Training complete
Browse files
README.md
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: gemma
|
| 4 |
+
base_model: google/paligemma-3b-pt-224
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: pali_191805
|
| 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 |
+
# pali_191805
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [google/paligemma-3b-pt-224](https://huggingface.co/google/paligemma-3b-pt-224) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.8563
|
| 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: 2e-05
|
| 39 |
+
- train_batch_size: 2
|
| 40 |
+
- eval_batch_size: 2
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 8
|
| 43 |
+
- total_train_batch_size: 16
|
| 44 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_steps: 2
|
| 47 |
+
- num_epochs: 5
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 53 |
+
| 18.2133 | 0.0444 | 50 | 1.7766 |
|
| 54 |
+
| 11.9694 | 0.0889 | 100 | 1.3043 |
|
| 55 |
+
| 9.7625 | 0.1333 | 150 | 1.1940 |
|
| 56 |
+
| 9.0576 | 0.1778 | 200 | 1.1325 |
|
| 57 |
+
| 9.3286 | 0.2222 | 250 | 1.0906 |
|
| 58 |
+
| 8.5435 | 0.2667 | 300 | 1.0586 |
|
| 59 |
+
| 8.2508 | 0.3111 | 350 | 1.0357 |
|
| 60 |
+
| 8.3642 | 0.3556 | 400 | 1.0151 |
|
| 61 |
+
| 8.0343 | 0.4 | 450 | 0.9982 |
|
| 62 |
+
| 8.1537 | 0.4444 | 500 | 0.9818 |
|
| 63 |
+
| 7.6705 | 0.4889 | 550 | 0.9672 |
|
| 64 |
+
| 7.6794 | 0.5333 | 600 | 0.9557 |
|
| 65 |
+
| 7.3842 | 0.5778 | 650 | 0.9470 |
|
| 66 |
+
| 7.5392 | 0.6222 | 700 | 0.9343 |
|
| 67 |
+
| 7.3926 | 0.6667 | 750 | 0.9233 |
|
| 68 |
+
| 7.5391 | 0.7111 | 800 | 0.9141 |
|
| 69 |
+
| 7.3299 | 0.7556 | 850 | 0.9053 |
|
| 70 |
+
| 7.3423 | 0.8 | 900 | 0.8974 |
|
| 71 |
+
| 7.4747 | 0.8444 | 950 | 0.8911 |
|
| 72 |
+
| 7.252 | 0.8889 | 1000 | 0.8832 |
|
| 73 |
+
| 7.1392 | 0.9333 | 1050 | 0.8783 |
|
| 74 |
+
| 6.9769 | 0.9778 | 1100 | 0.8719 |
|
| 75 |
+
| 7.0285 | 1.0222 | 1150 | 0.8665 |
|
| 76 |
+
| 6.8336 | 1.0667 | 1200 | 0.8613 |
|
| 77 |
+
| 6.748 | 1.1111 | 1250 | 0.8563 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### Framework versions
|
| 81 |
+
|
| 82 |
+
- PEFT 0.14.0
|
| 83 |
+
- Transformers 4.51.3
|
| 84 |
+
- Pytorch 2.6.0+cu124
|
| 85 |
+
- Datasets 3.6.0
|
| 86 |
+
- Tokenizers 0.21.1
|