Model save
Browse files
README.md
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: rel-cl-lstm-3
|
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 |
+
# rel-cl-lstm-3
|
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: 3.9834
|
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: 3
|
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 |
+
| 4.8333 | 0.03 | 76319 | 4.7955 |
|
48 |
+
| 4.5414 | 1.03 | 152638 | 4.5069 |
|
49 |
+
| 4.3958 | 0.03 | 228957 | 4.3693 |
|
50 |
+
| 4.3064 | 1.03 | 305276 | 4.2841 |
|
51 |
+
| 4.2412 | 0.03 | 381595 | 4.2253 |
|
52 |
+
| 4.1888 | 1.03 | 457914 | 4.1822 |
|
53 |
+
| 4.1518 | 0.03 | 534233 | 4.1503 |
|
54 |
+
| 4.1231 | 1.03 | 610552 | 4.1251 |
|
55 |
+
| 4.0901 | 0.03 | 686871 | 4.1043 |
|
56 |
+
| 4.0684 | 1.03 | 763190 | 4.0883 |
|
57 |
+
| 4.0494 | 0.03 | 839509 | 4.0748 |
|
58 |
+
| 4.0311 | 1.03 | 915828 | 4.0629 |
|
59 |
+
| 4.0094 | 0.03 | 992147 | 4.0531 |
|
60 |
+
| 3.9984 | 1.03 | 1068466 | 4.0447 |
|
61 |
+
| 3.9843 | 0.03 | 1144785 | 4.0374 |
|
62 |
+
| 3.9745 | 1.03 | 1221104 | 4.0315 |
|
63 |
+
| 3.9639 | 0.03 | 1297424 | 4.0246 |
|
64 |
+
| 3.9518 | 1.03 | 1373744 | 4.0196 |
|
65 |
+
| 3.9425 | 0.03 | 1450064 | 4.0152 |
|
66 |
+
| 3.9366 | 1.03 | 1526384 | 4.0120 |
|
67 |
+
| 3.9314 | 0.03 | 1602704 | 4.0092 |
|
68 |
+
| 3.9281 | 1.03 | 1679024 | 4.0062 |
|
69 |
+
| 3.9248 | 0.03 | 1755344 | 4.0037 |
|
70 |
+
| 3.9168 | 1.03 | 1831664 | 4.0010 |
|
71 |
+
| 3.9081 | 0.03 | 1907984 | 3.9989 |
|
72 |
+
| 3.9019 | 1.03 | 1984304 | 3.9969 |
|
73 |
+
| 3.8948 | 0.03 | 2060624 | 3.9948 |
|
74 |
+
| 3.891 | 1.03 | 2136944 | 3.9935 |
|
75 |
+
| 3.8871 | 0.03 | 2213264 | 3.9923 |
|
76 |
+
| 3.8802 | 1.03 | 2289584 | 3.9913 |
|
77 |
+
| 3.8797 | 0.03 | 2365904 | 3.9902 |
|
78 |
+
| 3.8769 | 1.03 | 2442224 | 3.9892 |
|
79 |
+
| 3.8733 | 0.03 | 2518544 | 3.9886 |
|
80 |
+
| 3.8671 | 1.03 | 2594864 | 3.9875 |
|
81 |
+
| 3.8637 | 0.03 | 2671184 | 3.9867 |
|
82 |
+
| 3.8642 | 1.03 | 2747504 | 3.9858 |
|
83 |
+
| 3.8642 | 0.03 | 2823824 | 3.9848 |
|
84 |
+
| 3.8653 | 1.03 | 2900144 | 3.9842 |
|
85 |
+
| 3.8671 | 0.03 | 2976464 | 3.9836 |
|
86 |
+
| 3.8639 | 0.02 | 3052726 | 3.9834 |
|
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
|