|
{ |
|
"best_metric": 3.04049015045166, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-25", |
|
"epoch": 0.3249390739236393, |
|
"eval_steps": 25, |
|
"global_step": 25, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.012997562956945572, |
|
"grad_norm": 2.1815783977508545, |
|
"learning_rate": 5e-05, |
|
"loss": 4.2735, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.012997562956945572, |
|
"eval_loss": 4.643681526184082, |
|
"eval_runtime": 4.5171, |
|
"eval_samples_per_second": 114.898, |
|
"eval_steps_per_second": 14.39, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.025995125913891144, |
|
"grad_norm": 2.4761829376220703, |
|
"learning_rate": 0.0001, |
|
"loss": 4.3582, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.03899268887083672, |
|
"grad_norm": 2.5254948139190674, |
|
"learning_rate": 9.989294616193017e-05, |
|
"loss": 4.4128, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.05199025182778229, |
|
"grad_norm": 2.0806477069854736, |
|
"learning_rate": 9.957224306869053e-05, |
|
"loss": 4.1466, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.06498781478472786, |
|
"grad_norm": 1.82292902469635, |
|
"learning_rate": 9.903926402016153e-05, |
|
"loss": 3.8892, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.07798537774167344, |
|
"grad_norm": 1.9830964803695679, |
|
"learning_rate": 9.829629131445342e-05, |
|
"loss": 3.8104, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.09098294069861901, |
|
"grad_norm": 1.7637877464294434, |
|
"learning_rate": 9.73465064747553e-05, |
|
"loss": 3.6088, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.10398050365556458, |
|
"grad_norm": 1.730930209159851, |
|
"learning_rate": 9.619397662556435e-05, |
|
"loss": 3.4998, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.11697806661251016, |
|
"grad_norm": 1.2427796125411987, |
|
"learning_rate": 9.484363707663442e-05, |
|
"loss": 3.4402, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.12997562956945571, |
|
"grad_norm": 1.4184691905975342, |
|
"learning_rate": 9.330127018922194e-05, |
|
"loss": 3.3537, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.1429731925264013, |
|
"grad_norm": 1.116524577140808, |
|
"learning_rate": 9.157348061512727e-05, |
|
"loss": 3.361, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.15597075548334688, |
|
"grad_norm": 1.3125693798065186, |
|
"learning_rate": 8.966766701456177e-05, |
|
"loss": 3.3196, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.16896831844029245, |
|
"grad_norm": 1.5652897357940674, |
|
"learning_rate": 8.759199037394887e-05, |
|
"loss": 3.3531, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.18196588139723802, |
|
"grad_norm": 1.2380902767181396, |
|
"learning_rate": 8.535533905932738e-05, |
|
"loss": 3.3461, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.19496344435418358, |
|
"grad_norm": 0.9211981892585754, |
|
"learning_rate": 8.296729075500344e-05, |
|
"loss": 3.2463, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.20796100731112915, |
|
"grad_norm": 1.0457210540771484, |
|
"learning_rate": 8.043807145043604e-05, |
|
"loss": 3.2257, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.22095857026807472, |
|
"grad_norm": 1.1892938613891602, |
|
"learning_rate": 7.777851165098012e-05, |
|
"loss": 3.1579, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.23395613322502032, |
|
"grad_norm": 1.3801074028015137, |
|
"learning_rate": 7.500000000000001e-05, |
|
"loss": 3.1586, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.2469536961819659, |
|
"grad_norm": 1.560684323310852, |
|
"learning_rate": 7.211443451095007e-05, |
|
"loss": 3.1782, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.25995125913891143, |
|
"grad_norm": 1.7278943061828613, |
|
"learning_rate": 6.91341716182545e-05, |
|
"loss": 3.0888, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.272948822095857, |
|
"grad_norm": 1.8793681859970093, |
|
"learning_rate": 6.607197326515808e-05, |
|
"loss": 3.0725, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.2859463850528026, |
|
"grad_norm": 1.8100998401641846, |
|
"learning_rate": 6.294095225512603e-05, |
|
"loss": 3.1031, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.29894394800974816, |
|
"grad_norm": 1.5798654556274414, |
|
"learning_rate": 5.9754516100806423e-05, |
|
"loss": 2.9822, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.31194151096669376, |
|
"grad_norm": 1.183044195175171, |
|
"learning_rate": 5.6526309611002594e-05, |
|
"loss": 3.0436, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.3249390739236393, |
|
"grad_norm": 0.942845344543457, |
|
"learning_rate": 5.327015646150716e-05, |
|
"loss": 2.9858, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.3249390739236393, |
|
"eval_loss": 3.04049015045166, |
|
"eval_runtime": 4.5118, |
|
"eval_samples_per_second": 115.032, |
|
"eval_steps_per_second": 14.407, |
|
"step": 25 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 50, |
|
"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": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 3.91521434075136e+16, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|