| { | |
| "best_metric": 0.09947212040424347, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.2045112781954888, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02406015037593985, | |
| "grad_norm": 1.3677129745483398, | |
| "learning_rate": 5e-05, | |
| "loss": 0.617, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02406015037593985, | |
| "eval_loss": 0.7637547254562378, | |
| "eval_runtime": 13.5686, | |
| "eval_samples_per_second": 20.636, | |
| "eval_steps_per_second": 2.579, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0481203007518797, | |
| "grad_norm": 1.44648277759552, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6564, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07218045112781955, | |
| "grad_norm": 1.387004017829895, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.6, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0962406015037594, | |
| "grad_norm": 0.9299198985099792, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.3271, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.12030075187969924, | |
| "grad_norm": 0.6560674905776978, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.1985, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1443609022556391, | |
| "grad_norm": 0.2988099753856659, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.1393, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16842105263157894, | |
| "grad_norm": 0.7401416897773743, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.1598, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1924812030075188, | |
| "grad_norm": 0.36938604712486267, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.121, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.21654135338345865, | |
| "grad_norm": 0.22712348401546478, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.1083, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.24060150375939848, | |
| "grad_norm": 0.4414423108100891, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.1249, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2646616541353383, | |
| "grad_norm": 0.37042954564094543, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.1205, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2887218045112782, | |
| "grad_norm": 0.10716293007135391, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.1069, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.31278195488721805, | |
| "grad_norm": 0.17751727998256683, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.1103, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3368421052631579, | |
| "grad_norm": 0.2624951899051666, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1109, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3609022556390977, | |
| "grad_norm": 0.18556217849254608, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.1058, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3849624060150376, | |
| "grad_norm": 0.03690000995993614, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.1023, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.40902255639097745, | |
| "grad_norm": 0.08423636853694916, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.1017, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4330827067669173, | |
| "grad_norm": 0.24046602845191956, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.1048, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 0.1586795449256897, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.1007, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.48120300751879697, | |
| "grad_norm": 0.09818024188280106, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0983, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5052631578947369, | |
| "grad_norm": 0.09239000827074051, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0997, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5293233082706766, | |
| "grad_norm": 0.11240614205598831, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.1022, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5533834586466165, | |
| "grad_norm": 0.10554036498069763, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.1031, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5774436090225564, | |
| "grad_norm": 0.10103685408830643, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.1021, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6015037593984962, | |
| "grad_norm": 0.07299824804067612, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0998, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6015037593984962, | |
| "eval_loss": 0.09957851469516754, | |
| "eval_runtime": 13.5326, | |
| "eval_samples_per_second": 20.691, | |
| "eval_steps_per_second": 2.586, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6255639097744361, | |
| "grad_norm": 0.02670644409954548, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0999, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.649624060150376, | |
| "grad_norm": 0.02877388522028923, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0983, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6736842105263158, | |
| "grad_norm": 0.031500719487667084, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.096, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6977443609022557, | |
| "grad_norm": 0.048165999352931976, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0958, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.7218045112781954, | |
| "grad_norm": 0.09344542026519775, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0965, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7458646616541353, | |
| "grad_norm": 0.12452530115842819, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0986, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.7699248120300752, | |
| "grad_norm": 0.12313531339168549, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1015, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.793984962406015, | |
| "grad_norm": 0.1442219614982605, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.105, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8180451127819549, | |
| "grad_norm": 0.06111603602766991, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.1014, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 0.027853839099407196, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0995, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8661654135338346, | |
| "grad_norm": 0.13428233563899994, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.1005, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8902255639097745, | |
| "grad_norm": 0.12706559896469116, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.1006, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "grad_norm": 0.15370112657546997, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1004, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.9383458646616541, | |
| "grad_norm": 0.1685517281293869, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.1, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.9624060150375939, | |
| "grad_norm": 0.06856564432382584, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0956, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9864661654135338, | |
| "grad_norm": 0.1981419026851654, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.097, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.0120300751879698, | |
| "grad_norm": 0.07202955335378647, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.1529, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.0360902255639097, | |
| "grad_norm": 0.030848056077957153, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.101, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.0601503759398496, | |
| "grad_norm": 0.03846440464258194, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1012, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.0842105263157895, | |
| "grad_norm": 0.036180026829242706, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.1004, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.1082706766917294, | |
| "grad_norm": 0.025751329958438873, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0993, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.132330827067669, | |
| "grad_norm": 0.06255143880844116, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0998, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.156390977443609, | |
| "grad_norm": 0.04273088276386261, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0987, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.1804511278195489, | |
| "grad_norm": 0.02951870672404766, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0958, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.2045112781954888, | |
| "grad_norm": 0.03614836931228638, | |
| "learning_rate": 0.0, | |
| "loss": 0.0964, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.2045112781954888, | |
| "eval_loss": 0.09947212040424347, | |
| "eval_runtime": 13.5385, | |
| "eval_samples_per_second": 20.682, | |
| "eval_steps_per_second": 2.585, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0205688403853312e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |