End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: llama3.2
|
| 4 |
+
base_model: meta-llama/Llama-3.2-1B-Instruct
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: llama-fine-tuned
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# llama-fine-tuned
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.3503
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0001
|
| 39 |
+
- train_batch_size: 2
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 1
|
| 45 |
+
- mixed_precision_training: Native AMP
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 51 |
+
| 1.6035 | 0.0357 | 50 | 0.9702 |
|
| 52 |
+
| 0.6392 | 0.0714 | 100 | 0.6272 |
|
| 53 |
+
| 0.5979 | 0.1071 | 150 | 0.5398 |
|
| 54 |
+
| 0.5629 | 0.1429 | 200 | 0.5044 |
|
| 55 |
+
| 0.4761 | 0.1786 | 250 | 0.4689 |
|
| 56 |
+
| 0.4998 | 0.2143 | 300 | 0.4494 |
|
| 57 |
+
| 0.4363 | 0.25 | 350 | 0.4524 |
|
| 58 |
+
| 0.4433 | 0.2857 | 400 | 0.4322 |
|
| 59 |
+
| 0.4882 | 0.3214 | 450 | 0.4135 |
|
| 60 |
+
| 0.4316 | 0.3571 | 500 | 0.4017 |
|
| 61 |
+
| 0.389 | 0.3929 | 550 | 0.3951 |
|
| 62 |
+
| 0.4041 | 0.4286 | 600 | 0.3908 |
|
| 63 |
+
| 0.456 | 0.4643 | 650 | 0.3860 |
|
| 64 |
+
| 0.3872 | 0.5 | 700 | 0.3788 |
|
| 65 |
+
| 0.3962 | 0.5357 | 750 | 0.3792 |
|
| 66 |
+
| 0.3524 | 0.5714 | 800 | 0.3762 |
|
| 67 |
+
| 0.3409 | 0.6071 | 850 | 0.3700 |
|
| 68 |
+
| 0.421 | 0.6429 | 900 | 0.3746 |
|
| 69 |
+
| 0.349 | 0.6786 | 950 | 0.3634 |
|
| 70 |
+
| 0.4194 | 0.7143 | 1000 | 0.3665 |
|
| 71 |
+
| 0.3621 | 0.75 | 1050 | 0.3607 |
|
| 72 |
+
| 0.3663 | 0.7857 | 1100 | 0.3603 |
|
| 73 |
+
| 0.3434 | 0.8214 | 1150 | 0.3592 |
|
| 74 |
+
| 0.3609 | 0.8571 | 1200 | 0.3553 |
|
| 75 |
+
| 0.342 | 0.8929 | 1250 | 0.3524 |
|
| 76 |
+
| 0.3889 | 0.9286 | 1300 | 0.3513 |
|
| 77 |
+
| 0.3604 | 0.9643 | 1350 | 0.3508 |
|
| 78 |
+
| 0.354 | 1.0 | 1400 | 0.3503 |
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
### Framework versions
|
| 82 |
+
|
| 83 |
+
- PEFT 0.13.2
|
| 84 |
+
- Transformers 4.47.0
|
| 85 |
+
- Pytorch 2.5.1+cu121
|
| 86 |
+
- Tokenizers 0.21.0
|