|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"eval_steps": 500, |
|
"global_step": 82, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.012195121951219513, |
|
"grad_norm": 10.0, |
|
"learning_rate": 2.2222222222222223e-05, |
|
"loss": 4.6342, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.06097560975609756, |
|
"grad_norm": 8.5, |
|
"learning_rate": 0.00011111111111111112, |
|
"loss": 4.6731, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.12195121951219512, |
|
"grad_norm": 3.34375, |
|
"learning_rate": 0.00019990741151022301, |
|
"loss": 4.3963, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.18292682926829268, |
|
"grad_norm": 2.890625, |
|
"learning_rate": 0.00019668478136052774, |
|
"loss": 4.2375, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.24390243902439024, |
|
"grad_norm": 2.28125, |
|
"learning_rate": 0.00018900275764346768, |
|
"loss": 4.1537, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.3048780487804878, |
|
"grad_norm": 2.4375, |
|
"learning_rate": 0.00017721565844991643, |
|
"loss": 4.1163, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.36585365853658536, |
|
"grad_norm": 2.328125, |
|
"learning_rate": 0.00016186714032625035, |
|
"loss": 4.0943, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.4268292682926829, |
|
"grad_norm": 1.9375, |
|
"learning_rate": 0.0001436651231956064, |
|
"loss": 4.0725, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.4878048780487805, |
|
"grad_norm": 1.8515625, |
|
"learning_rate": 0.00012344913895704097, |
|
"loss": 4.0395, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.5487804878048781, |
|
"grad_norm": 1.6328125, |
|
"learning_rate": 0.00010215160974362223, |
|
"loss": 4.0439, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.6097560975609756, |
|
"grad_norm": 1.625, |
|
"learning_rate": 8.075484180291701e-05, |
|
"loss": 4.0223, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.6707317073170732, |
|
"grad_norm": 1.7265625, |
|
"learning_rate": 6.024571857174443e-05, |
|
"loss": 4.0318, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.7317073170731707, |
|
"grad_norm": 1.78125, |
|
"learning_rate": 4.1570182637163155e-05, |
|
"loss": 4.0052, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.7926829268292683, |
|
"grad_norm": 1.7421875, |
|
"learning_rate": 2.5589606012863963e-05, |
|
"loss": 4.0278, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.8536585365853658, |
|
"grad_norm": 1.7734375, |
|
"learning_rate": 1.30410610653389e-05, |
|
"loss": 4.019, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.9146341463414634, |
|
"grad_norm": 1.609375, |
|
"learning_rate": 4.503324514474483e-06, |
|
"loss": 4.0281, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.975609756097561, |
|
"grad_norm": 1.609375, |
|
"learning_rate": 3.701825065392184e-07, |
|
"loss": 4.0339, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"step": 82, |
|
"total_flos": 684585123840000.0, |
|
"train_loss": 4.120773559663354, |
|
"train_runtime": 106.8255, |
|
"train_samples_per_second": 12.263, |
|
"train_steps_per_second": 0.768 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 82, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 100, |
|
"total_flos": 684585123840000.0, |
|
"train_batch_size": 16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|