Hugging Face's logo

pszemraj
/
mega-small-2048-C1024-tk_id-simplewiki-MR50

Fill-Mask
Transformers
PyTorch
Safetensors
mega
Generated from Trainer
Inference Endpoints
Model card Files Community
1
pszemraj commited on
Commit
107f1a8
·
1 Parent(s): 799cc39

Model save

Browse files
Files changed (2) hide show
  1. README.md +89 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: pszemraj/random-mega-small-2048
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: PT-simple_wikipedia_LM-random-mega-small-2048-MR0.50-C1024-tk_id
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # PT-simple_wikipedia_LM-random-mega-small-2048-MR0.50-C1024-tk_id
17
+
18
+ This model is a fine-tuned version of [pszemraj/random-mega-small-2048](https://huggingface.co/pszemraj/random-mega-small-2048) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 3.4773
21
+ - Accuracy: 0.4591
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0005
41
+ - train_batch_size: 1
42
+ - eval_batch_size: 1
43
+ - seed: 3208
44
+ - gradient_accumulation_steps: 64
45
+ - total_train_batch_size: 64
46
+ - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-07
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_ratio: 0.05
49
+ - num_epochs: 3.0
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
+ | 7.2691 | 0.11 | 50 | 7.1000 | 0.0677 |
56
+ | 7.1597 | 0.22 | 100 | 6.8388 | 0.0794 |
57
+ | 6.5476 | 0.33 | 150 | 6.4004 | 0.1359 |
58
+ | 6.5335 | 0.44 | 200 | 6.1776 | 0.1708 |
59
+ | 5.7228 | 0.55 | 250 | 5.6106 | 0.2437 |
60
+ | 5.4574 | 0.66 | 300 | 5.1391 | 0.2884 |
61
+ | 5.2275 | 0.78 | 350 | 4.8626 | 0.3174 |
62
+ | 4.9589 | 0.89 | 400 | 4.6454 | 0.3374 |
63
+ | 4.6406 | 1.0 | 450 | 4.4498 | 0.3578 |
64
+ | 4.8251 | 1.11 | 500 | 4.3055 | 0.3706 |
65
+ | 4.4728 | 1.22 | 550 | 4.1877 | 0.3821 |
66
+ | 4.3975 | 1.33 | 600 | 4.0709 | 0.3955 |
67
+ | 4.4245 | 1.44 | 650 | 3.9909 | 0.4045 |
68
+ | 4.2613 | 1.55 | 700 | 3.8976 | 0.4128 |
69
+ | 4.1806 | 1.66 | 750 | 3.8515 | 0.4177 |
70
+ | 3.9469 | 1.77 | 800 | 3.7883 | 0.4227 |
71
+ | 3.9563 | 1.88 | 850 | 3.7314 | 0.4306 |
72
+ | 4.0063 | 1.99 | 900 | 3.6975 | 0.4336 |
73
+ | 3.9274 | 2.1 | 950 | 3.6561 | 0.4378 |
74
+ | 3.788 | 2.21 | 1000 | 3.6280 | 0.4410 |
75
+ | 3.8711 | 2.33 | 1050 | 3.5736 | 0.4467 |
76
+ | 3.8623 | 2.44 | 1100 | 3.5535 | 0.4496 |
77
+ | 3.8575 | 2.55 | 1150 | 3.5407 | 0.4521 |
78
+ | 4.0079 | 2.66 | 1200 | 3.5172 | 0.4543 |
79
+ | 3.8265 | 2.77 | 1250 | 3.4786 | 0.4591 |
80
+ | 3.9513 | 2.88 | 1300 | 3.4741 | 0.4578 |
81
+ | 3.554 | 2.99 | 1350 | 3.4773 | 0.4591 |
82
+
83
+
84
+ ### Framework versions
85
+
86
+ - Transformers 4.33.1
87
+ - Pytorch 2.2.0.dev20230907+cu118
88
+ - Datasets 2.13.1
89
+ - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34b57042a19e6dc02908161fa9ca55788881587b4ac15ae81aa18008c72306fb
3
  size 270274934
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cde798b4b202c201046f490e78d3f5f60478aeb7dfaea85b414854329a37be2
3
  size 270274934