| { | |
| "best_metric": 0.5200080275535583, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.5657708628005658, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011315417256011316, | |
| "grad_norm": 2.1943609714508057, | |
| "learning_rate": 5e-05, | |
| "loss": 8.4242, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011315417256011316, | |
| "eval_loss": 0.8281431198120117, | |
| "eval_runtime": 44.4369, | |
| "eval_samples_per_second": 13.39, | |
| "eval_steps_per_second": 1.688, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02263083451202263, | |
| "grad_norm": 2.6719741821289062, | |
| "learning_rate": 0.0001, | |
| "loss": 9.9323, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.033946251768033946, | |
| "grad_norm": 3.0640249252319336, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.7148, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04526166902404526, | |
| "grad_norm": 3.3661434650421143, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.8608, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.056577086280056574, | |
| "grad_norm": 3.1292307376861572, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 10.2639, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06789250353606789, | |
| "grad_norm": 2.260249614715576, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 9.5547, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07920792079207921, | |
| "grad_norm": 2.1925923824310303, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 9.9299, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09052333804809053, | |
| "grad_norm": 2.2138164043426514, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.326, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10183875530410184, | |
| "grad_norm": 1.9601538181304932, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 9.7972, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11315417256011315, | |
| "grad_norm": 2.3362250328063965, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 9.9417, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12446958981612447, | |
| "grad_norm": 2.5164709091186523, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 10.341, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.13578500707213578, | |
| "grad_norm": 2.4237403869628906, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 9.0907, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1471004243281471, | |
| "grad_norm": 2.3622500896453857, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 7.2716, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15841584158415842, | |
| "grad_norm": 2.7323813438415527, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 8.3576, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16973125884016974, | |
| "grad_norm": 2.5983994007110596, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 8.8552, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.18104667609618105, | |
| "grad_norm": 2.3216371536254883, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 8.3984, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.19236209335219237, | |
| "grad_norm": 1.7305115461349487, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 8.3699, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2036775106082037, | |
| "grad_norm": 1.699713945388794, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 8.8624, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.214992927864215, | |
| "grad_norm": 1.6283882856369019, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 8.9808, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2263083451202263, | |
| "grad_norm": 1.6349085569381714, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 9.9526, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2376237623762376, | |
| "grad_norm": 1.7173153162002563, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 9.4905, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.24893917963224893, | |
| "grad_norm": 1.9035966396331787, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 9.6389, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.26025459688826025, | |
| "grad_norm": 1.9487980604171753, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 9.2311, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.27157001414427157, | |
| "grad_norm": 2.21173095703125, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 8.8328, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2828854314002829, | |
| "grad_norm": 2.991882562637329, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 8.3784, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2828854314002829, | |
| "eval_loss": 0.5269150733947754, | |
| "eval_runtime": 45.0688, | |
| "eval_samples_per_second": 13.202, | |
| "eval_steps_per_second": 1.664, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2942008486562942, | |
| "grad_norm": 0.8682360053062439, | |
| "learning_rate": 5e-05, | |
| "loss": 7.2005, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3055162659123055, | |
| "grad_norm": 0.9563512802124023, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 7.9264, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.31683168316831684, | |
| "grad_norm": 1.096703052520752, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 8.04, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.32814710042432815, | |
| "grad_norm": 1.0564768314361572, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 8.4954, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.33946251768033947, | |
| "grad_norm": 1.1875149011611938, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 8.2755, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3507779349363508, | |
| "grad_norm": 1.1350054740905762, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 8.7413, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3620933521923621, | |
| "grad_norm": 1.2498562335968018, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 9.1359, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3734087694483734, | |
| "grad_norm": 1.4139655828475952, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 8.9738, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.38472418670438474, | |
| "grad_norm": 1.4577665328979492, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 8.6911, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.39603960396039606, | |
| "grad_norm": 1.629506230354309, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 9.1795, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4073550212164074, | |
| "grad_norm": 1.74530029296875, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 9.2998, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4186704384724187, | |
| "grad_norm": 2.077608346939087, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 8.95, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.42998585572843, | |
| "grad_norm": 1.909153699874878, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 6.992, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.44130127298444133, | |
| "grad_norm": 0.8186285495758057, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 7.3094, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4526166902404526, | |
| "grad_norm": 0.9286304116249084, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 7.8571, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4639321074964639, | |
| "grad_norm": 0.9646059274673462, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 8.4043, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.4752475247524752, | |
| "grad_norm": 0.9747306108474731, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 7.5189, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.48656294200848654, | |
| "grad_norm": 1.110140323638916, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 8.197, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.49787835926449786, | |
| "grad_norm": 1.2244906425476074, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 8.6932, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5091937765205092, | |
| "grad_norm": 1.2957104444503784, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 9.1472, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5205091937765205, | |
| "grad_norm": 1.3898643255233765, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 9.3223, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5318246110325319, | |
| "grad_norm": 1.5572975873947144, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 8.9785, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5431400282885431, | |
| "grad_norm": 1.7228946685791016, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 8.6731, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5544554455445545, | |
| "grad_norm": 2.0071144104003906, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 9.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5657708628005658, | |
| "grad_norm": 2.848938226699829, | |
| "learning_rate": 0.0, | |
| "loss": 7.8565, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5657708628005658, | |
| "eval_loss": 0.5200080275535583, | |
| "eval_runtime": 43.7314, | |
| "eval_samples_per_second": 13.606, | |
| "eval_steps_per_second": 1.715, | |
| "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": 1.0954378319683912e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |