Model save
Browse files
README.md
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: full2-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 |
+
# full2-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: 3.9703
|
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 |
+
| 4.7949 | 0.03 | 76320 | 4.7623 |
|
48 |
+
| 4.5075 | 1.03 | 152640 | 4.4794 |
|
49 |
+
| 4.3602 | 0.03 | 228960 | 4.3429 |
|
50 |
+
| 4.2766 | 1.03 | 305280 | 4.2588 |
|
51 |
+
| 4.2113 | 0.03 | 381600 | 4.2022 |
|
52 |
+
| 4.1648 | 1.03 | 457920 | 4.1606 |
|
53 |
+
| 4.1336 | 0.03 | 534240 | 4.1292 |
|
54 |
+
| 4.1008 | 1.03 | 610560 | 4.1050 |
|
55 |
+
| 4.0722 | 0.03 | 686880 | 4.0849 |
|
56 |
+
| 4.0491 | 1.03 | 763200 | 4.0689 |
|
57 |
+
| 4.0263 | 0.03 | 839520 | 4.0557 |
|
58 |
+
| 4.0088 | 1.03 | 915840 | 4.0452 |
|
59 |
+
| 3.9954 | 0.03 | 992160 | 4.0355 |
|
60 |
+
| 3.9784 | 1.03 | 1068480 | 4.0274 |
|
61 |
+
| 3.9641 | 0.03 | 1144800 | 4.0212 |
|
62 |
+
| 3.9491 | 1.03 | 1221120 | 4.0152 |
|
63 |
+
| 3.9347 | 0.03 | 1297440 | 4.0090 |
|
64 |
+
| 3.9257 | 1.03 | 1373760 | 4.0047 |
|
65 |
+
| 3.9144 | 0.03 | 1450080 | 4.0009 |
|
66 |
+
| 3.9137 | 1.03 | 1526400 | 3.9975 |
|
67 |
+
| 3.9061 | 0.03 | 1602720 | 3.9940 |
|
68 |
+
| 3.9037 | 1.03 | 1679040 | 3.9917 |
|
69 |
+
| 3.9045 | 0.03 | 1755360 | 3.9893 |
|
70 |
+
| 3.8999 | 1.03 | 1831680 | 3.9873 |
|
71 |
+
| 3.8897 | 0.03 | 1908000 | 3.9854 |
|
72 |
+
| 3.8842 | 1.03 | 1984320 | 3.9832 |
|
73 |
+
| 3.8789 | 0.03 | 2060640 | 3.9805 |
|
74 |
+
| 3.8724 | 1.03 | 2136960 | 3.9793 |
|
75 |
+
| 3.8717 | 0.03 | 2213280 | 3.9778 |
|
76 |
+
| 3.8658 | 1.03 | 2289600 | 3.9768 |
|
77 |
+
| 3.8594 | 0.03 | 2365920 | 3.9757 |
|
78 |
+
| 3.8523 | 1.03 | 2442240 | 3.9751 |
|
79 |
+
| 3.8455 | 0.03 | 2518560 | 3.9739 |
|
80 |
+
| 3.8431 | 0.03 | 2594880 | 3.9734 |
|
81 |
+
| 3.8368 | 0.03 | 2671200 | 3.9728 |
|
82 |
+
| 3.8431 | 1.03 | 2747520 | 3.9721 |
|
83 |
+
| 3.8423 | 0.03 | 2823840 | 3.9716 |
|
84 |
+
| 3.8432 | 0.03 | 2900160 | 3.9712 |
|
85 |
+
| 3.8477 | 1.03 | 2976480 | 3.9706 |
|
86 |
+
| 3.8461 | 0.02 | 3052726 | 3.9703 |
|
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
|