| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.444444444444445, |
| "eval_steps": 500, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.2222222222222222, |
| "grad_norm": 5.216339111328125, |
| "learning_rate": 2.45e-05, |
| "loss": 14.61, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.4444444444444444, |
| "grad_norm": 7.058466911315918, |
| "learning_rate": 4.9500000000000004e-05, |
| "loss": 13.7946, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 4.601776599884033, |
| "learning_rate": 4.727777777777778e-05, |
| "loss": 8.9659, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.8888888888888888, |
| "grad_norm": 2.722055196762085, |
| "learning_rate": 4.4500000000000004e-05, |
| "loss": 4.6933, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.1111111111111112, |
| "grad_norm": 1.416906476020813, |
| "learning_rate": 4.172222222222222e-05, |
| "loss": 1.9597, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "grad_norm": 0.4822404384613037, |
| "learning_rate": 3.894444444444444e-05, |
| "loss": 1.8221, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.5555555555555556, |
| "grad_norm": 0.4802704453468323, |
| "learning_rate": 3.6166666666666674e-05, |
| "loss": 1.4957, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 0.6341160535812378, |
| "learning_rate": 3.338888888888889e-05, |
| "loss": 1.4374, |
| "step": 400 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.6768759489059448, |
| "learning_rate": 3.061111111111111e-05, |
| "loss": 1.1836, |
| "step": 450 |
| }, |
| { |
| "epoch": 2.2222222222222223, |
| "grad_norm": 0.6946759819984436, |
| "learning_rate": 2.7833333333333333e-05, |
| "loss": 1.0751, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.4444444444444446, |
| "grad_norm": 0.41082316637039185, |
| "learning_rate": 2.5055555555555555e-05, |
| "loss": 0.8647, |
| "step": 550 |
| }, |
| { |
| "epoch": 2.6666666666666665, |
| "grad_norm": 0.7865115404129028, |
| "learning_rate": 2.2277777777777778e-05, |
| "loss": 0.7527, |
| "step": 600 |
| }, |
| { |
| "epoch": 2.888888888888889, |
| "grad_norm": 0.7649757266044617, |
| "learning_rate": 1.9500000000000003e-05, |
| "loss": 0.6811, |
| "step": 650 |
| }, |
| { |
| "epoch": 3.111111111111111, |
| "grad_norm": 0.9702394008636475, |
| "learning_rate": 1.6722222222222222e-05, |
| "loss": 0.5942, |
| "step": 700 |
| }, |
| { |
| "epoch": 3.3333333333333335, |
| "grad_norm": 0.6544240117073059, |
| "learning_rate": 1.3944444444444446e-05, |
| "loss": 0.5397, |
| "step": 750 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 0.5421030521392822, |
| "learning_rate": 1.1166666666666668e-05, |
| "loss": 0.4963, |
| "step": 800 |
| }, |
| { |
| "epoch": 3.7777777777777777, |
| "grad_norm": 0.5874505639076233, |
| "learning_rate": 8.38888888888889e-06, |
| "loss": 0.4572, |
| "step": 850 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.6153783202171326, |
| "learning_rate": 5.611111111111112e-06, |
| "loss": 0.4489, |
| "step": 900 |
| }, |
| { |
| "epoch": 4.222222222222222, |
| "grad_norm": 1.0292067527770996, |
| "learning_rate": 2.8333333333333335e-06, |
| "loss": 0.4271, |
| "step": 950 |
| }, |
| { |
| "epoch": 4.444444444444445, |
| "grad_norm": 0.5997017621994019, |
| "learning_rate": 5.555555555555556e-08, |
| "loss": 0.4281, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.444444444444445, |
| "step": 1000, |
| "total_flos": 1.099960418304e+16, |
| "train_loss": 2.8363659076690673, |
| "train_runtime": 1221.2493, |
| "train_samples_per_second": 13.101, |
| "train_steps_per_second": 0.819 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.099960418304e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
