Update README.md
Browse files
README.md
CHANGED
@@ -8,16 +8,33 @@ model-index:
|
|
8 |
results: []
|
9 |
---
|
10 |
|
11 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
-
should probably proofread and complete it, then remove this comment. -->
|
13 |
-
|
14 |
# togetherchat-dev-7b
|
15 |
|
16 |
-
This model is a fine-tuned version of [togethercomputer/LLaMA-2-7B-32K](https://huggingface.co/togethercomputer/LLaMA-2-7B-32K)
|
|
|
|
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
20 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
|
22 |
## Intended uses & limitations
|
23 |
|
|
|
8 |
results: []
|
9 |
---
|
10 |
|
|
|
|
|
|
|
11 |
# togetherchat-dev-7b
|
12 |
|
13 |
+
This model is a fine-tuned version of [togethercomputer/LLaMA-2-7B-32K](https://huggingface.co/togethercomputer/LLaMA-2-7B-32K) using 5000 examples and 3 datasets:
|
14 |
+
|
15 |
+
platypus_dataset = load_dataset("garage-bAInd/Open-Platypus")
|
16 |
+
codealpaca_dataset = load_dataset("sahil2801/CodeAlpaca-20k")
|
17 |
+
evol_codealpaca_dataset = load_dataset("theblackcat102/evol-codealpaca-v1")
|
18 |
+
|
19 |
|
20 |
## Model description
|
21 |
|
22 |
+
Step Training Loss
|
23 |
+
-------------
|
24 |
+
-60 1.293000-
|
25 |
+
-120 0.673600-
|
26 |
+
-180 0.633200-
|
27 |
+
-240 0.611600-
|
28 |
+
-300 0.633000-
|
29 |
+
-360 0.589500-
|
30 |
+
-480 0.587600-
|
31 |
+
-540 0.569000-
|
32 |
+
-600 0.548700-
|
33 |
+
-660 0.553100-
|
34 |
+
-720 0.531500-
|
35 |
+
-780 0.506400-
|
36 |
+
-840 0.512500-
|
37 |
+
-------------
|
38 |
|
39 |
## Intended uses & limitations
|
40 |
|