End of training
Browse files- README.md +16 -18
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -96,7 +96,7 @@ special_tokens:
|
|
| 96 |
|
| 97 |
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 the None dataset.
|
| 98 |
It achieves the following results on the evaluation set:
|
| 99 |
-
- Loss: 0.
|
| 100 |
|
| 101 |
## Model description
|
| 102 |
|
|
@@ -133,23 +133,21 @@ The following hyperparameters were used during training:
|
|
| 133 |
|
| 134 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 135 |
|:-------------:|:------:|:----:|:---------------:|
|
| 136 |
-
|
|
| 137 |
-
|
|
| 138 |
-
| 0.
|
| 139 |
-
| 0.
|
| 140 |
-
| 0.
|
| 141 |
-
| 0.
|
| 142 |
-
| 0.
|
| 143 |
-
| 0.
|
| 144 |
-
| 0.
|
| 145 |
-
| 0.
|
| 146 |
-
| 0.
|
| 147 |
-
| 0.
|
| 148 |
-
| 0.
|
| 149 |
-
| 0.
|
| 150 |
-
| 0.
|
| 151 |
-
| 0.051 | 3.5114 | 165 | 0.0213 |
|
| 152 |
-
| 0.0184 | 3.7614 | 176 | 0.0212 |
|
| 153 |
|
| 154 |
|
| 155 |
### Framework versions
|
|
|
|
| 96 |
|
| 97 |
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 the None dataset.
|
| 98 |
It achieves the following results on the evaluation set:
|
| 99 |
+
- Loss: 0.0557
|
| 100 |
|
| 101 |
## Model description
|
| 102 |
|
|
|
|
| 133 |
|
| 134 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 135 |
|:-------------:|:------:|:----:|:---------------:|
|
| 136 |
+
| 1.7724 | 0.0303 | 1 | 1.7779 |
|
| 137 |
+
| 1.2158 | 0.2727 | 9 | 1.0692 |
|
| 138 |
+
| 0.2116 | 0.5455 | 18 | 0.1796 |
|
| 139 |
+
| 0.1051 | 0.8182 | 27 | 0.1048 |
|
| 140 |
+
| 0.0762 | 1.0227 | 36 | 0.0859 |
|
| 141 |
+
| 0.0704 | 1.2955 | 45 | 0.0763 |
|
| 142 |
+
| 0.0661 | 1.5682 | 54 | 0.0692 |
|
| 143 |
+
| 0.073 | 1.8409 | 63 | 0.0646 |
|
| 144 |
+
| 0.0625 | 2.0455 | 72 | 0.0621 |
|
| 145 |
+
| 0.0522 | 2.3182 | 81 | 0.0602 |
|
| 146 |
+
| 0.0472 | 2.5909 | 90 | 0.0580 |
|
| 147 |
+
| 0.0545 | 2.8636 | 99 | 0.0571 |
|
| 148 |
+
| 0.0467 | 3.0682 | 108 | 0.0561 |
|
| 149 |
+
| 0.057 | 3.3409 | 117 | 0.0557 |
|
| 150 |
+
| 0.0477 | 3.6136 | 126 | 0.0557 |
|
|
|
|
|
|
|
| 151 |
|
| 152 |
|
| 153 |
### Framework versions
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 101036698
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8807cbd5b63ed7c6a4e11d0030904f68fe580184ce532161badaa79e40a890f9
|
| 3 |
size 101036698
|