TopperThijs commited on
Commit
0ea0246
1 Parent(s): 1812756

End of training

Browse files
Files changed (1) hide show
  1. README.md +60 -0
README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: tiiuae/falcon-7b
3
+ library_name: peft
4
+ license: apache-2.0
5
+ tags:
6
+ - trl
7
+ - sft
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: Falcon-complete-10-15
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
+ # Falcon-complete-10-15
18
+
19
+ This model is a fine-tuned version of [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 2.4762
22
+ - Model Preparation Time: 0.004
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 0.0002
42
+ - train_batch_size: 2
43
+ - eval_batch_size: 8
44
+ - seed: 42
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: constant
47
+ - lr_scheduler_warmup_ratio: 0.03
48
+ - num_epochs: 10
49
+
50
+ ### Training results
51
+
52
+
53
+
54
+ ### Framework versions
55
+
56
+ - PEFT 0.11.1
57
+ - Transformers 4.43.3
58
+ - Pytorch 2.3.0+cu121
59
+ - Datasets 2.18.0
60
+ - Tokenizers 0.19.1