| { | |
| "best_metric": 0.492282509803772, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.12556898446083817, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0025113796892167633, | |
| "grad_norm": 23.013229370117188, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4457, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025113796892167633, | |
| "eval_loss": 0.8236261010169983, | |
| "eval_runtime": 181.4712, | |
| "eval_samples_per_second": 14.785, | |
| "eval_steps_per_second": 1.852, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005022759378433527, | |
| "grad_norm": 28.304847717285156, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5399, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00753413906765029, | |
| "grad_norm": 19.628828048706055, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.553, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010045518756867053, | |
| "grad_norm": 17.90690040588379, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.5527, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012556898446083818, | |
| "grad_norm": 53.380088806152344, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.6371, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01506827813530058, | |
| "grad_norm": 15.596626281738281, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.5356, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017579657824517345, | |
| "grad_norm": 17.02699089050293, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.5747, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.020091037513734106, | |
| "grad_norm": 18.998044967651367, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.6059, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02260241720295087, | |
| "grad_norm": 17.732620239257812, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.5665, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.025113796892167636, | |
| "grad_norm": 19.301992416381836, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.5724, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.027625176581384397, | |
| "grad_norm": 22.4119873046875, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.6152, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03013655627060116, | |
| "grad_norm": 31.2508487701416, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.7137, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03264793595981792, | |
| "grad_norm": 29.12340545654297, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.6268, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03515931564903469, | |
| "grad_norm": 14.437383651733398, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.4061, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03767069533825145, | |
| "grad_norm": 14.781952857971191, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.4458, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04018207502746821, | |
| "grad_norm": 9.472990036010742, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.4814, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04269345471668498, | |
| "grad_norm": 10.511188507080078, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.4886, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04520483440590174, | |
| "grad_norm": 10.828303337097168, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.4739, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0477162140951185, | |
| "grad_norm": 13.374417304992676, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.5088, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05022759378433527, | |
| "grad_norm": 14.084159851074219, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4852, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05273897347355203, | |
| "grad_norm": 13.295788764953613, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.5103, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.055250353162768794, | |
| "grad_norm": 12.699968338012695, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.518, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05776173285198556, | |
| "grad_norm": 16.647933959960938, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.5954, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06027311254120232, | |
| "grad_norm": 28.137985229492188, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.6517, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06278449223041908, | |
| "grad_norm": 33.814674377441406, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.6456, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06278449223041908, | |
| "eval_loss": 0.518934965133667, | |
| "eval_runtime": 181.5268, | |
| "eval_samples_per_second": 14.78, | |
| "eval_steps_per_second": 1.851, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06529587191963585, | |
| "grad_norm": 9.209891319274902, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3203, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06780725160885262, | |
| "grad_norm": 14.673049926757812, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.4129, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07031863129806938, | |
| "grad_norm": 14.608511924743652, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.4394, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07283001098728614, | |
| "grad_norm": 11.686541557312012, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.4547, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0753413906765029, | |
| "grad_norm": 9.099536895751953, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.4592, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07785277036571966, | |
| "grad_norm": 9.882477760314941, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.4395, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08036415005493643, | |
| "grad_norm": 9.75089168548584, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.4752, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0828755297441532, | |
| "grad_norm": 14.58424186706543, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.4783, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08538690943336996, | |
| "grad_norm": 17.86821746826172, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.5316, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08789828912258672, | |
| "grad_norm": 18.498552322387695, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.5342, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09040966881180348, | |
| "grad_norm": 24.58167839050293, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.5721, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09292104850102025, | |
| "grad_norm": 27.7944393157959, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.7302, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.095432428190237, | |
| "grad_norm": 29.117172241210938, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5114, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09794380787945378, | |
| "grad_norm": 5.468899726867676, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.32, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.10045518756867054, | |
| "grad_norm": 7.967328071594238, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.4181, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1029665672578873, | |
| "grad_norm": 7.048090934753418, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.447, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10547794694710406, | |
| "grad_norm": 7.55548095703125, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.4456, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10798932663632083, | |
| "grad_norm": 7.440658092498779, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.4538, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11050070632553759, | |
| "grad_norm": 8.213162422180176, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4458, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11301208601475436, | |
| "grad_norm": 11.403858184814453, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.4657, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11552346570397112, | |
| "grad_norm": 13.041141510009766, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.4781, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11803484539318788, | |
| "grad_norm": 12.925886154174805, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.5108, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12054622508240465, | |
| "grad_norm": 20.79706573486328, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.6018, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1230576047716214, | |
| "grad_norm": 30.63442039489746, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.6667, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.12556898446083817, | |
| "grad_norm": 26.500112533569336, | |
| "learning_rate": 0.0, | |
| "loss": 0.6593, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12556898446083817, | |
| "eval_loss": 0.492282509803772, | |
| "eval_runtime": 182.685, | |
| "eval_samples_per_second": 14.686, | |
| "eval_steps_per_second": 1.839, | |
| "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": 5.68818318635434e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |