Zangs3011 commited on
Commit
7f98365
1 Parent(s): ce9f31a

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +29 -0
README.md ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ datasets:
3
+ - tatsu-lab/alpaca
4
+ library_name: peft
5
+ tags:
6
+ - facebook/opt-125m
7
+ - code
8
+ - instruct
9
+ - alpaca-instruct
10
+ - alpaca
11
+ ---
12
+
13
+ We finetuned facebook/opt-125m on tatsu-lab/alpaca Dataset for 10 epochs using [MonsterAPI](https://monsterapi.ai) no-code [LLM finetuner](https://docs.monsterapi.ai/fine-tune-a-large-language-model-llm).
14
+
15
+ This dataset is HuggingFaceH4/tatsu-lab/alpaca unfiltered, removing 36 instances of blatant alignment.
16
+
17
+ The finetuning session got completed in 40 minutes and costed us only `$4` for the entire finetuning run!
18
+
19
+ #### Hyperparameters & Run details:
20
+ - Model: facebook/opt-125m
21
+ - Dataset: tatsu-lab/alpaca
22
+ - Learning rate: 0.0003
23
+ - Number of epochs: 10
24
+ - Data split: Training: 90% / Validation: 10%
25
+ - Gradient accumulation steps: 1
26
+ -
27
+ ---
28
+ license: apache-2.0
29
+ ---