Periodic upload

README.md

@@ -3,13 +3,13 @@
 license: apache-2.0
 library_name: transformers
 ---
-## Model Trained Sequentially on Hugging Face Datasets
+# Modelo Fine-Tuned Secuencialmente
+
 **Base Model:** arnir0/Tiny-LLM
-This model is being fine-tuned sequentially using LoRA on various datasets
-available on the Hugging Face Hub. The resulting model (base + adapter merged) is saved
-at the root of this repository as `model.safetensors`.
-### Training Progress
-- **Datasets Processed:** 5
-- **Text Examples Processed:** 18
-- **Tokens Processed:** 9216
-- **Last Update:** 2025-05-06 13:49:24 UTC
+
+## Progreso de Entrenamiento
+
+- **Datasets procesados:** 0.0
+- **Ejemplos de texto procesados:** 0.0
+- **Tokens procesados:** 0.0
+- **Última subida:** 2025-05-06 14:31:08 UTC

training.log

@@ -0,0 +1,9 @@
+2025-05-06 16:30:06,158 INFO: Gradio: Loading model and tokenizer from arnir0/Tiny-LLM (model), arnir0/Tiny-LLM (tokenizer)
+2025-05-06 16:30:08,577 INFO: Gradio: Model arnir0/Tiny-LLM and tokenizer loaded.
+2025-05-06 16:30:08,578 INFO: Interfaz Gradio iniciada en http://0.0.0.0:7860
+2025-05-06 16:30:08,587 INFO: Servidor de métricas Prometheus iniciado en el puerto 8000.
+2025-05-06 16:30:08,587 INFO: Fetching new list of datasets...
+2025-05-06 16:30:41,406 INFO: HTTP Request: GET http://localhost:7860/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-06 16:30:41,433 INFO: HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK"
+2025-05-06 16:31:07,974 INFO: Fetched 379843 datasets to process.
+2025-05-06 16:31:08,585 INFO: Preparing data for nvidia/Nemotron-CrossThink, config: default