| { | |
| "best_metric": 1.0755832195281982, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.009917806181272703, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00019835612362545404, | |
| "grad_norm": 3.42954683303833, | |
| "learning_rate": 5e-05, | |
| "loss": 6.8945, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00019835612362545404, | |
| "eval_loss": 6.829679012298584, | |
| "eval_runtime": 392.1332, | |
| "eval_samples_per_second": 86.613, | |
| "eval_steps_per_second": 10.828, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003967122472509081, | |
| "grad_norm": 3.4046621322631836, | |
| "learning_rate": 0.0001, | |
| "loss": 6.6774, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005950683708763622, | |
| "grad_norm": 3.521897077560425, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 6.7743, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007934244945018162, | |
| "grad_norm": 3.42401123046875, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.1141, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0009917806181272703, | |
| "grad_norm": 3.1044297218322754, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 5.59, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0011901367417527244, | |
| "grad_norm": 2.840792655944824, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 5.2416, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013884928653781783, | |
| "grad_norm": 2.5770530700683594, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 4.6201, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0015868489890036323, | |
| "grad_norm": 2.357764959335327, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.278, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0017852051126290864, | |
| "grad_norm": 2.208768844604492, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 4.1866, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0019835612362545407, | |
| "grad_norm": 2.3419127464294434, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.6927, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0021819173598799945, | |
| "grad_norm": 2.2363104820251465, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 3.5168, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002380273483505449, | |
| "grad_norm": 2.5871493816375732, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.5412, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0025786296071309027, | |
| "grad_norm": 2.4603450298309326, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.4244, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0027769857307563565, | |
| "grad_norm": 2.657694101333618, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.1756, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002975341854381811, | |
| "grad_norm": 2.0038065910339355, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.8973, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0031736979780072646, | |
| "grad_norm": 1.5983942747116089, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.5824, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.003372054101632719, | |
| "grad_norm": 1.6725854873657227, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.4963, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0035704102252581728, | |
| "grad_norm": 1.6831201314926147, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.3172, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003768766348883627, | |
| "grad_norm": 1.5336560010910034, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.2309, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.003967122472509081, | |
| "grad_norm": 1.5436307191848755, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.8518, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004165478596134535, | |
| "grad_norm": 1.317272424697876, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.7868, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004363834719759989, | |
| "grad_norm": 1.2942112684249878, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.6163, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.004562190843385443, | |
| "grad_norm": 1.62408447265625, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.7883, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004760546967010898, | |
| "grad_norm": 1.7384992837905884, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.7993, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0049589030906363515, | |
| "grad_norm": 2.017239570617676, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.827, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0049589030906363515, | |
| "eval_loss": 1.6422466039657593, | |
| "eval_runtime": 389.184, | |
| "eval_samples_per_second": 87.27, | |
| "eval_steps_per_second": 10.91, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005157259214261805, | |
| "grad_norm": 1.9225361347198486, | |
| "learning_rate": 5e-05, | |
| "loss": 1.934, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.005355615337887259, | |
| "grad_norm": 1.6286966800689697, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.6607, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.005553971461512713, | |
| "grad_norm": 1.5591243505477905, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.6271, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.005752327585138168, | |
| "grad_norm": 1.3496639728546143, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.4905, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.005950683708763622, | |
| "grad_norm": 1.1657429933547974, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.2554, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0061490398323890754, | |
| "grad_norm": 1.1974936723709106, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.1984, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.006347395956014529, | |
| "grad_norm": 1.2555491924285889, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.3582, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.006545752079639984, | |
| "grad_norm": 1.268581509590149, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.1061, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.006744108203265438, | |
| "grad_norm": 1.210546851158142, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.2048, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.006942464326890892, | |
| "grad_norm": 1.3306183815002441, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.1493, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0071408204505163456, | |
| "grad_norm": 1.5224374532699585, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.2848, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.007339176574141799, | |
| "grad_norm": 1.2854976654052734, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.0915, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.007537532697767254, | |
| "grad_norm": 1.5203335285186768, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.3953, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.007735888821392708, | |
| "grad_norm": 1.3025851249694824, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.2828, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.007934244945018163, | |
| "grad_norm": 1.3689641952514648, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.1448, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008132601068643617, | |
| "grad_norm": 1.2690826654434204, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.2001, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.00833095719226907, | |
| "grad_norm": 1.004398226737976, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.0619, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.008529313315894524, | |
| "grad_norm": 1.0098557472229004, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.0085, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.008727669439519978, | |
| "grad_norm": 1.0918034315109253, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.0509, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.008926025563145432, | |
| "grad_norm": 1.0433894395828247, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.9432, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.009124381686770886, | |
| "grad_norm": 0.8852425217628479, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.8706, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.00932273781039634, | |
| "grad_norm": 0.9674733281135559, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.9719, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.009521093934021795, | |
| "grad_norm": 0.9817253351211548, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.9108, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.009719450057647249, | |
| "grad_norm": 1.0266602039337158, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.9272, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.009917806181272703, | |
| "grad_norm": 1.561460018157959, | |
| "learning_rate": 0.0, | |
| "loss": 1.1452, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.009917806181272703, | |
| "eval_loss": 1.0755832195281982, | |
| "eval_runtime": 383.5523, | |
| "eval_samples_per_second": 88.551, | |
| "eval_steps_per_second": 11.07, | |
| "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": 1.059536353886208e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |