| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9974554707379135, | |
| "eval_steps": 500, | |
| "global_step": 49, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.020356234096692113, | |
| "grad_norm": 0.1697569042444229, | |
| "learning_rate": 2e-05, | |
| "loss": 1.8967, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04071246819338423, | |
| "grad_norm": 0.16455122828483582, | |
| "learning_rate": 4e-05, | |
| "loss": 1.9742, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.061068702290076333, | |
| "grad_norm": 0.1334070861339569, | |
| "learning_rate": 6e-05, | |
| "loss": 1.8263, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08142493638676845, | |
| "grad_norm": 0.19785284996032715, | |
| "learning_rate": 8e-05, | |
| "loss": 1.8359, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.10178117048346055, | |
| "grad_norm": 0.16298870742321014, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8452, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12213740458015267, | |
| "grad_norm": 0.1491611897945404, | |
| "learning_rate": 0.00012, | |
| "loss": 1.8554, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.14249363867684478, | |
| "grad_norm": 0.14379450678825378, | |
| "learning_rate": 0.00014, | |
| "loss": 1.7928, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1628498727735369, | |
| "grad_norm": 0.11020653694868088, | |
| "learning_rate": 0.00016, | |
| "loss": 1.8638, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.183206106870229, | |
| "grad_norm": 0.20387399196624756, | |
| "learning_rate": 0.00018, | |
| "loss": 1.6861, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2035623409669211, | |
| "grad_norm": 0.18219953775405884, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7959, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22391857506361323, | |
| "grad_norm": 0.15169978141784668, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 1.827, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.24427480916030533, | |
| "grad_norm": 0.08840368688106537, | |
| "learning_rate": 0.00019870502626379127, | |
| "loss": 1.8324, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.26463104325699743, | |
| "grad_norm": 0.08657640218734741, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 1.8853, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.28498727735368956, | |
| "grad_norm": 0.10179179906845093, | |
| "learning_rate": 0.00019485364419471454, | |
| "loss": 1.8181, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3053435114503817, | |
| "grad_norm": 0.08559463918209076, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 1.9153, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3256997455470738, | |
| "grad_norm": 0.1002177819609642, | |
| "learning_rate": 0.000188545602565321, | |
| "loss": 1.869, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3460559796437659, | |
| "grad_norm": 0.08648160099983215, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 1.7103, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.366412213740458, | |
| "grad_norm": 0.0936996191740036, | |
| "learning_rate": 0.00017994427634035015, | |
| "loss": 1.906, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.38676844783715014, | |
| "grad_norm": 0.09296493977308273, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 1.8598, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4071246819338422, | |
| "grad_norm": 0.08220034092664719, | |
| "learning_rate": 0.00016927243535095997, | |
| "loss": 1.7883, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.42748091603053434, | |
| "grad_norm": 0.08138112723827362, | |
| "learning_rate": 0.00016324453755953773, | |
| "loss": 1.839, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.44783715012722647, | |
| "grad_norm": 0.089788056910038, | |
| "learning_rate": 0.00015680647467311557, | |
| "loss": 1.9511, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.4681933842239186, | |
| "grad_norm": 0.08236150443553925, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.7003, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.48854961832061067, | |
| "grad_norm": 0.0797291249036789, | |
| "learning_rate": 0.00014286925614030542, | |
| "loss": 1.8304, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5089058524173028, | |
| "grad_norm": 0.11056578904390335, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 1.8363, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5292620865139949, | |
| "grad_norm": 0.08862095326185226, | |
| "learning_rate": 0.0001278217463916453, | |
| "loss": 1.8398, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.549618320610687, | |
| "grad_norm": 0.07724796235561371, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 1.8102, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5699745547073791, | |
| "grad_norm": 0.08631068468093872, | |
| "learning_rate": 0.0001120536680255323, | |
| "loss": 1.7571, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5903307888040712, | |
| "grad_norm": 0.0852205753326416, | |
| "learning_rate": 0.00010402659401094152, | |
| "loss": 1.7623, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6106870229007634, | |
| "grad_norm": 0.09490972757339478, | |
| "learning_rate": 9.597340598905852e-05, | |
| "loss": 1.7686, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6310432569974554, | |
| "grad_norm": 0.0830993726849556, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 1.8706, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.6513994910941476, | |
| "grad_norm": 0.1042318046092987, | |
| "learning_rate": 7.999743062239557e-05, | |
| "loss": 1.8053, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6717557251908397, | |
| "grad_norm": 0.07309404015541077, | |
| "learning_rate": 7.217825360835473e-05, | |
| "loss": 1.7835, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6921119592875318, | |
| "grad_norm": 0.07798247784376144, | |
| "learning_rate": 6.453951129574644e-05, | |
| "loss": 1.8351, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.712468193384224, | |
| "grad_norm": 0.10470892488956451, | |
| "learning_rate": 5.713074385969457e-05, | |
| "loss": 1.6869, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.732824427480916, | |
| "grad_norm": 0.062327221035957336, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.8249, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.7531806615776081, | |
| "grad_norm": 0.09498722851276398, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 1.6566, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.7735368956743003, | |
| "grad_norm": 0.07665014266967773, | |
| "learning_rate": 3.675546244046228e-05, | |
| "loss": 1.766, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.7938931297709924, | |
| "grad_norm": 0.07265973836183548, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 1.789, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8142493638676844, | |
| "grad_norm": 0.07454241812229156, | |
| "learning_rate": 2.514892518288988e-05, | |
| "loss": 1.831, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8346055979643766, | |
| "grad_norm": 0.07916758209466934, | |
| "learning_rate": 2.0055723659649904e-05, | |
| "loss": 1.8673, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.8549618320610687, | |
| "grad_norm": 0.0858256071805954, | |
| "learning_rate": 1.5480991445620542e-05, | |
| "loss": 1.6331, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.8753180661577609, | |
| "grad_norm": 0.09055773913860321, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 1.6856, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.8956743002544529, | |
| "grad_norm": 0.08801382780075073, | |
| "learning_rate": 8.002055634117578e-06, | |
| "loss": 1.7838, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.916030534351145, | |
| "grad_norm": 0.08115601539611816, | |
| "learning_rate": 5.146355805285452e-06, | |
| "loss": 1.7345, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.9363867684478372, | |
| "grad_norm": 0.07437321543693542, | |
| "learning_rate": 2.905818257394799e-06, | |
| "loss": 1.84, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.9567430025445293, | |
| "grad_norm": 0.08822711557149887, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 1.6885, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.9770992366412213, | |
| "grad_norm": 0.09608830511569977, | |
| "learning_rate": 3.2426918657900704e-07, | |
| "loss": 1.6825, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.9974554707379135, | |
| "grad_norm": 0.07894308120012283, | |
| "learning_rate": 0.0, | |
| "loss": 1.6886, | |
| "step": 49 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 49, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.32140082998018e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |