update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: opt-350m-finetuned-v4-seinfeld
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# opt-350m-finetuned-v4-seinfeld
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 2.4775
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 0.0005
|
37 |
+
- train_batch_size: 8
|
38 |
+
- eval_batch_size: 8
|
39 |
+
- seed: 42
|
40 |
+
- gradient_accumulation_steps: 8
|
41 |
+
- total_train_batch_size: 64
|
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: 15
|
46 |
+
- mixed_precision_training: Native AMP
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
+
| 2.8604 | 0.79 | 8 | 2.7539 |
|
53 |
+
| 2.8058 | 1.59 | 16 | 2.6860 |
|
54 |
+
| 2.7427 | 2.4 | 24 | 2.6338 |
|
55 |
+
| 2.6593 | 3.2 | 32 | 2.5925 |
|
56 |
+
| 2.5373 | 3.99 | 40 | 2.5601 |
|
57 |
+
| 2.4923 | 4.79 | 48 | 2.5370 |
|
58 |
+
| 2.4102 | 5.59 | 56 | 2.5216 |
|
59 |
+
| 2.3373 | 6.4 | 64 | 2.5049 |
|
60 |
+
| 2.2341 | 7.2 | 72 | 2.4963 |
|
61 |
+
| 2.1286 | 7.99 | 80 | 2.4862 |
|
62 |
+
| 2.0673 | 8.79 | 88 | 2.4908 |
|
63 |
+
| 1.9938 | 9.59 | 96 | 2.4881 |
|
64 |
+
| 1.9015 | 10.4 | 104 | 2.4854 |
|
65 |
+
| 1.8172 | 11.2 | 112 | 2.5058 |
|
66 |
+
| 1.7113 | 11.99 | 120 | 2.4950 |
|
67 |
+
| 1.6409 | 12.79 | 128 | 2.5082 |
|
68 |
+
| 1.5622 | 13.59 | 136 | 2.5172 |
|
69 |
+
| 1.4724 | 14.4 | 144 | 2.5464 |
|
70 |
+
|
71 |
+
|
72 |
+
### Framework versions
|
73 |
+
|
74 |
+
- Transformers 4.26.1
|
75 |
+
- Pytorch 1.13.1+cu116
|
76 |
+
- Datasets 2.10.0
|
77 |
+
- Tokenizers 0.13.2
|