| { | |
| "best_metric": 1.860011100769043, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-600", | |
| "epoch": 0.16383370878558262, | |
| "eval_steps": 50, | |
| "global_step": 600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002730561813093044, | |
| "eval_loss": 4.23640251159668, | |
| "eval_runtime": 242.769, | |
| "eval_samples_per_second": 25.407, | |
| "eval_steps_per_second": 6.352, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027305618130930437, | |
| "grad_norm": 17.406291961669922, | |
| "learning_rate": 0.0002, | |
| "loss": 10.2808, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005461123626186087, | |
| "grad_norm": 11.717205047607422, | |
| "learning_rate": 0.0001998582695676762, | |
| "loss": 8.3282, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008191685439279131, | |
| "grad_norm": 12.451804161071777, | |
| "learning_rate": 0.00019943348002101371, | |
| "loss": 8.6122, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010922247252372175, | |
| "grad_norm": 14.363651275634766, | |
| "learning_rate": 0.00019872683547213446, | |
| "loss": 8.3687, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01365280906546522, | |
| "grad_norm": 34.83021545410156, | |
| "learning_rate": 0.00019774033898178667, | |
| "loss": 8.9732, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01365280906546522, | |
| "eval_loss": 2.319276809692383, | |
| "eval_runtime": 244.7603, | |
| "eval_samples_per_second": 25.2, | |
| "eval_steps_per_second": 6.3, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.016383370878558262, | |
| "grad_norm": 10.075106620788574, | |
| "learning_rate": 0.0001964767868814516, | |
| "loss": 8.2567, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.019113932691651306, | |
| "grad_norm": 12.682146072387695, | |
| "learning_rate": 0.00019493976084683813, | |
| "loss": 8.2734, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.02184449450474435, | |
| "grad_norm": 13.281365394592285, | |
| "learning_rate": 0.00019313361774523385, | |
| "loss": 8.0909, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.024575056317837397, | |
| "grad_norm": 18.51453971862793, | |
| "learning_rate": 0.00019106347728549135, | |
| "loss": 8.4039, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.02730561813093044, | |
| "grad_norm": 36.62446212768555, | |
| "learning_rate": 0.00018873520750565718, | |
| "loss": 8.0267, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02730561813093044, | |
| "eval_loss": 2.1572701930999756, | |
| "eval_runtime": 245.0524, | |
| "eval_samples_per_second": 25.17, | |
| "eval_steps_per_second": 6.293, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.030036179944023484, | |
| "grad_norm": 10.612593650817871, | |
| "learning_rate": 0.0001861554081393806, | |
| "loss": 7.8833, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.032766741757116524, | |
| "grad_norm": 10.446393966674805, | |
| "learning_rate": 0.0001833313919082515, | |
| "loss": 8.3278, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.03549730357020957, | |
| "grad_norm": 14.34956169128418, | |
| "learning_rate": 0.00018027116379309638, | |
| "loss": 8.2577, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.03822786538330261, | |
| "grad_norm": 14.526724815368652, | |
| "learning_rate": 0.00017698339834299061, | |
| "loss": 7.8844, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.040958427196395655, | |
| "grad_norm": 37.110965728759766, | |
| "learning_rate": 0.00017347741508630672, | |
| "loss": 8.4204, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.040958427196395655, | |
| "eval_loss": 2.1126084327697754, | |
| "eval_runtime": 244.2124, | |
| "eval_samples_per_second": 25.257, | |
| "eval_steps_per_second": 6.314, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0436889890094887, | |
| "grad_norm": 12.598857879638672, | |
| "learning_rate": 0.0001697631521134985, | |
| "loss": 7.9538, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.04641955082258175, | |
| "grad_norm": 11.983827590942383, | |
| "learning_rate": 0.00016585113790650388, | |
| "loss": 8.1731, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.04915011263567479, | |
| "grad_norm": 13.680892944335938, | |
| "learning_rate": 0.0001617524614946192, | |
| "loss": 7.9786, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.05188067444876784, | |
| "grad_norm": 16.39923858642578, | |
| "learning_rate": 0.0001574787410214407, | |
| "loss": 7.8267, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.05461123626186088, | |
| "grad_norm": 35.790550231933594, | |
| "learning_rate": 0.00015304209081197425, | |
