not-lain/finetuned_deepseek_ocr

README.md

@@ -1,9 +1,14 @@
 ---
-library_name: transformers
+library_name: peft
 license: mit
 base_model: deepseek-ai/DeepSeek-OCR
 tags:
-- generated_from_trainer
+- base_model:adapter:deepseek-ai/DeepSeek-OCR
+- lora
+- sft
+- transformers
+- trl
+pipeline_tag: text-generation
 model-index:
 - name: finetuned_deepseek_ocr
   results: []
@@ -34,12 +39,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0005
-- train_batch_size: 2
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- training_steps: 3
+- training_steps: 8
 
 ### Training results
 
@@ -47,7 +52,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
+- PEFT 0.17.1
 - Transformers 4.46.3
 - Pytorch 2.6.0+cu124
 - Datasets 4.3.0
-- Tokenizers 0.20.3
+- Tokenizers 0.20.3

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b286d1de8ead082ffe7f4d74bdb4fa3570ae09031c382169ecab15c1f03bb9dd
+oid sha256:5b495ec84536d6424b2d80c560fe16eb1ffd638e871c98668ce4f122f8115bec
 size 2958552

runs/Oct30_17-20-43_368ad1980789/events.out.tfevents.1761844845.368ad1980789.6156.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4861e14d1685ec7b7d5a1534232b5a82654c6e95ffcfca427dfcc6035550041f
-size 9149
+oid sha256:31c15e392639fc44aecc2ad2c096a2535a7e19148e27e655a40f4b890fc3bc75
+size 9704