palicoqiqi
commited on
palicoqiqi/paligemma_ocr_final
Browse files- README.md +12 -13
- adapter_model.safetensors +1 -1
README.md
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
---
|
2 |
library_name: peft
|
3 |
license: gemma
|
4 |
-
base_model: google/paligemma-3b-
|
5 |
tags:
|
6 |
- generated_from_trainer
|
7 |
model-index:
|
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# paligemma_ocr_final
|
16 |
|
17 |
-
This model is a fine-tuned version of [google/paligemma-3b-
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss:
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -36,11 +36,11 @@ More information needed
|
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
- learning_rate: 0.0001
|
39 |
-
- train_batch_size:
|
40 |
-
- eval_batch_size:
|
41 |
- seed: 42
|
42 |
-
- gradient_accumulation_steps:
|
43 |
-
- total_train_batch_size:
|
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
|
@@ -50,12 +50,11 @@ The following hyperparameters were used during training:
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:------:|:----:|:---------------:|
|
53 |
-
|
|
54 |
-
|
|
55 |
-
|
|
56 |
-
|
|
57 |
-
|
|
58 |
-
| 8.0924 | 1.7978 | 120 | 1.9992 |
|
59 |
|
60 |
|
61 |
### Framework versions
|
|
|
1 |
---
|
2 |
library_name: peft
|
3 |
license: gemma
|
4 |
+
base_model: google/paligemma-3b-mix-448
|
5 |
tags:
|
6 |
- generated_from_trainer
|
7 |
model-index:
|
|
|
14 |
|
15 |
# paligemma_ocr_final
|
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: 0.6634
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
- learning_rate: 0.0001
|
39 |
+
- train_batch_size: 2
|
40 |
+
- eval_batch_size: 2
|
41 |
- seed: 42
|
42 |
+
- gradient_accumulation_steps: 2
|
43 |
+
- total_train_batch_size: 4
|
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
|
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:------:|:----:|:---------------:|
|
53 |
+
| 2.4537 | 0.3745 | 100 | 0.8158 |
|
54 |
+
| 1.5798 | 0.7491 | 200 | 0.7222 |
|
55 |
+
| 1.7108 | 1.1236 | 300 | 0.6713 |
|
56 |
+
| 1.2932 | 1.4981 | 400 | 0.6523 |
|
57 |
+
| 1.203 | 1.8727 | 500 | 0.6634 |
|
|
|
58 |
|
59 |
|
60 |
### Framework versions
|
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 sha256:8908f41c5d6e39ccb9c88b12b781995d63bae36ea54dda6c04dd5f9b5a2205e5
|
3 |
size 45258384
|