| { | |
| "best_metric": 0.4945218563079834, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6294256490952006, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012588512981904013, | |
| "grad_norm": 0.9374328851699829, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2967, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012588512981904013, | |
| "eval_loss": 3.410280227661133, | |
| "eval_runtime": 28.691, | |
| "eval_samples_per_second": 18.682, | |
| "eval_steps_per_second": 2.335, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.025177025963808025, | |
| "grad_norm": 1.306756854057312, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7038, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03776553894571204, | |
| "grad_norm": 1.3629939556121826, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.5091, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05035405192761605, | |
| "grad_norm": 1.4472253322601318, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.5138, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06294256490952006, | |
| "grad_norm": 2.081310749053955, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.539, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07553107789142408, | |
| "grad_norm": 1.6973925828933716, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.0807, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08811959087332809, | |
| "grad_norm": 1.6589587926864624, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.0102, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1007081038552321, | |
| "grad_norm": 2.2432773113250732, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.0128, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11329661683713611, | |
| "grad_norm": 3.0825912952423096, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.8282, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.12588512981904013, | |
| "grad_norm": 2.0198371410369873, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.5822, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13847364280094415, | |
| "grad_norm": 1.7006489038467407, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.4039, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.15106215578284815, | |
| "grad_norm": 1.9521818161010742, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.4428, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16365066876475218, | |
| "grad_norm": 1.730639100074768, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.1403, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.17623918174665618, | |
| "grad_norm": 1.5531525611877441, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.3026, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1888276947285602, | |
| "grad_norm": 1.7489203214645386, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.087, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2014162077104642, | |
| "grad_norm": 1.7740451097488403, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.2439, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.21400472069236823, | |
| "grad_norm": 1.3824913501739502, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.1082, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.22659323367427223, | |
| "grad_norm": 0.8740619421005249, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.0499, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.23918174665617625, | |
| "grad_norm": 0.7334346175193787, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.9394, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.25177025963808025, | |
| "grad_norm": 1.1040862798690796, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.0259, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.26435877261998425, | |
| "grad_norm": 1.1865637302398682, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.9681, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2769472856018883, | |
| "grad_norm": 0.9018222093582153, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.979, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2895357985837923, | |
| "grad_norm": 1.158233642578125, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.8494, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3021243115656963, | |
| "grad_norm": 1.046151876449585, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.851, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3147128245476003, | |
| "grad_norm": 1.4118893146514893, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.808, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3147128245476003, | |
| "eval_loss": 0.7922729849815369, | |
| "eval_runtime": 28.7104, | |
| "eval_samples_per_second": 18.669, | |
| "eval_steps_per_second": 2.334, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.32730133752950435, | |
| "grad_norm": 1.1050761938095093, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9919, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.33988985051140835, | |
| "grad_norm": 1.3330028057098389, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.9198, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.35247836349331235, | |
| "grad_norm": 1.1018527746200562, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.8412, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.36506687647521635, | |
| "grad_norm": 0.9233662486076355, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.8082, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3776553894571204, | |
| "grad_norm": 0.9848074316978455, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.7682, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 0.8084222674369812, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.6514, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4028324154209284, | |
| "grad_norm": 1.097373127937317, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.7189, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4154209284028324, | |
| "grad_norm": 1.6498360633850098, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.6969, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.42800944138473646, | |
| "grad_norm": 1.8005599975585938, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.6476, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.44059795436664045, | |
| "grad_norm": 1.278456687927246, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.5076, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.45318646734854445, | |
| "grad_norm": 1.1756541728973389, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.5192, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.46577498033044845, | |
| "grad_norm": 1.3729151487350464, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.5166, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4783634933123525, | |
| "grad_norm": 1.0366138219833374, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.6122, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4909520062942565, | |
| "grad_norm": 0.9966530203819275, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.7652, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5035405192761605, | |
| "grad_norm": 0.8695334196090698, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.629, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5161290322580645, | |
| "grad_norm": 1.0313053131103516, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.6526, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5287175452399685, | |
| "grad_norm": 0.9505526423454285, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.6085, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5413060582218725, | |
| "grad_norm": 1.02927565574646, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.5774, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5538945712037766, | |
| "grad_norm": 0.9868349432945251, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4886, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5664830841856806, | |
| "grad_norm": 1.0703577995300293, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.5164, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5790715971675846, | |
| "grad_norm": 0.9647153615951538, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.4849, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5916601101494886, | |
| "grad_norm": 1.2369579076766968, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.425, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6042486231313926, | |
| "grad_norm": 1.017994999885559, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.3793, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6168371361132966, | |
| "grad_norm": 1.1479705572128296, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.3435, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6294256490952006, | |
| "grad_norm": 1.798177719116211, | |
| "learning_rate": 0.0, | |
| "loss": 0.4222, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6294256490952006, | |
| "eval_loss": 0.4945218563079834, | |
| "eval_runtime": 28.7393, | |
| "eval_samples_per_second": 18.65, | |
| "eval_steps_per_second": 2.331, | |
| "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": 1.1111570021023744e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |