|
{ |
|
"best_metric": 0.23422786593437195, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-50", |
|
"epoch": 0.8298755186721992, |
|
"eval_steps": 25, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.016597510373443983, |
|
"grad_norm": 0.8566427826881409, |
|
"learning_rate": 5e-06, |
|
"loss": 1.3612, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.016597510373443983, |
|
"eval_loss": 0.433116614818573, |
|
"eval_runtime": 38.1295, |
|
"eval_samples_per_second": 2.675, |
|
"eval_steps_per_second": 0.341, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.03319502074688797, |
|
"grad_norm": 0.7513838410377502, |
|
"learning_rate": 1e-05, |
|
"loss": 1.9834, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.04979253112033195, |
|
"grad_norm": 0.7404050827026367, |
|
"learning_rate": 1.5e-05, |
|
"loss": 1.1839, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.06639004149377593, |
|
"grad_norm": 0.8764183521270752, |
|
"learning_rate": 2e-05, |
|
"loss": 1.3947, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.08298755186721991, |
|
"grad_norm": 0.8077886700630188, |
|
"learning_rate": 2.5e-05, |
|
"loss": 1.2916, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.0995850622406639, |
|
"grad_norm": 0.9004972577095032, |
|
"learning_rate": 3e-05, |
|
"loss": 1.6755, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.11618257261410789, |
|
"grad_norm": 0.9186983108520508, |
|
"learning_rate": 3.5e-05, |
|
"loss": 1.2001, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.13278008298755187, |
|
"grad_norm": 0.8388381004333496, |
|
"learning_rate": 4e-05, |
|
"loss": 1.5173, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.14937759336099585, |
|
"grad_norm": 0.6618286967277527, |
|
"learning_rate": 4.5e-05, |
|
"loss": 0.8895, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.16597510373443983, |
|
"grad_norm": 0.609593391418457, |
|
"learning_rate": 5e-05, |
|
"loss": 0.9865, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.1825726141078838, |
|
"grad_norm": 0.657666802406311, |
|
"learning_rate": 5.500000000000001e-05, |
|
"loss": 0.9409, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.1991701244813278, |
|
"grad_norm": 0.6308622360229492, |
|
"learning_rate": 6e-05, |
|
"loss": 0.7595, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.2157676348547718, |
|
"grad_norm": 0.6136456727981567, |
|
"learning_rate": 6.500000000000001e-05, |
|
"loss": 0.8264, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.23236514522821577, |
|
"grad_norm": 0.647283673286438, |
|
"learning_rate": 7e-05, |
|
"loss": 0.6253, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.24896265560165975, |
|
"grad_norm": 0.611138105392456, |
|
"learning_rate": 7.500000000000001e-05, |
|
"loss": 0.6837, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.26556016597510373, |
|
"grad_norm": 0.49807682633399963, |
|
"learning_rate": 8e-05, |
|
"loss": 0.5476, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.2821576763485477, |
|
"grad_norm": 0.7244577407836914, |
|
"learning_rate": 8.5e-05, |
|
"loss": 0.5216, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.2987551867219917, |
|
"grad_norm": 0.7856899499893188, |
|
"learning_rate": 9e-05, |
|
"loss": 0.6427, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.3153526970954357, |
|
"grad_norm": 0.6447245478630066, |
|
"learning_rate": 9.5e-05, |
|
"loss": 0.5674, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.33195020746887965, |
|
"grad_norm": 0.8941850066184998, |
|
"learning_rate": 0.0001, |
|
"loss": 0.4936, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.34854771784232363, |
|
"grad_norm": 0.7632863521575928, |
|
"learning_rate": 9.972609476841367e-05, |
|
"loss": 0.5072, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.3651452282157676, |
|
"grad_norm": 0.742627739906311, |
|
"learning_rate": 9.890738003669029e-05, |
|
"loss": 1.59, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.3817427385892116, |
|
"grad_norm": 0.5677568316459656, |
|
"learning_rate": 9.755282581475769e-05, |
|
"loss": 0.4986, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.3983402489626556, |
|
"grad_norm": 0.47893428802490234, |
|
"learning_rate": 9.567727288213005e-05, |
|
"loss": 0.4859, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.4149377593360996, |
|
"grad_norm": 0.3274975121021271, |
|
"learning_rate": 9.330127018922194e-05, |
|
"loss": 0.7008, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.4149377593360996, |
|
"eval_loss": 0.2505565285682678, |
|
"eval_runtime": 38.4539, |
|
"eval_samples_per_second": 2.653, |
|
"eval_steps_per_second": 0.338, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.4315352697095436, |
|
"grad_norm": 0.5019552111625671, |
|
"learning_rate": 9.045084971874738e-05, |
|
"loss": 1.2942, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.44813278008298757, |
|
"grad_norm": 0.37283846735954285, |
|
"learning_rate": 8.715724127386972e-05, |
|
"loss": 0.8131, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.46473029045643155, |
|
"grad_norm": 0.32147935032844543, |
|
"learning_rate": 8.345653031794292e-05, |
|
"loss": 0.452, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.48132780082987553, |
|
"grad_norm": 0.40596452355384827, |
|
"learning_rate": 7.938926261462366e-05, |
|
"loss": 0.7471, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.4979253112033195, |
|
"grad_norm": 0.31123867630958557, |
|
"learning_rate": 7.500000000000001e-05, |
|
"loss": 1.1211, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.5145228215767634, |
|
"grad_norm": 0.3040826916694641, |
|
"learning_rate": 7.033683215379002e-05, |
|
"loss": 0.6645, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.5311203319502075, |
|
"grad_norm": 0.360746830701828, |
|
"learning_rate": 6.545084971874738e-05, |
|
"loss": 0.5069, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.5477178423236515, |
|
"grad_norm": 0.28188955783843994, |
|
"learning_rate": 6.0395584540887963e-05, |
|
"loss": 0.374, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.5643153526970954, |
|
"grad_norm": 0.352664977312088, |
|
"learning_rate": 5.522642316338268e-05, |
|
"loss": 0.5923, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.5809128630705395, |
|
"grad_norm": 0.4458906054496765, |
|
"learning_rate": 5e-05, |
|
"loss": 0.9785, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.5975103734439834, |
|
"grad_norm": 0.37693920731544495, |
|
"learning_rate": 4.477357683661734e-05, |
|
"loss": 0.4362, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.6141078838174274, |
|
"grad_norm": 0.6866313219070435, |
|
"learning_rate": 3.960441545911204e-05, |
|
"loss": 0.8713, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.6307053941908713, |
|
"grad_norm": 0.5577489733695984, |
|
"learning_rate": 3.4549150281252636e-05, |
|
"loss": 0.5318, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.6473029045643154, |
|
"grad_norm": 0.31835877895355225, |
|
"learning_rate": 2.9663167846209998e-05, |
|
"loss": 0.4399, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.6639004149377593, |
|
"grad_norm": 0.4343944489955902, |
|
"learning_rate": 2.500000000000001e-05, |
|
"loss": 0.7351, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.6804979253112033, |
|
"grad_norm": 0.6331047415733337, |
|
"learning_rate": 2.061073738537635e-05, |
|
"loss": 0.6234, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.6970954356846473, |
|
"grad_norm": 0.2764015793800354, |
|
"learning_rate": 1.6543469682057106e-05, |
|
"loss": 0.5407, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.7136929460580913, |
|
"grad_norm": 0.28386223316192627, |
|
"learning_rate": 1.2842758726130283e-05, |
|
"loss": 1.0469, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.7302904564315352, |
|
"grad_norm": 0.31652379035949707, |
|
"learning_rate": 9.549150281252633e-06, |
|
"loss": 0.5524, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.7468879668049793, |
|
"grad_norm": 0.4024736285209656, |
|
"learning_rate": 6.698729810778065e-06, |
|
"loss": 0.6643, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.7634854771784232, |
|
"grad_norm": 0.38829195499420166, |
|
"learning_rate": 4.322727117869951e-06, |
|
"loss": 0.4115, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.7800829875518672, |
|
"grad_norm": 0.3871329426765442, |
|
"learning_rate": 2.4471741852423237e-06, |
|
"loss": 0.3885, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.7966804979253111, |
|
"grad_norm": 0.2926025986671448, |
|
"learning_rate": 1.0926199633097157e-06, |
|
"loss": 0.584, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.8132780082987552, |
|
"grad_norm": 0.2687753438949585, |
|
"learning_rate": 2.7390523158633554e-07, |
|
"loss": 0.907, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.8298755186721992, |
|
"grad_norm": 0.24473470449447632, |
|
"learning_rate": 0.0, |
|
"loss": 0.4286, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.8298755186721992, |
|
"eval_loss": 0.23422786593437195, |
|
"eval_runtime": 38.453, |
|
"eval_samples_per_second": 2.653, |
|
"eval_steps_per_second": 0.338, |
|
"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": 3, |
|
"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": 2.3699634505383936e+17, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|