| { | |
| "best_metric": 1.5239598751068115, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06749915626054674, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013499831252109348, | |
| "grad_norm": 0.31275564432144165, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7465, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013499831252109348, | |
| "eval_loss": 1.7111924886703491, | |
| "eval_runtime": 60.3744, | |
| "eval_samples_per_second": 82.651, | |
| "eval_steps_per_second": 10.336, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026999662504218697, | |
| "grad_norm": 0.34583768248558044, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6862, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004049949375632805, | |
| "grad_norm": 0.3333629369735718, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.7035, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005399932500843739, | |
| "grad_norm": 0.21653343737125397, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.649, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006749915626054675, | |
| "grad_norm": 0.24989359080791473, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.7273, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00809989875126561, | |
| "grad_norm": 0.2923509180545807, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.6266, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009449881876476544, | |
| "grad_norm": 0.325923353433609, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.7665, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010799865001687479, | |
| "grad_norm": 0.3030674159526825, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.7743, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012149848126898413, | |
| "grad_norm": 0.3152262270450592, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.5873, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01349983125210935, | |
| "grad_norm": 0.4141990840435028, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.7246, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014849814377320284, | |
| "grad_norm": 0.47063368558883667, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.5555, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01619979750253122, | |
| "grad_norm": 0.4061478078365326, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.5787, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017549780627742154, | |
| "grad_norm": 0.5104323029518127, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.6475, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01889976375295309, | |
| "grad_norm": 0.44571298360824585, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.607, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.020249746878164023, | |
| "grad_norm": 0.3044547438621521, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.5872, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021599730003374958, | |
| "grad_norm": 0.2421780675649643, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.6613, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.022949713128585892, | |
| "grad_norm": 0.22122955322265625, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.5829, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.024299696253796826, | |
| "grad_norm": 0.242802232503891, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.6043, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02564967937900776, | |
| "grad_norm": 0.26226282119750977, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.6446, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0269996625042187, | |
| "grad_norm": 0.3033332824707031, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6284, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.028349645629429633, | |
| "grad_norm": 0.27396708726882935, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.5846, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.029699628754640568, | |
| "grad_norm": 0.2887237071990967, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.5392, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.031049611879851502, | |
| "grad_norm": 0.34173640608787537, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.6312, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03239959500506244, | |
| "grad_norm": 0.39167019724845886, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.5356, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03374957813027337, | |
| "grad_norm": 0.4541545808315277, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.4292, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03374957813027337, | |
| "eval_loss": 1.5458736419677734, | |
| "eval_runtime": 60.2586, | |
| "eval_samples_per_second": 82.81, | |
| "eval_steps_per_second": 10.355, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03509956125548431, | |
| "grad_norm": 0.1637115478515625, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5338, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03644954438069524, | |
| "grad_norm": 0.15709365904331207, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.6281, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03779952750590618, | |
| "grad_norm": 0.1496843695640564, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.5876, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03914951063111711, | |
| "grad_norm": 0.1532595306634903, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.6034, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.040499493756328046, | |
| "grad_norm": 0.17774361371994019, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.6162, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.041849476881538984, | |
| "grad_norm": 0.20477358996868134, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.6262, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.043199460006749915, | |
| "grad_norm": 0.2279857099056244, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.6413, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04454944313196085, | |
| "grad_norm": 0.26761552691459656, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.6181, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.045899426257171784, | |
| "grad_norm": 0.2836780548095703, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.661, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04724940938238272, | |
| "grad_norm": 0.28761908411979675, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.4622, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04859939250759365, | |
| "grad_norm": 0.2977994382381439, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.4873, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04994937563280459, | |
| "grad_norm": 0.35102325677871704, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.3988, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.05129935875801552, | |
| "grad_norm": 0.14832736551761627, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.6195, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05264934188322646, | |
| "grad_norm": 0.12129808962345123, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.6259, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0539993250084374, | |
| "grad_norm": 0.12143447995185852, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.5587, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05534930813364833, | |
| "grad_norm": 0.13339225947856903, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.543, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.056699291258859266, | |
| "grad_norm": 0.1377297043800354, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.5017, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0580492743840702, | |
| "grad_norm": 0.1632794588804245, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.5993, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.059399257509281135, | |
| "grad_norm": 0.17088504135608673, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.644, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.060749240634492066, | |
| "grad_norm": 0.1868760585784912, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.645, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.062099223759703004, | |
| "grad_norm": 0.21565905213356018, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.5193, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06344920688491394, | |
| "grad_norm": 0.24631474912166595, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.5493, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06479919001012488, | |
| "grad_norm": 0.2667161226272583, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.4677, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0661491731353358, | |
| "grad_norm": 0.31782612204551697, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.4427, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06749915626054674, | |
| "grad_norm": 0.36279669404029846, | |
| "learning_rate": 0.0, | |
| "loss": 1.3635, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06749915626054674, | |
| "eval_loss": 1.5239598751068115, | |
| "eval_runtime": 60.733, | |
| "eval_samples_per_second": 82.163, | |
| "eval_steps_per_second": 10.274, | |
| "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": 9.411196468225638e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |