{ "best_metric": 2.5868451595306396, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.13065490772497143, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0026130981544994283, "grad_norm": 0.16858744621276855, "learning_rate": 5e-05, "loss": 2.5233, "step": 1 }, { "epoch": 0.0026130981544994283, "eval_loss": 3.012192726135254, "eval_runtime": 29.7641, "eval_samples_per_second": 86.614, "eval_steps_per_second": 10.852, "step": 1 }, { "epoch": 0.005226196308998857, "grad_norm": 0.1825653314590454, "learning_rate": 0.0001, "loss": 2.5518, "step": 2 }, { "epoch": 0.007839294463498285, "grad_norm": 0.1806764155626297, "learning_rate": 9.989294616193017e-05, "loss": 2.572, "step": 3 }, { "epoch": 0.010452392617997713, "grad_norm": 0.18963511288166046, "learning_rate": 9.957224306869053e-05, "loss": 2.6212, "step": 4 }, { "epoch": 0.013065490772497142, "grad_norm": 0.19405661523342133, "learning_rate": 9.903926402016153e-05, "loss": 2.6667, "step": 5 }, { "epoch": 0.01567858892699657, "grad_norm": 0.20833389461040497, "learning_rate": 9.829629131445342e-05, "loss": 2.6152, "step": 6 }, { "epoch": 0.018291687081496, "grad_norm": 0.26200610399246216, "learning_rate": 9.73465064747553e-05, "loss": 2.5644, "step": 7 }, { "epoch": 0.020904785235995427, "grad_norm": 0.32988935708999634, "learning_rate": 9.619397662556435e-05, "loss": 2.6215, "step": 8 }, { "epoch": 0.023517883390494855, "grad_norm": 0.45379143953323364, "learning_rate": 9.484363707663442e-05, "loss": 3.0514, "step": 9 }, { "epoch": 0.026130981544994283, "grad_norm": 0.6125020980834961, "learning_rate": 9.330127018922194e-05, "loss": 2.9257, "step": 10 }, { "epoch": 0.02874407969949371, "grad_norm": 0.8592873215675354, "learning_rate": 9.157348061512727e-05, "loss": 3.2911, "step": 11 }, { "epoch": 0.03135717785399314, "grad_norm": 1.2533773183822632, "learning_rate": 8.966766701456177e-05, "loss": 3.7178, "step": 12 }, { "epoch": 0.03397027600849257, "grad_norm": 0.33008843660354614, "learning_rate": 8.759199037394887e-05, "loss": 2.477, "step": 13 }, { "epoch": 0.036583374162992, "grad_norm": 0.35662442445755005, "learning_rate": 8.535533905932738e-05, "loss": 2.5109, "step": 14 }, { "epoch": 0.039196472317491425, "grad_norm": 0.3099682331085205, "learning_rate": 8.296729075500344e-05, "loss": 2.5523, "step": 15 }, { "epoch": 0.04180957047199085, "grad_norm": 0.25707748532295227, "learning_rate": 8.043807145043604e-05, "loss": 2.4262, "step": 16 }, { "epoch": 0.04442266862649028, "grad_norm": 0.2552078366279602, "learning_rate": 7.777851165098012e-05, "loss": 2.4859, "step": 17 }, { "epoch": 0.04703576678098971, "grad_norm": 0.2537156343460083, "learning_rate": 7.500000000000001e-05, "loss": 2.5177, "step": 18 }, { "epoch": 0.04964886493548914, "grad_norm": 0.32268282771110535, "learning_rate": 7.211443451095007e-05, "loss": 2.5539, "step": 19 }, { "epoch": 0.05226196308998857, "grad_norm": 0.35638126730918884, "learning_rate": 6.91341716182545e-05, "loss": 2.5592, "step": 20 }, { "epoch": 0.054875061244487995, "grad_norm": 0.39644405245780945, "learning_rate": 6.607197326515808e-05, "loss": 2.5554, "step": 21 }, { "epoch": 0.05748815939898742, "grad_norm": 0.5287861824035645, "learning_rate": 6.294095225512603e-05, "loss": 2.916, "step": 22 }, { "epoch": 0.06010125755348685, "grad_norm": 0.614913284778595, "learning_rate": 5.9754516100806423e-05, "loss": 2.8861, "step": 23 }, { "epoch": 0.06271435570798628, "grad_norm": 0.7370900511741638, "learning_rate": 5.6526309611002594e-05, "loss": 2.8397, "step": 24 }, { "epoch": 0.06532745386248572, "grad_norm": 1.218734860420227, "learning_rate": 5.327015646150716e-05, "loss": 3.0845, "step": 25 }, { "epoch": 0.06532745386248572, "eval_loss": 