palgemoriginlora88
Browse files- README.md +99 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: google/paligemma-3b-pt-224
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: gemma
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: paligemma_vqav2_warnup
|
| 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_warnup
|
| 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: 0.8534
|
| 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: 10
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 4
|
| 43 |
+
- total_train_batch_size: 40
|
| 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: 1000
|
| 47 |
+
- num_epochs: 12
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
| 53 |
+
| 7.0325 | 0.3125 | 100 | 7.1622 |
|
| 54 |
+
| 6.5146 | 0.625 | 200 | 5.6221 |
|
| 55 |
+
| 4.4912 | 0.9375 | 300 | 3.4696 |
|
| 56 |
+
| 3.2824 | 1.25 | 400 | 2.6386 |
|
| 57 |
+
| 2.6828 | 1.5625 | 500 | 2.1185 |
|
| 58 |
+
| 2.2276 | 1.875 | 600 | 1.7020 |
|
| 59 |
+
| 1.9293 | 2.1875 | 700 | 1.4613 |
|
| 60 |
+
| 1.7957 | 2.5 | 800 | 1.3059 |
|
| 61 |
+
| 1.6281 | 2.8125 | 900 | 1.1815 |
|
| 62 |
+
| 1.4253 | 3.125 | 1000 | 1.1008 |
|
| 63 |
+
| 1.4404 | 3.4375 | 1100 | 1.0513 |
|
| 64 |
+
| 1.4239 | 3.75 | 1200 | 1.0156 |
|
| 65 |
+
| 1.2985 | 4.0625 | 1300 | 0.9709 |
|
| 66 |
+
| 1.243 | 4.375 | 1400 | 0.9393 |
|
| 67 |
+
| 1.2105 | 4.6875 | 1500 | 0.9237 |
|
| 68 |
+
| 1.2035 | 5.0 | 1600 | 0.9088 |
|
| 69 |
+
| 1.0704 | 5.3125 | 1700 | 0.8927 |
|
| 70 |
+
| 1.0891 | 5.625 | 1800 | 0.8735 |
|
| 71 |
+
| 1.0861 | 5.9375 | 1900 | 0.8598 |
|
| 72 |
+
| 0.9853 | 6.25 | 2000 | 0.8530 |
|
| 73 |
+
| 0.9866 | 6.5625 | 2100 | 0.8392 |
|
| 74 |
+
| 1.0206 | 6.875 | 2200 | 0.8399 |
|
| 75 |
+
| 0.8914 | 7.1875 | 2300 | 0.8293 |
|
| 76 |
+
| 0.9062 | 7.5 | 2400 | 0.8325 |
|
| 77 |
+
| 0.8579 | 7.8125 | 2500 | 0.8147 |
|
| 78 |
+
| 0.828 | 8.125 | 2600 | 0.8267 |
|
| 79 |
+
| 0.7969 | 8.4375 | 2700 | 0.8321 |
|
| 80 |
+
| 0.8175 | 8.75 | 2800 | 0.8179 |
|
| 81 |
+
| 0.7948 | 9.0625 | 2900 | 0.8356 |
|
| 82 |
+
| 0.7221 | 9.375 | 3000 | 0.8104 |
|
| 83 |
+
| 0.7124 | 9.6875 | 3100 | 0.8266 |
|
| 84 |
+
| 0.7199 | 10.0 | 3200 | 0.8143 |
|
| 85 |
+
| 0.6601 | 10.3125 | 3300 | 0.8399 |
|
| 86 |
+
| 0.6517 | 10.625 | 3400 | 0.8415 |
|
| 87 |
+
| 0.6509 | 10.9375 | 3500 | 0.8221 |
|
| 88 |
+
| 0.5981 | 11.25 | 3600 | 0.8582 |
|
| 89 |
+
| 0.6011 | 11.5625 | 3700 | 0.8481 |
|
| 90 |
+
| 0.5756 | 11.875 | 3800 | 0.8534 |
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
### Framework versions
|
| 94 |
+
|
| 95 |
+
- PEFT 0.13.0
|
| 96 |
+
- Transformers 4.46.0.dev0
|
| 97 |
+
- Pytorch 2.4.1+cu121
|
| 98 |
+
- Datasets 3.0.1
|
| 99 |
+
- Tokenizers 0.20.0
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1446313752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc66535d3e2fec0b7be40a69d8c39c4162c54c36fa84dcb12a7057d126d2cc88
|
| 3 |
size 1446313752
|