|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.7317073170731707, |
|
"eval_steps": 500, |
|
"global_step": 600, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.024390243902439025, |
|
"grad_norm": 0.18664376437664032, |
|
"learning_rate": 0.00019631901840490797, |
|
"loss": 2.606, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.04878048780487805, |
|
"grad_norm": 0.15699957311153412, |
|
"learning_rate": 0.0001914110429447853, |
|
"loss": 2.3256, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.07317073170731707, |
|
"grad_norm": 0.15484048426151276, |
|
"learning_rate": 0.00018650306748466258, |
|
"loss": 2.3271, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.0975609756097561, |
|
"grad_norm": 0.16558347642421722, |
|
"learning_rate": 0.00018159509202453987, |
|
"loss": 2.271, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.12195121951219512, |
|
"grad_norm": 0.14375853538513184, |
|
"learning_rate": 0.0001766871165644172, |
|
"loss": 2.2443, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.14634146341463414, |
|
"grad_norm": 0.18161948025226593, |
|
"learning_rate": 0.0001717791411042945, |
|
"loss": 2.197, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.17073170731707318, |
|
"grad_norm": 0.21335937082767487, |
|
"learning_rate": 0.00016687116564417177, |
|
"loss": 2.2971, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.1951219512195122, |
|
"grad_norm": 0.15174631774425507, |
|
"learning_rate": 0.00016196319018404909, |
|
"loss": 2.1882, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.21951219512195122, |
|
"grad_norm": 0.23237347602844238, |
|
"learning_rate": 0.0001570552147239264, |
|
"loss": 2.1903, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.24390243902439024, |
|
"grad_norm": 0.17385663092136383, |
|
"learning_rate": 0.0001521472392638037, |
|
"loss": 2.2466, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.2682926829268293, |
|
"grad_norm": 0.166335791349411, |
|
"learning_rate": 0.00014723926380368098, |
|
"loss": 2.2083, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.2926829268292683, |
|
"grad_norm": 0.14538025856018066, |
|
"learning_rate": 0.00014233128834355828, |
|
"loss": 2.1973, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.3170731707317073, |
|
"grad_norm": 0.1764744222164154, |
|
"learning_rate": 0.0001374233128834356, |
|
"loss": 2.1772, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.34146341463414637, |
|
"grad_norm": 0.14891883730888367, |
|
"learning_rate": 0.00013251533742331288, |
|
"loss": 2.1626, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.36585365853658536, |
|
"grad_norm": 0.156418576836586, |
|
"learning_rate": 0.00012760736196319017, |
|
"loss": 2.181, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.3902439024390244, |
|
"grad_norm": 0.17010940611362457, |
|
"learning_rate": 0.0001226993865030675, |
|
"loss": 2.1736, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.4146341463414634, |
|
"grad_norm": 0.1576879322528839, |
|
"learning_rate": 0.0001177914110429448, |
|
"loss": 2.2331, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 0.43902439024390244, |
|
"grad_norm": 0.15243475139141083, |
|
"learning_rate": 0.00011288343558282209, |
|
"loss": 2.1011, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 0.4634146341463415, |
|
"grad_norm": 0.1490599811077118, |
|
"learning_rate": 0.00010797546012269939, |
|
"loss": 2.2281, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 0.4878048780487805, |
|
"grad_norm": 0.1911603808403015, |
|
"learning_rate": 0.0001030674846625767, |
|
"loss": 2.2504, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.5121951219512195, |
|
"grad_norm": 0.1803751140832901, |
|
"learning_rate": 9.815950920245399e-05, |
|
"loss": 2.2071, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 0.5365853658536586, |
|
"grad_norm": 0.17362748086452484, |
|
"learning_rate": 9.325153374233129e-05, |
|
"loss": 2.1655, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 0.5609756097560976, |
|
"grad_norm": 0.1631132960319519, |
|
"learning_rate": 8.83435582822086e-05, |
|
"loss": 2.2041, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 0.5853658536585366, |
|
"grad_norm": 0.19363833963871002, |
|
"learning_rate": 8.343558282208588e-05, |
|
"loss": 2.1586, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 0.6097560975609756, |
|
"grad_norm": 0.13957522809505463, |
|
"learning_rate": 7.85276073619632e-05, |
|
"loss": 2.1926, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.6341463414634146, |
|
"grad_norm": 0.17832429707050323, |
|
"learning_rate": 7.361963190184049e-05, |
|
"loss": 2.1349, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 0.6585365853658537, |
|
"grad_norm": 0.18703627586364746, |
|
"learning_rate": 6.87116564417178e-05, |
|
"loss": 2.1496, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 0.6829268292682927, |
|
"grad_norm": 0.17039725184440613, |
|
"learning_rate": 6.380368098159509e-05, |
|
"loss": 2.1705, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 0.7073170731707317, |
|
"grad_norm": 0.16600735485553741, |
|
"learning_rate": 5.88957055214724e-05, |
|
"loss": 2.1669, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 0.7317073170731707, |
|
"grad_norm": 0.18191538751125336, |
|
"learning_rate": 5.3987730061349695e-05, |
|
"loss": 2.1634, |
|
"step": 600 |
|
} |
|
], |
|
"logging_steps": 20, |
|
"max_steps": 820, |
|
"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": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.49441038516224e+17, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|