Commit
·
ac18ab3
1
Parent(s):
aea3426
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: gpt2
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: MammoLLM2
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# MammoLLM2
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 1.6666
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 0.0005
|
| 38 |
+
- train_batch_size: 64
|
| 39 |
+
- eval_batch_size: 64
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 4
|
| 42 |
+
- total_train_batch_size: 256
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: cosine
|
| 45 |
+
- lr_scheduler_warmup_steps: 1000
|
| 46 |
+
- num_epochs: 50
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 52 |
+
| 1.7888 | 1.24 | 500 | 1.0984 |
|
| 53 |
+
| 1.1179 | 2.49 | 1000 | 1.0209 |
|
| 54 |
+
| 1.0556 | 3.73 | 1500 | 0.9913 |
|
| 55 |
+
| 1.01 | 4.98 | 2000 | 0.9653 |
|
| 56 |
+
| 0.9723 | 6.22 | 2500 | 0.9608 |
|
| 57 |
+
| 0.9425 | 7.47 | 3000 | 0.9455 |
|
| 58 |
+
| 0.9149 | 8.71 | 3500 | 0.9391 |
|
| 59 |
+
| 0.8877 | 9.96 | 4000 | 0.9253 |
|
| 60 |
+
| 0.8478 | 11.2 | 4500 | 0.9317 |
|
| 61 |
+
| 0.8142 | 12.45 | 5000 | 0.9313 |
|
| 62 |
+
| 0.7814 | 13.69 | 5500 | 0.9299 |
|
| 63 |
+
| 0.7494 | 14.93 | 6000 | 0.9330 |
|
| 64 |
+
| 0.7071 | 16.18 | 6500 | 0.9588 |
|
| 65 |
+
| 0.6774 | 17.42 | 7000 | 0.9704 |
|
| 66 |
+
| 0.6511 | 18.67 | 7500 | 0.9828 |
|
| 67 |
+
| 0.6275 | 19.91 | 8000 | 1.0007 |
|
| 68 |
+
| 0.595 | 21.16 | 8500 | 1.0432 |
|
| 69 |
+
| 0.5698 | 22.4 | 9000 | 1.0641 |
|
| 70 |
+
| 0.546 | 23.65 | 9500 | 1.0879 |
|
| 71 |
+
| 0.523 | 24.89 | 10000 | 1.0982 |
|
| 72 |
+
| 0.4913 | 26.14 | 10500 | 1.1579 |
|
| 73 |
+
| 0.4622 | 27.38 | 11000 | 1.1923 |
|
| 74 |
+
| 0.4378 | 28.62 | 11500 | 1.2152 |
|
| 75 |
+
| 0.4131 | 29.87 | 12000 | 1.2440 |
|
| 76 |
+
| 0.3846 | 31.11 | 12500 | 1.3181 |
|
| 77 |
+
| 0.3592 | 32.36 | 13000 | 1.3497 |
|
| 78 |
+
| 0.3411 | 33.6 | 13500 | 1.3847 |
|
| 79 |
+
| 0.324 | 34.85 | 14000 | 1.4070 |
|
| 80 |
+
| 0.3061 | 36.09 | 14500 | 1.4755 |
|
| 81 |
+
| 0.2903 | 37.34 | 15000 | 1.5078 |
|
| 82 |
+
| 0.2795 | 38.58 | 15500 | 1.5351 |
|
| 83 |
+
| 0.2701 | 39.83 | 16000 | 1.5639 |
|
| 84 |
+
| 0.2605 | 41.07 | 16500 | 1.5972 |
|
| 85 |
+
| 0.2521 | 42.31 | 17000 | 1.6191 |
|
| 86 |
+
| 0.2467 | 43.56 | 17500 | 1.6300 |
|
| 87 |
+
| 0.2425 | 44.8 | 18000 | 1.6453 |
|
| 88 |
+
| 0.2386 | 46.05 | 18500 | 1.6554 |
|
| 89 |
+
| 0.2356 | 47.29 | 19000 | 1.6628 |
|
| 90 |
+
| 0.2344 | 48.54 | 19500 | 1.6663 |
|
| 91 |
+
| 0.2333 | 49.78 | 20000 | 1.6666 |
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
### Framework versions
|
| 95 |
+
|
| 96 |
+
- Transformers 4.31.0
|
| 97 |
+
- Pytorch 2.0.1+cu117
|
| 98 |
+
- Datasets 2.14.3
|
| 99 |
+
- Tokenizers 0.13.3
|