Model save
Browse files- README.md +81 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- llama-factory
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
| 8 |
+
model-index:
|
| 9 |
+
- name: llama-3-86-lora-pretrain_v2
|
| 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 |
+
# llama-3-86-lora-pretrain_v2
|
| 17 |
+
|
| 18 |
+
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.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 2.2355
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 0.0001
|
| 40 |
+
- train_batch_size: 1
|
| 41 |
+
- eval_batch_size: 1
|
| 42 |
+
- seed: 42
|
| 43 |
+
- distributed_type: multi-GPU
|
| 44 |
+
- num_devices: 2
|
| 45 |
+
- gradient_accumulation_steps: 8
|
| 46 |
+
- total_train_batch_size: 16
|
| 47 |
+
- total_eval_batch_size: 2
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: cosine
|
| 50 |
+
- lr_scheduler_warmup_steps: 500
|
| 51 |
+
- num_epochs: 3.0
|
| 52 |
+
- mixed_precision_training: Native AMP
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 58 |
+
| 2.8142 | 0.1877 | 100 | 2.8566 |
|
| 59 |
+
| 2.7235 | 0.3755 | 200 | 2.6776 |
|
| 60 |
+
| 2.5809 | 0.5632 | 300 | 2.5664 |
|
| 61 |
+
| 2.3971 | 0.7510 | 400 | 2.4458 |
|
| 62 |
+
| 2.4147 | 0.9387 | 500 | 2.3812 |
|
| 63 |
+
| 2.3987 | 1.1265 | 600 | 2.3436 |
|
| 64 |
+
| 2.3 | 1.3142 | 700 | 2.3193 |
|
| 65 |
+
| 2.3219 | 1.5020 | 800 | 2.2951 |
|
| 66 |
+
| 2.377 | 1.6897 | 900 | 2.2763 |
|
| 67 |
+
| 2.2977 | 1.8775 | 1000 | 2.2623 |
|
| 68 |
+
| 2.269 | 2.0652 | 1100 | 2.2525 |
|
| 69 |
+
| 2.2305 | 2.2530 | 1200 | 2.2442 |
|
| 70 |
+
| 2.3866 | 2.4407 | 1300 | 2.2396 |
|
| 71 |
+
| 2.3217 | 2.6285 | 1400 | 2.2369 |
|
| 72 |
+
| 2.2007 | 2.8162 | 1500 | 2.2355 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
### Framework versions
|
| 76 |
+
|
| 77 |
+
- PEFT 0.10.0
|
| 78 |
+
- Transformers 4.40.0
|
| 79 |
+
- Pytorch 2.2.1
|
| 80 |
+
- Datasets 2.18.0
|
| 81 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 13648432
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a13daa8b607dcd3521ab611af3c96d1db2ea95fbfe187192b6a37e4725625de6
|
| 3 |
size 13648432
|