|
{ |
|
"best_metric": 1.2664278745651245, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-25", |
|
"epoch": 0.015162140136080207, |
|
"eval_steps": 25, |
|
"global_step": 25, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0006064856054432083, |
|
"grad_norm": 3.9560394287109375, |
|
"learning_rate": 5e-05, |
|
"loss": 2.268, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0006064856054432083, |
|
"eval_loss": 2.7075867652893066, |
|
"eval_runtime": 2.9346, |
|
"eval_samples_per_second": 17.038, |
|
"eval_steps_per_second": 4.43, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0012129712108864166, |
|
"grad_norm": 3.552264451980591, |
|
"learning_rate": 0.0001, |
|
"loss": 2.0962, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0018194568163296249, |
|
"grad_norm": 3.2752976417541504, |
|
"learning_rate": 9.958086757163489e-05, |
|
"loss": 1.9936, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.002425942421772833, |
|
"grad_norm": 1.3922207355499268, |
|
"learning_rate": 9.833127793065098e-05, |
|
"loss": 1.5374, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.0030324280272160417, |
|
"grad_norm": 0.974947452545166, |
|
"learning_rate": 9.627450856774539e-05, |
|
"loss": 1.3778, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.0036389136326592498, |
|
"grad_norm": 1.0462532043457031, |
|
"learning_rate": 9.3448873204592e-05, |
|
"loss": 1.4328, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.004245399238102458, |
|
"grad_norm": 0.8969913125038147, |
|
"learning_rate": 8.990700808169889e-05, |
|
"loss": 1.4041, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.004851884843545666, |
|
"grad_norm": 0.943970799446106, |
|
"learning_rate": 8.571489144483944e-05, |
|
"loss": 1.4869, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.0054583704489888744, |
|
"grad_norm": 0.861596941947937, |
|
"learning_rate": 8.095061449516903e-05, |
|
"loss": 1.5613, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.006064856054432083, |
|
"grad_norm": 0.8148055672645569, |
|
"learning_rate": 7.570292669790186e-05, |
|
"loss": 1.6122, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.0066713416598752915, |
|
"grad_norm": 0.9539321660995483, |
|
"learning_rate": 7.006958254769438e-05, |
|
"loss": 1.7334, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.0072778272653184995, |
|
"grad_norm": 1.0071280002593994, |
|
"learning_rate": 6.415552058736854e-05, |
|
"loss": 1.9099, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.007884312870761708, |
|
"grad_norm": 0.8137369751930237, |
|
"learning_rate": 5.80709086014102e-05, |
|
"loss": 1.3876, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.008490798476204917, |
|
"grad_norm": 0.8395057320594788, |
|
"learning_rate": 5.192909139858981e-05, |
|
"loss": 1.0561, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.009097284081648125, |
|
"grad_norm": 0.7751932740211487, |
|
"learning_rate": 4.584447941263149e-05, |
|
"loss": 1.0989, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.009703769687091333, |
|
"grad_norm": 0.7089543342590332, |
|
"learning_rate": 3.9930417452305626e-05, |
|
"loss": 1.0819, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.01031025529253454, |
|
"grad_norm": 0.7607638835906982, |
|
"learning_rate": 3.4297073302098156e-05, |
|
"loss": 1.0064, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.010916740897977749, |
|
"grad_norm": 1.0309456586837769, |
|
"learning_rate": 2.9049385504830985e-05, |
|
"loss": 1.129, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.011523226503420959, |
|
"grad_norm": 1.016621708869934, |
|
"learning_rate": 2.4285108555160577e-05, |
|
"loss": 1.2013, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.012129712108864167, |
|
"grad_norm": 1.0528644323349, |
|
"learning_rate": 2.0092991918301108e-05, |
|
"loss": 1.277, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.012736197714307375, |
|
"grad_norm": 0.867617130279541, |
|
"learning_rate": 1.6551126795408016e-05, |
|
"loss": 1.2926, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.013342683319750583, |
|
"grad_norm": 0.9080958366394043, |
|
"learning_rate": 1.3725491432254624e-05, |
|
"loss": 1.4072, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.013949168925193791, |
|
"grad_norm": 0.8537561893463135, |
|
"learning_rate": 1.1668722069349041e-05, |
|
"loss": 1.4946, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.014555654530636999, |
|
"grad_norm": 0.6739559173583984, |
|
"learning_rate": 1.0419132428365116e-05, |
|
"loss": 1.6581, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.015162140136080207, |
|
"grad_norm": 0.7529584765434265, |
|
"learning_rate": 1e-05, |
|
"loss": 1.6946, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.015162140136080207, |
|
"eval_loss": 1.2664278745651245, |
|
"eval_runtime": 2.9983, |
|
"eval_samples_per_second": 16.676, |
|
"eval_steps_per_second": 4.336, |
|
"step": 25 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 25, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 25, |
|
"stateful_callbacks": { |
|
"EarlyStoppingCallback": { |
|
"args": { |
|
"early_stopping_patience": 1, |
|
"early_stopping_threshold": 0.0 |
|
}, |
|
"attributes": { |
|
"early_stopping_patience_counter": 0 |
|
} |
|
}, |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 2.629552387915776e+17, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|