| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 1.4972273567467653, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.029574861367837338, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.029574861367837338, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.1107, | |
| "eval_samples_per_second": 16.074, | |
| "eval_steps_per_second": 4.179, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.059149722735674676, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.08872458410351201, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.11829944547134935, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.997376600647783e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1478743068391867, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.989509461357426e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.17744916820702403, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.976407754861426e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.20702402957486138, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2365988909426987, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.934567829727386e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.266173752310536, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.905878394570453e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2957486136783734, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.872051902290737e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.32532347504621073, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.35489833641404805, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.789151450663723e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3844731977818854, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.740174149534693e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.41404805914972276, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.686252995020249e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4436229205175601, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4731977818853974, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.563836295460398e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5027726432532348, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.495483482810688e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.532347504621072, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.422472115147382e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5619223659889094, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5914972273567468, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.2628195591462e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6210720887245841, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.176364518546989e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6506469500924215, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.08562300137157e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6802218114602587, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.7097966728280961, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.891708613973126e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7393715341959335, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.788761839251559e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7393715341959335, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.1567, | |
| "eval_samples_per_second": 15.839, | |
| "eval_steps_per_second": 4.118, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7689463955637708, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.7985212569316081, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.8280961182994455, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.457416554680877e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.8576709796672828, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.339895749467238e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.8872458410351202, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.219063752844926e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9168207024029574, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.9463955637707948, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.968033420621935e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.9759704251386322, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.838127775159452e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.024029574861368, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.705495977301078e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.0536044362292052, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.0831792975970425, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.43267549363537e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.11275415896488, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.292804904308087e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.1423290203327172, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.150843984658754e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.1719038817005545, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.201478743068392, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.861315478964841e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.2310536044362292, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.714085470206609e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.2606284658040665, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.56543989209901e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.2902033271719038, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.3197781885397413, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.264596732629e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.3493530499075785, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.112749920933111e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.378927911275416, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.960188670239154e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.4085027726432533, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.4380776340110906, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.653634995836856e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.4676524953789278, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.4972273567467653, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.346365004163145e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.4972273567467653, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.145, | |
| "eval_samples_per_second": 15.898, | |
| "eval_steps_per_second": 4.134, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 95, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.658027780734976e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |