Enhance train.py with Configurable Training Parameters

- Updated version to 2.0.73 across multiple files
- Refactored TrainModel to use configurable training parameters with default fallbacks
- Improved flexibility of training configuration by allowing custom settings via config
- Dynamically set training arguments based on provided configuration

docker/Dockerfile

@@ -1,6 +1,6 @@
 FROM python:3.11-slim
 WORKDIR /app
 COPY . .
-RUN pip install flask praisonai==2.0.72 gunicorn markdown
+RUN pip install flask praisonai==2.0.73 gunicorn markdown
 EXPOSE 8080
 CMD ["gunicorn", "-b", "0.0.0.0:8080", "api:app"]

docs/api/praisonai/deploy.html

@@ -110,7 +110,7 @@ <h2 id="raises">Raises</h2>
             file.write(&#34;FROM python:3.11-slim\n&#34;)
             file.write(&#34;WORKDIR /app\n&#34;)
             file.write(&#34;COPY . .\n&#34;)
-            file.write(&#34;RUN pip install flask praisonai==2.0.72 gunicorn markdown\n&#34;)
+            file.write(&#34;RUN pip install flask praisonai==2.0.73 gunicorn markdown\n&#34;)
             file.write(&#34;EXPOSE 8080\n&#34;)
             file.write(&#39;CMD [&#34;gunicorn&#34;, &#34;-b&#34;, &#34;0.0.0.0:8080&#34;, &#34;api:app&#34;]\n&#39;)
 

praisonai.rb

@@ -3,7 +3,7 @@ class Praisonai < Formula
 
     desc "AI tools for various AI applications"
     homepage "https://github.com/MervinPraison/PraisonAI"
-    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/2.0.72.tar.gz"
+    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/2.0.73.tar.gz"
     sha256 "1828fb9227d10f991522c3f24f061943a254b667196b40b1a3e4a54a8d30ce32"  # Replace with actual SHA256 checksum
     license "MIT"
 

praisonai/deploy.py

@@ -56,7 +56,7 @@ def create_dockerfile(self):
             file.write("FROM python:3.11-slim\n")
             file.write("WORKDIR /app\n")
             file.write("COPY . .\n")
-            file.write("RUN pip install flask praisonai==2.0.72 gunicorn markdown\n")
+            file.write("RUN pip install flask praisonai==2.0.73 gunicorn markdown\n")
             file.write("EXPOSE 8080\n")
             file.write('CMD ["gunicorn", "-b", "0.0.0.0:8080", "api:app"]\n')
 

praisonai/train.py

@@ -217,23 +217,23 @@ def train_model(self):
         tokenized_dataset = self.tokenize_dataset(raw_dataset)
         print("DEBUG: Dataset tokenization complete.")
         training_args = TrainingArguments(
-            per_device_train_batch_size=2,
-            gradient_accumulation_steps=4,
-            warmup_steps=5,
-            max_steps=60,
-            learning_rate=2e-4,
-            fp16=not is_bfloat16_supported(),
-            bf16=is_bfloat16_supported(),
-            logging_steps=1,
-            optim="adamw_8bit",
-            weight_decay=0.01,
-            lr_scheduler_type="linear",
-            seed=3407,
-            output_dir="outputs",
+            per_device_train_batch_size=self.config.get("per_device_train_batch_size", 2),
+            gradient_accumulation_steps=self.config.get("gradient_accumulation_steps", 2),
+            warmup_steps=self.config.get("warmup_steps", 50),
+            max_steps=self.config.get("max_steps", 2800),
+            learning_rate=self.config.get("learning_rate", 2e-4),
+            fp16=self.config.get("fp16", not is_bfloat16_supported()),
+            bf16=self.config.get("bf16", is_bfloat16_supported()),
+            logging_steps=self.config.get("logging_steps", 15),
+            optim=self.config.get("optim", "adamw_8bit"),
+            weight_decay=self.config.get("weight_decay", 0.01),
+            lr_scheduler_type=self.config.get("lr_scheduler_type", "linear"),
+            seed=self.config.get("seed", 3407),
+            output_dir=self.config.get("output_dir", "outputs"),
             report_to="none" if not os.getenv("PRAISON_WANDB") else "wandb",
-            save_steps=100 if os.getenv("PRAISON_WANDB") else None,
+            save_steps=self.config.get("save_steps", 100) if os.getenv("PRAISON_WANDB") else None,
             run_name=os.getenv("PRAISON_WANDB_RUN_NAME", "praisonai-train") if os.getenv("PRAISON_WANDB") else None,
-            remove_unused_columns=False,
+            remove_unused_columns=self.config.get("remove_unused_columns", False),
         )
         # Since the dataset is pre-tokenized, we supply a dummy dataset_text_field.
         trainer = SFTTrainer(

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "PraisonAI"
-version = "2.0.72"
+version = "2.0.73"
 description = "PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent collaboration."
 readme = "README.md"
 license = ""
@@ -84,7 +84,7 @@ autogen = ["pyautogen>=0.2.19", "praisonai-tools>=0.0.7", "crewai"]
 
 [tool.poetry]
 name = "PraisonAI"
-version = "2.0.72"
+version = "2.0.73"
 description = "PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human–agent collaboration."
 authors = ["Mervin Praison"]
 license = ""