Model save
Browse files
README.md
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: pp-mod-subj-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 |
+
# pp-mod-subj-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: 4.0239
|
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 |
+
| 4.7782 | 0.03 | 76319 | 4.7947 |
|
48 |
+
| 4.497 | 1.03 | 152638 | 4.5206 |
|
49 |
+
| 4.3593 | 0.03 | 228957 | 4.3906 |
|
50 |
+
| 4.2699 | 1.03 | 305276 | 4.3090 |
|
51 |
+
| 4.2082 | 0.03 | 381595 | 4.2532 |
|
52 |
+
| 4.1581 | 1.03 | 457914 | 4.2119 |
|
53 |
+
| 4.1228 | 0.03 | 534233 | 4.1819 |
|
54 |
+
| 4.0934 | 0.03 | 610552 | 4.1579 |
|
55 |
+
| 4.0643 | 1.03 | 686871 | 4.1380 |
|
56 |
+
| 4.0416 | 0.03 | 763190 | 4.1222 |
|
57 |
+
| 4.023 | 1.03 | 839509 | 4.1085 |
|
58 |
+
| 4.004 | 0.03 | 915828 | 4.0972 |
|
59 |
+
| 3.9818 | 1.03 | 992147 | 4.0878 |
|
60 |
+
| 3.9693 | 0.03 | 1068466 | 4.0803 |
|
61 |
+
| 3.9563 | 1.03 | 1144785 | 4.0747 |
|
62 |
+
| 3.9442 | 0.03 | 1221104 | 4.0679 |
|
63 |
+
| 3.9348 | 1.03 | 1297423 | 4.0634 |
|
64 |
+
| 3.9245 | 0.03 | 1373743 | 4.0571 |
|
65 |
+
| 3.9172 | 1.03 | 1450063 | 4.0535 |
|
66 |
+
| 3.9145 | 0.03 | 1526383 | 4.0490 |
|
67 |
+
| 3.9112 | 1.03 | 1602703 | 4.0470 |
|
68 |
+
| 3.9002 | 2.03 | 1679023 | 4.0447 |
|
69 |
+
| 3.8944 | 0.03 | 1755343 | 4.0421 |
|
70 |
+
| 3.885 | 1.03 | 1831663 | 4.0401 |
|
71 |
+
| 3.8777 | 0.03 | 1907983 | 4.0379 |
|
72 |
+
| 3.8724 | 1.03 | 1984303 | 4.0357 |
|
73 |
+
| 3.8686 | 2.03 | 2060623 | 4.0345 |
|
74 |
+
| 3.8636 | 0.03 | 2136943 | 4.0330 |
|
75 |
+
| 3.8617 | 1.03 | 2213263 | 4.0317 |
|
76 |
+
| 3.8563 | 2.03 | 2289583 | 4.0301 |
|
77 |
+
| 3.8527 | 0.03 | 2365903 | 4.0287 |
|
78 |
+
| 3.8468 | 1.03 | 2442223 | 4.0286 |
|
79 |
+
| 3.8424 | 2.03 | 2518543 | 4.0272 |
|
80 |
+
| 3.8413 | 0.03 | 2594863 | 4.0268 |
|
81 |
+
| 3.8364 | 1.03 | 2671183 | 4.0260 |
|
82 |
+
| 3.8379 | 2.03 | 2747503 | 4.0261 |
|
83 |
+
| 3.8402 | 0.03 | 2823823 | 4.0251 |
|
84 |
+
| 3.8354 | 1.03 | 2900143 | 4.0246 |
|
85 |
+
| 3.8352 | 2.03 | 2976463 | 4.0242 |
|
86 |
+
| 3.8297 | 0.02 | 3052726 | 4.0239 |
|
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
|