| { | |
| "best_metric": 1.0723166465759277, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-500", | |
| "epoch": 0.34916201117318435, | |
| "eval_steps": 50, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006983240223463687, | |
| "eval_loss": 1.370945930480957, | |
| "eval_runtime": 52.0353, | |
| "eval_samples_per_second": 11.588, | |
| "eval_steps_per_second": 2.902, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006983240223463687, | |
| "grad_norm": 0.7985172271728516, | |
| "learning_rate": 4.2000000000000004e-05, | |
| "loss": 1.0747, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013966480446927373, | |
| "grad_norm": 0.5064533352851868, | |
| "learning_rate": 8.400000000000001e-05, | |
| "loss": 0.9049, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02094972067039106, | |
| "grad_norm": 0.6195475459098816, | |
| "learning_rate": 0.000126, | |
| "loss": 0.9139, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.027932960893854747, | |
| "grad_norm": 0.5974525213241577, | |
| "learning_rate": 0.00016800000000000002, | |
| "loss": 0.8777, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.034916201117318434, | |
| "grad_norm": 1.1508451700210571, | |
| "learning_rate": 0.00021, | |
| "loss": 2.2731, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.034916201117318434, | |
| "eval_loss": 1.2975257635116577, | |
| "eval_runtime": 52.0378, | |
| "eval_samples_per_second": 11.588, | |
| "eval_steps_per_second": 2.902, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04189944134078212, | |
| "grad_norm": 0.47768744826316833, | |
| "learning_rate": 0.00020974422527728155, | |
| "loss": 0.9301, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.04888268156424581, | |
| "grad_norm": 0.4488859176635742, | |
| "learning_rate": 0.0002089781472178649, | |
| "loss": 0.8632, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.055865921787709494, | |
| "grad_norm": 0.4876834750175476, | |
| "learning_rate": 0.0002077054980770496, | |
| "loss": 0.9053, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06284916201117319, | |
| "grad_norm": 0.6040335893630981, | |
| "learning_rate": 0.00020593247807352348, | |
| "loss": 0.9912, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.06983240223463687, | |
| "grad_norm": 1.2908031940460205, | |
| "learning_rate": 0.00020366772518252038, | |
| "loss": 2.3175, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06983240223463687, | |
| "eval_loss": 1.2717502117156982, | |
| "eval_runtime": 52.2379, | |
| "eval_samples_per_second": 11.543, | |
| "eval_steps_per_second": 2.891, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07681564245810056, | |
| "grad_norm": 0.556641697883606, | |
| "learning_rate": 0.0002009222730524731, | |
| "loss": 0.9617, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.08379888268156424, | |
| "grad_norm": 0.45357635617256165, | |
| "learning_rate": 0.00019770949725018733, | |
| "loss": 0.9447, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.09078212290502793, | |
| "grad_norm": 0.530303418636322, | |
| "learning_rate": 0.00019404505009642473, | |
| "loss": 0.8661, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.09776536312849161, | |
| "grad_norm": 0.544837474822998, | |
| "learning_rate": 0.0001899467844093695, | |
| "loss": 0.8477, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.10474860335195531, | |
| "grad_norm": 1.3659236431121826, | |
| "learning_rate": 0.00018543466652749268, | |
| "loss": 2.1598, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.10474860335195531, | |
| "eval_loss": 1.2168477773666382, | |
| "eval_runtime": 52.7182, | |
| "eval_samples_per_second": 11.438, | |
| "eval_steps_per_second": 2.864, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.11173184357541899, | |
| "grad_norm": 0.4937569499015808, | |
| "learning_rate": 0.00018053067903555837, | |
| "loss": 0.9268, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.11871508379888268, | |
| "grad_norm": 0.45097047090530396, | |
| "learning_rate": 0.00017525871366768012, | |
| "loss": 0.8534, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.12569832402234637, | |
| "grad_norm": 0.442699670791626, | |
| "learning_rate": 0.00016964445490919413, | |
| "loss": 0.8584, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.13268156424581007, | |
| "grad_norm": 0.49953675270080566, | |
| "learning_rate": 0.00016371525486442843, | |
| "loss": 0.7786, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.13966480446927373, | |
| "grad_norm": 1.2703161239624023, | |
| "learning_rate": 0.0001575, | |
| "loss": 1.9828, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.13966480446927373, | |
| "eval_loss": 1.1949564218521118, | |
| "eval_runtime": 51.9478, | |
| "eval_samples_per_second": 11.608, | |
| "eval_steps_per_second": 2.907, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14664804469273743, | |
| "grad_norm": 0.4466894268989563, | |
| "learning_rate": 0.00015102897041285315, | |
| "loss": 0.9098, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.15363128491620112, | |
| "grad_norm": 0.4285886287689209, | |
| "learning_rate": 0.00014433369230867077, | |
| "loss": 0.9563, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.16061452513966482, | |
| "grad_norm": 0.4518221616744995, | |
| "learning_rate": 0.0001374467844093695, | |
| "loss": 0.748, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.16759776536312848, | |
| "grad_norm": 0.6178202033042908, | |
| "learning_rate": 0.0001304017990379651, | |
| "loss": 0.9594, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.17458100558659218, | |
| "grad_norm": 1.0840479135513306, | |
| "learning_rate": 0.0001232330586550277, | |
| "loss": 2.2842, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.17458100558659218, | |
| "eval_loss": 1.148054599761963, | |
| "eval_runtime": 52.0966, | |
| "eval_samples_per_second": 11.575, | |
| "eval_steps_per_second": 2.898, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.18156424581005587, | |
| "grad_norm": 0.48482319712638855, | |
| "learning_rate": 0.00011597548864310363, | |
| "loss": 0.9017, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.18854748603351956, | |
| "grad_norm": 0.42090746760368347, | |
| "learning_rate": 0.00010866444715376263, | |
| "loss": 0.8558, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.19553072625698323, | |
| "grad_norm": 0.44340935349464417, | |
| "learning_rate": 0.00010133555284623744, | |
| "loss": 0.7718, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.20251396648044692, | |
| "grad_norm": 0.5416050553321838, | |
| "learning_rate": 9.402451135689641e-05, | |
| "loss": 0.8102, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.20949720670391062, | |
| "grad_norm": 1.8410241603851318, | |
| "learning_rate": 8.676694134497232e-05, | |
| "loss": 1.9591, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.20949720670391062, | |
| "eval_loss": 1.1187446117401123, | |
| "eval_runtime": 51.9082, | |
| "eval_samples_per_second": 11.617, | |
| "eval_steps_per_second": 2.909, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2164804469273743, | |
| "grad_norm": 0.4224921762943268, | |
| "learning_rate": 7.95982009620349e-05, | |
| "loss": 0.9126, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.22346368715083798, | |
| "grad_norm": 0.41170719265937805, | |
| "learning_rate": 7.255321559063053e-05, | |
| "loss": 0.819, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.23044692737430167, | |
| "grad_norm": 0.4653985798358917, | |
| "learning_rate": 6.566630769132923e-05, | |
| "loss": 0.8104, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.23743016759776536, | |
| "grad_norm": 0.4874189496040344, | |
| "learning_rate": 5.897102958714686e-05, | |
| "loss": 0.8025, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.24441340782122906, | |
| "grad_norm": 1.3538293838500977, | |
| "learning_rate": 5.250000000000002e-05, | |
| "loss": 2.2914, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.24441340782122906, | |
| "eval_loss": 1.0988595485687256, | |
| "eval_runtime": 53.0976, | |
| "eval_samples_per_second": 11.356, | |
| "eval_steps_per_second": 2.844, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.25139664804469275, | |
| "grad_norm": 0.40342968702316284, | |
| "learning_rate": 4.62847451355716e-05, | |
| "loss": 0.846, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.25837988826815644, | |
| "grad_norm": 0.3979036509990692, | |
| "learning_rate": 4.035554509080588e-05, | |
| "loss": 0.8506, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.26536312849162014, | |
| "grad_norm": 0.46212857961654663, | |
| "learning_rate": 3.474128633231992e-05, | |
| "loss": 0.769, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.2723463687150838, | |
| "grad_norm": 0.49502870440483093, | |
| "learning_rate": 2.946932096444165e-05, | |
| "loss": 0.9183, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.27932960893854747, | |
| "grad_norm": 1.1559889316558838, | |
| "learning_rate": 2.456533347250732e-05, | |
| "loss": 2.3416, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.27932960893854747, | |
| "eval_loss": 1.0803192853927612, | |
| "eval_runtime": 51.8492, | |
| "eval_samples_per_second": 11.63, | |
| "eval_steps_per_second": 2.912, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.28631284916201116, | |
| "grad_norm": 0.40684303641319275, | |
| "learning_rate": 2.005321559063053e-05, | |
| "loss": 0.8687, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.29329608938547486, | |
| "grad_norm": 0.3868181109428406, | |
| "learning_rate": 1.5954949903575276e-05, | |
| "loss": 0.7972, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.30027932960893855, | |
| "grad_norm": 0.415388286113739, | |
| "learning_rate": 1.2290502749812666e-05, | |
| "loss": 0.7463, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.30726256983240224, | |
| "grad_norm": 0.5129038095474243, | |
| "learning_rate": 9.077726947526898e-06, | |
| "loss": 0.8726, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.31424581005586594, | |
| "grad_norm": 1.1775633096694946, | |
| "learning_rate": 6.332274817479627e-06, | |
| "loss": 2.3677, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.31424581005586594, | |
| "eval_loss": 1.0729554891586304, | |
| "eval_runtime": 51.7424, | |
| "eval_samples_per_second": 11.654, | |
| "eval_steps_per_second": 2.918, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.32122905027932963, | |
| "grad_norm": 0.3964717388153076, | |
| "learning_rate": 4.067521926476516e-06, | |
| "loss": 0.8386, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.32821229050279327, | |
| "grad_norm": 0.3847760558128357, | |
| "learning_rate": 2.294501922950403e-06, | |
| "loss": 0.7781, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.33519553072625696, | |
| "grad_norm": 0.4073781669139862, | |
| "learning_rate": 1.021852782135112e-06, | |
| "loss": 0.752, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.34217877094972066, | |
| "grad_norm": 0.47937291860580444, | |
| "learning_rate": 2.5577472271845927e-07, | |
| "loss": 0.8182, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.34916201117318435, | |
| "grad_norm": 1.1718170642852783, | |
| "learning_rate": 0.0, | |
| "loss": 2.1401, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.34916201117318435, | |
| "eval_loss": 1.0723166465759277, | |
| "eval_runtime": 52.1413, | |
| "eval_samples_per_second": 11.565, | |
| "eval_steps_per_second": 2.896, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": 1.408558478917632e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |