SourCoachSauers
commited on
Commit
•
966e43b
1
Parent(s):
5e98232
color_descriptions
Browse files- README.md +26 -1
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -17,6 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
# results
|
18 |
|
19 |
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on an unknown dataset.
|
|
|
|
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -44,10 +46,33 @@ The following hyperparameters were used during training:
|
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: cosine
|
46 |
- lr_scheduler_warmup_ratio: 0.03
|
47 |
-
-
|
48 |
|
49 |
### Training results
|
50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
|
52 |
|
53 |
### Framework versions
|
|
|
17 |
# results
|
18 |
|
19 |
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.5881
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: cosine
|
48 |
- lr_scheduler_warmup_ratio: 0.03
|
49 |
+
- num_epochs: 2
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
+
|:-------------:|:------:|:----:|:---------------:|
|
55 |
+
| 0.6511 | 0.0948 | 50 | 0.7913 |
|
56 |
+
| 0.5479 | 0.1896 | 100 | 0.7001 |
|
57 |
+
| 0.5125 | 0.2844 | 150 | 0.6768 |
|
58 |
+
| 0.4974 | 0.3791 | 200 | 0.6564 |
|
59 |
+
| 0.4947 | 0.4739 | 250 | 0.6490 |
|
60 |
+
| 0.4802 | 0.5687 | 300 | 0.6383 |
|
61 |
+
| 0.4762 | 0.6635 | 350 | 0.6289 |
|
62 |
+
| 0.4678 | 0.7583 | 400 | 0.6233 |
|
63 |
+
| 0.4742 | 0.8531 | 450 | 0.6157 |
|
64 |
+
| 0.4633 | 0.9479 | 500 | 0.6127 |
|
65 |
+
| 0.6096 | 1.0427 | 550 | 0.6027 |
|
66 |
+
| 0.6137 | 1.1374 | 600 | 0.5986 |
|
67 |
+
| 0.6163 | 1.2322 | 650 | 0.5963 |
|
68 |
+
| 0.6078 | 1.3270 | 700 | 0.5943 |
|
69 |
+
| 0.6019 | 1.4218 | 750 | 0.5921 |
|
70 |
+
| 0.615 | 1.5166 | 800 | 0.5906 |
|
71 |
+
| 0.6061 | 1.6114 | 850 | 0.5897 |
|
72 |
+
| 0.6106 | 1.7062 | 900 | 0.5890 |
|
73 |
+
| 0.6027 | 1.8009 | 950 | 0.5886 |
|
74 |
+
| 0.6094 | 1.8957 | 1000 | 0.5883 |
|
75 |
+
| 0.5261 | 1.9905 | 1050 | 0.5881 |
|
76 |
|
77 |
|
78 |
### Framework versions
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 57701064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a2f716d20045f5a32c6b9a608f618466fe254493721f18005d2f1dd889029eb
|
3 |
size 57701064
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5368
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6d9c3d4237312a4bba1a2b8b3197b72e01c812c239c98b08f19e97a2f942d4e
|
3 |
size 5368
|