| { | |
| "best_metric": 1.2340582609176636, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.01612448099326803, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00032248961986536056, | |
| "grad_norm": 0.45406192541122437, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0193, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00032248961986536056, | |
| "eval_loss": 1.9531915187835693, | |
| "eval_runtime": 189.1229, | |
| "eval_samples_per_second": 110.457, | |
| "eval_steps_per_second": 13.811, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006449792397307211, | |
| "grad_norm": 0.915189802646637, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1085, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0009674688595960818, | |
| "grad_norm": 1.0581778287887573, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.0704, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012899584794614422, | |
| "grad_norm": 0.8824008703231812, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.0313, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001612448099326803, | |
| "grad_norm": 1.065260887145996, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.0284, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0019349377191921636, | |
| "grad_norm": 1.1925026178359985, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.2103, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002257427339057524, | |
| "grad_norm": 1.5321978330612183, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.2093, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0025799169589228845, | |
| "grad_norm": 2.056502103805542, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2419, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0029024065787882454, | |
| "grad_norm": 1.9517987966537476, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.5124, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003224896198653606, | |
| "grad_norm": 1.9934046268463135, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.5296, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0035473858185189663, | |
| "grad_norm": 3.4072160720825195, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.766, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.003869875438384327, | |
| "grad_norm": 2.966559648513794, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.7101, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004192365058249687, | |
| "grad_norm": 0.3839709460735321, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.1557, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.004514854678115048, | |
| "grad_norm": 0.6887500286102295, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.4262, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004837344297980409, | |
| "grad_norm": 0.6592994332313538, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.0372, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005159833917845769, | |
| "grad_norm": 0.722044825553894, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.8434, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00548232353771113, | |
| "grad_norm": 0.6898185014724731, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.9528, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005804813157576491, | |
| "grad_norm": 0.6522444486618042, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.8918, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006127302777441851, | |
| "grad_norm": 0.7075480222702026, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.0995, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.006449792397307212, | |
| "grad_norm": 0.8886283040046692, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.203, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0067722820171725725, | |
| "grad_norm": 1.0472253561019897, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.1886, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0070947716370379325, | |
| "grad_norm": 0.9946570992469788, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.3704, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.007417261256903293, | |
| "grad_norm": 0.9166963696479797, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.5007, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.007739750876768654, | |
| "grad_norm": 1.3275251388549805, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.5536, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.008062240496634015, | |
| "grad_norm": 2.037898302078247, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.9408, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008062240496634015, | |
| "eval_loss": 1.2614442110061646, | |
| "eval_runtime": 164.7739, | |
| "eval_samples_per_second": 126.78, | |
| "eval_steps_per_second": 15.852, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008384730116499374, | |
| "grad_norm": 0.424387127161026, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1484, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.008707219736364735, | |
| "grad_norm": 0.5464354157447815, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.9558, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.009029709356230096, | |
| "grad_norm": 0.658257246017456, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.9587, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.009352198976095457, | |
| "grad_norm": 0.6939743757247925, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.8963, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.009674688595960818, | |
| "grad_norm": 0.7916174530982971, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.9807, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009997178215826179, | |
| "grad_norm": 0.6796430945396423, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.7502, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.010319667835691538, | |
| "grad_norm": 0.6769554018974304, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.0012, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.010642157455556899, | |
| "grad_norm": 0.9456203579902649, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.2304, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01096464707542226, | |
| "grad_norm": 0.8935078382492065, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.1537, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.01128713669528762, | |
| "grad_norm": 0.8256329298019409, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.3514, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.011609626315152981, | |
| "grad_norm": 1.2557326555252075, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.4169, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.011932115935018342, | |
| "grad_norm": 1.5488860607147217, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.5628, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.012254605554883701, | |
| "grad_norm": 0.3189387321472168, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.0827, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.012577095174749062, | |
| "grad_norm": 0.7208530306816101, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.52, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.012899584794614423, | |
| "grad_norm": 0.4742284417152405, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.9261, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.013222074414479784, | |
| "grad_norm": 0.4814181327819824, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.799, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.013544564034345145, | |
| "grad_norm": 0.5407553911209106, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.7985, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.013867053654210506, | |
| "grad_norm": 0.5527483820915222, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.9168, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.014189543274075865, | |
| "grad_norm": 0.5612297058105469, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.0413, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.014512032893941226, | |
| "grad_norm": 0.6964607834815979, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.8882, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.014834522513806587, | |
| "grad_norm": 0.8896213173866272, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.21, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.015157012133671948, | |
| "grad_norm": 0.7992110252380371, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.2457, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.015479501753537309, | |
| "grad_norm": 0.8591369390487671, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.3872, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.015801991373402668, | |
| "grad_norm": 0.972260057926178, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.5417, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.01612448099326803, | |
| "grad_norm": 2.331629514694214, | |
| "learning_rate": 0.0, | |
| "loss": 1.6333, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01612448099326803, | |
| "eval_loss": 1.2340582609176636, | |
| "eval_runtime": 163.7842, | |
| "eval_samples_per_second": 127.546, | |
| "eval_steps_per_second": 15.948, | |
| "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": 3.1311125014380544e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |