Model save
Browse files- README.md +74 -0
- generation_config.json +6 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: BEE-spoke-data/NanoLlama-GQA-L10-A32_KV8-v12-minipile
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: NanoLlama-GQA-L10-A32_KV8-v12-minipile-knowledge-inoc-concat-v1-2048-vN
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# NanoLlama-GQA-L10-A32_KV8-v12-minipile-knowledge-inoc-concat-v1-2048-vN
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [BEE-spoke-data/NanoLlama-GQA-L10-A32_KV8-v12-minipile](https://huggingface.co/BEE-spoke-data/NanoLlama-GQA-L10-A32_KV8-v12-minipile) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 2.5937
|
| 21 |
+
- Accuracy: 0.4948
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.00025
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 4
|
| 43 |
+
- seed: 2280
|
| 44 |
+
- gradient_accumulation_steps: 16
|
| 45 |
+
- total_train_batch_size: 128
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: inverse_sqrt
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.05
|
| 49 |
+
- num_epochs: 1.0
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 55 |
+
| 2.5744 | 0.08 | 200 | 2.7138 | 0.4776 |
|
| 56 |
+
| 2.5387 | 0.16 | 400 | 2.6713 | 0.4836 |
|
| 57 |
+
| 2.4718 | 0.23 | 600 | 2.6462 | 0.4873 |
|
| 58 |
+
| 2.4681 | 0.31 | 800 | 2.6328 | 0.4892 |
|
| 59 |
+
| 2.5351 | 0.39 | 1000 | 2.6227 | 0.4908 |
|
| 60 |
+
| 2.5316 | 0.47 | 1200 | 2.6159 | 0.4914 |
|
| 61 |
+
| 2.527 | 0.54 | 1400 | 2.6103 | 0.4921 |
|
| 62 |
+
| 2.4838 | 0.62 | 1600 | 2.6058 | 0.4930 |
|
| 63 |
+
| 2.4483 | 0.7 | 1800 | 2.6024 | 0.4934 |
|
| 64 |
+
| 2.426 | 0.78 | 2000 | 2.5998 | 0.4937 |
|
| 65 |
+
| 2.4685 | 0.86 | 2200 | 2.5961 | 0.4944 |
|
| 66 |
+
| 2.4473 | 0.93 | 2400 | 2.5937 | 0.4948 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- Transformers 4.36.0.dev0
|
| 72 |
+
- Pytorch 2.1.0
|
| 73 |
+
- Datasets 2.15.0
|
| 74 |
+
- Tokenizers 0.15.0
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.36.0.dev0"
|
| 6 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 435736840
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66a03ba6a3b48c9b3e2f92dc13db8f0a7a8680f2dda96cf525f2214df68fc111
|
| 3 |
size 435736840
|