Update README.md

README.md

@@ -2,6 +2,66 @@
 library_name: transformers
 tags: []
 ---
+```
+wandb: - 0.003 MB of 0.003 MB uploaded
+wandb: \ 0.003 MB of 0.003 MB uploaded
+wandb:                                                                                
+wandb: 
+wandb: Run history:
+wandb:               eval/loss █▅▅▄▃▂▂▂▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁
+wandb:            eval/runtime ▆▃▃▁▂▅█▅▄▄▄▄▄▄▅▄▆▄▂▅▃▄▆▆▂▆▅
+wandb: eval/samples_per_second ▃▆▆█▇▄▁▄▅▅▅▅▅▅▄▅▃▅▇▄▆▅▃▃▇▃▄
+wandb:   eval/steps_per_second ▃▆▆█▇▄▁▄▄▄▅▅▄▅▄▅▃▆▇▃▆▅▃▃▇▃▄
+wandb:             train/epoch ▁▁▁▁▁▂▂▂▂▂▂▃▃▃▃▃▃▄▄▄▅▅▅▅▅▅▅▆▆▆▆▆▇▇▇▇▇███
+wandb:       train/global_step ▁▁▁▂▂▂▂▂▂▃▃▃▃▃▃▄▄▄▄▄▄▄▅▅▅▅▅▅▆▆▆▆▇▇▇▇▇███
+wandb:         train/grad_norm ▇▂▂▂▁▃█▃▂▁▃▂▃▂▁▂▃▃▄▃▂▃▃▃▄▂▃▃▄▃▂▃▃▃▃▄▄▅▄▃
+wandb:     train/learning_rate ███▇▇▇▇▇▇▆▆▆▆▆▅▅▅▅▅▅▄▄▄▄▄▄▃▃▃▃▃▂▂▂▂▂▂▁▁▁
+wandb:              train/loss █▃▃▃▁▄▂▂▃▁▃▂▂▂▁▃▂▂▁▃▂▂▂▁▃▂▂▂▁▃▂▂▂▃▁▂▂▁▃▁
+wandb: 
+wandb: Run summary:
+wandb:                eval/loss 0.92221
+wandb:             eval/runtime 93.6611
+wandb:  eval/samples_per_second 3.587
+wandb:    eval/steps_per_second 1.196
+wandb:               total_flos 2.952274602780672e+16
+wandb:              train/epoch 2.46201
+wandb:        train/global_step 810
+wandb:          train/grad_norm 0.81067
+wandb:      train/learning_rate 3e-05
+wandb:               train/loss 0.7747
+wandb:               train_loss 1.05936
+wandb:            train_runtime 8326.639
+wandb: train_samples_per_second 1.58
+wandb:   train_steps_per_second 0.198
+
+training_arguments = SFTConfig(
+    output_dir=new_model,
+    run_name="fine_tune_ocr_correction",
+    per_device_train_batch_size=2,
+    per_device_eval_batch_size=3,
+    gradient_accumulation_steps=4,
+    optim="paged_adamw_32bit",
+    num_train_epochs=5, 
+    eval_strategy="steps",
+    eval_steps=30,  # normally 10 steps, but our dataset is small
+    save_steps=30,
+    logging_steps=20,  # Log progress every 20 steps
+    warmup_steps=10,
+    logging_strategy="steps",
+    learning_rate=5e-5,
+    fp16=use_fp16, 
+    bf16=use_bf16,  
+    group_by_length=True,
+    report_to="wandb",
+    max_seq_length=1220,
+    save_strategy="steps",
+    dataset_text_field="text",
+    load_best_model_at_end = True
+)
+
+Dataset complet 
+```
+
 
 # Model Card for Model ID