Commit
•
55432ba
1
Parent(s):
6ac6440
palicoqiqi/paligemma_VQAv2_enel645
Browse files- README.md +73 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: paligemma_vqav2_1
|
| 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 |
+
# paligemma_vqav2_1
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [google/paligemma-3b-pt-224](https://huggingface.co/google/paligemma-3b-pt-224) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.4158
|
| 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: 8
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 4
|
| 43 |
+
- total_train_batch_size: 32
|
| 44 |
+
- optimizer: Use OptimizerNames.ADAMW_HF 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: 12
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
| 53 |
+
| No log | 0.9976 | 318 | 0.3705 |
|
| 54 |
+
| 1.1065 | 1.9984 | 637 | 0.2753 |
|
| 55 |
+
| 1.1065 | 2.9992 | 956 | 0.2679 |
|
| 56 |
+
| 0.2268 | 4.0 | 1275 | 0.2718 |
|
| 57 |
+
| 0.1558 | 4.9976 | 1593 | 0.2638 |
|
| 58 |
+
| 0.1558 | 5.9984 | 1912 | 0.2820 |
|
| 59 |
+
| 0.1057 | 6.9992 | 2231 | 0.3018 |
|
| 60 |
+
| 0.0623 | 8.0 | 2550 | 0.3286 |
|
| 61 |
+
| 0.0623 | 8.9976 | 2868 | 0.3621 |
|
| 62 |
+
| 0.0325 | 9.9984 | 3187 | 0.3919 |
|
| 63 |
+
| 0.0191 | 10.9992 | 3506 | 0.4125 |
|
| 64 |
+
| 0.0191 | 11.9718 | 3816 | 0.4158 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- PEFT 0.13.2
|
| 70 |
+
- Transformers 4.46.2
|
| 71 |
+
- Pytorch 2.1.2.post304
|
| 72 |
+
- Datasets 3.1.0
|
| 73 |
+
- Tokenizers 0.20.3
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 45258384
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ac127f12ec1a474cf14c7d2fd9ab807ac747b00e98a8266ccdf95ecebf0f965
|
| 3 |
size 45258384
|