|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 18.0, |
|
"eval_steps": 500, |
|
"global_step": 3816, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 0.00019900471698113207, |
|
"loss": 6.1329, |
|
"step": 212 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 5.14426851272583, |
|
"eval_runtime": 3.8194, |
|
"eval_samples_per_second": 176.991, |
|
"eval_steps_per_second": 22.255, |
|
"step": 212 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 0.00019800471698113207, |
|
"loss": 4.6548, |
|
"step": 424 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 3.559998035430908, |
|
"eval_runtime": 3.8713, |
|
"eval_samples_per_second": 174.616, |
|
"eval_steps_per_second": 21.956, |
|
"step": 424 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 0.00019700471698113207, |
|
"loss": 3.2979, |
|
"step": 636 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_loss": 2.3220388889312744, |
|
"eval_runtime": 3.7585, |
|
"eval_samples_per_second": 179.86, |
|
"eval_steps_per_second": 22.616, |
|
"step": 636 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"learning_rate": 0.00019600471698113207, |
|
"loss": 2.2394, |
|
"step": 848 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_loss": 1.5198729038238525, |
|
"eval_runtime": 3.8733, |
|
"eval_samples_per_second": 174.529, |
|
"eval_steps_per_second": 21.945, |
|
"step": 848 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 0.00019500471698113208, |
|
"loss": 1.5436, |
|
"step": 1060 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_loss": 1.0844509601593018, |
|
"eval_runtime": 3.7882, |
|
"eval_samples_per_second": 178.45, |
|
"eval_steps_per_second": 22.438, |
|
"step": 1060 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"learning_rate": 0.0001940047169811321, |
|
"loss": 1.1087, |
|
"step": 1272 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_loss": 0.8275050520896912, |
|
"eval_runtime": 3.8596, |
|
"eval_samples_per_second": 175.146, |
|
"eval_steps_per_second": 22.023, |
|
"step": 1272 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"learning_rate": 0.00019300943396226416, |
|
"loss": 0.8094, |
|
"step": 1484 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"eval_loss": 0.6410268545150757, |
|
"eval_runtime": 3.826, |
|
"eval_samples_per_second": 176.686, |
|
"eval_steps_per_second": 22.216, |
|
"step": 1484 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"learning_rate": 0.00019200943396226417, |
|
"loss": 0.5999, |
|
"step": 1696 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"eval_loss": 0.5242534279823303, |
|
"eval_runtime": 3.7888, |
|
"eval_samples_per_second": 178.42, |
|
"eval_steps_per_second": 22.434, |
|
"step": 1696 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"learning_rate": 0.00019100943396226417, |
|
"loss": 0.4333, |
|
"step": 1908 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"eval_loss": 0.4525991678237915, |
|
"eval_runtime": 3.7762, |
|
"eval_samples_per_second": 179.014, |
|
"eval_steps_per_second": 22.509, |
|
"step": 1908 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"learning_rate": 0.00019000943396226417, |
|
"loss": 0.3096, |
|
"step": 2120 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"eval_loss": 0.3988202214241028, |
|
"eval_runtime": 3.3771, |
|
"eval_samples_per_second": 200.169, |
|
"eval_steps_per_second": 25.169, |
|
"step": 2120 |
|
}, |
|
{ |
|
"epoch": 11.0, |
|
"learning_rate": 0.00018900943396226415, |
|
"loss": 0.225, |
|
"step": 2332 |
|
}, |
|
{ |
|
"epoch": 11.0, |
|
"eval_loss": 0.37283995747566223, |
|
"eval_runtime": 3.3836, |
|
"eval_samples_per_second": 199.788, |
|
"eval_steps_per_second": 25.121, |
|
"step": 2332 |
|
}, |
|
{ |
|
"epoch": 12.0, |
|
"learning_rate": 0.00018800943396226415, |
|
"loss": 0.1484, |
|
"step": 2544 |
|
}, |
|
{ |
|
"epoch": 12.0, |
|
"eval_loss": 0.36433306336402893, |
|
"eval_runtime": 3.9173, |
|
"eval_samples_per_second": 172.567, |
|
"eval_steps_per_second": 21.698, |
|
"step": 2544 |
|
}, |
|
{ |
|
"epoch": 13.0, |
|
"learning_rate": 0.00018700943396226415, |
|
"loss": 0.1086, |
|
"step": 2756 |
|
}, |
|
{ |
|
"epoch": 13.0, |
|
"eval_loss": 0.3588293790817261, |
|
"eval_runtime": 3.3573, |
|
"eval_samples_per_second": 201.351, |
|
"eval_steps_per_second": 25.318, |
|
"step": 2756 |
|
}, |
|
{ |
|
"epoch": 14.0, |
|
"learning_rate": 0.00018600943396226415, |
|
"loss": 0.0794, |
|
"step": 2968 |
|
}, |
|
{ |
|
"epoch": 14.0, |
|
"eval_loss": 0.34358447790145874, |
|
"eval_runtime": 3.5044, |
|
"eval_samples_per_second": 192.9, |
|
"eval_steps_per_second": 24.255, |
|
"step": 2968 |
|
}, |
|
{ |
|
"epoch": 15.0, |
|
"learning_rate": 0.00018500943396226416, |
|
"loss": 0.0629, |
|
"step": 3180 |
|
}, |
|
{ |
|
"epoch": 15.0, |
|
"eval_loss": 0.3459497392177582, |
|
"eval_runtime": 3.9331, |
|
"eval_samples_per_second": 171.873, |
|
"eval_steps_per_second": 21.611, |
|
"step": 3180 |
|
}, |
|
{ |
|
"epoch": 16.0, |
|
"learning_rate": 0.00018400943396226416, |
|
"loss": 0.0499, |
|
"step": 3392 |
|
}, |
|
{ |
|
"epoch": 16.0, |
|
"eval_loss": 0.35890209674835205, |
|
"eval_runtime": 3.9531, |
|
"eval_samples_per_second": 171.003, |
|
"eval_steps_per_second": 21.502, |
|
"step": 3392 |
|
}, |
|
{ |
|
"epoch": 17.0, |
|
"learning_rate": 0.00018300943396226416, |
|
"loss": 0.0381, |
|
"step": 3604 |
|
}, |
|
{ |
|
"epoch": 17.0, |
|
"eval_loss": 0.36232635378837585, |
|
"eval_runtime": 3.436, |
|
"eval_samples_per_second": 196.742, |
|
"eval_steps_per_second": 24.738, |
|
"step": 3604 |
|
}, |
|
{ |
|
"epoch": 18.0, |
|
"learning_rate": 0.00018200943396226417, |
|
"loss": 0.0328, |
|
"step": 3816 |
|
}, |
|
{ |
|
"epoch": 18.0, |
|
"eval_loss": 0.33994847536087036, |
|
"eval_runtime": 3.6854, |
|
"eval_samples_per_second": 183.428, |
|
"eval_steps_per_second": 23.064, |
|
"step": 3816 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 42400, |
|
"num_train_epochs": 200, |
|
"save_steps": 500, |
|
"total_flos": 5130952967846592.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|