armahlovis
commited on
Commit
•
68929ff
1
Parent(s):
e611c8d
Update README.md
Browse files
README.md
CHANGED
@@ -15,15 +15,15 @@ This model is fine tunned on GPT2 to generate text following the writings of W
|
|
15 |
|
16 |
## Model Description
|
17 |
|
18 |
-
The model is designed to be finned tunning with writting from Historical black black writers who
|
19 |
-
|
20 |
|
21 |
|
22 |
|
23 |
- **Developed by:** [More Information Needed]
|
24 |
- **Shared by [optional]:** [More Information Needed]
|
25 |
- **Model type:** [More Information Needed]
|
26 |
-
- **Language(s) (NLP):** [More Information Needed]
|
27 |
- **License:** [More Information Needed]
|
28 |
- **Finetuned from model [optional]:** [More Information Needed]
|
29 |
|
@@ -99,6 +99,13 @@ Use the code below to get started with the model.
|
|
99 |
### Training Hyperparameters
|
100 |
|
101 |
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
102 |
|
103 |
### Speeds, Sizes, Times [optional]
|
104 |
|
|
|
15 |
|
16 |
## Model Description
|
17 |
|
18 |
+
The model is designed to be finned tunning with writting from Historical black black writers who wrote on freedom and emancipation. This first version has GPT2
|
19 |
+
fintunned with the writings of W. E. Burghardt Du Bois.
|
20 |
|
21 |
|
22 |
|
23 |
- **Developed by:** [More Information Needed]
|
24 |
- **Shared by [optional]:** [More Information Needed]
|
25 |
- **Model type:** [More Information Needed]
|
26 |
+
- **Language(s) (NLP):** [More Information Needed] English
|
27 |
- **License:** [More Information Needed]
|
28 |
- **Finetuned from model [optional]:** [More Information Needed]
|
29 |
|
|
|
99 |
### Training Hyperparameters
|
100 |
|
101 |
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
102 |
+
- Num examples = 1005
|
103 |
+
Num Epochs = 3
|
104 |
+
Instantaneous batch size per device = 8
|
105 |
+
Total train batch size (w. parallel, distributed & accumulation) = 8
|
106 |
+
Gradient Accumulation steps = 1
|
107 |
+
Total optimization steps = 378
|
108 |
+
Number of trainable parameters = 124439808
|
109 |
|
110 |
### Speeds, Sizes, Times [optional]
|
111 |
|