{ "best_metric": 1.8663398027420044, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.021730272986554392, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00043460545973108785, "grad_norm": 3.6428310871124268, "learning_rate": 5e-05, "loss": 7.0678, "step": 1 }, { "epoch": 0.00043460545973108785, "eval_loss": 8.863859176635742, "eval_runtime": 520.8702, "eval_samples_per_second": 29.76, "eval_steps_per_second": 3.721, "step": 1 }, { "epoch": 0.0008692109194621757, "grad_norm": 3.6137490272521973, "learning_rate": 0.0001, "loss": 7.5798, "step": 2 }, { "epoch": 0.0013038163791932636, "grad_norm": 3.5387916564941406, "learning_rate": 9.989294616193017e-05, "loss": 7.8649, "step": 3 }, { "epoch": 0.0017384218389243514, "grad_norm": 3.1044230461120605, "learning_rate": 9.957224306869053e-05, "loss": 7.3023, "step": 4 }, { "epoch": 0.0021730272986554395, "grad_norm": 3.1415839195251465, "learning_rate": 9.903926402016153e-05, "loss": 6.8687, "step": 5 }, { "epoch": 0.002607632758386527, "grad_norm": 2.928459405899048, "learning_rate": 9.829629131445342e-05, "loss": 6.8827, "step": 6 }, { "epoch": 0.003042238218117615, "grad_norm": 4.029196262359619, "learning_rate": 9.73465064747553e-05, "loss": 6.9884, "step": 7 }, { "epoch": 0.003476843677848703, "grad_norm": 5.686116695404053, "learning_rate": 9.619397662556435e-05, "loss": 7.7616, "step": 8 }, { "epoch": 0.0039114491375797904, "grad_norm": 5.42177677154541, "learning_rate": 9.484363707663442e-05, "loss": 7.391, "step": 9 }, { "epoch": 0.004346054597310879, "grad_norm": 5.021265029907227, "learning_rate": 9.330127018922194e-05, "loss": 6.7983, "step": 10 }, { "epoch": 0.004780660057041967, "grad_norm": 6.333199977874756, "learning_rate": 9.157348061512727e-05, "loss": 6.7481, "step": 11 }, { "epoch": 0.005215265516773054, "grad_norm": 7.418224811553955, "learning_rate": 8.966766701456177e-05, "loss": 6.6947, "step": 12 }, { "epoch": 0.005649870976504143, "grad_norm": 3.2496867179870605, "learning_rate": 8.759199037394887e-05, "loss": 3.9873, "step": 13 }, { "epoch": 0.00608447643623523, "grad_norm": 4.192821025848389, "learning_rate": 8.535533905932738e-05, "loss": 2.7285, "step": 14 }, { "epoch": 0.006519081895966318, "grad_norm": 3.1794285774230957, "learning_rate": 8.296729075500344e-05, "loss": 2.5878, "step": 15 }, { "epoch": 0.006953687355697406, "grad_norm": 3.229170799255371, "learning_rate": 8.043807145043604e-05, "loss": 2.4362, "step": 16 }, { "epoch": 0.007388292815428494, "grad_norm": 3.8524668216705322, "learning_rate": 7.777851165098012e-05, "loss": 2.8875, "step": 17 }, { "epoch": 0.007822898275159581, "grad_norm": 3.6905882358551025, "learning_rate": 7.500000000000001e-05, "loss": 2.9941, "step": 18 }, { "epoch": 0.00825750373489067, "grad_norm": 4.126130104064941, "learning_rate": 7.211443451095007e-05, "loss": 3.7596, "step": 19 }, { "epoch": 0.008692109194621758, "grad_norm": 4.413054943084717, "learning_rate": 6.91341716182545e-05, "loss": 4.2052, "step": 20 }, { "epoch": 0.009126714654352846, "grad_norm": 5.591436862945557, "learning_rate": 6.607197326515808e-05, "loss": 4.5358, "step": 21 }, { "epoch": 0.009561320114083933, "grad_norm": 5.638125896453857, "learning_rate": 6.294095225512603e-05, "loss": 4.1111, "step": 22 }, { "epoch": 0.00999592557381502, "grad_norm": 8.838471412658691, "learning_rate": 5.9754516100806423e-05, "loss": 3.7575, "step": 23 }, { "epoch": 0.010430531033546108, "grad_norm": 9.507844924926758, "learning_rate": 5.6526309611002594e-05, "loss": 3.5695, "step": 24 }, { "epoch": 0.010865136493277196, "grad_norm": 10.272314071655273, "learning_rate": 5.327015646150716e-05, "loss": 3.5708, "step": 25 }, { "epoch": 0.010865136493277196, "eval_loss": 2.611330509185791, "eval_runtime": 938.3058, "eval_samples_per_second": 16.52, "eval_steps_per_second": 2.065, "step": 25 }, { "epoch": 0.011299741953008285, "grad_norm": 4.896826267242432, "learning_rate": 5e-05, "loss": 1.9688, "step": 26 }, { "epoch": 0.011734347412739373, "grad_norm": 5.283179759979248, "learning_rate": 4.6729843538492847e-05, "loss": 1.6019, "step": 27 }, { "epoch": 0.01216895287247046, "grad_norm": 4.623892784118652, "learning_rate": 4.347369038899744e-05, "loss": 1.2992, "step": 28 }, { "epoch": 0.012603558332201548, "grad_norm": 3.667201519012451, "learning_rate": 4.0245483899193595e-05, "loss": 1.601, "step": 29 }, { "epoch": 0.013038163791932636, "grad_norm": 2.6739249229431152, "learning_rate": 3.705904774487396e-05, "loss": 1.7889, "step": 30 }, { "epoch": 0.013472769251663724, "grad_norm": 2.9542391300201416, "learning_rate": 3.392802673484193e-05, "loss": 2.5814, "step": 31 }, { "epoch": 0.013907374711394811, "grad_norm": 3.9561479091644287, "learning_rate": 3.086582838174551e-05, "loss": 3.0254, "step": 32 }, { "epoch": 0.0143419801711259, "grad_norm": 6.196057319641113, "learning_rate": 2.7885565489049946e-05, "loss": 2.8031, "step": 33 }, { "epoch": 0.014776585630856988, "grad_norm": 5.7320876121521, "learning_rate": 2.500000000000001e-05, "loss": 3.0618, "step": 34 }, { "epoch": 0.015211191090588076, "grad_norm": 7.060523986816406, "learning_rate": 2.2221488349019903e-05, "loss": 2.7292, "step": 35 }, { "epoch": 0.015645796550319162, "grad_norm": 7.061924934387207, "learning_rate": 1.9561928549563968e-05, "loss": 2.3804, "step": 36 }, { "epoch": 0.016080402010050253, "grad_norm": 8.16179084777832, "learning_rate": 1.703270924499656e-05, "loss": 2.4146, "step": 37 }, { "epoch": 0.01651500746978134, "grad_norm": 3.796286106109619, "learning_rate": 1.4644660940672627e-05, "loss": 2.2274, "step": 38 }, { "epoch": 0.016949612929512428, "grad_norm": 3.4712982177734375, "learning_rate": 1.2408009626051137e-05, "loss": 1.2515, "step": 39 }, { "epoch": 0.017384218389243516, "grad_norm": 3.254138946533203, "learning_rate": 1.0332332985438248e-05, "loss": 0.9577, "step": 40 }, { "epoch": 0.017818823848974603, "grad_norm": 3.0390448570251465, "learning_rate": 8.426519384872733e-06, "loss": 1.1358, "step": 41 }, { "epoch": 0.01825342930870569, "grad_norm": 2.8244662284851074, "learning_rate": 6.698729810778065e-06, "loss": 1.1089, "step": 42 }, { "epoch": 0.01868803476843678, "grad_norm": 2.83131742477417, "learning_rate": 5.156362923365588e-06, "loss": 1.5349, "step": 43 }, { "epoch": 0.019122640228167866, "grad_norm": 3.1617980003356934, "learning_rate": 3.8060233744356633e-06, "loss": 2.025, "step": 44 }, { "epoch": 0.019557245687898954, "grad_norm": 3.827831268310547, "learning_rate": 2.653493525244721e-06, "loss": 2.6416, "step": 45 }, { "epoch": 0.01999185114763004, "grad_norm": 3.7935428619384766, "learning_rate": 1.70370868554659e-06, "loss": 2.6091, "step": 46 }, { "epoch": 0.02042645660736113, "grad_norm": 3.7722864151000977, "learning_rate": 9.607359798384785e-07, "loss": 2.6035, "step": 47 }, { "epoch": 0.020861062067092217, "grad_norm": 3.868345022201538, "learning_rate": 4.277569313094809e-07, "loss": 2.4314, "step": 48 }, { "epoch": 0.021295667526823304, "grad_norm": 5.436539173126221, "learning_rate": 1.0705383806982606e-07, "loss": 2.1646, "step": 49 }, { "epoch": 0.021730272986554392, "grad_norm": 6.8189239501953125, "learning_rate": 0.0, "loss": 2.1201, "step": 50 }, { "epoch": 0.021730272986554392, "eval_loss": 1.8663398027420044, "eval_runtime": 697.6266, "eval_samples_per_second": 22.22, "eval_steps_per_second": 2.778, "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": 5.624057810649088e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }