|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.9987966305655837, |
|
"eval_steps": 500, |
|
"global_step": 415, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 1.9951807228915665e-05, |
|
"loss": 2.2931, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 1.951807228915663e-05, |
|
"loss": 2.0987, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 1.9036144578313255e-05, |
|
"loss": 1.7961, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 1.8602409638554217e-05, |
|
"loss": 1.4878, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 1.8120481927710845e-05, |
|
"loss": 1.3422, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 1.763855421686747e-05, |
|
"loss": 1.1479, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 1.71566265060241e-05, |
|
"loss": 1.0238, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 1.6674698795180724e-05, |
|
"loss": 0.9852, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 1.6192771084337352e-05, |
|
"loss": 0.9658, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 1.5710843373493977e-05, |
|
"loss": 0.9545, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 1.5228915662650604e-05, |
|
"loss": 0.9265, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 1.474698795180723e-05, |
|
"loss": 0.9566, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 1.4265060240963857e-05, |
|
"loss": 0.8895, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 1.3783132530120482e-05, |
|
"loss": 0.8826, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 1.3301204819277109e-05, |
|
"loss": 0.886, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 1.2819277108433736e-05, |
|
"loss": 0.8821, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 1.2337349397590364e-05, |
|
"loss": 0.9209, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 1.185542168674699e-05, |
|
"loss": 0.828, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 1.1373493975903616e-05, |
|
"loss": 0.9175, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 1.0891566265060243e-05, |
|
"loss": 0.9145, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 1.0409638554216868e-05, |
|
"loss": 0.9042, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 9.927710843373494e-06, |
|
"loss": 0.8954, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 9.445783132530121e-06, |
|
"loss": 0.834, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 8.963855421686748e-06, |
|
"loss": 0.8795, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 8.481927710843375e-06, |
|
"loss": 0.8797, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 8.000000000000001e-06, |
|
"loss": 0.8589, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 7.518072289156627e-06, |
|
"loss": 0.8869, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 7.036144578313253e-06, |
|
"loss": 0.8291, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 6.554216867469881e-06, |
|
"loss": 0.8698, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 6.0722891566265066e-06, |
|
"loss": 0.8348, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 5.590361445783133e-06, |
|
"loss": 0.7995, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 5.108433734939759e-06, |
|
"loss": 0.8363, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 4.626506024096386e-06, |
|
"loss": 0.8116, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 4.144578313253013e-06, |
|
"loss": 0.8179, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 3.6626506024096385e-06, |
|
"loss": 0.8906, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 3.1807228915662653e-06, |
|
"loss": 0.8595, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 2.698795180722892e-06, |
|
"loss": 0.8551, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 2.2168674698795183e-06, |
|
"loss": 0.7622, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 1.7349397590361446e-06, |
|
"loss": 0.8164, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 1.2530120481927713e-06, |
|
"loss": 0.8376, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 7.710843373493978e-07, |
|
"loss": 0.8681, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 2.891566265060241e-07, |
|
"loss": 0.8199, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"step": 415, |
|
"total_flos": 3.270828015747072e+17, |
|
"train_loss": 0.9609996382012425, |
|
"train_runtime": 5748.5662, |
|
"train_samples_per_second": 6.937, |
|
"train_steps_per_second": 0.072 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 415, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 500, |
|
"total_flos": 3.270828015747072e+17, |
|
"train_batch_size": 24, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|