2.6269185543060303, "eval_runtime": 29.1899, "eval_samples_per_second": 88.318, "eval_steps_per_second": 11.065, "step": 25 }, { "epoch": 0.06794055201698514, "grad_norm": 0.23122720420360565, "learning_rate": 5e-05, "loss": 2.378, "step": 26 }, { "epoch": 0.07055365017148457, "grad_norm": 0.23574258387088776, "learning_rate": 4.6729843538492847e-05, "loss": 2.3677, "step": 27 }, { "epoch": 0.073166748325984, "grad_norm": 0.2773175835609436, "learning_rate": 4.347369038899744e-05, "loss": 2.4514, "step": 28 }, { "epoch": 0.07577984648048343, "grad_norm": 0.2590325176715851, "learning_rate": 4.0245483899193595e-05, "loss": 2.4457, "step": 29 }, { "epoch": 0.07839294463498285, "grad_norm": 0.2623507082462311, "learning_rate": 3.705904774487396e-05, "loss": 2.4593, "step": 30 }, { "epoch": 0.08100604278948229, "grad_norm": 0.2827397882938385, "learning_rate": 3.392802673484193e-05, "loss": 2.5734, "step": 31 }, { "epoch": 0.0836191409439817, "grad_norm": 0.31998294591903687, "learning_rate": 3.086582838174551e-05, "loss": 2.5782, "step": 32 }, { "epoch": 0.08623223909848114, "grad_norm": 0.3966841697692871, "learning_rate": 2.7885565489049946e-05, "loss": 2.7672, "step": 33 }, { "epoch": 0.08884533725298056, "grad_norm": 0.4778576195240021, "learning_rate": 2.500000000000001e-05, "loss": 2.6645, "step": 34 }, { "epoch": 0.09145843540748, "grad_norm": 0.5237305164337158, "learning_rate": 2.2221488349019903e-05, "loss": 2.7975, "step": 35 }, { "epoch": 0.09407153356197942, "grad_norm": 0.6229977011680603, "learning_rate": 1.9561928549563968e-05, "loss": 2.5883, "step": 36 }, { "epoch": 0.09668463171647886, "grad_norm": 0.8404539227485657, "learning_rate": 1.703270924499656e-05, "loss": 2.905, "step": 37 }, { "epoch": 0.09929772987097828, "grad_norm": 0.21332432329654694, "learning_rate": 1.4644660940672627e-05, "loss": 2.4021, "step": 38 }, { "epoch": 0.10191082802547771, "grad_norm": 0.19318430125713348, "learning_rate": 1.2408009626051137e-05, "loss": 2.4462, "step": 39 }, { "epoch": 0.10452392617997713, "grad_norm": 0.21098162233829498, "learning_rate": 1.0332332985438248e-05, "loss": 2.4113, "step": 40 }, { "epoch": 0.10713702433447657, "grad_norm": 0.2191692739725113, "learning_rate": 8.426519384872733e-06, "loss": 2.4363, "step": 41 }, { "epoch": 0.10975012248897599, "grad_norm": 0.2183644026517868, "learning_rate": 6.698729810778065e-06, "loss": 2.5644, "step": 42 }, { "epoch": 0.11236322064347543, "grad_norm": 0.26048311591148376, "learning_rate": 5.156362923365588e-06, "loss": 2.6047, "step": 43 }, { "epoch": 0.11497631879797485, "grad_norm": 0.29173219203948975, "learning_rate": 3.8060233744356633e-06, "loss": 2.5677, "step": 44 }, { "epoch": 0.11758941695247428, "grad_norm": 0.2908892333507538, "learning_rate": 2.653493525244721e-06, "loss": 2.427, "step": 45 }, { "epoch": 0.1202025151069737, "grad_norm": 0.38975709676742554, "learning_rate": 1.70370868554659e-06, "loss": 2.6845, "step": 46 }, { "epoch": 0.12281561326147314, "grad_norm": 0.5010013580322266, "learning_rate": 9.607359798384785e-07, "loss": 2.6234, "step": 47 }, { "epoch": 0.12542871141597256, "grad_norm": 0.5796919465065002, "learning_rate": 4.277569313094809e-07, "loss": 2.552, "step": 48 }, { "epoch": 0.12804180957047198, "grad_norm": 0.7231181263923645, "learning_rate": 1.0705383806982606e-07, "loss": 2.7567, "step": 49 }, { "epoch": 0.13065490772497143, "grad_norm": 1.140039324760437, "learning_rate": 0.0, "loss": 3.0138, "step": 50 }, { "epoch": 0.13065490772497143, "eval_loss": 2.5868451595306396, "eval_runtime": 29.1661, "eval_samples_per_second": 88.39, "eval_steps_per_second": 11.074, "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 }