| { | |
| "best_metric": 0.6646984219551086, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.061597690086621755, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001231953801732435, | |
| "grad_norm": 1.4951938390731812, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.8121, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001231953801732435, | |
| "eval_loss": 2.4635820388793945, | |
| "eval_runtime": 3.447, | |
| "eval_samples_per_second": 14.505, | |
| "eval_steps_per_second": 3.771, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00246390760346487, | |
| "grad_norm": 1.7550477981567383, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 2.1289, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003695861405197305, | |
| "grad_norm": 1.997981071472168, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1937, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00492781520692974, | |
| "grad_norm": 1.8525218963623047, | |
| "learning_rate": 9.997376600647783e-05, | |
| "loss": 2.0099, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006159769008662175, | |
| "grad_norm": 1.6681252717971802, | |
| "learning_rate": 9.989509461357426e-05, | |
| "loss": 1.7067, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00739172281039461, | |
| "grad_norm": 1.6790170669555664, | |
| "learning_rate": 9.976407754861426e-05, | |
| "loss": 1.549, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008623676612127045, | |
| "grad_norm": 2.22214674949646, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 1.5006, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00985563041385948, | |
| "grad_norm": 2.076958417892456, | |
| "learning_rate": 9.934567829727386e-05, | |
| "loss": 1.3701, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011087584215591915, | |
| "grad_norm": 1.8793498277664185, | |
| "learning_rate": 9.905878394570453e-05, | |
| "loss": 1.1889, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01231953801732435, | |
| "grad_norm": 1.9051135778427124, | |
| "learning_rate": 9.872051902290737e-05, | |
| "loss": 1.1137, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013551491819056785, | |
| "grad_norm": 1.5732001066207886, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 1.0469, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01478344562078922, | |
| "grad_norm": 1.9609421491622925, | |
| "learning_rate": 9.789151450663723e-05, | |
| "loss": 1.1223, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.016015399422521656, | |
| "grad_norm": 1.8344721794128418, | |
| "learning_rate": 9.740174149534693e-05, | |
| "loss": 1.0626, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01724735322425409, | |
| "grad_norm": 1.5016754865646362, | |
| "learning_rate": 9.686252995020249e-05, | |
| "loss": 0.9166, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.018479307025986526, | |
| "grad_norm": 1.0660717487335205, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 0.8678, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01971126082771896, | |
| "grad_norm": 0.9451479315757751, | |
| "learning_rate": 9.563836295460398e-05, | |
| "loss": 0.8882, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.020943214629451395, | |
| "grad_norm": 0.8659009337425232, | |
| "learning_rate": 9.495483482810688e-05, | |
| "loss": 0.822, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02217516843118383, | |
| "grad_norm": 0.8729805946350098, | |
| "learning_rate": 9.422472115147382e-05, | |
| "loss": 0.8542, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.023407122232916265, | |
| "grad_norm": 0.8671184778213501, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 0.8336, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0246390760346487, | |
| "grad_norm": 0.8609638214111328, | |
| "learning_rate": 9.2628195591462e-05, | |
| "loss": 0.8219, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.025871029836381135, | |
| "grad_norm": 0.9347344636917114, | |
| "learning_rate": 9.176364518546989e-05, | |
| "loss": 0.8306, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02710298363811357, | |
| "grad_norm": 0.8969244956970215, | |
| "learning_rate": 9.08562300137157e-05, | |
| "loss": 0.8232, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.028334937439846004, | |
| "grad_norm": 1.0083746910095215, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 0.8318, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02956689124157844, | |
| "grad_norm": 1.0339181423187256, | |
| "learning_rate": 8.891708613973126e-05, | |
| "loss": 0.8636, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.030798845043310877, | |
| "grad_norm": 1.1391716003417969, | |
| "learning_rate": 8.788761839251559e-05, | |
| "loss": 0.9234, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.030798845043310877, | |
| "eval_loss": 0.7983564734458923, | |
| "eval_runtime": 3.5175, | |
| "eval_samples_per_second": 14.214, | |
| "eval_steps_per_second": 3.696, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03203079884504331, | |
| "grad_norm": 1.529720425605774, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.8309, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.033262752646775744, | |
| "grad_norm": 1.6183327436447144, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 0.7803, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03449470644850818, | |
| "grad_norm": 1.110182285308838, | |
| "learning_rate": 8.457416554680877e-05, | |
| "loss": 0.7443, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03572666025024061, | |
| "grad_norm": 0.8818290829658508, | |
| "learning_rate": 8.339895749467238e-05, | |
| "loss": 0.7466, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03695861405197305, | |
| "grad_norm": 0.9471279978752136, | |
| "learning_rate": 8.219063752844926e-05, | |
| "loss": 0.7426, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03819056785370548, | |
| "grad_norm": 1.0536586046218872, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 0.7339, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03942252165543792, | |
| "grad_norm": 0.8326343894004822, | |
| "learning_rate": 7.968033420621935e-05, | |
| "loss": 0.6976, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04065447545717036, | |
| "grad_norm": 0.823235273361206, | |
| "learning_rate": 7.838127775159452e-05, | |
| "loss": 0.7378, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04188642925890279, | |
| "grad_norm": 0.8146088719367981, | |
| "learning_rate": 7.705495977301078e-05, | |
| "loss": 0.7537, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04311838306063523, | |
| "grad_norm": 0.852783739566803, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 0.7191, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04435033686236766, | |
| "grad_norm": 0.9801528453826904, | |
| "learning_rate": 7.43267549363537e-05, | |
| "loss": 0.774, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0455822906641001, | |
| "grad_norm": 1.0414175987243652, | |
| "learning_rate": 7.292804904308087e-05, | |
| "loss": 0.8229, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04681424446583253, | |
| "grad_norm": 0.8394467234611511, | |
| "learning_rate": 7.150843984658754e-05, | |
| "loss": 0.7731, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04804619826756497, | |
| "grad_norm": 0.8109716773033142, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 0.6696, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0492781520692974, | |
| "grad_norm": 0.7383696436882019, | |
| "learning_rate": 6.861315478964841e-05, | |
| "loss": 0.6555, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05051010587102984, | |
| "grad_norm": 0.7810937166213989, | |
| "learning_rate": 6.714085470206609e-05, | |
| "loss": 0.6789, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05174205967276227, | |
| "grad_norm": 0.7691031694412231, | |
| "learning_rate": 6.56543989209901e-05, | |
| "loss": 0.6582, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05297401347449471, | |
| "grad_norm": 0.9100735783576965, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 0.7069, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05420596727622714, | |
| "grad_norm": 0.931399405002594, | |
| "learning_rate": 6.264596732629e-05, | |
| "loss": 0.7135, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05543792107795958, | |
| "grad_norm": 0.8463882803916931, | |
| "learning_rate": 6.112749920933111e-05, | |
| "loss": 0.6697, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05666987487969201, | |
| "grad_norm": 0.85605788230896, | |
| "learning_rate": 5.960188670239154e-05, | |
| "loss": 0.6989, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05790182868142445, | |
| "grad_norm": 0.8102529048919678, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 0.6696, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.05913378248315688, | |
| "grad_norm": 0.8773670196533203, | |
| "learning_rate": 5.653634995836856e-05, | |
| "loss": 0.7289, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06036573628488932, | |
| "grad_norm": 0.856377363204956, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.7178, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.061597690086621755, | |
| "grad_norm": 0.9929988384246826, | |
| "learning_rate": 5.346365004163145e-05, | |
| "loss": 0.7789, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.061597690086621755, | |
| "eval_loss": 0.6646984219551086, | |
| "eval_runtime": 3.5125, | |
| "eval_samples_per_second": 14.235, | |
| "eval_steps_per_second": 3.701, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 95, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.968083617316864e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |