| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 1000, |
| "global_step": 144, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.06944444444444445, |
| "grad_norm": 8.71909236907959, |
| "learning_rate": 1e-06, |
| "loss": 2.6593, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.1388888888888889, |
| "grad_norm": 8.853459358215332, |
| "learning_rate": 1e-06, |
| "loss": 2.4766, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.20833333333333334, |
| "grad_norm": 6.577568054199219, |
| "learning_rate": 1e-06, |
| "loss": 2.495, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.2777777777777778, |
| "grad_norm": 8.3203706741333, |
| "learning_rate": 1e-06, |
| "loss": 2.6105, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.3472222222222222, |
| "grad_norm": 7.732483863830566, |
| "learning_rate": 1e-06, |
| "loss": 2.4744, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.4166666666666667, |
| "grad_norm": 6.6942548751831055, |
| "learning_rate": 1e-06, |
| "loss": 2.5163, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.4861111111111111, |
| "grad_norm": 5.781284809112549, |
| "learning_rate": 1e-06, |
| "loss": 2.3854, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.5555555555555556, |
| "grad_norm": 7.311328887939453, |
| "learning_rate": 1e-06, |
| "loss": 2.4442, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.625, |
| "grad_norm": 6.254249572753906, |
| "learning_rate": 1e-06, |
| "loss": 2.2468, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.6944444444444444, |
| "grad_norm": 7.6778669357299805, |
| "learning_rate": 1e-06, |
| "loss": 2.2565, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.7638888888888888, |
| "grad_norm": 7.495645523071289, |
| "learning_rate": 1e-06, |
| "loss": 2.4391, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.8333333333333334, |
| "grad_norm": 5.458991527557373, |
| "learning_rate": 1e-06, |
| "loss": 2.2362, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.9027777777777778, |
| "grad_norm": 5.659170627593994, |
| "learning_rate": 1e-06, |
| "loss": 2.2188, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.9722222222222222, |
| "grad_norm": 4.8217997550964355, |
| "learning_rate": 1e-06, |
| "loss": 2.154, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.0416666666666667, |
| "grad_norm": 6.693627834320068, |
| "learning_rate": 1e-06, |
| "loss": 2.1182, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.1111111111111112, |
| "grad_norm": 6.67255973815918, |
| "learning_rate": 1e-06, |
| "loss": 2.1879, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.1805555555555556, |
| "grad_norm": 4.831326007843018, |
| "learning_rate": 1e-06, |
| "loss": 2.1077, |
| "step": 85 |
| }, |
| { |
| "epoch": 1.25, |
| "grad_norm": 4.830414295196533, |
| "learning_rate": 1e-06, |
| "loss": 2.026, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.3194444444444444, |
| "grad_norm": 5.039080619812012, |
| "learning_rate": 1e-06, |
| "loss": 2.0585, |
| "step": 95 |
| }, |
| { |
| "epoch": 1.3888888888888888, |
| "grad_norm": 5.749475002288818, |
| "learning_rate": 1e-06, |
| "loss": 2.0486, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.4583333333333333, |
| "grad_norm": 5.0571770668029785, |
| "learning_rate": 1e-06, |
| "loss": 1.9616, |
| "step": 105 |
| }, |
| { |
| "epoch": 1.5277777777777777, |
| "grad_norm": 4.597809314727783, |
| "learning_rate": 1e-06, |
| "loss": 1.9063, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.5972222222222223, |
| "grad_norm": 5.453224182128906, |
| "learning_rate": 1e-06, |
| "loss": 2.1802, |
| "step": 115 |
| }, |
| { |
| "epoch": 1.6666666666666665, |
| "grad_norm": 4.519564628601074, |
| "learning_rate": 1e-06, |
| "loss": 2.2049, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.7361111111111112, |
| "grad_norm": 4.976806163787842, |
| "learning_rate": 1e-06, |
| "loss": 1.8881, |
| "step": 125 |
| }, |
| { |
| "epoch": 1.8055555555555556, |
| "grad_norm": 4.543058395385742, |
| "learning_rate": 1e-06, |
| "loss": 2.0673, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.875, |
| "grad_norm": 4.89597225189209, |
| "learning_rate": 1e-06, |
| "loss": 2.0158, |
| "step": 135 |
| }, |
| { |
| "epoch": 1.9444444444444444, |
| "grad_norm": 4.95186185836792, |
| "learning_rate": 1e-06, |
| "loss": 2.0052, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.0, |
| "step": 144, |
| "total_flos": 9.601343958286336e+16, |
| "train_loss": 2.2213990655210285, |
| "train_runtime": 2501.8045, |
| "train_samples_per_second": 0.921, |
| "train_steps_per_second": 0.058 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 144, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 200, |
| "total_flos": 9.601343958286336e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
