| { | |
| "best_metric": 0.9173004627227783, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.12543116964565695, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005017246785826278, | |
| "grad_norm": 10.303523063659668, | |
| "learning_rate": 5e-05, | |
| "loss": 20.3254, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005017246785826278, | |
| "eval_loss": 1.2978161573410034, | |
| "eval_runtime": 4.7491, | |
| "eval_samples_per_second": 10.528, | |
| "eval_steps_per_second": 2.737, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010034493571652555, | |
| "grad_norm": 10.276937484741211, | |
| "learning_rate": 0.0001, | |
| "loss": 21.204, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.015051740357478834, | |
| "grad_norm": 9.593537330627441, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 21.2612, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02006898714330511, | |
| "grad_norm": 7.457390308380127, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 20.5788, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02508623392913139, | |
| "grad_norm": 6.21054744720459, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 20.2998, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.030103480714957668, | |
| "grad_norm": 6.098522186279297, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 16.6053, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.035120727500783946, | |
| "grad_norm": 5.591812610626221, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 15.4707, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04013797428661022, | |
| "grad_norm": 4.332369327545166, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 14.4678, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.045155221072436504, | |
| "grad_norm": 4.643701076507568, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 14.5388, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05017246785826278, | |
| "grad_norm": 4.316195487976074, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 14.6748, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.055189714644089054, | |
| "grad_norm": 6.267123222351074, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 14.7721, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.060206961429915336, | |
| "grad_norm": 4.699112892150879, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 14.8929, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06522420821574161, | |
| "grad_norm": 6.970594882965088, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 15.4255, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07024145500156789, | |
| "grad_norm": 8.095081329345703, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 16.0384, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07525870178739416, | |
| "grad_norm": 5.648611545562744, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 16.1937, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08027594857322044, | |
| "grad_norm": 4.975302219390869, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 16.0918, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08529319535904673, | |
| "grad_norm": 4.795402526855469, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 16.0038, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.09031044214487301, | |
| "grad_norm": 7.83776330947876, | |
| "learning_rate": 7.75e-05, | |
| "loss": 16.4963, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09532768893069928, | |
| "grad_norm": 3.627122163772583, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 14.9381, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.10034493571652556, | |
| "grad_norm": 3.868642568588257, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 13.6192, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10536218250235184, | |
| "grad_norm": 3.3879823684692383, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 12.9079, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11037942928817811, | |
| "grad_norm": 2.9493606090545654, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 12.8852, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.11539667607400439, | |
| "grad_norm": 3.189535617828369, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 13.657, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.12041392285983067, | |
| "grad_norm": 3.6464903354644775, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 13.5806, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12543116964565695, | |
| "grad_norm": 4.111282825469971, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 14.581, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12543116964565695, | |
| "eval_loss": 0.9173004627227783, | |
| "eval_runtime": 4.6046, | |
| "eval_samples_per_second": 10.859, | |
| "eval_steps_per_second": 2.823, | |
| "step": 25 | |
| } | |
| ], | |
| "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": 1, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.949258989581107e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |