End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: llama3.2
|
| 4 |
+
base_model: meta-llama/Llama-3.2-1B-Instruct
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:meta-llama/Llama-3.2-1B-Instruct
|
| 7 |
+
- lora
|
| 8 |
+
- transformers
|
| 9 |
+
pipeline_tag: text-generation
|
| 10 |
+
model-index:
|
| 11 |
+
- name: llama3_1b_xsum_lora-finalmodel
|
| 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 |
+
# llama3_1b_xsum_lora-finalmodel
|
| 19 |
+
|
| 20 |
+
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.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 1.8001
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.0002
|
| 42 |
+
- train_batch_size: 2
|
| 43 |
+
- eval_batch_size: 2
|
| 44 |
+
- seed: 42
|
| 45 |
+
- gradient_accumulation_steps: 4
|
| 46 |
+
- total_train_batch_size: 8
|
| 47 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 1
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
+
|:-------------:|:------:|:-----:|:---------------:|
|
| 55 |
+
| 1.9495 | 0.0784 | 2000 | 1.9472 |
|
| 56 |
+
| 1.916 | 0.1568 | 4000 | 1.8971 |
|
| 57 |
+
| 1.8764 | 0.2352 | 6000 | 1.8705 |
|
| 58 |
+
| 1.888 | 0.3137 | 8000 | 1.8549 |
|
| 59 |
+
| 1.8387 | 0.3921 | 10000 | 1.8423 |
|
| 60 |
+
| 1.872 | 0.4705 | 12000 | 1.8342 |
|
| 61 |
+
| 1.8299 | 0.5489 | 14000 | 1.8244 |
|
| 62 |
+
| 1.8417 | 0.6273 | 16000 | 1.8188 |
|
| 63 |
+
| 1.8185 | 0.7057 | 18000 | 1.8116 |
|
| 64 |
+
| 1.8218 | 0.7841 | 20000 | 1.8073 |
|
| 65 |
+
| 1.8071 | 0.8626 | 22000 | 1.8029 |
|
| 66 |
+
| 1.8267 | 0.9410 | 24000 | 1.8001 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- PEFT 0.17.1
|
| 72 |
+
- Transformers 4.57.1
|
| 73 |
+
- Pytorch 2.6.0+cu124
|
| 74 |
+
- Datasets 3.6.0
|
| 75 |
+
- Tokenizers 0.22.1
|