|
{
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 3.0,
|
|
"eval_steps": 500,
|
|
"global_step": 1953,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.07680491551459294,
|
|
"grad_norm": 0.15998965501785278,
|
|
"learning_rate": 0.0002,
|
|
"loss": 0.8173,
|
|
"step": 50
|
|
},
|
|
{
|
|
"epoch": 0.15360983102918588,
|
|
"grad_norm": 0.1599128544330597,
|
|
"learning_rate": 0.00019965952472163515,
|
|
"loss": 0.5618,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 0.2304147465437788,
|
|
"grad_norm": 0.1505613625049591,
|
|
"learning_rate": 0.0001986404173548442,
|
|
"loss": 0.5308,
|
|
"step": 150
|
|
},
|
|
{
|
|
"epoch": 0.30721966205837176,
|
|
"grad_norm": 0.13830986618995667,
|
|
"learning_rate": 0.0001969496175169149,
|
|
"loss": 0.5155,
|
|
"step": 200
|
|
},
|
|
{
|
|
"epoch": 0.38402457757296465,
|
|
"grad_norm": 0.12936702370643616,
|
|
"learning_rate": 0.00019459863871875693,
|
|
"loss": 0.5085,
|
|
"step": 250
|
|
},
|
|
{
|
|
"epoch": 0.4608294930875576,
|
|
"grad_norm": 0.1287979781627655,
|
|
"learning_rate": 0.00019160348996358483,
|
|
"loss": 0.4953,
|
|
"step": 300
|
|
},
|
|
{
|
|
"epoch": 0.5376344086021505,
|
|
"grad_norm": 0.13770239055156708,
|
|
"learning_rate": 0.0001879845667335219,
|
|
"loss": 0.4883,
|
|
"step": 350
|
|
},
|
|
{
|
|
"epoch": 0.6144393241167435,
|
|
"grad_norm": 0.12349069118499756,
|
|
"learning_rate": 0.00018376651210645086,
|
|
"loss": 0.4828,
|
|
"step": 400
|
|
},
|
|
{
|
|
"epoch": 0.6912442396313364,
|
|
"grad_norm": 0.1296069324016571,
|
|
"learning_rate": 0.0001789780489488379,
|
|
"loss": 0.4793,
|
|
"step": 450
|
|
},
|
|
{
|
|
"epoch": 0.7680491551459293,
|
|
"grad_norm": 0.14504997432231903,
|
|
"learning_rate": 0.0001736517843272136,
|
|
"loss": 0.4772,
|
|
"step": 500
|
|
},
|
|
{
|
|
"epoch": 0.8448540706605223,
|
|
"grad_norm": 0.13662400841712952,
|
|
"learning_rate": 0.00016782398747017174,
|
|
"loss": 0.4714,
|
|
"step": 550
|
|
},
|
|
{
|
|
"epoch": 0.9216589861751152,
|
|
"grad_norm": 0.13271653652191162,
|
|
"learning_rate": 0.0001615343427928555,
|
|
"loss": 0.4658,
|
|
"step": 600
|
|
},
|
|
{
|
|
"epoch": 0.9984639016897081,
|
|
"grad_norm": 0.13312594592571259,
|
|
"learning_rate": 0.00015482567966571136,
|
|
"loss": 0.464,
|
|
"step": 650
|
|
},
|
|
{
|
|
"epoch": 1.075268817204301,
|
|
"grad_norm": 0.13460350036621094,
|
|
"learning_rate": 0.00014774368076765274,
|
|
"loss": 0.4452,
|
|
"step": 700
|
|
},
|
|
{
|
|
"epoch": 1.1520737327188941,
|
|
"grad_norm": 0.12317976355552673,
|
|
"learning_rate": 0.00014033657100960355,
|
|
"loss": 0.446,
|
|
"step": 750
|
|
},
|
|
{
|
|
"epoch": 1.228878648233487,
|
|
"grad_norm": 0.12744882702827454,
|
|
"learning_rate": 0.0001326547891466988,
|
|
"loss": 0.443,
|
|
"step": 800
|
|
},
|
|
{
|
|
"epoch": 1.30568356374808,
|
|
"grad_norm": 0.13042095303535461,
|
|
"learning_rate": 0.00012475064431530065,
|
|
"loss": 0.4436,
|
|
"step": 850
|
|
},
|
|
{
|
|
"epoch": 1.3824884792626728,
|
|
"grad_norm": 0.12759792804718018,
|
|
"learning_rate": 0.00011667795983364332,
|
|
"loss": 0.4436,
|
|
"step": 900
|
|
},
|
|
{
|
|
"epoch": 1.4592933947772657,
|
|
"grad_norm": 0.1353318691253662,
|
|
"learning_rate": 0.00010849170669164763,
|
|
"loss": 0.4385,
|
|
"step": 950
|
|
},
|
|
{
|
|
"epoch": 1.5360983102918588,
|
|
"grad_norm": 0.13270655274391174,
|
|
"learning_rate": 0.00010024762922565933,
|
|
"loss": 0.4358,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"epoch": 1.6129032258064515,
|
|
"grad_norm": 0.13536469638347626,
|
|
"learning_rate": 9.200186552708023e-05,
|
|
"loss": 0.4349,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"epoch": 1.6897081413210446,
|
|
"grad_norm": 0.1286744475364685,
|
|
"learning_rate": 8.381056516972252e-05,
|
|
"loss": 0.4354,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"epoch": 1.7665130568356375,
|
|
"grad_norm": 0.13123248517513275,
|
|
"learning_rate": 7.572950685897294e-05,
|
|
"loss": 0.4312,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"epoch": 1.8433179723502304,
|
|
"grad_norm": 0.13481922447681427,
|
|
"learning_rate": 6.781371860638826e-05,
|
|
"loss": 0.4294,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"epoch": 1.9201228878648233,
|
|
"grad_norm": 0.14667406678199768,
|
|
"learning_rate": 6.0117103016143915e-05,
|
|
"loss": 0.4303,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"epoch": 1.9969278033794162,
|
|
"grad_norm": 0.1356251984834671,
|
|
"learning_rate": 5.269207023495112e-05,
|
|
"loss": 0.4298,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"epoch": 2.0737327188940093,
|
|
"grad_norm": 0.13895529508590698,
|
|
"learning_rate": 4.5589181064870644e-05,
|
|
"loss": 0.4159,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"epoch": 2.150537634408602,
|
|
"grad_norm": 0.14071515202522278,
|
|
"learning_rate": 3.885680266925016e-05,
|
|
"loss": 0.4165,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"epoch": 2.227342549923195,
|
|
"grad_norm": 0.13694094121456146,
|
|
"learning_rate": 3.254077921625578e-05,
|
|
"loss": 0.4129,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"epoch": 2.3041474654377883,
|
|
"grad_norm": 0.14088453352451324,
|
|
"learning_rate": 2.668411970275374e-05,
|
|
"loss": 0.4149,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"epoch": 2.380952380952381,
|
|
"grad_norm": 0.14287617802619934,
|
|
"learning_rate": 2.1326705084307108e-05,
|
|
"loss": 0.4115,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"epoch": 2.457757296466974,
|
|
"grad_norm": 0.13957332074642181,
|
|
"learning_rate": 1.6505016705586474e-05,
|
|
"loss": 0.4094,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"epoch": 2.5345622119815667,
|
|
"grad_norm": 0.13585838675498962,
|
|
"learning_rate": 1.2251887880450496e-05,
|
|
"loss": 0.4116,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"epoch": 2.61136712749616,
|
|
"grad_norm": 0.13778972625732422,
|
|
"learning_rate": 8.596280313312355e-06,
|
|
"loss": 0.415,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"epoch": 2.688172043010753,
|
|
"grad_norm": 0.14230361580848694,
|
|
"learning_rate": 5.563086884252388e-06,
|
|
"loss": 0.4111,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"epoch": 2.7649769585253456,
|
|
"grad_norm": 0.13878688216209412,
|
|
"learning_rate": 3.1729621408124188e-06,
|
|
"loss": 0.4057,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"epoch": 2.8417818740399383,
|
|
"grad_norm": 0.14506730437278748,
|
|
"learning_rate": 1.4421816507394603e-06,
|
|
"loss": 0.4103,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"epoch": 2.9185867895545314,
|
|
"grad_norm": 0.14065757393836975,
|
|
"learning_rate": 3.8253117341641166e-07,
|
|
"loss": 0.409,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"epoch": 2.9953917050691246,
|
|
"grad_norm": 0.1373552829027176,
|
|
"learning_rate": 1.2264046680088292e-09,
|
|
"loss": 0.4089,
|
|
"step": 1950
|
|
}
|
|
],
|
|
"logging_steps": 50,
|
|
"max_steps": 1953,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 3,
|
|
"save_steps": 500,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1.9206625186912666e+17,
|
|
"train_batch_size": 2,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|
|
|