{ "best_metric": 1.049103021621704, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.010930753675465924, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00021861507350931847, "grad_norm": 2.3790552616119385, "learning_rate": 2e-05, "loss": 2.1813, "step": 1 }, { "epoch": 0.00021861507350931847, "eval_loss": 3.3091351985931396, "eval_runtime": 566.5157, "eval_samples_per_second": 13.599, "eval_steps_per_second": 1.7, "step": 1 }, { "epoch": 0.00043723014701863694, "grad_norm": 2.4088428020477295, "learning_rate": 4e-05, "loss": 2.2045, "step": 2 }, { "epoch": 0.0006558452205279554, "grad_norm": 2.1781888008117676, "learning_rate": 6e-05, "loss": 2.1147, "step": 3 }, { "epoch": 0.0008744602940372739, "grad_norm": 1.6938015222549438, "learning_rate": 8e-05, "loss": 1.9903, "step": 4 }, { "epoch": 0.0010930753675465923, "grad_norm": 1.1523576974868774, "learning_rate": 0.0001, "loss": 1.9169, "step": 5 }, { "epoch": 0.0013116904410559109, "grad_norm": 1.6266422271728516, "learning_rate": 9.987820251299122e-05, "loss": 1.7474, "step": 6 }, { "epoch": 0.0015303055145652292, "grad_norm": 1.3725090026855469, "learning_rate": 9.951340343707852e-05, "loss": 1.7467, "step": 7 }, { "epoch": 0.0017489205880745478, "grad_norm": 0.9670947790145874, "learning_rate": 9.890738003669029e-05, "loss": 1.5984, "step": 8 }, { "epoch": 0.001967535661583866, "grad_norm": 0.945730447769165, "learning_rate": 9.806308479691595e-05, "loss": 1.5176, "step": 9 }, { "epoch": 0.0021861507350931847, "grad_norm": 0.845664381980896, "learning_rate": 9.698463103929542e-05, "loss": 1.5347, "step": 10 }, { "epoch": 0.002404765808602503, "grad_norm": 0.87636399269104, "learning_rate": 9.567727288213005e-05, "loss": 1.5821, "step": 11 }, { "epoch": 0.0026233808821118218, "grad_norm": 0.7581028938293457, "learning_rate": 9.414737964294636e-05, "loss": 1.5204, "step": 12 }, { "epoch": 0.00284199595562114, "grad_norm": 0.9650707244873047, "learning_rate": 9.24024048078213e-05, "loss": 1.5236, "step": 13 }, { "epoch": 0.0030606110291304584, "grad_norm": 0.7284338474273682, "learning_rate": 9.045084971874738e-05, "loss": 1.444, "step": 14 }, { "epoch": 0.003279226102639777, "grad_norm": 0.721749484539032, "learning_rate": 8.83022221559489e-05, "loss": 1.4216, "step": 15 }, { "epoch": 0.0034978411761490955, "grad_norm": 0.6694514751434326, "learning_rate": 8.596699001693255e-05, "loss": 1.3595, "step": 16 }, { "epoch": 0.003716456249658414, "grad_norm": 0.678149402141571, "learning_rate": 8.345653031794292e-05, "loss": 1.3797, "step": 17 }, { "epoch": 0.003935071323167732, "grad_norm": 0.7223522663116455, "learning_rate": 8.07830737662829e-05, "loss": 1.3239, "step": 18 }, { "epoch": 0.004153686396677051, "grad_norm": 0.6647931933403015, "learning_rate": 7.795964517353735e-05, "loss": 1.4202, "step": 19 }, { "epoch": 0.004372301470186369, "grad_norm": 0.6496835947036743, "learning_rate": 7.500000000000001e-05, "loss": 1.3503, "step": 20 }, { "epoch": 0.004590916543695688, "grad_norm": 0.654890775680542, "learning_rate": 7.191855733945387e-05, "loss": 1.2475, "step": 21 }, { "epoch": 0.004809531617205006, "grad_norm": 0.7162601351737976, "learning_rate": 6.873032967079561e-05, "loss": 1.3218, "step": 22 }, { "epoch": 0.005028146690714325, "grad_norm": 0.732305109500885, "learning_rate": 6.545084971874738e-05, "loss": 1.3565, "step": 23 }, { "epoch": 0.0052467617642236435, "grad_norm": 0.7211049795150757, "learning_rate": 6.209609477998338e-05, "loss": 1.3016, "step": 24 }, { "epoch": 0.005465376837732962, "grad_norm": 0.7151786088943481, "learning_rate": 5.868240888334653e-05, "loss": 1.3656, "step": 25 }, { "epoch": 0.005465376837732962, "eval_loss": 1.0510051250457764, "eval_runtime": 571.0181, "eval_samples_per_second": 13.492, "eval_steps_per_second": 1.686, "step": 25 }, { "epoch": 0.00568399191124228, "grad_norm": 0.7088556289672852, "learning_rate": 5.522642316338268e-05, "loss": 1.2678, "step": 26 }, { "epoch": 0.005902606984751598, "grad_norm": 0.7126575112342834, "learning_rate": 5.174497483512506e-05, "loss": 1.315, "step": 27 }, { "epoch": 0.006121222058260917, "grad_norm": 0.7205974459648132, "learning_rate": 4.825502516487497e-05, "loss": 1.2119, "step": 28 }, { "epoch": 0.006339837131770235, "grad_norm": 0.6830354332923889, "learning_rate": 4.477357683661734e-05, "loss": 1.2151, "step": 29 }, { "epoch": 0.006558452205279554, "grad_norm": 0.6415659785270691, "learning_rate": 4.131759111665349e-05, "loss": 1.2253, "step": 30 }, { "epoch": 0.0067770672787888725, "grad_norm": 0.6351765990257263, "learning_rate": 3.790390522001662e-05, "loss": 1.1, "step": 31 }, { "epoch": 0.006995682352298191, "grad_norm": 0.6895049810409546, "learning_rate": 3.4549150281252636e-05, "loss": 1.1679, "step": 32 }, { "epoch": 0.00721429742580751, "grad_norm": 0.6956767439842224, "learning_rate": 3.12696703292044e-05, "loss": 1.1575, "step": 33 }, { "epoch": 0.007432912499316828, "grad_norm": 0.795951247215271, "learning_rate": 2.8081442660546125e-05, "loss": 1.1705, "step": 34 }, { "epoch": 0.007651527572826147, "grad_norm": 1.151456594467163, "learning_rate": 2.500000000000001e-05, "loss": 0.2722, "step": 35 }, { "epoch": 0.007870142646335464, "grad_norm": 1.0940009355545044, "learning_rate": 2.2040354826462668e-05, "loss": 0.2685, "step": 36 }, { "epoch": 0.008088757719844783, "grad_norm": 1.43516206741333, "learning_rate": 1.9216926233717085e-05, "loss": 0.2708, "step": 37 }, { "epoch": 0.008307372793354102, "grad_norm": 1.237060308456421, "learning_rate": 1.6543469682057106e-05, "loss": 0.4588, "step": 38 }, { "epoch": 0.00852598786686342, "grad_norm": 0.879013180732727, "learning_rate": 1.4033009983067452e-05, "loss": 0.2302, "step": 39 }, { "epoch": 0.008744602940372739, "grad_norm": 0.793963611125946, "learning_rate": 1.1697777844051105e-05, "loss": 0.2223, "step": 40 }, { "epoch": 0.008963218013882057, "grad_norm": 1.5157628059387207, "learning_rate": 9.549150281252633e-06, "loss": 0.261, "step": 41 }, { "epoch": 0.009181833087391376, "grad_norm": 2.050135374069214, "learning_rate": 7.597595192178702e-06, "loss": 0.3103, "step": 42 }, { "epoch": 0.009400448160900694, "grad_norm": 1.0070862770080566, "learning_rate": 5.852620357053651e-06, "loss": 0.2538, "step": 43 }, { "epoch": 0.009619063234410013, "grad_norm": 1.5608525276184082, "learning_rate": 4.322727117869951e-06, "loss": 0.2355, "step": 44 }, { "epoch": 0.009837678307919331, "grad_norm": 2.536520004272461, "learning_rate": 3.0153689607045845e-06, "loss": 0.3299, "step": 45 }, { "epoch": 0.01005629338142865, "grad_norm": 2.5030901432037354, "learning_rate": 1.9369152030840556e-06, "loss": 0.3479, "step": 46 }, { "epoch": 0.010274908454937969, "grad_norm": 2.2683932781219482, "learning_rate": 1.0926199633097157e-06, "loss": 0.2691, "step": 47 }, { "epoch": 0.010493523528447287, "grad_norm": 2.113285779953003, "learning_rate": 4.865965629214819e-07, "loss": 0.2866, "step": 48 }, { "epoch": 0.010712138601956606, "grad_norm": 1.0461803674697876, "learning_rate": 1.2179748700879012e-07, "loss": 0.9829, "step": 49 }, { "epoch": 0.010930753675465924, "grad_norm": 1.0210597515106201, "learning_rate": 0.0, "loss": 0.2243, "step": 50 }, { "epoch": 0.010930753675465924, "eval_loss": 1.049103021621704, "eval_runtime": 570.7917, "eval_samples_per_second": 13.497, "eval_steps_per_second": 1.687, "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": 5, "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": 7.42942937532334e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null }