| { | |
| "best_metric": 0.022800911217927933, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.5031446540880503, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010062893081761006, | |
| "grad_norm": 0.3639535903930664, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2333, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010062893081761006, | |
| "eval_loss": 0.4395422637462616, | |
| "eval_runtime": 30.7306, | |
| "eval_samples_per_second": 21.802, | |
| "eval_steps_per_second": 2.733, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02012578616352201, | |
| "grad_norm": 0.4397262632846832, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2646, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03018867924528302, | |
| "grad_norm": 0.5376619696617126, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.2733, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04025157232704402, | |
| "grad_norm": 0.4236920475959778, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.2062, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.050314465408805034, | |
| "grad_norm": 0.4180348813533783, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.1301, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06037735849056604, | |
| "grad_norm": 0.24690310657024384, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.0738, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07044025157232704, | |
| "grad_norm": 0.22631782293319702, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.0576, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08050314465408805, | |
| "grad_norm": 0.2507324516773224, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0559, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09056603773584905, | |
| "grad_norm": 0.15755386650562286, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.036, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.10062893081761007, | |
| "grad_norm": 0.1995922476053238, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0363, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11069182389937107, | |
| "grad_norm": 0.1199517473578453, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.0254, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.12075471698113208, | |
| "grad_norm": 0.12893110513687134, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.0282, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.13081761006289308, | |
| "grad_norm": 0.3422263264656067, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.0821, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.14088050314465408, | |
| "grad_norm": 0.2876516282558441, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0627, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1509433962264151, | |
| "grad_norm": 0.3431037366390228, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.0537, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1610062893081761, | |
| "grad_norm": 0.24425195157527924, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0486, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1710691823899371, | |
| "grad_norm": 0.3430141806602478, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0428, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1811320754716981, | |
| "grad_norm": 0.13116921484470367, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0343, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.19119496855345913, | |
| "grad_norm": 0.2921256124973297, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0277, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.20125786163522014, | |
| "grad_norm": 0.09132912009954453, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.024, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.21132075471698114, | |
| "grad_norm": 0.0867147147655487, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0217, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.22138364779874214, | |
| "grad_norm": 0.10501576960086823, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0184, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.23144654088050315, | |
| "grad_norm": 0.08421722054481506, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.013, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.24150943396226415, | |
| "grad_norm": 0.08997359871864319, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0145, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.25157232704402516, | |
| "grad_norm": 0.21365149319171906, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.023, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.25157232704402516, | |
| "eval_loss": 0.03939060494303703, | |
| "eval_runtime": 30.8538, | |
| "eval_samples_per_second": 21.715, | |
| "eval_steps_per_second": 2.723, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.26163522012578616, | |
| "grad_norm": 0.33435148000717163, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0727, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.27169811320754716, | |
| "grad_norm": 0.32047706842422485, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0474, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.28176100628930817, | |
| "grad_norm": 0.082615427672863, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0325, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2918238993710692, | |
| "grad_norm": 0.38494592905044556, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0357, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3018867924528302, | |
| "grad_norm": 0.32642385363578796, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0315, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3119496855345912, | |
| "grad_norm": 0.1752299666404724, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0231, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3220125786163522, | |
| "grad_norm": 0.31406933069229126, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0218, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3320754716981132, | |
| "grad_norm": 0.1449318379163742, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0171, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3421383647798742, | |
| "grad_norm": 0.0971163660287857, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0179, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3522012578616352, | |
| "grad_norm": 0.06397205591201782, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0136, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3622641509433962, | |
| "grad_norm": 0.09287846088409424, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0155, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3723270440251572, | |
| "grad_norm": 0.11693109571933746, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0119, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.38238993710691827, | |
| "grad_norm": 0.207436203956604, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.059, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.39245283018867927, | |
| "grad_norm": 0.23645782470703125, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0438, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4025157232704403, | |
| "grad_norm": 0.2462545931339264, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.039, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4125786163522013, | |
| "grad_norm": 0.1835210770368576, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0284, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.4226415094339623, | |
| "grad_norm": 0.16804800927639008, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0279, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.4327044025157233, | |
| "grad_norm": 0.047770529985427856, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0179, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4427672955974843, | |
| "grad_norm": 0.05572060868144035, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0162, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4528301886792453, | |
| "grad_norm": 0.04772639647126198, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0148, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4628930817610063, | |
| "grad_norm": 0.05174249783158302, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0129, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.4729559748427673, | |
| "grad_norm": 0.046342507004737854, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0095, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4830188679245283, | |
| "grad_norm": 0.05481298267841339, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.012, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4930817610062893, | |
| "grad_norm": 0.04954361915588379, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0139, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5031446540880503, | |
| "grad_norm": 0.09124169498682022, | |
| "learning_rate": 0.0, | |
| "loss": 0.0171, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5031446540880503, | |
| "eval_loss": 0.022800911217927933, | |
| "eval_runtime": 30.727, | |
| "eval_samples_per_second": 21.805, | |
| "eval_steps_per_second": 2.734, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1111570021023744e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |