{ "best_metric": 0.48065781593322754, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.047031158142269255, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0009406231628453851, "grad_norm": 9.278800010681152, "learning_rate": 5e-05, "loss": 1.0665, "step": 1 }, { "epoch": 0.0009406231628453851, "eval_loss": 1.3672261238098145, "eval_runtime": 357.1528, "eval_samples_per_second": 20.053, "eval_steps_per_second": 2.509, "step": 1 }, { "epoch": 0.0018812463256907702, "grad_norm": 9.454571723937988, "learning_rate": 0.0001, "loss": 1.1219, "step": 2 }, { "epoch": 0.0028218694885361554, "grad_norm": 3.554928779602051, "learning_rate": 9.989294616193017e-05, "loss": 0.8661, "step": 3 }, { "epoch": 0.0037624926513815404, "grad_norm": 8.035897254943848, "learning_rate": 9.957224306869053e-05, "loss": 0.864, "step": 4 }, { "epoch": 0.004703115814226925, "grad_norm": 1.914970874786377, "learning_rate": 9.903926402016153e-05, "loss": 0.6396, "step": 5 }, { "epoch": 0.005643738977072311, "grad_norm": 1.7866945266723633, "learning_rate": 9.829629131445342e-05, "loss": 0.6384, "step": 6 }, { "epoch": 0.006584362139917695, "grad_norm": 1.609639286994934, "learning_rate": 9.73465064747553e-05, "loss": 0.6046, "step": 7 }, { "epoch": 0.007524985302763081, "grad_norm": 1.64801824092865, "learning_rate": 9.619397662556435e-05, "loss": 0.5935, "step": 8 }, { "epoch": 0.008465608465608466, "grad_norm": 1.6314135789871216, "learning_rate": 9.484363707663442e-05, "loss": 0.6356, "step": 9 }, { "epoch": 0.00940623162845385, "grad_norm": 1.4281870126724243, "learning_rate": 9.330127018922194e-05, "loss": 0.5954, "step": 10 }, { "epoch": 0.010346854791299235, "grad_norm": 1.4309544563293457, "learning_rate": 9.157348061512727e-05, "loss": 0.5273, "step": 11 }, { "epoch": 0.011287477954144622, "grad_norm": 1.7998919486999512, "learning_rate": 8.966766701456177e-05, "loss": 0.5526, "step": 12 }, { "epoch": 0.012228101116990006, "grad_norm": 1.4200043678283691, "learning_rate": 8.759199037394887e-05, "loss": 0.5697, "step": 13 }, { "epoch": 0.01316872427983539, "grad_norm": 1.0186113119125366, "learning_rate": 8.535533905932738e-05, "loss": 0.5172, "step": 14 }, { "epoch": 0.014109347442680775, "grad_norm": 1.1935527324676514, "learning_rate": 8.296729075500344e-05, "loss": 0.5575, "step": 15 }, { "epoch": 0.015049970605526162, "grad_norm": 1.1734066009521484, "learning_rate": 8.043807145043604e-05, "loss": 0.5612, "step": 16 }, { "epoch": 0.015990593768371548, "grad_norm": 1.0498110055923462, "learning_rate": 7.777851165098012e-05, "loss": 0.5582, "step": 17 }, { "epoch": 0.016931216931216932, "grad_norm": 1.109232783317566, "learning_rate": 7.500000000000001e-05, "loss": 0.5777, "step": 18 }, { "epoch": 0.017871840094062317, "grad_norm": 1.086000919342041, "learning_rate": 7.211443451095007e-05, "loss": 0.5232, "step": 19 }, { "epoch": 0.0188124632569077, "grad_norm": 1.0963627099990845, "learning_rate": 6.91341716182545e-05, "loss": 0.4975, "step": 20 }, { "epoch": 0.019753086419753086, "grad_norm": 1.3133893013000488, "learning_rate": 6.607197326515808e-05, "loss": 0.5509, "step": 21 }, { "epoch": 0.02069370958259847, "grad_norm": 1.212689995765686, "learning_rate": 6.294095225512603e-05, "loss": 0.5253, "step": 22 }, { "epoch": 0.021634332745443855, "grad_norm": 1.15071439743042, "learning_rate": 5.9754516100806423e-05, "loss": 0.5126, "step": 23 }, { "epoch": 0.022574955908289243, "grad_norm": 1.2678868770599365, "learning_rate": 5.6526309611002594e-05, "loss": 0.516, "step": 24 }, { "epoch": 0.023515579071134628, "grad_norm": 1.3126546144485474, "learning_rate": 5.327015646150716e-05, "loss": 0.4731, "step": 25 }, { "epoch": 0.023515579071134628, "eval_loss": 0.508665144443512, "eval_runtime": 315.5228, "eval_samples_per_second": 22.699, "eval_steps_per_second": 2.84, "step": 25 }, { "epoch": 0.024456202233980012, "grad_norm": 0.8437718152999878, "learning_rate": 5e-05, "loss": 0.5489, "step": 26 }, { "epoch": 0.025396825396825397, "grad_norm": 0.8871003985404968, "learning_rate": 4.6729843538492847e-05, "loss": 0.5273, "step": 27 }, { "epoch": 0.02633744855967078, "grad_norm": 0.8110382556915283, "learning_rate": 4.347369038899744e-05, "loss": 0.4564, "step": 28 }, { "epoch": 0.027278071722516166, "grad_norm": 0.8688730001449585, "learning_rate": 4.0245483899193595e-05, "loss": 0.4854, "step": 29 }, { "epoch": 0.02821869488536155, "grad_norm": 1.044745922088623, "learning_rate": 3.705904774487396e-05, "loss": 0.5399, "step": 30 }, { "epoch": 0.02915931804820694, "grad_norm": 0.9957165122032166, "learning_rate": 3.392802673484193e-05, "loss": 0.4804, "step": 31 }, { "epoch": 0.030099941211052323, "grad_norm": 1.0578233003616333, "learning_rate": 3.086582838174551e-05, "loss": 0.5136, "step": 32 }, { "epoch": 0.031040564373897708, "grad_norm": 1.0405433177947998, "learning_rate": 2.7885565489049946e-05, "loss": 0.4951, "step": 33 }, { "epoch": 0.031981187536743096, "grad_norm": 1.1319266557693481, "learning_rate": 2.500000000000001e-05, "loss": 0.4955, "step": 34 }, { "epoch": 0.03292181069958848, "grad_norm": 1.1135867834091187, "learning_rate": 2.2221488349019903e-05, "loss": 0.5042, "step": 35 }, { "epoch": 0.033862433862433865, "grad_norm": 1.0377700328826904, "learning_rate": 1.9561928549563968e-05, "loss": 0.4832, "step": 36 }, { "epoch": 0.03480305702527925, "grad_norm": 1.257242202758789, "learning_rate": 1.703270924499656e-05, "loss": 0.4273, "step": 37 }, { "epoch": 0.035743680188124634, "grad_norm": 0.8728300333023071, "learning_rate": 1.4644660940672627e-05, "loss": 0.4586, "step": 38 }, { "epoch": 0.03668430335097002, "grad_norm": 0.7657201886177063, "learning_rate": 1.2408009626051137e-05, "loss": 0.4409, "step": 39 }, { "epoch": 0.0376249265138154, "grad_norm": 0.9262546300888062, "learning_rate": 1.0332332985438248e-05, "loss": 0.4937, "step": 40 }, { "epoch": 0.03856554967666079, "grad_norm": 0.8848750591278076, "learning_rate": 8.426519384872733e-06, "loss": 0.489, "step": 41 }, { "epoch": 0.03950617283950617, "grad_norm": 0.8872339129447937, "learning_rate": 6.698729810778065e-06, "loss": 0.4796, "step": 42 }, { "epoch": 0.04044679600235156, "grad_norm": 0.9265215992927551, "learning_rate": 5.156362923365588e-06, "loss": 0.4922, "step": 43 }, { "epoch": 0.04138741916519694, "grad_norm": 0.9621391892433167, "learning_rate": 3.8060233744356633e-06, "loss": 0.4666, "step": 44 }, { "epoch": 0.042328042328042326, "grad_norm": 0.9457005262374878, "learning_rate": 2.653493525244721e-06, "loss": 0.4935, "step": 45 }, { "epoch": 0.04326866549088771, "grad_norm": 0.9700300097465515, "learning_rate": 1.70370868554659e-06, "loss": 0.4628, "step": 46 }, { "epoch": 0.044209288653733095, "grad_norm": 1.1647878885269165, "learning_rate": 9.607359798384785e-07, "loss": 0.4651, "step": 47 }, { "epoch": 0.045149911816578486, "grad_norm": 1.135780692100525, "learning_rate": 4.277569313094809e-07, "loss": 0.4648, "step": 48 }, { "epoch": 0.04609053497942387, "grad_norm": 1.0905580520629883, "learning_rate": 1.0705383806982606e-07, "loss": 0.4625, "step": 49 }, { "epoch": 0.047031158142269255, "grad_norm": 1.2157825231552124, "learning_rate": 0.0, "loss": 0.4432, "step": 50 }, { "epoch": 0.047031158142269255, "eval_loss": 0.48065781593322754, "eval_runtime": 408.5813, "eval_samples_per_second": 17.529, "eval_steps_per_second": 2.193, "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": 5.658024559509504e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }