{ "best_metric": 3.6351683139801025, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.059417706476530004, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0011883541295306002, "grad_norm": 0.8201372027397156, "learning_rate": 5e-05, "loss": 3.8926, "step": 1 }, { "epoch": 0.0011883541295306002, "eval_loss": 4.030940532684326, "eval_runtime": 6.3143, "eval_samples_per_second": 897.805, "eval_steps_per_second": 112.285, "step": 1 }, { "epoch": 0.0023767082590612004, "grad_norm": 0.8224248886108398, "learning_rate": 0.0001, "loss": 3.9675, "step": 2 }, { "epoch": 0.0035650623885918, "grad_norm": 0.7688699960708618, "learning_rate": 9.989294616193017e-05, "loss": 3.9722, "step": 3 }, { "epoch": 0.004753416518122401, "grad_norm": 0.674767255783081, "learning_rate": 9.957224306869053e-05, "loss": 3.9571, "step": 4 }, { "epoch": 0.0059417706476530005, "grad_norm": 0.7187216877937317, "learning_rate": 9.903926402016153e-05, "loss": 4.0018, "step": 5 }, { "epoch": 0.0071301247771836, "grad_norm": 0.7618054747581482, "learning_rate": 9.829629131445342e-05, "loss": 3.9173, "step": 6 }, { "epoch": 0.008318478906714201, "grad_norm": 0.7201687693595886, "learning_rate": 9.73465064747553e-05, "loss": 3.8358, "step": 7 }, { "epoch": 0.009506833036244802, "grad_norm": 0.8512358665466309, "learning_rate": 9.619397662556435e-05, "loss": 3.8229, "step": 8 }, { "epoch": 0.0106951871657754, "grad_norm": 0.8960956335067749, "learning_rate": 9.484363707663442e-05, "loss": 4.0595, "step": 9 }, { "epoch": 0.011883541295306001, "grad_norm": 1.1318275928497314, "learning_rate": 9.330127018922194e-05, "loss": 4.0056, "step": 10 }, { "epoch": 0.013071895424836602, "grad_norm": 2.0533359050750732, "learning_rate": 9.157348061512727e-05, "loss": 3.6666, "step": 11 }, { "epoch": 0.0142602495543672, "grad_norm": 2.345188617706299, "learning_rate": 8.966766701456177e-05, "loss": 3.794, "step": 12 }, { "epoch": 0.015448603683897801, "grad_norm": 1.2211459875106812, "learning_rate": 8.759199037394887e-05, "loss": 3.8926, "step": 13 }, { "epoch": 0.016636957813428402, "grad_norm": 1.8413808345794678, "learning_rate": 8.535533905932738e-05, "loss": 3.8035, "step": 14 }, { "epoch": 0.017825311942959002, "grad_norm": 1.8401907682418823, "learning_rate": 8.296729075500344e-05, "loss": 3.8536, "step": 15 }, { "epoch": 0.019013666072489603, "grad_norm": 1.4689157009124756, "learning_rate": 8.043807145043604e-05, "loss": 3.8415, "step": 16 }, { "epoch": 0.020202020202020204, "grad_norm": 1.282709002494812, "learning_rate": 7.777851165098012e-05, "loss": 3.7771, "step": 17 }, { "epoch": 0.0213903743315508, "grad_norm": 1.0199166536331177, "learning_rate": 7.500000000000001e-05, "loss": 3.7448, "step": 18 }, { "epoch": 0.0225787284610814, "grad_norm": 0.7743180394172668, "learning_rate": 7.211443451095007e-05, "loss": 3.7384, "step": 19 }, { "epoch": 0.023767082590612002, "grad_norm": 0.9698879718780518, "learning_rate": 6.91341716182545e-05, "loss": 3.7292, "step": 20 }, { "epoch": 0.024955436720142603, "grad_norm": 1.0978937149047852, "learning_rate": 6.607197326515808e-05, "loss": 3.7939, "step": 21 }, { "epoch": 0.026143790849673203, "grad_norm": 0.9687146544456482, "learning_rate": 6.294095225512603e-05, "loss": 3.9402, "step": 22 }, { "epoch": 0.027332144979203804, "grad_norm": 1.7143734693527222, "learning_rate": 5.9754516100806423e-05, "loss": 3.8069, "step": 23 }, { "epoch": 0.0285204991087344, "grad_norm": 2.6094236373901367, "learning_rate": 5.6526309611002594e-05, "loss": 3.7251, "step": 24 }, { "epoch": 0.029708853238265002, "grad_norm": 2.66898775100708, "learning_rate": 5.327015646150716e-05, "loss": 3.9362, "step": 25 }, { "epoch": 0.029708853238265002, "eval_loss": 3.714874029159546, "eval_runtime": 6.4212, "eval_samples_per_second": 882.856, "eval_steps_per_second": 110.415, "step": 25 }, { "epoch": 0.030897207367795602, "grad_norm": 1.2974178791046143, "learning_rate": 5e-05, "loss": 3.7341, "step": 26 }, { "epoch": 0.03208556149732621, "grad_norm": 1.031351923942566, "learning_rate": 4.6729843538492847e-05, "loss": 3.7016, "step": 27 }, { "epoch": 0.033273915626856804, "grad_norm": 1.0251359939575195, "learning_rate": 4.347369038899744e-05, "loss": 3.6931, "step": 28 }, { "epoch": 0.0344622697563874, "grad_norm": 0.9949640035629272, "learning_rate": 4.0245483899193595e-05, "loss": 3.6911, "step": 29 }, { "epoch": 0.035650623885918005, "grad_norm": 0.8370141386985779, "learning_rate": 3.705904774487396e-05, "loss": 3.6648, "step": 30 }, { "epoch": 0.0368389780154486, "grad_norm": 0.9060866236686707, "learning_rate": 3.392802673484193e-05, "loss": 3.6316, "step": 31 }, { "epoch": 0.038027332144979206, "grad_norm": 0.8701076507568359, "learning_rate": 3.086582838174551e-05, "loss": 3.5968, "step": 32 }, { "epoch": 0.0392156862745098, "grad_norm": 0.9388744235038757, "learning_rate": 2.7885565489049946e-05, "loss": 3.6498, "step": 33 }, { "epoch": 0.04040404040404041, "grad_norm": 1.0234813690185547, "learning_rate": 2.500000000000001e-05, "loss": 3.8231, "step": 34 }, { "epoch": 0.041592394533571005, "grad_norm": 1.0543227195739746, "learning_rate": 2.2221488349019903e-05, "loss": 3.7402, "step": 35 }, { "epoch": 0.0427807486631016, "grad_norm": 1.6869027614593506, "learning_rate": 1.9561928549563968e-05, "loss": 3.4193, "step": 36 }, { "epoch": 0.043969102792632206, "grad_norm": 1.9161655902862549, "learning_rate": 1.703270924499656e-05, "loss": 3.5989, "step": 37 }, { "epoch": 0.0451574569221628, "grad_norm": 0.759306013584137, "learning_rate": 1.4644660940672627e-05, "loss": 3.6862, "step": 38 }, { "epoch": 0.04634581105169341, "grad_norm": 0.649087131023407, "learning_rate": 1.2408009626051137e-05, "loss": 3.6656, "step": 39 }, { "epoch": 0.047534165181224004, "grad_norm": 0.6661444306373596, "learning_rate": 1.0332332985438248e-05, "loss": 3.6831, "step": 40 }, { "epoch": 0.0487225193107546, "grad_norm": 0.6483848094940186, "learning_rate": 8.426519384872733e-06, "loss": 3.6934, "step": 41 }, { "epoch": 0.049910873440285206, "grad_norm": 0.7084142565727234, "learning_rate": 6.698729810778065e-06, "loss": 3.6674, "step": 42 }, { "epoch": 0.0510992275698158, "grad_norm": 0.6352037787437439, "learning_rate": 5.156362923365588e-06, "loss": 3.595, "step": 43 }, { "epoch": 0.05228758169934641, "grad_norm": 0.6377587914466858, "learning_rate": 3.8060233744356633e-06, "loss": 3.6109, "step": 44 }, { "epoch": 0.053475935828877004, "grad_norm": 0.6174927949905396, "learning_rate": 2.653493525244721e-06, "loss": 3.6114, "step": 45 }, { "epoch": 0.05466428995840761, "grad_norm": 0.6506552696228027, "learning_rate": 1.70370868554659e-06, "loss": 3.6519, "step": 46 }, { "epoch": 0.055852644087938205, "grad_norm": 1.0320889949798584, "learning_rate": 9.607359798384785e-07, "loss": 4.0101, "step": 47 }, { "epoch": 0.0570409982174688, "grad_norm": 1.1787259578704834, "learning_rate": 4.277569313094809e-07, "loss": 3.6113, "step": 48 }, { "epoch": 0.058229352346999406, "grad_norm": 1.8807204961776733, "learning_rate": 1.0705383806982606e-07, "loss": 3.4709, "step": 49 }, { "epoch": 0.059417706476530004, "grad_norm": 2.1668412685394287, "learning_rate": 0.0, "loss": 3.6621, "step": 50 }, { "epoch": 0.059417706476530004, "eval_loss": 3.6351683139801025, "eval_runtime": 6.3495, "eval_samples_per_second": 892.83, "eval_steps_per_second": 111.663, "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": 3509570928377856.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }