| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009556118304744612, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003822447321897845, | |
| "grad_norm": 6.0184736251831055, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 4.6425, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003822447321897845, | |
| "eval_loss": 5.886753082275391, | |
| "eval_runtime": 235.5914, | |
| "eval_samples_per_second": 9.355, | |
| "eval_steps_per_second": 4.678, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000764489464379569, | |
| "grad_norm": 6.729464530944824, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 4.965, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011467341965693536, | |
| "grad_norm": 6.846334457397461, | |
| "learning_rate": 0.0001, | |
| "loss": 4.804, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001528978928759138, | |
| "grad_norm": 5.922602653503418, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 4.5205, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0019112236609489226, | |
| "grad_norm": 4.700122833251953, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 4.2375, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0022934683931387072, | |
| "grad_norm": 5.692227363586426, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.5447, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0026757131253284916, | |
| "grad_norm": 6.327576637268066, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 4.0891, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003057957857518276, | |
| "grad_norm": 7.014576435089111, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 4.6651, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0034402025897080604, | |
| "grad_norm": 5.033721923828125, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.0995, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0038224473218978453, | |
| "grad_norm": 4.756032943725586, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 4.1288, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00420469205408763, | |
| "grad_norm": 4.503414154052734, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 3.9138, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0045869367862774145, | |
| "grad_norm": 5.417407035827637, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.8291, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0049691815184671985, | |
| "grad_norm": 4.673385143280029, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 3.6087, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005351426250656983, | |
| "grad_norm": 4.72328519821167, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 4.0141, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005733670982846767, | |
| "grad_norm": 4.933603286743164, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.6198, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006115915715036552, | |
| "grad_norm": 4.5453972816467285, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 3.3622, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006498160447226337, | |
| "grad_norm": 4.865222930908203, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 3.2046, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006880405179416121, | |
| "grad_norm": 5.340005397796631, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.3491, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007262649911605906, | |
| "grad_norm": 4.902261257171631, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 3.2672, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0076448946437956905, | |
| "grad_norm": 5.233785152435303, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 2.9632, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008027139375985475, | |
| "grad_norm": 4.948408603668213, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.2824, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00840938410817526, | |
| "grad_norm": 5.471080303192139, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 2.6134, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.008791628840365044, | |
| "grad_norm": 5.066695213317871, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 2.939, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.009173873572554829, | |
| "grad_norm": 5.192546844482422, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 3.0767, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.009556118304744612, | |
| "grad_norm": 5.16768741607666, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 2.9899, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009556118304744612, | |
| "eval_loss": 2.9074714183807373, | |
| "eval_runtime": 237.9901, | |
| "eval_samples_per_second": 9.261, | |
| "eval_steps_per_second": 4.63, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9934148626022400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |