Model save
Browse files- README.md +76 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: lightonai/LightOnOCR-1B-1025
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: lightonocr-books-test
|
| 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 |
+
# lightonocr-books-test
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [lightonai/LightOnOCR-1B-1025](https://huggingface.co/lightonai/LightOnOCR-1B-1025) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.1889
|
| 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: 6e-05
|
| 39 |
+
- train_batch_size: 4
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 4
|
| 43 |
+
- total_train_batch_size: 16
|
| 44 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 10
|
| 47 |
+
- num_epochs: 1
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 53 |
+
| 0.9036 | 0.0619 | 50 | 0.2168 |
|
| 54 |
+
| 0.7522 | 0.1239 | 100 | 0.2168 |
|
| 55 |
+
| 0.7561 | 0.1858 | 150 | 0.2153 |
|
| 56 |
+
| 0.8117 | 0.2478 | 200 | 0.2066 |
|
| 57 |
+
| 0.7541 | 0.3097 | 250 | 0.2011 |
|
| 58 |
+
| 0.6631 | 0.3716 | 300 | 0.2009 |
|
| 59 |
+
| 0.7019 | 0.4336 | 350 | 0.1979 |
|
| 60 |
+
| 0.853 | 0.4955 | 400 | 0.1953 |
|
| 61 |
+
| 0.7941 | 0.5574 | 450 | 0.1914 |
|
| 62 |
+
| 0.7765 | 0.6194 | 500 | 0.1901 |
|
| 63 |
+
| 0.6321 | 0.6813 | 550 | 0.1915 |
|
| 64 |
+
| 0.7474 | 0.7433 | 600 | 0.1900 |
|
| 65 |
+
| 0.6291 | 0.8052 | 650 | 0.1887 |
|
| 66 |
+
| 0.6896 | 0.8671 | 700 | 0.1892 |
|
| 67 |
+
| 0.7958 | 0.9291 | 750 | 0.1896 |
|
| 68 |
+
| 0.5989 | 0.9910 | 800 | 0.1889 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- Transformers 5.0.0.dev0
|
| 74 |
+
- Pytorch 2.9.0+cu128
|
| 75 |
+
- Datasets 4.3.0
|
| 76 |
+
- Tokenizers 0.22.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2322532728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4112132d1ab157759886b69e1c40c5e3e61ea9894c0e2d5960e7282d3eaf9beb
|
| 3 |
size 2322532728
|