End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
base_model: HuggingFaceM4/idefics-9b
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- diffusiondb
|
| 8 |
+
model-index:
|
| 9 |
+
- name: idefics-9b-ft-describe-diffusion-bf16
|
| 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 |
+
# idefics-9b-ft-describe-diffusion-bf16
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [HuggingFaceM4/idefics-9b](https://huggingface.co/HuggingFaceM4/idefics-9b) on the diffusiondb dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 1.4081
|
| 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: 0.0002
|
| 40 |
+
- train_batch_size: 2
|
| 41 |
+
- eval_batch_size: 2
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 32
|
| 44 |
+
- total_train_batch_size: 64
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_ratio: 0.03
|
| 48 |
+
- num_epochs: 2
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
+
| 2.0874 | 0.07 | 50 | 2.1257 |
|
| 55 |
+
| 2.0532 | 0.14 | 100 | 1.9973 |
|
| 56 |
+
| 1.9417 | 0.21 | 150 | 1.9246 |
|
| 57 |
+
| 1.8358 | 0.28 | 200 | 1.8735 |
|
| 58 |
+
| 1.8499 | 0.36 | 250 | 1.8305 |
|
| 59 |
+
| 1.7695 | 0.43 | 300 | 1.7770 |
|
| 60 |
+
| 1.7505 | 0.5 | 350 | 1.7454 |
|
| 61 |
+
| 1.713 | 0.57 | 400 | 1.7115 |
|
| 62 |
+
| 1.7352 | 0.64 | 450 | 1.6791 |
|
| 63 |
+
| 1.6689 | 0.71 | 500 | 1.6526 |
|
| 64 |
+
| 1.6183 | 0.78 | 550 | 1.6257 |
|
| 65 |
+
| 1.6118 | 0.85 | 600 | 1.6001 |
|
| 66 |
+
| 1.6095 | 0.92 | 650 | 1.5800 |
|
| 67 |
+
| 1.5598 | 1.0 | 700 | 1.5598 |
|
| 68 |
+
| 1.4785 | 1.07 | 750 | 1.5403 |
|
| 69 |
+
| 1.4999 | 1.14 | 800 | 1.5219 |
|
| 70 |
+
| 1.4589 | 1.21 | 850 | 1.5063 |
|
| 71 |
+
| 1.4559 | 1.28 | 900 | 1.4942 |
|
| 72 |
+
| 1.4332 | 1.35 | 950 | 1.4792 |
|
| 73 |
+
| 1.4859 | 1.42 | 1000 | 1.4658 |
|
| 74 |
+
| 1.3888 | 1.49 | 1050 | 1.4537 |
|
| 75 |
+
| 1.4032 | 1.56 | 1100 | 1.4445 |
|
| 76 |
+
| 1.3702 | 1.64 | 1150 | 1.4352 |
|
| 77 |
+
| 1.3625 | 1.71 | 1200 | 1.4276 |
|
| 78 |
+
| 1.4067 | 1.78 | 1250 | 1.4199 |
|
| 79 |
+
| 1.3829 | 1.85 | 1300 | 1.4149 |
|
| 80 |
+
| 1.4251 | 1.92 | 1350 | 1.4103 |
|
| 81 |
+
| 1.3619 | 1.99 | 1400 | 1.4081 |
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
### Framework versions
|
| 85 |
+
|
| 86 |
+
- Transformers 4.32.0
|
| 87 |
+
- Pytorch 2.0.1+cu118
|
| 88 |
+
- Datasets 2.14.4
|
| 89 |
+
- Tokenizers 0.13.3
|