|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.15594541910331383, |
|
"eval_steps": 500, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 5e-05, |
|
"loss": 1.0506, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.0001, |
|
"loss": 0.9988, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.00015000000000000001, |
|
"loss": 0.9783, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.0002, |
|
"loss": 0.9849, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00025, |
|
"loss": 1.0159, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00030000000000000003, |
|
"loss": 0.9847, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00034999999999999994, |
|
"loss": 0.9101, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.0004, |
|
"loss": 0.9445, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.00045, |
|
"loss": 0.8578, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.0005, |
|
"loss": 0.9356, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.0005499999999999999, |
|
"loss": 0.8395, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.0006000000000000001, |
|
"loss": 0.9002, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00065, |
|
"loss": 0.8955, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.0006499959204043461, |
|
"loss": 0.902, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.0006499836817198032, |
|
"loss": 0.8578, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.0006499632842536263, |
|
"loss": 0.9005, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.0006499347285178979, |
|
"loss": 0.8539, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.0006498980152295153, |
|
"loss": 0.8595, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.0006498531453101735, |
|
"loss": 0.8845, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.0006498001198863406, |
|
"loss": 0.8924, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.000649738940289231, |
|
"loss": 0.8365, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.0006496696080547707, |
|
"loss": 0.8462, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.0006495921249235596, |
|
"loss": 0.8528, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.0006495064928408277, |
|
"loss": 0.8159, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.0006494127139563859, |
|
"loss": 0.8245, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.000649310790624572, |
|
"loss": 0.8081, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.0006492007254041924, |
|
"loss": 0.8535, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.0006490825210584566, |
|
"loss": 0.8162, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.0006489561805549089, |
|
"loss": 0.8456, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.0006488217070653535, |
|
"loss": 0.7799, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.0006486791039657748, |
|
"loss": 0.8088, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.0006485283748362524, |
|
"loss": 0.8683, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.0006483695234608723, |
|
"loss": 0.8871, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.0006482025538276304, |
|
"loss": 0.7711, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.0006480274701283335, |
|
"loss": 0.7621, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.0006478442767584937, |
|
"loss": 0.8243, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.0006476529783172177, |
|
"loss": 0.8257, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.0006474535796070919, |
|
"loss": 0.8141, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.0006472460856340619, |
|
"loss": 0.8109, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.000647030501607306, |
|
"loss": 0.7873, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.000646806832939105, |
|
"loss": 0.7386, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.0006465750852447068, |
|
"loss": 0.8636, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.0006463352643421846, |
|
"loss": 0.7357, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.0006460873762522906, |
|
"loss": 0.8142, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.0006458314271983063, |
|
"loss": 0.7275, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.0006455674236058847, |
|
"loss": 0.8029, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.00064529537210289, |
|
"loss": 0.7901, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.0006450152795192307, |
|
"loss": 0.7788, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.0006447271528866881, |
|
"loss": 0.7621, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.0006444309994387402, |
|
"loss": 0.7537, |
|
"step": 50 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 640, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 2, |
|
"save_steps": 50, |
|
"total_flos": 1.2960384418676736e+17, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|