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-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 |
+
# pp-mod-subj-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: 4.0221
|
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 |
+
| 4.7923 | 0.03 | 76319 | 4.8102 |
|
48 |
+
| 4.5063 | 1.03 | 152638 | 4.5307 |
|
49 |
+
| 4.365 | 0.03 | 228957 | 4.3961 |
|
50 |
+
| 4.2747 | 1.03 | 305276 | 4.3126 |
|
51 |
+
| 4.212 | 0.03 | 381595 | 4.2551 |
|
52 |
+
| 4.1642 | 1.03 | 457914 | 4.2132 |
|
53 |
+
| 4.1266 | 0.03 | 534233 | 4.1807 |
|
54 |
+
| 4.0965 | 1.03 | 610552 | 4.1574 |
|
55 |
+
| 4.0676 | 0.03 | 686871 | 4.1386 |
|
56 |
+
| 4.0454 | 1.03 | 763190 | 4.1230 |
|
57 |
+
| 4.0256 | 0.03 | 839509 | 4.1096 |
|
58 |
+
| 4.0096 | 0.03 | 915828 | 4.0983 |
|
59 |
+
| 3.9875 | 1.03 | 992147 | 4.0892 |
|
60 |
+
| 3.9708 | 0.03 | 1068466 | 4.0805 |
|
61 |
+
| 3.9619 | 1.03 | 1144785 | 4.0743 |
|
62 |
+
| 3.9492 | 0.03 | 1221104 | 4.0677 |
|
63 |
+
| 3.9395 | 1.03 | 1297423 | 4.0635 |
|
64 |
+
| 3.9333 | 0.03 | 1373743 | 4.0583 |
|
65 |
+
| 3.9224 | 1.03 | 1450063 | 4.0539 |
|
66 |
+
| 3.9179 | 0.03 | 1526383 | 4.0510 |
|
67 |
+
| 3.9137 | 1.03 | 1602703 | 4.0476 |
|
68 |
+
| 3.9059 | 2.03 | 1679023 | 4.0453 |
|
69 |
+
| 3.8991 | 0.03 | 1755343 | 4.0420 |
|
70 |
+
| 3.8915 | 1.03 | 1831663 | 4.0406 |
|
71 |
+
| 3.8835 | 2.03 | 1907983 | 4.0377 |
|
72 |
+
| 3.88 | 0.03 | 1984303 | 4.0361 |
|
73 |
+
| 3.8762 | 1.03 | 2060623 | 4.0347 |
|
74 |
+
| 3.8699 | 0.03 | 2136943 | 4.0329 |
|
75 |
+
| 3.8691 | 0.03 | 2213263 | 4.0315 |
|
76 |
+
| 3.8616 | 1.03 | 2289583 | 4.0305 |
|
77 |
+
| 3.8593 | 0.03 | 2365903 | 4.0288 |
|
78 |
+
| 3.8529 | 1.03 | 2442223 | 4.0275 |
|
79 |
+
| 3.8463 | 0.03 | 2518543 | 4.0265 |
|
80 |
+
| 3.845 | 1.03 | 2594863 | 4.0255 |
|
81 |
+
| 3.8398 | 0.03 | 2671183 | 4.0249 |
|
82 |
+
| 3.8416 | 1.03 | 2747503 | 4.0241 |
|
83 |
+
| 3.8438 | 2.03 | 2823823 | 4.0235 |
|
84 |
+
| 3.8409 | 0.03 | 2900143 | 4.0229 |
|
85 |
+
| 3.8403 | 1.03 | 2976463 | 4.0227 |
|
86 |
+
| 3.8357 | 2.02 | 3052726 | 4.0221 |
|
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
|