| { | |
| "best_metric": 0.8104254007339478, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.05534417156693186, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011068834313386372, | |
| "grad_norm": 36.721168518066406, | |
| "learning_rate": 5e-05, | |
| "loss": 14.1912, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011068834313386372, | |
| "eval_loss": 13.724494934082031, | |
| "eval_runtime": 91.0519, | |
| "eval_samples_per_second": 66.852, | |
| "eval_steps_per_second": 8.358, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022137668626772745, | |
| "grad_norm": 45.76126480102539, | |
| "learning_rate": 0.0001, | |
| "loss": 13.95, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0033206502940159115, | |
| "grad_norm": 44.33281707763672, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 12.4936, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004427533725354549, | |
| "grad_norm": 41.054508209228516, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 7.0168, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005534417156693186, | |
| "grad_norm": 22.34103012084961, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.5822, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006641300588031823, | |
| "grad_norm": 25.822521209716797, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.2788, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00774818401937046, | |
| "grad_norm": 10.615482330322266, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.4014, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008855067450709098, | |
| "grad_norm": 6.933248519897461, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.0412, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009961950882047734, | |
| "grad_norm": 2.6085708141326904, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.8551, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011068834313386372, | |
| "grad_norm": 3.8146591186523438, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.8501, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012175717744725008, | |
| "grad_norm": 7.357889175415039, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.8831, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.013282601176063646, | |
| "grad_norm": 4.156259059906006, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.8321, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014389484607402282, | |
| "grad_norm": 13.24997615814209, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.0533, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01549636803874092, | |
| "grad_norm": 4.824550628662109, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.8486, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.016603251470079558, | |
| "grad_norm": 2.509622097015381, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.7962, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017710134901418196, | |
| "grad_norm": 3.590033769607544, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.8333, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01881701833275683, | |
| "grad_norm": 6.873021125793457, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.8969, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.019923901764095468, | |
| "grad_norm": 5.084534645080566, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.8647, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.021030785195434106, | |
| "grad_norm": 2.3888447284698486, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.8115, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.022137668626772744, | |
| "grad_norm": 1.8158559799194336, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.8075, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02324455205811138, | |
| "grad_norm": 2.9052810668945312, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.8259, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.024351435489450016, | |
| "grad_norm": 2.515951156616211, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.8207, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.025458318920788654, | |
| "grad_norm": 3.8959262371063232, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.8512, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.026565202352127292, | |
| "grad_norm": 2.965120792388916, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.8395, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02767208578346593, | |
| "grad_norm": 1.2737544775009155, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.8124, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02767208578346593, | |
| "eval_loss": 0.8200458288192749, | |
| "eval_runtime": 90.9598, | |
| "eval_samples_per_second": 66.92, | |
| "eval_steps_per_second": 8.366, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.028778969214804564, | |
| "grad_norm": 3.0076019763946533, | |
| "learning_rate": 5e-05, | |
| "loss": 0.914, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.029885852646143202, | |
| "grad_norm": 2.437142848968506, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.8225, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03099273607748184, | |
| "grad_norm": 2.596731185913086, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.8304, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.032099619508820475, | |
| "grad_norm": 1.6621183156967163, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.8103, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.033206502940159116, | |
| "grad_norm": 0.6339697241783142, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.8156, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03431338637149775, | |
| "grad_norm": 2.309584617614746, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.8227, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03542026980283639, | |
| "grad_norm": 1.88184654712677, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.819, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.036527153234175026, | |
| "grad_norm": 1.8324432373046875, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.8012, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03763403666551366, | |
| "grad_norm": 1.9068471193313599, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8098, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0387409200968523, | |
| "grad_norm": 0.5746772885322571, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.8211, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.039847803528190937, | |
| "grad_norm": 1.8682575225830078, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.8151, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04095468695952958, | |
| "grad_norm": 1.3192604780197144, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.8096, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04206157039086821, | |
| "grad_norm": 10.249944686889648, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.9605, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04316845382220685, | |
| "grad_norm": 1.324076533317566, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.8249, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04427533725354549, | |
| "grad_norm": 0.9887760877609253, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.8182, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04538222068488412, | |
| "grad_norm": 1.1598294973373413, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.8137, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04648910411622276, | |
| "grad_norm": 1.0750510692596436, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.8027, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0475959875475614, | |
| "grad_norm": 1.1602271795272827, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.8111, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04870287097890003, | |
| "grad_norm": 2.6957943439483643, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8029, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.049809754410238674, | |
| "grad_norm": 1.0971044301986694, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.807, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05091663784157731, | |
| "grad_norm": 2.0505218505859375, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.8122, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05202352127291594, | |
| "grad_norm": 1.332539439201355, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.8038, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.053130404704254584, | |
| "grad_norm": 1.3104387521743774, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.807, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05423728813559322, | |
| "grad_norm": 1.1924852132797241, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.8063, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05534417156693186, | |
| "grad_norm": 1.5198986530303955, | |
| "learning_rate": 0.0, | |
| "loss": 0.812, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05534417156693186, | |
| "eval_loss": 0.8104254007339478, | |
| "eval_runtime": 91.4608, | |
| "eval_samples_per_second": 66.553, | |
| "eval_steps_per_second": 8.321, | |
| "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": 1.6535390389692006e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |