| { | |
| "best_metric": 0.871764600276947, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.12439744985227803, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004975897994091121, | |
| "grad_norm": 0.23871222138404846, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.0835, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004975897994091121, | |
| "eval_loss": 1.137823224067688, | |
| "eval_runtime": 1.0224, | |
| "eval_samples_per_second": 48.904, | |
| "eval_steps_per_second": 12.715, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009951795988182242, | |
| "grad_norm": 0.41071704030036926, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.9659, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.014927693982273364, | |
| "grad_norm": 0.39753258228302, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0785, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.019903591976364484, | |
| "grad_norm": 0.3230868875980377, | |
| "learning_rate": 9.997376600647783e-05, | |
| "loss": 1.0597, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.024879489970455606, | |
| "grad_norm": 0.27026239037513733, | |
| "learning_rate": 9.989509461357426e-05, | |
| "loss": 1.0604, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.029855387964546728, | |
| "grad_norm": 0.43072497844696045, | |
| "learning_rate": 9.976407754861426e-05, | |
| "loss": 1.088, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.034831285958637846, | |
| "grad_norm": 0.2670774459838867, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 1.0971, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03980718395272897, | |
| "grad_norm": 0.2514101266860962, | |
| "learning_rate": 9.934567829727386e-05, | |
| "loss": 1.1188, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04478308194682009, | |
| "grad_norm": 0.23422400653362274, | |
| "learning_rate": 9.905878394570453e-05, | |
| "loss": 1.1227, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04975897994091121, | |
| "grad_norm": 0.28173166513442993, | |
| "learning_rate": 9.872051902290737e-05, | |
| "loss": 1.1324, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.054734877935002334, | |
| "grad_norm": 0.2882803976535797, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 1.1169, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.059710775929093456, | |
| "grad_norm": 0.38014933466911316, | |
| "learning_rate": 9.789151450663723e-05, | |
| "loss": 1.0644, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06468667392318457, | |
| "grad_norm": 0.19597893953323364, | |
| "learning_rate": 9.740174149534693e-05, | |
| "loss": 1.0606, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06966257191727569, | |
| "grad_norm": 0.20651479065418243, | |
| "learning_rate": 9.686252995020249e-05, | |
| "loss": 0.866, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07463846991136681, | |
| "grad_norm": 0.22201478481292725, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 0.943, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07961436790545794, | |
| "grad_norm": 0.19648012518882751, | |
| "learning_rate": 9.563836295460398e-05, | |
| "loss": 0.8928, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08459026589954906, | |
| "grad_norm": 0.1876300871372223, | |
| "learning_rate": 9.495483482810688e-05, | |
| "loss": 0.964, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08956616389364018, | |
| "grad_norm": 0.19657588005065918, | |
| "learning_rate": 9.422472115147382e-05, | |
| "loss": 0.9633, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0945420618877313, | |
| "grad_norm": 0.19236579537391663, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 0.9711, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09951795988182242, | |
| "grad_norm": 0.2960802912712097, | |
| "learning_rate": 9.2628195591462e-05, | |
| "loss": 1.042, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10449385787591355, | |
| "grad_norm": 0.22051385045051575, | |
| "learning_rate": 9.176364518546989e-05, | |
| "loss": 0.9778, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.10946975587000467, | |
| "grad_norm": 0.22082725167274475, | |
| "learning_rate": 9.08562300137157e-05, | |
| "loss": 1.0256, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.11444565386409579, | |
| "grad_norm": 0.23512785136699677, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 1.0135, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.11942155185818691, | |
| "grad_norm": 0.25989964604377747, | |
| "learning_rate": 8.891708613973126e-05, | |
| "loss": 0.9302, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12439744985227803, | |
| "grad_norm": 0.3857329487800598, | |
| "learning_rate": 8.788761839251559e-05, | |
| "loss": 0.9751, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12439744985227803, | |
| "eval_loss": 0.871764600276947, | |
| "eval_runtime": 1.0251, | |
| "eval_samples_per_second": 48.774, | |
| "eval_steps_per_second": 12.681, | |
| "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": 4.16708196040704e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |