| { | |
| "best_metric": 0.5413779616355896, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.00546477949614733, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00010929558992294661, | |
| "grad_norm": 0.08892586827278137, | |
| "learning_rate": 5e-06, | |
| "loss": 0.407, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00010929558992294661, | |
| "eval_loss": 0.9313396215438843, | |
| "eval_runtime": 1188.3423, | |
| "eval_samples_per_second": 12.968, | |
| "eval_steps_per_second": 6.484, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00021859117984589322, | |
| "grad_norm": 0.10184711962938309, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3912, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0003278867697688398, | |
| "grad_norm": 0.1291767805814743, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.5147, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00043718235969178644, | |
| "grad_norm": 0.13007928431034088, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4359, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0005464779496147331, | |
| "grad_norm": 0.14250938594341278, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.4897, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006557735395376796, | |
| "grad_norm": 0.15091027319431305, | |
| "learning_rate": 3e-05, | |
| "loss": 0.5612, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0007650691294606263, | |
| "grad_norm": 0.14838960766792297, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.5994, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0008743647193835729, | |
| "grad_norm": 0.1545994132757187, | |
| "learning_rate": 4e-05, | |
| "loss": 0.6009, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0009836603093065195, | |
| "grad_norm": 0.15585535764694214, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.5009, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0010929558992294661, | |
| "grad_norm": 0.18895578384399414, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6854, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012022514891524127, | |
| "grad_norm": 0.20997057855129242, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.6106, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0013115470790753593, | |
| "grad_norm": 0.20784635841846466, | |
| "learning_rate": 6e-05, | |
| "loss": 0.7, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0014208426689983058, | |
| "grad_norm": 0.20637793838977814, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 0.4913, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0015301382589212526, | |
| "grad_norm": 0.18955039978027344, | |
| "learning_rate": 7e-05, | |
| "loss": 0.5854, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0016394338488441992, | |
| "grad_norm": 0.19074691832065582, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5278, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0017487294387671457, | |
| "grad_norm": 0.1751364767551422, | |
| "learning_rate": 8e-05, | |
| "loss": 0.4145, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0018580250286900923, | |
| "grad_norm": 0.17601102590560913, | |
| "learning_rate": 8.5e-05, | |
| "loss": 0.5324, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.001967320618613039, | |
| "grad_norm": 0.18196499347686768, | |
| "learning_rate": 9e-05, | |
| "loss": 0.5041, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0020766162085359857, | |
| "grad_norm": 0.18326377868652344, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.4329, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0021859117984589322, | |
| "grad_norm": 0.23563292622566223, | |
| "learning_rate": 0.0001, | |
| "loss": 0.484, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002295207388381879, | |
| "grad_norm": 0.21941961348056793, | |
| "learning_rate": 9.999238475781957e-05, | |
| "loss": 0.6038, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0024045029783048254, | |
| "grad_norm": 0.18175636231899261, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 0.5373, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.002513798568227772, | |
| "grad_norm": 0.1632622629404068, | |
| "learning_rate": 9.99314767377287e-05, | |
| "loss": 0.4324, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0026230941581507185, | |
| "grad_norm": 0.18101082742214203, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.5009, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002732389748073665, | |
| "grad_norm": 0.36991167068481445, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 0.6138, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0028416853379966116, | |
| "grad_norm": 0.15769365429878235, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 0.4178, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0029509809279195586, | |
| "grad_norm": 0.1861845850944519, | |
| "learning_rate": 9.962730758206611e-05, | |
| "loss": 0.5209, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.003060276517842505, | |
| "grad_norm": 0.17047907412052155, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.575, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.003169572107765452, | |
| "grad_norm": 0.15702685713768005, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.4291, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0032788676976883984, | |
| "grad_norm": 0.2200898826122284, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.6081, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.003388163287611345, | |
| "grad_norm": 0.225937157869339, | |
| "learning_rate": 9.908135917238321e-05, | |
| "loss": 0.5231, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0034974588775342915, | |
| "grad_norm": 0.2006777971982956, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.4612, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.003606754467457238, | |
| "grad_norm": 0.22215096652507782, | |
| "learning_rate": 9.871850323926177e-05, | |
| "loss": 0.6789, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0037160500573801846, | |
| "grad_norm": 0.2149656116962433, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 0.4645, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.003825345647303131, | |
| "grad_norm": 0.22449809312820435, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.5203, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.003934641237226078, | |
| "grad_norm": 0.21824942529201508, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.3769, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.004043936827149024, | |
| "grad_norm": 0.37824153900146484, | |
| "learning_rate": 9.781523779815179e-05, | |
| "loss": 0.433, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.004153232417071971, | |
| "grad_norm": 1.0172040462493896, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.6214, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0042625280069949175, | |
| "grad_norm": 0.28730088472366333, | |
| "learning_rate": 9.727592877996585e-05, | |
| "loss": 0.6083, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0043718235969178645, | |
| "grad_norm": 0.2713054418563843, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.5272, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004481119186840811, | |
| "grad_norm": 0.40768107771873474, | |
| "learning_rate": 9.667902132486009e-05, | |
| "loss": 0.6015, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.004590414776763758, | |
| "grad_norm": 0.3207384943962097, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.6781, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.004699710366686705, | |
| "grad_norm": 0.3168956935405731, | |
| "learning_rate": 9.602524267262203e-05, | |
| "loss": 0.6227, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.004809005956609651, | |
| "grad_norm": 0.3231648802757263, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.7363, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.004918301546532598, | |
| "grad_norm": 0.32550543546676636, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.6612, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.005027597136455544, | |
| "grad_norm": 0.4946689009666443, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 0.7281, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.005136892726378491, | |
| "grad_norm": 0.41630205512046814, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 0.5782, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.005246188316301437, | |
| "grad_norm": 0.4432646334171295, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.6469, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.005355483906224384, | |
| "grad_norm": 0.7148913145065308, | |
| "learning_rate": 9.373098535696979e-05, | |
| "loss": 0.9674, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.00546477949614733, | |
| "grad_norm": 0.6914791464805603, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.5803, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00546477949614733, | |
| "eval_loss": 0.5413779616355896, | |
| "eval_runtime": 1194.3838, | |
| "eval_samples_per_second": 12.902, | |
| "eval_steps_per_second": 6.451, | |
| "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": 5, | |
| "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": 6.686777211774566e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |