| { | |
| "best_metric": 6.91412353515625, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.26883425852498, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.025376685170499604, | |
| "grad_norm": 0.7004460096359253, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9221, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.025376685170499604, | |
| "eval_loss": 6.944462299346924, | |
| "eval_runtime": 0.1152, | |
| "eval_samples_per_second": 434.074, | |
| "eval_steps_per_second": 112.859, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05075337034099921, | |
| "grad_norm": 0.6931402087211609, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9198, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0761300555114988, | |
| "grad_norm": 0.23951783776283264, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 6.9389, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.10150674068199841, | |
| "grad_norm": 0.24534912407398224, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 6.9407, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.126883425852498, | |
| "grad_norm": 0.23312632739543915, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 6.9474, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1522601110229976, | |
| "grad_norm": 0.2653202712535858, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 6.9404, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.17763679619349723, | |
| "grad_norm": 0.29398810863494873, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 6.9344, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.20301348136399683, | |
| "grad_norm": 0.33159613609313965, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 6.9315, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.22839016653449642, | |
| "grad_norm": 0.33163586258888245, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 6.9403, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.253766851704996, | |
| "grad_norm": 0.3883456587791443, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 6.9259, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.27914353687549565, | |
| "grad_norm": 0.6985044479370117, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 6.8995, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3045202220459952, | |
| "grad_norm": 0.5428418517112732, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 6.909, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.32989690721649484, | |
| "grad_norm": 0.2652731239795685, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 6.9292, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.35527359238699446, | |
| "grad_norm": 0.2631296217441559, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 6.9314, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.38065027755749403, | |
| "grad_norm": 0.23014403879642487, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 6.937, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.40602696272799366, | |
| "grad_norm": 0.2576012909412384, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 6.9293, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.4314036478984933, | |
| "grad_norm": 0.2961735129356384, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 6.9245, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.45678033306899285, | |
| "grad_norm": 0.30337101221084595, | |
| "learning_rate": 7.75e-05, | |
| "loss": 6.9231, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4821570182394925, | |
| "grad_norm": 0.2677088677883148, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 6.9252, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.507533703409992, | |
| "grad_norm": 0.5016420483589172, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 6.9028, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5329103885804917, | |
| "grad_norm": 0.6997107267379761, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 6.8873, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5582870737509913, | |
| "grad_norm": 0.37420928478240967, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 6.9067, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5836637589214909, | |
| "grad_norm": 0.2798817455768585, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 6.9219, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.6090404440919904, | |
| "grad_norm": 0.25544771552085876, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 6.9211, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.63441712926249, | |
| "grad_norm": 0.21856531500816345, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 6.9325, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.63441712926249, | |
| "eval_loss": 6.922487258911133, | |
| "eval_runtime": 0.1164, | |
| "eval_samples_per_second": 429.492, | |
| "eval_steps_per_second": 111.668, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6597938144329897, | |
| "grad_norm": 0.2449556142091751, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 6.9239, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6851704996034893, | |
| "grad_norm": 0.30131685733795166, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 6.9162, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.7105471847739889, | |
| "grad_norm": 0.32581567764282227, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 6.914, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.7359238699444886, | |
| "grad_norm": 0.32971295714378357, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 6.9164, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.7613005551149881, | |
| "grad_norm": 0.617648720741272, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 6.877, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7866772402854877, | |
| "grad_norm": 0.6868042349815369, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 6.8734, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.8120539254559873, | |
| "grad_norm": 0.3134247362613678, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 6.9059, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.8374306106264869, | |
| "grad_norm": 0.2802397608757019, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 6.9128, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8628072957969866, | |
| "grad_norm": 0.2617209851741791, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 6.9152, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.8881839809674861, | |
| "grad_norm": 0.23401491343975067, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 6.9297, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.9135606661379857, | |
| "grad_norm": 0.3026781976222992, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 6.9084, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.9389373513084853, | |
| "grad_norm": 0.29526880383491516, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 6.9079, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.964314036478985, | |
| "grad_norm": 0.34165528416633606, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 6.9084, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.9896907216494846, | |
| "grad_norm": 0.31630247831344604, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 6.9171, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.015067406819984, | |
| "grad_norm": 0.6814719438552856, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 10.9955, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0404440919904838, | |
| "grad_norm": 0.6847633123397827, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 6.8728, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.0658207771609833, | |
| "grad_norm": 0.4051920473575592, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 6.7039, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.0911974623314828, | |
| "grad_norm": 0.3018025755882263, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 7.3555, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.1165741475019826, | |
| "grad_norm": 0.2783207595348358, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 6.7517, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.141950832672482, | |
| "grad_norm": 0.21331705152988434, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 6.6381, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.1673275178429818, | |
| "grad_norm": 0.2783212661743164, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 7.109, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.1927042030134813, | |
| "grad_norm": 0.2744676172733307, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 6.6019, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.218080888183981, | |
| "grad_norm": 0.3599938750267029, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 7.6122, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.2434575733544806, | |
| "grad_norm": 0.2515687644481659, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 5.8057, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.26883425852498, | |
| "grad_norm": 0.7015694975852966, | |
| "learning_rate": 1e-05, | |
| "loss": 7.5716, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.26883425852498, | |
| "eval_loss": 6.91412353515625, | |
| "eval_runtime": 0.1195, | |
| "eval_samples_per_second": 418.264, | |
| "eval_steps_per_second": 108.749, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 5705957376000.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |