| { | |
| "best_metric": 0.4162628650665283, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.7586533902323376, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.015173067804646752, | |
| "grad_norm": 17.388423919677734, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 30.457, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015173067804646752, | |
| "eval_loss": 0.8401981592178345, | |
| "eval_runtime": 4.1216, | |
| "eval_samples_per_second": 12.131, | |
| "eval_steps_per_second": 12.131, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.030346135609293504, | |
| "grad_norm": 10.178067207336426, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 30.335, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04551920341394026, | |
| "grad_norm": 10.258736610412598, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 28.3123, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06069227121858701, | |
| "grad_norm": 10.296838760375977, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 27.9287, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07586533902323377, | |
| "grad_norm": 12.867237091064453, | |
| "learning_rate": 0.00015, | |
| "loss": 25.3598, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09103840682788052, | |
| "grad_norm": 12.431685447692871, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 22.2146, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.10621147463252727, | |
| "grad_norm": 13.944931983947754, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 19.7453, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.12138454243717402, | |
| "grad_norm": 23.274085998535156, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 19.6562, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.13655761024182078, | |
| "grad_norm": 23.921234130859375, | |
| "learning_rate": 0.00027, | |
| "loss": 15.7789, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.15173067804646753, | |
| "grad_norm": 31.0799560546875, | |
| "learning_rate": 0.0003, | |
| "loss": 18.6639, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16690374585111428, | |
| "grad_norm": 27.46465301513672, | |
| "learning_rate": 0.00029995027012714694, | |
| "loss": 15.0467, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.18207681365576103, | |
| "grad_norm": 21.228845596313477, | |
| "learning_rate": 0.00029980111348272456, | |
| "loss": 16.0005, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.19724988146040778, | |
| "grad_norm": 17.686410903930664, | |
| "learning_rate": 0.00029955262896727894, | |
| "loss": 15.2921, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.21242294926505453, | |
| "grad_norm": 16.29988670349121, | |
| "learning_rate": 0.00029920498134218835, | |
| "loss": 14.4487, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.22759601706970128, | |
| "grad_norm": 18.719757080078125, | |
| "learning_rate": 0.0002987584011204152, | |
| "loss": 12.782, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.24276908487434803, | |
| "grad_norm": 19.07723617553711, | |
| "learning_rate": 0.0002982131844136615, | |
| "loss": 12.9955, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2579421526789948, | |
| "grad_norm": 45.31391143798828, | |
| "learning_rate": 0.0002975696927360274, | |
| "loss": 23.8883, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.27311522048364156, | |
| "grad_norm": 27.076311111450195, | |
| "learning_rate": 0.0002968283527643036, | |
| "loss": 21.5994, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2882882882882883, | |
| "grad_norm": 15.616254806518555, | |
| "learning_rate": 0.00029598965605505737, | |
| "loss": 18.592, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.30346135609293506, | |
| "grad_norm": 18.812135696411133, | |
| "learning_rate": 0.000295054158718698, | |
| "loss": 16.3996, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3186344238975818, | |
| "grad_norm": 14.7747163772583, | |
| "learning_rate": 0.0002940224810507402, | |
| "loss": 16.5481, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.33380749170222856, | |
| "grad_norm": 13.129542350769043, | |
| "learning_rate": 0.00029289530712050735, | |
| "loss": 14.6397, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3489805595068753, | |
| "grad_norm": 13.189936637878418, | |
| "learning_rate": 0.0002916733843175492, | |
| "loss": 14.889, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.36415362731152207, | |
| "grad_norm": 11.230732917785645, | |
| "learning_rate": 0.000290357522856074, | |
| "loss": 13.3495, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3793266951161688, | |
| "grad_norm": 10.45602798461914, | |
| "learning_rate": 0.0002889485952377242, | |
| "loss": 13.97, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3793266951161688, | |
| "eval_loss": 0.4615178406238556, | |
| "eval_runtime": 4.1945, | |
| "eval_samples_per_second": 11.92, | |
| "eval_steps_per_second": 11.92, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.39449976292081557, | |
| "grad_norm": 9.400847434997559, | |
| "learning_rate": 0.0002874475356730507, | |
| "loss": 13.0953, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4096728307254623, | |
| "grad_norm": 10.215126037597656, | |
| "learning_rate": 0.0002858553394620707, | |
| "loss": 14.0127, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.42484589853010907, | |
| "grad_norm": 8.064435958862305, | |
| "learning_rate": 0.0002841730623343193, | |
| "loss": 12.4928, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4400189663347558, | |
| "grad_norm": 10.052416801452637, | |
| "learning_rate": 0.00028240181974883207, | |
| "loss": 14.195, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.45519203413940257, | |
| "grad_norm": 9.893036842346191, | |
| "learning_rate": 0.00028054278615452326, | |
| "loss": 12.9534, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4703651019440493, | |
| "grad_norm": 9.579009056091309, | |
| "learning_rate": 0.0002785971942114498, | |
| "loss": 11.9894, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.48553816974869607, | |
| "grad_norm": 10.615213394165039, | |
| "learning_rate": 0.0002765663339734778, | |
| "loss": 11.5054, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5007112375533428, | |
| "grad_norm": 18.542469024658203, | |
| "learning_rate": 0.0002744515520328928, | |
| "loss": 17.3979, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5158843053579896, | |
| "grad_norm": 15.90185260772705, | |
| "learning_rate": 0.00027225425062752165, | |
| "loss": 16.0495, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5310573731626363, | |
| "grad_norm": 12.792567253112793, | |
| "learning_rate": 0.0002699758867109579, | |
| "loss": 15.2643, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5462304409672831, | |
| "grad_norm": 9.845219612121582, | |
| "learning_rate": 0.0002676179709865066, | |
| "loss": 13.5142, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5614035087719298, | |
| "grad_norm": 12.22781753540039, | |
| "learning_rate": 0.00026518206690549, | |
| "loss": 14.2178, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5765765765765766, | |
| "grad_norm": 10.745471954345703, | |
| "learning_rate": 0.0002626697896305779, | |
| "loss": 12.9431, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5917496443812233, | |
| "grad_norm": 10.67679500579834, | |
| "learning_rate": 0.00026008280496482984, | |
| "loss": 15.1994, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6069227121858701, | |
| "grad_norm": 8.882881164550781, | |
| "learning_rate": 0.000257422828247159, | |
| "loss": 14.0005, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6220957799905168, | |
| "grad_norm": 9.826411247253418, | |
| "learning_rate": 0.00025469162321495147, | |
| "loss": 12.5264, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6372688477951636, | |
| "grad_norm": 8.515768051147461, | |
| "learning_rate": 0.00025189100083459397, | |
| "loss": 11.0442, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6524419155998104, | |
| "grad_norm": 9.0559720993042, | |
| "learning_rate": 0.00024902281810068475, | |
| "loss": 11.7402, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6676149834044571, | |
| "grad_norm": 9.556861877441406, | |
| "learning_rate": 0.0002460889768047263, | |
| "loss": 12.4502, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6827880512091038, | |
| "grad_norm": 8.837124824523926, | |
| "learning_rate": 0.0002430914222741134, | |
| "loss": 12.4087, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6979611190137506, | |
| "grad_norm": 15.878302574157715, | |
| "learning_rate": 0.00024003214208225522, | |
| "loss": 11.0582, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7131341868183974, | |
| "grad_norm": 9.87769603729248, | |
| "learning_rate": 0.00023691316473068452, | |
| "loss": 11.3891, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7283072546230441, | |
| "grad_norm": 8.35490608215332, | |
| "learning_rate": 0.00023373655830402968, | |
| "loss": 9.9121, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7434803224276908, | |
| "grad_norm": 17.935434341430664, | |
| "learning_rate": 0.00023050442909874007, | |
| "loss": 16.9965, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7586533902323376, | |
| "grad_norm": 15.285179138183594, | |
| "learning_rate": 0.00022721892022647462, | |
| "loss": 16.4137, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7586533902323376, | |
| "eval_loss": 0.4162628650665283, | |
| "eval_runtime": 4.1979, | |
| "eval_samples_per_second": 11.911, | |
| "eval_steps_per_second": 11.911, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 132, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.95507593986048e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |