| { | |
| "best_metric": 0.5452532172203064, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.020758731641496705, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004151746328299341, | |
| "grad_norm": 377.5227966308594, | |
| "learning_rate": 5e-05, | |
| "loss": 128.8738, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004151746328299341, | |
| "eval_loss": 9.024163246154785, | |
| "eval_runtime": 678.47, | |
| "eval_samples_per_second": 23.917, | |
| "eval_steps_per_second": 2.991, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008303492656598682, | |
| "grad_norm": 409.34124755859375, | |
| "learning_rate": 0.0001, | |
| "loss": 141.3958, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0012455238984898022, | |
| "grad_norm": 312.35101318359375, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 127.1079, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0016606985313197364, | |
| "grad_norm": 672.0693969726562, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 101.7809, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0020758731641496706, | |
| "grad_norm": 431.4256591796875, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 182.7217, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0024910477969796044, | |
| "grad_norm": 1824.4056396484375, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 86.9111, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0029062224298095386, | |
| "grad_norm": 123.24996948242188, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 49.6599, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003321397062639473, | |
| "grad_norm": 35.04706954956055, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 47.4024, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0037365716954694066, | |
| "grad_norm": 46.73086166381836, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 47.2966, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004151746328299341, | |
| "grad_norm": 13.349804878234863, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 46.118, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004566920961129275, | |
| "grad_norm": 32.715354919433594, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 46.5278, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004982095593959209, | |
| "grad_norm": 1636.382568359375, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 118.1171, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005397270226789143, | |
| "grad_norm": 923.6768188476562, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 89.8615, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005812444859619077, | |
| "grad_norm": 432.9980773925781, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 47.3111, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0062276194924490115, | |
| "grad_norm": 636.610595703125, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 48.9343, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006642794125278946, | |
| "grad_norm": 1527.2369384765625, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 56.1184, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00705796875810888, | |
| "grad_norm": 286.00689697265625, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 47.9084, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.007473143390938813, | |
| "grad_norm": 39.90363311767578, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 46.906, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007888318023768747, | |
| "grad_norm": 16.350696563720703, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 46.0326, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.008303492656598683, | |
| "grad_norm": 18.461915969848633, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 45.4721, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008718667289428616, | |
| "grad_norm": 34.859214782714844, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 44.6744, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00913384192225855, | |
| "grad_norm": 42.21925354003906, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 43.6556, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.009549016555088484, | |
| "grad_norm": 54.80242156982422, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 42.6972, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.009964191187918418, | |
| "grad_norm": 102.70449829101562, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 45.8084, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.010379365820748353, | |
| "grad_norm": 1259.2509765625, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 115.2336, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010379365820748353, | |
| "eval_loss": 2.830770969390869, | |
| "eval_runtime": 389.2434, | |
| "eval_samples_per_second": 41.689, | |
| "eval_steps_per_second": 5.213, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010794540453578286, | |
| "grad_norm": 90.39044189453125, | |
| "learning_rate": 5e-05, | |
| "loss": 41.3358, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.011209715086408221, | |
| "grad_norm": 107.48399353027344, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 37.8233, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.011624889719238155, | |
| "grad_norm": 123.58059692382812, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 36.4973, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.012040064352068088, | |
| "grad_norm": 146.50843811035156, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 34.2894, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.012455238984898023, | |
| "grad_norm": 161.9147186279297, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 32.1584, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012870413617727956, | |
| "grad_norm": 189.58154296875, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 30.0903, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.013285588250557891, | |
| "grad_norm": 216.47386169433594, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 28.0404, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.013700762883387825, | |
| "grad_norm": 251.19036865234375, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 25.0547, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01411593751621776, | |
| "grad_norm": 284.711181640625, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 22.4096, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.014531112149047693, | |
| "grad_norm": 316.04901123046875, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 19.3858, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.014946286781877626, | |
| "grad_norm": 348.51702880859375, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 16.01, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.015361461414707562, | |
| "grad_norm": 656.499267578125, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 50.5854, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.015776636047537495, | |
| "grad_norm": 539.625244140625, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 39.0507, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.01619181068036743, | |
| "grad_norm": 329.3690490722656, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 9.2602, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.016606985313197365, | |
| "grad_norm": 228.13270568847656, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 6.9433, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.017022159946027297, | |
| "grad_norm": 169.77978515625, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 6.0569, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.017437334578857232, | |
| "grad_norm": 143.93309020996094, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 5.7341, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.017852509211687167, | |
| "grad_norm": 102.2474136352539, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 5.0804, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0182676838445171, | |
| "grad_norm": 81.61624908447266, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 5.1245, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.018682858477347034, | |
| "grad_norm": 69.04170989990234, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 5.4536, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01909803311017697, | |
| "grad_norm": 60.76116180419922, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 5.0234, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.019513207743006904, | |
| "grad_norm": 45.23762130737305, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 4.7514, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.019928382375836835, | |
| "grad_norm": 62.682037353515625, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 5.2911, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.02034355700866677, | |
| "grad_norm": 132.07171630859375, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 9.7136, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.020758731641496705, | |
| "grad_norm": 744.1082153320312, | |
| "learning_rate": 0.0, | |
| "loss": 46.2426, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.020758731641496705, | |
| "eval_loss": 0.5452532172203064, | |
| "eval_runtime": 625.0682, | |
| "eval_samples_per_second": 25.96, | |
| "eval_steps_per_second": 3.246, | |
| "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": 5.259104775831552e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |