| { | |
| "best_metric": 0.7138856053352356, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.024351637647631805, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00048703275295263604, | |
| "grad_norm": 0.9803401231765747, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7861, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00048703275295263604, | |
| "eval_loss": 0.8942872285842896, | |
| "eval_runtime": 51.9273, | |
| "eval_samples_per_second": 66.612, | |
| "eval_steps_per_second": 8.339, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009740655059052721, | |
| "grad_norm": 1.1294515132904053, | |
| "learning_rate": 4e-05, | |
| "loss": 0.7208, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014610982588579083, | |
| "grad_norm": 0.9016605019569397, | |
| "learning_rate": 6e-05, | |
| "loss": 0.7667, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0019481310118105442, | |
| "grad_norm": 0.7527462244033813, | |
| "learning_rate": 8e-05, | |
| "loss": 0.7398, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0024351637647631805, | |
| "grad_norm": 0.9840023517608643, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7867, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0029221965177158166, | |
| "grad_norm": 0.9419175386428833, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.8, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0034092292706684527, | |
| "grad_norm": 0.7598497271537781, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.7592, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0038962620236210883, | |
| "grad_norm": 0.7673574686050415, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.9013, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004383294776573725, | |
| "grad_norm": 0.7381260395050049, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.7764, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004870327529526361, | |
| "grad_norm": 0.714454174041748, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.7444, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005357360282478997, | |
| "grad_norm": 0.6722792387008667, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.7756, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005844393035431633, | |
| "grad_norm": 0.635112464427948, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.6944, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006331425788384269, | |
| "grad_norm": 0.678276538848877, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.8756, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006818458541336905, | |
| "grad_norm": 0.6368759274482727, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.78, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0073054912942895405, | |
| "grad_norm": 0.7172012329101562, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.7305, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007792524047242177, | |
| "grad_norm": 0.7138480544090271, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.739, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008279556800194814, | |
| "grad_norm": 0.7303044199943542, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.7779, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00876658955314745, | |
| "grad_norm": 0.662376344203949, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.7247, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009253622306100086, | |
| "grad_norm": 0.7490028142929077, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.795, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009740655059052722, | |
| "grad_norm": 0.7047131061553955, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.7535, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010227687812005358, | |
| "grad_norm": 0.7217375040054321, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.768, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010714720564957994, | |
| "grad_norm": 0.6535186171531677, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.7139, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01120175331791063, | |
| "grad_norm": 0.6596193909645081, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.7265, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011688786070863266, | |
| "grad_norm": 0.6467200517654419, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.7714, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.012175818823815902, | |
| "grad_norm": 0.634857714176178, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.7147, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012175818823815902, | |
| "eval_loss": 0.7277498245239258, | |
| "eval_runtime": 51.908, | |
| "eval_samples_per_second": 66.637, | |
| "eval_steps_per_second": 8.342, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012662851576768538, | |
| "grad_norm": 0.6293425559997559, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.8072, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.013149884329721175, | |
| "grad_norm": 0.6541574597358704, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.7148, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01363691708267381, | |
| "grad_norm": 0.699476957321167, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 0.7722, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.014123949835626447, | |
| "grad_norm": 0.6306124925613403, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.7482, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.014610982588579081, | |
| "grad_norm": 0.6237121224403381, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.6539, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015098015341531717, | |
| "grad_norm": 0.712128758430481, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.6752, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.015585048094484353, | |
| "grad_norm": 0.6385212540626526, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.6965, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.01607208084743699, | |
| "grad_norm": 0.6857041120529175, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.7628, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.016559113600389627, | |
| "grad_norm": 0.6993204951286316, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 0.7362, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.017046146353342263, | |
| "grad_norm": 0.7859645485877991, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8235, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0175331791062949, | |
| "grad_norm": 0.6398217082023621, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.6597, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.018020211859247535, | |
| "grad_norm": 0.7026098966598511, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 0.6772, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.01850724461220017, | |
| "grad_norm": 0.7147570848464966, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.747, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.018994277365152808, | |
| "grad_norm": 0.7010482549667358, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.6467, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.019481310118105444, | |
| "grad_norm": 0.6586910486221313, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.7252, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01996834287105808, | |
| "grad_norm": 0.673101007938385, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.6697, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.020455375624010716, | |
| "grad_norm": 0.7123458981513977, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.6856, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.020942408376963352, | |
| "grad_norm": 0.7723951935768127, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 0.6852, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.021429441129915988, | |
| "grad_norm": 0.7186630368232727, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.6545, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.021916473882868624, | |
| "grad_norm": 0.7315675616264343, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.71, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02240350663582126, | |
| "grad_norm": 0.7585425972938538, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 0.6676, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.022890539388773896, | |
| "grad_norm": 0.7263960242271423, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.6473, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.023377572141726533, | |
| "grad_norm": 0.7787749171257019, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.6453, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.02386460489467917, | |
| "grad_norm": 0.8783103227615356, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.7039, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.024351637647631805, | |
| "grad_norm": 0.9412726759910583, | |
| "learning_rate": 0.0, | |
| "loss": 0.5764, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.024351637647631805, | |
| "eval_loss": 0.7138856053352356, | |
| "eval_runtime": 51.8403, | |
| "eval_samples_per_second": 66.724, | |
| "eval_steps_per_second": 8.353, | |
| "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": 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": 3603404933824512.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |