{ "best_metric": 1.3699287176132202, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.013988948730502902, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0002797789746100581, "grad_norm": 0.6465584635734558, "learning_rate": 5e-05, "loss": 2.118, "step": 1 }, { "epoch": 0.0002797789746100581, "eval_loss": 4.790634632110596, "eval_runtime": 289.2395, "eval_samples_per_second": 83.253, "eval_steps_per_second": 10.407, "step": 1 }, { "epoch": 0.0005595579492201162, "grad_norm": 2.5087602138519287, "learning_rate": 0.0001, "loss": 2.6891, "step": 2 }, { "epoch": 0.0008393369238301741, "grad_norm": 0.9508360028266907, "learning_rate": 9.989294616193017e-05, "loss": 2.0486, "step": 3 }, { "epoch": 0.0011191158984402323, "grad_norm": 2.047938108444214, "learning_rate": 9.957224306869053e-05, "loss": 2.4271, "step": 4 }, { "epoch": 0.0013988948730502902, "grad_norm": 1.5518584251403809, "learning_rate": 9.903926402016153e-05, "loss": 2.4762, "step": 5 }, { "epoch": 0.0016786738476603483, "grad_norm": 1.4775992631912231, "learning_rate": 9.829629131445342e-05, "loss": 1.7401, "step": 6 }, { "epoch": 0.0019584528222704066, "grad_norm": 1.544517993927002, "learning_rate": 9.73465064747553e-05, "loss": 1.4728, "step": 7 }, { "epoch": 0.0022382317968804646, "grad_norm": 1.8040289878845215, "learning_rate": 9.619397662556435e-05, "loss": 1.3946, "step": 8 }, { "epoch": 0.0025180107714905223, "grad_norm": 2.4660112857818604, "learning_rate": 9.484363707663442e-05, "loss": 1.7147, "step": 9 }, { "epoch": 0.0027977897461005804, "grad_norm": 2.0649449825286865, "learning_rate": 9.330127018922194e-05, "loss": 1.7031, "step": 10 }, { "epoch": 0.0030775687207106384, "grad_norm": 2.4061238765716553, "learning_rate": 9.157348061512727e-05, "loss": 1.9757, "step": 11 }, { "epoch": 0.0033573476953206965, "grad_norm": 2.4563279151916504, "learning_rate": 8.966766701456177e-05, "loss": 1.7803, "step": 12 }, { "epoch": 0.0036371266699307546, "grad_norm": 0.5359807014465332, "learning_rate": 8.759199037394887e-05, "loss": 2.2399, "step": 13 }, { "epoch": 0.003916905644540813, "grad_norm": 1.2272266149520874, "learning_rate": 8.535533905932738e-05, "loss": 1.9047, "step": 14 }, { "epoch": 0.004196684619150871, "grad_norm": 1.0862828493118286, "learning_rate": 8.296729075500344e-05, "loss": 1.301, "step": 15 }, { "epoch": 0.004476463593760929, "grad_norm": 1.1301478147506714, "learning_rate": 8.043807145043604e-05, "loss": 1.0877, "step": 16 }, { "epoch": 0.0047562425683709865, "grad_norm": 0.6900333166122437, "learning_rate": 7.777851165098012e-05, "loss": 2.3771, "step": 17 }, { "epoch": 0.005036021542981045, "grad_norm": 1.064914584159851, "learning_rate": 7.500000000000001e-05, "loss": 1.4573, "step": 18 }, { "epoch": 0.005315800517591103, "grad_norm": 0.865281879901886, "learning_rate": 7.211443451095007e-05, "loss": 1.4298, "step": 19 }, { "epoch": 0.005595579492201161, "grad_norm": 0.8051082491874695, "learning_rate": 6.91341716182545e-05, "loss": 1.8025, "step": 20 }, { "epoch": 0.005875358466811219, "grad_norm": 1.1772493124008179, "learning_rate": 6.607197326515808e-05, "loss": 1.3583, "step": 21 }, { "epoch": 0.006155137441421277, "grad_norm": 1.3897396326065063, "learning_rate": 6.294095225512603e-05, "loss": 1.4897, "step": 22 }, { "epoch": 0.006434916416031335, "grad_norm": 1.128356695175171, "learning_rate": 5.9754516100806423e-05, "loss": 1.6885, "step": 23 }, { "epoch": 0.006714695390641393, "grad_norm": 1.4930022954940796, "learning_rate": 5.6526309611002594e-05, "loss": 1.5661, "step": 24 }, { "epoch": 0.006994474365251451, "grad_norm": 2.4758732318878174, "learning_rate": 5.327015646150716e-05, "loss": 2.3086, "step": 25 }, { "epoch": 0.006994474365251451, "eval_loss": 1.424196720123291, "eval_runtime": 