|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.504424778761062, |
|
"eval_steps": 500, |
|
"global_step": 170, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.08849557522123894, |
|
"grad_norm": 0.5826612710952759, |
|
"learning_rate": 0.0001983291392776536, |
|
"loss": 1.568, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.17699115044247787, |
|
"grad_norm": 0.46946820616722107, |
|
"learning_rate": 0.0001933060369780995, |
|
"loss": 1.4838, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.26548672566371684, |
|
"grad_norm": 0.3986819386482239, |
|
"learning_rate": 0.00018510177871569567, |
|
"loss": 1.4448, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.35398230088495575, |
|
"grad_norm": 0.5314409732818604, |
|
"learning_rate": 0.0001739960787076297, |
|
"loss": 1.4881, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.4424778761061947, |
|
"grad_norm": 0.40135467052459717, |
|
"learning_rate": 0.00016036757230212216, |
|
"loss": 1.4295, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.5309734513274337, |
|
"grad_norm": 0.38325050473213196, |
|
"learning_rate": 0.0001446809068662752, |
|
"loss": 1.4488, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.6194690265486725, |
|
"grad_norm": 0.5114065408706665, |
|
"learning_rate": 0.00012747090019864335, |
|
"loss": 1.4666, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.7079646017699115, |
|
"grad_norm": 0.5297059416770935, |
|
"learning_rate": 0.00010932430656620158, |
|
"loss": 1.5029, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.7964601769911505, |
|
"grad_norm": 0.43477290868759155, |
|
"learning_rate": 9.085981203052594e-05, |
|
"loss": 1.4866, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.8849557522123894, |
|
"grad_norm": 0.34949564933776855, |
|
"learning_rate": 7.270694109823492e-05, |
|
"loss": 1.4985, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.9734513274336283, |
|
"grad_norm": 0.5180746912956238, |
|
"learning_rate": 5.54845938478161e-05, |
|
"loss": 1.4586, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 1.0619469026548674, |
|
"grad_norm": 0.4795304536819458, |
|
"learning_rate": 3.9779945283420495e-05, |
|
"loss": 1.3711, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 1.1504424778761062, |
|
"grad_norm": 0.46757686138153076, |
|
"learning_rate": 2.6128426316520773e-05, |
|
"loss": 1.3495, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 1.238938053097345, |
|
"grad_norm": 0.4402760863304138, |
|
"learning_rate": 1.4995468899539278e-05, |
|
"loss": 1.3061, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 1.3274336283185841, |
|
"grad_norm": 0.3704012334346771, |
|
"learning_rate": 6.760637688935456e-06, |
|
"loss": 1.296, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.415929203539823, |
|
"grad_norm": 0.4756225347518921, |
|
"learning_rate": 1.704689249419289e-06, |
|
"loss": 1.2514, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 1.504424778761062, |
|
"grad_norm": 0.4762488603591919, |
|
"learning_rate": 0.0, |
|
"loss": 1.2664, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 1.504424778761062, |
|
"step": 170, |
|
"total_flos": 4.635056723931955e+16, |
|
"train_loss": 1.4186260223388671, |
|
"train_runtime": 516.77, |
|
"train_samples_per_second": 5.225, |
|
"train_steps_per_second": 0.329 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 170, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 2, |
|
"save_steps": 500, |
|
"total_flos": 4.635056723931955e+16, |
|
"train_batch_size": 16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|