Update README.md
Browse files
README.md
CHANGED
@@ -19,10 +19,22 @@ base_model: unsloth/mistral-7b-bnb-4bit
|
|
19 |
|
20 |
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
21 |
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
Number of trainable parameters = 41,943,040
|
27 |
-
|
|
|
|
|
|
|
|
|
28 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
|
|
19 |
|
20 |
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
21 |
|
22 |
+
Num GPUs = 1
|
23 |
+
|
24 |
+
Num Epochs = 2
|
25 |
+
|
26 |
+
Batch size per device = 2
|
27 |
+
|
28 |
+
Gradient Accumulation steps = 2
|
29 |
+
|
30 |
+
Total batch size = 8
|
31 |
+
|
32 |
+
otal steps = 2
|
33 |
+
|
34 |
Number of trainable parameters = 41,943,040
|
35 |
+
|
36 |
+
Total Samples = 800
|
37 |
+
|
38 |
+
Source of reports: [ORKL](https://orkl.eu/)
|
39 |
+
|
40 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|