{ "best_metric": 0.16742652654647827, "best_model_checkpoint": "miner_id_24/checkpoint-100", "epoch": 0.2403846153846154, "eval_steps": 50, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.002403846153846154, "grad_norm": 1.1853702068328857, "learning_rate": 1e-06, "loss": 0.5942, "step": 1 }, { "epoch": 0.002403846153846154, "eval_loss": 1.188090205192566, "eval_runtime": 12.7629, "eval_samples_per_second": 13.79, "eval_steps_per_second": 3.447, "step": 1 }, { "epoch": 0.004807692307692308, "grad_norm": 1.4127286672592163, "learning_rate": 2e-06, "loss": 0.7545, "step": 2 }, { "epoch": 0.007211538461538462, "grad_norm": 1.4509857892990112, "learning_rate": 3e-06, "loss": 0.6684, "step": 3 }, { "epoch": 0.009615384615384616, "grad_norm": 1.5004510879516602, "learning_rate": 4e-06, "loss": 0.7764, "step": 4 }, { "epoch": 0.01201923076923077, "grad_norm": 1.8388277292251587, "learning_rate": 4.9999999999999996e-06, "loss": 0.9586, "step": 5 }, { "epoch": 0.014423076923076924, "grad_norm": 1.8136910200119019, "learning_rate": 6e-06, "loss": 0.7699, "step": 6 }, { "epoch": 0.016826923076923076, "grad_norm": 1.7008845806121826, "learning_rate": 7e-06, "loss": 0.6792, "step": 7 }, { "epoch": 0.019230769230769232, "grad_norm": 1.8676527738571167, "learning_rate": 8e-06, "loss": 0.846, "step": 8 }, { "epoch": 0.021634615384615384, "grad_norm": 2.0595245361328125, "learning_rate": 9e-06, "loss": 0.7905, "step": 9 }, { "epoch": 0.02403846153846154, "grad_norm": 2.2339797019958496, "learning_rate": 9.999999999999999e-06, "loss": 0.8244, "step": 10 }, { "epoch": 0.026442307692307692, "grad_norm": 1.8361808061599731, "learning_rate": 1.1e-05, "loss": 0.6951, "step": 11 }, { "epoch": 0.028846153846153848, "grad_norm": 2.103513240814209, "learning_rate": 1.2e-05, "loss": 0.8303, "step": 12 }, { "epoch": 0.03125, "grad_norm": 1.8775490522384644, "learning_rate": 1.3000000000000001e-05, "loss": 0.669, "step": 13 }, { "epoch": 0.03365384615384615, "grad_norm": 2.3700971603393555, "learning_rate": 1.4e-05, "loss": 0.694, "step": 14 }, { "epoch": 0.036057692307692304, "grad_norm": 1.9218188524246216, "learning_rate": 1.5e-05, "loss": 0.5904, "step": 15 }, { "epoch": 0.038461538461538464, "grad_norm": 1.9600694179534912, "learning_rate": 1.6e-05, "loss": 0.8039, "step": 16 }, { "epoch": 0.040865384615384616, "grad_norm": 1.5222437381744385, "learning_rate": 1.7e-05, "loss": 0.3499, "step": 17 }, { "epoch": 0.04326923076923077, "grad_norm": 1.8209494352340698, "learning_rate": 1.8e-05, "loss": 0.5223, "step": 18 }, { "epoch": 0.04567307692307692, "grad_norm": 1.699657678604126, "learning_rate": 1.9e-05, "loss": 0.5394, "step": 19 }, { "epoch": 0.04807692307692308, "grad_norm": 1.1377636194229126, "learning_rate": 1.9999999999999998e-05, "loss": 0.4437, "step": 20 }, { "epoch": 0.05048076923076923, "grad_norm": 1.1468883752822876, "learning_rate": 2.1e-05, "loss": 0.2422, "step": 21 }, { "epoch": 0.052884615384615384, "grad_norm": 1.6879323720932007, "learning_rate": 2.2e-05, "loss": 0.5082, "step": 22 }, { "epoch": 0.055288461538461536, "grad_norm": 1.2606359720230103, "learning_rate": 2.3000000000000003e-05, "loss": 0.2604, "step": 23 }, { "epoch": 0.057692307692307696, "grad_norm": 2.3082375526428223, "learning_rate": 2.4e-05, "loss": 0.384, "step": 24 }, { "epoch": 0.06009615384615385, "grad_norm": 1.574620246887207, "learning_rate": 2.5e-05, "loss": 0.3298, "step": 25 }, { "epoch": 0.0625, "grad_norm": 1.626622200012207, "learning_rate": 2.6000000000000002e-05, "loss": 