Commit
•
8e98956
1
Parent(s):
8e9d665
chain-texts-0.1-mixtral-8x7b
Browse files
README.md
CHANGED
|
@@ -19,8 +19,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
# mistral_instruct_generation
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [cognitivecomputations/dolphin-2.2.1-mistral-7b](https://huggingface.co/cognitivecomputations/dolphin-2.2.1-mistral-7b) on the generator dataset.
|
| 22 |
-
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 1.5008
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -48,28 +46,6 @@ The following hyperparameters were used during training:
|
|
| 48 |
- lr_scheduler_warmup_steps: 0.03
|
| 49 |
- num_epochs: 3
|
| 50 |
|
| 51 |
-
### Training results
|
| 52 |
-
|
| 53 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
-
|:-------------:|:------:|:----:|:---------------:|
|
| 55 |
-
| 1.9388 | 0.1869 | 20 | 1.8326 |
|
| 56 |
-
| 1.7574 | 0.3738 | 40 | 1.6963 |
|
| 57 |
-
| 1.6736 | 0.5607 | 60 | 1.6514 |
|
| 58 |
-
| 1.6703 | 0.7477 | 80 | 1.6321 |
|
| 59 |
-
| 1.6708 | 0.9346 | 100 | 1.6113 |
|
| 60 |
-
| 1.6049 | 1.1215 | 120 | 1.5912 |
|
| 61 |
-
| 1.6446 | 1.3084 | 140 | 1.5891 |
|
| 62 |
-
| 1.5222 | 1.4953 | 160 | 1.5691 |
|
| 63 |
-
| 1.6022 | 1.6822 | 180 | 1.5599 |
|
| 64 |
-
| 1.4326 | 1.8692 | 200 | 1.5512 |
|
| 65 |
-
| 1.4876 | 2.0561 | 220 | 1.5548 |
|
| 66 |
-
| 1.4821 | 2.2430 | 240 | 1.5379 |
|
| 67 |
-
| 1.3868 | 2.4299 | 260 | 1.5326 |
|
| 68 |
-
| 1.5277 | 2.6168 | 280 | 1.5286 |
|
| 69 |
-
| 1.5205 | 2.8037 | 300 | 1.5084 |
|
| 70 |
-
| 1.4125 | 2.9907 | 320 | 1.5008 |
|
| 71 |
-
|
| 72 |
-
|
| 73 |
### Framework versions
|
| 74 |
|
| 75 |
- PEFT 0.10.0
|
|
|
|
| 19 |
# mistral_instruct_generation
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [cognitivecomputations/dolphin-2.2.1-mistral-7b](https://huggingface.co/cognitivecomputations/dolphin-2.2.1-mistral-7b) on the generator dataset.
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 46 |
- lr_scheduler_warmup_steps: 0.03
|
| 47 |
- num_epochs: 3
|
| 48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
### Framework versions
|
| 50 |
|
| 51 |
- PEFT 0.10.0
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e93218612a35c41f3f154c7607a8f27c50bfcf507bc1c115991ba8d602604af
|
| 3 |
+
size 109069176
|
runs/Apr25_16-29-44_5a64c3d72f47/events.out.tfevents.1714062584.5a64c3d72f47.797.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20573f80d39a4591ab730ecf7bbe35b55f08f4c34be6ff4db51c6484327c2f78
|
| 3 |
+
size 4184
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4de7e0bc9eb6478f2441b556f02b1149fd84c0ae240ec8ac1e66d6966fdb56f
|
| 3 |
size 4984
|