| "loss": 7.9481, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.05461123626186088, | |
| "eval_loss": 2.1126017570495605, | |
| "eval_runtime": 244.847, | |
| "eval_samples_per_second": 25.191, | |
| "eval_steps_per_second": 6.298, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.057341798074953924, | |
| "grad_norm": 11.671783447265625, | |
| "learning_rate": 0.00014845508703326504, | |
| "loss": 8.1613, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.06007235988804697, | |
| "grad_norm": 11.406132698059082, | |
| "learning_rate": 0.00014373073204588556, | |
| "loss": 7.8322, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.06280292170114, | |
| "grad_norm": 11.966191291809082, | |
| "learning_rate": 0.00013888241754733208, | |
| "loss": 7.5859, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.06553348351423305, | |
| "grad_norm": 14.312826156616211, | |
| "learning_rate": 0.00013392388661180303, | |
| "loss": 8.059, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.06826404532732609, | |
| "grad_norm": 26.518217086791992, | |
| "learning_rate": 0.0001288691947339621, | |
| "loss": 7.8758, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.06826404532732609, | |
| "eval_loss": 2.0528900623321533, | |
| "eval_runtime": 245.0717, | |
| "eval_samples_per_second": 25.168, | |
| "eval_steps_per_second": 6.292, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.07099460714041914, | |
| "grad_norm": 11.75592041015625, | |
| "learning_rate": 0.0001237326699871115, | |
| "loss": 7.8156, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.07372516895351218, | |
| "grad_norm": 10.208357810974121, | |
| "learning_rate": 0.00011852887240871145, | |
| "loss": 7.9382, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.07645573076660522, | |
| "grad_norm": 12.978534698486328, | |
| "learning_rate": 0.00011327255272837221, | |
| "loss": 7.6911, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.07918629257969827, | |
| "grad_norm": 15.648476600646973, | |
| "learning_rate": 0.00010797861055530831, | |
| "loss": 7.5699, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.08191685439279131, | |
| "grad_norm": 31.975311279296875, | |
| "learning_rate": 0.00010266205214377748, | |
| "loss": 8.2882, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.08191685439279131, | |
| "eval_loss": 2.002148151397705, | |
| "eval_runtime": 245.0084, | |
| "eval_samples_per_second": 25.175, | |
| "eval_steps_per_second": 6.294, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.08464741620588435, | |
| "grad_norm": 10.377389907836914, | |
| "learning_rate": 9.733794785622253e-05, | |
| "loss": 7.7774, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.0873779780189774, | |
| "grad_norm": 10.131440162658691, | |
| "learning_rate": 9.202138944469168e-05, | |
| "loss": 7.7762, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.09010853983207044, | |
| "grad_norm": 12.15221118927002, | |
| "learning_rate": 8.672744727162781e-05, | |
| "loss": 7.8511, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.0928391016451635, | |
| "grad_norm": 13.989408493041992, | |
| "learning_rate": 8.147112759128859e-05, | |
| "loss": 7.7617, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.09556966345825654, | |
| "grad_norm": 24.143465042114258, | |
| "learning_rate": 7.626733001288851e-05, | |
| "loss": 8.1177, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.09556966345825654, | |
| "eval_loss": 1.9585822820663452, | |
| "eval_runtime": 245.0532, | |
| "eval_samples_per_second": 25.17, | |
| "eval_steps_per_second": 6.293, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.09830022527134959, | |
| "grad_norm": 10.882676124572754, | |
| "learning_rate": 7.113080526603792e-05, | |
| "loss": 7.953, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.10103078708444263, | |
| "grad_norm": 10.572400093078613, | |
| "learning_rate": 6.607611338819697e-05, | |
| "loss": 7.8085, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.10376134889753567, | |
| "grad_norm": 12.119694709777832, | |
| "learning_rate": 6.111758245266794e-05, | |
| "loss": 7.6887, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.10649191071062872, | |
| "grad_norm": 15.668352127075195, | |
| "learning_rate": 5.626926795411447e-05, | |
| "loss": 7.7462, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.10922247252372176, | |
| "grad_norm": 22.603986740112305, | |
| "learning_rate": 5.1544912966734994e-05, | |
| "loss": 7.8605, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.10922247252372176, | |
| "eval_loss": 1.8981908559799194, | |
| "eval_runtime": 245.2102, | |
| "eval_samples_per_second": 25.154, | |
