|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"global_step": 16, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0, |
|
"loss": 2.9912, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"eval_accuracy": 0.040365853658536587, |
|
"eval_loss": 2.744140625, |
|
"eval_runtime": 4.9375, |
|
"eval_samples_per_second": 20.253, |
|
"eval_steps_per_second": 0.405, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0, |
|
"loss": 2.9329, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"eval_accuracy": 0.040365853658536587, |
|
"eval_loss": 2.744140625, |
|
"eval_runtime": 6.0216, |
|
"eval_samples_per_second": 16.607, |
|
"eval_steps_per_second": 0.332, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.0, |
|
"loss": 2.9138, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"eval_accuracy": 0.038902439024390244, |
|
"eval_loss": 2.826171875, |
|
"eval_runtime": 6.6113, |
|
"eval_samples_per_second": 15.126, |
|
"eval_steps_per_second": 0.303, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 5e-05, |
|
"loss": 2.9395, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"eval_accuracy": 0.038902439024390244, |
|
"eval_loss": 2.826171875, |
|
"eval_runtime": 7.2265, |
|
"eval_samples_per_second": 13.838, |
|
"eval_steps_per_second": 0.277, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 5e-05, |
|
"loss": 2.9109, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"eval_accuracy": 0.039878048780487806, |
|
"eval_loss": 2.794921875, |
|
"eval_runtime": 7.453, |
|
"eval_samples_per_second": 13.417, |
|
"eval_steps_per_second": 0.268, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 5e-05, |
|
"loss": 2.8391, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"eval_accuracy": 0.040284552845528454, |
|
"eval_loss": 2.74609375, |
|
"eval_runtime": 6.8467, |
|
"eval_samples_per_second": 14.606, |
|
"eval_steps_per_second": 0.292, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 5e-05, |
|
"loss": 2.9368, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"eval_accuracy": 0.03983739837398374, |
|
"eval_loss": 2.720703125, |
|
"eval_runtime": 7.2744, |
|
"eval_samples_per_second": 13.747, |
|
"eval_steps_per_second": 0.275, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 5e-05, |
|
"loss": 2.7583, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"eval_accuracy": 0.040325203252032524, |
|
"eval_loss": 2.70703125, |
|
"eval_runtime": 6.8783, |
|
"eval_samples_per_second": 14.539, |
|
"eval_steps_per_second": 0.291, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 5e-05, |
|
"loss": 2.9756, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"eval_accuracy": 0.04083333333333333, |
|
"eval_loss": 2.68359375, |
|
"eval_runtime": 7.0122, |
|
"eval_samples_per_second": 14.261, |
|
"eval_steps_per_second": 0.285, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 5e-05, |
|
"loss": 2.8442, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"eval_accuracy": 0.04034552845528455, |
|
"eval_loss": 2.673828125, |
|
"eval_runtime": 7.0273, |
|
"eval_samples_per_second": 14.23, |
|
"eval_steps_per_second": 0.285, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 5e-05, |
|
"loss": 2.7312, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"eval_accuracy": 0.04054878048780488, |
|
"eval_loss": 2.66796875, |
|
"eval_runtime": 6.8584, |
|
"eval_samples_per_second": 14.581, |
|
"eval_steps_per_second": 0.292, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 5e-05, |
|
"loss": 2.7439, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"eval_accuracy": 0.040365853658536587, |
|
"eval_loss": 2.669921875, |
|
"eval_runtime": 6.8135, |
|
"eval_samples_per_second": 14.677, |
|
"eval_steps_per_second": 0.294, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 5e-05, |
|
"loss": 2.9075, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"eval_accuracy": 0.04034552845528455, |
|
"eval_loss": 2.6796875, |
|
"eval_runtime": 6.1497, |
|
"eval_samples_per_second": 16.261, |
|
"eval_steps_per_second": 0.325, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 5e-05, |
|
"loss": 2.8518, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"eval_accuracy": 0.04034552845528455, |
|
"eval_loss": 2.6796875, |
|
"eval_runtime": 6.4271, |
|
"eval_samples_per_second": 15.559, |
|
"eval_steps_per_second": 0.311, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 5e-05, |
|
"loss": 2.8579, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"eval_accuracy": 0.04044715447154471, |
|
"eval_loss": 2.677734375, |
|
"eval_runtime": 7.2159, |
|
"eval_samples_per_second": 13.858, |
|
"eval_steps_per_second": 0.277, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 5e-05, |
|
"loss": 2.8916, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.040325203252032524, |
|
"eval_loss": 2.6953125, |
|
"eval_runtime": 6.3862, |
|
"eval_samples_per_second": 15.659, |
|
"eval_steps_per_second": 0.313, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"step": 16, |
|
"total_flos": 4999961640960.0, |
|
"train_loss": 2.8766326904296875, |
|
"train_runtime": 267.0978, |
|
"train_samples_per_second": 3.744, |
|
"train_steps_per_second": 0.06 |
|
} |
|
], |
|
"max_steps": 16, |
|
"num_train_epochs": 1, |
|
"total_flos": 4999961640960.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|