update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- generator
|
7 |
+
model-index:
|
8 |
+
- name: gpt2-concat-switch-rarity-no-cut
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# gpt2-concat-switch-rarity-no-cut
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 4.3032
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 0.0005
|
39 |
+
- train_batch_size: 64
|
40 |
+
- eval_batch_size: 64
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: cosine
|
44 |
+
- lr_scheduler_warmup_steps: 1000
|
45 |
+
- num_epochs: 6
|
46 |
+
- mixed_precision_training: Native AMP
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
52 |
+
| 6.7037 | 0.29 | 500 | 5.6319 |
|
53 |
+
| 5.3373 | 0.58 | 1000 | 5.2001 |
|
54 |
+
| 4.9919 | 0.87 | 1500 | 4.9536 |
|
55 |
+
| 4.7185 | 1.17 | 2000 | 4.8020 |
|
56 |
+
| 4.5556 | 1.46 | 2500 | 4.6811 |
|
57 |
+
| 4.4476 | 1.75 | 3000 | 4.5737 |
|
58 |
+
| 4.3298 | 2.04 | 3500 | 4.4863 |
|
59 |
+
| 4.1272 | 2.33 | 4000 | 4.4421 |
|
60 |
+
| 4.0996 | 2.62 | 4500 | 4.3853 |
|
61 |
+
| 4.0564 | 2.91 | 5000 | 4.3350 |
|
62 |
+
| 3.8676 | 3.21 | 5500 | 4.3248 |
|
63 |
+
| 3.8015 | 3.5 | 6000 | 4.2945 |
|
64 |
+
| 3.7787 | 3.79 | 6500 | 4.2610 |
|
65 |
+
| 3.6894 | 4.08 | 7000 | 4.2563 |
|
66 |
+
| 3.5111 | 4.37 | 7500 | 4.2530 |
|
67 |
+
| 3.5076 | 4.66 | 8000 | 4.2365 |
|
68 |
+
| 3.4984 | 4.95 | 8500 | 4.2243 |
|
69 |
+
| 3.341 | 5.24 | 9000 | 4.2363 |
|
70 |
+
| 3.3189 | 5.54 | 9500 | 4.2358 |
|
71 |
+
| 3.3196 | 5.83 | 10000 | 4.2346 |
|
72 |
+
|
73 |
+
|
74 |
+
### Framework versions
|
75 |
+
|
76 |
+
- Transformers 4.26.1
|
77 |
+
- Pytorch 1.11.0+cu113
|
78 |
+
- Datasets 2.13.0
|
79 |
+
- Tokenizers 0.13.3
|