| "eval_steps_per_second": 6.288, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.1119530343368148, | |
| "grad_norm": 11.885726928710938, | |
| "learning_rate": 4.695790918802576e-05, | |
| "loss": 7.2024, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.11468359614990785, | |
| "grad_norm": 11.538261413574219, | |
| "learning_rate": 4.252125897855932e-05, | |
| "loss": 7.3657, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.11741415796300089, | |
| "grad_norm": 12.95737075805664, | |
| "learning_rate": 3.824753850538082e-05, | |
| "loss": 7.6156, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.12014471977609394, | |
| "grad_norm": 13.987143516540527, | |
| "learning_rate": 3.414886209349615e-05, | |
| "loss": 7.5926, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.12287528158918698, | |
| "grad_norm": 17.603551864624023, | |
| "learning_rate": 3.0236847886501542e-05, | |
| "loss": 7.9609, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.12287528158918698, | |
| "eval_loss": 1.8793390989303589, | |
| "eval_runtime": 244.4883, | |
| "eval_samples_per_second": 25.228, | |
| "eval_steps_per_second": 6.307, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.12560584340228, | |
| "grad_norm": 11.999287605285645, | |
| "learning_rate": 2.6522584913693294e-05, | |
| "loss": 7.4036, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.12833640521537307, | |
| "grad_norm": 12.017765998840332, | |
| "learning_rate": 2.301660165700936e-05, | |
| "loss": 7.5689, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.1310669670284661, | |
| "grad_norm": 12.495355606079102, | |
| "learning_rate": 1.9728836206903656e-05, | |
| "loss": 7.765, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.13379752884155915, | |
| "grad_norm": 13.036554336547852, | |
| "learning_rate": 1.6668608091748495e-05, | |
| "loss": 7.1911, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.13652809065465218, | |
| "grad_norm": 23.29970359802246, | |
| "learning_rate": 1.3844591860619383e-05, | |
| "loss": 7.5728, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.13652809065465218, | |
| "eval_loss": 1.8650081157684326, | |
| "eval_runtime": 245.1119, | |
| "eval_samples_per_second": 25.164, | |
| "eval_steps_per_second": 6.291, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.13925865246774524, | |
| "grad_norm": 10.133707046508789, | |
| "learning_rate": 1.1264792494342857e-05, | |
| "loss": 7.0925, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.14198921428083827, | |
| "grad_norm": 10.4485445022583, | |
| "learning_rate": 8.936522714508678e-06, | |
| "loss": 7.8088, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.14471977609393133, | |
| "grad_norm": 13.265645980834961, | |
| "learning_rate": 6.866382254766157e-06, | |
| "loss": 7.6878, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.14745033790702436, | |
| "grad_norm": 12.639242172241211, | |
| "learning_rate": 5.060239153161872e-06, | |
| "loss": 7.4659, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.15018089972011742, | |
| "grad_norm": 26.739566802978516, | |
| "learning_rate": 3.5232131185484076e-06, | |
| "loss": 7.7885, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.15018089972011742, | |
| "eval_loss": 1.862091302871704, | |
| "eval_runtime": 245.1426, | |
| "eval_samples_per_second": 25.161, | |
| "eval_steps_per_second": 6.29, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.15291146153321045, | |
| "grad_norm": 11.77377986907959, | |
| "learning_rate": 2.259661018213333e-06, | |
| "loss": 7.2398, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.1556420233463035, | |
| "grad_norm": 10.591424942016602, | |
| "learning_rate": 1.2731645278655445e-06, | |
| "loss": 7.6634, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.15837258515939653, | |
| "grad_norm": 12.146462440490723, | |
| "learning_rate": 5.665199789862907e-07, | |
| "loss": 7.112, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.1611031469724896, | |
| "grad_norm": 15.12509822845459, | |
| "learning_rate": 1.4173043232380557e-07, | |
| "loss": 7.505, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.16383370878558262, | |
| "grad_norm": 28.584569931030273, | |
| "learning_rate": 0.0, | |
| "loss": 7.9429, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.16383370878558262, | |
| "eval_loss": 1.860011100769043, | |
| "eval_runtime": 244.4477, | |
| "eval_samples_per_second": 25.232, | |
| "eval_steps_per_second": 6.308, | |
| "step": 600 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "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": 4.218776992088064e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |