| 2025-07-04 16:42:03,629 - trainer_MyTestExp - INFO - info:66 - 📄 Using default configuration | |
| 2025-07-04 16:42:03,630 - trainer_MyTestExp - INFO - info:66 - 🔧 Configuration: { | |
| "data": { | |
| "tickers": [ | |
| "AAPL", | |
| "MSFT", | |
| "GOOGL", | |
| "AMZN", | |
| "TSLA" | |
| ], | |
| "period": "5y", | |
| "interval": "1d", | |
| "use_sp500": false | |
| }, | |
| "environment": { | |
| "initial_balance": 10000, | |
| "transaction_cost": 0.001, | |
| "max_position_size": 1.0, | |
| "lookback_window": 60, | |
| "reward_type": "return" | |
| }, | |
| "training": { | |
| "algorithm": "PPO", | |
| "total_timesteps": 500000, | |
| "learning_rate": 0.0003, | |
| "batch_size": 64, | |
| "n_epochs": 10, | |
| "gamma": 0.99, | |
| "eval_freq": 1000, | |
| "n_eval_episodes": 5, | |
| "save_freq": 10000, | |
| "seed": 42 | |
| } | |
| } | |
| 2025-07-04 16:42:03,631 - trainer_MyTestExp - INFO - info:66 - 💾 Configuration saved to experiments/MyTestExp/config.json | |
| 2025-07-04 16:42:03,632 - trainer_MyTestExp - INFO - info:66 - 🎯 Trainer initialized for experiment: MyTestExp | |
| 2025-07-04 16:42:03,633 - trainer_MyTestExp - INFO - info:66 - 📁 Experiment directory: experiments/MyTestExp | |
| 2025-07-04 16:42:03,633 - trainer_MyTestExp - INFO - info:66 - 🚀 Starting complete training pipeline | |
| 2025-07-04 16:42:03,634 - trainer_MyTestExp - INFO - info:66 - ⏱️ Starting Data Preparation... | |
| 2025-07-04 16:42:03,636 - trainer_MyTestExp - INFO - info:66 - 📦 Loading existing processed data... | |
| 2025-07-04 16:42:04,036 - trainer_MyTestExp - INFO - info:66 - ✅ Loaded processed data for 5 stocks | |
| 2025-07-04 16:42:04,038 - trainer_MyTestExp - INFO - info:66 - === DATA INFORMATION === | |
| 2025-07-04 16:42:04,039 - trainer_MyTestExp - INFO - info:66 - num_stocks: 5 | |
| 2025-07-04 16:42:04,039 - trainer_MyTestExp - INFO - info:66 - stocks: ['AMZN', 'MSFT', 'GOOGL', 'TSLA', 'AAPL'] | |
| 2025-07-04 16:42:04,040 - trainer_MyTestExp - INFO - info:66 - total_data_points: 5887 | |
| 2025-07-04 16:42:04,041 - trainer_MyTestExp - INFO - info:66 - feature_dimensions: | |
| 2025-07-04 16:42:04,042 - trainer_MyTestExp - INFO - info:66 - AMZN: {'sequences': 1147, 'timesteps': 60, 'features': 50} | |
| 2025-07-04 16:42:04,042 - trainer_MyTestExp - INFO - info:66 - MSFT: {'sequences': 1185, 'timesteps': 60, 'features': 50} | |
| 2025-07-04 16:42:04,044 - trainer_MyTestExp - INFO - info:66 - GOOGL: {'sequences': 1185, 'timesteps': 60, 'features': 50} | |
| 2025-07-04 16:42:04,044 - trainer_MyTestExp - INFO - info:66 - TSLA: {'sequences': 1185, 'timesteps': 60, 'features': 50} | |
| 2025-07-04 16:42:04,045 - trainer_MyTestExp - INFO - info:66 - AAPL: {'sequences': 1185, 'timesteps': 60, 'features': 50} | |
| 2025-07-04 16:42:04,046 - trainer_MyTestExp - INFO - info:66 - date_ranges: | |
| 2025-07-04 16:42:04,046 - trainer_MyTestExp - INFO - info:66 - AMZN: {'start': '2020-12-08 00:00:00-05:00', 'end': '2025-07-03 00:00:00-04:00', 'total_days': 1147} | |
| 2025-07-04 16:42:04,047 - trainer_MyTestExp - INFO - info:66 - MSFT: {'start': '2020-10-14 00:00:00-04:00', 'end': '2025-07-03 00:00:00-04:00', 'total_days': 1185} | |
