Commit
•
22feb0b
1
Parent(s):
6c770b5
End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: TinyLlama-1.1B-Chat-SchemaLinking-v1
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# TinyLlama-1.1B-Chat-SchemaLinking-v1
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0697
|
| 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: 0.0001
|
| 41 |
+
- train_batch_size: 1
|
| 42 |
+
- eval_batch_size: 1
|
| 43 |
+
- seed: 14
|
| 44 |
+
- gradient_accumulation_steps: 8
|
| 45 |
+
- total_train_batch_size: 8
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.03
|
| 49 |
+
- num_epochs: 5
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 56 |
+
| 0.3573 | 0.2334 | 250 | 0.1872 |
|
| 57 |
+
| 0.1155 | 0.4668 | 500 | 0.1122 |
|
| 58 |
+
| 0.079 | 0.7002 | 750 | 0.0828 |
|
| 59 |
+
| 0.0672 | 0.9336 | 1000 | 0.0741 |
|
| 60 |
+
| 0.0555 | 1.1670 | 1250 | 0.0720 |
|
| 61 |
+
| 0.055 | 1.4004 | 1500 | 0.0701 |
|
| 62 |
+
| 0.053 | 1.6338 | 1750 | 0.0681 |
|
| 63 |
+
| 0.0526 | 1.8672 | 2000 | 0.0664 |
|
| 64 |
+
| 0.047 | 2.1006 | 2250 | 0.0647 |
|
| 65 |
+
| 0.0406 | 2.3340 | 2500 | 0.0646 |
|
| 66 |
+
| 0.0411 | 2.5674 | 2750 | 0.0620 |
|
| 67 |
+
| 0.0352 | 2.8010 | 3000 | 0.0660 |
|
| 68 |
+
| 0.0337 | 3.0344 | 3250 | 0.0646 |
|
| 69 |
+
| 0.0326 | 3.2678 | 3500 | 0.0633 |
|
| 70 |
+
| 0.0323 | 3.5012 | 3750 | 0.0625 |
|
| 71 |
+
| 0.0321 | 3.7346 | 4000 | 0.0614 |
|
| 72 |
+
| 0.0317 | 3.9680 | 4250 | 0.0616 |
|
| 73 |
+
| 0.0271 | 4.2014 | 4500 | 0.0676 |
|
| 74 |
+
| 0.0258 | 4.4348 | 4750 | 0.0688 |
|
| 75 |
+
| 0.0257 | 4.6682 | 5000 | 0.0678 |
|
| 76 |
+
| 0.0227 | 4.9019 | 5250 | 0.0697 |
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
### Framework versions
|
| 80 |
+
|
| 81 |
+
- PEFT 0.13.2
|
| 82 |
+
- Transformers 4.45.2
|
| 83 |
+
- Pytorch 2.4.1+cu121
|
| 84 |
+
- Datasets 3.0.1
|
| 85 |
+
- Tokenizers 0.20.1
|