{ "best_metric": 4.028105735778809, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.1467620620069712, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.002935241240139424, "grad_norm": 1.0239430665969849, "learning_rate": 5e-05, "loss": 3.8981, "step": 1 }, { "epoch": 0.002935241240139424, "eval_loss": 5.815672874450684, "eval_runtime": 14.0337, "eval_samples_per_second": 163.606, "eval_steps_per_second": 20.451, "step": 1 }, { "epoch": 0.005870482480278848, "grad_norm": 1.9530309438705444, "learning_rate": 0.0001, "loss": 4.5273, "step": 2 }, { "epoch": 0.008805723720418272, "grad_norm": 1.8931856155395508, "learning_rate": 9.989294616193017e-05, "loss": 4.7057, "step": 3 }, { "epoch": 0.011740964960557695, "grad_norm": 2.567333221435547, "learning_rate": 9.957224306869053e-05, "loss": 4.7502, "step": 4 }, { "epoch": 0.01467620620069712, "grad_norm": 1.4395949840545654, "learning_rate": 9.903926402016153e-05, "loss": 4.8912, "step": 5 }, { "epoch": 0.017611447440836543, "grad_norm": 1.5201845169067383, "learning_rate": 9.829629131445342e-05, "loss": 5.056, "step": 6 }, { "epoch": 0.020546688680975967, "grad_norm": 1.8026448488235474, "learning_rate": 9.73465064747553e-05, "loss": 5.1448, "step": 7 }, { "epoch": 0.02348192992111539, "grad_norm": 1.9539623260498047, "learning_rate": 9.619397662556435e-05, "loss": 5.1671, "step": 8 }, { "epoch": 0.026417171161254815, "grad_norm": 2.1242480278015137, "learning_rate": 9.484363707663442e-05, "loss": 5.4479, "step": 9 }, { "epoch": 0.02935241240139424, "grad_norm": 2.840369701385498, "learning_rate": 9.330127018922194e-05, "loss": 5.4989, "step": 10 }, { "epoch": 0.032287653641533666, "grad_norm": 3.428213357925415, "learning_rate": 9.157348061512727e-05, "loss": 5.7564, "step": 11 }, { "epoch": 0.035222894881673086, "grad_norm": 2.512089967727661, "learning_rate": 8.966766701456177e-05, "loss": 5.7054, "step": 12 }, { "epoch": 0.038158136121812514, "grad_norm": 0.8332175016403198, "learning_rate": 8.759199037394887e-05, "loss": 3.8813, "step": 13 }, { "epoch": 0.041093377361951934, "grad_norm": 1.1140429973602295, "learning_rate": 8.535533905932738e-05, "loss": 3.9291, "step": 14 }, { "epoch": 0.04402861860209136, "grad_norm": 1.1462697982788086, "learning_rate": 8.296729075500344e-05, "loss": 3.9426, "step": 15 }, { "epoch": 0.04696385984223078, "grad_norm": 1.049325704574585, "learning_rate": 8.043807145043604e-05, "loss": 3.8919, "step": 16 }, { "epoch": 0.04989910108237021, "grad_norm": 1.6786147356033325, "learning_rate": 7.777851165098012e-05, "loss": 4.1401, "step": 17 }, { "epoch": 0.05283434232250963, "grad_norm": 1.5152158737182617, "learning_rate": 7.500000000000001e-05, "loss": 4.3537, "step": 18 }, { "epoch": 0.05576958356264906, "grad_norm": 1.5700799226760864, "learning_rate": 7.211443451095007e-05, "loss": 4.1969, "step": 19 }, { "epoch": 0.05870482480278848, "grad_norm": 1.7648606300354004, "learning_rate": 6.91341716182545e-05, "loss": 4.2697, "step": 20 }, { "epoch": 0.061640066042927905, "grad_norm": 2.7130236625671387, "learning_rate": 6.607197326515808e-05, "loss": 4.3922, "step": 21 }, { "epoch": 0.06457530728306733, "grad_norm": 2.8758461475372314, "learning_rate": 6.294095225512603e-05, "loss": 4.5291, "step": 22 }, { "epoch": 0.06751054852320675, "grad_norm": 2.656874418258667, "learning_rate": 5.9754516100806423e-05, "loss": 4.454, "step": 23 }, { "epoch": 0.07044578976334617, "grad_norm": 2.822298288345337, "learning_rate": 5.6526309611002594e-05, "loss": 4.6382, "step": 24 }, { "epoch": 0.0733810310034856, "grad_norm": 2.601090669631958, "learning_rate": 5.327015646150716e-05, "loss": 4.7237, "step": 25 }, { "epoch": 0.0733810310034856, "eval_loss": 4.178318977355957, "eval_runtime": 13.9396, "eval_samples_per_second": 164.711, "eval_steps_per_second": 20.589, "step": 25 }, { "epoch": 0.07631627224362503, "grad_norm": 1.2970190048217773, "learning_rate": 5e-05, "loss": 3.3026, "step": 26 }, { "epoch": 0.07925151348376444, "grad_norm": 2.200300931930542, "learning_rate": 4.6729843538492847e-05, "loss": 3.5441, "step": 27 }, { "epoch": 0.08218675472390387, "grad_norm": 1.8640614748001099, "learning_rate": 4.347369038899744e-05, "loss": 3.6378, "step": 28 }, { "epoch": 0.0851219959640433, "grad_norm": 1.2264716625213623, "learning_rate": 4.0245483899193595e-05, "loss": 3.555, "step": 29 }, { "epoch": 0.08805723720418272, "grad_norm": 1.5774284601211548, "learning_rate": 3.705904774487396e-05, "loss": 3.8577, "step": 30 }, { "epoch": 0.09099247844432214, "grad_norm": 1.717018485069275, "learning_rate": 3.392802673484193e-05, "loss": 3.7962, "step": 31 }, { "epoch": 0.09392771968446156, "grad_norm": 1.5714224576950073, "learning_rate": 3.086582838174551e-05, "loss": 3.9705, "step": 32 }, { "epoch": 0.09686296092460099, "grad_norm": 1.3049858808517456, "learning_rate": 2.7885565489049946e-05, "loss": 3.9805, "step": 33 }, { "epoch": 0.09979820216474042, "grad_norm": 1.8364142179489136, "learning_rate": 2.500000000000001e-05, "loss": 4.1243, "step": 34 }, { "epoch": 0.10273344340487983, "grad_norm": 1.8525341749191284, "learning_rate": 2.2221488349019903e-05, "loss": 4.049, "step": 35 }, { "epoch": 0.10566868464501926, "grad_norm": 2.7360332012176514, "learning_rate": 1.9561928549563968e-05, "loss": 4.3234, "step": 36 }, { "epoch": 0.10860392588515869, "grad_norm": 1.7006713151931763, "learning_rate": 1.703270924499656e-05, "loss": 4.5007, "step": 37 }, { "epoch": 0.11153916712529811, "grad_norm": 3.3105547428131104, "learning_rate": 1.4644660940672627e-05, "loss": 3.5437, "step": 38 }, { "epoch": 0.11447440836543754, "grad_norm": 2.7863497734069824, "learning_rate": 1.2408009626051137e-05, "loss": 3.422, "step": 39 }, { "epoch": 0.11740964960557695, "grad_norm": 3.747509002685547, "learning_rate": 1.0332332985438248e-05, "loss": 3.4732, "step": 40 }, { "epoch": 0.12034489084571638, "grad_norm": 3.606635332107544, "learning_rate": 8.426519384872733e-06, "loss": 3.5158, "step": 41 }, { "epoch": 0.12328013208585581, "grad_norm": 2.7214155197143555, "learning_rate": 6.698729810778065e-06, "loss": 3.6458, "step": 42 }, { "epoch": 0.12621537332599522, "grad_norm": 1.4316763877868652, "learning_rate": 5.156362923365588e-06, "loss": 3.667, "step": 43 }, { "epoch": 0.12915061456613466, "grad_norm": 1.5033129453659058, "learning_rate": 3.8060233744356633e-06, "loss": 3.9072, "step": 44 }, { "epoch": 0.13208585580627408, "grad_norm": 3.340280294418335, "learning_rate": 2.653493525244721e-06, "loss": 3.91, "step": 45 }, { "epoch": 0.1350210970464135, "grad_norm": 1.2967872619628906, "learning_rate": 1.70370868554659e-06, "loss": 3.838, "step": 46 }, { "epoch": 0.13795633828655293, "grad_norm": 1.9000120162963867, "learning_rate": 9.607359798384785e-07, "loss": 4.0708, "step": 47 }, { "epoch": 0.14089157952669235, "grad_norm": 1.6708569526672363, "learning_rate": 4.277569313094809e-07, "loss": 4.1453, "step": 48 }, { "epoch": 0.1438268207668318, "grad_norm": 1.74222993850708, "learning_rate": 1.0705383806982606e-07, "loss": 4.2787, "step": 49 }, { "epoch": 0.1467620620069712, "grad_norm": 2.433371067047119, "learning_rate": 0.0, "loss": 4.2654, "step": 50 }, { "epoch": 0.1467620620069712, "eval_loss": 4.028105735778809, "eval_runtime": 13.8349, "eval_samples_per_second": 165.957, "eval_steps_per_second": 20.745, "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": 1.13737243557888e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }