pszemraj commited on
Commit
ce101b7
1 Parent(s): 36406bb

Model save

Browse files
Files changed (3) hide show
  1. README.md +89 -0
  2. generation_config.json +7 -0
  3. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: pszemraj/random-mega-ar-small-4096
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: PT-random-mega-ar-small-4096-wikitext_document_level-1024ctx-v1
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-random-mega-ar-small-4096-wikitext_document_level-1024ctx-v1
17
+
18
+ This model is a fine-tuned version of [pszemraj/random-mega-ar-small-4096](https://huggingface.co/pszemraj/random-mega-ar-small-4096) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 4.0338
21
+ - Accuracy: 0.3243
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: 4
42
+ - eval_batch_size: 1
43
+ - seed: 80085
44
+ - gradient_accumulation_steps: 32
45
+ - total_train_batch_size: 128
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
+ | 7.3662 | 0.11 | 100 | 7.2782 | 0.0935 |
56
+ | 6.3064 | 0.22 | 200 | 6.2066 | 0.1634 |
57
+ | 5.8203 | 0.33 | 300 | 5.7299 | 0.1931 |
58
+ | 5.55 | 0.44 | 400 | 5.4173 | 0.2117 |
59
+ | 5.3194 | 0.55 | 500 | 5.1937 | 0.2278 |
60
+ | 5.1678 | 0.66 | 600 | 5.0206 | 0.2406 |
61
+ | 5.0375 | 0.77 | 700 | 4.8891 | 0.2508 |
62
+ | 4.9194 | 0.88 | 800 | 4.7592 | 0.2605 |
63
+ | 4.8272 | 0.99 | 900 | 4.6653 | 0.2681 |
64
+ | 4.7571 | 1.1 | 1000 | 4.5817 | 0.2754 |
65
+ | 4.6345 | 1.21 | 1100 | 4.5066 | 0.2820 |
66
+ | 4.6218 | 1.32 | 1200 | 4.4472 | 0.2867 |
67
+ | 4.5585 | 1.43 | 1300 | 4.3827 | 0.2923 |
68
+ | 4.5047 | 1.54 | 1400 | 4.3328 | 0.2963 |
69
+ | 4.4726 | 1.65 | 1500 | 4.2860 | 0.3002 |
70
+ | 4.4094 | 1.76 | 1600 | 4.2452 | 0.3038 |
71
+ | 4.3705 | 1.87 | 1700 | 4.2168 | 0.3062 |
72
+ | 4.3739 | 1.98 | 1800 | 4.1852 | 0.3095 |
73
+ | 4.2836 | 2.09 | 1900 | 4.1599 | 0.3112 |
74
+ | 4.302 | 2.2 | 2000 | 4.1307 | 0.3149 |
75
+ | 4.2847 | 2.31 | 2100 | 4.1113 | 0.3165 |
76
+ | 4.2348 | 2.42 | 2200 | 4.0925 | 0.3184 |
77
+ | 4.2837 | 2.53 | 2300 | 4.0743 | 0.3207 |
78
+ | 4.2058 | 2.64 | 2400 | 4.0612 | 0.3217 |
79
+ | 4.22 | 2.75 | 2500 | 4.0494 | 0.3224 |
80
+ | 4.1827 | 2.86 | 2600 | 4.0397 | 0.3237 |
81
+ | 4.1967 | 2.97 | 2700 | 4.0338 | 0.3243 |
82
+
83
+
84
+ ### Framework versions
85
+
86
+ - Transformers 4.32.1
87
+ - Pytorch 2.1.0.dev20230727+cu118
88
+ - Datasets 2.13.1
89
+ - Tokenizers 0.13.3
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.32.1"
7
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b26cb03c188b3eb15ac72b0fbe547a0d48e2c7934cef6c12ad670350dbe20e94
3
  size 259284978
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f746f5f75acc0edf01e9847cd6ef307c60dfaff315c31e4425cda0d325e7cc6b
3
  size 259284978