update model card README.md
Browse files
README.md
CHANGED
|
@@ -3,6 +3,8 @@ license: mit
|
|
| 3 |
base_model: gpt2-medium
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: results
|
| 8 |
results: []
|
|
@@ -15,7 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on the None dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 0.
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -44,92 +47,92 @@ The following hyperparameters were used during training:
|
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
| 47 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
-
|
| 49 |
-
| 0.
|
| 50 |
-
| 0.
|
| 51 |
-
| 0.
|
| 52 |
-
| 0.
|
| 53 |
-
| 0.
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
| 106 |
-
| 0.
|
| 107 |
-
| 0.
|
| 108 |
-
| 0.
|
| 109 |
-
| 0.
|
| 110 |
-
| 0.
|
| 111 |
-
| 0.
|
| 112 |
-
| 0.
|
| 113 |
-
| 0.
|
| 114 |
-
| 0.
|
| 115 |
-
| 0.
|
| 116 |
-
| 0.
|
| 117 |
-
| 0.
|
| 118 |
-
| 0.
|
| 119 |
-
| 0.
|
| 120 |
-
| 0.
|
| 121 |
-
| 0.
|
| 122 |
-
| 0.
|
| 123 |
-
| 0.
|
| 124 |
-
| 0.
|
| 125 |
-
| 0.
|
| 126 |
-
| 0.
|
| 127 |
-
| 0.
|
| 128 |
-
| 0.
|
| 129 |
-
| 0.
|
| 130 |
-
| 0.
|
| 131 |
-
| 0.
|
| 132 |
-
| 0.
|
| 133 |
|
| 134 |
|
| 135 |
### Framework versions
|
|
|
|
| 3 |
base_model: gpt2-medium
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
model-index:
|
| 9 |
- name: results
|
| 10 |
results: []
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on the None dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.5570
|
| 21 |
+
- Accuracy: 0.7508
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 52 |
+
| 0.6473 | 0.04 | 50 | 0.5683 | 0.7454 |
|
| 53 |
+
| 0.6367 | 0.07 | 100 | 0.5670 | 0.7525 |
|
| 54 |
+
| 0.6016 | 0.11 | 150 | 0.5676 | 0.7508 |
|
| 55 |
+
| 0.6014 | 0.14 | 200 | 0.5498 | 0.75 |
|
| 56 |
+
| 0.5801 | 0.18 | 250 | 0.5446 | 0.75 |
|
| 57 |
+
| 0.4534 | 0.21 | 300 | 0.5383 | 0.7512 |
|
| 58 |
+
| 0.669 | 0.25 | 350 | 0.5700 | 0.75 |
|
| 59 |
+
| 0.5556 | 0.29 | 400 | 0.5536 | 0.7496 |
|
| 60 |
+
| 0.5652 | 0.32 | 450 | 0.6341 | 0.75 |
|
| 61 |
+
| 0.5801 | 0.36 | 500 | 0.5416 | 0.7454 |
|
| 62 |
+
| 0.6476 | 0.39 | 550 | 0.5319 | 0.7508 |
|
| 63 |
+
| 0.5473 | 0.43 | 600 | 0.5422 | 0.7492 |
|
| 64 |
+
| 0.5094 | 0.46 | 650 | 0.5532 | 0.7504 |
|
| 65 |
+
| 0.5656 | 0.5 | 700 | 0.5375 | 0.7504 |
|
| 66 |
+
| 0.532 | 0.54 | 750 | 0.5617 | 0.7137 |
|
| 67 |
+
| 0.5738 | 0.57 | 800 | 0.5501 | 0.7521 |
|
| 68 |
+
| 0.544 | 0.61 | 850 | 0.5449 | 0.7538 |
|
| 69 |
+
| 0.5271 | 0.64 | 900 | 0.5682 | 0.7496 |
|
| 70 |
+
| 0.9725 | 0.68 | 950 | 0.7980 | 0.4921 |
|
| 71 |
+
| 0.5955 | 0.71 | 1000 | 0.5220 | 0.7538 |
|
| 72 |
+
| 0.5588 | 0.75 | 1050 | 0.5247 | 0.75 |
|
| 73 |
+
| 0.612 | 0.79 | 1100 | 0.5183 | 0.7483 |
|
| 74 |
+
| 0.6124 | 0.82 | 1150 | 0.5260 | 0.7542 |
|
| 75 |
+
| 0.421 | 0.86 | 1200 | 0.5509 | 0.7508 |
|
| 76 |
+
| 0.4582 | 0.89 | 1250 | 0.5249 | 0.75 |
|
| 77 |
+
| 0.588 | 0.93 | 1300 | 0.5633 | 0.7267 |
|
| 78 |
+
| 0.549 | 0.96 | 1350 | 0.5179 | 0.7492 |
|
| 79 |
+
| 0.495 | 1.0 | 1400 | 0.5456 | 0.7512 |
|
| 80 |
+
| 0.435 | 1.04 | 1450 | 0.5596 | 0.7504 |
|
| 81 |
+
| 0.6061 | 1.07 | 1500 | 0.5421 | 0.7433 |
|
| 82 |
+
| 0.5542 | 1.11 | 1550 | 0.5117 | 0.7554 |
|
| 83 |
+
| 0.4277 | 1.14 | 1600 | 0.5291 | 0.7521 |
|
| 84 |
+
| 0.4415 | 1.18 | 1650 | 0.5354 | 0.7538 |
|
| 85 |
+
| 0.5029 | 1.21 | 1700 | 0.5084 | 0.7579 |
|
| 86 |
+
| 0.6079 | 1.25 | 1750 | 0.5798 | 0.7554 |
|
| 87 |
+
| 0.5692 | 1.29 | 1800 | 0.5003 | 0.755 |
|
| 88 |
+
| 0.5297 | 1.32 | 1850 | 0.5563 | 0.7588 |
|
| 89 |
+
| 0.6938 | 1.36 | 1900 | 0.5064 | 0.7529 |
|
| 90 |
+
| 0.5679 | 1.39 | 1950 | 0.5505 | 0.7508 |
|
| 91 |
+
| 0.4503 | 1.43 | 2000 | 0.5133 | 0.7554 |
|
| 92 |
+
| 0.519 | 1.46 | 2050 | 0.4946 | 0.7525 |
|
| 93 |
+
| 0.513 | 1.5 | 2100 | 0.5156 | 0.7283 |
|
| 94 |
+
| 0.5393 | 1.54 | 2150 | 0.5003 | 0.7546 |
|
| 95 |
+
| 0.6162 | 1.57 | 2200 | 0.4916 | 0.7625 |
|
| 96 |
+
| 0.5526 | 1.61 | 2250 | 0.4980 | 0.755 |
|
| 97 |
+
| 0.4472 | 1.64 | 2300 | 0.5001 | 0.76 |
|
| 98 |
+
| 0.5678 | 1.68 | 2350 | 0.4958 | 0.7558 |
|
| 99 |
+
| 0.3894 | 1.71 | 2400 | 0.4968 | 0.7646 |
|
| 100 |
+
| 0.4086 | 1.75 | 2450 | 0.5065 | 0.7583 |
|
| 101 |
+
| 0.4652 | 1.79 | 2500 | 0.5091 | 0.7567 |
|
| 102 |
+
| 0.4837 | 1.82 | 2550 | 0.5190 | 0.7312 |
|
| 103 |
+
| 0.4745 | 1.86 | 2600 | 0.4998 | 0.7567 |
|
| 104 |
+
| 0.456 | 1.89 | 2650 | 0.5035 | 0.7558 |
|
| 105 |
+
| 0.5784 | 1.93 | 2700 | 0.4997 | 0.7504 |
|
| 106 |
+
| 0.452 | 1.96 | 2750 | 0.5315 | 0.7517 |
|
| 107 |
+
| 0.5682 | 2.0 | 2800 | 0.5827 | 0.7521 |
|
| 108 |
+
| 0.6134 | 2.04 | 2850 | 0.4944 | 0.7421 |
|
| 109 |
+
| 0.3451 | 2.07 | 2900 | 0.5505 | 0.7575 |
|
| 110 |
+
| 0.3682 | 2.11 | 2950 | 0.5122 | 0.7504 |
|
| 111 |
+
| 0.3737 | 2.14 | 3000 | 0.8033 | 0.7546 |
|
| 112 |
+
| 0.4899 | 2.18 | 3050 | 0.5645 | 0.7446 |
|
| 113 |
+
| 0.4885 | 2.21 | 3100 | 0.5229 | 0.7554 |
|
| 114 |
+
| 0.4121 | 2.25 | 3150 | 0.5172 | 0.7425 |
|
| 115 |
+
| 0.3926 | 2.29 | 3200 | 0.5685 | 0.7512 |
|
| 116 |
+
| 0.4242 | 2.32 | 3250 | 0.5380 | 0.7425 |
|
| 117 |
+
| 0.4133 | 2.36 | 3300 | 0.5996 | 0.7488 |
|
| 118 |
+
| 0.4322 | 2.39 | 3350 | 0.5769 | 0.7533 |
|
| 119 |
+
| 0.4561 | 2.43 | 3400 | 0.5525 | 0.7583 |
|
| 120 |
+
| 0.2765 | 2.46 | 3450 | 0.5399 | 0.7546 |
|
| 121 |
+
| 0.4422 | 2.5 | 3500 | 0.5782 | 0.7554 |
|
| 122 |
+
| 0.4343 | 2.54 | 3550 | 0.5325 | 0.7338 |
|
| 123 |
+
| 0.3551 | 2.57 | 3600 | 0.5518 | 0.7504 |
|
| 124 |
+
| 0.4058 | 2.61 | 3650 | 0.5585 | 0.7579 |
|
| 125 |
+
| 0.4838 | 2.64 | 3700 | 0.5433 | 0.7379 |
|
| 126 |
+
| 0.3821 | 2.68 | 3750 | 0.5244 | 0.7562 |
|
| 127 |
+
| 0.4906 | 2.71 | 3800 | 0.5202 | 0.7525 |
|
| 128 |
+
| 0.3046 | 2.75 | 3850 | 0.5430 | 0.7575 |
|
| 129 |
+
| 0.4317 | 2.79 | 3900 | 0.5369 | 0.7546 |
|
| 130 |
+
| 0.5641 | 2.82 | 3950 | 0.5406 | 0.7546 |
|
| 131 |
+
| 0.4866 | 2.86 | 4000 | 0.5454 | 0.7546 |
|
| 132 |
+
| 0.3687 | 2.89 | 4050 | 0.5450 | 0.7558 |
|
| 133 |
+
| 0.484 | 2.93 | 4100 | 0.5456 | 0.7521 |
|
| 134 |
+
| 0.2599 | 2.96 | 4150 | 0.5472 | 0.7533 |
|
| 135 |
+
| 0.3381 | 3.0 | 4200 | 0.5461 | 0.7508 |
|
| 136 |
|
| 137 |
|
| 138 |
### Framework versions
|