0.3545, "step": 26 }, { "epoch": 0.06490384615384616, "grad_norm": 1.2426509857177734, "learning_rate": 2.7000000000000002e-05, "loss": 0.2729, "step": 27 }, { "epoch": 0.0673076923076923, "grad_norm": 0.9696183800697327, "learning_rate": 2.8e-05, "loss": 0.1175, "step": 28 }, { "epoch": 0.06971153846153846, "grad_norm": 1.4881669282913208, "learning_rate": 2.9e-05, "loss": 0.3583, "step": 29 }, { "epoch": 0.07211538461538461, "grad_norm": 2.0574419498443604, "learning_rate": 3e-05, "loss": 0.4548, "step": 30 }, { "epoch": 0.07451923076923077, "grad_norm": 1.8662818670272827, "learning_rate": 2.9984895998119723e-05, "loss": 0.4393, "step": 31 }, { "epoch": 0.07692307692307693, "grad_norm": 1.9631654024124146, "learning_rate": 2.993961440992859e-05, "loss": 0.3641, "step": 32 }, { "epoch": 0.07932692307692307, "grad_norm": 1.6589587926864624, "learning_rate": 2.9864246426519023e-05, "loss": 0.2092, "step": 33 }, { "epoch": 0.08173076923076923, "grad_norm": 1.5731538534164429, "learning_rate": 2.9758943828979444e-05, "loss": 0.1979, "step": 34 }, { "epoch": 0.08413461538461539, "grad_norm": 2.270122766494751, "learning_rate": 2.9623918682727355e-05, "loss": 0.2475, "step": 35 }, { "epoch": 0.08653846153846154, "grad_norm": 1.6105525493621826, "learning_rate": 2.9459442910437798e-05, "loss": 0.2663, "step": 36 }, { "epoch": 0.0889423076923077, "grad_norm": 1.0379960536956787, "learning_rate": 2.9265847744427305e-05, "loss": 0.0822, "step": 37 }, { "epoch": 0.09134615384615384, "grad_norm": 1.4877510070800781, "learning_rate": 2.904352305959606e-05, "loss": 0.1749, "step": 38 }, { "epoch": 0.09375, "grad_norm": 1.4685450792312622, "learning_rate": 2.8792916588271762e-05, "loss": 0.176, "step": 39 }, { "epoch": 0.09615384615384616, "grad_norm": 0.9629994630813599, "learning_rate": 2.8514533018536286e-05, "loss": 0.089, "step": 40 }, { "epoch": 0.0985576923076923, "grad_norm": 0.7029222846031189, "learning_rate": 2.820893297785107e-05, "loss": 0.0612, "step": 41 }, { "epoch": 0.10096153846153846, "grad_norm": 1.3228390216827393, "learning_rate": 2.7876731904027994e-05, "loss": 0.0963, "step": 42 }, { "epoch": 0.10336538461538461, "grad_norm": 1.0944647789001465, "learning_rate": 2.7518598805819542e-05, "loss": 0.1305, "step": 43 }, { "epoch": 0.10576923076923077, "grad_norm": 0.9398048520088196, "learning_rate": 2.7135254915624213e-05, "loss": 0.0518, "step": 44 }, { "epoch": 0.10817307692307693, "grad_norm": 1.0688811540603638, "learning_rate": 2.672747223702045e-05, "loss": 0.1383, "step": 45 }, { "epoch": 0.11057692307692307, "grad_norm": 1.6178768873214722, "learning_rate": 2.6296071990054167e-05, "loss": 0.2288, "step": 46 }, { "epoch": 0.11298076923076923, "grad_norm": 1.1201609373092651, "learning_rate": 2.5841922957410875e-05, "loss": 0.045, "step": 47 }, { "epoch": 0.11538461538461539, "grad_norm": 0.6004620790481567, "learning_rate": 2.5365939734802973e-05, "loss": 0.0313, "step": 48 }, { "epoch": 0.11778846153846154, "grad_norm": 1.3882133960723877, "learning_rate": 2.4869080889095693e-05, "loss": 0.1741, "step": 49 }, { "epoch": 0.1201923076923077, "grad_norm": 1.3401930332183838, "learning_rate": 2.4352347027881003e-05, "loss": 0.1004, "step": 50 }, { "epoch": 0.1201923076923077, "eval_loss": 0.27240392565727234, "eval_runtime": 13.0087, "eval_samples_per_second": 13.529, "eval_steps_per_second": 3.382, "step": 50 }, { "epoch": 0.12259615384615384, "grad_norm": 1.4361435174942017, "learning_rate": 2.3816778784387097e-05, "loss": 0.3142, "step": 51 }, { "epoch": 0.125, "grad_norm": 1.8554904460906982, "learning_rate": 2.3263454721781537e-05, "loss": 0.3407, "step": 52 }, { "epoch": 0.12740384615384615, "grad_norm": 1.6358041763305664, "learning_rate": 2.2693489161088592e-05, "loss": 0.3693, "step": 53 }, { "epoch": 0.12980769230769232, "grad_norm": 1.2670414447784424, "learning_rate": 2.210802993709498e-05, "loss": 0.2198, "step": 54 }, { "epoch": 0.13221153846153846, "grad_norm": 0.6511435508728027, "learning_rate": 2.1508256086763372e-05, "loss": 0.1036, "step": 55 }, { "epoch": 0.1346153846153846, "grad_norm": 0.963407576084137, "learning_rate": 2.0895375474808857e-05, "loss": 0.2021, "step": 56 }, { "epoch": 0.13701923076923078, "grad_norm": 0.9860010743141174, "learning_rate": 2.0270622361220143e-05, "loss": 0.1904, "step": 57 }, { "epoch": 0.13942307692307693, "grad_norm": 0.9964820146560669, "learning_rate": 1.963525491562421e-05, "loss": 0.2028, "step": 58 }, { "epoch": 0.14182692307692307, "grad_norm": 1.0610746145248413, "learning_rate": 1.8990552683500128e-05, "loss": 0.2599, "step": 59 }, { "epoch": 0.14423076923076922, "grad_norm": 1.155051827430725, "learning_rate": 1.8337814009344716e-05, "loss": 0.2026, "step": 60 }, { "epoch": 0.1466346153846154, "grad_norm": 1.2364827394485474, "learning_rate": 1.767835342197955e-05, "loss": 0.3114, "step": 61 }, { "epoch": 0.14903846153846154, "grad_norm": 1.4400686025619507, "learning_rate": 1.7013498987264832e-05, "loss": 0.2923, "step": 62 }, { "epoch": 0.15144230769230768, "grad_norm": 1.1243747472763062, "learning_rate": 1.6344589633551502e-05, "loss": 0.1879, "step": 63 }, { "epoch": 0.15384615384615385, "grad_norm": 1.5310815572738647, "learning_rate": 1.5672972455257726e-05, "loss": 0.3505, "step": 64 }, { "epoch": 0.15625, "grad_norm": 1.378562331199646, "learning_rate": 1.5e-05, "loss": 0.2591, "step": 65 }, { "epoch": 0.15865384615384615, "grad_norm": 1.165916085243225, "learning_rate": 1.4327027544742281e-05, "loss": 0.1593, "step": 66 }, { "epoch": 0.16105769230769232, "grad_norm": 1.6357243061065674, "learning_rate": 1.36554103664485e-05, "loss": 0.2098, "step": 67 }, { "epoch": 0.16346153846153846, "grad_norm": 0.8705613613128662, "learning_rate": 1.2986501012735174e-05, "loss": 0.2364, "step": 68 }, { "epoch": 0.1658653846153846, "grad_norm": 1.1955105066299438, "learning_rate": 1.2321646578020452e-05, "loss": 0.2471, "step": 69 }, { "epoch": 0.16826923076923078, "grad_norm": 0.6993159651756287, "learning_rate": 1.1662185990655285e-05, "loss": 0.1146, "step": 70 }, { "epoch": 0.17067307692307693, "grad_norm": 1.1817651987075806, "learning_rate": 1.1009447316499875e-05, "loss": 0.2651, "step": 71 }, { "epoch": 0.17307692307692307, "grad_norm": 0.9822415709495544, "learning_rate": 1.036474508437579e-05, "loss": 0.1596, "step": 72 }, { "epoch": 0.17548076923076922, "grad_norm": 0.9577003717422485, "learning_rate": 9.729377638779859e-06, "loss": 0.1591, "step": 73 }, { "epoch": 0.1778846153846154, "grad_norm": 1.019766926765442, "learning_rate": 9.104624525191147e-06, "loss": 0.1723, "step": 74 }, { "epoch": 0.18028846153846154, "grad_norm": 0.8245567083358765, "learning_rate": 8.491743913236629e-06, "loss": 0.1188, "step": 75 }, { "epoch": 0.18269230769230768, "grad_norm": 1.1882052421569824, "learning_rate": 7.89197006290502e-06, "loss": 0.1337, "step": 76 }, { "epoch": 0.18509615384615385, "grad_norm": 1.280745506286621, "learning_rate": 7.30651083891141e-06, "loss": 0.2059, "step": 77 }, { "epoch": 