| { | |
| "best_metric": 1.8007385730743408, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.8547008547008547, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.017094017094017096, | |
| "grad_norm": 3.938539743423462, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 3.4641, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017094017094017096, | |
| "eval_loss": 4.367037296295166, | |
| "eval_runtime": 1.8323, | |
| "eval_samples_per_second": 27.289, | |
| "eval_steps_per_second": 3.82, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03418803418803419, | |
| "grad_norm": 4.934310436248779, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 3.7733, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05128205128205128, | |
| "grad_norm": 4.855484962463379, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 3.6143, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06837606837606838, | |
| "grad_norm": 5.6892476081848145, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 3.701, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08547008547008547, | |
| "grad_norm": 4.726133823394775, | |
| "learning_rate": 0.00015, | |
| "loss": 3.2567, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10256410256410256, | |
| "grad_norm": 3.7231974601745605, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 2.7275, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11965811965811966, | |
| "grad_norm": 2.9245429039001465, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 2.7143, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.13675213675213677, | |
| "grad_norm": 3.1964733600616455, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 2.3785, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.15384615384615385, | |
| "grad_norm": 3.5964674949645996, | |
| "learning_rate": 0.00027, | |
| "loss": 2.6142, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.17094017094017094, | |
| "grad_norm": 3.1771557331085205, | |
| "learning_rate": 0.0003, | |
| "loss": 2.5761, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18803418803418803, | |
| "grad_norm": 2.4278526306152344, | |
| "learning_rate": 0.00029993535093404976, | |
| "loss": 2.1675, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 3.4053242206573486, | |
| "learning_rate": 0.00029974145946288876, | |
| "loss": 2.1913, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 3.4192192554473877, | |
| "learning_rate": 0.00029941849271855034, | |
| "loss": 2.1841, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.23931623931623933, | |
| "grad_norm": 3.6070780754089355, | |
| "learning_rate": 0.00029896672909434605, | |
| "loss": 1.6725, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2564102564102564, | |
| "grad_norm": 3.5193164348602295, | |
| "learning_rate": 0.0002983865580048935, | |
| "loss": 2.4415, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.27350427350427353, | |
| "grad_norm": 2.824167490005493, | |
| "learning_rate": 0.00029767847955044656, | |
| "loss": 2.1966, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2905982905982906, | |
| "grad_norm": 2.186579465866089, | |
| "learning_rate": 0.0002968431040858144, | |
| "loss": 2.1251, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 2.0862064361572266, | |
| "learning_rate": 0.0002958811516942438, | |
| "loss": 2.1255, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3247863247863248, | |
| "grad_norm": 2.040565013885498, | |
| "learning_rate": 0.0002947934515667162, | |
| "loss": 2.1153, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3418803418803419, | |
| "grad_norm": 2.1491634845733643, | |
| "learning_rate": 0.0002935809412871952, | |
| "loss": 2.1219, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.358974358974359, | |
| "grad_norm": 2.158245325088501, | |
| "learning_rate": 0.00029224466602444126, | |
| "loss": 2.045, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.37606837606837606, | |
| "grad_norm": 2.090855121612549, | |
| "learning_rate": 0.00029078577763108886, | |
| "loss": 1.9201, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.39316239316239315, | |
| "grad_norm": 2.34712553024292, | |
| "learning_rate": 0.0002892055336507641, | |
| "loss": 2.1339, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 2.3505215644836426, | |
| "learning_rate": 0.00028750529623409766, | |
| "loss": 2.167, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.42735042735042733, | |
| "grad_norm": 2.1497771739959717, | |
| "learning_rate": 0.0002856865309645679, | |
| "loss": 1.9427, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.42735042735042733, | |
| "eval_loss": 2.0743188858032227, | |
| "eval_runtime": 1.8525, | |
| "eval_samples_per_second": 26.991, | |
| "eval_steps_per_second": 3.779, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 2.295942544937134, | |
| "learning_rate": 0.0002837508055951863, | |
| "loss": 1.8171, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.46153846153846156, | |
| "grad_norm": 2.5262718200683594, | |
| "learning_rate": 0.00028169978869711386, | |
| "loss": 1.6738, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.47863247863247865, | |
| "grad_norm": 2.7707014083862305, | |
| "learning_rate": 0.00027953524822137317, | |
| "loss": 1.6301, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.49572649572649574, | |
| "grad_norm": 2.6095831394195557, | |
| "learning_rate": 0.00027725904997489724, | |
| "loss": 2.1898, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 2.4387624263763428, | |
| "learning_rate": 0.0002748731560122267, | |
| "loss": 2.2275, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5299145299145299, | |
| "grad_norm": 2.2945480346679688, | |
| "learning_rate": 0.00027237962294424355, | |
| "loss": 1.9293, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5470085470085471, | |
| "grad_norm": 2.197488784790039, | |
| "learning_rate": 0.0002697806001653979, | |
| "loss": 2.0488, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5641025641025641, | |
| "grad_norm": 2.2360706329345703, | |
| "learning_rate": 0.0002670783280009569, | |
| "loss": 2.0198, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5811965811965812, | |
| "grad_norm": 2.0630950927734375, | |
| "learning_rate": 0.00026427513577587217, | |
| "loss": 1.6752, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5982905982905983, | |
| "grad_norm": 2.5239932537078857, | |
| "learning_rate": 0.0002613734398069308, | |
| "loss": 1.9719, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 2.581416130065918, | |
| "learning_rate": 0.0002583757413199203, | |
| "loss": 2.0279, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6324786324786325, | |
| "grad_norm": 2.4350247383117676, | |
| "learning_rate": 0.0002552846242936032, | |
| "loss": 2.0634, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6495726495726496, | |
| "grad_norm": 2.4420244693756104, | |
| "learning_rate": 0.00025210275323235944, | |
| "loss": 2.0166, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 2.505471706390381, | |
| "learning_rate": 0.00024883287086941667, | |
| "loss": 1.8165, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6837606837606838, | |
| "grad_norm": 2.3507983684539795, | |
| "learning_rate": 0.00024547779580264874, | |
| "loss": 1.6553, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7008547008547008, | |
| "grad_norm": 2.3374176025390625, | |
| "learning_rate": 0.00024204042006497906, | |
| "loss": 1.2892, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.717948717948718, | |
| "grad_norm": 2.7650320529937744, | |
| "learning_rate": 0.0002385237066314845, | |
| "loss": 1.3018, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7350427350427351, | |
| "grad_norm": 1.938658356666565, | |
| "learning_rate": 0.00023493068686534756, | |
| "loss": 1.8023, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.7521367521367521, | |
| "grad_norm": 2.1138954162597656, | |
| "learning_rate": 0.00023126445790485917, | |
| "loss": 2.0602, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 2.6716885566711426, | |
| "learning_rate": 0.0002275281799937241, | |
| "loss": 1.9736, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7863247863247863, | |
| "grad_norm": 2.3430912494659424, | |
| "learning_rate": 0.00022372507375697015, | |
| "loss": 1.8303, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.8034188034188035, | |
| "grad_norm": 2.5371756553649902, | |
| "learning_rate": 0.00021985841742480953, | |
| "loss": 1.6751, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 2.3102569580078125, | |
| "learning_rate": 0.00021593154400684523, | |
| "loss": 1.7225, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8376068376068376, | |
| "grad_norm": 2.714444637298584, | |
| "learning_rate": 0.00021194783841905826, | |
| "loss": 1.7524, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.8547008547008547, | |
| "grad_norm": 2.427034616470337, | |
| "learning_rate": 0.00020791073456605222, | |
| "loss": 1.5867, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8547008547008547, | |
| "eval_loss": 1.8007385730743408, | |
| "eval_runtime": 1.8575, | |
| "eval_samples_per_second": 26.918, | |
| "eval_steps_per_second": 3.768, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 117, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "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": 2.09052260892672e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |