| { | |
| "best_metric": 10.363272666931152, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.2936857562408223, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005873715124816446, | |
| "grad_norm": 0.15584339201450348, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3832, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005873715124816446, | |
| "eval_loss": 10.380758285522461, | |
| "eval_runtime": 3.6353, | |
| "eval_samples_per_second": 315.52, | |
| "eval_steps_per_second": 39.612, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011747430249632892, | |
| "grad_norm": 0.14473983645439148, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3827, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01762114537444934, | |
| "grad_norm": 0.1327889859676361, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.3817, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.023494860499265784, | |
| "grad_norm": 0.12545689940452576, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.3798, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02936857562408223, | |
| "grad_norm": 0.12021041661500931, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 10.3802, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03524229074889868, | |
| "grad_norm": 0.11450187116861343, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.3801, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.041116005873715125, | |
| "grad_norm": 0.11224997043609619, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 10.3793, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04698972099853157, | |
| "grad_norm": 0.11222485452890396, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3792, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05286343612334802, | |
| "grad_norm": 0.11607800424098969, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 10.3793, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05873715124816446, | |
| "grad_norm": 0.11430998146533966, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3762, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06461086637298091, | |
| "grad_norm": 0.11606329679489136, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 10.3729, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07048458149779736, | |
| "grad_norm": 0.12196508795022964, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.3719, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0763582966226138, | |
| "grad_norm": 0.1646091341972351, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 10.3762, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08223201174743025, | |
| "grad_norm": 0.16281186044216156, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3761, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0881057268722467, | |
| "grad_norm": 0.15427953004837036, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 10.3758, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09397944199706314, | |
| "grad_norm": 0.1527239978313446, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.3745, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09985315712187959, | |
| "grad_norm": 0.148397296667099, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 10.3733, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.10572687224669604, | |
| "grad_norm": 0.148326113820076, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3729, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.11160058737151249, | |
| "grad_norm": 0.14326217770576477, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 10.3734, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.11747430249632893, | |
| "grad_norm": 0.14348213374614716, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3744, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12334801762114538, | |
| "grad_norm": 0.15196223556995392, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 10.3727, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.12922173274596183, | |
| "grad_norm": 0.15216338634490967, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.3709, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.13509544787077826, | |
| "grad_norm": 0.15067099034786224, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 10.3704, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.14096916299559473, | |
| "grad_norm": 0.15914303064346313, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.3667, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.14684287812041116, | |
| "grad_norm": 0.1697520911693573, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 10.3637, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.14684287812041116, | |
| "eval_loss": 10.368462562561035, | |
| "eval_runtime": 3.6356, | |
| "eval_samples_per_second": 315.488, | |
| "eval_steps_per_second": 39.608, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1527165932452276, | |
| "grad_norm": 0.21917545795440674, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3686, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.15859030837004406, | |
| "grad_norm": 0.20469699800014496, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 10.3687, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1644640234948605, | |
| "grad_norm": 0.20218636095523834, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.3679, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.17033773861967694, | |
| "grad_norm": 0.19212639331817627, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 10.3662, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1762114537444934, | |
| "grad_norm": 0.18560166656970978, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.3675, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.18208516886930984, | |
| "grad_norm": 0.18543921411037445, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 10.368, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.18795888399412627, | |
| "grad_norm": 0.18739567697048187, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3678, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.19383259911894274, | |
| "grad_norm": 0.1920151710510254, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 10.3679, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.19970631424375918, | |
| "grad_norm": 0.18959976732730865, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.3669, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2055800293685756, | |
| "grad_norm": 0.1854933500289917, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 10.3668, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.21145374449339208, | |
| "grad_norm": 0.18347898125648499, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 10.3623, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2173274596182085, | |
| "grad_norm": 0.1941113919019699, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 10.3596, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.22320117474302498, | |
| "grad_norm": 0.24184665083885193, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3645, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2290748898678414, | |
| "grad_norm": 0.24406494200229645, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 10.3634, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.23494860499265785, | |
| "grad_norm": 0.23579344153404236, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.3638, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.24082232011747431, | |
| "grad_norm": 0.2283434420824051, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 10.3634, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.24669603524229075, | |
| "grad_norm": 0.21662116050720215, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.3624, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2525697503671072, | |
| "grad_norm": 0.21385407447814941, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 10.3656, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.25844346549192365, | |
| "grad_norm": 0.20657625794410706, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3659, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2643171806167401, | |
| "grad_norm": 0.20029610395431519, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 10.3655, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2701908957415565, | |
| "grad_norm": 0.2030303031206131, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 10.365, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.27606461086637296, | |
| "grad_norm": 0.20757298171520233, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 10.3641, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.28193832599118945, | |
| "grad_norm": 0.20119069516658783, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 10.3643, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2878120411160059, | |
| "grad_norm": 0.1982789784669876, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 10.3607, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2936857562408223, | |
| "grad_norm": 0.20990411937236786, | |
| "learning_rate": 0.0, | |
| "loss": 10.3577, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2936857562408223, | |
| "eval_loss": 10.363272666931152, | |
| "eval_runtime": 3.6828, | |
| "eval_samples_per_second": 311.451, | |
| "eval_steps_per_second": 39.101, | |
| "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": 43062090006528.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |