| { | |
| "best_metric": 2.0112826824188232, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.008557980316645272, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00017115960633290543, | |
| "grad_norm": 0.3384851813316345, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 2.1057, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017115960633290543, | |
| "eval_loss": 2.140085220336914, | |
| "eval_runtime": 252.4143, | |
| "eval_samples_per_second": 38.984, | |
| "eval_steps_per_second": 19.492, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00034231921266581085, | |
| "grad_norm": 0.3000636100769043, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 2.0679, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005134788189987163, | |
| "grad_norm": 0.31949612498283386, | |
| "learning_rate": 1e-05, | |
| "loss": 2.2765, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006846384253316217, | |
| "grad_norm": 0.2581222355365753, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 1.8811, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008557980316645272, | |
| "grad_norm": 0.2666412889957428, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 2.021, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0010269576379974327, | |
| "grad_norm": 0.26130983233451843, | |
| "learning_rate": 2e-05, | |
| "loss": 1.8714, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011981172443303381, | |
| "grad_norm": 0.22150737047195435, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 1.7815, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013692768506632434, | |
| "grad_norm": 0.25391674041748047, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 2.0571, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015404364569961489, | |
| "grad_norm": 0.2351103127002716, | |
| "learning_rate": 3e-05, | |
| "loss": 1.7819, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0017115960633290544, | |
| "grad_norm": 0.24356381595134735, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.9668, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0018827556696619598, | |
| "grad_norm": 0.25410857796669006, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 2.0877, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0020539152759948653, | |
| "grad_norm": 0.2615646719932556, | |
| "learning_rate": 4e-05, | |
| "loss": 2.0598, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002225074882327771, | |
| "grad_norm": 0.24895967543125153, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 2.0459, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0023962344886606763, | |
| "grad_norm": 0.24129140377044678, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 2.1703, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0025673940949935813, | |
| "grad_norm": 0.21726980805397034, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0914, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002738553701326487, | |
| "grad_norm": 0.20076154172420502, | |
| "learning_rate": 5.333333333333333e-05, | |
| "loss": 1.9858, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0029097133076593923, | |
| "grad_norm": 0.15559637546539307, | |
| "learning_rate": 5.666666666666667e-05, | |
| "loss": 1.8849, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0030808729139922978, | |
| "grad_norm": 0.16304416954517365, | |
| "learning_rate": 6e-05, | |
| "loss": 2.1007, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0032520325203252032, | |
| "grad_norm": 0.15507805347442627, | |
| "learning_rate": 6.333333333333333e-05, | |
| "loss": 2.0215, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0034231921266581087, | |
| "grad_norm": 0.1489063948392868, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 2.0716, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003594351732991014, | |
| "grad_norm": 0.15571531653404236, | |
| "learning_rate": 7e-05, | |
| "loss": 1.9169, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0037655113393239197, | |
| "grad_norm": 0.15557806193828583, | |
| "learning_rate": 7.333333333333333e-05, | |
| "loss": 1.996, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.003936670945656825, | |
| "grad_norm": 0.17348982393741608, | |
| "learning_rate": 7.666666666666667e-05, | |
| "loss": 2.0536, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004107830551989731, | |
| "grad_norm": 0.16075366735458374, | |
| "learning_rate": 8e-05, | |
| "loss": 2.0326, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004278990158322636, | |
| "grad_norm": 0.1705283671617508, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 2.0816, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004450149764655542, | |
| "grad_norm": 0.1489923745393753, | |
| "learning_rate": 8.666666666666667e-05, | |
| "loss": 1.9582, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.004621309370988447, | |
| "grad_norm": 0.15770766139030457, | |
| "learning_rate": 9e-05, | |
| "loss": 2.1467, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004792468977321353, | |
| "grad_norm": 0.13497239351272583, | |
| "learning_rate": 9.333333333333334e-05, | |
| "loss": 1.9728, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.004963628583654257, | |
| "grad_norm": 0.14810675382614136, | |
| "learning_rate": 9.666666666666667e-05, | |
| "loss": 2.0339, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.005134788189987163, | |
| "grad_norm": 0.12770140171051025, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9108, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005305947796320068, | |
| "grad_norm": 0.14340223371982574, | |
| "learning_rate": 9.999146252290264e-05, | |
| "loss": 1.9649, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.005477107402652974, | |
| "grad_norm": 0.13468272984027863, | |
| "learning_rate": 9.996585300715116e-05, | |
| "loss": 1.9385, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.005648267008985879, | |
| "grad_norm": 0.1366954743862152, | |
| "learning_rate": 9.99231801983717e-05, | |
| "loss": 1.9931, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.005819426615318785, | |
| "grad_norm": 0.12960107624530792, | |
| "learning_rate": 9.986345866928941e-05, | |
| "loss": 1.7814, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.00599058622165169, | |
| "grad_norm": 0.13072721660137177, | |
| "learning_rate": 9.978670881475172e-05, | |
| "loss": 1.9877, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0061617458279845955, | |
| "grad_norm": 0.14742650091648102, | |
| "learning_rate": 9.96929568447637e-05, | |
| "loss": 2.0895, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.006332905434317501, | |
| "grad_norm": 0.1375843733549118, | |
| "learning_rate": 9.958223477553714e-05, | |
| "loss": 1.9882, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0065040650406504065, | |
| "grad_norm": 0.1338900923728943, | |
| "learning_rate": 9.94545804185573e-05, | |
| "loss": 2.1235, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.006675224646983312, | |
| "grad_norm": 0.139565572142601, | |
| "learning_rate": 9.931003736767013e-05, | |
| "loss": 1.9161, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0068463842533162175, | |
| "grad_norm": 0.1471727341413498, | |
| "learning_rate": 9.91486549841951e-05, | |
| "loss": 1.8279, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007017543859649123, | |
| "grad_norm": 0.14104895293712616, | |
| "learning_rate": 9.89704883800683e-05, | |
| "loss": 1.9517, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.007188703465982028, | |
| "grad_norm": 0.14945568144321442, | |
| "learning_rate": 9.877559839902184e-05, | |
| "loss": 1.8598, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.007359863072314934, | |
| "grad_norm": 0.16899332404136658, | |
| "learning_rate": 9.85640515958057e-05, | |
| "loss": 2.0511, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.007531022678647839, | |
| "grad_norm": 0.16674430668354034, | |
| "learning_rate": 9.833592021345937e-05, | |
| "loss": 2.0885, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.007702182284980745, | |
| "grad_norm": 0.1767071783542633, | |
| "learning_rate": 9.809128215864097e-05, | |
| "loss": 2.0406, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00787334189131365, | |
| "grad_norm": 0.183282271027565, | |
| "learning_rate": 9.783022097502204e-05, | |
| "loss": 1.8779, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.008044501497646555, | |
| "grad_norm": 0.22200380265712738, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.8805, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.008215661103979461, | |
| "grad_norm": 0.2835330367088318, | |
| "learning_rate": 9.725919140804099e-05, | |
| "loss": 2.1045, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.008386820710312366, | |
| "grad_norm": 0.6013146638870239, | |
| "learning_rate": 9.694941803075283e-05, | |
| "loss": 2.1857, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.008557980316645272, | |
| "grad_norm": 0.7531317472457886, | |
| "learning_rate": 9.662361147021779e-05, | |
| "loss": 2.1909, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008557980316645272, | |
| "eval_loss": 2.0112826824188232, | |
| "eval_runtime": 253.1487, | |
| "eval_samples_per_second": 38.87, | |
| "eval_steps_per_second": 19.435, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 1928297315303424.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |