| { | |
| "best_metric": 0.729594349861145, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.013190001978500296, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002638000395700059, | |
| "grad_norm": 7.958331108093262, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2561, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002638000395700059, | |
| "eval_loss": 4.780569553375244, | |
| "eval_runtime": 461.6755, | |
| "eval_samples_per_second": 55.316, | |
| "eval_steps_per_second": 6.916, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005276000791400118, | |
| "grad_norm": 13.485570907592773, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1953, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007914001187100178, | |
| "grad_norm": 19.63498878479004, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.081, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010552001582800237, | |
| "grad_norm": 10.698768615722656, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.2366, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013190001978500296, | |
| "grad_norm": 18.16755485534668, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.2662, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0015828002374200355, | |
| "grad_norm": 9.718000411987305, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.6695, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0018466002769900415, | |
| "grad_norm": 8.218741416931152, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.2669, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0021104003165600474, | |
| "grad_norm": 3.292022705078125, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.0033, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0023742003561300533, | |
| "grad_norm": 3.1292548179626465, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.7957, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0026380003957000592, | |
| "grad_norm": 3.5087814331054688, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.7045, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002901800435270065, | |
| "grad_norm": 4.11509895324707, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.4757, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.003165600474840071, | |
| "grad_norm": 5.83006477355957, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.2856, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003429400514410077, | |
| "grad_norm": 5.71228551864624, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.1455, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003693200553980083, | |
| "grad_norm": 6.7645063400268555, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.1394, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003957000593550089, | |
| "grad_norm": 5.063263416290283, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.987, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004220800633120095, | |
| "grad_norm": 2.66418719291687, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.863, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004484600672690101, | |
| "grad_norm": 1.3248200416564941, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.7932, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004748400712260107, | |
| "grad_norm": 2.8736984729766846, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.7753, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0050122007518301126, | |
| "grad_norm": 1.8802906274795532, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.758, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0052760007914001185, | |
| "grad_norm": 0.8349721431732178, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7169, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005539800830970124, | |
| "grad_norm": 0.5164936780929565, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.6801, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00580360087054013, | |
| "grad_norm": 0.52817702293396, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.6917, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006067400910110136, | |
| "grad_norm": 0.6094891428947449, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.6945, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006331200949680142, | |
| "grad_norm": 0.29039666056632996, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.6798, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006595000989250148, | |
| "grad_norm": 0.2607605457305908, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.6943, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006595000989250148, | |
| "eval_loss": 0.8254014849662781, | |
| "eval_runtime": 461.9586, | |
| "eval_samples_per_second": 55.282, | |
| "eval_steps_per_second": 6.912, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006858801028820154, | |
| "grad_norm": 4.407656192779541, | |
| "learning_rate": 5e-05, | |
| "loss": 1.147, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.00712260106839016, | |
| "grad_norm": 4.337778091430664, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.0982, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007386401107960166, | |
| "grad_norm": 3.240676164627075, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.025, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.007650201147530172, | |
| "grad_norm": 1.9950593709945679, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.9391, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.007914001187100178, | |
| "grad_norm": 0.30276378989219666, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.6943, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008177801226670185, | |
| "grad_norm": 0.40190184116363525, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.6835, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.00844160126624019, | |
| "grad_norm": 0.35267969965934753, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.6931, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.008705401305810196, | |
| "grad_norm": 0.4400714933872223, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.6803, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.008969201345380201, | |
| "grad_norm": 0.31493258476257324, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.6759, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009233001384950208, | |
| "grad_norm": 0.3836783766746521, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.696, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.009496801424520213, | |
| "grad_norm": 0.3818792998790741, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.694, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.00976060146409022, | |
| "grad_norm": 0.2685048580169678, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.6738, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.010024401503660225, | |
| "grad_norm": 0.901552140712738, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.8282, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.010288201543230232, | |
| "grad_norm": 1.1144156455993652, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.8752, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.010552001582800237, | |
| "grad_norm": 0.9842584729194641, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.8399, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010815801622370244, | |
| "grad_norm": 0.9597560167312622, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.8426, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.011079601661940249, | |
| "grad_norm": 0.4202268123626709, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.7629, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.011343401701510256, | |
| "grad_norm": 0.39397257566452026, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.6832, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.01160720174108026, | |
| "grad_norm": 0.40432485938072205, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.6811, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.011871001780650267, | |
| "grad_norm": 0.3644748032093048, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.6841, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012134801820220273, | |
| "grad_norm": 0.378349632024765, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.6887, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.01239860185979028, | |
| "grad_norm": 0.3869484066963196, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.6898, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.012662401899360284, | |
| "grad_norm": 0.4297974705696106, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.6707, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.012926201938930291, | |
| "grad_norm": 0.3628126084804535, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.6951, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.013190001978500296, | |
| "grad_norm": 0.4723879396915436, | |
| "learning_rate": 0.0, | |
| "loss": 0.6894, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.013190001978500296, | |
| "eval_loss": 0.729594349861145, | |
| "eval_runtime": 461.5438, | |
| "eval_samples_per_second": 55.332, | |
| "eval_steps_per_second": 6.918, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 2.229252309123072e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |