| { | |
| "best_metric": 1.9444246292114258, | |
| "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": 1.6482079029083252, | |
| "learning_rate": 5e-05, | |
| "loss": 2.656, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0730593607305936, | |
| "eval_loss": 2.7438390254974365, | |
| "eval_runtime": 0.9774, | |
| "eval_samples_per_second": 51.154, | |
| "eval_steps_per_second": 13.3, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1461187214611872, | |
| "grad_norm": 1.9226343631744385, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7281, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2191780821917808, | |
| "grad_norm": 1.4800227880477905, | |
| "learning_rate": 9.986128001799077e-05, | |
| "loss": 2.6887, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2922374429223744, | |
| "grad_norm": 1.1125712394714355, | |
| "learning_rate": 9.94459753267812e-05, | |
| "loss": 2.4225, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.365296803652968, | |
| "grad_norm": 1.1823503971099854, | |
| "learning_rate": 9.875664641789545e-05, | |
| "loss": 2.3918, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4383561643835616, | |
| "grad_norm": 0.8967756032943726, | |
| "learning_rate": 9.779754323328192e-05, | |
| "loss": 2.3929, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5114155251141552, | |
| "grad_norm": 0.7958990931510925, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.2641, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5844748858447488, | |
| "grad_norm": 0.6753748655319214, | |
| "learning_rate": 9.509529358847655e-05, | |
| "loss": 2.2993, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6575342465753424, | |
| "grad_norm": 0.7301414608955383, | |
| "learning_rate": 9.336880739593416e-05, | |
| "loss": 2.2233, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.730593607305936, | |
| "grad_norm": 0.687423050403595, | |
| "learning_rate": 9.140576474687264e-05, | |
| "loss": 2.2194, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8036529680365296, | |
| "grad_norm": 0.5609395503997803, | |
| "learning_rate": 8.921826845200139e-05, | |
| "loss": 2.1855, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8767123287671232, | |
| "grad_norm": 0.5811583399772644, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.2311, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9497716894977168, | |
| "grad_norm": 0.7160845994949341, | |
| "learning_rate": 8.422516217485826e-05, | |
| "loss": 2.1034, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.045662100456621, | |
| "grad_norm": 0.9691987633705139, | |
| "learning_rate": 8.14503363531613e-05, | |
| "loss": 3.6047, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.1187214611872145, | |
| "grad_norm": 0.5950197577476501, | |
| "learning_rate": 7.85124354122177e-05, | |
| "loss": 2.0689, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.191780821917808, | |
| "grad_norm": 0.6271862387657166, | |
| "learning_rate": 7.542957248827961e-05, | |
| "loss": 2.0355, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.2648401826484017, | |
| "grad_norm": 0.6004878878593445, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.9554, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.3378995433789953, | |
| "grad_norm": 0.6051047444343567, | |
| "learning_rate": 6.890576474687263e-05, | |
| "loss": 2.1242, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.410958904109589, | |
| "grad_norm": 0.5908260345458984, | |
| "learning_rate": 6.550504137351576e-05, | |
| "loss": 2.01, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.4840182648401825, | |
| "grad_norm": 0.6053179502487183, | |
| "learning_rate": 6.203955092681039e-05, | |
| "loss": 1.6291, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.5570776255707761, | |
| "grad_norm": 0.7734953165054321, | |
| "learning_rate": 5.8530659307753036e-05, | |
| "loss": 2.283, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.6301369863013697, | |
| "grad_norm": 0.7120858430862427, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.0543, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.7031963470319633, | |
| "grad_norm": 0.718116283416748, | |
| "learning_rate": 5.1469340692246995e-05, | |
| "loss": 1.637, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.776255707762557, | |
| "grad_norm": 0.7466245293617249, | |
| "learning_rate": 4.7960449073189606e-05, | |
| "loss": 2.0311, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.8493150684931505, | |
| "grad_norm": 0.7178733348846436, | |
| "learning_rate": 4.4494958626484276e-05, | |
| "loss": 1.9781, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.8493150684931505, | |
| "eval_loss": 1.9444246292114258, | |
| "eval_runtime": 0.975, | |
| "eval_samples_per_second": 51.282, | |
| "eval_steps_per_second": 13.333, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.9223744292237441, | |
| "grad_norm": 0.9402605891227722, | |
| "learning_rate": 4.109423525312738e-05, | |
| "loss": 2.0855, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.018264840182648, | |
| "grad_norm": 1.2514342069625854, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 2.9363, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.091324200913242, | |
| "grad_norm": 0.7443793416023254, | |
| "learning_rate": 3.45704275117204e-05, | |
| "loss": 1.8411, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.1643835616438354, | |
| "grad_norm": 0.7808946371078491, | |
| "learning_rate": 3.1487564587782306e-05, | |
| "loss": 1.8517, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.237442922374429, | |
| "grad_norm": 0.7538257837295532, | |
| "learning_rate": 2.854966364683872e-05, | |
| "loss": 1.5841, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.3105022831050226, | |
| "grad_norm": 0.8428553342819214, | |
| "learning_rate": 2.577483782514174e-05, | |
| "loss": 2.0184, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.383561643835616, | |
| "grad_norm": 0.8057328462600708, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.829, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.45662100456621, | |
| "grad_norm": 0.8969247937202454, | |
| "learning_rate": 2.0781731547998614e-05, | |
| "loss": 1.6691, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.5296803652968034, | |
| "grad_norm": 0.9457578063011169, | |
| "learning_rate": 1.8594235253127375e-05, | |
| "loss": 1.8235, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.602739726027397, | |
| "grad_norm": 0.9133532643318176, | |
| "learning_rate": 1.6631192604065855e-05, | |
| "loss": 1.8459, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.6757990867579906, | |
| "grad_norm": 0.8409977555274963, | |
| "learning_rate": 1.490470641152345e-05, | |
| "loss": 1.6627, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.748858447488584, | |
| "grad_norm": 0.9554385542869568, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.7595, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.821917808219178, | |
| "grad_norm": 0.9131757020950317, | |
| "learning_rate": 1.2202456766718093e-05, | |
| "loss": 1.7983, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.8949771689497714, | |
| "grad_norm": 0.9879626631736755, | |
| "learning_rate": 1.1243353582104556e-05, | |
| "loss": 1.741, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.968036529680365, | |
| "grad_norm": 1.428398847579956, | |
| "learning_rate": 1.0554024673218807e-05, | |
| "loss": 2.4764, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.0639269406392695, | |
| "grad_norm": 1.055842399597168, | |
| "learning_rate": 1.0138719982009242e-05, | |
| "loss": 1.9769, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 3.136986301369863, | |
| "grad_norm": 0.9232267141342163, | |
| "learning_rate": 1e-05, | |
| "loss": 1.7724, | |
| "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 | |
| } | |