| 2025-07-04 16:42:04,049 - trainer_MyTestExp - INFO - info:66 - GOOGL: {'start': '2020-10-14 00:00:00-04:00', 'end': '2025-07-03 00:00:00-04:00', 'total_days': 1185} | |
| 2025-07-04 16:42:04,049 - trainer_MyTestExp - INFO - info:66 - TSLA: {'start': '2020-10-14 00:00:00-04:00', 'end': '2025-07-03 00:00:00-04:00', 'total_days': 1185} | |
| 2025-07-04 16:42:04,050 - trainer_MyTestExp - INFO - info:66 - AAPL: {'start': '2020-10-14 00:00:00-04:00', 'end': '2025-07-03 00:00:00-04:00', 'total_days': 1185} | |
| 2025-07-04 16:42:04,051 - trainer_MyTestExp - INFO - info:66 - data_statistics: | |
| 2025-07-04 16:42:04,052 - trainer_MyTestExp - INFO - info:66 - AMZN: {'mean_reward': 0.0005594119760782921, 'std_reward': 0.022296406035272005, 'min_reward': -0.140494377749234, 'max_reward': 0.13535901735711864} | |
| 2025-07-04 16:42:04,052 - trainer_MyTestExp - INFO - info:66 - MSFT: {'mean_reward': 0.0008731624810708478, 'std_reward': 0.016632783789797784, 'min_reward': -0.0771562052939444, 'max_reward': 0.10133680183689964} | |
| 2025-07-04 16:42:04,053 - trainer_MyTestExp - INFO - info:66 - GOOGL: {'mean_reward': 0.0009044145449009408, 'std_reward': 0.019663019787478423, 'min_reward': -0.0950939635085033, 'max_reward': 0.1022436334871546} | |
| 2025-07-04 16:42:04,054 - trainer_MyTestExp - INFO - info:66 - TSLA: {'mean_reward': 0.0013615600221650649, 'std_reward': 0.03903042109805533, 'min_reward': -0.1542620682219512, 'max_reward': 0.22689989839624536} | |
| 2025-07-04 16:42:04,055 - trainer_MyTestExp - INFO - info:66 - AAPL: {'mean_reward': 0.0006670026996126003, 'std_reward': 0.018039907632620762, 'min_reward': -0.09245607865732186, 'max_reward': 0.15328847287251235} | |
| 2025-07-04 16:42:04,056 - trainer_MyTestExp - INFO - info:66 - ⏱️ Data Preparation completed in 0:00:00.421859 | |
| 2025-07-04 16:42:04,057 - trainer_MyTestExp - INFO - info:66 - ⏱️ Starting Environment Creation... | |
| 2025-07-04 16:42:04,057 - trainer_MyTestExp - INFO - info:66 - 🏪 Environment configuration: | |
| 2025-07-04 16:42:04,058 - trainer_MyTestExp - INFO - info:66 - initial_balance: 10000 | |
| 2025-07-04 16:42:04,059 - trainer_MyTestExp - INFO - info:66 - transaction_cost: 0.001 | |
| 2025-07-04 16:42:04,060 - trainer_MyTestExp - INFO - info:66 - max_position_size: 1.0 | |
| 2025-07-04 16:42:04,060 - trainer_MyTestExp - INFO - info:66 - lookback_window: 60 | |
| 2025-07-04 16:42:04,061 - trainer_MyTestExp - INFO - info:66 - reward_type: return | |
| 2025-07-04 16:42:04,062 - trainer_MyTestExp - INFO - info:66 - Creating environments: |██████░░░░░░░░░░░░░░░░░░░░░░░░| 20.0% (1/5) | |
| 2025-07-04 16:42:04,065 - trainer_MyTestExp - INFO - info:66 - Creating environments: |████████████░░░░░░░░░░░░░░░░░░| 40.0% (2/5) | |
| 2025-07-04 16:42:04,068 - trainer_MyTestExp - INFO - info:66 - Creating environments: |██████████████████░░░░░░░░░░░░| 60.0% (3/5) | |
| 2025-07-04 16:42:04,070 - trainer_MyTestExp - INFO - info:66 - Creating environments: |████████████████████████░░░░░░| 80.0% (4/5) | |
| 2025-07-04 16:42:04,072 - trainer_MyTestExp - INFO - info:66 - Creating environments: |██████████████████████████████| 100.0% (5/5) | |
| 2025-07-04 16:42:04,075 - trainer_MyTestExp - INFO - info:66 - ✅ Created environments for 5 stocks | |
| 2025-07-04 16:42:04,075 - trainer_MyTestExp - INFO - info:66 - ⏱️ Environment Creation completed in 0:00:00.018392 | |
| 2025-07-04 16:42:04,076 - trainer_MyTestExp - INFO - info:66 - ⏱️ Starting Model Creation... | |
| 2025-07-04 16:42:04,084 - trainer_MyTestExp - INFO - info:66 - 🎲 Random seed set to: 42 | |
| 2025-07-04 16:42:07,604 - trainer_MyTestExp - INFO - info:66 - === MODEL INFORMATION === | |
| 2025-07-04 16:42:07,605 - trainer_MyTestExp - INFO - info:66 - algorithm: PPO | |
| 2025-07-04 16:42:07,606 - trainer_MyTestExp - INFO - info:66 - policy: MlpPolicy | |
| 2025-07-04 16:42:07,606 - trainer_MyTestExp - INFO - info:66 - observation_space: Box(-inf, inf, (3008,), float32) | |
| 2025-07-04 16:42:07,607 - trainer_MyTestExp - INFO - info:66 - action_space: Box(0.0, [2. 1.], (2,), float32) | |
| 2025-07-04 16:42:07,608 - trainer_MyTestExp - INFO - info:66 - total_parameters: 393669 | |
| 2025-07-04 16:42:07,609 - trainer_MyTestExp - INFO - info:66 - trainable_parameters: 393669 | |
| 2025-07-04 16:42:07,609 - trainer_MyTestExp - INFO - info:66 - model_parameters: {'learning_rate': 0.0003, 'gamma': 0.99, 'verbose': 0, 'seed': 42, 'tensorboard_log': 'experiments/MyTestExp/logs/tensorboard', 'batch_size': 64, 'n_epochs': 10, 'clip_range': 0.2, 'ent_coef': 0.0} | |
| 2025-07-04 16:42:07,610 - trainer_MyTestExp - INFO - info:66 - device: cuda | |
| 2025-07-04 16:42:07,612 - trainer_MyTestExp - INFO - info:66 - ✅ PPO model created with 393,669 parameters | |
| 2025-07-04 16:42:07,612 - trainer_MyTestExp - INFO - info:66 - ⏱️ Model Creation completed in 0:00:03.536618 | |
| 2025-07-04 16:42:07,613 - trainer_MyTestExp - INFO - info:66 - ⏱️ Starting Model Training... | |
| 2025-07-04 16:42:07,614 - trainer_MyTestExp - INFO - info:66 - 🚀 Starting training with parameters: | |
| 2025-07-04 16:42:07,615 - trainer_MyTestExp - INFO - info:66 - Total timesteps: 500,000 | |
| 2025-07-04 16:42:07,616 - trainer_MyTestExp - INFO - info:66 - Learning rate: 0.0003 | |
| 2025-07-04 16:42:07,616 - trainer_MyTestExp - INFO - info:66 - Evaluation frequency: 1000 | |
| 2025-07-04 16:42:07,617 - trainer_MyTestExp - INFO - info:66 - Save frequency: 10000 | |
| 2025-07-04 16:53:55,946 - trainer_MyTestExp - INFO - info:66 - ✅ Training completed successfully! | |
| 2025-07-04 16:53:55,969 - trainer_MyTestExp - INFO - info:66 - 💾 Final model saved to experiments/MyTestExp/models/final_model | |
| 2025-07-04 16:53:55,970 - trainer_MyTestExp - INFO - info:66 - ⏱️ Model Training completed in 0:11:48.356779 | |
| 2025-07-04 16:53:55,970 - trainer_MyTestExp - INFO - info:66 - ⏱️ Starting Model Evaluation... | |
| 2025-07-04 16:53:55,971 - trainer_MyTestExp - INFO - info:66 - Evaluating AMZN: |██████░░░░░░░░░░░░░░░░░░░░░░░░| 20.0% (1/5) | |
| 2025-07-04 16:53:55,974 - trainer_MyTestExp - ERROR - error:78 - Training pipeline failed: Error: Unexpected observation shape () for Box environment, please use (3008,) or (n_env, 3008) for the observation shape. | |