|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.14245690678569733, |
|
"eval_steps": 500, |
|
"global_step": 3000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0047485635595232445, |
|
"grad_norm": 0.3049672544002533, |
|
"learning_rate": 8.333333333333334e-06, |
|
"loss": 0.623, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.009497127119046489, |
|
"grad_norm": 0.09646450728178024, |
|
"learning_rate": 1.6666666666666667e-05, |
|
"loss": 0.29, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.014245690678569733, |
|
"grad_norm": 0.16680897772312164, |
|
"learning_rate": 2.5e-05, |
|
"loss": 0.1391, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.018994254238092978, |
|
"grad_norm": 0.17046234011650085, |
|
"learning_rate": 3.3333333333333335e-05, |
|
"loss": 0.1325, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.023742817797616222, |
|
"grad_norm": 0.08646216243505478, |
|
"learning_rate": 4.166666666666667e-05, |
|
"loss": 0.1238, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.028491381357139467, |
|
"grad_norm": 0.09403830766677856, |
|
"learning_rate": 5e-05, |
|
"loss": 0.1128, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.03323994491666271, |
|
"grad_norm": 0.08856412768363953, |
|
"learning_rate": 4.9786121534345265e-05, |
|
"loss": 0.1134, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.037988508476185956, |
|
"grad_norm": 0.1673099398612976, |
|
"learning_rate": 4.914814565722671e-05, |
|
"loss": 0.1108, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.0427370720357092, |
|
"grad_norm": 0.07016578316688538, |
|
"learning_rate": 4.8096988312782174e-05, |
|
"loss": 0.1088, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 0.047485635595232445, |
|
"grad_norm": 0.07002697139978409, |
|
"learning_rate": 4.665063509461097e-05, |
|
"loss": 0.1096, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.05223419915475569, |
|
"grad_norm": 0.16299889981746674, |
|
"learning_rate": 4.4833833507280884e-05, |
|
"loss": 0.1071, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 0.056982762714278934, |
|
"grad_norm": 0.06416748464107513, |
|
"learning_rate": 4.267766952966369e-05, |
|
"loss": 0.107, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 0.06173132627380217, |
|
"grad_norm": 0.06463466584682465, |
|
"learning_rate": 4.021903572521802e-05, |
|
"loss": 0.1062, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 0.06647988983332542, |
|
"grad_norm": 0.07041608542203903, |
|
"learning_rate": 3.7500000000000003e-05, |
|
"loss": 0.1065, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 0.07122845339284867, |
|
"grad_norm": 0.07932303100824356, |
|
"learning_rate": 3.456708580912725e-05, |
|
"loss": 0.1044, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.07597701695237191, |
|
"grad_norm": 0.061066512018442154, |
|
"learning_rate": 3.147047612756302e-05, |
|
"loss": 0.1034, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 0.08072558051189516, |
|
"grad_norm": 0.06134779006242752, |
|
"learning_rate": 2.8263154805501297e-05, |
|
"loss": 0.1034, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 0.0854741440714184, |
|
"grad_norm": 0.06713131070137024, |
|
"learning_rate": 2.5e-05, |
|
"loss": 0.1049, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 0.09022270763094165, |
|
"grad_norm": 0.09950446337461472, |
|
"learning_rate": 2.173684519449872e-05, |
|
"loss": 0.105, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 0.09497127119046489, |
|
"grad_norm": 0.06452978402376175, |
|
"learning_rate": 1.852952387243698e-05, |
|
"loss": 0.1054, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.09971983474998813, |
|
"grad_norm": 0.11814086139202118, |
|
"learning_rate": 1.5432914190872757e-05, |
|
"loss": 0.1031, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 0.10446839830951138, |
|
"grad_norm": 0.08128858357667923, |
|
"learning_rate": 1.2500000000000006e-05, |
|
"loss": 0.103, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 0.10921696186903462, |
|
"grad_norm": 0.07054319977760315, |
|
"learning_rate": 9.780964274781984e-06, |
|
"loss": 0.103, |
|
"step": 2300 |
|
}, |
|
{ |
|
"epoch": 0.11396552542855787, |
|
"grad_norm": 0.06334717571735382, |
|
"learning_rate": 7.3223304703363135e-06, |
|
"loss": 0.1034, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 0.11871408898808111, |
|
"grad_norm": 0.07204329967498779, |
|
"learning_rate": 5.166166492719124e-06, |
|
"loss": 0.1059, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.12346265254760434, |
|
"grad_norm": 0.05405697599053383, |
|
"learning_rate": 3.3493649053890326e-06, |
|
"loss": 0.105, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 0.1282112161071276, |
|
"grad_norm": 0.06032924726605415, |
|
"learning_rate": 1.9030116872178316e-06, |
|
"loss": 0.1009, |
|
"step": 2700 |
|
}, |
|
{ |
|
"epoch": 0.13295977966665085, |
|
"grad_norm": 0.07012154161930084, |
|
"learning_rate": 8.51854342773295e-07, |
|
"loss": 0.1042, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 0.1377083432261741, |
|
"grad_norm": 0.07376914471387863, |
|
"learning_rate": 2.1387846565474045e-07, |
|
"loss": 0.103, |
|
"step": 2900 |
|
}, |
|
{ |
|
"epoch": 0.14245690678569733, |
|
"grad_norm": 0.09159684926271439, |
|
"learning_rate": 0.0, |
|
"loss": 0.1014, |
|
"step": 3000 |
|
} |
|
], |
|
"logging_steps": 100, |
|
"max_steps": 3000, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 200, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.658973782016e+17, |
|
"train_batch_size": 16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|