289.7423, "eval_samples_per_second": 83.108, "eval_steps_per_second": 10.389, "step": 25 }, { "epoch": 0.007274253339861509, "grad_norm": 0.4121569097042084, "learning_rate": 5e-05, "loss": 2.0963, "step": 26 }, { "epoch": 0.007554032314471567, "grad_norm": 1.4843387603759766, "learning_rate": 4.6729843538492847e-05, "loss": 0.9371, "step": 27 }, { "epoch": 0.007833811289081626, "grad_norm": 0.6254419684410095, "learning_rate": 4.347369038899744e-05, "loss": 1.6501, "step": 28 }, { "epoch": 0.008113590263691683, "grad_norm": 0.8778519034385681, "learning_rate": 4.0245483899193595e-05, "loss": 1.8644, "step": 29 }, { "epoch": 0.008393369238301742, "grad_norm": 0.7816627025604248, "learning_rate": 3.705904774487396e-05, "loss": 2.0246, "step": 30 }, { "epoch": 0.0086731482129118, "grad_norm": 0.9954394698143005, "learning_rate": 3.392802673484193e-05, "loss": 1.1687, "step": 31 }, { "epoch": 0.008952927187521859, "grad_norm": 0.9548348188400269, "learning_rate": 3.086582838174551e-05, "loss": 1.219, "step": 32 }, { "epoch": 0.009232706162131916, "grad_norm": 1.2620952129364014, "learning_rate": 2.7885565489049946e-05, "loss": 1.1794, "step": 33 }, { "epoch": 0.009512485136741973, "grad_norm": 1.0139468908309937, "learning_rate": 2.500000000000001e-05, "loss": 1.2746, "step": 34 }, { "epoch": 0.009792264111352032, "grad_norm": 1.1678214073181152, "learning_rate": 2.2221488349019903e-05, "loss": 1.5503, "step": 35 }, { "epoch": 0.01007204308596209, "grad_norm": 1.3892196416854858, "learning_rate": 1.9561928549563968e-05, "loss": 1.7002, "step": 36 }, { "epoch": 0.010351822060572148, "grad_norm": 1.8984113931655884, "learning_rate": 1.703270924499656e-05, "loss": 1.9451, "step": 37 }, { "epoch": 0.010631601035182205, "grad_norm": 0.5597782135009766, "learning_rate": 1.4644660940672627e-05, "loss": 2.2111, "step": 38 }, { "epoch": 0.010911380009792264, "grad_norm": 0.8374670743942261, "learning_rate": 1.2408009626051137e-05, "loss": 1.7816, "step": 39 }, { "epoch": 0.011191158984402321, "grad_norm": 0.7428615689277649, "learning_rate": 1.0332332985438248e-05, "loss": 1.6842, "step": 40 }, { "epoch": 0.01147093795901238, "grad_norm": 0.6815183758735657, "learning_rate": 8.426519384872733e-06, "loss": 1.2802, "step": 41 }, { "epoch": 0.011750716933622438, "grad_norm": 0.8600313067436218, "learning_rate": 6.698729810778065e-06, "loss": 1.6241, "step": 42 }, { "epoch": 0.012030495908232497, "grad_norm": 0.8320652842521667, "learning_rate": 5.156362923365588e-06, "loss": 1.5642, "step": 43 }, { "epoch": 0.012310274882842554, "grad_norm": 0.804832398891449, "learning_rate": 3.8060233744356633e-06, "loss": 1.2987, "step": 44 }, { "epoch": 0.012590053857452613, "grad_norm": 0.8696397542953491, "learning_rate": 2.653493525244721e-06, "loss": 1.4127, "step": 45 }, { "epoch": 0.01286983283206267, "grad_norm": 1.23816978931427, "learning_rate": 1.70370868554659e-06, "loss": 1.2822, "step": 46 }, { "epoch": 0.013149611806672729, "grad_norm": 1.4849238395690918, "learning_rate": 9.607359798384785e-07, "loss": 1.195, "step": 47 }, { "epoch": 0.013429390781282786, "grad_norm": 1.1128456592559814, "learning_rate": 4.277569313094809e-07, "loss": 1.6807, "step": 48 }, { "epoch": 0.013709169755892845, "grad_norm": 1.8592028617858887, "learning_rate": 1.0705383806982606e-07, "loss": 1.7832, "step": 49 }, { "epoch": 0.013988948730502902, "grad_norm": 2.0527429580688477, "learning_rate": 0.0, "loss": 1.8282, "step": 50 }, { "epoch": 0.013988948730502902, "eval_loss": 1.3699287176132202, "eval_runtime": 289.4463, "eval_samples_per_second": 83.193, "eval_steps_per_second": 10.399, "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": 1.0741049715379405e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }