| { | |
| "best_metric": 3.357673168182373, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.9026128266033253, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03800475059382423, | |
| "grad_norm": 0.33629336953163147, | |
| "learning_rate": 5e-05, | |
| "loss": 3.669, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03800475059382423, | |
| "eval_loss": 3.8881068229675293, | |
| "eval_runtime": 2.4606, | |
| "eval_samples_per_second": 72.339, | |
| "eval_steps_per_second": 9.347, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07600950118764846, | |
| "grad_norm": 0.42253753542900085, | |
| "learning_rate": 0.0001, | |
| "loss": 3.6932, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11401425178147269, | |
| "grad_norm": 0.4703884422779083, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.6224, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.15201900237529692, | |
| "grad_norm": 0.5285553932189941, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.72, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19002375296912113, | |
| "grad_norm": 0.5211747884750366, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.7434, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.22802850356294538, | |
| "grad_norm": 0.5990889072418213, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.9806, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2660332541567696, | |
| "grad_norm": 0.28917452692985535, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.6418, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.30403800475059384, | |
| "grad_norm": 0.3966493308544159, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.571, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.342042755344418, | |
| "grad_norm": 0.4186142385005951, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.5154, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.38004750593824227, | |
| "grad_norm": 0.4471973776817322, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.4972, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4180522565320665, | |
| "grad_norm": 0.5375720262527466, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 3.5775, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.45605700712589076, | |
| "grad_norm": 0.5469061136245728, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.6396, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.49406175771971494, | |
| "grad_norm": 0.7819376587867737, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.9765, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5320665083135392, | |
| "grad_norm": 0.3394373655319214, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.5144, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5700712589073634, | |
| "grad_norm": 0.3765534460544586, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 3.4602, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6080760095011877, | |
| "grad_norm": 0.36004090309143066, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 3.3679, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6460807600950119, | |
| "grad_norm": 0.40536168217658997, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 3.402, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.684085510688836, | |
| "grad_norm": 0.43434950709342957, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 3.2927, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7220902612826603, | |
| "grad_norm": 0.4626035988330841, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 3.6605, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7600950118764845, | |
| "grad_norm": 0.38905563950538635, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.4843, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7980997624703088, | |
| "grad_norm": 0.4623677432537079, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 3.4253, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.836104513064133, | |
| "grad_norm": 0.5135887861251831, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 3.3537, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8741092636579573, | |
| "grad_norm": 0.48013439774513245, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 3.4339, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9121140142517815, | |
| "grad_norm": 0.40351372957229614, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.1647, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9501187648456056, | |
| "grad_norm": 0.44421958923339844, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 3.4674, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9501187648456056, | |
| "eval_loss": 3.4557735919952393, | |
| "eval_runtime": 2.4794, | |
| "eval_samples_per_second": 71.79, | |
| "eval_steps_per_second": 9.276, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9881235154394299, | |
| "grad_norm": 0.6033377051353455, | |
| "learning_rate": 5e-05, | |
| "loss": 3.8401, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0285035629453683, | |
| "grad_norm": 0.6220775246620178, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 6.2136, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.0665083135391924, | |
| "grad_norm": 0.3605939447879791, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 3.0169, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.1045130641330165, | |
| "grad_norm": 0.4560985863208771, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 3.3652, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1425178147268409, | |
| "grad_norm": 0.5514870285987854, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 3.1878, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.180522565320665, | |
| "grad_norm": 0.5774045586585999, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 3.0743, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2185273159144894, | |
| "grad_norm": 0.7691540122032166, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.6026, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.2565320665083135, | |
| "grad_norm": 0.38054758310317993, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.9451, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.2945368171021379, | |
| "grad_norm": 0.44550177454948425, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 3.8813, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.332541567695962, | |
| "grad_norm": 0.5434937477111816, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 3.1944, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.3705463182897861, | |
| "grad_norm": 0.47107967734336853, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 3.3142, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4085510688836105, | |
| "grad_norm": 0.55793297290802, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 3.24, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.4465558194774346, | |
| "grad_norm": 0.7050827741622925, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.4012, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.484560570071259, | |
| "grad_norm": 0.976097583770752, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 3.7907, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.522565320665083, | |
| "grad_norm": 0.37063631415367126, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 3.5599, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5605700712589075, | |
| "grad_norm": 0.39631596207618713, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 3.1048, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.5985748218527316, | |
| "grad_norm": 0.4788654148578644, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 3.2364, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6365795724465557, | |
| "grad_norm": 0.5167055130004883, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 3.1073, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.67458432304038, | |
| "grad_norm": 0.6170525550842285, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.2586, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7125890736342044, | |
| "grad_norm": 0.700023889541626, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 3.5919, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.7505938242280283, | |
| "grad_norm": 0.3638046085834503, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.8131, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.7885985748218527, | |
| "grad_norm": 0.4485277235507965, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 3.6761, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.826603325415677, | |
| "grad_norm": 0.4701801538467407, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 3.2881, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.8646080760095012, | |
| "grad_norm": 0.46767908334732056, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 3.3644, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9026128266033253, | |
| "grad_norm": 0.5206577181816101, | |
| "learning_rate": 0.0, | |
| "loss": 3.0493, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9026128266033253, | |
| "eval_loss": 3.357673168182373, | |
| "eval_runtime": 2.3659, | |
| "eval_samples_per_second": 75.237, | |
| "eval_steps_per_second": 9.722, | |
| "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": 1.0671517724783411e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |