Model save
Browse files- README.md +80 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: llama3
|
| 4 |
+
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:meta-llama/Meta-Llama-3-8B-Instruct
|
| 7 |
+
- llama-factory
|
| 8 |
+
- transformers
|
| 9 |
+
pipeline_tag: text-generation
|
| 10 |
+
model-index:
|
| 11 |
+
- name: test
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# test
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.3585
|
| 23 |
+
- Num Input Tokens Seen: 46944
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 0.03
|
| 43 |
+
- train_batch_size: 4
|
| 44 |
+
- eval_batch_size: 4
|
| 45 |
+
- seed: 123
|
| 46 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- num_epochs: 1
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:-----------------:|
|
| 55 |
+
| 3.6273 | 0.056 | 7 | 6.9320 | 2880 |
|
| 56 |
+
| 6.3813 | 0.112 | 14 | 1.6228 | 5920 |
|
| 57 |
+
| 1.4507 | 0.168 | 21 | 0.4040 | 8416 |
|
| 58 |
+
| 1.7771 | 0.224 | 28 | 3.6187 | 11264 |
|
| 59 |
+
| 0.7848 | 0.28 | 35 | 0.3667 | 13824 |
|
| 60 |
+
| 0.4314 | 0.336 | 42 | 0.3662 | 16672 |
|
| 61 |
+
| 0.4096 | 0.392 | 49 | 0.5265 | 19296 |
|
| 62 |
+
| 0.5554 | 0.448 | 56 | 0.3925 | 22432 |
|
| 63 |
+
| 0.4968 | 0.504 | 63 | 2.6525 | 25504 |
|
| 64 |
+
| 0.3298 | 0.56 | 70 | 0.3776 | 28064 |
|
| 65 |
+
| 0.3663 | 0.616 | 77 | 0.3627 | 30720 |
|
| 66 |
+
| 0.3654 | 0.672 | 84 | 0.3526 | 33504 |
|
| 67 |
+
| 0.3495 | 0.728 | 91 | 0.3546 | 36128 |
|
| 68 |
+
| 0.412 | 0.784 | 98 | 0.3497 | 38592 |
|
| 69 |
+
| 0.349 | 0.84 | 105 | 0.3538 | 41280 |
|
| 70 |
+
| 0.3482 | 0.896 | 112 | 0.3566 | 44160 |
|
| 71 |
+
| 0.3258 | 0.952 | 119 | 0.3585 | 46944 |
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
### Framework versions
|
| 75 |
+
|
| 76 |
+
- PEFT 0.17.1
|
| 77 |
+
- Transformers 4.51.3
|
| 78 |
+
- Pytorch 2.9.0+cu128
|
| 79 |
+
- Datasets 4.0.0
|
| 80 |
+
- Tokenizers 0.21.4
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 819328
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:308c02334376417c3f33d701e2db55625d8083123a385fa627c9d29e1afa9412
|
| 3 |
size 819328
|