| { | |
| "best_metric": 11.5, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.001818909381934592, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.637818763869184e-05, | |
| "grad_norm": 2.948543624370359e-05, | |
| "learning_rate": 1.0060000000000002e-05, | |
| "loss": 23.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.637818763869184e-05, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 151.3578, | |
| "eval_samples_per_second": 76.474, | |
| "eval_steps_per_second": 19.12, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.275637527738368e-05, | |
| "grad_norm": 2.2105969037511386e-05, | |
| "learning_rate": 2.0120000000000004e-05, | |
| "loss": 23.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00010913456291607552, | |
| "grad_norm": 1.7058524463209324e-05, | |
| "learning_rate": 3.018e-05, | |
| "loss": 23.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00014551275055476736, | |
| "grad_norm": 2.060344922938384e-05, | |
| "learning_rate": 4.024000000000001e-05, | |
| "loss": 23.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0001818909381934592, | |
| "grad_norm": 2.0100153051316738e-05, | |
| "learning_rate": 5.03e-05, | |
| "loss": 23.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00021826912583215103, | |
| "grad_norm": 3.034624933206942e-05, | |
| "learning_rate": 6.036e-05, | |
| "loss": 23.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00025464731347084286, | |
| "grad_norm": 2.815291918523144e-05, | |
| "learning_rate": 7.042e-05, | |
| "loss": 23.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0002910255011095347, | |
| "grad_norm": 1.748102658893913e-05, | |
| "learning_rate": 8.048000000000002e-05, | |
| "loss": 23.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00032740368874822657, | |
| "grad_norm": 3.207884219591506e-05, | |
| "learning_rate": 9.054000000000001e-05, | |
| "loss": 23.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003637818763869184, | |
| "grad_norm": 2.7205978767597117e-05, | |
| "learning_rate": 0.0001006, | |
| "loss": 23.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00040016006402561027, | |
| "grad_norm": 1.864074874902144e-05, | |
| "learning_rate": 0.00010007052631578948, | |
| "loss": 23.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00043653825166430207, | |
| "grad_norm": 2.7616073566605337e-05, | |
| "learning_rate": 9.954105263157895e-05, | |
| "loss": 23.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0004729164393029939, | |
| "grad_norm": 3.965870928368531e-05, | |
| "learning_rate": 9.901157894736842e-05, | |
| "loss": 23.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0005092946269416857, | |
| "grad_norm": 4.447407991392538e-05, | |
| "learning_rate": 9.84821052631579e-05, | |
| "loss": 23.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0005456728145803776, | |
| "grad_norm": 3.3188109227921814e-05, | |
| "learning_rate": 9.795263157894737e-05, | |
| "loss": 23.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005820510022190694, | |
| "grad_norm": 2.72152046818519e-05, | |
| "learning_rate": 9.742315789473686e-05, | |
| "loss": 23.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0006184291898577613, | |
| "grad_norm": 4.269916098564863e-05, | |
| "learning_rate": 9.689368421052633e-05, | |
| "loss": 23.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0006548073774964531, | |
| "grad_norm": 7.144509436329827e-05, | |
| "learning_rate": 9.63642105263158e-05, | |
| "loss": 23.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0006911855651351449, | |
| "grad_norm": 5.8125104260398075e-05, | |
| "learning_rate": 9.583473684210527e-05, | |
| "loss": 23.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0007275637527738368, | |
| "grad_norm": 5.5581836932105944e-05, | |
| "learning_rate": 9.530526315789474e-05, | |
| "loss": 23.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0007639419404125286, | |
| "grad_norm": 4.992326284991577e-05, | |
| "learning_rate": 9.477578947368422e-05, | |
| "loss": 23.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0008003201280512205, | |
| "grad_norm": 3.754639328690246e-05, | |
| "learning_rate": 9.424631578947369e-05, | |
| "loss": 23.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0008366983156899123, | |
| "grad_norm": 4.4129676098236814e-05, | |
| "learning_rate": 9.371684210526316e-05, | |
| "loss": 23.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0008730765033286041, | |
| "grad_norm": 3.2032086892286316e-05, | |
| "learning_rate": 9.318736842105263e-05, | |
| "loss": 23.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.000909454690967296, | |
| "grad_norm": 7.238514808705077e-05, | |
| "learning_rate": 9.26578947368421e-05, | |
| "loss": 23.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0009458328786059878, | |
| "grad_norm": 5.7584187743486837e-05, | |
| "learning_rate": 9.212842105263159e-05, | |
| "loss": 23.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0009822110662446796, | |
| "grad_norm": 7.019707845756784e-05, | |
| "learning_rate": 9.159894736842107e-05, | |
| "loss": 23.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0010185892538833714, | |
| "grad_norm": 5.2452742238529027e-05, | |
| "learning_rate": 9.106947368421054e-05, | |
| "loss": 23.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0010549674415220635, | |
| "grad_norm": 0.00011238550359848887, | |
| "learning_rate": 9.054000000000001e-05, | |
| "loss": 23.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0010913456291607553, | |
| "grad_norm": 0.00013983648386783898, | |
| "learning_rate": 9.001052631578948e-05, | |
| "loss": 23.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001127723816799447, | |
| "grad_norm": 6.872925587231293e-05, | |
| "learning_rate": 8.948105263157895e-05, | |
| "loss": 23.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0011641020044381389, | |
| "grad_norm": 5.7285513321403414e-05, | |
| "learning_rate": 8.895157894736842e-05, | |
| "loss": 23.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0012004801920768306, | |
| "grad_norm": 0.00013172421313356608, | |
| "learning_rate": 8.842210526315789e-05, | |
| "loss": 23.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0012368583797155227, | |
| "grad_norm": 8.472959598293528e-05, | |
| "learning_rate": 8.789263157894738e-05, | |
| "loss": 23.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0012732365673542145, | |
| "grad_norm": 9.260691149393097e-05, | |
| "learning_rate": 8.736315789473685e-05, | |
| "loss": 23.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0013096147549929063, | |
| "grad_norm": 0.00011570382775971666, | |
| "learning_rate": 8.683368421052632e-05, | |
| "loss": 23.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.001345992942631598, | |
| "grad_norm": 0.00013264735753182322, | |
| "learning_rate": 8.63042105263158e-05, | |
| "loss": 23.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0013823711302702899, | |
| "grad_norm": 7.428869866998866e-05, | |
| "learning_rate": 8.577473684210527e-05, | |
| "loss": 23.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0014187493179089819, | |
| "grad_norm": 9.110313112614676e-05, | |
| "learning_rate": 8.524526315789474e-05, | |
| "loss": 23.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0014551275055476737, | |
| "grad_norm": 0.00014309283869806677, | |
| "learning_rate": 8.471578947368421e-05, | |
| "loss": 23.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0014915056931863655, | |
| "grad_norm": 0.00016003995551727712, | |
| "learning_rate": 8.41863157894737e-05, | |
| "loss": 23.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0015278838808250573, | |
| "grad_norm": 0.00016799979493953288, | |
| "learning_rate": 8.365684210526317e-05, | |
| "loss": 23.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.001564262068463749, | |
| "grad_norm": 0.00016025554214138538, | |
| "learning_rate": 8.312736842105264e-05, | |
| "loss": 23.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.001600640256102441, | |
| "grad_norm": 0.000203637799131684, | |
| "learning_rate": 8.259789473684211e-05, | |
| "loss": 23.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0016370184437411329, | |
| "grad_norm": 9.858429984888062e-05, | |
| "learning_rate": 8.206842105263158e-05, | |
| "loss": 23.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0016733966313798247, | |
| "grad_norm": 0.00014126356109045446, | |
| "learning_rate": 8.153894736842105e-05, | |
| "loss": 23.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0017097748190185165, | |
| "grad_norm": 0.00022886847727932036, | |
| "learning_rate": 8.100947368421053e-05, | |
| "loss": 23.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0017461530066572083, | |
| "grad_norm": 0.00025842548348009586, | |
| "learning_rate": 8.048000000000002e-05, | |
| "loss": 23.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0017825311942959, | |
| "grad_norm": 0.00010498856863705441, | |
| "learning_rate": 7.995052631578949e-05, | |
| "loss": 23.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.001818909381934592, | |
| "grad_norm": 0.0002834200859069824, | |
| "learning_rate": 7.942105263157896e-05, | |
| "loss": 23.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.001818909381934592, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 151.2778, | |
| "eval_samples_per_second": 76.515, | |
| "eval_steps_per_second": 19.13, | |
| "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": 2030002962432.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |