|
{ |
|
"best_metric": NaN, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-25", |
|
"epoch": 0.05536332179930796, |
|
"eval_steps": 25, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0011072664359861593, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 3.4832, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0011072664359861593, |
|
"eval_loss": NaN, |
|
"eval_runtime": 74.4584, |
|
"eval_samples_per_second": 81.71, |
|
"eval_steps_per_second": 10.22, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0022145328719723185, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0033217993079584776, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.989294616193017e-05, |
|
"loss": 0.0, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.004429065743944637, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.957224306869053e-05, |
|
"loss": 0.0, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.005536332179930796, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.903926402016153e-05, |
|
"loss": 0.0, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.006643598615916955, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.829629131445342e-05, |
|
"loss": 0.0, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.007750865051903114, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.73465064747553e-05, |
|
"loss": 0.0, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.008858131487889274, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.619397662556435e-05, |
|
"loss": 0.0, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.009965397923875432, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.484363707663442e-05, |
|
"loss": 0.0, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.011072664359861591, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.330127018922194e-05, |
|
"loss": 0.0, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.01217993079584775, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.157348061512727e-05, |
|
"loss": 0.0, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.01328719723183391, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.966766701456177e-05, |
|
"loss": 0.0, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.01439446366782007, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.759199037394887e-05, |
|
"loss": 0.0, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.015501730103806228, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.535533905932738e-05, |
|
"loss": 0.0, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.01660899653979239, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.296729075500344e-05, |
|
"loss": 0.0, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.017716262975778548, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.043807145043604e-05, |
|
"loss": 0.0, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.018823529411764704, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.777851165098012e-05, |
|
"loss": 0.0, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.019930795847750864, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.500000000000001e-05, |
|
"loss": 0.0, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.021038062283737023, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.211443451095007e-05, |
|
"loss": 0.0, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.022145328719723183, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.91341716182545e-05, |
|
"loss": 0.0, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.023252595155709342, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.607197326515808e-05, |
|
"loss": 0.0, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.0243598615916955, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.294095225512603e-05, |
|
"loss": 0.0, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.02546712802768166, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.9754516100806423e-05, |
|
"loss": 0.0, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.02657439446366782, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.6526309611002594e-05, |
|
"loss": 0.0, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.02768166089965398, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.327015646150716e-05, |
|
"loss": 0.0, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.02768166089965398, |
|
"eval_loss": NaN, |
|
"eval_runtime": 74.6587, |
|
"eval_samples_per_second": 81.491, |
|
"eval_steps_per_second": 10.193, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.02878892733564014, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.0298961937716263, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.6729843538492847e-05, |
|
"loss": 0.0, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.031003460207612455, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.347369038899744e-05, |
|
"loss": 0.0, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.03211072664359862, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.0245483899193595e-05, |
|
"loss": 0.0, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.03321799307958478, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.705904774487396e-05, |
|
"loss": 0.0, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.03432525951557094, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.392802673484193e-05, |
|
"loss": 0.0, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.035432525951557096, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.086582838174551e-05, |
|
"loss": 0.0, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.036539792387543256, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.7885565489049946e-05, |
|
"loss": 0.0, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.03764705882352941, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.500000000000001e-05, |
|
"loss": 0.0, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.03875432525951557, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.2221488349019903e-05, |
|
"loss": 0.0, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.03986159169550173, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.9561928549563968e-05, |
|
"loss": 0.0, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.04096885813148789, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.703270924499656e-05, |
|
"loss": 0.0, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.042076124567474046, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.4644660940672627e-05, |
|
"loss": 0.0, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.043183391003460206, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.2408009626051137e-05, |
|
"loss": 0.0, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.044290657439446365, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.0332332985438248e-05, |
|
"loss": 0.0, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.045397923875432525, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.426519384872733e-06, |
|
"loss": 0.0, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.046505190311418684, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.698729810778065e-06, |
|
"loss": 0.0, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.047612456747404844, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.156362923365588e-06, |
|
"loss": 0.0, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.048719723183391, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.8060233744356633e-06, |
|
"loss": 0.0, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.04982698961937716, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.653493525244721e-06, |
|
"loss": 0.0, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.05093425605536332, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.70370868554659e-06, |
|
"loss": 0.0, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.05204152249134948, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.607359798384785e-07, |
|
"loss": 0.0, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.05314878892733564, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.277569313094809e-07, |
|
"loss": 0.0, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.0542560553633218, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.0705383806982606e-07, |
|
"loss": 0.0, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.05536332179930796, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0, |
|
"loss": 0.0, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.05536332179930796, |
|
"eval_loss": NaN, |
|
"eval_runtime": 74.8418, |
|
"eval_samples_per_second": 81.291, |
|
"eval_steps_per_second": 10.168, |
|
"step": 50 |
|
} |
|
], |
|
"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": 1 |
|
} |
|
}, |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.1184730655005082e+17, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|