0.1875, "grad_norm": 1.2217323780059814, "learning_rate": 6.736545278218464e-06, "loss": 0.1497, "step": 78 }, { "epoch": 0.18990384615384615, "grad_norm": 1.676806926727295, "learning_rate": 6.1832212156129045e-06, "loss": 0.3201, "step": 79 }, { "epoch": 0.19230769230769232, "grad_norm": 0.6855142712593079, "learning_rate": 5.647652972118998e-06, "loss": 0.0886, "step": 80 }, { "epoch": 0.19471153846153846, "grad_norm": 0.7604547142982483, "learning_rate": 5.130919110904311e-06, "loss": 0.0928, "step": 81 }, { "epoch": 0.1971153846153846, "grad_norm": 2.1085703372955322, "learning_rate": 4.6340602651970304e-06, "loss": 0.3099, "step": 82 }, { "epoch": 0.19951923076923078, "grad_norm": 0.9963690042495728, "learning_rate": 4.158077042589129e-06, "loss": 0.1087, "step": 83 }, { "epoch": 0.20192307692307693, "grad_norm": 0.759389340877533, "learning_rate": 3.7039280099458373e-06, "loss": 0.0829, "step": 84 }, { "epoch": 0.20432692307692307, "grad_norm": 1.397197961807251, "learning_rate": 3.272527762979553e-06, "loss": 0.3221, "step": 85 }, { "epoch": 0.20673076923076922, "grad_norm": 1.0370326042175293, "learning_rate": 2.86474508437579e-06, "loss": 0.1324, "step": 86 }, { "epoch": 0.2091346153846154, "grad_norm": 1.5068193674087524, "learning_rate": 2.4814011941804603e-06, "loss": 0.1953, "step": 87 }, { "epoch": 0.21153846153846154, "grad_norm": 1.1959068775177002, "learning_rate": 2.1232680959720085e-06, "loss": 0.156, "step": 88 }, { "epoch": 0.21394230769230768, "grad_norm": 1.044714331626892, "learning_rate": 1.79106702214893e-06, "loss": 0.1243, "step": 89 }, { "epoch": 0.21634615384615385, "grad_norm": 0.5632033348083496, "learning_rate": 1.4854669814637145e-06, "loss": 0.0374, "step": 90 }, { "epoch": 0.21875, "grad_norm": 1.1526877880096436, "learning_rate": 1.2070834117282414e-06, "loss": 0.1291, "step": 91 }, { "epoch": 0.22115384615384615, "grad_norm": 1.084242820739746, "learning_rate": 9.56476940403942e-07, "loss": 0.1528, "step": 92 }, { "epoch": 0.22355769230769232, "grad_norm": 0.7737883925437927, "learning_rate": 7.341522555726971e-07, "loss": 0.0896, "step": 93 }, { "epoch": 0.22596153846153846, "grad_norm": 1.2481120824813843, "learning_rate": 5.405570895622014e-07, "loss": 0.1249, "step": 94 }, { "epoch": 0.2283653846153846, "grad_norm": 0.6681073307991028, "learning_rate": 3.760813172726457e-07, "loss": 0.0611, "step": 95 }, { "epoch": 0.23076923076923078, "grad_norm": 0.6517145037651062, "learning_rate": 2.41056171020555e-07, "loss": 0.0768, "step": 96 }, { "epoch": 0.23317307692307693, "grad_norm": 0.5658121109008789, "learning_rate": 1.357535734809795e-07, "loss": 0.0474, "step": 97 }, { "epoch": 0.23557692307692307, "grad_norm": 0.8237670660018921, "learning_rate": 6.038559007141397e-08, "loss": 0.1009, "step": 98 }, { "epoch": 0.23798076923076922, "grad_norm": 0.4112774729728699, "learning_rate": 1.510400188028116e-08, "loss": 0.0223, "step": 99 }, { "epoch": 0.2403846153846154, "grad_norm": 0.7369557619094849, "learning_rate": 0.0, "loss": 0.0593, "step": 100 }, { "epoch": 0.2403846153846154, "eval_loss": 0.16742652654647827, "eval_runtime": 12.9878, "eval_samples_per_second": 13.551, "eval_steps_per_second": 3.388, "step": 100 } ], "logging_steps": 1, "max_steps": 100, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 50, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 5, "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": 3.5547217133568e+16, "train_batch_size": 4, "trial_name": null, "trial_params": null }