Hugging Face's logo

Weni
/
ZeroShot-3.3.27-Mistral-7b-Multilanguage-3.2.0

PEFT
Safetensors
mistral
trl
sft
Generated from Trainer
Model card Files
xet
 Community
ironrock commited on
Commit
7a994f9
·
verified ·
1 Parent(s): ae9bcda

Model save

Browse files
Files changed (2) hide show
  1. README.md +112 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ base_model: mistralai/Mistral-7B-Instruct-v0.2
9
+ model-index:
10
+ - name: ZeroShot-3.3.27-Mistral-7b-Multilanguage-3.2.0
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # ZeroShot-3.3.27-Mistral-7b-Multilanguage-3.2.0
18
+
19
+ This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.0451
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: 0.0002
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 2
45
+ - total_train_batch_size: 16
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 3
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:-----:|:----:|:---------------:|
56
+ | 0.1426 | 0.06 | 100 | 0.1108 |
57
+ | 0.1003 | 0.12 | 200 | 0.0847 |
58
+ | 0.0986 | 0.19 | 300 | 0.0862 |
59
+ | 0.1013 | 0.25 | 400 | 0.0937 |
60
+ | 0.0942 | 0.31 | 500 | 0.0942 |
61
+ | 0.0963 | 0.37 | 600 | 0.1027 |
62
+ | 0.0953 | 0.43 | 700 | 0.0946 |
63
+ | 0.0955 | 0.5 | 800 | 0.0849 |
64
+ | 0.0909 | 0.56 | 900 | 0.0812 |
65
+ | 0.1022 | 0.62 | 1000 | 0.0816 |
66
+ | 0.0929 | 0.68 | 1100 | 0.0787 |
67
+ | 0.0727 | 0.74 | 1200 | 0.0842 |
68
+ | 0.0889 | 0.81 | 1300 | 0.0933 |
69
+ | 0.0729 | 0.87 | 1400 | 0.0879 |
70
+ | 0.0827 | 0.93 | 1500 | 0.0819 |
71
+ | 0.0773 | 0.99 | 1600 | 0.0773 |
72
+ | 0.0512 | 1.05 | 1700 | 0.0835 |
73
+ | 0.0573 | 1.12 | 1800 | 0.0787 |
74
+ | 0.0427 | 1.18 | 1900 | 0.0829 |
75
+ | 0.0486 | 1.24 | 2000 | 0.0787 |
76
+ | 0.0467 | 1.3 | 2100 | 0.0685 |
77
+ | 0.0517 | 1.36 | 2200 | 0.0886 |
78
+ | 0.041 | 1.43 | 2300 | 0.0696 |
79
+ | 0.0542 | 1.49 | 2400 | 0.0676 |
80
+ | 0.0391 | 1.55 | 2500 | 0.0738 |
81
+ | 0.0436 | 1.61 | 2600 | 0.0586 |
82
+ | 0.0499 | 1.67 | 2700 | 0.0640 |
83
+ | 0.0385 | 1.74 | 2800 | 0.0594 |
84
+ | 0.0497 | 1.8 | 2900 | 0.0547 |
85
+ | 0.0312 | 1.86 | 3000 | 0.0603 |
86
+ | 0.039 | 1.92 | 3100 | 0.0479 |
87
+ | 0.0328 | 1.98 | 3200 | 0.0459 |
88
+ | 0.0202 | 2.05 | 3300 | 0.0521 |
89
+ | 0.0125 | 2.11 | 3400 | 0.0517 |
90
+ | 0.0085 | 2.17 | 3500 | 0.0472 |
91
+ | 0.0056 | 2.23 | 3600 | 0.0556 |
92
+ | 0.0183 | 2.29 | 3700 | 0.0495 |
93
+ | 0.0081 | 2.36 | 3800 | 0.0506 |
94
+ | 0.0079 | 2.42 | 3900 | 0.0526 |
95
+ | 0.0069 | 2.48 | 4000 | 0.0451 |
96
+ | 0.0081 | 2.54 | 4100 | 0.0459 |
97
+ | 0.0115 | 2.6 | 4200 | 0.0451 |
98
+ | 0.0067 | 2.67 | 4300 | 0.0464 |
99
+ | 0.0052 | 2.73 | 4400 | 0.0469 |
100
+ | 0.0127 | 2.79 | 4500 | 0.0459 |
101
+ | 0.0097 | 2.85 | 4600 | 0.0457 |
102
+ | 0.0113 | 2.91 | 4700 | 0.0456 |
103
+ | 0.0123 | 2.98 | 4800 | 0.0455 |
104
+
105
+
106
+ ### Framework versions
107
+
108
+ - PEFT 0.9.0
109
+ - Transformers 4.38.2
110
+ - Pytorch 2.1.0+cu121
111
+ - Datasets 2.18.0
112
+ - Tokenizers 0.15.2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14756bb4defb09ec888da43a3128c86b1ace8fc4b8898f7c889df749bdae2869
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8bf4127134c0ed468482e73a7e7bb01ecd05fc3893cd76572307d8d23657048
3
  size 83945296