| { | |
| "best_metric": 1.4005824327468872, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.17152658662092624, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003430531732418525, | |
| "grad_norm": 0.16048245131969452, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3828, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003430531732418525, | |
| "eval_loss": 1.6361936330795288, | |
| "eval_runtime": 5.2611, | |
| "eval_samples_per_second": 93.326, | |
| "eval_steps_per_second": 11.785, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00686106346483705, | |
| "grad_norm": 0.1984727531671524, | |
| "learning_rate": 4e-05, | |
| "loss": 1.5358, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010291595197255575, | |
| "grad_norm": 0.1846027374267578, | |
| "learning_rate": 6e-05, | |
| "loss": 1.5176, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0137221269296741, | |
| "grad_norm": 0.16914626955986023, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5953, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.017152658662092625, | |
| "grad_norm": 0.14692679047584534, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5694, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02058319039451115, | |
| "grad_norm": 0.14007890224456787, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.5877, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.024013722126929673, | |
| "grad_norm": 0.13771860301494598, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.6277, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0274442538593482, | |
| "grad_norm": 0.1634935438632965, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.5757, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.030874785591766724, | |
| "grad_norm": 0.15958215296268463, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.5977, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03430531732418525, | |
| "grad_norm": 0.1567670851945877, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.6619, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03773584905660377, | |
| "grad_norm": 0.14375092089176178, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.5868, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0411663807890223, | |
| "grad_norm": 0.14736394584178925, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.5765, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.044596912521440824, | |
| "grad_norm": 0.15958210825920105, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.5493, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.048027444253859346, | |
| "grad_norm": 0.16828711330890656, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.5114, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.051457975986277875, | |
| "grad_norm": 0.1824846714735031, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.5466, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0548885077186964, | |
| "grad_norm": 0.1855524331331253, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 1.5199, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.058319039451114926, | |
| "grad_norm": 0.16226811707019806, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.4811, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06174957118353345, | |
| "grad_norm": 0.17381711304187775, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.5475, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06518010291595197, | |
| "grad_norm": 0.18333570659160614, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.508, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0686106346483705, | |
| "grad_norm": 0.17648880183696747, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.4546, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07204116638078903, | |
| "grad_norm": 0.19324468076229095, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.5031, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07547169811320754, | |
| "grad_norm": 0.1974824219942093, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.4409, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07890222984562607, | |
| "grad_norm": 0.18028214573860168, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.4744, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0823327615780446, | |
| "grad_norm": 0.17756997048854828, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.4487, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08576329331046312, | |
| "grad_norm": 0.1955912560224533, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.4887, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08576329331046312, | |
| "eval_loss": 1.450131893157959, | |
| "eval_runtime": 5.3446, | |
| "eval_samples_per_second": 91.868, | |
| "eval_steps_per_second": 11.6, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08919382504288165, | |
| "grad_norm": 0.20282359421253204, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 1.4278, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.09262435677530018, | |
| "grad_norm": 0.21370434761047363, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 1.4757, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09605488850771869, | |
| "grad_norm": 0.23179413378238678, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 1.454, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09948542024013722, | |
| "grad_norm": 0.20548944175243378, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 1.4483, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.10291595197255575, | |
| "grad_norm": 0.2094879001379013, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.4118, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10634648370497427, | |
| "grad_norm": 0.21441254019737244, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 1.4775, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1097770154373928, | |
| "grad_norm": 0.20647598803043365, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.3529, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.11320754716981132, | |
| "grad_norm": 0.2284150868654251, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 1.3661, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11663807890222985, | |
| "grad_norm": 0.22950738668441772, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 1.3721, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.12006861063464837, | |
| "grad_norm": 0.24025064706802368, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.3951, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1234991423670669, | |
| "grad_norm": 0.2534557580947876, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.4142, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1269296740994854, | |
| "grad_norm": 0.23205174505710602, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.4247, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.13036020583190394, | |
| "grad_norm": 0.23094086349010468, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.4081, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.13379073756432247, | |
| "grad_norm": 0.24359112977981567, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.432, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.137221269296741, | |
| "grad_norm": 0.25243625044822693, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.4048, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14065180102915953, | |
| "grad_norm": 0.27146971225738525, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.438, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.14408233276157806, | |
| "grad_norm": 0.26898500323295593, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.4197, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.14751286449399656, | |
| "grad_norm": 0.2611740231513977, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.4379, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1509433962264151, | |
| "grad_norm": 0.2807406485080719, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.4284, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.15437392795883362, | |
| "grad_norm": 0.2983769178390503, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.397, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.15780445969125215, | |
| "grad_norm": 0.29316747188568115, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 1.4727, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.16123499142367068, | |
| "grad_norm": 0.30776265263557434, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 1.5411, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1646655231560892, | |
| "grad_norm": 0.3639960289001465, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 1.4666, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1680960548885077, | |
| "grad_norm": 0.3686543405056, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 1.4686, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.17152658662092624, | |
| "grad_norm": 0.4303509593009949, | |
| "learning_rate": 0.0, | |
| "loss": 1.4826, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17152658662092624, | |
| "eval_loss": 1.4005824327468872, | |
| "eval_runtime": 5.282, | |
| "eval_samples_per_second": 92.958, | |
| "eval_steps_per_second": 11.738, | |
| "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": 2206627552296960.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |