| { | |
| "best_metric": 0.3289429247379303, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.095890410958904, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.021917808219178082, | |
| "grad_norm": 0.5309956073760986, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9998, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.021917808219178082, | |
| "eval_loss": 0.922959566116333, | |
| "eval_runtime": 9.1452, | |
| "eval_samples_per_second": 33.679, | |
| "eval_steps_per_second": 4.265, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.043835616438356165, | |
| "grad_norm": 0.5928106904029846, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0009, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06575342465753424, | |
| "grad_norm": 0.8899253010749817, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.929, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08767123287671233, | |
| "grad_norm": 0.49359744787216187, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.8794, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1095890410958904, | |
| "grad_norm": 0.3235899806022644, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.743, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.13150684931506848, | |
| "grad_norm": 0.39300400018692017, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.7132, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.15342465753424658, | |
| "grad_norm": 0.39621931314468384, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.698, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.17534246575342466, | |
| "grad_norm": 0.3912685513496399, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.5889, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.19726027397260273, | |
| "grad_norm": 0.38956552743911743, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.6055, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2191780821917808, | |
| "grad_norm": 0.3890872597694397, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.5892, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2410958904109589, | |
| "grad_norm": 0.5318353772163391, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.6983, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.26301369863013696, | |
| "grad_norm": 0.41043034195899963, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6318, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.28493150684931506, | |
| "grad_norm": 0.4656475782394409, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.6167, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.30684931506849317, | |
| "grad_norm": 0.41714492440223694, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.4218, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3287671232876712, | |
| "grad_norm": 0.3533284366130829, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.4141, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3506849315068493, | |
| "grad_norm": 0.35052743554115295, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.4045, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3726027397260274, | |
| "grad_norm": 0.27618181705474854, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3598, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.39452054794520547, | |
| "grad_norm": 0.38521695137023926, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.4095, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.41643835616438357, | |
| "grad_norm": 0.3628874123096466, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.3647, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4383561643835616, | |
| "grad_norm": 0.47639554738998413, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4001, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4602739726027397, | |
| "grad_norm": 0.34673455357551575, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.3208, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4821917808219178, | |
| "grad_norm": 0.3707224428653717, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.3568, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5041095890410959, | |
| "grad_norm": 0.4798612892627716, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.4584, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5260273972602739, | |
| "grad_norm": 0.46572381258010864, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.474, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.547945205479452, | |
| "grad_norm": 0.20725858211517334, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.3185, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.547945205479452, | |
| "eval_loss": 0.35994160175323486, | |
| "eval_runtime": 9.1482, | |
| "eval_samples_per_second": 33.668, | |
| "eval_steps_per_second": 4.263, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5698630136986301, | |
| "grad_norm": 0.18687774240970612, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3405, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5917808219178082, | |
| "grad_norm": 0.3074064254760742, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.3813, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6136986301369863, | |
| "grad_norm": 0.2549058496952057, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.3335, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6356164383561644, | |
| "grad_norm": 0.26571619510650635, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.3624, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6575342465753424, | |
| "grad_norm": 0.15630757808685303, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.3252, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6794520547945205, | |
| "grad_norm": 0.16660596430301666, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.3038, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.7013698630136986, | |
| "grad_norm": 0.17555654048919678, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.3429, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7232876712328767, | |
| "grad_norm": 0.23803046345710754, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.3609, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7452054794520548, | |
| "grad_norm": 0.4200612008571625, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3764, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7671232876712328, | |
| "grad_norm": 0.3633013963699341, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.3541, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.7890410958904109, | |
| "grad_norm": 0.24594148993492126, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.3537, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.810958904109589, | |
| "grad_norm": 0.22163063287734985, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.3045, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8328767123287671, | |
| "grad_norm": 0.2199605107307434, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.357, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8547945205479452, | |
| "grad_norm": 0.12918148934841156, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.3086, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8767123287671232, | |
| "grad_norm": 0.14422573149204254, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.3898, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8986301369863013, | |
| "grad_norm": 0.15807737410068512, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.353, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.9205479452054794, | |
| "grad_norm": 0.1642392873764038, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.3235, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.9424657534246575, | |
| "grad_norm": 0.16775958240032196, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.3054, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.9643835616438357, | |
| "grad_norm": 0.16809241473674774, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.3338, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9863013698630136, | |
| "grad_norm": 0.21692153811454773, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.3834, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0082191780821919, | |
| "grad_norm": 0.24826471507549286, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.4381, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.0301369863013699, | |
| "grad_norm": 0.22392581403255463, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.3558, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.0520547945205478, | |
| "grad_norm": 0.1663098931312561, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.3249, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.073972602739726, | |
| "grad_norm": 0.1651916652917862, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.3191, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.095890410958904, | |
| "grad_norm": 0.13541460037231445, | |
| "learning_rate": 0.0, | |
| "loss": 0.3003, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.095890410958904, | |
| "eval_loss": 0.3289429247379303, | |
| "eval_runtime": 9.3344, | |
| "eval_samples_per_second": 32.996, | |
| "eval_steps_per_second": 4.178, | |
| "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": 6.09155760273752e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |