End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: t5-base
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- glue
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: t5-base_qnli_dense_epochs-8
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Text Classification
|
| 15 |
+
type: text-classification
|
| 16 |
+
dataset:
|
| 17 |
+
name: glue
|
| 18 |
+
type: glue
|
| 19 |
+
config: qnli
|
| 20 |
+
split: validation
|
| 21 |
+
args: qnli
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.9269632070291048
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
+
|
| 31 |
+
# t5-base_qnli_dense_epochs-8
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the glue dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.1982
|
| 36 |
+
- Accuracy: 0.9270
|
| 37 |
+
|
| 38 |
+
## Model description
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Intended uses & limitations
|
| 43 |
+
|
| 44 |
+
More information needed
|
| 45 |
+
|
| 46 |
+
## Training and evaluation data
|
| 47 |
+
|
| 48 |
+
More information needed
|
| 49 |
+
|
| 50 |
+
## Training procedure
|
| 51 |
+
|
| 52 |
+
### Training hyperparameters
|
| 53 |
+
|
| 54 |
+
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 5e-05
|
| 56 |
+
- train_batch_size: 16
|
| 57 |
+
- eval_batch_size: 64
|
| 58 |
+
- seed: 0
|
| 59 |
+
- distributed_type: multi-GPU
|
| 60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 61 |
+
- lr_scheduler_type: linear
|
| 62 |
+
- lr_scheduler_warmup_steps: 20
|
| 63 |
+
- num_epochs: 8
|
| 64 |
+
|
| 65 |
+
### Training results
|
| 66 |
+
|
| 67 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 68 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 69 |
+
| 0.6742 | 0.01 | 50 | 0.6559 | 0.5380 |
|
| 70 |
+
| 0.4309 | 0.02 | 100 | 0.4215 | 0.8433 |
|
| 71 |
+
| 0.4535 | 0.02 | 150 | 0.3441 | 0.8644 |
|
| 72 |
+
| 0.2523 | 0.03 | 200 | 0.2892 | 0.8957 |
|
| 73 |
+
| 0.2616 | 0.04 | 250 | 0.2927 | 0.8986 |
|
| 74 |
+
| 0.2088 | 0.05 | 300 | 0.3608 | 0.8796 |
|
| 75 |
+
| 0.2454 | 0.05 | 350 | 0.2730 | 0.9087 |
|
| 76 |
+
| 0.2824 | 0.06 | 400 | 0.2819 | 0.8900 |
|
| 77 |
+
| 0.308 | 0.07 | 450 | 0.2904 | 0.8966 |
|
| 78 |
+
| 0.2035 | 0.08 | 500 | 0.3073 | 0.8951 |
|
| 79 |
+
| 0.2096 | 0.08 | 550 | 0.2743 | 0.9061 |
|
| 80 |
+
| 0.338 | 0.09 | 600 | 0.2520 | 0.9072 |
|
| 81 |
+
| 0.2484 | 0.1 | 650 | 0.2702 | 0.9030 |
|
| 82 |
+
| 0.2042 | 0.11 | 700 | 0.2476 | 0.9138 |
|
| 83 |
+
| 0.2908 | 0.11 | 750 | 0.2194 | 0.9180 |
|
| 84 |
+
| 0.1985 | 0.12 | 800 | 0.2432 | 0.9169 |
|
| 85 |
+
| 0.19 | 0.13 | 850 | 0.2615 | 0.9112 |
|
| 86 |
+
| 0.2186 | 0.14 | 900 | 0.2289 | 0.9215 |
|
| 87 |
+
| 0.2208 | 0.15 | 950 | 0.2272 | 0.9204 |
|
| 88 |
+
| 0.3049 | 0.15 | 1000 | 0.3508 | 0.8880 |
|
| 89 |
+
| 0.3373 | 0.16 | 1050 | 0.2363 | 0.9105 |
|
| 90 |
+
| 0.2493 | 0.17 | 1100 | 0.2196 | 0.9206 |
|
| 91 |
+
| 0.2359 | 0.18 | 1150 | 0.2160 | 0.9237 |
|
| 92 |
+
| 0.2207 | 0.18 | 1200 | 0.2211 | 0.9217 |
|
| 93 |
+
| 0.2824 | 0.19 | 1250 | 0.2386 | 0.9182 |
|
| 94 |
+
| 0.3605 | 0.2 | 1300 | 0.2548 | 0.9112 |
|
| 95 |
+
| 0.2763 | 0.21 | 1350 | 0.2579 | 0.9149 |
|
| 96 |
+
| 0.2299 | 0.21 | 1400 | 0.2104 | 0.9226 |
|
| 97 |
+
| 0.1787 | 0.22 | 1450 | 0.2280 | 0.9224 |
|
| 98 |
+
| 0.1961 | 0.23 | 1500 | 0.2244 | 0.9233 |
|
| 99 |
+
| 0.1923 | 0.24 | 1550 | 0.2245 | 0.9231 |
|
| 100 |
+
| 0.1844 | 0.24 | 1600 | 0.2735 | 0.9123 |
|
| 101 |
+
| 0.1714 | 0.25 | 1650 | 0.3108 | 0.9121 |
|
| 102 |
+
| 0.2606 | 0.26 | 1700 | 0.2238 | 0.9189 |
|
| 103 |
+
| 0.3326 | 0.27 | 1750 | 0.2363 | 0.9132 |
|
| 104 |
+
| 0.1379 | 0.27 | 1800 | 0.2429 | 0.9094 |
|
| 105 |
+
| 0.2266 | 0.28 | 1850 | 0.2416 | 0.9224 |
|
| 106 |
+
| 0.2654 | 0.29 | 1900 | 0.2277 | 0.9242 |
|
| 107 |
+
| 0.6668 | 0.3 | 1950 | 0.2808 | 0.9092 |
|
| 108 |
+
| 0.1875 | 0.31 | 2000 | 0.1982 | 0.9270 |
|
| 109 |
+
|
| 110 |
+
|
| 111 |
+
### Framework versions
|
| 112 |
+
|
| 113 |
+
- Transformers 4.34.1
|
| 114 |
+
- Pytorch 2.0.1+cu117
|
| 115 |
+
- Datasets 2.9.0
|
| 116 |
+
- Tokenizers 0.14.1
|