| { | |
| "best_metric": 1.9449502229690552, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.136986301369863, | |
| "eval_steps": 25, | |
| "global_step": 42, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0730593607305936, | |
| "grad_norm": 1.630955696105957, | |
| "learning_rate": 5e-05, | |
| "loss": 2.656, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0730593607305936, | |
| "eval_loss": 2.7438390254974365, | |
| "eval_runtime": 0.9832, | |
| "eval_samples_per_second": 50.855, | |
| "eval_steps_per_second": 13.222, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1461187214611872, | |
| "grad_norm": 1.9037554264068604, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7281, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2191780821917808, | |
| "grad_norm": 1.482515811920166, | |
| "learning_rate": 9.986128001799077e-05, | |
| "loss": 2.6894, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2922374429223744, | |
| "grad_norm": 1.0775504112243652, | |
| "learning_rate": 9.94459753267812e-05, | |
| "loss": 2.4234, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.365296803652968, | |
| "grad_norm": 1.1510299444198608, | |
| "learning_rate": 9.875664641789545e-05, | |
| "loss": 2.3912, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4383561643835616, | |
| "grad_norm": 0.8954657912254333, | |
| "learning_rate": 9.779754323328192e-05, | |
| "loss": 2.3933, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5114155251141552, | |
| "grad_norm": 0.7784850597381592, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.2629, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5844748858447488, | |
| "grad_norm": 0.6699449419975281, | |
| "learning_rate": 9.509529358847655e-05, | |
| "loss": 2.2983, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6575342465753424, | |
| "grad_norm": 0.7167125344276428, | |
| "learning_rate": 9.336880739593416e-05, | |
| "loss": 2.2229, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.730593607305936, | |
| "grad_norm": 0.6821659207344055, | |
| "learning_rate": 9.140576474687264e-05, | |
| "loss": 2.2196, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8036529680365296, | |
| "grad_norm": 0.5606189370155334, | |
| "learning_rate": 8.921826845200139e-05, | |
| "loss": 2.1865, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8767123287671232, | |
| "grad_norm": 0.5747855305671692, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.2302, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9497716894977168, | |
| "grad_norm": 0.7128291726112366, | |
| "learning_rate": 8.422516217485826e-05, | |
| "loss": 2.105, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.045662100456621, | |
| "grad_norm": 0.9701964259147644, | |
| "learning_rate": 8.14503363531613e-05, | |
| "loss": 3.6055, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.1187214611872145, | |
| "grad_norm": 0.544215977191925, | |
| "learning_rate": 7.85124354122177e-05, | |
| "loss": 2.0683, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.191780821917808, | |
| "grad_norm": 0.6170773506164551, | |
| "learning_rate": 7.542957248827961e-05, | |
| "loss": 2.0378, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.2648401826484017, | |
| "grad_norm": 0.5937121510505676, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.9573, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.3378995433789953, | |
| "grad_norm": 0.5988708734512329, | |
| "learning_rate": 6.890576474687263e-05, | |
| "loss": 2.1244, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.410958904109589, | |
| "grad_norm": 0.5857730507850647, | |
| "learning_rate": 6.550504137351576e-05, | |
| "loss": 2.013, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.4840182648401825, | |
| "grad_norm": 0.6009112596511841, | |
| "learning_rate": 6.203955092681039e-05, | |
| "loss": 1.6306, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.5570776255707761, | |
| "grad_norm": 0.7636632919311523, | |
| "learning_rate": 5.8530659307753036e-05, | |
| "loss": 2.2839, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.6301369863013697, | |
| "grad_norm": 0.7096514701843262, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.0574, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.7031963470319633, | |
| "grad_norm": 0.6771715879440308, | |
| "learning_rate": 5.1469340692246995e-05, | |
| "loss": 1.6397, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.776255707762557, | |
| "grad_norm": 0.7442609071731567, | |
| "learning_rate": 4.7960449073189606e-05, | |
| "loss": 2.0326, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.8493150684931505, | |
| "grad_norm": 0.717400074005127, | |
| "learning_rate": 4.4494958626484276e-05, | |
| "loss": 1.9805, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.8493150684931505, | |
| "eval_loss": 1.9449502229690552, | |
| "eval_runtime": 0.9766, | |
| "eval_samples_per_second": 51.196, | |
| "eval_steps_per_second": 13.311, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.9223744292237441, | |
| "grad_norm": 0.9425220489501953, | |
| "learning_rate": 4.109423525312738e-05, | |
| "loss": 2.0892, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.018264840182648, | |
| "grad_norm": 1.2423070669174194, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 2.944, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.091324200913242, | |
| "grad_norm": 0.7437182068824768, | |
| "learning_rate": 3.45704275117204e-05, | |
| "loss": 1.8443, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.1643835616438354, | |
| "grad_norm": 0.7723404765129089, | |
| "learning_rate": 3.1487564587782306e-05, | |
| "loss": 1.8569, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.237442922374429, | |
| "grad_norm": 0.7458028793334961, | |
| "learning_rate": 2.854966364683872e-05, | |
| "loss": 1.5894, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.3105022831050226, | |
| "grad_norm": 0.8333907723426819, | |
| "learning_rate": 2.577483782514174e-05, | |
| "loss": 2.0206, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.383561643835616, | |
| "grad_norm": 0.7999001145362854, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.8319, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.45662100456621, | |
| "grad_norm": 0.8819563388824463, | |
| "learning_rate": 2.0781731547998614e-05, | |
| "loss": 1.6749, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.5296803652968034, | |
| "grad_norm": 0.9369629621505737, | |
| "learning_rate": 1.8594235253127375e-05, | |
| "loss": 1.8284, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.602739726027397, | |
| "grad_norm": 0.9049533605575562, | |
| "learning_rate": 1.6631192604065855e-05, | |
| "loss": 1.8499, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.6757990867579906, | |
| "grad_norm": 0.8291096091270447, | |
| "learning_rate": 1.490470641152345e-05, | |
| "loss": 1.6656, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.748858447488584, | |
| "grad_norm": 0.933771550655365, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.7633, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.821917808219178, | |
| "grad_norm": 0.9030247330665588, | |
| "learning_rate": 1.2202456766718093e-05, | |
| "loss": 1.8017, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.8949771689497714, | |
| "grad_norm": 0.9774025678634644, | |
| "learning_rate": 1.1243353582104556e-05, | |
| "loss": 1.7459, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.968036529680365, | |
| "grad_norm": 1.4044599533081055, | |
| "learning_rate": 1.0554024673218807e-05, | |
| "loss": 2.4792, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.0639269406392695, | |
| "grad_norm": 1.0370107889175415, | |
| "learning_rate": 1.0138719982009242e-05, | |
| "loss": 1.9816, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 3.136986301369863, | |
| "grad_norm": 0.9146576523780823, | |
| "learning_rate": 1e-05, | |
| "loss": 1.7765, | |
| "step": 42 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 42, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 1.3648395138760704e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |