Commit
•
23917eb
1
Parent(s):
4f5e40d
adishourya/roco_caption_pg
Browse files
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: google/paligemma-3b-mix-448
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: gemma
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: resultsroco__captions__google_paligemma-3b-mix-448__fullrun__2911-095336
|
| 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 |
+
# resultsroco__captions__google_paligemma-3b-mix-448__fullrun__2911-095336
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [google/paligemma-3b-mix-448](https://huggingface.co/google/paligemma-3b-mix-448) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 2.6451
|
| 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: 1e-05
|
| 39 |
+
- train_batch_size: 4
|
| 40 |
+
- eval_batch_size: 4
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 16
|
| 43 |
+
- total_train_batch_size: 64
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: constant
|
| 46 |
+
- lr_scheduler_warmup_steps: 2
|
| 47 |
+
- num_epochs: 10
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:------:|:-----:|:---------------:|
|
| 54 |
+
| 2.8798 | 0.9998 | 1022 | 2.8440 |
|
| 55 |
+
| 2.7474 | 1.9996 | 2044 | 2.7501 |
|
| 56 |
+
| 2.6883 | 2.9994 | 3066 | 2.7063 |
|
| 57 |
+
| 2.6667 | 3.9993 | 4088 | 2.6809 |
|
| 58 |
+
| 2.5908 | 4.9991 | 5110 | 2.6667 |
|
| 59 |
+
| 2.6089 | 5.9999 | 6133 | 2.6562 |
|
| 60 |
+
| 2.5774 | 6.9997 | 7155 | 2.6467 |
|
| 61 |
+
| 2.5092 | 7.9995 | 8177 | 2.6429 |
|
| 62 |
+
| 2.5263 | 8.9993 | 9199 | 2.6425 |
|
| 63 |
+
| 2.4526 | 9.9982 | 10220 | 2.6451 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
### Framework versions
|
| 67 |
+
|
| 68 |
+
- PEFT 0.13.0
|
| 69 |
+
- Transformers 4.45.1
|
| 70 |
+
- Pytorch 2.3.0.post101
|
| 71 |
+
- Datasets 2.19.1
|
| 72 |
+
- Tokenizers 0.20.0
|