End of training
Browse files- README.md +15 -1
- adapter_model.bin +1 -1
README.md
CHANGED
@@ -2,6 +2,7 @@
|
|
2 |
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
|
|
5 |
- generated_from_trainer
|
6 |
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
7 |
model-index:
|
@@ -84,7 +85,9 @@ xformers_attention: null
|
|
84 |
|
85 |
# mistral-lora
|
86 |
|
87 |
-
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on
|
|
|
|
|
88 |
|
89 |
## Model description
|
90 |
|
@@ -117,6 +120,17 @@ The following hyperparameters were used during training:
|
|
117 |
- lr_scheduler_warmup_steps: 10
|
118 |
- num_epochs: 2
|
119 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
120 |
### Framework versions
|
121 |
|
122 |
- PEFT 0.8.2
|
|
|
2 |
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
+
- axolotl
|
6 |
- generated_from_trainer
|
7 |
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
8 |
model-index:
|
|
|
85 |
|
86 |
# mistral-lora
|
87 |
|
88 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset.
|
89 |
+
It achieves the following results on the evaluation set:
|
90 |
+
- Loss: 0.0298
|
91 |
|
92 |
## Model description
|
93 |
|
|
|
120 |
- lr_scheduler_warmup_steps: 10
|
121 |
- num_epochs: 2
|
122 |
|
123 |
+
### Training results
|
124 |
+
|
125 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
126 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
127 |
+
| 2.2964 | 0.02 | 1 | 2.1559 |
|
128 |
+
| 0.0487 | 0.41 | 21 | 0.0479 |
|
129 |
+
| 0.0367 | 0.81 | 42 | 0.0387 |
|
130 |
+
| 0.0331 | 1.19 | 63 | 0.0333 |
|
131 |
+
| 0.0209 | 1.6 | 84 | 0.0298 |
|
132 |
+
|
133 |
+
|
134 |
### Framework versions
|
135 |
|
136 |
- PEFT 0.8.2
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 84047946
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70a7d2ffe31a0728f95e49b0399658f33f28d33f7297d849dbeaa2c3eadf2d07
|
3 |
size 84047946
|