| { | |
| "best_metric": 10.347302436828613, | |
| "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": 0.031631357967853546, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 10.3783, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.0025215886008184e-05, | |
| "eval_loss": 10.376290321350098, | |
| "eval_runtime": 0.1629, | |
| "eval_samples_per_second": 306.865, | |
| "eval_steps_per_second": 42.961, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.005043177201637e-05, | |
| "grad_norm": 0.03165977820754051, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 10.3765, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00012007564765802456, | |
| "grad_norm": 0.029739394783973694, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 10.3763, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00016010086354403274, | |
| "grad_norm": 0.03128078579902649, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 10.3774, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00020012607943004093, | |
| "grad_norm": 0.03327089175581932, | |
| "learning_rate": 0.00015, | |
| "loss": 10.3771, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00024015129531604912, | |
| "grad_norm": 0.031221648678183556, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 10.3756, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002801765112020573, | |
| "grad_norm": 0.033140648156404495, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 10.3776, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0003202017270880655, | |
| "grad_norm": 0.03264706954360008, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 10.3761, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00036022694297407367, | |
| "grad_norm": 0.03237176313996315, | |
| "learning_rate": 0.00027, | |
| "loss": 10.3775, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00040025215886008186, | |
| "grad_norm": 0.03519490361213684, | |
| "learning_rate": 0.0003, | |
| "loss": 10.377, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00044027737474609005, | |
| "grad_norm": 0.03602423146367073, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 10.3766, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00048030259063209824, | |
| "grad_norm": 0.0372912622988224, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 10.3748, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0005203278065181064, | |
| "grad_norm": 0.0409846268594265, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 10.3753, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0005603530224041146, | |
| "grad_norm": 0.038565054535865784, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 10.3746, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0006003782382901228, | |
| "grad_norm": 0.04584704712033272, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 10.3769, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.000640403454176131, | |
| "grad_norm": 0.0443044938147068, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 10.3734, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0006804286700621392, | |
| "grad_norm": 0.046843986958265305, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 10.3719, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0007204538859481473, | |
| "grad_norm": 0.0493725948035717, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 10.3713, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0007604791018341555, | |
| "grad_norm": 0.057320885360240936, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 10.3733, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0008005043177201637, | |
| "grad_norm": 0.056451402604579926, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 10.3725, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0008405295336061719, | |
| "grad_norm": 0.06416947394609451, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 10.3709, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0008805547494921801, | |
| "grad_norm": 0.06632953882217407, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 10.3709, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0009205799653781882, | |
| "grad_norm": 0.07961234450340271, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 10.3681, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0009606051812641965, | |
| "grad_norm": 0.07279147952795029, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 10.37, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0010006303971502046, | |
| "grad_norm": 0.08351346105337143, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 10.3697, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0010006303971502046, | |
| "eval_loss": 10.366039276123047, | |
| "eval_runtime": 0.1456, | |
| "eval_samples_per_second": 343.361, | |
| "eval_steps_per_second": 48.071, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0010406556130362129, | |
| "grad_norm": 0.09310437738895416, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 10.3658, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.001080680828922221, | |
| "grad_norm": 0.09378130733966827, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 10.3663, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0011207060448082291, | |
| "grad_norm": 0.10403110831975937, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 10.3658, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0011607312606942374, | |
| "grad_norm": 0.09855637699365616, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 10.3649, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0012007564765802456, | |
| "grad_norm": 0.09459754824638367, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 10.3645, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0012407816924662537, | |
| "grad_norm": 0.10157828778028488, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 10.3639, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.001280806908352262, | |
| "grad_norm": 0.09586312621831894, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 10.3597, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0013208321242382701, | |
| "grad_norm": 0.09686974436044693, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 10.3595, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0013608573401242784, | |
| "grad_norm": 0.10700739920139313, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 10.3619, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0014008825560102864, | |
| "grad_norm": 0.10100480914115906, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 10.3571, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0014409077718962947, | |
| "grad_norm": 0.08027458190917969, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 10.3593, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.001480932987782303, | |
| "grad_norm": 0.08975960314273834, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 10.3537, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.001520958203668311, | |
| "grad_norm": 0.07283489406108856, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 10.3551, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0015609834195543192, | |
| "grad_norm": 0.07702310383319855, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 10.3544, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0016010086354403274, | |
| "grad_norm": 0.07644236087799072, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 10.3538, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0016410338513263357, | |
| "grad_norm": 0.08016783744096756, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 10.3513, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0016810590672123437, | |
| "grad_norm": 0.0817168653011322, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 10.3543, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.001721084283098352, | |
| "grad_norm": 0.06613239645957947, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 10.3509, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0017611094989843602, | |
| "grad_norm": 0.0739089846611023, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 10.352, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0018011347148703684, | |
| "grad_norm": 0.0704953670501709, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 10.3511, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0018411599307563765, | |
| "grad_norm": 0.06712953001260757, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 10.3521, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0018811851466423847, | |
| "grad_norm": 0.04802524298429489, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 10.3529, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.001921210362528393, | |
| "grad_norm": 0.0486036092042923, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 10.3516, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.001961235578414401, | |
| "grad_norm": 0.04487287998199463, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 10.3525, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0020012607943004092, | |
| "grad_norm": 0.061715804040431976, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 10.3493, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0020012607943004092, | |
| "eval_loss": 10.347302436828613, | |
| "eval_runtime": 0.1452, | |
| "eval_samples_per_second": 344.282, | |
| "eval_steps_per_second": 48.2, | |
| "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 | |
| } | |