Hugging Face's logo

nerottt
/
out

PEFT
Safetensors
Generated from Trainer
Model card Files Community
nerottt commited on
Commit
c0e3fa0
•
1 Parent(s): 5bd8f96

End of training

Browse files
Files changed (2) hide show
  1. README.md +98 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: microsoft/phi-2
7
+ model-index:
8
+ - name: out
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # out
16
+
17
+ This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.9839
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 2e-05
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 16
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: constant
44
+ - num_epochs: 20
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-------:|:----:|:---------------:|
50
+ | 2.5886 | 0.4889 | 22 | 2.6622 |
51
+ | 2.6172 | 0.9778 | 44 | 2.5162 |
52
+ | 2.502 | 1.4667 | 66 | 2.3493 |
53
+ | 2.031 | 1.9556 | 88 | 2.2040 |
54
+ | 2.1055 | 2.4444 | 110 | 2.0898 |
55
+ | 2.0684 | 2.9333 | 132 | 2.0072 |
56
+ | 1.7919 | 3.4222 | 154 | 1.9535 |
57
+ | 1.608 | 3.9111 | 176 | 1.9187 |
58
+ | 1.7458 | 4.4 | 198 | 1.9064 |
59
+ | 1.7142 | 4.8889 | 220 | 1.8939 |
60
+ | 1.7855 | 5.3778 | 242 | 1.8945 |
61
+ | 1.6425 | 5.8667 | 264 | 1.8936 |
62
+ | 1.6711 | 6.3556 | 286 | 1.8951 |
63
+ | 1.6882 | 6.8444 | 308 | 1.9007 |
64
+ | 1.4663 | 7.3333 | 330 | 1.9092 |
65
+ | 1.6227 | 7.8222 | 352 | 1.9037 |
66
+ | 1.4768 | 8.3111 | 374 | 1.9042 |
67
+ | 1.5643 | 8.8 | 396 | 1.9142 |
68
+ | 1.4109 | 9.2889 | 418 | 1.9128 |
69
+ | 1.5431 | 9.7778 | 440 | 1.9283 |
70
+ | 1.5034 | 10.2667 | 462 | 1.9184 |
71
+ | 1.3418 | 10.7556 | 484 | 1.9188 |
72
+ | 1.5773 | 11.2444 | 506 | 1.9224 |
73
+ | 1.4452 | 11.7333 | 528 | 1.9315 |
74
+ | 1.3154 | 12.2222 | 550 | 1.9313 |
75
+ | 1.3509 | 12.7111 | 572 | 1.9380 |
76
+ | 1.3372 | 13.2 | 594 | 1.9430 |
77
+ | 1.3439 | 13.6889 | 616 | 1.9436 |
78
+ | 1.2385 | 14.1778 | 638 | 1.9430 |
79
+ | 1.2669 | 14.6667 | 660 | 1.9453 |
80
+ | 1.2923 | 15.1556 | 682 | 1.9504 |
81
+ | 1.1558 | 15.6444 | 704 | 1.9531 |
82
+ | 1.3123 | 16.1333 | 726 | 1.9582 |
83
+ | 1.2309 | 16.6222 | 748 | 1.9588 |
84
+ | 1.1934 | 17.1111 | 770 | 1.9617 |
85
+ | 1.1893 | 17.6 | 792 | 1.9639 |
86
+ | 1.1561 | 18.0889 | 814 | 1.9662 |
87
+ | 1.244 | 18.5778 | 836 | 1.9749 |
88
+ | 1.1299 | 19.0667 | 858 | 1.9799 |
89
+ | 1.1213 | 19.5556 | 880 | 1.9839 |
90
+
91
+
92
+ ### Framework versions
93
+
94
+ - PEFT 0.11.1
95
+ - Transformers 4.41.0
96
+ - Pytorch 2.0.1+cu118
97
+ - Datasets 2.19.1
98
+ - Tokenizers 0.19.1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a56e86dbcf61d686440316a3db094c9d8580a6769b011e14cbcead925074a733
3
  size 1132702680
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e10b6bc5a8bc145f81b029b2fcaeab2a7cd509a1b6f4f4a56e8ebb7d24738a56
3
  size 1132702680