|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 5.112, |
|
"eval_steps": 500, |
|
"global_step": 1600, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.16, |
|
"grad_norm": 0.18150772154331207, |
|
"learning_rate": 0.0001, |
|
"loss": 1.222, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"grad_norm": 0.19756411015987396, |
|
"learning_rate": 0.0002, |
|
"loss": 1.0496, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"grad_norm": 0.16334174573421478, |
|
"learning_rate": 0.0001943566591422122, |
|
"loss": 1.0084, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"grad_norm": 0.1872260421514511, |
|
"learning_rate": 0.0001887133182844244, |
|
"loss": 0.9866, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"grad_norm": 0.1755620241165161, |
|
"learning_rate": 0.0001830699774266366, |
|
"loss": 0.9553, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"grad_norm": 0.18523474037647247, |
|
"learning_rate": 0.00017742663656884877, |
|
"loss": 0.9591, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 1.1184, |
|
"grad_norm": 0.18473008275032043, |
|
"learning_rate": 0.00017178329571106095, |
|
"loss": 0.9414, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 1.2784, |
|
"grad_norm": 0.18801915645599365, |
|
"learning_rate": 0.00016613995485327313, |
|
"loss": 0.906, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 1.4384000000000001, |
|
"grad_norm": 0.18927383422851562, |
|
"learning_rate": 0.00016049661399548536, |
|
"loss": 0.9321, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 1.5984, |
|
"grad_norm": 0.1739863157272339, |
|
"learning_rate": 0.00015485327313769753, |
|
"loss": 0.9218, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.7584, |
|
"grad_norm": 0.16567449271678925, |
|
"learning_rate": 0.0001492099322799097, |
|
"loss": 0.9324, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 1.9184, |
|
"grad_norm": 0.17867760360240936, |
|
"learning_rate": 0.0001435665914221219, |
|
"loss": 0.9298, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 2.0768, |
|
"grad_norm": 0.17996446788311005, |
|
"learning_rate": 0.0001379232505643341, |
|
"loss": 0.9146, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 2.2368, |
|
"grad_norm": 0.17823895812034607, |
|
"learning_rate": 0.0001322799097065463, |
|
"loss": 0.8931, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 2.3968, |
|
"grad_norm": 0.17624235153198242, |
|
"learning_rate": 0.00012663656884875847, |
|
"loss": 0.915, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 2.5568, |
|
"grad_norm": 0.2087327539920807, |
|
"learning_rate": 0.00012099322799097066, |
|
"loss": 0.8858, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 2.7168, |
|
"grad_norm": 0.19803094863891602, |
|
"learning_rate": 0.00011534988713318284, |
|
"loss": 0.8868, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 2.8768000000000002, |
|
"grad_norm": 0.19719158113002777, |
|
"learning_rate": 0.00010970654627539505, |
|
"loss": 0.9044, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 3.0352, |
|
"grad_norm": 0.18085877597332, |
|
"learning_rate": 0.00010406320541760724, |
|
"loss": 0.8841, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 3.1952, |
|
"grad_norm": 0.1980597972869873, |
|
"learning_rate": 9.841986455981941e-05, |
|
"loss": 0.8758, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 3.3552, |
|
"grad_norm": 0.21820344030857086, |
|
"learning_rate": 9.27765237020316e-05, |
|
"loss": 0.8696, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 3.5152, |
|
"grad_norm": 0.2168891280889511, |
|
"learning_rate": 8.71331828442438e-05, |
|
"loss": 0.874, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 3.6752000000000002, |
|
"grad_norm": 0.18441538512706757, |
|
"learning_rate": 8.148984198645599e-05, |
|
"loss": 0.8641, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 3.8352, |
|
"grad_norm": 0.18984852731227875, |
|
"learning_rate": 7.584650112866818e-05, |
|
"loss": 0.8836, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 3.9952, |
|
"grad_norm": 0.20449557900428772, |
|
"learning_rate": 7.020316027088037e-05, |
|
"loss": 0.8687, |
|
"step": 1250 |
|
}, |
|
{ |
|
"epoch": 4.1536, |
|
"grad_norm": 0.18471935391426086, |
|
"learning_rate": 6.455981941309256e-05, |
|
"loss": 0.8615, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 4.3136, |
|
"grad_norm": 0.1952802985906601, |
|
"learning_rate": 5.891647855530474e-05, |
|
"loss": 0.8669, |
|
"step": 1350 |
|
}, |
|
{ |
|
"epoch": 4.4736, |
|
"grad_norm": 0.1887563169002533, |
|
"learning_rate": 5.3273137697516925e-05, |
|
"loss": 0.8499, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 4.6336, |
|
"grad_norm": 0.19429226219654083, |
|
"learning_rate": 4.762979683972912e-05, |
|
"loss": 0.8415, |
|
"step": 1450 |
|
}, |
|
{ |
|
"epoch": 4.7936, |
|
"grad_norm": 0.18455220758914948, |
|
"learning_rate": 4.198645598194131e-05, |
|
"loss": 0.8678, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 4.9536, |
|
"grad_norm": 0.20824351906776428, |
|
"learning_rate": 3.63431151241535e-05, |
|
"loss": 0.8519, |
|
"step": 1550 |
|
}, |
|
{ |
|
"epoch": 5.112, |
|
"grad_norm": 0.1955386996269226, |
|
"learning_rate": 3.069977426636569e-05, |
|
"loss": 0.8507, |
|
"step": 1600 |
|
} |
|
], |
|
"logging_steps": 50, |
|
"max_steps": 1872, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 6, |
|
"save_steps": 100, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 4.981518228386611e+17, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|