| { |
| "best_metric": 1.9266914129257202, |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", |
| "epoch": 0.07399186089530152, |
| "eval_steps": 25, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0014798372179060304, |
| "grad_norm": 2.129586935043335, |
| "learning_rate": 2e-05, |
| "loss": 8.8458, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0014798372179060304, |
| "eval_loss": 2.549591064453125, |
| "eval_runtime": 27.4011, |
| "eval_samples_per_second": 41.568, |
| "eval_steps_per_second": 5.219, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0029596744358120607, |
| "grad_norm": 2.134746789932251, |
| "learning_rate": 4e-05, |
| "loss": 9.1871, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.004439511653718091, |
| "grad_norm": 2.0432419776916504, |
| "learning_rate": 6e-05, |
| "loss": 8.7238, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0059193488716241215, |
| "grad_norm": 1.9869104623794556, |
| "learning_rate": 8e-05, |
| "loss": 9.2447, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.007399186089530152, |
| "grad_norm": 1.9248343706130981, |
| "learning_rate": 0.0001, |
| "loss": 8.9723, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.008879023307436182, |
| "grad_norm": 1.9572157859802246, |
| "learning_rate": 9.987820251299122e-05, |
| "loss": 8.8129, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.010358860525342212, |
| "grad_norm": 1.7023802995681763, |
| "learning_rate": 9.951340343707852e-05, |
| "loss": 8.4475, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.011838697743248243, |
| "grad_norm": 1.5187019109725952, |
| "learning_rate": 9.890738003669029e-05, |
| "loss": 8.0999, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.013318534961154272, |
| "grad_norm": 1.5758388042449951, |
| "learning_rate": 9.806308479691595e-05, |
| "loss": 8.2545, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.014798372179060304, |
| "grad_norm": 1.7771358489990234, |
| "learning_rate": 9.698463103929542e-05, |
| "loss": 8.3517, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.016278209396966333, |
| "grad_norm": 1.8085169792175293, |
| "learning_rate": 9.567727288213005e-05, |
| "loss": 7.7781, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.017758046614872364, |
| "grad_norm": 1.7134963274002075, |
| "learning_rate": 9.414737964294636e-05, |
| "loss": 8.2057, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.019237883832778396, |
| "grad_norm": 1.593971610069275, |
| "learning_rate": 9.24024048078213e-05, |
| "loss": 8.1811, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.020717721050684423, |
| "grad_norm": 1.6796249151229858, |
| "learning_rate": 9.045084971874738e-05, |
| "loss": 8.2568, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.022197558268590455, |
| "grad_norm": 2.30429744720459, |
| "learning_rate": 8.83022221559489e-05, |
| "loss": 8.2857, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.023677395486496486, |
| "grad_norm": 1.4573338031768799, |
| "learning_rate": 8.596699001693255e-05, |
| "loss": 8.1385, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.025157232704402517, |
| "grad_norm": 1.3977992534637451, |
| "learning_rate": 8.345653031794292e-05, |
| "loss": 8.2235, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.026637069922308545, |
| "grad_norm": 1.5306203365325928, |
| "learning_rate": 8.07830737662829e-05, |
| "loss": 8.2804, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.028116907140214576, |
| "grad_norm": 1.3745988607406616, |
| "learning_rate": 7.795964517353735e-05, |
| "loss": 7.831, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.029596744358120607, |
| "grad_norm": 1.3429087400436401, |
| "learning_rate": 7.500000000000001e-05, |
| "loss": 7.5392, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.03107658157602664, |
| "grad_norm": 1.4494553804397583, |
| "learning_rate": 7.191855733945387e-05, |
| "loss": 8.4962, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.032556418793932666, |
| "grad_norm": 1.5279874801635742, |
| "learning_rate": 6.873032967079561e-05, |
| "loss": 7.8566, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.0340362560118387, |
| "grad_norm": 1.348048448562622, |
| "learning_rate": 6.545084971874738e-05, |
| "loss": 7.6185, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.03551609322974473, |
| "grad_norm": 1.3786513805389404, |
| "learning_rate": 6.209609477998338e-05, |
| "loss": 8.0027, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.03699593044765076, |
| "grad_norm": 1.4435409307479858, |
| "learning_rate": 5.868240888334653e-05, |
| "loss": 7.9214, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.03699593044765076, |
| "eval_loss": 1.9655485153198242, |
| "eval_runtime": 27.7998, |
| "eval_samples_per_second": 40.972, |
| "eval_steps_per_second": 5.144, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.03847576766555679, |
| "grad_norm": 1.4376296997070312, |
| "learning_rate": 5.522642316338268e-05, |
| "loss": 7.7903, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.03995560488346282, |
| "grad_norm": 1.3910493850708008, |
| "learning_rate": 5.174497483512506e-05, |
| "loss": 7.8588, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.04143544210136885, |
| "grad_norm": 1.4668195247650146, |
| "learning_rate": 4.825502516487497e-05, |
| "loss": 7.3172, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.04291527931927488, |
| "grad_norm": 1.402090072631836, |
| "learning_rate": 4.477357683661734e-05, |
| "loss": 7.7589, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.04439511653718091, |
| "grad_norm": 1.4813686609268188, |
| "learning_rate": 4.131759111665349e-05, |
| "loss": 7.8017, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.04587495375508694, |
| "grad_norm": 2.463548421859741, |
| "learning_rate": 3.790390522001662e-05, |
| "loss": 7.6135, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.04735479097299297, |
| "grad_norm": 1.5885082483291626, |
| "learning_rate": 3.4549150281252636e-05, |
| "loss": 8.5428, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.048834628190899, |
| "grad_norm": 1.560816764831543, |
| "learning_rate": 3.12696703292044e-05, |
| "loss": 7.8812, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.050314465408805034, |
| "grad_norm": 1.5413081645965576, |
| "learning_rate": 2.8081442660546125e-05, |
| "loss": 7.6855, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.05179430262671106, |
| "grad_norm": 1.4592106342315674, |
| "learning_rate": 2.500000000000001e-05, |
| "loss": 7.7255, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.05327413984461709, |
| "grad_norm": 1.670977234840393, |
| "learning_rate": 2.2040354826462668e-05, |
| "loss": 8.4883, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.05475397706252312, |
| "grad_norm": 1.8226683139801025, |
| "learning_rate": 1.9216926233717085e-05, |
| "loss": 8.7609, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.05623381428042915, |
| "grad_norm": 1.6706664562225342, |
| "learning_rate": 1.6543469682057106e-05, |
| "loss": 8.6615, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.05771365149833518, |
| "grad_norm": 1.6275519132614136, |
| "learning_rate": 1.4033009983067452e-05, |
| "loss": 8.1914, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.059193488716241215, |
| "grad_norm": 1.7154792547225952, |
| "learning_rate": 1.1697777844051105e-05, |
| "loss": 7.8306, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.060673325934147246, |
| "grad_norm": 1.9715549945831299, |
| "learning_rate": 9.549150281252633e-06, |
| "loss": 7.6668, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.06215316315205328, |
| "grad_norm": 1.7641280889511108, |
| "learning_rate": 7.597595192178702e-06, |
| "loss": 8.4745, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.06363300036995931, |
| "grad_norm": 1.7766765356063843, |
| "learning_rate": 5.852620357053651e-06, |
| "loss": 8.406, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.06511283758786533, |
| "grad_norm": 1.8936883211135864, |
| "learning_rate": 4.322727117869951e-06, |
| "loss": 8.5094, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.06659267480577137, |
| "grad_norm": 1.8665753602981567, |
| "learning_rate": 3.0153689607045845e-06, |
| "loss": 8.6963, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.0680725120236774, |
| "grad_norm": 2.0399463176727295, |
| "learning_rate": 1.9369152030840556e-06, |
| "loss": 8.3318, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.06955234924158342, |
| "grad_norm": 1.9355149269104004, |
| "learning_rate": 1.0926199633097157e-06, |
| "loss": 7.987, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.07103218645948946, |
| "grad_norm": 2.051863670349121, |
| "learning_rate": 4.865965629214819e-07, |
| "loss": 8.1395, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.07251202367739548, |
| "grad_norm": 2.5829217433929443, |
| "learning_rate": 1.2179748700879012e-07, |
| "loss": 8.7321, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.07399186089530152, |
| "grad_norm": 2.865070343017578, |
| "learning_rate": 0.0, |
| "loss": 7.8764, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.07399186089530152, |
| "eval_loss": 1.9266914129257202, |
| "eval_runtime": 27.9034, |
| "eval_samples_per_second": 40.819, |
| "eval_steps_per_second": 5.125, |
| "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": 1.888596025933824e+16, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
