| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.2590361445783134, |
| "eval_steps": 500, |
| "global_step": 3000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08, |
| "learning_rate": 5.000000000000001e-07, |
| "loss": 0.2303, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 1.0000000000000002e-06, |
| "loss": 0.21, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 1.5e-06, |
| "loss": 0.2118, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 2.0000000000000003e-06, |
| "loss": 0.2131, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 2.5e-06, |
| "loss": 0.2076, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 3e-06, |
| "loss": 0.2116, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 3.5e-06, |
| "loss": 0.2154, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.2129, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 4.5e-06, |
| "loss": 0.211, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 5e-06, |
| "loss": 0.2178, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 5.500000000000001e-06, |
| "loss": 0.2104, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 6e-06, |
| "loss": 0.215, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.98, |
| "learning_rate": 6.5000000000000004e-06, |
| "loss": 0.2107, |
| "step": 1300 |
| }, |
| { |
| "epoch": 1.05, |
| "learning_rate": 7e-06, |
| "loss": 0.2091, |
| "step": 1400 |
| }, |
| { |
| "epoch": 1.13, |
| "learning_rate": 7.500000000000001e-06, |
| "loss": 0.207, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.2, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 0.1942, |
| "step": 1600 |
| }, |
| { |
| "epoch": 1.28, |
| "learning_rate": 8.5e-06, |
| "loss": 0.2037, |
| "step": 1700 |
| }, |
| { |
| "epoch": 1.36, |
| "learning_rate": 9e-06, |
| "loss": 0.2071, |
| "step": 1800 |
| }, |
| { |
| "epoch": 1.43, |
| "learning_rate": 9.5e-06, |
| "loss": 0.2072, |
| "step": 1900 |
| }, |
| { |
| "epoch": 1.51, |
| "learning_rate": 1e-05, |
| "loss": 0.2035, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.58, |
| "learning_rate": 9.666666666666667e-06, |
| "loss": 0.21, |
| "step": 2100 |
| }, |
| { |
| "epoch": 1.66, |
| "learning_rate": 9.333333333333334e-06, |
| "loss": 0.2062, |
| "step": 2200 |
| }, |
| { |
| "epoch": 1.73, |
| "learning_rate": 9e-06, |
| "loss": 0.2067, |
| "step": 2300 |
| }, |
| { |
| "epoch": 1.81, |
| "learning_rate": 8.666666666666668e-06, |
| "loss": 0.2043, |
| "step": 2400 |
| }, |
| { |
| "epoch": 1.88, |
| "learning_rate": 8.333333333333334e-06, |
| "loss": 0.1953, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.96, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 0.2021, |
| "step": 2600 |
| }, |
| { |
| "epoch": 2.03, |
| "learning_rate": 7.666666666666667e-06, |
| "loss": 0.1764, |
| "step": 2700 |
| }, |
| { |
| "epoch": 2.11, |
| "learning_rate": 7.333333333333333e-06, |
| "loss": 0.1506, |
| "step": 2800 |
| }, |
| { |
| "epoch": 2.18, |
| "learning_rate": 7e-06, |
| "loss": 0.152, |
| "step": 2900 |
| }, |
| { |
| "epoch": 2.26, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": 0.1539, |
| "step": 3000 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 5000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 1000, |
| "total_flos": 6.92547243687936e+18, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
