Aharneish commited on
Commit
7c148ef
·
verified ·
1 Parent(s): 2450b7d

End of training

Browse files
Files changed (2) hide show
  1. README.md +75 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-v0.1
9
+ model-index:
10
+ - name: mistral-test_1
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
+ # mistral-test_1
18
+
19
+ This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 2.2947
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: 1e-05
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 4
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 5
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:-----:|:----:|:---------------:|
53
+ | 1.8128 | 1.36 | 2500 | 2.1855 |
54
+ | 1.7961 | 1.63 | 3000 | 2.1808 |
55
+ | 1.7701 | 1.9 | 3500 | 2.2271 |
56
+ | 1.7186 | 2.17 | 4000 | 2.2265 |
57
+ | 1.6784 | 2.44 | 4500 | 2.2547 |
58
+ | 1.6692 | 2.71 | 5000 | 2.2547 |
59
+ | 1.6752 | 2.98 | 5500 | 2.2470 |
60
+ | 1.6206 | 3.26 | 6000 | 2.2842 |
61
+ | 1.599 | 3.53 | 6500 | 2.2663 |
62
+ | 1.6054 | 3.8 | 7000 | 2.2560 |
63
+ | 1.593 | 4.07 | 7500 | 2.3039 |
64
+ | 1.5771 | 4.34 | 8000 | 2.2797 |
65
+ | 1.5636 | 4.61 | 8500 | 2.2915 |
66
+ | 1.5551 | 4.88 | 9000 | 2.2947 |
67
+
68
+
69
+ ### Framework versions
70
+
71
+ - PEFT 0.9.0
72
+ - Transformers 4.38.1
73
+ - Pytorch 2.1.2
74
+ - Datasets 2.16.0
75
+ - Tokenizers 0.15.2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31a455cdbe6276fff38dcdb2fb1406089feaaa84fa72aa82c8ea345012d91172
3
  size 27280152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96a3572e67476d3f4609a190a5ca052e2a523a7d3cc0465be88f1ba1daf1b8b0
3
  size 27280152