Model save
Browse files
README.md
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: full-lstm-0
|
6 |
+
results: []
|
7 |
+
---
|
8 |
+
|
9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
10 |
+
should probably proofread and complete it, then remove this comment. -->
|
11 |
+
|
12 |
+
# full-lstm-0
|
13 |
+
|
14 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
|
15 |
+
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 3.9694
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 5e-05
|
36 |
+
- train_batch_size: 32
|
37 |
+
- eval_batch_size: 32
|
38 |
+
- seed: 0
|
39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
+
- lr_scheduler_type: linear
|
41 |
+
- training_steps: 3052726
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
46 |
+
|:-------------:|:-----:|:-------:|:---------------:|
|
47 |
+
| 4.8015 | 0.03 | 76319 | 4.7666 |
|
48 |
+
| 4.5084 | 1.03 | 152638 | 4.4785 |
|
49 |
+
| 4.3627 | 0.03 | 228957 | 4.3422 |
|
50 |
+
| 4.2719 | 1.03 | 305276 | 4.2587 |
|
51 |
+
| 4.207 | 0.03 | 381595 | 4.2008 |
|
52 |
+
| 4.157 | 1.03 | 457914 | 4.1598 |
|
53 |
+
| 4.1211 | 0.03 | 534233 | 4.1288 |
|
54 |
+
| 4.0934 | 0.03 | 610552 | 4.1043 |
|
55 |
+
| 4.0625 | 1.03 | 686871 | 4.0851 |
|
56 |
+
| 4.0403 | 0.03 | 763190 | 4.0690 |
|
57 |
+
| 4.0192 | 0.03 | 839509 | 4.0562 |
|
58 |
+
| 4.0046 | 0.03 | 915828 | 4.0454 |
|
59 |
+
| 3.9833 | 0.03 | 992148 | 4.0356 |
|
60 |
+
| 3.9707 | 1.03 | 1068468 | 4.0273 |
|
61 |
+
| 3.9639 | 0.03 | 1144788 | 4.0195 |
|
62 |
+
| 3.9539 | 1.03 | 1221108 | 4.0139 |
|
63 |
+
| 3.9372 | 0.03 | 1297428 | 4.0088 |
|
64 |
+
| 3.9294 | 1.03 | 1373748 | 4.0042 |
|
65 |
+
| 3.9158 | 0.03 | 1450068 | 4.0000 |
|
66 |
+
| 3.9084 | 1.03 | 1526388 | 3.9959 |
|
67 |
+
| 3.9068 | 0.03 | 1602708 | 3.9934 |
|
68 |
+
| 3.9023 | 0.03 | 1679028 | 3.9910 |
|
69 |
+
| 3.9014 | 0.03 | 1755348 | 3.9886 |
|
70 |
+
| 3.8972 | 1.03 | 1831668 | 3.9863 |
|
71 |
+
| 3.8877 | 0.03 | 1907988 | 3.9832 |
|
72 |
+
| 3.8826 | 1.03 | 1984308 | 3.9816 |
|
73 |
+
| 3.8796 | 0.03 | 2060628 | 3.9805 |
|
74 |
+
| 3.8705 | 0.03 | 2136948 | 3.9788 |
|
75 |
+
| 3.8694 | 0.03 | 2213268 | 3.9773 |
|
76 |
+
| 3.863 | 1.03 | 2289588 | 3.9766 |
|
77 |
+
| 3.857 | 0.03 | 2365908 | 3.9751 |
|
78 |
+
| 3.8545 | 1.03 | 2442228 | 3.9737 |
|
79 |
+
| 3.8461 | 0.03 | 2518548 | 3.9731 |
|
80 |
+
| 3.8429 | 1.03 | 2594868 | 3.9722 |
|
81 |
+
| 3.8378 | 0.03 | 2671188 | 3.9716 |
|
82 |
+
| 3.8349 | 0.03 | 2747508 | 3.9707 |
|
83 |
+
| 3.8407 | 0.03 | 2823828 | 3.9704 |
|
84 |
+
| 3.8386 | 1.03 | 2900148 | 3.9700 |
|
85 |
+
| 3.8431 | 0.03 | 2976468 | 3.9696 |
|
86 |
+
| 3.8437 | 0.02 | 3052726 | 3.9694 |
|
87 |
+
|
88 |
+
|
89 |
+
### Framework versions
|
90 |
+
|
91 |
+
- Transformers 4.33.3
|
92 |
+
- Pytorch 2.0.1
|
93 |
+
- Datasets 2.12.0
|
94 |
+
- Tokenizers 0.13.3
|