| { | |
| "best_metric": 0.7101312875747681, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.03241885156218341, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012967540624873365, | |
| "grad_norm": 16.785573959350586, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 43.7265, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012967540624873365, | |
| "eval_loss": 1.705428123474121, | |
| "eval_runtime": 2.9276, | |
| "eval_samples_per_second": 17.079, | |
| "eval_steps_per_second": 4.441, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002593508124974673, | |
| "grad_norm": 28.982810974121094, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 42.8946, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0038902621874620093, | |
| "grad_norm": 32.87180709838867, | |
| "learning_rate": 0.0001, | |
| "loss": 40.5252, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005187016249949346, | |
| "grad_norm": 44.707279205322266, | |
| "learning_rate": 9.997376600647783e-05, | |
| "loss": 37.9476, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006483770312436682, | |
| "grad_norm": 36.72836685180664, | |
| "learning_rate": 9.989509461357426e-05, | |
| "loss": 32.5188, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0077805243749240185, | |
| "grad_norm": 38.171810150146484, | |
| "learning_rate": 9.976407754861426e-05, | |
| "loss": 25.5456, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009077278437411355, | |
| "grad_norm": 57.68375015258789, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 23.8212, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010374032499898692, | |
| "grad_norm": 31.480140686035156, | |
| "learning_rate": 9.934567829727386e-05, | |
| "loss": 17.8454, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011670786562386027, | |
| "grad_norm": 31.195682525634766, | |
| "learning_rate": 9.905878394570453e-05, | |
| "loss": 21.7711, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012967540624873364, | |
| "grad_norm": 27.705665588378906, | |
| "learning_rate": 9.872051902290737e-05, | |
| "loss": 27.2241, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0142642946873607, | |
| "grad_norm": 27.043445587158203, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 33.6918, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015561048749848037, | |
| "grad_norm": 33.10136413574219, | |
| "learning_rate": 9.789151450663723e-05, | |
| "loss": 42.3679, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.016857802812335374, | |
| "grad_norm": 22.521921157836914, | |
| "learning_rate": 9.740174149534693e-05, | |
| "loss": 41.087, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01815455687482271, | |
| "grad_norm": 19.09137535095215, | |
| "learning_rate": 9.686252995020249e-05, | |
| "loss": 34.6201, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.019451310937310045, | |
| "grad_norm": 15.93561840057373, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 28.9021, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.020748064999797384, | |
| "grad_norm": 13.309250831604004, | |
| "learning_rate": 9.563836295460398e-05, | |
| "loss": 19.9195, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02204481906228472, | |
| "grad_norm": 10.42359447479248, | |
| "learning_rate": 9.495483482810688e-05, | |
| "loss": 11.9618, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.023341573124772055, | |
| "grad_norm": 15.537765502929688, | |
| "learning_rate": 9.422472115147382e-05, | |
| "loss": 14.3353, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02463832718725939, | |
| "grad_norm": 11.342974662780762, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 9.9775, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02593508124974673, | |
| "grad_norm": 14.146580696105957, | |
| "learning_rate": 9.2628195591462e-05, | |
| "loss": 14.0379, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.027231835312234064, | |
| "grad_norm": 15.346806526184082, | |
| "learning_rate": 9.176364518546989e-05, | |
| "loss": 13.1845, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0285285893747214, | |
| "grad_norm": 14.695765495300293, | |
| "learning_rate": 9.08562300137157e-05, | |
| "loss": 18.4925, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.029825343437208735, | |
| "grad_norm": 15.247776985168457, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 23.5953, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.031122097499696074, | |
| "grad_norm": 19.08445930480957, | |
| "learning_rate": 8.891708613973126e-05, | |
| "loss": 37.6228, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03241885156218341, | |
| "grad_norm": 23.201744079589844, | |
| "learning_rate": 8.788761839251559e-05, | |
| "loss": 35.105, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03241885156218341, | |
| "eval_loss": 0.7101312875747681, | |
| "eval_runtime": 2.9691, | |
| "eval_samples_per_second": 16.84, | |
| "eval_steps_per_second": 4.378, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 95, | |
| "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": 2.6303741225336832e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |