| { | |
| "best_metric": 10.347744941711426, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0020012607943004092, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.0025215886008184e-05, | |
| "grad_norm": 0.028526226058602333, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 10.3783, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.0025215886008184e-05, | |
| "eval_loss": 10.376290321350098, | |
| "eval_runtime": 0.12, | |
| "eval_samples_per_second": 416.641, | |
| "eval_steps_per_second": 58.33, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.005043177201637e-05, | |
| "grad_norm": 0.029773740097880363, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 10.3765, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00012007564765802456, | |
| "grad_norm": 0.02794136479496956, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 10.3763, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00016010086354403274, | |
| "grad_norm": 0.030925514176487923, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 10.3774, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00020012607943004093, | |
| "grad_norm": 0.03159649670124054, | |
| "learning_rate": 0.00015, | |
| "loss": 10.3771, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00024015129531604912, | |
| "grad_norm": 0.028680993244051933, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 10.3756, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002801765112020573, | |
| "grad_norm": 0.03433338180184364, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 10.3776, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0003202017270880655, | |
| "grad_norm": 0.03138856589794159, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 10.3761, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00036022694297407367, | |
| "grad_norm": 0.030663292855024338, | |
| "learning_rate": 0.00027, | |
| "loss": 10.3776, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00040025215886008186, | |
| "grad_norm": 0.034716520458459854, | |
| "learning_rate": 0.0003, | |
| "loss": 10.377, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00044027737474609005, | |
| "grad_norm": 0.03367249295115471, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 10.3767, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00048030259063209824, | |
| "grad_norm": 0.03586790710687637, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 10.3749, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0005203278065181064, | |
| "grad_norm": 0.03616034612059593, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 10.3755, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0005603530224041146, | |
| "grad_norm": 0.03707385063171387, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 10.3747, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0006003782382901228, | |
| "grad_norm": 0.040910378098487854, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 10.3772, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.000640403454176131, | |
| "grad_norm": 0.037733159959316254, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 10.3738, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0006804286700621392, | |
| "grad_norm": 0.04005344212055206, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 10.3723, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0007204538859481473, | |
| "grad_norm": 0.03841446712613106, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 10.3719, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0007604791018341555, | |
| "grad_norm": 0.04704993590712547, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 10.3739, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0008005043177201637, | |
| "grad_norm": 0.04559043422341347, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 10.3732, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0008405295336061719, | |
| "grad_norm": 0.052254363894462585, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 10.3717, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0008805547494921801, | |
| "grad_norm": 0.05502045899629593, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 10.3717, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0009205799653781882, | |
| "grad_norm": 0.061194684356451035, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 10.3695, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0009606051812641965, | |
| "grad_norm": 0.059378888458013535, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 10.3712, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0010006303971502046, | |
| "grad_norm": 0.06684457510709763, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 10.371, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0010006303971502046, | |
| "eval_loss": 10.367866516113281, | |
| "eval_runtime": 0.1084, | |
| "eval_samples_per_second": 461.359, | |
| "eval_steps_per_second": 64.59, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0010406556130362129, | |
| "grad_norm": 0.07267913222312927, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 10.3678, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.001080680828922221, | |
| "grad_norm": 0.07705136388540268, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 10.3684, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0011207060448082291, | |
| "grad_norm": 0.08530186861753464, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 10.3682, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0011607312606942374, | |
| "grad_norm": 0.08188481628894806, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 10.3672, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0012007564765802456, | |
| "grad_norm": 0.08364146202802658, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 10.367, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0012407816924662537, | |
| "grad_norm": 0.09279844909906387, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 10.3662, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.001280806908352262, | |
| "grad_norm": 0.08991207182407379, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 10.3624, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0013208321242382701, | |
| "grad_norm": 0.09190763533115387, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 10.3623, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0013608573401242784, | |
| "grad_norm": 0.10333334654569626, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 10.3643, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0014008825560102864, | |
| "grad_norm": 0.10039209574460983, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 10.3599, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0014409077718962947, | |
| "grad_norm": 0.08169548213481903, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 10.3611, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.001480932987782303, | |
| "grad_norm": 0.0989358052611351, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 10.3563, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.001520958203668311, | |
| "grad_norm": 0.07897914946079254, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 10.3573, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0015609834195543192, | |
| "grad_norm": 0.08730727434158325, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 10.3569, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0016010086354403274, | |
| "grad_norm": 0.08495213836431503, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 10.3552, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0016410338513263357, | |
| "grad_norm": 0.08885069191455841, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 10.3535, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0016810590672123437, | |
| "grad_norm": 0.08947066962718964, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 10.3559, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.001721084283098352, | |
| "grad_norm": 0.06976769864559174, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 10.3517, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0017611094989843602, | |
| "grad_norm": 0.0737992525100708, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 10.353, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0018011347148703684, | |
| "grad_norm": 0.06612483412027359, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 10.351, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0018411599307563765, | |
| "grad_norm": 0.06353169679641724, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 10.3521, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0018811851466423847, | |
| "grad_norm": 0.05199315771460533, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 10.353, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.001921210362528393, | |
| "grad_norm": 0.04880088195204735, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 10.3521, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.001961235578414401, | |
| "grad_norm": 0.046220581978559494, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 10.3528, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0020012607943004092, | |
| "grad_norm": 0.05683967471122742, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 10.3495, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0020012607943004092, | |
| "eval_loss": 10.347744941711426, | |
| "eval_runtime": 0.107, | |
| "eval_samples_per_second": 467.451, | |
| "eval_steps_per_second": 65.443, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "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": 5612706299904.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |