|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.05, |
|
"eval_steps": 500, |
|
"global_step": 500, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"grad_norm": 114.5, |
|
"learning_rate": 2.2000000000000002e-08, |
|
"loss": 8.3264, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"grad_norm": 118.0, |
|
"learning_rate": 4.4000000000000004e-08, |
|
"loss": 8.3249, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"grad_norm": 118.5, |
|
"learning_rate": 6.6e-08, |
|
"loss": 8.3005, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"grad_norm": 116.5, |
|
"learning_rate": 8.800000000000001e-08, |
|
"loss": 8.2821, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"grad_norm": 116.5, |
|
"learning_rate": 1.1e-07, |
|
"loss": 8.3168, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"grad_norm": 120.0, |
|
"learning_rate": 1.32e-07, |
|
"loss": 8.288, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"grad_norm": 117.5, |
|
"learning_rate": 1.5400000000000003e-07, |
|
"loss": 8.3383, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"grad_norm": 119.0, |
|
"learning_rate": 1.7600000000000001e-07, |
|
"loss": 8.2777, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"grad_norm": 118.0, |
|
"learning_rate": 1.98e-07, |
|
"loss": 8.2758, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"grad_norm": 118.0, |
|
"learning_rate": 2.2e-07, |
|
"loss": 8.2869, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"grad_norm": 117.0, |
|
"learning_rate": 2.42e-07, |
|
"loss": 8.2819, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"grad_norm": 116.0, |
|
"learning_rate": 2.64e-07, |
|
"loss": 8.2884, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"grad_norm": 117.0, |
|
"learning_rate": 2.8600000000000005e-07, |
|
"loss": 8.229, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"grad_norm": 115.5, |
|
"learning_rate": 3.0800000000000006e-07, |
|
"loss": 8.2103, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"grad_norm": 114.0, |
|
"learning_rate": 3.3e-07, |
|
"loss": 8.2098, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"grad_norm": 114.5, |
|
"learning_rate": 3.5200000000000003e-07, |
|
"loss": 8.2018, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"grad_norm": 115.0, |
|
"learning_rate": 3.7400000000000004e-07, |
|
"loss": 8.1996, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"grad_norm": 115.0, |
|
"learning_rate": 3.96e-07, |
|
"loss": 8.1512, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"grad_norm": 112.5, |
|
"learning_rate": 4.18e-07, |
|
"loss": 8.1395, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"grad_norm": 113.0, |
|
"learning_rate": 4.4e-07, |
|
"loss": 8.1209, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"grad_norm": 111.0, |
|
"learning_rate": 4.62e-07, |
|
"loss": 8.0906, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"grad_norm": 111.5, |
|
"learning_rate": 4.84e-07, |
|
"loss": 8.0615, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"grad_norm": 109.0, |
|
"learning_rate": 5.06e-07, |
|
"loss": 8.0154, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"grad_norm": 110.5, |
|
"learning_rate": 5.28e-07, |
|
"loss": 7.986, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"grad_norm": 110.5, |
|
"learning_rate": 5.5e-07, |
|
"loss": 7.9651, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"grad_norm": 107.0, |
|
"learning_rate": 5.720000000000001e-07, |
|
"loss": 7.8918, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"grad_norm": 109.0, |
|
"learning_rate": 5.94e-07, |
|
"loss": 7.8074, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"grad_norm": 102.5, |
|
"learning_rate": 6.160000000000001e-07, |
|
"loss": 7.7464, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"grad_norm": 103.5, |
|
"learning_rate": 6.38e-07, |
|
"loss": 7.6693, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"grad_norm": 105.0, |
|
"learning_rate": 6.6e-07, |
|
"loss": 7.6443, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"grad_norm": 103.0, |
|
"learning_rate": 6.82e-07, |
|
"loss": 7.5796, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"grad_norm": 100.0, |
|
"learning_rate": 7.040000000000001e-07, |
|
"loss": 7.4966, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"grad_norm": 103.0, |
|
"learning_rate": 7.260000000000001e-07, |
|
"loss": 7.4265, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"grad_norm": 98.5, |
|
"learning_rate": 7.480000000000001e-07, |
|
"loss": 7.3721, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"grad_norm": 100.0, |
|
"learning_rate": 7.7e-07, |
|
"loss": 7.2681, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"grad_norm": 102.0, |
|
"learning_rate": 7.92e-07, |
|
"loss": 7.207, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"grad_norm": 106.0, |
|
"learning_rate": 8.140000000000001e-07, |
|
"loss": 7.1546, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"grad_norm": 104.0, |
|
"learning_rate": 8.36e-07, |
|
"loss": 7.0713, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"grad_norm": 104.5, |
|
"learning_rate": 8.580000000000001e-07, |
|
"loss": 6.9667, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"grad_norm": 100.5, |
|
"learning_rate": 8.8e-07, |
|
"loss": 6.8803, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"grad_norm": 92.5, |
|
"learning_rate": 9.02e-07, |
|
"loss": 6.7517, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"grad_norm": 96.0, |
|
"learning_rate": 9.24e-07, |
|
"loss": 6.6599, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"grad_norm": 94.5, |
|
"learning_rate": 9.46e-07, |
|
"loss": 6.5193, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"grad_norm": 90.0, |
|
"learning_rate": 9.68e-07, |
|
"loss": 6.4, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"grad_norm": 87.5, |
|
"learning_rate": 9.9e-07, |
|
"loss": 6.3021, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"grad_norm": 87.0, |
|
"learning_rate": 1.012e-06, |
|
"loss": 6.1852, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"grad_norm": 82.0, |
|
"learning_rate": 1.034e-06, |
|
"loss": 6.0423, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"grad_norm": 84.0, |
|
"learning_rate": 1.056e-06, |
|
"loss": 5.9377, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"grad_norm": 82.5, |
|
"learning_rate": 1.078e-06, |
|
"loss": 5.7858, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"grad_norm": 81.0, |
|
"learning_rate": 1.1e-06, |
|
"loss": 5.6391, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"eval_loss": 5.58803129196167, |
|
"eval_runtime": 64.9971, |
|
"eval_samples_per_second": 15.385, |
|
"eval_steps_per_second": 15.385, |
|
"step": 500 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 1500, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 500, |
|
"total_flos": 8069610209280000.0, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|