Update README.md
Browse files
README.md
CHANGED
@@ -5,4 +5,32 @@ datasets:
|
|
5 |
base_model: mistralai/Mistral-7B-Instruct-v0.1
|
6 |
---
|
7 |
First model fine tune trained from https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1.
|
8 |
-
Code to create this here: https://colab.research.google.com/drive/1Wsi7q1sBJlXrVZAbxhMRZuKnhSFeU9mu?usp=sharing
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
base_model: mistralai/Mistral-7B-Instruct-v0.1
|
6 |
---
|
7 |
First model fine tune trained from https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1.
|
8 |
+
Code to create this here: https://colab.research.google.com/drive/1Wsi7q1sBJlXrVZAbxhMRZuKnhSFeU9mu?usp=sharing
|
9 |
+
|
10 |
+
Parameters used for fine tuning:
|
11 |
+
`model_params={
|
12 |
+
"project_name": project_name,
|
13 |
+
"model_name": model_name,
|
14 |
+
"repo_id": username+'/'+repo_name,
|
15 |
+
"block_size": block_size,
|
16 |
+
"model_max_length": max_token_length,
|
17 |
+
"logging_steps": -1,
|
18 |
+
"evaluation_strategy": "epoch",
|
19 |
+
"save_total_limit": 1,
|
20 |
+
"save_strategy": "epoch",
|
21 |
+
"mixed_precision": "fp16",
|
22 |
+
"lr": 0.00003,
|
23 |
+
"epochs": 3,
|
24 |
+
"batch_size": 1,
|
25 |
+
"warmup_ratio": 0.1,
|
26 |
+
"gradient_accumulation": 1,
|
27 |
+
"optimizer": "adamw_torch",
|
28 |
+
"scheduler": "linear",
|
29 |
+
"weight_decay": 0,
|
30 |
+
"max_grad_norm": 1,
|
31 |
+
"seed": 42,
|
32 |
+
"quantization": "int4",
|
33 |
+
"lora_r": 16,
|
34 |
+
"lora_alpha": 32,
|
35 |
+
"lora_dropout": 0.05
|
36 |
+
}`
|