 | 0.5871 |
|
| 92 |
-
| 0.8479 | 0.52 | 12000 | 0.8771 | 0.5938 |
|
| 93 |
-
| 0.8451 | 0.56 | 13000 | 0.8965 | 0.5844 |
|
| 94 |
-
| 0.8433 | 0.61 | 14000 | 0.8814 | 0.5937 |
|
| 95 |
-
| 0.8331 | 0.65 | 15000 | 0.8721 | 0.5983 |
|
| 96 |
-
| 0.8267 | 0.7 | 16000 | 0.8691 | 0.5978 |
|
| 97 |
-
| 0.8254 | 0.74 | 17000 | 0.8646 | 0.5999 |
|
| 98 |
-
| 0.8214 | 0.78 | 18000 | 0.8700 | 0.6004 |
|
| 99 |
-
| 0.815 | 0.83 | 19000 | 0.8621 | 0.6016 |
|
| 100 |
-
| 0.8145 | 0.87 | 20000 | 0.8482 | 0.6119 |
|
| 101 |
-
| 0.8067 | 0.91 | 21000 | 0.8601 | 0.6053 |
|
| 102 |
-
| 0.8063 | 0.96 | 22000 | 0.8535 | 0.6093 |
|
| 103 |
-
| 0.8008 | 1.0 | 23000 | 0.8455 | 0.6123 |
|
| 104 |
-
| 0.7863 | 1.04 | 24000 | 0.8524 | 0.6107 |
|
| 105 |
-
| 0.7918 | 1.09 | 25000 | 0.8450 | 0.6142 |
|
| 106 |
-
| 0.7746 | 1.13 | 26000 | 0.8531 | 0.6095 |
|
| 107 |
-
| 0.7855 | 1.17 | 27000 | 0.8442 | 0.6150 |
|
| 108 |
-
| 0.7903 | 1.22 | 28000 | 0.8386 | 0.6162 |
|
| 109 |
-
| 0.7808 | 1.26 | 29000 | 0.8403 | 0.6178 |
|
| 110 |
-
| 0.7847 | 1.3 | 30000 | 0.8421 | 0.6145 |
|
| 111 |
-
| 0.7822 | 1.35 | 31000 | 0.8427 | 0.6157 |
|
| 112 |
-
| 0.769 | 1.39 | 32000 | 0.8397 | 0.6187 |
|
| 113 |
-
| 0.7822 | 1.43 | 33000 | 0.8315 | 0.6213 |
|
| 114 |
-
| 0.771 | 1.48 | 34000 | 0.8505 | 0.6141 |
|
| 115 |
-
| 0.7713 | 1.52 | 35000 | 0.8482 | 0.6142 |
|
| 116 |
-
| 0.7663 | 1.56 | 36000 | 0.8490 | 0.6169 |
|
| 117 |
-
| 0.7653 | 1.61 | 37000 | 0.8295 | 0.6229 |
|
| 118 |
-
| 0.7669 | 1.65 | 38000 | 0.8313 | 0.6217 |
|
| 119 |
-
| 0.77 | 1.69 | 39000 | 0.8309 | 0.6234 |
|
| 120 |
-
| 0.763 | 1.74 | 40000 | 0.8310 | 0.6256 |
|
| 121 |
-
| 0.7609 | 1.78 | 41000 | 0.8302 | 0.6228 |
|
| 122 |
-
| 0.7627 | 1.83 | 42000 | 0.8242 | 0.6269 |
|
| 123 |
-
| 0.7617 | 1.87 | 43000 | 0.8232 | 0.6264 |
|
| 124 |
-
| 0.7636 | 1.91 | 44000 | 0.8265 | 0.6261 |
|
| 125 |
-
| 0.7585 | 1.96 | 45000 | 0.8258 | 0.6268 |
|
| 126 |
-
| 0.7572 | 2.0 | 46000 | 0.8223 | 0.6278 |
|
| 127 |
-
| 0.7396 | 2.04 | 47000 | 0.8348 | 0.6242 |
|
| 128 |
-
| 0.7344 | 2.09 | 48000 | 0.8299 | 0.6270 |
|
| 129 |
-
| 0.7385 | 2.13 | 49000 | 0.8314 | 0.6240 |
|
| 130 |
-
| 0.7275 | 2.17 | 50000 | 0.8312 | 0.6255 |
|
| 131 |
-
|
| 132 |
-
|
| 133 |
### Framework versions
|
| 134 |
|
| 135 |
- Transformers 4.17.0
|
|
|
|
| 23 |
- accuracy
|
| 24 |
model-index:
|
| 25 |
- name: pixel-base-finetuned-xnli-translate-train-all
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
|
| 27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 28 |
should probably proofread and complete it, then remove this comment. -->
|
|
|
|
| 30 |
# pixel-base-finetuned-xnli-translate-train-all
|
| 31 |
|
| 32 |
This model is a fine-tuned version of [Team-PIXEL/pixel-base](https://huggingface.co/Team-PIXEL/pixel-base) on the XNLI dataset.
|
|
|
|
|
|
|
|
|
|
| 33 |
|
| 34 |
## Model description
|
| 35 |
|
|
|
|
| 58 |
- training_steps: 50000
|
| 59 |
- mixed_precision_training: Apex, opt level O1
|
| 60 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
### Framework versions
|
| 62 |
|
| 63 |
- Transformers 4.17.0
|