| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 113, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.008908685968819599, |
| "grad_norm": 47.238216400146484, |
| "learning_rate": 4.166666666666666e-08, |
| "loss": 1.6878271102905273, |
| "step": 1, |
| "token_acc": 0.8026243849097867 |
| }, |
| { |
| "epoch": 0.044543429844097995, |
| "grad_norm": 42.44779968261719, |
| "learning_rate": 2.0833333333333333e-07, |
| "loss": 1.6754802465438843, |
| "step": 5, |
| "token_acc": 0.7994841162096117 |
| }, |
| { |
| "epoch": 0.08908685968819599, |
| "grad_norm": 49.14453125, |
| "learning_rate": 2.4913894091195504e-07, |
| "loss": 1.6546676635742188, |
| "step": 10, |
| "token_acc": 0.7997270914243728 |
| }, |
| { |
| "epoch": 0.133630289532294, |
| "grad_norm": 46.674034118652344, |
| "learning_rate": 2.4566120963893017e-07, |
| "loss": 1.5866923332214355, |
| "step": 15, |
| "token_acc": 0.7979928779540304 |
| }, |
| { |
| "epoch": 0.17817371937639198, |
| "grad_norm": 44.81178283691406, |
| "learning_rate": 2.3958774686174805e-07, |
| "loss": 1.5554664611816407, |
| "step": 20, |
| "token_acc": 0.799013827848644 |
| }, |
| { |
| "epoch": 0.22271714922049, |
| "grad_norm": 36.78907012939453, |
| "learning_rate": 2.3104920831241437e-07, |
| "loss": 1.3084081649780273, |
| "step": 25, |
| "token_acc": 0.803969693735994 |
| }, |
| { |
| "epoch": 0.267260579064588, |
| "grad_norm": 29.89940071105957, |
| "learning_rate": 2.2022927981322682e-07, |
| "loss": 1.2958971023559571, |
| "step": 30, |
| "token_acc": 0.8049758404441246 |
| }, |
| { |
| "epoch": 0.311804008908686, |
| "grad_norm": 28.320785522460938, |
| "learning_rate": 2.0736072572451387e-07, |
| "loss": 1.2554569244384766, |
| "step": 35, |
| "token_acc": 0.8120755517826825 |
| }, |
| { |
| "epoch": 0.35634743875278396, |
| "grad_norm": 17.16994857788086, |
| "learning_rate": 1.9272038158738265e-07, |
| "loss": 1.1012828826904297, |
| "step": 40, |
| "token_acc": 0.8207843959731543 |
| }, |
| { |
| "epoch": 0.40089086859688194, |
| "grad_norm": 14.638218879699707, |
| "learning_rate": 1.7662319868254856e-07, |
| "loss": 0.8975942611694336, |
| "step": 45, |
| "token_acc": 0.8407118055555556 |
| }, |
| { |
| "epoch": 0.44543429844098, |
| "grad_norm": 12.209929466247559, |
| "learning_rate": 1.5941546862203247e-07, |
| "loss": 0.838934326171875, |
| "step": 50, |
| "token_acc": 0.8435168162647345 |
| }, |
| { |
| "epoch": 0.48997772828507796, |
| "grad_norm": 13.096250534057617, |
| "learning_rate": 1.4146737373010233e-07, |
| "loss": 0.8201694488525391, |
| "step": 55, |
| "token_acc": 0.8506590136054422 |
| }, |
| { |
| "epoch": 0.534521158129176, |
| "grad_norm": 11.963576316833496, |
| "learning_rate": 1.2316502347383543e-07, |
| "loss": 0.8491922378540039, |
| "step": 60, |
| "token_acc": 0.8426031812038673 |
| }, |
| { |
| "epoch": 0.579064587973274, |
| "grad_norm": 11.79444694519043, |
| "learning_rate": 1.0490214826006647e-07, |
| "loss": 0.7839408874511719, |
| "step": 65, |
| "token_acc": 0.8460634547591069 |
| }, |
| { |
| "epoch": 0.623608017817372, |
| "grad_norm": 11.655221939086914, |
| "learning_rate": 8.707162928641263e-08, |
| "loss": 0.780324649810791, |
| "step": 70, |
| "token_acc": 0.8450373532550693 |
| }, |
| { |
| "epoch": 0.6681514476614699, |
| "grad_norm": 12.212353706359863, |
| "learning_rate": 7.005704666096235e-08, |
| "loss": 0.787574577331543, |
| "step": 75, |
| "token_acc": 0.8394213757935269 |
| }, |
| { |
| "epoch": 0.7126948775055679, |
| "grad_norm": 11.612573623657227, |
| "learning_rate": 5.422442761221037e-08, |
| "loss": 0.7592183113098144, |
| "step": 80, |
| "token_acc": 0.8449086161879895 |
| }, |
| { |
| "epoch": 0.7572383073496659, |
| "grad_norm": 11.407973289489746, |
| "learning_rate": 3.991437230636718e-08, |
| "loss": 0.7407634735107422, |
| "step": 85, |
| "token_acc": 0.8492975734355045 |
| }, |
| { |
| "epoch": 0.8017817371937639, |
| "grad_norm": 10.480648040771484, |
| "learning_rate": 2.7434726665869255e-08, |
| "loss": 0.7494807243347168, |
| "step": 90, |
| "token_acc": 0.8455267110062218 |
| }, |
| { |
| "epoch": 0.8463251670378619, |
| "grad_norm": 11.382109642028809, |
| "learning_rate": 1.7053959815522364e-08, |
| "loss": 0.7324390411376953, |
| "step": 95, |
| "token_acc": 0.850085360648741 |
| }, |
| { |
| "epoch": 0.89086859688196, |
| "grad_norm": 12.241870880126953, |
| "learning_rate": 8.99538862436322e-09, |
| "loss": 0.7613142013549805, |
| "step": 100, |
| "token_acc": 0.8418187640089657 |
| }, |
| { |
| "epoch": 0.9354120267260579, |
| "grad_norm": 11.869834899902344, |
| "learning_rate": 3.432373588130144e-09, |
| "loss": 0.761406135559082, |
| "step": 105, |
| "token_acc": 0.8450719009131941 |
| }, |
| { |
| "epoch": 0.9799554565701559, |
| "grad_norm": 11.23639965057373, |
| "learning_rate": 4.845894012080187e-10, |
| "loss": 0.7615683078765869, |
| "step": 110, |
| "token_acc": 0.8465909090909091 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 113, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 25, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 5.923389119261573e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
