End of training
Browse files- README.md +15 -16
- adapter_model.safetensors +1 -1
- training_args.bin +2 -2
README.md
CHANGED
|
@@ -1,15 +1,13 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
library_name: peft
|
| 4 |
license: gemma
|
|
|
|
| 5 |
tags:
|
|
|
|
| 6 |
- generated_from_trainer
|
| 7 |
-
- ColPali
|
| 8 |
model-index:
|
| 9 |
- name: finetune_colpali_v1_2-ufo-4bit
|
| 10 |
results: []
|
| 11 |
-
datasets:
|
| 12 |
-
- davanstrien/ufo-ColPali
|
| 13 |
---
|
| 14 |
|
| 15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -17,9 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
# finetune_colpali_v1_2-ufo-4bit
|
| 19 |
|
| 20 |
-
This model is a fine-tuned version of [vidore/colpaligemma-3b-pt-448-base](https://huggingface.co/vidore/colpaligemma-3b-pt-448-base) on
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
-
- Loss: 0.
|
|
|
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
@@ -46,22 +45,22 @@ The following hyperparameters were used during training:
|
|
| 46 |
- total_train_batch_size: 8
|
| 47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
- lr_scheduler_type: linear
|
| 49 |
-
- lr_scheduler_warmup_steps:
|
| 50 |
-
- num_epochs:
|
| 51 |
|
| 52 |
### Training results
|
| 53 |
|
| 54 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
-
|
| 56 |
-
| No log | 0.0041 | 1 | 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
|
|
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|
| 62 |
|
| 63 |
-
- PEFT 0.11.1
|
| 64 |
- Transformers 4.44.2
|
| 65 |
- Pytorch 2.4.1+cu121
|
| 66 |
- Datasets 3.0.0
|
| 67 |
-
- Tokenizers 0.19.1
|
|
|
|
| 1 |
---
|
| 2 |
+
library_name: transformers
|
|
|
|
| 3 |
license: gemma
|
| 4 |
+
base_model: vidore/colpaligemma-3b-pt-448-base
|
| 5 |
tags:
|
| 6 |
+
- colpali
|
| 7 |
- generated_from_trainer
|
|
|
|
| 8 |
model-index:
|
| 9 |
- name: finetune_colpali_v1_2-ufo-4bit
|
| 10 |
results: []
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 15 |
|
| 16 |
# finetune_colpali_v1_2-ufo-4bit
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [vidore/colpaligemma-3b-pt-448-base](https://huggingface.co/vidore/colpaligemma-3b-pt-448-base) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.1064
|
| 21 |
+
- Model Preparation Time: 0.0056
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 45 |
- total_train_batch_size: 8
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_steps: 100
|
| 49 |
+
- num_epochs: 1.5
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time |
|
| 54 |
+
|:-------------:|:------:|:----:|:---------------:|:----------------------:|
|
| 55 |
+
| No log | 0.0041 | 1 | 0.1879 | 0.0056 |
|
| 56 |
+
| 0.1193 | 0.4090 | 100 | 0.1136 | 0.0056 |
|
| 57 |
+
| 0.1287 | 0.8180 | 200 | 0.1122 | 0.0056 |
|
| 58 |
+
| 0.0662 | 1.2270 | 300 | 0.1063 | 0.0056 |
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|
| 62 |
|
|
|
|
| 63 |
- Transformers 4.44.2
|
| 64 |
- Pytorch 2.4.1+cu121
|
| 65 |
- Datasets 3.0.0
|
| 66 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 157071680
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4628eb8863cc29a8454b84ba05230947cddc40973f73f0147c3ff550f1655c97
|
| 3 |
size 157071680
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6dc70ef2d489a8733ed6dce697261494ae1f7fb1afec04738b4fa1020cdc095
|
| 3 |
+
size 5240
|